Merge branch 'for-6.17/selftests' into for-linus

- upgrade the python scripts in hid-selftests to match hid-tools
  version 0.10 (Benjamin Tissoires)

.mailmap

@@ -223,6 +223,8 @@ Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 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>
 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>
@@ -830,3 +832,6 @@ Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>
+Zijun Hu <zijun.hu@oss.qualcomm.com> <quic_zijuhu@quicinc.com>
+Zijun Hu <zijun.hu@oss.qualcomm.com> <zijuhu@codeaurora.org>
+Zijun Hu <zijun_hu@htc.com>

Documentation/ABI/testing/sysfs-devices-power

@@ -56,7 +56,7 @@ Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../async attribute allows the user space to
-		enable or diasble the device's suspend and resume callbacks to
+		enable or disable the device's suspend and resume callbacks to
 		be executed asynchronously (ie. in separate threads, in parallel
 		with the main suspend/resume thread) during system-wide power
 		transitions (eg. suspend to RAM, hibernation).

Documentation/ABI/testing/sysfs-driver-ufs

@@ -711,7 +711,7 @@ Description:	This file shows the thin provisioning type. This is one of
 
 		The file is read only.
 
-What:		/sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resourse_count
+What:		/sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resource_count
 Date:		February 2018
 Contact:	Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
 Description:	This file shows the total physical memory resources. This is

Documentation/ABI/testing/sysfs-edac-scrub

@@ -49,6 +49,12 @@ Description:
 		(RO) Supported minimum scrub cycle duration in seconds
 		by the memory scrubber.
 
+		Device-based scrub: returns the minimum scrub cycle
+		supported by the memory device.
+
+		Region-based scrub: returns the max of minimum scrub cycles
+		supported by individual memory devices that back the region.
+
 What:		/sys/bus/edac/devices/<dev-name>/scrubX/max_cycle_duration
 Date:		March 2025
 KernelVersion:	6.15
@@ -57,6 +63,16 @@ Description:
 		(RO) Supported maximum scrub cycle duration in seconds
 		by the memory scrubber.
 
+		Device-based scrub: returns the maximum scrub cycle supported
+		by the memory device.
+
+		Region-based scrub: returns the min of maximum scrub cycles
+		supported by individual memory devices that back the region.
+
+		If the memory device does not provide maximum scrub cycle
+		information, return the maximum supported value of the scrub
+		cycle field.
+
 What:		/sys/bus/edac/devices/<dev-name>/scrubX/current_cycle_duration
 Date:		March 2025
 KernelVersion:	6.15

Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml

@@ -26,7 +26,8 @@ properties:
       - const: realtek,rtl9301-i2c
 
   reg:
-    description: Register offset and size this I2C controller.
+    items:
+      - description: Register offset and size this I2C controller.
 
   "#address-cells":
     const: 1

Documentation/devicetree/bindings/input/elan,ekth6915.yaml

@@ -4,14 +4,14 @@
 $id: http://devicetree.org/schemas/input/elan,ekth6915.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Elan eKTH6915 touchscreen controller
+title: Elan I2C-HID touchscreen controllers
 
 maintainers:
   - Douglas Anderson <dianders@chromium.org>
 
 description:
-  Supports the Elan eKTH6915 touchscreen controller.
-  This touchscreen controller uses the i2c-hid protocol with a reset GPIO.
+  Supports the Elan eKTH6915 and other I2C-HID touchscreen controllers.
+  These touchscreen controller use the i2c-hid protocol with a reset GPIO.
 
 allOf:
   - $ref: /schemas/input/touchscreen/touchscreen.yaml#
@@ -23,12 +23,14 @@ properties:
           - enum:
               - elan,ekth5015m
           - const: elan,ekth6915
+      - items:
+          - const: elan,ekth8d18
+          - const: elan,ekth6a12nay
       - enum:
           - elan,ekth6915
           - elan,ekth6a12nay
 
-  reg:
-    const: 0x10
+  reg: true
 
   interrupts:
     maxItems: 1

Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml

@@ -80,6 +80,8 @@ examples:
       interrupt-parent = <&intc>;
       interrupts = <296 IRQ_TYPE_LEVEL_HIGH>;
       interrupt-names = "macirq";
+      phy-handle = <&phy0>;
+      phy-mode = "rgmii-id";
       resets = <&rst 30>;
       reset-names = "stmmaceth";
       snps,multicast-filter-bins = <0>;
@@ -91,7 +93,6 @@ examples:
       snps,mtl-rx-config = <&gmac0_mtl_rx_setup>;
       snps,mtl-tx-config = <&gmac0_mtl_tx_setup>;
       snps,axi-config = <&gmac0_stmmac_axi_setup>;
-      status = "disabled";
 
       gmac0_mtl_rx_setup: rx-queues-config {
         snps,rx-queues-to-use = <8>;

Documentation/devicetree/bindings/serial/8250.yaml

@@ -45,7 +45,7 @@ allOf:
                   - ns16550
                   - ns16550a
     then:
-      anyOf:
+      oneOf:
         - required: [ clock-frequency ]
         - required: [ clocks ]
 

Documentation/networking/tls.rst

@@ -16,11 +16,13 @@ User interface
 Creating a TLS connection
 -------------------------
 
-First create a new TCP socket and set the TLS ULP.
+First create a new TCP socket and once the connection is established set the
+TLS ULP.
 
 .. code-block:: c
 
   sock = socket(AF_INET, SOCK_STREAM, 0);
+  connect(sock, addr, addrlen);
   setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls"));
 
 Setting the TLS ULP allows us to set/get TLS socket options. Currently

Documentation/process/maintainer-netdev.rst

@@ -312,7 +312,7 @@ Posting as one thread is discouraged because it confuses patchwork
 (as of patchwork 2.2.2).
 
 Co-posting selftests
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 Selftests should be part of the same series as the code changes.
 Specifically for fixes both code change and related test should go into

Documentation/wmi/acpi-interface.rst

@@ -36,7 +36,7 @@ Offset  Size (in bytes) Content
 
 The WMI object flags control whether the method or notification ID is used:
 
-- 0x1: Data block usage is expensive and must be explicitly enabled/disabled.
+- 0x1: Data block is expensive to collect.
 - 0x2: Data block contains WMI methods.
 - 0x4: Data block contains ASCIZ string.
 - 0x8: Data block describes a WMI event, use notification ID instead
@@ -83,14 +83,18 @@ event as hexadecimal value. Their first parameter is an integer with a value
 of 0 if the WMI event should be disabled, other values will enable
 the WMI event.
 
+Those ACPI methods are always called even for WMI events not registered as
+being expensive to collect to match the behavior of the Windows driver.
+
 WCxx ACPI methods
 -----------------
-Similar to the ``WExx`` ACPI methods, except that it controls data collection
-instead of events and thus the last two characters of the ACPI method name are
-the method ID of the data block to enable/disable.
+Similar to the ``WExx`` ACPI methods, except that instead of WMI events it controls
+data collection of data blocks registered as being expensive to collect. Thus the
+last two characters of the ACPI method name are the method ID of the data block
+to enable/disable.
 
 Those ACPI methods are also called before setting data blocks to match the
-behaviour of the Windows driver.
+behavior of the Windows driver.
 
 _WED ACPI method
 ----------------

MAINTAINERS

@@ -15550,6 +15550,7 @@ F:	drivers/net/ethernet/mellanox/mlx4/en_*
 MELLANOX ETHERNET DRIVER (mlx5e)
 M:	Saeed Mahameed <saeedm@nvidia.com>
 M:	Tariq Toukan <tariqt@nvidia.com>
+M:	Mark Bloch <mbloch@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://www.nvidia.com/networking/
@@ -15619,6 +15620,7 @@ MELLANOX MLX5 core VPI driver
 M:	Saeed Mahameed <saeedm@nvidia.com>
 M:	Leon Romanovsky <leonro@nvidia.com>
 M:	Tariq Toukan <tariqt@nvidia.com>
+M:	Mark Bloch <mbloch@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
@@ -15676,6 +15678,8 @@ MEMBLOCK AND MEMORY MANAGEMENT INITIALIZATION
 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 for-next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git fixes
 F:	Documentation/core-api/boot-time-mm.rst
 F:	Documentation/core-api/kho/bindings/memblock/*
 F:	include/linux/memblock.h
@@ -15848,6 +15852,17 @@ F:	mm/numa.c
 F:	mm/numa_emulation.c
 F:	mm/numa_memblks.c
 
+MEMORY MANAGEMENT - OOM KILLER
+M:	Michal Hocko <mhocko@suse.com>
+R:	David Rientjes <rientjes@google.com>
+R:	Shakeel Butt <shakeel.butt@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	include/linux/oom.h
+F:	include/trace/events/oom.h
+F:	include/uapi/linux/oom.h
+F:	mm/oom_kill.c
+
 MEMORY MANAGEMENT - PAGE ALLOCATOR
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Vlastimil Babka <vbabka@suse.cz>
@@ -15862,8 +15877,17 @@ F:	include/linux/compaction.h
 F:	include/linux/gfp.h
 F:	include/linux/page-isolation.h
 F:	mm/compaction.c
+F:	mm/debug_page_alloc.c
+F:	mm/fail_page_alloc.c
 F:	mm/page_alloc.c
+F:	mm/page_ext.c
+F:	mm/page_frag_cache.c
 F:	mm/page_isolation.c
+F:	mm/page_owner.c
+F:	mm/page_poison.c
+F:	mm/page_reporting.c
+F:	mm/show_mem.c
+F:	mm/shuffle.c
 
 MEMORY MANAGEMENT - RECLAIM
 M:	Andrew Morton <akpm@linux-foundation.org>
@@ -15923,9 +15947,9 @@ F:	mm/swapfile.c
 MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@redhat.com>
+M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Zi Yan <ziy@nvidia.com>
 R:	Baolin Wang <baolin.wang@linux.alibaba.com>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Nico Pache <npache@redhat.com>
 R:	Ryan Roberts <ryan.roberts@arm.com>
@@ -21176,7 +21200,7 @@ M:	Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml
+F:	Documentation/devicetree/bindings/net/renesas,rzv2h-gbeth.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
 
 RENESAS RZ/V2H(P) USB2PHY PORT RESET DRIVER
@@ -21388,7 +21412,7 @@ N:	spacemit
 K:	spacemit
 
 RISC-V THEAD SoC SUPPORT
-M:	Drew Fustini <drew@pdp7.com>
+M:	Drew Fustini <fustini@kernel.org>
 M:	Guo Ren <guoren@kernel.org>
 M:	Fu Wei <wefu@redhat.com>
 L:	linux-riscv@lists.infradead.org
@@ -22564,9 +22588,11 @@ S:	Maintained
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
+M:	D. Wythe <alibuda@linux.alibaba.com>
+M:	Dust Li <dust.li@linux.alibaba.com>
+M:	Sidraya Jayagond <sidraya@linux.ibm.com>
 M:	Wenjia Zhang <wenjia@linux.ibm.com>
-M:	Jan Karcher <jaka@linux.ibm.com>
-R:	D. Wythe <alibuda@linux.alibaba.com>
+R:	Mahanta Jambigi <mjambigi@linux.ibm.com>
 R:	Tony Lu <tonylu@linux.alibaba.com>
 R:	Wen Gu <guwen@linux.alibaba.com>
 L:	linux-rdma@vger.kernel.org
@@ -24077,6 +24103,7 @@ M:	Bin Du <bin.du@amd.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-designware-amdisp.c
+F:	include/linux/soc/amd/isp4_misc.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
 M:	Jaehoon Chung <jh80.chung@samsung.com>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/arm64/boot/dts/apple/spi1-nvram.dtsi

@@ -20,8 +20,6 @@
 		compatible = "jedec,spi-nor";
 		reg = <0x0>;
 		spi-max-frequency = <25000000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
 
 		partitions {
 			compatible = "fixed-partitions";

arch/arm64/boot/dts/apple/t8103-j293.dts

@@ -100,6 +100,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j293-summit", "apple,summit";

arch/arm64/boot/dts/apple/t8103-jxxx.dtsi

@@ -71,7 +71,7 @@
  */
 &port00 {
 	bus-range = <1 1>;
-	wifi0: network@0,0 {
+	wifi0: wifi@0,0 {
 		compatible = "pci14e4,4425";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
 		/* To be filled by the loader */

arch/arm64/boot/dts/apple/t8103.dtsi

@@ -405,8 +405,6 @@
 			compatible = "apple,t8103-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {

arch/arm64/boot/dts/apple/t8112-j493.dts

@@ -63,6 +63,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j493-summit", "apple,summit";

arch/arm64/boot/dts/apple/t8112.dtsi

@@ -420,8 +420,6 @@
 			compatible = "apple,t8112-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {

arch/arm64/configs/defconfig

@@ -1573,6 +1573,7 @@ CONFIG_RESET_QCOM_AOSS=y
 CONFIG_RESET_QCOM_PDC=m
 CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_RESET_TI_SCI=y
+CONFIG_PHY_SNPS_EUSB2=m
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_CAN_TRANSCEIVER=m
 CONFIG_PHY_NXP_PTN3222=m
@@ -1597,7 +1598,6 @@ CONFIG_PHY_QCOM_EDP=m
 CONFIG_PHY_QCOM_PCIE2=m
 CONFIG_PHY_QCOM_QMP=m
 CONFIG_PHY_QCOM_QUSB2=m
-CONFIG_PHY_QCOM_SNPS_EUSB2=m
 CONFIG_PHY_QCOM_EUSB2_REPEATER=m
 CONFIG_PHY_QCOM_M31_USB=m
 CONFIG_PHY_QCOM_USB_HS=m

arch/loongarch/include/asm/addrspace.h

@@ -18,12 +18,12 @@
 /*
  * This gives the physical RAM offset.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef PHYS_OFFSET
 #define PHYS_OFFSET	_UL(0)
 #endif
 extern unsigned long vm_map_base;
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #ifndef IO_BASE
 #define IO_BASE			CSR_DMW0_BASE
@@ -66,7 +66,7 @@ extern unsigned long vm_map_base;
 #define FIXADDR_TOP		((unsigned long)(long)(int)0xfffe0000)
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ATYPE_
 #define _ATYPE32_
 #define _ATYPE64_
@@ -85,7 +85,7 @@ extern unsigned long vm_map_base;
 /*
  *  32/64-bit LoongArch address spaces
  */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ACAST32_
 #define _ACAST64_
 #else

arch/loongarch/include/asm/alternative-asm.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_ALTERNATIVE_ASM_H
 #define _ASM_ALTERNATIVE_ASM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/asm.h>
 
@@ -77,6 +77,6 @@
 	.previous
 .endm
 
-#endif  /*  __ASSEMBLY__  */
+#endif  /*  __ASSEMBLER__  */
 
 #endif /* _ASM_ALTERNATIVE_ASM_H */

arch/loongarch/include/asm/alternative.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_ALTERNATIVE_H
 #define _ASM_ALTERNATIVE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/stddef.h>
@@ -106,6 +106,6 @@ extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
 	(asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory"))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_ALTERNATIVE_H */

arch/loongarch/include/asm/asm-extable.h

@@ -7,7 +7,7 @@
 #define EX_TYPE_UACCESS_ERR_ZERO	2
 #define EX_TYPE_BPF			3
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
 	.pushsection	__ex_table, "a";		\
@@ -22,7 +22,7 @@
 	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0)
 	.endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #include <linux/bits.h>
 #include <linux/stringify.h>
@@ -60,6 +60,6 @@
 #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
 	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ASM_EXTABLE_H */

arch/loongarch/include/asm/asm.h

@@ -110,7 +110,7 @@
 #define LONG_SRA	srai.w
 #define LONG_SRAV	sra.w
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define LONG		.word
 #endif
 #define LONGSIZE	4
@@ -131,7 +131,7 @@
 #define LONG_SRA	srai.d
 #define LONG_SRAV	sra.d
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define LONG		.dword
 #endif
 #define LONGSIZE	8
@@ -158,7 +158,7 @@
 
 #define PTR_SCALESHIFT	2
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define PTR		.word
 #endif
 #define PTRSIZE		4
@@ -181,7 +181,7 @@
 
 #define PTR_SCALESHIFT	3
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define PTR		.dword
 #endif
 #define PTRSIZE		8

arch/loongarch/include/asm/cpu.h

@@ -46,7 +46,7 @@
 
 #define PRID_PRODUCT_MASK	0x0fff
 
-#if !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLER__)
 
 enum cpu_type_enum {
 	CPU_UNKNOWN,
@@ -55,7 +55,7 @@ enum cpu_type_enum {
 	CPU_LAST
 };
 
-#endif /* !__ASSEMBLY */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * ISA Level encodings

arch/loongarch/include/asm/ftrace.h

@@ -14,7 +14,7 @@
 
 #define MCOUNT_INSN_SIZE 4		/* sizeof mcount call */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifndef CONFIG_DYNAMIC_FTRACE
 
@@ -84,7 +84,7 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
 
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* CONFIG_FUNCTION_TRACER */
 

arch/loongarch/include/asm/gpr-num.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_GPR_NUM_H
 #define __ASM_GPR_NUM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.equ	.L__gpr_num_zero, 0
 	.irp	num,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
@@ -25,7 +25,7 @@
 	.equ	.L__gpr_num_$s\num, 23 + \num
 	.endr
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define __DEFINE_ASM_GPR_NUMS					\
 "	.equ	.L__gpr_num_zero, 0\n"				\
@@ -47,6 +47,6 @@
 "	.equ	.L__gpr_num_$s\\num, 23 + \\num\n"		\
 "	.endr\n"						\
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_GPR_NUM_H */

arch/loongarch/include/asm/irqflags.h

@@ -5,7 +5,7 @@
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/stringify.h>
@@ -80,6 +80,6 @@ static inline int arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
-#endif /* #ifndef __ASSEMBLY__ */
+#endif /* #ifndef __ASSEMBLER__ */
 
 #endif /* _ASM_IRQFLAGS_H */

arch/loongarch/include/asm/jump_label.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_JUMP_LABEL_H
 #define __ASM_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -50,5 +50,5 @@ l_yes:
 	return true;
 }
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif	/* __ASM_JUMP_LABEL_H */

arch/loongarch/include/asm/kasan.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <linux/mmzone.h>

arch/loongarch/include/asm/loongarch.h

@@ -9,15 +9,15 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <larchintrin.h>
 
 /* CPUCFG */
 #define read_cpucfg(reg) __cpucfg(reg)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /* LoongArch Registers */
 #define REG_ZERO	0x0
@@ -53,7 +53,7 @@
 #define REG_S7		0x1e
 #define REG_S8		0x1f
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* Bit fields for CPUCFG registers */
 #define LOONGARCH_CPUCFG0		0x0
@@ -171,7 +171,7 @@
  * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h
  */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* CSR */
 #define csr_read32(reg) __csrrd_w(reg)
@@ -187,7 +187,7 @@
 #define iocsr_write32(val, reg) __iocsrwr_w(val, reg)
 #define iocsr_write64(val, reg) __iocsrwr_d(val, reg)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* CSR register number */
 
@@ -1195,7 +1195,7 @@
 #define LOONGARCH_IOCSR_EXTIOI_ROUTE_BASE	0x1c00
 #define IOCSR_EXTIOI_VECTOR_NUM			256
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static __always_inline u64 drdtime(void)
 {
@@ -1357,7 +1357,7 @@ __BUILD_CSR_OP(tlbidx)
 #define clear_csr_estat(val)	\
 	csr_xchg32(~(val), val, LOONGARCH_CSR_ESTAT)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* Generic EntryLo bit definitions */
 #define ENTRYLO_V		(_ULCAST_(1) << 0)

arch/loongarch/include/asm/orc_types.h

@@ -34,7 +34,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -53,6 +53,6 @@ struct orc_entry {
 	unsigned int	type:3;
 	unsigned int	signal:1;
 };
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */

arch/loongarch/include/asm/page.h

@@ -15,7 +15,7 @@
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/kernel.h>
 #include <linux/pfn.h>
@@ -110,6 +110,6 @@ extern int __virt_addr_valid(volatile void *kaddr);
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PAGE_H */

arch/loongarch/include/asm/pgtable-bits.h

@@ -92,7 +92,7 @@
 #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_WUC)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define _PAGE_IOREMAP		pgprot_val(PAGE_KERNEL_SUC)
 
@@ -127,6 +127,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PGTABLE_BITS_H */

arch/loongarch/include/asm/pgtable.h

@@ -55,7 +55,7 @@
 
 #define USER_PTRS_PER_PGD       ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/mm_types.h>
 #include <linux/mmzone.h>
@@ -618,6 +618,6 @@ static inline long pmd_protnone(pmd_t pmd)
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PGTABLE_H */

arch/loongarch/include/asm/prefetch.h

@@ -8,7 +8,7 @@
 #define Pref_Load	0
 #define Pref_Store	8
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.macro	__pref hint addr
 #ifdef CONFIG_CPU_HAS_PREFETCH

arch/loongarch/include/asm/smp.h

@@ -39,7 +39,7 @@ int loongson_cpu_disable(void);
 void loongson_cpu_die(unsigned int cpu);
 #endif
 
-static inline void plat_smp_setup(void)
+static inline void __init plat_smp_setup(void)
 {
 	loongson_smp_setup();
 }

arch/loongarch/include/asm/thread_info.h

@@ -10,7 +10,7 @@
 
 #ifdef __KERNEL__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/processor.h>
 
@@ -53,7 +53,7 @@ static inline struct thread_info *current_thread_info(void)
 
 register unsigned long current_stack_pointer __asm__("$sp");
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* thread information allocation */
 #define THREAD_SIZE		SZ_16K

arch/loongarch/include/asm/types.h

@@ -8,7 +8,7 @@
 #include <asm-generic/int-ll64.h>
 #include <uapi/asm/types.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ULCAST_
 #define _U64CAST_
 #else

arch/loongarch/include/asm/unwind_hints.h

@@ -5,7 +5,7 @@
 #include <linux/objtool.h>
 #include <asm/orc_types.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro UNWIND_HINT_UNDEFINED
 	UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
@@ -23,7 +23,7 @@
 	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
 .endm
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #define UNWIND_HINT_SAVE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
@@ -31,6 +31,6 @@
 #define UNWIND_HINT_RESTORE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */

arch/loongarch/include/asm/vdso/arch_data.h

@@ -7,7 +7,7 @@
 #ifndef _VDSO_ARCH_DATA_H
 #define _VDSO_ARCH_DATA_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/vdso.h>
@@ -20,6 +20,6 @@ struct vdso_arch_data {
 	struct vdso_pcpu_data pdata[NR_CPUS];
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/loongarch/include/asm/vdso/getrandom.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vdso.h>
@@ -28,6 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */

arch/loongarch/include/asm/vdso/gettimeofday.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_VDSO_GETTIMEOFDAY_H
 #define __ASM_VDSO_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vdso.h>
@@ -89,6 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable loongarch_vdso_hres_capable
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/loongarch/include/asm/vdso/processor.h

@@ -5,10 +5,10 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define cpu_relax()	barrier()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */

arch/loongarch/include/asm/vdso/vdso.h

@@ -7,7 +7,7 @@
 #ifndef _ASM_VDSO_VDSO_H
 #define _ASM_VDSO_VDSO_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/page.h>
@@ -16,6 +16,6 @@
 
 #define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/loongarch/include/asm/vdso/vsyscall.h

@@ -2,13 +2,13 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */

arch/loongarch/kernel/acpi.c

@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/efi-bgrt.h>
+#include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/memblock.h>

arch/loongarch/kernel/alternative.c

@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <asm/alternative.h>

arch/loongarch/kernel/efi.c

@@ -144,6 +144,18 @@ void __init efi_init(void)
 		if (efi_memmap_init_early(&data) < 0)
 			panic("Unable to map EFI memory map.\n");
 
+		/*
+		 * Reserve the physical memory region occupied by the EFI
+		 * memory map table (header + descriptors). This is crucial
+		 * for kdump, as the kdump kernel relies on this original
+		 * memmap passed by the bootloader. Without reservation,
+		 * this region could be overwritten by the primary kernel.
+		 * Also, set the EFI_PRESERVE_BS_REGIONS flag to indicate that
+		 * critical boot services code/data regions like this are preserved.
+		 */
+		memblock_reserve((phys_addr_t)boot_memmap, sizeof(*tbl) + data.size);
+		set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags);
+
 		early_memunmap(tbl, sizeof(*tbl));
 	}
 

arch/loongarch/kernel/elf.c

@@ -6,7 +6,6 @@
 
 #include <linux/binfmts.h>
 #include <linux/elf.h>
-#include <linux/export.h>
 #include <linux/sched.h>
 
 #include <asm/cpu-features.h>

arch/loongarch/kernel/kfpu.c

@@ -4,6 +4,7 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <asm/fpu.h>
 #include <asm/smp.h>

arch/loongarch/kernel/paravirt.c

@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/irq_work.h>

arch/loongarch/kernel/time.c

@@ -102,7 +102,7 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev
 	return 0;
 }
 
-static unsigned long __init get_loops_per_jiffy(void)
+static unsigned long get_loops_per_jiffy(void)
 {
 	unsigned long lpj = (unsigned long)const_clock_freq;
 

arch/loongarch/kernel/traps.c

@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/module.h>
+#include <linux/export.h>
 #include <linux/extable.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>

arch/loongarch/kernel/unwind_guess.c

@@ -3,6 +3,7 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <asm/unwind.h>
+#include <linux/export.h>
 
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {

arch/loongarch/kernel/unwind_orc.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/objtool.h>
+#include <linux/export.h>
 #include <linux/module.h>
+#include <linux/objtool.h>
 #include <linux/sort.h>
 #include <asm/exception.h>
 #include <asm/orc_header.h>

arch/loongarch/kernel/unwind_prologue.c

@@ -3,6 +3,7 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <linux/cpumask.h>
+#include <linux/export.h>
 #include <linux/ftrace.h>
 #include <linux/kallsyms.h>
 

arch/loongarch/kvm/intc/eiointc.c

@@ -9,7 +9,8 @@
 
 static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 {
-	int ipnum, cpu, irq_index, irq_mask, irq;
+	int ipnum, cpu, cpuid, irq_index, irq_mask, irq;
+	struct kvm_vcpu *vcpu;
 
 	for (irq = 0; irq < EIOINTC_IRQS; irq++) {
 		ipnum = s->ipmap.reg_u8[irq / 32];
@@ -20,7 +21,12 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 		irq_index = irq / 32;
 		irq_mask = BIT(irq & 0x1f);
 
-		cpu = s->coremap.reg_u8[irq];
+		cpuid = s->coremap.reg_u8[irq];
+		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
+		if (!vcpu)
+			continue;
+
+		cpu = vcpu->vcpu_id;
 		if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask))
 			set_bit(irq, s->sw_coreisr[cpu][ipnum]);
 		else
@@ -66,20 +72,25 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 }
 
 static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s,
-					int irq, void *pvalue, u32 len, bool notify)
+					int irq, u64 val, u32 len, bool notify)
 {
-	int i, cpu;
-	u64 val = *(u64 *)pvalue;
+	int i, cpu, cpuid;
+	struct kvm_vcpu *vcpu;
 
 	for (i = 0; i < len; i++) {
-		cpu = val & 0xff;
+		cpuid = val & 0xff;
 		val = val >> 8;
 
 		if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) {
-			cpu = ffs(cpu) - 1;
-			cpu = (cpu >= 4) ? 0 : cpu;
+			cpuid = ffs(cpuid) - 1;
+			cpuid = (cpuid >= 4) ? 0 : cpuid;
 		}
 
+		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
+		if (!vcpu)
+			continue;
+
+		cpu = vcpu->vcpu_id;
 		if (s->sw_coremap[irq + i] == cpu)
 			continue;
 
@@ -305,6 +316,11 @@ static int kvm_eiointc_read(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	vcpu->kvm->stat.eiointc_read_exits++;
 	spin_lock_irqsave(&eiointc->lock, flags);
 	switch (len) {
@@ -398,7 +414,7 @@ static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq;
 		s->coremap.reg_u8[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -436,17 +452,16 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		break;
 	case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END:
 		index = (offset - EIOINTC_ENABLE_START) >> 1;
-		old_data = s->enable.reg_u32[index];
+		old_data = s->enable.reg_u16[index];
 		s->enable.reg_u16[index] = data;
 		/*
 		 * 1: enable irq.
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u16[index] & ~old_data & s->isr.reg_u16[index];
-		index = index << 1;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -455,7 +470,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u16[index] & old_data & s->isr.reg_u16[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
@@ -484,7 +499,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 1;
 		s->coremap.reg_u16[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -529,10 +544,9 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u32[index] & ~old_data & s->isr.reg_u32[index];
-		index = index << 2;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -541,7 +555,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u32[index] & old_data & s->isr.reg_u32[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
@@ -570,7 +584,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 2;
 		s->coremap.reg_u32[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -615,10 +629,9 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u64[index] & ~old_data & s->isr.reg_u64[index];
-		index = index << 3;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -627,7 +640,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u64[index] & old_data & s->isr.reg_u64[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
@@ -656,7 +669,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 3;
 		s->coremap.reg_u64[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -679,6 +692,11 @@ static int kvm_eiointc_write(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	vcpu->kvm->stat.eiointc_write_exits++;
 	spin_lock_irqsave(&eiointc->lock, flags);
 	switch (len) {
@@ -787,7 +805,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 	int ret = 0;
 	unsigned long flags;
 	unsigned long type = (unsigned long)attr->attr;
-	u32 i, start_irq;
+	u32 i, start_irq, val;
 	void __user *data;
 	struct loongarch_eiointc *s = dev->kvm->arch.eiointc;
 
@@ -795,8 +813,14 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 	spin_lock_irqsave(&s->lock, flags);
 	switch (type) {
 	case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU:
-		if (copy_from_user(&s->num_cpu, data, 4))
+		if (copy_from_user(&val, data, 4))
 			ret = -EFAULT;
+		else {
+			if (val >= EIOINTC_ROUTE_MAX_VCPUS)
+				ret = -EINVAL;
+			else
+				s->num_cpu = val;
+		}
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE:
 		if (copy_from_user(&s->features, data, 4))
@@ -809,7 +833,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 		for (i = 0; i < (EIOINTC_IRQS / 4); i++) {
 			start_irq = i * 4;
 			eiointc_update_sw_coremap(s, start_irq,
-					(void *)&s->coremap.reg_u32[i], sizeof(u32), false);
+					s->coremap.reg_u32[i], sizeof(u32), false);
 		}
 		break;
 	default:
@@ -824,7 +848,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 					struct kvm_device_attr *attr,
 					bool is_write)
 {
-	int addr, cpuid, offset, ret = 0;
+	int addr, cpu, offset, ret = 0;
 	unsigned long flags;
 	void *p = NULL;
 	void __user *data;
@@ -832,7 +856,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 
 	s = dev->kvm->arch.eiointc;
 	addr = attr->attr;
-	cpuid = addr >> 16;
+	cpu = addr >> 16;
 	addr &= 0xffff;
 	data = (void __user *)attr->addr;
 	switch (addr) {
@@ -857,8 +881,11 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 		p = &s->isr.reg_u32[offset];
 		break;
 	case EIOINTC_COREISR_START ... EIOINTC_COREISR_END:
+		if (cpu >= s->num_cpu)
+			return -EINVAL;
+
 		offset = (addr - EIOINTC_COREISR_START) / 4;
-		p = &s->coreisr.reg_u32[cpuid][offset];
+		p = &s->coreisr.reg_u32[cpu][offset];
 		break;
 	case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END:
 		offset = (addr - EIOINTC_COREMAP_START) / 4;
@@ -899,9 +926,15 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev,
 	data = (void __user *)attr->addr;
 	switch (addr) {
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU:
+		if (is_write)
+			return ret;
+
 		p = &s->num_cpu;
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE:
+		if (is_write)
+			return ret;
+
 		p = &s->features;
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE:

arch/loongarch/lib/crc32-loongarch.c

@@ -11,6 +11,7 @@
 
 #include <asm/cpu-features.h>
 #include <linux/crc32.h>
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/unaligned.h>
 

arch/loongarch/lib/csum.c

@@ -2,6 +2,7 @@
 // Copyright (C) 2019-2020 Arm Ltd.
 
 #include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/kasan-checks.h>
 #include <linux/kernel.h>
 

arch/loongarch/mm/ioremap.c

@@ -16,12 +16,12 @@ void __init early_iounmap(void __iomem *addr, unsigned long size)
 
 }
 
-void *early_memremap_ro(resource_size_t phys_addr, unsigned long size)
+void * __init early_memremap_ro(resource_size_t phys_addr, unsigned long size)
 {
 	return early_memremap(phys_addr, size);
 }
 
-void *early_memremap_prot(resource_size_t phys_addr, unsigned long size,
+void * __init early_memremap_prot(resource_size_t phys_addr, unsigned long size,
 		    unsigned long prot_val)
 {
 	return early_memremap(phys_addr, size);

arch/loongarch/pci/pci.c

@@ -3,7 +3,6 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/kernel.h>
-#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/types.h>

arch/riscv/Kconfig

@@ -63,7 +63,8 @@ config RISCV
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_CFI_CLANG
+	# clang >= 17: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2
+	select ARCH_SUPPORTS_CFI_CLANG if CLANG_VERSION >= 170000
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU

arch/riscv/include/asm/pgtable.h

@@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
  */
 #ifdef CONFIG_64BIT
 #define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)
-#define TASK_SIZE_MAX	LONG_MAX
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)

arch/riscv/include/asm/runtime-const.h

@@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u
 		addi_insn_mask &= 0x07fff;
 	}
 
-	if (lower_immediate & 0x00000fff) {
+	if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) {
 		/* replace upper 12 bits of addi with lower 12 bits of val */
 		addi_insn &= addi_insn_mask;
 		addi_insn |= (lower_immediate & 0x00000fff) << 20;

arch/riscv/include/asm/uaccess.h

@@ -127,6 +127,7 @@ do {								\
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 #define __get_user_8(x, ptr, label)				\
+do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
 	u32 __lo, __hi;						\
 	asm_goto_output(					\
@@ -141,7 +142,7 @@ do {								\
 		: : label);                                     \
 	(x) = (__typeof__(x))((__typeof__((x) - (x)))(		\
 		(((u64)__hi << 32) | __lo)));			\
-
+} while (0)
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 #define __get_user_8(x, ptr, label)				\
 do {								\

arch/riscv/include/asm/vdso/getrandom.h

@@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	register unsigned int flags asm("a2") = _flags;
 
 	asm volatile ("ecall\n"
-		      : "+r" (ret)
+		      : "=r" (ret)
 		      : "r" (nr), "r" (buffer), "r" (len), "r" (flags)
 		      : "memory");
 

arch/riscv/include/asm/vector.h

@@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VSB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (
@@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VLB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (

arch/riscv/kernel/cpu_ops_sbi.c

@@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi;
 
 /*
  * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
- * be invoked from multiple threads in parallel. Define a per cpu data
+ * be invoked from multiple threads in parallel. Define an array of boot data
  * to handle that.
  */
-static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+static struct sbi_hart_boot_data boot_data[NR_CPUS];
 
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
@@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	unsigned long hartid = cpuid_to_hartid_map(cpuid);
 	unsigned long hsm_data;
-	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+	struct sbi_hart_boot_data *bdata = &boot_data[cpuid];
 
 	/* Make sure tidle is updated */
 	smp_mb();

arch/riscv/kernel/setup.c

@@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
+EXPORT_SYMBOL_GPL(boot_cpu_hartid);
 
 /*
  * Place kernel memory regions on the resource tree so that

arch/riscv/kernel/traps_misaligned.c

@@ -454,7 +454,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 
 	val.data_u64 = 0;
 	if (user_mode(regs)) {
-		if (copy_from_user_nofault(&val, (u8 __user *)addr, len))
+		if (copy_from_user(&val, (u8 __user *)addr, len))
 			return -1;
 	} else {
 		memcpy(&val, (u8 *)addr, len);
@@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
 		return -EOPNOTSUPP;
 
 	if (user_mode(regs)) {
-		if (copy_to_user_nofault((u8 __user *)addr, &val, len))
+		if (copy_to_user((u8 __user *)addr, &val, len))
 			return -1;
 	} else {
 		memcpy((u8 *)addr, &val, len);

arch/riscv/kernel/vdso/vdso.lds.S

@@ -30,7 +30,7 @@ SECTIONS
 		*(.data .data.* .gnu.linkonce.d.*)
 		*(.dynbss)
 		*(.bss .bss.* .gnu.linkonce.b.*)
-	}
+	}						:text
 
 	.note		: { *(.note.*) }		:text	:note
 

arch/riscv/kernel/vendor_extensions/sifive.c

@@ -8,7 +8,7 @@
 #include <linux/types.h>
 
 /* All SiFive vendor extensions supported in Linux */
-const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
+static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
 	__RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF),
 	__RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ),
 	__RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD),

arch/s390/include/asm/ptrace.h

@@ -265,7 +265,7 @@ static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *r
 	addr = kernel_stack_pointer(regs) + n * sizeof(long);
 	if (!regs_within_kernel_stack(regs, addr))
 		return 0;
-	return READ_ONCE_NOCHECK(addr);
+	return READ_ONCE_NOCHECK(*(unsigned long *)addr);
 }
 
 /**

arch/s390/pci/pci_event.c

@@ -54,6 +54,7 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res)
 	case PCI_ERS_RESULT_CAN_RECOVER:
 	case PCI_ERS_RESULT_RECOVERED:
 	case PCI_ERS_RESULT_NEED_RESET:
+	case PCI_ERS_RESULT_NONE:
 		return false;
 	default:
 		return true;
@@ -78,10 +79,6 @@ static bool is_driver_supported(struct pci_driver *driver)
 		return false;
 	if (!driver->err_handler->error_detected)
 		return false;
-	if (!driver->err_handler->slot_reset)
-		return false;
-	if (!driver->err_handler->resume)
-		return false;
 	return true;
 }
 
@@ -106,6 +103,10 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
 	struct zpci_dev *zdev = to_zpci(pdev);
 	int rc;
 
+	/* The underlying device may have been disabled by the event */
+	if (!zdev_enabled(zdev))
+		return PCI_ERS_RESULT_NEED_RESET;
+
 	pr_info("%s: Unblocking device access for examination\n", pci_name(pdev));
 	rc = zpci_reset_load_store_blocked(zdev);
 	if (rc) {
@@ -114,16 +115,18 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
 		return PCI_ERS_RESULT_NEED_RESET;
 	}
 
-	if (driver->err_handler->mmio_enabled) {
+	if (driver->err_handler->mmio_enabled)
 		ers_res = driver->err_handler->mmio_enabled(pdev);
-		if (ers_result_indicates_abort(ers_res)) {
-			pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
-				pci_name(pdev));
-			return ers_res;
-		} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
-			pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
-			return ers_res;
-		}
+	else
+		ers_res = PCI_ERS_RESULT_NONE;
+
+	if (ers_result_indicates_abort(ers_res)) {
+		pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
+			pci_name(pdev));
+		return ers_res;
+	} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
+		pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+		return ers_res;
 	}
 
 	pr_debug("%s: Unblocking DMA\n", pci_name(pdev));
@@ -150,7 +153,12 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev,
 		return ers_res;
 	}
 	pdev->error_state = pci_channel_io_normal;
-	ers_res = driver->err_handler->slot_reset(pdev);
+
+	if (driver->err_handler->slot_reset)
+		ers_res = driver->err_handler->slot_reset(pdev);
+	else
+		ers_res = PCI_ERS_RESULT_NONE;
+
 	if (ers_result_indicates_abort(ers_res)) {
 		pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev));
 		return ers_res;
@@ -214,7 +222,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 		goto out_unlock;
 	}
 
-	if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) {
+	if (ers_res != PCI_ERS_RESULT_NEED_RESET) {
 		ers_res = zpci_event_do_error_state_clear(pdev, driver);
 		if (ers_result_indicates_abort(ers_res)) {
 			status_str = "failed (abort on MMIO enable)";
@@ -225,6 +233,16 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 	if (ers_res == PCI_ERS_RESULT_NEED_RESET)
 		ers_res = zpci_event_do_reset(pdev, driver);
 
+	/*
+	 * ers_res can be PCI_ERS_RESULT_NONE either because the driver
+	 * decided to return it, indicating that it abstains from voting
+	 * on how to recover, or because it didn't implement the callback.
+	 * Both cases assume, that if there is nothing else causing a
+	 * disconnect, we recovered successfully.
+	 */
+	if (ers_res == PCI_ERS_RESULT_NONE)
+		ers_res = PCI_ERS_RESULT_RECOVERED;
+
 	if (ers_res != PCI_ERS_RESULT_RECOVERED) {
 		pr_err("%s: Automatic recovery failed; operator intervention is required\n",
 		       pci_name(pdev));
@@ -273,6 +291,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = NULL;
 	pci_ers_result_t ers_res;
+	u32 fh = 0;
+	int rc;
 
 	zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
@@ -281,6 +301,15 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	if (zdev) {
 		mutex_lock(&zdev->state_lock);
+		rc = clp_refresh_fh(zdev->fid, &fh);
+		if (rc)
+			goto no_pdev;
+		if (!fh || ccdf->fh != fh) {
+			/* Ignore events with stale handles */
+			zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n",
+				 ccdf->fid, fh, ccdf->fh);
+			goto no_pdev;
+		}
 		zpci_update_fh(zdev, ccdf->fh);
 		if (zdev->zbus->bus)
 			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);

arch/x86/include/asm/debugreg.h

@@ -9,6 +9,14 @@
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
 
+/*
+ * Define bits that are always set to 1 in DR7, only bit 10 is
+ * architecturally reserved to '1'.
+ *
+ * This is also the init/reset value for DR7.
+ */
+#define DR7_FIXED_1	0x00000400
+
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
 #ifndef CONFIG_PARAVIRT_XXL
@@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 
 static inline void hw_breakpoint_disable(void)
 {
-	/* Zero the control register for HW Breakpoint */
-	set_debugreg(0UL, 7);
+	/* Reset the control register for HW Breakpoint */
+	set_debugreg(DR7_FIXED_1, 7);
 
 	/* Zero-out the individual HW breakpoint address registers */
 	set_debugreg(0UL, 0);
@@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void)
 		return 0;
 
 	get_debugreg(dr7, 7);
-	dr7 &= ~0x400; /* architecturally set bit */
+
+	/* Architecturally set bit */
+	dr7 &= ~DR7_FIXED_1;
 	if (dr7)
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
+
 	/*
 	 * Ensure the compiler doesn't lower the above statements into
 	 * the critical section; disabling breakpoints late would not

arch/x86/include/asm/kvm_host.h

@@ -31,6 +31,7 @@
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
@@ -249,7 +250,6 @@ enum x86_intercept_stage;
 #define DR7_BP_EN_MASK	0x000000ff
 #define DR7_GE		(1 << 9)
 #define DR7_GD		(1 << 13)
-#define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff2bff
 
 #define KVM_GUESTDBG_VALID_MASK \

arch/x86/include/uapi/asm/debugreg.h

@@ -15,7 +15,26 @@
    which debugging register was responsible for the trap.  The other bits
    are either reserved or not of interest to us. */
 
-/* Define reserved bits in DR6 which are always set to 1 */
+/*
+ * Define bits in DR6 which are set to 1 by default.
+ *
+ * This is also the DR6 architectural value following Power-up, Reset or INIT.
+ *
+ * Note, with the introduction of Bus Lock Detection (BLD) and Restricted
+ * Transactional Memory (RTM), the DR6 register has been modified:
+ *
+ * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports
+ *    Bus Lock Detection.  The assertion of a bus lock could clear it.
+ *
+ * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports
+ *    restricted transactional memory.  #DB occurred inside an RTM region
+ *    could clear it.
+ *
+ * Apparently, DR6.BLD and DR6.RTM are active low bits.
+ *
+ * As a result, DR6_RESERVED is an incorrect name now, but it is kept for
+ * compatibility.
+ */
 #define DR6_RESERVED	(0xFFFF0FF0)
 
 #define DR_TRAP0	(0x1)		/* db0 */

arch/x86/kernel/cpu/amd.c

@@ -9,7 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>

arch/x86/kernel/cpu/common.c

@@ -2243,20 +2243,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-/*
- * Clear all 6 debug registers:
- */
-static void clear_all_debug_regs(void)
+static void initialize_debug_regs(void)
 {
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		/* Ignore db4, db5 */
-		if ((i == 4) || (i == 5))
-			continue;
-
-		set_debugreg(0, i);
-	}
+	/* Control register first -- to make sure everything is disabled. */
+	set_debugreg(DR7_FIXED_1, 7);
+	set_debugreg(DR6_RESERVED, 6);
+	/* dr5 and dr4 don't exist */
+	set_debugreg(0, 3);
+	set_debugreg(0, 2);
+	set_debugreg(0, 1);
+	set_debugreg(0, 0);
 }
 
 #ifdef CONFIG_KGDB
@@ -2417,7 +2413,7 @@ void cpu_init(void)
 
 	load_mm_ldt(&init_mm);
 
-	clear_all_debug_regs();
+	initialize_debug_regs();
 	dbg_restore_debug_regs();
 
 	doublefault_init_cpu_tss();

arch/x86/kernel/kgdb.c

@@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
 	struct perf_event *bp;
 
 	/* Disable hardware debugging while we are in kgdb: */
-	set_debugreg(0UL, 7);
+	set_debugreg(DR7_FIXED_1, 7);
 	for (i = 0; i < HBP_NUM; i++) {
 		if (!breakinfo[i].enabled)
 			continue;

arch/x86/kernel/process_32.c

@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))
 		return;
 
 	printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",

arch/x86/kernel/process_64.c

@@ -133,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) {
 		printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
 		       log_lvl, d0, d1, d2);
 		printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",

arch/x86/kernel/traps.c

@@ -1022,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
 #endif
 }
 
-static __always_inline unsigned long debug_read_clear_dr6(void)
+static __always_inline unsigned long debug_read_reset_dr6(void)
 {
 	unsigned long dr6;
 
+	get_debugreg(dr6, 6);
+	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
 	/*
 	 * The Intel SDM says:
 	 *
-	 *   Certain debug exceptions may clear bits 0-3. The remaining
-	 *   contents of the DR6 register are never cleared by the
-	 *   processor. To avoid confusion in identifying debug
-	 *   exceptions, debug handlers should clear the register before
-	 *   returning to the interrupted task.
+	 *   Certain debug exceptions may clear bits 0-3 of DR6.
 	 *
-	 * Keep it simple: clear DR6 immediately.
+	 *   BLD induced #DB clears DR6.BLD and any other debug
+	 *   exception doesn't modify DR6.BLD.
+	 *
+	 *   RTM induced #DB clears DR6.RTM and any other debug
+	 *   exception sets DR6.RTM.
+	 *
+	 *   To avoid confusion in identifying debug exceptions,
+	 *   debug handlers should set DR6.BLD and DR6.RTM, and
+	 *   clear other DR6 bits before returning.
+	 *
+	 * Keep it simple: write DR6 with its architectural reset
+	 * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately.
 	 */
-	get_debugreg(dr6, 6);
 	set_debugreg(DR6_RESERVED, 6);
-	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
 
 	return dr6;
 }
@@ -1239,13 +1247,13 @@ out:
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	exc_debug_kernel(regs, debug_read_clear_dr6());
+	exc_debug_kernel(regs, debug_read_reset_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	exc_debug_user(regs, debug_read_clear_dr6());
+	exc_debug_user(regs, debug_read_reset_dr6());
 }
 
 #ifdef CONFIG_X86_FRED
@@ -1264,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 {
 	/*
 	 * FRED #DB stores DR6 on the stack in the format which
-	 * debug_read_clear_dr6() returns for the IDT entry points.
+	 * debug_read_reset_dr6() returns for the IDT entry points.
 	 */
 	unsigned long dr6 = fred_event_data(regs);
 
@@ -1279,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6 = debug_read_clear_dr6();
+	unsigned long dr6 = debug_read_reset_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);

arch/x86/kvm/x86.c

@@ -11035,7 +11035,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (unlikely(vcpu->arch.switch_db_regs &&
 		     !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
@@ -11044,7 +11044,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
 			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
 	} else if (unlikely(hw_breakpoint_active())) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 	}
 
 	vcpu->arch.host_debugctl = get_debugctlmsr();

block/genhd.c

@@ -128,23 +128,27 @@ static void part_stat_read_all(struct block_device *part,
 static void bdev_count_inflight_rw(struct block_device *part,
 		unsigned int inflight[2], bool mq_driver)
 {
+	int write = 0;
+	int read = 0;
 	int cpu;
 
 	if (mq_driver) {
 		blk_mq_in_driver_rw(part, inflight);
-	} else {
-		for_each_possible_cpu(cpu) {
-			inflight[READ] += part_stat_local_read_cpu(
-						part, in_flight[READ], cpu);
-			inflight[WRITE] += part_stat_local_read_cpu(
-						part, in_flight[WRITE], cpu);
-		}
+		return;
 	}
 
-	if (WARN_ON_ONCE((int)inflight[READ] < 0))
-		inflight[READ] = 0;
-	if (WARN_ON_ONCE((int)inflight[WRITE] < 0))
-		inflight[WRITE] = 0;
+	for_each_possible_cpu(cpu) {
+		read += part_stat_local_read_cpu(part, in_flight[READ], cpu);
+		write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu);
+	}
+
+	/*
+	 * While iterating all CPUs, some IOs may be issued from a CPU already
+	 * traversed and complete on a CPU that has not yet been traversed,
+	 * causing the inflight number to be negative.
+	 */
+	inflight[READ] = read > 0 ? read : 0;
+	inflight[WRITE] = write > 0 ? write : 0;
 }
 
 /**

crypto/wp512.c

@@ -21,10 +21,10 @@
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mm.h>
-#include <asm/byteorder.h>
-#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
 #define WP512_DIGEST_SIZE 64
 #define WP384_DIGEST_SIZE 48
@@ -37,9 +37,6 @@
 
 struct wp512_ctx {
 	u8  bitLength[WP512_LENGTHBYTES];
-	u8  buffer[WP512_BLOCK_SIZE];
-	int bufferBits;
-	int bufferPos;
 	u64 hash[WP512_DIGEST_SIZE/8];
 };
 
@@ -779,16 +776,16 @@ static const u64 rc[WHIRLPOOL_ROUNDS] = {
  * The core Whirlpool transform.
  */
 
-static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx) {
+static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx,
+						   const u8 *buffer) {
 	int i, r;
 	u64 K[8];        /* the round key */
 	u64 block[8];    /* mu(buffer) */
 	u64 state[8];    /* the cipher state */
 	u64 L[8];
-	const __be64 *buffer = (const __be64 *)wctx->buffer;
 
 	for (i = 0; i < 8; i++)
-		block[i] = be64_to_cpu(buffer[i]);
+		block[i] = get_unaligned_be64(buffer + i * 8);
 
 	state[0] = block[0] ^ (K[0] = wctx->hash[0]);
 	state[1] = block[1] ^ (K[1] = wctx->hash[1]);
@@ -991,8 +988,6 @@ static int wp512_init(struct shash_desc *desc) {
 	int i;
 
 	memset(wctx->bitLength, 0, 32);
-	wctx->bufferBits = wctx->bufferPos = 0;
-	wctx->buffer[0] = 0;
 	for (i = 0; i < 8; i++) {
 		wctx->hash[i] = 0L;
 	}
@@ -1000,84 +995,54 @@ static int wp512_init(struct shash_desc *desc) {
 	return 0;
 }
 
-static int wp512_update(struct shash_desc *desc, const u8 *source,
-			 unsigned int len)
+static void wp512_add_length(u8 *bitLength, u64 value)
 {
-	struct wp512_ctx *wctx = shash_desc_ctx(desc);
-	int sourcePos    = 0;
-	unsigned int bits_len = len * 8; // convert to number of bits
-	int sourceGap    = (8 - ((int)bits_len & 7)) & 7;
-	int bufferRem    = wctx->bufferBits & 7;
+	u32 carry;
 	int i;
-	u32 b, carry;
-	u8 *buffer       = wctx->buffer;
-	u8 *bitLength    = wctx->bitLength;
-	int bufferBits   = wctx->bufferBits;
-	int bufferPos    = wctx->bufferPos;
 
-	u64 value = bits_len;
 	for (i = 31, carry = 0; i >= 0 && (carry != 0 || value != 0ULL); i--) {
 		carry += bitLength[i] + ((u32)value & 0xff);
 		bitLength[i] = (u8)carry;
 		carry >>= 8;
 		value >>= 8;
 	}
-	while (bits_len > 8) {
-		b = ((source[sourcePos] << sourceGap) & 0xff) |
-		((source[sourcePos + 1] & 0xff) >> (8 - sourceGap));
-		buffer[bufferPos++] |= (u8)(b >> bufferRem);
-		bufferBits += 8 - bufferRem;
-		if (bufferBits == WP512_BLOCK_SIZE * 8) {
-			wp512_process_buffer(wctx);
-			bufferBits = bufferPos = 0;
-		}
-		buffer[bufferPos] = b << (8 - bufferRem);
-		bufferBits += bufferRem;
-		bits_len -= 8;
-		sourcePos++;
-	}
-	if (bits_len > 0) {
-		b = (source[sourcePos] << sourceGap) & 0xff;
-		buffer[bufferPos] |= b >> bufferRem;
-	} else {
-		b = 0;
-	}
-	if (bufferRem + bits_len < 8) {
-		bufferBits += bits_len;
-	} else {
-		bufferPos++;
-		bufferBits += 8 - bufferRem;
-		bits_len -= 8 - bufferRem;
-		if (bufferBits == WP512_BLOCK_SIZE * 8) {
-			wp512_process_buffer(wctx);
-			bufferBits = bufferPos = 0;
-		}
-		buffer[bufferPos] = b << (8 - bufferRem);
-		bufferBits += (int)bits_len;
-	}
-
-	wctx->bufferBits   = bufferBits;
-	wctx->bufferPos    = bufferPos;
-
-	return 0;
 }
 
-static int wp512_final(struct shash_desc *desc, u8 *out)
+static int wp512_update(struct shash_desc *desc, const u8 *source,
+			 unsigned int len)
+{
+	struct wp512_ctx *wctx = shash_desc_ctx(desc);
+	unsigned int remain = len % WP512_BLOCK_SIZE;
+	u64 bits_len = (len - remain) * 8ull;
+	u8 *bitLength    = wctx->bitLength;
+
+	wp512_add_length(bitLength, bits_len);
+	do {
+		wp512_process_buffer(wctx, source);
+		source += WP512_BLOCK_SIZE;
+		bits_len -= WP512_BLOCK_SIZE * 8;
+	} while (bits_len);
+
+	return remain;
+}
+
+static int wp512_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int bufferPos, u8 *out)
 {
 	struct wp512_ctx *wctx = shash_desc_ctx(desc);
 	int i;
-	u8 *buffer      = wctx->buffer;
 	u8 *bitLength   = wctx->bitLength;
-	int bufferBits  = wctx->bufferBits;
-	int bufferPos   = wctx->bufferPos;
 	__be64 *digest  = (__be64 *)out;
+	u8 buffer[WP512_BLOCK_SIZE];
 
-	buffer[bufferPos] |= 0x80U >> (bufferBits & 7);
+	wp512_add_length(bitLength, bufferPos * 8);
+	memcpy(buffer, src, bufferPos);
+	buffer[bufferPos] = 0x80U;
 	bufferPos++;
 	if (bufferPos > WP512_BLOCK_SIZE - WP512_LENGTHBYTES) {
 		if (bufferPos < WP512_BLOCK_SIZE)
 			memset(&buffer[bufferPos], 0, WP512_BLOCK_SIZE - bufferPos);
-		wp512_process_buffer(wctx);
+		wp512_process_buffer(wctx, buffer);
 		bufferPos = 0;
 	}
 	if (bufferPos < WP512_BLOCK_SIZE - WP512_LENGTHBYTES)
@@ -1086,31 +1051,32 @@ static int wp512_final(struct shash_desc *desc, u8 *out)
 	bufferPos = WP512_BLOCK_SIZE - WP512_LENGTHBYTES;
 	memcpy(&buffer[WP512_BLOCK_SIZE - WP512_LENGTHBYTES],
 		   bitLength, WP512_LENGTHBYTES);
-	wp512_process_buffer(wctx);
+	wp512_process_buffer(wctx, buffer);
+	memzero_explicit(buffer, sizeof(buffer));
 	for (i = 0; i < WP512_DIGEST_SIZE/8; i++)
 		digest[i] = cpu_to_be64(wctx->hash[i]);
-	wctx->bufferBits   = bufferBits;
-	wctx->bufferPos    = bufferPos;
 
 	return 0;
 }
 
-static int wp384_final(struct shash_desc *desc, u8 *out)
+static int wp384_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *out)
 {
 	u8 D[64];
 
-	wp512_final(desc, D);
+	wp512_finup(desc, src, len, D);
 	memcpy(out, D, WP384_DIGEST_SIZE);
 	memzero_explicit(D, WP512_DIGEST_SIZE);
 
 	return 0;
 }
 
-static int wp256_final(struct shash_desc *desc, u8 *out)
+static int wp256_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *out)
 {
 	u8 D[64];
 
-	wp512_final(desc, D);
+	wp512_finup(desc, src, len, D);
 	memcpy(out, D, WP256_DIGEST_SIZE);
 	memzero_explicit(D, WP512_DIGEST_SIZE);
 
@@ -1121,11 +1087,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP512_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp512_final,
+	.finup		=	wp512_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp512",
 		.cra_driver_name =	"wp512-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -1133,11 +1100,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP384_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp384_final,
+	.finup		=	wp384_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp384",
 		.cra_driver_name =	"wp384-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -1145,11 +1113,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP256_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp256_final,
+	.finup		=	wp256_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp256",
 		.cra_driver_name =	"wp256-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}

drivers/acpi/battery.c

@@ -243,23 +243,10 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 	case POWER_SUPPLY_PROP_POWER_NOW:
-		if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN) {
+		if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN)
 			ret = -ENODEV;
-			break;
-		}
-
-		val->intval = battery->rate_now * 1000;
-		/*
-		 * When discharging, the current should be reported as a
-		 * negative number as per the power supply class interface
-		 * definition.
-		 */
-		if (psp == POWER_SUPPLY_PROP_CURRENT_NOW &&
-		    (battery->state & ACPI_BATTERY_STATE_DISCHARGING) &&
-		    acpi_battery_handle_discharging(battery)
-				== POWER_SUPPLY_STATUS_DISCHARGING)
-			val->intval = -val->intval;
-
+		else
+			val->intval = battery->rate_now * 1000;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
 	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:

drivers/ata/ahci.c

@@ -1450,7 +1450,7 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 		{
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-				DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "ASUSPRO D840MB_M840SA"),
 			},
 			/* 320 is broken, there is no known good version. */
 		},

drivers/base/power/main.c

@@ -1236,6 +1236,7 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
+	pm_restore_gfp_mask();
 	dpm_resume(state);
 	dpm_complete(state);
 }
@@ -2176,8 +2177,10 @@ int dpm_suspend_start(pm_message_t state)
 	error = dpm_prepare(state);
 	if (error)
 		dpm_save_failed_step(SUSPEND_PREPARE);
-	else
+	else {
+		pm_restrict_gfp_mask();
 		error = dpm_suspend(state);
+	}
 
 	dpm_show_time(starttime, state, error, "start");
 	return error;

drivers/block/brd.c

@@ -64,13 +64,15 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector,
 
 	rcu_read_unlock();
 	page = alloc_page(gfp | __GFP_ZERO | __GFP_HIGHMEM);
-	rcu_read_lock();
-	if (!page)
+	if (!page) {
+		rcu_read_lock();
 		return ERR_PTR(-ENOMEM);
+	}
 
 	xa_lock(&brd->brd_pages);
 	ret = __xa_cmpxchg(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT, NULL,
 			page, gfp);
+	rcu_read_lock();
 	if (ret) {
 		xa_unlock(&brd->brd_pages);
 		__free_page(page);

drivers/block/ublk_drv.c

@@ -1148,8 +1148,8 @@ exit:
 	blk_mq_end_request(req, res);
 }
 
-static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
-				 int res, unsigned issue_flags)
+static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io,
+						     struct request *req)
 {
 	/* read cmd first because req will overwrite it */
 	struct io_uring_cmd *cmd = io->cmd;
@@ -1164,6 +1164,13 @@ static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
 	io->flags &= ~UBLK_IO_FLAG_ACTIVE;
 
 	io->req = req;
+	return cmd;
+}
+
+static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
+				 int res, unsigned issue_flags)
+{
+	struct io_uring_cmd *cmd = __ublk_prep_compl_io_cmd(io, req);
 
 	/* tell ublksrv one io request is coming */
 	io_uring_cmd_done(cmd, res, 0, issue_flags);
@@ -1416,6 +1423,14 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+static inline bool ublk_belong_to_same_batch(const struct ublk_io *io,
+					     const struct ublk_io *io2)
+{
+	return (io_uring_cmd_ctx_handle(io->cmd) ==
+		io_uring_cmd_ctx_handle(io2->cmd)) &&
+		(io->task == io2->task);
+}
+
 static void ublk_queue_rqs(struct rq_list *rqlist)
 {
 	struct rq_list requeue_list = { };
@@ -1427,14 +1442,16 @@ static void ublk_queue_rqs(struct rq_list *rqlist)
 		struct ublk_queue *this_q = req->mq_hctx->driver_data;
 		struct ublk_io *this_io = &this_q->ios[req->tag];
 
-		if (io && io->task != this_io->task && !rq_list_empty(&submit_list))
+		if (ublk_prep_req(this_q, req, true) != BLK_STS_OK) {
+			rq_list_add_tail(&requeue_list, req);
+			continue;
+		}
+
+		if (io && !ublk_belong_to_same_batch(io, this_io) &&
+				!rq_list_empty(&submit_list))
 			ublk_queue_cmd_list(io, &submit_list);
 		io = this_io;
-
-		if (ublk_prep_req(this_q, req, true) == BLK_STS_OK)
-			rq_list_add_tail(&submit_list, req);
-		else
-			rq_list_add_tail(&requeue_list, req);
+		rq_list_add_tail(&submit_list, req);
 	}
 
 	if (!rq_list_empty(&submit_list))
@@ -2148,10 +2165,9 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq,
 	return 0;
 }
 
-static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io)
+static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io,
+			  struct request *req)
 {
-	struct request *req = io->req;
-
 	/*
 	 * We have handled UBLK_IO_NEED_GET_DATA command,
 	 * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just
@@ -2178,6 +2194,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	u32 cmd_op = cmd->cmd_op;
 	unsigned tag = ub_cmd->tag;
 	int ret = -EINVAL;
+	struct request *req;
 
 	pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n",
 			__func__, cmd->cmd_op, ub_cmd->q_id, tag,
@@ -2236,11 +2253,19 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			goto out;
 		break;
 	case UBLK_IO_NEED_GET_DATA:
-		io->addr = ub_cmd->addr;
-		if (!ublk_get_data(ubq, io))
-			return -EIOCBQUEUED;
-
-		return UBLK_IO_RES_OK;
+		/*
+		 * ublk_get_data() may fail and fallback to requeue, so keep
+		 * uring_cmd active first and prepare for handling new requeued
+		 * request
+		 */
+		req = io->req;
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
+		io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV;
+		if (likely(ublk_get_data(ubq, io, req))) {
+			__ublk_prep_compl_io_cmd(io, req);
+			return UBLK_IO_RES_OK;
+		}
+		break;
 	default:
 		goto out;
 	}
@@ -2825,7 +2850,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	if (copy_from_user(&info, argp, sizeof(info)))
 		return -EFAULT;
 
-	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES)
+	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth ||
+	    info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues)
 		return -EINVAL;
 
 	if (capable(CAP_SYS_ADMIN))

drivers/cxl/core/edac.c

@@ -103,10 +103,10 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
 				u8 *cap, u16 *cycle, u8 *flags, u8 *min_cycle)
 {
 	struct cxl_mailbox *cxl_mbox;
-	u8 min_scrub_cycle = U8_MAX;
 	struct cxl_region_params *p;
 	struct cxl_memdev *cxlmd;
 	struct cxl_region *cxlr;
+	u8 min_scrub_cycle = 0;
 	int i, ret;
 
 	if (!cxl_ps_ctx->cxlr) {
@@ -133,8 +133,12 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
 		if (ret)
 			return ret;
 
+		/*
+		 * The min_scrub_cycle of a region is the max of minimum scrub
+		 * cycles supported by memdevs that back the region.
+		 */
 		if (min_cycle)
-			min_scrub_cycle = min(*min_cycle, min_scrub_cycle);
+			min_scrub_cycle = max(*min_cycle, min_scrub_cycle);
 	}
 
 	if (min_cycle)
@@ -1099,8 +1103,10 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
 	old_rec = xa_store(&array_rec->rec_gen_media,
 			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
 			   GFP_KERNEL);
-	if (xa_is_err(old_rec))
+	if (xa_is_err(old_rec)) {
+		kfree(rec);
 		return xa_err(old_rec);
+	}
 
 	kfree(old_rec);
 
@@ -1127,8 +1133,10 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
 	old_rec = xa_store(&array_rec->rec_dram,
 			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
 			   GFP_KERNEL);
-	if (xa_is_err(old_rec))
+	if (xa_is_err(old_rec)) {
+		kfree(rec);
 		return xa_err(old_rec);
+	}
 
 	kfree(old_rec);
 
@@ -1315,7 +1323,7 @@ cxl_mem_get_rec_dram(struct cxl_memdev *cxlmd,
 		attrbs.bank = ctx->bank;
 	break;
 	case EDAC_REPAIR_RANK_SPARING:
-		attrbs.repair_type = CXL_BANK_SPARING;
+		attrbs.repair_type = CXL_RANK_SPARING;
 		break;
 	default:
 		return NULL;

drivers/cxl/core/features.c

@@ -544,7 +544,7 @@ static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs,
 	u32 flags;
 
 	if (rpc_in->op_size < sizeof(uuid_t))
-		return ERR_PTR(-EINVAL);
+		return false;
 
 	feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid);
 	if (IS_ERR(feat))

drivers/cxl/core/ras.c

@@ -31,40 +31,38 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 					       ras_cap.header_log);
 }
 
-static void cxl_cper_trace_corr_prot_err(struct pci_dev *pdev,
-				  struct cxl_ras_capability_regs ras_cap)
+static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd,
+					 struct cxl_ras_capability_regs ras_cap)
 {
 	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
-	struct cxl_dev_state *cxlds;
 
-	cxlds = pci_get_drvdata(pdev);
-	if (!cxlds)
-		return;
-
-	trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
+	trace_cxl_aer_correctable_error(cxlmd, status);
 }
 
-static void cxl_cper_trace_uncorr_prot_err(struct pci_dev *pdev,
-				    struct cxl_ras_capability_regs ras_cap)
+static void
+cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
+			       struct cxl_ras_capability_regs ras_cap)
 {
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
-	struct cxl_dev_state *cxlds;
 	u32 fe;
 
-	cxlds = pci_get_drvdata(pdev);
-	if (!cxlds)
-		return;
-
 	if (hweight32(status) > 1)
 		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
 				   ras_cap.cap_control));
 	else
 		fe = status;
 
-	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe,
+	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe,
 					  ras_cap.header_log);
 }
 
+static int match_memdev_by_parent(struct device *dev, const void *uport)
+{
+	if (is_cxl_memdev(dev) && dev->parent == uport)
+		return 1;
+	return 0;
+}
+
 static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 {
 	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
@@ -73,13 +71,12 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 		pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment,
 					    data->prot_err.agent_addr.bus,
 					    devfn);
+	struct cxl_memdev *cxlmd;
 	int port_type;
 
 	if (!pdev)
 		return;
 
-	guard(device)(&pdev->dev);
-
 	port_type = pci_pcie_type(pdev);
 	if (port_type == PCI_EXP_TYPE_ROOT_PORT ||
 	    port_type == PCI_EXP_TYPE_DOWNSTREAM ||
@@ -92,10 +89,20 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 		return;
 	}
 
+	guard(device)(&pdev->dev);
+	if (!pdev->dev.driver)
+		return;
+
+	struct device *mem_dev __free(put_device) = bus_find_device(
+		&cxl_bus_type, NULL, pdev, match_memdev_by_parent);
+	if (!mem_dev)
+		return;
+
+	cxlmd = to_cxl_memdev(mem_dev);
 	if (data->severity == AER_CORRECTABLE)
-		cxl_cper_trace_corr_prot_err(pdev, data->ras_cap);
+		cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap);
 	else
-		cxl_cper_trace_uncorr_prot_err(pdev, data->ras_cap);
+		cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap);
 }
 
 static void cxl_cper_prot_err_work_fn(struct work_struct *work)

drivers/dma-buf/dma-resv.c

@@ -685,11 +685,13 @@ long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 	dma_resv_iter_begin(&cursor, obj, usage);
 	dma_resv_for_each_fence_unlocked(&cursor, fence) {
 
-		ret = dma_fence_wait_timeout(fence, intr, ret);
-		if (ret <= 0) {
-			dma_resv_iter_end(&cursor);
-			return ret;
-		}
+		ret = dma_fence_wait_timeout(fence, intr, timeout);
+		if (ret <= 0)
+			break;
+
+		/* Even for zero timeout the return value is 1 */
+		if (timeout)
+			timeout = ret;
 	}
 	dma_resv_iter_end(&cursor);
 

drivers/edac/amd64_edac.c

@@ -1209,7 +1209,9 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	if (csrow_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_PRIMARY;
 
-	/* Asymmetric dual-rank DIMM support. */
+	if (csrow_sec_enabled(2 * dimm, ctrl, pvt))
+		cs_mode |= CS_EVEN_SECONDARY;
+
 	if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_SECONDARY;
 
@@ -1230,12 +1232,13 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	return cs_mode;
 }
 
-static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
-				  int csrow_nr, int dimm)
+static int calculate_cs_size(u32 mask, unsigned int cs_mode)
 {
-	u32 msb, weight, num_zero_bits;
-	u32 addr_mask_deinterleaved;
-	int size = 0;
+	int msb, weight, num_zero_bits;
+	u32 deinterleaved_mask;
+
+	if (!mask)
+		return 0;
 
 	/*
 	 * The number of zero bits in the mask is equal to the number of bits
@@ -1248,19 +1251,30 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 	 * without swapping with the most significant bit. This can be handled
 	 * by keeping the MSB where it is and ignoring the single zero bit.
 	 */
-	msb = fls(addr_mask_orig) - 1;
-	weight = hweight_long(addr_mask_orig);
+	msb = fls(mask) - 1;
+	weight = hweight_long(mask);
 	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
 
 	/* Take the number of zero bits off from the top of the mask. */
-	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
+	deinterleaved_mask = GENMASK(msb - num_zero_bits, 1);
+	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask);
+
+	return (deinterleaved_mask >> 2) + 1;
+}
+
+static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec,
+				  unsigned int cs_mode, int csrow_nr, int dimm)
+{
+	int size;
 
 	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
-	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
-	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
+	edac_dbg(1, "  Primary AddrMask: 0x%x\n", addr_mask);
 
 	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
-	size = (addr_mask_deinterleaved >> 2) + 1;
+	size = calculate_cs_size(addr_mask, cs_mode);
+
+	edac_dbg(1, "  Secondary AddrMask: 0x%x\n", addr_mask_sec);
+	size += calculate_cs_size(addr_mask_sec, cs_mode);
 
 	/* Return size in MBs. */
 	return size >> 10;
@@ -1269,8 +1283,8 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
+	u32 addr_mask = 0, addr_mask_sec = 0;
 	int cs_mask_nr = csrow_nr;
-	u32 addr_mask_orig;
 	int dimm, size = 0;
 
 	/* No Chip Selects are enabled. */
@@ -1308,13 +1322,13 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 	if (!pvt->flags.zn_regs_v2)
 		cs_mask_nr >>= 1;
 
-	/* Asymmetric dual-rank DIMM support. */
-	if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY))
-		addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr];
-	else
-		addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr];
+	if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY))
+		addr_mask = pvt->csels[umc].csmasks[cs_mask_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm);
+	if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY))
+		addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr];
+
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm);
 }
 
 static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -3512,9 +3526,10 @@ static void gpu_get_err_info(struct mce *m, struct err_info *err)
 static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
-	u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask		= pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask_sec	= pvt->csels[umc].csmasks_sec[csrow_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1);
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1);
 }
 
 static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)

drivers/firmware/arm_ffa/driver.c

@@ -110,7 +110,7 @@ struct ffa_drv_info {
 	struct work_struct sched_recv_irq_work;
 	struct xarray partition_info;
 	DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS));
-	struct mutex notify_lock; /* lock to protect notifier hashtable  */
+	rwlock_t notify_lock; /* lock to protect notifier hashtable  */
 };
 
 static struct ffa_drv_info *drv_info;
@@ -1250,13 +1250,12 @@ notifier_hnode_get_by_type(u16 notify_id, enum notify_type type)
 	return NULL;
 }
 
-static int
-update_notifier_cb(struct ffa_device *dev, int notify_id, void *cb,
-		   void *cb_data, bool is_registration, bool is_framework)
+static int update_notifier_cb(struct ffa_device *dev, int notify_id,
+			      struct notifier_cb_info *cb, bool is_framework)
 {
 	struct notifier_cb_info *cb_info = NULL;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
-	bool cb_found;
+	bool cb_found, is_registration = !!cb;
 
 	if (is_framework)
 		cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, dev->vm_id,
@@ -1270,20 +1269,10 @@ update_notifier_cb(struct ffa_device *dev, int notify_id, void *cb,
 		return -EINVAL;
 
 	if (is_registration) {
-		cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
-		if (!cb_info)
-			return -ENOMEM;
-
-		cb_info->dev = dev;
-		cb_info->cb_data = cb_data;
-		if (is_framework)
-			cb_info->fwk_cb = cb;
-		else
-			cb_info->cb = cb;
-
-		hash_add(drv_info->notifier_hash, &cb_info->hnode, notify_id);
+		hash_add(drv_info->notifier_hash, &cb->hnode, notify_id);
 	} else {
 		hash_del(&cb_info->hnode);
+		kfree(cb_info);
 	}
 
 	return 0;
@@ -1300,20 +1289,19 @@ static int __ffa_notify_relinquish(struct ffa_device *dev, int notify_id,
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
-	mutex_lock(&drv_info->notify_lock);
+	write_lock(&drv_info->notify_lock);
 
-	rc = update_notifier_cb(dev, notify_id, NULL, NULL, false,
-				is_framework);
+	rc = update_notifier_cb(dev, notify_id, NULL, is_framework);
 	if (rc) {
 		pr_err("Could not unregister notification callback\n");
-		mutex_unlock(&drv_info->notify_lock);
+		write_unlock(&drv_info->notify_lock);
 		return rc;
 	}
 
 	if (!is_framework)
 		rc = ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 
-	mutex_unlock(&drv_info->notify_lock);
+	write_unlock(&drv_info->notify_lock);
 
 	return rc;
 }
@@ -1334,6 +1322,7 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 {
 	int rc;
 	u32 flags = 0;
+	struct notifier_cb_info *cb_info = NULL;
 
 	if (ffa_notifications_disabled())
 		return -EOPNOTSUPP;
@@ -1341,28 +1330,40 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
-	mutex_lock(&drv_info->notify_lock);
+	cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
+	if (!cb_info)
+		return -ENOMEM;
+
+	cb_info->dev = dev;
+	cb_info->cb_data = cb_data;
+	if (is_framework)
+		cb_info->fwk_cb = cb;
+	else
+		cb_info->cb = cb;
+
+	write_lock(&drv_info->notify_lock);
 
 	if (!is_framework) {
 		if (is_per_vcpu)
 			flags = PER_VCPU_NOTIFICATION_FLAG;
 
 		rc = ffa_notification_bind(dev->vm_id, BIT(notify_id), flags);
-		if (rc) {
-			mutex_unlock(&drv_info->notify_lock);
-			return rc;
-		}
+		if (rc)
+			goto out_unlock_free;
 	}
 
-	rc = update_notifier_cb(dev, notify_id, cb, cb_data, true,
-				is_framework);
+	rc = update_notifier_cb(dev, notify_id, cb_info, is_framework);
 	if (rc) {
 		pr_err("Failed to register callback for %d - %d\n",
 		       notify_id, rc);
 		if (!is_framework)
 			ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 	}
-	mutex_unlock(&drv_info->notify_lock);
+
+out_unlock_free:
+	write_unlock(&drv_info->notify_lock);
+	if (rc)
+		kfree(cb_info);
 
 	return rc;
 }
@@ -1406,9 +1407,9 @@ static void handle_notif_callbacks(u64 bitmap, enum notify_type type)
 		if (!(bitmap & 1))
 			continue;
 
-		mutex_lock(&drv_info->notify_lock);
+		read_lock(&drv_info->notify_lock);
 		cb_info = notifier_hnode_get_by_type(notify_id, type);
-		mutex_unlock(&drv_info->notify_lock);
+		read_unlock(&drv_info->notify_lock);
 
 		if (cb_info && cb_info->cb)
 			cb_info->cb(notify_id, cb_info->cb_data);
@@ -1446,9 +1447,9 @@ static void handle_fwk_notif_callbacks(u32 bitmap)
 
 	ffa_rx_release();
 
-	mutex_lock(&drv_info->notify_lock);
+	read_lock(&drv_info->notify_lock);
 	cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, &uuid);
-	mutex_unlock(&drv_info->notify_lock);
+	read_unlock(&drv_info->notify_lock);
 
 	if (cb_info && cb_info->fwk_cb)
 		cb_info->fwk_cb(notify_id, cb_info->cb_data, buf);
@@ -1973,7 +1974,7 @@ static void ffa_notifications_setup(void)
 		goto cleanup;
 
 	hash_init(drv_info->notifier_hash);
-	mutex_init(&drv_info->notify_lock);
+	rwlock_init(&drv_info->notify_lock);
 
 	drv_info->notif_enabled = true;
 	return;

drivers/firmware/samsung/exynos-acpm.c

@@ -430,6 +430,9 @@ int acpm_do_xfer(const struct acpm_handle *handle, const struct acpm_xfer *xfer)
 		return -EOPNOTSUPP;
 	}
 
+	msg.chan_id = xfer->acpm_chan_id;
+	msg.chan_type = EXYNOS_MBOX_CHAN_TYPE_DOORBELL;
+
 	scoped_guard(mutex, &achan->tx_lock) {
 		tx_front = readl(achan->tx.front);
 		idx = (tx_front + 1) % achan->qlen;
@@ -446,25 +449,15 @@ int acpm_do_xfer(const struct acpm_handle *handle, const struct acpm_xfer *xfer)
 
 		/* Advance TX front. */
 		writel(idx, achan->tx.front);
+
+		ret = mbox_send_message(achan->chan, (void *)&msg);
+		if (ret < 0)
+			return ret;
+
+		mbox_client_txdone(achan->chan, 0);
 	}
 
-	msg.chan_id = xfer->acpm_chan_id;
-	msg.chan_type = EXYNOS_MBOX_CHAN_TYPE_DOORBELL;
-	ret = mbox_send_message(achan->chan, (void *)&msg);
-	if (ret < 0)
-		return ret;
-
-	ret = acpm_wait_for_message_response(achan, xfer);
-
-	/*
-	 * NOTE: we might prefer not to need the mailbox ticker to manage the
-	 * transfer queueing since the protocol layer queues things by itself.
-	 * Unfortunately, we have to kick the mailbox framework after we have
-	 * received our message.
-	 */
-	mbox_client_txdone(achan->chan, ret);
-
-	return ret;
+	return acpm_wait_for_message_response(achan, xfer);
 }
 
 /**