From 0cb6f1e436accba7882bb3115408d1474c1e14af Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 1 Dec 2023 18:53:40 +0100
Subject: [PATCH 001/352] KVM: x86: Implement test_cc() in C

Current test_cc() uses the fastop infrastructure to test flags using
SETcc instructions. However, int3_emulate_jcc() already fully
implements the flags->CC mapping, use that.

Removes a pile of gnarly asm.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103439.637049932@infradead.org
---
 arch/x86/include/asm/text-patching.h | 20 ++++++++++------
 arch/x86/kvm/emulate.c               | 34 ++--------------------------
 2 files changed, 15 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 5337f1be18f6..f2d142a0a862 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -178,9 +178,9 @@ void int3_emulate_ret(struct pt_regs *regs)
 }
 
 static __always_inline
-void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp)
+bool __emulate_cc(unsigned long flags, u8 cc)
 {
-	static const unsigned long jcc_mask[6] = {
+	static const unsigned long cc_mask[6] = {
 		[0] = X86_EFLAGS_OF,
 		[1] = X86_EFLAGS_CF,
 		[2] = X86_EFLAGS_ZF,
@@ -193,15 +193,21 @@ void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned lo
 	bool match;
 
 	if (cc < 0xc) {
-		match = regs->flags & jcc_mask[cc >> 1];
+		match = flags & cc_mask[cc >> 1];
 	} else {
-		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
-			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
+		match = ((flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
+			((flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
 		if (cc >= 0xe)
-			match = match || (regs->flags & X86_EFLAGS_ZF);
+			match = match || (flags & X86_EFLAGS_ZF);
 	}
 
-	if ((match && !invert) || (!match && invert))
+	return (match && !invert) || (!match && invert);
+}
+
+static __always_inline
+void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp)
+{
+	if (__emulate_cc(regs->flags, cc))
 		ip += disp;
 
 	int3_emulate_jmp(regs, ip);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1349e278cd2a..9526d692a1d6 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -26,6 +26,7 @@
 #include <asm/debugreg.h>
 #include <asm/nospec-branch.h>
 #include <asm/ibt.h>
+#include <asm/text-patching.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -416,31 +417,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	ON64(FOP3E(op##q, rax, rdx, cl)) \
 	FOP_END
 
-/* Special case for SETcc - 1 instruction per cc */
-#define FOP_SETCC(op) \
-	FOP_FUNC(op) \
-	#op " %al \n\t" \
-	FOP_RET(op)
-
-FOP_START(setcc)
-FOP_SETCC(seto)
-FOP_SETCC(setno)
-FOP_SETCC(setc)
-FOP_SETCC(setnc)
-FOP_SETCC(setz)
-FOP_SETCC(setnz)
-FOP_SETCC(setbe)
-FOP_SETCC(setnbe)
-FOP_SETCC(sets)
-FOP_SETCC(setns)
-FOP_SETCC(setp)
-FOP_SETCC(setnp)
-FOP_SETCC(setl)
-FOP_SETCC(setnl)
-FOP_SETCC(setle)
-FOP_SETCC(setnle)
-FOP_END;
-
 FOP_START(salc)
 FOP_FUNC(salc)
 "pushf; sbb %al, %al; popf \n\t"
@@ -1068,13 +1044,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 
 static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 {
-	u8 rc;
-	void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
-
-	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
-	asm("push %[flags]; popf; " CALL_NOSPEC
-	    : "=a"(rc), ASM_CALL_CONSTRAINT : [thunk_target]"r"(fop), [flags]"r"(flags));
-	return rc;
+	return __emulate_cc(flags, condition & 0xf);
 }
 
 static void fetch_register_operand(struct operand *op)

From 6204aea36b74cd2001a142e92e492e301597eafb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 11:51:49 +0200
Subject: [PATCH 002/352] KVM: x86: Introduce EM_ASM_1

Replace fastops with C based stubs. There are a bunch of problems with
the current fastop infrastructure, most all related to their special
calling convention, which bypasses the normal C-ABI.

There are two immediate problems with this at present:

 - it relies on RET preserving EFLAGS; whereas C-ABI does not.

 - it circumvents compiler based control-flow-integrity checking
   because its all asm magic.

The first is a problem for some mitigations where the
x86_indirect_return_thunk needs to include non-trivial work that
clobbers EFLAGS (eg. the Skylake call depth tracking thing).

The second is a problem because it presents a 'naked' indirect call on
kCFI builds, making it a prime target for control flow hijacking.

Additionally, given that a large chunk of virtual machine performance
relies on absolutely avoiding vmexit these days, this emulation stuff
just isn't that critical for performance anymore.

As such, replace the fastop calls with normal C functions using the
'execute' member.

As noted by Paolo: this code was performance critical for pre-Westmere
(2010) and only when running big real mode code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103439.773781574@infradead.org
---
 arch/x86/kvm/emulate.c | 71 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 58 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9526d692a1d6..5b8a1adeb456 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -267,11 +267,56 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 		     X86_EFLAGS_PF|X86_EFLAGS_CF)
 
 #ifdef CONFIG_X86_64
-#define ON64(x) x
+#define ON64(x...) x
 #else
-#define ON64(x)
+#define ON64(x...)
 #endif
 
+#define EM_ASM_START(op) \
+static int em_##op(struct x86_emulate_ctxt *ctxt) \
+{ \
+	unsigned long flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; \
+	int bytes = 1, ok = 1; \
+	if (!(ctxt->d & ByteOp)) \
+		bytes = ctxt->dst.bytes; \
+	switch (bytes) {
+
+#define __EM_ASM(str) \
+		asm("push %[flags]; popf \n\t" \
+		    "10: " str \
+		    "pushf; pop %[flags] \n\t" \
+		    "11: \n\t" \
+		    : "+a" (ctxt->dst.val), \
+		      "+d" (ctxt->src.val), \
+		      [flags] "+D" (flags), \
+		      "+S" (ok) \
+		    : "c" (ctxt->src2.val))
+
+#define __EM_ASM_1(op, dst) \
+		__EM_ASM(#op " %%" #dst " \n\t")
+
+#define __EM_ASM_1_EX(op, dst) \
+		__EM_ASM(#op " %%" #dst " \n\t" \
+			 _ASM_EXTABLE_TYPE_REG(10b, 11f, EX_TYPE_ZERO_REG, %%esi))
+
+#define __EM_ASM_2(op, dst, src) \
+		__EM_ASM(#op " %%" #src ", %%" #dst " \n\t")
+
+#define EM_ASM_END \
+	} \
+	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); \
+	return !ok ? emulate_de(ctxt) : X86EMUL_CONTINUE; \
+}
+
+/* 1-operand, using "a" (dst) */
+#define EM_ASM_1(op) \
+	EM_ASM_START(op) \
+	case 1: __EM_ASM_1(op##b, al); break; \
+	case 2: __EM_ASM_1(op##w, ax); break; \
+	case 4: __EM_ASM_1(op##l, eax); break; \
+	ON64(case 8: __EM_ASM_1(op##q, rax); break;) \
+	EM_ASM_END
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1002,10 +1047,10 @@ FASTOP3WCL(shrd);
 
 FASTOP2W(imul);
 
-FASTOP1(not);
-FASTOP1(neg);
-FASTOP1(inc);
-FASTOP1(dec);
+EM_ASM_1(not);
+EM_ASM_1(neg);
+EM_ASM_1(inc);
+EM_ASM_1(dec);
 
 FASTOP2CL(rol);
 FASTOP2CL(ror);
@@ -4021,8 +4066,8 @@ static const struct opcode group2[] = {
 static const struct opcode group3[] = {
 	F(DstMem | SrcImm | NoWrite, em_test),
 	F(DstMem | SrcImm | NoWrite, em_test),
-	F(DstMem | SrcNone | Lock, em_not),
-	F(DstMem | SrcNone | Lock, em_neg),
+	I(DstMem | SrcNone | Lock, em_not),
+	I(DstMem | SrcNone | Lock, em_neg),
 	F(DstXacc | Src2Mem, em_mul_ex),
 	F(DstXacc | Src2Mem, em_imul_ex),
 	F(DstXacc | Src2Mem, em_div_ex),
@@ -4030,14 +4075,14 @@ static const struct opcode group3[] = {
 };
 
 static const struct opcode group4[] = {
-	F(ByteOp | DstMem | SrcNone | Lock, em_inc),
-	F(ByteOp | DstMem | SrcNone | Lock, em_dec),
+	I(ByteOp | DstMem | SrcNone | Lock, em_inc),
+	I(ByteOp | DstMem | SrcNone | Lock, em_dec),
 	N, N, N, N, N, N,
 };
 
 static const struct opcode group5[] = {
-	F(DstMem | SrcNone | Lock,		em_inc),
-	F(DstMem | SrcNone | Lock,		em_dec),
+	I(DstMem | SrcNone | Lock,		em_inc),
+	I(DstMem | SrcNone | Lock,		em_dec),
 	I(SrcMem | NearBranch | IsBranch,       em_call_near_abs),
 	I(SrcMemFAddr | ImplicitOps | IsBranch, em_call_far),
 	I(SrcMem | NearBranch | IsBranch,       em_jmp_abs),
@@ -4237,7 +4282,7 @@ static const struct opcode opcode_table[256] = {
 	/* 0x38 - 0x3F */
 	F6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
-	X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)),
+	X8(I(DstReg, em_inc)), X8(I(DstReg, em_dec)),
 	/* 0x50 - 0x57 */
 	X8(I(SrcReg | Stack, em_push)),
 	/* 0x58 - 0x5F */

From b26deb0cad4af9f522496fd25dc3ebca759e65a4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:25:21 +0200
Subject: [PATCH 003/352] KVM: x86: Introduce EM_ASM_2

Replace the FASTOP2 instructions.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103439.903697475@infradead.org
---
 arch/x86/kvm/emulate.c | 85 +++++++++++++++++++++++-------------------
 1 file changed, 47 insertions(+), 38 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5b8a1adeb456..ec4793fe347c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -317,6 +317,15 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_1(op##q, rax); break;) \
 	EM_ASM_END
 
+/* 2-operand, using "a" (dst), "d" (src) */
+#define EM_ASM_2(op) \
+	EM_ASM_START(op) \
+	case 1: __EM_ASM_2(op##b, al, dl); break; \
+	case 2: __EM_ASM_2(op##w, ax, dx); break; \
+	case 4: __EM_ASM_2(op##l, eax, edx); break; \
+	ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \
+	EM_ASM_END
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1027,15 +1036,16 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
-FASTOP2(add);
-FASTOP2(or);
-FASTOP2(adc);
-FASTOP2(sbb);
-FASTOP2(and);
-FASTOP2(sub);
-FASTOP2(xor);
-FASTOP2(cmp);
-FASTOP2(test);
+EM_ASM_2(add);
+EM_ASM_2(or);
+EM_ASM_2(adc);
+EM_ASM_2(sbb);
+EM_ASM_2(and);
+EM_ASM_2(sub);
+EM_ASM_2(xor);
+EM_ASM_2(cmp);
+EM_ASM_2(test);
+EM_ASM_2(xadd);
 
 FASTOP1SRC2(mul, mul_ex);
 FASTOP1SRC2(imul, imul_ex);
@@ -1067,7 +1077,6 @@ FASTOP2W(bts);
 FASTOP2W(btr);
 FASTOP2W(btc);
 
-FASTOP2(xadd);
 
 FASTOP2R(cmp, cmp_r);
 
@@ -2304,7 +2313,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 	ctxt->dst.val = reg_read(ctxt, VCPU_REGS_RAX);
 	ctxt->src.orig_val = ctxt->src.val;
 	ctxt->src.val = ctxt->dst.orig_val;
-	fastop(ctxt, em_cmp);
+	em_cmp(ctxt);
 
 	if (ctxt->eflags & X86_EFLAGS_ZF) {
 		/* Success: write back to memory; no update of EAX */
@@ -3069,7 +3078,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt)
 	ctxt->src.type = OP_IMM;
 	ctxt->src.val = 0;
 	ctxt->src.bytes = 1;
-	fastop(ctxt, em_or);
+	em_or(ctxt);
 	ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF);
 	if (cf)
 		ctxt->eflags |= X86_EFLAGS_CF;
@@ -3095,7 +3104,7 @@ static int em_aam(struct x86_emulate_ctxt *ctxt)
 	ctxt->src.type = OP_IMM;
 	ctxt->src.val = 0;
 	ctxt->src.bytes = 1;
-	fastop(ctxt, em_or);
+	em_or(ctxt);
 
 	return X86EMUL_CONTINUE;
 }
@@ -3113,7 +3122,7 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
 	ctxt->src.type = OP_IMM;
 	ctxt->src.val = 0;
 	ctxt->src.bytes = 1;
-	fastop(ctxt, em_or);
+	em_or(ctxt);
 
 	return X86EMUL_CONTINUE;
 }
@@ -3998,9 +4007,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define I2bvIP(_f, _e, _i, _p) \
 	IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p)
 
-#define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
-		F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
-		F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
+#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
+		I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
+		I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
 
 static const struct opcode group7_rm0[] = {
 	N,
@@ -4038,14 +4047,14 @@ static const struct opcode group7_rm7[] = {
 };
 
 static const struct opcode group1[] = {
-	F(Lock, em_add),
-	F(Lock | PageTable, em_or),
-	F(Lock, em_adc),
-	F(Lock, em_sbb),
-	F(Lock | PageTable, em_and),
-	F(Lock, em_sub),
-	F(Lock, em_xor),
-	F(NoWrite, em_cmp),
+	I(Lock, em_add),
+	I(Lock | PageTable, em_or),
+	I(Lock, em_adc),
+	I(Lock, em_sbb),
+	I(Lock | PageTable, em_and),
+	I(Lock, em_sub),
+	I(Lock, em_xor),
+	I(NoWrite, em_cmp),
 };
 
 static const struct opcode group1A[] = {
@@ -4064,8 +4073,8 @@ static const struct opcode group2[] = {
 };
 
 static const struct opcode group3[] = {
-	F(DstMem | SrcImm | NoWrite, em_test),
-	F(DstMem | SrcImm | NoWrite, em_test),
+	I(DstMem | SrcImm | NoWrite, em_test),
+	I(DstMem | SrcImm | NoWrite, em_test),
 	I(DstMem | SrcNone | Lock, em_not),
 	I(DstMem | SrcNone | Lock, em_neg),
 	F(DstXacc | Src2Mem, em_mul_ex),
@@ -4258,29 +4267,29 @@ static const struct instr_dual instr_dual_8d = {
 
 static const struct opcode opcode_table[256] = {
 	/* 0x00 - 0x07 */
-	F6ALU(Lock, em_add),
+	I6ALU(Lock, em_add),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg),
 	/* 0x08 - 0x0F */
-	F6ALU(Lock | PageTable, em_or),
+	I6ALU(Lock | PageTable, em_or),
 	I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg),
 	N,
 	/* 0x10 - 0x17 */
-	F6ALU(Lock, em_adc),
+	I6ALU(Lock, em_adc),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg),
 	/* 0x18 - 0x1F */
-	F6ALU(Lock, em_sbb),
+	I6ALU(Lock, em_sbb),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg),
 	/* 0x20 - 0x27 */
-	F6ALU(Lock | PageTable, em_and), N, N,
+	I6ALU(Lock | PageTable, em_and), N, N,
 	/* 0x28 - 0x2F */
-	F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
+	I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
 	/* 0x30 - 0x37 */
-	F6ALU(Lock, em_xor), N, N,
+	I6ALU(Lock, em_xor), N, N,
 	/* 0x38 - 0x3F */
-	F6ALU(NoWrite, em_cmp), N, N,
+	I6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
 	X8(I(DstReg, em_inc)), X8(I(DstReg, em_dec)),
 	/* 0x50 - 0x57 */
@@ -4306,7 +4315,7 @@ static const struct opcode opcode_table[256] = {
 	G(DstMem | SrcImm, group1),
 	G(ByteOp | DstMem | SrcImm | No64, group1),
 	G(DstMem | SrcImmByte, group1),
-	F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
+	I2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
 	I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov),
@@ -4329,7 +4338,7 @@ static const struct opcode opcode_table[256] = {
 	I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov),
 	F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r),
 	/* 0xA8 - 0xAF */
-	F2bv(DstAcc | SrcImm | NoWrite, em_test),
+	I2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
 	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
@@ -4467,7 +4476,7 @@ static const struct opcode twobyte_table[256] = {
 	I(DstReg | SrcMem | ModRM, em_bsr_c),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xC0 - 0xC7 */
-	F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
+	I2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
 	N, ID(0, &instr_dual_0f_c3),
 	N, N, N, GD(0, &group9),
 	/* 0xC8 - 0xCF */

From 2df2b52c98db03c10ebe93fa270b1e2baf47f8a0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:52:05 +0200
Subject: [PATCH 004/352] KVM: x86: Introduce EM_ASM_2R

Replace the FASTOP2R instruction.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.024933524@infradead.org
---
 arch/x86/kvm/emulate.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ec4793fe347c..7af30efe15c9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -326,6 +326,15 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \
 	EM_ASM_END
 
+/* 2-operand, reversed */
+#define EM_ASM_2R(op, name) \
+	EM_ASM_START(name) \
+	case 1: __EM_ASM_2(op##b, dl, al); break; \
+	case 2: __EM_ASM_2(op##w, dx, ax); break; \
+	case 4: __EM_ASM_2(op##l, edx, eax); break; \
+	ON64(case 8: __EM_ASM_2(op##q, rdx, rax); break;) \
+	EM_ASM_END
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1077,8 +1086,7 @@ FASTOP2W(bts);
 FASTOP2W(btr);
 FASTOP2W(btc);
 
-
-FASTOP2R(cmp, cmp_r);
+EM_ASM_2R(cmp, cmp_r);
 
 static int em_bsf_c(struct x86_emulate_ctxt *ctxt)
 {
@@ -4336,12 +4344,12 @@ static const struct opcode opcode_table[256] = {
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov),
-	F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r),
+	I2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r),
 	/* 0xA8 - 0xAF */
 	I2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
-	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
+	I2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */

From 975e51783cfd0abc303817e8bf1ab2f630834c2a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:30:37 +0200
Subject: [PATCH 005/352] KVM: x86: Introduce EM_ASM_2W

Replace the FASTOP2W instructions.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.142923581@infradead.org
---
 arch/x86/kvm/emulate.c | 47 +++++++++++++++++++++++++-----------------
 1 file changed, 28 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7af30efe15c9..05a97ece5a99 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -335,6 +335,15 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_2(op##q, rdx, rax); break;) \
 	EM_ASM_END
 
+/* 2-operand, word only (no byte op) */
+#define EM_ASM_2W(op) \
+	EM_ASM_START(op) \
+	case 1: break; \
+	case 2: __EM_ASM_2(op##w, ax, dx); break; \
+	case 4: __EM_ASM_2(op##l, eax, edx); break; \
+	ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \
+	EM_ASM_END
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1064,7 +1073,7 @@ FASTOP1SRC2EX(idiv, idiv_ex);
 FASTOP3WCL(shld);
 FASTOP3WCL(shrd);
 
-FASTOP2W(imul);
+EM_ASM_2W(imul);
 
 EM_ASM_1(not);
 EM_ASM_1(neg);
@@ -1079,12 +1088,12 @@ FASTOP2CL(shl);
 FASTOP2CL(shr);
 FASTOP2CL(sar);
 
-FASTOP2W(bsf);
-FASTOP2W(bsr);
-FASTOP2W(bt);
-FASTOP2W(bts);
-FASTOP2W(btr);
-FASTOP2W(btc);
+EM_ASM_2W(bsf);
+EM_ASM_2W(bsr);
+EM_ASM_2W(bt);
+EM_ASM_2W(bts);
+EM_ASM_2W(btr);
+EM_ASM_2W(btc);
 
 EM_ASM_2R(cmp, cmp_r);
 
@@ -1093,7 +1102,7 @@ static int em_bsf_c(struct x86_emulate_ctxt *ctxt)
 	/* If src is zero, do not writeback, but update flags */
 	if (ctxt->src.val == 0)
 		ctxt->dst.type = OP_NONE;
-	return fastop(ctxt, em_bsf);
+	return em_bsf(ctxt);
 }
 
 static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
@@ -1101,7 +1110,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 	/* If src is zero, do not writeback, but update flags */
 	if (ctxt->src.val == 0)
 		ctxt->dst.type = OP_NONE;
-	return fastop(ctxt, em_bsr);
+	return em_bsr(ctxt);
 }
 
 static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
@@ -3221,7 +3230,7 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt)
 static int em_imul_3op(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = ctxt->src2.val;
-	return fastop(ctxt, em_imul);
+	return em_imul(ctxt);
 }
 
 static int em_cwd(struct x86_emulate_ctxt *ctxt)
@@ -4135,10 +4144,10 @@ static const struct group_dual group7 = { {
 
 static const struct opcode group8[] = {
 	N, N, N, N,
-	F(DstMem | SrcImmByte | NoWrite,		em_bt),
-	F(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
-	F(DstMem | SrcImmByte | Lock,			em_btr),
-	F(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
+	I(DstMem | SrcImmByte | NoWrite,		em_bt),
+	I(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
+	I(DstMem | SrcImmByte | Lock,			em_btr),
+	I(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
 };
 
 /*
@@ -4459,27 +4468,27 @@ static const struct opcode twobyte_table[256] = {
 	/* 0xA0 - 0xA7 */
 	I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg),
 	II(ImplicitOps, em_cpuid, cpuid),
-	F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt),
+	I(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
 	II(EmulateOnUD | ImplicitOps, em_rsm, rsm),
-	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
+	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
-	GD(0, &group15), F(DstReg | SrcMem | ModRM, em_imul),
+	GD(0, &group15), I(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable | SrcWrite, em_cmpxchg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
-	F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
+	I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
 	I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xB8 - 0xBF */
 	N, N,
 	G(BitOp, group8),
-	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
+	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
 	I(DstReg | SrcMem | ModRM, em_bsf_c),
 	I(DstReg | SrcMem | ModRM, em_bsr_c),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),

From 67e944aff63cb6b9c236d9cc2b4d870aeefd306f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:34:42 +0200
Subject: [PATCH 006/352] KVM: x86: Introduce EM_ASM_2CL

Replace the FASTOP2CL instructions.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.251039692@infradead.org
---
 arch/x86/kvm/emulate.c | 39 ++++++++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 05a97ece5a99..9a7854093981 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -344,6 +344,15 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \
 	EM_ASM_END
 
+/* 2-operand, using "a" (dst) and CL (src2) */
+#define EM_ASM_2CL(op) \
+	EM_ASM_START(op) \
+	case 1: __EM_ASM_2(op##b, al, cl); break; \
+	case 2: __EM_ASM_2(op##w, ax, cl); break; \
+	case 4: __EM_ASM_2(op##l, eax, cl); break; \
+	ON64(case 8: __EM_ASM_2(op##q, rax, cl); break;) \
+	EM_ASM_END
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1080,13 +1089,13 @@ EM_ASM_1(neg);
 EM_ASM_1(inc);
 EM_ASM_1(dec);
 
-FASTOP2CL(rol);
-FASTOP2CL(ror);
-FASTOP2CL(rcl);
-FASTOP2CL(rcr);
-FASTOP2CL(shl);
-FASTOP2CL(shr);
-FASTOP2CL(sar);
+EM_ASM_2CL(rol);
+EM_ASM_2CL(ror);
+EM_ASM_2CL(rcl);
+EM_ASM_2CL(rcr);
+EM_ASM_2CL(shl);
+EM_ASM_2CL(shr);
+EM_ASM_2CL(sar);
 
 EM_ASM_2W(bsf);
 EM_ASM_2W(bsr);
@@ -4079,14 +4088,14 @@ static const struct opcode group1A[] = {
 };
 
 static const struct opcode group2[] = {
-	F(DstMem | ModRM, em_rol),
-	F(DstMem | ModRM, em_ror),
-	F(DstMem | ModRM, em_rcl),
-	F(DstMem | ModRM, em_rcr),
-	F(DstMem | ModRM, em_shl),
-	F(DstMem | ModRM, em_shr),
-	F(DstMem | ModRM, em_shl),
-	F(DstMem | ModRM, em_sar),
+	I(DstMem | ModRM, em_rol),
+	I(DstMem | ModRM, em_ror),
+	I(DstMem | ModRM, em_rcl),
+	I(DstMem | ModRM, em_rcr),
+	I(DstMem | ModRM, em_shl),
+	I(DstMem | ModRM, em_shr),
+	I(DstMem | ModRM, em_shl),
+	I(DstMem | ModRM, em_sar),
 };
 
 static const struct opcode group3[] = {

From af4fe07aa1e07610d3208a85210b896c87e2105e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:40:12 +0200
Subject: [PATCH 007/352] KVM: x86: Introduce EM_ASM_1SRC2

Replace the FASTOP1SRC2*() instructions.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.394654786@infradead.org
---
 arch/x86/kvm/emulate.c | 34 ++++++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9a7854093981..beac2f4c4744 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -317,6 +317,24 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_1(op##q, rax); break;) \
 	EM_ASM_END
 
+/* 1-operand, using "c" (src2) */
+#define EM_ASM_1SRC2(op, name) \
+	EM_ASM_START(name) \
+	case 1: __EM_ASM_1(op##b, cl); break; \
+	case 2: __EM_ASM_1(op##w, cx); break; \
+	case 4: __EM_ASM_1(op##l, ecx); break; \
+	ON64(case 8: __EM_ASM_1(op##q, rcx); break;) \
+	EM_ASM_END
+
+/* 1-operand, using "c" (src2) with exception */
+#define EM_ASM_1SRC2EX(op, name) \
+	EM_ASM_START(name) \
+	case 1: __EM_ASM_1_EX(op##b, cl); break; \
+	case 2: __EM_ASM_1_EX(op##w, cx); break; \
+	case 4: __EM_ASM_1_EX(op##l, ecx); break; \
+	ON64(case 8: __EM_ASM_1_EX(op##q, rcx); break;) \
+	EM_ASM_END
+
 /* 2-operand, using "a" (dst), "d" (src) */
 #define EM_ASM_2(op) \
 	EM_ASM_START(op) \
@@ -1074,10 +1092,10 @@ EM_ASM_2(cmp);
 EM_ASM_2(test);
 EM_ASM_2(xadd);
 
-FASTOP1SRC2(mul, mul_ex);
-FASTOP1SRC2(imul, imul_ex);
-FASTOP1SRC2EX(div, div_ex);
-FASTOP1SRC2EX(idiv, idiv_ex);
+EM_ASM_1SRC2(mul, mul_ex);
+EM_ASM_1SRC2(imul, imul_ex);
+EM_ASM_1SRC2EX(div, div_ex);
+EM_ASM_1SRC2EX(idiv, idiv_ex);
 
 FASTOP3WCL(shld);
 FASTOP3WCL(shrd);
@@ -4103,10 +4121,10 @@ static const struct opcode group3[] = {
 	I(DstMem | SrcImm | NoWrite, em_test),
 	I(DstMem | SrcNone | Lock, em_not),
 	I(DstMem | SrcNone | Lock, em_neg),
-	F(DstXacc | Src2Mem, em_mul_ex),
-	F(DstXacc | Src2Mem, em_imul_ex),
-	F(DstXacc | Src2Mem, em_div_ex),
-	F(DstXacc | Src2Mem, em_idiv_ex),
+	I(DstXacc | Src2Mem, em_mul_ex),
+	I(DstXacc | Src2Mem, em_imul_ex),
+	I(DstXacc | Src2Mem, em_div_ex),
+	I(DstXacc | Src2Mem, em_idiv_ex),
 };
 
 static const struct opcode group4[] = {

From 2d82acd7d6a7eba2ed2bf84ab7440c1ad7c27958 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:47:50 +0200
Subject: [PATCH 008/352] KVM: x86: Introduce EM_ASM_3WCL

Replace the FASTOP3WCL instructions.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.513865075@infradead.org
---
 arch/x86/kvm/emulate.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index beac2f4c4744..390b8a93cd2c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -302,6 +302,9 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 #define __EM_ASM_2(op, dst, src) \
 		__EM_ASM(#op " %%" #src ", %%" #dst " \n\t")
 
+#define __EM_ASM_3(op, dst, src, src2) \
+		__EM_ASM(#op " %%" #src2 ", %%" #src ", %%" #dst " \n\t")
+
 #define EM_ASM_END \
 	} \
 	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); \
@@ -371,6 +374,16 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_2(op##q, rax, cl); break;) \
 	EM_ASM_END
 
+/* 3-operand, using "a" (dst), "d" (src) and CL (src2) */
+#define EM_ASM_3WCL(op) \
+	EM_ASM_START(op) \
+	case 1: break; \
+	case 2: __EM_ASM_3(op##w, ax, dx, cl); break; \
+	case 4: __EM_ASM_3(op##l, eax, edx, cl); break; \
+	ON64(case 8: __EM_ASM_3(op##q, rax, rdx, cl); break;) \
+	EM_ASM_END
+
+
 /*
  * fastop functions have a special calling convention:
  *
@@ -1097,8 +1110,8 @@ EM_ASM_1SRC2(imul, imul_ex);
 EM_ASM_1SRC2EX(div, div_ex);
 EM_ASM_1SRC2EX(idiv, idiv_ex);
 
-FASTOP3WCL(shld);
-FASTOP3WCL(shrd);
+EM_ASM_3WCL(shld);
+EM_ASM_3WCL(shrd);
 
 EM_ASM_2W(imul);
 
@@ -4496,14 +4509,14 @@ static const struct opcode twobyte_table[256] = {
 	I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg),
 	II(ImplicitOps, em_cpuid, cpuid),
 	I(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt),
-	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
-	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
+	I(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
+	I(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
 	II(EmulateOnUD | ImplicitOps, em_rsm, rsm),
 	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
-	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
-	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
+	I(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
+	I(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
 	GD(0, &group15), I(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable | SrcWrite, em_cmpxchg),

From 77892e1fef34db650aa3de4be1d27267ca7f1330 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 13:07:14 +0200
Subject: [PATCH 009/352] KVM: x86: Convert em_salc() to C

Implement the SALC (Set AL if Carry) instruction in C.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.634145269@infradead.org
---
 arch/x86/kvm/emulate.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 390b8a93cd2c..94008cd12f1e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -529,11 +529,14 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	ON64(FOP3E(op##q, rax, rdx, cl)) \
 	FOP_END
 
-FOP_START(salc)
-FOP_FUNC(salc)
-"pushf; sbb %al, %al; popf \n\t"
-FOP_RET(salc)
-FOP_END;
+static int em_salc(struct x86_emulate_ctxt *ctxt)
+{
+	/*
+	 * Set AL 0xFF if CF is set, or 0x00 when clear.
+	 */
+	ctxt->dst.val = 0xFF * !!(ctxt->eflags & X86_EFLAGS_CF);
+	return X86EMUL_CONTINUE;
+}
 
 /*
  * XXX: inoutclob user must know where the argument is being expanded.
@@ -4423,7 +4426,7 @@ static const struct opcode opcode_table[256] = {
 	G(Src2CL | ByteOp, group2), G(Src2CL, group2),
 	I(DstAcc | SrcImmUByte | No64, em_aam),
 	I(DstAcc | SrcImmUByte | No64, em_aad),
-	F(DstAcc | ByteOp | No64, em_salc),
+	I(DstAcc | ByteOp | No64, em_salc),
 	I(DstAcc | SrcXLat | ByteOp, em_mov),
 	/* 0xD8 - 0xDF */
 	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,

From a1d34a444ce8c9a6ec4376247f80f0b777c6d3fe Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 26 Apr 2025 12:55:35 +0200
Subject: [PATCH 010/352] KVM: x86: Remove fastops

No more FASTOPs, remove the remains.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.751192860@infradead.org
---
 arch/x86/kvm/emulate.c | 172 +----------------------------------------
 1 file changed, 1 insertion(+), 171 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 94008cd12f1e..796d0c64f9ba 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -167,7 +167,6 @@
 #define Unaligned   ((u64)2 << 41)  /* Explicitly unaligned (e.g. MOVDQU) */
 #define Avx         ((u64)3 << 41)  /* Advanced Vector Extensions */
 #define Aligned16   ((u64)4 << 41)  /* Aligned to 16 byte boundary (e.g. FXSAVE) */
-#define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
 #define NoMod	    ((u64)1 << 47)  /* Mod field is ignored */
@@ -203,7 +202,6 @@ struct opcode {
 		const struct escape *esc;
 		const struct instr_dual *idual;
 		const struct mode_dual *mdual;
-		void (*fastop)(struct fastop *fake);
 	} u;
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 };
@@ -383,152 +381,6 @@ static int em_##op(struct x86_emulate_ctxt *ctxt) \
 	ON64(case 8: __EM_ASM_3(op##q, rax, rdx, cl); break;) \
 	EM_ASM_END
 
-
-/*
- * fastop functions have a special calling convention:
- *
- * dst:    rax        (in/out)
- * src:    rdx        (in/out)
- * src2:   rcx        (in)
- * flags:  rflags     (in/out)
- * ex:     rsi        (in:fastop pointer, out:zero if exception)
- *
- * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
- * different operand sizes can be reached by calculation, rather than a jump
- * table (which would be bigger than the code).
- *
- * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR
- * and 1 for the straight line speculation INT3, leaves 7 bytes for the
- * body of the function.  Currently none is larger than 4.
- */
-static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
-
-#define FASTOP_SIZE	16
-
-#define __FOP_FUNC(name) \
-	".align " __stringify(FASTOP_SIZE) " \n\t" \
-	".type " name ", @function \n\t" \
-	name ":\n\t" \
-	ASM_ENDBR \
-	IBT_NOSEAL(name)
-
-#define FOP_FUNC(name) \
-	__FOP_FUNC(#name)
-
-#define __FOP_RET(name) \
-	"11: " ASM_RET \
-	".size " name ", .-" name "\n\t"
-
-#define FOP_RET(name) \
-	__FOP_RET(#name)
-
-#define __FOP_START(op, align) \
-	extern void em_##op(struct fastop *fake); \
-	asm(".pushsection .text, \"ax\" \n\t" \
-	    ".global em_" #op " \n\t" \
-	    ".align " __stringify(align) " \n\t" \
-	    "em_" #op ":\n\t"
-
-#define FOP_START(op) __FOP_START(op, FASTOP_SIZE)
-
-#define FOP_END \
-	    ".popsection")
-
-#define __FOPNOP(name) \
-	__FOP_FUNC(name) \
-	__FOP_RET(name)
-
-#define FOPNOP() \
-	__FOPNOP(__stringify(__UNIQUE_ID(nop)))
-
-#define FOP1E(op,  dst) \
-	__FOP_FUNC(#op "_" #dst) \
-	"10: " #op " %" #dst " \n\t" \
-	__FOP_RET(#op "_" #dst)
-
-#define FOP1EEX(op,  dst) \
-	FOP1E(op, dst) _ASM_EXTABLE_TYPE_REG(10b, 11b, EX_TYPE_ZERO_REG, %%esi)
-
-#define FASTOP1(op) \
-	FOP_START(op) \
-	FOP1E(op##b, al) \
-	FOP1E(op##w, ax) \
-	FOP1E(op##l, eax) \
-	ON64(FOP1E(op##q, rax))	\
-	FOP_END
-
-/* 1-operand, using src2 (for MUL/DIV r/m) */
-#define FASTOP1SRC2(op, name) \
-	FOP_START(name) \
-	FOP1E(op, cl) \
-	FOP1E(op, cx) \
-	FOP1E(op, ecx) \
-	ON64(FOP1E(op, rcx)) \
-	FOP_END
-
-/* 1-operand, using src2 (for MUL/DIV r/m), with exceptions */
-#define FASTOP1SRC2EX(op, name) \
-	FOP_START(name) \
-	FOP1EEX(op, cl) \
-	FOP1EEX(op, cx) \
-	FOP1EEX(op, ecx) \
-	ON64(FOP1EEX(op, rcx)) \
-	FOP_END
-
-#define FOP2E(op,  dst, src)	   \
-	__FOP_FUNC(#op "_" #dst "_" #src) \
-	#op " %" #src ", %" #dst " \n\t" \
-	__FOP_RET(#op "_" #dst "_" #src)
-
-#define FASTOP2(op) \
-	FOP_START(op) \
-	FOP2E(op##b, al, dl) \
-	FOP2E(op##w, ax, dx) \
-	FOP2E(op##l, eax, edx) \
-	ON64(FOP2E(op##q, rax, rdx)) \
-	FOP_END
-
-/* 2 operand, word only */
-#define FASTOP2W(op) \
-	FOP_START(op) \
-	FOPNOP() \
-	FOP2E(op##w, ax, dx) \
-	FOP2E(op##l, eax, edx) \
-	ON64(FOP2E(op##q, rax, rdx)) \
-	FOP_END
-
-/* 2 operand, src is CL */
-#define FASTOP2CL(op) \
-	FOP_START(op) \
-	FOP2E(op##b, al, cl) \
-	FOP2E(op##w, ax, cl) \
-	FOP2E(op##l, eax, cl) \
-	ON64(FOP2E(op##q, rax, cl)) \
-	FOP_END
-
-/* 2 operand, src and dest are reversed */
-#define FASTOP2R(op, name) \
-	FOP_START(name) \
-	FOP2E(op##b, dl, al) \
-	FOP2E(op##w, dx, ax) \
-	FOP2E(op##l, edx, eax) \
-	ON64(FOP2E(op##q, rdx, rax)) \
-	FOP_END
-
-#define FOP3E(op,  dst, src, src2) \
-	__FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
-	#op " %" #src2 ", %" #src ", %" #dst " \n\t"\
-	__FOP_RET(#op "_" #dst "_" #src "_" #src2)
-
-/* 3-operand, word-only, src2=cl */
-#define FASTOP3WCL(op) \
-	FOP_START(op) \
-	FOPNOP() \
-	FOP3E(op##w, ax, dx, cl) \
-	FOP3E(op##l, eax, edx, cl) \
-	ON64(FOP3E(op##q, rax, rdx, cl)) \
-	FOP_END
-
 static int em_salc(struct x86_emulate_ctxt *ctxt)
 {
 	/*
@@ -4052,7 +3904,6 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define MD(_f, _m) { .flags = ((_f) | ModeDual), .u.mdual = (_m) }
 #define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
-#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
 #define II(_f, _e, _i) \
 	{ .flags = (_f)|Intercept, .u.execute = (_e), .intercept = x86_intercept_##_i }
 #define IIP(_f, _e, _i, _p) \
@@ -5158,24 +5009,6 @@ static void fetch_possible_mmx_operand(struct operand *op)
 		kvm_read_mmx_reg(op->addr.mm, &op->mm_val);
 }
 
-static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
-{
-	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
-
-	if (!(ctxt->d & ByteOp))
-		fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
-
-	asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
-	    : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
-	      [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
-	    : "c"(ctxt->src2.val));
-
-	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
-	if (!fop) /* exception is returned in fop variable */
-		return emulate_de(ctxt);
-	return X86EMUL_CONTINUE;
-}
-
 void init_decode_cache(struct x86_emulate_ctxt *ctxt)
 {
 	/* Clear fields that are set conditionally but read without a guard. */
@@ -5340,10 +5173,7 @@ special_insn:
 		ctxt->eflags &= ~X86_EFLAGS_RF;
 
 	if (ctxt->execute) {
-		if (ctxt->d & Fastop)
-			rc = fastop(ctxt, ctxt->fop);
-		else
-			rc = ctxt->execute(ctxt);
+		rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		goto writeback;

From 0e20f1f4c2cb77130cfe903a058a08883645dc4b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 12 Apr 2025 13:55:49 +0200
Subject: [PATCH 011/352] x86/hyperv: Clean up hv_do_hypercall()

What used to be a simple few instructions has turned into a giant mess
(for x86_64). Not only does it use static_branch wrong, it mixes it
with dynamic branches for no apparent reason.

Notably it uses static_branch through an out-of-line function call,
which completely defeats the purpose, since instead of a simple
JMP/NOP site, you get a CALL+RET+TEST+Jcc sequence in return, which is
absolutely idiotic.

Add to that a dynamic test of hyperv_paravisor_present, something
which is set once and never changed.

Replace all this idiocy with a single direct function call to the
right hypercall variant.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103440.897136093@infradead.org
---
 arch/x86/hyperv/hv_init.c       |  20 +++++
 arch/x86/hyperv/ivm.c           |  15 ++++
 arch/x86/include/asm/mshyperv.h | 137 ++++++++++----------------------
 arch/x86/kernel/cpu/mshyperv.c  |  19 +++--
 4 files changed, 89 insertions(+), 102 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index afdbda2dd7b7..5ef1e647ebc0 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -37,7 +37,27 @@
 #include <linux/export.h>
 
 void *hv_hypercall_pg;
+
+#ifdef CONFIG_X86_64
+u64 hv_std_hypercall(u64 control, u64 param1, u64 param2)
+{
+	u64 hv_status;
+
+	if (!hv_hypercall_pg)
+		return U64_MAX;
+
+	register u64 __r8 asm("r8") = param2;
+	asm volatile (CALL_NOSPEC
+		      : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+		        "+c" (control), "+d" (param1), "+r" (__r8)
+		      : THUNK_TARGET(hv_hypercall_pg)
+		      : "cc", "memory", "r9", "r10", "r11");
+
+	return hv_status;
+}
+#else
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
+#endif
 
 union hv_ghcb * __percpu *hv_ghcb_pg;
 
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index ade6c665c97e..21042fa49088 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -385,9 +385,23 @@ int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu)
 	return ret;
 }
 
+u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2)
+{
+	u64 hv_status;
+
+	register u64 __r8 asm("r8") = param2;
+	asm volatile("vmmcall"
+		     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+		       "+c" (control), "+d" (param1), "+r" (__r8)
+		     : : "cc", "memory", "r9", "r10", "r11");
+
+	return hv_status;
+}
+
 #else
 static inline void hv_ghcb_msr_write(u64 msr, u64 value) {}
 static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {}
+u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2) { return U64_MAX; }
 #endif /* CONFIG_AMD_MEM_ENCRYPT */
 
 #ifdef CONFIG_INTEL_TDX_GUEST
@@ -437,6 +451,7 @@ u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2)
 #else
 static inline void hv_tdx_msr_write(u64 msr, u64 value) {}
 static inline void hv_tdx_msr_read(u64 msr, u64 *value) {}
+u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) { return U64_MAX; }
 #endif /* CONFIG_INTEL_TDX_GUEST */
 
 #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index abc4659f5809..605abd02158d 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -6,6 +6,7 @@
 #include <linux/nmi.h>
 #include <linux/msi.h>
 #include <linux/io.h>
+#include <linux/static_call.h>
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
 #include <asm/msr.h>
@@ -39,16 +40,21 @@ static inline unsigned char hv_get_nmi_reason(void)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_HYPERV)
-extern bool hyperv_paravisor_present;
+extern u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
+extern u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2);
+extern u64 hv_std_hypercall(u64 control, u64 param1, u64 param2);
 
+#if IS_ENABLED(CONFIG_HYPERV)
 extern void *hv_hypercall_pg;
 
 extern union hv_ghcb * __percpu *hv_ghcb_pg;
 
 bool hv_isolation_type_snp(void);
 bool hv_isolation_type_tdx(void);
-u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
+
+#ifdef CONFIG_X86_64
+DECLARE_STATIC_CALL(hv_hypercall, hv_std_hypercall);
+#endif
 
 /*
  * DEFAULT INIT GPAT and SEGMENT LIMIT value in struct VMSA
@@ -65,37 +71,15 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 {
 	u64 input_address = input ? virt_to_phys(input) : 0;
 	u64 output_address = output ? virt_to_phys(output) : 0;
-	u64 hv_status;
 
 #ifdef CONFIG_X86_64
-	if (hv_isolation_type_tdx() && !hyperv_paravisor_present)
-		return hv_tdx_hypercall(control, input_address, output_address);
-
-	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %[output_address], %%r8\n"
-				     "vmmcall"
-				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
-				       "+c" (control), "+d" (input_address)
-				     : [output_address] "r" (output_address)
-				     : "cc", "memory", "r8", "r9", "r10", "r11");
-		return hv_status;
-	}
-
-	if (!hv_hypercall_pg)
-		return U64_MAX;
-
-	__asm__ __volatile__("mov %[output_address], %%r8\n"
-			     CALL_NOSPEC
-			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
-			       "+c" (control), "+d" (input_address)
-			     : [output_address] "r" (output_address),
-			       THUNK_TARGET(hv_hypercall_pg)
-			     : "cc", "memory", "r8", "r9", "r10", "r11");
+	return static_call_mod(hv_hypercall)(control, input_address, output_address);
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
 	u32 input_address_lo = lower_32_bits(input_address);
 	u32 output_address_hi = upper_32_bits(output_address);
 	u32 output_address_lo = lower_32_bits(output_address);
+	u64 hv_status;
 
 	if (!hv_hypercall_pg)
 		return U64_MAX;
@@ -108,48 +92,30 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 			       "D"(output_address_hi), "S"(output_address_lo),
 			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory");
-#endif /* !x86_64 */
 	return hv_status;
+#endif /* !x86_64 */
 }
 
 /* Fast hypercall with 8 bytes of input and no output */
 static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
 {
+#ifdef CONFIG_X86_64
+	return static_call_mod(hv_hypercall)(control, input1, 0);
+#else
+	u32 input1_hi = upper_32_bits(input1);
+	u32 input1_lo = lower_32_bits(input1);
 	u64 hv_status;
 
-#ifdef CONFIG_X86_64
-	if (hv_isolation_type_tdx() && !hyperv_paravisor_present)
-		return hv_tdx_hypercall(control, input1, 0);
-
-	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__(
-				"vmmcall"
-				: "=a" (hv_status), ASM_CALL_CONSTRAINT,
-				"+c" (control), "+d" (input1)
-				:: "cc", "r8", "r9", "r10", "r11");
-	} else {
-		__asm__ __volatile__(CALL_NOSPEC
-				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
-				       "+c" (control), "+d" (input1)
-				     : THUNK_TARGET(hv_hypercall_pg)
-				     : "cc", "r8", "r9", "r10", "r11");
-	}
-#else
-	{
-		u32 input1_hi = upper_32_bits(input1);
-		u32 input1_lo = lower_32_bits(input1);
-
-		__asm__ __volatile__ (CALL_NOSPEC
-				      : "=A"(hv_status),
-					"+c"(input1_lo),
-					ASM_CALL_CONSTRAINT
-				      :	"A" (control),
-					"b" (input1_hi),
-					THUNK_TARGET(hv_hypercall_pg)
-				      : "cc", "edi", "esi");
-	}
-#endif
+	__asm__ __volatile__ (CALL_NOSPEC
+			      : "=A"(hv_status),
+			      "+c"(input1_lo),
+			      ASM_CALL_CONSTRAINT
+			      :	"A" (control),
+			      "b" (input1_hi),
+			      THUNK_TARGET(hv_hypercall_pg)
+			      : "cc", "edi", "esi");
 	return hv_status;
+#endif
 }
 
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
@@ -162,45 +128,24 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 /* Fast hypercall with 16 bytes of input */
 static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 {
+#ifdef CONFIG_X86_64
+	return static_call_mod(hv_hypercall)(control, input1, input2);
+#else
+	u32 input1_hi = upper_32_bits(input1);
+	u32 input1_lo = lower_32_bits(input1);
+	u32 input2_hi = upper_32_bits(input2);
+	u32 input2_lo = lower_32_bits(input2);
 	u64 hv_status;
 
-#ifdef CONFIG_X86_64
-	if (hv_isolation_type_tdx() && !hyperv_paravisor_present)
-		return hv_tdx_hypercall(control, input1, input2);
-
-	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %[input2], %%r8\n"
-				     "vmmcall"
-				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
-				       "+c" (control), "+d" (input1)
-				     : [input2] "r" (input2)
-				     : "cc", "r8", "r9", "r10", "r11");
-	} else {
-		__asm__ __volatile__("mov %[input2], %%r8\n"
-				     CALL_NOSPEC
-				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
-				       "+c" (control), "+d" (input1)
-				     : [input2] "r" (input2),
-				       THUNK_TARGET(hv_hypercall_pg)
-				     : "cc", "r8", "r9", "r10", "r11");
-	}
-#else
-	{
-		u32 input1_hi = upper_32_bits(input1);
-		u32 input1_lo = lower_32_bits(input1);
-		u32 input2_hi = upper_32_bits(input2);
-		u32 input2_lo = lower_32_bits(input2);
-
-		__asm__ __volatile__ (CALL_NOSPEC
-				      : "=A"(hv_status),
-					"+c"(input1_lo), ASM_CALL_CONSTRAINT
-				      :	"A" (control), "b" (input1_hi),
-					"D"(input2_hi), "S"(input2_lo),
-					THUNK_TARGET(hv_hypercall_pg)
-				      : "cc");
-	}
-#endif
+	__asm__ __volatile__ (CALL_NOSPEC
+			      : "=A"(hv_status),
+			      "+c"(input1_lo), ASM_CALL_CONSTRAINT
+			      :	"A" (control), "b" (input1_hi),
+			      "D"(input2_hi), "S"(input2_lo),
+			      THUNK_TARGET(hv_hypercall_pg)
+			      : "cc");
 	return hv_status;
+#endif
 }
 
 static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c78f860419d6..3c71effe9ff5 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -38,10 +38,6 @@
 bool hv_nested;
 struct ms_hyperv_info ms_hyperv;
 
-/* Used in modules via hv_do_hypercall(): see arch/x86/include/asm/mshyperv.h */
-bool hyperv_paravisor_present __ro_after_init;
-EXPORT_SYMBOL_GPL(hyperv_paravisor_present);
-
 #if IS_ENABLED(CONFIG_HYPERV)
 static inline unsigned int hv_get_nested_msr(unsigned int reg)
 {
@@ -288,8 +284,18 @@ static void __init x86_setup_ops_for_tsc_pg_clock(void)
 	old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
 	x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
 }
+
+#ifdef CONFIG_X86_64
+DEFINE_STATIC_CALL(hv_hypercall, hv_std_hypercall);
+EXPORT_STATIC_CALL_TRAMP_GPL(hv_hypercall);
+#define hypercall_update(hc) static_call_update(hv_hypercall, hc)
+#endif
 #endif /* CONFIG_HYPERV */
 
+#ifndef hypercall_update
+#define hypercall_update(hc) (void)hc
+#endif
+
 static uint32_t  __init ms_hyperv_platform(void)
 {
 	u32 eax;
@@ -484,14 +490,14 @@ static void __init ms_hyperv_init_platform(void)
 			ms_hyperv.shared_gpa_boundary =
 				BIT_ULL(ms_hyperv.shared_gpa_boundary_bits);
 
-		hyperv_paravisor_present = !!ms_hyperv.paravisor_present;
-
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
 
 
 		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) {
 			static_branch_enable(&isolation_type_snp);
+			if (!ms_hyperv.paravisor_present)
+				hypercall_update(hv_snp_hypercall);
 		} else if (hv_get_isolation_type() == HV_ISOLATION_TYPE_TDX) {
 			static_branch_enable(&isolation_type_tdx);
 
@@ -499,6 +505,7 @@ static void __init ms_hyperv_init_platform(void)
 			ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED;
 
 			if (!ms_hyperv.paravisor_present) {
+				hypercall_update(hv_tdx_hypercall);
 				/*
 				 * Mark the Hyper-V TSC page feature as disabled
 				 * in a TDX VM without paravisor so that the

From c8ed0812646e1335c80a8f204c1b92b2f9d76119 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 12 Apr 2025 13:55:55 +0200
Subject: [PATCH 012/352] x86/hyperv: Use direct call to hypercall-page

Instead of using an indirect call to the hypercall page, use a direct
call instead. This avoids all CFI problems, including the one where
the hypercall page doesn't have IBT on.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103441.011387946@infradead.org
---
 arch/x86/hyperv/hv_init.c | 61 +++++++++++++++++++--------------------
 1 file changed, 30 insertions(+), 31 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 5ef1e647ebc0..e890fd37e9c2 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -17,7 +17,6 @@
 #include <asm/desc.h>
 #include <asm/e820/api.h>
 #include <asm/sev.h>
-#include <asm/ibt.h>
 #include <asm/hypervisor.h>
 #include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
@@ -39,23 +38,41 @@
 void *hv_hypercall_pg;
 
 #ifdef CONFIG_X86_64
+static u64 __hv_hyperfail(u64 control, u64 param1, u64 param2)
+{
+	return U64_MAX;
+}
+
+DEFINE_STATIC_CALL(__hv_hypercall, __hv_hyperfail);
+
 u64 hv_std_hypercall(u64 control, u64 param1, u64 param2)
 {
 	u64 hv_status;
 
-	if (!hv_hypercall_pg)
-		return U64_MAX;
-
 	register u64 __r8 asm("r8") = param2;
-	asm volatile (CALL_NOSPEC
+	asm volatile ("call " STATIC_CALL_TRAMP_STR(__hv_hypercall)
 		      : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 		        "+c" (control), "+d" (param1), "+r" (__r8)
-		      : THUNK_TARGET(hv_hypercall_pg)
-		      : "cc", "memory", "r9", "r10", "r11");
+		      : : "cc", "memory", "r9", "r10", "r11");
 
 	return hv_status;
 }
+
+typedef u64 (*hv_hypercall_f)(u64 control, u64 param1, u64 param2);
+
+static inline void hv_set_hypercall_pg(void *ptr)
+{
+	hv_hypercall_pg = ptr;
+
+	if (!ptr)
+		ptr = &__hv_hyperfail;
+	static_call_update(__hv_hypercall, (hv_hypercall_f)ptr);
+}
 #else
+static inline void hv_set_hypercall_pg(void *ptr)
+{
+	hv_hypercall_pg = ptr;
+}
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 #endif
 
@@ -350,7 +367,7 @@ static int hv_suspend(void)
 	 * pointer is restored on resume.
 	 */
 	hv_hypercall_pg_saved = hv_hypercall_pg;
-	hv_hypercall_pg = NULL;
+	hv_set_hypercall_pg(NULL);
 
 	/* Disable the hypercall page in the hypervisor */
 	rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -376,7 +393,7 @@ static void hv_resume(void)
 		vmalloc_to_pfn(hv_hypercall_pg_saved);
 	wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	hv_hypercall_pg = hv_hypercall_pg_saved;
+	hv_set_hypercall_pg(hv_hypercall_pg_saved);
 	hv_hypercall_pg_saved = NULL;
 
 	/*
@@ -496,8 +513,8 @@ void __init hyperv_init(void)
 	if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present)
 		goto skip_hypercall_pg_init;
 
-	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
-			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
+	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, MODULES_VADDR,
+			MODULES_END, GFP_KERNEL, PAGE_KERNEL_ROX,
 			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
 			__builtin_return_address(0));
 	if (hv_hypercall_pg == NULL)
@@ -535,27 +552,9 @@ void __init hyperv_init(void)
 		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	}
 
-skip_hypercall_pg_init:
-	/*
-	 * Some versions of Hyper-V that provide IBT in guest VMs have a bug
-	 * in that there's no ENDBR64 instruction at the entry to the
-	 * hypercall page. Because hypercalls are invoked via an indirect call
-	 * to the hypercall page, all hypercall attempts fail when IBT is
-	 * enabled, and Linux panics. For such buggy versions, disable IBT.
-	 *
-	 * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall
-	 * page, so if future Linux kernel versions enable IBT for 32-bit
-	 * builds, additional hypercall page hackery will be required here
-	 * to provide an ENDBR32.
-	 */
-#ifdef CONFIG_X86_KERNEL_IBT
-	if (cpu_feature_enabled(X86_FEATURE_IBT) &&
-	    *(u32 *)hv_hypercall_pg != gen_endbr()) {
-		setup_clear_cpu_cap(X86_FEATURE_IBT);
-		pr_warn("Disabling IBT because of Hyper-V bug\n");
-	}
-#endif
+	hv_set_hypercall_pg(hv_hypercall_pg);
 
+skip_hypercall_pg_init:
 	/*
 	 * hyperv_init() is called before LAPIC is initialized: see
 	 * apic_intr_mode_init() -> x86_platform.apic_post_init() and

From 2d1435b742156f6d4adc8b9ab0f24b35d879266e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 2 May 2025 07:24:01 -0700
Subject: [PATCH 013/352] x86/fred: Install system vector handlers even if FRED
 isn't fully enabled

Install the system vector IRQ handlers for FRED even if FRED isn't fully
enabled in hardware.  This will allow KVM to use the FRED IRQ path even
on non-FRED hardware, which in turn will eliminate a non-CFI indirect CALL
(KVM currently invokes the IRQ handler via an IDT lookup on the vector).

[sean: extract from diff, drop stub, write changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250714103441.121251108@infradead.org
---
 arch/x86/include/asm/idtentry.h | 9 ++-------
 arch/x86/kernel/irqinit.c       | 6 ++++--
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index a4ec27c67988..abd637e54e94 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -460,17 +460,12 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #endif
 
 void idt_install_sysvec(unsigned int n, const void *function);
-
-#ifdef CONFIG_X86_FRED
 void fred_install_sysvec(unsigned int vector, const idtentry_t function);
-#else
-static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { }
-#endif
 
 #define sysvec_install(vector, function) {				\
-	if (cpu_feature_enabled(X86_FEATURE_FRED))			\
+	if (IS_ENABLED(CONFIG_X86_FRED))				\
 		fred_install_sysvec(vector, function);			\
-	else								\
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))			\
 		idt_install_sysvec(vector, asm_##function);		\
 }
 
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index f79c5edc0b89..6ab9eac64670 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -97,9 +97,11 @@ void __init native_init_IRQ(void)
 	/* Execute any quirks before the call gates are initialised: */
 	x86_init.irqs.pre_vector_init();
 
-	if (cpu_feature_enabled(X86_FEATURE_FRED))
+	/* FRED's IRQ path may be used even if FRED isn't fully enabled. */
+	if (IS_ENABLED(CONFIG_X86_FRED))
 		fred_complete_exception_setup();
-	else
+
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
 		idt_setup_apic_and_irq_gates();
 
 	lapic_assign_system_vectors();

From deed19b9b28724bd32e85063c60718c0a6803906 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Fri, 6 Jun 2025 13:04:25 +0200
Subject: [PATCH 014/352] x86/fred: Play nice with invoking
 asm_fred_entry_from_kvm() on non-FRED hardware

Modify asm_fred_entry_from_kvm() to allow it to be invoked by KVM even
when FRED isn't fully enabled, e.g. when running with
CONFIG_X86_FRED=y on non-FRED hardware.  This will allow forcing KVM
to always use the FRED entry points for 64-bit kernels, which in turn
will eliminate a rather gross non-CFI indirect call that KVM uses to
trampoline IRQs by doing IDT lookups.

The point of asm_fred_entry_from_kvm() is to bridge between C
(vmx:handle_external_interrupt_irqoff()) and more C
(__fred_entry_from_kvm()) while changing the calling context to appear
like an interrupt (pt_regs). Making the whole thing bound by C ABI.

All that remains for non-FRED hardware is to restore RSP (to undo the
redzone and alignment). However the trivial change would result in
code like:

  push %rbp
  mov %rsp, %rbp

  sub $REDZONE, %rsp
  and $MASK, %rsp

  PUSH_AND_CLEAR_REGS
   push %rbp

  POP_REGS
   pop %rbp <-- *objtool fail*

  mov %rbp, %rsp
  pop %rbp
  ret

And this will confuse objtool something wicked -- it gets confused by
the extra pop %rbp, not realizing the push and pop preserve the value.

Rather than trying to each objtool about this, recognise that since
the code is bound by C ABI on both ends and interrupts are not allowed
to change pt_regs (only exceptions are) it is sufficient to PUSH_REGS
in order to create pt_regs, but there is no reason to POP_REGS --
provided the callee-saved registers are preserved.

So avoid clearing callee-saved regs and skip POP_REGS.

[Original patch by Sean; much of this version by Josh; Changelog,
comments and final form by Peterz]

Originally-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103441.245417052@infradead.org
---
 arch/x86/entry/calling.h       | 11 +++++------
 arch/x86/entry/entry_64_fred.S | 35 ++++++++++++++++++++++++++--------
 arch/x86/kernel/asm-offsets.c  |  1 +
 3 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 94519688b007..77e2d920a640 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -99,7 +99,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 .endm
 
-.macro CLEAR_REGS clear_bp=1
+.macro CLEAR_REGS clear_callee=1
 	/*
 	 * Sanitize registers of values that a speculation attack might
 	 * otherwise want to exploit. The lower registers are likely clobbered
@@ -113,20 +113,19 @@ For 32-bit we have the following conventions - kernel is built with
 	xorl	%r9d,  %r9d	/* nospec r9  */
 	xorl	%r10d, %r10d	/* nospec r10 */
 	xorl	%r11d, %r11d	/* nospec r11 */
+	.if \clear_callee
 	xorl	%ebx,  %ebx	/* nospec rbx */
-	.if \clear_bp
 	xorl	%ebp,  %ebp	/* nospec rbp */
-	.endif
 	xorl	%r12d, %r12d	/* nospec r12 */
 	xorl	%r13d, %r13d	/* nospec r13 */
 	xorl	%r14d, %r14d	/* nospec r14 */
 	xorl	%r15d, %r15d	/* nospec r15 */
-
+	.endif
 .endm
 
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_callee=1 unwind_hint=1
 	PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint
-	CLEAR_REGS clear_bp=\clear_bp
+	CLEAR_REGS clear_callee=\clear_callee
 .endm
 
 .macro POP_REGS pop_rdi=1
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index 29c5c32c16c3..0d00ec8ee79a 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -112,18 +112,37 @@ SYM_FUNC_START(asm_fred_entry_from_kvm)
 	push %rax				/* Return RIP */
 	push $0					/* Error code, 0 for IRQ/NMI */
 
-	PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0
+	PUSH_AND_CLEAR_REGS clear_callee=0 unwind_hint=0
+
 	movq %rsp, %rdi				/* %rdi -> pt_regs */
-	call __fred_entry_from_kvm		/* Call the C entry point */
-	POP_REGS
-	ERETS
-1:
 	/*
-	 * Objtool doesn't understand what ERETS does, this hint tells it that
-	 * yes, we'll reach here and with what stack state. A save/restore pair
-	 * isn't strictly needed, but it's the simplest form.
+	 * At this point: {rdi, rsi, rdx, rcx, r8, r9}, {r10, r11}, {rax, rdx}
+	 * are clobbered, which corresponds to: arguments, extra caller-saved
+	 * and return. All registers a C function is allowed to clobber.
+	 *
+	 * Notably, the callee-saved registers: {rbx, r12, r13, r14, r15}
+	 * are untouched, with the exception of rbp, which carries the stack
+	 * frame and will be restored before exit.
+	 *
+	 * Further calling another C function will not alter this state.
+	 */
+	call __fred_entry_from_kvm		/* Call the C entry point */
+
+	/*
+	 * When FRED, use ERETS to potentially clear NMIs, otherwise simply
+	 * restore the stack pointer.
+	 */
+	ALTERNATIVE "nop; nop; mov %rbp, %rsp", \
+	            __stringify(add $C_PTREGS_SIZE, %rsp; ERETS), \
+		    X86_FEATURE_FRED
+
+1:	/*
+	 * Objtool doesn't understand ERETS, and the cfi register state is
+	 * different from initial_func_cfi due to PUSH_REGS. Tell it the state
+	 * is similar to where UNWIND_HINT_SAVE is.
 	 */
 	UNWIND_HINT_RESTORE
+
 	pop %rbp
 	RET
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 6259b474073b..32ba599a51f8 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -102,6 +102,7 @@ static void __used common(void)
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+	OFFSET(C_PTREGS_SIZE, pt_regs, orig_ax);
 
 	/* TLB state for the entry code */
 	OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);

From 28d11e4548b75d0960429344f12d5f6cc9cee25b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 1 May 2025 11:10:39 -0700
Subject: [PATCH 015/352] x86/fred: KVM: VMX: Always use FRED for IRQs when
 CONFIG_X86_FRED=y

Now that FRED provides C-code entry points for handling IRQs, use the
FRED infrastructure for forwarding IRQs even if FRED is fully
disabled, e.g. isn't supported in hardware. Avoiding the non-FRED
assembly trampolines into the IDT handlers for IRQs eliminates the
associated non-CFI indirect call (KVM performs a CALL by doing a
lookup on the IDT using the IRQ vector).

Keep NMIs on the legacy IDT path, as the FRED NMI entry code relies on
FRED's architectural behavior with respect to NMI blocking, i.e. doesn't
jump through the myriad hoops needed to deal with IRET "unexpectedly"
unmasking NMIs.  KVM's NMI path already makes a direct CALL to C-code,
i.e. isn't problematic for CFI.  KVM does make a short detour through
assembly code to build the stack frame, but the "FRED entry from KVM"
path does the same.

Force FRED for 64-bit kernels if KVM_INTEL is enabled, as the benefits of
eliminating the IRQ trampoline usage far outwieghts the code overhead for
FRED.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250714103441.381946911@infradead.org
---
 arch/x86/kvm/Kconfig   | 1 +
 arch/x86/kvm/vmx/vmx.c | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 2c86673155c9..b92ef117f355 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -97,6 +97,7 @@ config KVM_INTEL
 	depends on KVM && IA32_FEAT_CTL
 	select KVM_GENERIC_PRIVATE_MEM if INTEL_TDX_HOST
 	select KVM_GENERIC_MEMORY_ATTRIBUTES if INTEL_TDX_HOST
+	select X86_FRED if X86_64
 	help
 	  Provides support for KVM on processors equipped with Intel's VT
 	  extensions, a.k.a. Virtual Machine Extensions (VMX).
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index aa157fe5b7b3..f7f6c04a41d6 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6913,8 +6913,14 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu,
 	    "unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
+	/*
+	 * Invoke the kernel's IRQ handler for the vector.  Use the FRED path
+	 * when it's available even if FRED isn't fully enabled, e.g. even if
+	 * FRED isn't supported in hardware, in order to avoid the indirect
+	 * CALL in the non-FRED path.
+	 */
 	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
-	if (cpu_feature_enabled(X86_FEATURE_FRED))
+	if (IS_ENABLED(CONFIG_X86_FRED))
 		fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector);
 	else
 		vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector));

From 894af4a1cde61c3401f237184fb770f72ff12df8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 12 Apr 2025 13:56:01 +0200
Subject: [PATCH 016/352] objtool: Validate kCFI calls

Validate that all indirect calls adhere to kCFI rules. Notably doing
nocfi indirect call to a cfi function is broken.

Apparently some Rust 'core' code violates this and explodes when ran
with FineIBT.

All the ANNOTATE_NOCFI_SYM sites are prime targets for attackers.

 - runtime EFI is especially henous because it also needs to disable
   IBT. Basically calling unknown code without CFI protection at
   runtime is a massice security issue.

 - Kexec image handover; if you can exploit this, you get to keep it :-)

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Link: https://lkml.kernel.org/r/20250714103441.496787279@infradead.org
---
 arch/x86/kernel/machine_kexec_64.c  |  4 +++
 arch/x86/kvm/vmx/vmenter.S          |  4 +++
 arch/x86/platform/efi/efi_stub_64.S |  4 +++
 drivers/misc/lkdtm/perms.c          |  5 ++++
 include/linux/objtool.h             | 10 +++++++
 include/linux/objtool_types.h       |  1 +
 tools/include/linux/objtool_types.h |  1 +
 tools/objtool/check.c               | 42 +++++++++++++++++++++++++++++
 tools/objtool/include/objtool/elf.h |  1 +
 9 files changed, 72 insertions(+)

diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 697fb99406e6..8593760c255a 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -453,6 +453,10 @@ void __nocfi machine_kexec(struct kimage *image)
 
 	__ftrace_enabled_restore(save_ftrace_enabled);
 }
+/*
+ * Handover to the next kernel, no CFI concern.
+ */
+ANNOTATE_NOCFI_SYM(machine_kexec);
 
 /* arch-dependent functionality related to kexec file-based syscall */
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 0a6cf5bff2aa..bc255d709d8a 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -361,6 +361,10 @@ SYM_FUNC_END(vmread_error_trampoline)
 
 .section .text, "ax"
 
+#ifndef CONFIG_X86_FRED
+
 SYM_FUNC_START(vmx_do_interrupt_irqoff)
 	VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1
 SYM_FUNC_END(vmx_do_interrupt_irqoff)
+
+#endif
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 2206b8bc47b8..f0a5fba0717e 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -11,6 +11,10 @@
 #include <asm/nospec-branch.h>
 
 SYM_FUNC_START(__efi_call)
+	/*
+	 * The EFI code doesn't have any CFI, annotate away the CFI violation.
+	 */
+	ANNOTATE_NOCFI_SYM
 	pushq %rbp
 	movq %rsp, %rbp
 	and $~0xf, %rsp
diff --git a/drivers/misc/lkdtm/perms.c b/drivers/misc/lkdtm/perms.c
index 6c24426104ba..e1f5e9abb301 100644
--- a/drivers/misc/lkdtm/perms.c
+++ b/drivers/misc/lkdtm/perms.c
@@ -9,6 +9,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mman.h>
 #include <linux/uaccess.h>
+#include <linux/objtool.h>
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 
@@ -86,6 +87,10 @@ static noinline __nocfi void execute_location(void *dst, bool write)
 	func();
 	pr_err("FAIL: func returned\n");
 }
+/*
+ * Explicitly doing the wrong thing for testing.
+ */
+ANNOTATE_NOCFI_SYM(execute_location);
 
 static void execute_user_location(void *dst)
 {
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 366ad004d794..46ebaa46e6c5 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -184,6 +184,15 @@
  * WARN using UD2.
  */
 #define ANNOTATE_REACHABLE(label)	__ASM_ANNOTATE(label, ANNOTYPE_REACHABLE)
+/*
+ * This should not be used; it annotates away CFI violations. There are a few
+ * valid use cases like kexec handover to the next kernel image, and there is
+ * no security concern there.
+ *
+ * There are also a few real issues annotated away, like EFI because we can't
+ * control the EFI code.
+ */
+#define ANNOTATE_NOCFI_SYM(sym)		asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOCFI))
 
 #else
 #define ANNOTATE_NOENDBR		ANNOTATE type=ANNOTYPE_NOENDBR
@@ -194,6 +203,7 @@
 #define ANNOTATE_INTRA_FUNCTION_CALL	ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL
 #define ANNOTATE_UNRET_BEGIN		ANNOTATE type=ANNOTYPE_UNRET_BEGIN
 #define ANNOTATE_REACHABLE		ANNOTATE type=ANNOTYPE_REACHABLE
+#define ANNOTATE_NOCFI_SYM		ANNOTATE type=ANNOTYPE_NOCFI
 #endif
 
 #if defined(CONFIG_NOINSTR_VALIDATION) && \
diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h
index df5d9fa84dba..aceac94632c8 100644
--- a/include/linux/objtool_types.h
+++ b/include/linux/objtool_types.h
@@ -65,5 +65,6 @@ struct unwind_hint {
 #define ANNOTYPE_IGNORE_ALTS		6
 #define ANNOTYPE_INTRA_FUNCTION_CALL	7
 #define ANNOTYPE_REACHABLE		8
+#define ANNOTYPE_NOCFI			9
 
 #endif /* _LINUX_OBJTOOL_TYPES_H */
diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h
index df5d9fa84dba..aceac94632c8 100644
--- a/tools/include/linux/objtool_types.h
+++ b/tools/include/linux/objtool_types.h
@@ -65,5 +65,6 @@ struct unwind_hint {
 #define ANNOTYPE_IGNORE_ALTS		6
 #define ANNOTYPE_INTRA_FUNCTION_CALL	7
 #define ANNOTYPE_REACHABLE		8
+#define ANNOTYPE_NOCFI			9
 
 #endif /* _LINUX_OBJTOOL_TYPES_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index d14f20ef1db1..79eab61cd944 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2392,6 +2392,8 @@ static int __annotate_ifc(struct objtool_file *file, int type, struct instructio
 
 static int __annotate_late(struct objtool_file *file, int type, struct instruction *insn)
 {
+	struct symbol *sym;
+
 	switch (type) {
 	case ANNOTYPE_NOENDBR:
 		/* early */
@@ -2433,6 +2435,15 @@ static int __annotate_late(struct objtool_file *file, int type, struct instructi
 		insn->dead_end = false;
 		break;
 
+	case ANNOTYPE_NOCFI:
+		sym = insn->sym;
+		if (!sym) {
+			ERROR_INSN(insn, "dodgy NOCFI annotation");
+			return -1;
+		}
+		insn->sym->nocfi = 1;
+		break;
+
 	default:
 		ERROR_INSN(insn, "Unknown annotation type: %d", type);
 		return -1;
@@ -4002,6 +4013,37 @@ static int validate_retpoline(struct objtool_file *file)
 		warnings++;
 	}
 
+	if (!opts.cfi)
+		return warnings;
+
+	/*
+	 * kCFI call sites look like:
+	 *
+	 *     movl $(-0x12345678), %r10d
+	 *     addl -4(%r11), %r10d
+	 *     jz 1f
+	 *     ud2
+	 *  1: cs call __x86_indirect_thunk_r11
+	 *
+	 * Verify all indirect calls are kCFI adorned by checking for the
+	 * UD2. Notably, doing __nocfi calls to regular (cfi) functions is
+	 * broken.
+	 */
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
+		struct symbol *sym = insn->sym;
+
+		if (sym && (sym->type == STT_NOTYPE ||
+			    sym->type == STT_FUNC) && !sym->nocfi) {
+			struct instruction *prev =
+				prev_insn_same_sym(file, insn);
+
+			if (!prev || prev->type != INSN_BUG) {
+				WARN_INSN(insn, "no-cfi indirect call!");
+				warnings++;
+			}
+		}
+	}
+
 	return warnings;
 }
 
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 0a2fa3ac0079..df8434d3b744 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -70,6 +70,7 @@ struct symbol {
 	u8 local_label       : 1;
 	u8 frame_pointer     : 1;
 	u8 ignore	     : 1;
+	u8 nocfi             : 1;
 	struct list_head pv_target;
 	struct reloc *relocs;
 	struct section *group_sec;

From 03777dbd8c9d825fc6f792e4e85be9e4ce4c7f8f Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Wed, 23 Jul 2025 09:12:11 +0200
Subject: [PATCH 017/352] x86/kconfig: Drop unused and needless config
 X86_64_SMP

As part of

  38a4968b3190 ("x86/percpu/64: Remove INIT_PER_CPU macros"),

the only use of the config option X86_64_SMP in the kernel tree is removed. As
this config option X86_64_SMP is just equivalent to X86_64 && SMP, the source
code in the tree just uses that expression in the few places where needed. Note
further that this option cannot be explicitly enabled or disabled when
configuring the kernel build configuration.

Drop this needless and unused config option. No functional change.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250723071211.622802-1-lukas.bulwahn@redhat.com
---
 arch/x86/Kconfig | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 58d890fe2100..2eb3bb6fb371 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -410,10 +410,6 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
 
-config X86_64_SMP
-	def_bool y
-	depends on X86_64 && SMP
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 

From a35da57357221a989e59ced9407ba4f2d4d6d2d2 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 19 Aug 2025 10:57:49 +0200
Subject: [PATCH 018/352] crypto: x86 - Remove CONFIG_AS_GFNI

Current minimum required version of binutils is 2.30, which supports GFNI
instruction mnemonics.

Remove check for assembler support of GFNI instructions and all relevant
macros for conditional compilation.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/20250819085855.333380-1-ubizjak@gmail.com
---
 arch/x86/Kconfig.assembler               |  5 -----
 arch/x86/crypto/Kconfig                  |  2 +-
 arch/x86/crypto/aria-aesni-avx-asm_64.S  | 10 ----------
 arch/x86/crypto/aria-aesni-avx2-asm_64.S | 10 +---------
 arch/x86/crypto/aria_aesni_avx2_glue.c   |  4 +---
 arch/x86/crypto/aria_aesni_avx_glue.c    |  4 +---
 6 files changed, 4 insertions(+), 31 deletions(-)

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index c827f694fb72..6b95be002465 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,11 +6,6 @@ config AS_AVX512
 	help
 	  Supported by binutils >= 2.25 and LLVM integrated assembler
 
-config AS_GFNI
-	def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2)
-	help
-	  Supported by binutils >= 2.30 and LLVM integrated assembler
-
 config AS_VAES
 	def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2)
 	help
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index 94016c60561e..2f8a447f3546 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -319,7 +319,7 @@ config CRYPTO_ARIA_AESNI_AVX2_X86_64
 
 config CRYPTO_ARIA_GFNI_AVX512_X86_64
 	tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)"
-	depends on 64BIT && AS_GFNI
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_ALGAPI
 	select CRYPTO_ARIA
diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S
index 9556dacd9841..932fb17308e7 100644
--- a/arch/x86/crypto/aria-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S
@@ -295,7 +295,6 @@
 	vpshufb t1, t0, t2;				\
 	vpxor t2, x7, x7;
 
-#ifdef CONFIG_AS_GFNI
 #define aria_sbox_8way_gfni(x0, x1, x2, x3,		\
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
@@ -318,8 +317,6 @@
 	vgf2p8affineinvqb $0, t2, x3, x3;		\
 	vgf2p8affineinvqb $0, t2, x7, x7
 
-#endif /* CONFIG_AS_GFNI */
-
 #define aria_sbox_8way(x0, x1, x2, x3,            	\
 		       x4, x5, x6, x7,			\
 		       t0, t1, t2, t3,			\
@@ -561,7 +558,6 @@
 			     y4, y5, y6, y7,		\
 			     mem_tmp, 8);
 
-#ifdef CONFIG_AS_GFNI
 #define aria_fe_gfni(x0, x1, x2, x3,			\
 		     x4, x5, x6, x7,			\
 		     y0, y1, y2, y3,			\
@@ -719,8 +715,6 @@
 			     y4, y5, y6, y7,		\
 			     mem_tmp, 8);
 
-#endif /* CONFIG_AS_GFNI */
-
 /* NB: section is mergeable, all elements must be aligned 16-byte blocks */
 .section	.rodata.cst16, "aM", @progbits, 16
 .align 16
@@ -772,7 +766,6 @@
 .Ltf_hi__x2__and__fwd_aff:
 	.octa 0x3F893781E95FE1576CDA64D2BA0CB204
 
-#ifdef CONFIG_AS_GFNI
 /* AES affine: */
 #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0)
 .Ltf_aff_bitmatrix:
@@ -871,7 +864,6 @@
 		    BV8(0, 0, 0, 0, 0, 1, 0, 0),
 		    BV8(0, 0, 0, 0, 0, 0, 1, 0),
 		    BV8(0, 0, 0, 0, 0, 0, 0, 1))
-#endif /* CONFIG_AS_GFNI */
 
 /* 4-bit mask */
 .section	.rodata.cst4.L0f0f0f0f, "aM", @progbits, 4
@@ -1140,7 +1132,6 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_ctr_crypt_16way)
 	RET;
 SYM_FUNC_END(aria_aesni_avx_ctr_crypt_16way)
 
-#ifdef CONFIG_AS_GFNI
 SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way)
 	/* input:
 	*      %r9: rk
@@ -1359,4 +1350,3 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way)
 	FRAME_END
 	RET;
 SYM_FUNC_END(aria_aesni_avx_gfni_ctr_crypt_16way)
-#endif /* CONFIG_AS_GFNI */
diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S
index c60fa2980630..ed53d4f46bd7 100644
--- a/arch/x86/crypto/aria-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S
@@ -302,7 +302,6 @@
 	vpbroadcastb ((round * 16) + idx + 4)(rk), t0;	\
 	vpxor t0, x7, x7;
 
-#ifdef CONFIG_AS_GFNI
 #define aria_sbox_8way_gfni(x0, x1, x2, x3,		\
 			    x4, x5, x6, x7,		\
 			    t0, t1, t2, t3,		\
@@ -325,7 +324,6 @@
 	vgf2p8affineinvqb $0, t2, x3, x3;		\
 	vgf2p8affineinvqb $0, t2, x7, x7
 
-#endif /* CONFIG_AS_GFNI */
 #define aria_sbox_8way(x0, x1, x2, x3,			\
 		       x4, x5, x6, x7,			\
 		       t0, t1, t2, t3,			\
@@ -598,7 +596,7 @@
 	aria_load_state_8way(y0, y1, y2, y3,		\
 			     y4, y5, y6, y7,		\
 			     mem_tmp, 8);
-#ifdef CONFIG_AS_GFNI
+
 #define aria_fe_gfni(x0, x1, x2, x3,			\
 		     x4, x5, x6, x7,			\
 		     y0, y1, y2, y3,			\
@@ -752,7 +750,6 @@
 	aria_load_state_8way(y0, y1, y2, y3,		\
 			     y4, y5, y6, y7,		\
 			     mem_tmp, 8);
-#endif /* CONFIG_AS_GFNI */
 
 .section        .rodata.cst32.shufb_16x16b, "aM", @progbits, 32
 .align 32
@@ -806,7 +803,6 @@
 .Ltf_hi__x2__and__fwd_aff:
 	.octa 0x3F893781E95FE1576CDA64D2BA0CB204
 
-#ifdef CONFIG_AS_GFNI
 .section	.rodata.cst8, "aM", @progbits, 8
 .align 8
 /* AES affine: */
@@ -868,8 +864,6 @@
 		    BV8(0, 0, 0, 0, 0, 0, 1, 0),
 		    BV8(0, 0, 0, 0, 0, 0, 0, 1))
 
-#endif /* CONFIG_AS_GFNI */
-
 /* 4-bit mask */
 .section	.rodata.cst4.L0f0f0f0f, "aM", @progbits, 4
 .align 4
@@ -1219,7 +1213,6 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_ctr_crypt_32way)
 	RET;
 SYM_FUNC_END(aria_aesni_avx2_ctr_crypt_32way)
 
-#ifdef CONFIG_AS_GFNI
 SYM_FUNC_START_LOCAL(__aria_aesni_avx2_gfni_crypt_32way)
 	/* input:
 	 *      %r9: rk
@@ -1438,4 +1431,3 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_ctr_crypt_32way)
 	FRAME_END
 	RET;
 SYM_FUNC_END(aria_aesni_avx2_gfni_ctr_crypt_32way)
-#endif /* CONFIG_AS_GFNI */
diff --git a/arch/x86/crypto/aria_aesni_avx2_glue.c b/arch/x86/crypto/aria_aesni_avx2_glue.c
index 007b250f774c..1487a49bfbac 100644
--- a/arch/x86/crypto/aria_aesni_avx2_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx2_glue.c
@@ -26,7 +26,6 @@ asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst,
 						const u8 *src,
 						u8 *keystream, u8 *iv);
 EXPORT_SYMBOL_GPL(aria_aesni_avx2_ctr_crypt_32way);
-#ifdef CONFIG_AS_GFNI
 asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst,
 						   const u8 *src);
 EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_encrypt_32way);
@@ -37,7 +36,6 @@ asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst,
 						     const u8 *src,
 						     u8 *keystream, u8 *iv);
 EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_ctr_crypt_32way);
-#endif /* CONFIG_AS_GFNI */
 
 static struct aria_avx_ops aria_ops;
 
@@ -213,7 +211,7 @@ static int __init aria_avx2_init(void)
 		return -ENODEV;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) {
+	if (boot_cpu_has(X86_FEATURE_GFNI)) {
 		aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way;
 		aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way;
 		aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way;
diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c
index 4c88ef4eba82..e4e3d78915a5 100644
--- a/arch/x86/crypto/aria_aesni_avx_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx_glue.c
@@ -26,7 +26,6 @@ asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst,
 					       const u8 *src,
 					       u8 *keystream, u8 *iv);
 EXPORT_SYMBOL_GPL(aria_aesni_avx_ctr_crypt_16way);
-#ifdef CONFIG_AS_GFNI
 asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst,
 						  const u8 *src);
 EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_encrypt_16way);
@@ -37,7 +36,6 @@ asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst,
 						    const u8 *src,
 						    u8 *keystream, u8 *iv);
 EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_ctr_crypt_16way);
-#endif /* CONFIG_AS_GFNI */
 
 static struct aria_avx_ops aria_ops;
 
@@ -199,7 +197,7 @@ static int __init aria_avx_init(void)
 		return -ENODEV;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) {
+	if (boot_cpu_has(X86_FEATURE_GFNI)) {
 		aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way;
 		aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way;
 		aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way;

From 4593311290006793a38a9cbd91d4a65b63cd7b76 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 19 Aug 2025 10:57:50 +0200
Subject: [PATCH 019/352] crypto: X86 - Remove CONFIG_AS_VAES

Current minimum required version of binutils is 2.30, which supports VAES
instruction mnemonics.

Remove check for assembler support of VAES instructions and all relevant macros
for conditional compilation.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/20250819085855.333380-2-ubizjak@gmail.com
---
 arch/x86/Kconfig.assembler           |  5 -----
 arch/x86/crypto/Makefile             |  2 +-
 arch/x86/crypto/aes-ctr-avx-x86_64.S |  4 ++--
 arch/x86/crypto/aes-xts-avx-x86_64.S |  4 ++--
 arch/x86/crypto/aesni-intel_glue.c   | 14 +++++++-------
 5 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 6b95be002465..8d1808407674 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,11 +6,6 @@ config AS_AVX512
 	help
 	  Supported by binutils >= 2.25 and LLVM integrated assembler
 
-config AS_VAES
-	def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2)
-	help
-	  Supported by binutils >= 2.30 and LLVM integrated assembler
-
 config AS_VPCLMULQDQ
 	def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2)
 	help
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index d402963d6b57..50f1c0414c00 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -47,7 +47,7 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
 aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \
 			       aes-gcm-aesni-x86_64.o \
 			       aes-xts-avx-x86_64.o
-ifeq ($(CONFIG_AS_VAES)$(CONFIG_AS_VPCLMULQDQ),yy)
+ifeq ($(CONFIG_AS_VPCLMULQDQ),y)
 aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o
 endif
 
diff --git a/arch/x86/crypto/aes-ctr-avx-x86_64.S b/arch/x86/crypto/aes-ctr-avx-x86_64.S
index bbbfd80f5a50..ec957b25b062 100644
--- a/arch/x86/crypto/aes-ctr-avx-x86_64.S
+++ b/arch/x86/crypto/aes-ctr-avx-x86_64.S
@@ -552,7 +552,7 @@ SYM_TYPED_FUNC_START(aes_xctr_crypt_aesni_avx)
 	_aes_ctr_crypt	1
 SYM_FUNC_END(aes_xctr_crypt_aesni_avx)
 
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 .set	VL, 32
 .set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx2)
@@ -570,4 +570,4 @@ SYM_FUNC_END(aes_ctr64_crypt_vaes_avx512)
 SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx512)
 	_aes_ctr_crypt	1
 SYM_FUNC_END(aes_xctr_crypt_vaes_avx512)
-#endif // CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ
+#endif // CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index db79cdf81588..e44e56817d82 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -886,7 +886,7 @@ SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx)
 	_aes_xts_crypt	0
 SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
 
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 .set	VL, 32
 .set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
@@ -904,4 +904,4 @@ SYM_FUNC_END(aes_xts_encrypt_vaes_avx512)
 SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx512)
 	_aes_xts_crypt	0
 SYM_FUNC_END(aes_xts_decrypt_vaes_avx512)
-#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+#endif /* CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 061b1ced93c5..d5a2f5b2c01b 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -828,7 +828,7 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{		       \
 }}
 
 DEFINE_AVX_SKCIPHER_ALGS(aesni_avx, "aesni-avx", 500);
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 DEFINE_AVX_SKCIPHER_ALGS(vaes_avx2, "vaes-avx2", 600);
 DEFINE_AVX_SKCIPHER_ALGS(vaes_avx512, "vaes-avx512", 800);
 #endif
@@ -912,7 +912,7 @@ struct aes_gcm_key_avx10 {
 #define FLAG_RFC4106	BIT(0)
 #define FLAG_ENC	BIT(1)
 #define FLAG_AVX	BIT(2)
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 #  define FLAG_AVX10_256	BIT(3)
 #  define FLAG_AVX10_512	BIT(4)
 #else
@@ -1519,7 +1519,7 @@ DEFINE_GCM_ALGS(aesni_avx, FLAG_AVX,
 		"generic-gcm-aesni-avx", "rfc4106-gcm-aesni-avx",
 		AES_GCM_KEY_AESNI_SIZE, 500);
 
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 /* aes_gcm_algs_vaes_avx10_256 */
 DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256,
 		"generic-gcm-vaes-avx10_256", "rfc4106-gcm-vaes-avx10_256",
@@ -1529,7 +1529,7 @@ DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256,
 DEFINE_GCM_ALGS(vaes_avx10_512, FLAG_AVX10_512,
 		"generic-gcm-vaes-avx10_512", "rfc4106-gcm-vaes-avx10_512",
 		AES_GCM_KEY_AVX10_SIZE, 800);
-#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+#endif /* CONFIG_AS_VPCLMULQDQ */
 
 static int __init register_avx_algs(void)
 {
@@ -1551,7 +1551,7 @@ static int __init register_avx_algs(void)
 	 * Similarly, the assembler support was added at about the same time.
 	 * For simplicity, just always check for VAES and VPCLMULQDQ together.
 	 */
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
 	    !boot_cpu_has(X86_FEATURE_VAES) ||
 	    !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) ||
@@ -1592,7 +1592,7 @@ static int __init register_avx_algs(void)
 				    ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512));
 	if (err)
 		return err;
-#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+#endif /* CONFIG_AS_VPCLMULQDQ */
 	return 0;
 }
 
@@ -1607,7 +1607,7 @@ static void unregister_avx_algs(void)
 {
 	unregister_skciphers(skcipher_algs_aesni_avx);
 	unregister_aeads(aes_gcm_algs_aesni_avx);
-#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+#if defined(CONFIG_AS_VPCLMULQDQ)
 	unregister_skciphers(skcipher_algs_vaes_avx2);
 	unregister_skciphers(skcipher_algs_vaes_avx512);
 	unregister_aeads(aes_gcm_algs_vaes_avx10_256);

From e084e9f8151f1d37b085317752d36b4fa2fec9b9 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 19 Aug 2025 10:57:51 +0200
Subject: [PATCH 020/352] crypto: x86 - Remove CONFIG_AS_VPCLMULQDQ

Current minimum required version of binutils is 2.30, which supports VPCLMULQDQ
instruction mnemonics.

Remove check for assembler support of VPCLMULQDQ instructions and all relevant
macros for conditional compilation.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/20250819085855.333380-3-ubizjak@gmail.com
---
 arch/x86/Kconfig.assembler           |  5 -----
 arch/x86/crypto/Makefile             |  6 ++----
 arch/x86/crypto/aes-ctr-avx-x86_64.S |  2 --
 arch/x86/crypto/aes-xts-avx-x86_64.S |  2 --
 arch/x86/crypto/aesni-intel_glue.c   | 22 +++-------------------
 5 files changed, 5 insertions(+), 32 deletions(-)

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 8d1808407674..ea0e9dfdfc5c 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,11 +6,6 @@ config AS_AVX512
 	help
 	  Supported by binutils >= 2.25 and LLVM integrated assembler
 
-config AS_VPCLMULQDQ
-	def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2)
-	help
-	  Supported by binutils >= 2.30 and LLVM integrated assembler
-
 config AS_WRUSS
 	def_bool $(as-instr64,wrussq %rax$(comma)(%rbx))
 	help
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 50f1c0414c00..419252db968c 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -46,10 +46,8 @@ obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
 aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \
 			       aes-gcm-aesni-x86_64.o \
-			       aes-xts-avx-x86_64.o
-ifeq ($(CONFIG_AS_VPCLMULQDQ),y)
-aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o
-endif
+			       aes-xts-avx-x86_64.o \
+			       aes-gcm-avx10-x86_64.o
 
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
diff --git a/arch/x86/crypto/aes-ctr-avx-x86_64.S b/arch/x86/crypto/aes-ctr-avx-x86_64.S
index ec957b25b062..2745918f68ee 100644
--- a/arch/x86/crypto/aes-ctr-avx-x86_64.S
+++ b/arch/x86/crypto/aes-ctr-avx-x86_64.S
@@ -552,7 +552,6 @@ SYM_TYPED_FUNC_START(aes_xctr_crypt_aesni_avx)
 	_aes_ctr_crypt	1
 SYM_FUNC_END(aes_xctr_crypt_aesni_avx)
 
-#if defined(CONFIG_AS_VPCLMULQDQ)
 .set	VL, 32
 .set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx2)
@@ -570,4 +569,3 @@ SYM_FUNC_END(aes_ctr64_crypt_vaes_avx512)
 SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx512)
 	_aes_ctr_crypt	1
 SYM_FUNC_END(aes_xctr_crypt_vaes_avx512)
-#endif // CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index e44e56817d82..a30753a3e207 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -886,7 +886,6 @@ SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx)
 	_aes_xts_crypt	0
 SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
 
-#if defined(CONFIG_AS_VPCLMULQDQ)
 .set	VL, 32
 .set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
@@ -904,4 +903,3 @@ SYM_FUNC_END(aes_xts_encrypt_vaes_avx512)
 SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx512)
 	_aes_xts_crypt	0
 SYM_FUNC_END(aes_xts_decrypt_vaes_avx512)
-#endif /* CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index d5a2f5b2c01b..d953ac470aae 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -828,10 +828,8 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{		       \
 }}
 
 DEFINE_AVX_SKCIPHER_ALGS(aesni_avx, "aesni-avx", 500);
-#if defined(CONFIG_AS_VPCLMULQDQ)
 DEFINE_AVX_SKCIPHER_ALGS(vaes_avx2, "vaes-avx2", 600);
 DEFINE_AVX_SKCIPHER_ALGS(vaes_avx512, "vaes-avx512", 800);
-#endif
 
 /* The common part of the x86_64 AES-GCM key struct */
 struct aes_gcm_key {
@@ -912,17 +910,8 @@ struct aes_gcm_key_avx10 {
 #define FLAG_RFC4106	BIT(0)
 #define FLAG_ENC	BIT(1)
 #define FLAG_AVX	BIT(2)
-#if defined(CONFIG_AS_VPCLMULQDQ)
-#  define FLAG_AVX10_256	BIT(3)
-#  define FLAG_AVX10_512	BIT(4)
-#else
-   /*
-    * This should cause all calls to the AVX10 assembly functions to be
-    * optimized out, avoiding the need to ifdef each call individually.
-    */
-#  define FLAG_AVX10_256	0
-#  define FLAG_AVX10_512	0
-#endif
+#define FLAG_AVX10_256	BIT(3)
+#define FLAG_AVX10_512	BIT(4)
 
 static inline struct aes_gcm_key *
 aes_gcm_key_get(struct crypto_aead *tfm, int flags)
@@ -1519,7 +1508,6 @@ DEFINE_GCM_ALGS(aesni_avx, FLAG_AVX,
 		"generic-gcm-aesni-avx", "rfc4106-gcm-aesni-avx",
 		AES_GCM_KEY_AESNI_SIZE, 500);
 
-#if defined(CONFIG_AS_VPCLMULQDQ)
 /* aes_gcm_algs_vaes_avx10_256 */
 DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256,
 		"generic-gcm-vaes-avx10_256", "rfc4106-gcm-vaes-avx10_256",
@@ -1529,7 +1517,6 @@ DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256,
 DEFINE_GCM_ALGS(vaes_avx10_512, FLAG_AVX10_512,
 		"generic-gcm-vaes-avx10_512", "rfc4106-gcm-vaes-avx10_512",
 		AES_GCM_KEY_AVX10_SIZE, 800);
-#endif /* CONFIG_AS_VPCLMULQDQ */
 
 static int __init register_avx_algs(void)
 {
@@ -1551,7 +1538,6 @@ static int __init register_avx_algs(void)
 	 * Similarly, the assembler support was added at about the same time.
 	 * For simplicity, just always check for VAES and VPCLMULQDQ together.
 	 */
-#if defined(CONFIG_AS_VPCLMULQDQ)
 	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
 	    !boot_cpu_has(X86_FEATURE_VAES) ||
 	    !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) ||
@@ -1592,7 +1578,7 @@ static int __init register_avx_algs(void)
 				    ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512));
 	if (err)
 		return err;
-#endif /* CONFIG_AS_VPCLMULQDQ */
+
 	return 0;
 }
 
@@ -1607,12 +1593,10 @@ static void unregister_avx_algs(void)
 {
 	unregister_skciphers(skcipher_algs_aesni_avx);
 	unregister_aeads(aes_gcm_algs_aesni_avx);
-#if defined(CONFIG_AS_VPCLMULQDQ)
 	unregister_skciphers(skcipher_algs_vaes_avx2);
 	unregister_skciphers(skcipher_algs_vaes_avx512);
 	unregister_aeads(aes_gcm_algs_vaes_avx10_256);
 	unregister_aeads(aes_gcm_algs_vaes_avx10_512);
-#endif
 }
 #else /* CONFIG_X86_64 */
 static struct aead_alg aes_gcm_algs_aesni[0];

From ae7c0996c0e0f7d3bd3665020e1fbb4d99b7373e Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 19 Aug 2025 10:57:52 +0200
Subject: [PATCH 021/352] x86/kconfig: Remove CONFIG_AS_AVX512

Commit

  5f5305dea066 ("raid6: skip avx512 checks")

and commit

  bc23fe6dc172 ("crypto: x86 - Remove CONFIG_AS_AVX512 handling")

removed all uses of CONFIG_AS_AVX512.

Remove check for assembler support of AVX-512 instructions.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250819085855.333380-4-ubizjak@gmail.com
---
 arch/x86/Kconfig.assembler | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index ea0e9dfdfc5c..b1c59fb0a4c9 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -1,11 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
 
-config AS_AVX512
-	def_bool $(as-instr,vpmovm2b %k1$(comma)%zmm5)
-	help
-	  Supported by binutils >= 2.25 and LLVM integrated assembler
-
 config AS_WRUSS
 	def_bool $(as-instr64,wrussq %rax$(comma)(%rbx))
 	help

From 5be502174bf0f5d0aafaab57fa4512723d6d2973 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Fri, 22 Aug 2025 00:16:44 -0700
Subject: [PATCH 022/352] x86/entry/fred: Push __KERNEL_CS directly

Push __KERNEL_CS directly, rather than moving it into RAX and then
pushing RAX.

No functional changes.

Suggested-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250822071644.1405268-1-xin@zytor.com
---
 arch/x86/entry/entry_64_fred.S | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index 29c5c32c16c3..cb5ff2b1f6e7 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -97,8 +97,7 @@ SYM_FUNC_START(asm_fred_entry_from_kvm)
 	push %rdi			/* fred_ss handed in by the caller */
 	push %rbp
 	pushf
-	mov $__KERNEL_CS, %rax
-	push %rax
+	push $__KERNEL_CS
 
 	/*
 	 * Unlike the IDT event delivery, FRED _always_ pushes an error code

From d20a5d96eddb95b4faa33247ec653a580c48fdfa Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 16 Jun 2025 10:30:41 +0200
Subject: [PATCH 023/352] x86/idle: Use MONITORX and MWAITX mnemonics in
 <asm/mwait.h>

Current minimum required version of binutils is 2.30, which supports MONITORX
and MWAITX instruction mnemonics.

Replace the byte-wise specification of MONITORX and MWAITX with these proper
mnemonics.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250616083056.157460-1-ubizjak@gmail.com
---
 arch/x86/include/asm/mwait.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 6ca6516c7492..e4815e15dc9a 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -36,9 +36,7 @@ static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
 
 static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitorx %eax, %ecx, %edx" */
-	asm volatile(".byte 0x0f, 0x01, 0xfa"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	asm volatile("monitorx" :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
 static __always_inline void __mwait(u32 eax, u32 ecx)
@@ -80,9 +78,7 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
 	/* No need for TSA buffer clearing on AMD */
 
-	/* "mwaitx %eax, %ebx, %ecx" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb"
-		     :: "a" (eax), "b" (ebx), "c" (ecx));
+	asm volatile("mwaitx" :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
 /*

From 966f504977e3a04fcadbaf199e3302e95e8958b7 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 16 Jun 2025 10:35:57 +0200
Subject: [PATCH 024/352] x86/asm: Use RDPKRU and WRPKRU mnemonics in
 <asm/special_insns.h>

Current minimum required version of binutils is 2.30, which supports RDPKRU and
WRPKRU instruction mnemonics.

Replace the byte-wise specification of RDPKRU and WRPKRU with these proper
mnemonics.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/20250616083611.157740-1-ubizjak@gmail.com
---
 arch/x86/include/asm/special_insns.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index fde2bd7af19e..c99914569352 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -75,9 +75,7 @@ static inline u32 rdpkru(void)
 	 * "rdpkru" instruction.  Places PKRU contents in to EAX,
 	 * clears EDX and requires that ecx=0.
 	 */
-	asm volatile(".byte 0x0f,0x01,0xee\n\t"
-		     : "=a" (pkru), "=d" (edx)
-		     : "c" (ecx));
+	asm volatile("rdpkru" : "=a" (pkru), "=d" (edx) : "c" (ecx));
 	return pkru;
 }
 
@@ -89,8 +87,7 @@ static inline void wrpkru(u32 pkru)
 	 * "wrpkru" instruction.  Loads contents in EAX to PKRU,
 	 * requires that ecx = edx = 0.
 	 */
-	asm volatile(".byte 0x0f,0x01,0xef\n\t"
-		     : : "a" (pkru), "c"(ecx), "d"(edx));
+	asm volatile("wrpkru" : : "a" (pkru), "c"(ecx), "d"(edx));
 }
 
 #else

From 045f6a6e4dbaa0ecdee43bc2362676ff62ba5456 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 1 Aug 2025 10:45:31 +0200
Subject: [PATCH 025/352] x86/mtrr: Remove license boilerplate text with bad
 FSF address

The Free Software Foundation does not reside in "675 Mass Ave, Cambridge"
anymore, so no need to mention that address in the source code here.  But
instead of updating the address to their current location, just drop the
license boilerplate text and use a proper SPDX license identifier instead.  The
text talks about the "GNU *Library* General Public License" and "any later
version", so LGPL-2.0+ is the right choice here.

  [ bp: Massage commit message. ]

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250801084531.34089-1-thuth@redhat.com
---
 arch/x86/include/asm/mtrr.h        | 15 +--------------
 arch/x86/kernel/cpu/mtrr/cleanup.c | 15 +--------------
 arch/x86/kernel/cpu/mtrr/mtrr.c    | 15 +--------------
 3 files changed, 3 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index c69e269937c5..76b95bd1a405 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: LGPL-2.0+ */
 /*  Generic MTRR (Memory Type Range Register) ioctls.
 
     Copyright (C) 1997-1999  Richard Gooch
 
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Library General Public
-    License as published by the Free Software Foundation; either
-    version 2 of the License, or (at your option) any later version.
-
-    This library 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
-    Library General Public License for more details.
-
-    You should have received a copy of the GNU Library General Public
-    License along with this library; if not, write to the Free
-    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
     Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
     The postal address is:
       Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 18cf79d6e2c5..763534d77f59 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.0+
 /*
  * MTRR (Memory Type Range Register) cleanup
  *
  *  Copyright (C) 2009 Yinghai Lu
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Library General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library 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
- * Library General Public License for more details.
- *
- * You should have received a copy of the GNU Library General Public
- * License along with this library; if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/init.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index ecbda0341a8a..4b3d492afe17 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: LGPL-2.0+
 /*  Generic MTRR (Memory Type Range Register) driver.
 
     Copyright (C) 1997-2000  Richard Gooch
     Copyright (c) 2002	     Patrick Mochel
 
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Library General Public
-    License as published by the Free Software Foundation; either
-    version 2 of the License, or (at your option) any later version.
-
-    This library 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
-    Library General Public License for more details.
-
-    You should have received a copy of the GNU Library General Public
-    License along with this library; if not, write to the Free
-    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
     Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
     The postal address is:
       Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.

From 290434474c332a2ba9c8499fe699c7f2e1153280 Mon Sep 17 00:00:00 2001
From: Tingmao Wang <m@maowtm.org>
Date: Sun, 6 Apr 2025 17:18:42 +0100
Subject: [PATCH 026/352] fs/9p: Refresh metadata in d_revalidate for uncached
 mode too

Currently if another process keeps a file open, due to existing dentry in
the dcache, other processes will not see updated metadata of that file if
it is changed on the server, even in uncached mode.

This can also manifest as -ENODATA when reading a file that has shrunk on
the server (even if it's re-opened in another process), or -ENOTSUPP if
the file has changed type (e.g. regular file to directory) on the server.
We can end up in a situation where both `readdir` or `read` fails until
the file is closed by all processes using it.

This commit fixes that, and invalidates the dentry altogether if the inode
type is changed (for uncached mode).

Signed-off-by: Tingmao Wang <m@maowtm.org>
Message-ID: <bfac417f65cc1d6812be822f8913f0d4ba0c1052.1743956147.git.m@maowtm.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_dentry.c     | 11 ++++++++++-
 fs/9p/vfs_inode.c      |  8 +++++++-
 fs/9p/vfs_inode_dotl.c |  8 +++++++-
 3 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 04795508a795..ffa45ee38f83 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -66,6 +66,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	struct p9_fid *fid;
 	struct inode *inode;
 	struct v9fs_inode *v9inode;
+	unsigned int cached;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -75,7 +76,11 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_valid;
 
 	v9inode = V9FS_I(inode);
-	if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
+	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
+
+	cached = v9ses->cache & (CACHE_META | CACHE_LOOSE);
+
+	if (!cached || v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
 		int retval;
 		struct v9fs_session_info *v9ses;
 
@@ -92,6 +97,8 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 
 		if (retval == -ENOENT)
 			return 0;
+		if (!cached && v9inode->cache_validity & V9FS_INO_INVALID_ATTR)
+			return 0;
 		if (retval < 0)
 			return retval;
 	}
@@ -127,6 +134,8 @@ const struct dentry_operations v9fs_cached_dentry_operations = {
 };
 
 const struct dentry_operations v9fs_dentry_operations = {
+	.d_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = __v9fs_lookup_revalidate,
 	.d_release = v9fs_dentry_release,
 	.d_unalias_trylock = v9fs_dentry_unalias_trylock,
 	.d_unalias_unlock = v9fs_dentry_unalias_unlock,
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 399d455d50d6..caff65d8b2bb 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1349,8 +1349,14 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 	 * Don't update inode if the file type is different
 	 */
 	umode = p9mode2unixmode(v9ses, st, &rdev);
-	if (inode_wrong_type(inode, umode))
+	if (inode_wrong_type(inode, umode)) {
+		/*
+		 * Do this as a way of letting the caller know the inode should not
+		 * be reused
+		 */
+		v9fs_invalidate_inode_attr(inode);
 		goto out;
+	}
 
 	/*
 	 * We don't want to refresh inode->i_size,
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 5b5fda617b80..0fafc603b64a 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -902,8 +902,14 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
 	/*
 	 * Don't update inode if the file type is different
 	 */
-	if (inode_wrong_type(inode, st->st_mode))
+	if (inode_wrong_type(inode, st->st_mode)) {
+		/*
+		 * Do this as a way of letting the caller know the inode should not
+		 * be reused
+		 */
+		v9fs_invalidate_inode_attr(inode);
 		goto out;
+	}
 
 	/*
 	 * We don't want to refresh inode->i_size,

From 0172a934747f21d2fca4870ec84518c97f5178fc Mon Sep 17 00:00:00 2001
From: Tingmao Wang <m@maowtm.org>
Date: Sun, 6 Apr 2025 17:18:43 +0100
Subject: [PATCH 027/352] fs/9p: Invalidate dentry if inode type change
 detected in cached mode

This is an extension of the last commit to cached mode as well.  While
server-side changes when using cached mode is not expected, when it does
happen we can get things like -EOPNOTSUPP.  With this change at least when
we realize the inode has updated (for example after a `touch` on the
client), we can get a new one.

Signed-off-by: Tingmao Wang <m@maowtm.org>
Message-ID: <01afd3c77d5cda181780dc931baa8f3fc54562c8.1743956147.git.m@maowtm.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_dentry.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index ffa45ee38f83..ddf7424b5850 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -97,7 +97,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 
 		if (retval == -ENOENT)
 			return 0;
-		if (!cached && v9inode->cache_validity & V9FS_INO_INVALID_ATTR)
+		if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR)
 			return 0;
 		if (retval < 0)
 			return retval;

From c667c54c5875bf57641cd3bedc2cae66f2f08854 Mon Sep 17 00:00:00 2001
From: Tingmao Wang <m@maowtm.org>
Date: Sun, 6 Apr 2025 17:18:44 +0100
Subject: [PATCH 028/352] fs/9p: Add p9_debug(VFS) in d_revalidate

This was a useful debugging / validation aid, and can explain why a
GETATTR request is made.

Signed-off-by: Tingmao Wang <m@maowtm.org>
Message-ID: <00829a99549e33d26139fa4d756c466629f13e00.1743956147.git.m@maowtm.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/vfs_dentry.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index ddf7424b5850..f3248a3e5402 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -85,8 +85,13 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 		struct v9fs_session_info *v9ses;
 
 		fid = v9fs_fid_lookup(dentry);
-		if (IS_ERR(fid))
+		if (IS_ERR(fid)) {
+			p9_debug(
+				P9_DEBUG_VFS,
+				"v9fs_fid_lookup: dentry = %pd (%p), got error %pe\n",
+				dentry, dentry, fid);
 			return PTR_ERR(fid);
+		}
 
 		v9ses = v9fs_inode2v9ses(inode);
 		if (v9fs_proto_dotl(v9ses))
@@ -95,14 +100,25 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 			retval = v9fs_refresh_inode(fid, inode);
 		p9_fid_put(fid);
 
-		if (retval == -ENOENT)
+		if (retval == -ENOENT) {
+			p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) invalidated due to ENOENT\n",
+				 dentry, dentry);
 			return 0;
-		if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR)
+		}
+		if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
+			p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) invalidated due to type change\n",
+				 dentry, dentry);
 			return 0;
-		if (retval < 0)
+		}
+		if (retval < 0) {
+			p9_debug(P9_DEBUG_VFS,
+				"refresh inode: dentry = %pd (%p), got error %pe\n",
+				dentry, dentry, ERR_PTR(retval));
 			return retval;
+		}
 	}
 out_valid:
+	p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) is valid\n", dentry, dentry);
 	return 1;
 }
 

From c04db81cd0288dfc68b7a0f7d09bd49b40bba451 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Sun, 22 Jun 2025 22:39:56 +0900
Subject: [PATCH 029/352] net/9p: Fix buffer overflow in USB transport layer

A buffer overflow vulnerability exists in the USB 9pfs transport layer
where inconsistent size validation between packet header parsing and
actual data copying allows a malicious USB host to overflow heap buffers.

The issue occurs because:
- usb9pfs_rx_header() validates only the declared size in packet header
- usb9pfs_rx_complete() uses req->actual (actual received bytes) for
memcpy

This allows an attacker to craft packets with small declared size
(bypassing validation) but large actual payload (triggering overflow
in memcpy).

Add validation in usb9pfs_rx_complete() to ensure req->actual does not
exceed the buffer capacity before copying data.

Reported-by: Yuhao Jiang <danisjiang@gmail.com>
Closes: https://lkml.kernel.org/r/20250616132539.63434-1-danisjiang@gmail.com
Fixes: a3be076dc174 ("net/9p/usbg: Add new usb gadget function transport")
Cc: stable@vger.kernel.org
Message-ID: <20250622-9p-usb_overflow-v3-1-ab172691b946@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 net/9p/trans_usbg.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/9p/trans_usbg.c b/net/9p/trans_usbg.c
index 6b694f117aef..468f7e8f0277 100644
--- a/net/9p/trans_usbg.c
+++ b/net/9p/trans_usbg.c
@@ -231,6 +231,8 @@ static void usb9pfs_rx_complete(struct usb_ep *ep, struct usb_request *req)
 	struct f_usb9pfs *usb9pfs = ep->driver_data;
 	struct usb_composite_dev *cdev = usb9pfs->function.config->cdev;
 	struct p9_req_t *p9_rx_req;
+	unsigned int req_size = req->actual;
+	int status = REQ_STATUS_RCVD;
 
 	if (req->status) {
 		dev_err(&cdev->gadget->dev, "%s usb9pfs complete --> %d, %d/%d\n",
@@ -242,11 +244,19 @@ static void usb9pfs_rx_complete(struct usb_ep *ep, struct usb_request *req)
 	if (!p9_rx_req)
 		return;
 
-	memcpy(p9_rx_req->rc.sdata, req->buf, req->actual);
+	if (req_size > p9_rx_req->rc.capacity) {
+		dev_err(&cdev->gadget->dev,
+			"%s received data size %u exceeds buffer capacity %zu\n",
+			ep->name, req_size, p9_rx_req->rc.capacity);
+		req_size = 0;
+		status = REQ_STATUS_ERROR;
+	}
 
-	p9_rx_req->rc.size = req->actual;
+	memcpy(p9_rx_req->rc.sdata, req->buf, req_size);
 
-	p9_client_cb(usb9pfs->client, p9_rx_req, REQ_STATUS_RCVD);
+	p9_rx_req->rc.size = req_size;
+
+	p9_client_cb(usb9pfs->client, p9_rx_req, status);
 	p9_req_put(usb9pfs->client, p9_rx_req);
 
 	complete(&usb9pfs->received);

From 674b56aa57f9379854cb6798c3bbcef7e7b51ab7 Mon Sep 17 00:00:00 2001
From: Nalivayko Sergey <Sergey.Nalivayko@kaspersky.com>
Date: Tue, 15 Jul 2025 18:48:15 +0300
Subject: [PATCH 030/352] net/9p: fix double req put in p9_fd_cancelled

Syzkaller reports a KASAN issue as below:

general protection fault, probably for non-canonical address 0xfbd59c0000000021: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: maybe wild-memory-access in range [0xdead000000000108-0xdead00000000010f]
CPU: 0 PID: 5083 Comm: syz-executor.2 Not tainted 6.1.134-syzkaller-00037-g855bd1d7d838 #0
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
RIP: 0010:__list_del include/linux/list.h:114 [inline]
RIP: 0010:__list_del_entry include/linux/list.h:137 [inline]
RIP: 0010:list_del include/linux/list.h:148 [inline]
RIP: 0010:p9_fd_cancelled+0xe9/0x200 net/9p/trans_fd.c:734

Call Trace:
 <TASK>
 p9_client_flush+0x351/0x440 net/9p/client.c:614
 p9_client_rpc+0xb6b/0xc70 net/9p/client.c:734
 p9_client_version net/9p/client.c:920 [inline]
 p9_client_create+0xb51/0x1240 net/9p/client.c:1027
 v9fs_session_init+0x1f0/0x18f0 fs/9p/v9fs.c:408
 v9fs_mount+0xba/0xcb0 fs/9p/vfs_super.c:126
 legacy_get_tree+0x108/0x220 fs/fs_context.c:632
 vfs_get_tree+0x8e/0x300 fs/super.c:1573
 do_new_mount fs/namespace.c:3056 [inline]
 path_mount+0x6a6/0x1e90 fs/namespace.c:3386
 do_mount fs/namespace.c:3399 [inline]
 __do_sys_mount fs/namespace.c:3607 [inline]
 __se_sys_mount fs/namespace.c:3584 [inline]
 __x64_sys_mount+0x283/0x300 fs/namespace.c:3584
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x35/0x80 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

This happens because of a race condition between:

- The 9p client sending an invalid flush request and later cleaning it up;
- The 9p client in p9_read_work() canceled all pending requests.

      Thread 1                              Thread 2
    ...
    p9_client_create()
    ...
    p9_fd_create()
    ...
    p9_conn_create()
    ...
    // start Thread 2
    INIT_WORK(&m->rq, p9_read_work);
                                        p9_read_work()
    ...
    p9_client_rpc()
    ...
                                        ...
                                        p9_conn_cancel()
                                        ...
                                        spin_lock(&m->req_lock);
    ...
    p9_fd_cancelled()
    ...
                                        ...
                                        spin_unlock(&m->req_lock);
                                        // status rewrite
                                        p9_client_cb(m->client, req, REQ_STATUS_ERROR)
                                        // first remove
                                        list_del(&req->req_list);
                                        ...

    spin_lock(&m->req_lock)
    ...
    // second remove
    list_del(&req->req_list);
    spin_unlock(&m->req_lock)
  ...

Commit 74d6a5d56629 ("9p/trans_fd: Fix concurrency del of req_list in
p9_fd_cancelled/p9_read_work") fixes a concurrency issue in the 9p filesystem
client where the req_list could be deleted simultaneously by both
p9_read_work and p9_fd_cancelled functions, but for the case where req->status
equals REQ_STATUS_RCVD.

Update the check for req->status in p9_fd_cancelled to skip processing not
just received requests, but anything that is not SENT, as whatever
changed the state from SENT also removed the request from its list.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: afd8d6541155 ("9P: Add cancelled() to the transport functions.")
Cc: stable@vger.kernel.org
Signed-off-by: Nalivayko Sergey <Sergey.Nalivayko@kaspersky.com>
Message-ID: <20250715154815.3501030-1-Sergey.Nalivayko@kaspersky.com>
[updated the check from status == RECV || status == ERROR to status != SENT]
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 net/9p/trans_fd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 339ec4e54778..8992d8bebbdd 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -726,10 +726,10 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
 	spin_lock(&m->req_lock);
-	/* Ignore cancelled request if message has been received
-	 * before lock.
-	 */
-	if (req->status == REQ_STATUS_RCVD) {
+	/* Ignore cancelled request if status changed since the request was
+	 * processed in p9_client_flush()
+	*/
+	if (req->status != REQ_STATUS_SENT) {
 		spin_unlock(&m->req_lock);
 		return 0;
 	}

From 13bdfb53aa04eeb8022af87288c5bc0a5d13a834 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 16 Jun 2025 10:56:30 +0200
Subject: [PATCH 031/352] x86/sgx: Use ENCLS mnemonic in
 <kernel/cpu/sgx/encls.h>

Current minimum required version of binutils is 2.30, which supports ENCLS
instruction mnemonic.

Replace the byte-wise specification of ENCLS with this proper mnemonic.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/20250616085716.158942-1-ubizjak@gmail.com
---
 arch/x86/kernel/cpu/sgx/encls.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h
index 99004b02e2ed..42a088a337c5 100644
--- a/arch/x86/kernel/cpu/sgx/encls.h
+++ b/arch/x86/kernel/cpu/sgx/encls.h
@@ -68,7 +68,7 @@ static inline bool encls_failed(int ret)
 	({							\
 	int ret;						\
 	asm volatile(						\
-	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
+	"1: encls\n"						\
 	"2:\n"							\
 	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret)						\
@@ -111,8 +111,8 @@ static inline bool encls_failed(int ret)
 	({							\
 	int ret;						\
 	asm volatile(						\
-	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
-	"   xor %%eax,%%eax;\n"					\
+	"1: encls\n\t"						\
+	"xor %%eax,%%eax\n"					\
 	"2:\n"							\
 	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret), "=b"(rbx_out)				\

From 5d5f08fd0cd970184376bee07d59f635c8403f63 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Fri, 29 Aug 2025 16:30:15 +0800
Subject: [PATCH 032/352] xtensa: simdisk: add input size check in
 proc_write_simdisk

A malicious user could pass an arbitrarily bad value
to memdup_user_nul(), potentially causing kernel crash.

This follows the same pattern as commit ee76746387f6
("netdevsim: prevent bad user input in nsim_dev_health_break_write()")

Fixes: b6c7e873daf7 ("xtensa: ISS: add host file-based simulated disk")
Fixes: 16e5c1fc3604 ("convert a bunch of open-coded instances of memdup_user_nul()")
Cc: stable@vger.kernel.org
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Message-Id: <20250829083015.1992751-1-linmq006@gmail.com>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/platforms/iss/simdisk.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 6ed009318d24..3cafc8feddee 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -231,10 +231,14 @@ static ssize_t proc_read_simdisk(struct file *file, char __user *buf,
 static ssize_t proc_write_simdisk(struct file *file, const char __user *buf,
 			size_t count, loff_t *ppos)
 {
-	char *tmp = memdup_user_nul(buf, count);
+	char *tmp;
 	struct simdisk *dev = pde_data(file_inode(file));
 	int err;
 
+	if (count == 0 || count > PAGE_SIZE)
+		return -EINVAL;
+
+	tmp = memdup_user_nul(buf, count);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
 

From 038c7dc66e2744e5df57163b8f957745ae10d23e Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:40 -0700
Subject: [PATCH 033/352] compiler_types.h: Move __nocfi out of
 compiler-specific header

Prepare for GCC KCFI support and move the __nocfi attribute from
compiler-clang.h to compiler_types.h. This was already gated by
CONFIG_CFI_CLANG, so this remains safe for non-KCFI GCC builds.

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-1-kees@kernel.org
---
 include/linux/compiler-clang.h | 5 -----
 include/linux/compiler_types.h | 4 +++-
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index fa4ffe037bc7..7a4568e421dc 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -96,11 +96,6 @@
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
-#if __has_feature(kcfi)
-/* Disable CFI checking inside a function. */
-#define __nocfi		__attribute__((__no_sanitize__("kcfi")))
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 16755431fc11..a910f9fa5341 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -432,7 +432,9 @@ struct ftrace_likely_data {
 # define __noscs
 #endif
 
-#ifndef __nocfi
+#if defined(CONFIG_CFI_CLANG)
+# define __nocfi		__attribute__((__no_sanitize__("kcfi")))
+#else
 # define __nocfi
 #endif
 

From 628a15e0536abb7658cd243553312d3f65c0aff2 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:41 -0700
Subject: [PATCH 034/352] x86/traps: Clarify KCFI instruction layout

Just a nit-picky change to the KCFI indirect call check instruction
documentation. The addl offset isn't always -4 (it depends on patchable
function entry configuration).

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-2-kees@kernel.org
---
 arch/x86/kernel/cfi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index 77086cf565ec..638eb5c933e0 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -27,7 +27,7 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
 	 * for indirect call checks:
 	 *
 	 *   movl    -<id>, %r10d       ; 6 bytes
-	 *   addl    -4(%reg), %r10d    ; 4 bytes
+	 *   addl    -<pos>(%reg), %r10d; 4 bytes
 	 *   je      .Ltmp1             ; 2 bytes
 	 *   ud2                        ; <- regs->ip
 	 *   .Ltmp1:

From 24452d9ef17502965021ce5df30f4e184245a5ac Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:42 -0700
Subject: [PATCH 035/352] x86/cfi: Document the "cfi=" bootparam options

The kernel-parameters.txt didn't have a section for the cfi= options.
Add it.

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-3-kees@kernel.org
---
 Documentation/admin-guide/kernel-parameters.txt | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 747a55abf494..8bbffbb334ab 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -608,6 +608,23 @@
 	ccw_timeout_log	[S390]
 			See Documentation/arch/s390/common_io.rst for details.
 
+	cfi=		[X86-64] Set Control Flow Integrity checking features
+			when CONFIG_FINEIBT is enabled.
+			Format: feature[,feature...]
+			Default: auto
+
+			auto:	  Use FineIBT if IBT available, otherwise kCFI.
+				  Under FineIBT, enable "paranoid" mode when
+				  FRED is not available.
+			off:	  Turn off CFI checking.
+			kcfi:	  Use kCFI (disable FineIBT).
+			fineibt:  Use FineIBT (even if IBT not available).
+			norand:   Do not re-randomize CFI hashes.
+			paranoid: Add caller hash checking under FineIBT.
+			bhi:	  Enable register poisoning to stop speculation
+				  across FineIBT. (Disabled by default.)
+			warn:	  Do not enforce CFI checking: warn only.
+
 	cgroup_disable=	[KNL] Disable a particular controller or optional feature
 			Format: {name of the controller(s) or feature(s) to disable}
 			The effects of cgroup_disable=foo are:

From 9f303a35d1df27cdc7b895b077985b0e1c4473c2 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:43 -0700
Subject: [PATCH 036/352] x86/cfi: Standardize on common "CFI:" prefix for CFI
 reports

Use a regular "CFI:" prefix for CFI reports during alternatives setup,
including reporting when nothing has happened (i.e. CONFIG_FINEIBT=n).

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-4-kees@kernel.org
---
 arch/x86/kernel/alternative.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7bde68247b5f..d8f4ac95b4df 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1266,26 +1266,26 @@ static __init int cfi_parse_cmdline(char *str)
 		} else if (!strcmp(str, "norand")) {
 			cfi_rand = false;
 		} else if (!strcmp(str, "warn")) {
-			pr_alert("CFI mismatch non-fatal!\n");
+			pr_alert("CFI: mismatch non-fatal!\n");
 			cfi_warn = true;
 		} else if (!strcmp(str, "paranoid")) {
 			if (cfi_mode == CFI_FINEIBT) {
 				cfi_paranoid = true;
 			} else {
-				pr_err("Ignoring paranoid; depends on fineibt.\n");
+				pr_err("CFI: ignoring paranoid; depends on fineibt.\n");
 			}
 		} else if (!strcmp(str, "bhi")) {
 #ifdef CONFIG_FINEIBT_BHI
 			if (cfi_mode == CFI_FINEIBT) {
 				cfi_bhi = true;
 			} else {
-				pr_err("Ignoring bhi; depends on fineibt.\n");
+				pr_err("CFI: ignoring bhi; depends on fineibt.\n");
 			}
 #else
-			pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n");
+			pr_err("CFI: ignoring bhi; depends on FINEIBT_BHI=y.\n");
 #endif
 		} else {
-			pr_err("Ignoring unknown cfi option (%s).", str);
+			pr_err("CFI: Ignoring unknown option (%s).", str);
 		}
 
 		str = next;
@@ -1757,7 +1757,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	switch (cfi_mode) {
 	case CFI_OFF:
 		if (builtin)
-			pr_info("Disabling CFI\n");
+			pr_info("CFI: disabled\n");
 		return;
 
 	case CFI_KCFI:
@@ -1766,7 +1766,8 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			goto err;
 
 		if (builtin)
-			pr_info("Using kCFI\n");
+			pr_info("CFI: Using %sretpoline kCFI\n",
+				cfi_rand ? "rehashed " : "");
 		return;
 
 	case CFI_FINEIBT:
@@ -2005,6 +2006,8 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
+	if (IS_ENABLED(CONFIG_CFI) && builtin)
+		pr_info("CFI: Using standard kCFI\n");
 }
 
 #ifdef CONFIG_X86_KERNEL_IBT

From 026211c40b055485b4c65c10d644a92864623225 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:44 -0700
Subject: [PATCH 037/352] x86/cfi: Add "debug" option to "cfi=" bootparam

Add "debug" option for "cfi=" bootparam to get details on early CFI
initialization steps so future Kees can find breakage easier.

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-5-kees@kernel.org
---
 Documentation/admin-guide/kernel-parameters.txt |  1 +
 arch/x86/kernel/alternative.c                   | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8bbffbb334ab..c8337d0e6ba3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -624,6 +624,7 @@
 			bhi:	  Enable register poisoning to stop speculation
 				  across FineIBT. (Disabled by default.)
 			warn:	  Do not enforce CFI checking: warn only.
+			debug:    Report CFI initialization details.
 
 	cgroup_disable=	[KNL] Disable a particular controller or optional feature
 			Format: {name of the controller(s) or feature(s) to disable}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index d8f4ac95b4df..7d4a992dadc3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1177,6 +1177,7 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+static bool cfi_debug __ro_after_init;
 
 #ifdef CONFIG_FINEIBT_BHI
 bool cfi_bhi __ro_after_init = false;
@@ -1259,6 +1260,8 @@ static __init int cfi_parse_cmdline(char *str)
 		} else if (!strcmp(str, "off")) {
 			cfi_mode = CFI_OFF;
 			cfi_rand = false;
+		} else if (!strcmp(str, "debug")) {
+			cfi_debug = true;
 		} else if (!strcmp(str, "kcfi")) {
 			cfi_mode = CFI_KCFI;
 		} else if (!strcmp(str, "fineibt")) {
@@ -1707,6 +1710,8 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 	return 0;
 }
 
+#define pr_cfi_debug(X...) if (cfi_debug) pr_info(X)
+
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
@@ -1734,6 +1739,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	 * rewrite them. This disables all CFI. If this succeeds but any of the
 	 * later stages fails, we're without CFI.
 	 */
+	pr_cfi_debug("CFI: disabling all indirect call checking\n");
 	ret = cfi_disable_callers(start_retpoline, end_retpoline);
 	if (ret)
 		goto err;
@@ -1744,14 +1750,19 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			cfi_bpf_hash = cfi_rehash(cfi_bpf_hash);
 			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
 		}
+		pr_cfi_debug("CFI: cfi_seed: 0x%08x\n", cfi_seed);
 
+		pr_cfi_debug("CFI: rehashing all preambles\n");
 		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
+		pr_cfi_debug("CFI: rehashing all indirect calls\n");
 		ret = cfi_rand_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
+	} else {
+		pr_cfi_debug("CFI: rehashing disabled\n");
 	}
 
 	switch (cfi_mode) {
@@ -1761,6 +1772,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_KCFI:
+		pr_cfi_debug("CFI: re-enabling all indirect call checking\n");
 		ret = cfi_enable_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
@@ -1771,17 +1783,20 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_FINEIBT:
+		pr_cfi_debug("CFI: adding FineIBT to all preambles\n");
 		/* place the FineIBT preamble at func()-16 */
 		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
 		/* rewrite the callers to target func()-16 */
+		pr_cfi_debug("CFI: rewriting indirect call sites to use FineIBT\n");
 		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
 		/* now that nobody targets func()+0, remove ENDBR there */
+		pr_cfi_debug("CFI: removing old endbr insns\n");
 		cfi_rewrite_endbr(start_cfi, end_cfi);
 
 		if (builtin) {
@@ -2324,6 +2339,7 @@ void __init alternative_instructions(void)
 
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
 			__cfi_sites, __cfi_sites_end, true);
+	cfi_debug = false;
 
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since

From 0b815825b1b0bd6762ca028e9b6631b002efb7ca Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 3 Sep 2025 20:46:45 -0700
Subject: [PATCH 038/352] x86/cfi: Remove __noinitretpoline and __noretpoline

Commit 66f793099a63 ("x86/retpoline: Avoid retpolines for built-in __init
functions") disabled retpolines in __init sections (__noinitretpoline)
as a precaution against potential issues with retpolines in early boot,
but it has not been a problem in practice (i.e. see Clang below).

Commit 87358710c1fb ("x86/retpoline: Support retpoline builds with Clang")
narrowed this to only GCC, as Clang doesn't have per-function control
over retpoline emission. As such, Clang has been booting with retpolines
in __init since retpoline support was introduced.

Clang KCFI has been instrumenting __init since CFI was introduced.

With the introduction of KCFI for GCC, KCFI instrumentation with
retpolines disabled means that objtool does not construct .retpoline_sites
section entries for the non-retpoline KCFI calls. At boot, the KCFI
rehashing code, via __apply_fineibt(), misses all __init KCFI calls
(since they are not retpolines), resulting in immediate hash mismatches:
all preambles are rehashed (via .cfi_sites) and none of the __init call
sites are rehashed.

Remove __noinitretpoline since it provides no meaningful utility and
creates problems with CFI. Additionally remove __noretpoline since it
is now unused.

Alternatively, cfi_rand_callers() could walk the .kcfi_traps section which
is exactly the list of KCFI instrumentation sites. But it seems better to
have as few differences in common instruction sequences between compilers
as possible, so better to remove the special handling of retpolines in
__init for GCC.

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250904034656.3670313-6-kees@kernel.org
---
 include/linux/compiler-gcc.h | 4 ----
 include/linux/init.h         | 8 --------
 2 files changed, 12 deletions(-)

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 5d07c469b571..5de824a0b3d7 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -35,10 +35,6 @@
 	(typeof(ptr)) (__ptr + (off));					\
 })
 
-#ifdef CONFIG_MITIGATION_RETPOLINE
-#define __noretpoline __attribute__((__indirect_branch__("keep")))
-#endif
-
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 #define __latent_entropy __attribute__((latent_entropy))
 #endif
diff --git a/include/linux/init.h b/include/linux/init.h
index a60d32d227ee..17c1bc712e23 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -7,13 +7,6 @@
 #include <linux/stringify.h>
 #include <linux/types.h>
 
-/* Built-in __init functions needn't be compiled with retpoline */
-#if defined(__noretpoline) && !defined(MODULE)
-#define __noinitretpoline __noretpoline
-#else
-#define __noinitretpoline
-#endif
-
 /* These macros are used to mark some functions or 
  * initialized data (doesn't apply to uninitialized data)
  * as `initialization' functions. The kernel can take this
@@ -50,7 +43,6 @@
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
 #define __init		__section(".init.text") __cold __latent_entropy	\
-						__noinitretpoline	\
 						__no_kstack_erase
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")

From 85a2d4a890dce3cfc9c14aa91afc3dd7af8e3bf5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 1 Sep 2025 12:49:58 +0200
Subject: [PATCH 039/352] x86,ibt: Use UDB instead of 0xEA

A while ago [0] FineIBT started using the 0xEA instruction to raise #UD.
All existing parts will generate #UD in 64bit mode on that instruction.

However; Intel/AMD have not blessed using this instruction, it is on
their 'reserved' opcode list for future use.

Peter Anvin worked the committees and got use of 0xD6 blessed, it
shall be called UDB (per the next SDM or so), and it being a single
byte instruction is easy to slip into a single byte immediate -- as
is done by this very patch.

Reworking the FineIBT code to use UDB wasn't entirely trivial. Notably
the FineIBT-BHI1 case ran out of bytes. In order to condense the
encoding some it was required to move the hash register from R10D to
EAX (thanks hpa!).

Per the x86_64 ABI, RAX is used to pass the number of vector registers
for vararg function calls -- something that should not happen in the
kernel. More so, the kernel is built with -mskip-rax-setup, which
should leave RAX completely unused, allowing its re-use.

 [ For BPF; while the bpf2bpf tail-call uses RAX in its calling
   convention, that does not use CFI and is unaffected. Only the
   'regular' C->BPF transition is covered by CFI. ]

The ENDBR poison value is changed from 'OSP NOP3' to 'NOPL -42(%RAX)',
this is basically NOP4 but with UDB as its immediate. As such it is
still a non-standard NOP value unique to prior ENDBR sites, but now
also provides UDB.

Per Agner Fog's optimization guide, Jcc is assumed not-taken. That is,
the expected path should be the fallthrough case for improved
throughput.

Since the preamble now relies on the ENDBR poison to provide UDB, the
code is changed to write the poison right along with the initial
preamble -- this is possible because the ITS mitigation already
disabled IBT over rewriting the CFI scheme.

The scheme in detail:

Preamble:

  FineIBT			FineIBT-BHI1			FineIBT-BHI

  __cfi_\func:			__cfi_\func:			__cfi_\func:
    endbr			  endbr				  endbr
    subl       $0x12345678, %eax  subl      $0x12345678, %eax	  subl       $0x12345678, %eax
    jne.d32,np \func+3		  cmovne    %rax, %rdi		  cs cs call __bhi_args_N
                                  jne.d8,np \func+3
  \func:			\func:				\func:
    nopl       -42(%rax)	  nopl      -42(%rax)		  nopl       -42(%rax)

Notably there are 7 bytes available after the SUBL; this enables the
BHI1 case to fit without the nasty overlapping case it had previously.
The !BHI case uses Jcc.d32,np to consume all 7 bytes without the need
for an additional NOP, while the BHI case uses CS padding to align the
CALL with the end of the preamble such that it returns to \func+0.

Caller:

  FineIBT				Paranoid-FineIBT

  fineibt_caller:			fineibt_caller:
    mov     $0x12345678, %eax		  mov    $0x12345678, %eax
    lea     -10(%r11), %r11		  cmp    -0x11(%r11), %eax
    nop5				  cs lea -0x10(%r11), %r11
  retpoline:				retpoline:
    cs call __x86_indirect_thunk_r11	  jne    fineibt_caller+0xd
					  call   *%r11
					  nop

Notably this is before apply_retpolines() which will fix up the
retpoline call -- since all parts with IBT also have eIBRS (lets
ignore ITS). Typically the retpoline site is rewritten (when still
intact) into:

    call *%r11
    nop3

[0] 06926c6cdb95 ("x86/ibt: Optimize the FineIBT instruction sequence")

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250901191307.GI4067720@noisy.programming.kicks-ass.net
---
 arch/x86/include/asm/bug.h    |   9 +-
 arch/x86/include/asm/cfi.h    |  14 +--
 arch/x86/include/asm/ibt.h    |  10 +-
 arch/x86/kernel/alternative.c | 217 +++++++++++++++++++---------------
 arch/x86/kernel/traps.c       |   8 +-
 arch/x86/lib/bhi.S            |  58 ++++-----
 arch/x86/lib/retpoline.S      |   4 +-
 arch/x86/net/bpf_jit_comp.c   |   6 +-
 8 files changed, 178 insertions(+), 148 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 20fcb8507ad1..880ca15073ed 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -5,14 +5,19 @@
 #include <linux/stringify.h>
 #include <linux/instrumentation.h>
 #include <linux/objtool.h>
+#include <asm/asm.h>
 
 /*
  * Despite that some emulators terminate on UD2, we use it for WARN().
  */
-#define ASM_UD2		".byte 0x0f, 0x0b"
+#define ASM_UD2		_ASM_BYTES(0x0f, 0x0b)
 #define INSN_UD2	0x0b0f
 #define LEN_UD2		2
 
+#define ASM_UDB		_ASM_BYTES(0xd6)
+#define INSN_UDB	0xd6
+#define LEN_UDB		1
+
 /*
  * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
  */
@@ -26,7 +31,7 @@
 #define BUG_UD2			0xfffe
 #define BUG_UD1			0xfffd
 #define BUG_UD1_UBSAN		0xfffc
-#define BUG_EA			0xffea
+#define BUG_UDB			0xffd6
 #define BUG_LOCK		0xfff0
 
 #ifdef CONFIG_GENERIC_BUG
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 1751f1eb95ef..3fcfdd996962 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -71,12 +71,10 @@
  *
  * __cfi_foo:
  *   endbr64
- *   subl 0x12345678, %r10d
- *   jz   foo
- *   ud2
- *   nop
+ *   subl 0x12345678, %eax
+ *   jne.32,pn foo+3
  * foo:
- *   osp nop3			# was endbr64
+ *   nopl -42(%rax)		# was endbr64
  *   ... code here ...
  *   ret
  *
@@ -86,9 +84,9 @@
  * indirect caller:
  *   lea foo(%rip), %r11
  *   ...
- *   movl $0x12345678, %r10d
- *   subl $16, %r11
- *   nop4
+ *   movl $0x12345678, %eax
+ *   lea  -0x10(%r11), %r11
+ *   nop5
  *   call *%r11
  *
  */
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 28d845257303..5e45d6424722 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -59,10 +59,10 @@ static __always_inline __attribute_const__ u32 gen_endbr(void)
 static __always_inline __attribute_const__ u32 gen_endbr_poison(void)
 {
 	/*
-	 * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it
-	 * will be unique to (former) ENDBR sites.
+	 * 4 byte NOP that isn't NOP4, such that it will be unique to (former)
+	 * ENDBR sites. Additionally it carries UDB as immediate.
 	 */
-	return 0x001f0f66; /* osp nopl (%rax) */
+	return 0xd6401f0f; /* nopl -42(%rax) */
 }
 
 static inline bool __is_endbr(u32 val)
@@ -70,10 +70,6 @@ static inline bool __is_endbr(u32 val)
 	if (val == gen_endbr_poison())
 		return true;
 
-	/* See cfi_fineibt_bhi_preamble() */
-	if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
-		return true;
-
 	val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
 	return val == gen_endbr();
 }
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7d4a992dadc3..3d6a88443616 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -147,10 +147,10 @@ static void *its_init_thunk(void *thunk, int reg)
 		/*
 		 * When ITS uses indirect branch thunk the fineibt_paranoid
 		 * caller sequence doesn't fit in the caller site. So put the
-		 * remaining part of the sequence (<ea> + JNE) into the ITS
+		 * remaining part of the sequence (UDB + JNE) into the ITS
 		 * thunk.
 		 */
-		bytes[i++] = 0xea; /* invalid instruction */
+		bytes[i++] = 0xd6; /* UDB */
 		bytes[i++] = 0x75; /* JNE */
 		bytes[i++] = 0xfd;
 
@@ -163,7 +163,7 @@ static void *its_init_thunk(void *thunk, int reg)
 		reg -= 8;
 	}
 	bytes[i++] = 0xff;
-	bytes[i++] = 0xe0 + reg; /* jmp *reg */
+	bytes[i++] = 0xe0 + reg; /* JMP *reg */
 	bytes[i++] = 0xcc;
 
 	return thunk + offset;
@@ -970,7 +970,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 		case JMP32_INSN_OPCODE:
 			/* Check for cfi_paranoid + ITS */
 			dest = addr + insn.length + insn.immediate.value;
-			if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) {
+			if (dest[-1] == 0xd6 && (dest[0] & 0xf0) == 0x70) {
 				WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
 				continue;
 			}
@@ -1303,9 +1303,8 @@ early_param("cfi", cfi_parse_cmdline);
  *
  * __cfi_\func:					__cfi_\func:
  *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
- *	nop					     subl   $0x12345678,%r10d   // 7
- *	nop					     jne    __cfi_\func+6	// 2
- *	nop					     nop3			// 3
+ *	nop					     subl   $0x12345678,%eax    // 5
+ *	nop					     jne.d32,pn \func+3		// 7
  *	nop
  *	nop
  *	nop
@@ -1314,34 +1313,45 @@ early_param("cfi", cfi_parse_cmdline);
  *	nop
  *	nop
  *	nop
+ *	nop
+ * \func:					\func:
+ *	endbr64					     nopl -42(%rax)
  *
  *
  * caller:					caller:
- *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
+ *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%eax	// 5
  *	addl	$-15(%r11),%r10d	 // 4	     lea    -0x10(%r11),%r11	// 4
- *	je	1f			 // 2	     nop4			// 4
+ *	je	1f			 // 2	     nop5			// 5
  *	ud2				 // 2
  * 1:	cs call	__x86_indirect_thunk_r11 // 6	     call   *%r11; nop3;	// 6
  *
+ *
+ * Notably, the FineIBT sequences are crafted such that branches are presumed
+ * non-taken. This is based on Agner Fog's optimization manual, which states:
+ *
+ *  "Make conditional jumps most often not taken: The efficiency and throughput
+ *   for not-taken branches is better than for taken branches on most
+ *   processors. Therefore, it is good to place the most frequent branch first"
  */
 
 /*
  * <fineibt_preamble_start>:
  *  0:   f3 0f 1e fa             endbr64
- *  4:   41 81 <ea> 78 56 34 12  sub    $0x12345678, %r10d
- *  b:   75 f9                   jne    6 <fineibt_preamble_start+0x6>
- *  d:   0f 1f 00                nopl   (%rax)
+ *  4:   2d 78 56 34 12          sub    $0x12345678, %eax
+ *  9:   2e 0f 85 03 00 00 00    jne,pn 13 <fineibt_preamble_start+0x13>
+ * 10:   0f 1f 40 d6             nopl   -0x2a(%rax)
  *
- * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as
- * (bad) on x86_64 and raises #UD.
+ * Note that the JNE target is the 0xD6 byte inside the NOPL, this decodes as
+ * UDB on x86_64 and raises #UD.
  */
 asm(	".pushsection .rodata				\n"
 	"fineibt_preamble_start:			\n"
 	"	endbr64					\n"
-	"	subl	$0x12345678, %r10d		\n"
+	"	subl	$0x12345678, %eax		\n"
 	"fineibt_preamble_bhi:				\n"
-	"	jne	fineibt_preamble_start+6	\n"
-	ASM_NOP3
+	"	cs jne.d32 fineibt_preamble_start+0x13	\n"
+	"#fineibt_func:					\n"
+	"	nopl	-42(%rax)			\n"
 	"fineibt_preamble_end:				\n"
 	".popsection\n"
 );
@@ -1352,20 +1362,20 @@ extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
 #define fineibt_preamble_bhi  (fineibt_preamble_bhi - fineibt_preamble_start)
-#define fineibt_preamble_ud   6
-#define fineibt_preamble_hash 7
+#define fineibt_preamble_ud   0x13
+#define fineibt_preamble_hash 5
 
 /*
  * <fineibt_caller_start>:
- *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
- *  6:   4d 8d 5b f0             lea    -0x10(%r11), %r11
- *  a:   0f 1f 40 00             nopl   0x0(%rax)
+ *  0:   b8 78 56 34 12          mov    $0x12345678, %eax
+ *  5:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+ *  9:   0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
  */
 asm(	".pushsection .rodata			\n"
 	"fineibt_caller_start:			\n"
-	"	movl	$0x12345678, %r10d	\n"
+	"	movl	$0x12345678, %eax	\n"
 	"	lea	-0x10(%r11), %r11	\n"
-	ASM_NOP4
+	ASM_NOP5
 	"fineibt_caller_end:			\n"
 	".popsection				\n"
 );
@@ -1374,7 +1384,7 @@ extern u8 fineibt_caller_start[];
 extern u8 fineibt_caller_end[];
 
 #define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start)
-#define fineibt_caller_hash 2
+#define fineibt_caller_hash 1
 
 #define fineibt_caller_jmp (fineibt_caller_size - 2)
 
@@ -1391,9 +1401,9 @@ extern u8 fineibt_caller_end[];
  * of adding a load.
  *
  * <fineibt_paranoid_start>:
- *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
- *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
- *  a:   4d 8d 5b <f0>           lea    -0x10(%r11), %r11
+ *  0:   b8 78 56 34 12          mov    $0x12345678, %eax
+ *  5:   41 3b 43 f5             cmp    -0x11(%r11), %eax
+ *  9:   2e 4d 8d 5b <f0>        cs lea -0x10(%r11), %r11
  *  e:   75 fd                   jne    d <fineibt_paranoid_start+0xd>
  * 10:   41 ff d3                call   *%r11
  * 13:   90                      nop
@@ -1405,9 +1415,10 @@ extern u8 fineibt_caller_end[];
  */
 asm(	".pushsection .rodata				\n"
 	"fineibt_paranoid_start:			\n"
-	"	movl	$0x12345678, %r10d		\n"
-	"	cmpl	-9(%r11), %r10d			\n"
-	"	lea	-0x10(%r11), %r11		\n"
+	"	mov	$0x12345678, %eax		\n"
+	"	cmpl	-11(%r11), %eax			\n"
+	"	cs lea	-0x10(%r11), %r11		\n"
+	"#fineibt_caller_size:                          \n"
 	"	jne	fineibt_paranoid_start+0xd	\n"
 	"fineibt_paranoid_ind:				\n"
 	"	call	*%r11				\n"
@@ -1523,51 +1534,67 @@ static int cfi_rand_preamble(s32 *start, s32 *end)
 	return 0;
 }
 
+/*
+ * Inline the bhi-arity 1 case:
+ *
+ * __cfi_foo:
+ *  0: f3 0f 1e fa             endbr64
+ *  4: 2d 78 56 34 12          sub    $0x12345678, %eax
+ *  9: 49 0f 45 fa             cmovne %rax, %rdi
+ *  d: 2e 75 03                jne,pn    foo+0x3
+ *
+ * foo:
+ * 10: 0f 1f 40 <d6>           nopl -42(%rax)
+ *
+ * Notably, this scheme is incompatible with permissive CFI
+ * because the CMOVcc is unconditional and RDI will have been
+ * clobbered.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_bhi1_start:				\n"
+	"	cmovne %rax, %rdi			\n"
+	"	cs jne fineibt_bhi1_func + 0x3		\n"
+	"fineibt_bhi1_func:				\n"
+	"	nopl -42(%rax)				\n"
+	"fineibt_bhi1_end:				\n"
+	".popsection					\n"
+);
+
+extern u8 fineibt_bhi1_start[];
+extern u8 fineibt_bhi1_end[];
+
+#define fineibt_bhi1_size (fineibt_bhi1_end - fineibt_bhi1_start)
+
 static void cfi_fineibt_bhi_preamble(void *addr, int arity)
 {
+	u8 bytes[MAX_INSN_SIZE];
+
 	if (!arity)
 		return;
 
 	if (!cfi_warn && arity == 1) {
-		/*
-		 * Crazy scheme to allow arity-1 inline:
-		 *
-		 * __cfi_foo:
-		 *  0: f3 0f 1e fa             endbr64
-		 *  4: 41 81 <ea> 78 56 34 12  sub     0x12345678, %r10d
-		 *  b: 49 0f 45 fa             cmovne  %r10, %rdi
-		 *  f: 75 f5                   jne     __cfi_foo+6
-		 * 11: 0f 1f 00                nopl    (%rax)
-		 *
-		 * Code that direct calls to foo()+0, decodes the tail end as:
-		 *
-		 * foo:
-		 *  0: f5                      cmc
-		 *  1: 0f 1f 00                nopl    (%rax)
-		 *
-		 * which clobbers CF, but does not affect anything ABI
-		 * wise.
-		 *
-		 * Notably, this scheme is incompatible with permissive CFI
-		 * because the CMOVcc is unconditional and RDI will have been
-		 * clobbered.
-		 */
-		const u8 magic[9] = {
-			0x49, 0x0f, 0x45, 0xfa,
-			0x75, 0xf5,
-			BYTES_NOP3,
-		};
-
-		text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
-
+		text_poke_early(addr + fineibt_preamble_bhi,
+				fineibt_bhi1_start, fineibt_bhi1_size);
 		return;
 	}
 
-	text_poke_early(addr + fineibt_preamble_bhi,
-			text_gen_insn(CALL_INSN_OPCODE,
-				      addr + fineibt_preamble_bhi,
-				      __bhi_args[arity]),
-			CALL_INSN_SIZE);
+	/*
+	 * Replace the bytes at fineibt_preamble_bhi with a CALL instruction
+	 * that lines up exactly with the end of the preamble, such that the
+	 * return address will be foo+0.
+	 *
+	 * __cfi_foo:
+	 *  0: f3 0f 1e fa             endbr64
+	 *  4: 2d 78 56 34 12          sub    $0x12345678, %eax
+	 *  9: 2e 2e e8 DD DD DD DD    cs cs call __bhi_args[arity]
+	 */
+	bytes[0] = 0x2e;
+	bytes[1] = 0x2e;
+	__text_gen_insn(bytes + 2, CALL_INSN_OPCODE,
+			addr + fineibt_preamble_bhi + 2,
+			__bhi_args[arity], CALL_INSN_SIZE);
+
+	text_poke_early(addr + fineibt_preamble_bhi, bytes, 7);
 }
 
 static int cfi_rewrite_preamble(s32 *start, s32 *end)
@@ -1658,8 +1685,6 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
-	BUG_ON(fineibt_paranoid_size != 20);
-
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 		struct insn insn;
@@ -1712,13 +1737,18 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 
 #define pr_cfi_debug(X...) if (cfi_debug) pr_info(X)
 
+#define FINEIBT_WARN(_f, _v) \
+	WARN_ONCE((_f) != (_v), "FineIBT: " #_f " %ld != %d\n", _f, _v)
+
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
 	int ret;
 
-	if (WARN_ONCE(fineibt_preamble_size != 16,
-		      "FineIBT preamble wrong size: %ld", fineibt_preamble_size))
+	if (FINEIBT_WARN(fineibt_preamble_size, 20)			||
+	    FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20)	||
+	    FINEIBT_WARN(fineibt_caller_size, 14)			||
+	    FINEIBT_WARN(fineibt_paranoid_size, 20))
 		return;
 
 	if (cfi_mode == CFI_AUTO) {
@@ -1839,11 +1869,11 @@ static void poison_cfi(void *addr)
 
 		/*
 		 * __cfi_\func:
-		 *	osp nopl (%rax)
-		 *	subl	$0, %r10d
-		 *	jz	1f
-		 *	ud2
-		 * 1:	nop
+		 *	nopl	-42(%rax)
+		 *	sub	$0, %eax
+		 *	jne	\func+3
+		 * \func:
+		 *	nopl	-42(%rax)
 		 */
 		poison_endbr(addr);
 		poison_hash(addr + fineibt_preamble_hash);
@@ -1869,12 +1899,14 @@ static void poison_cfi(void *addr)
 	}
 }
 
+#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE)
+
 /*
- * When regs->ip points to a 0xEA byte in the FineIBT preamble,
+ * When regs->ip points to a 0xD6 byte in the FineIBT preamble,
  * return true and fill out target and type.
  *
  * We check the preamble by checking for the ENDBR instruction relative to the
- * 0xEA instruction.
+ * UDB instruction.
  */
 static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
@@ -1884,10 +1916,10 @@ static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target,
 	if (!exact_endbr((void *)addr))
 		return false;
 
-	*target = addr + fineibt_preamble_size;
+	*target = addr + fineibt_prefix_size;
 
 	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
-	*type = (u32)regs->r10 + hash;
+	*type = (u32)regs->ax + hash;
 
 	/*
 	 * Since regs->ip points to the middle of an instruction; it cannot
@@ -1925,12 +1957,12 @@ static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32
 	__get_kernel_nofault(&addr, regs->sp, unsigned long, Efault);
 	*target = addr;
 
-	addr -= fineibt_preamble_size;
+	addr -= fineibt_prefix_size;
 	if (!exact_endbr((void *)addr))
 		return false;
 
 	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
-	*type = (u32)regs->r10 + hash;
+	*type = (u32)regs->ax + hash;
 
 	/*
 	 * The UD2 sites are constructed with a RET immediately following,
@@ -1947,7 +1979,7 @@ static bool is_paranoid_thunk(unsigned long addr)
 	u32 thunk;
 
 	__get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault);
-	return (thunk & 0x00FFFFFF) == 0xfd75ea;
+	return (thunk & 0x00FFFFFF) == 0xfd75d6;
 
 Efault:
 	return false;
@@ -1955,8 +1987,7 @@ Efault:
 
 /*
  * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
- * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS
- * thunk.
+ * sequence, or to UDB + Jcc.d8 for cfi_paranoid + ITS thunk.
  */
 static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
@@ -1966,8 +1997,8 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target,
 		return false;
 
 	if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) {
-		*target = regs->r11 + fineibt_preamble_size;
-		*type = regs->r10;
+		*target = regs->r11 + fineibt_prefix_size;
+		*type = regs->ax;
 
 		/*
 		 * Since the trapping instruction is the exact, but LOCK prefixed,
@@ -1979,14 +2010,14 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target,
 	/*
 	 * The cfi_paranoid + ITS thunk combination results in:
 	 *
-	 *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
-	 *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
-	 *  a:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+	 *  0:   b8 78 56 34 12          mov    $0x12345678, %eax
+	 *  5:   41 3b 43 f7             cmp    -11(%r11), %eax
+	 *  a:   2e 3d 8d 5b f0          cs lea -0x10(%r11), %r11
 	 *  e:   2e e8 XX XX XX XX	 cs call __x86_indirect_paranoid_thunk_r11
 	 *
 	 * Where the paranoid_thunk looks like:
 	 *
-	 *  1d:  <ea>                    (bad)
+	 *  1d:  <d6>                    udb
 	 *  __x86_indirect_paranoid_thunk_r11:
 	 *  1e:  75 fd                   jne 1d
 	 *  __x86_indirect_its_thunk_r11:
@@ -1995,8 +2026,8 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target,
 	 *
 	 */
 	if (is_paranoid_thunk(regs->ip)) {
-		*target = regs->r11 + fineibt_preamble_size;
-		*type = regs->r10;
+		*target = regs->r11 + fineibt_prefix_size;
+		*type = regs->ax;
 
 		regs->ip = *target;
 		return true;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 36354b470590..6b22611e69cc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -97,7 +97,7 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
  * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
  * If it's a UD1, further decode to determine its use:
  *
- * FineIBT:      ea                      (bad)
+ * FineIBT:      d6                      udb
  * FineIBT:      f0 75 f9                lock jne . - 6
  * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
  * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
@@ -130,9 +130,9 @@ __always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 		WARN_ON_ONCE(!lock);
 		return BUG_LOCK;
 
-	case 0xea:
+	case 0xd6:
 		*len = addr - start;
-		return BUG_EA;
+		return BUG_UDB;
 
 	case OPCODE_ESCAPE:
 		break;
@@ -341,7 +341,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 		}
 		fallthrough;
 
-	case BUG_EA:
+	case BUG_UDB:
 	case BUG_LOCK:
 		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 			handled = true;
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
index 58891681261b..aad1e5839202 100644
--- a/arch/x86/lib/bhi.S
+++ b/arch/x86/lib/bhi.S
@@ -5,7 +5,7 @@
 #include <asm/nospec-branch.h>
 
 /*
- * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ * Notably, the FineIBT preamble calling these will have ZF set and eax zero.
  *
  * The very last element is in fact larger than 32 bytes, but since its the
  * last element, this does not matter,
@@ -36,7 +36,7 @@ SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_1
-	cmovne %r10, %rdi
+	cmovne %rax, %rdi
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -53,8 +53,8 @@ SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_1
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -64,9 +64,9 @@ SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_1
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
-	cmovne %r10, %rdx
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
+	cmovne %rax, %rdx
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -76,10 +76,10 @@ SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_2
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
-	cmovne %r10, %rdx
-	cmovne %r10, %rcx
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
+	cmovne %rax, %rdx
+	cmovne %rax, %rcx
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -89,11 +89,11 @@ SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_2
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
-	cmovne %r10, %rdx
-	cmovne %r10, %rcx
-	cmovne %r10, %r8
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
+	cmovne %rax, %rdx
+	cmovne %rax, %rcx
+	cmovne %rax, %r8
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -110,12 +110,12 @@ SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_2
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
-	cmovne %r10, %rdx
-	cmovne %r10, %rcx
-	cmovne %r10, %r8
-	cmovne %r10, %r9
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
+	cmovne %rax, %rdx
+	cmovne %rax, %rcx
+	cmovne %rax, %r8
+	cmovne %rax, %r9
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
@@ -125,13 +125,13 @@ SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_FUNC
 	jne .Lud_2
-	cmovne %r10, %rdi
-	cmovne %r10, %rsi
-	cmovne %r10, %rdx
-	cmovne %r10, %rcx
-	cmovne %r10, %r8
-	cmovne %r10, %r9
-	cmovne %r10, %rsp
+	cmovne %rax, %rdi
+	cmovne %rax, %rsi
+	cmovne %rax, %rdx
+	cmovne %rax, %rcx
+	cmovne %rax, %r8
+	cmovne %rax, %r9
+	cmovne %rax, %rsp
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index d78d769a02bd..24b7aca454ec 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -373,10 +373,10 @@ SYM_FUNC_END(call_depth_return_thunk)
 .macro ITS_THUNK reg
 
 /*
- * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (1: udb; jne 1b)
  * that complete the fineibt_paranoid caller sequence.
  */
-1:	.byte 0xea
+1:	ASM_UDB
 SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7e3fca164620..5178ef1aa5c7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -419,12 +419,12 @@ static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
-	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
+	EMIT1_off32(0x2d, hash);			/* subl $hash, %eax	*/
 	if (cfi_bhi) {
+		EMIT2(0x2e, 0x2e);			/* cs cs */
 		emit_call(&prog, __bhi_args[arity], ip + 11);
 	} else {
-		EMIT2(0x75, 0xf9);			/* jne.d8 .-7		*/
-		EMIT3(0x0f, 0x1f, 0x00);		/* nop3			*/
+		EMIT3_off32(0x2e, 0x0f, 0x85, 3);	/* jne.d32,pn 3		*/
 	}
 	EMIT_ENDBR_POISON();
 

From 4a1e02b15ac174c3c6d5e358e67c4ba980e7b336 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 2 Sep 2025 11:20:35 +0200
Subject: [PATCH 040/352] x86,retpoline: Optimize patch_retpoline()

Currently the very common retpoline: "CS CALL __x86_indirect_thunk_r11"
is transformed into "CALL *R11; NOP3" for eIBRS/BHI_NO parts.

Similarly, paranoid fineibt has: "CALL *R11; NOP".

Recognise that CS stuffing can avoid the extra NOP. However, due to
prefix decode penalties, make sure to not emit too many CS prefixes.
Notably: "CS CALL __x86_indirect_thunk_rax" must not become "CS CS CS
CS CALL *RAX". Prefix decode penalties are typically many more cycles
than decoding an extra NOP.

Additionally, if the retpoline is a tail-call, the "JMP *%\reg" should
be followed by INT3 for straight-line-speculation mitigation, since
emit_indirect() now has a length argument, move this into
emit_indirect() such that other users (paranoid-fineibt) also do this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250902104627.GM4068168@noisy.programming.kicks-ass.net
---
 arch/x86/kernel/alternative.c | 42 ++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 3d6a88443616..69fb818df2ee 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -713,20 +713,33 @@ static inline bool is_jcc32(struct insn *insn)
 #if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*
- * CALL/JMP *%\reg
+ * [CS]{,3} CALL/JMP *%\reg [INT3]*
  */
-static int emit_indirect(int op, int reg, u8 *bytes)
+static int emit_indirect(int op, int reg, u8 *bytes, int len)
 {
+	int cs = 0, bp = 0;
 	int i = 0;
 	u8 modrm;
 
+	/*
+	 * Set @len to the excess bytes after writing the instruction.
+	 */
+	len -= 2 + (reg >= 8);
+	WARN_ON_ONCE(len < 0);
+
 	switch (op) {
 	case CALL_INSN_OPCODE:
 		modrm = 0x10; /* Reg = 2; CALL r/m */
+		/*
+		 * Additional NOP is better than prefix decode penalty.
+		 */
+		if (len <= 3)
+			cs = len;
 		break;
 
 	case JMP32_INSN_OPCODE:
 		modrm = 0x20; /* Reg = 4; JMP r/m */
+		bp = len;
 		break;
 
 	default:
@@ -734,6 +747,9 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 		return -1;
 	}
 
+	while (cs--)
+		bytes[i++] = 0x2e; /* CS-prefix */
+
 	if (reg >= 8) {
 		bytes[i++] = 0x41; /* REX.B prefix */
 		reg -= 8;
@@ -745,6 +761,9 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 	bytes[i++] = 0xff; /* opcode */
 	bytes[i++] = modrm;
 
+	while (bp--)
+		bytes[i++] = 0xcc; /* INT3 */
+
 	return i;
 }
 
@@ -918,20 +937,11 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		return emit_its_trampoline(addr, insn, reg, bytes);
 #endif
 
-	ret = emit_indirect(op, reg, bytes + i);
+	ret = emit_indirect(op, reg, bytes + i, insn->length - i);
 	if (ret < 0)
 		return ret;
 	i += ret;
 
-	/*
-	 * The compiler is supposed to EMIT an INT3 after every unconditional
-	 * JMP instruction due to AMD BTC. However, if the compiler is too old
-	 * or MITIGATION_SLS isn't enabled, we still need an INT3 after
-	 * indirect JMPs even on Intel.
-	 */
-	if (op == JMP32_INSN_OPCODE && i < insn->length)
-		bytes[i++] = INT3_INSN_OPCODE;
-
 	for (; i < insn->length;)
 		bytes[i++] = BYTES_NOP1;
 
@@ -1421,8 +1431,7 @@ asm(	".pushsection .rodata				\n"
 	"#fineibt_caller_size:                          \n"
 	"	jne	fineibt_paranoid_start+0xd	\n"
 	"fineibt_paranoid_ind:				\n"
-	"	call	*%r11				\n"
-	"	nop					\n"
+	"	cs call	*%r11				\n"
 	"fineibt_paranoid_end:				\n"
 	".popsection					\n"
 );
@@ -1724,8 +1733,9 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 			emit_paranoid_trampoline(addr + fineibt_caller_size,
 						 &insn, 11, bytes + fineibt_caller_size);
 		} else {
-			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
-			if (WARN_ON_ONCE(ret != 3))
+			int len = fineibt_paranoid_size - fineibt_paranoid_ind;
+			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind, len);
+			if (WARN_ON_ONCE(ret != len))
 				continue;
 		}
 

From c6c973dbfa5e34b1572bcd1852adcad1b5d08fab Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sun, 7 Sep 2025 20:33:38 +0200
Subject: [PATCH 041/352] x86/asm: Remove code depending on
 __GCC_ASM_FLAG_OUTPUTS__

The minimum supported GCC version is 8.1, which supports flag output operands
and always defines __GCC_ASM_FLAG_OUTPUTS__ macro.

Remove code depending on __GCC_ASM_FLAG_OUTPUTS__ and use the "=@ccCOND" flag
output operand directly.

Use the equivalent "=@ccz" instead of "=@cce" flag output operand for
CMPXCHG8B and CMPXCHG16B instructions. These instructions set a single flag
bit - the Zero flag - and "=@ccz" is used to distinguish the CC user from
comparison instructions, where set ZERO flag indeed means that the values are
equal.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250905121723.GCaLrU04lP2A50PT-B@fat_crate.local
---
 arch/x86/boot/bitops.h               |  2 +-
 arch/x86/boot/boot.h                 |  8 ++++----
 arch/x86/boot/string.c               |  4 ++--
 arch/x86/include/asm/archrandom.h    |  6 ++----
 arch/x86/include/asm/asm.h           | 12 ------------
 arch/x86/include/asm/bitops.h        | 18 ++++++------------
 arch/x86/include/asm/cmpxchg.h       | 12 ++++--------
 arch/x86/include/asm/cmpxchg_32.h    |  6 ++----
 arch/x86/include/asm/cmpxchg_64.h    |  3 +--
 arch/x86/include/asm/percpu.h        | 12 ++++--------
 arch/x86/include/asm/rmwcc.h         | 26 ++------------------------
 arch/x86/include/asm/sev.h           |  3 +--
 arch/x86/include/asm/signal.h        |  3 +--
 arch/x86/include/asm/special_insns.h |  3 +--
 arch/x86/include/asm/uaccess.h       |  7 +++----
 tools/arch/x86/include/asm/asm.h     | 12 ------------
 tools/perf/bench/find-bit-bench.c    |  2 +-
 17 files changed, 35 insertions(+), 104 deletions(-)

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 8518ae214c9b..79e15971529d 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -27,7 +27,7 @@ static inline bool variable_test_bit(int nr, const void *addr)
 	bool v;
 	const u32 *p = addr;
 
-	asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
+	asm("btl %2,%1" : "=@ccc" (v) : "m" (*p), "Ir" (nr));
 	return v;
 }
 
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 60580836daf7..a3c58ebe3662 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -155,15 +155,15 @@ static inline void wrgs32(u32 v, addr_t addr)
 static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("fs repe cmpsb" CC_SET(nz)
-		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("fs repe cmpsb"
+		     : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("gs repe cmpsb" CC_SET(nz)
-		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("gs repe cmpsb"
+		     : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index f35369bb14c5..b25c6a9303b7 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -32,8 +32,8 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe cmpsb" CC_SET(nz)
-	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm("repe cmpsb"
+	    : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 02bae8e0758b..4c305305871b 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -23,8 +23,7 @@ static inline bool __must_check rdrand_long(unsigned long *v)
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
 		asm volatile("rdrand %[out]"
-			     CC_SET(c)
-			     : CC_OUT(c) (ok), [out] "=r" (*v));
+			     : "=@ccc" (ok), [out] "=r" (*v));
 		if (ok)
 			return true;
 	} while (--retry);
@@ -35,8 +34,7 @@ static inline bool __must_check rdseed_long(unsigned long *v)
 {
 	bool ok;
 	asm volatile("rdseed %[out]"
-		     CC_SET(c)
-		     : CC_OUT(c) (ok), [out] "=r" (*v));
+		     : "=@ccc" (ok), [out] "=r" (*v));
 	return ok;
 }
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index f963848024a5..d5c8d3afe196 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -122,18 +122,6 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 }
 #endif
 
-/*
- * Macros to generate condition code outputs from inline assembly,
- * The output operand must be type "bool".
- */
-#ifdef __GCC_ASM_FLAG_OUTPUTS__
-# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
-# define CC_OUT(c) "=@cc" #c
-#else
-# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
-# define CC_OUT(c) [_cc_ ## c] "=qm"
-#endif
-
 #ifdef __KERNEL__
 
 # include <asm/extable_fixup_types.h>
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index eebbc8889e70..33153dcd119c 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -99,8 +99,7 @@ static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
 {
 	bool negative;
 	asm_inline volatile(LOCK_PREFIX "xorb %2,%1"
-		CC_SET(s)
-		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
+		: "=@ccs" (negative), WBYTE_ADDR(addr)
 		: "iq" ((char)mask) : "memory");
 	return negative;
 }
@@ -149,8 +148,7 @@ arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 	bool oldbit;
 
 	asm(__ASM_SIZE(bts) " %2,%1"
-	    CC_SET(c)
-	    : CC_OUT(c) (oldbit)
+	    : "=@ccc" (oldbit)
 	    : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -175,8 +173,7 @@ arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 	bool oldbit;
 
 	asm volatile(__ASM_SIZE(btr) " %2,%1"
-		     CC_SET(c)
-		     : CC_OUT(c) (oldbit)
+		     : "=@ccc" (oldbit)
 		     : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -187,8 +184,7 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	bool oldbit;
 
 	asm volatile(__ASM_SIZE(btc) " %2,%1"
-		     CC_SET(c)
-		     : CC_OUT(c) (oldbit)
+		     : "=@ccc" (oldbit)
 		     : ADDR, "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -211,8 +207,7 @@ static __always_inline bool constant_test_bit_acquire(long nr, const volatile un
 	bool oldbit;
 
 	asm volatile("testb %2,%1"
-		     CC_SET(nz)
-		     : CC_OUT(nz) (oldbit)
+		     : "=@ccnz" (oldbit)
 		     : "m" (((unsigned char *)addr)[nr >> 3]),
 		       "i" (1 << (nr & 7))
 		     :"memory");
@@ -225,8 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	bool oldbit;
 
 	asm volatile(__ASM_SIZE(bt) " %2,%1"
-		     CC_SET(c)
-		     : CC_OUT(c) (oldbit)
+		     : "=@ccc" (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
 
 	return oldbit;
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index b61f32c3459f..a88b06f1c35e 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -166,8 +166,7 @@ extern void __add_wrong_size(void)
 	{								\
 		volatile u8 *__ptr = (volatile u8 *)(_ptr);		\
 		asm_inline volatile(lock "cmpxchgb %[new], %[ptr]"	\
-			     CC_SET(z)					\
-			     : CC_OUT(z) (success),			\
+			     : "=@ccz" (success),			\
 			       [ptr] "+m" (*__ptr),			\
 			       [old] "+a" (__old)			\
 			     : [new] "q" (__new)			\
@@ -178,8 +177,7 @@ extern void __add_wrong_size(void)
 	{								\
 		volatile u16 *__ptr = (volatile u16 *)(_ptr);		\
 		asm_inline volatile(lock "cmpxchgw %[new], %[ptr]"	\
-			     CC_SET(z)					\
-			     : CC_OUT(z) (success),			\
+			     : "=@ccz" (success),			\
 			       [ptr] "+m" (*__ptr),			\
 			       [old] "+a" (__old)			\
 			     : [new] "r" (__new)			\
@@ -190,8 +188,7 @@ extern void __add_wrong_size(void)
 	{								\
 		volatile u32 *__ptr = (volatile u32 *)(_ptr);		\
 		asm_inline volatile(lock "cmpxchgl %[new], %[ptr]"	\
-			     CC_SET(z)					\
-			     : CC_OUT(z) (success),			\
+			     : "=@ccz" (success),			\
 			       [ptr] "+m" (*__ptr),			\
 			       [old] "+a" (__old)			\
 			     : [new] "r" (__new)			\
@@ -202,8 +199,7 @@ extern void __add_wrong_size(void)
 	{								\
 		volatile u64 *__ptr = (volatile u64 *)(_ptr);		\
 		asm_inline volatile(lock "cmpxchgq %[new], %[ptr]"	\
-			     CC_SET(z)					\
-			     : CC_OUT(z) (success),			\
+			     : "=@ccz" (success),			\
 			       [ptr] "+m" (*__ptr),			\
 			       [old] "+a" (__old)			\
 			     : [new] "r" (__new)			\
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 371f7906019e..1f80a62be969 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -46,8 +46,7 @@ static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new
 	bool ret;							\
 									\
 	asm_inline volatile(_lock "cmpxchg8b %[ptr]"			\
-		     CC_SET(e)						\
-		     : CC_OUT(e) (ret),					\
+		     : "=@ccz" (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
@@ -125,8 +124,7 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 		ALTERNATIVE(_lock_loc					\
 			    "call cmpxchg8b_emu",			\
 			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		CC_SET(e)						\
-		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+		: ALT_OUTPUT_SP("=@ccz" (ret),				\
 				"+a" (o.low), "+d" (o.high))		\
 		: "b" (n.low), "c" (n.high),				\
 		  [ptr] "S" (_ptr)					\
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 71d1e72ed879..5afea056fb20 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -66,8 +66,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 	bool ret;							\
 									\
 	asm_inline volatile(_lock "cmpxchg16b %[ptr]"			\
-		     CC_SET(e)						\
-		     : CC_OUT(e) (ret),					\
+		     : "=@ccz" (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b0d03b6c279b..332428caaed2 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -309,8 +309,7 @@ do {									\
 									\
 	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
 		  __percpu_arg([var])					\
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
+		  : "=@ccz" (success),					\
 		    [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
@@ -367,8 +366,7 @@ do {									\
 	asm_inline qual (						\
 		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		CC_SET(z)						\
-		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+		: ALT_OUTPUT_SP("=@ccz" (success),			\
 				[var] "+m" (__my_cpu_var(_var)),	\
 				"+a" (old__.low), "+d" (old__.high))	\
 		: "b" (new__.low), "c" (new__.high),			\
@@ -436,8 +434,7 @@ do {									\
 	asm_inline qual (						\
 		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		CC_SET(z)						\
-		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+		: ALT_OUTPUT_SP("=@ccz" (success),			\
 				[var] "+m" (__my_cpu_var(_var)),	\
 				"+a" (old__.low), "+d" (old__.high))	\
 		: "b" (new__.low), "c" (new__.high),			\
@@ -585,8 +582,7 @@ do {									\
 	bool oldbit;							\
 									\
 	asm volatile("btl %[nr], " __percpu_arg([var])			\
-		     CC_SET(c)						\
-		     : CC_OUT(c) (oldbit)				\
+		     : "=@ccc" (oldbit)					\
 		     : [var] "m" (__my_cpu_var(_var)),			\
 		       [nr] "rI" (_nr));				\
 	oldbit;								\
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 3821ee3fae35..54c8fc430684 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -6,37 +6,15 @@
 
 #define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
-#ifndef __GCC_ASM_FLAG_OUTPUTS__
-
-/* Use asm goto */
-
-#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
-({									\
-	bool c = false;							\
-	asm goto (fullop "; j" #cc " %l[cc_label]"		\
-			: : [var] "m" (_var), ## __VA_ARGS__		\
-			: clobbers : cc_label);				\
-	if (0) {							\
-cc_label:	c = true;						\
-	}								\
-	c;								\
-})
-
-#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
-
-/* Use flags output or a set instruction */
-
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c;								\
-	asm_inline volatile (fullop CC_SET(cc)				\
-			: [var] "+m" (_var), CC_OUT(cc) (c)		\
+	asm_inline volatile (fullop					\
+			: [var] "+m" (_var), "=@cc" #cc (c)		\
 			: __VA_ARGS__ : clobbers);			\
 	c;								\
 })
 
-#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
-
 #define GEN_UNARY_RMWcc_4(op, var, cc, arg0)				\
 	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
 
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 02236962fdb1..7cb8e09e749b 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -491,8 +491,7 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
 
 	/* "pvalidate" mnemonic support in binutils 2.36 and newer */
 	asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t"
-		     CC_SET(c)
-		     : CC_OUT(c) (no_rmpupdate), "=a"(rc)
+		     : "=@ccc"(no_rmpupdate), "=a"(rc)
 		     : "a"(vaddr), "c"(rmp_psize), "d"(validate)
 		     : "memory", "cc");
 
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index c72d46175374..5c03aaa89014 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -83,8 +83,7 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
 	bool ret;
-	asm("btl %2,%1" CC_SET(c)
-	    : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1));
+	asm("btl %2,%1" : "=@ccc"(ret) : "m"(*set), "Ir"(_sig-1));
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index c99914569352..46aa2c9c1bda 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -284,8 +284,7 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	 * See movdir64b()'s comment on operand specification.
 	 */
 	asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90"
-		     CC_SET(z)
-		     : CC_OUT(z) (zf), "+m" (*__dst)
+		     : "=@ccz" (zf), "+m" (*__dst)
 		     : "m" (*__src), "a" (__dst), "d" (__src));
 
 	/* Submission failure is indicated via EFLAGS.ZF=1 */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 3a7755c1a441..91a3fb8ae7ff 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -378,7 +378,7 @@ do {									\
 	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
-		     : CC_OUT(z) (success),				\
+		     : "=@ccz" (success),				\
 		       [ptr] "+m" (*_ptr),				\
 		       [old] "+a" (__old)				\
 		     : [new] ltype (__new)				\
@@ -397,7 +397,7 @@ do {									\
 	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
-		     : CC_OUT(z) (success),				\
+		     : "=@ccz" (success),				\
 		       "+A" (__old),					\
 		       [ptr] "+m" (*_ptr)				\
 		     : "b" ((u32)__new),				\
@@ -417,11 +417,10 @@ do {									\
 	__typeof__(*(_ptr)) __new = (_new);				\
 	asm volatile("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
-		     CC_SET(z)						\
 		     "2:\n"						\
 		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG,	\
 					   %[errout])			\
-		     : CC_OUT(z) (success),				\
+		     : "=@ccz" (success),				\
 		       [errout] "+r" (__err),				\
 		       [ptr] "+m" (*_ptr),				\
 		       [old] "+a" (__old)				\
diff --git a/tools/arch/x86/include/asm/asm.h b/tools/arch/x86/include/asm/asm.h
index dbe39b44256b..6e1b357c374b 100644
--- a/tools/arch/x86/include/asm/asm.h
+++ b/tools/arch/x86/include/asm/asm.h
@@ -108,18 +108,6 @@
 
 #endif
 
-/*
- * Macros to generate condition code outputs from inline assembly,
- * The output operand must be type "bool".
- */
-#ifdef __GCC_ASM_FLAG_OUTPUTS__
-# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
-# define CC_OUT(c) "=@cc" #c
-#else
-# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
-# define CC_OUT(c) [_cc_ ## c] "=qm"
-#endif
-
 #ifdef __KERNEL__
 
 /* Exception table entry */
diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c
index 7e25b0e413f6..e697c20951bc 100644
--- a/tools/perf/bench/find-bit-bench.c
+++ b/tools/perf/bench/find-bit-bench.c
@@ -37,7 +37,7 @@ static noinline void workload(int val)
 	accumulator++;
 }
 
-#if (defined(__i386__) || defined(__x86_64__)) && defined(__GCC_ASM_FLAG_OUTPUTS__)
+#if defined(__i386__) || defined(__x86_64__)
 static bool asm_test_bit(long nr, const unsigned long *addr)
 {
 	bool oldbit;

From 68a74490629eb606ad77a88dd84515f35525e267 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 11 Aug 2025 22:00:12 +0900
Subject: [PATCH 042/352] fs: hpfs: Avoid multiple
 -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.

So, in order to avoid ending up with a flexible-array member in the
middle of other structs, we use the `struct_group_tagged()` helper
to create a new tagged `struct bplus_header_fixed`. This structure
groups together all the members of the flexible `struct bplus_header`
except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct member currently causing
trouble from `struct bplus_header` to `struct bplus_header_fixed`.

We also want to ensure that when new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement `struct bplus_header_fixed`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

We also use `container_of()` (via a wrapper) whenever we need to retrieve
a pointer to the flexible structure, through which we can access the
flexible-array member, if necessary.

So, with these changes, fix 26 of the following type of warnings:
fs/hpfs/hpfs.h:456:23: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
fs/hpfs/hpfs.h:498:23: 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: Mikulas Patocka <mpatocka@redhat.com>
---
 fs/hpfs/anode.c | 43 ++++++++++++++++++++++---------------------
 fs/hpfs/ea.c    |  2 +-
 fs/hpfs/file.c  |  4 +++-
 fs/hpfs/hpfs.h  | 44 +++++++++++++++++++++++++++++++-------------
 fs/hpfs/map.c   |  8 ++++----
 5 files changed, 61 insertions(+), 40 deletions(-)

diff --git a/fs/hpfs/anode.c b/fs/hpfs/anode.c
index c14c9a035ee0..a4f5321eafae 100644
--- a/fs/hpfs/anode.c
+++ b/fs/hpfs/anode.c
@@ -27,7 +27,7 @@ secno hpfs_bplus_lookup(struct super_block *s, struct inode *inode,
 				a = le32_to_cpu(btree->u.internal[i].down);
 				brelse(bh);
 				if (!(anode = hpfs_map_anode(s, a, &bh))) return -1;
-				btree = &anode->btree;
+				btree = GET_BTREE_PTR(&anode->btree);
 				goto go_down;
 			}
 		hpfs_error(s, "sector %08x not found in internal anode %08x", sec, a);
@@ -69,12 +69,13 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 	int n;
 	unsigned fs;
 	int c1, c2 = 0;
+
 	if (fnod) {
 		if (!(fnode = hpfs_map_fnode(s, node, &bh))) return -1;
-		btree = &fnode->btree;
+		btree = GET_BTREE_PTR(&fnode->btree);
 	} else {
 		if (!(anode = hpfs_map_anode(s, node, &bh))) return -1;
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 	}
 	a = node;
 	go_down:
@@ -91,7 +92,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 		if (hpfs_sb(s)->sb_chk)
 			if (hpfs_stop_cycles(s, a, &c1, &c2, "hpfs_add_sector_to_btree #1")) return -1;
 		if (!(anode = hpfs_map_anode(s, a, &bh))) return -1;
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 		goto go_down;
 	}
 	if (n >= 0) {
@@ -151,7 +152,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 		}
 		brelse(bh);
 		bh = bh1;
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 	}
 	btree->n_free_nodes--; n = btree->n_used_nodes++;
 	le16_add_cpu(&btree->first_free, 12);
@@ -168,10 +169,10 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 			if (hpfs_stop_cycles(s, up, &c1, &c2, "hpfs_add_sector_to_btree #2")) return -1;
 		if (up != node || !fnod) {
 			if (!(anode = hpfs_map_anode(s, up, &bh))) return -1;
-			btree = &anode->btree;
+			btree = GET_BTREE_PTR(&anode->btree);
 		} else {
 			if (!(fnode = hpfs_map_fnode(s, up, &bh))) return -1;
-			btree = &fnode->btree;
+			btree = GET_BTREE_PTR(&fnode->btree);
 		}
 		if (btree->n_free_nodes) {
 			btree->n_free_nodes--; n = btree->n_used_nodes++;
@@ -206,8 +207,8 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 			anode->btree.n_used_nodes = 1;
 			anode->btree.n_free_nodes = 59;
 			anode->btree.first_free = cpu_to_le16(16);
-			anode->btree.u.internal[0].down = cpu_to_le32(a);
-			anode->btree.u.internal[0].file_secno = cpu_to_le32(-1);
+			GET_BTREE_PTR(&anode->btree)->u.internal[0].down = cpu_to_le32(a);
+			GET_BTREE_PTR(&anode->btree)->u.internal[0].file_secno = cpu_to_le32(-1);
 			mark_buffer_dirty(bh);
 			brelse(bh);
 			if ((anode = hpfs_map_anode(s, a, &bh))) {
@@ -229,20 +230,20 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi
 			brelse(bh2);
 			return -1;
 		}
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 	} else {
 		if (!(fnode = hpfs_map_fnode(s, node, &bh))) {
 			brelse(bh2);
 			return -1;
 		}
-		btree = &fnode->btree;
+		btree = GET_BTREE_PTR(&fnode->btree);
 	}
 	ranode->up = cpu_to_le32(node);
 	memcpy(&ranode->btree, btree, le16_to_cpu(btree->first_free));
 	if (fnod)
 		ranode->btree.flags |= BP_fnode_parent;
-	ranode->btree.n_free_nodes = (bp_internal(&ranode->btree) ? 60 : 40) - ranode->btree.n_used_nodes;
-	if (bp_internal(&ranode->btree)) for (n = 0; n < ranode->btree.n_used_nodes; n++) {
+	GET_BTREE_PTR(&ranode->btree)->n_free_nodes = (bp_internal(GET_BTREE_PTR(&ranode->btree)) ? 60 : 40) - GET_BTREE_PTR(&ranode->btree)->n_used_nodes;
+	if (bp_internal(GET_BTREE_PTR(&ranode->btree))) for (n = 0; n < GET_BTREE_PTR(&ranode->btree)->n_used_nodes; n++) {
 		struct anode *unode;
 		if ((unode = hpfs_map_anode(s, le32_to_cpu(ranode->u.internal[n].down), &bh1))) {
 			unode->up = cpu_to_le32(ra);
@@ -291,7 +292,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree)
 			if (hpfs_stop_cycles(s, ano, &d1, &d2, "hpfs_remove_btree #1"))
 				return;
 		if (!(anode = hpfs_map_anode(s, ano, &bh))) return;
-		btree1 = &anode->btree;
+		btree1 = GET_BTREE_PTR(&anode->btree);
 		level++;
 		pos = 0;
 	}
@@ -307,7 +308,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree)
 	ano = le32_to_cpu(anode->up);
 	if (--level) {
 		if (!(anode = hpfs_map_anode(s, ano, &bh))) return;
-		btree1 = &anode->btree;
+		btree1 = GET_BTREE_PTR(&anode->btree);
 	} else btree1 = btree;
 	for (i = 0; i < btree1->n_used_nodes; i++) {
 		if (le32_to_cpu(btree1->u.internal[i].down) == oano) {
@@ -332,7 +333,7 @@ static secno anode_lookup(struct super_block *s, anode_secno a, unsigned sec)
 	struct anode *anode;
 	struct buffer_head *bh;
 	if (!(anode = hpfs_map_anode(s, a, &bh))) return -1;
-	return hpfs_bplus_lookup(s, NULL, &anode->btree, sec, bh);
+	return hpfs_bplus_lookup(s, NULL, GET_BTREE_PTR(&anode->btree), sec, bh);
 }
 
 int hpfs_ea_read(struct super_block *s, secno a, int ano, unsigned pos,
@@ -388,7 +389,7 @@ void hpfs_ea_remove(struct super_block *s, secno a, int ano, unsigned len)
 	struct buffer_head *bh;
 	if (ano) {
 		if (!(anode = hpfs_map_anode(s, a, &bh))) return;
-		hpfs_remove_btree(s, &anode->btree);
+		hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree));
 		brelse(bh);
 		hpfs_free_sectors(s, a, 1);
 	} else hpfs_free_sectors(s, a, (len + 511) >> 9);
@@ -407,10 +408,10 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs)
 	int c1, c2 = 0;
 	if (fno) {
 		if (!(fnode = hpfs_map_fnode(s, f, &bh))) return;
-		btree = &fnode->btree;
+		btree = GET_BTREE_PTR(&fnode->btree);
 	} else {
 		if (!(anode = hpfs_map_anode(s, f, &bh))) return;
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 	}
 	if (!secs) {
 		hpfs_remove_btree(s, btree);
@@ -448,7 +449,7 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs)
 			if (hpfs_stop_cycles(s, node, &c1, &c2, "hpfs_truncate_btree"))
 				return;
 		if (!(anode = hpfs_map_anode(s, node, &bh))) return;
-		btree = &anode->btree;
+		btree = GET_BTREE_PTR(&anode->btree);
 	}	
 	nodes = btree->n_used_nodes + btree->n_free_nodes;
 	for (i = 0; i < btree->n_used_nodes; i++)
@@ -485,7 +486,7 @@ void hpfs_remove_fnode(struct super_block *s, fnode_secno fno)
 	struct extended_attribute *ea;
 	struct extended_attribute *ea_end;
 	if (!(fnode = hpfs_map_fnode(s, fno, &bh))) return;
-	if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, &fnode->btree);
+	if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, GET_BTREE_PTR(&fnode->btree));
 	else hpfs_remove_dtree(s, le32_to_cpu(fnode->u.external[0].disk_secno));
 	ea_end = fnode_end_ea(fnode);
 	for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea))
diff --git a/fs/hpfs/ea.c b/fs/hpfs/ea.c
index 102ba18e561f..2149d3ca530b 100644
--- a/fs/hpfs/ea.c
+++ b/fs/hpfs/ea.c
@@ -41,7 +41,7 @@ void hpfs_ea_ext_remove(struct super_block *s, secno a, int ano, unsigned len)
 		struct buffer_head *bh;
 		struct anode *anode;
 		if ((anode = hpfs_map_anode(s, a, &bh))) {
-			hpfs_remove_btree(s, &anode->btree);
+			hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree));
 			brelse(bh);
 			hpfs_free_sectors(s, a, 1);
 		}
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 263b5bbe1849..29e876705369 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -51,7 +51,9 @@ static secno hpfs_bmap(struct inode *inode, unsigned file_secno, unsigned *n_sec
 		return hpfs_inode->i_disk_sec + n;
 	}
 	if (!(fnode = hpfs_map_fnode(inode->i_sb, inode->i_ino, &bh))) return 0;
-	disk_secno = hpfs_bplus_lookup(inode->i_sb, inode, &fnode->btree, file_secno, bh);
+	disk_secno = hpfs_bplus_lookup(inode->i_sb, inode,
+				       GET_BTREE_PTR(&fnode->btree),
+				       file_secno, bh);
 	if (disk_secno == -1) return 0;
 	if (hpfs_chk_sectors(inode->i_sb, disk_secno, 1, "bmap")) return 0;
 	n = file_secno - hpfs_inode->i_file_sec;
diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h
index 281dec8f636b..353f73c914d9 100644
--- a/fs/hpfs/hpfs.h
+++ b/fs/hpfs/hpfs.h
@@ -394,27 +394,45 @@ enum {
 	BP_binary_search = 0x40,
 	BP_internal = 0x80
 };
+
+/**
+ * GET_BTREE_PTR() - Get a pointer to struct bplus_header
+ *
+ * Wrapper around container_of() to retrieve a pointer to struct
+ * bplus_header from a pointer to struct bplus_header_fixed.
+ *
+ * @ptr: Pointer to struct bplus_header_fixed.
+ *
+ */
+#define GET_BTREE_PTR(ptr) \
+	container_of(ptr, struct bplus_header, __hdr)
+
 struct bplus_header
 {
-  u8 flags;				/* bit 0 - high bit of first free entry offset
+	/* New members MUST be added within the struct_group() macro below. */
+	struct_group_tagged(bplus_header_fixed, __hdr,
+		u8 flags;		/* bit 0 - high bit of first free entry offset
 					   bit 5 - we're pointed to by an fnode,
 					   the data btree or some ea or the
 					   main ea bootage pointer ea_secno
 					   bit 6 - suggest binary search (unused)
 					   bit 7 - 1 -> (internal) tree of anodes
 						   0 -> (leaf) list of extents */
-  u8 fill[3];
-  u8 n_free_nodes;			/* free nodes in following array */
-  u8 n_used_nodes;			/* used nodes in following array */
-  __le16 first_free;			/* offset from start of header to
+		u8 fill[3];
+		u8 n_free_nodes;	/* free nodes in following array */
+		u8 n_used_nodes;	/* used nodes in following array */
+		__le16 first_free;	/* offset from start of header to
 					   first free node in array */
-  union {
-	/* (internal) 2-word entries giving subtree pointers */
-	DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal);
-	/* (external) 3-word entries giving sector runs */
-	DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external);
-  } u;
+	);
+	union {
+		/* (internal) 2-word entries giving subtree pointers */
+		DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal);
+		/* (external) 3-word entries giving sector runs */
+		DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external);
+	} u;
 };
+static_assert(offsetof(struct bplus_header, u.internal) == sizeof(struct bplus_header_fixed),
+	      "struct member likely outside of struct_group_tagged()");
 
 static inline bool bp_internal(struct bplus_header *bp)
 {
@@ -453,7 +471,7 @@ struct fnode
   __le16 flags;				/* bit 1 set -> ea_secno is an anode */
 					/* bit 8 set -> directory.  first & only extent
 					   points to dnode. */
-  struct bplus_header btree;		/* b+ tree, 8 extents or 12 subtrees */
+  struct bplus_header_fixed btree;	/* b+ tree, 8 extents or 12 subtrees */
   union {
     struct bplus_leaf_node external[8];
     struct bplus_internal_node internal[12];
@@ -495,7 +513,7 @@ struct anode
   __le32 self;				/* pointer to this anode */
   __le32 up;				/* parent anode or fnode */
 
-  struct bplus_header btree;		/* b+tree, 40 extents or 60 subtrees */
+  struct bplus_header_fixed btree;	/* b+tree, 40 extents or 60 subtrees */
   union {
     struct bplus_leaf_node external[40];
     struct bplus_internal_node internal[60];
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index ecd9fccd1663..be73233502f8 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -178,14 +178,14 @@ struct fnode *hpfs_map_fnode(struct super_block *s, ino_t ino, struct buffer_hea
 			}
 			if (!fnode_is_dir(fnode)) {
 				if ((unsigned)fnode->btree.n_used_nodes + (unsigned)fnode->btree.n_free_nodes !=
-				    (bp_internal(&fnode->btree) ? 12 : 8)) {
+				    (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 12 : 8)) {
 					hpfs_error(s,
 					   "bad number of nodes in fnode %08lx",
 					    (unsigned long)ino);
 					goto bail;
 				}
 				if (le16_to_cpu(fnode->btree.first_free) !=
-				    8 + fnode->btree.n_used_nodes * (bp_internal(&fnode->btree) ? 8 : 12)) {
+				    8 + fnode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 8 : 12)) {
 					hpfs_error(s,
 					    "bad first_free pointer in fnode %08lx",
 					    (unsigned long)ino);
@@ -233,12 +233,12 @@ struct anode *hpfs_map_anode(struct super_block *s, anode_secno ano, struct buff
 				goto bail;
 			}
 			if ((unsigned)anode->btree.n_used_nodes + (unsigned)anode->btree.n_free_nodes !=
-			    (bp_internal(&anode->btree) ? 60 : 40)) {
+			    (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 60 : 40)) {
 				hpfs_error(s, "bad number of nodes in anode %08x", ano);
 				goto bail;
 			}
 			if (le16_to_cpu(anode->btree.first_free) !=
-			    8 + anode->btree.n_used_nodes * (bp_internal(&anode->btree) ? 8 : 12)) {
+			    8 + anode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 8 : 12)) {
 				hpfs_error(s, "bad first_free pointer in anode %08x", ano);
 				goto bail;
 			}

From fd8a620f195e7966d83c367def68818a2cc71177 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Tue, 27 May 2025 17:00:08 +0800
Subject: [PATCH 043/352] hpfs: Replace simple_strtoul with kstrtoint in
 hpfs_parse_param

kstrtoint() is better because simple_strtoul() ignores overflow and the
type of 'timeshift' is 'int' rather than 'unsigned long'. Using kstrtoint()
is more concise too.

Signed-off-by: Su Hui <suhui@nfschina.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 fs/hpfs/super.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 42b779b4d87f..8ab85e7ac91e 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -404,15 +404,11 @@ static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 	case Opt_timeshift:
 		{
-			int m = 1;
 			char *rhs = param->string;
 			int timeshift;
 
-			if (*rhs == '-') m = -1;
-			if (*rhs == '+' || *rhs == '-') rhs++;
-			timeshift = simple_strtoul(rhs, &rhs, 0) * m;
-			if (*rhs)
-					return -EINVAL;
+			if (kstrtoint(rhs, 0, &timeshift))
+				return -EINVAL;
 			ctx->timeshift = timeshift;
 			break;
 		}

From 32058c38d3b79a28963a59ac0353644dc24775cd Mon Sep 17 00:00:00 2001
From: Yikang Yue <yikangy2@illinois.edu>
Date: Sat, 3 May 2025 20:44:34 -0500
Subject: [PATCH 044/352] fs/hpfs: Fix error code for new_inode() failure in
 mkdir/create/mknod/symlink

The function call new_inode() is a primitive for allocating an inode in memory,
rather than planning disk space for it. Therefore, -ENOMEM should be returned
as the error code rather than -ENOSPC.

To be specific, new_inode()'s call path looks like this:
new_inode
  new_inode_pseudo
    alloc_inode
      ops->alloc_inode (hpfs_alloc_inode)
        alloc_inode_sb
          kmem_cache_alloc_lru

Therefore, the failure of new_inode() indicates a memory presure issue (-ENOMEM),
not a lack of disk space. However, the current implementation of
hpfs_mkdir/create/mknod/symlink incorrectly returns -ENOSPC when new_inode() fails.
This patch fix this by set err to -ENOMEM before the goto statement.

BTW, we also noticed that other nested calls within these four functions,
like hpfs_alloc_f/dnode and hpfs_add_dirent, might also fail due to memory presure.
But similarly, only -ENOSPC is returned. Addressing these will involve code
modifications in other functions, and we plan to submit dedicated patches for these
issues in the future. For this patch, we focus on new_inode().

Signed-off-by: Yikang Yue <yikangy2@illinois.edu>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 fs/hpfs/namei.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index e3cdc421dfba..353e13a615f5 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -52,8 +52,10 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	dee.fnode = cpu_to_le32(fno);
 	dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb));
 	result = new_inode(dir->i_sb);
-	if (!result)
+	if (!result) {
+		err = -ENOMEM;
 		goto bail2;
+	}
 	hpfs_init_inode(result);
 	result->i_ino = fno;
 	hpfs_i(result)->i_parent_dir = dir->i_ino;
@@ -153,9 +155,10 @@ static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir,
 	dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb));
 
 	result = new_inode(dir->i_sb);
-	if (!result)
+	if (!result) {
+		err = -ENOMEM;
 		goto bail1;
-	
+	}
 	hpfs_init_inode(result);
 	result->i_ino = fno;
 	result->i_mode |= S_IFREG;
@@ -239,9 +242,10 @@ static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb));
 
 	result = new_inode(dir->i_sb);
-	if (!result)
+	if (!result) {
+		err = -ENOMEM;
 		goto bail1;
-
+	}
 	hpfs_init_inode(result);
 	result->i_ino = fno;
 	hpfs_i(result)->i_parent_dir = dir->i_ino;
@@ -314,8 +318,10 @@ static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb));
 
 	result = new_inode(dir->i_sb);
-	if (!result)
+	if (!result) {
+		err = -ENOMEM;
 		goto bail1;
+	}
 	result->i_ino = fno;
 	hpfs_init_inode(result);
 	hpfs_i(result)->i_parent_dir = dir->i_ino;

From 4c8bad3ed035ab85ad9b0d247154be43a53ef84d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 15 Sep 2025 14:05:39 +0200
Subject: [PATCH 045/352] xtensa: use HZ_PER_MHZ in platform_calibrate_ccount

Replace the hardcoded 1000000UL with the HZ_PER_MHZ unit macro, and add
a space in "10 MHz" to improve the readability of the error message.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Message-Id: <20250915120540.2150841-3-thorsten.blum@linux.dev>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/kernel/platform.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/xtensa/kernel/platform.c b/arch/xtensa/kernel/platform.c
index 926b8bf0f14c..f14713060fd4 100644
--- a/arch/xtensa/kernel/platform.c
+++ b/arch/xtensa/kernel/platform.c
@@ -14,6 +14,7 @@
 
 #include <linux/printk.h>
 #include <linux/types.h>
+#include <linux/units.h>
 #include <asm/platform.h>
 #include <asm/timex.h>
 
@@ -38,7 +39,7 @@ void __weak platform_idle(void)
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 void __weak platform_calibrate_ccount(void)
 {
-	pr_err("ERROR: Cannot calibrate cpu frequency! Assuming 10MHz.\n");
-	ccount_freq = 10 * 1000000UL;
+	pr_err("ERROR: Cannot calibrate cpu frequency! Assuming 10 MHz.\n");
+	ccount_freq = 10 * HZ_PER_MHZ;
 }
 #endif

From 06ce29264f1d46f00fdb46b0c2d9fb060ce72368 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 3 Sep 2025 15:11:27 -0400
Subject: [PATCH 046/352] dt-bindings: rtc: pcf85063: remove
 quartz-load-femtofarads restriction for nxp,pcf85063

Original TXT binding doc have not limitition about quartz-load-femtofarads,
which only allow 7000 for nxp,pcf85063.

So remove it to fix below CHECK_DTBS warnings:
arch/arm/boot/dts/nxp/imx/imx6dl-skov-revc-lt2.dtb: rtc@51 (nxp,pcf85063): quartz-load-femtofarads:0: 7000 was expected
        from schema $id: http://devicetree.org/schemas/rtc/nxp,pcf85063.yaml#

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250903191128.439164-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/nxp,pcf85063.yaml          | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml
index 1e6277e524c2..f7013cd8fc20 100644
--- a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml
+++ b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml
@@ -62,16 +62,6 @@ allOf:
     then:
       properties:
         quartz-load-femtofarads: false
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - nxp,pcf85063
-    then:
-      properties:
-        quartz-load-femtofarads:
-          const: 7000
   - if:
       properties:
         compatible:

From 0dbb84b5c447ddf2681ed0248a6fb7c9fc3fdb6c Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 27 Aug 2025 15:33:55 -0400
Subject: [PATCH 047/352] dt-bindings: rtc: trivial-rtc: add dallas,m41t00

Add compatible string dallas,m41t00 for dallas m41t00 RTC.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250827193356.78368-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/devicetree/bindings/rtc/trivial-rtc.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
index 5e0c7cd25cc6..587b7cd5806c 100644
--- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
@@ -38,6 +38,8 @@ properties:
       - dallas,ds1672
       # Extremely Accurate I²C RTC with Integrated Crystal and SRAM
       - dallas,ds3232
+      # Dallas m41t00 Real-time Clock
+      - dallas,m41t00
       # SD2405AL Real-Time Clock
       - dfrobot,sd2405al
       # EM Microelectronic EM3027 RTC

From d06b24f805b5c86c83f4182f32ed1cdd7c690171 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 30 Aug 2025 15:00:25 +0200
Subject: [PATCH 048/352] rtc: s3c: Drop unused defines

Drop defines for S3C2416 and S3C2443 SoCs which are not used anywhere.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250830130024.142815-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s3c.h | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/rtc/rtc-s3c.h b/drivers/rtc/rtc-s3c.h
index 3552914aa611..44e9d6c9428f 100644
--- a/drivers/rtc/rtc-s3c.h
+++ b/drivers/rtc/rtc-s3c.h
@@ -24,22 +24,6 @@
 #define S3C2410_TICNT		S3C2410_RTCREG(0x44)
 #define S3C2410_TICNT_ENABLE	(1 << 7)
 
-/* S3C2443: tick count is 15 bit wide
- * TICNT[6:0] contains upper 7 bits
- * TICNT1[7:0] contains lower 8 bits
- */
-#define S3C2443_TICNT_PART(x)	((x & 0x7f00) >> 8)
-#define S3C2443_TICNT1		S3C2410_RTCREG(0x4C)
-#define S3C2443_TICNT1_PART(x)	(x & 0xff)
-
-/* S3C2416: tick count is 32 bit wide
- * TICNT[6:0] contains bits [14:8]
- * TICNT1[7:0] contains lower 8 bits
- * TICNT2[16:0] contains upper 17 bits
- */
-#define S3C2416_TICNT2		S3C2410_RTCREG(0x48)
-#define S3C2416_TICNT2_PART(x)	((x & 0xffff8000) >> 15)
-
 #define S3C2410_RTCALM		S3C2410_RTCREG(0x50)
 #define S3C2410_RTCALM_ALMEN	(1 << 6)
 #define S3C2410_RTCALM_YEAREN	(1 << 5)

From 9693342805748bcf0c02b16ac0a0aa852688dea9 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 30 Aug 2025 15:00:26 +0200
Subject: [PATCH 049/352] rtc: s3c: Drop support for S3C2410

Samsung S3C24xx family of SoCs was removed the Linux kernel in the
commit 61b7f8920b17 ("ARM: s3c: remove all s3c24xx support"), in January
2023.  There are no in-kernel users of remaining S3C24xx compatibles.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250830130024.142815-5-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s3c.c | 49 ++-----------------------------------------
 drivers/rtc/rtc-s3c.h |  3 ---
 2 files changed, 2 insertions(+), 50 deletions(-)

diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 79b2a16f15ad..291c0ccb0acd 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -331,7 +331,7 @@ static const struct rtc_class_ops s3c_rtcops = {
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
 
-static void s3c24xx_rtc_enable(struct s3c_rtc *info)
+static void s3c6410_rtc_enable(struct s3c_rtc *info)
 {
 	unsigned int con, tmp;
 
@@ -361,19 +361,6 @@ static void s3c24xx_rtc_enable(struct s3c_rtc *info)
 	}
 }
 
-static void s3c24xx_rtc_disable(struct s3c_rtc *info)
-{
-	unsigned int con;
-
-	con = readw(info->base + S3C2410_RTCCON);
-	con &= ~S3C2410_RTCCON_RTCEN;
-	writew(con, info->base + S3C2410_RTCCON);
-
-	con = readb(info->base + S3C2410_TICNT);
-	con &= ~S3C2410_TICNT_ENABLE;
-	writeb(con, info->base + S3C2410_TICNT);
-}
-
 static void s3c6410_rtc_disable(struct s3c_rtc *info)
 {
 	unsigned int con;
@@ -538,53 +525,21 @@ static int s3c_rtc_resume(struct device *dev)
 #endif
 static SIMPLE_DEV_PM_OPS(s3c_rtc_pm_ops, s3c_rtc_suspend, s3c_rtc_resume);
 
-static void s3c24xx_rtc_irq(struct s3c_rtc *info, int mask)
-{
-	rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF);
-}
-
 static void s3c6410_rtc_irq(struct s3c_rtc *info, int mask)
 {
 	rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF);
 	writeb(mask, info->base + S3C2410_INTP);
 }
 
-static const struct s3c_rtc_data s3c2410_rtc_data = {
-	.irq_handler		= s3c24xx_rtc_irq,
-	.enable			= s3c24xx_rtc_enable,
-	.disable		= s3c24xx_rtc_disable,
-};
-
-static const struct s3c_rtc_data s3c2416_rtc_data = {
-	.irq_handler		= s3c24xx_rtc_irq,
-	.enable			= s3c24xx_rtc_enable,
-	.disable		= s3c24xx_rtc_disable,
-};
-
-static const struct s3c_rtc_data s3c2443_rtc_data = {
-	.irq_handler		= s3c24xx_rtc_irq,
-	.enable			= s3c24xx_rtc_enable,
-	.disable		= s3c24xx_rtc_disable,
-};
-
 static const struct s3c_rtc_data s3c6410_rtc_data = {
 	.needs_src_clk		= true,
 	.irq_handler		= s3c6410_rtc_irq,
-	.enable			= s3c24xx_rtc_enable,
+	.enable			= s3c6410_rtc_enable,
 	.disable		= s3c6410_rtc_disable,
 };
 
 static const __maybe_unused struct of_device_id s3c_rtc_dt_match[] = {
 	{
-		.compatible = "samsung,s3c2410-rtc",
-		.data = &s3c2410_rtc_data,
-	}, {
-		.compatible = "samsung,s3c2416-rtc",
-		.data = &s3c2416_rtc_data,
-	}, {
-		.compatible = "samsung,s3c2443-rtc",
-		.data = &s3c2443_rtc_data,
-	}, {
 		.compatible = "samsung,s3c6410-rtc",
 		.data = &s3c6410_rtc_data,
 	}, {
diff --git a/drivers/rtc/rtc-s3c.h b/drivers/rtc/rtc-s3c.h
index 44e9d6c9428f..11d7a1255ce4 100644
--- a/drivers/rtc/rtc-s3c.h
+++ b/drivers/rtc/rtc-s3c.h
@@ -21,9 +21,6 @@
 #define S3C2443_RTCCON_TICSEL	(1 << 4)
 #define S3C64XX_RTCCON_TICEN	(1 << 8)
 
-#define S3C2410_TICNT		S3C2410_RTCREG(0x44)
-#define S3C2410_TICNT_ENABLE	(1 << 7)
-
 #define S3C2410_RTCALM		S3C2410_RTCREG(0x50)
 #define S3C2410_RTCALM_ALMEN	(1 << 6)
 #define S3C2410_RTCALM_YEAREN	(1 << 5)

From bf7ab18cd741ae82ee8d8e356f73ce3003f6b2fc Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 30 Aug 2025 15:00:27 +0200
Subject: [PATCH 050/352] dt-bindings: rtc: s3c: Drop S3C2410

Samsung S3C24xx family of SoCs was removed the Linux kernel in the
commit 61b7f8920b17 ("ARM: s3c: remove all s3c24xx support"), in January
2023.  There are no in-kernel users of remaining S3C24xx compatibles.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250830130024.142815-6-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/s3c-rtc.yaml      | 40 ++-----------------
 1 file changed, 3 insertions(+), 37 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
index bf4e11d6dffb..338874e7ed7f 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml
@@ -13,9 +13,6 @@ properties:
   compatible:
     oneOf:
       - enum:
-          - samsung,s3c2410-rtc
-          - samsung,s3c2416-rtc
-          - samsung,s3c2443-rtc
           - samsung,s3c6410-rtc
       - items:
           - enum:
@@ -29,19 +26,12 @@ properties:
     maxItems: 1
 
   clocks:
-    description:
-      Must contain a list of phandle and clock specifier for the rtc
-      clock and in the case of a s3c6410 compatible controller, also
-      a source clock.
-    minItems: 1
     maxItems: 2
 
   clock-names:
-    description:
-      Must contain "rtc" and for a s3c6410 compatible controller
-      also "rtc_src".
-    minItems: 1
-    maxItems: 2
+    items:
+      - const: rtc
+      - const: rtc_src
 
   interrupts:
     description:
@@ -54,30 +44,6 @@ properties:
 
 allOf:
   - $ref: rtc.yaml#
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - samsung,s3c6410-rtc
-              - samsung,exynos3250-rtc
-    then:
-      properties:
-        clocks:
-          minItems: 2
-          maxItems: 2
-        clock-names:
-          items:
-            - const: rtc
-            - const: rtc_src
-    else:
-      properties:
-        clocks:
-          minItems: 1
-          maxItems: 1
-        clock-names:
-          items:
-            - const: rtc
 
 unevaluatedProperties: false
 

From a6f1a4f05970664004a9370459c6799c1b2f2dcf Mon Sep 17 00:00:00 2001
From: Josua Mayer <josua@solid-run.com>
Date: Mon, 25 Aug 2025 19:54:09 +0200
Subject: [PATCH 051/352] rtc: pcf2127: clear minute/second interrupt

PCF2127 can generate interrupt every full second or minute configured
from control and status register 1, bits MI (1) and SI (0).

On interrupt control register 2 bit MSF (7) is set and must be cleared
to continue normal operation.

While the driver never enables this interrupt on its own, users or
firmware may do so - e.g. as an easy way to test the interrupt.

Add preprocessor definition for MSF bit and include it in the irq
bitmask to ensure minute and second interrupts are cleared when fired.

This fixes an issue where the rtc enters a test mode and becomes
unresponsive after a second interrupt has fired and is not cleared in
time. In this state register writes to control registers have no
effect and the interrupt line is kept asserted [1]:

[1] userspace commands to put rtc into unresponsive state:
$ i2cget -f -y 2 0x51 0x00
0x04
$ i2cset -f -y 2 0x51 0x00 0x05 # set bit 0 SI
$ i2cget -f -y 2 0x51 0x00
0x84 # bit 8 EXT_TEST set
$ i2cset -f -y 2 0x51 0x00 0x05 # try overwrite control register
$ i2cget -f -y 2 0x51 0x00
0x84 # no change

Signed-off-by: Josua Mayer <josua@solid-run.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20250825-rtc-irq-v1-1-0133319406a7@solid-run.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 2e1ac0c42e93..3ba1de30e89c 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -42,6 +42,7 @@
 #define PCF2127_BIT_CTRL2_AF			BIT(4)
 #define PCF2127_BIT_CTRL2_TSF2			BIT(5)
 #define PCF2127_BIT_CTRL2_WDTF			BIT(6)
+#define PCF2127_BIT_CTRL2_MSF			BIT(7)
 /* Control register 3 */
 #define PCF2127_REG_CTRL3		0x02
 #define PCF2127_BIT_CTRL3_BLIE			BIT(0)
@@ -96,7 +97,8 @@
 #define PCF2127_CTRL2_IRQ_MASK ( \
 		PCF2127_BIT_CTRL2_AF | \
 		PCF2127_BIT_CTRL2_WDTF | \
-		PCF2127_BIT_CTRL2_TSF2)
+		PCF2127_BIT_CTRL2_TSF2 | \
+		PCF2127_BIT_CTRL2_MSF)
 
 #define PCF2127_MAX_TS_SUPPORTED	4
 

From 18a3510bc87d48deec0abb72bc9e0b2f8393ff0b Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 14 Jul 2025 08:08:45 +0200
Subject: [PATCH 052/352] rtc: efi: Remove wakeup functionality

The EFI rtc driver is used by non-x86 architectures only, and exposes
the get/set wakeup time functionality provided by the underlying
platform. This is usually broken on most platforms, and not widely used
to begin with [if at all], so let's just remove it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Feng Tang <feng.tang@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250714060843.4029171-6-ardb+git@google.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-efi.c | 76 ++-----------------------------------------
 1 file changed, 2 insertions(+), 74 deletions(-)

diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c
index fa8bf82df948..b4f44999ef0f 100644
--- a/drivers/rtc/rtc-efi.c
+++ b/drivers/rtc/rtc-efi.c
@@ -112,48 +112,6 @@ convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime)
 	return true;
 }
 
-static int efi_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
-{
-	efi_time_t eft;
-	efi_status_t status;
-
-	/*
-	 * As of EFI v1.10, this call always returns an unsupported status
-	 */
-	status = efi.get_wakeup_time((efi_bool_t *)&wkalrm->enabled,
-				     (efi_bool_t *)&wkalrm->pending, &eft);
-
-	if (status != EFI_SUCCESS)
-		return -EINVAL;
-
-	if (!convert_from_efi_time(&eft, &wkalrm->time))
-		return -EIO;
-
-	return rtc_valid_tm(&wkalrm->time);
-}
-
-static int efi_set_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
-{
-	efi_time_t eft;
-	efi_status_t status;
-
-	convert_to_efi_time(&wkalrm->time, &eft);
-
-	/*
-	 * XXX Fixme:
-	 * As of EFI 0.92 with the firmware I have on my
-	 * machine this call does not seem to work quite
-	 * right
-	 *
-	 * As of v1.10, this call always returns an unsupported status
-	 */
-	status = efi.set_wakeup_time((efi_bool_t)wkalrm->enabled, &eft);
-
-	dev_warn(dev, "write status is %d\n", (int)status);
-
-	return status == EFI_SUCCESS ? 0 : -EINVAL;
-}
-
 static int efi_read_time(struct device *dev, struct rtc_time *tm)
 {
 	efi_status_t status;
@@ -188,17 +146,13 @@ static int efi_set_time(struct device *dev, struct rtc_time *tm)
 
 static int efi_procfs(struct device *dev, struct seq_file *seq)
 {
-	efi_time_t        eft, alm;
+	efi_time_t        eft;
 	efi_time_cap_t    cap;
-	efi_bool_t        enabled, pending;
-	struct rtc_device *rtc = dev_get_drvdata(dev);
 
 	memset(&eft, 0, sizeof(eft));
-	memset(&alm, 0, sizeof(alm));
 	memset(&cap, 0, sizeof(cap));
 
 	efi.get_time(&eft, &cap);
-	efi.get_wakeup_time(&enabled, &pending, &alm);
 
 	seq_printf(seq,
 		   "Time\t\t: %u:%u:%u.%09u\n"
@@ -214,26 +168,6 @@ static int efi_procfs(struct device *dev, struct seq_file *seq)
 		/* XXX fixme: convert to string? */
 		seq_printf(seq, "Timezone\t: %u\n", eft.timezone);
 
-	if (test_bit(RTC_FEATURE_ALARM, rtc->features)) {
-		seq_printf(seq,
-			   "Alarm Time\t: %u:%u:%u.%09u\n"
-			   "Alarm Date\t: %u-%u-%u\n"
-			   "Alarm Daylight\t: %u\n"
-			   "Enabled\t\t: %s\n"
-			   "Pending\t\t: %s\n",
-			   alm.hour, alm.minute, alm.second, alm.nanosecond,
-			   alm.year, alm.month, alm.day,
-			   alm.daylight,
-			   enabled == 1 ? "yes" : "no",
-			   pending == 1 ? "yes" : "no");
-
-		if (alm.timezone == EFI_UNSPECIFIED_TIMEZONE)
-			seq_puts(seq, "Timezone\t: unspecified\n");
-		else
-			/* XXX fixme: convert to string? */
-			seq_printf(seq, "Timezone\t: %u\n", alm.timezone);
-	}
-
 	/*
 	 * now prints the capabilities
 	 */
@@ -249,8 +183,6 @@ static int efi_procfs(struct device *dev, struct seq_file *seq)
 static const struct rtc_class_ops efi_rtc_ops = {
 	.read_time	= efi_read_time,
 	.set_time	= efi_set_time,
-	.read_alarm	= efi_read_alarm,
-	.set_alarm	= efi_set_alarm,
 	.proc		= efi_procfs,
 };
 
@@ -271,11 +203,7 @@ static int __init efi_rtc_probe(struct platform_device *dev)
 	platform_set_drvdata(dev, rtc);
 
 	rtc->ops = &efi_rtc_ops;
-	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features);
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES))
-		set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features);
-	else
-		clear_bit(RTC_FEATURE_ALARM, rtc->features);
+	clear_bit(RTC_FEATURE_ALARM, rtc->features);
 
 	device_init_wakeup(&dev->dev, true);
 

From 84454c4e504b1fe86f77a898190d63b4193ca25d Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 7 Aug 2025 16:44:13 -0500
Subject: [PATCH 053/352] dt-bindings: rtc: Drop isil,isl12057.txt

The "isil,isl12057" compatible is already supported by rtc-ds1307.yaml,
so remove the old text binding.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250807214414.4172910-1-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/isil,isl12057.txt | 74 -------------------
 1 file changed, 74 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/rtc/isil,isl12057.txt

diff --git a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
deleted file mode 100644
index ff7c43555199..000000000000
--- a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
+++ /dev/null
@@ -1,74 +0,0 @@
-Intersil ISL12057 I2C RTC/Alarm chip
-
-ISL12057 is a trivial I2C device (it has simple device tree bindings,
-consisting of a compatible field, an address and possibly an interrupt
-line).
-
-Nonetheless, it also supports an option boolean property
-("wakeup-source") to handle the specific use-case found
-on at least three in-tree users of the chip (NETGEAR ReadyNAS 102, 104
-and 2120 ARM-based NAS); On those devices, the IRQ#2 pin of the chip
-(associated with the alarm supported by the driver) is not connected
-to the SoC but to a PMIC. It allows the device to be powered up when
-RTC alarm rings. In order to mark the device has a wakeup source and
-get access to the 'wakealarm' sysfs entry, this specific property can
-be set when the IRQ#2 pin of the chip is not connected to the SoC but
-can wake up the device.
-
-Required properties supported by the device:
-
- - "compatible": must be "isil,isl12057"
- - "reg": I2C bus address of the device
-
-Optional properties:
-
- - "wakeup-source": mark the chip as a wakeup source, independently of
-    the availability of an IRQ line connected to the SoC.
-
-
-Example isl12057 node without IRQ#2 pin connected (no alarm support):
-
-	isl12057: isl12057@68 {
-		compatible = "isil,isl12057";
-		reg = <0x68>;
-	};
-
-
-Example isl12057 node with IRQ#2 pin connected to main SoC via MPP6 (note
-that the pinctrl-related properties below are given for completeness and
-may not be required or may be different depending on your system or
-SoC, and the main function of the MPP used as IRQ line, i.e.
-"interrupt-parent" and "interrupts" are usually sufficient):
-
-		    pinctrl {
-				...
-
-				rtc_alarm_pin: rtc_alarm_pin {
-					marvell,pins = "mpp6";
-					marvell,function = "gpio";
-				};
-
-				...
-
-		    };
-
-	...
-
-	isl12057: isl12057@68 {
-		compatible = "isil,isl12057";
-		reg = <0x68>;
-		pinctrl-0 = <&rtc_alarm_pin>;
-		pinctrl-names = "default";
-		interrupt-parent = <&gpio0>;
-		interrupts = <6 IRQ_TYPE_EDGE_FALLING>;
-	};
-
-
-Example isl12057 node without IRQ#2 pin connected to the SoC but to a
-PMIC, allowing the device to be started based on configured alarm:
-
-	isl12057: isl12057@68 {
-		compatible = "isil,isl12057";
-		reg = <0x68>;
-		wakeup-source;
-	};

From f0ea5f6e75f6b8bbe5d393720bfaf804d04e383f Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Wed, 13 Aug 2025 18:15:03 +0200
Subject: [PATCH 054/352] rtc: remove unneeded 'fast_io' parameter in
 regmap_config

When using MMIO with regmap, fast_io is implied. No need to set it
again.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250813161517.4746-18-wsa+renesas@sang-engineering.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-meson.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/rtc/rtc-meson.c b/drivers/rtc/rtc-meson.c
index 47e9ebf58ffc..21eceb9e2e13 100644
--- a/drivers/rtc/rtc-meson.c
+++ b/drivers/rtc/rtc-meson.c
@@ -72,7 +72,6 @@ static const struct regmap_config meson_rtc_peripheral_regmap_config = {
 	.val_bits	= 32,
 	.reg_stride	= 4,
 	.max_register	= RTC_REG4,
-	.fast_io	= true,
 };
 
 /* RTC front-end serialiser controls */

From f2e44e5fb2de9a464b4fc94d8de071da7ebfda15 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 21 Aug 2025 16:57:01 -0500
Subject: [PATCH 055/352] dt-bindings: rtc: Fix Xicor X1205 vendor prefix

The vendor for the Xircom X1205 RTC is not Xircom, but Xicor which was
acquired by Intersil.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250821215703.869628-1-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/devicetree/bindings/rtc/trivial-rtc.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
index 587b7cd5806c..b47822370d6f 100644
--- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
@@ -85,8 +85,8 @@ properties:
       - via,vt8500-rtc
       # I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC
       - whwave,sd3078
-      # Xircom X1205 I2C RTC
-      - xircom,x1205
+      # Xicor/Intersil X1205 I2C RTC
+      - xicor,x1205
 
   reg:
     maxItems: 1

From 606d19ee37de3a72f1b6e95a4ea544f6f20dbb46 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 21 Aug 2025 16:57:02 -0500
Subject: [PATCH 056/352] rtc: x1205: Fix Xicor X1205 vendor prefix

The vendor for the X1205 RTC is not Xircom, but Xicor which was acquired
by Intersil. Since the I2C subsystem drops the vendor prefix for driver
matching, the vendor prefix hasn't mattered.

Fixes: 6875404fdb44 ("rtc: x1205: Add DT probing support")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250821215703.869628-2-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-x1205.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-x1205.c b/drivers/rtc/rtc-x1205.c
index 4bcd7ca32f27..b8a0fccef14e 100644
--- a/drivers/rtc/rtc-x1205.c
+++ b/drivers/rtc/rtc-x1205.c
@@ -669,7 +669,7 @@ static const struct i2c_device_id x1205_id[] = {
 MODULE_DEVICE_TABLE(i2c, x1205_id);
 
 static const struct of_device_id x1205_dt_ids[] = {
-	{ .compatible = "xircom,x1205", },
+	{ .compatible = "xicor,x1205", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, x1205_dt_ids);

From a531350d2fe58f7fc4516e555f22391dee94efd9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Le=20Goffic?= <clement.legoffic@foss.st.com>
Date: Tue, 15 Jul 2025 16:07:13 +0200
Subject: [PATCH 057/352] rtc: optee: fix memory leak on driver removal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a memory leak in case of driver removal.
Free the shared memory used for arguments exchanges between kernel and
OP-TEE RTC PTA.

Fixes: 81c2f059ab90 ("rtc: optee: add RTC driver for OP-TEE RTC PTA")
Signed-off-by: Clément Le Goffic <clement.legoffic@foss.st.com>
Link: https://lore.kernel.org/r/20250715-upstream-optee-rtc-v1-1-e0fdf8aae545@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index 9f8b5d4a8f6b..6b77c122fdc1 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -320,6 +320,7 @@ static int optee_rtc_remove(struct device *dev)
 {
 	struct optee_rtc *priv = dev_get_drvdata(dev);
 
+	tee_shm_free(priv->shm);
 	tee_client_close_session(priv->ctx, priv->session_id);
 	tee_client_close_context(priv->ctx);
 

From 44fee00f2139894b2ae4433f0661d70134b511c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Le=20Goffic?= <clement.legoffic@foss.st.com>
Date: Tue, 15 Jul 2025 16:07:14 +0200
Subject: [PATCH 058/352] rtc: optee: remove unnecessary memory operations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove memcpy by using directly the shared memory.
Remove memset be initialize variable to 0 on stack.

Signed-off-by: Clément Le Goffic <clement.legoffic@foss.st.com>
Link: https://lore.kernel.org/r/20250715-upstream-optee-rtc-v1-2-e0fdf8aae545@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index 6b77c122fdc1..b65953eb7ca1 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -97,18 +97,9 @@ static int optee_rtc_settime(struct device *dev, struct rtc_time *tm)
 	struct optee_rtc *priv = dev_get_drvdata(dev);
 	struct tee_ioctl_invoke_arg inv_arg = {0};
 	struct tee_param param[4] = {0};
-	struct optee_rtc_time optee_tm;
-	void *rtc_data;
+	struct optee_rtc_time *optee_tm;
 	int ret;
 
-	optee_tm.tm_sec = tm->tm_sec;
-	optee_tm.tm_min = tm->tm_min;
-	optee_tm.tm_hour = tm->tm_hour;
-	optee_tm.tm_mday = tm->tm_mday;
-	optee_tm.tm_mon = tm->tm_mon;
-	optee_tm.tm_year = tm->tm_year + 1900;
-	optee_tm.tm_wday = tm->tm_wday;
-
 	inv_arg.func = TA_CMD_RTC_SET_TIME;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
@@ -117,11 +108,17 @@ static int optee_rtc_settime(struct device *dev, struct rtc_time *tm)
 	param[0].u.memref.shm = priv->shm;
 	param[0].u.memref.size = sizeof(struct optee_rtc_time);
 
-	rtc_data = tee_shm_get_va(priv->shm, 0);
-	if (IS_ERR(rtc_data))
-		return PTR_ERR(rtc_data);
+	optee_tm = tee_shm_get_va(priv->shm, 0);
+	if (IS_ERR(optee_tm))
+		return PTR_ERR(optee_tm);
 
-	memcpy(rtc_data, &optee_tm, sizeof(struct optee_rtc_time));
+	optee_tm->tm_min = tm->tm_min;
+	optee_tm->tm_sec = tm->tm_sec;
+	optee_tm->tm_hour = tm->tm_hour;
+	optee_tm->tm_mday = tm->tm_mday;
+	optee_tm->tm_mon = tm->tm_mon;
+	optee_tm->tm_year = tm->tm_year + 1900;
+	optee_tm->tm_wday = tm->tm_wday;
 
 	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
 	if (ret < 0 || inv_arg.ret != 0)
@@ -241,14 +238,12 @@ static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
 static int optee_rtc_probe(struct device *dev)
 {
 	struct tee_client_device *rtc_device = to_tee_client_device(dev);
-	struct tee_ioctl_open_session_arg sess_arg;
+	struct tee_ioctl_open_session_arg sess_arg = {0};
 	struct optee_rtc *priv;
 	struct rtc_device *rtc;
 	struct tee_shm *shm;
 	int ret, err;
 
-	memset(&sess_arg, 0, sizeof(sess_arg));
-
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;

From 6266aea864fa5484f6e8313f913a69e794765fab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Le=20Goffic?= <clement.legoffic@foss.st.com>
Date: Tue, 15 Jul 2025 16:07:15 +0200
Subject: [PATCH 059/352] rtc: optee: add alarm related rtc ops to optee rtc
 driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add read_alarm and set_alarm ops from the rtc framework.
The support of an alarm is handled by a kernel thread waiting in OP-TEE
for an asynchronous notification that comes in the interrupt
handler of the alarm interruption on OP-TEE secure world.

Once the notification arrives, the kernel thread previously suspended
is rescheduled (this is handled by the OP-TEE kernel driver) and comes
back with the alarm information to the kernel.

A second session is therefore needed to enable/disable/cancel a waiting
alarm event as the kernel thread stopped in OP-TEE takes a form of mutex
on the session and so no one can use this session in parallel.

Signed-off-by: Clément Le Goffic <clement.legoffic@foss.st.com>
Link: https://lore.kernel.org/r/20250715-upstream-optee-rtc-v1-3-e0fdf8aae545@foss.st.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 434 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 413 insertions(+), 21 deletions(-)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index b65953eb7ca1..27db403e3047 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -5,19 +5,104 @@
 
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/rtc.h>
 #include <linux/tee_drv.h>
 
-#define RTC_INFO_VERSION	0x1
+#define RTC_INFO_VERSION			0x1
 
-#define TA_CMD_RTC_GET_INFO		0x0
-#define TA_CMD_RTC_GET_TIME		0x1
-#define TA_CMD_RTC_SET_TIME		0x2
-#define TA_CMD_RTC_GET_OFFSET		0x3
-#define TA_CMD_RTC_SET_OFFSET		0x4
+#define TA_RTC_FEATURE_CORRECTION		BIT(0)
+#define TA_RTC_FEATURE_ALARM			BIT(1)
+#define TA_RTC_FEATURE_WAKEUP_ALARM		BIT(2)
 
-#define TA_RTC_FEATURE_CORRECTION	BIT(0)
+enum rtc_optee_pta_cmd {
+	/*  PTA_CMD_RTC_GET_INFO - Get RTC information
+	 *
+	 * [out]        memref[0]  RTC buffer memory reference containing a struct pta_rtc_info
+	 */
+	PTA_CMD_RTC_GET_INF = 0x0,
+
+	/*
+	 * PTA_CMD_RTC_GET_TIME - Get time from RTC
+	 *
+	 * [out]    memref[0]  RTC buffer memory reference containing a struct pta_rtc_time
+	 */
+	PTA_CMD_RTC_GET_TIME = 0x1,
+
+	/*
+	 * PTA_CMD_RTC_SET_TIME - Set time from RTC
+	 *
+	 * [in]     memref[0]  RTC buffer memory reference containing a struct pta_rtc_time to be
+	 *                     used as RTC time
+	 */
+	PTA_CMD_RTC_SET_TIME = 0x2,
+
+	/*
+	 * PTA_CMD_RTC_GET_OFFSET - Get RTC offset
+	 *
+	 * [out]    value[0].a  RTC offset (signed 32bit value)
+	 */
+	PTA_CMD_RTC_GET_OFFSET = 0x3,
+
+	/*
+	 * PTA_CMD_RTC_SET_OFFSET - Set RTC offset
+	 *
+	 * [in]     value[0].a  RTC offset to be set (signed 32bit value)
+	 */
+	PTA_CMD_RTC_SET_OFFSET = 0x4,
+
+	/*
+	 * PTA_CMD_RTC_READ_ALARM - Read RTC alarm
+	 *
+	 * [out]     memref[0]  RTC buffer memory reference containing a struct pta_rtc_alarm
+	 */
+	PTA_CMD_RTC_READ_ALARM = 0x5,
+
+	/*
+	 * PTA_CMD_RTC_SET_ALARM - Set RTC alarm
+	 *
+	 * [in]     memref[0]  RTC buffer memory reference containing a struct pta_rtc_alarm to be
+	 *                     used as RTC alarm
+	 */
+	PTA_CMD_RTC_SET_ALARM = 0x6,
+
+	/*
+	 * PTA_CMD_RTC_ENABLE_ALARM - Enable Alarm
+	 *
+	 * [in]     value[0].a  RTC IRQ flag (uint32_t), 0 to disable the alarm, 1 to enable
+	 */
+	PTA_CMD_RTC_ENABLE_ALARM = 0x7,
+
+	/*
+	 * PTA_CMD_RTC_WAIT_ALARM - Get alarm event
+	 *
+	 * [out]     value[0].a  RTC wait alarm return status (uint32_t):
+	 *                       - 0: No alarm event
+	 *                       - 1: Alarm event occurred
+	 *                       - 2: Alarm event canceled
+	 */
+	PTA_CMD_RTC_WAIT_ALARM = 0x8,
+
+	/*
+	 * PTA_CMD_RTC_CANCEL_WAIT - Cancel wait for alarm event
+	 */
+	PTA_CMD_RTC_CANCEL_WAIT = 0x9,
+
+	/*
+	 * PTA_CMD_RTC_SET_WAKE_ALARM_STATUS - Set RTC wake alarm status flag
+	 *
+	 * [in]     value[0].a RTC IRQ wake alarm flag (uint32_t), 0 to disable the wake up
+	 *                     capability, 1 to enable.
+	 */
+	PTA_CMD_RTC_SET_WAKE_ALARM_STATUS = 0xA,
+};
+
+enum rtc_wait_alarm_status {
+	WAIT_ALARM_RESET = 0x0,
+	WAIT_ALARM_ALARM_OCCURRED = 0x1,
+	WAIT_ALARM_CANCELED = 0x2,
+};
 
 struct optee_rtc_time {
 	u32 tm_sec;
@@ -29,6 +114,12 @@ struct optee_rtc_time {
 	u32 tm_wday;
 };
 
+struct optee_rtc_alarm {
+	u8 enabled;
+	u8 pending;
+	struct optee_rtc_time time;
+};
+
 struct optee_rtc_info {
 	u64 version;
 	u64 features;
@@ -41,15 +132,21 @@ struct optee_rtc_info {
  * @dev:		OP-TEE based RTC device.
  * @ctx:		OP-TEE context handler.
  * @session_id:		RTC TA session identifier.
+ * @session2_id:	RTC wait alarm session identifier.
  * @shm:		Memory pool shared with RTC device.
  * @features:		Bitfield of RTC features
+ * @alarm_task:		RTC wait alamr task.
+ * @rtc:		RTC device.
  */
 struct optee_rtc {
 	struct device *dev;
 	struct tee_context *ctx;
 	u32 session_id;
+	u32 session2_id;
 	struct tee_shm *shm;
 	u64 features;
+	struct task_struct *alarm_task;
+	struct rtc_device *rtc;
 };
 
 static int optee_rtc_readtime(struct device *dev, struct rtc_time *tm)
@@ -60,7 +157,7 @@ static int optee_rtc_readtime(struct device *dev, struct rtc_time *tm)
 	struct tee_param param[4] = {0};
 	int ret;
 
-	inv_arg.func = TA_CMD_RTC_GET_TIME;
+	inv_arg.func = PTA_CMD_RTC_GET_TIME;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
 
@@ -100,7 +197,7 @@ static int optee_rtc_settime(struct device *dev, struct rtc_time *tm)
 	struct optee_rtc_time *optee_tm;
 	int ret;
 
-	inv_arg.func = TA_CMD_RTC_SET_TIME;
+	inv_arg.func = PTA_CMD_RTC_SET_TIME;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
 
@@ -137,7 +234,7 @@ static int optee_rtc_readoffset(struct device *dev, long *offset)
 	if (!(priv->features & TA_RTC_FEATURE_CORRECTION))
 		return -EOPNOTSUPP;
 
-	inv_arg.func = TA_CMD_RTC_GET_OFFSET;
+	inv_arg.func = PTA_CMD_RTC_GET_OFFSET;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
 
@@ -162,7 +259,7 @@ static int optee_rtc_setoffset(struct device *dev, long offset)
 	if (!(priv->features & TA_RTC_FEATURE_CORRECTION))
 		return -EOPNOTSUPP;
 
-	inv_arg.func = TA_CMD_RTC_SET_OFFSET;
+	inv_arg.func = PTA_CMD_RTC_SET_OFFSET;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
 
@@ -176,13 +273,228 @@ static int optee_rtc_setoffset(struct device *dev, long offset)
 	return 0;
 }
 
+static int optee_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct optee_rtc_alarm *optee_alarm;
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_READ_ALARM;
+	inv_arg.session = priv->session_id;
+	inv_arg.num_params = 1;
+
+	/* Fill invoke cmd params */
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+	param[0].u.memref.shm = priv->shm;
+	param[0].u.memref.size = sizeof(struct optee_rtc_alarm);
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	optee_alarm = tee_shm_get_va(priv->shm, 0);
+	if (IS_ERR(optee_alarm))
+		return PTR_ERR(alarm);
+
+	if (param[0].u.memref.size != sizeof(*optee_alarm))
+		return -EPROTO;
+
+	alarm->enabled = optee_alarm->enabled;
+	alarm->pending = optee_alarm->pending;
+	alarm->time.tm_sec = optee_alarm->time.tm_sec;
+	alarm->time.tm_min = optee_alarm->time.tm_min;
+	alarm->time.tm_hour = optee_alarm->time.tm_hour;
+	alarm->time.tm_mday = optee_alarm->time.tm_mday;
+	alarm->time.tm_mon = optee_alarm->time.tm_mon;
+	alarm->time.tm_year = optee_alarm->time.tm_year - 1900;
+	alarm->time.tm_wday = optee_alarm->time.tm_wday;
+	alarm->time.tm_yday = rtc_year_days(alarm->time.tm_mday,
+					    alarm->time.tm_mon,
+					    alarm->time.tm_year);
+
+	return 0;
+}
+
+static int optee_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct optee_rtc_alarm *optee_alarm;
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_SET_ALARM;
+	inv_arg.session = priv->session_id;
+	inv_arg.num_params = 1;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+	param[0].u.memref.shm = priv->shm;
+	param[0].u.memref.size = sizeof(struct optee_rtc_alarm);
+
+	optee_alarm = tee_shm_get_va(priv->shm, 0);
+	if (IS_ERR(optee_alarm))
+		return PTR_ERR(optee_alarm);
+
+	optee_alarm->enabled = alarm->enabled;
+	optee_alarm->pending = alarm->pending;
+	optee_alarm->time.tm_sec = alarm->time.tm_sec;
+	optee_alarm->time.tm_min = alarm->time.tm_min;
+	optee_alarm->time.tm_hour = alarm->time.tm_hour;
+	optee_alarm->time.tm_mday = alarm->time.tm_mday;
+	optee_alarm->time.tm_mon = alarm->time.tm_mon;
+	optee_alarm->time.tm_year = alarm->time.tm_year + 1900;
+	optee_alarm->time.tm_wday = alarm->time.tm_wday;
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	return 0;
+}
+
+static int optee_rtc_enable_alarm(struct device *dev, unsigned int enabled)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_ENABLE_ALARM;
+	inv_arg.session = priv->session_id;
+	inv_arg.num_params = 1;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT;
+	param[0].u.value.a = (bool)enabled;
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	return 0;
+}
+
 static const struct rtc_class_ops optee_rtc_ops = {
-	.read_time	= optee_rtc_readtime,
-	.set_time	= optee_rtc_settime,
-	.set_offset	= optee_rtc_setoffset,
-	.read_offset	= optee_rtc_readoffset,
+	.read_time		= optee_rtc_readtime,
+	.set_time		= optee_rtc_settime,
+	.set_offset		= optee_rtc_setoffset,
+	.read_offset		= optee_rtc_readoffset,
+	.read_alarm		= optee_rtc_read_alarm,
+	.set_alarm		= optee_rtc_set_alarm,
+	.alarm_irq_enable	= optee_rtc_enable_alarm,
 };
 
+static int optee_rtc_wait_alarm(struct device *dev, int *return_status)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_WAIT_ALARM;
+	inv_arg.session = priv->session2_id;
+	inv_arg.num_params = 1;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT;
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	*return_status = param[0].u.value.a;
+
+	return 0;
+}
+
+static int optee_rtc_cancel_wait_alarm(struct device *dev)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_CANCEL_WAIT;
+	inv_arg.session = priv->session_id;
+	inv_arg.num_params = 0;
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	return 0;
+}
+
+static int optee_rtc_set_alarm_wake_status(struct device *dev, bool status)
+{
+	struct optee_rtc *priv = dev_get_drvdata(dev);
+	struct tee_ioctl_invoke_arg inv_arg = {0};
+	struct tee_param param[1] = {0};
+	int ret;
+
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		return -EOPNOTSUPP;
+
+	inv_arg.func = PTA_CMD_RTC_SET_WAKE_ALARM_STATUS;
+	inv_arg.session = priv->session_id;
+	inv_arg.num_params = 1;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT;
+	param[0].u.value.a = status;
+
+	ret = tee_client_invoke_func(priv->ctx, &inv_arg, param);
+
+	if (ret < 0 || inv_arg.ret != 0)
+		return ret ? ret : -EPROTO;
+
+	return 0;
+}
+
+static int optee_rtc_handle_alarm_event(void *data)
+{
+	struct optee_rtc *priv = (struct optee_rtc *)data;
+	int wait_alarm_return_status = 0;
+	int ret;
+
+	while (!kthread_should_stop()) {
+		ret = optee_rtc_wait_alarm(priv->dev, &wait_alarm_return_status);
+		if (ret) {
+			dev_err(priv->dev, "Failed to wait for alarm: %d\n", ret);
+			return ret;
+		}
+		switch (wait_alarm_return_status) {
+		case WAIT_ALARM_ALARM_OCCURRED:
+			dev_dbg(priv->dev, "Alarm occurred\n");
+			rtc_update_irq(priv->rtc, 1, RTC_IRQF | RTC_AF);
+			break;
+		case WAIT_ALARM_CANCELED:
+			dev_dbg(priv->dev, "Alarm canceled\n");
+			break;
+		default:
+			dev_warn(priv->dev, "Unknown return status: %d\n",
+				 wait_alarm_return_status);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static int optee_rtc_read_info(struct device *dev, struct rtc_device *rtc,
 			       u64 *features)
 {
@@ -193,7 +505,7 @@ static int optee_rtc_read_info(struct device *dev, struct rtc_device *rtc,
 	struct optee_rtc_time *tm;
 	int ret;
 
-	inv_arg.func = TA_CMD_RTC_GET_INFO;
+	inv_arg.func = PTA_CMD_RTC_GET_INF;
 	inv_arg.session = priv->session_id;
 	inv_arg.num_params = 4;
 
@@ -238,6 +550,7 @@ static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
 static int optee_rtc_probe(struct device *dev)
 {
 	struct tee_client_device *rtc_device = to_tee_client_device(dev);
+	struct tee_ioctl_open_session_arg sess2_arg = {0};
 	struct tee_ioctl_open_session_arg sess_arg = {0};
 	struct optee_rtc *priv;
 	struct rtc_device *rtc;
@@ -252,12 +565,14 @@ static int optee_rtc_probe(struct device *dev)
 	if (IS_ERR(rtc))
 		return PTR_ERR(rtc);
 
+	priv->rtc = rtc;
+
 	/* Open context with TEE driver */
 	priv->ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, NULL);
 	if (IS_ERR(priv->ctx))
 		return -ENODEV;
 
-	/* Open session with rtc Trusted App */
+	/* Open first session with rtc Pseudo Trusted App */
 	export_uuid(sess_arg.uuid, &rtc_device->id.uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL;
 
@@ -269,6 +584,11 @@ static int optee_rtc_probe(struct device *dev)
 	}
 	priv->session_id = sess_arg.session;
 
+	/*
+	 * Shared memory is used for passing an instance of either struct optee_rtc_info,
+	 * struct optee_rtc_time or struct optee_rtc_alarm to OP-TEE service.
+	 * The former is by definition large enough to cover both parameter cases.
+	 */
 	shm = tee_shm_alloc_kernel_buf(priv->ctx, sizeof(struct optee_rtc_info));
 	if (IS_ERR(shm)) {
 		dev_err(priv->dev, "tee_shm_alloc_kernel_buf failed\n");
@@ -288,19 +608,69 @@ static int optee_rtc_probe(struct device *dev)
 		goto out_shm;
 	}
 
+	/* Handle feature's related setup before registering to rtc framework */
+	if (priv->features & TA_RTC_FEATURE_ALARM) {
+		priv->alarm_task = kthread_create(optee_rtc_handle_alarm_event,
+						  priv, "rtc_alarm_evt");
+		if (IS_ERR(priv->alarm_task)) {
+			dev_err(dev, "Failed to create alarm thread\n");
+			goto out_shm;
+		}
+
+		/*
+		 * In case of supported alarm feature on optee side, we create a kthread
+		 * that will, in a new optee session, call a PTA interface "rtc_wait_alarm".
+		 * This call return in case of alarm and in case of canceled alarm.
+		 * The new optee session is therefore only needed in this case as we cannot
+		 * use the same session for parallel calls to optee PTA.
+		 * Hence one session is reserved to wait for alarms and the other to make
+		 * standard calls to RTC PTA.
+		 */
+
+		/* Open second session with rtc Trusted App */
+		export_uuid(sess2_arg.uuid, &rtc_device->id.uuid);
+		sess2_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL;
+
+		ret = tee_client_open_session(priv->ctx, &sess2_arg, NULL);
+		if (ret < 0 || sess2_arg.ret != 0) {
+			dev_err(dev, "tee_client_open_session failed, err: %x\n", sess2_arg.ret);
+			err = -EINVAL;
+			goto out_thrd;
+		}
+		priv->session2_id = sess2_arg.session;
+
+		if (priv->features & TA_RTC_FEATURE_WAKEUP_ALARM)
+			device_init_wakeup(dev, true);
+	}
+
 	err = devm_rtc_register_device(rtc);
 	if (err)
-		goto out_shm;
+		goto out_wk;
 
 	/*
-	 * We must clear this bit after registering because rtc_register_device
-	 * will set it if it sees that .set_offset is provided.
+	 * We must clear those bits after registering because registering a rtc_device
+	 * will set them if it sees that .set_offset and .set_alarm are provided.
 	 */
 	if (!(priv->features & TA_RTC_FEATURE_CORRECTION))
 		clear_bit(RTC_FEATURE_CORRECTION, rtc->features);
+	if (!(priv->features & TA_RTC_FEATURE_ALARM))
+		clear_bit(RTC_FEATURE_ALARM, rtc->features);
+
+	/* Start the thread after the rtc is setup */
+	if (priv->alarm_task) {
+		wake_up_process(priv->alarm_task);
+		dev_dbg(dev, "Wait alarm thread successfully started\n");
+	}
 
 	return 0;
-
+out_wk:
+	if (priv->features & TA_RTC_FEATURE_ALARM) {
+		device_init_wakeup(dev, false);
+		tee_client_close_session(priv->ctx, priv->session2_id);
+	}
+out_thrd:
+	if (priv->features & TA_RTC_FEATURE_ALARM)
+		kthread_stop(priv->alarm_task);
 out_shm:
 	tee_shm_free(priv->shm);
 out_sess:
@@ -315,6 +685,13 @@ static int optee_rtc_remove(struct device *dev)
 {
 	struct optee_rtc *priv = dev_get_drvdata(dev);
 
+	if (priv->features & TA_RTC_FEATURE_ALARM) {
+		optee_rtc_cancel_wait_alarm(dev);
+		kthread_stop(priv->alarm_task);
+		device_init_wakeup(dev, false);
+		tee_client_close_session(priv->ctx, priv->session2_id);
+	}
+
 	tee_shm_free(priv->shm);
 	tee_client_close_session(priv->ctx, priv->session_id);
 	tee_client_close_context(priv->ctx);
@@ -322,6 +699,20 @@ static int optee_rtc_remove(struct device *dev)
 	return 0;
 }
 
+static int optee_rtc_suspend(struct device *dev)
+{
+	int res = optee_rtc_set_alarm_wake_status(dev, device_may_wakeup(dev));
+
+	if (res) {
+		dev_err(dev, "Unable to transmit wakeup information to optee rtc\n");
+		return res;
+	}
+
+	return 0;
+}
+
+DEFINE_SIMPLE_DEV_PM_OPS(optee_rtc_pm_ops, optee_rtc_suspend, NULL);
+
 static const struct tee_client_device_id optee_rtc_id_table[] = {
 	{UUID_INIT(0xf389f8c8, 0x845f, 0x496c,
 		   0x8b, 0xbe, 0xd6, 0x4b, 0xd2, 0x4c, 0x92, 0xfd)},
@@ -337,6 +728,7 @@ static struct tee_client_driver optee_rtc_driver = {
 		.bus		= &tee_bus_type,
 		.probe		= optee_rtc_probe,
 		.remove		= optee_rtc_remove,
+		.pm		= pm_sleep_ptr(&optee_rtc_pm_ops),
 	},
 };
 

From a6de182daa2b1a627d88a594526a0db4ac1e396e Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@riscstar.com>
Date: Mon, 25 Aug 2025 12:20:53 -0500
Subject: [PATCH 060/352] rtc: spacemit: support the SpacemiT P1 RTC

Add support for the RTC found in the SpacemiT P1 PMIC.  Initially
only setting and reading the time are supported.

The PMIC is implemented as a multi-function device.  This RTC is
probed based on this driver being named in a MFD cell in the simple
MFD I2C driver.

Signed-off-by: Alex Elder <elder@riscstar.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20250825172057.163883-5-elder@riscstar.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig           |  10 ++
 drivers/rtc/Makefile          |   1 +
 drivers/rtc/rtc-spacemit-p1.c | 167 ++++++++++++++++++++++++++++++++++
 3 files changed, 178 insertions(+)
 create mode 100644 drivers/rtc/rtc-spacemit-p1.c

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 64f6e9756aff..31d355b103d4 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -406,6 +406,16 @@ config RTC_DRV_MAX77686
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-max77686.
 
+config RTC_DRV_SPACEMIT_P1
+	tristate "SpacemiT P1 RTC"
+	depends on ARCH_SPACEMIT || COMPILE_TEST
+	select MFD_SPACEMIT_P1
+	default ARCH_SPACEMIT
+	help
+	  Enable support for the RTC function in the SpacemiT P1 PMIC.
+	  This driver can also be built as a module, which will be called
+	  "spacemit-p1-rtc".
+
 config RTC_DRV_NCT3018Y
 	tristate "Nuvoton NCT3018Y"
 	depends on OF
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 789bddfea99d..f41fdb4fabae 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -171,6 +171,7 @@ obj-$(CONFIG_RTC_DRV_SD2405AL)	+= rtc-sd2405al.o
 obj-$(CONFIG_RTC_DRV_SD3078)	+= rtc-sd3078.o
 obj-$(CONFIG_RTC_DRV_SH)	+= rtc-sh.o
 obj-$(CONFIG_RTC_DRV_SNVS)	+= rtc-snvs.o
+obj-$(CONFIG_RTC_DRV_SPACEMIT_P1)	+= rtc-spacemit-p1.o
 obj-$(CONFIG_RTC_DRV_SPEAR)	+= rtc-spear.o
 obj-$(CONFIG_RTC_DRV_STARFIRE)	+= rtc-starfire.o
 obj-$(CONFIG_RTC_DRV_STK17TA8)	+= rtc-stk17ta8.o
diff --git a/drivers/rtc/rtc-spacemit-p1.c b/drivers/rtc/rtc-spacemit-p1.c
new file mode 100644
index 000000000000..43ab62494bb4
--- /dev/null
+++ b/drivers/rtc/rtc-spacemit-p1.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for the RTC found in the SpacemiT P1 PMIC
+ *
+ * Copyright (C) 2025 by RISCstar Solutions Corporation.  All rights reserved.
+ */
+
+#include <linux/bits.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+
+#define MOD_NAME	"spacemit-p1-rtc"
+
+/*
+ * Six consecutive 1-byte registers hold the seconds, minutes, hours,
+ * day-of-month, month, and year (respectively).
+ *
+ * The range of values in these registers is:
+ *    seconds	0-59
+ *    minutes	0-59
+ *    hours	0-59
+ *    day	0-30 (struct tm is 1-31)
+ *    month	0-11
+ *    year	years since 2000 (struct tm is since 1900)
+ *
+ * Note that the day and month must be converted after reading and
+ * before writing.
+ */
+#define RTC_TIME		0x0d	/* Offset of the seconds register */
+
+#define RTC_CTRL		0x1d
+#define RTC_EN		BIT(2)
+
+/* Number of attempts to read a consistent time stamp before giving up */
+#define RTC_READ_TRIES		20	/* At least 1 */
+
+struct p1_rtc {
+	struct regmap *regmap;
+	struct rtc_device *rtc;
+};
+
+/*
+ * The P1 hardware documentation states that the register values are
+ * latched to ensure a consistent time snapshot within the registers,
+ * but these are in fact unstable due to a bug in the hardware design.
+ * So we loop until we get two identical readings.
+ */
+static int p1_rtc_read_time(struct device *dev, struct rtc_time *t)
+{
+	struct p1_rtc *p1 = dev_get_drvdata(dev);
+	struct regmap *regmap = p1->regmap;
+	u32 count = RTC_READ_TRIES;
+	u8 seconds;
+	u8 time[6];
+	int ret;
+
+	if (!regmap_test_bits(regmap, RTC_CTRL, RTC_EN))
+		return -EINVAL;		/* RTC is disabled */
+
+	ret = regmap_bulk_read(regmap, RTC_TIME, time, sizeof(time));
+	if (ret)
+		return ret;
+
+	do {
+		seconds = time[0];
+		ret = regmap_bulk_read(regmap, RTC_TIME, time, sizeof(time));
+		if (ret)
+			return ret;
+	} while (time[0] != seconds && --count);
+
+	if (!count)
+		return -EIO;		/* Unable to get a consistent result */
+
+	t->tm_sec = time[0] & GENMASK(5, 0);
+	t->tm_min = time[1] & GENMASK(5, 0);
+	t->tm_hour = time[2] & GENMASK(4, 0);
+	t->tm_mday = (time[3] & GENMASK(4, 0)) + 1;
+	t->tm_mon = time[4] & GENMASK(3, 0);
+	t->tm_year = (time[5] & GENMASK(5, 0)) + 100;
+
+	return 0;
+}
+
+/*
+ * The P1 hardware documentation states that values in the registers are
+ * latched so when written they represent a consistent time snapshot.
+ * Nevertheless, this is not guaranteed by the implementation, so we must
+ * disable the RTC while updating it.
+ */
+static int p1_rtc_set_time(struct device *dev, struct rtc_time *t)
+{
+	struct p1_rtc *p1 = dev_get_drvdata(dev);
+	struct regmap *regmap = p1->regmap;
+	u8 time[6];
+	int ret;
+
+	time[0] = t->tm_sec;
+	time[1] = t->tm_min;
+	time[2] = t->tm_hour;
+	time[3] = t->tm_mday - 1;
+	time[4] = t->tm_mon;
+	time[5] = t->tm_year - 100;
+
+	/* Disable the RTC to update; re-enable again when done */
+	ret = regmap_clear_bits(regmap, RTC_CTRL, RTC_EN);
+	if (ret)
+		return ret;
+
+	/* If something goes wrong, leave the RTC disabled */
+	ret = regmap_bulk_write(regmap, RTC_TIME, time, sizeof(time));
+	if (ret)
+		return ret;
+
+	return regmap_set_bits(regmap, RTC_CTRL, RTC_EN);
+}
+
+static const struct rtc_class_ops p1_rtc_class_ops = {
+	.read_time = p1_rtc_read_time,
+	.set_time = p1_rtc_set_time,
+};
+
+static int p1_rtc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rtc_device *rtc;
+	struct p1_rtc *p1;
+
+	p1 = devm_kzalloc(dev, sizeof(*p1), GFP_KERNEL);
+	if (!p1)
+		return -ENOMEM;
+	dev_set_drvdata(dev, p1);
+
+	p1->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!p1->regmap)
+		return dev_err_probe(dev, -ENODEV, "failed to get regmap\n");
+
+	rtc = devm_rtc_allocate_device(dev);
+	if (IS_ERR(rtc))
+		return dev_err_probe(dev, PTR_ERR(rtc),
+				     "error allocating device\n");
+	p1->rtc = rtc;
+
+	rtc->ops = &p1_rtc_class_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->range_max = RTC_TIMESTAMP_END_2063;
+
+	clear_bit(RTC_FEATURE_ALARM, rtc->features);
+	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features);
+
+	return devm_rtc_register_device(rtc);
+}
+
+static struct platform_driver p1_rtc_driver = {
+	.probe = p1_rtc_probe,
+	.driver = {
+		.name = MOD_NAME,
+	},
+};
+
+module_platform_driver(p1_rtc_driver);
+
+MODULE_DESCRIPTION("SpacemiT P1 RTC driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" MOD_NAME);

From e8fe3f07a357c39d429e02ca34f740692d88967a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 19 Aug 2025 18:10:13 +0200
Subject: [PATCH 061/352] 9p/trans_fd: p9_fd_request: kick rx thread if EPOLLIN

p9_read_work() doesn't set Rworksched and doesn't do schedule_work(m->rq)
if list_empty(&m->req_list).

However, if the pipe is full, we need to read more data and this used to
work prior to commit aaec5a95d59615 ("pipe_read: don't wake up the writer
if the pipe is still full").

p9_read_work() does p9_fd_read() -> ... -> anon_pipe_read() which (before
the commit above) triggered the unnecessary wakeup. This wakeup calls
p9_pollwake() which kicks p9_poll_workfn() -> p9_poll_mux(), p9_poll_mux()
will notice EPOLLIN and schedule_work(&m->rq).

This no longer happens after the optimization above, change p9_fd_request()
to use p9_poll_mux() instead of only checking for EPOLLOUT.

Reported-by: syzbot+d1b5dace43896bc386c3@syzkaller.appspotmail.com
Tested-by: syzbot+d1b5dace43896bc386c3@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68a2de8f.050a0220.e29e5.0097.GAE@google.com/
Link: https://lore.kernel.org/all/67dedd2f.050a0220.31a16b.003f.GAE@google.com/
Co-developed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Message-ID: <20250819161013.GB11345@redhat.com>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 net/9p/trans_fd.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 8992d8bebbdd..a516745f732f 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -666,7 +666,6 @@ static void p9_poll_mux(struct p9_conn *m)
 
 static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 {
-	__poll_t n;
 	int err;
 	struct p9_trans_fd *ts = client->trans;
 	struct p9_conn *m = &ts->conn;
@@ -686,13 +685,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 	list_add_tail(&req->req_list, &m->unsent_req_list);
 	spin_unlock(&m->req_lock);
 
-	if (test_and_clear_bit(Wpending, &m->wsched))
-		n = EPOLLOUT;
-	else
-		n = p9_fd_poll(m->client, NULL, NULL);
-
-	if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
-		schedule_work(&m->wq);
+	p9_poll_mux(m);
 
 	return 0;
 }

From f0c260f175510e7e8a518e8e09bd57a96188f108 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Thu, 18 Sep 2025 13:04:47 +0530
Subject: [PATCH 062/352] ntb_hw_amd: Update amd_ntb_get_link_status to support
 latest generation secondary topology

In the NTB secondary topology configuration of the latest generation,
the device behaves like an endpoint. Hence, add endpoint support and
update amd_ntb_get_link_status to accommodate endpoint devices.

Co-developed-by: Sanath S <Sanath.S@amd.com>
Signed-off-by: Sanath S <Sanath.S@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/amd/ntb_hw_amd.c | 18 +++++++++++++++++-
 drivers/ntb/hw/amd/ntb_hw_amd.h |  1 +
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index 63ceed89b62e..1a163596ddf5 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -197,13 +197,22 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx,
 
 static int amd_ntb_get_link_status(struct amd_ntb_dev *ndev)
 {
-	struct pci_dev *pdev = NULL;
+	struct pci_dev *pdev = ndev->ntb.pdev;
 	struct pci_dev *pci_swds = NULL;
 	struct pci_dev *pci_swus = NULL;
 	u32 stat;
 	int rc;
 
 	if (ndev->ntb.topo == NTB_TOPO_SEC) {
+		if (ndev->dev_data->is_endpoint) {
+			rc = pcie_capability_read_dword(pdev, PCI_EXP_LNKCTL, &stat);
+			if (rc)
+				return rc;
+
+			ndev->lnk_sta = stat;
+			return 0;
+		}
+
 		/* Locate the pointer to Downstream Switch for this device */
 		pci_swds = pci_upstream_bridge(ndev->ntb.pdev);
 		if (pci_swds) {
@@ -1311,6 +1320,11 @@ static const struct ntb_dev_data dev_data[] = {
 		.mw_count = 2,
 		.mw_idx = 2,
 	},
+	{ /* for device 0x17d7 */
+		.mw_count = 2,
+		.mw_idx = 2,
+		.is_endpoint = true,
+	},
 };
 
 static const struct pci_device_id amd_ntb_pci_tbl[] = {
@@ -1319,6 +1333,8 @@ static const struct pci_device_id amd_ntb_pci_tbl[] = {
 	{ PCI_VDEVICE(AMD, 0x14c0), (kernel_ulong_t)&dev_data[1] },
 	{ PCI_VDEVICE(AMD, 0x14c3), (kernel_ulong_t)&dev_data[1] },
 	{ PCI_VDEVICE(AMD, 0x155a), (kernel_ulong_t)&dev_data[1] },
+	{ PCI_VDEVICE(AMD, 0x17d4), (kernel_ulong_t)&dev_data[1] },
+	{ PCI_VDEVICE(AMD, 0x17d7), (kernel_ulong_t)&dev_data[2] },
 	{ PCI_VDEVICE(HYGON, 0x145b), (kernel_ulong_t)&dev_data[0] },
 	{ 0, }
 };
diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h
index 5f337b1572a0..e8c3165fa38b 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.h
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.h
@@ -168,6 +168,7 @@ enum {
 struct ntb_dev_data {
 	const unsigned char mw_count;
 	const unsigned int mw_idx;
+	const bool is_endpoint;
 };
 
 struct amd_ntb_dev;

From eb4431bf8823cc55be6c705c122980be0690a904 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Thu, 18 Sep 2025 13:04:48 +0530
Subject: [PATCH 063/352] MAINTAINERS: Update for the NTB AMD driver maintainer

Adding myself to the maintainers list for the ntb_hw_amd driver.

Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..3210b975e46b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18027,6 +18027,7 @@ F:	Documentation/core-api/symbol-namespaces.rst
 F:	scripts/nsdeps
 
 NTB AMD DRIVER
+M:	Basavaraj Natikar <Basavaraj.Natikar@amd.com>
 M:	Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
 L:	ntb@lists.linux.dev
 S:	Supported

From 3db835dd8f9a78e9709cb48b77d89b41792e9281 Mon Sep 17 00:00:00 2001
From: fuyuanli <fuyuanli0722@gmail.com>
Date: Mon, 25 Aug 2025 17:15:08 +0800
Subject: [PATCH 064/352] ntb: Add mutex to make link_event_callback executed
 linearly.

Since the CPU selected by schedule_work is uncertain, multiple link_event
callbacks may be executed at same time. For example, after peer's link is
up, it is down quickly before local link_work completed. If link_cleanup
is added to the workqueue of another CPU, then link_work and link_cleanup
may be executed at the same time. So add a mutex to prevent them from being
executed concurrently.

Signed-off-by: fuyuanli <fuyuanli@didiglobal.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb_transport.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 4f775c3e218f..eb875e3db2e3 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -59,6 +59,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
+#include <linux/mutex.h>
 #include "linux/ntb.h"
 #include "linux/ntb_transport.h"
 
@@ -241,6 +242,9 @@ struct ntb_transport_ctx {
 	struct work_struct link_cleanup;
 
 	struct dentry *debugfs_node_dir;
+
+	/* Make sure workq of link event be executed serially */
+	struct mutex link_event_lock;
 };
 
 enum {
@@ -1024,6 +1028,7 @@ static void ntb_transport_link_cleanup_work(struct work_struct *work)
 	struct ntb_transport_ctx *nt =
 		container_of(work, struct ntb_transport_ctx, link_cleanup);
 
+	guard(mutex)(&nt->link_event_lock);
 	ntb_transport_link_cleanup(nt);
 }
 
@@ -1047,6 +1052,8 @@ static void ntb_transport_link_work(struct work_struct *work)
 	u32 val;
 	int rc = 0, i, spad;
 
+	guard(mutex)(&nt->link_event_lock);
+
 	/* send the local info, in the opposite order of the way we read it */
 
 	if (nt->use_msi) {

From 5ad865862a0fd349163243e1834ed98ba9b81905 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 2 Jul 2025 18:48:33 +0200
Subject: [PATCH 065/352] NTB: epf: Allow arbitrary BAR mapping

The NTB epf host driver assumes the BAR number associated with a memory
window is just incremented from the BAR number associated with MW1. This
seems to have been enough so far but this is not really how the endpoint
side work and the two could easily become mis-aligned.

ntb_epf_mw_to_bar() even assumes that the BAR number is the memory window
index + 2, which means the function only returns a proper result if BAR_2
is associated with MW1.

Instead, fully describe and allow arbitrary NTB BAR mapping.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/epf/ntb_hw_epf.c | 103 ++++++++++++++++----------------
 1 file changed, 53 insertions(+), 50 deletions(-)

diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c
index 00f0e78f685b..2b51156e01b0 100644
--- a/drivers/ntb/hw/epf/ntb_hw_epf.c
+++ b/drivers/ntb/hw/epf/ntb_hw_epf.c
@@ -49,6 +49,7 @@
 #define NTB_EPF_COMMAND_TIMEOUT	1000 /* 1 Sec */
 
 enum pci_barno {
+	NO_BAR = -1,
 	BAR_0,
 	BAR_1,
 	BAR_2,
@@ -57,16 +58,26 @@ enum pci_barno {
 	BAR_5,
 };
 
+enum epf_ntb_bar {
+	BAR_CONFIG,
+	BAR_PEER_SPAD,
+	BAR_DB,
+	BAR_MW1,
+	BAR_MW2,
+	BAR_MW3,
+	BAR_MW4,
+	NTB_BAR_NUM,
+};
+
+#define NTB_EPF_MAX_MW_COUNT	(NTB_BAR_NUM - BAR_MW1)
+
 struct ntb_epf_dev {
 	struct ntb_dev ntb;
 	struct device *dev;
 	/* Mutex to protect providing commands to NTB EPF */
 	struct mutex cmd_lock;
 
-	enum pci_barno ctrl_reg_bar;
-	enum pci_barno peer_spad_reg_bar;
-	enum pci_barno db_reg_bar;
-	enum pci_barno mw_bar;
+	const enum pci_barno *barno_map;
 
 	unsigned int mw_count;
 	unsigned int spad_count;
@@ -85,17 +96,6 @@ struct ntb_epf_dev {
 
 #define ntb_ndev(__ntb) container_of(__ntb, struct ntb_epf_dev, ntb)
 
-struct ntb_epf_data {
-	/* BAR that contains both control region and self spad region */
-	enum pci_barno ctrl_reg_bar;
-	/* BAR that contains peer spad region */
-	enum pci_barno peer_spad_reg_bar;
-	/* BAR that contains Doorbell region and Memory window '1' */
-	enum pci_barno db_reg_bar;
-	/* BAR that contains memory windows*/
-	enum pci_barno mw_bar;
-};
-
 static int ntb_epf_send_command(struct ntb_epf_dev *ndev, u32 command,
 				u32 argument)
 {
@@ -144,7 +144,7 @@ static int ntb_epf_mw_to_bar(struct ntb_epf_dev *ndev, int idx)
 		return -EINVAL;
 	}
 
-	return idx + 2;
+	return ndev->barno_map[BAR_MW1 + idx];
 }
 
 static int ntb_epf_mw_count(struct ntb_dev *ntb, int pidx)
@@ -413,7 +413,9 @@ static int ntb_epf_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx,
 		return -EINVAL;
 	}
 
-	bar = idx + ndev->mw_bar;
+	bar = ntb_epf_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
 
 	mw_size = pci_resource_len(ntb->pdev, bar);
 
@@ -455,7 +457,9 @@ static int ntb_epf_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
 	if (idx == 0)
 		offset = readl(ndev->ctrl_reg + NTB_EPF_MW1_OFFSET);
 
-	bar = idx + ndev->mw_bar;
+	bar = ntb_epf_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
 
 	if (base)
 		*base = pci_resource_start(ndev->ntb.pdev, bar) + offset;
@@ -560,6 +564,11 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)
 	ndev->mw_count = readl(ndev->ctrl_reg + NTB_EPF_MW_COUNT);
 	ndev->spad_count = readl(ndev->ctrl_reg + NTB_EPF_SPAD_COUNT);
 
+	if (ndev->mw_count > NTB_EPF_MAX_MW_COUNT) {
+		dev_err(dev, "Unsupported MW count: %u\n", ndev->mw_count);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -596,14 +605,15 @@ static int ntb_epf_init_pci(struct ntb_epf_dev *ndev,
 		dev_warn(&pdev->dev, "Cannot DMA highmem\n");
 	}
 
-	ndev->ctrl_reg = pci_iomap(pdev, ndev->ctrl_reg_bar, 0);
+	ndev->ctrl_reg = pci_iomap(pdev, ndev->barno_map[BAR_CONFIG], 0);
 	if (!ndev->ctrl_reg) {
 		ret = -EIO;
 		goto err_pci_regions;
 	}
 
-	if (ndev->peer_spad_reg_bar) {
-		ndev->peer_spad_reg = pci_iomap(pdev, ndev->peer_spad_reg_bar, 0);
+	if (ndev->barno_map[BAR_PEER_SPAD] != ndev->barno_map[BAR_CONFIG]) {
+		ndev->peer_spad_reg = pci_iomap(pdev,
+						ndev->barno_map[BAR_PEER_SPAD], 0);
 		if (!ndev->peer_spad_reg) {
 			ret = -EIO;
 			goto err_pci_regions;
@@ -614,7 +624,7 @@ static int ntb_epf_init_pci(struct ntb_epf_dev *ndev,
 		ndev->peer_spad_reg = ndev->ctrl_reg + spad_off  + spad_sz;
 	}
 
-	ndev->db_reg = pci_iomap(pdev, ndev->db_reg_bar, 0);
+	ndev->db_reg = pci_iomap(pdev, ndev->barno_map[BAR_DB], 0);
 	if (!ndev->db_reg) {
 		ret = -EIO;
 		goto err_pci_regions;
@@ -659,12 +669,7 @@ static void ntb_epf_cleanup_isr(struct ntb_epf_dev *ndev)
 static int ntb_epf_pci_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *id)
 {
-	enum pci_barno peer_spad_reg_bar = BAR_1;
-	enum pci_barno ctrl_reg_bar = BAR_0;
-	enum pci_barno db_reg_bar = BAR_2;
-	enum pci_barno mw_bar = BAR_2;
 	struct device *dev = &pdev->dev;
-	struct ntb_epf_data *data;
 	struct ntb_epf_dev *ndev;
 	int ret;
 
@@ -675,18 +680,10 @@ static int ntb_epf_pci_probe(struct pci_dev *pdev,
 	if (!ndev)
 		return -ENOMEM;
 
-	data = (struct ntb_epf_data *)id->driver_data;
-	if (data) {
-		peer_spad_reg_bar = data->peer_spad_reg_bar;
-		ctrl_reg_bar = data->ctrl_reg_bar;
-		db_reg_bar = data->db_reg_bar;
-		mw_bar = data->mw_bar;
-	}
+	ndev->barno_map = (const enum pci_barno *)id->driver_data;
+	if (!ndev->barno_map)
+		return -EINVAL;
 
-	ndev->peer_spad_reg_bar = peer_spad_reg_bar;
-	ndev->ctrl_reg_bar = ctrl_reg_bar;
-	ndev->db_reg_bar = db_reg_bar;
-	ndev->mw_bar = mw_bar;
 	ndev->dev = dev;
 
 	ntb_epf_init_struct(ndev, pdev);
@@ -730,30 +727,36 @@ static void ntb_epf_pci_remove(struct pci_dev *pdev)
 	ntb_epf_deinit_pci(ndev);
 }
 
-static const struct ntb_epf_data j721e_data = {
-	.ctrl_reg_bar = BAR_0,
-	.peer_spad_reg_bar = BAR_1,
-	.db_reg_bar = BAR_2,
-	.mw_bar = BAR_2,
+static const enum pci_barno j721e_map[NTB_BAR_NUM] = {
+	[BAR_CONFIG]	= BAR_0,
+	[BAR_PEER_SPAD]	= BAR_1,
+	[BAR_DB]	= BAR_2,
+	[BAR_MW1]	= BAR_2,
+	[BAR_MW2]	= BAR_3,
+	[BAR_MW3]	= BAR_4,
+	[BAR_MW4]	= BAR_5
 };
 
-static const struct ntb_epf_data mx8_data = {
-	.ctrl_reg_bar = BAR_0,
-	.peer_spad_reg_bar = BAR_0,
-	.db_reg_bar = BAR_2,
-	.mw_bar = BAR_4,
+static const enum pci_barno mx8_map[NTB_BAR_NUM] = {
+	[BAR_CONFIG]	= BAR_0,
+	[BAR_PEER_SPAD]	= BAR_0,
+	[BAR_DB]	= BAR_2,
+	[BAR_MW1]	= BAR_4,
+	[BAR_MW2]	= BAR_5,
+	[BAR_MW3]	= NO_BAR,
+	[BAR_MW4]	= NO_BAR
 };
 
 static const struct pci_device_id ntb_epf_pci_tbl[] = {
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_J721E),
 		.class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00,
-		.driver_data = (kernel_ulong_t)&j721e_data,
+		.driver_data = (kernel_ulong_t)j721e_map,
 	},
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, 0x0809),
 		.class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00,
-		.driver_data = (kernel_ulong_t)&mx8_data,
+		.driver_data = (kernel_ulong_t)mx8_map,
 	},
 	{ },
 };

From 006824a1cb3bd4001745a2b1cc83c43fad522851 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 2 Jul 2025 18:48:34 +0200
Subject: [PATCH 066/352] NTB: epf: Add Renesas rcar support

Add virtual non-transparent bridge support for Renesas rcar platform

Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/epf/ntb_hw_epf.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c
index 2b51156e01b0..d3ecf25a5162 100644
--- a/drivers/ntb/hw/epf/ntb_hw_epf.c
+++ b/drivers/ntb/hw/epf/ntb_hw_epf.c
@@ -747,6 +747,16 @@ static const enum pci_barno mx8_map[NTB_BAR_NUM] = {
 	[BAR_MW4]	= NO_BAR
 };
 
+static const enum pci_barno rcar_barno[NTB_BAR_NUM] = {
+	[BAR_CONFIG]	= BAR_0,
+	[BAR_PEER_SPAD]	= BAR_0,
+	[BAR_DB]	= BAR_4,
+	[BAR_MW1]	= BAR_2,
+	[BAR_MW2]	= NO_BAR,
+	[BAR_MW3]	= NO_BAR,
+	[BAR_MW4]	= NO_BAR,
+};
+
 static const struct pci_device_id ntb_epf_pci_tbl[] = {
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_J721E),
@@ -758,6 +768,11 @@ static const struct pci_device_id ntb_epf_pci_tbl[] = {
 		.class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00,
 		.driver_data = (kernel_ulong_t)mx8_map,
 	},
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0030),
+		.class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00,
+		.driver_data = (kernel_ulong_t)rcar_barno,
+	},
 	{ },
 };
 

From 623fa18f6c94e589b29c4e6277943364f1bb71d6 Mon Sep 17 00:00:00 2001
From: "Randall P. Embry" <rpembry@gmail.com>
Date: Fri, 26 Sep 2025 18:27:29 +0900
Subject: [PATCH 067/352] 9p: clean up comment typos
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a few minor typos in comments (e.g. "trasnport" → "transport").

Signed-off-by: Randall P. Embry <rpembry@gmail.com>
Message-ID: <20250926-v9fs_misc-v1-1-a8b3907fc04d@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/v9fs.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 77e9c4387c1d..01e70a464b60 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -438,8 +438,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		v9ses->flags &= ~V9FS_ACCESS_MASK;
 		v9ses->flags |= V9FS_ACCESS_USER;
 	}
-	/*FIXME !! */
-	/* for legacy mode, fall back to V9FS_ACCESS_ANY */
+	/* FIXME: for legacy mode, fall back to V9FS_ACCESS_ANY */
 	if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) &&
 		((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) {
 
@@ -450,7 +449,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	if (!v9fs_proto_dotl(v9ses) ||
 		!((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
 		/*
-		 * We support ACL checks on clinet only if the protocol is
+		 * We support ACL checks on client only if the protocol is
 		 * 9P2000.L and access is V9FS_ACCESS_CLIENT.
 		 */
 		v9ses->flags &= ~V9FS_ACL_MASK;
@@ -669,7 +668,7 @@ static int __init init_v9fs(void)
 	int err;
 
 	pr_info("Installing v9fs 9p2000 file system support\n");
-	/* TODO: Setup list of registered trasnport modules */
+	/* TODO: Setup list of registered transport modules */
 
 	err = v9fs_init_inode_cache();
 	if (err < 0) {

From 86db0c32f16c5538ddb740f54669ace8f3a1f3d7 Mon Sep 17 00:00:00 2001
From: "Randall P. Embry" <rpembry@gmail.com>
Date: Fri, 26 Sep 2025 18:27:30 +0900
Subject: [PATCH 068/352] 9p: fix /sys/fs/9p/caches overwriting itself
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

caches_show() overwrote its buffer on each iteration,
so only the last cache tag was visible in sysfs output.

Properly append with snprintf(buf + count, …).

Signed-off-by: Randall P. Embry <rpembry@gmail.com>
Message-ID: <20250926-v9fs_misc-v1-2-a8b3907fc04d@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/v9fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 01e70a464b60..4d289c56578f 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -560,7 +560,7 @@ static ssize_t caches_show(struct kobject *kobj,
 	spin_lock(&v9fs_sessionlist_lock);
 	list_for_each_entry(v9ses, &v9fs_sessionlist, slist) {
 		if (v9ses->cachetag) {
-			n = snprintf(buf, limit, "%s\n", v9ses->cachetag);
+			n = snprintf(buf + count, limit, "%s\n", v9ses->cachetag);
 			if (n < 0) {
 				count = n;
 				break;

From 528f218b31aac4bbfc58914d43766a22ab545d48 Mon Sep 17 00:00:00 2001
From: "Randall P. Embry" <rpembry@gmail.com>
Date: Fri, 26 Sep 2025 18:27:31 +0900
Subject: [PATCH 069/352] 9p: sysfs_init: don't hardcode error to ENOMEM

v9fs_sysfs_init() always returned -ENOMEM on failure;
return the actual sysfs_create_group() error instead.

Signed-off-by: Randall P. Embry <rpembry@gmail.com>
Message-ID: <20250926-v9fs_misc-v1-3-a8b3907fc04d@codewreck.org>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 fs/9p/v9fs.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 4d289c56578f..a020a8f00a1a 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -596,13 +596,16 @@ static const struct attribute_group v9fs_attr_group = {
 
 static int __init v9fs_sysfs_init(void)
 {
+	int ret;
+
 	v9fs_kobj = kobject_create_and_add("9p", fs_kobj);
 	if (!v9fs_kobj)
 		return -ENOMEM;
 
-	if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) {
+	ret = sysfs_create_group(v9fs_kobj, &v9fs_attr_group);
+	if (ret) {
 		kobject_put(v9fs_kobj);
-		return -ENOMEM;
+		return ret;
 	}
 
 	return 0;

From 27e06650a5eafe832a90fd2604f0c5e920857fae Mon Sep 17 00:00:00 2001
From: Wang Haoran <haoranwangsec@gmail.com>
Date: Sat, 20 Sep 2025 15:44:41 +0800
Subject: [PATCH 070/352] scsi: target: target_core_configfs: Add length check
 to avoid buffer overflow

A buffer overflow arises from the usage of snprintf to write into the
buffer "buf" in target_lu_gp_members_show function located in
/drivers/target/target_core_configfs.c. This buffer is allocated with
size LU_GROUP_NAME_BUF (256 bytes).

snprintf(...) formats multiple strings into buf with the HBA name
(hba->hba_group.cg_item), a slash character, a devicename (dev->
dev_group.cg_item) and a newline character, the total formatted string
length may exceed the buffer size of 256 bytes.

Since snprintf() returns the total number of bytes that would have been
written (the length of %s/%sn ), this value may exceed the buffer length
(256 bytes) passed to memcpy(), this will ultimately cause function
memcpy reporting a buffer overflow error.

An additional check of the return value of snprintf() can avoid this
buffer overflow.

Reported-by: Wang Haoran <haoranwangsec@gmail.com>
Reported-by: ziiiro <yuanmingbuaa@gmail.com>
Signed-off-by: Wang Haoran <haoranwangsec@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_configfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0904ecae253a..b19acd662726 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2774,7 +2774,7 @@ static ssize_t target_lu_gp_members_show(struct config_item *item, char *page)
 			config_item_name(&dev->dev_group.cg_item));
 		cur_len++; /* Extra byte for NULL terminator */
 
-		if ((cur_len + len) > PAGE_SIZE) {
+		if ((cur_len + len) > PAGE_SIZE || cur_len > LU_GROUP_NAME_BUF) {
 			pr_warn("Ran out of lu_gp_show_attr"
 				"_members buffer\n");
 			break;

From 285654d58a747eb431ee538c803c077d90525674 Mon Sep 17 00:00:00 2001
From: John Meneghini <jmeneghi@redhat.com>
Date: Thu, 25 Sep 2025 09:07:29 -0400
Subject: [PATCH 071/352] Revert "scsi: qla2xxx: Fix memcpy() field-spanning
 write issue"

This reverts commit 6f4b10226b6b1e7d1ff3cdb006cf0f6da6eed71e.

We've been testing this patch and it turns out there is a significant
bug here. This leaks memory and causes a driver hang.

Link: https://lore.kernel.org/linux-scsi/yq1zfajqpec.fsf@ca-mkp.ca.oracle.com/
Signed-off-by: John Meneghini <jmeneghi@redhat.com>
Acked-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  | 10 ++++------
 drivers/scsi/qla2xxx/qla_isr.c  | 17 +++++++++--------
 drivers/scsi/qla2xxx/qla_nvme.c |  2 +-
 drivers/scsi/qla2xxx/qla_os.c   |  5 ++---
 4 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 604e66bead1e..cb95b7b12051 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4890,7 +4890,9 @@ struct purex_item {
 			     struct purex_item *pkt);
 	atomic_t in_use;
 	uint16_t size;
-	uint8_t iocb[] __counted_by(size);
+	struct {
+		uint8_t iocb[64];
+	} iocb;
 };
 
 #include "qla_edif.h"
@@ -5099,6 +5101,7 @@ typedef struct scsi_qla_host {
 		struct list_head head;
 		spinlock_t lock;
 	} purex_list;
+	struct purex_item default_item;
 
 	struct name_list_extended gnl;
 	/* Count of active session/fcport */
@@ -5127,11 +5130,6 @@ typedef struct scsi_qla_host {
 #define DPORT_DIAG_IN_PROGRESS                 BIT_0
 #define DPORT_DIAG_CHIP_RESET_IN_PROGRESS      BIT_1
 	uint16_t dport_status;
-
-	/* Must be last --ends in a flexible-array member. */
-	TRAILING_OVERLAP(struct purex_item, default_item, iocb,
-		uint8_t __default_item_iocb[QLA_DEFAULT_PAYLOAD_SIZE];
-	);
 } scsi_qla_host_t;
 
 struct qla27xx_image_status {
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 4559b490614d..c4c6b5c6658c 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1077,17 +1077,17 @@ static struct purex_item *
 qla24xx_alloc_purex_item(scsi_qla_host_t *vha, uint16_t size)
 {
 	struct purex_item *item = NULL;
+	uint8_t item_hdr_size = sizeof(*item);
 
 	if (size > QLA_DEFAULT_PAYLOAD_SIZE) {
-		item = kzalloc(struct_size(item, iocb, size), GFP_ATOMIC);
+		item = kzalloc(item_hdr_size +
+		    (size - QLA_DEFAULT_PAYLOAD_SIZE), GFP_ATOMIC);
 	} else {
 		if (atomic_inc_return(&vha->default_item.in_use) == 1) {
 			item = &vha->default_item;
 			goto initialize_purex_header;
 		} else {
-			item = kzalloc(
-				struct_size(item, iocb, QLA_DEFAULT_PAYLOAD_SIZE),
-				GFP_ATOMIC);
+			item = kzalloc(item_hdr_size, GFP_ATOMIC);
 		}
 	}
 	if (!item) {
@@ -1127,16 +1127,17 @@ qla24xx_queue_purex_item(scsi_qla_host_t *vha, struct purex_item *pkt,
  * @vha: SCSI driver HA context
  * @pkt: ELS packet
  */
-static struct purex_item *
-qla24xx_copy_std_pkt(struct scsi_qla_host *vha, void *pkt)
+static struct purex_item
+*qla24xx_copy_std_pkt(struct scsi_qla_host *vha, void *pkt)
 {
 	struct purex_item *item;
 
-	item = qla24xx_alloc_purex_item(vha, QLA_DEFAULT_PAYLOAD_SIZE);
+	item = qla24xx_alloc_purex_item(vha,
+					QLA_DEFAULT_PAYLOAD_SIZE);
 	if (!item)
 		return item;
 
-	memcpy(&item->iocb, pkt, QLA_DEFAULT_PAYLOAD_SIZE);
+	memcpy(&item->iocb, pkt, sizeof(item->iocb));
 	return item;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 065f9bcca26f..316594aa40cc 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -1308,7 +1308,7 @@ void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp)
 
 	ql_dbg(ql_dbg_unsol, vha, 0x2121,
 	       "PURLS OP[%01x] size %d xchg addr 0x%x portid %06x\n",
-	       item->iocb[3], item->size, uctx->exchange_address,
+	       item->iocb.iocb[3], item->size, uctx->exchange_address,
 	       fcport->d_id.b24);
 	/* +48    0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F
 	 * ----- -----------------------------------------------
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 98a5c105fdfd..9a2f328200ab 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -6459,10 +6459,9 @@ dealloc:
 void
 qla24xx_free_purex_item(struct purex_item *item)
 {
-	if (item == &item->vha->default_item) {
+	if (item == &item->vha->default_item)
 		memset(&item->vha->default_item, 0, sizeof(struct purex_item));
-		memset(&item->vha->__default_item_iocb, 0, QLA_DEFAULT_PAYLOAD_SIZE);
-	} else
+	else
 		kfree(item);
 }
 

From f966e02ae52192928d544262ee7a68611e333031 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Fri, 26 Sep 2025 09:29:26 +0800
Subject: [PATCH 072/352] scsi: ufs: core: Fix runtime suspend error deadlock

Resolve the deadlock issue during runtime suspend when an error triggers
the error handler. Prevent the deadlock by checking pm_op_in_progress
and performing a quick recovery.  This approach ensures that the error
handler does not wait indefinitely for runtime PM to resume, allowing
runtime suspend to proceed smoothly.

Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Suggested-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Message-Id: <20250926012940.3933367-1-peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index b2e103aa4e62..fd7defb3e2cf 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6673,6 +6673,14 @@ static void ufshcd_err_handler(struct work_struct *work)
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
+	ufshcd_rpm_get_noresume(hba);
+	if (hba->pm_op_in_progress) {
+		ufshcd_link_recovery(hba);
+		ufshcd_rpm_put(hba);
+		return;
+	}
+	ufshcd_rpm_put(hba);
+
 	ufshcd_err_handling_prepare(hba);
 
 	spin_lock_irqsave(hba->host->host_lock, flags);

From 0ba7a254afd037cfc2b656f379c54b43c6e574e8 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 29 Sep 2025 13:27:30 +0200
Subject: [PATCH 073/352] scsi: ufs: core: Fix PM QoS mutex initialization

hba->pm_qos_mutex is used very early as a part of ufshcd_init(), so it
need to be initialized before that call. This fixes the following
warning:

------------[ cut here ]------------
DEBUG_LOCKS_WARN_ON(lock->magic != lock)
WARNING: kernel/locking/mutex.c:577 at __mutex_lock+0x268/0x894, CPU#4: kworker/u32:4/72
Modules linked in:
CPU: 4 UID: 0 PID: 72 Comm: kworker/u32:4 Not tainted 6.17.0-rc7-next-20250926+ #11223 PREEMPT
Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
Workqueue: events_unbound deferred_probe_work_func
pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __mutex_lock+0x268/0x894
lr : __mutex_lock+0x268/0x894
...
Call trace:
 __mutex_lock+0x268/0x894 (P)
 mutex_lock_nested+0x24/0x30
 ufshcd_pm_qos_update+0x30/0x78
 ufshcd_setup_clocks+0x2d4/0x3c4
 ufshcd_init+0x234/0x126c
 ufshcd_pltfrm_init+0x62c/0x82c
 ufs_qcom_probe+0x20/0x58
 platform_probe+0x5c/0xac
 really_probe+0xbc/0x298
 __driver_probe_device+0x78/0x12c
 driver_probe_device+0x40/0x164
 __device_attach_driver+0xb8/0x138
 bus_for_each_drv+0x80/0xdc
 __device_attach+0xa8/0x1b0
 device_initial_probe+0x14/0x20
 bus_probe_device+0xb0/0xb4
 deferred_probe_work_func+0x8c/0xc8
 process_one_work+0x208/0x60c
 worker_thread+0x244/0x388
 kthread+0x150/0x228
 ret_from_fork+0x10/0x20
irq event stamp: 57267
hardirqs last  enabled at (57267): [<ffffd761485e868c>] _raw_spin_unlock_irqrestore+0x74/0x78
hardirqs last disabled at (57266): [<ffffd76147b13c44>] clk_enable_lock+0x7c/0xf0
softirqs last  enabled at (56270): [<ffffd7614734446c>] handle_softirqs+0x4c4/0x4dc
softirqs last disabled at (56265): [<ffffd76147290690>] __do_softirq+0x14/0x20
---[ end trace 0000000000000000 ]---

Fixes: 79dde5f7dc7c ("scsi: ufs: core: Fix data race in CPU latency PM QoS request handling")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Message-Id: <20250929112730.3782765-1-m.szyprowski@samsung.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index fd7defb3e2cf..319dd6f6229b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10669,6 +10669,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	 */
 	spin_lock_init(&hba->clk_gating.lock);
 
+	/* Initialize mutex for PM QoS request synchronization */
+	mutex_init(&hba->pm_qos_mutex);
+
 	/*
 	 * Set the default power management level for runtime and system PM.
 	 * Host controller drivers can override them in their
@@ -10757,9 +10760,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	mutex_init(&hba->wb_mutex);
 
-	/* Initialize mutex for PM QoS request synchronization */
-	mutex_init(&hba->pm_qos_mutex);
-
 	init_rwsem(&hba->clk_scaling_lock);
 
 	ufshcd_init_clk_gating(hba);

From 60cd16a3b7439ccb699d0bf533799eeb894fd217 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Sat, 20 Sep 2025 21:42:01 +0800
Subject: [PATCH 074/352] scsi: mvsas: Fix use-after-free bugs in
 mvs_work_queue

During the detaching of Marvell's SAS/SATA controller, the original code
calls cancel_delayed_work() in mvs_free() to cancel the delayed work
item mwq->work_q. However, if mwq->work_q is already running, the
cancel_delayed_work() may fail to cancel it. This can lead to
use-after-free scenarios where mvs_free() frees the mvs_info while
mvs_work_queue() is still executing and attempts to access the
already-freed mvs_info.

A typical race condition is illustrated below:

CPU 0 (remove)            | CPU 1 (delayed work callback)
mvs_pci_remove()          |
  mvs_free()              | mvs_work_queue()
    cancel_delayed_work() |
      kfree(mvi)          |
                          |   mvi-> // UAF

Replace cancel_delayed_work() with cancel_delayed_work_sync() to ensure
that the delayed work item is properly canceled and any executing
delayed work item completes before the mvs_info is deallocated.

This bug was found by static analysis.

Fixes: 20b09c2992fe ("[SCSI] mvsas: add support for 94xx; layout change; bug fixes")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mvsas/mv_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 2c72da6b8cf0..7f1ad305eee6 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -124,7 +124,7 @@ static void mvs_free(struct mvs_info *mvi)
 	if (mvi->shost)
 		scsi_host_put(mvi->shost);
 	list_for_each_entry(mwq, &mvi->wq_list, entry)
-		cancel_delayed_work(&mwq->work_q);
+		cancel_delayed_work_sync(&mwq->work_q);
 	kfree(mvi->rsvd_tags);
 	kfree(mvi);
 }

From 74662f9f92b67c0ca55139c5aa392da0f0a26c08 Mon Sep 17 00:00:00 2001
From: Steven 'Steve' Kendall <skend@chromium.org>
Date: Mon, 29 Sep 2025 21:33:34 +0000
Subject: [PATCH 075/352] ALSA: hda/hdmi: Add pin fix for HP ProDesk model

The HP ProDesk 400 (SSID 103c:83f3) also needs a quirk for
enabling HDMI outputs.  This patch adds the required quirk
entry.

Signed-off-by: Steven 'Steve' Kendall <skend@chromium.org>
Cc: <stable@vger.kernel.org>
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 dc38bfd9dba5..111c9b5335af 100644
--- a/sound/hda/codecs/hdmi/hdmi.c
+++ b/sound/hda/codecs/hdmi/hdmi.c
@@ -1549,6 +1549,7 @@ 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, 0x83f3, "HP ProDesk 400", 1),
 	SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),

From adefb2ccea1e96b452cbbc39150bc0ccf1688b99 Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Tue, 16 Sep 2025 14:18:28 -0300
Subject: [PATCH 076/352] drm/v3d: create a dedicated lock for dma fence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't mix dma fence lock with the active_job lock. Use fence_lock to
protect the dma fence used by drm scheduler when signalling a job
completion and queue_lock to protect concurrent access to active bin job
in OOM and stats collection for a given file priv. The issue was
uncovered when PREEMPT_RT on with a system freeze when opening multiple
Chromium tabs on Raspberry Pi 5.

Link: https://github.com/raspberrypi/linux/issues/7035
Fixes: fa6a20c87470 ("drm/v3d: Address race-condition between per-fd GPU stats and fd release")
Signed-off-by: Melissa Wen <mwen@igalia.com>
Acked-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://lore.kernel.org/r/20250916172022.2779837-1-mwen@igalia.com
---
 drivers/gpu/drm/v3d/v3d_drv.h   | 2 ++
 drivers/gpu/drm/v3d/v3d_fence.c | 2 +-
 drivers/gpu/drm/v3d/v3d_gem.c   | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 0317f3d7452a..1884686985b8 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -62,6 +62,8 @@ struct v3d_queue_state {
 	/* Currently active job for this queue */
 	struct v3d_job *active_job;
 	spinlock_t queue_lock;
+	/* Protect dma fence for signalling job completion */
+	spinlock_t fence_lock;
 };
 
 /* Performance monitor object. The perform lifetime is controlled by userspace
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index 8f8471adae34..c82500a1df73 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -15,7 +15,7 @@ struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q)
 	fence->dev = &v3d->drm;
 	fence->queue = q;
 	fence->seqno = ++queue->emit_seqno;
-	dma_fence_init(&fence->base, &v3d_fence_ops, &queue->queue_lock,
+	dma_fence_init(&fence->base, &v3d_fence_ops, &queue->fence_lock,
 		       queue->fence_context, fence->seqno);
 
 	return &fence->base;
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index c77d90aa9b82..bb110d35f749 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -273,6 +273,7 @@ v3d_gem_init(struct drm_device *dev)
 		seqcount_init(&queue->stats.lock);
 
 		spin_lock_init(&queue->queue_lock);
+		spin_lock_init(&queue->fence_lock);
 	}
 
 	spin_lock_init(&v3d->mm_lock);

From bb7663dec67b691528f104894429b3859fb16c14 Mon Sep 17 00:00:00 2001
From: Daniel Lee <chullee@google.com>
Date: Mon, 29 Sep 2025 18:09:39 -0700
Subject: [PATCH 077/352] scsi: ufs: sysfs: Make HID attributes visible

Call sysfs_update_group() after reading the device descriptor to ensure
the HID sysfs attributes are visible when the feature is supported.

Fixes: ae7795a8c258 ("scsi: ufs: core: Add HID support")
Signed-off-by: Daniel Lee <chullee@google.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs-sysfs.c | 2 +-
 drivers/ufs/core/ufs-sysfs.h | 1 +
 drivers/ufs/core/ufshcd.c    | 2 ++
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 0086816b27cd..c040afc6668e 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -1949,7 +1949,7 @@ static umode_t ufs_sysfs_hid_is_visible(struct kobject *kobj,
 	return	hba->dev_info.hid_sup ? attr->mode : 0;
 }
 
-static const struct attribute_group ufs_sysfs_hid_group = {
+const struct attribute_group ufs_sysfs_hid_group = {
 	.name = "hid",
 	.attrs = ufs_sysfs_hid,
 	.is_visible = ufs_sysfs_hid_is_visible,
diff --git a/drivers/ufs/core/ufs-sysfs.h b/drivers/ufs/core/ufs-sysfs.h
index 8d94af3b8077..6efb82a082fd 100644
--- a/drivers/ufs/core/ufs-sysfs.h
+++ b/drivers/ufs/core/ufs-sysfs.h
@@ -14,5 +14,6 @@ void ufs_sysfs_remove_nodes(struct device *dev);
 
 extern const struct attribute_group ufs_sysfs_unit_descriptor_group;
 extern const struct attribute_group ufs_sysfs_lun_attributes_group;
+extern const struct attribute_group ufs_sysfs_hid_group;
 
 #endif
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 319dd6f6229b..127b691402f9 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8480,6 +8480,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 				DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP) &
 				UFS_DEV_HID_SUPPORT;
 
+	sysfs_update_group(&hba->dev->kobj, &ufs_sysfs_hid_group);
+
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 
 	err = ufshcd_read_string_desc(hba, model_index,

From 558ae4579810fa0fef011944230c65a6f3087f85 Mon Sep 17 00:00:00 2001
From: Hoyoung Seo <hy50.seo@samsung.com>
Date: Tue, 30 Sep 2025 15:14:28 +0900
Subject: [PATCH 078/352] scsi: ufs: core: Include UTP error in
 INT_FATAL_ERRORS

When a UTP error occurs in isolation, UFS is not currently recoverable.
This is because the UTP error is not considered fatal in the error
handling code, leading to either an I/O timeout or an OCS error.

Add the UTP error flag to INT_FATAL_ERRORS so the controller will be
reset in this situation.

  sd 0:0:0:0: [sda] tag#38 UNKNOWN(0x2003) Result: hostbyte=0x07
  driverbyte=DRIVER_OK cmd_age=0s
  sd 0:0:0:0: [sda] tag#38 CDB: opcode=0x28 28 00 00 51 24 e2 00 00 08 00
  I/O error, dev sda, sector 42542864 op 0x0:(READ) flags 0x80700 phys_seg
  8 prio class 2
  OCS error from controller = 9 for tag 39
  pa_err[1] = 0x80000010 at 2667224756 us
  pa_err: total cnt=2
  dl_err[0] = 0x80000002 at 2667148060 us
  dl_err[1] = 0x80002000 at 2667282844 us
  No record of nl_err
  No record of tl_err
  No record of dme_err
  No record of auto_hibern8_err
  fatal_err[0] = 0x804 at 2667282836 us

  ---------------------------------------------------
  		REGISTER
  ---------------------------------------------------
                             NAME	      OFFSET	         VALUE
                      STD HCI SFR	  0xfffffff0	           0x0
                             AHIT	        0x18	         0x814
                 INTERRUPT STATUS	        0x20	        0x1000
                 INTERRUPT ENABLE	        0x24	       0x70ef5

[mkp: commit desc]

Signed-off-by: Hoyoung Seo <hy50.seo@samsung.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Message-Id: <20250930061428.617955-1-hy50.seo@samsung.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/ufs/ufshci.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h
index 612500a7088f..e64b70132101 100644
--- a/include/ufs/ufshci.h
+++ b/include/ufs/ufshci.h
@@ -180,6 +180,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 #define UTP_TASK_REQ_COMPL			0x200
 #define UIC_COMMAND_COMPL			0x400
 #define DEVICE_FATAL_ERROR			0x800
+#define UTP_ERROR				0x1000
 #define CONTROLLER_FATAL_ERROR			0x10000
 #define SYSTEM_BUS_FATAL_ERROR			0x20000
 #define CRYPTO_ENGINE_FATAL_ERROR		0x40000
@@ -199,7 +200,8 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 				CONTROLLER_FATAL_ERROR |\
 				SYSTEM_BUS_FATAL_ERROR |\
 				CRYPTO_ENGINE_FATAL_ERROR |\
-				UIC_LINK_LOST)
+				UIC_LINK_LOST |\
+				UTP_ERROR)
 
 /* HCS - Host Controller Status 30h */
 #define DEVICE_PRESENT				0x1

From d391bb1955747edc9f92e67d35c79ada996a93eb Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Mon, 4 Aug 2025 15:24:11 +0800
Subject: [PATCH 079/352] fbdev: xenfb: Use vmalloc_array to simplify code

Use vmalloc_array() instead of vmalloc() to simplify the function
xenfb_probe().

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/xen-fbfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index c90f48ebb15e..d8f3bfb2dd6c 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -390,7 +390,7 @@ static int xenfb_probe(struct xenbus_device *dev,
 
 	info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	info->gfns = vmalloc(array_size(sizeof(unsigned long), info->nr_pages));
+	info->gfns = vmalloc_array(info->nr_pages, sizeof(unsigned long));
 	if (!info->gfns)
 		goto error_nomem;
 

From 43b30be2e7211d982b005d118dd6a12f97b9d458 Mon Sep 17 00:00:00 2001
From: Zsolt Kajtar <soci@c64.rulez.org>
Date: Sun, 10 Aug 2025 17:47:54 +0200
Subject: [PATCH 080/352] fbdev: s3fb: Implement powersave for S3 FB

This patch implements power saving for S3 cards by powering down the
RAMDAC and stopping MCLK and DCLK while the card is supposed to be
suspended.

The RAMDAC is also disabled while the screen is blanked and the DCLK
in stopped while in DPMS power off.

The practical difference it makes is that on a machine with such a
card the display will be placed in DPMS power off while standby is
activated (due to stopped DCLK). Same like when using other cards with
implemented power saving functionality.

Without it on my setup the connected display powers up and stays that
way showing VT63 while in standby. Sort of annoying as before standby
it's specifically placed into DPMS off in Xorg for a while.

The used functionality should exists for sure on Trio32 to Aurora64V
(according to the documentation) so I think it's generally applicable.
I'm using this on S3 Trio 3D and S3 Virge DX.

Signed-off-by: Zsolt Kajtar <soci@c64.rulez.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/s3fb.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index ff84106ecf1c..9b3fca9b3e08 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -988,34 +988,30 @@ static int s3fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 static int s3fb_blank(int blank_mode, struct fb_info *info)
 {
 	struct s3fb_info *par = info->par;
+	u8 data;
+
+	data = (blank_mode == FB_BLANK_UNBLANK) ? 0x00 : 0x20;
+	svga_wseq_mask(par->state.vgabase, 0x01, data, 0x20);
+	svga_wseq_mask(par->state.vgabase, 0x18, data, 0x20);
 
 	switch (blank_mode) {
-	case FB_BLANK_UNBLANK:
-		fb_dbg(info, "unblank\n");
-		svga_wcrt_mask(par->state.vgabase, 0x56, 0x00, 0x06);
-		svga_wseq_mask(par->state.vgabase, 0x01, 0x00, 0x20);
-		break;
-	case FB_BLANK_NORMAL:
-		fb_dbg(info, "blank\n");
-		svga_wcrt_mask(par->state.vgabase, 0x56, 0x00, 0x06);
-		svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20);
+	default:
+		data = 0x00;
 		break;
 	case FB_BLANK_HSYNC_SUSPEND:
-		fb_dbg(info, "hsync\n");
-		svga_wcrt_mask(par->state.vgabase, 0x56, 0x02, 0x06);
-		svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20);
+		data = 0x02;
 		break;
 	case FB_BLANK_VSYNC_SUSPEND:
-		fb_dbg(info, "vsync\n");
-		svga_wcrt_mask(par->state.vgabase, 0x56, 0x04, 0x06);
-		svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20);
+		data = 0x04;
 		break;
 	case FB_BLANK_POWERDOWN:
-		fb_dbg(info, "sync down\n");
-		svga_wcrt_mask(par->state.vgabase, 0x56, 0x06, 0x06);
-		svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20);
+		data = 0x06;
 		break;
 	}
+	svga_wcrt_mask(par->state.vgabase, 0x56, data, 0x06);
+
+	data = (blank_mode == FB_BLANK_POWERDOWN) ? 0x01 : 0x00;
+	svga_wseq_mask(par->state.vgabase, 0x14, data, 0x01);
 
 	return 0;
 }
@@ -1445,6 +1441,8 @@ static int __maybe_unused s3_pci_suspend(struct device *dev)
 	}
 
 	fb_set_suspend(info, 1);
+	svga_wseq_mask(par->state.vgabase, 0x18, 0x20, 0x20);
+	svga_wseq_mask(par->state.vgabase, 0x14, 0x03, 0x03);
 
 	mutex_unlock(&(par->open_lock));
 	console_unlock();
@@ -1471,6 +1469,9 @@ static int __maybe_unused s3_pci_resume(struct device *dev)
 		return 0;
 	}
 
+	vga_wseq(par->state.vgabase, 0x08, 0x06);
+	svga_wseq_mask(par->state.vgabase, 0x18, 0x00, 0x20);
+	svga_wseq_mask(par->state.vgabase, 0x14, 0x00, 0x03);
 	s3fb_set_par(info);
 	fb_set_suspend(info, 0);
 

From 69c9820d40892f7c10db03c5364795f5bb12aced Mon Sep 17 00:00:00 2001
From: Zsolt Kajtar <soci@c64.rulez.org>
Date: Mon, 18 Aug 2025 22:44:26 +0200
Subject: [PATCH 081/352] fbdev: s3fb: Implement 1 and 2 BPP modes, improve 4
 BPP

With the right setup S3 cards can display 1 and 2 BPP packed pixel
modes, even in high resolutions. So this patch makes them available.

The 4 BPP packed pixel mode had one pixel column of garbage on the
left side due to how the shift register works, this is fixed now.

There was a limitation that only 8 pixel wide fonts could be used at 4
BPP. Since the CFB routines were updated to handle reverse pixel
ordering correctly that limitation doesn't exists and was removed now.

In 4 BPP interleaved planes mode font widths of multiply of 8 are
accepted now, not just 8 pixels.

The horizontal screen position will not move as much between modes as it
used to. That was caused by the various amount of pipeline delay which
is compensated now as much as possible.

While adjusting the code direct port access of PEL registers was
corrected. Should work now on systems where these are memory mapped.

I've noticed that when in 1 BPP mode the console is used with Unicode
fonts erasing might be done with non-blanks. That's a bug in the VT code
and so not part of this patch.

Signed-off-by: Zsolt Kajtar <soci@c64.rulez.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/Kconfig |   1 +
 drivers/video/fbdev/s3fb.c  | 140 ++++++++++++++++++++++++++----------
 2 files changed, 105 insertions(+), 36 deletions(-)

diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index c21484d15f0c..1500dca8c416 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -1060,6 +1060,7 @@ config FB_S3
 	select FB_TILEBLITTING
 	select FB_SVGALIB
 	select VGASTATE
+	select FB_CFB_REV_PIXELS_IN_BYTE
 	select FONT_8x16 if FRAMEBUFFER_CONSOLE
 	help
 	  Driver for graphics boards with S3 Trio / S3 Virge chip.
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index 9b3fca9b3e08..a6cfed0a87fa 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -50,10 +50,14 @@ struct s3fb_info {
 static const struct svga_fb_format s3fb_formats[] = {
 	{ 0,  {0, 6, 0},  {0, 6, 0},  {0, 6, 0}, {0, 0, 0}, 0,
 		FB_TYPE_TEXT, FB_AUX_TEXT_SVGA_STEP4,	FB_VISUAL_PSEUDOCOLOR, 8, 16},
-	{ 4,  {0, 4, 0},  {0, 4, 0},  {0, 4, 0}, {0, 0, 0}, 0,
-		FB_TYPE_PACKED_PIXELS, 0,		FB_VISUAL_PSEUDOCOLOR, 8, 16},
+	{ 1,  {0, 1, 0},  {0, 1, 0},  {0, 1, 0}, {0, 0, 0}, 2,
+		FB_TYPE_PACKED_PIXELS, 0,		FB_VISUAL_PSEUDOCOLOR, 32, 64},
+	{ 2,  {0, 2, 0},  {0, 2, 0},  {0, 2, 0}, {0, 0, 0}, 2,
+		FB_TYPE_PACKED_PIXELS, 0,		FB_VISUAL_PSEUDOCOLOR, 16, 32},
 	{ 4,  {0, 4, 0},  {0, 4, 0},  {0, 4, 0}, {0, 0, 0}, 1,
 		FB_TYPE_INTERLEAVED_PLANES, 1,		FB_VISUAL_PSEUDOCOLOR, 8, 16},
+	{ 4,  {0, 4, 0},  {0, 4, 0},  {0, 4, 0}, {0, 0, 0}, 2,
+		FB_TYPE_PACKED_PIXELS, 0,		FB_VISUAL_PSEUDOCOLOR, 8, 16},
 	{ 8,  {0, 8, 0},  {0, 8, 0},  {0, 8, 0}, {0, 0, 0}, 0,
 		FB_TYPE_PACKED_PIXELS, 0,		FB_VISUAL_PSEUDOCOLOR, 4, 8},
 	{16,  {10, 5, 0}, {5, 5, 0},  {0, 5, 0}, {0, 0, 0}, 0,
@@ -557,7 +561,7 @@ static int s3fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	/* 32bpp mode is not supported on VIRGE VX,
 	   24bpp is not supported on others */
-	if ((par->chip == CHIP_988_VIRGE_VX) ? (rv == 7) : (rv == 6))
+	if ((par->chip == CHIP_988_VIRGE_VX) ? (rv == 9) : (rv == 8))
 		rv = -EINVAL;
 
 	if (rv < 0) {
@@ -607,7 +611,7 @@ static int s3fb_set_par(struct fb_info *info)
 	struct s3fb_info *par = info->par;
 	u32 value, mode, hmul, offset_value, screen_size, multiplex, dbytes;
 	u32 bpp = info->var.bits_per_pixel;
-	u32 htotal, hsstart;
+	u32 htotal, hsstart, pel_msk;
 
 	if (bpp != 0) {
 		info->fix.ypanstep = 1;
@@ -617,9 +621,11 @@ static int s3fb_set_par(struct fb_info *info)
 		info->tileops = NULL;
 
 		/* in 4bpp supports 8p wide tiles only, any tiles otherwise */
-		if (bpp == 4) {
+		if (bpp == 4 && (info->var.nonstd & 1) != 0) {
+			int i;
 			bitmap_zero(info->pixmap.blit_x, FB_MAX_BLIT_WIDTH);
-			set_bit(8 - 1, info->pixmap.blit_x);
+			for (i = 8; i <= FB_MAX_BLIT_WIDTH; i += 8)
+				set_bit(i - 1, info->pixmap.blit_x);
 		} else {
 			bitmap_fill(info->pixmap.blit_x, FB_MAX_BLIT_WIDTH);
 		}
@@ -730,7 +736,7 @@ static int s3fb_set_par(struct fb_info *info)
 		vga_wcrt(par->state.vgabase, 0x50, 0x00);
 		vga_wcrt(par->state.vgabase, 0x67, 0x50);
 		msleep(10); /* screen remains blank sometimes without this */
-		vga_wcrt(par->state.vgabase, 0x63, (mode <= 2) ? 0x90 : 0x09);
+		vga_wcrt(par->state.vgabase, 0x63, (mode <= 4) ? 0x90 : 0x09);
 		vga_wcrt(par->state.vgabase, 0x66, 0x90);
 	}
 
@@ -763,12 +769,17 @@ static int s3fb_set_par(struct fb_info *info)
 	svga_wcrt_mask(par->state.vgabase, 0x31, 0x00, 0x40);
 	multiplex = 0;
 	hmul = 1;
+	pel_msk = 0xff;
+
+	svga_wcrt_mask(par->state.vgabase, 0x08, 0x00, 0x60);
+	svga_wcrt_mask(par->state.vgabase, 0x05, 0x00, 0x60);
 
 	/* Set mode-specific register values */
 	switch (mode) {
 	case 0:
 		fb_dbg(info, "text mode\n");
 		svga_set_textmode_vga_regs(par->state.vgabase);
+		pel_msk = 0x0f;
 
 		/* Set additional registers like in 8-bit mode */
 		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
@@ -783,8 +794,11 @@ static int s3fb_set_par(struct fb_info *info)
 		}
 		break;
 	case 1:
-		fb_dbg(info, "4 bit pseudocolor\n");
-		vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x40);
+		fb_dbg(info, "1 bit pseudocolor\n");
+		svga_wseq_mask(par->state.vgabase, 0x01, 0x10, 0x14);
+		svga_wcrt_mask(par->state.vgabase, 0x08, 0x60, 0x60);
+		svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60);
+		pel_msk = 0x01;
 
 		/* Set additional registers like in 8-bit mode */
 		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
@@ -794,7 +808,13 @@ static int s3fb_set_par(struct fb_info *info)
 		svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30);
 		break;
 	case 2:
-		fb_dbg(info, "4 bit pseudocolor, planar\n");
+		fb_dbg(info, "2 bit pseudocolor\n");
+		svga_wseq_mask(par->state.vgabase, 0x01, 0x04, 0x14);
+		svga_wseq_mask(par->state.vgabase, 0x04, 0x08, 0x08);
+		vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x20);
+		svga_wcrt_mask(par->state.vgabase, 0x08, 0x20, 0x60);
+		svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60);
+		pel_msk = 0x03;
 
 		/* Set additional registers like in 8-bit mode */
 		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
@@ -804,8 +824,35 @@ static int s3fb_set_par(struct fb_info *info)
 		svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30);
 		break;
 	case 3:
+		fb_dbg(info, "4 bit pseudocolor, planar\n");
+		pel_msk = 0x0f;
+
+		/* Set additional registers like in 8-bit mode */
+		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
+		svga_wcrt_mask(par->state.vgabase, 0x67, 0x00, 0xF0);
+		svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60);
+
+		/* disable enhanced mode */
+		svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30);
+		break;
+	case 4:
+		fb_dbg(info, "4 bit pseudocolor\n");
+		vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x40);
+		svga_wattr(par->state.vgabase, 0x33, 0x01);
+		svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60);
+		pel_msk = 0xf0;
+
+		/* Set additional registers like in 8-bit mode */
+		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
+		svga_wcrt_mask(par->state.vgabase, 0x67, 0x00, 0xF0);
+
+		/* disable enhanced mode */
+		svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30);
+		break;
+	case 5:
 		fb_dbg(info, "8 bit pseudocolor\n");
 		svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30);
+		svga_wcrt_mask(par->state.vgabase, 0x05, 0x20, 0x60);
 		if (info->var.pixclock > 20000 ||
 		    par->chip == CHIP_357_VIRGE_GX2 ||
 		    par->chip == CHIP_359_VIRGE_GX2P ||
@@ -819,7 +866,7 @@ static int s3fb_set_par(struct fb_info *info)
 			multiplex = 1;
 		}
 		break;
-	case 4:
+	case 6:
 		fb_dbg(info, "5/5/5 truecolor\n");
 		if (par->chip == CHIP_988_VIRGE_VX) {
 			if (info->var.pixclock > 20000)
@@ -847,7 +894,7 @@ static int s3fb_set_par(struct fb_info *info)
 				hmul = 2;
 		}
 		break;
-	case 5:
+	case 7:
 		fb_dbg(info, "5/6/5 truecolor\n");
 		if (par->chip == CHIP_988_VIRGE_VX) {
 			if (info->var.pixclock > 20000)
@@ -875,12 +922,12 @@ static int s3fb_set_par(struct fb_info *info)
 				hmul = 2;
 		}
 		break;
-	case 6:
+	case 8:
 		/* VIRGE VX case */
 		fb_dbg(info, "8/8/8 truecolor\n");
 		svga_wcrt_mask(par->state.vgabase, 0x67, 0xD0, 0xF0);
 		break;
-	case 7:
+	case 9:
 		fb_dbg(info, "8/8/8/8 truecolor\n");
 		svga_wcrt_mask(par->state.vgabase, 0x50, 0x30, 0x30);
 		svga_wcrt_mask(par->state.vgabase, 0x67, 0xD0, 0xF0);
@@ -889,6 +936,7 @@ static int s3fb_set_par(struct fb_info *info)
 		fb_err(info, "unsupported mode - bug\n");
 		return -EINVAL;
 	}
+	vga_w(par->state.vgabase, VGA_PEL_MSK, pel_msk);
 
 	if (par->chip != CHIP_988_VIRGE_VX) {
 		svga_wseq_mask(par->state.vgabase, 0x15, multiplex ? 0x10 : 0x00, 0x10);
@@ -927,33 +975,26 @@ static int s3fb_set_par(struct fb_info *info)
 static int s3fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 				u_int transp, struct fb_info *fb)
 {
+	struct s3fb_info *par = fb->par;
+	int cols;
+
 	switch (fb->var.bits_per_pixel) {
 	case 0:
+	case 1:
+	case 2:
 	case 4:
-		if (regno >= 16)
-			return -EINVAL;
-
-		if ((fb->var.bits_per_pixel == 4) &&
-		    (fb->var.nonstd == 0)) {
-			outb(0xF0, VGA_PEL_MSK);
-			outb(regno*16, VGA_PEL_IW);
-		} else {
-			outb(0x0F, VGA_PEL_MSK);
-			outb(regno, VGA_PEL_IW);
-		}
-		outb(red >> 10, VGA_PEL_D);
-		outb(green >> 10, VGA_PEL_D);
-		outb(blue >> 10, VGA_PEL_D);
-		break;
 	case 8:
-		if (regno >= 256)
+		cols = 1 << (fb->var.bits_per_pixel ? fb->var.bits_per_pixel : 4);
+		if (regno >= cols)
 			return -EINVAL;
 
-		outb(0xFF, VGA_PEL_MSK);
-		outb(regno, VGA_PEL_IW);
-		outb(red >> 10, VGA_PEL_D);
-		outb(green >> 10, VGA_PEL_D);
-		outb(blue >> 10, VGA_PEL_D);
+		if ((fb->var.bits_per_pixel == 4) && ((fb->var.nonstd & 1) == 0))
+			regno <<= 4;
+
+		vga_w(par->state.vgabase, VGA_PEL_IW, regno);
+		vga_w(par->state.vgabase, VGA_PEL_D, red >> 10);
+		vga_w(par->state.vgabase, VGA_PEL_D, green >> 10);
+		vga_w(par->state.vgabase, VGA_PEL_D, blue >> 10);
 		break;
 	case 16:
 		if (regno >= 16)
@@ -1041,6 +1082,33 @@ static int s3fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
 	return 0;
 }
 
+/* Get capabilities of accelerator based on the mode */
+
+static void s3fb_get_caps(struct fb_info *info, struct fb_blit_caps *caps,
+			  struct fb_var_screeninfo *var)
+{
+	int i;
+
+	if (var->bits_per_pixel == 0) {
+		/* can only support 256 8x16 bitmap */
+		bitmap_zero(caps->x, FB_MAX_BLIT_WIDTH);
+		set_bit(8 - 1, caps->x);
+		bitmap_zero(caps->y, FB_MAX_BLIT_HEIGHT);
+		set_bit(16 - 1, caps->y);
+		caps->len = 256;
+	} else {
+		if (var->bits_per_pixel == 4 && (var->nonstd & 1) != 0) {
+			bitmap_zero(caps->x, FB_MAX_BLIT_WIDTH);
+			for (i = 8; i <= FB_MAX_BLIT_WIDTH; i += 8)
+				set_bit(i - 1, caps->x);
+		} else {
+			bitmap_fill(caps->x, FB_MAX_BLIT_WIDTH);
+		}
+		bitmap_fill(caps->y, FB_MAX_BLIT_HEIGHT);
+		caps->len = ~(u32)0;
+	}
+}
+
 /* ------------------------------------------------------------------------- */
 
 /* Frame buffer operations */
@@ -1059,7 +1127,7 @@ static const struct fb_ops s3fb_ops = {
 	.fb_copyarea	= cfb_copyarea,
 	.fb_imageblit	= s3fb_imageblit,
 	__FB_DEFAULT_IOMEM_OPS_MMAP,
-	.fb_get_caps    = svga_get_caps,
+	.fb_get_caps	= s3fb_get_caps,
 };
 
 /* ------------------------------------------------------------------------- */

From aad1d99beaaf132e2024a52727c24894cdf9474a Mon Sep 17 00:00:00 2001
From: Zsolt Kajtar <soci@c64.rulez.org>
Date: Thu, 21 Aug 2025 04:42:48 +0200
Subject: [PATCH 082/352] fbdev: core: Fix ubsan warning in pixel_to_pat

It could be triggered on 32 bit big endian machines at 32 bpp in the
pattern realignment. In this case just return early as the result is
an identity.

Signed-off-by: Zsolt Kajtar <soci@c64.rulez.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/core/fb_fillrect.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/core/fb_fillrect.h b/drivers/video/fbdev/core/fb_fillrect.h
index 66042e534de7..f366670a53af 100644
--- a/drivers/video/fbdev/core/fb_fillrect.h
+++ b/drivers/video/fbdev/core/fb_fillrect.h
@@ -92,8 +92,7 @@ static unsigned long pixel_to_pat(int bpp, u32 color)
 		pattern = pattern | pattern << bpp;
 		break;
 	default:
-		pattern = color;
-		break;
+		return color;
 	}
 #ifndef __LITTLE_ENDIAN
 	pattern <<= (BITS_PER_LONG % bpp);

From c7d655ef2e0ca25ae2c46df47eb62ada9e820c78 Mon Sep 17 00:00:00 2001
From: Chelsy Ratnawat <chelsyratnawat2001@gmail.com>
Date: Sun, 24 Aug 2025 08:23:27 -0700
Subject: [PATCH 083/352] fbdev: Use string choices helpers

Use string_choices.h helpers instead of hard-coded strings.

Signed-off-by: Chelsy Ratnawat <chelsyratnawat2001@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/core/fbmon.c    | 7 ++++---
 drivers/video/fbdev/nvidia/nvidia.c | 3 ++-
 drivers/video/fbdev/pxafb.c         | 3 ++-
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c
index 3b779c27c271..0a65bef01e3c 100644
--- a/drivers/video/fbdev/core/fbmon.c
+++ b/drivers/video/fbdev/core/fbmon.c
@@ -36,6 +36,7 @@
 #include <video/of_videomode.h>
 #include <video/videomode.h>
 #include "../edid.h"
+#include <linux/string_choices.h>
 
 /*
  * EDID parser
@@ -320,9 +321,9 @@ static void get_dpms_capabilities(unsigned char flags,
 	if (flags & DPMS_STANDBY)
 		specs->dpms |= FB_DPMS_STANDBY;
 	DPRINTK("      DPMS: Active %s, Suspend %s, Standby %s\n",
-	       (flags & DPMS_ACTIVE_OFF) ? "yes" : "no",
-	       (flags & DPMS_SUSPEND)    ? "yes" : "no",
-	       (flags & DPMS_STANDBY)    ? "yes" : "no");
+	       str_yes_no(flags & DPMS_ACTIVE_OFF),
+	       str_yes_no(flags & DPMS_SUSPEND),
+	       str_yes_no(flags & DPMS_STANDBY));
 }
 
 static void get_chroma(unsigned char *block, struct fb_monspecs *specs)
diff --git a/drivers/video/fbdev/nvidia/nvidia.c b/drivers/video/fbdev/nvidia/nvidia.c
index cfaf9454014d..72b85f475605 100644
--- a/drivers/video/fbdev/nvidia/nvidia.c
+++ b/drivers/video/fbdev/nvidia/nvidia.c
@@ -22,6 +22,7 @@
 #include <linux/pci.h>
 #include <linux/console.h>
 #include <linux/backlight.h>
+#include <linux/string_choices.h>
 #ifdef CONFIG_BOOTX_TEXT
 #include <asm/btext.h>
 #endif
@@ -622,7 +623,7 @@ static int nvidiafb_set_par(struct fb_info *info)
 		else
 			par->FPDither = !!(NV_RD32(par->PRAMDAC, 0x083C) & 1);
 		printk(KERN_INFO PFX "Flat panel dithering %s\n",
-		       par->FPDither ? "enabled" : "disabled");
+		       str_enabled_disabled(par->FPDither));
 	}
 
 	info->fix.visual = (info->var.bits_per_pixel == 8) ?
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index baf87f34cc24..b96a8a96bce8 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -60,6 +60,7 @@
 #include <linux/soc/pxa/cpu.h>
 #include <video/of_display_timing.h>
 #include <video/videomode.h>
+#include <linux/string_choices.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -1419,7 +1420,7 @@ static inline void __pxafb_lcd_power(struct pxafb_info *fbi, int on)
 
 		if (ret < 0)
 			pr_warn("Unable to %s LCD supply regulator: %d\n",
-				on ? "enable" : "disable", ret);
+				str_enable_disable(on), ret);
 		else
 			fbi->lcd_supply_enabled = on;
 	}

From 4d23d9f7fa7c9ed10b5b32a4e4871ddce02b2337 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Sat, 30 Aug 2025 20:47:00 +0800
Subject: [PATCH 084/352] fbdev: mb862xxfb: Use int type to store negative
 error codes

Change the 'ret' variable in of_platform_mb862xx_probe() from unsigned long
to int, as it needs to store either negative error codes or zero.

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: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/mb862xx/mb862xxfbdrv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
index ade88e7bc760..676c6d3ccc12 100644
--- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
+++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
@@ -674,7 +674,7 @@ static int of_platform_mb862xx_probe(struct platform_device *ofdev)
 	struct fb_info *info;
 	struct resource res;
 	resource_size_t res_size;
-	unsigned long ret = -ENODEV;
+	int ret = -ENODEV;
 
 	if (of_address_to_resource(np, 0, &res)) {
 		dev_err(dev, "Invalid address\n");

From 2e3da8cfe3b281d503ef0e968af131323562ae7c Mon Sep 17 00:00:00 2001
From: Zsolt Kajtar <soci@c64.rulez.org>
Date: Wed, 3 Sep 2025 21:14:15 +0200
Subject: [PATCH 085/352] fbdev: s3fb: Revert mclk stop in suspend

There are systems which want to wait for as long as it takes for the
stopped video memory to answer. Mapping it out helps to avoid that
while the system is running but standby still hangs somehow. So just
leave the memory on in standby same as it was before my change.

Signed-off-by: Zsolt Kajtar <soci@c64.rulez.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/s3fb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index a6cfed0a87fa..ba30e5568cab 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -1510,7 +1510,7 @@ static int __maybe_unused s3_pci_suspend(struct device *dev)
 
 	fb_set_suspend(info, 1);
 	svga_wseq_mask(par->state.vgabase, 0x18, 0x20, 0x20);
-	svga_wseq_mask(par->state.vgabase, 0x14, 0x03, 0x03);
+	svga_wseq_mask(par->state.vgabase, 0x14, 0x01, 0x01);
 
 	mutex_unlock(&(par->open_lock));
 	console_unlock();
@@ -1539,7 +1539,7 @@ static int __maybe_unused s3_pci_resume(struct device *dev)
 
 	vga_wseq(par->state.vgabase, 0x08, 0x06);
 	svga_wseq_mask(par->state.vgabase, 0x18, 0x00, 0x20);
-	svga_wseq_mask(par->state.vgabase, 0x14, 0x00, 0x03);
+	svga_wseq_mask(par->state.vgabase, 0x14, 0x00, 0x01);
 	s3fb_set_par(info);
 	fb_set_suspend(info, 0);
 

From da1bb9135213744e7ec398826c8f2e843de4fb94 Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Mon, 15 Sep 2025 08:36:41 +0200
Subject: [PATCH 086/352] fbdev: simplefb: Fix use after free in
 simplefb_detach_genpds()

The pm_domain cleanup can not be devres managed as it uses struct
simplefb_par which is allocated within struct fb_info by
framebuffer_alloc(). This allocation is explicitly freed by
unregister_framebuffer() in simplefb_remove().
Devres managed cleanup runs after the device remove call and thus can no
longer access struct simplefb_par.
Call simplefb_detach_genpds() explicitly from simplefb_destroy() like
the cleanup functions for clocks and regulators.

Fixes an use after free on M2 Mac mini during
aperture_remove_conflicting_devices() using the downstream asahi kernel
with Debian's kernel config. For unknown reasons this started to
consistently dereference an invalid pointer in v6.16.3 based kernels.

[    6.736134] BUG: KASAN: slab-use-after-free in simplefb_detach_genpds+0x58/0x220
[    6.743545] Read of size 4 at addr ffff8000304743f0 by task (udev-worker)/227
[    6.750697]
[    6.752182] CPU: 6 UID: 0 PID: 227 Comm: (udev-worker) Tainted: G S                  6.16.3-asahi+ #16 PREEMPTLAZY
[    6.752186] Tainted: [S]=CPU_OUT_OF_SPEC
[    6.752187] Hardware name: Apple Mac mini (M2, 2023) (DT)
[    6.752189] Call trace:
[    6.752190]  show_stack+0x34/0x98 (C)
[    6.752194]  dump_stack_lvl+0x60/0x80
[    6.752197]  print_report+0x17c/0x4d8
[    6.752201]  kasan_report+0xb4/0x100
[    6.752206]  __asan_report_load4_noabort+0x20/0x30
[    6.752209]  simplefb_detach_genpds+0x58/0x220
[    6.752213]  devm_action_release+0x50/0x98
[    6.752216]  release_nodes+0xd0/0x2c8
[    6.752219]  devres_release_all+0xfc/0x178
[    6.752221]  device_unbind_cleanup+0x28/0x168
[    6.752224]  device_release_driver_internal+0x34c/0x470
[    6.752228]  device_release_driver+0x20/0x38
[    6.752231]  bus_remove_device+0x1b0/0x380
[    6.752234]  device_del+0x314/0x820
[    6.752238]  platform_device_del+0x3c/0x1e8
[    6.752242]  platform_device_unregister+0x20/0x50
[    6.752246]  aperture_detach_platform_device+0x1c/0x30
[    6.752250]  aperture_detach_devices+0x16c/0x290
[    6.752253]  aperture_remove_conflicting_devices+0x34/0x50
...
[    6.752343]
[    6.967409] Allocated by task 62:
[    6.970724]  kasan_save_stack+0x3c/0x70
[    6.974560]  kasan_save_track+0x20/0x40
[    6.978397]  kasan_save_alloc_info+0x40/0x58
[    6.982670]  __kasan_kmalloc+0xd4/0xd8
[    6.986420]  __kmalloc_noprof+0x194/0x540
[    6.990432]  framebuffer_alloc+0xc8/0x130
[    6.994444]  simplefb_probe+0x258/0x2378
...
[    7.054356]
[    7.055838] Freed by task 227:
[    7.058891]  kasan_save_stack+0x3c/0x70
[    7.062727]  kasan_save_track+0x20/0x40
[    7.066565]  kasan_save_free_info+0x4c/0x80
[    7.070751]  __kasan_slab_free+0x6c/0xa0
[    7.074675]  kfree+0x10c/0x380
[    7.077727]  framebuffer_release+0x5c/0x90
[    7.081826]  simplefb_destroy+0x1b4/0x2c0
[    7.085837]  put_fb_info+0x98/0x100
[    7.089326]  unregister_framebuffer+0x178/0x320
[    7.093861]  simplefb_remove+0x3c/0x60
[    7.097611]  platform_remove+0x60/0x98
[    7.101361]  device_remove+0xb8/0x160
[    7.105024]  device_release_driver_internal+0x2fc/0x470
[    7.110256]  device_release_driver+0x20/0x38
[    7.114529]  bus_remove_device+0x1b0/0x380
[    7.118628]  device_del+0x314/0x820
[    7.122116]  platform_device_del+0x3c/0x1e8
[    7.126302]  platform_device_unregister+0x20/0x50
[    7.131012]  aperture_detach_platform_device+0x1c/0x30
[    7.136157]  aperture_detach_devices+0x16c/0x290
[    7.140779]  aperture_remove_conflicting_devices+0x34/0x50
...

Reported-by: Daniel Huhardeaux <tech@tootai.net>
Cc: stable@vger.kernel.org
Fixes: 92a511a568e44 ("fbdev/simplefb: Add support for generic power-domains")
Signed-off-by: Janne Grunau <j@jannau.net>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/simplefb.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index 1893815dc67f..6acf5a00c2ba 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -93,6 +93,7 @@ struct simplefb_par {
 
 static void simplefb_clocks_destroy(struct simplefb_par *par);
 static void simplefb_regulators_destroy(struct simplefb_par *par);
+static void simplefb_detach_genpds(void *res);
 
 /*
  * fb_ops.fb_destroy is called by the last put_fb_info() call at the end
@@ -105,6 +106,7 @@ static void simplefb_destroy(struct fb_info *info)
 
 	simplefb_regulators_destroy(info->par);
 	simplefb_clocks_destroy(info->par);
+	simplefb_detach_genpds(info->par);
 	if (info->screen_base)
 		iounmap(info->screen_base);
 
@@ -445,13 +447,14 @@ static void simplefb_detach_genpds(void *res)
 		if (!IS_ERR_OR_NULL(par->genpds[i]))
 			dev_pm_domain_detach(par->genpds[i], true);
 	}
+	par->num_genpds = 0;
 }
 
 static int simplefb_attach_genpds(struct simplefb_par *par,
 				  struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	unsigned int i;
+	unsigned int i, num_genpds;
 	int err;
 
 	err = of_count_phandle_with_args(dev->of_node, "power-domains",
@@ -465,26 +468,35 @@ static int simplefb_attach_genpds(struct simplefb_par *par,
 		return err;
 	}
 
-	par->num_genpds = err;
+	num_genpds = err;
 
 	/*
 	 * Single power-domain devices are handled by the driver core, so
 	 * nothing to do here.
 	 */
-	if (par->num_genpds <= 1)
+	if (num_genpds <= 1) {
+		par->num_genpds = num_genpds;
 		return 0;
+	}
 
-	par->genpds = devm_kcalloc(dev, par->num_genpds, sizeof(*par->genpds),
+	par->genpds = devm_kcalloc(dev, num_genpds, sizeof(*par->genpds),
 				   GFP_KERNEL);
 	if (!par->genpds)
 		return -ENOMEM;
 
-	par->genpd_links = devm_kcalloc(dev, par->num_genpds,
+	par->genpd_links = devm_kcalloc(dev, num_genpds,
 					sizeof(*par->genpd_links),
 					GFP_KERNEL);
 	if (!par->genpd_links)
 		return -ENOMEM;
 
+	/*
+	 * Set par->num_genpds only after genpds and genpd_links are allocated
+	 * to exit early from simplefb_detach_genpds() without full
+	 * initialisation.
+	 */
+	par->num_genpds = num_genpds;
+
 	for (i = 0; i < par->num_genpds; i++) {
 		par->genpds[i] = dev_pm_domain_attach_by_id(dev, i);
 		if (IS_ERR(par->genpds[i])) {
@@ -506,9 +518,10 @@ static int simplefb_attach_genpds(struct simplefb_par *par,
 			dev_warn(dev, "failed to link power-domain %u\n", i);
 	}
 
-	return devm_add_action_or_reset(dev, simplefb_detach_genpds, par);
+	return 0;
 }
 #else
+static void simplefb_detach_genpds(void *res) { }
 static int simplefb_attach_genpds(struct simplefb_par *par,
 				  struct platform_device *pdev)
 {
@@ -622,18 +635,20 @@ static int simplefb_probe(struct platform_device *pdev)
 	ret = devm_aperture_acquire_for_platform_device(pdev, par->base, par->size);
 	if (ret) {
 		dev_err(&pdev->dev, "Unable to acquire aperture: %d\n", ret);
-		goto error_regulators;
+		goto error_genpds;
 	}
 	ret = register_framebuffer(info);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to register simplefb: %d\n", ret);
-		goto error_regulators;
+		goto error_genpds;
 	}
 
 	dev_info(&pdev->dev, "fb%d: simplefb registered!\n", info->node);
 
 	return 0;
 
+error_genpds:
+	simplefb_detach_genpds(par);
 error_regulators:
 	simplefb_regulators_destroy(par);
 error_clocks:

From f9a68cf7b9afeb1780527f840995fc4292a2202a Mon Sep 17 00:00:00 2001
From: Akiyoshi Kurita <weibu@redadmin.org>
Date: Tue, 30 Sep 2025 22:45:47 +0900
Subject: [PATCH 087/352] dt-bindings: mmc: Correct typo "upto" to "up to"

The word "upto" is a typo for "up to". Correct this typo in the
mmc-controller-common binding documentation.

Signed-off-by: Akiyoshi Kurita <weibu@redadmin.org>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../devicetree/bindings/mmc/mmc-controller-common.yaml          | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml
index 1e601da0339a..9a369c8e9cb8 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml
+++ b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml
@@ -85,7 +85,7 @@ properties:
         - for eMMC, the maximum supported frequency is 200MHz,
         - for SD/SDIO cards the SDR104 mode has a max supported
           frequency of 208MHz,
-        - some mmc host controllers do support a max frequency upto
+        - some mmc host controllers do support a max frequency up to
           384MHz.
       So, lets keep the maximum supported value here.
 

From 4e66293bb141df33d5eb1f922e16fe05913bf296 Mon Sep 17 00:00:00 2001
From: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Date: Wed, 1 Oct 2025 14:27:16 +0530
Subject: [PATCH 088/352] of: doc: Fix typo in doc comments.

synthetized => synthesized
definied => defined
sucess => success

Signed-off-by: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/irq.c     | 2 +-
 drivers/of/overlay.c | 2 +-
 include/linux/of.h   | 8 ++++----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index e7c12abd10ab..1ca66b6e267c 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -163,7 +163,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph
  * @out_irq:	structure of_phandle_args updated by this function
  *
  * This function is a low-level interrupt tree walking function. It
- * can be used to do a partial walk with synthetized reg and interrupts
+ * can be used to do a partial walk with synthesized reg and interrupts
  * properties, for example when resolving PCI interrupts when no device
  * node exist for the parent. It takes an interrupt specifier structure as
  * input, walks the tree looking for any interrupt-map properties, translates
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 1af6f52d0708..255e8362f600 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -135,7 +135,7 @@ static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain);
  * @nb:		Notifier block to register
  *
  * Register for notification on overlay operations on device tree nodes. The
- * reported actions definied by @of_reconfig_change. The notifier callback
+ * reported actions defined by @of_reconfig_change. The notifier callback
  * furthermore receives a pointer to the affected device tree node.
  *
  * Note that a notifier callback is not supposed to store pointers to a device
diff --git a/include/linux/of.h b/include/linux/of.h
index 5e2c6ed9370a..121a288ca92d 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1134,7 +1134,7 @@ static inline bool of_phandle_args_equal(const struct of_phandle_args *a1,
  * Search for a property in a device node and count the number of u8 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u8 and -ENODATA if the
  * property does not have a value.
  */
@@ -1153,7 +1153,7 @@ static inline int of_property_count_u8_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u16 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u16 and -ENODATA if the
  * property does not have a value.
  */
@@ -1172,7 +1172,7 @@ static inline int of_property_count_u16_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u32 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u32 and -ENODATA if the
  * property does not have a value.
  */
@@ -1191,7 +1191,7 @@ static inline int of_property_count_u32_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u64 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u64 and -ENODATA if the
  * property does not have a value.
  */

From a8de554774ae48efbe48ace79f8badae2daa2bf1 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 30 Sep 2025 16:16:18 +0800
Subject: [PATCH 089/352] of: unittest: Fix device reference count leak in
 of_unittest_pci_node_verify

In of_unittest_pci_node_verify(), when the add parameter is false,
device_find_any_child() obtains a reference to a child device. This
function implicitly calls get_device() to increment the device's
reference count before returning the pointer. However, the caller
fails to properly release this reference by calling put_device(),
leading to a device reference count leak. Add put_device() in the else
branch immediately after child_dev is no longer needed.

As the comment of device_find_any_child states: "NOTE: you will need
to drop the reference with put_device() after use".

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/unittest.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index e3503ec20f6c..388e9ec2cccf 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -4300,6 +4300,7 @@ static int of_unittest_pci_node_verify(struct pci_dev *pdev, bool add)
 		unittest(!np, "Child device tree node is not removed\n");
 		child_dev = device_find_any_child(&pdev->dev);
 		unittest(!child_dev, "Child device is not removed\n");
+		put_device(child_dev);
 	}
 
 failed:

From 59abe7bc7e7c70e9066b3e46874d1b7e6a13de14 Mon Sep 17 00:00:00 2001
From: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Date: Thu, 2 Oct 2025 10:31:25 +0300
Subject: [PATCH 090/352] ASoC: SOF: ipc3-topology: Fix multi-core and static
 pipelines tear down
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the case of static pipelines, freeing the widgets in the pipelines
that were not suspended after freeing the scheduler widgets results in
errors because the secondary cores are powered off when the scheduler
widgets are freed. Fix this by tearing down the leftover pipelines before
powering off the secondary cores.

Cc: stable@vger.kernel.org
Fixes: d7332c4a4f1a ("ASoC: SOF: ipc3-topology: Fix pipeline tear down logic")
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20251002073125.32471-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc3-topology.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index 473d416bc910..f449362a2905 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -2473,11 +2473,6 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 	if (ret < 0)
 		return ret;
 
-	/* free all the scheduler widgets now */
-	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
-	if (ret < 0)
-		return ret;
-
 	/*
 	 * Tear down all pipelines associated with PCMs that did not get suspended
 	 * and unset the prepare flag so that they can be set up again during resume.
@@ -2493,6 +2488,11 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 		}
 	}
 
+	/* free all the scheduler widgets now. This will also power down the secondary cores */
+	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
 	list_for_each_entry(sroute, &sdev->route_list, list)
 		sroute->setup = false;
 

From bcd1383516bb5a6f72b2d1e7f7ad42c4a14837d1 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Thu, 2 Oct 2025 10:47:15 +0300
Subject: [PATCH 091/352] ASoC: SOF: ipc4-pcm: fix delay calculation when DSP
 resamples
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the sampling rates going in (host) and out (dai) from the DSP
are different, the IPC4 delay reporting does not work correctly.
Add support for this case by scaling the all raw position values to
a common timebase before calculating real-time delay for the PCM.

Cc: stable@vger.kernel.org
Fixes: 0ea06680dfcb ("ASoC: SOF: ipc4-pcm: Correct the delay calculation")
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20251002074719.2084-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-pcm.c | 83 ++++++++++++++++++++++++++++++----------
 1 file changed, 62 insertions(+), 21 deletions(-)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index cb9a06792a47..769ba4fed56a 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -19,12 +19,14 @@
  * struct sof_ipc4_timestamp_info - IPC4 timestamp info
  * @host_copier: the host copier of the pcm stream
  * @dai_copier: the dai copier of the pcm stream
- * @stream_start_offset: reported by fw in memory window (converted to frames)
- * @stream_end_offset: reported by fw in memory window (converted to frames)
+ * @stream_start_offset: reported by fw in memory window (converted to
+ *                       frames at host_copier sampling rate)
+ * @stream_end_offset: reported by fw in memory window (converted to
+ *                     frames at host_copier sampling rate)
  * @llp_offset: llp offset in memory window
- * @boundary: wrap boundary should be used for the LLP frame counter
  * @delay: Calculated and stored in pointer callback. The stored value is
- *	   returned in the delay callback.
+ *         returned in the delay callback. Expressed in frames at host copier
+ *         sampling rate.
  */
 struct sof_ipc4_timestamp_info {
 	struct sof_ipc4_copier *host_copier;
@@ -33,7 +35,6 @@ struct sof_ipc4_timestamp_info {
 	u64 stream_end_offset;
 	u32 llp_offset;
 
-	u64 boundary;
 	snd_pcm_sframes_t delay;
 };
 
@@ -48,6 +49,16 @@ struct sof_ipc4_pcm_stream_priv {
 	bool chain_dma_allocated;
 };
 
+/*
+ * Modulus to use to compare host and link position counters. The sampling
+ * rates may be different, so the raw hardware counters will wrap
+ * around at different times. To calculate differences, use
+ * DELAY_BOUNDARY as a common modulus. This value must be smaller than
+ * the wrap-around point of any hardware counter, and larger than any
+ * valid delay measurement.
+ */
+#define DELAY_BOUNDARY		U32_MAX
+
 static inline struct sof_ipc4_timestamp_info *
 sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps)
 {
@@ -1049,6 +1060,35 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component,
 	return 0;
 }
 
+static u64 sof_ipc4_frames_dai_to_host(struct sof_ipc4_timestamp_info *time_info, u64 value)
+{
+	u64 dai_rate, host_rate;
+
+	if (!time_info->dai_copier || !time_info->host_copier)
+		return value;
+
+	/*
+	 * copiers do not change sampling rate, so we can use the
+	 * out_format independently of stream direction
+	 */
+	dai_rate = time_info->dai_copier->data.out_format.sampling_frequency;
+	host_rate = time_info->host_copier->data.out_format.sampling_frequency;
+
+	if (!dai_rate || !host_rate || dai_rate == host_rate)
+		return value;
+
+	/* take care not to overflow u64, rates can be up to 768000 */
+	if (value > U32_MAX) {
+		value = div64_u64(value, dai_rate);
+		value *= host_rate;
+	} else {
+		value *= host_rate;
+		value = div64_u64(value, dai_rate);
+	}
+
+	return value;
+}
+
 static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
 					    struct snd_pcm_substream *substream,
 					    struct snd_sof_pcm_stream *sps,
@@ -1099,14 +1139,13 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
 	time_info->stream_end_offset = ppl_reg.stream_end_offset;
 	do_div(time_info->stream_end_offset, dai_sample_size);
 
+	/* convert to host frame time */
+	time_info->stream_start_offset =
+		sof_ipc4_frames_dai_to_host(time_info, time_info->stream_start_offset);
+	time_info->stream_end_offset =
+		sof_ipc4_frames_dai_to_host(time_info, time_info->stream_end_offset);
+
 out:
-	/*
-	 * Calculate the wrap boundary need to be used for delay calculation
-	 * The host counter is in bytes, it will wrap earlier than the frames
-	 * based link counter.
-	 */
-	time_info->boundary = div64_u64(~((u64)0),
-					frames_to_bytes(substream->runtime, 1));
 	/* Initialize the delay value to 0 (no delay) */
 	time_info->delay = 0;
 
@@ -1149,6 +1188,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
 
 	/* For delay calculation we need the host counter */
 	host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream);
+
+	/* Store the original value to host_ptr */
 	host_ptr = host_cnt;
 
 	/* convert the host_cnt to frames */
@@ -1167,6 +1208,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
 		sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp));
 		dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l;
 	}
+
+	dai_cnt = sof_ipc4_frames_dai_to_host(time_info, dai_cnt);
 	dai_cnt += time_info->stream_end_offset;
 
 	/* In two cases dai dma counter is not accurate
@@ -1200,8 +1243,9 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
 		dai_cnt -= time_info->stream_start_offset;
 	}
 
-	/* Wrap the dai counter at the boundary where the host counter wraps */
-	div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt);
+	/* Convert to a common base before comparisons */
+	dai_cnt &= DELAY_BOUNDARY;
+	host_cnt &= DELAY_BOUNDARY;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		head_cnt = host_cnt;
@@ -1211,14 +1255,11 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
 		tail_cnt = host_cnt;
 	}
 
-	if (head_cnt < tail_cnt) {
-		time_info->delay = time_info->boundary - tail_cnt + head_cnt;
-		goto out;
-	}
+	if (unlikely(head_cnt < tail_cnt))
+		time_info->delay = DELAY_BOUNDARY - tail_cnt + head_cnt;
+	else
+		time_info->delay = head_cnt - tail_cnt;
 
-	time_info->delay =  head_cnt - tail_cnt;
-
-out:
 	/*
 	 * Convert the host byte counter to PCM pointer which wraps in buffer
 	 * and it is in frames

From bace10b59624e6bd8d68bc9304357f292f1b3dcf Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Thu, 2 Oct 2025 10:47:16 +0300
Subject: [PATCH 092/352] ASoC: SOF: ipc4-pcm: fix start offset calculation for
 chain DMA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Assumption that chain DMA module starts the link DMA when 1ms of
data is available from host is not correct. Instead the firmware
chain DMA module fills the link DMA with initial buffer of zeroes
and the host and link DMAs are started at the same time.

This results in a small error in delay calculation. This can become a
more severe problem if host DMA has delays that exceed 1ms. This results
in negative delay to be calculated and bogus values reported to
applications. This can confuse some applications like
alsa_conformance_test.

Fix the issue by correctly calculating the firmware chain DMA
preamble size and initializing the start offset to this value.

Cc: stable@vger.kernel.org
Fixes: a1d203d390e0 ("ASoC: SOF: ipc4-pcm: Enable delay reporting for ChainDMA streams")
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20251002074719.2084-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-pcm.c      | 14 ++++++++++----
 sound/soc/sof/ipc4-topology.c |  1 -
 sound/soc/sof/ipc4-topology.h |  2 ++
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 769ba4fed56a..9d29d2e56c00 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -1108,7 +1108,7 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
 		return -EINVAL;
 	} else if (host_copier->data.gtw_cfg.node_id == SOF_IPC4_CHAIN_DMA_NODE_ID) {
 		/*
-		 * While the firmware does not supports time_info reporting for
+		 * While the firmware does not support time_info reporting for
 		 * streams using ChainDMA, it is granted that ChainDMA can only
 		 * be used on Host+Link pairs where the link position is
 		 * accessible from the host side.
@@ -1116,10 +1116,16 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
 		 * Enable delay calculation in case of ChainDMA via host
 		 * accessible registers.
 		 *
-		 * The ChainDMA uses 2x 1ms ping-pong buffer, dai side starts
-		 * when 1ms data is available
+		 * The ChainDMA prefills the link DMA with a preamble
+		 * of zero samples. Set the stream start offset based
+		 * on size of the preamble (driver provided fifo size
+		 * multiplied by 2.5). We add 1ms of margin as the FW
+		 * will align the buffer size to DMA hardware
+		 * alignment that is not known to host.
 		 */
-		time_info->stream_start_offset = substream->runtime->rate / MSEC_PER_SEC;
+		int pre_ms = SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS * 5 / 2 + 1;
+
+		time_info->stream_start_offset = pre_ms * substream->runtime->rate / MSEC_PER_SEC;
 		goto out;
 	}
 
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index b6a732d0adb4..36568160f163 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -33,7 +33,6 @@ MODULE_PARM_DESC(ipc4_ignore_cpc,
 
 #define SOF_IPC4_GAIN_PARAM_ID  0
 #define SOF_IPC4_TPLG_ABI_SIZE 6
-#define SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS 2
 
 static DEFINE_IDA(alh_group_ida);
 static DEFINE_IDA(pipeline_ida);
diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index dfa1a6c2ffa8..6b29692dff16 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -263,6 +263,8 @@ struct sof_ipc4_dma_stream_ch_map {
 #define SOF_IPC4_DMA_METHOD_HDA   1
 #define SOF_IPC4_DMA_METHOD_GPDMA 2 /* defined for consistency but not used */
 
+#define SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS 2
+
 /**
  * struct sof_ipc4_dma_config: DMA configuration
  * @dma_method: HDAudio or GPDMA

From a7fe5ff832d61d9393095bc3dd5f06f4af7da3c1 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 2 Oct 2025 16:57:50 +0300
Subject: [PATCH 093/352] ASoC: SOF: ipc4-topology: Correct the minimum host
 DMA buffer size

The firmware has changed the minimum host buffer size from 2 periods to
4 periods (1 period is 1ms) which was missed by the kernel side.

Adjust the SOF_IPC4_MIN_DMA_BUFFER_SIZE to 4 ms to align with firmware.

Link: https://github.com/thesofproject/sof/commit/f0a14a3f410735db18a79eb7a5f40dc49fdee7a7
Fixes: 594c1bb9ff73 ("ASoC: SOF: ipc4-topology: Do not parse the DMA_BUFFER_SIZE token")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20251002135752.2430-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index dfa1a6c2ffa8..d6894fdd7e1d 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -70,8 +70,8 @@
 #define SOF_IPC4_CHAIN_DMA_NODE_ID	0x7fffffff
 #define SOF_IPC4_INVALID_NODE_ID	0xffffffff
 
-/* FW requires minimum 2ms DMA buffer size */
-#define SOF_IPC4_MIN_DMA_BUFFER_SIZE	2
+/* FW requires minimum 4ms DMA buffer size */
+#define SOF_IPC4_MIN_DMA_BUFFER_SIZE	4
 
 /*
  * The base of multi-gateways. Multi-gateways addressing starts from

From 3dcf683bf1062d69014fe81b90d285c7eb85ca8a Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 2 Oct 2025 16:57:51 +0300
Subject: [PATCH 094/352] ASoC: SOF: ipc4-topology: Account for different
 ChainDMA host buffer size

For ChainDMA the firmware allocates 5ms host buffer instead of the standard
4ms which should be taken into account when setting the constraint on the
buffer size.

Fixes: 842bb8b62cc6 ("ASoC: SOF: ipc4-topology: Save the DMA maximum burst size for PCMs")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20251002135752.2430-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 9 +++++++--
 sound/soc/sof/ipc4-topology.h | 3 +++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index b6a732d0adb4..60cd7955e24f 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -666,8 +666,13 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
 				      swidget->tuples,
 				      swidget->num_tuples, sizeof(u32), 1);
 		/* Set default DMA buffer size if it is not specified in topology */
-		if (!sps->dsp_max_burst_size_in_ms)
-			sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE;
+		if (!sps->dsp_max_burst_size_in_ms) {
+			struct snd_sof_widget *pipe_widget = swidget->spipe->pipe_widget;
+			struct sof_ipc4_pipeline *pipeline = pipe_widget->private;
+
+			sps->dsp_max_burst_size_in_ms = pipeline->use_chain_dma ?
+				SOF_IPC4_CHAIN_DMA_BUFFER_SIZE : SOF_IPC4_MIN_DMA_BUFFER_SIZE;
+		}
 	} else {
 		/* Capture data is copied from DSP to host in 1ms bursts */
 		spcm->stream[dir].dsp_max_burst_size_in_ms = 1;
diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index d6894fdd7e1d..fc3b6411b9b2 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -73,6 +73,9 @@
 /* FW requires minimum 4ms DMA buffer size */
 #define SOF_IPC4_MIN_DMA_BUFFER_SIZE	4
 
+/* ChainDMA in fw uses 5ms DMA buffer */
+#define SOF_IPC4_CHAIN_DMA_BUFFER_SIZE	5
+
 /*
  * The base of multi-gateways. Multi-gateways addressing starts from
  * ALH_MULTI_GTW_BASE and there are ALH_MULTI_GTW_COUNT multi-sources

From 45ad27d9a6f7c620d8bbc80be3bab1faf37dfa0a Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 2 Oct 2025 16:57:52 +0300
Subject: [PATCH 095/352] ASoC: SOF: Intel: hda-pcm: Place the constraint on
 period time instead of buffer time

Instead of constraining the ALSA buffer time to be double of the firmware
host buffer size, it is better to set it for the period time.
This will implicitly constrain the buffer time to a safe value
(num_periods is at least 2) and prohibits applications to set smaller
period size than what will be covered by the initial DMA burst.

Fixes: fe76d2e75a6d ("ASoC: SOF: Intel: hda-pcm: Use dsp_max_burst_size_in_ms to place constraint")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20251002135752.2430-4-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-pcm.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c
index 1dd8d2092c3b..da6c1e7263cd 100644
--- a/sound/soc/sof/intel/hda-pcm.c
+++ b/sound/soc/sof/intel/hda-pcm.c
@@ -29,6 +29,8 @@
 #define SDnFMT_BITS(x)	((x) << 4)
 #define SDnFMT_CHAN(x)	((x) << 0)
 
+#define HDA_MAX_PERIOD_TIME_HEADROOM	10
+
 static bool hda_always_enable_dmi_l1;
 module_param_named(always_enable_dmi_l1, hda_always_enable_dmi_l1, bool, 0444);
 MODULE_PARM_DESC(always_enable_dmi_l1, "SOF HDA always enable DMI l1");
@@ -291,19 +293,30 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
 	 * On playback start the DMA will transfer dsp_max_burst_size_in_ms
 	 * amount of data in one initial burst to fill up the host DMA buffer.
 	 * Consequent DMA burst sizes are shorter and their length can vary.
-	 * To make sure that userspace allocate large enough ALSA buffer we need
-	 * to place a constraint on the buffer time.
+	 * To avoid immediate xrun by the initial burst we need to place
+	 * constraint on the period size (via PERIOD_TIME) to cover the size of
+	 * the host buffer.
+	 * We need to add headroom of max 10ms as the firmware needs time to
+	 * settle to the 1ms pacing and initially it can run faster for few
+	 * internal periods.
 	 *
 	 * On capture the DMA will transfer 1ms chunks.
-	 *
-	 * Exact dsp_max_burst_size_in_ms constraint is racy, so set the
-	 * constraint to a minimum of 2x dsp_max_burst_size_in_ms.
 	 */
-	if (spcm->stream[direction].dsp_max_burst_size_in_ms)
+	if (spcm->stream[direction].dsp_max_burst_size_in_ms) {
+		unsigned int period_time = spcm->stream[direction].dsp_max_burst_size_in_ms;
+
+		/*
+		 * add headroom over the maximum burst size to cover the time
+		 * needed for the DMA pace to settle.
+		 * Limit the headroom time to HDA_MAX_PERIOD_TIME_HEADROOM
+		 */
+		period_time += min(period_time, HDA_MAX_PERIOD_TIME_HEADROOM);
+
 		snd_pcm_hw_constraint_minmax(substream->runtime,
-			SNDRV_PCM_HW_PARAM_BUFFER_TIME,
-			spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2,
+			SNDRV_PCM_HW_PARAM_PERIOD_TIME,
+			period_time * USEC_PER_MSEC,
 			UINT_MAX);
+	}
 
 	/* binding pcm substream to hda stream */
 	substream->runtime->private_data = &dsp_stream->hstream;

From 7a6e249f90fd8d3fcaa8c497bc72c8e61b988bf0 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Mon, 22 Sep 2025 17:36:16 +0700
Subject: [PATCH 096/352] Documentation: fb: Split toctree

Framebuffer docs toctree consists of driver-independent docs
(e.g. API docs) and driver-specific docs. The latter has much
more entries.

Group the docs into separate toctrees.

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 Documentation/fb/index.rst | 80 +++++++++++++++++++++-----------------
 1 file changed, 45 insertions(+), 35 deletions(-)

diff --git a/Documentation/fb/index.rst b/Documentation/fb/index.rst
index 33e3c49f8856..e2f7488b6e2e 100644
--- a/Documentation/fb/index.rst
+++ b/Documentation/fb/index.rst
@@ -4,42 +4,52 @@
 Frame Buffer
 ============
 
-.. toctree::
-    :maxdepth: 1
+General information
+===================
 
-    api
-    arkfb
-    aty128fb
-    cirrusfb
-    cmap_xfbdev
-    deferred_io
-    efifb
-    ep93xx-fb
-    fbcon
-    framebuffer
-    gxfb
-    intel810
-    internals
-    lxfb
-    matroxfb
-    metronomefb
-    modedb
-    pvr2fb
-    pxafb
-    s3fb
-    sa1100fb
-    sh7760fb
-    sisfb
-    sm501
-    sm712fb
-    sstfb
-    tgafb
-    tridentfb
-    udlfb
-    uvesafb
-    vesafb
-    viafb
-    vt8623fb
+.. toctree::
+   :maxdepth: 1
+
+   api
+   cmap_xfbdev
+   deferred_io
+   fbcon
+   framebuffer
+   internals
+   modedb
+
+Driver documentation
+====================
+
+.. toctree::
+   :maxdepth: 1
+
+   arkfb
+   aty128fb
+   cirrusfb
+   efifb
+   ep93xx-fb
+   gxfb
+   intel810
+   lxfb
+   matroxfb
+   metronomefb
+   pvr2fb
+   pxafb
+   s3fb
+   sa1100fb
+   sh7760fb
+   sisfb
+   sm501
+   sm712fb
+   sstfb
+   tgafb
+   tridentfb
+   udlfb
+   uvesafb
+   vesafb
+   viafb
+   vt8623fb
 
 .. only::  subproject and html
 

From 9070fbcb9af5dd351628d030973a143f9e1b0ed4 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Mon, 22 Sep 2025 17:36:14 +0700
Subject: [PATCH 097/352] Documentation: fb: ep93xx: Demote section headings

Section headings are formatted the same as title heading, thus
increasing number of entries in framebuffer toctree. Demote them.

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 Documentation/fb/ep93xx-fb.rst | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/Documentation/fb/ep93xx-fb.rst b/Documentation/fb/ep93xx-fb.rst
index 1dd67f4688c7..93b3494f5309 100644
--- a/Documentation/fb/ep93xx-fb.rst
+++ b/Documentation/fb/ep93xx-fb.rst
@@ -41,7 +41,6 @@ your board initialisation function::
 
 	ep93xx_register_fb(&some_board_fb_info);
 
-=====================
 Video Attribute Flags
 =====================
 
@@ -79,7 +78,6 @@ EP93XXFB_USE_SDCSN2		Use SDCSn[2] for the framebuffer.
 EP93XXFB_USE_SDCSN3		Use SDCSn[3] for the framebuffer.
 =============================== ======================================
 
-==================
 Platform callbacks
 ==================
 
@@ -101,7 +99,6 @@ obtained as follows::
 		/* Board specific framebuffer setup */
 	}
 
-======================
 Setting the video mode
 ======================
 
@@ -119,7 +116,6 @@ set when the module is installed::
 
 	modprobe ep93xx-fb video=320x240
 
-==============
 Screenpage bug
 ==============
 

From 9d079868ae4b519ab925296337050fd1f2a20720 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Mon, 22 Sep 2025 17:36:15 +0700
Subject: [PATCH 098/352] Documentation: fb: Retitle driver docs

Many framebuffer driver docs are copied from vesafb docs as their
template, including "What is <driver name>" title. Such title
implies the introductory section, however, and not the whole docs.

Retitle them.

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 Documentation/fb/aty128fb.rst | 8 +++-----
 Documentation/fb/efifb.rst    | 6 +++---
 Documentation/fb/gxfb.rst     | 8 +++-----
 Documentation/fb/lxfb.rst     | 9 +++------
 Documentation/fb/matroxfb.rst | 9 +++------
 Documentation/fb/pvr2fb.rst   | 6 +++---
 Documentation/fb/sa1100fb.rst | 9 +++------
 Documentation/fb/sisfb.rst    | 6 +++---
 Documentation/fb/sm712fb.rst  | 6 +++---
 Documentation/fb/tgafb.rst    | 6 +++---
 Documentation/fb/udlfb.rst    | 6 +++---
 Documentation/fb/vesafb.rst   | 6 +++---
 12 files changed, 36 insertions(+), 49 deletions(-)

diff --git a/Documentation/fb/aty128fb.rst b/Documentation/fb/aty128fb.rst
index 3f107718f933..0da8070a5521 100644
--- a/Documentation/fb/aty128fb.rst
+++ b/Documentation/fb/aty128fb.rst
@@ -1,8 +1,6 @@
-=================
-What is aty128fb?
-=================
-
-.. [This file is cloned from VesaFB/matroxfb]
+=========================================
+aty128fb - ATI Rage128 framebuffer driver
+=========================================
 
 This is a driver for a graphic framebuffer for ATI Rage128 based devices
 on Intel and PPC boxes.
diff --git a/Documentation/fb/efifb.rst b/Documentation/fb/efifb.rst
index 6badff64756f..3d4aab406dee 100644
--- a/Documentation/fb/efifb.rst
+++ b/Documentation/fb/efifb.rst
@@ -1,6 +1,6 @@
-==============
-What is efifb?
-==============
+===================================
+efifb - Generic EFI platform driver
+===================================
 
 This is a generic EFI platform driver for systems with UEFI firmware. The
 system must be booted via the EFI stub for this to be usable. efifb supports
diff --git a/Documentation/fb/gxfb.rst b/Documentation/fb/gxfb.rst
index 5738709bccbb..3fda485606bd 100644
--- a/Documentation/fb/gxfb.rst
+++ b/Documentation/fb/gxfb.rst
@@ -1,8 +1,6 @@
-=============
-What is gxfb?
-=============
-
-.. [This file is cloned from VesaFB/aty128fb]
+=======================================
+gxfb - AMD Geode GX2 framebuffer driver
+=======================================
 
 This is a graphics framebuffer driver for AMD Geode GX2 based processors.
 
diff --git a/Documentation/fb/lxfb.rst b/Documentation/fb/lxfb.rst
index 863e6b98fbae..0a176ab376e3 100644
--- a/Documentation/fb/lxfb.rst
+++ b/Documentation/fb/lxfb.rst
@@ -1,9 +1,6 @@
-=============
-What is lxfb?
-=============
-
-.. [This file is cloned from VesaFB/aty128fb]
-
+======================================
+lxfb - AMD Geode LX framebuffer driver
+======================================
 
 This is a graphics framebuffer driver for AMD Geode LX based processors.
 
diff --git a/Documentation/fb/matroxfb.rst b/Documentation/fb/matroxfb.rst
index 6158c49c8571..8ac7534a2e61 100644
--- a/Documentation/fb/matroxfb.rst
+++ b/Documentation/fb/matroxfb.rst
@@ -1,9 +1,6 @@
-=================
-What is matroxfb?
-=================
-
-.. [This file is cloned from VesaFB. Thanks go to Gerd Knorr]
-
+================================================
+matroxfb - Framebuffer driver for Matrox devices
+================================================
 
 This is a driver for a graphic framebuffer for Matrox devices on
 Alpha, Intel and PPC boxes.
diff --git a/Documentation/fb/pvr2fb.rst b/Documentation/fb/pvr2fb.rst
index fcf2c21c8fcf..315ce085a585 100644
--- a/Documentation/fb/pvr2fb.rst
+++ b/Documentation/fb/pvr2fb.rst
@@ -1,6 +1,6 @@
-===============
-What is pvr2fb?
-===============
+===============================================
+pvr2fb - PowerVR 2 graphics frame buffer driver
+===============================================
 
 This is a driver for PowerVR 2 based graphics frame buffers, such as the
 one found in the Dreamcast.
diff --git a/Documentation/fb/sa1100fb.rst b/Documentation/fb/sa1100fb.rst
index 67e2650e017d..c5ca019b361a 100644
--- a/Documentation/fb/sa1100fb.rst
+++ b/Documentation/fb/sa1100fb.rst
@@ -1,9 +1,6 @@
-=================
-What is sa1100fb?
-=================
-
-.. [This file is cloned from VesaFB/matroxfb]
-
+=================================================
+sa1100fb - SA-1100 LCD graphic framebuffer driver
+=================================================
 
 This is a driver for a graphic framebuffer for the SA-1100 LCD
 controller.
diff --git a/Documentation/fb/sisfb.rst b/Documentation/fb/sisfb.rst
index 8f4e502ea12e..9982f5ee0560 100644
--- a/Documentation/fb/sisfb.rst
+++ b/Documentation/fb/sisfb.rst
@@ -1,6 +1,6 @@
-==============
-What is sisfb?
-==============
+=====================================
+sisfb - SiS framebuffer device driver
+=====================================
 
 sisfb is a framebuffer device driver for SiS (Silicon Integrated Systems)
 graphics chips. Supported are:
diff --git a/Documentation/fb/sm712fb.rst b/Documentation/fb/sm712fb.rst
index 8e000f80b5bc..abbc6efae25f 100644
--- a/Documentation/fb/sm712fb.rst
+++ b/Documentation/fb/sm712fb.rst
@@ -1,6 +1,6 @@
-================
-What is sm712fb?
-================
+==========================================================
+sm712fb - Silicon Motion SM712 graphics framebuffer driver
+==========================================================
 
 This is a graphics framebuffer driver for Silicon Motion SM712 based processors.
 
diff --git a/Documentation/fb/tgafb.rst b/Documentation/fb/tgafb.rst
index 0c50d2134aa4..f0944da1ea5e 100644
--- a/Documentation/fb/tgafb.rst
+++ b/Documentation/fb/tgafb.rst
@@ -1,6 +1,6 @@
-==============
-What is tgafb?
-==============
+=======================================
+tgafb - TGA graphics framebuffer driver
+=======================================
 
 This is a driver for DECChip 21030 based graphics framebuffers, a.k.a. TGA
 cards, which are usually found in older Digital Alpha systems. The
diff --git a/Documentation/fb/udlfb.rst b/Documentation/fb/udlfb.rst
index 99cfbb7a1922..9e75ac6b07c3 100644
--- a/Documentation/fb/udlfb.rst
+++ b/Documentation/fb/udlfb.rst
@@ -1,6 +1,6 @@
-==============
-What is udlfb?
-==============
+==================================
+udlfb - DisplayLink USB 2.0 driver
+==================================
 
 This is a driver for DisplayLink USB 2.0 era graphics chips.
 
diff --git a/Documentation/fb/vesafb.rst b/Documentation/fb/vesafb.rst
index f890a4f5623b..d8241e38bb28 100644
--- a/Documentation/fb/vesafb.rst
+++ b/Documentation/fb/vesafb.rst
@@ -1,6 +1,6 @@
-===============
-What is vesafb?
-===============
+===========================================
+vesafb - Generic graphic framebuffer driver
+===========================================
 
 This is a generic driver for a graphic framebuffer on intel boxes.
 

From c3073f1da0517b63cf3e561d79c346e15bd8c5a8 Mon Sep 17 00:00:00 2001
From: Sukrut Heroorkar <hsukrut3@gmail.com>
Date: Tue, 23 Sep 2025 19:14:04 +0200
Subject: [PATCH 099/352] fbdev: radeonfb: Remove stale product link in Kconfig

The product page referenced in the FB_RADEON is no longer valid.
Remove it to avoid pointing to an invalid link.

Signed-off-by: Sukrut Heroorkar <hsukrut3@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/Kconfig | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index 1500dca8c416..ed1ecc0ded5c 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -948,9 +948,6 @@ config FB_RADEON
 	  a framebuffer device.  There are both PCI and AGP versions.  You
 	  don't need to choose this to run the Radeon in plain VGA mode.
 
-	  There is a product page at
-	  https://products.amd.com/en-us/GraphicCardResult.aspx
-
 config FB_RADEON_I2C
 	bool "DDC/I2C for ATI Radeon support"
 	depends on FB_RADEON

From c8fee6a7c5cbde4908804aafc469391c22e72be9 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 24 Sep 2025 10:33:40 +0200
Subject: [PATCH 100/352] fbdev: Make drivers depend on LCD_CLASS_DEVICE

LCD_CLASS_DEVICE is the user-controlled option that enables the LCD
display subsystem. Do not select it from fbdev drivers. Selecting it
from drivers can lead to cyclic dependencies within the config.

Some guidelines for using select can be found in the kernel docs at [1].

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://elixir.bootlin.com/linux/v6.16/source/Documentation/kbuild/kconfig-language.rst#L147 # [1]
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index ed1ecc0ded5c..19556d7629e0 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -126,9 +126,9 @@ config FB_ACORN
 config FB_CLPS711X
 	tristate "CLPS711X LCD support"
 	depends on FB && (ARCH_CLPS711X || COMPILE_TEST)
+	depends on LCD_CLASS_DEVICE
 	select FB_IOMEM_HELPERS
 	select FB_MODE_HELPERS
-	select LCD_CLASS_DEVICE
 	select VIDEOMODE_HELPERS
 	help
 	  Say Y to enable the Framebuffer driver for the Cirrus Logic
@@ -150,7 +150,7 @@ config FB_IMX
 	tristate "Freescale i.MX1/21/25/27 LCD support"
 	depends on FB && HAVE_CLK && HAS_IOMEM
 	depends on ARCH_MXC || COMPILE_TEST
-	select LCD_CLASS_DEVICE
+	depends on LCD_CLASS_DEVICE
 	select FB_IOMEM_HELPERS
 	select FB_MODE_HELPERS
 	select VIDEOMODE_HELPERS

From 98b7bf54338b797e3a11e8178ce0e806060d8fa3 Mon Sep 17 00:00:00 2001
From: Li Chen <me@linux.beauty>
Date: Tue, 30 Sep 2025 08:35:59 +0800
Subject: [PATCH 101/352] loop: fix backing file reference leak on validation
 error

loop_change_fd() and loop_configure() call loop_check_backing_file()
to validate the new backing file. If validation fails, the reference
acquired by fget() was not dropped, leaking a file reference.

Fix this by calling fput(file) before returning the error.

Cc: stable@vger.kernel.org
Cc: Markus Elfring <Markus.Elfring@web.de>
CC: Yang Erkun <yangerkun@huawei.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Yu Kuai <yukuai1@huaweicloud.com>
Fixes: f5c84eff634b ("loop: Add sanity check for read/write_iter")
Signed-off-by: Li Chen <chenl311@chinatelecom.cn>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yang Erkun <yangerkun@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 053a086d547e..94ec7f747f36 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -551,8 +551,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 		return -EBADF;
 
 	error = loop_check_backing_file(file);
-	if (error)
+	if (error) {
+		fput(file);
 		return error;
+	}
 
 	/* suppress uevents while reconfiguring the device */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1);
@@ -993,8 +995,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 		return -EBADF;
 
 	error = loop_check_backing_file(file);
-	if (error)
+	if (error) {
+		fput(file);
 		return error;
+	}
 
 	is_loop = is_loop_device(file);
 

From 510d76646a6a7beaa49fc0da7282e285a3dfce97 Mon Sep 17 00:00:00 2001
From: Tang Yizhou <yizhou.tang@shopee.com>
Date: Tue, 23 Sep 2025 19:21:36 +0800
Subject: [PATCH 102/352] block: Update a comment of disk statistics

>From commit 074a7aca7afa ("block: move stats from disk to part0"),
we know that:

* {disk|all}_stat_*() are gone.

* disk_stat_lock/unlock() are renamed to part_stat_lock/unlock().

Therefore, outdated comments should be updated accordingly.

Fixes: 074a7aca7afa ("block: move stats from disk to part0")
Signed-off-by: Tang Yizhou <yizhou.tang@shopee.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/part_stat.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index eeeff2a04529..729415e91215 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -17,8 +17,8 @@ struct disk_stats {
 /*
  * Macros to operate on percpu disk statistics:
  *
- * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should
- * be called between disk_stat_lock() and disk_stat_unlock().
+ * part_stat_{add|sub|inc|dec}() modify the stat counters and should
+ * be called between part_stat_lock() and part_stat_unlock().
  *
  * part_stat_read() can be called at any time.
  */

From 7bd03e3914f15720f8385d58bef0f1849df659e1 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 22 Sep 2025 12:12:07 +0200
Subject: [PATCH 103/352] drm/xe/tests: Fix build break on clang 16.0.6

The following error was reported when building with clang 16.0.6:

   In file included from drivers/gpu/drm/xe/xe_pci.c:1104:
>> drivers/gpu/drm/xe/tests/xe_pci.c:214:2: error: initializer \
   element is not a compile-time constant
           graphics_ip_xelp,
           ^~~~~~~~~~~~~~~~
   drivers/gpu/drm/xe/tests/xe_pci.c:221:2: error: initializer \
   element is not a compile-time constant
           media_ip_xem,
           ^~~~~~~~~~~~
   2 errors generated.

Fix that by explicit re-definition of pre-GMDID IPs, as there are
not so many of them.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202509192041.tQwdE4DS-lkp@intel.com/
Fixes: 5bb5258e357e ("drm/xe/tests: Add pre-GMDID IP descriptors to param generators")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250922101207.192028-1-michal.wajdeczko@intel.com
(cherry picked from commit 2de80e2da74b402a9d838b8e729cd01cf94cdcbc)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_pci.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c
index aa29ac759d5d..0f136bc85b76 100644
--- a/drivers/gpu/drm/xe/tests/xe_pci.c
+++ b/drivers/gpu/drm/xe/tests/xe_pci.c
@@ -211,15 +211,15 @@ static void xe_ip_kunit_desc(const struct xe_ip *param, char *desc)
  * param generator can be used for both
  */
 static const struct xe_ip pre_gmdid_graphics_ips[] = {
-	graphics_ip_xelp,
-	graphics_ip_xelpp,
-	graphics_ip_xehpg,
-	graphics_ip_xehpc,
+	{ 1200, "Xe_LP", &graphics_xelp },
+	{ 1210, "Xe_LP+", &graphics_xelp },
+	{ 1255, "Xe_HPG", &graphics_xehpg },
+	{ 1260, "Xe_HPC", &graphics_xehpc },
 };
 
 static const struct xe_ip pre_gmdid_media_ips[] = {
-	media_ip_xem,
-	media_ip_xehpm,
+	{ 1200, "Xe_M", &media_xem },
+	{ 1255, "Xe_HPM", &media_xem },
 };
 
 KUNIT_ARRAY_PARAM(pre_gmdid_graphics_ip, pre_gmdid_graphics_ips, xe_ip_kunit_desc);

From 7646423c7ff14156f5c163e995ba896ea9a0d559 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 24 Sep 2025 08:27:10 -0700
Subject: [PATCH 104/352] drm/xe/configfs: Fix engine class parsing

If mask is NULL, only the engine class should be accepted, so the
pattern string should be completely parsed. This should fix passing e.g.
rcs0 to ctx_restore_post_bb when it's only expecting the engine class.

Reported-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Closes: https://lore.kernel.org/r/20250922155544.67712-1-jonathan.cavitt@intel.com
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/aNJKnrCQmL9xS9Gv@stanley.mountain
Fixes: e2a9854d806e ("drm/xe/configfs: Allow to select by class only")
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250924152709.659483-3-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit dd797967160b79cc0ca2d2eb05fc55436b66dce0)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 8a9b950e7a6d..beade13efbae 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -324,8 +324,8 @@ static const struct engine_info *lookup_engine_info(const char *pattern, u64 *ma
 			continue;
 
 		pattern += strlen(engine_info[i].cls);
-		if (!mask && !*pattern)
-			return &engine_info[i];
+		if (!mask)
+			return *pattern ? NULL : &engine_info[i];
 
 		if (!strcmp(pattern, "*")) {
 			*mask = engine_info[i].mask;

From 59b7ed0ba2e0fc18dda19a2c48eea2c3cef652f3 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 24 Sep 2025 08:27:11 -0700
Subject: [PATCH 105/352] drm/xe/configfs: Improve doc for ctx_restore*
 attributes

Spell out the syntax instead of only using examples. Particularly
important the <engine-class> part since that's different than
engines_allowed and may confuse users. The same batch buffer is used for
all engines of a certain class.

Cc: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Fixes: e2a9854d806e ("drm/xe/configfs: Allow to select by class only")
Link: https://lore.kernel.org/r/20250924152709.659483-4-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 47ca7acff4011fa322853a3612f464b959e88210)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index beade13efbae..139663423185 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -126,8 +126,20 @@
  * not intended for normal execution and will taint the kernel with TAINT_TEST
  * when used.
  *
- * Currently this is implemented only for post and mid context restore.
- * Examples:
+ * The syntax allows to pass straight instructions to be executed by the engine
+ * in a batch buffer or set specific registers.
+ *
+ * #. Generic instruction::
+ *
+ *	<engine-class> cmd <instr> [[dword0] [dword1] [...]]
+ *
+ * #. Simple register setting::
+ *
+ *	<engine-class> reg <address> <value>
+ *
+ * Commands are saved per engine class: all instances of that class will execute
+ * those commands during context switch. The instruction, dword arguments,
+ * addresses and values are in hex format like in the examples below.
  *
  * #. Execute a LRI command to write 0xDEADBEEF to register 0x4f10 after the
  *    normal context restore::
@@ -154,7 +166,8 @@
  *       When using multiple lines, make sure to use a command that is
  *       implemented with a single write syscall, like HEREDOC.
  *
- * These attributes can only be set before binding to the device.
+ * Currently this is implemented only for post and mid context restore and
+ * these attributes can only be set before binding to the device.
  *
  * Remove devices
  * ==============

From de61d5944c87d21e5692823f30fb61c95df300bf Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Sun, 28 Sep 2025 19:48:10 +0200
Subject: [PATCH 106/352] drm/xe/vf: Rename sriov_update_device_info
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is a VF only function and its name should reflect that to
avoid any confusion. Move the VF check to the caller side.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://lore.kernel.org/r/20250928174811.198933-2-michal.wajdeczko@intel.com
(cherry picked from commit b88bb1eefa88f0cefc00fe5e78b1186cd8f9db78)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index fdb7b7498920..325b263f26fc 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -685,16 +685,15 @@ static int wait_for_lmem_ready(struct xe_device *xe)
 }
 ALLOW_ERROR_INJECTION(wait_for_lmem_ready, ERRNO); /* See xe_pci_probe() */
 
-static void sriov_update_device_info(struct xe_device *xe)
+static void vf_update_device_info(struct xe_device *xe)
 {
+	xe_assert(xe, IS_SRIOV_VF(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;
-	}
+	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;
 }
 
 static int xe_device_vram_alloc(struct xe_device *xe)
@@ -735,7 +734,8 @@ int xe_device_probe_early(struct xe_device *xe)
 
 	xe_sriov_probe_early(xe);
 
-	sriov_update_device_info(xe);
+	if (IS_SRIOV_VF(xe))
+		vf_update_device_info(xe);
 
 	err = xe_pcode_probe_early(xe);
 	if (err || xe_survivability_mode_is_requested(xe)) {

From 3734c8184d71c946c4128ce44ca1767c084f2358 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Sun, 28 Sep 2025 19:48:11 +0200
Subject: [PATCH 107/352] drm/xe/vf: Don't claim support for firmware late-bind
 if VF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In general, the VFs can't load firmwares so attempt to initialize
the firmware late-bind component leads to errors like:

 [] xe 0000:03:00.1: [drm] *ERROR* Late bind component not bound

Fixes: 918bd789d62e ("drm/xe/xe_late_bind_fw: Introduce xe_late_bind_fw")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/6190
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Badal Nilawar <badal.nilawar@intel.com>
Link: https://lore.kernel.org/r/20250928174811.198933-3-michal.wajdeczko@intel.com
(cherry picked from commit e35e288090f362be88d77b60d9846cea15df173e)
Signed-off-by: Lucas De Marchi <lucas.demarchi@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 325b263f26fc..2883b39c9b37 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -692,6 +692,7 @@ static void vf_update_device_info(struct xe_device *xe)
 	xe->info.probe_display = 0;
 	xe->info.has_heci_cscfi = 0;
 	xe->info.has_heci_gscfi = 0;
+	xe->info.has_late_bind = 0;
 	xe->info.skip_guc_pc = 1;
 	xe->info.skip_pcode = 1;
 }

From 17f6f6f25a98f10e8ebe022b7412a030462e7d2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Mon, 29 Sep 2025 13:26:49 +0200
Subject: [PATCH 108/352] drm/xe/bo: Fix an idle assertion for local bos
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before calling ttm_bo_populate() in the CPU fault path of a bo,
we assert that the bo is not being migrated. However, for
local bos we share the reservation object with other local bos
that might be in the process of being migrated. Also some VM
operations may attach USAGE_KERNEL fences to the common
reservation object and trigger false positives from the assert.

So remove the assert and instead wait for bo idle. This may
unnecessarily wait for idle in some cases but since we're
doing this wait later in the fault path anyway we might as
well do it here as well.

This fixes warnings like:
Sep 25 14:56:23 desky kernel: ------------[ cut here ]------------
Sep 25 14:56:23 desky kernel: xe 0000:03:00.0: [drm] Assertion `dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) || (tbo->ttm && ttm_tt_is_populated(tbo->ttm))` failed!
                              platform: BATTLEMAGE subplatform: 1
                              graphics: Xe2_HPG 20.01 step A0
                              media: Xe2_HPM 13.01 step A1
Sep 25 14:56:23 desky kernel: WARNING: CPU: 6 PID: 24767 at drivers/gpu/drm/xe/xe_bo.c:1748 xe_bo_fault_migrate+0x1bb/0x300 [xe]
Sep 25 14:56:23 desky kernel: Modules linked in: cpuid dm_crypt xt_conntrack nft_chain_nat xt_MASQUERADE nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 bridge stp llc xfrm_user xfr>
Sep 25 14:56:23 desky kernel:  snd_soc_sdca snd_seq_midi prime_numbers coretemp snd_seq_midi_event drm_ttm_helper snd_hda_codec drm_buddy drm_exec snd_rawmidi snd_soc_core snd_hda_cor>
Sep 25 14:56:23 desky kernel: CPU: 6 UID: 1000 PID: 24767 Comm: steamwebhelper Tainted: G     U  W           6.17.0-rc7+ #32 PREEMPT(voluntary)
Sep 25 14:56:23 desky kernel: Tainted: [U]=USER, [W]=WARN
Sep 25 14:56:23 desky kernel: Hardware name: Micro-Star International Co., Ltd. MS-7D36/PRO Z690-P DDR4 (MS-7D36), BIOS A.A1 10/18/2022
Sep 25 14:56:23 desky kernel: RIP: 0010:xe_bo_fault_migrate+0x1bb/0x300 [xe]
Sep 25 14:56:23 desky kernel: Code: fa 64 29 f9 48 c7 c7 40 e0 d3 c1 51 48 c7 c1 c0 e3 d3 c1 52 4c 8b 45 c0 41 50 44 8b 4d c8 4d 89 e0 48 8b 55 a8 e8 25 27 95 ef <0f> 0b 48 83 c4 40 4>
Sep 25 14:56:23 desky kernel: RSP: 0000:ffffae1ca88c7b10 EFLAGS: 00010286
Sep 25 14:56:23 desky kernel: RAX: 0000000000000000 RBX: ffff8d7cfd7e6800 RCX: 0000000000000027
Sep 25 14:56:23 desky kernel: RDX: ffff8d845019cec8 RSI: 0000000000000001 RDI: ffff8d845019cec0
Sep 25 14:56:23 desky kernel: RBP: ffffae1ca88c7bc8 R08: 0000000000000000 R09: 0000000000000000
Sep 25 14:56:23 desky kernel: R10: 0000000000000000 R11: 0000000000000004 R12: ffffffffc1db1faa
Sep 25 14:56:23 desky kernel: R13: ffffffffc1db2ab4 R14: 0000000000000001 R15: ffffae1ca88c7bd8
Sep 25 14:56:23 desky kernel: FS:  00007fb1baf31940(0000) GS:ffff8d849c870000(0000) knlGS:0000000000000000
Sep 25 14:56:23 desky kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Sep 25 14:56:23 desky kernel: CR2: 00007fb1b2860020 CR3: 00000001705a9004 CR4: 0000000000772ef0
Sep 25 14:56:23 desky kernel: PKRU: 55555558
Sep 25 14:56:23 desky kernel: Call Trace:
Sep 25 14:56:23 desky kernel:  <TASK>
Sep 25 14:56:23 desky kernel:  xe_bo_cpu_fault_fastpath+0x11e/0x220 [xe]
Sep 25 14:56:23 desky kernel:  xe_bo_cpu_fault+0x84/0x410 [xe]
Sep 25 14:56:23 desky kernel:  ? __x64_sys_mmap+0x33/0x50
Sep 25 14:56:23 desky kernel:  ? x64_sys_call+0x1b2e/0x20d0
Sep 25 14:56:23 desky kernel:  ? do_syscall_64+0x9d/0x1f0
Sep 25 14:56:23 desky kernel:  ? __check_object_size+0x4a/0x2e0
Sep 25 14:56:23 desky kernel:  __do_fault+0x36/0x190
Sep 25 14:56:23 desky kernel:  do_fault+0xcf/0x570
Sep 25 14:56:23 desky kernel:  __handle_mm_fault+0x92b/0xfe0
Sep 25 14:56:23 desky kernel:  ? ktime_get_mono_fast_ns+0x39/0xd0
Sep 25 14:56:23 desky kernel:  handle_mm_fault+0x164/0x2c0
Sep 25 14:56:23 desky kernel:  do_user_addr_fault+0x2cb/0x840
Sep 25 14:56:23 desky kernel:  exc_page_fault+0x75/0x180
Sep 25 14:56:23 desky kernel:  asm_exc_page_fault+0x27/0x30
Sep 25 14:56:23 desky kernel: RIP: 0033:0x7fb1bc388bb7
Sep 25 14:56:23 desky kernel: Code: 48 ff c7 48 01 fe 48 8d 54 11 80 0f 1f 84 00 00 00 00 00 c5 fe 6f 0e c5 fe 6f 56 20 c5 fe 6f 5e 40 c5 fe 6f 66 60 48 83 ee 80 <c5> fd 7f 0f c5 fd 7>
Sep 25 14:56:23 desky kernel: RSP: 002b:00007ffd7814fad8 EFLAGS: 00010207
Sep 25 14:56:23 desky kernel: RAX: 00007fb1b2860000 RBX: 0000000000000690 RCX: 00007fb1b2860000
Sep 25 14:56:23 desky kernel: RDX: 00007fb1b2860610 RSI: 0000556eda79f4c0 RDI: 00007fb1b2860020
Sep 25 14:56:23 desky kernel: RBP: 00007ffd7814fb60 R08: 0000000000000000 R09: 000000012be0e000
Sep 25 14:56:23 desky kernel: R10: 00007fb1b2860000 R11: 0000000000000246 R12: 0000556edd39a240
Sep 25 14:56:23 desky kernel: R13: 00007fb1b2dcb010 R14: 0000556eda79f420 R15: 0000000000000000
Sep 25 14:56:23 desky kernel:  </TASK>

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5250
Fixes: c2ae94cf8cd8 ("drm/xe: Convert the CPU fault handler for exhaustive eviction")
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250929112649.6131-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 8f1756a7ea33b352a54e6f53d76c552b3a424187)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c | 34 +++++++++++++++++++++++-----------
 1 file changed, 23 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 8422f3cab113..4410e28dee54 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1737,6 +1737,24 @@ static bool should_migrate_to_smem(struct xe_bo *bo)
 	       bo->attr.atomic_access == DRM_XE_ATOMIC_CPU;
 }
 
+static int xe_bo_wait_usage_kernel(struct xe_bo *bo, struct ttm_operation_ctx *ctx)
+{
+	long lerr;
+
+	if (ctx->no_wait_gpu)
+		return dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL) ?
+			0 : -EBUSY;
+
+	lerr = dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
+				     ctx->interruptible, MAX_SCHEDULE_TIMEOUT);
+	if (lerr < 0)
+		return lerr;
+	if (lerr == 0)
+		return -EBUSY;
+
+	return 0;
+}
+
 /* Populate the bo if swapped out, or migrate if the access mode requires that. */
 static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx,
 			       struct drm_exec *exec)
@@ -1745,10 +1763,9 @@ static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx,
 	int err = 0;
 
 	if (ttm_manager_type(tbo->bdev, tbo->resource->mem_type)->use_tt) {
-		xe_assert(xe_bo_device(bo),
-			  dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) ||
-			  (tbo->ttm && ttm_tt_is_populated(tbo->ttm)));
-		err = ttm_bo_populate(&bo->ttm, ctx);
+		err = xe_bo_wait_usage_kernel(bo, ctx);
+		if (!err)
+			err = ttm_bo_populate(&bo->ttm, ctx);
 	} else if (should_migrate_to_smem(bo)) {
 		xe_assert(xe_bo_device(bo), bo->flags & XE_BO_FLAG_SYSTEM);
 		err = xe_bo_migrate(bo, XE_PL_TT, ctx, exec);
@@ -1922,7 +1939,6 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf)
 			.no_wait_gpu = false,
 			.gfp_retry_mayfail = retry_after_wait,
 		};
-		long lerr;
 
 		err = drm_exec_lock_obj(&exec, &tbo->base);
 		drm_exec_retry_on_contention(&exec);
@@ -1942,13 +1958,9 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf)
 			break;
 		}
 
-		lerr = dma_resv_wait_timeout(tbo->base.resv,
-					     DMA_RESV_USAGE_KERNEL, true,
-					     MAX_SCHEDULE_TIMEOUT);
-		if (lerr < 0) {
-			err = lerr;
+		err = xe_bo_wait_usage_kernel(bo, &tctx);
+		if (err)
 			break;
-		}
 
 		if (!retry_after_wait)
 			ret = __xe_bo_cpu_fault(vmf, xe, bo);

From 5b440a8bbafcc673bcff33438c68ea03993948b2 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 24 Sep 2025 11:22:08 +0100
Subject: [PATCH 109/352] drm/xe/xe_late_bind_fw: Fix missing initialization of
 variable offset

The variable offset is not being initialized, and it is only set inside
a for-loop if entry->name is the same as manifest_entry. In the case
where it is not initialized a non-zero check on offset is potentialy checking
a bogus uninitalized value. Fix this by initializing offset to zero.

Fixes: efa29317a553 ("drm/xe/xe_late_bind_fw: Extract and print version info")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250924102208.9216-1-colin.i.king@gmail.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 20f3b28e2e07747fd27301f0f5deb3cb569ee15c)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_late_bind_fw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw.c b/drivers/gpu/drm/xe/xe_late_bind_fw.c
index 38f3feb2aecd..8f5082e689dc 100644
--- a/drivers/gpu/drm/xe/xe_late_bind_fw.c
+++ b/drivers/gpu/drm/xe/xe_late_bind_fw.c
@@ -60,7 +60,7 @@ static int parse_cpd_header(struct xe_late_bind_fw *lb_fw,
 	const struct gsc_manifest_header *manifest;
 	const struct gsc_cpd_entry *entry;
 	size_t min_size = sizeof(*header);
-	u32 offset;
+	u32 offset = 0;
 	int i;
 
 	/* manifest_entry is mandatory */
@@ -116,7 +116,7 @@ static int parse_lb_layout(struct xe_late_bind_fw *lb_fw,
 	const struct csc_fpt_header *header = data;
 	const struct csc_fpt_entry *entry;
 	size_t min_size = sizeof(*header);
-	u32 offset;
+	u32 offset = 0;
 	int i;
 
 	/* fpt_entry is mandatory */

From 10aa5c80603088d10c2cd5e7e27d561a8fb59c7e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 30 Sep 2025 14:27:52 +0200
Subject: [PATCH 110/352] drm/gpusvm, drm/xe: Fix userptr to not allow device
 private pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When userptr is used on SVM-enabled VMs, a non-NULL
hmm_range::dev_private_owner value might mean that
hmm_range_fault() attempts to return device private pages.
Either that will fail, or the userptr code will not know
how to handle those.

Use NULL for hmm_range::dev_private_owner to migrate
such pages to system. In order to do that, move the
struct drm_gpusvm::device_private_page_owner field to
struct drm_gpusvm_ctx::device_private_page_owner so that
it doesn't remain immutable over the drm_gpusvm lifetime.

v2:
- Don't conditionally compile xe_svm_devm_owner().
- Kerneldoc xe_svm_devm_owner().

Fixes: 9e9787414882 ("drm/xe/userptr: replace xe_hmm with gpusvm")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@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/20250930122752.96034-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit ad298d9ec957414dbf3d51f3c8bca4b6d2416c0c)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/drm_gpusvm.c    | 24 +++++++++++++-----------
 drivers/gpu/drm/xe/xe_svm.c     | 11 +++--------
 drivers/gpu/drm/xe/xe_svm.h     | 14 ++++++++++++++
 drivers/gpu/drm/xe/xe_userptr.c |  1 +
 drivers/gpu/drm/xe/xe_vm.c      |  1 +
 include/drm/drm_gpusvm.h        |  7 ++++---
 6 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index eeeeb99cfdf6..cb906765897e 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -361,7 +361,6 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = {
  * @name: Name of the GPU SVM.
  * @drm: Pointer to the DRM device structure.
  * @mm: Pointer to the mm_struct for the address space.
- * @device_private_page_owner: Device private pages owner.
  * @mm_start: Start address of GPU SVM.
  * @mm_range: Range of the GPU SVM.
  * @notifier_size: Size of individual notifiers.
@@ -383,7 +382,7 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = {
  */
 int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
 		    const char *name, struct drm_device *drm,
-		    struct mm_struct *mm, void *device_private_page_owner,
+		    struct mm_struct *mm,
 		    unsigned long mm_start, unsigned long mm_range,
 		    unsigned long notifier_size,
 		    const struct drm_gpusvm_ops *ops,
@@ -395,15 +394,13 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
 		mmgrab(mm);
 	} else {
 		/* No full SVM mode, only core drm_gpusvm_pages API. */
-		if (ops || num_chunks || mm_range || notifier_size ||
-		    device_private_page_owner)
+		if (ops || num_chunks || mm_range || notifier_size)
 			return -EINVAL;
 	}
 
 	gpusvm->name = name;
 	gpusvm->drm = drm;
 	gpusvm->mm = mm;
-	gpusvm->device_private_page_owner = device_private_page_owner;
 	gpusvm->mm_start = mm_start;
 	gpusvm->mm_range = mm_range;
 	gpusvm->notifier_size = notifier_size;
@@ -684,6 +681,7 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn,
  * @notifier: Pointer to the GPU SVM notifier structure
  * @start: Start address
  * @end: End address
+ * @dev_private_owner: The device private page owner
  *
  * Check if pages between start and end have been faulted in on the CPU. Use to
  * prevent migration of pages without CPU backing store.
@@ -692,14 +690,15 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn,
  */
 static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm,
 				   struct drm_gpusvm_notifier *notifier,
-				   unsigned long start, unsigned long end)
+				   unsigned long start, unsigned long end,
+				   void *dev_private_owner)
 {
 	struct hmm_range hmm_range = {
 		.default_flags = 0,
 		.notifier = &notifier->notifier,
 		.start = start,
 		.end = end,
-		.dev_private_owner = gpusvm->device_private_page_owner,
+		.dev_private_owner = dev_private_owner,
 	};
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
@@ -753,6 +752,7 @@ err_free:
  * @gpuva_start: Start address of GPUVA which mirrors CPU
  * @gpuva_end: End address of GPUVA which mirrors CPU
  * @check_pages_threshold: Check CPU pages for present threshold
+ * @dev_private_owner: The device private page owner
  *
  * This function determines the chunk size for the GPU SVM range based on the
  * fault address, GPU SVM chunk sizes, existing GPU SVM ranges, and the virtual
@@ -767,7 +767,8 @@ drm_gpusvm_range_chunk_size(struct drm_gpusvm *gpusvm,
 			    unsigned long fault_addr,
 			    unsigned long gpuva_start,
 			    unsigned long gpuva_end,
-			    unsigned long check_pages_threshold)
+			    unsigned long check_pages_threshold,
+			    void *dev_private_owner)
 {
 	unsigned long start, end;
 	int i = 0;
@@ -814,7 +815,7 @@ retry:
 		 * process-many-malloc' mallocs at least 64k at a time.
 		 */
 		if (end - start <= check_pages_threshold &&
-		    !drm_gpusvm_check_pages(gpusvm, notifier, start, end)) {
+		    !drm_gpusvm_check_pages(gpusvm, notifier, start, end, dev_private_owner)) {
 			++i;
 			goto retry;
 		}
@@ -957,7 +958,8 @@ drm_gpusvm_range_find_or_insert(struct drm_gpusvm *gpusvm,
 	chunk_size = drm_gpusvm_range_chunk_size(gpusvm, notifier, vas,
 						 fault_addr, gpuva_start,
 						 gpuva_end,
-						 ctx->check_pages_threshold);
+						 ctx->check_pages_threshold,
+						 ctx->device_private_page_owner);
 	if (chunk_size == LONG_MAX) {
 		err = -EINVAL;
 		goto err_notifier_remove;
@@ -1268,7 +1270,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 		.notifier = notifier,
 		.start = pages_start,
 		.end = pages_end,
-		.dev_private_owner = gpusvm->device_private_page_owner,
+		.dev_private_owner = ctx->device_private_page_owner,
 	};
 	void *zdd;
 	unsigned long timeout =
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 7f2f1f041f1d..7e2db71ff34e 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -67,11 +67,6 @@ void xe_svm_range_debug(struct xe_svm_range *range, const char *operation)
 	range_debug(range, operation);
 }
 
-static void *xe_svm_devm_owner(struct xe_device *xe)
-{
-	return xe;
-}
-
 static struct drm_gpusvm_range *
 xe_svm_range_alloc(struct drm_gpusvm *gpusvm)
 {
@@ -744,15 +739,14 @@ int xe_svm_init(struct xe_vm *vm)
 			  xe_svm_garbage_collector_work_func);
 
 		err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm,
-				      current->mm, xe_svm_devm_owner(vm->xe), 0,
-				      vm->size,
+				      current->mm, 0, vm->size,
 				      xe_modparam.svm_notifier_size * SZ_1M,
 				      &gpusvm_ops, fault_chunk_sizes,
 				      ARRAY_SIZE(fault_chunk_sizes));
 		drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock);
 	} else {
 		err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)",
-				      &vm->xe->drm, NULL, NULL, 0, 0, 0, NULL,
+				      &vm->xe->drm, NULL, 0, 0, 0, NULL,
 				      NULL, 0);
 	}
 
@@ -1017,6 +1011,7 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 		.devmem_only = need_vram && devmem_possible,
 		.timeslice_ms = need_vram && devmem_possible ?
 			vm->xe->atomic_svm_timeslice_ms : 0,
+		.device_private_page_owner = xe_svm_devm_owner(vm->xe),
 	};
 	struct xe_validation_ctx vctx;
 	struct drm_exec exec;
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index cef6ee7d6fe3..0955d2ac8d74 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -6,6 +6,20 @@
 #ifndef _XE_SVM_H_
 #define _XE_SVM_H_
 
+struct xe_device;
+
+/**
+ * xe_svm_devm_owner() - Return the owner of device private memory
+ * @xe: The xe device.
+ *
+ * Return: The owner of this device's device private memory to use in
+ * hmm_range_fault()-
+ */
+static inline void *xe_svm_devm_owner(struct xe_device *xe)
+{
+	return xe;
+}
+
 #if IS_ENABLED(CONFIG_DRM_XE_GPUSVM)
 
 #include <drm/drm_pagemap.h>
diff --git a/drivers/gpu/drm/xe/xe_userptr.c b/drivers/gpu/drm/xe/xe_userptr.c
index 91d09af71ced..f16e92cd8090 100644
--- a/drivers/gpu/drm/xe/xe_userptr.c
+++ b/drivers/gpu/drm/xe/xe_userptr.c
@@ -54,6 +54,7 @@ int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)
 	struct xe_device *xe = vm->xe;
 	struct drm_gpusvm_ctx ctx = {
 		.read_only = xe_vma_read_only(vma),
+		.device_private_page_owner = NULL,
 	};
 
 	lockdep_assert_held(&vm->lock);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 0cacab20ff85..027e6ce648c5 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2881,6 +2881,7 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op)
 	ctx.read_only = xe_vma_read_only(vma);
 	ctx.devmem_possible = devmem_possible;
 	ctx.check_pages_threshold = devmem_possible ? SZ_64K : 0;
+	ctx.device_private_page_owner = xe_svm_devm_owner(vm->xe);
 
 	/* TODO: Threading the migration */
 	xa_for_each(&op->prefetch_range.range, i, svm_range) {
diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index 5434048a2ca4..b92faa9a26b2 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -179,7 +179,6 @@ struct drm_gpusvm_range {
  * @name: Name of the GPU SVM
  * @drm: Pointer to the DRM device structure
  * @mm: Pointer to the mm_struct for the address space
- * @device_private_page_owner: Device private pages owner
  * @mm_start: Start address of GPU SVM
  * @mm_range: Range of the GPU SVM
  * @notifier_size: Size of individual notifiers
@@ -204,7 +203,6 @@ struct drm_gpusvm {
 	const char *name;
 	struct drm_device *drm;
 	struct mm_struct *mm;
-	void *device_private_page_owner;
 	unsigned long mm_start;
 	unsigned long mm_range;
 	unsigned long notifier_size;
@@ -226,6 +224,8 @@ struct drm_gpusvm {
 /**
  * struct drm_gpusvm_ctx - DRM GPU SVM context
  *
+ * @device_private_page_owner: The device-private page owner to use for
+ * this operation
  * @check_pages_threshold: Check CPU pages for present if chunk is less than or
  *                         equal to threshold. If not present, reduce chunk
  *                         size.
@@ -239,6 +239,7 @@ struct drm_gpusvm {
  * Context that is DRM GPUSVM is operating in (i.e. user arguments).
  */
 struct drm_gpusvm_ctx {
+	void *device_private_page_owner;
 	unsigned long check_pages_threshold;
 	unsigned long timeslice_ms;
 	unsigned int in_notifier :1;
@@ -249,7 +250,7 @@ struct drm_gpusvm_ctx {
 
 int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
 		    const char *name, struct drm_device *drm,
-		    struct mm_struct *mm, void *device_private_page_owner,
+		    struct mm_struct *mm,
 		    unsigned long mm_start, unsigned long mm_range,
 		    unsigned long notifier_size,
 		    const struct drm_gpusvm_ops *ops,

From 6982a462cb64c5f0a38cd8738398961ddfb883cf Mon Sep 17 00:00:00 2001
From: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Date: Thu, 2 Oct 2025 06:26:48 +0530
Subject: [PATCH 111/352] drm/xe/xe_late_bind_fw: Initialize uval variable in
 xe_late_bind_fw_num_fans()

Initialize the uval variable to 0 in xe_late_bind_fw_num_fans() to fix
a potential use of uninitialized variable warning and ensure predictable
behavior.

The variable is passed by reference to xe_pcode_read() which should
populate it on success, but initializing it to 0 provides a safe
default value and follows kernel coding best practices.

v2:
- uval = 0 which serves as both a safe default and the fallback
  value when the pcode read operation fails.

v3:
- Handle MMIO failure (Rodrigo)
- The function should probably return the error and make the uval as
  pointer-argument, like the pcode_read.
- Change the caller of this function to propagate the error
  upwards if mmio failed.

Fixes: 45832bf9c10f3 ("drm/xe/xe_late_bind_fw: Initialize late binding firmware")
Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Link: https://lore.kernel.org/r/20251002005648.3185636-1-mallesh.koujalagi@intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 07abc16c14693df703763c45e9fc0abfefc927d5)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_late_bind_fw.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw.c b/drivers/gpu/drm/xe/xe_late_bind_fw.c
index 8f5082e689dc..768442ca7da6 100644
--- a/drivers/gpu/drm/xe/xe_late_bind_fw.c
+++ b/drivers/gpu/drm/xe/xe_late_bind_fw.c
@@ -184,17 +184,13 @@ static const char *xe_late_bind_parse_status(uint32_t status)
 	}
 }
 
-static int xe_late_bind_fw_num_fans(struct xe_late_bind *late_bind)
+static int xe_late_bind_fw_num_fans(struct xe_late_bind *late_bind, u32 *num_fans)
 {
 	struct xe_device *xe = late_bind_to_xe(late_bind);
 	struct xe_tile *root_tile = xe_device_get_root_tile(xe);
-	u32 uval;
 
-	if (!xe_pcode_read(root_tile,
-			   PCODE_MBOX(FAN_SPEED_CONTROL, FSC_READ_NUM_FANS, 0), &uval, NULL))
-		return uval;
-	else
-		return 0;
+	return xe_pcode_read(root_tile,
+			     PCODE_MBOX(FAN_SPEED_CONTROL, FSC_READ_NUM_FANS, 0), num_fans, NULL);
 }
 
 void xe_late_bind_wait_for_worker_completion(struct xe_late_bind *late_bind)
@@ -314,7 +310,11 @@ static int __xe_late_bind_fw_init(struct xe_late_bind *late_bind, u32 fw_id)
 	lb_fw->flags &= ~INTEL_LB_FLAG_IS_PERSISTENT;
 
 	if (lb_fw->type == INTEL_LB_TYPE_FAN_CONTROL) {
-		num_fans = xe_late_bind_fw_num_fans(late_bind);
+		ret = xe_late_bind_fw_num_fans(late_bind, &num_fans);
+		if (ret) {
+			drm_dbg(&xe->drm, "Failed to read number of fans: %d\n", ret);
+			return 0; /* Not a fatal error, continue without fan control */
+		}
 		drm_dbg(&xe->drm, "Number of Fans: %d\n", num_fans);
 		if (!num_fans)
 			return 0;

From 18dbff48a1ea58100f9fa6886cfef286a96a5fb0 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 2 Oct 2025 10:47:17 +0300
Subject: [PATCH 112/352] ASoC: SOF: sof-audio: add dev_dbg_ratelimited wrapper

Add dev_dbg_ratelimited() wrapper for snd_sof_pcm specific debug prints
that needs rate limited.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20251002074719.2084-4-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/sof-audio.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index db6973c8eac3..a8b93a2eec9c 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -629,6 +629,11 @@ void snd_sof_pcm_init_elapsed_work(struct work_struct *work);
 		(__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir,		\
 		##__VA_ARGS__)
 
+#define spcm_dbg_ratelimited(__spcm, __dir, __fmt, ...)				\
+	dev_dbg_ratelimited((__spcm)->scomp->dev, "pcm%u (%s), dir %d: " __fmt,	\
+		(__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir,		\
+		##__VA_ARGS__)
+
 #define spcm_err(__spcm, __dir, __fmt, ...)					\
 	dev_err((__spcm)->scomp->dev, "%s: pcm%u (%s), dir %d: " __fmt,		\
 		__func__, (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir,	\

From a4b8152c09a832b089864e5e209a479bb0fb5cc9 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Thu, 2 Oct 2025 10:47:18 +0300
Subject: [PATCH 113/352] ASoC: SOF: ipc4-pcm: do not report invalid delay
 values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a sanity check for the calculated delay value before reporting it to
the application. If the value is clearly invalid, emit a rate limited
warning to kernel log and return a zero delay. This can occur e.g if the
host or link DMA hits a buffer over/underrun condition.

Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20251002074719.2084-5-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-pcm.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 9d29d2e56c00..c700972d32ed 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -59,6 +59,8 @@ struct sof_ipc4_pcm_stream_priv {
  */
 #define DELAY_BOUNDARY		U32_MAX
 
+#define DELAY_MAX		(DELAY_BOUNDARY >> 1)
+
 static inline struct sof_ipc4_timestamp_info *
 sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps)
 {
@@ -1266,6 +1268,13 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
 	else
 		time_info->delay = head_cnt - tail_cnt;
 
+	if (time_info->delay > DELAY_MAX) {
+		spcm_dbg_ratelimited(spcm, substream->stream,
+				     "inaccurate delay, host %llu dai_cnt %llu",
+				     host_cnt, dai_cnt);
+		time_info->delay = 0;
+	}
+
 	/*
 	 * Convert the host byte counter to PCM pointer which wraps in buffer
 	 * and it is in frames

From aaab61de1f1e44a2ab527e935474e2e03a0f6b08 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 2 Oct 2025 10:47:19 +0300
Subject: [PATCH 114/352] ASoC: SOF: Intel: Read the LLP via the associated
 Link DMA channel

It is allowed to mix Link and Host DMA channels in a way that their index
is different. In this case we would read the LLP from a channel which is
not used or used for other operation.

Such case can be reproduced on cAVS2.5 or ACE1 platforms with soundwire
configuration:
playback to SDW would take Host channel 0 (stream_tag 1) and no Link DMA
used
Second playback to HDMI (HDA) would use Host channel 1 (stream_tag 2) and
Link channel 0 (stream_tag 1).

In this case reading the LLP from channel 2 is incorrect as that is not the
Link channel used for the HDMI playback.

To correct this, we should look up the BE and get the channel used on the
Link side.

Fixes: 67b182bea08a ("ASoC: SOF: Intel: hda: Implement get_stream_position (Linear Link Position)")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://patch.msgid.link/20251002074719.2084-6-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-stream.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c
index a34f472ef175..9c3b3a9aaf83 100644
--- a/sound/soc/sof/intel/hda-stream.c
+++ b/sound/soc/sof/intel/hda-stream.c
@@ -1129,10 +1129,35 @@ u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
 			   struct snd_soc_component *component,
 			   struct snd_pcm_substream *substream)
 {
-	struct hdac_stream *hstream = substream->runtime->private_data;
-	struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream);
+	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+	struct snd_soc_pcm_runtime *be_rtd = NULL;
+	struct hdac_ext_stream *hext_stream;
+	struct snd_soc_dai *cpu_dai;
+	struct snd_soc_dpcm *dpcm;
 	u32 llp_l, llp_u;
 
+	/*
+	 * The LLP needs to be read from the Link DMA used for this FE as it is
+	 * allowed to use any combination of Link and Host channels
+	 */
+	for_each_dpcm_be(rtd, substream->stream, dpcm) {
+		if (dpcm->fe != rtd)
+			continue;
+
+		be_rtd = dpcm->be;
+	}
+
+	if (!be_rtd)
+		return 0;
+
+	cpu_dai = snd_soc_rtd_to_cpu(be_rtd, 0);
+	if (!cpu_dai)
+		return 0;
+
+	hext_stream = snd_soc_dai_get_dma_data(cpu_dai, substream);
+	if (!hext_stream)
+		return 0;
+
 	/*
 	 * The pplc_addr have been calculated during probe in
 	 * hda_dsp_stream_init():

From 0ca286477b5e2dc9a00ccd3ab1eaceb9fda4be06 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 3 Oct 2025 07:22:02 -0600
Subject: [PATCH 115/352] io_uring: update liburing git URL

Change the liburing git URL to point to the git.kernel.org servers,
rather than my private git.kernel.dk server. Due to continued AI
scraping of cgit etc, it's becoming quite the chore to maintain a
private git server.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 49ebdeb5b2d9..820ef0527666 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -29,7 +29,7 @@
  *
  * Also see the examples in the liburing library:
  *
- *	git://git.kernel.dk/liburing
+ *	git://git.kernel.org/pub/scm/linux/kernel/git/axboe/liburing.git
  *
  * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
  * from data shared between the kernel and application. This is done both

From 0892507f4a0b76eb897afc2bacca85e172512379 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 3 Oct 2025 12:29:09 +0300
Subject: [PATCH 116/352] mfd: ls2kbmc: Fix an IS_ERR() vs NULL check in
 probe()

The devm_kzalloc() function returns NULL on error so check for that
instead of error pointers.

Fixes: d952bba3fbb5 ("mfd: ls2kbmc: Add Loongson-2K BMC reset function support")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Message-ID: <df80c6d61229eb8f877c3694525c0f97e64a43e8.1759478975.git.dan.carpenter@linaro.org>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/mfd/ls2k-bmc-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mfd/ls2k-bmc-core.c b/drivers/mfd/ls2k-bmc-core.c
index e162b3c7c9f8..5f38514fa89e 100644
--- a/drivers/mfd/ls2k-bmc-core.c
+++ b/drivers/mfd/ls2k-bmc-core.c
@@ -469,7 +469,7 @@ static int ls2k_bmc_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return ret;
 
 	ddata = devm_kzalloc(&dev->dev, sizeof(*ddata), GFP_KERNEL);
-	if (IS_ERR(ddata)) {
+	if (!ddata) {
 		ret = -ENOMEM;
 		goto disable_pci;
 	}

From 4af66c2bcab06e6e515b23139122e745d7619680 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 3 Oct 2025 12:29:18 +0300
Subject: [PATCH 117/352] mfd: ls2kbmc: check for devm_mfd_add_devices()
 failure

Call pci_disable_device() if devm_mfd_add_devices() fails.

Fixes: 0d64f6d1ffe9 ("mfd: ls2kbmc: Introduce Loongson-2K BMC core driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Message-ID: <e3e7cf2cfded48c9fca8bc981c54bbcb7edb9580.1759478975.git.dan.carpenter@linaro.org>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/mfd/ls2k-bmc-core.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/ls2k-bmc-core.c b/drivers/mfd/ls2k-bmc-core.c
index 5f38514fa89e..69387dad6661 100644
--- a/drivers/mfd/ls2k-bmc-core.c
+++ b/drivers/mfd/ls2k-bmc-core.c
@@ -495,9 +495,13 @@ static int ls2k_bmc_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto disable_pci;
 	}
 
-	return devm_mfd_add_devices(&dev->dev, PLATFORM_DEVID_AUTO,
-				    ls2k_bmc_cells, ARRAY_SIZE(ls2k_bmc_cells),
-				    &dev->resource[0], 0, NULL);
+	ret = devm_mfd_add_devices(&dev->dev, PLATFORM_DEVID_AUTO,
+				   ls2k_bmc_cells, ARRAY_SIZE(ls2k_bmc_cells),
+				   &dev->resource[0], 0, NULL);
+	if (ret)
+		goto disable_pci;
+
+	return 0;
 
 disable_pci:
 	pci_disable_device(dev);

From 2d1684a077d62fddfac074052c162ec6573a34e1 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 19 Sep 2025 13:20:53 +0100
Subject: [PATCH 118/352] drm/xe/uapi: loosen used tracking restriction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently this is hidden behind perfmon_capable() since this is
technically an info leak, given that this is a system wide metric.
However the granularity reported here is always PAGE_SIZE aligned, which
matches what the core kernel is already willing to expose to userspace
if querying how many free RAM pages there are on the system, and that
doesn't need any special privileges. In addition other drm drivers seem
happy to expose this.

The motivation here if with oneAPI where they want to use the system
wide 'used' reporting here, so not the per-client fdinfo stats. This has
also come up with some perf overlay applications wanting this
information.

Fixes: 1105ac15d2a1 ("drm/xe/uapi: restrict system wide accounting")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Joshua Santosh <joshua.santosh.ranjan@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250919122052.420979-2-matthew.auld@intel.com
(cherry picked from commit 4d0b035fd6dae8ee48e9c928b10f14877e595356)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_query.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index e1b603aba61b..2e9ff33ed2fe 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -276,8 +276,7 @@ static int query_mem_regions(struct xe_device *xe,
 	mem_regions->mem_regions[0].instance = 0;
 	mem_regions->mem_regions[0].min_page_size = PAGE_SIZE;
 	mem_regions->mem_regions[0].total_size = man->size << PAGE_SHIFT;
-	if (perfmon_capable())
-		mem_regions->mem_regions[0].used = ttm_resource_manager_usage(man);
+	mem_regions->mem_regions[0].used = ttm_resource_manager_usage(man);
 	mem_regions->num_mem_regions = 1;
 
 	for (i = XE_PL_VRAM0; i <= XE_PL_VRAM1; ++i) {
@@ -293,13 +292,11 @@ static int query_mem_regions(struct xe_device *xe,
 			mem_regions->mem_regions[mem_regions->num_mem_regions].total_size =
 				man->size;
 
-			if (perfmon_capable()) {
-				xe_ttm_vram_get_used(man,
-					&mem_regions->mem_regions
-					[mem_regions->num_mem_regions].used,
-					&mem_regions->mem_regions
-					[mem_regions->num_mem_regions].cpu_visible_used);
-			}
+			xe_ttm_vram_get_used(man,
+					     &mem_regions->mem_regions
+					     [mem_regions->num_mem_regions].used,
+					     &mem_regions->mem_regions
+					     [mem_regions->num_mem_regions].cpu_visible_used);
 
 			mem_regions->mem_regions[mem_regions->num_mem_regions].cpu_visible_size =
 				xe_ttm_vram_get_cpu_visible_size(man);

From 08fdfd260e641da203f80aff8d3ed19c5ecceb7d Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 25 Sep 2025 02:31:46 +0000
Subject: [PATCH 119/352] drm/xe/hw_engine_group: Fix double write lock release
 in error path

In xe_hw_engine_group_get_mode(), a write lock is acquired before
calling switch_mode(), which in turn invokes
xe_hw_engine_group_suspend_faulting_lr_jobs().

On failure inside xe_hw_engine_group_suspend_faulting_lr_jobs(),
the write lock is released there, and then again in
xe_hw_engine_group_get_mode(), leading to a double release.

Fix this by keeping both acquire and release operation in
xe_hw_engine_group_get_mode().

Fixes: 770bd1d34113 ("drm/xe/hw_engine_group: Ensure safe transition between execution modes")
Cc: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://lore.kernel.org/r/20250925023145.1203004-2-shuicheng.lin@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 662d98b8b373007fa1b08ba93fee11f6fd3e387c)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_hw_engine_group.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c
index 58bee3ffe881..fa4db5f23342 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c
@@ -213,17 +213,13 @@ static int xe_hw_engine_group_suspend_faulting_lr_jobs(struct xe_hw_engine_group
 
 		err = q->ops->suspend_wait(q);
 		if (err)
-			goto err_suspend;
+			return err;
 	}
 
 	if (need_resume)
 		xe_hw_engine_group_resume_faulting_lr_jobs(group);
 
 	return 0;
-
-err_suspend:
-	up_write(&group->mode_sem);
-	return err;
 }
 
 /**

From 1af59cd5cc2b65d7fc95165f056695ce3f171133 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Thu, 18 Sep 2025 16:02:00 +0530
Subject: [PATCH 120/352] drm/xe/i2c: Don't rely on d3cold.allowed flag in
 system PM path

In S3 and above sleep states, the device can loose power regardless of
d3cold.allowed flag. Bring up I2C controller explicitly in system PM
path to ensure its normal operation after losing power.

v2: Cover S3 and above states (Rodrigo)

Fixes: 0ea07b69517a ("drm/xe/pm: Wire up suspend/resume for I2C controller")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250918103200.2952576-1-raag.jadav@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit e4863f1159befcd70df24fcb5458afaf2feab043)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index d6625c71115b..2c5a44377994 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -201,7 +201,7 @@ int xe_pm_resume(struct xe_device *xe)
 	if (err)
 		goto err;
 
-	xe_i2c_pm_resume(xe, xe->d3cold.allowed);
+	xe_i2c_pm_resume(xe, true);
 
 	xe_irq_resume(xe);
 

From 3637d34b35b287ab830e66048841ace404382b67 Mon Sep 17 00:00:00 2001
From: Albin Babu Varghese <albinbabuvarghese20@gmail.com>
Date: Fri, 3 Oct 2025 03:32:09 -0400
Subject: [PATCH 121/352] fbdev: Add bounds checking in bit_putcs to fix
 vmalloc-out-of-bounds

Add bounds checking to prevent writes past framebuffer boundaries when
rendering text near screen edges. Return early if the Y position is off-screen
and clip image height to screen boundary. Break from the rendering loop if the
X position is off-screen. When clipping image width to fit the screen, update
the character count to match the clipped width to prevent buffer size
mismatches.

Without the character count update, bit_putcs_aligned and bit_putcs_unaligned
receive mismatched parameters where the buffer is allocated for the clipped
width but cnt reflects the original larger count, causing out-of-bounds writes.

Reported-by: syzbot+48b0652a95834717f190@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=48b0652a95834717f190
Suggested-by: Helge Deller <deller@gmx.de>
Tested-by: syzbot+48b0652a95834717f190@syzkaller.appspotmail.com
Signed-off-by: Albin Babu Varghese <albinbabuvarghese20@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/core/bitblit.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index f9475c14f733..a9ec7f488522 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -160,6 +160,11 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info,
 	image.height = vc->vc_font.height;
 	image.depth = 1;
 
+	if (image.dy >= info->var.yres)
+		return;
+
+	image.height = min(image.height, info->var.yres - image.dy);
+
 	if (attribute) {
 		buf = kmalloc(cellsize, GFP_ATOMIC);
 		if (!buf)
@@ -173,6 +178,18 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info,
 			cnt = count;
 
 		image.width = vc->vc_font.width * cnt;
+
+		if (image.dx >= info->var.xres)
+			break;
+
+		if (image.dx + image.width > info->var.xres) {
+			image.width = info->var.xres - image.dx;
+			cnt = image.width / vc->vc_font.width;
+			if (cnt == 0)
+				break;
+			image.width = cnt * vc->vc_font.width;
+		}
+
 		pitch = DIV_ROUND_UP(image.width, 8) + scan_align;
 		pitch &= ~scan_align;
 		size = pitch * image.height + buf_align;

From d3c2191d493a9a017ea816f3b38dfbcadb6cccb5 Mon Sep 17 00:00:00 2001
From: Harshal Gohel <hg@simonwunderlich.de>
Date: Sat, 27 Sep 2025 11:52:17 +0200
Subject: [PATCH 122/352] i2c: rtl9300: Implement I2C block read and write

It was noticed that the original implementation of SMBus Block Write in the
driver was actually an I2C Block Write. Both differ only in the Count byte
before the actual data:

  S Addr Wr [A] Comm [A] Count [A] Data [A] Data [A] ... [A] Data [A] P

The I2C Block Write is just skipping this Count byte and starts directly
with the data:

  S Addr Wr [A] Comm [A] Data [A] Data [A] ... [A] Data [A] P

The I2C controller of RTL93xx doesn't handle this Count byte special and it
is simply another one of (16 possible) data bytes. Adding support for the
I2C Block Write therefore only requires skipping the count byte (0) in
data->block.

It is similar for reads. The SMBUS Block read is having a Count byte before
the data:

  S Addr Wr [A] Comm [A]
            Sr Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P

And the I2C Block Read is directly starting with the actual data:

  S Addr Wr [A] Comm [A]
            Sr Addr Rd [A] [Data] A [Data] A ... A [Data] NA P

The I2C controller is also not handling this byte in a special way. It
simply provides every byte after the Rd marker + Ack as part of the 16 byte
receive buffer (registers). The content of this buffer just has to be
copied to the right position in the receive data->block.

Signed-off-by: Harshal Gohel <hg@simonwunderlich.de>
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>
Reviewed-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Tested-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/all/20250927-i2c-rtl9300-multi-byte-v7-2-c0fd0e78b818@narfation.org
---
 drivers/i2c/busses/i2c-rtl9300.c | 38 ++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index af991b28e4f8..9e6232075137 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -186,22 +186,32 @@ static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write,
 		return -EIO;
 
 	if (read_write == I2C_SMBUS_READ) {
-		if (size == I2C_SMBUS_BYTE || size == I2C_SMBUS_BYTE_DATA) {
+		switch (size) {
+		case I2C_SMBUS_BYTE:
+		case I2C_SMBUS_BYTE_DATA:
 			ret = regmap_read(i2c->regmap,
 					  i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val);
 			if (ret)
 				return ret;
 			data->byte = val & 0xff;
-		} else if (size == I2C_SMBUS_WORD_DATA) {
+			break;
+		case I2C_SMBUS_WORD_DATA:
 			ret = regmap_read(i2c->regmap,
 					  i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val);
 			if (ret)
 				return ret;
 			data->word = val & 0xffff;
-		} else {
+			break;
+		case I2C_SMBUS_I2C_BLOCK_DATA:
+			ret = rtl9300_i2c_read(i2c, &data->block[1], len);
+			if (ret)
+				return ret;
+			break;
+		default:
 			ret = rtl9300_i2c_read(i2c, &data->block[0], len);
 			if (ret)
 				return ret;
+			break;
 		}
 	}
 
@@ -290,6 +300,25 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 		len = data->block[0] + 1;
 		break;
 
+	case I2C_SMBUS_I2C_BLOCK_DATA:
+		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;
+		if (read_write == I2C_SMBUS_WRITE) {
+			ret = rtl9300_i2c_write(i2c, &data->block[1], data->block[0]);
+			if (ret)
+				goto out_unlock;
+		}
+		len = data->block[0];
+		break;
+
 	default:
 		dev_err(&adap->dev, "Unsupported transaction %d\n", size);
 		ret = -EOPNOTSUPP;
@@ -307,7 +336,8 @@ out_unlock:
 static u32 rtl9300_i2c_func(struct i2c_adapter *a)
 {
 	return I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_BYTE_DATA |
-	       I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_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 85f1c01ce2f98a4925d2610d9d3f4c2749eb9331 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:23 +0000
Subject: [PATCH 123/352] i2c: rtl9300: use regmap fields and API for registers

Adapt the RTL9300 I2C controller driver to use more of the regmap
API, especially make use of reg_field and regmap_field instead of macros
to represent registers. Most register operations are performed through
regmap_field_* API then.

Handle SCL selection using separate chip-specific functions since this
is already known to differ between the Realtek SoC families in such a
way that this cannot be properly handled using just a different
reg_field.

This makes it easier to add support for newer generations or to handle
differences between specific revisions within a series. Just by
defining a separate driver data structure with the corresponding
register field definitions and linking it to a new compatible.

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/20250927101931.71575-2-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 194 ++++++++++++++++++++-----------
 1 file changed, 125 insertions(+), 69 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 9e6232075137..8483bab72146 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -23,97 +23,117 @@ struct rtl9300_i2c_chan {
 	u8 sda_pin;
 };
 
+enum rtl9300_i2c_reg_scope {
+	REG_SCOPE_GLOBAL,
+	REG_SCOPE_MASTER,
+};
+
+struct rtl9300_i2c_reg_field {
+	struct reg_field field;
+	enum rtl9300_i2c_reg_scope scope;
+};
+
+enum rtl9300_i2c_reg_fields {
+	F_DATA_WIDTH = 0,
+	F_DEV_ADDR,
+	F_I2C_FAIL,
+	F_I2C_TRIG,
+	F_MEM_ADDR,
+	F_MEM_ADDR_WIDTH,
+	F_RD_MODE,
+	F_RWOP,
+	F_SCL_FREQ,
+	F_SCL_SEL,
+	F_SDA_OUT_SEL,
+	F_SDA_SEL,
+
+	/* keep last */
+	F_NUM_FIELDS
+};
+
+struct rtl9300_i2c_drv_data {
+	struct rtl9300_i2c_reg_field field_desc[F_NUM_FIELDS];
+	int (*select_scl)(struct rtl9300_i2c *i2c, u8 scl);
+	u32 data_reg;
+	u8 max_nchan;
+};
+
 #define RTL9300_I2C_MUX_NCHAN	8
 
 struct rtl9300_i2c {
 	struct regmap *regmap;
 	struct device *dev;
 	struct rtl9300_i2c_chan chans[RTL9300_I2C_MUX_NCHAN];
+	struct regmap_field *fields[F_NUM_FIELDS];
 	u32 reg_base;
+	u32 data_reg;
 	u8 sda_pin;
 	struct mutex lock;
 };
 
 #define RTL9300_I2C_MST_CTRL1				0x0
-#define  RTL9300_I2C_MST_CTRL1_MEM_ADDR_OFS		8
-#define  RTL9300_I2C_MST_CTRL1_MEM_ADDR_MASK		GENMASK(31, 8)
-#define  RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_OFS		4
-#define  RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_MASK		GENMASK(6, 4)
-#define  RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL		BIT(3)
-#define  RTL9300_I2C_MST_CTRL1_RWOP			BIT(2)
-#define  RTL9300_I2C_MST_CTRL1_I2C_FAIL			BIT(1)
-#define  RTL9300_I2C_MST_CTRL1_I2C_TRIG			BIT(0)
 #define RTL9300_I2C_MST_CTRL2				0x4
-#define  RTL9300_I2C_MST_CTRL2_RD_MODE			BIT(15)
-#define  RTL9300_I2C_MST_CTRL2_DEV_ADDR_OFS		8
-#define  RTL9300_I2C_MST_CTRL2_DEV_ADDR_MASK		GENMASK(14, 8)
-#define  RTL9300_I2C_MST_CTRL2_DATA_WIDTH_OFS		4
-#define  RTL9300_I2C_MST_CTRL2_DATA_WIDTH_MASK		GENMASK(7, 4)
-#define  RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_OFS	2
-#define  RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_MASK	GENMASK(3, 2)
-#define  RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS		0
-#define  RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK		GENMASK(1, 0)
 #define RTL9300_I2C_MST_DATA_WORD0			0x8
 #define RTL9300_I2C_MST_DATA_WORD1			0xc
 #define RTL9300_I2C_MST_DATA_WORD2			0x10
 #define RTL9300_I2C_MST_DATA_WORD3			0x14
-
 #define RTL9300_I2C_MST_GLB_CTRL			0x384
 
 static int rtl9300_i2c_reg_addr_set(struct rtl9300_i2c *i2c, u32 reg, u16 len)
 {
-	u32 val, mask;
 	int ret;
 
-	val = len << RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_OFS;
-	mask = RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_MASK;
-
-	ret = regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL2, mask, val);
+	ret = regmap_field_write(i2c->fields[F_MEM_ADDR_WIDTH], len);
 	if (ret)
 		return ret;
 
-	val = reg << RTL9300_I2C_MST_CTRL1_MEM_ADDR_OFS;
-	mask = RTL9300_I2C_MST_CTRL1_MEM_ADDR_MASK;
+	return regmap_field_write(i2c->fields[F_MEM_ADDR], reg);
+}
 
-	return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val);
+static int rtl9300_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl)
+{
+	return regmap_field_write(i2c->fields[F_SCL_SEL], 1);
 }
 
 static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, u8 sda_pin)
 {
+	struct rtl9300_i2c_drv_data *drv_data;
 	int ret;
-	u32 val, mask;
 
-	ret = regmap_update_bits(i2c->regmap, RTL9300_I2C_MST_GLB_CTRL, BIT(sda_pin), BIT(sda_pin));
+	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
+
+	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(sda_pin), BIT(sda_pin));
 	if (ret)
 		return ret;
 
-	val = (sda_pin << RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_OFS) |
-		RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL;
-	mask = RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_MASK | RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL;
+	ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], sda_pin);
+	if (ret)
+		return ret;
 
-	return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val);
+	return drv_data->select_scl(i2c, 0);
 }
 
 static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan,
 				   u16 addr, u16 len)
 {
-	u32 val, mask;
+	int ret;
 
 	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;
+	ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq);
+	if (ret)
+		return ret;
 
-	val |= addr << RTL9300_I2C_MST_CTRL2_DEV_ADDR_OFS;
-	mask |= RTL9300_I2C_MST_CTRL2_DEV_ADDR_MASK;
+	ret = regmap_field_write(i2c->fields[F_DEV_ADDR], addr);
+	if (ret)
+		return ret;
 
-	val |= ((len - 1) & 0xf) << RTL9300_I2C_MST_CTRL2_DATA_WIDTH_OFS;
-	mask |= RTL9300_I2C_MST_CTRL2_DATA_WIDTH_MASK;
+	ret = regmap_field_write(i2c->fields[F_DATA_WIDTH], (len - 1) & 0xf);
+	if (ret)
+		return ret;
 
-	mask |= RTL9300_I2C_MST_CTRL2_RD_MODE;
-
-	return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL2, mask, val);
+	return regmap_field_write(i2c->fields[F_RD_MODE], 0);
 }
 
 static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len)
@@ -124,8 +144,7 @@ static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len)
 	if (len > 16)
 		return -EIO;
 
-	ret = regmap_bulk_read(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0,
-			       vals, ARRAY_SIZE(vals));
+	ret = regmap_bulk_read(i2c->regmap, i2c->data_reg, vals, ARRAY_SIZE(vals));
 	if (ret)
 		return ret;
 
@@ -152,52 +171,49 @@ static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len)
 		vals[reg] |= buf[i] << shift;
 	}
 
-	return regmap_bulk_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0,
-				vals, ARRAY_SIZE(vals));
+	return regmap_bulk_write(i2c->regmap, i2c->data_reg, vals, ARRAY_SIZE(vals));
 }
 
 static int rtl9300_i2c_writel(struct rtl9300_i2c *i2c, u32 data)
 {
-	return regmap_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, data);
+	return regmap_write(i2c->regmap, i2c->data_reg, data);
 }
 
 static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write,
 				    int size, union i2c_smbus_data *data, int len)
 {
-	u32 val, mask;
+	u32 val;
 	int ret;
 
-	val = read_write == I2C_SMBUS_WRITE ? RTL9300_I2C_MST_CTRL1_RWOP : 0;
-	mask = RTL9300_I2C_MST_CTRL1_RWOP;
-
-	val |= RTL9300_I2C_MST_CTRL1_I2C_TRIG;
-	mask |= RTL9300_I2C_MST_CTRL1_I2C_TRIG;
-
-	ret = regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val);
+	ret = regmap_field_write(i2c->fields[F_RWOP], read_write == I2C_SMBUS_WRITE);
 	if (ret)
 		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, 100000);
+	ret = regmap_field_write(i2c->fields[F_I2C_TRIG], 1);
 	if (ret)
 		return ret;
 
-	if (val & RTL9300_I2C_MST_CTRL1_I2C_FAIL)
+	ret = regmap_field_read_poll_timeout(i2c->fields[F_I2C_TRIG], val, !val, 100, 100000);
+	if (ret)
+		return ret;
+
+	ret = regmap_field_read(i2c->fields[F_I2C_FAIL], &val);
+	if (ret)
+		return ret;
+	if (val)
 		return -EIO;
 
 	if (read_write == I2C_SMBUS_READ) {
 		switch (size) {
 		case I2C_SMBUS_BYTE:
 		case I2C_SMBUS_BYTE_DATA:
-			ret = regmap_read(i2c->regmap,
-					  i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val);
+			ret = regmap_read(i2c->regmap, i2c->data_reg, &val);
 			if (ret)
 				return ret;
 			data->byte = val & 0xff;
 			break;
 		case I2C_SMBUS_WORD_DATA:
-			ret = regmap_read(i2c->regmap,
-					  i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val);
+			ret = regmap_read(i2c->regmap, i2c->data_reg, &val);
 			if (ret)
 				return ret;
 			data->word = val & 0xffff;
@@ -355,9 +371,11 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct rtl9300_i2c *i2c;
+	struct fwnode_handle *child;
+	struct rtl9300_i2c_drv_data *drv_data;
+	struct reg_field fields[F_NUM_FIELDS];
 	u32 clock_freq, sda_pin;
 	int ret, i = 0;
-	struct fwnode_handle *child;
 
 	i2c = devm_kzalloc(dev, sizeof(*i2c), GFP_KERNEL);
 	if (!i2c)
@@ -376,9 +394,22 @@ 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)
+	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
+	if (device_get_child_node_count(dev) > drv_data->max_nchan)
 		return dev_err_probe(dev, -EINVAL, "Too many channels\n");
 
+	i2c->data_reg = i2c->reg_base + drv_data->data_reg;
+	for (i = 0; i < F_NUM_FIELDS; i++) {
+		fields[i] = drv_data->field_desc[i].field;
+		if (drv_data->field_desc[i].scope == REG_SCOPE_MASTER)
+			fields[i].reg += i2c->reg_base;
+	}
+	ret = devm_regmap_field_bulk_alloc(dev, i2c->regmap, i2c->fields,
+					   fields, F_NUM_FIELDS);
+	if (ret)
+		return ret;
+
+	i = 0;
 	device_for_each_child_node(dev, child) {
 		struct rtl9300_i2c_chan *chan = &i2c->chans[i];
 		struct i2c_adapter *adap = &chan->adap;
@@ -395,7 +426,6 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 		case I2C_MAX_STANDARD_MODE_FREQ:
 			chan->bus_freq = RTL9300_I2C_STD_FREQ;
 			break;
-
 		case I2C_MAX_FAST_MODE_FREQ:
 			chan->bus_freq = RTL9300_I2C_FAST_FREQ;
 			break;
@@ -427,11 +457,37 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 	return 0;
 }
 
+#define GLB_REG_FIELD(reg, msb, lsb)    \
+	{ .field = REG_FIELD(reg, msb, lsb), .scope = REG_SCOPE_GLOBAL }
+#define MST_REG_FIELD(reg, msb, lsb)    \
+	{ .field = REG_FIELD(reg, msb, lsb), .scope = REG_SCOPE_MASTER }
+
+static const struct rtl9300_i2c_drv_data rtl9300_i2c_drv_data = {
+	.field_desc = {
+		[F_MEM_ADDR]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 8, 31),
+		[F_SDA_OUT_SEL]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 4, 6),
+		[F_SCL_SEL]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 3, 3),
+		[F_RWOP]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 2, 2),
+		[F_I2C_FAIL]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 1, 1),
+		[F_I2C_TRIG]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 0, 0),
+		[F_RD_MODE]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 15, 15),
+		[F_DEV_ADDR]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 8, 14),
+		[F_DATA_WIDTH]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 4, 7),
+		[F_MEM_ADDR_WIDTH]	= MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 2, 3),
+		[F_SCL_FREQ]		= MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 0, 1),
+		[F_SDA_SEL]		= GLB_REG_FIELD(RTL9300_I2C_MST_GLB_CTRL, 0, 7),
+	},
+	.select_scl = rtl9300_i2c_select_scl,
+	.data_reg = RTL9300_I2C_MST_DATA_WORD0,
+	.max_nchan = RTL9300_I2C_MUX_NCHAN,
+};
+
+
 static const struct of_device_id i2c_rtl9300_dt_ids[] = {
-	{ .compatible = "realtek,rtl9301-i2c" },
-	{ .compatible = "realtek,rtl9302b-i2c" },
-	{ .compatible = "realtek,rtl9302c-i2c" },
-	{ .compatible = "realtek,rtl9303-i2c" },
+	{ .compatible = "realtek,rtl9301-i2c", .data = (void *) &rtl9300_i2c_drv_data },
+	{ .compatible = "realtek,rtl9302b-i2c", .data = (void *) &rtl9300_i2c_drv_data },
+	{ .compatible = "realtek,rtl9302c-i2c", .data = (void *) &rtl9300_i2c_drv_data },
+	{ .compatible = "realtek,rtl9303-i2c", .data = (void *) &rtl9300_i2c_drv_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, i2c_rtl9300_dt_ids);

From 0395a5e8fd07645df6743fd2a6883708196d9d75 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:24 +0000
Subject: [PATCH 124/352] dt-bindings: i2c: realtek,rtl9301-i2c: fix wording
 and typos

Fix wording of binding description to use plural because there is not
only a single RTL9300 SoC. RTL9300 describes a whole family of Realtek
SoCs.

Add missing word 'of' in description of reg property.

Change 'SDA pin' to 'SDA line number' because the property must contain
the SDA (channel) number ranging from 0-7 instead of a real pin number.

Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.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/20250927101931.71575-3-jelonek.jonas@gmail.com
---
 .../devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml        | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
index 69ac5db8b914..274e2ab8b612 100644
--- a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
@@ -10,7 +10,7 @@ maintainers:
   - Chris Packham <chris.packham@alliedtelesis.co.nz>
 
 description:
-  The RTL9300 SoC has two I2C controllers. Each of these has an SCL line (which
+  RTL9300 SoCs have two I2C controllers. Each of these has an SCL line (which
   if not-used for SCL can be a GPIO). There are 8 common SDA lines that can be
   assigned to either I2C controller.
 
@@ -27,7 +27,7 @@ properties:
 
   reg:
     items:
-      - description: Register offset and size this I2C controller.
+      - description: Register offset and size of this I2C controller.
 
   "#address-cells":
     const: 1
@@ -42,7 +42,7 @@ patternProperties:
 
     properties:
       reg:
-        description: The SDA pin associated with the I2C bus.
+        description: The SDA line number associated with the I2C bus.
         maxItems: 1
 
     required:

From c840492ad7487dcb58b0f5f249793e7350114076 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:25 +0000
Subject: [PATCH 125/352] i2c: rtl9300: rename internal sda_pin to sda_num

Rename the internally used 'sda_pin' to 'sda_num' to make it clear that
this is NOT the actual pin number of the GPIO pin but rather the logical
SDA channel number. Although the alternate function SDA_Y is sometimes
given with the GPIO number, this is not always the case. Thus, avoid any
confusion or misconfiguration by giving the variable the correct name.

This follows the description change in the devicetree bindings.

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/20250927101931.71575-4-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 8483bab72146..f9b5ac7670c2 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -20,7 +20,7 @@ struct rtl9300_i2c_chan {
 	struct i2c_adapter adap;
 	struct rtl9300_i2c *i2c;
 	enum rtl9300_bus_freq bus_freq;
-	u8 sda_pin;
+	u8 sda_num;
 };
 
 enum rtl9300_i2c_reg_scope {
@@ -67,7 +67,7 @@ struct rtl9300_i2c {
 	struct regmap_field *fields[F_NUM_FIELDS];
 	u32 reg_base;
 	u32 data_reg;
-	u8 sda_pin;
+	u8 sda_num;
 	struct mutex lock;
 };
 
@@ -102,11 +102,11 @@ static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, u8 sda_pin)
 
 	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
 
-	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(sda_pin), BIT(sda_pin));
+	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(sda_num), BIT(sda_num));
 	if (ret)
 		return ret;
 
-	ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], sda_pin);
+	ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], sda_num);
 	if (ret)
 		return ret;
 
@@ -243,11 +243,11 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 	int len = 0, ret;
 
 	mutex_lock(&i2c->lock);
-	if (chan->sda_pin != i2c->sda_pin) {
+	if (chan->sda_num != i2c->sda_num) {
 		ret = rtl9300_i2c_config_io(i2c, chan->sda_pin);
 		if (ret)
 			goto out_unlock;
-		i2c->sda_pin = chan->sda_pin;
+		i2c->sda_num = chan->sda_num;
 	}
 
 	switch (size) {
@@ -374,7 +374,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 	struct fwnode_handle *child;
 	struct rtl9300_i2c_drv_data *drv_data;
 	struct reg_field fields[F_NUM_FIELDS];
-	u32 clock_freq, sda_pin;
+	u32 clock_freq, sda_num;
 	int ret, i = 0;
 
 	i2c = devm_kzalloc(dev, sizeof(*i2c), GFP_KERNEL);
@@ -414,7 +414,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 		struct rtl9300_i2c_chan *chan = &i2c->chans[i];
 		struct i2c_adapter *adap = &chan->adap;
 
-		ret = fwnode_property_read_u32(child, "reg", &sda_pin);
+		ret = fwnode_property_read_u32(child, "reg", &sda_num);
 		if (ret)
 			return ret;
 
@@ -431,11 +431,11 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 			break;
 		default:
 			dev_warn(i2c->dev, "SDA%d clock-frequency %d not supported using default\n",
-				 sda_pin, clock_freq);
+				 sda_num, clock_freq);
 			break;
 		}
 
-		chan->sda_pin = sda_pin;
+		chan->sda_num = sda_num;
 		chan->i2c = i2c;
 		adap = &i2c->chans[i].adap;
 		adap->owner = THIS_MODULE;
@@ -445,14 +445,14 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 		adap->dev.parent = dev;
 		i2c_set_adapdata(adap, chan);
 		adap->dev.of_node = to_of_node(child);
-		snprintf(adap->name, sizeof(adap->name), "%s SDA%d\n", dev_name(dev), sda_pin);
+		snprintf(adap->name, sizeof(adap->name), "%s SDA%d\n", dev_name(dev), sda_num);
 		i++;
 
 		ret = devm_i2c_add_adapter(dev, adap);
 		if (ret)
 			return ret;
 	}
-	i2c->sda_pin = 0xff;
+	i2c->sda_num = 0xff;
 
 	return 0;
 }

From d1cef7afc3c79260d4d1a86f7a814de2a1bf3fe4 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:26 +0000
Subject: [PATCH 126/352] i2c: rtl9300: move setting SCL frequency to config_io

Move the register operation to set the SCL frequency to the
rtl9300_i2c_config_io function instead of the rtl9300_i2c_config_xfer
function. This rather belongs there next to selecting the current SDA
output line.

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/20250927101931.71575-5-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index f9b5ac7670c2..4177cfb77094 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -95,18 +95,23 @@ static int rtl9300_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl)
 	return regmap_field_write(i2c->fields[F_SCL_SEL], 1);
 }
 
-static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, u8 sda_pin)
+static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan)
 {
 	struct rtl9300_i2c_drv_data *drv_data;
 	int ret;
 
 	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
 
-	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(sda_num), BIT(sda_num));
+	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(chan->sda_num),
+				       BIT(chan->sda_num));
 	if (ret)
 		return ret;
 
-	ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], sda_num);
+	ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], chan->sda_num);
+	if (ret)
+		return ret;
+
+	ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq);
 	if (ret)
 		return ret;
 
@@ -121,10 +126,6 @@ static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c
 	if (len < 1 || len > 16)
 		return -EINVAL;
 
-	ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq);
-	if (ret)
-		return ret;
-
 	ret = regmap_field_write(i2c->fields[F_DEV_ADDR], addr);
 	if (ret)
 		return ret;
@@ -244,7 +245,7 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 
 	mutex_lock(&i2c->lock);
 	if (chan->sda_num != i2c->sda_num) {
-		ret = rtl9300_i2c_config_io(i2c, chan->sda_pin);
+		ret = rtl9300_i2c_config_io(i2c, chan);
 		if (ret)
 			goto out_unlock;
 		i2c->sda_num = chan->sda_num;

From d5b4fd6ed8ea3eb5dc072285a5e4c0ee32e829b2 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:27 +0000
Subject: [PATCH 127/352] i2c: rtl9300: do not set read mode on every transfer

Move the operation to set the read mode from config_xfer to probe.

The I2C controller of RTL9300 and RTL9310 support a legacy message mode
for READs with 'Read Address Data' instead of the standard format 'Write
Address ; Read Data'. There is no way to pass that via smbus_xfer, thus
there is no point in supported this in the driver and moreover no point
in setting this on every transaction. Setting this once in the probe
call is sufficient.

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/20250927101931.71575-6-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 4177cfb77094..9e3517b09b3d 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -130,11 +130,7 @@ static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c
 	if (ret)
 		return ret;
 
-	ret = regmap_field_write(i2c->fields[F_DATA_WIDTH], (len - 1) & 0xf);
-	if (ret)
-		return ret;
-
-	return regmap_field_write(i2c->fields[F_RD_MODE], 0);
+	return regmap_field_write(i2c->fields[F_DATA_WIDTH], (len - 1) & 0xf);
 }
 
 static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len)
@@ -455,6 +451,11 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 	}
 	i2c->sda_num = 0xff;
 
+	/* only use standard read format */
+	ret = regmap_field_write(i2c->fields[F_RD_MODE], 0);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 

From 059374aa0ab11a758a9e2219e90361911397b03d Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:28 +0000
Subject: [PATCH 128/352] i2c: rtl9300: separate xfer configuration and
 execution

So far, the rtl9300_i2c_smbus_xfer code is quite a mess with function
calls distributed over the whole function setting different values in
different cases. Calls to rtl9300_i2c_config_xfer and
rtl9300_i2c_reg_addr_set are used in every case-block with varying
values whose meaning is not instantly obvious. In some cases, there are
additional calls within these case-blocks doing more things.

This is in general a bad design and especially really bad for
readability and maintainability because it distributes changes or
issues to multiple locations due to the same function being called with
different hardcoded values in different places.

To have a good structure, setting different parameters based on the
desired operation should not be interleaved with applying these
parameters to the hardware registers. Or in different words, the
parameter site should be mixed with the call site.

Thus, separate configuration and execution of an SMBus xfer within
rtl9300_i2c_smbus_xfer to improve readability and maintainability. Add a
new 'struct rtl9300_i2c_xfer' to carry the required parameters for an
xfer which are configured based on the input parameters within a single
switch-case block, without having any function calls within this block.

The function calls to actually apply these values to the hardware
registers then appear below in a single place and just operate on the
passed instance of 'struct rtl9300_i2c_xfer'. These are
'rtl9300_i2c_prepare_xfer' which combines applying all parameters of the
xfer to the corresponding register, and 'rtl9300_i2c_do_xfer' which
actually executes the xfer and does post-processing if needed.

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/20250927101931.71575-7-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 242 +++++++++++++++----------------
 1 file changed, 118 insertions(+), 124 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 9e3517b09b3d..fb3ebbd46a18 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -8,6 +8,7 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
+#include <linux/unaligned.h>
 
 enum rtl9300_bus_freq {
 	RTL9300_I2C_STD_FREQ,
@@ -71,6 +72,22 @@ struct rtl9300_i2c {
 	struct mutex lock;
 };
 
+enum rtl9300_i2c_xfer_type {
+	RTL9300_I2C_XFER_BYTE,
+	RTL9300_I2C_XFER_WORD,
+	RTL9300_I2C_XFER_BLOCK,
+};
+
+struct rtl9300_i2c_xfer {
+	enum rtl9300_i2c_xfer_type type;
+	u16 dev_addr;
+	u8 reg_addr;
+	u8 reg_addr_len;
+	u8 *data;
+	u8 data_len;
+	bool write;
+};
+
 #define RTL9300_I2C_MST_CTRL1				0x0
 #define RTL9300_I2C_MST_CTRL2				0x4
 #define RTL9300_I2C_MST_DATA_WORD0			0x8
@@ -95,12 +112,22 @@ static int rtl9300_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl)
 	return regmap_field_write(i2c->fields[F_SCL_SEL], 1);
 }
 
-static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan)
+static int rtl9300_i2c_config_chan(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan)
 {
 	struct rtl9300_i2c_drv_data *drv_data;
 	int ret;
 
+	if (i2c->sda_num == chan->sda_num)
+		return 0;
+
+	ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq);
+	if (ret)
+		return ret;
+
 	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
+	ret = drv_data->select_scl(i2c, 0);
+	if (ret)
+		return ret;
 
 	ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(chan->sda_num),
 				       BIT(chan->sda_num));
@@ -111,29 +138,11 @@ static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, struct rtl9300_i2c_cha
 	if (ret)
 		return ret;
 
-	ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq);
-	if (ret)
-		return ret;
-
-	return drv_data->select_scl(i2c, 0);
+	i2c->sda_num = chan->sda_num;
+	return 0;
 }
 
-static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan,
-				   u16 addr, u16 len)
-{
-	int ret;
-
-	if (len < 1 || len > 16)
-		return -EINVAL;
-
-	ret = regmap_field_write(i2c->fields[F_DEV_ADDR], addr);
-	if (ret)
-		return ret;
-
-	return regmap_field_write(i2c->fields[F_DATA_WIDTH], (len - 1) & 0xf);
-}
-
-static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len)
+static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, u8 len)
 {
 	u32 vals[4] = {};
 	int i, ret;
@@ -153,7 +162,7 @@ static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len)
 	return 0;
 }
 
-static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len)
+static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, u8 len)
 {
 	u32 vals[4] = {};
 	int i;
@@ -176,16 +185,51 @@ static int rtl9300_i2c_writel(struct rtl9300_i2c *i2c, u32 data)
 	return regmap_write(i2c->regmap, i2c->data_reg, data);
 }
 
-static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write,
-				    int size, union i2c_smbus_data *data, int len)
+static int rtl9300_i2c_prepare_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_xfer *xfer)
+{
+	int ret;
+
+	if (xfer->data_len < 1 || xfer->data_len > 16)
+		return -EINVAL;
+
+	ret = regmap_field_write(i2c->fields[F_DEV_ADDR], xfer->dev_addr);
+	if (ret)
+		return ret;
+
+	ret = rtl9300_i2c_reg_addr_set(i2c, xfer->reg_addr, xfer->reg_addr_len);
+	if (ret)
+		return ret;
+
+	ret = regmap_field_write(i2c->fields[F_RWOP], xfer->write);
+	if (ret)
+		return ret;
+
+	ret = regmap_field_write(i2c->fields[F_DATA_WIDTH], (xfer->data_len - 1) & 0xf);
+	if (ret)
+		return ret;
+
+	if (xfer->write) {
+		switch (xfer->type) {
+		case RTL9300_I2C_XFER_BYTE:
+			ret = rtl9300_i2c_writel(i2c, *xfer->data);
+			break;
+		case RTL9300_I2C_XFER_WORD:
+			ret = rtl9300_i2c_writel(i2c, get_unaligned((const u16 *)xfer->data));
+			break;
+		default:
+			ret = rtl9300_i2c_write(i2c, xfer->data, xfer->data_len);
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static int rtl9300_i2c_do_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_xfer *xfer)
 {
 	u32 val;
 	int ret;
 
-	ret = regmap_field_write(i2c->fields[F_RWOP], read_write == I2C_SMBUS_WRITE);
-	if (ret)
-		return ret;
-
 	ret = regmap_field_write(i2c->fields[F_I2C_TRIG], 1);
 	if (ret)
 		return ret;
@@ -200,28 +244,24 @@ static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write,
 	if (val)
 		return -EIO;
 
-	if (read_write == I2C_SMBUS_READ) {
-		switch (size) {
-		case I2C_SMBUS_BYTE:
-		case I2C_SMBUS_BYTE_DATA:
+	if (!xfer->write) {
+		switch (xfer->type) {
+		case RTL9300_I2C_XFER_BYTE:
 			ret = regmap_read(i2c->regmap, i2c->data_reg, &val);
 			if (ret)
 				return ret;
-			data->byte = val & 0xff;
+
+			*xfer->data = val & 0xff;
 			break;
-		case I2C_SMBUS_WORD_DATA:
+		case RTL9300_I2C_XFER_WORD:
 			ret = regmap_read(i2c->regmap, i2c->data_reg, &val);
 			if (ret)
 				return ret;
-			data->word = val & 0xffff;
-			break;
-		case I2C_SMBUS_I2C_BLOCK_DATA:
-			ret = rtl9300_i2c_read(i2c, &data->block[1], len);
-			if (ret)
-				return ret;
+
+			put_unaligned(val & 0xffff, (u16*)xfer->data);
 			break;
 		default:
-			ret = rtl9300_i2c_read(i2c, &data->block[0], len);
+			ret = rtl9300_i2c_read(i2c, xfer->data, xfer->data_len);
 			if (ret)
 				return ret;
 			break;
@@ -237,108 +277,62 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 {
 	struct rtl9300_i2c_chan *chan = i2c_get_adapdata(adap);
 	struct rtl9300_i2c *i2c = chan->i2c;
-	int len = 0, ret;
+	struct rtl9300_i2c_xfer xfer = {0};
+	int ret;
+
+	if (addr > 0x7f)
+		return -EINVAL;
 
 	mutex_lock(&i2c->lock);
-	if (chan->sda_num != i2c->sda_num) {
-		ret = rtl9300_i2c_config_io(i2c, chan);
-		if (ret)
-			goto out_unlock;
-		i2c->sda_num = chan->sda_num;
-	}
+
+	ret = rtl9300_i2c_config_chan(i2c, chan);
+	if (ret)
+		goto out_unlock;
+
+	xfer.dev_addr = addr & 0x7f;
+	xfer.write = (read_write == I2C_SMBUS_WRITE);
+	xfer.reg_addr = command;
+	xfer.reg_addr_len = 1;
 
 	switch (size) {
 	case I2C_SMBUS_BYTE:
-		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0);
-			if (ret)
-				goto out_unlock;
-			ret = rtl9300_i2c_reg_addr_set(i2c, command, 1);
-			if (ret)
-				goto out_unlock;
-		} else {
-			ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 1);
-			if (ret)
-				goto out_unlock;
-			ret = rtl9300_i2c_reg_addr_set(i2c, 0, 0);
-			if (ret)
-				goto out_unlock;
-		}
+		xfer.data = (read_write == I2C_SMBUS_READ) ? &data->byte : &command;
+		xfer.data_len = 1;
+		xfer.reg_addr = 0;
+		xfer.reg_addr_len = 0;
+		xfer.type = RTL9300_I2C_XFER_BYTE;
 		break;
-
 	case I2C_SMBUS_BYTE_DATA:
-		ret = rtl9300_i2c_reg_addr_set(i2c, command, 1);
-		if (ret)
-			goto out_unlock;
-		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 1);
-		if (ret)
-			goto out_unlock;
-		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_writel(i2c, data->byte);
-			if (ret)
-				goto out_unlock;
-		}
+		xfer.data = &data->byte;
+		xfer.data_len = 1;
+		xfer.type = RTL9300_I2C_XFER_BYTE;
 		break;
-
 	case I2C_SMBUS_WORD_DATA:
-		ret = rtl9300_i2c_reg_addr_set(i2c, command, 1);
-		if (ret)
-			goto out_unlock;
-		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 2);
-		if (ret)
-			goto out_unlock;
-		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_writel(i2c, data->word);
-			if (ret)
-				goto out_unlock;
-		}
+		xfer.data = (u8 *)&data->word;
+		xfer.data_len = 2;
+		xfer.type = RTL9300_I2C_XFER_WORD;
 		break;
-
 	case I2C_SMBUS_BLOCK_DATA:
-		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] + 1);
-		if (ret)
-			goto out_unlock;
-		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_write(i2c, &data->block[0], data->block[0] + 1);
-			if (ret)
-				goto out_unlock;
-		}
-		len = data->block[0] + 1;
+		xfer.data = &data->block[0];
+		xfer.data_len = data->block[0] + 1;
+		xfer.type = RTL9300_I2C_XFER_BLOCK;
 		break;
-
 	case I2C_SMBUS_I2C_BLOCK_DATA:
-		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;
-		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_write(i2c, &data->block[1], data->block[0]);
-			if (ret)
-				goto out_unlock;
-		}
-		len = data->block[0];
+		xfer.data = &data->block[1];
+		xfer.data_len = data->block[0];
+		xfer.type = RTL9300_I2C_XFER_BLOCK;
 		break;
-
 	default:
 		dev_err(&adap->dev, "Unsupported transaction %d\n", size);
 		ret = -EOPNOTSUPP;
 		goto out_unlock;
 	}
 
-	ret = rtl9300_i2c_execute_xfer(i2c, read_write, size, data, len);
+	ret = rtl9300_i2c_prepare_xfer(i2c, &xfer);
+	if (ret)
+		goto out_unlock;
+
+	ret = rtl9300_i2c_do_xfer(i2c, &xfer);
 
 out_unlock:
 	mutex_unlock(&i2c->lock);

From 46fe8265685cb6003a0989b53e11e8afa4826572 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:29 +0000
Subject: [PATCH 129/352] i2c: rtl9300: use scoped guard instead of explicit
 lock/unlock

Use the scoped guard infrastructure which unlocks a mutex automatically
when the guard goes out of scope, instead of explicit lock and unlock.
This simplifies the code and control flow in rtl9300_i2c_smbus_xfer and
removes the need of using goto in error cases to unlock before
returning.

Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
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/20250927101931.71575-8-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index fb3ebbd46a18..c67463228604 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -72,6 +72,8 @@ struct rtl9300_i2c {
 	struct mutex lock;
 };
 
+DEFINE_GUARD(rtl9300_i2c, struct rtl9300_i2c *, mutex_lock(&_T->lock), mutex_unlock(&_T->lock))
+
 enum rtl9300_i2c_xfer_type {
 	RTL9300_I2C_XFER_BYTE,
 	RTL9300_I2C_XFER_WORD,
@@ -283,11 +285,11 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 	if (addr > 0x7f)
 		return -EINVAL;
 
-	mutex_lock(&i2c->lock);
+	guard(rtl9300_i2c)(i2c);
 
 	ret = rtl9300_i2c_config_chan(i2c, chan);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	xfer.dev_addr = addr & 0x7f;
 	xfer.write = (read_write == I2C_SMBUS_WRITE);
@@ -324,20 +326,14 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 		break;
 	default:
 		dev_err(&adap->dev, "Unsupported transaction %d\n", size);
-		ret = -EOPNOTSUPP;
-		goto out_unlock;
+		return -EOPNOTSUPP;
 	}
 
 	ret = rtl9300_i2c_prepare_xfer(i2c, &xfer);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
-	ret = rtl9300_i2c_do_xfer(i2c, &xfer);
-
-out_unlock:
-	mutex_unlock(&i2c->lock);
-
-	return ret;
+	return rtl9300_i2c_do_xfer(i2c, &xfer);
 }
 
 static u32 rtl9300_i2c_func(struct i2c_adapter *a)

From 99fd09e01db2c6fc4c6ffe851b337f64ff93e1b5 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:30 +0000
Subject: [PATCH 130/352] dt-bindings: i2c: realtek,rtl9301-i2c: extend for
 RTL9310 support

Adjust the regex for child-node address to account for the fact that
RTL9310 supports 12 instead of only 8 SDA lines. Also, narrow this per
variant.

Add a vendor-specific property to explicitly specify the SCL line number
of the defined I2C controller/master. This is required, in particular
for RTL9310, to operate on the correct SCL for each controller. Require
this property to be specified for RTL9310.

Add compatibles for known SoC variants RTL9311, RTL9312 and RTL9313.

Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Markus Stockhausen <markus.stockhausen@gmx.de>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250927101931.71575-9-jelonek.jonas@gmail.com
---
 .../bindings/i2c/realtek,rtl9301-i2c.yaml     | 39 ++++++++++++++++++-
 1 file changed, 37 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
index 274e2ab8b612..17ce39c19ab1 100644
--- a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
@@ -13,6 +13,8 @@ description:
   RTL9300 SoCs have two I2C controllers. Each of these has an SCL line (which
   if not-used for SCL can be a GPIO). There are 8 common SDA lines that can be
   assigned to either I2C controller.
+  RTL9310 SoCs have equal capabilities but support 12 common SDA lines which
+  can be assigned to either I2C controller.
 
 properties:
   compatible:
@@ -23,7 +25,15 @@ properties:
               - realtek,rtl9302c-i2c
               - realtek,rtl9303-i2c
           - const: realtek,rtl9301-i2c
-      - const: realtek,rtl9301-i2c
+      - items:
+          - enum:
+              - realtek,rtl9311-i2c
+              - realtek,rtl9312-i2c
+              - realtek,rtl9313-i2c
+          - const: realtek,rtl9310-i2c
+      - enum:
+          - realtek,rtl9301-i2c
+          - realtek,rtl9310-i2c
 
   reg:
     items:
@@ -35,8 +45,14 @@ properties:
   "#size-cells":
     const: 0
 
+  realtek,scl:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      The SCL line number of this I2C controller.
+    enum: [ 0, 1 ]
+
 patternProperties:
-  '^i2c@[0-7]$':
+  '^i2c@[0-9ab]$':
     $ref: /schemas/i2c/i2c-controller.yaml
     unevaluatedProperties: false
 
@@ -48,6 +64,25 @@ patternProperties:
     required:
       - reg
 
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: realtek,rtl9310-i2c
+    then:
+      required:
+        - realtek,scl
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: realtek,rtl9301-i2c
+    then:
+      patternProperties:
+        '^i2c@[89ab]$': false
+
 required:
   - compatible
   - reg

From 1e33137d47105a807262aa17e028374463876f85 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sat, 27 Sep 2025 10:19:31 +0000
Subject: [PATCH 131/352] i2c: rtl9300: add support for RTL9310 I2C controller

Add support for the internal I2C controllers of RTL9310 series based
SoCs to the driver for RTL9300. Add register definitions, chip-specific
functions and compatible strings for known RTL9310-based SoCs RTL9311,
RTL9312 and RTL9313.

Make use of a new device tree property 'realtek,scl' which needs to be
specified in case both or only the second master is used. This is
required due how the register layout changed in contrast to RTL9300,
which has SCL selection in a global register instead of a
master-specific one.

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: Markus Stockhausen <markus.stockhausen@gmx.de>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250927101931.71575-10-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 47 ++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index c67463228604..4723e48cfe18 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -60,14 +60,16 @@ struct rtl9300_i2c_drv_data {
 };
 
 #define RTL9300_I2C_MUX_NCHAN	8
+#define RTL9310_I2C_MUX_NCHAN	12
 
 struct rtl9300_i2c {
 	struct regmap *regmap;
 	struct device *dev;
-	struct rtl9300_i2c_chan chans[RTL9300_I2C_MUX_NCHAN];
+	struct rtl9300_i2c_chan chans[RTL9310_I2C_MUX_NCHAN];
 	struct regmap_field *fields[F_NUM_FIELDS];
 	u32 reg_base;
 	u32 data_reg;
+	u8 scl_num;
 	u8 sda_num;
 	struct mutex lock;
 };
@@ -98,6 +100,12 @@ struct rtl9300_i2c_xfer {
 #define RTL9300_I2C_MST_DATA_WORD3			0x14
 #define RTL9300_I2C_MST_GLB_CTRL			0x384
 
+#define RTL9310_I2C_MST_IF_CTRL				0x1004
+#define RTL9310_I2C_MST_IF_SEL				0x1008
+#define RTL9310_I2C_MST_CTRL				0x0
+#define RTL9310_I2C_MST_MEMADDR_CTRL			0x4
+#define RTL9310_I2C_MST_DATA_CTRL			0x8
+
 static int rtl9300_i2c_reg_addr_set(struct rtl9300_i2c *i2c, u32 reg, u16 len)
 {
 	int ret;
@@ -114,6 +122,11 @@ static int rtl9300_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl)
 	return regmap_field_write(i2c->fields[F_SCL_SEL], 1);
 }
 
+static int rtl9310_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl)
+{
+	return regmap_field_update_bits(i2c->fields[F_SCL_SEL], BIT(scl), BIT(scl));
+}
+
 static int rtl9300_i2c_config_chan(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan)
 {
 	struct rtl9300_i2c_drv_data *drv_data;
@@ -127,7 +140,7 @@ static int rtl9300_i2c_config_chan(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c
 		return ret;
 
 	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
-	ret = drv_data->select_scl(i2c, 0);
+	ret = drv_data->select_scl(i2c, i2c->scl_num);
 	if (ret)
 		return ret;
 
@@ -361,7 +374,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 	struct fwnode_handle *child;
 	struct rtl9300_i2c_drv_data *drv_data;
 	struct reg_field fields[F_NUM_FIELDS];
-	u32 clock_freq, sda_num;
+	u32 clock_freq, scl_num, sda_num;
 	int ret, i = 0;
 
 	i2c = devm_kzalloc(dev, sizeof(*i2c), GFP_KERNEL);
@@ -379,6 +392,11 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = device_property_read_u32(dev, "realtek,scl", &scl_num);
+	if (ret || scl_num != 1)
+		scl_num = 0;
+	i2c->scl_num = (u8)scl_num;
+
 	platform_set_drvdata(pdev, i2c);
 
 	drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev);
@@ -474,12 +492,35 @@ static const struct rtl9300_i2c_drv_data rtl9300_i2c_drv_data = {
 	.max_nchan = RTL9300_I2C_MUX_NCHAN,
 };
 
+static const struct rtl9300_i2c_drv_data rtl9310_i2c_drv_data = {
+	.field_desc = {
+		[F_SCL_SEL]		= GLB_REG_FIELD(RTL9310_I2C_MST_IF_SEL, 12, 13),
+		[F_SDA_SEL]		= GLB_REG_FIELD(RTL9310_I2C_MST_IF_SEL, 0, 11),
+		[F_SCL_FREQ]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 30, 31),
+		[F_DEV_ADDR]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 11, 17),
+		[F_SDA_OUT_SEL]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 18, 21),
+		[F_MEM_ADDR_WIDTH]	= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 9, 10),
+		[F_DATA_WIDTH]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 5, 8),
+		[F_RD_MODE]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 4, 4),
+		[F_RWOP]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 2, 2),
+		[F_I2C_FAIL]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 1, 1),
+		[F_I2C_TRIG]		= MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 0, 0),
+		[F_MEM_ADDR]		= MST_REG_FIELD(RTL9310_I2C_MST_MEMADDR_CTRL, 0, 23),
+	},
+	.select_scl = rtl9310_i2c_select_scl,
+	.data_reg = RTL9310_I2C_MST_DATA_CTRL,
+	.max_nchan = RTL9310_I2C_MUX_NCHAN,
+};
 
 static const struct of_device_id i2c_rtl9300_dt_ids[] = {
 	{ .compatible = "realtek,rtl9301-i2c", .data = (void *) &rtl9300_i2c_drv_data },
 	{ .compatible = "realtek,rtl9302b-i2c", .data = (void *) &rtl9300_i2c_drv_data },
 	{ .compatible = "realtek,rtl9302c-i2c", .data = (void *) &rtl9300_i2c_drv_data },
 	{ .compatible = "realtek,rtl9303-i2c", .data = (void *) &rtl9300_i2c_drv_data },
+	{ .compatible = "realtek,rtl9310-i2c", .data = (void *) &rtl9310_i2c_drv_data },
+	{ .compatible = "realtek,rtl9311-i2c", .data = (void *) &rtl9310_i2c_drv_data },
+	{ .compatible = "realtek,rtl9312-i2c", .data = (void *) &rtl9310_i2c_drv_data },
+	{ .compatible = "realtek,rtl9313-i2c", .data = (void *) &rtl9310_i2c_drv_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, i2c_rtl9300_dt_ids);

From 328b80b29a6a165c47fcc04d2bef3e09ed1d28f9 Mon Sep 17 00:00:00 2001
From: Adam Holliday <dochollidayxx@gmail.com>
Date: Tue, 30 Sep 2025 11:09:14 -0400
Subject: [PATCH 132/352] ALSA: hda/realtek: Add quirk for ASUS ROG Zephyrus
 Duo

The ASUS ROG Zephyrus Duo 15 SE (GX551QS) with ALC 289 codec requires specific
pin configuration for proper volume control. Without this quirk, volume
adjustments produce a muffled sound effect as only certain channels attenuate,
leaving bass frequency at full volume.

Testing with hdajackretask confirms these pin tweaks fix the issue:
- Pin 0x17: Internal Speaker (LFE)
- Pin 0x1e: Internal Speaker

Signed-off-by: Adam Holliday <dochollidayxx@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 3c42f66fe000..214eb9df6ef8 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -3735,6 +3735,7 @@ enum {
 	ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC,
 	ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1,
 	ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC,
+	ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -6164,6 +6165,14 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
 	},
+	[ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x17, 0x90170151 }, /* Internal Speaker LFE */
+			{ 0x1e, 0x90170150 }, /* Internal Speaker */
+			{ }
+		},
+	}
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -6718,6 +6727,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),

From 7a6399e327f4d5607d984c336c9c6e1cfcd9194a Mon Sep 17 00:00:00 2001
From: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Date: Wed, 1 Oct 2025 14:37:57 +0530
Subject: [PATCH 133/352] ALSA: emu10k1: Fix typo in docs

interally => internally

Signed-off-by: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/cards/emu-mixer.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/sound/cards/emu-mixer.rst b/Documentation/sound/cards/emu-mixer.rst
index d87a6338d3d8..edcedada4c96 100644
--- a/Documentation/sound/cards/emu-mixer.rst
+++ b/Documentation/sound/cards/emu-mixer.rst
@@ -66,7 +66,7 @@ FX-bus
 
 name='Clock Source',index=0
 ---------------------------
-This control allows switching the word clock between interally generated
+This control allows switching the word clock between internally generated
 44.1 or 48 kHz, or a number of external sources.
 
 Note: the sources for the 1616 CardBus card are unclear. Please report your

From de7342228b7343774d6a9981c2ddbfb5e201044b Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Sat, 4 Oct 2025 22:23:29 +0800
Subject: [PATCH 134/352] bpf: Finish constification of 1st parameter of
 bpf_d_path()

The commit 1b8abbb12128 ("bpf...d_path(): constify path argument")
constified the first parameter of the bpf_d_path(), but failed to
update it in all places. Finish constification.

Otherwise the selftest fail to build:
.../selftests/bpf/bpf_experimental.h:222:12: error: conflicting types for 'bpf_path_d_path'
  222 | extern int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz) __ksym;
      |            ^
.../selftests/bpf/tools/include/vmlinux.h:153922:12: note: previous declaration is here
 153922 | extern int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) __weak __ksym;

Fixes: 1b8abbb12128 ("bpf...d_path(): constify path argument")
Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h                                | 2 +-
 scripts/bpf_doc.py                                      | 1 +
 tools/include/uapi/linux/bpf.h                          | 2 +-
 tools/testing/selftests/bpf/progs/verifier_vfs_accept.c | 2 +-
 4 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ae83d8649ef1..6829936d33f5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4891,7 +4891,7 @@ union bpf_attr {
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
  *
- * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * long bpf_d_path(const struct path *path, char *buf, u32 sz)
  *	Description
  *		Return full path for given **struct path** object, which
  *		needs to be the kernel BTF *path* object. The path is
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index c77dc40f7689..15d113a1bc1d 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -788,6 +788,7 @@ class PrinterHelpersHeader(Printer):
             'struct task_struct',
             'struct cgroup',
             'struct path',
+            'const struct path',
             'struct btf_ptr',
             'struct inode',
             'struct socket',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ae83d8649ef1..6829936d33f5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4891,7 +4891,7 @@ union bpf_attr {
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
  *
- * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * long bpf_d_path(const struct path *path, char *buf, u32 sz)
  *	Description
  *		Return full path for given **struct path** object, which
  *		needs to be the kernel BTF *path* object. The path is
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
index 3e2d76ee8050..55398c04290a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
@@ -70,7 +70,7 @@ __success
 int BPF_PROG(path_d_path_from_file_argument, struct file *file)
 {
 	int ret;
-	struct path *path;
+	const struct path *path;
 
 	/* The f_path member is a path which is embedded directly within a
 	 * file. Therefore, a pointer to such embedded members are still

From b71a6e2a1b710ea31c363a72c75f510ef35d8e69 Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul@sk.com>
Date: Thu, 2 Oct 2025 17:12:35 +0900
Subject: [PATCH 135/352] i2c: rename wait_for_completion callback to
 wait_for_completion_cb

Functionally no change. Remove the ambiguity of 'wait_for_completion'.
It helps development of the DEPT dependency tracker, but seems favorable
in any case.

Signed-off-by: Byungchul Park <byungchul@sk.com>
[wsa: reworded commit message]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/algos/i2c-algo-pca.c      | 2 +-
 drivers/i2c/busses/i2c-pca-isa.c      | 2 +-
 drivers/i2c/busses/i2c-pca-platform.c | 2 +-
 include/linux/i2c-algo-pca.h          | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 74b66aec33d4..ee86df4cff4b 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -30,7 +30,7 @@ static int i2c_debug;
 #define pca_clock(adap) adap->i2c_clock
 #define pca_set_con(adap, val) pca_outw(adap, I2C_PCA_CON, val)
 #define pca_get_con(adap) pca_inw(adap, I2C_PCA_CON)
-#define pca_wait(adap) adap->wait_for_completion(adap->data)
+#define pca_wait(adap) adap->wait_for_completion_cb(adap->data)
 
 static void pca_reset(struct i2c_algo_pca_data *adap)
 {
diff --git a/drivers/i2c/busses/i2c-pca-isa.c b/drivers/i2c/busses/i2c-pca-isa.c
index 85e8cf58e8bf..0cbf2f509527 100644
--- a/drivers/i2c/busses/i2c-pca-isa.c
+++ b/drivers/i2c/busses/i2c-pca-isa.c
@@ -95,7 +95,7 @@ static struct i2c_algo_pca_data pca_isa_data = {
 	/* .data intentionally left NULL, not needed with ISA */
 	.write_byte		= pca_isa_writebyte,
 	.read_byte		= pca_isa_readbyte,
-	.wait_for_completion	= pca_isa_waitforcompletion,
+	.wait_for_completion_cb	= pca_isa_waitforcompletion,
 	.reset_chip		= pca_isa_resetchip,
 };
 
diff --git a/drivers/i2c/busses/i2c-pca-platform.c b/drivers/i2c/busses/i2c-pca-platform.c
index 87da8241b927..c0f35ebbe37d 100644
--- a/drivers/i2c/busses/i2c-pca-platform.c
+++ b/drivers/i2c/busses/i2c-pca-platform.c
@@ -180,7 +180,7 @@ static int i2c_pca_pf_probe(struct platform_device *pdev)
 	}
 
 	i2c->algo_data.data = i2c;
-	i2c->algo_data.wait_for_completion = i2c_pca_pf_waitforcompletion;
+	i2c->algo_data.wait_for_completion_cb = i2c_pca_pf_waitforcompletion;
 	if (i2c->gpio)
 		i2c->algo_data.reset_chip = i2c_pca_pf_resetchip;
 	else
diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h
index 7c522fdd9ea7..e305bf32e40a 100644
--- a/include/linux/i2c-algo-pca.h
+++ b/include/linux/i2c-algo-pca.h
@@ -71,7 +71,7 @@ struct i2c_algo_pca_data {
 	void 				*data;	/* private low level data */
 	void (*write_byte)		(void *data, int reg, int val);
 	int  (*read_byte)		(void *data, int reg);
-	int  (*wait_for_completion)	(void *data);
+	int  (*wait_for_completion_cb)	(void *data);
 	void (*reset_chip)		(void *data);
 	/* For PCA9564, use one of the predefined frequencies:
 	 * 330000, 288000, 217000, 146000, 88000, 59000, 44000, 36000

From d51e7cfca3fe5540466322c33d665674530148dd Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 25 Sep 2025 23:05:18 +0200
Subject: [PATCH 136/352] i2c: mt65xx: convert set_speed function to void

cppcheck rightfully reports:
drivers/i2c/busses/i2c-mt65xx.c:1464:6: warning: Condition 'ret' is always false [knownConditionTrueFalse]

Make the function void and simplify the code.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/i2c/busses/i2c-mt65xx.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index dee40704825c..aefdbee1f03c 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -868,7 +868,7 @@ static int mtk_i2c_calculate_speed(struct mtk_i2c *i2c, unsigned int clk_src,
 	return 0;
 }
 
-static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk)
+static void mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk)
 {
 	unsigned int clk_src;
 	unsigned int step_cnt;
@@ -938,9 +938,6 @@ static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk)
 
 		break;
 	}
-
-
-	return 0;
 }
 
 static void i2c_dump_register(struct mtk_i2c *i2c)
@@ -1460,11 +1457,7 @@ static int mtk_i2c_probe(struct platform_device *pdev)
 
 	strscpy(i2c->adap.name, I2C_DRV_NAME, sizeof(i2c->adap.name));
 
-	ret = mtk_i2c_set_speed(i2c, clk_get_rate(i2c->clocks[speed_clk].clk));
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to set the speed.\n");
-		return -EINVAL;
-	}
+	mtk_i2c_set_speed(i2c, clk_get_rate(i2c->clocks[speed_clk].clk));
 
 	if (i2c->dev_comp->max_dma_support > 32) {
 		ret = dma_set_mask(&pdev->dev,

From a6b4f791cdc56655b2dee8ac793f5b28dc4e542d Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 24 Sep 2025 17:28:46 -0500
Subject: [PATCH 137/352] dt-bindings: rtc: Convert apm,xgene-rtc to DT schema

Convert the APM XGene RTC binding to DT schema format. It's a
straight-forward conversion.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250924222848.2949235-1-robh@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../bindings/rtc/apm,xgene-rtc.yaml           | 45 +++++++++++++++++++
 .../devicetree/bindings/rtc/xgene-rtc.txt     | 28 ------------
 2 files changed, 45 insertions(+), 28 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml
 delete mode 100644 Documentation/devicetree/bindings/rtc/xgene-rtc.txt

diff --git a/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml b/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml
new file mode 100644
index 000000000000..b8f46536fd5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/apm,xgene-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: APM X-Gene Real Time Clock
+
+maintainers:
+  - Khuong Dinh <khuong@os.amperecomputing.com>
+
+properties:
+  compatible:
+    const: apm,xgene-rtc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - '#clock-cells'
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    rtc@10510000 {
+        compatible = "apm,xgene-rtc";
+        reg = <0x10510000 0x400>;
+        interrupts = <0x0 0x46 0x4>;
+        #clock-cells = <1>;
+        clocks = <&rtcclk 0>;
+    };
diff --git a/Documentation/devicetree/bindings/rtc/xgene-rtc.txt b/Documentation/devicetree/bindings/rtc/xgene-rtc.txt
deleted file mode 100644
index fd195c358446..000000000000
--- a/Documentation/devicetree/bindings/rtc/xgene-rtc.txt
+++ /dev/null
@@ -1,28 +0,0 @@
-* APM X-Gene Real Time Clock
-
-RTC controller for the APM X-Gene Real Time Clock
-
-Required properties:
-- compatible : Should be "apm,xgene-rtc"
-- reg: physical base address of the controller and length of memory mapped
-  region.
-- interrupts: IRQ line for the RTC.
-- #clock-cells: Should be 1.
-- clocks: Reference to the clock entry.
-
-Example:
-
-rtcclk: rtcclk {
-	compatible = "fixed-clock";
-	#clock-cells = <1>;
-	clock-frequency = <100000000>;
-	clock-output-names = "rtcclk";
-};
-
-rtc: rtc@10510000 {
-	compatible = "apm,xgene-rtc";
-	reg = <0x0 0x10510000 0x0 0x400>;
-	interrupts = <0x0 0x46 0x4>;
-	#clock-cells = <1>;
-	clocks = <&rtcclk 0>;
-};

From 8bbd727453b497722b3e31b5d634c35faa953fbd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 18 Sep 2025 12:49:31 +0300
Subject: [PATCH 138/352] rtc: optee: fix error code in probe()

Return an error code if kthread_create() fails.  Currently the code
returns success.

Fixes: 6266aea864fa ("rtc: optee: add alarm related rtc ops to optee rtc driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/21f1a18008f1bbc8f70d0bd5c05b72fbf5fc9c7d.1758182509.git.dan.carpenter@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index 27db403e3047..7b44d7723cae 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -614,6 +614,7 @@ static int optee_rtc_probe(struct device *dev)
 						  priv, "rtc_alarm_evt");
 		if (IS_ERR(priv->alarm_task)) {
 			dev_err(dev, "Failed to create alarm thread\n");
+			err = PTR_ERR(priv->alarm_task);
 			goto out_shm;
 		}
 

From eb7392a019642f0ef5b9acd5e56a3f051d64a5ef Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 18 Sep 2025 12:49:48 +0300
Subject: [PATCH 139/352] rtc: optee: Fix error code in optee_rtc_read_alarm()

Return "optee_alarm" instead of "alarm".  The "alarm" pointer is a valid
pointer and not an error pointer.

Fixes: 6266aea864fa ("rtc: optee: add alarm related rtc ops to optee rtc driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/9e3718fe1128964907619ad325c0c5f5c1354ace.1758182509.git.dan.carpenter@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index 7b44d7723cae..3d5662aa1bd8 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -299,7 +299,7 @@ static int optee_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 
 	optee_alarm = tee_shm_get_va(priv->shm, 0);
 	if (IS_ERR(optee_alarm))
-		return PTR_ERR(alarm);
+		return PTR_ERR(optee_alarm);
 
 	if (param[0].u.memref.size != sizeof(*optee_alarm))
 		return -EPROTO;

From b650cf9108efea71e51f1287f2e5ccd2144979af Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sun, 5 Oct 2025 22:19:24 +0200
Subject: [PATCH 140/352] rtc: optee: make optee_rtc_pm_ops static

Fix sparse warningg:
drivers/rtc/rtc-optee.c:714:1: sparse: sparse: symbol 'optee_rtc_pm_ops' was not
declared. Should it be static?

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202509230549.L26lw7UZ-lkp@intel.com/
Link: https://lore.kernel.org/r/20251005201925.3757345-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-optee.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c
index 3d5662aa1bd8..184c6d142801 100644
--- a/drivers/rtc/rtc-optee.c
+++ b/drivers/rtc/rtc-optee.c
@@ -712,7 +712,7 @@ static int optee_rtc_suspend(struct device *dev)
 	return 0;
 }
 
-DEFINE_SIMPLE_DEV_PM_OPS(optee_rtc_pm_ops, optee_rtc_suspend, NULL);
+static DEFINE_SIMPLE_DEV_PM_OPS(optee_rtc_pm_ops, optee_rtc_suspend, NULL);
 
 static const struct tee_client_device_id optee_rtc_id_table[] = {
 	{UUID_INIT(0xf389f8c8, 0x845f, 0x496c,

From a5a19e80b235ed2c456dbab59c85ca43e87e01bf Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sun, 5 Oct 2025 22:30:48 +0200
Subject: [PATCH 141/352] rtc: Kconfig: move symbols to proper section

There is only one HID RTC, the following symbols are for on-SoC RTCs

Link: https://lore.kernel.org/r/20251005203048.3759240-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 31d355b103d4..17531bfe3dea 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -2044,20 +2044,6 @@ config RTC_DRV_RENESAS_RTCA3
 	  This driver can also be built as a module, if so, the module
 	  will be called "rtc-rtca3".
 
-comment "HID Sensor RTC drivers"
-
-config RTC_DRV_HID_SENSOR_TIME
-	tristate "HID Sensor Time"
-	depends on USB_HID
-	depends on HID_SENSOR_HUB && IIO
-	select HID_SENSOR_IIO_COMMON
-	help
-	  Say yes here to build support for the HID Sensors of type Time.
-	  This drivers makes such sensors available as RTCs.
-
-	  If this driver is compiled as a module, it will be named
-	  rtc-hid-sensor-time.
-
 config RTC_DRV_GOLDFISH
 	tristate "Goldfish Real Time Clock"
 	depends on HAS_IOMEM
@@ -2132,4 +2118,18 @@ config RTC_DRV_S32G
 	  This RTC module can be used as a wakeup source.
 	  Please note that it is not battery-powered.
 
+comment "HID Sensor RTC drivers"
+
+config RTC_DRV_HID_SENSOR_TIME
+	tristate "HID Sensor Time"
+	depends on USB_HID
+	depends on HID_SENSOR_HUB && IIO
+	select HID_SENSOR_IIO_COMMON
+	help
+	  Say yes here to build support for the HID Sensors of type Time.
+	  This drivers makes such sensors available as RTCs.
+
+	  If this driver is compiled as a module, it will be named
+	  rtc-hid-sensor-time.
+
 endif # RTC_CLASS

From 75b002a38d4f740d51f0e09dcd778541f61a2797 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?T=C3=B3th=20J=C3=A1nos?= <gomba007@gmail.com>
Date: Mon, 7 Apr 2025 13:48:49 +0200
Subject: [PATCH 142/352] rtc: sd2405al: Add I2C address.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is common to include the I2C address of the device in the source
file.

Signed-off-by: Tóth János <gomba007@gmail.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-sd2405al.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-sd2405al.c b/drivers/rtc/rtc-sd2405al.c
index 00c3033e8079..708ea5d964de 100644
--- a/drivers/rtc/rtc-sd2405al.c
+++ b/drivers/rtc/rtc-sd2405al.c
@@ -5,7 +5,9 @@
  * Datasheet:
  * https://image.dfrobot.com/image/data/TOY0021/SD2405AL%20datasheet%20(Angelo%20v0.1).pdf
  *
- * Copyright (C) 2024 Tóth János <gomba007@gmail.com>
+ * I2C slave address: 0x32
+ *
+ * Copyright (C) 2024-2025 Tóth János <gomba007@gmail.com>
  */
 
 #include <linux/bcd.h>

From f38bdd730914be1fcd63240af89a2dc802148c8a Mon Sep 17 00:00:00 2001
From: Xianwei Zhao <xianwei.zhao@amlogic.com>
Date: Tue, 22 Jul 2025 19:30:48 +0800
Subject: [PATCH 143/352] rtc: amlogic-a4: Optimize global variables

Convert a global variable into a local one of aml_rtc_probe().

Signed-off-by: Xianwei Zhao <xianwei.zhao@amlogic.com>
Link: https://lore.kernel.org/r/20250722-rtc-regmap-v2-1-58bc17187a11@amlogic.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-amlogic-a4.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c
index 09d78c2cc691..1928b29c1045 100644
--- a/drivers/rtc/rtc-amlogic-a4.c
+++ b/drivers/rtc/rtc-amlogic-a4.c
@@ -72,13 +72,6 @@ struct aml_rtc_data {
 	const struct aml_rtc_config *config;
 };
 
-static const struct regmap_config aml_rtc_regmap_config = {
-	.reg_bits = 32,
-	.val_bits = 32,
-	.reg_stride = 4,
-	.max_register = RTC_REAL_TIME,
-};
-
 static inline u32 gray_to_binary(u32 gray)
 {
 	u32 bcd = gray;
@@ -328,6 +321,13 @@ static int aml_rtc_probe(struct platform_device *pdev)
 	void __iomem *base;
 	int ret = 0;
 
+	const struct regmap_config aml_rtc_regmap_config = {
+		.reg_bits = 32,
+		.val_bits = 32,
+		.reg_stride = 4,
+		.max_register = RTC_REAL_TIME,
+	};
+
 	rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL);
 	if (!rtc)
 		return -ENOMEM;

From e22f4d1321e0055065f274e20bf6d1dbf4b500f5 Mon Sep 17 00:00:00 2001
From: Harini T <harini.t@amd.com>
Date: Wed, 30 Jul 2025 19:51:10 +0530
Subject: [PATCH 144/352] rtc: zynqmp: Restore alarm functionality after kexec
 transition

During kexec reboots, RTC alarms that are fired during the kernel
transition experience delayed execution. The new kernel would eventually
honor these alarms, but the interrupt handlers would only execute after
the driver probe is completed rather than at the intended alarm time.

This is because pending alarm interrupt status from the previous kernel
is not properly cleared during driver initialization, causing timing
discrepancies in alarm delivery.

To ensure precise alarm timing across kexec transitions, enhance the
probe function to:
1. Clear any pending alarm interrupt status from previous boot.
2. Detect existing valid alarms and preserve their state.
3. Re-enable alarm interrupts for future alarms.

Signed-off-by: Harini T <harini.t@amd.com>
Link: https://lore.kernel.org/r/20250730142110.2354507-1-harini.t@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-zynqmp.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index f39102b66eac..3baa2b481d9f 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -277,6 +277,10 @@ static irqreturn_t xlnx_rtc_interrupt(int irq, void *id)
 static int xlnx_rtc_probe(struct platform_device *pdev)
 {
 	struct xlnx_rtc_dev *xrtcdev;
+	bool is_alarm_set = false;
+	u32 pending_alrm_irq;
+	u32 current_time;
+	u32 alarm_time;
 	int ret;
 
 	xrtcdev = devm_kzalloc(&pdev->dev, sizeof(*xrtcdev), GFP_KERNEL);
@@ -296,6 +300,17 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 	if (IS_ERR(xrtcdev->reg_base))
 		return PTR_ERR(xrtcdev->reg_base);
 
+	/* Clear any pending alarm interrupts from previous kernel/boot */
+	pending_alrm_irq = readl(xrtcdev->reg_base + RTC_INT_STS) & RTC_INT_ALRM;
+	if (pending_alrm_irq)
+		writel(pending_alrm_irq, xrtcdev->reg_base + RTC_INT_STS);
+
+	/* Check if a valid alarm is already set from previous kernel/boot */
+	alarm_time = readl(xrtcdev->reg_base + RTC_ALRM);
+	current_time = readl(xrtcdev->reg_base + RTC_CUR_TM);
+	if (alarm_time > current_time && alarm_time != 0)
+		is_alarm_set = true;
+
 	xrtcdev->alarm_irq = platform_get_irq_byname(pdev, "alarm");
 	if (xrtcdev->alarm_irq < 0)
 		return xrtcdev->alarm_irq;
@@ -337,6 +352,10 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 
 	xlnx_init_rtc(xrtcdev);
 
+	/* Re-enable alarm interrupt if a valid alarm was found */
+	if (is_alarm_set)
+		writel(RTC_INT_ALRM, xrtcdev->reg_base + RTC_INT_EN);
+
 	device_init_wakeup(&pdev->dev, true);
 
 	return devm_rtc_register_device(xrtcdev->rtc);

From 87064da2db7be537a7da20a25c18ba912c4db9e1 Mon Sep 17 00:00:00 2001
From: Bruno Thomsen <bruno.thomsen@gmail.com>
Date: Tue, 2 Sep 2025 20:22:35 +0200
Subject: [PATCH 145/352] rtc: pcf2127: fix watchdog interrupt mask on pcf2131

When using interrupt pin (INT A) as watchdog output all other
interrupt sources need to be disabled to avoid additional
resets. Resulting INT_A_MASK1 value is 55 (0x37).

Signed-off-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20250902182235.6825-1-bruno.thomsen@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 3ba1de30e89c..bb4fe81d3d62 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -608,6 +608,21 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
 			set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status);
 	}
 
+	/*
+	 * When using interrupt pin (INT A) as watchdog output, only allow
+	 * watchdog interrupt (PCF2131_BIT_INT_WD_CD) and disable (mask) all
+	 * other interrupts.
+	 */
+	if (pcf2127->cfg->type == PCF2131) {
+		ret = regmap_write(pcf2127->regmap,
+				   PCF2131_REG_INT_A_MASK1,
+				   PCF2131_BIT_INT_BLIE |
+				   PCF2131_BIT_INT_BIE |
+				   PCF2131_BIT_INT_AIE |
+				   PCF2131_BIT_INT_SI |
+				   PCF2131_BIT_INT_MI);
+	}
+
 	return devm_watchdog_register_device(dev, &pcf2127->wdd);
 }
 

From 5ac2c0279053a2c5265d46903432fb26ae2d0da2 Mon Sep 17 00:00:00 2001
From: Zack Rusin <zack.rusin@broadcom.com>
Date: Wed, 17 Sep 2025 11:36:55 -0400
Subject: [PATCH 146/352] drm/vmwgfx: Fix a null-ptr access in the cursor
 snooper

Check that the resource which is converted to a surface exists before
trying to use the cursor snooper on it.

vmw_cmd_res_check allows explicit invalid (SVGA3D_INVALID_ID) identifiers
because some svga commands accept SVGA3D_INVALID_ID to mean "no surface",
unfortunately functions that accept the actual surfaces as objects might
(and in case of the cursor snooper, do not) be able to handle null
objects. Make sure that we validate not only the identifier (via the
vmw_cmd_res_check) but also check that the actual resource exists before
trying to do something with it.

Fixes unchecked null-ptr reference in the snooping code.

Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Fixes: c0951b797e7d ("drm/vmwgfx: Refactor resource management")
Reported-by: Kuzey Arda Bulut <kuzeyardabulut@gmail.com>
Cc: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Ian Forbes <ian.forbes@broadcom.com>
Link: https://lore.kernel.org/r/20250917153655.1968583-1-zack.rusin@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 819704ac675d..d539f25b5fbe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1497,6 +1497,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		       SVGA3dCmdHeader *header)
 {
 	struct vmw_bo *vmw_bo = NULL;
+	struct vmw_resource *res;
 	struct vmw_surface *srf = NULL;
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdSurfaceDMA);
 	int ret;
@@ -1532,18 +1533,24 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 
 	dirty = (cmd->body.transfer == SVGA3D_WRITE_HOST_VRAM) ?
 		VMW_RES_DIRTY_SET : 0;
-	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
-				dirty, user_surface_converter,
-				&cmd->body.host.sid, NULL);
+	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, dirty,
+				user_surface_converter, &cmd->body.host.sid,
+				NULL);
 	if (unlikely(ret != 0)) {
 		if (unlikely(ret != -ERESTARTSYS))
 			VMW_DEBUG_USER("could not find surface for DMA.\n");
 		return ret;
 	}
 
-	srf = vmw_res_to_srf(sw_context->res_cache[vmw_res_surface].res);
+	res = sw_context->res_cache[vmw_res_surface].res;
+	if (!res) {
+		VMW_DEBUG_USER("Invalid DMA surface.\n");
+		return -EINVAL;
+	}
 
-	vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo, header);
+	srf = vmw_res_to_srf(res);
+	vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo,
+			     header);
 
 	return 0;
 }

From dfe1323ab3c8a4dd5625ebfdba44dc47df84512a Mon Sep 17 00:00:00 2001
From: Ian Forbes <ian.forbes@broadcom.com>
Date: Fri, 26 Sep 2025 14:54:25 -0500
Subject: [PATCH 147/352] drm/vmwgfx: Fix Use-after-free in validation

Nodes stored in the validation duplicates hashtable come from an arena
allocator that is cleared at the end of vmw_execbuf_process. All nodes
are expected to be cleared in vmw_validation_drop_ht but this node escaped
because its resource was destroyed prematurely.

Fixes: 64ad2abfe9a6 ("drm/vmwgfx: Adapt validation code for reference-free lookups")
Reported-by: Kuzey Arda Bulut <kuzeyardabulut@gmail.com>
Signed-off-by: Ian Forbes <ian.forbes@broadcom.com>
Reviewed-by: Zack Rusin <zack.rusin@broadcom.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/r/20250926195427.1405237-1-ian.forbes@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_validation.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index 7ee93e7191c7..4d0fb71f6211 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -308,8 +308,10 @@ int vmw_validation_add_resource(struct vmw_validation_context *ctx,
 		hash_add_rcu(ctx->sw_context->res_ht, &node->hash.head, node->hash.key);
 	}
 	node->res = vmw_resource_reference_unless_doomed(res);
-	if (!node->res)
+	if (!node->res) {
+		hash_del_rcu(&node->hash.head);
 		return -ESRCH;
+	}
 
 	node->first_usage = 1;
 	if (!res->dev_priv->has_mob) {

From 228c5d44dffe8c293cd2d2f0e7ea45e64565b1c4 Mon Sep 17 00:00:00 2001
From: Ian Forbes <ian.forbes@broadcom.com>
Date: Fri, 26 Sep 2025 14:54:26 -0500
Subject: [PATCH 148/352] drm/vmwgfx: Fix copy-paste typo in validation

'entry' should be 'val' which is the loop iterator.

Fixes: 9e931f2e0970 ("drm/vmwgfx: Refactor resource validation hashtable to use linux/hashtable implementation.")
Signed-off-by: Ian Forbes <ian.forbes@broadcom.com>
Reviewed-by: Zack Rusin <zack.rusin@broadcom.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/r/20250926195427.1405237-2-ian.forbes@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_validation.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index 4d0fb71f6211..35dc94c3db39 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -638,7 +638,7 @@ void vmw_validation_drop_ht(struct vmw_validation_context *ctx)
 		hash_del_rcu(&val->hash.head);
 
 	list_for_each_entry(val, &ctx->resource_ctx_list, head)
-		hash_del_rcu(&entry->hash.head);
+		hash_del_rcu(&val->hash.head);
 
 	ctx->sw_context = NULL;
 }

From 4d920ed684392ae064af62957d6f5a90312dfaf6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sun, 5 Oct 2025 18:20:37 -0700
Subject: [PATCH 149/352] libbpf: Fix undefined behavior in
 {get,put}_unaligned_be32()

These violate aliasing rules and may be miscompiled unless
-fno-strict-aliasing is used.  Replace them with the standard memcpy()
solution.  Note that compilers know how to optimize this properly.

Fixes: 4a1c9e544b8d ("libbpf: remove linux/unaligned.h dependency for libbpf_sha256()")
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20251006012037.159295-1-ebiggers@kernel.org
---
 tools/lib/bpf/libbpf_utils.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/tools/lib/bpf/libbpf_utils.c b/tools/lib/bpf/libbpf_utils.c
index 5d66bc6ff098..ac3beae54cf6 100644
--- a/tools/lib/bpf/libbpf_utils.c
+++ b/tools/lib/bpf/libbpf_utils.c
@@ -148,16 +148,20 @@ const char *libbpf_errstr(int err)
 	}
 }
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpacked"
-#pragma GCC diagnostic ignored "-Wattributes"
-struct __packed_u32 { __u32 __val; } __attribute__((packed));
-#pragma GCC diagnostic pop
+static inline __u32 get_unaligned_be32(const void *p)
+{
+	__be32 val;
 
-#define get_unaligned_be32(p) be32_to_cpu((((struct __packed_u32 *)(p))->__val))
-#define put_unaligned_be32(v, p) do {							\
-	((struct __packed_u32 *)(p))->__val = cpu_to_be32(v);				\
-} while (0)
+	memcpy(&val, p, sizeof(val));
+	return be32_to_cpu(val);
+}
+
+static inline void put_unaligned_be32(__u32 val, void *p)
+{
+	__be32 be_val = cpu_to_be32(val);
+
+	memcpy(p, &be_val, sizeof(be_val));
+}
 
 #define SHA256_BLOCK_LENGTH 64
 #define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z)))

From 66128f4287b04aef4d4db9bf5035985ab51487d5 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 6 Oct 2025 14:33:42 +0200
Subject: [PATCH 150/352] kbuild: uapi: Strip comments before size type check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On m68k, check_sizetypes in headers_check reports:

    ./usr/include/asm/bootinfo-amiga.h:17: found __[us]{8,16,32,64} type without #include <linux/types.h>

This header file does not use any of the Linux-specific integer types,
but merely refers to them from comments, so this is a false positive.
As of commit c3a9d74ee413bdb3 ("kbuild: uapi: upgrade check_sizetypes()
warning to error"), this check was promoted to an error, breaking m68k
all{mod,yes}config builds.

Fix this by stripping simple comments before looking for Linux-specific
integer types.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Link: https://patch.msgid.link/949f096337e28d50510e970ae3ba3ec9c1342ec0.1759753998.git.geert@linux-m68k.org
[nathan: Adjust comment and remove unnecessary escaping from slashes in
         regex]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 usr/include/headers_check.pl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl
index 21c2fb9520e6..1fbc8785f96e 100755
--- a/usr/include/headers_check.pl
+++ b/usr/include/headers_check.pl
@@ -155,6 +155,8 @@ sub check_sizetypes
 	if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) {
 		check_include_typesh($included);
 	}
+	# strip single-line comments, as types may be referenced within them
+	$line =~ s@/\*.*?\*/@@;
 	if ($line =~ m/__[us](8|16|32|64)\b/) {
 		printf STDERR "$filename:$lineno: " .
 		              "found __[us]{8,16,32,64} type " .

From e7933f5b019c1daef0a138661d6e504f0259de98 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Sun, 5 Oct 2025 19:01:48 +0200
Subject: [PATCH 151/352] smb: client: Reduce the scopes for a few variables in
 two functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* cifs_lookup():
  Move the definition for the local variable “cfid” into an else branch
  so that the corresponding setting will only be performed if a NULL inode
  was detected during lookup by this function.

* cifs_d_revalidate():
  Move the definition for the local variables “inode” and “rc” into
  an if branch so that the corresponding setting will only be performed
  after a d_really_is_positive() call.

  Move the definition for the local variable “cfid” into an else branch
  so that the corresponding setting will only be performed if further data
  processing will be needed for an open_cached_dir_by_dentry() call.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Henrique Carvalho <henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/dir.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index fc67a6441c96..7472fddadd4f 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -678,7 +678,6 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	const char *full_path;
 	void *page;
 	int retry_count = 0;
-	struct cached_fid *cfid = NULL;
 
 	xid = get_xid();
 
@@ -717,6 +716,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	if (d_really_is_positive(direntry)) {
 		cifs_dbg(FYI, "non-NULL inode in lookup\n");
 	} else {
+		struct cached_fid *cfid = NULL;
+
 		cifs_dbg(FYI, "NULL inode in lookup\n");
 
 		/*
@@ -785,15 +786,13 @@ static int
 cifs_d_revalidate(struct inode *dir, const struct qstr *name,
 		  struct dentry *direntry, unsigned int flags)
 {
-	struct inode *inode = NULL;
-	struct cached_fid *cfid;
-	int rc;
-
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	if (d_really_is_positive(direntry)) {
-		inode = d_inode(direntry);
+		int rc;
+		struct inode *inode = d_inode(direntry);
+
 		if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode)))
 			CIFS_I(inode)->time = 0; /* force reval */
 
@@ -836,6 +835,7 @@ cifs_d_revalidate(struct inode *dir, const struct qstr *name,
 	} else {
 		struct cifs_sb_info *cifs_sb = CIFS_SB(dir->i_sb);
 		struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+		struct cached_fid *cfid;
 
 		if (!open_cached_dir_by_dentry(tcon, direntry->d_parent, &cfid)) {
 			/*

From 61da08ecb55264fa1e2c7b8c8a630bed716edbdb Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Mon, 6 Oct 2025 16:39:35 -0500
Subject: [PATCH 152/352] smb: client: Use common code in cifs_lookup()

Use three additional labels so that another bit of common code can be
better reused at the end of this function implementation.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/dir.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 7472fddadd4f..f64e992ec724 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -678,6 +678,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	const char *full_path;
 	void *page;
 	int retry_count = 0;
+	struct dentry *de;
 
 	xid = get_xid();
 
@@ -689,16 +690,15 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	cifs_sb = CIFS_SB(parent_dir_inode->i_sb);
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
-		free_xid(xid);
-		return ERR_CAST(tlink);
+		de = ERR_CAST(tlink);
+		goto free_xid;
 	}
 	pTcon = tlink_tcon(tlink);
 
 	rc = check_name(direntry, pTcon);
 	if (unlikely(rc)) {
-		cifs_put_tlink(tlink);
-		free_xid(xid);
-		return ERR_PTR(rc);
+		de = ERR_PTR(rc);
+		goto put_tlink;
 	}
 
 	/* can not grab the rename sem here since it would
@@ -707,10 +707,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	page = alloc_dentry_path();
 	full_path = build_path_from_dentry(direntry, page);
 	if (IS_ERR(full_path)) {
-		cifs_put_tlink(tlink);
-		free_xid(xid);
-		free_dentry_path(page);
-		return ERR_CAST(full_path);
+		de = ERR_CAST(full_path);
+		goto free_dentry_path;
 	}
 
 	if (d_really_is_positive(direntry)) {
@@ -776,10 +774,14 @@ again:
 	}
 
 out:
+	de = d_splice_alias(newInode, direntry);
+free_dentry_path:
 	free_dentry_path(page);
+put_tlink:
 	cifs_put_tlink(tlink);
+free_xid:
 	free_xid(xid);
-	return d_splice_alias(newInode, direntry);
+	return de;
 }
 
 static int

From 23f3770e1a53e6c7a553135011f547209e141e72 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 3 Oct 2025 09:34:18 +0200
Subject: [PATCH 153/352] bpf: Fix metadata_dst leak
 __bpf_redirect_neigh_v{4,6}

Cilium has a BPF egress gateway feature which forces outgoing K8s Pod
traffic to pass through dedicated egress gateways which then SNAT the
traffic in order to interact with stable IPs outside the cluster.

The traffic is directed to the gateway via vxlan tunnel in collect md
mode. A recent BPF change utilized the bpf_redirect_neigh() helper to
forward packets after the arrival and decap on vxlan, which turned out
over time that the kmalloc-256 slab usage in kernel was ever-increasing.

The issue was that vxlan allocates the metadata_dst object and attaches
it through a fake dst entry to the skb. The latter was never released
though given bpf_redirect_neigh() was merely setting the new dst entry
via skb_dst_set() without dropping an existing one first.

Fixes: b4ab31414970 ("bpf: Add redirect_neigh helper as redirect drop-in")
Reported-by: Yusuke Suzuki <yusuke.suzuki@isovalent.com>
Reported-by: Julian Wiedmann <jwi@isovalent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jordan Rife <jrife@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jordan Rife <jrife@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20251003073418.291171-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 5d1838ff1ab9..76628df1fc82 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2281,6 +2281,7 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
 		if (IS_ERR(dst))
 			goto out_drop;
 
+		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 	} else if (nh->nh_family != AF_INET6) {
 		goto out_drop;
@@ -2389,6 +2390,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
 			goto out_drop;
 		}
 
+		skb_dst_drop(skb);
 		skb_dst_set(skb, &rt->dst);
 	}
 

From 196754c2a04a8ba682b00ea7c818897295c98967 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 27 Sep 2025 15:26:05 +0300
Subject: [PATCH 154/352] irqchip/aspeed-scu-ic: Fix an IS_ERR() vs NULL check

of_iomap() doesn't return error pointers, it returns NULL.  Fix the error
checking to check for NULL pointers.

Fixes: 86cd4301c285 ("irqchip/aspeed-scu-ic: Refactor driver to support variant-based initialization")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/irqchip/irq-aspeed-scu-ic.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c
index 5584e0f82cce..bee59c8c4c93 100644
--- a/drivers/irqchip/irq-aspeed-scu-ic.c
+++ b/drivers/irqchip/irq-aspeed-scu-ic.c
@@ -215,8 +215,8 @@ static int aspeed_scu_ic_of_init_common(struct aspeed_scu_ic *scu_ic,
 	int irq, rc = 0;
 
 	scu_ic->base = of_iomap(node, 0);
-	if (IS_ERR(scu_ic->base)) {
-		rc = PTR_ERR(scu_ic->base);
+	if (!scu_ic->base) {
+		rc = -ENOMEM;
 		goto err;
 	}
 

From f75e07bf5226da640fa99a0594687c780d9bace4 Mon Sep 17 00:00:00 2001
From: Lucas Zampieri <lzampier@redhat.com>
Date: Tue, 23 Sep 2025 15:43:19 +0100
Subject: [PATCH 155/352] irqchip/sifive-plic: Avoid interrupt ID 0 handling
 during suspend/resume

According to the PLIC specification[1], global interrupt sources are
assigned small unsigned integer identifiers beginning at the value 1.
An interrupt ID of 0 is reserved to mean "no interrupt".

The current plic_irq_resume() and plic_irq_suspend() functions incorrectly
start the loop from index 0, which accesses the register space for the
reserved interrupt ID 0.

Change the loop to start from index 1, skipping the reserved
interrupt ID 0 as per the PLIC specification.

This prevents potential undefined behavior when accessing the reserved
register space during suspend/resume cycles.

Fixes: e80f0b6a2cf3 ("irqchip/irq-sifive-plic: Add syscore callbacks for hibernation")
Co-developed-by: Jia Wang <wangjia@ultrarisc.com>
Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
Co-developed-by: Charles Mirabile <cmirabil@redhat.com>
Signed-off-by: Charles Mirabile <cmirabil@redhat.com>
Signed-off-by: Lucas Zampieri <lzampier@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://github.com/riscv/riscv-plic-spec/releases/tag/1.0.0
---
 drivers/irqchip/irq-sifive-plic.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 559fda8fb3a8..cbd7697bc148 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -254,7 +254,8 @@ static int plic_irq_suspend(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++) {
+	/* irq ID 0 is reserved */
+	for (i = 1; i < priv->nr_irqs; i++) {
 		__assign_bit(i, priv->prio_save,
 			     readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID));
 	}
@@ -285,7 +286,8 @@ static void plic_irq_resume(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++) {
+	/* irq ID 0 is reserved */
+	for (i = 1; i < priv->nr_irqs; i++) {
 		index = BIT_WORD(i);
 		writel((priv->prio_save[index] & BIT_MASK(i)) ? 1 : 0,
 		       priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID);

From 15623c860c93aac71d22e7bedb7661ff2d3418de Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Mon, 29 Sep 2025 11:02:05 +0200
Subject: [PATCH 156/352] nsfs: handle inode number mismatches gracefully in
 file handles

Replace VFS_WARN_ON_ONCE() with graceful error handling when file
handles contain inode numbers that don't match the actual namespace
inode. This prevents userspace from triggering kernel warnings by
providing malformed file handles to open_by_handle_at().

The issue occurs when userspace provides a file handle with valid
namespace type and ID that successfully locates a namespace, but
specifies an incorrect inode number. Previously, this would trigger
VFS_WARN_ON_ONCE() when comparing the real inode number against the
provided value.

Since file handle data is user-controllable, inode number mismatches
should be treated as invalid input rather than kernel consistency
errors. Handle this case by returning NULL to indicate the file
handle is invalid, rather than warning about what is essentially
user input validation.

Reported-by: syzbot+9eefe09bedd093f156c2@syzkaller.appspotmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index 648dc59bef7f..79b026a36fb6 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -490,7 +490,9 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 
 		VFS_WARN_ON_ONCE(ns->ns_id != fid->ns_id);
 		VFS_WARN_ON_ONCE(ns->ns_type != fid->ns_type);
-		VFS_WARN_ON_ONCE(ns->inum != fid->ns_inum);
+
+		if (ns->inum != fid->ns_inum)
+			return NULL;
 
 		if (!__ns_ref_get(ns))
 			return NULL;

From deafd21efdd106f9744e2339e0c70c0f4ba565c3 Mon Sep 17 00:00:00 2001
From: Zhou Yuhang <zhouyuhang@kylinos.cn>
Date: Wed, 24 Sep 2025 20:21:39 +0800
Subject: [PATCH 157/352] fs: update comment in init_file()

The f_count member in struct file has been replaced by f_ref,
so update f_count to f_ref in the comment.

Signed-off-by: Zhou Yuhang <zhouyuhang@kylinos.cn>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index b223d873e48b..cd4a3db4659a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -192,7 +192,7 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	f->f_sb_err	= 0;
 
 	/*
-	 * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While
+	 * We're SLAB_TYPESAFE_BY_RCU so initialize f_ref last. While
 	 * fget-rcu pattern users need to be able to handle spurious
 	 * refcount bumps we should reinitialize the reused file first.
 	 */

From d68a29a6a229f8b4f3b19dbcd0bb02881316d642 Mon Sep 17 00:00:00 2001
From: Tong Li <djfkvcing117@gmail.com>
Date: Tue, 30 Sep 2025 19:02:58 +0800
Subject: [PATCH 158/352] rust: file: add intra-doc link for 'EBADF'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The `BadFdError` doc comment mentions the `EBADF` constant but does
not currently provide a navigation target for readers of the
generated docs. Turning the references into intra-doc links matches
the rest of the module and makes the documentation easier to
explore.

Suggested-by: Onur Özkan <work@onurozkan.dev>
Link: https://github.com/Rust-for-Linux/linux/issues/1186
Signed-off-by: Tong Li <djfkvcing117@gmail.com>
Reviewed-by: Onur Özkan <work@onurozkan.dev>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 rust/kernel/fs/file.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/fs/file.rs b/rust/kernel/fs/file.rs
index cf06e73a6da0..cd6987850332 100644
--- a/rust/kernel/fs/file.rs
+++ b/rust/kernel/fs/file.rs
@@ -448,9 +448,9 @@ impl Drop for FileDescriptorReservation {
     }
 }
 
-/// Represents the `EBADF` error code.
+/// Represents the [`EBADF`] error code.
 ///
-/// Used for methods that can only fail with `EBADF`.
+/// Used for methods that can only fail with [`EBADF`].
 #[derive(Copy, Clone, Eq, PartialEq)]
 pub struct BadFdError;
 

From 154d1e7ad9e5ce4b2aaefd3862b3dba545ad978d Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Tue, 30 Sep 2025 13:42:57 +0800
Subject: [PATCH 159/352] dax: skip read lock assertion for read-only
 filesystems

The commit 168316db3583("dax: assert that i_rwsem is held
exclusive for writes") added lock assertions to ensure proper
locking in DAX operations. However, these assertions trigger
false-positive lockdep warnings since read lock is unnecessary
on read-only filesystems(e.g., erofs).

This patch skips the read lock assertion for read-only filesystems,
eliminating the spurious warnings while maintaining the integrity
checks for writable filesystems.

Fixes: 168316db3583 ("dax: assert that i_rwsem is held exclusive for writes")
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: Christian Brauner <brauner@kernel.org>
---
 fs/dax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/dax.c b/fs/dax.c
index 89f071ba7b10..516f995a988c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1725,7 +1725,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE) {
 		lockdep_assert_held_write(&iomi.inode->i_rwsem);
 		iomi.flags |= IOMAP_WRITE;
-	} else {
+	} else if (!sb_rdonly(iomi.inode->i_sb)) {
 		lockdep_assert_held(&iomi.inode->i_rwsem);
 	}
 

From 56094ad3eaa21e6621396cc33811d8f72847a834 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 2 Oct 2025 17:55:07 +0200
Subject: [PATCH 160/352] vfs: Don't leak disconnected dentries on umount

When user calls open_by_handle_at() on some inode that is not cached, we
will create disconnected dentry for it. If such dentry is a directory,
exportfs_decode_fh_raw() will then try to connect this dentry to the
dentry tree through reconnect_path(). It may happen for various reasons
(such as corrupted fs or race with rename) that the call to
lookup_one_unlocked() in reconnect_one() will fail to find the dentry we
are trying to reconnect and instead create a new dentry under the
parent. Now this dentry will not be marked as disconnected although the
parent still may well be disconnected (at least in case this
inconsistency happened because the fs is corrupted and .. doesn't point
to the real parent directory). This creates inconsistency in
disconnected flags but AFAICS it was mostly harmless. At least until
commit f1ee616214cb ("VFS: don't keep disconnected dentries on d_anon")
which removed adding of most disconnected dentries to sb->s_anon list.
Thus after this commit cleanup of disconnected dentries implicitely
relies on the fact that dput() will immediately reclaim such dentries.
However when some leaf dentry isn't marked as disconnected, as in the
scenario described above, the reclaim doesn't happen and the dentries
are "leaked". Memory reclaim can eventually reclaim them but otherwise
they stay in memory and if umount comes first, we hit infamous "Busy
inodes after unmount" bug. Make sure all dentries created under a
disconnected parent are marked as disconnected as well.

Reported-by: syzbot+1d79ebe5383fc016cf07@syzkaller.appspotmail.com
Fixes: f1ee616214cb ("VFS: don't keep disconnected dentries on d_anon")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/dcache.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/dcache.c b/fs/dcache.c
index a067fa0a965a..035cccbc9276 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2557,6 +2557,8 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 	spin_lock(&parent->d_lock);
 	new->d_parent = dget_dlock(parent);
 	hlist_add_head(&new->d_sib, &parent->d_children);
+	if (parent->d_flags & DCACHE_DISCONNECTED)
+		new->d_flags |= DCACHE_DISCONNECTED;
 	spin_unlock(&parent->d_lock);
 
 retry:

From a779e27f24aeb679969ddd1fdd7f636e22ddbc1e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 7 Oct 2025 11:32:42 +0200
Subject: [PATCH 161/352] coredump: fix core_pattern input validation

In be1e0283021e ("coredump: don't pointlessly check and spew warnings")
we tried to fix input validation so it only happens during a write to
core_pattern. This would avoid needlessly logging a lot of warnings
during a read operation. However the logic accidently got inverted in
this commit. Fix it so the input validation only happens on write and is
skipped on read.

Fixes: be1e0283021e ("coredump: don't pointlessly check and spew warnings")
Fixes: 16195d2c7dd2 ("coredump: validate socket name as it is written")
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Yu Watanabe <watanabe.yu@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/coredump.c | 2 +-
 fs/exec.c     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/coredump.c b/fs/coredump.c
index b5fc06a092a4..5c1c381ee380 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1468,7 +1468,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
 	ssize_t retval;
 	char old_core_pattern[CORENAME_MAX_SIZE];
 
-	if (write)
+	if (!write)
 		return proc_dostring(table, write, buffer, lenp, ppos);
 
 	retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE);
diff --git a/fs/exec.c b/fs/exec.c
index 6b70c6726d31..4298e7e08d5d 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 && !write)
+	if (!error && write)
 		validate_coredump_safety();
 	return error;
 }

From e2c69490dda5d4c9f1bfbb2898989c8f3530e354 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Mon, 6 Oct 2025 13:18:57 -0700
Subject: [PATCH 162/352] ipmi: Fix handling of messages with provided receive
 message pointer

Prior to commit b52da4054ee0 ("ipmi: Rework user message limit handling"),
i_ipmi_request() used to increase the user reference counter if the receive
message is provided by the caller of IPMI API functions. This is no longer
the case. However, ipmi_free_recv_msg() is still called and decreases the
reference counter. This results in the reference counter reaching zero,
the user data pointer is released, and all kinds of interesting crashes are
seen.

Fix the problem by increasing user reference counter if the receive message
has been provided by the caller.

Fixes: b52da4054ee0 ("ipmi: Rework user message limit handling")
Reported-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Message-ID: <20251006201857.3433837-1-linux@roeck-us.net>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_msghandler.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a0b67a35a5f0..3700ab4eba3e 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -2301,8 +2301,11 @@ static int i_ipmi_request(struct ipmi_user     *user,
 	if (supplied_recv) {
 		recv_msg = supplied_recv;
 		recv_msg->user = user;
-		if (user)
+		if (user) {
 			atomic_inc(&user->nr_msgs);
+			/* The put happens when the message is freed. */
+			kref_get(&user->refcount);
+		}
 	} else {
 		recv_msg = ipmi_alloc_recv_msg(user);
 		if (IS_ERR(recv_msg))

From 7ddb711b6e0d33e0a673b49f69dff0d950ed60b9 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Tue, 7 Oct 2025 18:37:08 +0800
Subject: [PATCH 163/352] ALSA: hda/tas2781: Enable init_profile_id for device
 initialization

Optimize the time consumption of profile switching, init_profile saves
the common settings of different profiles, such as the dsp coefficients,
etc, which can greatly reduce the profile switching time comsumption and
remove the repetitive settings.

Fixes: e83dcd139e77 ("ASoC: tas2781: Add keyword "init" in profile section")
Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 4dea442d8c30..a126f04c3ed7 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -474,6 +474,12 @@ static void tasdevice_dspfw_init(void *context)
 	if (tas_priv->fmw->nr_configurations > 0)
 		tas_priv->cur_conf = 0;
 
+	/* Init common setting for different audio profiles */
+	if (tas_priv->rcabin.init_profile_id >= 0)
+		tasdevice_select_cfg_blk(tas_priv,
+			tas_priv->rcabin.init_profile_id,
+			TASDEVICE_BIN_BLK_PRE_POWER_UP);
+
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
@@ -770,6 +776,12 @@ static int tas2781_system_resume(struct device *dev)
 	tasdevice_reset(tas_hda->priv);
 	tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog);
 
+	/* Init common setting for different audio profiles */
+	if (tas_hda->priv->rcabin.init_profile_id >= 0)
+		tasdevice_select_cfg_blk(tas_hda->priv,
+			tas_hda->priv->rcabin.init_profile_id,
+			TASDEVICE_BIN_BLK_PRE_POWER_UP);
+
 	if (tas_hda->priv->playback_started)
 		tasdevice_tuning_switch(tas_hda->priv, 0);
 

From f4ace70faa8ff2890774bac86762e036a3651066 Mon Sep 17 00:00:00 2001
From: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Date: Tue, 7 Oct 2025 09:00:57 -0300
Subject: [PATCH 164/352] ALSA: usb: fpc: replace kmalloc_array followed by
 copy_from_user with memdup_array_user

Replace kmalloc_array() followed by copy_from_user() with
memdup_array_user() to improve and simplify fcp_ioctl_set_meter_map().

No functional changes intended.

Signed-off-by: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/fcp.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c
index 5ee8d8b66058..11e9a96b46ff 100644
--- a/sound/usb/fcp.c
+++ b/sound/usb/fcp.c
@@ -641,12 +641,9 @@ static int fcp_ioctl_set_meter_map(struct usb_mixer_interface *mixer,
 		return -EINVAL;
 
 	/* Allocate and copy the map data */
-	tmp_map = kmalloc_array(map.map_size, sizeof(s16), GFP_KERNEL);
-	if (!tmp_map)
-		return -ENOMEM;
-
-	if (copy_from_user(tmp_map, arg->map, map.map_size * sizeof(s16)))
-		return -EFAULT;
+	tmp_map = memdup_array_user(arg->map, map.map_size, sizeof(s16));
+	if (IS_ERR(tmp_map))
+		return PTR_ERR(tmp_map);
 
 	err = validate_meter_map(tmp_map, map.map_size, map.meter_slots);
 	if (err < 0)

From 4c4ed5e073a923fb3323022e1131cb51ad8df7a0 Mon Sep 17 00:00:00 2001
From: Valerio Setti <vsetti@baylibre.com>
Date: Tue, 7 Oct 2025 00:12:19 +0200
Subject: [PATCH 165/352] ASoC: meson: aiu-encoder-i2s: fix bit clock polarity

According to I2S specs audio data is sampled on the rising edge of the
clock and it can change on the falling one. When operating in normal mode
this SoC behaves the opposite so a clock polarity inversion is required
in this case.

This was tested on an OdroidC2 (Amlogic S905 SoC) board.

Signed-off-by: Valerio Setti <vsetti@baylibre.com>
Reviewed-by: Jerome Brunet <jbrunet@baylibre.com>
Tested-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://patch.msgid.link/20251007-fix-i2s-polarity-v1-1-86704d9cda10@baylibre.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/aiu-encoder-i2s.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/sound/soc/meson/aiu-encoder-i2s.c b/sound/soc/meson/aiu-encoder-i2s.c
index a0dd914c8ed1..3b4061508c18 100644
--- a/sound/soc/meson/aiu-encoder-i2s.c
+++ b/sound/soc/meson/aiu-encoder-i2s.c
@@ -236,8 +236,12 @@ static int aiu_encoder_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	    inv == SND_SOC_DAIFMT_IB_IF)
 		val |= AIU_CLK_CTRL_LRCLK_INVERT;
 
-	if (inv == SND_SOC_DAIFMT_IB_NF ||
-	    inv == SND_SOC_DAIFMT_IB_IF)
+	/*
+	 * The SoC changes data on the rising edge of the bitclock
+	 * so an inversion of the bitclock is required in normal mode
+	 */
+	if (inv == SND_SOC_DAIFMT_NB_NF ||
+	    inv == SND_SOC_DAIFMT_NB_IF)
 		val |= AIU_CLK_CTRL_AOCLK_INVERT;
 
 	/* Signal skew */
@@ -328,4 +332,3 @@ const struct snd_soc_dai_ops aiu_encoder_i2s_dai_ops = {
 	.startup	= aiu_encoder_i2s_startup,
 	.shutdown	= aiu_encoder_i2s_shutdown,
 };
-

From a27539810e1e61efcfdeb51777ed875dc61e9d49 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Tue, 7 Oct 2025 16:09:50 +0800
Subject: [PATCH 166/352] ASoC: rt722: add settings for rt722VB

This patch adds settings for RT722VB.

Signed-off-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20251007080950.1999411-1-shumingf@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt722-sdca-sdw.c |  2 +-
 sound/soc/codecs/rt722-sdca.c     | 14 ++++++++++++++
 sound/soc/codecs/rt722-sdca.h     |  6 ++++++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c
index 70700bdb80a1..5ea40c1b159a 100644
--- a/sound/soc/codecs/rt722-sdca-sdw.c
+++ b/sound/soc/codecs/rt722-sdca-sdw.c
@@ -21,7 +21,7 @@ static int rt722_sdca_mbq_size(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case 0x2f01 ... 0x2f0a:
 	case 0x2f35 ... 0x2f36:
-	case 0x2f50:
+	case 0x2f50 ... 0x2f52:
 	case 0x2f54:
 	case 0x2f58 ... 0x2f5d:
 	case SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0):
diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c
index 333611490ae3..79b8b7e70a33 100644
--- a/sound/soc/codecs/rt722-sdca.c
+++ b/sound/soc/codecs/rt722-sdca.c
@@ -1378,6 +1378,9 @@ static void rt722_sdca_dmic_preset(struct rt722_sdca_priv *rt722)
 		/* PHYtiming TDZ/TZD control */
 		regmap_write(rt722->regmap, 0x2f03, 0x06);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f52, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1415,6 +1418,9 @@ static void rt722_sdca_amp_preset(struct rt722_sdca_priv *rt722)
 			SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT_OT23,
 				RT722_SDCA_CTL_VENDOR_DEF, CH_08), 0x04);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f54, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1506,6 +1512,9 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722)
 		rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4,
 			0x0010);
 
+		if (rt722->hw_vid == RT722_VB)
+			regmap_write(rt722->regmap, 0x2f51, 0x00);
+
 		/* clear flag */
 		regmap_write(rt722->regmap,
 			SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0),
@@ -1516,6 +1525,7 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722)
 int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave)
 {
 	struct rt722_sdca_priv *rt722 = dev_get_drvdata(dev);
+	unsigned int val;
 
 	rt722->disable_irq = false;
 
@@ -1545,6 +1555,10 @@ int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave)
 
 	pm_runtime_get_noresume(&slave->dev);
 
+	rt722_sdca_index_read(rt722, RT722_VENDOR_REG, RT722_JD_PRODUCT_NUM, &val);
+	rt722->hw_vid = (val & 0x0f00) >> 8;
+	dev_dbg(&slave->dev, "%s hw_vid=0x%x\n", __func__, rt722->hw_vid);
+
 	rt722_sdca_dmic_preset(rt722);
 	rt722_sdca_amp_preset(rt722);
 	rt722_sdca_jack_preset(rt722);
diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h
index 3c383705dd3c..823abee9ab76 100644
--- a/sound/soc/codecs/rt722-sdca.h
+++ b/sound/soc/codecs/rt722-sdca.h
@@ -39,6 +39,7 @@ struct  rt722_sdca_priv {
 	/* For DMIC */
 	bool fu1e_dapm_mute;
 	bool fu1e_mixer_mute[4];
+	int hw_vid;
 };
 
 struct rt722_sdca_dmic_kctrl_priv {
@@ -233,6 +234,11 @@ enum rt722_sdca_jd_src {
 	RT722_JD1,
 };
 
+enum rt722_sdca_version {
+	RT722_VA,
+	RT722_VB,
+};
+
 int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave);
 int rt722_sdca_init(struct device *dev, struct regmap *regmap, struct sdw_slave *slave);
 int rt722_sdca_index_write(struct rt722_sdca_priv *rt722,

From 2f8229d53d984c6a05b71ac9e9583d4354e3b91f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 7 Oct 2025 07:46:00 -0600
Subject: [PATCH 167/352] io_uring/waitid: always prune wait queue entry in
 io_waitid_wait()

For a successful return, always remove our entry from the wait queue
entry list. Previously this was skipped if a cancelation was in
progress, but this can race with another invocation of the wait queue
entry callback.

Cc: stable@vger.kernel.org
Fixes: f31ecf671ddc ("io_uring: add IORING_OP_WAITID support")
Reported-by: syzbot+b9e83021d9c642a33d8c@syzkaller.appspotmail.com
Tested-by: syzbot+b9e83021d9c642a33d8c@syzkaller.appspotmail.com
Link: https://lore.kernel.org/io-uring/68e5195e.050a0220.256323.001f.GAE@google.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/waitid.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/io_uring/waitid.c b/io_uring/waitid.c
index 26c118f3918d..f25110fb1b12 100644
--- a/io_uring/waitid.c
+++ b/io_uring/waitid.c
@@ -230,13 +230,14 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode,
 	if (!pid_child_should_wake(wo, p))
 		return 0;
 
+	list_del_init(&wait->entry);
+
 	/* cancel is in progress */
 	if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK)
 		return 1;
 
 	req->io_task_work.func = io_waitid_cb;
 	io_req_task_work_add(req);
-	list_del_init(&wait->entry);
 	return 1;
 }
 

From beb97995b97532e1f215e3295e6843e59862f94b Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Tue, 7 Oct 2025 14:18:18 +0800
Subject: [PATCH 168/352] io_uring: use tab indentation for
 IORING_SEND_VECTORIZED comment

Be consistent with tab style of "liburing/src/include/liburing/io_uring.h".

Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a0cc1cc0dd01..263bed13473e 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -404,7 +404,7 @@ enum io_uring_op {
  *				will be	contiguous from the starting buffer ID.
  *
  * IORING_SEND_VECTORIZED	If set, SEND[_ZC] will take a pointer to a io_vec
- * 				to allow vectorized send operations.
+ *				to allow vectorized send operations.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)

From 1ed06c83506ecaaf1836ddeb7c65772ff86d8d53 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Oct 2025 11:06:25 +0200
Subject: [PATCH 169/352] block: remove bio_iov_iter_get_pages

Switch the only caller to bio_iov_iter_get_pages, and explain why it does
not have any alignment requirements.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c     | 6 +++++-
 include/linux/bio.h | 5 -----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 165f2234f00f..6cce652c7fa6 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -283,7 +283,11 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask);
 	if (!bio)
 		return -ENOMEM;
-	ret = bio_iov_iter_get_pages(bio, iter);
+	/*
+	 * No alignment requirements on our part to support arbitrary
+	 * passthrough commands.
+	 */
+	ret = bio_iov_iter_get_pages_aligned(bio, iter, 0);
 	if (ret)
 		goto out_put;
 	ret = blk_rq_append_bio(rq, bio);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a64a30131031..b01dae9506de 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -449,11 +449,6 @@ int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
 int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter,
 		unsigned len_align_mask);
 
-static inline int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
-{
-	return bio_iov_iter_get_pages_aligned(bio, iter, 0);
-}
-
 void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);

From 82dd5d763c9b718e2d655b9565e0a06a91bb83dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Oct 2025 11:06:26 +0200
Subject: [PATCH 170/352] block: rename bio_iov_iter_get_pages_aligned to
 bio_iov_iter_get_pages

Now that the bio_iov_iter_get_pages is free again, use it instead of
the more complicated now.  Also drop the unused export.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c            | 5 ++---
 block/blk-map.c        | 2 +-
 include/linux/bio.h    | 2 +-
 include/linux/blkdev.h | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 3a1a848940dd..b3a79285c278 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1316,7 +1316,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 }
 
 /**
- * bio_iov_iter_get_pages_aligned - add user or kernel pages to a bio
+ * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be added
  * @len_align_mask: the mask to align the total size to, 0 for any length
@@ -1336,7 +1336,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
  * MM encounters an error pinning the requested pages, it stops. Error
  * is returned only if 0 pages could be pinned.
  */
-int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter,
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 			   unsigned len_align_mask)
 {
 	int ret = 0;
@@ -1360,7 +1360,6 @@ int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter,
 		return bio_iov_iter_align_down(bio, iter, len_align_mask);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages_aligned);
 
 static void submit_bio_wait_endio(struct bio *bio)
 {
diff --git a/block/blk-map.c b/block/blk-map.c
index 6cce652c7fa6..60faf036fb6e 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -287,7 +287,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	 * No alignment requirements on our part to support arbitrary
 	 * passthrough commands.
 	 */
-	ret = bio_iov_iter_get_pages_aligned(bio, iter, 0);
+	ret = bio_iov_iter_get_pages(bio, iter, 0);
 	if (ret)
 		goto out_put;
 	ret = blk_rq_append_bio(rq, bio);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b01dae9506de..16c1c85613b7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -446,7 +446,7 @@ int submit_bio_wait(struct bio *bio);
 int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
 		size_t len, enum req_op op);
 
-int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter,
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 		unsigned len_align_mask);
 
 void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 066e5309bd45..c97e8b0e67b6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1876,7 +1876,7 @@ static inline int bio_split_rw_at(struct bio *bio,
 static inline int bio_iov_iter_get_bdev_pages(struct bio *bio,
 		struct iov_iter *iter, struct block_device *bdev)
 {
-	return bio_iov_iter_get_pages_aligned(bio, iter,
+	return bio_iov_iter_get_pages(bio, iter,
 					bdev_logical_block_size(bdev) - 1);
 }
 

From cb6d51a4115781fd9de6108932e866a332e38406 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Oct 2025 11:06:27 +0200
Subject: [PATCH 171/352] iomap: open code bio_iov_iter_get_bdev_pages

Prepare for passing different alignments, and to retired
bio_iov_iter_get_bdev_pages as a global helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/iomap/direct-io.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 9802b2cc29bb..5d5d63efbd57 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -433,7 +433,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
 
-		ret = bio_iov_iter_get_bdev_pages(bio, dio->submit.iter, iomap->bdev);
+		ret = bio_iov_iter_get_pages(bio, dio->submit.iter,
+				bdev_logical_block_size(iomap->bdev) - 1);
 		if (unlikely(ret)) {
 			/*
 			 * We have to stop part way through an IO. We must fall

From 506aa235f6e0baa00bf792df82a5e9f618b7a5d8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Oct 2025 11:06:28 +0200
Subject: [PATCH 172/352] block: move bio_iov_iter_get_bdev_pages to
 block/fops.c

Keep bio_iov_iter_get_bdev_pages local with the callers, as blindly
looking at the bdev logical block size is often not the best idea
unless on a block device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/fops.c           | 13 ++++++++++---
 include/linux/blkdev.h |  7 -------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index c2c0396ea9ee..5e3db9fead77 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -43,6 +43,13 @@ static bool blkdev_dio_invalid(struct block_device *bdev, struct kiocb *iocb,
 			(bdev_logical_block_size(bdev) - 1);
 }
 
+static inline int blkdev_iov_iter_get_pages(struct bio *bio,
+		struct iov_iter *iter, struct block_device *bdev)
+{
+	return bio_iov_iter_get_pages(bio, iter,
+			bdev_logical_block_size(bdev) - 1);
+}
+
 #define DIO_INLINE_BIO_VECS 4
 
 static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
@@ -78,7 +85,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_ATOMIC)
 		bio.bi_opf |= REQ_ATOMIC;
 
-	ret = bio_iov_iter_get_bdev_pages(&bio, iter, bdev);
+	ret = blkdev_iov_iter_get_pages(&bio, iter, bdev);
 	if (unlikely(ret))
 		goto out;
 	ret = bio.bi_iter.bi_size;
@@ -212,7 +219,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
 
-		ret = bio_iov_iter_get_bdev_pages(bio, iter, bdev);
+		ret = blkdev_iov_iter_get_pages(bio, iter, bdev);
 		if (unlikely(ret)) {
 			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
@@ -348,7 +355,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		 */
 		bio_iov_bvec_set(bio, iter);
 	} else {
-		ret = bio_iov_iter_get_bdev_pages(bio, iter, bdev);
+		ret = blkdev_iov_iter_get_pages(bio, iter, bdev);
 		if (unlikely(ret))
 			goto out_bio_put;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c97e8b0e67b6..d4db5039836d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1873,13 +1873,6 @@ static inline int bio_split_rw_at(struct bio *bio,
 	return bio_split_io_at(bio, lim, segs, max_bytes, lim->dma_alignment);
 }
 
-static inline int bio_iov_iter_get_bdev_pages(struct bio *bio,
-		struct iov_iter *iter, struct block_device *bdev)
-{
-	return bio_iov_iter_get_pages(bio, iter,
-					bdev_logical_block_size(bdev) - 1);
-}
-
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
 
 #endif /* _LINUX_BLKDEV_H */

From 16794e524d310780163fdd49d0bf7fac30f8dbc8 Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Tue, 5 Aug 2025 11:35:30 -0400
Subject: [PATCH 173/352] parisc: Remove spurious if statement from
 raw_copy_from_user()

Accidently introduced in commit 91428ca9320e.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
Fixes: 91428ca9320e ("parisc: Check region is readable by user in raw_copy_from_user()")
Cc: stable@vger.kernel.org # v5.12+
---
 arch/parisc/lib/memcpy.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 69d65ffab312..03165c82dfdb 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -41,7 +41,6 @@ unsigned long raw_copy_from_user(void *dst, const void __user *src,
 	mtsp(get_kernel_space(), SR_TEMP2);
 
 	/* Check region is user accessible */
-	if (start)
 	while (start < end) {
 		if (!prober_user(SR_TEMP1, start)) {
 			newlen = (start - (unsigned long) src);

From 8ec5a066f88f89bd52094ba18792b34c49dcd55a Mon Sep 17 00:00:00 2001
From: Sam James <sam@gentoo.org>
Date: Wed, 1 Oct 2025 23:58:40 +0100
Subject: [PATCH 174/352] parisc: don't reference obsolete termio struct for
 TC* constants

Similar in nature to ab107276607af90b13a5994997e19b7b9731e251. glibc-2.42
drops the legacy termio struct, but the ioctls.h header still defines some
TC* constants in terms of termio (via sizeof). Hardcode the values instead.

This fixes building Python for example, which falls over like:
  ./Modules/termios.c:1119:16: error: invalid application of 'sizeof' to incomplete type 'struct termio'

Link: https://bugs.gentoo.org/961769
Link: https://bugs.gentoo.org/962600
Co-authored-by: Stian Halseth <stian@itx.no>
Cc: stable@vger.kernel.org
Signed-off-by: Sam James <sam@gentoo.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/uapi/asm/ioctls.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h
index 82d1148c6379..74b4027a4e80 100644
--- a/arch/parisc/include/uapi/asm/ioctls.h
+++ b/arch/parisc/include/uapi/asm/ioctls.h
@@ -10,10 +10,10 @@
 #define TCSETS		_IOW('T', 17, struct termios) /* TCSETATTR */
 #define TCSETSW		_IOW('T', 18, struct termios) /* TCSETATTRD */
 #define TCSETSF		_IOW('T', 19, struct termios) /* TCSETATTRF */
-#define TCGETA		_IOR('T', 1, struct termio)
-#define TCSETA		_IOW('T', 2, struct termio)
-#define TCSETAW		_IOW('T', 3, struct termio)
-#define TCSETAF		_IOW('T', 4, struct termio)
+#define TCGETA          0x40125401
+#define TCSETA          0x80125402
+#define TCSETAW         0x80125403
+#define TCSETAF         0x80125404
 #define TCSBRK		_IO('T', 5)
 #define TCXONC		_IO('T', 6)
 #define TCFLSH		_IO('T', 7)

From 6fb2e09c3abca500ad3ef88afdd291515323d668 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 7 Oct 2025 16:56:48 +0200
Subject: [PATCH 175/352] parisc: Report emulation faults via perf

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/traps.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index b9b3d527bc90..4c7c5df80bd0 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -31,6 +31,7 @@
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
 #include <linux/kfence.h>
+#include <linux/perf_event.h>
 
 #include <asm/assembly.h>
 #include <asm/io.h>
@@ -633,6 +634,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 		/* Assist Exception Trap, i.e. floating point exception. */
 		die_if_kernel("Floating point exception", regs, 0); /* quiet */
 		__inc_irq_stat(irq_fpassist_count);
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 		handle_fpe(regs);
 		return;
 

From 912b9fd7c7775060900ad315f0ceb616f9381bc3 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 7 Oct 2025 16:57:33 +0200
Subject: [PATCH 176/352] parisc: Report software alignment faults via perf

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/unaligned.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 00e97204783e..fb64d9ce0b17 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -13,6 +13,7 @@
 #include <linux/uaccess.h>
 #include <linux/sysctl.h>
 #include <linux/unaligned.h>
+#include <linux/perf_event.h>
 #include <asm/hardirq.h>
 #include <asm/traps.h>
 #include "unaligned.h"
@@ -378,6 +379,7 @@ void handle_unaligned(struct pt_regs *regs)
 	int ret = ERR_NOTHANDLED;
 
 	__inc_irq_stat(irq_unaligned_count);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->ior);
 
 	/* log a message with pacing */
 	if (user_mode(regs)) {

From 0a98b40b8fe1bdebf3cb78924cef60af322c4437 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 7 Oct 2025 16:32:25 +0200
Subject: [PATCH 177/352] smb: client: Return a status code only as a constant
 in cifs_spnego_key_instantiate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Return a status code without storing it in an intermediate variable.

* Delete the local variable “ret” and the label “error”
  which became unnecessary with this refactoring.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_spnego.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c
index 43b86fa4d695..9891f55bac1e 100644
--- a/fs/smb/client/cifs_spnego.c
+++ b/fs/smb/client/cifs_spnego.c
@@ -24,20 +24,14 @@ static const struct cred *spnego_cred;
 static int
 cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
-	char *payload;
-	int ret;
+	char *payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL);
 
-	ret = -ENOMEM;
-	payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL);
 	if (!payload)
-		goto error;
+		return -ENOMEM;
 
 	/* attach the data */
 	key->payload.data[0] = payload;
-	ret = 0;
-
-error:
-	return ret;
+	return 0;
 }
 
 static void

From e2080b70c5851a132547bec3bd7dde847e649678 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 7 Oct 2025 17:45:28 +0200
Subject: [PATCH 178/352] smb: client: Improve unlocking of a mutex in
 cifs_get_swn_reg()

Use two additional labels so that another bit of common code can be better
reused at the end of this function implementation.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_swn.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c
index 7233c6a7e6d7..35a3e73c1958 100644
--- a/fs/smb/client/cifs_swn.c
+++ b/fs/smb/client/cifs_swn.c
@@ -313,17 +313,15 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg = cifs_find_swn_reg(tcon);
 	if (!IS_ERR(reg)) {
 		kref_get(&reg->ref_count);
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return reg;
+		goto unlock;
 	} else if (PTR_ERR(reg) != -EEXIST) {
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return reg;
+		goto unlock;
 	}
 
 	reg = kmalloc(sizeof(struct cifs_swn_reg), GFP_ATOMIC);
 	if (reg == NULL) {
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto fail_unlock;
 	}
 
 	kref_init(&reg->ref_count);
@@ -354,7 +352,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT);
 
 	reg->tcon = tcon;
-
+unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
 	return reg;
@@ -365,6 +363,7 @@ fail_idr:
 	idr_remove(&cifs_swnreg_idr, reg->id);
 fail:
 	kfree(reg);
+fail_unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 	return ERR_PTR(ret);
 }

From 7ded7d37e5f5b36b4acd74380156cf07b6640c5b Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 6 Oct 2025 14:39:56 -0700
Subject: [PATCH 179/352] scripts/Makefile.extrawarn: Respect CONFIG_WERROR /
 W=e for hostprogs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 27758d8c2583 ("kbuild: enable -Werror for hostprogs")
unconditionally enabled -Werror for the compiler, assembler, and linker
when building the host programs, as the build footprint of the host
programs is small (thus risk of build failures from warnings are low)
and that stage of the build may not have Kconfig values (thus
CONFIG_WERROR could not be used as a precondition).

While turning warnings into errors unconditionally happens in a few
places within the kernel, it can be disruptive to people who may be
building with newer compilers, such as while doing a bisect. While it is
possible to avoid this behavior by passing HOSTCFLAGS=-w or
HOSTCFLAGS=-Wno-error, it may not be the most intuitive for regular
users not intimately familiar with Kbuild.

Avoid being disruptive to the entire build by depending on the explicit
opt-in of CONFIG_WERROR or W=e to enable -Werror and the like while
building the host programs. While this means there is a small portion of
the build that does not have -Werror enabled (namely scripts/kconfig/*
and scripts/basic/fixdep), it is better than not having it altogether.

Fixes: 27758d8c2583 ("kbuild: enable -Werror for hostprogs")
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Reported-by: Askar Safin <safinaskar@gmail.com>
Closes: https://lore.kernel.org/20251005011100.1035272-1-safinaskar@gmail.com/
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Tested-by: Miguel Ojeda <ojeda@kernel.org> # Rust
Link: https://patch.msgid.link/20251006-kbuild-hostprogs-werror-fix-v1-1-23cf1ffced5c@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/Makefile.extrawarn | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 1434cb6208cb..6af392f9cd02 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -223,9 +223,11 @@ KBUILD_USERCFLAGS	+= -Werror
 KBUILD_USERLDFLAGS	+= -Wl,--fatal-warnings
 KBUILD_RUSTFLAGS	+= -Dwarnings
 
-endif
-
-# Hostprog flags are used during build bootstrapping and can not rely on CONFIG_ symbols.
+# While hostprog flags are used during build bootstrapping (thus should not
+# depend on CONFIG_ symbols), -Werror is disruptive and should be opted into.
+# Only apply -Werror to hostprogs built after the initial Kconfig stage.
 KBUILD_HOSTCFLAGS	+= -Werror
 KBUILD_HOSTLDFLAGS	+= -Wl,--fatal-warnings
 KBUILD_HOSTRUSTFLAGS	+= -Dwarnings
+
+endif

From 38492c5743f8b7213ca86f0cd72ea625af35d5ef Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Tue, 7 Oct 2025 04:46:47 +0100
Subject: [PATCH 180/352] gen_init_cpio: Ignore fsync() returning EINVAL on
 pipes

The reproducer:
echo | ./usr/gen_init_cpio /dev/stdin > /dev/null

fsync() on a pipe fd returns -EINVAL, which makes gen_init_cpio fail.
Ignore -EINVAL from fsync().

Fixes: ae18b94099b0 ("gen_init_cpio: support -o <output_file> parameter")
Cc: David Disseldorp <ddiss@suse.de>
Cc: Nicolas Schier <nsc@kernel.org>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: David Disseldorp <ddiss@suse.de>
Link: https://patch.msgid.link/20251007-gen_init_cpio-pipe-v2-1-b098ab94b58a@arista.com
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 usr/gen_init_cpio.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c
index 75e9561ba313..b7296edc6626 100644
--- a/usr/gen_init_cpio.c
+++ b/usr/gen_init_cpio.c
@@ -112,7 +112,10 @@ static int cpio_trailer(void)
 	    push_pad(padlen(offset, 512)) < 0)
 		return -1;
 
-	return fsync(outfd);
+	if (fsync(outfd) < 0 && errno != EINVAL)
+		return -1;
+
+	return 0;
 }
 
 static int cpio_mkslink(const char *name, const char *target,

From 610cb23bcc75bcd9fead3e41cbd867cccd0eb229 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 7 Oct 2025 17:08:16 +0200
Subject: [PATCH 181/352] parisc: Add initial kernel-side perf_event support

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/Kconfig                      |  3 ++
 arch/parisc/include/asm/perf_event.h     |  8 ++-
 arch/parisc/include/uapi/asm/perf_regs.h | 63 ++++++++++++++++++++++++
 arch/parisc/kernel/Makefile              |  1 +
 arch/parisc/kernel/perf_event.c          | 27 ++++++++++
 arch/parisc/kernel/perf_regs.c           | 61 +++++++++++++++++++++++
 6 files changed, 162 insertions(+), 1 deletion(-)
 create mode 100644 arch/parisc/include/uapi/asm/perf_regs.h
 create mode 100644 arch/parisc/kernel/perf_event.c
 create mode 100644 arch/parisc/kernel/perf_regs.c

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 2efa4b08b7b8..7abc5f16c280 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -31,6 +31,9 @@ config PARISC
 	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select PERF_USE_VMALLOC
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
diff --git a/arch/parisc/include/asm/perf_event.h b/arch/parisc/include/asm/perf_event.h
index 1e0fd8ba6c03..8a2925029d15 100644
--- a/arch/parisc/include/asm/perf_event.h
+++ b/arch/parisc/include/asm/perf_event.h
@@ -1,6 +1,12 @@
 #ifndef __ASM_PARISC_PERF_EVENT_H
 #define __ASM_PARISC_PERF_EVENT_H
 
-/* Empty, just to avoid compiling error */
+#include <asm/psw.h>
+
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->gr[0] = KERNEL_PSW; \
+	(regs)->iaoq[0] = (__ip); \
+	asm volatile("copy %%sp, %0\n":"=r"((regs)->gr[30])); \
+}
 
 #endif /* __ASM_PARISC_PERF_EVENT_H */
diff --git a/arch/parisc/include/uapi/asm/perf_regs.h b/arch/parisc/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..1ae687bb3d3c
--- /dev/null
+++ b/arch/parisc/include/uapi/asm/perf_regs.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_PARISC_PERF_REGS_H
+#define _UAPI_ASM_PARISC_PERF_REGS_H
+
+/* see struct user_regs_struct */
+enum perf_event_parisc_regs {
+	PERF_REG_PARISC_R0,	/* PSW is in gr[0] */
+	PERF_REG_PARISC_R1,
+	PERF_REG_PARISC_R2,
+	PERF_REG_PARISC_R3,
+	PERF_REG_PARISC_R4,
+	PERF_REG_PARISC_R5,
+	PERF_REG_PARISC_R6,
+	PERF_REG_PARISC_R7,
+	PERF_REG_PARISC_R8,
+	PERF_REG_PARISC_R9,
+	PERF_REG_PARISC_R10,
+	PERF_REG_PARISC_R11,
+	PERF_REG_PARISC_R12,
+	PERF_REG_PARISC_R13,
+	PERF_REG_PARISC_R14,
+	PERF_REG_PARISC_R15,
+	PERF_REG_PARISC_R16,
+	PERF_REG_PARISC_R17,
+	PERF_REG_PARISC_R18,
+	PERF_REG_PARISC_R19,
+	PERF_REG_PARISC_R20,
+	PERF_REG_PARISC_R21,
+	PERF_REG_PARISC_R22,
+	PERF_REG_PARISC_R23,
+	PERF_REG_PARISC_R24,
+	PERF_REG_PARISC_R25,
+	PERF_REG_PARISC_R26,
+	PERF_REG_PARISC_R27,
+	PERF_REG_PARISC_R28,
+	PERF_REG_PARISC_R29,
+	PERF_REG_PARISC_R30,
+	PERF_REG_PARISC_R31,
+
+	PERF_REG_PARISC_SR0,
+	PERF_REG_PARISC_SR1,
+	PERF_REG_PARISC_SR2,
+	PERF_REG_PARISC_SR3,
+	PERF_REG_PARISC_SR4,
+	PERF_REG_PARISC_SR5,
+	PERF_REG_PARISC_SR6,
+	PERF_REG_PARISC_SR7,
+
+	PERF_REG_PARISC_IAOQ0,
+	PERF_REG_PARISC_IAOQ1,
+	PERF_REG_PARISC_IASQ0,
+	PERF_REG_PARISC_IASQ1,
+
+	PERF_REG_PARISC_SAR,	/* CR11 */
+	PERF_REG_PARISC_IIR,	/* CR19 */
+	PERF_REG_PARISC_ISR,	/* CR20 */
+	PERF_REG_PARISC_IOR,	/* CR21 */
+	PERF_REG_PARISC_IPSW,	/* CR22 */
+
+	PERF_REG_PARISC_MAX
+};
+
+#endif /* _UAPI_ASM_PARISC_PERF_REGS_H */
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile
index d5055ba33722..9157bc8bdf41 100644
--- a/arch/parisc/kernel/Makefile
+++ b/arch/parisc/kernel/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY)	+= topology.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o perf_regs.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_KPROBES)			+= kprobes.o
 obj-$(CONFIG_KEXEC_CORE)		+= kexec.o relocate_kernel.o
diff --git a/arch/parisc/kernel/perf_event.c b/arch/parisc/kernel/perf_event.c
new file mode 100644
index 000000000000..f90b83886ab4
--- /dev/null
+++ b/arch/parisc/kernel/perf_event.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Performance event support for parisc
+ *
+ * Copyright (C) 2025 by Helge Deller <deller@gmx.de>
+ */
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <asm/unwind.h>
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+
+	struct unwind_frame_info info;
+
+	unwind_frame_init_task(&info, current, NULL);
+	while (1) {
+		if (unwind_once(&info) < 0 || info.ip == 0)
+			break;
+
+		if (!__kernel_text_address(info.ip) ||
+			perf_callchain_store(entry, info.ip))
+				return;
+	}
+}
diff --git a/arch/parisc/kernel/perf_regs.c b/arch/parisc/kernel/perf_regs.c
new file mode 100644
index 000000000000..68458e2f6197
--- /dev/null
+++ b/arch/parisc/kernel/perf_regs.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (C) 2025 by Helge Deller <deller@gmx.de> */
+
+#include <linux/perf_event.h>
+#include <linux/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	switch (idx) {
+	case PERF_REG_PARISC_R0 ... PERF_REG_PARISC_R31:
+		return regs->gr[idx - PERF_REG_PARISC_R0];
+	case PERF_REG_PARISC_SR0 ... PERF_REG_PARISC_SR7:
+		return regs->sr[idx - PERF_REG_PARISC_SR0];
+	case PERF_REG_PARISC_IASQ0 ... PERF_REG_PARISC_IASQ1:
+		return regs->iasq[idx - PERF_REG_PARISC_IASQ0];
+	case PERF_REG_PARISC_IAOQ0 ... PERF_REG_PARISC_IAOQ1:
+		return regs->iasq[idx - PERF_REG_PARISC_IAOQ0];
+	case PERF_REG_PARISC_SAR:	/* CR11 */
+		return regs->sar;
+	case PERF_REG_PARISC_IIR:	/* CR19 */
+		return regs->iir;
+	case PERF_REG_PARISC_ISR:	/* CR20 */
+		return regs->isr;
+	case PERF_REG_PARISC_IOR:	/* CR21 */
+		return regs->ior;
+	case PERF_REG_PARISC_IPSW:	/* CR22 */
+		return regs->ipsw;
+	};
+	WARN_ON_ONCE((u32)idx >= PERF_REG_PARISC_MAX);
+	return 0;
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_PARISC_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	if (!IS_ENABLED(CONFIG_64BIT))
+		return PERF_SAMPLE_REGS_ABI_32;
+
+	if (test_tsk_thread_flag(task, TIF_32BIT))
+		return PERF_SAMPLE_REGS_ABI_32;
+
+	return PERF_SAMPLE_REGS_ABI_64;
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}

From 507296328b36ffd00ec1f4fde5b8acafb7222ec7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 25 Sep 2025 20:45:21 +0200
Subject: [PATCH 182/352] drm/amdgpu: Add additional DCE6 SCL registers

Fixes: 102b2f587ac8 ("drm/amd/display: dce_transform: DCE6 Scaling Horizontal Filter Init (v2)")
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h       | 7 +++++++
 drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
index 9de01ae574c0..067eddd9c62d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
@@ -4115,6 +4115,7 @@
 #define mmSCL0_SCL_COEF_RAM_CONFLICT_STATUS 0x1B55
 #define mmSCL0_SCL_COEF_RAM_SELECT 0x1B40
 #define mmSCL0_SCL_COEF_RAM_TAP_DATA 0x1B41
+#define mmSCL0_SCL_SCALER_ENABLE 0x1B42
 #define mmSCL0_SCL_CONTROL 0x1B44
 #define mmSCL0_SCL_DEBUG 0x1B6A
 #define mmSCL0_SCL_DEBUG2 0x1B69
@@ -4144,6 +4145,7 @@
 #define mmSCL1_SCL_COEF_RAM_CONFLICT_STATUS 0x1E55
 #define mmSCL1_SCL_COEF_RAM_SELECT 0x1E40
 #define mmSCL1_SCL_COEF_RAM_TAP_DATA 0x1E41
+#define mmSCL1_SCL_SCALER_ENABLE 0x1E42
 #define mmSCL1_SCL_CONTROL 0x1E44
 #define mmSCL1_SCL_DEBUG 0x1E6A
 #define mmSCL1_SCL_DEBUG2 0x1E69
@@ -4173,6 +4175,7 @@
 #define mmSCL2_SCL_COEF_RAM_CONFLICT_STATUS 0x4155
 #define mmSCL2_SCL_COEF_RAM_SELECT 0x4140
 #define mmSCL2_SCL_COEF_RAM_TAP_DATA 0x4141
+#define mmSCL2_SCL_SCALER_ENABLE 0x4142
 #define mmSCL2_SCL_CONTROL 0x4144
 #define mmSCL2_SCL_DEBUG 0x416A
 #define mmSCL2_SCL_DEBUG2 0x4169
@@ -4202,6 +4205,7 @@
 #define mmSCL3_SCL_COEF_RAM_CONFLICT_STATUS 0x4455
 #define mmSCL3_SCL_COEF_RAM_SELECT 0x4440
 #define mmSCL3_SCL_COEF_RAM_TAP_DATA 0x4441
+#define mmSCL3_SCL_SCALER_ENABLE 0x4442
 #define mmSCL3_SCL_CONTROL 0x4444
 #define mmSCL3_SCL_DEBUG 0x446A
 #define mmSCL3_SCL_DEBUG2 0x4469
@@ -4231,6 +4235,7 @@
 #define mmSCL4_SCL_COEF_RAM_CONFLICT_STATUS 0x4755
 #define mmSCL4_SCL_COEF_RAM_SELECT 0x4740
 #define mmSCL4_SCL_COEF_RAM_TAP_DATA 0x4741
+#define mmSCL4_SCL_SCALER_ENABLE 0x4742
 #define mmSCL4_SCL_CONTROL 0x4744
 #define mmSCL4_SCL_DEBUG 0x476A
 #define mmSCL4_SCL_DEBUG2 0x4769
@@ -4260,6 +4265,7 @@
 #define mmSCL5_SCL_COEF_RAM_CONFLICT_STATUS 0x4A55
 #define mmSCL5_SCL_COEF_RAM_SELECT 0x4A40
 #define mmSCL5_SCL_COEF_RAM_TAP_DATA 0x4A41
+#define mmSCL5_SCL_SCALER_ENABLE 0x4A42
 #define mmSCL5_SCL_CONTROL 0x4A44
 #define mmSCL5_SCL_DEBUG 0x4A6A
 #define mmSCL5_SCL_DEBUG2 0x4A69
@@ -4287,6 +4293,7 @@
 #define mmSCL_COEF_RAM_CONFLICT_STATUS 0x1B55
 #define mmSCL_COEF_RAM_SELECT 0x1B40
 #define mmSCL_COEF_RAM_TAP_DATA 0x1B41
+#define mmSCL_SCALER_ENABLE 0x1B42
 #define mmSCL_CONTROL 0x1B44
 #define mmSCL_DEBUG 0x1B6A
 #define mmSCL_DEBUG2 0x1B69
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
index 2d6a598a6c25..9317a7afa621 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
@@ -8650,6 +8650,8 @@
 #define REGAMMA_LUT_INDEX__REGAMMA_LUT_INDEX__SHIFT 0x00000000
 #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK_MASK 0x00000007L
 #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK__SHIFT 0x00000000
+#define SCL_SCALER_ENABLE__SCL_SCALE_EN_MASK 0x00000001L
+#define SCL_SCALER_ENABLE__SCL_SCALE_EN__SHIFT 0x00000000
 #define SCL_ALU_CONTROL__SCL_ALU_DISABLE_MASK 0x00000001L
 #define SCL_ALU_CONTROL__SCL_ALU_DISABLE__SHIFT 0x00000000
 #define SCL_BYPASS_CONTROL__SCL_BYPASS_MODE_MASK 0x00000003L

From d60f9c45d1bff7e20ecd57492ef7a5e33c94a37c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 25 Sep 2025 20:45:22 +0200
Subject: [PATCH 183/352] drm/amd/display: Add missing DCE6
 SCL_HORZ_FILTER_INIT* SRIs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Without these, it's impossible to program these registers.

Fixes: 102b2f587ac8 ("drm/amd/display: dce_transform: DCE6 Scaling Horizontal Filter Init (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/display/dc/dce/dce_transform.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
index cbce194ec7b8..ff746fba850b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
@@ -155,6 +155,8 @@
 	SRI(SCL_COEF_RAM_TAP_DATA, SCL, id), \
 	SRI(VIEWPORT_START, SCL, id), \
 	SRI(VIEWPORT_SIZE, SCL, id), \
+	SRI(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL, id), \
+	SRI(SCL_HORZ_FILTER_INIT_CHROMA, SCL, id), \
 	SRI(SCL_HORZ_FILTER_SCALE_RATIO, SCL, id), \
 	SRI(SCL_VERT_FILTER_SCALE_RATIO, SCL, id), \
 	SRI(SCL_VERT_FILTER_INIT, SCL, id), \

From c0aa7cf49dd6cb302fe28e7183992b772cb7420c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 25 Sep 2025 20:45:23 +0200
Subject: [PATCH 184/352] drm/amd/display: Properly clear SCL_*_FILTER_CONTROL
 on DCE6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, the code would set a bit field which didn't exist
on DCE6 so it would be effectively a no-op.

Fixes: b70aaf5586f2 ("drm/amd/display: dce_transform: add DCE6 specific macros,functions")
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/dce/dce_transform.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index 2b1673d69ea8..e5c2fb134d14 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -527,8 +527,7 @@ static void dce60_transform_set_scaler(
 		if (coeffs_v != xfm_dce->filter_v || coeffs_h != xfm_dce->filter_h) {
 			/* 4. Program vertical filters */
 			if (xfm_dce->filter_v == NULL)
-				REG_SET(SCL_VERT_FILTER_CONTROL, 0,
-						SCL_V_2TAP_HARDCODE_COEF_EN, 0);
+				REG_WRITE(SCL_VERT_FILTER_CONTROL, 0);
 			program_multi_taps_filter(
 					xfm_dce,
 					data->taps.v_taps,
@@ -542,8 +541,7 @@ static void dce60_transform_set_scaler(
 
 			/* 5. Program horizontal filters */
 			if (xfm_dce->filter_h == NULL)
-				REG_SET(SCL_HORZ_FILTER_CONTROL, 0,
-						SCL_H_2TAP_HARDCODE_COEF_EN, 0);
+				REG_WRITE(SCL_HORZ_FILTER_CONTROL, 0);
 			program_multi_taps_filter(
 					xfm_dce,
 					data->taps.h_taps,

From a7dc87f3448bea5ebe054f14e861074b9c289c65 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 25 Sep 2025 20:45:24 +0200
Subject: [PATCH 185/352] drm/amd/display: Properly disable scaling on DCE6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SCL_SCALER_ENABLE can be used to enable/disable the scaler
on DCE6. Program it to 0 when scaling isn't used, 1 when used.
Additionally, clear some other registers when scaling is
disabled and program the SCL_UPDATE register as recommended.

This fixes visible glitches for users whose BIOS sets up a
mode with scaling at boot, which DC was unable to clean up.

Fixes: b70aaf5586f2 ("drm/amd/display: dce_transform: add DCE6 specific macros,functions")
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/display/dc/dce/dce_transform.c    | 15 +++++++++++----
 .../gpu/drm/amd/display/dc/dce/dce_transform.h    |  2 ++
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index e5c2fb134d14..1ab5ae9b5ea5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -154,10 +154,13 @@ static bool dce60_setup_scaling_configuration(
 	REG_SET(SCL_BYPASS_CONTROL, 0, SCL_BYPASS_MODE, 0);
 
 	if (data->taps.h_taps + data->taps.v_taps <= 2) {
-		/* Set bypass */
-
-		/* DCE6 has no SCL_MODE register, skip scale mode programming */
+		/* Disable scaler functionality */
+		REG_WRITE(SCL_SCALER_ENABLE, 0);
 
+		/* Clear registers that can cause glitches even when the scaler is off */
+		REG_WRITE(SCL_TAP_CONTROL, 0);
+		REG_WRITE(SCL_AUTOMATIC_MODE_CONTROL, 0);
+		REG_WRITE(SCL_F_SHARP_CONTROL, 0);
 		return false;
 	}
 
@@ -165,7 +168,7 @@ static bool dce60_setup_scaling_configuration(
 			SCL_H_NUM_OF_TAPS, data->taps.h_taps - 1,
 			SCL_V_NUM_OF_TAPS, data->taps.v_taps - 1);
 
-	/* DCE6 has no SCL_MODE register, skip scale mode programming */
+	REG_WRITE(SCL_SCALER_ENABLE, 1);
 
 	/* DCE6 has no SCL_BOUNDARY_MODE bit, skip replace out of bound pixels */
 
@@ -502,6 +505,8 @@ static void dce60_transform_set_scaler(
 	REG_SET(DC_LB_MEM_SIZE, 0,
 		DC_LB_MEM_SIZE, xfm_dce->lb_memory_size);
 
+	REG_WRITE(SCL_UPDATE, 0x00010000);
+
 	/* Clear SCL_F_SHARP_CONTROL value to 0 */
 	REG_WRITE(SCL_F_SHARP_CONTROL, 0);
 
@@ -564,6 +569,8 @@ static void dce60_transform_set_scaler(
 	/* DCE6 has no SCL_COEF_UPDATE_COMPLETE bit to flip to new coefficient memory */
 
 	/* DCE6 DATA_FORMAT register does not support ALPHA_EN */
+
+	REG_WRITE(SCL_UPDATE, 0);
 }
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
index ff746fba850b..eb716e8337e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
@@ -155,6 +155,7 @@
 	SRI(SCL_COEF_RAM_TAP_DATA, SCL, id), \
 	SRI(VIEWPORT_START, SCL, id), \
 	SRI(VIEWPORT_SIZE, SCL, id), \
+	SRI(SCL_SCALER_ENABLE, SCL, id), \
 	SRI(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL, id), \
 	SRI(SCL_HORZ_FILTER_INIT_CHROMA, SCL, id), \
 	SRI(SCL_HORZ_FILTER_SCALE_RATIO, SCL, id), \
@@ -592,6 +593,7 @@ struct dce_transform_registers {
 	uint32_t SCL_VERT_FILTER_SCALE_RATIO;
 	uint32_t SCL_HORZ_FILTER_INIT;
 #if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t SCL_SCALER_ENABLE;
 	uint32_t SCL_HORZ_FILTER_INIT_RGB_LUMA;
 	uint32_t SCL_HORZ_FILTER_INIT_CHROMA;
 #endif

From 0e190a0446ec517666dab4691b296a9b758e590f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 25 Sep 2025 20:45:25 +0200
Subject: [PATCH 186/352] drm/amd/display: Disable scaling on DCE6 for now
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Scaling doesn't work on DCE6 at the moment, the current
register programming produces incorrect output when using
fractional scaling (between 100-200%) on resolutions higher
than 1080p.

Disable it until we figure out how to program it properly.

Fixes: 7c15fd86aaec ("drm/amd/display: dc/dce: add initial DCE6 support (v10)")
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/display/dc/resource/dce60/dce60_resource.c    | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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 53c67ebe779f..b75be6ad64f6 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
@@ -404,13 +404,13 @@ static const struct dc_plane_cap plane_cap = {
 	},
 
 	.max_upscale_factor = {
-			.argb8888 = 16000,
+			.argb8888 = 1,
 			.nv12 = 1,
 			.fp16 = 1
 	},
 
 	.max_downscale_factor = {
-			.argb8888 = 250,
+			.argb8888 = 1,
 			.nv12 = 1,
 			.fp16 = 1
 	}

From 0c6734288566f9642037882c4cb1684d5ecc6b57 Mon Sep 17 00:00:00 2001
From: Heng Zhou <Heng.Zhou@amd.com>
Date: Fri, 26 Sep 2025 11:07:44 +0800
Subject: [PATCH 187/352] drm/amdgpu: Fix for GPU reset being blocked by KIQ
 I/O.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is some probability that reset workqueue is blocked by KIQ I/O for 10+ seconds after gpu hangs.
So we need to add a in_reset check during each KIQ register poll.

Signed-off-by: Heng Zhou <Heng.Zhou@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_gfx.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a09ccf7d8aa2..ebe2b4c68b0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1102,6 +1102,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_read;
+
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
 	}
@@ -1171,6 +1174,8 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_write;
 
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);

From 58e6fc2fb94f0f409447e5d46cf6a417b6397fbc Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Tue, 27 May 2025 11:09:53 -0400
Subject: [PATCH 188/352] drm/amdkfd: Fix kfd process ref leaking when userptr
 unmapping

kfd_lookup_process_by_pid hold the kfd process reference to ensure it
doesn't get destroyed while sending the segfault event to user space.

Calling kfd_lookup_process_by_pid as function parameter leaks the kfd
process refcount and miss the NULL pointer check if app process is
already destroyed.

Fixes: 2d274bf7099b ("amd/amdkfd: Trigger segfault for early userptr unmmapping")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 7c54fe6b0f5d..83020963dfde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2586,12 +2586,17 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			 * from the KFD, trigger a segmentation fault in VM debug mode.
 			 */
 			if (amdgpu_ttm_adev(bo->tbo.bdev)->debug_vm_userptr) {
+				struct kfd_process *p;
+
 				pr_err("Pid %d unmapped memory before destroying userptr at GPU addr 0x%llx\n",
 								pid_nr(process_info->pid), mem->va);
 
 				// Send GPU VM fault to user space
-				kfd_signal_vm_fault_event_with_userptr(kfd_lookup_process_by_pid(process_info->pid),
-								mem->va);
+				p = kfd_lookup_process_by_pid(process_info->pid);
+				if (p) {
+					kfd_signal_vm_fault_event_with_userptr(p, mem->va);
+					kfd_unref_process(p);
+				}
 			}
 
 			ret = 0;

From 7574f30337e19045f03126b4c51f525b84e5049e Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Mon, 15 Sep 2025 15:57:32 -0400
Subject: [PATCH 189/352] drm/amdkfd: Fix mmap write lock not release

If mmap write lock is taken while draining retry fault, mmap write lock
is not released because svm_range_restore_pages calls mmap_read_unlock
then returns. This causes deadlock and system hangs later because mmap
read or write lock cannot be taken.

Downgrade mmap write lock to read lock if draining retry fault fix this
bug.

Signed-off-by: Philip Yang <Philip.Yang@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_svm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 273f42e3afdd..9d72411c3379 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3045,6 +3045,8 @@ retry_write_locked:
 	if (svms->checkpoint_ts[gpuidx] != 0) {
 		if (amdgpu_ih_ts_after_or_equal(ts,  svms->checkpoint_ts[gpuidx])) {
 			pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
+			if (write_locked)
+				mmap_write_downgrade(mm);
 			r = -EAGAIN;
 			goto out_unlock_svms;
 		} else {

From c760bcda83571e07b72c10d9da175db5051ed971 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 25 Sep 2025 14:10:57 -0500
Subject: [PATCH 190/352] drm/amd: Check whether secure display TA loaded
 successfully

[Why]
Not all renoir hardware supports secure display.  If the TA is present
but the feature isn't supported it will fail to load or send commands.
This shows ERR messages to the user that make it seems like there is
a problem.

[How]
Check the resp_status of the context to see if there was an error
before trying to send any secure display commands.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1415
Signed-off-by: Mario Limonciello <mario.limonciello@amd.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 1578e4e2bf84..8c0e5d03de50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2352,7 +2352,7 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	}
 
 	ret = psp_ta_load(psp, &psp->securedisplay_context.context);
-	if (!ret) {
+	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
 	} else

From 8dbac5cf8bd55a01a8a0e792a6ed866856506f60 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <shaoyun.liu@amd.com>
Date: Wed, 24 Sep 2025 21:40:57 -0400
Subject: [PATCH 191/352] drm/amd/amdgpu: Fix the mes version that support
 inv_tlbs

MES version 0x83 is not stable to use the inv_tlbs API. Defer it to 0x84 vertsion.

Fixes: 85442bac8466 ("drm/amd/amdgpu: Fix the mes version that support inv_tlbs")
Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 404cc8c2ff2c..f4a19357ccbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -337,7 +337,7 @@ static void gmc_v12_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	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) >= 0x83) {
+	    (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x84) {
 		struct mes_inv_tlbs_pasid_input input = {0};
 		input.pasid = pasid;
 		input.flush_type = flush_type;

From b809ca91a5b7eccba065460200512f83cc87987a Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 25 Sep 2025 18:02:18 +0800
Subject: [PATCH 192/352] drm/amdgpu: Merge amdgpu_vm_set_pasid into
 amdgpu_vm_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As KFD no longer uses a separate PASID, the global amdgpu_vm_set_pasid()function is no longer necessary.
Merge its functionality directly intoamdgpu_vm_init() to simplify code flow and eliminate redundant locking.

v2: remove superflous check
  adjust amdgpu_vm_fin and remove amdgpu_vm_set_pasid (Chritian)

v3: drop amdgpu_vm_assert_locked (Chritian)

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4614
Fixes: 59e4405e9ee2 ("drm/amdgpu: revert to old status lock handling v3")
Reviewed-by: Christian König <christian.koenig@amd.com>
Suggested-by: Christian König <christian.koenig@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_kms.c | 10 +---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c  | 65 ++++++++-----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h  |  5 +-
 3 files changed, 24 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 8676400834fc..a9327472c651 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1421,14 +1421,10 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 	amdgpu_debugfs_vm_init(file_priv);
 
-	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id);
+	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id, pasid);
 	if (r)
 		goto error_pasid;
 
-	r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid);
-	if (r)
-		goto error_vm;
-
 	fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL);
 	if (!fpriv->prt_va) {
 		r = -ENOMEM;
@@ -1468,10 +1464,8 @@ error_vm:
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 error_pasid:
-	if (pasid) {
+	if (pasid)
 		amdgpu_pasid_free(pasid);
-		amdgpu_vm_set_pasid(adev, &fpriv->vm, 0);
-	}
 
 	kfree(fpriv);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 8c28e8923f02..643d2be9065b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -138,48 +138,6 @@ static void amdgpu_vm_assert_locked(struct amdgpu_vm *vm)
 	dma_resv_assert_held(vm->root.bo->tbo.base.resv);
 }
 
-/**
- * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping
- *
- * @adev: amdgpu_device pointer
- * @vm: amdgpu_vm pointer
- * @pasid: the pasid the VM is using on this GPU
- *
- * Set the pasid this VM is using on this GPU, can also be used to remove the
- * pasid by passing in zero.
- *
- */
-int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			u32 pasid)
-{
-	int r;
-
-	amdgpu_vm_assert_locked(vm);
-
-	if (vm->pasid == pasid)
-		return 0;
-
-	if (vm->pasid) {
-		r = xa_err(xa_erase_irq(&adev->vm_manager.pasids, vm->pasid));
-		if (r < 0)
-			return r;
-
-		vm->pasid = 0;
-	}
-
-	if (pasid) {
-		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm,
-					GFP_KERNEL));
-		if (r < 0)
-			return r;
-
-		vm->pasid = pasid;
-	}
-
-
-	return 0;
-}
-
 /**
  * amdgpu_vm_bo_evicted - vm_bo is evicted
  *
@@ -2554,6 +2512,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * @adev: amdgpu_device pointer
  * @vm: requested vm
  * @xcp_id: GPU partition selection id
+ * @pasid: the pasid the VM is using on this GPU
  *
  * Init @vm fields.
  *
@@ -2561,7 +2520,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int32_t xcp_id)
+		   int32_t xcp_id, uint32_t pasid)
 {
 	struct amdgpu_bo *root_bo;
 	struct amdgpu_bo_vm *root;
@@ -2638,12 +2597,26 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		dev_dbg(adev->dev, "Failed to create task info for VM\n");
 
+	/* Store new PASID in XArray (if non-zero) */
+	if (pasid != 0) {
+		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm, GFP_KERNEL));
+		if (r < 0)
+			goto error_free_root;
+
+		vm->pasid = pasid;
+	}
+
 	amdgpu_bo_unreserve(vm->root.bo);
 	amdgpu_bo_unref(&root_bo);
 
 	return 0;
 
 error_free_root:
+	/* If PASID was partially set, erase it from XArray before failing */
+	if (vm->pasid != 0) {
+		xa_erase_irq(&adev->vm_manager.pasids, vm->pasid);
+		vm->pasid = 0;
+	}
 	amdgpu_vm_pt_free_root(adev, vm);
 	amdgpu_bo_unreserve(vm->root.bo);
 	amdgpu_bo_unref(&root_bo);
@@ -2749,7 +2722,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
-	amdgpu_vm_set_pasid(adev, vm, 0);
+	/* Remove PASID mapping before destroying VM */
+	if (vm->pasid != 0) {
+		xa_erase_irq(&adev->vm_manager.pasids, vm->pasid);
+		vm->pasid = 0;
+	}
 	dma_fence_wait(vm->last_unlocked, false);
 	dma_fence_put(vm->last_unlocked);
 	dma_fence_wait(vm->last_tlb_flush, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index adc5c9161fa8..f15cef8fa58a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -503,11 +503,8 @@ extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs;
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
-int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			u32 pasid);
-
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id, uint32_t pasid);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,

From 4538a93bbbf104d7b7ce769bec48ff360bce583b Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 19 Sep 2025 11:04:44 +0530
Subject: [PATCH 193/352] drm/amd/pm: Avoid interface mismatch messaging

PMFW interface version is not used by some IP implementations like SMU
v13.0.6/12, instead rely on PMFW version checks. Avoid the log if
interface version is not used.

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.c       | 3 ++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 2 +-
 drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h               | 2 ++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 1a1f2a6b2e52..a89075e25717 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -288,7 +288,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
 	 * Considering above, we just leave user a verbal message instead
 	 * of halt driver loading.
 	 */
-	if (if_version != smu->smc_driver_if_version) {
+	if (smu->smc_driver_if_version != SMU_IGNORE_IF_VERSION &&
+	    if_version != smu->smc_driver_if_version) {
 		dev_info(adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, "
 			 "smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			 smu->smc_driver_if_version, if_version,
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 cbe5b06438c1..72ca6302da63 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
@@ -3933,7 +3933,7 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
 	smu->feature_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ?
 		smu_v13_0_12_feature_mask_map : smu_v13_0_6_feature_mask_map;
 	smu->table_map = smu_v13_0_6_table_map;
-	smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION;
+	smu->smc_driver_if_version = SMU_IGNORE_IF_VERSION;
 	smu->smc_fw_caps |= SMU_FW_CAP_RAS_PRI;
 	smu_v13_0_set_smu_mailbox_registers(smu);
 	smu_v13_0_6_set_temp_funcs(smu);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index d588f74b98de..0ae91c8b6d72 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -40,6 +40,8 @@
 #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
 #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
 
+#define SMU_IGNORE_IF_VERSION 0xFFFFFFFF
+
 #define smu_cmn_init_soft_gpu_metrics(ptr, frev, crev)                   \
 	do {                                                             \
 		typecheck(struct gpu_metrics_v##frev##_##crev *, (ptr)); \

From 1f086d2508ebe494d13fd587d1f5e2b908379efc Mon Sep 17 00:00:00 2001
From: Felix Kuehling <felix.kuehling@amd.com>
Date: Fri, 3 Oct 2025 16:05:46 -0400
Subject: [PATCH 194/352] drm/amdkfd: Fix two comments in kfd_ioctl.h

Queue read and write pointers are "to KFD", not "from KFD".

Suggested-by: Robert Liu <robert.liu@amd.com>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Robert Liu <robert.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/uapi/linux/kfd_ioctl.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 04c7d283dc7d..5d1727a6d040 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -67,8 +67,8 @@ struct kfd_ioctl_get_version_args {
 
 struct kfd_ioctl_create_queue_args {
 	__u64 ring_base_address;	/* to KFD */
-	__u64 write_pointer_address;	/* from KFD */
-	__u64 read_pointer_address;	/* from KFD */
+	__u64 write_pointer_address;	/* to KFD */
+	__u64 read_pointer_address;	/* to KFD */
 	__u64 doorbell_offset;	/* from KFD */
 
 	__u32 ring_size;		/* to KFD */

From 9b608fe94870fe46bd2c41fcda99e74dabd6bbc6 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 29 Sep 2025 17:59:26 +0530
Subject: [PATCH 195/352] drm/amdgpu: Check swus/ds for switch state save

For saving switch state, check if the GPU is having SWUS/DS
architecture. Otherwise, skip saving.

Reported-by: Roman Elshin <roman.elshin@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4602
Fixes: 1dd2fa0e00f1 ("drm/amdgpu: Save and restore switch state")
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_device.c | 23 ++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a77000c2e0bb..929936c8d87c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -7157,28 +7157,35 @@ 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);
+	struct pci_dev *swus, *swds;
 	int r;
 
-	if (!parent || parent->vendor != PCI_VENDOR_ID_ATI)
+	swds = pci_upstream_bridge(adev->pdev);
+	if (!swds || swds->vendor != PCI_VENDOR_ID_ATI ||
+	    pci_pcie_type(swds) != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+	swus = pci_upstream_bridge(swds);
+	if (!swus ||
+	    (swus->vendor != PCI_VENDOR_ID_ATI &&
+	     swus->vendor != PCI_VENDOR_ID_AMD) ||
+	    pci_pcie_type(swus) != PCI_EXP_TYPE_UPSTREAM)
 		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);
+	r = pci_save_state(swds);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(swds);
 
-	parent = pci_upstream_bridge(parent);
-	r = pci_save_state(parent);
+	r = pci_save_state(swus);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(swus);
 
-	adev->pcie_reset_ctx.swus = parent;
+	adev->pcie_reset_ctx.swus = swus;
 }
 
 static void amdgpu_device_load_switch_state(struct amdgpu_device *adev)

From 8d557eab3a396c5c0068d7b4ad920f2bf261e484 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Mon, 29 Sep 2025 16:44:28 +0800
Subject: [PATCH 196/352] drm/amdgpu: Fix general protection fault in
 amdgpu_vm_bo_reset_state_machine
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After GPU reset with VRAM loss, a general protection fault occurs
during user queue restoration when accessing vm_bo->vm after
spinlock release in amdgpu_vm_bo_reset_state_machine.

The root cause is that vm_bo points to the last entry from the
list_for_each_entry loop, but this becomes invalid after the
spinlock is released. Accessing vm_bo->vm at this point leads
to memory corruption.

Crash log shows:
[  326.981811] Oops: general protection fault, probably for non-canonical address 0x4156415741e58ac8: 0000 [#1] SMP NOPTI
[  326.981820] CPU: 13 UID: 0 PID: 1035 Comm: kworker/13:3 Tainted: G            E       6.16.0+ #25 PREEMPT(voluntary)
[  326.981826] Tainted: [E]=UNSIGNED_MODULE
[  326.981827] Hardware name: Gigabyte Technology Co., Ltd. X870E AORUS PRO ICE/X870E AORUS PRO ICE, BIOS F3i 12/19/2024
[  326.981831] Workqueue: events amdgpu_userq_restore_worker [amdgpu]
[  326.981999] RIP: 0010:amdgpu_vm_assert_locked+0x16/0x70 [amdgpu]
[  326.982094] Code: 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48 85 ff 74 45 48 8b 87 80 03 00 00 48 85 c0 74 40 <48> 8b b8 80 01 00 00 48 85 ff 74 3b 8b 05 0c b7 0e f0 85 c0 75 05
[  326.982098] RSP: 0018:ffffaa91c2a6bc20 EFLAGS: 00010206
[  326.982100] RAX: 4156415741e58948 RBX: ffff9e8f013e8330 RCX: 0000000000000000
[  326.982102] RDX: 0000000000000005 RSI: 000000001d254e88 RDI: ffffffffc144814a
[  326.982104] RBP: ffffaa91c2a6bc68 R08: 0000004c21a25674 R09: 0000000000000001
[  326.982106] R10: 0000000000000001 R11: dccaf3f2f82863fc R12: ffff9e8f013e8000
[  326.982108] R13: ffff9e8f013e8000 R14: 0000000000000000 R15: ffff9e8f09980000
[  326.982110] FS:  0000000000000000(0000) GS:ffff9e9e79995000(0000) knlGS:0000000000000000
[  326.982112] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  326.982114] CR2: 000055ed6c9caa80 CR3: 0000000797060000 CR4: 0000000000750ef0
[  326.982116] PKRU: 55555554

Reviewed-by: Christian König <christian.koenig@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_vm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 643d2be9065b..2823208d8624 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -265,7 +265,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 		vm_bo->moved = true;
 	spin_unlock(&vm->invalidated_lock);
 
-	amdgpu_vm_assert_locked(vm_bo->vm);
+	amdgpu_vm_assert_locked(vm);
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 

From bd8acfcfce7d711372c2c45f4c5e24ea650c26bf Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Sat, 4 Oct 2025 22:39:24 +0800
Subject: [PATCH 197/352] drm/amd/pm: Disable VCN queue reset on SMU v13.0.6
 due to regression

Disable VCN reset capability for the program 4 as it's
causing regressions.

Fixes: 9d20f37a106f ("drm/amd/pm: Add VCN reset support for SMU v13.0.6")
Reviewed-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/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 3 +--
 1 file changed, 1 insertion(+), 2 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 72ca6302da63..285cf7979693 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
@@ -450,8 +450,7 @@ 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 == 0) && (fw_ver >= 0x00558200)) ||
-	    ((pgm == 4) && (fw_ver >= 0x04557100)))
+	if ((pgm == 0) && (fw_ver >= 0x00558200))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
 }
 

From ddbfac152830e38d488ff8e45ab7eaf5d72f8527 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 2 Oct 2025 23:00:45 +0200
Subject: [PATCH 198/352] drm/amd/display: Fix unsafe uses of kernel mode FPU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The point of isolating code that uses kernel mode FPU in separate
compilation units is to ensure that even implicit uses of, e.g., SIMD
registers for spilling occur only in a context where this is permitted,
i.e., from inside a kernel_fpu_begin/end block.

This is important on arm64, which uses -mgeneral-regs-only to build all
kernel code, with the exception of such compilation units where FP or
SIMD registers are expected to be used. Given that the compiler may
invent uses of FP/SIMD anywhere in such a unit, none of its code may be
accessible from outside a kernel_fpu_begin/end block.

This means that all callers into such compilation units must use the
DC_FP start/end macros, which must not occur there themselves. For
robustness, all functions with external linkage that reside there should
call dc_assert_fp_enabled() to assert that the FPU context was set up
correctly.

Fix this for the DCN35, DCN351 and DCN36 implementations.

Cc: Austin Zheng <austin.zheng@amd.com>
Cc: Jun Lei <jun.lei@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Leo Li <sunpeng.li@amd.com>
Cc: Rodrigo Siqueira <siqueira@igalia.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dml/dcn31/dcn31_fpu.c    |  4 ++++
 .../drm/amd/display/dc/dml/dcn35/dcn35_fpu.c    |  6 ++++--
 .../drm/amd/display/dc/dml/dcn351/dcn351_fpu.c  |  4 ++--
 .../display/dc/resource/dcn35/dcn35_resource.c  | 16 +++++++++++++++-
 .../dc/resource/dcn351/dcn351_resource.c        | 17 ++++++++++++++++-
 .../display/dc/resource/dcn36/dcn36_resource.c  | 16 +++++++++++++++-
 6 files changed, 56 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index 17a21bcbde17..1a28061bb9ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -808,6 +808,8 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 
 int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc)
 {
+	dc_assert_fp_enabled();
+
 	return soc->clock_limits[0].dispclk_mhz * 10000.0 / (1.0 + soc->dcn_downspread_percent / 100.0);
 }
 
@@ -815,6 +817,8 @@ int dcn_get_approx_det_segs_required_for_pstate(
 		struct _vcs_dpi_soc_bounding_box_st *soc,
 		int pix_clk_100hz, int bpp, int seg_size_kb)
 {
+	dc_assert_fp_enabled();
+
 	/* Roughly calculate required crb to hide latency. In practice there is slightly
 	 * more buffer available for latency hiding
 	 */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index c9dd920744c9..817a370e80a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -445,6 +445,8 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 	bool upscaled = false;
 	const unsigned int max_allowed_vblank_nom = 1023;
 
+	dc_assert_fp_enabled();
+
 	dcn31_populate_dml_pipes_from_context(dc, context, pipes,
 					      validate_mode);
 
@@ -498,9 +500,7 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 
-		DC_FP_START();
 		dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt);
-		DC_FP_END();
 
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
 		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
@@ -581,6 +581,8 @@ void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context)
 	unsigned int i, plane_count = 0;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
+	dc_assert_fp_enabled();
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index 8cda18ce1a76..77023b619f1e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -478,6 +478,8 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc,
 	bool upscaled = false;
 	const unsigned int max_allowed_vblank_nom = 1023;
 
+	dc_assert_fp_enabled();
+
 	dcn31_populate_dml_pipes_from_context(dc, context, pipes,
 					      validate_mode);
 
@@ -531,9 +533,7 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 
-		DC_FP_START();
 		dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt);
-		DC_FP_END();
 
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
 		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 07552445e424..fff57f23f4f7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -1760,6 +1760,20 @@ enum dc_status dcn35_patch_unknown_plane_state(struct dc_plane_state *plane_stat
 }
 
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+}
+
 static struct resource_funcs dcn35_res_pool_funcs = {
 	.destroy = dcn35_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1770,7 +1784,7 @@ static struct resource_funcs dcn35_res_pool_funcs = {
 	.validate_bandwidth = dcn35_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index cb0478a9a34d..0abd163b425e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -1732,6 +1732,21 @@ static enum dc_status dcn351_validate_bandwidth(struct dc *dc,
 	return out ? DC_OK : DC_FAIL_BANDWIDTH_VALIDATE;
 }
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn351_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+
+}
+
 static struct resource_funcs dcn351_res_pool_funcs = {
 	.destroy = dcn351_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1742,7 +1757,7 @@ static struct resource_funcs dcn351_res_pool_funcs = {
 	.validate_bandwidth = dcn351_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn351_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
index 126090c9bb8a..ca125ee6c2fb 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
@@ -1734,6 +1734,20 @@ static enum dc_status dcn35_validate_bandwidth(struct dc *dc,
 }
 
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+}
+
 static struct resource_funcs dcn36_res_pool_funcs = {
 	.destroy = dcn36_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1744,7 +1758,7 @@ static struct resource_funcs dcn36_res_pool_funcs = {
 	.validate_bandwidth = dcn35_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,

From a107aeb6a2150dd552673caefc771e2222d584de Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Mon, 6 Oct 2025 12:45:25 +0200
Subject: [PATCH 199/352] drm/amdgpu: partially revert "revert to old status
 lock handling v3"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The CI systems are pointing out list corruptions, so we still need to
fix something here.

Keep the asserts, but revert the lock changes for now.

Fixes: 59e4405e9ee2 ("drm/amdgpu: revert to old status lock handling v3")
Signed-off-by: Christian König <christian.koenig@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_userq.c |   8 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    | 146 ++++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h    |  15 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c |   4 +
 4 files changed, 105 insertions(+), 68 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 48e0932f5b62..1add21160d21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -726,12 +726,12 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 	struct amdgpu_bo *bo;
 	int ret;
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated,
 					 struct amdgpu_bo_va,
 					 base.vm_status);
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		bo = bo_va->base.bo;
 		ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 2);
@@ -748,9 +748,9 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 		if (ret)
 			return ret;
 
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 2823208d8624..c1a801203949 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -153,10 +153,12 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
 
 	vm_bo->moved = true;
 	amdgpu_vm_assert_locked(vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	if (bo->tbo.type == ttm_bo_type_kernel)
 		list_move(&vm_bo->vm_status, &vm->evicted);
 	else
 		list_move_tail(&vm_bo->vm_status, &vm->evicted);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 /**
  * amdgpu_vm_bo_moved - vm_bo is moved
@@ -169,7 +171,9 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -183,7 +187,9 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+	spin_unlock(&vm_bo->vm->status_lock);
 	vm_bo->moved = false;
 }
 
@@ -197,9 +203,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
 {
-	spin_lock(&vm_bo->vm->invalidated_lock);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated);
-	spin_unlock(&vm_bo->vm->invalidated_lock);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -212,9 +218,10 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
 {
-	amdgpu_vm_assert_locked(vm_bo->vm);
 	vm_bo->moved = true;
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -228,10 +235,13 @@ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
-	if (vm_bo->bo->parent)
+	if (vm_bo->bo->parent) {
+		spin_lock(&vm_bo->vm->status_lock);
 		list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
-	else
+		spin_unlock(&vm_bo->vm->status_lock);
+	} else {
 		amdgpu_vm_bo_idle(vm_bo);
+	}
 }
 
 /**
@@ -245,7 +255,9 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->done);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -259,13 +271,13 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 {
 	struct amdgpu_vm_bo_base *vm_bo, *tmp;
 
-	spin_lock(&vm->invalidated_lock);
+	amdgpu_vm_assert_locked(vm);
+
+	spin_lock(&vm->status_lock);
 	list_splice_init(&vm->done, &vm->invalidated);
 	list_for_each_entry(vm_bo, &vm->invalidated, vm_status)
 		vm_bo->moved = true;
-	spin_unlock(&vm->invalidated_lock);
 
-	amdgpu_vm_assert_locked(vm);
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 
@@ -275,13 +287,14 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 		else if (bo->parent)
 			list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
 	}
+	spin_unlock(&vm->status_lock);
 }
 
 /**
  * amdgpu_vm_update_shared - helper to update shared memory stat
  * @base: base structure for tracking BO usage in a VM
  *
- * Takes the vm stats_lock and updates the shared memory stat. If the basic
+ * Takes the vm status_lock and updates the shared memory stat. If the basic
  * stat changed (e.g. buffer was moved) amdgpu_vm_update_stats need to be called
  * as well.
  */
@@ -294,7 +307,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base)
 	bool shared;
 
 	dma_resv_assert_held(bo->tbo.base.resv);
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base);
 	if (base->shared != shared) {
 		base->shared = shared;
@@ -306,7 +319,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base)
 			vm->stats[bo_memtype].drm.private += size;
 		}
 	}
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -331,11 +344,11 @@ void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo)
  *        be bo->tbo.resource
  * @sign: if we should add (+1) or subtract (-1) from the stat
  *
- * Caller need to have the vm stats_lock held. Useful for when multiple update
+ * Caller need to have the vm status_lock held. Useful for when multiple update
  * need to happen at the same time.
  */
 static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base,
-					  struct ttm_resource *res, int sign)
+			    struct ttm_resource *res, int sign)
 {
 	struct amdgpu_vm *vm = base->vm;
 	struct amdgpu_bo *bo = base->bo;
@@ -359,8 +372,7 @@ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base,
 		 */
 		if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE)
 			vm->stats[res_memtype].drm.purgeable += size;
-		if (!(bo->preferred_domains &
-		      amdgpu_mem_type_to_domain(res_memtype)))
+		if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(res_memtype)))
 			vm->stats[bo_memtype].evicted += size;
 	}
 }
@@ -379,9 +391,9 @@ void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base,
 {
 	struct amdgpu_vm *vm = base->vm;
 
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	amdgpu_vm_update_stats_locked(base, res, sign);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -407,10 +419,10 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 	base->next = bo->vm_bo;
 	bo->vm_bo = base;
 
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	base->shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base);
 	amdgpu_vm_update_stats_locked(base, bo->tbo.resource, +1);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 
 	if (!amdgpu_vm_is_bo_always_valid(vm, bo))
 		return;
@@ -469,10 +481,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec,
 	int ret;
 
 	/* We can only trust prev->next while holding the lock */
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	while (!list_is_head(prev->next, &vm->done)) {
 		bo_va = list_entry(prev->next, typeof(*bo_va), base.vm_status);
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		bo = bo_va->base.bo;
 		if (bo) {
@@ -480,10 +492,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec,
 			if (unlikely(ret))
 				return ret;
 		}
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 		prev = prev->next;
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
@@ -579,7 +591,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		       void *param)
 {
 	uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
-	struct amdgpu_vm_bo_base *bo_base, *tmp;
+	struct amdgpu_vm_bo_base *bo_base;
 	struct amdgpu_bo *bo;
 	int r;
 
@@ -592,7 +604,13 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			return r;
 	}
 
-	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->evicted)) {
+		bo_base = list_first_entry(&vm->evicted,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
+
 		bo = bo_base->bo;
 
 		r = validate(param, bo);
@@ -605,21 +623,26 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			vm->update_funcs->map_table(to_amdgpu_bo_vm(bo));
 			amdgpu_vm_bo_relocated(bo_base);
 		}
+		spin_lock(&vm->status_lock);
 	}
+	while (ticket && !list_empty(&vm->evicted_user)) {
+		bo_base = list_first_entry(&vm->evicted_user,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
 
-	if (ticket) {
-		list_for_each_entry_safe(bo_base, tmp, &vm->evicted_user,
-					 vm_status) {
-			bo = bo_base->bo;
-			dma_resv_assert_held(bo->tbo.base.resv);
+		bo = bo_base->bo;
+		dma_resv_assert_held(bo->tbo.base.resv);
 
-			r = validate(param, bo);
-			if (r)
-				return r;
+		r = validate(param, bo);
+		if (r)
+			return r;
 
-			amdgpu_vm_bo_invalidated(bo_base);
-		}
+		amdgpu_vm_bo_invalidated(bo_base);
+
+		spin_lock(&vm->status_lock);
 	}
+	spin_unlock(&vm->status_lock);
 
 	amdgpu_vm_eviction_lock(vm);
 	vm->evicting = false;
@@ -648,7 +671,9 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 	ret = !vm->evicting;
 	amdgpu_vm_eviction_unlock(vm);
 
+	spin_lock(&vm->status_lock);
 	ret &= list_empty(&vm->evicted);
+	spin_unlock(&vm->status_lock);
 
 	spin_lock(&vm->immediate.lock);
 	ret &= !vm->immediate.stopped;
@@ -939,13 +964,18 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm, bool immediate)
 {
 	struct amdgpu_vm_update_params params;
-	struct amdgpu_vm_bo_base *entry, *tmp;
+	struct amdgpu_vm_bo_base *entry;
 	bool flush_tlb_needed = false;
+	LIST_HEAD(relocated);
 	int r, idx;
 
 	amdgpu_vm_assert_locked(vm);
 
-	if (list_empty(&vm->relocated))
+	spin_lock(&vm->status_lock);
+	list_splice_init(&vm->relocated, &relocated);
+	spin_unlock(&vm->status_lock);
+
+	if (list_empty(&relocated))
 		return 0;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx))
@@ -961,7 +991,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	list_for_each_entry(entry, &vm->relocated, vm_status) {
+	list_for_each_entry(entry, &relocated, vm_status) {
 		/* vm_flush_needed after updating moved PDEs */
 		flush_tlb_needed |= entry->moved;
 
@@ -977,7 +1007,9 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (flush_tlb_needed)
 		atomic64_inc(&vm->tlb_seq);
 
-	list_for_each_entry_safe(entry, tmp, &vm->relocated, vm_status) {
+	while (!list_empty(&relocated)) {
+		entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base,
+					 vm_status);
 		amdgpu_vm_bo_idle(entry);
 	}
 
@@ -1204,9 +1236,9 @@ error_free:
 void amdgpu_vm_get_memory(struct amdgpu_vm *vm,
 			  struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM])
 {
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	memcpy(stats, vm->stats, sizeof(*stats) * __AMDGPU_PL_NUM);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -1573,24 +1605,29 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 			   struct amdgpu_vm *vm,
 			   struct ww_acquire_ctx *ticket)
 {
-	struct amdgpu_bo_va *bo_va, *tmp;
+	struct amdgpu_bo_va *bo_va;
 	struct dma_resv *resv;
 	bool clear, unlock;
 	int r;
 
-	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->moved)) {
+		bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va,
+					 base.vm_status);
+		spin_unlock(&vm->status_lock);
+
 		/* Per VM BOs never need to bo cleared in the page tables */
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
+		spin_lock(&vm->status_lock);
 	}
 
-	spin_lock(&vm->invalidated_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va,
 					 base.vm_status);
 		resv = bo_va->base.bo->tbo.base.resv;
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		/* Try to reserve the BO to avoid clearing its ptes */
 		if (!adev->debug_vm && dma_resv_trylock(resv)) {
@@ -1622,9 +1659,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		     bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM))
 			amdgpu_vm_bo_evicted_user(&bo_va->base);
 
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
@@ -2153,9 +2190,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev,
 		}
 	}
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	list_del(&bo_va->base.vm_status);
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
@@ -2263,10 +2300,10 @@ void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem,
 	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
 
-		spin_lock(&vm->stats_lock);
+		spin_lock(&vm->status_lock);
 		amdgpu_vm_update_stats_locked(bo_base, bo->tbo.resource, -1);
 		amdgpu_vm_update_stats_locked(bo_base, new_mem, +1);
-		spin_unlock(&vm->stats_lock);
+		spin_unlock(&vm->status_lock);
 	}
 
 	amdgpu_vm_bo_invalidate(bo, evicted);
@@ -2534,12 +2571,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	INIT_LIST_HEAD(&vm->relocated);
 	INIT_LIST_HEAD(&vm->moved);
 	INIT_LIST_HEAD(&vm->idle);
-	spin_lock_init(&vm->invalidated_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
+	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->done);
 	INIT_KFIFO(vm->faults);
-	spin_lock_init(&vm->stats_lock);
 
 	r = amdgpu_vm_init_entities(adev, vm);
 	if (r)
@@ -3015,6 +3051,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 
 	amdgpu_vm_assert_locked(vm);
 
+	spin_lock(&vm->status_lock);
 	seq_puts(m, "\tIdle BOs:\n");
 	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) {
 		if (!bo_va->base.bo)
@@ -3052,13 +3089,11 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 	id = 0;
 
 	seq_puts(m, "\tInvalidated BOs:\n");
-	spin_lock(&vm->invalidated_lock);
 	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) {
 		if (!bo_va->base.bo)
 			continue;
 		total_invalidated += amdgpu_bo_print_info(id++,	bo_va->base.bo, m);
 	}
-	spin_unlock(&vm->invalidated_lock);
 	total_invalidated_objs = id;
 	id = 0;
 
@@ -3068,6 +3103,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 			continue;
 		total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
 	}
+	spin_unlock(&vm->status_lock);
 	total_done_objs = id;
 
 	seq_printf(m, "\tTotal idle size:        %12lld\tobjs:\t%d\n", total_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index f15cef8fa58a..cf0ec94e8a07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -203,11 +203,11 @@ struct amdgpu_vm_bo_base {
 	/* protected by bo being reserved */
 	struct amdgpu_vm_bo_base	*next;
 
-	/* protected by vm reservation and invalidated_lock */
+	/* protected by vm status_lock */
 	struct list_head		vm_status;
 
 	/* if the bo is counted as shared in mem stats
-	 * protected by vm BO being reserved */
+	 * protected by vm status_lock */
 	bool				shared;
 
 	/* protected by the BO being reserved */
@@ -343,8 +343,10 @@ struct amdgpu_vm {
 	bool			evicting;
 	unsigned int		saved_flags;
 
-	/* Memory statistics for this vm, protected by stats_lock */
-	spinlock_t		stats_lock;
+	/* Lock to protect vm_bo add/del/move on all lists of vm */
+	spinlock_t		status_lock;
+
+	/* Memory statistics for this vm, protected by status_lock */
 	struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM];
 
 	/*
@@ -352,8 +354,6 @@ struct amdgpu_vm {
 	 * PDs, PTs or per VM BOs. The state transits are:
 	 *
 	 * evicted -> relocated (PDs, PTs) or moved (per VM BOs) -> idle
-	 *
-	 * Lists are protected by the root PD dma_resv lock.
 	 */
 
 	/* Per-VM and PT BOs who needs a validation */
@@ -374,10 +374,7 @@ struct amdgpu_vm {
 	 * state transits are:
 	 *
 	 * evicted_user or invalidated -> done
-	 *
-	 * Lists are protected by the invalidated_lock.
 	 */
-	spinlock_t		invalidated_lock;
 
 	/* BOs for user mode queues that need a validation */
 	struct list_head	evicted_user;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 7a4c12ff9b18..f794fb1cc06e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -543,7 +543,9 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 	entry->bo->vm_bo = NULL;
 	ttm_bo_set_bulk_move(&entry->bo->tbo, NULL);
 
+	spin_lock(&entry->vm->status_lock);
 	list_del(&entry->vm_status);
+	spin_unlock(&entry->vm->status_lock);
 	amdgpu_bo_unref(&entry->bo);
 }
 
@@ -587,6 +589,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params,
 	struct amdgpu_vm_pt_cursor seek;
 	struct amdgpu_vm_bo_base *entry;
 
+	spin_lock(&params->vm->status_lock);
 	for_each_amdgpu_vm_pt_dfs_safe(params->adev, params->vm, cursor, seek, entry) {
 		if (entry && entry->bo)
 			list_move(&entry->vm_status, &params->tlb_flush_waitlist);
@@ -594,6 +597,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params,
 
 	/* enter start node now */
 	list_move(&cursor->entry->vm_status, &params->tlb_flush_waitlist);
+	spin_unlock(&params->vm->status_lock);
 }
 
 /**

From 2e97663760e5fb7ee14f399c68e57b894f01e505 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 6 Oct 2025 10:39:03 +0530
Subject: [PATCH 200/352] drm/amdgpu: Report individual reset error

If reinitialization of one of the GPUs fails after reset, it logs
failure on all subsequent GPUs eventhough they have resumed
successfully.

A sample log where only device at 0000:95:00.0 had a failure -

	amdgpu 0000:15:00.0: amdgpu: GPU reset(19) succeeded!
	amdgpu 0000:65:00.0: amdgpu: GPU reset(19) succeeded!
	amdgpu 0000:75:00.0: amdgpu: GPU reset(19) succeeded!
	amdgpu 0000:85:00.0: amdgpu: GPU reset(19) succeeded!
	amdgpu 0000:95:00.0: amdgpu: GPU reset(19) failed
	amdgpu 0000:e5:00.0: amdgpu: GPU reset(19) failed
	amdgpu 0000:f5:00.0: amdgpu: GPU reset(19) failed
	amdgpu 0000:05:00.0: amdgpu: GPU reset(19) failed
	amdgpu 0000:15:00.0: amdgpu: GPU reset end with ret = -5

To avoid confusion, report the error for each device
separately and return the first error as the overall result.

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_device.c | 25 +++++++++++++---------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 929936c8d87c..7a899fb4de29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6389,23 +6389,28 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 
-		if (tmp_adev->asic_reset_res)
-			r = tmp_adev->asic_reset_res;
-
-		tmp_adev->asic_reset_res = 0;
-
-		if (r) {
+		if (tmp_adev->asic_reset_res) {
 			/* bad news, how to tell it to userspace ?
 			 * for ras error, we should report GPU bad status instead of
 			 * reset failure
 			 */
 			if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
 			    !amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
-				dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
-					atomic_read(&tmp_adev->gpu_reset_counter));
-			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+				dev_info(
+					tmp_adev->dev,
+					"GPU reset(%d) failed with error %d \n",
+					atomic_read(
+						&tmp_adev->gpu_reset_counter),
+					tmp_adev->asic_reset_res);
+			amdgpu_vf_error_put(tmp_adev,
+					    AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0,
+					    tmp_adev->asic_reset_res);
+			if (!r)
+				r = tmp_adev->asic_reset_res;
+			tmp_adev->asic_reset_res = 0;
 		} else {
-			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n",
+				 atomic_read(&tmp_adev->gpu_reset_counter));
 			if (amdgpu_acpi_smart_shift_update(tmp_adev,
 							   AMDGPU_SS_DEV_D0))
 				dev_warn(tmp_adev->dev,

From 5949e7c4890c3cf65e783c83c355b95e21f10dba Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Wed, 24 Sep 2025 14:37:01 -0400
Subject: [PATCH 201/352] drm/amd/display: Enable Dynamic DTBCLK Switch

[WHAT]
Since dcn35, DTBCLK can be disabled when no DP2 sink connected for
power saving purpose.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Signed-off-by: Alex Hung <alex.hung@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, 4 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 8e1622bf7a42..0d03e324d5b9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2000,6 +2000,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.flags.disable_ips_in_vpb = 0;
 
+	/* DCN35 and above supports dynamic DTBCLK switch */
+	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 5, 0))
+		init_data.flags.allow_0_dtb_clk = true;
+
 	/* Enable DWB for tested platforms only */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;

From d07e142641417e67f3bfc9d8ba3da8a69c39cfcd Mon Sep 17 00:00:00 2001
From: Jesse Agate <jesse.agate@amd.com>
Date: Fri, 13 Jun 2025 14:20:53 -0400
Subject: [PATCH 202/352] drm/amd/display: Incorrect Mirror Cositing

[WHY]
hinit/vinit are incorrect in the case of mirroring.

[HOW]
Cositing sign must be flipped when image is mirrored in the vertical
or horizontal direction.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Samson Tam <samson.tam@amd.com>
Signed-off-by: Jesse Agate <jesse.agate@amd.com>
Signed-off-by: Brendan Leder <breleder@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
index 55b929ca7982..b1fb0f8a253a 100644
--- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
+++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
@@ -641,16 +641,16 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in,
 		/* this gives the direction of the cositing (negative will move
 		 * left, right otherwise)
 		 */
-		int sign = 1;
+		int h_sign = flip_horz_scan_dir ? -1 : 1;
+		int v_sign = flip_vert_scan_dir ? -1 : 1;
 
 		switch (spl_in->basic_in.cositing) {
-
 		case CHROMA_COSITING_TOPLEFT:
-			init_adj_h = spl_fixpt_from_fraction(sign, 4);
-			init_adj_v = spl_fixpt_from_fraction(sign, 4);
+			init_adj_h = spl_fixpt_from_fraction(h_sign, 4);
+			init_adj_v = spl_fixpt_from_fraction(v_sign, 4);
 			break;
 		case CHROMA_COSITING_LEFT:
-			init_adj_h = spl_fixpt_from_fraction(sign, 4);
+			init_adj_h = spl_fixpt_from_fraction(h_sign, 4);
 			init_adj_v = spl_fixpt_zero;
 			break;
 		case CHROMA_COSITING_NONE:

From ce47f7498598f4cf8729a6b93722c98814385e78 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Sun, 5 Oct 2025 20:36:33 +0200
Subject: [PATCH 203/352] smb: client: Use common code in cifs_do_create()

Use a label once more so that a bit of common code can be better reused
at the end of this function implementation.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Enzo Matsumiya <ematsumiya@suse.de>
Reviewed-by: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/dir.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index f64e992ec724..da5597dbf5b9 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -200,8 +200,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 
 	full_path = build_path_from_dentry(direntry, page);
 	if (IS_ERR(full_path)) {
-		free_dentry_path(page);
-		return PTR_ERR(full_path);
+		rc = PTR_ERR(full_path);
+		goto out;
 	}
 
 	/* If we're caching, we need to be able to fill in around partial writes. */

From 4468490251c0392e0c87a3f1c1c1585a89f6ffa6 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 7 Oct 2025 18:25:27 +0200
Subject: [PATCH 204/352] smb: client: Return directly after a failed
 genlmsg_new() in cifs_swn_send_register_message()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Return directly after a call of the function “genlmsg_new” failed
  at the beginning.

* Delete the label “fail” which became unnecessary
  with this refactoring.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_swn.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c
index 35a3e73c1958..68a1f87c446d 100644
--- a/fs/smb/client/cifs_swn.c
+++ b/fs/smb/client/cifs_swn.c
@@ -82,10 +82,8 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 	int ret;
 
 	skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (skb == NULL) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	if (!skb)
+		return -ENOMEM;
 
 	hdr = genlmsg_put(skb, 0, 0, &cifs_genl_family, 0, CIFS_GENL_CMD_SWN_REGISTER);
 	if (hdr == NULL) {
@@ -172,7 +170,6 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 nlmsg_fail:
 	genlmsg_cancel(skb, hdr);
 	nlmsg_free(skb);
-fail:
 	return ret;
 }
 

From e4bea919584ff292c9156cf7d641a2ab3cbe27b0 Mon Sep 17 00:00:00 2001
From: Shuhao Fu <sfual@cse.ust.hk>
Date: Wed, 8 Oct 2025 00:17:09 +0800
Subject: [PATCH 205/352] drm/nouveau: fix bad ret code in nouveau_bo_move_prep

In `nouveau_bo_move_prep`, if `nouveau_mem_map` fails, an error code
should be returned. Currently, it returns zero even if vmm addr is not
correctly mapped.

Cc: stable@vger.kernel.org
Reviewed-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Shuhao Fu <sfual@cse.ust.hk>
Fixes: 9ce523cc3bf2 ("drm/nouveau: separate buffer object backing memory from nvkm structures")
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index b96f0555ca14..f26562eafffc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -929,7 +929,7 @@ done:
 		nvif_vmm_put(vmm, &old_mem->vma[1]);
 		nvif_vmm_put(vmm, &old_mem->vma[0]);
 	}
-	return 0;
+	return ret;
 }
 
 static int

From fa02d505a3ef7c5c55b7b2aee1df2bdc178ce1ad Mon Sep 17 00:00:00 2001
From: Umang Jain <uajain@igalia.com>
Date: Mon, 29 Sep 2025 13:10:24 +0530
Subject: [PATCH 206/352] MAINTAINERS, .mailmap: update Umang's email address

Map my new professional email address in .mailmap and also update
the IMX283 driver entry with the same.

At the same time, update my role to a reviewer for the IMX283 driver.

Link: https://lkml.kernel.org/r/20250929074025.84407-1-uajain@igalia.com
Signed-off-by: Umang Jain <uajain@igalia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index 46c4c3b58ec5..d2edd256b19d 100644
--- a/.mailmap
+++ b/.mailmap
@@ -803,6 +803,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@onelan.co.uk>
 Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
+Umang Jain <uajain@igalia.com> <umang.jain@ideasonboard.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
 Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
diff --git a/MAINTAINERS b/MAINTAINERS
index 8f5208ad442b..edba4d5d2250 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23882,7 +23882,7 @@ F:	drivers/media/i2c/imx274.c
 
 SONY IMX283 SENSOR DRIVER
 M:	Kieran Bingham <kieran.bingham@ideasonboard.com>
-M:	Umang Jain <umang.jain@ideasonboard.com>
+R:	Umang Jain <uajain@igalia.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media.git

From 469661d0d3a55a7ba1e7cb847c26baf78cace086 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 21 Sep 2025 08:44:55 +0300
Subject: [PATCH 207/352] kho: check if kho is finalized in
 __kho_preserve_order()

Patch series "kho: add support for preserving vmalloc allocations", v5.

Following the discussion about preservation of memfd with LUO [1] these
patches add support for preserving vmalloc allocations.

Any KHO uses case presumes that there's a data structure that lists
physical addresses of preserved folios (and potentially some additional
metadata).  Allowing vmalloc preservations with KHO allows scalable
preservation of such data structures.

For instance, instead of allocating array describing preserved folios in
the fdt, memfd preservation can use vmalloc:

        preserved_folios = vmalloc_array(nr_folios, sizeof(*preserved_folios));
        memfd_luo_preserve_folios(preserved_folios, folios, nr_folios);
        kho_preserve_vmalloc(preserved_folios, &folios_info);


This patch (of 4):

Instead of checking if kho is finalized in each caller of
__kho_preserve_order(), do it in the core function itself.

Link: https://lkml.kernel.org/r/20250921054458.4043761-1-rppt@kernel.org
Link: https://lkml.kernel.org/r/20250921054458.4043761-2-rppt@kernel.org
Link: https://lore.kernel.org/all/20250807014442.3829950-30-pasha.tatashin@soleen.com [1]
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/kexec_handover.c | 55 +++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 29 deletions(-)

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 5083c68c3a4e..b8d0d63f6145 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -107,6 +107,29 @@ struct kho_serialization {
 	struct khoser_mem_chunk *preserved_mem_map;
 };
 
+struct kho_out {
+	struct blocking_notifier_head chain_head;
+
+	struct dentry *dir;
+
+	struct mutex lock; /* protects KHO FDT finalization */
+
+	struct kho_serialization ser;
+	bool finalized;
+};
+
+static struct kho_out kho_out = {
+	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
+	.lock = __MUTEX_INITIALIZER(kho_out.lock),
+	.ser = {
+		.fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
+		.track = {
+			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
+		},
+	},
+	.finalized = false,
+};
+
 static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
 {
 	void *elm, *res;
@@ -165,6 +188,9 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
 
 	might_sleep();
 
+	if (kho_out.finalized)
+		return -EBUSY;
+
 	physxa = xa_load(&track->orders, order);
 	if (!physxa) {
 		int err;
@@ -667,29 +693,6 @@ int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
 }
 EXPORT_SYMBOL_GPL(kho_add_subtree);
 
-struct kho_out {
-	struct blocking_notifier_head chain_head;
-
-	struct dentry *dir;
-
-	struct mutex lock; /* protects KHO FDT finalization */
-
-	struct kho_serialization ser;
-	bool finalized;
-};
-
-static struct kho_out kho_out = {
-	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
-	.lock = __MUTEX_INITIALIZER(kho_out.lock),
-	.ser = {
-		.fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
-		.track = {
-			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
-		},
-	},
-	.finalized = false,
-};
-
 int register_kho_notifier(struct notifier_block *nb)
 {
 	return blocking_notifier_chain_register(&kho_out.chain_head, nb);
@@ -717,9 +720,6 @@ int kho_preserve_folio(struct folio *folio)
 	const unsigned int order = folio_order(folio);
 	struct kho_mem_track *track = &kho_out.ser.track;
 
-	if (kho_out.finalized)
-		return -EBUSY;
-
 	return __kho_preserve_order(track, pfn, order);
 }
 EXPORT_SYMBOL_GPL(kho_preserve_folio);
@@ -743,9 +743,6 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
 	int err = 0;
 	struct kho_mem_track *track = &kho_out.ser.track;
 
-	if (kho_out.finalized)
-		return -EBUSY;
-
 	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
 		return -EINVAL;
 

From 8375b76517cb52bac0903071feedc218c45d74d2 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 21 Sep 2025 08:44:56 +0300
Subject: [PATCH 208/352] kho: replace kho_preserve_phys() with
 kho_preserve_pages()

to make it clear that KHO operates on pages rather than on a random
physical address.

The kho_preserve_pages() will be also used in upcoming support for vmalloc
preservation.

Link: https://lkml.kernel.org/r/20250921054458.4043761-3-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kexec_handover.h |  5 +++--
 kernel/kexec_handover.c        | 27 ++++++++++++---------------
 mm/memblock.c                  |  4 +++-
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index 559d13a3bc44..cec663b39861 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -18,6 +18,7 @@ enum kho_event {
 
 struct folio;
 struct notifier_block;
+struct page;
 
 #define DECLARE_KHOSER_PTR(name, type) \
 	union {                        \
@@ -43,7 +44,7 @@ bool kho_is_enabled(void);
 bool is_kho_boot(void);
 
 int kho_preserve_folio(struct folio *folio);
-int kho_preserve_phys(phys_addr_t phys, size_t size);
+int kho_preserve_pages(struct page *page, unsigned int nr_pages);
 struct folio *kho_restore_folio(phys_addr_t phys);
 int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
 int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
@@ -71,7 +72,7 @@ static inline int kho_preserve_folio(struct folio *folio)
 	return -EOPNOTSUPP;
 }
 
-static inline int kho_preserve_phys(phys_addr_t phys, size_t size)
+static inline int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index b8d0d63f6145..1c44a55f758e 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -725,26 +725,23 @@ int kho_preserve_folio(struct folio *folio)
 EXPORT_SYMBOL_GPL(kho_preserve_folio);
 
 /**
- * kho_preserve_phys - preserve a physically contiguous range across kexec.
- * @phys: physical address of the range.
- * @size: size of the range.
+ * kho_preserve_pages - preserve contiguous pages across kexec
+ * @page: first page in the list.
+ * @nr_pages: number of pages.
  *
- * Instructs KHO to preserve the memory range from @phys to @phys + @size
- * across kexec.
+ * Preserve a contiguous list of order 0 pages. Must be restored using
+ * kho_restore_pages() to ensure the pages are restored properly as order 0.
  *
  * Return: 0 on success, error code on failure
  */
-int kho_preserve_phys(phys_addr_t phys, size_t size)
+int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 {
-	unsigned long pfn = PHYS_PFN(phys);
-	unsigned long failed_pfn = 0;
-	const unsigned long start_pfn = pfn;
-	const unsigned long end_pfn = PHYS_PFN(phys + size);
-	int err = 0;
 	struct kho_mem_track *track = &kho_out.ser.track;
-
-	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
-		return -EINVAL;
+	const unsigned long start_pfn = page_to_pfn(page);
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn = start_pfn;
+	unsigned long failed_pfn = 0;
+	int err = 0;
 
 	while (pfn < end_pfn) {
 		const unsigned int order =
@@ -764,7 +761,7 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(kho_preserve_phys);
+EXPORT_SYMBOL_GPL(kho_preserve_pages);
 
 /* Handling for debug/kho/out */
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 120a501a887a..e23e16618e9b 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2452,8 +2452,10 @@ static int reserve_mem_kho_finalize(struct kho_serialization *ser)
 
 	for (i = 0; i < reserved_mem_count; i++) {
 		struct reserve_mem_table *map = &reserved_mem_table[i];
+		struct page *page = phys_to_page(map->start);
+		unsigned int nr_pages = map->size >> PAGE_SHIFT;
 
-		err |= kho_preserve_phys(map->start, map->size);
+		err |= kho_preserve_pages(page, nr_pages);
 	}
 
 	err |= kho_preserve_folio(page_folio(kho_fdt));

From a667300bd53f272a3055238bcefe108f88836270 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 21 Sep 2025 08:44:57 +0300
Subject: [PATCH 209/352] kho: add support for preserving vmalloc allocations

A vmalloc allocation is preserved using binary structure similar to global
KHO memory tracker.  It's a linked list of pages where each page is an
array of physical address of pages in vmalloc area.

kho_preserve_vmalloc() hands out the physical address of the head page to
the caller.  This address is used as the argument to kho_vmalloc_restore()
to restore the mapping in the vmalloc address space and populate it with
the preserved pages.

[pasha.tatashin@soleen.com: free chunks using free_page() not kfree()]
  Link: https://lkml.kernel.org/r/mafs0a52idbeg.fsf@kernel.org
[akpm@linux-foundation.org: coding-style cleanups]
Link: https://lkml.kernel.org/r/20250921054458.4043761-4-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kexec_handover.h |  28 ++++
 kernel/kexec_handover.c        | 281 +++++++++++++++++++++++++++++++++
 2 files changed, 309 insertions(+)

diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index cec663b39861..25042c1d8d54 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -39,13 +39,24 @@ struct page;
 
 struct kho_serialization;
 
+struct kho_vmalloc_chunk;
+struct kho_vmalloc {
+	DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *);
+	unsigned int total_pages;
+	unsigned short flags;
+	unsigned short order;
+};
+
 #ifdef CONFIG_KEXEC_HANDOVER
 bool kho_is_enabled(void);
 bool is_kho_boot(void);
 
 int kho_preserve_folio(struct folio *folio);
 int kho_preserve_pages(struct page *page, unsigned int nr_pages);
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation);
 struct folio *kho_restore_folio(phys_addr_t phys);
+struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages);
+void *kho_restore_vmalloc(const struct kho_vmalloc *preservation);
 int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
 int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
 
@@ -77,11 +88,28 @@ static inline int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 	return -EOPNOTSUPP;
 }
 
+static inline int kho_preserve_vmalloc(void *ptr,
+				       struct kho_vmalloc *preservation)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct folio *kho_restore_folio(phys_addr_t phys)
 {
 	return NULL;
 }
 
+static inline struct page *kho_restore_pages(phys_addr_t phys,
+					     unsigned int nr_pages)
+{
+	return NULL;
+}
+
+static inline void *kho_restore_vmalloc(const struct kho_vmalloc *preservation)
+{
+	return NULL;
+}
+
 static inline int kho_add_subtree(struct kho_serialization *ser,
 				  const char *name, void *fdt)
 {
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 1c44a55f758e..76f0940fb485 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -18,6 +18,7 @@
 #include <linux/memblock.h>
 #include <linux/notifier.h>
 #include <linux/page-isolation.h>
+#include <linux/vmalloc.h>
 
 #include <asm/early_ioremap.h>
 
@@ -274,6 +275,37 @@ struct folio *kho_restore_folio(phys_addr_t phys)
 }
 EXPORT_SYMBOL_GPL(kho_restore_folio);
 
+/**
+ * kho_restore_pages - restore list of contiguous order 0 pages.
+ * @phys: physical address of the first page.
+ * @nr_pages: number of pages.
+ *
+ * Restore a contiguous list of order 0 pages that was preserved with
+ * kho_preserve_pages().
+ *
+ * Return: 0 on success, error code on failure
+ */
+struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages)
+{
+	const unsigned long start_pfn = PHYS_PFN(phys);
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn = start_pfn;
+
+	while (pfn < end_pfn) {
+		const unsigned int order =
+			min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
+		struct page *page = kho_restore_page(PFN_PHYS(pfn));
+
+		if (!page)
+			return NULL;
+		split_page(page, order);
+		pfn += 1 << order;
+	}
+
+	return pfn_to_page(start_pfn);
+}
+EXPORT_SYMBOL_GPL(kho_restore_pages);
+
 /* Serialize and deserialize struct kho_mem_phys across kexec
  *
  * Record all the bitmaps in a linked list of pages for the next kernel to
@@ -763,6 +795,255 @@ int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 }
 EXPORT_SYMBOL_GPL(kho_preserve_pages);
 
+struct kho_vmalloc_hdr {
+	DECLARE_KHOSER_PTR(next, struct kho_vmalloc_chunk *);
+};
+
+#define KHO_VMALLOC_SIZE				\
+	((PAGE_SIZE - sizeof(struct kho_vmalloc_hdr)) / \
+	 sizeof(phys_addr_t))
+
+struct kho_vmalloc_chunk {
+	struct kho_vmalloc_hdr hdr;
+	phys_addr_t phys[KHO_VMALLOC_SIZE];
+};
+
+static_assert(sizeof(struct kho_vmalloc_chunk) == PAGE_SIZE);
+
+/* vmalloc flags KHO supports */
+#define KHO_VMALLOC_SUPPORTED_FLAGS	(VM_ALLOC | VM_ALLOW_HUGE_VMAP)
+
+/* KHO internal flags for vmalloc preservations */
+#define KHO_VMALLOC_ALLOC	0x0001
+#define KHO_VMALLOC_HUGE_VMAP	0x0002
+
+static unsigned short vmalloc_flags_to_kho(unsigned int vm_flags)
+{
+	unsigned short kho_flags = 0;
+
+	if (vm_flags & VM_ALLOC)
+		kho_flags |= KHO_VMALLOC_ALLOC;
+	if (vm_flags & VM_ALLOW_HUGE_VMAP)
+		kho_flags |= KHO_VMALLOC_HUGE_VMAP;
+
+	return kho_flags;
+}
+
+static unsigned int kho_flags_to_vmalloc(unsigned short kho_flags)
+{
+	unsigned int vm_flags = 0;
+
+	if (kho_flags & KHO_VMALLOC_ALLOC)
+		vm_flags |= VM_ALLOC;
+	if (kho_flags & KHO_VMALLOC_HUGE_VMAP)
+		vm_flags |= VM_ALLOW_HUGE_VMAP;
+
+	return vm_flags;
+}
+
+static struct kho_vmalloc_chunk *new_vmalloc_chunk(struct kho_vmalloc_chunk *cur)
+{
+	struct kho_vmalloc_chunk *chunk;
+	int err;
+
+	chunk = (struct kho_vmalloc_chunk *)get_zeroed_page(GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	err = kho_preserve_pages(virt_to_page(chunk), 1);
+	if (err)
+		goto err_free;
+	if (cur)
+		KHOSER_STORE_PTR(cur->hdr.next, chunk);
+	return chunk;
+
+err_free:
+	free_page((unsigned long)chunk);
+	return NULL;
+}
+
+static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk)
+{
+	struct kho_mem_track *track = &kho_out.ser.track;
+	unsigned long pfn = PHYS_PFN(virt_to_phys(chunk));
+
+	__kho_unpreserve(track, pfn, pfn + 1);
+
+	for (int i = 0; chunk->phys[i]; i++) {
+		pfn = PHYS_PFN(chunk->phys[i]);
+		__kho_unpreserve(track, pfn, pfn + 1);
+	}
+}
+
+static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc)
+{
+	struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(kho_vmalloc->first);
+
+	while (chunk) {
+		struct kho_vmalloc_chunk *tmp = chunk;
+
+		kho_vmalloc_unpreserve_chunk(chunk);
+
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+		free_page((unsigned long)tmp);
+	}
+}
+
+/**
+ * kho_preserve_vmalloc - preserve memory allocated with vmalloc() across kexec
+ * @ptr: pointer to the area in vmalloc address space
+ * @preservation: placeholder for preservation metadata
+ *
+ * Instructs KHO to preserve the area in vmalloc address space at @ptr. The
+ * physical pages mapped at @ptr will be preserved and on successful return
+ * @preservation will hold the physical address of a structure that describes
+ * the preservation.
+ *
+ * NOTE: The memory allocated with vmalloc_node() variants cannot be reliably
+ * restored on the same node
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation)
+{
+	struct kho_vmalloc_chunk *chunk;
+	struct vm_struct *vm = find_vm_area(ptr);
+	unsigned int order, flags, nr_contig_pages;
+	unsigned int idx = 0;
+	int err;
+
+	if (!vm)
+		return -EINVAL;
+
+	if (vm->flags & ~KHO_VMALLOC_SUPPORTED_FLAGS)
+		return -EOPNOTSUPP;
+
+	flags = vmalloc_flags_to_kho(vm->flags);
+	order = get_vm_area_page_order(vm);
+
+	chunk = new_vmalloc_chunk(NULL);
+	if (!chunk)
+		return -ENOMEM;
+	KHOSER_STORE_PTR(preservation->first, chunk);
+
+	nr_contig_pages = (1 << order);
+	for (int i = 0; i < vm->nr_pages; i += nr_contig_pages) {
+		phys_addr_t phys = page_to_phys(vm->pages[i]);
+
+		err = kho_preserve_pages(vm->pages[i], nr_contig_pages);
+		if (err)
+			goto err_free;
+
+		chunk->phys[idx++] = phys;
+		if (idx == ARRAY_SIZE(chunk->phys)) {
+			chunk = new_vmalloc_chunk(chunk);
+			if (!chunk)
+				goto err_free;
+			idx = 0;
+		}
+	}
+
+	preservation->total_pages = vm->nr_pages;
+	preservation->flags = flags;
+	preservation->order = order;
+
+	return 0;
+
+err_free:
+	kho_vmalloc_free_chunks(preservation);
+	return err;
+}
+EXPORT_SYMBOL_GPL(kho_preserve_vmalloc);
+
+/**
+ * kho_restore_vmalloc - recreates and populates an area in vmalloc address
+ * space from the preserved memory.
+ * @preservation: preservation metadata.
+ *
+ * Recreates an area in vmalloc address space and populates it with memory that
+ * was preserved using kho_preserve_vmalloc().
+ *
+ * Return: pointer to the area in the vmalloc address space, NULL on failure.
+ */
+void *kho_restore_vmalloc(const struct kho_vmalloc *preservation)
+{
+	struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(preservation->first);
+	unsigned int align, order, shift, vm_flags;
+	unsigned long total_pages, contig_pages;
+	unsigned long addr, size;
+	struct vm_struct *area;
+	struct page **pages;
+	unsigned int idx = 0;
+	int err;
+
+	vm_flags = kho_flags_to_vmalloc(preservation->flags);
+	if (vm_flags & ~KHO_VMALLOC_SUPPORTED_FLAGS)
+		return NULL;
+
+	total_pages = preservation->total_pages;
+	pages = kvmalloc_array(total_pages, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+	order = preservation->order;
+	contig_pages = (1 << order);
+	shift = PAGE_SHIFT + order;
+	align = 1 << shift;
+
+	while (chunk) {
+		struct page *page;
+
+		for (int i = 0; chunk->phys[i]; i++) {
+			phys_addr_t phys = chunk->phys[i];
+
+			if (idx + contig_pages > total_pages)
+				goto err_free_pages_array;
+
+			page = kho_restore_pages(phys, contig_pages);
+			if (!page)
+				goto err_free_pages_array;
+
+			for (int j = 0; j < contig_pages; j++)
+				pages[idx++] = page;
+
+			phys += contig_pages * PAGE_SIZE;
+		}
+
+		page = kho_restore_pages(virt_to_phys(chunk), 1);
+		if (!page)
+			goto err_free_pages_array;
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+		__free_page(page);
+	}
+
+	if (idx != total_pages)
+		goto err_free_pages_array;
+
+	area = __get_vm_area_node(total_pages * PAGE_SIZE, align, shift,
+				  vm_flags, VMALLOC_START, VMALLOC_END,
+				  NUMA_NO_NODE, GFP_KERNEL,
+				  __builtin_return_address(0));
+	if (!area)
+		goto err_free_pages_array;
+
+	addr = (unsigned long)area->addr;
+	size = get_vm_area_size(area);
+	err = vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, shift);
+	if (err)
+		goto err_free_vm_area;
+
+	area->nr_pages = total_pages;
+	area->pages = pages;
+
+	return area->addr;
+
+err_free_vm_area:
+	free_vm_area(area);
+err_free_pages_array:
+	kvfree(pages);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kho_restore_vmalloc);
+
 /* Handling for debug/kho/out */
 
 static struct dentry *debugfs_root;

From 90eb9ae35727a662789c850efaf225ffe5511fae Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 21 Sep 2025 08:44:58 +0300
Subject: [PATCH 210/352] lib/test_kho: use kho_preserve_vmalloc instead of
 storing addresses in fdt

KHO test stores physical addresses of the preserved folios directly in
fdt.  Use kho_preserve_vmalloc() instead of it and kho_restore_vmalloc()
to retrieve the addresses after kexec.

This makes the test more scalable from one side and adds tests coverage
for kho_preserve_vmalloc() from the other.

Link: https://lkml.kernel.org/r/20250921054458.4043761-5-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/test_kho.c | 41 +++++++++++++++++++++++++++++------------
 1 file changed, 29 insertions(+), 12 deletions(-)

diff --git a/lib/test_kho.c b/lib/test_kho.c
index fe8504e3407b..60cd899ea745 100644
--- a/lib/test_kho.c
+++ b/lib/test_kho.c
@@ -32,6 +32,7 @@ module_param(max_mem, long, 0644);
 struct kho_test_state {
 	unsigned int nr_folios;
 	struct folio **folios;
+	phys_addr_t *folios_info;
 	struct folio *fdt;
 	__wsum csum;
 };
@@ -67,18 +68,15 @@ static struct notifier_block kho_test_nb = {
 
 static int kho_test_save_data(struct kho_test_state *state, void *fdt)
 {
-	phys_addr_t *folios_info;
+	phys_addr_t *folios_info __free(kvfree) = NULL;
+	struct kho_vmalloc folios_info_phys;
 	int err = 0;
 
-	err |= fdt_begin_node(fdt, "data");
-	err |= fdt_property(fdt, "nr_folios", &state->nr_folios,
-			    sizeof(state->nr_folios));
-	err |= fdt_property_placeholder(fdt, "folios_info",
-					state->nr_folios * sizeof(*folios_info),
-					(void **)&folios_info);
-	err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum));
-	err |= fdt_end_node(fdt);
+	folios_info = vmalloc_array(state->nr_folios, sizeof(*folios_info));
+	if (!folios_info)
+		return -ENOMEM;
 
+	err = kho_preserve_vmalloc(folios_info, &folios_info_phys);
 	if (err)
 		return err;
 
@@ -93,6 +91,17 @@ static int kho_test_save_data(struct kho_test_state *state, void *fdt)
 			break;
 	}
 
+	err |= fdt_begin_node(fdt, "data");
+	err |= fdt_property(fdt, "nr_folios", &state->nr_folios,
+			    sizeof(state->nr_folios));
+	err |= fdt_property(fdt, "folios_info", &folios_info_phys,
+			    sizeof(folios_info_phys));
+	err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum));
+	err |= fdt_end_node(fdt);
+
+	if (!err)
+		state->folios_info = no_free_ptr(folios_info);
+
 	return err;
 }
 
@@ -209,8 +218,9 @@ err_free_folios:
 
 static int kho_test_restore_data(const void *fdt, int node)
 {
+	const struct kho_vmalloc *folios_info_phys;
 	const unsigned int *nr_folios;
-	const phys_addr_t *folios_info;
+	phys_addr_t *folios_info;
 	const __wsum *old_csum;
 	__wsum csum = 0;
 	int len;
@@ -225,8 +235,12 @@ static int kho_test_restore_data(const void *fdt, int node)
 	if (!old_csum || len != sizeof(*old_csum))
 		return -EINVAL;
 
-	folios_info = fdt_getprop(fdt, node, "folios_info", &len);
-	if (!folios_info || len != sizeof(*folios_info) * *nr_folios)
+	folios_info_phys = fdt_getprop(fdt, node, "folios_info", &len);
+	if (!folios_info_phys || len != sizeof(*folios_info_phys))
+		return -EINVAL;
+
+	folios_info = kho_restore_vmalloc(folios_info_phys);
+	if (!folios_info)
 		return -EINVAL;
 
 	for (int i = 0; i < *nr_folios; i++) {
@@ -246,6 +260,8 @@ static int kho_test_restore_data(const void *fdt, int node)
 		folio_put(folio);
 	}
 
+	vfree(folios_info);
+
 	if (csum != *old_csum)
 		return -EINVAL;
 
@@ -304,6 +320,7 @@ static void kho_test_cleanup(void)
 		folio_put(kho_test_state.folios[i]);
 
 	kvfree(kho_test_state.folios);
+	vfree(kho_test_state.folios_info);
 	folio_put(kho_test_state.fdt);
 }
 

From fcc0669c5aa681994c507b50f1c706c969d99730 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Mon, 22 Sep 2025 15:02:03 -0700
Subject: [PATCH 211/352] memcg: skip cgroup_file_notify if spinning is not
 allowed

Generally memcg charging is allowed from all the contexts including NMI
where even spinning on spinlock can cause locking issues.  However one
call chain was missed during the addition of memcg charging from any
context support.  That is try_charge_memcg() -> memcg_memory_event() ->
cgroup_file_notify().

The possible function call tree under cgroup_file_notify() can acquire
many different spin locks in spinning mode.  Some of them are
cgroup_file_kn_lock, kernfs_notify_lock, pool_workqeue's lock.  So, let's
just skip cgroup_file_notify() from memcg charging if the context does not
allow spinning.

Alternative approach was also explored where instead of skipping
cgroup_file_notify(), we defer the memcg event processing to irq_work [1].
However it adds complexity and it was decided to keep things simple until
we need more memcg events with !allow_spinning requirement.

Link: https://lore.kernel.org/all/5qi2llyzf7gklncflo6gxoozljbm4h3tpnuv4u4ej4ztysvi6f@x44v7nz2wdzd/ [1]
Link: https://lkml.kernel.org/r/20250922220203.261714-1-shakeel.butt@linux.dev
Fixes: 3ac4638a734a ("memcg: make memcg_rstat_updated nmi safe")
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Michal Hocko <mhocko@suse.com>
Closes: https://lore.kernel.org/all/20250905061919.439648-1-yepeilin@google.com/
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peilin Ye <yepeilin@google.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h | 26 +++++++++++++++++++-------
 mm/memcontrol.c            |  7 ++++---
 2 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 16fe0306e50e..873e510d6f8d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1001,22 +1001,28 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 	count_memcg_events_mm(mm, idx, 1);
 }
 
-static inline void memcg_memory_event(struct mem_cgroup *memcg,
-				      enum memcg_memory_event event)
+static inline void __memcg_memory_event(struct mem_cgroup *memcg,
+					enum memcg_memory_event event,
+					bool allow_spinning)
 {
 	bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
 			  event == MEMCG_SWAP_FAIL;
 
+	/* For now only MEMCG_MAX can happen with !allow_spinning context. */
+	VM_WARN_ON_ONCE(!allow_spinning && event != MEMCG_MAX);
+
 	atomic_long_inc(&memcg->memory_events_local[event]);
-	if (!swap_event)
+	if (!swap_event && allow_spinning)
 		cgroup_file_notify(&memcg->events_local_file);
 
 	do {
 		atomic_long_inc(&memcg->memory_events[event]);
-		if (swap_event)
-			cgroup_file_notify(&memcg->swap_events_file);
-		else
-			cgroup_file_notify(&memcg->events_file);
+		if (allow_spinning) {
+			if (swap_event)
+				cgroup_file_notify(&memcg->swap_events_file);
+			else
+				cgroup_file_notify(&memcg->events_file);
+		}
 
 		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 			break;
@@ -1026,6 +1032,12 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 		 !mem_cgroup_is_root(memcg));
 }
 
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+				      enum memcg_memory_event event)
+{
+	__memcg_memory_event(memcg, event, true);
+}
+
 static inline void memcg_memory_event_mm(struct mm_struct *mm,
 					 enum memcg_memory_event event)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e090f29eb03b..4deda33625f4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2307,12 +2307,13 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	bool drained = false;
 	bool raised_max_event = false;
 	unsigned long pflags;
+	bool allow_spinning = gfpflags_allow_spinning(gfp_mask);
 
 retry:
 	if (consume_stock(memcg, nr_pages))
 		return 0;
 
-	if (!gfpflags_allow_spinning(gfp_mask))
+	if (!allow_spinning)
 		/* Avoid the refill and flush of the older stock */
 		batch = nr_pages;
 
@@ -2348,7 +2349,7 @@ retry:
 	if (!gfpflags_allow_blocking(gfp_mask))
 		goto nomem;
 
-	memcg_memory_event(mem_over_limit, MEMCG_MAX);
+	__memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning);
 	raised_max_event = true;
 
 	psi_memstall_enter(&pflags);
@@ -2415,7 +2416,7 @@ force:
 	 * a MEMCG_MAX event.
 	 */
 	if (!raised_max_event)
-		memcg_memory_event(mem_over_limit, MEMCG_MAX);
+		__memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning);
 
 	/*
 	 * The allocation either can't fail or will lead to more memory

From 1ce6473d17e78e3cb9a40147658231731a551828 Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Mon, 22 Sep 2025 10:14:58 +0800
Subject: [PATCH 212/352] mm/thp: fix MTE tag mismatch when replacing
 zero-filled subpages

When both THP and MTE are enabled, splitting a THP and replacing its
zero-filled subpages with the shared zeropage can cause MTE tag mismatch
faults in userspace.

Remapping zero-filled subpages to the shared zeropage is unsafe, as the
zeropage has a fixed tag of zero, which may not match the tag expected by
the userspace pointer.

KSM already avoids this problem by using memcmp_pages(), which on arm64
intentionally reports MTE-tagged pages as non-identical to prevent unsafe
merging.

As suggested by David[1], this patch adopts the same pattern, replacing the
memchr_inv() byte-level check with a call to pages_identical(). This
leverages existing architecture-specific logic to determine if a page is
truly identical to the shared zeropage.

Having both the THP shrinker and KSM rely on pages_identical() makes the
design more future-proof, IMO. Instead of handling quirks in generic code,
we just let the architecture decide what makes two pages identical.

[1] https://lore.kernel.org/all/ca2106a3-4bb2-4457-81af-301fd99fbef4@redhat.com

Link: https://lkml.kernel.org/r/20250922021458.68123-1-lance.yang@linux.dev
Fixes: b1f202060afe ("mm: remap unused subpages to shared zeropage when splitting isolated thp")
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Reported-by: Qun-wei Lin <Qun-wei.Lin@mediatek.com>
Closes: https://lore.kernel.org/all/a7944523fcc3634607691c35311a5d59d1a3f8d4.camel@mediatek.com
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Usama Arif <usamaarif642@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: andrew.yang <andrew.yang@mediatek.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 15 +++------------
 mm/migrate.c     |  8 +-------
 2 files changed, 4 insertions(+), 19 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5acca24bbabb..1b81680b4225 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -4104,32 +4104,23 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
 static bool thp_underused(struct folio *folio)
 {
 	int num_zero_pages = 0, num_filled_pages = 0;
-	void *kaddr;
 	int i;
 
 	if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1)
 		return false;
 
 	for (i = 0; i < folio_nr_pages(folio); i++) {
-		kaddr = kmap_local_folio(folio, i * PAGE_SIZE);
-		if (!memchr_inv(kaddr, 0, PAGE_SIZE)) {
-			num_zero_pages++;
-			if (num_zero_pages > khugepaged_max_ptes_none) {
-				kunmap_local(kaddr);
+		if (pages_identical(folio_page(folio, i), ZERO_PAGE(0))) {
+			if (++num_zero_pages > khugepaged_max_ptes_none)
 				return true;
-			}
 		} else {
 			/*
 			 * Another path for early exit once the number
 			 * of non-zero filled pages exceeds threshold.
 			 */
-			num_filled_pages++;
-			if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) {
-				kunmap_local(kaddr);
+			if (++num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none)
 				return false;
-			}
 		}
-		kunmap_local(kaddr);
 	}
 	return false;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index aee61a980374..ce83c2c3c287 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -300,9 +300,7 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
 					  unsigned long idx)
 {
 	struct page *page = folio_page(folio, idx);
-	bool contains_data;
 	pte_t newpte;
-	void *addr;
 
 	if (PageCompound(page))
 		return false;
@@ -319,11 +317,7 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
 	 * this subpage has been non present. If the subpage is only zero-filled
 	 * then map it to the shared zeropage.
 	 */
-	addr = kmap_local_page(page);
-	contains_data = memchr_inv(addr, 0, PAGE_SIZE);
-	kunmap_local(addr);
-
-	if (contains_data)
+	if (!pages_identical(page, ZERO_PAGE(0)))
 		return false;
 
 	newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address),

From 9658d698a8a83540bf6a6c80d13c9a61590ee985 Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Tue, 30 Sep 2025 16:10:40 +0800
Subject: [PATCH 213/352] mm/rmap: fix soft-dirty and uffd-wp bit loss when
 remapping zero-filled mTHP subpage to shared zeropage

When splitting an mTHP and replacing a zero-filled subpage with the shared
zeropage, try_to_map_unused_to_zeropage() currently drops several
important PTE bits.

For userspace tools like CRIU, which rely on the soft-dirty mechanism for
incremental snapshots, losing the soft-dirty bit means modified pages are
missed, leading to inconsistent memory state after restore.

As pointed out by David, the more critical uffd-wp bit is also dropped.
This breaks the userfaultfd write-protection mechanism, causing writes to
be silently missed by monitoring applications, which can lead to data
corruption.

Preserve both the soft-dirty and uffd-wp bits from the old PTE when
creating the new zeropage mapping to ensure they are correctly tracked.

Link: https://lkml.kernel.org/r/20250930081040.80926-1-lance.yang@linux.dev
Fixes: b1f202060afe ("mm: remap unused subpages to shared zeropage when splitting isolated thp")
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Dev Jain <dev.jain@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/migrate.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index ce83c2c3c287..e3065c9edb55 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -296,8 +296,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 }
 
 static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
-					  struct folio *folio,
-					  unsigned long idx)
+		struct folio *folio, pte_t old_pte, unsigned long idx)
 {
 	struct page *page = folio_page(folio, idx);
 	pte_t newpte;
@@ -306,7 +305,7 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
 		return false;
 	VM_BUG_ON_PAGE(!PageAnon(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(pte_present(ptep_get(pvmw->pte)), page);
+	VM_BUG_ON_PAGE(pte_present(old_pte), page);
 
 	if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) ||
 	    mm_forbids_zeropage(pvmw->vma->vm_mm))
@@ -322,6 +321,12 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw,
 
 	newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address),
 					pvmw->vma->vm_page_prot));
+
+	if (pte_swp_soft_dirty(old_pte))
+		newpte = pte_mksoft_dirty(newpte);
+	if (pte_swp_uffd_wp(old_pte))
+		newpte = pte_mkuffd_wp(newpte);
+
 	set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte);
 
 	dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio));
@@ -364,13 +369,13 @@ static bool remove_migration_pte(struct folio *folio,
 			continue;
 		}
 #endif
+		old_pte = ptep_get(pvmw.pte);
 		if (rmap_walk_arg->map_unused_to_zeropage &&
-		    try_to_map_unused_to_zeropage(&pvmw, folio, idx))
+		    try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx))
 			continue;
 
 		folio_get(folio);
 		pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
-		old_pte = ptep_get(pvmw.pte);
 
 		entry = pte_to_swp_entry(old_pte);
 		if (!is_migration_entry_young(entry))

From b93af2cc8e036754c0d9970d9ddc47f43cc94b9f Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 29 Sep 2025 17:44:09 -0700
Subject: [PATCH 214/352] mm/damon/vaddr: do not repeat pte_offset_map_lock()
 until success

DAMON's virtual address space operation set implementation (vaddr) calls
pte_offset_map_lock() inside the page table walk callback function.  This
is for reading and writing page table accessed bits.  If
pte_offset_map_lock() fails, it retries by returning the page table walk
callback function with ACTION_AGAIN.

pte_offset_map_lock() can continuously fail if the target is a pmd
migration entry, though.  Hence it could cause an infinite page table walk
if the migration cannot be done until the page table walk is finished.
This indeed caused a soft lockup when CPU hotplugging and DAMON were
running in parallel.

Avoid the infinite loop by simply not retrying the page table walk.  DAMON
is promising only a best-effort accuracy, so missing access to such pages
is no problem.

Link: https://lkml.kernel.org/r/20250930004410.55228-1-sj@kernel.org
Fixes: 7780d04046a2 ("mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails")
Signed-off-by: SeongJae Park <sj@kernel.org>
Reported-by: Xinyu Zheng <zhengxinyu6@huawei.com>
Closes: https://lore.kernel.org/20250918030029.2652607-1-zhengxinyu6@huawei.com
Acked-by: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>	[6.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/vaddr.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 8c048f9b129e..7e834467b2d8 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -328,10 +328,8 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
 	}
 
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-	if (!pte) {
-		walk->action = ACTION_AGAIN;
+	if (!pte)
 		return 0;
-	}
 	if (!pte_present(ptep_get(pte)))
 		goto out;
 	damon_ptep_mkold(pte, walk->vma, addr);
@@ -481,10 +479,8 @@ regular_page:
 #endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-	if (!pte) {
-		walk->action = ACTION_AGAIN;
+	if (!pte)
 		return 0;
-	}
 	ptent = ptep_get(pte);
 	if (!pte_present(ptent))
 		goto out;

From f04aad36a07cc17b7a5d5b9a2d386ce6fae63e93 Mon Sep 17 00:00:00 2001
From: Jakub Acs <acsjakub@amazon.de>
Date: Wed, 1 Oct 2025 09:03:52 +0000
Subject: [PATCH 215/352] mm/ksm: fix flag-dropping behavior in ksm_madvise

syzkaller discovered the following crash: (kernel BUG)

[   44.607039] ------------[ cut here ]------------
[   44.607422] kernel BUG at mm/userfaultfd.c:2067!
[   44.608148] Oops: invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN NOPTI
[   44.608814] CPU: 1 UID: 0 PID: 2475 Comm: reproducer Not tainted 6.16.0-rc6 #1 PREEMPT(none)
[   44.609635] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
[   44.610695] RIP: 0010:userfaultfd_release_all+0x3a8/0x460

<snip other registers, drop unreliable trace>

[   44.617726] Call Trace:
[   44.617926]  <TASK>
[   44.619284]  userfaultfd_release+0xef/0x1b0
[   44.620976]  __fput+0x3f9/0xb60
[   44.621240]  fput_close_sync+0x110/0x210
[   44.622222]  __x64_sys_close+0x8f/0x120
[   44.622530]  do_syscall_64+0x5b/0x2f0
[   44.622840]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   44.623244] RIP: 0033:0x7f365bb3f227

Kernel panics because it detects UFFD inconsistency during
userfaultfd_release_all().  Specifically, a VMA which has a valid pointer
to vma->vm_userfaultfd_ctx, but no UFFD flags in vma->vm_flags.

The inconsistency is caused in ksm_madvise(): when user calls madvise()
with MADV_UNMEARGEABLE on a VMA that is registered for UFFD in MINOR mode,
it accidentally clears all flags stored in the upper 32 bits of
vma->vm_flags.

Assuming x86_64 kernel build, unsigned long is 64-bit and unsigned int and
int are 32-bit wide.  This setup causes the following mishap during the &=
~VM_MERGEABLE assignment.

VM_MERGEABLE is a 32-bit constant of type unsigned int, 0x8000'0000.
After ~ is applied, it becomes 0x7fff'ffff unsigned int, which is then
promoted to unsigned long before the & operation.  This promotion fills
upper 32 bits with leading 0s, as we're doing unsigned conversion (and
even for a signed conversion, this wouldn't help as the leading bit is 0).
& operation thus ends up AND-ing vm_flags with 0x0000'0000'7fff'ffff
instead of intended 0xffff'ffff'7fff'ffff and hence accidentally clears
the upper 32-bits of its value.

Fix it by changing `VM_MERGEABLE` constant to unsigned long, using the
BIT() macro.

Note: other VM_* flags are not affected: This only happens to the
VM_MERGEABLE flag, as the other VM_* flags are all constants of type int
and after ~ operation, they end up with leading 1 and are thus converted
to unsigned long with leading 1s.

Note 2:
After commit 31defc3b01d9 ("userfaultfd: remove (VM_)BUG_ON()s"), this is
no longer a kernel BUG, but a WARNING at the same place:

[   45.595973] WARNING: CPU: 1 PID: 2474 at mm/userfaultfd.c:2067

but the root-cause (flag-drop) remains the same.

[akpm@linux-foundation.org: rust bindgen wasn't able to handle BIT(), from Miguel]
  Link: https://lore.kernel.org/oe-kbuild-all/202510030449.VfSaAjvd-lkp@intel.com/
Link: https://lkml.kernel.org/r/20251001090353.57523-2-acsjakub@amazon.de
Fixes: 7677f7fd8be7 ("userfaultfd: add minor fault registration mode")
Signed-off-by: Jakub Acs <acsjakub@amazon.de>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: SeongJae Park <sj@kernel.org>
Tested-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Xu Xin <xu.xin16@zte.com.cn>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h              | 2 +-
 rust/bindings/bindings_helper.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 06978b4dbeb8..70a2a76007d4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -323,7 +323,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
 #define VM_HUGEPAGE	0x20000000	/* MADV_HUGEPAGE marked this vma */
 #define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
-#define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
+#define VM_MERGEABLE	BIT(31)		/* KSM may merge identical pages */
 
 #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
 #define VM_HIGH_ARCH_BIT_0	32	/* bit only usable on 64-bit architectures */
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 04b75d4d01c3..2e43c66635a2 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -108,6 +108,7 @@ const xa_mark_t RUST_CONST_HELPER_XA_PRESENT = XA_PRESENT;
 
 const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC;
 const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC1 = XA_FLAGS_ALLOC1;
+const vm_flags_t RUST_CONST_HELPER_VM_MERGEABLE = VM_MERGEABLE;
 
 #if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_RUST)
 #include "../../drivers/android/binder/rust_binder.h"

From 28bba2c2935e219d6cb6946e16b9a0b7c47913be Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Fri, 3 Oct 2025 16:52:36 +0100
Subject: [PATCH 216/352] fsnotify: pass correct offset to fsnotify_mmap_perm()

fsnotify_mmap_perm() requires a byte offset for the file about to be
mmap'ed.  But it is called from vm_mmap_pgoff(), which has a page offset.
Previously the conversion was done incorrectly so let's fix it, being
careful not to overflow on 32-bit platforms.

Discovered during code review.

Link: https://lkml.kernel.org/r/20251003155238.2147410-1-ryan.roberts@arm.com
Fixes: 066e053fe208 ("fsnotify: add pre-content hooks on mmap()")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Kiryl Shutsemau <kas@kernel.org>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@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>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/util.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/util.c b/mm/util.c
index 6c1d64ed0221..8989d5767528 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -566,6 +566,7 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot,
 	unsigned long flag, unsigned long pgoff)
 {
+	loff_t off = (loff_t)pgoff << PAGE_SHIFT;
 	unsigned long ret;
 	struct mm_struct *mm = current->mm;
 	unsigned long populate;
@@ -573,7 +574,7 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 
 	ret = security_mmap_file(file, prot, flag);
 	if (!ret)
-		ret = fsnotify_mmap_perm(file, prot, pgoff >> PAGE_SHIFT, len);
+		ret = fsnotify_mmap_perm(file, prot, off, len);
 	if (!ret) {
 		if (mmap_write_lock_killable(mm))
 			return -EINTR;

From f52ce0ea90c83a28904c7cc203a70e6434adfecb Mon Sep 17 00:00:00 2001
From: Yang Shi <yang@os.amperecomputing.com>
Date: Mon, 29 Sep 2025 13:24:02 -0700
Subject: [PATCH 217/352] mm: hugetlb: avoid soft lockup when mprotect to large
 memory area
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When calling mprotect() to a large hugetlb memory area in our customer's
workload (~300GB hugetlb memory), soft lockup was observed:

watchdog: BUG: soft lockup - CPU#98 stuck for 23s! [t2_new_sysv:126916]

CPU: 98 PID: 126916 Comm: t2_new_sysv Kdump: loaded Not tainted 6.17-rc7
Hardware name: GIGACOMPUTING R2A3-T40-AAV1/Jefferson CIO, BIOS 5.4.4.1 07/15/2025
pstate: 20400009 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : mte_clear_page_tags+0x14/0x24
lr : mte_sync_tags+0x1c0/0x240
sp : ffff80003150bb80
x29: ffff80003150bb80 x28: ffff00739e9705a8 x27: 0000ffd2d6a00000
x26: 0000ff8e4bc00000 x25: 00e80046cde00f45 x24: 0000000000022458
x23: 0000000000000000 x22: 0000000000000004 x21: 000000011b380000
x20: ffff000000000000 x19: 000000011b379f40 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
x11: 0000000000000000 x10: 0000000000000000 x9 : ffffc875e0aa5e2c
x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000
x5 : fffffc01ce7a5c00 x4 : 00000000046cde00 x3 : fffffc0000000000
x2 : 0000000000000004 x1 : 0000000000000040 x0 : ffff0046cde7c000

Call trace:
  mte_clear_page_tags+0x14/0x24
  set_huge_pte_at+0x25c/0x280
  hugetlb_change_protection+0x220/0x430
  change_protection+0x5c/0x8c
  mprotect_fixup+0x10c/0x294
  do_mprotect_pkey.constprop.0+0x2e0/0x3d4
  __arm64_sys_mprotect+0x24/0x44
  invoke_syscall+0x50/0x160
  el0_svc_common+0x48/0x144
  do_el0_svc+0x30/0xe0
  el0_svc+0x30/0xf0
  el0t_64_sync_handler+0xc4/0x148
  el0t_64_sync+0x1a4/0x1a8

Soft lockup is not triggered with THP or base page because there is
cond_resched() called for each PMD size.

Although the soft lockup was triggered by MTE, it should be not MTE
specific.  The other processing which takes long time in the loop may
trigger soft lockup too.

So add cond_resched() for hugetlb to avoid soft lockup.

Link: https://lkml.kernel.org/r/20250929202402.1663290-1-yang@os.amperecomputing.com
Fixes: 8f860591ffb2 ("[PATCH] Enable mprotect on huge pages")
Signed-off-by: Yang Shi <yang@os.amperecomputing.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com>
Reviewed-by: Christoph Lameter (Ampere) <cl@gentwo.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6cac826cb61f..795ee393eac0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7222,6 +7222,8 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 						psize);
 		}
 		spin_unlock(ptl);
+
+		cond_resched();
 	}
 	/*
 	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare

From 229c586b5e86979badb7cb0d38717b88a9e95ddd Mon Sep 17 00:00:00 2001
From: T Pratham <t-pratham@ti.com>
Date: Tue, 7 Oct 2025 19:27:51 +0530
Subject: [PATCH 218/352] crypto: skcipher - Fix reqsize handling

Commit afddce13ce81d ("crypto: api - Add reqsize to crypto_alg")
introduced cra_reqsize field in crypto_alg struct to replace type
specific reqsize fields. It looks like this was introduced specifically
for ahash and acomp from the commit description as subsequent commits
add necessary changes in these alg frameworks.

However, this is being recommended for use in all crypto algs [1]
instead of setting reqsize using crypto_*_set_reqsize(). Using
cra_reqsize in skcipher algorithms, hence, causes memory
corruptions and crashes as the underlying functions in the algorithm
framework have not been updated to set the reqsize properly from
cra_reqsize. [2]

Add proper set_reqsize calls in the skcipher init function to
properly initialize reqsize for these algorithms in the framework.

[1]: https://lore.kernel.org/linux-crypto/aCL8BxpHr5OpT04k@gondor.apana.org.au/
[2]: https://gist.github.com/Pratham-T/24247446f1faf4b7843e4014d5089f6b

Fixes: afddce13ce81d ("crypto: api - Add reqsize to crypto_alg")
Fixes: 52f641bc63a4 ("crypto: ti - Add driver for DTHE V2 AES Engine (ECB, CBC)")
Signed-off-by: T Pratham <t-pratham@ti.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/skcipher.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index de5fc91bba26..8fa5d9686d08 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -294,6 +294,8 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 		return crypto_init_lskcipher_ops_sg(tfm);
 	}
 
+	crypto_skcipher_set_reqsize(skcipher, crypto_tfm_alg_reqsize(tfm));
+
 	if (alg->exit)
 		skcipher->base.exit = crypto_skcipher_exit_tfm;
 

From 2a27f6a8fb5722223d526843040f747e9b0e8060 Mon Sep 17 00:00:00 2001
From: Celeste Liu <uwu@coelacanthus.name>
Date: Tue, 30 Sep 2025 19:34:28 +0800
Subject: [PATCH 219/352] can: gs_usb: increase max interface to U8_MAX

This issue was found by Runcheng Lu when develop HSCanT USB to CAN FD
converter[1]. The original developers may have only 3 interfaces
device to test so they write 3 here and wait for future change.

During the HSCanT development, we actually used 4 interfaces, so the
limitation of 3 is not enough now. But just increase one is not
future-proofed. Since the channel index type in gs_host_frame is u8,
just make canch[] become a flexible array with a u8 index, so it
naturally constraint by U8_MAX and avoid statically allocate 256
pointer for every gs_usb device.

[1]: https://github.com/cherry-embedded/HSCanT-hardware

Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices")
Reported-by: Runcheng Lu <runcheng.lu@hpmicro.com>
Cc: stable@vger.kernel.org
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Celeste Liu <uwu@coelacanthus.name>
Link: https://patch.msgid.link/20250930-gs-usb-max-if-v5-1-863330bf6666@coelacanthus.name
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index c9482d6e947b..9fb4cbbd6d6d 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -289,11 +289,6 @@ struct gs_host_frame {
 #define GS_MAX_RX_URBS 30
 #define GS_NAPI_WEIGHT 32
 
-/* Maximum number of interfaces the driver supports per device.
- * Current hardware only supports 3 interfaces. The future may vary.
- */
-#define GS_MAX_INTF 3
-
 struct gs_tx_context {
 	struct gs_can *dev;
 	unsigned int echo_id;
@@ -324,7 +319,6 @@ struct gs_can {
 
 /* usb interface struct */
 struct gs_usb {
-	struct gs_can *canch[GS_MAX_INTF];
 	struct usb_anchor rx_submitted;
 	struct usb_device *udev;
 
@@ -336,9 +330,11 @@ struct gs_usb {
 
 	unsigned int hf_size_rx;
 	u8 active_channels;
+	u8 channel_cnt;
 
 	unsigned int pipe_in;
 	unsigned int pipe_out;
+	struct gs_can *canch[] __counted_by(channel_cnt);
 };
 
 /* 'allocate' a tx context.
@@ -599,7 +595,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	}
 
 	/* device reports out of range channel id */
-	if (hf->channel >= GS_MAX_INTF)
+	if (hf->channel >= parent->channel_cnt)
 		goto device_detach;
 
 	dev = parent->canch[hf->channel];
@@ -699,7 +695,7 @@ resubmit_urb:
 	/* USB failure take down all interfaces */
 	if (rc == -ENODEV) {
 device_detach:
-		for (rc = 0; rc < GS_MAX_INTF; rc++) {
+		for (rc = 0; rc < parent->channel_cnt; rc++) {
 			if (parent->canch[rc])
 				netif_device_detach(parent->canch[rc]->netdev);
 		}
@@ -1460,17 +1456,19 @@ static int gs_usb_probe(struct usb_interface *intf,
 	icount = dconf.icount + 1;
 	dev_info(&intf->dev, "Configuring for %u interfaces\n", icount);
 
-	if (icount > GS_MAX_INTF) {
+	if (icount > type_max(parent->channel_cnt)) {
 		dev_err(&intf->dev,
 			"Driver cannot handle more that %u CAN interfaces\n",
-			GS_MAX_INTF);
+			type_max(parent->channel_cnt));
 		return -EINVAL;
 	}
 
-	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	parent = kzalloc(struct_size(parent, canch, icount), GFP_KERNEL);
 	if (!parent)
 		return -ENOMEM;
 
+	parent->channel_cnt = icount;
+
 	init_usb_anchor(&parent->rx_submitted);
 
 	usb_set_intfdata(intf, parent);
@@ -1531,7 +1529,7 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		return;
 	}
 
-	for (i = 0; i < GS_MAX_INTF; i++)
+	for (i = 0; i < parent->channel_cnt; i++)
 		if (parent->canch[i])
 			gs_destroy_candev(parent->canch[i]);
 

From a12f0bc764da3781da2019c60826f47a6d7ed64f Mon Sep 17 00:00:00 2001
From: Celeste Liu <uwu@coelacanthus.name>
Date: Tue, 30 Sep 2025 14:53:39 +0800
Subject: [PATCH 220/352] can: gs_usb: gs_make_candev(): populate
 net_device->dev_port

The gs_usb driver supports USB devices with more than 1 CAN channel.
In old kernel before 3.15, it uses net_device->dev_id to distinguish
different channel in userspace, which was done in commit
acff76fa45b4 ("can: gs_usb: gs_make_candev(): set netdev->dev_id").
But since 3.15, the correct way is populating net_device->dev_port.
And according to documentation, if network device support multiple
interface, lack of net_device->dev_port SHALL be treated as a bug.

Fixes: acff76fa45b4 ("can: gs_usb: gs_make_candev(): set netdev->dev_id")
Cc: stable@vger.kernel.org
Signed-off-by: Celeste Liu <uwu@coelacanthus.name>
Link: https://patch.msgid.link/20250930-gs-usb-populate-net_device-dev_port-v1-1-68a065de6937@coelacanthus.name
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 9fb4cbbd6d6d..69b8d6da651b 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1245,6 +1245,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 
 	netdev->flags |= IFF_ECHO; /* we support full roundtrip echo */
 	netdev->dev_id = channel;
+	netdev->dev_port = channel;
 
 	/* dev setup */
 	strcpy(dev->bt_const.name, KBUILD_MODNAME);

From ba569fb07a7e9e9b71e9282e27e993ba859295c2 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 6 Aug 2025 17:46:32 +0200
Subject: [PATCH 221/352] can: m_can: m_can_plat_remove(): add missing
 pm_runtime_disable()

Commit 227619c3ff7c ("can: m_can: move runtime PM enable/disable to
m_can_platform") moved the PM runtime enable from the m_can core
driver into the m_can_platform.

That patch forgot to move the pm_runtime_disable() to
m_can_plat_remove(), so that unloading the m_can_platform driver
causes an "Unbalanced pm_runtime_enable!" error message.

Add the missing pm_runtime_disable() to m_can_plat_remove() to fix the
problem.

Cc: Patrik Flykt <patrik.flykt@linux.intel.com>
Fixes: 227619c3ff7c ("can: m_can: move runtime PM enable/disable to m_can_platform")
Reviewed-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://patch.msgid.link/20250929-m_can-fix-state-handling-v4-1-682b49b49d9a@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index b832566efda0..057eaa7b8b4b 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -180,7 +180,7 @@ static void m_can_plat_remove(struct platform_device *pdev)
 	struct m_can_classdev *mcan_class = &priv->cdev;
 
 	m_can_class_unregister(mcan_class);
-
+	pm_runtime_disable(mcan_class->dev);
 	m_can_class_free_dev(mcan_class->net);
 }
 

From 3d9db29b45f970d81acf61cf91a65442efbeb997 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 6 Aug 2025 16:56:15 +0200
Subject: [PATCH 222/352] can: m_can: m_can_handle_state_errors(): fix CAN
 state transition to Error Active

The CAN Error State is determined by the receive and transmit error
counters. The CAN error counters decrease when reception/transmission
is successful, so that a status transition back to the Error Active
status is possible. This transition is not handled by
m_can_handle_state_errors().

Add the missing detection of the Error Active state to
m_can_handle_state_errors() and extend the handling of this state in
m_can_handle_state_change().

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Fixes: cd0d83eab2e0 ("can: m_can: m_can_handle_state_change(): fix state change")
Reviewed-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://patch.msgid.link/20250929-m_can-fix-state-handling-v4-2-682b49b49d9a@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 55 +++++++++++++++++++++--------------
 1 file changed, 33 insertions(+), 22 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index e1d725979685..ac864183a536 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -812,6 +812,9 @@ static int m_can_handle_state_change(struct net_device *dev,
 	u32 timestamp = 0;
 
 	switch (new_state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		cdev->can.state = CAN_STATE_ERROR_ACTIVE;
+		break;
 	case CAN_STATE_ERROR_WARNING:
 		/* error warning state */
 		cdev->can.can_stats.error_warning++;
@@ -841,6 +844,12 @@ static int m_can_handle_state_change(struct net_device *dev,
 	__m_can_get_berr_counter(dev, &bec);
 
 	switch (new_state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+		break;
 	case CAN_STATE_ERROR_WARNING:
 		/* error warning state */
 		cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
@@ -877,30 +886,33 @@ static int m_can_handle_state_change(struct net_device *dev,
 	return 1;
 }
 
-static int m_can_handle_state_errors(struct net_device *dev, u32 psr)
+static enum can_state
+m_can_state_get_by_psr(struct m_can_classdev *cdev)
+{
+	u32 reg_psr;
+
+	reg_psr = m_can_read(cdev, M_CAN_PSR);
+
+	if (reg_psr & PSR_BO)
+		return CAN_STATE_BUS_OFF;
+	if (reg_psr & PSR_EP)
+		return CAN_STATE_ERROR_PASSIVE;
+	if (reg_psr & PSR_EW)
+		return CAN_STATE_ERROR_WARNING;
+
+	return CAN_STATE_ERROR_ACTIVE;
+}
+
+static int m_can_handle_state_errors(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
-	int work_done = 0;
+	enum can_state new_state;
 
-	if (psr & PSR_EW && cdev->can.state != CAN_STATE_ERROR_WARNING) {
-		netdev_dbg(dev, "entered error warning state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_ERROR_WARNING);
-	}
+	new_state = m_can_state_get_by_psr(cdev);
+	if (new_state == cdev->can.state)
+		return 0;
 
-	if (psr & PSR_EP && cdev->can.state != CAN_STATE_ERROR_PASSIVE) {
-		netdev_dbg(dev, "entered error passive state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_ERROR_PASSIVE);
-	}
-
-	if (psr & PSR_BO && cdev->can.state != CAN_STATE_BUS_OFF) {
-		netdev_dbg(dev, "entered error bus off state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_BUS_OFF);
-	}
-
-	return work_done;
+	return m_can_handle_state_change(dev, new_state);
 }
 
 static void m_can_handle_other_err(struct net_device *dev, u32 irqstatus)
@@ -1031,8 +1043,7 @@ static int m_can_rx_handler(struct net_device *dev, int quota, u32 irqstatus)
 	}
 
 	if (irqstatus & IR_ERR_STATE)
-		work_done += m_can_handle_state_errors(dev,
-						       m_can_read(cdev, M_CAN_PSR));
+		work_done += m_can_handle_state_errors(dev);
 
 	if (irqstatus & IR_ERR_BUS_30X)
 		work_done += m_can_handle_bus_errors(dev, irqstatus,

From 4942c42fe1849e6d68dfb5b36ccba344a9fac016 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 6 Aug 2025 18:24:12 +0200
Subject: [PATCH 223/352] can: m_can: m_can_chip_config(): bring up interface
 in correct state

In some SoCs (observed on the STM32MP15) the M_CAN IP core keeps the
CAN state and CAN error counters over an internal reset cycle. An
external reset is not always possible, due to the shared reset with
the other CAN core. This caused the core not always be in Error Active
state when bringing up the controller.

Instead of always setting the CAN state to Error Active in
m_can_chip_config(), fix this by reading and decoding the Protocol
Status Regitser (PSR) and set the CAN state accordingly.

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Reviewed-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://patch.msgid.link/20250929-m_can-fix-state-handling-v4-3-682b49b49d9a@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index ac864183a536..b6db5b57241c 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1617,7 +1617,7 @@ static int m_can_start(struct net_device *dev)
 	netdev_queue_set_dql_min_limit(netdev_get_tx_queue(cdev->net, 0),
 				       cdev->tx_max_coalesced_frames);
 
-	cdev->can.state = CAN_STATE_ERROR_ACTIVE;
+	cdev->can.state = m_can_state_get_by_psr(cdev);
 
 	m_can_enable_all_interrupts(cdev);
 

From a9e30a22d6f23a2684c248871cad4c3061181639 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 12 Aug 2025 16:58:31 +0200
Subject: [PATCH 224/352] can: m_can: fix CAN state in system PM

A suspend/resume cycle on a down interface results in the interface
coming up in Error Active state. A suspend/resume cycle on an Up
interface will always result in Error Active state, regardless of the
actual CAN state.

During suspend, only set running interfaces to CAN_STATE_SLEEPING.
During resume only touch the CAN state of running interfaces. For
wakeup sources, set the CAN state depending on the Protocol Status
Regitser (PSR), for non wakeup source interfaces m_can_start() will do
the same.

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Reviewed-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://patch.msgid.link/20250929-m_can-fix-state-handling-v4-4-682b49b49d9a@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index b6db5b57241c..f2576e577058 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -2503,12 +2503,11 @@ int m_can_class_suspend(struct device *dev)
 		}
 
 		m_can_clk_stop(cdev);
+		cdev->can.state = CAN_STATE_SLEEPING;
 	}
 
 	pinctrl_pm_select_sleep_state(dev);
 
-	cdev->can.state = CAN_STATE_SLEEPING;
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(m_can_class_suspend);
@@ -2521,8 +2520,6 @@ int m_can_class_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
-	cdev->can.state = CAN_STATE_ERROR_ACTIVE;
-
 	if (netif_running(ndev)) {
 		ret = m_can_clk_start(cdev);
 		if (ret)
@@ -2540,6 +2537,8 @@ int m_can_class_resume(struct device *dev)
 			if (cdev->ops->init)
 				ret = cdev->ops->init(cdev);
 
+			cdev->can.state = m_can_state_get_by_psr(cdev);
+
 			m_can_write(cdev, M_CAN_IE, cdev->active_interrupts);
 		} else {
 			ret  = m_can_start(ndev);

From 455281c0ef4e2cabdfe2e8b83fa6010d5210811c Mon Sep 17 00:00:00 2001
From: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Date: Tue, 7 Oct 2025 15:12:05 -0300
Subject: [PATCH 225/352] loop: remove redundant __GFP_NOWARN flag

GFP_NOWAIT already includes __GFP_NOWARN, so let's remove the
redundant __GFP_NOWARN.

Signed-off-by: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 94ec7f747f36..13ce229d450c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -824,7 +824,7 @@ static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd)
 	if (worker)
 		goto queue_work;
 
-	worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT | __GFP_NOWARN);
+	worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT);
 	/*
 	 * In the event we cannot allocate a worker, just queue on the
 	 * rootcg worker and issue the I/O as the rootcg

From 09cfd3c52ea76f43b3cb15e570aeddf633d65e80 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 8 Oct 2025 13:38:06 +0100
Subject: [PATCH 226/352] io_uring/zcrx: fix overshooting recv limit

It's reported that sometimes a zcrx request can receive more than was
requested. It's caused by io_zcrx_recv_skb() adjusting desc->count for
all received buffers including frag lists, but then doing recursive
calls to process frag list skbs, which leads to desc->count double
accounting and underflow.

Reported-and-tested-by: Matthias Jasny <matthiasjasny@gmail.com>
Fixes: 6699ec9a23f85 ("io_uring/zcrx: add a read limit to recvzc requests")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 723e4266b91f..ef73440b605a 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -1236,12 +1236,16 @@ io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 
 		end = start + frag_iter->len;
 		if (offset < end) {
+			size_t count;
+
 			copy = end - offset;
 			if (copy > len)
 				copy = len;
 
 			off = offset - start;
+			count = desc->count;
 			ret = io_zcrx_recv_skb(desc, frag_iter, off, copy);
+			desc->count = count;
 			if (ret < 0)
 				goto out;
 

From e9a9dcb4ccb32446165800a9d83058e95c4833d2 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 8 Oct 2025 13:39:01 +0100
Subject: [PATCH 227/352] io_uring/zcrx: increment fallback loop src offset

Don't forget to adjust the source offset in io_copy_page(), otherwise
it'll be copying into the same location in some cases for highmem
setups.

Fixes: e67645bb7f3f4 ("io_uring/zcrx: prepare fallback for larger pages")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index ef73440b605a..a816f5902091 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -1079,6 +1079,7 @@ static ssize_t io_copy_page(struct io_copy_cache *cc, struct page *src_page,
 
 		cc->size -= n;
 		cc->offset += n;
+		src_offset += n;
 		len -= n;
 		copied += n;
 	}

From f0c029d2ff42499a62c873c14428f02bf94c28af Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 1 Oct 2025 15:09:07 +0200
Subject: [PATCH 228/352] tracing/osnoise: Replace kmalloc + copy_from_user
 with memdup_user_nul

Replace kmalloc() followed by copy_from_user() with memdup_user_nul() to
simplify and improve osnoise_cpus_write(). Remove the manual
NUL-termination.

No functional changes intended.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20251001130907.364673-2-thorsten.blum@linux.dev
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index dc734867f0fc..26d0c99125f5 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -24,6 +24,7 @@
 #include <linux/sched/clock.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/sched.h>
+#include <linux/string.h>
 #include "trace.h"
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -2325,13 +2326,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	if (count < 1)
 		return 0;
 
-	buf = kmalloc(count + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, count))
-		return -EFAULT;
-	buf[count] = '\0';
+	buf = memdup_user_nul(ubuf, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	if (!zalloc_cpumask_var(&osnoise_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;

From 4f7bf54b07e5acf79edd58dafede4096854776cd Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 8 Oct 2025 11:48:35 -0400
Subject: [PATCH 229/352] tracing: Fix wakeup tracers on failure of acquiring
 calltime

The functions wakeup_graph_entry() and wakeup_graph_return() both call
func_prolog_preempt_disable() that will test if the data->disable is
already set and if not, increment it and disable preemption. If it was
set, it returns false and the caller exits.

The caller of this function must decrement the disable counter, but misses
doing so if the calltime fails to be acquired.

Instead of exiting out when calltime is NULL, change the logic to do the
work if it is not NULL and still do the clean up at the end of the
function if it is NULL.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20251008114835.027b878a@gandalf.local.home
Fixes: a485ea9e3ef3 ("tracing: Fix irqsoff and wakeup latency tracers when using function graph")
Reported-by: Sasha Levin <sashal@kernel.org>
Closes: https://lore.kernel.org/linux-trace-kernel/20251006175848.1906912-1-sashal@kernel.org/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_sched_wakeup.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index bf1cb80742ae..e3f2e4f56faa 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -138,12 +138,10 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 		return 0;
 
 	calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime));
-	if (!calltime)
-		return 0;
-
-	*calltime = trace_clock_local();
-
-	ret = __trace_graph_entry(tr, trace, trace_ctx);
+	if (calltime) {
+		*calltime = trace_clock_local();
+		ret = __trace_graph_entry(tr, trace, trace_ctx);
+	}
 	local_dec(&data->disabled);
 	preempt_enable_notrace();
 
@@ -169,12 +167,10 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 	rettime = trace_clock_local();
 
 	calltime = fgraph_retrieve_data(gops->idx, &size);
-	if (!calltime)
-		return;
+	if (calltime)
+		__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
 
-	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
 	local_dec(&data->disabled);
-
 	preempt_enable_notrace();
 	return;
 }

From c834a97962c708ff5bb8582ca76b0e1225feb675 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 8 Oct 2025 11:49:43 -0400
Subject: [PATCH 230/352] tracing: Fix irqoff tracers on failure of acquiring
 calltime

The functions irqsoff_graph_entry() and irqsoff_graph_return() both call
func_prolog_dec() that will test if the data->disable is already set and
if not, increment it and return. If it was set, it returns false and the
caller exits.

The caller of this function must decrement the disable counter, but misses
doing so if the calltime fails to be acquired.

Instead of exiting out when calltime is NULL, change the logic to do the
work if it is not NULL and still do the clean up at the end of the
function if it is NULL.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20251008114943.6f60f30f@gandalf.local.home
Fixes: a485ea9e3ef3 ("tracing: Fix irqsoff and wakeup latency tracers when using function graph")
Reported-by: Sasha Levin <sashal@kernel.org>
Closes: https://lore.kernel.org/linux-trace-kernel/20251006175848.1906912-2-sashal@kernel.org/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_irqsoff.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 5496758b6c76..4c45c49b06c8 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -184,7 +184,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 	unsigned long flags;
 	unsigned int trace_ctx;
 	u64 *calltime;
-	int ret;
+	int ret = 0;
 
 	if (ftrace_graph_ignore_func(gops, trace))
 		return 0;
@@ -202,13 +202,11 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 		return 0;
 
 	calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime));
-	if (!calltime)
-		return 0;
-
-	*calltime = trace_clock_local();
-
-	trace_ctx = tracing_gen_ctx_flags(flags);
-	ret = __trace_graph_entry(tr, trace, trace_ctx);
+	if (calltime) {
+		*calltime = trace_clock_local();
+		trace_ctx = tracing_gen_ctx_flags(flags);
+		ret = __trace_graph_entry(tr, trace, trace_ctx);
+	}
 	local_dec(&data->disabled);
 
 	return ret;
@@ -233,11 +231,10 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 
 	rettime = trace_clock_local();
 	calltime = fgraph_retrieve_data(gops->idx, &size);
-	if (!calltime)
-		return;
-
-	trace_ctx = tracing_gen_ctx_flags(flags);
-	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
+	if (calltime) {
+		trace_ctx = tracing_gen_ctx_flags(flags);
+		__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
+	}
 	local_dec(&data->disabled);
 }
 

From 27c0a7b05d13a0dc54ed0b95fc12218210fdea1a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 31 Jul 2025 12:02:27 -0700
Subject: [PATCH 231/352] libceph: Use HMAC-SHA256 library instead of
 crypto_shash

Use the HMAC-SHA256 library functions instead of crypto_shash.  This is
simpler and faster.

Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  4 +-
 net/ceph/Kconfig               |  3 +-
 net/ceph/messenger_v2.c        | 77 ++++++++++------------------------
 3 files changed, 26 insertions(+), 58 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 1717cc57cdac..4b49592a738f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -2,6 +2,7 @@
 #ifndef __FS_CEPH_MESSENGER_H
 #define __FS_CEPH_MESSENGER_H
 
+#include <crypto/sha2.h>
 #include <linux/bvec.h>
 #include <linux/crypto.h>
 #include <linux/kref.h>
@@ -412,7 +413,8 @@ struct ceph_connection_v2_info {
 	struct ceph_msg_data_cursor in_cursor;
 	struct ceph_msg_data_cursor out_cursor;
 
-	struct crypto_shash *hmac_tfm;  /* post-auth signature */
+	struct hmac_sha256_key hmac_key;  /* post-auth signature */
+	bool hmac_key_set;
 	struct crypto_aead *gcm_tfm;  /* on-wire encryption */
 	struct aead_request *gcm_req;
 	struct crypto_wait gcm_wait;
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index 0aa21fcbf6ec..ea60e3ef0834 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -6,8 +6,7 @@ config CEPH_LIB
 	select CRYPTO_AES
 	select CRYPTO_CBC
 	select CRYPTO_GCM
-	select CRYPTO_HMAC
-	select CRYPTO_SHA256
+	select CRYPTO_LIB_SHA256
 	select CRYPTO
 	select KEYS
 	default n
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 5483b4eed94e..c54c8b5a6526 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -709,7 +709,7 @@ static int setup_crypto(struct ceph_connection *con,
 
 	dout("%s con %p con_mode %d session_key_len %d con_secret_len %d\n",
 	     __func__, con, con->v2.con_mode, session_key_len, con_secret_len);
-	WARN_ON(con->v2.hmac_tfm || con->v2.gcm_tfm || con->v2.gcm_req);
+	WARN_ON(con->v2.hmac_key_set || con->v2.gcm_tfm || con->v2.gcm_req);
 
 	if (con->v2.con_mode != CEPH_CON_MODE_CRC &&
 	    con->v2.con_mode != CEPH_CON_MODE_SECURE) {
@@ -723,22 +723,8 @@ static int setup_crypto(struct ceph_connection *con,
 		return 0;  /* auth_none */
 	}
 
-	noio_flag = memalloc_noio_save();
-	con->v2.hmac_tfm = crypto_alloc_shash("hmac(sha256)", 0, 0);
-	memalloc_noio_restore(noio_flag);
-	if (IS_ERR(con->v2.hmac_tfm)) {
-		ret = PTR_ERR(con->v2.hmac_tfm);
-		con->v2.hmac_tfm = NULL;
-		pr_err("failed to allocate hmac tfm context: %d\n", ret);
-		return ret;
-	}
-
-	ret = crypto_shash_setkey(con->v2.hmac_tfm, session_key,
-				  session_key_len);
-	if (ret) {
-		pr_err("failed to set hmac key: %d\n", ret);
-		return ret;
-	}
+	hmac_sha256_preparekey(&con->v2.hmac_key, session_key, session_key_len);
+	con->v2.hmac_key_set = true;
 
 	if (con->v2.con_mode == CEPH_CON_MODE_CRC) {
 		WARN_ON(con_secret_len);
@@ -793,38 +779,26 @@ static int setup_crypto(struct ceph_connection *con,
 	return 0;  /* auth_x, secure mode */
 }
 
-static int ceph_hmac_sha256(struct ceph_connection *con,
-			    const struct kvec *kvecs, int kvec_cnt, u8 *hmac)
+static void ceph_hmac_sha256(struct ceph_connection *con,
+			     const struct kvec *kvecs, int kvec_cnt,
+			     u8 hmac[SHA256_DIGEST_SIZE])
 {
-	SHASH_DESC_ON_STACK(desc, con->v2.hmac_tfm);  /* tfm arg is ignored */
-	int ret;
+	struct hmac_sha256_ctx ctx;
 	int i;
 
-	dout("%s con %p hmac_tfm %p kvec_cnt %d\n", __func__, con,
-	     con->v2.hmac_tfm, kvec_cnt);
+	dout("%s con %p hmac_key_set %d kvec_cnt %d\n", __func__, con,
+	     con->v2.hmac_key_set, kvec_cnt);
 
-	if (!con->v2.hmac_tfm) {
+	if (!con->v2.hmac_key_set) {
 		memset(hmac, 0, SHA256_DIGEST_SIZE);
-		return 0;  /* auth_none */
+		return;  /* auth_none */
 	}
 
-	desc->tfm = con->v2.hmac_tfm;
-	ret = crypto_shash_init(desc);
-	if (ret)
-		goto out;
-
-	for (i = 0; i < kvec_cnt; i++) {
-		ret = crypto_shash_update(desc, kvecs[i].iov_base,
-					  kvecs[i].iov_len);
-		if (ret)
-			goto out;
-	}
-
-	ret = crypto_shash_final(desc, hmac);
-
-out:
-	shash_desc_zero(desc);
-	return ret;  /* auth_x, both plain and secure modes */
+	/* auth_x, both plain and secure modes */
+	hmac_sha256_init(&ctx, &con->v2.hmac_key);
+	for (i = 0; i < kvec_cnt; i++)
+		hmac_sha256_update(&ctx, kvecs[i].iov_base, kvecs[i].iov_len);
+	hmac_sha256_final(&ctx, hmac);
 }
 
 static void gcm_inc_nonce(struct ceph_gcm_nonce *nonce)
@@ -1455,17 +1429,14 @@ static int prepare_auth_request_more(struct ceph_connection *con,
 static int prepare_auth_signature(struct ceph_connection *con)
 {
 	void *buf;
-	int ret;
 
 	buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE,
 						  con_secure(con)));
 	if (!buf)
 		return -ENOMEM;
 
-	ret = ceph_hmac_sha256(con, con->v2.in_sign_kvecs,
-			       con->v2.in_sign_kvec_cnt, CTRL_BODY(buf));
-	if (ret)
-		return ret;
+	ceph_hmac_sha256(con, con->v2.in_sign_kvecs, con->v2.in_sign_kvec_cnt,
+			 CTRL_BODY(buf));
 
 	return prepare_control(con, FRAME_TAG_AUTH_SIGNATURE, buf,
 			       SHA256_DIGEST_SIZE);
@@ -2460,10 +2431,8 @@ static int process_auth_signature(struct ceph_connection *con,
 		return -EINVAL;
 	}
 
-	ret = ceph_hmac_sha256(con, con->v2.out_sign_kvecs,
-			       con->v2.out_sign_kvec_cnt, hmac);
-	if (ret)
-		return ret;
+	ceph_hmac_sha256(con, con->v2.out_sign_kvecs, con->v2.out_sign_kvec_cnt,
+			 hmac);
 
 	ceph_decode_need(&p, end, SHA256_DIGEST_SIZE, bad);
 	if (crypto_memneq(p, hmac, SHA256_DIGEST_SIZE)) {
@@ -3814,10 +3783,8 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con)
 	memzero_explicit(&con->v2.in_gcm_nonce, CEPH_GCM_IV_LEN);
 	memzero_explicit(&con->v2.out_gcm_nonce, CEPH_GCM_IV_LEN);
 
-	if (con->v2.hmac_tfm) {
-		crypto_free_shash(con->v2.hmac_tfm);
-		con->v2.hmac_tfm = NULL;
-	}
+	memzero_explicit(&con->v2.hmac_key, sizeof(con->v2.hmac_key));
+	con->v2.hmac_key_set = false;
 	if (con->v2.gcm_req) {
 		aead_request_free(con->v2.gcm_req);
 		con->v2.gcm_req = NULL;

From fa073039466f16141807a0f32840ecdceb00e22a Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Fri, 6 Dec 2024 17:50:14 +0100
Subject: [PATCH 232/352] ceph: make ceph_start_io_*() killable

This allows killing processes that wait for a lock when one process is
stuck waiting for the Ceph server.  This is similar to the NFS commit
38a125b31504 ("fs/nfs/io: make nfs_start_io_*() killable").

[ idryomov: drop comment on include, formatting ]

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/file.c | 20 +++++++++++---------
 fs/ceph/io.c   | 47 +++++++++++++++++++++++++++++++++--------------
 fs/ceph/io.h   |  8 +++++---
 3 files changed, 49 insertions(+), 26 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 978acd3d4b32..08681cf66137 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2121,10 +2121,10 @@ again:
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	if (direct_lock)
-		ceph_start_io_direct(inode);
-	else
-		ceph_start_io_read(inode);
+	ret = direct_lock ? ceph_start_io_direct(inode) :
+			    ceph_start_io_read(inode);
+	if (ret)
+		return ret;
 
 	if (!(fi->flags & CEPH_F_SYNC) && !direct_lock)
 		want |= CEPH_CAP_FILE_CACHE;
@@ -2277,7 +2277,9 @@ static ssize_t ceph_splice_read(struct file *in, loff_t *ppos,
 	    (fi->flags & CEPH_F_SYNC))
 		return copy_splice_read(in, ppos, pipe, len, flags);
 
-	ceph_start_io_read(inode);
+	ret = ceph_start_io_read(inode);
+	if (ret)
+		return ret;
 
 	want = CEPH_CAP_FILE_CACHE;
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
@@ -2356,10 +2358,10 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		direct_lock = true;
 
 retry_snap:
-	if (direct_lock)
-		ceph_start_io_direct(inode);
-	else
-		ceph_start_io_write(inode);
+	err = direct_lock ? ceph_start_io_direct(inode) :
+			    ceph_start_io_write(inode);
+	if (err)
+		goto out_unlocked;
 
 	if (iocb->ki_flags & IOCB_APPEND) {
 		err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
diff --git a/fs/ceph/io.c b/fs/ceph/io.c
index c456509b31c3..e10f44182a4c 100644
--- a/fs/ceph/io.c
+++ b/fs/ceph/io.c
@@ -47,20 +47,29 @@ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
  * Note that buffered writes and truncates both take a write lock on
  * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
  */
-void
-ceph_start_io_read(struct inode *inode)
+int ceph_start_io_read(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	int err;
 
 	/* Be an optimist! */
-	down_read(&inode->i_rwsem);
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
 	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT))
-		return;
+		return 0;
 	up_read(&inode->i_rwsem);
+
 	/* Slow path.... */
-	down_write(&inode->i_rwsem);
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
 	ceph_block_o_direct(ci, inode);
 	downgrade_write(&inode->i_rwsem);
+
+	return 0;
 }
 
 /**
@@ -83,11 +92,12 @@ ceph_end_io_read(struct inode *inode)
  * Declare that a buffered write operation is about to start, and ensure
  * that we block all direct I/O.
  */
-void
-ceph_start_io_write(struct inode *inode)
+int ceph_start_io_write(struct inode *inode)
 {
-	down_write(&inode->i_rwsem);
-	ceph_block_o_direct(ceph_inode(inode), inode);
+	int err = down_write_killable(&inode->i_rwsem);
+	if (!err)
+		ceph_block_o_direct(ceph_inode(inode), inode);
+	return err;
 }
 
 /**
@@ -133,20 +143,29 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
  * Note that buffered writes and truncates both take a write lock on
  * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
  */
-void
-ceph_start_io_direct(struct inode *inode)
+int ceph_start_io_direct(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	int err;
 
 	/* Be an optimist! */
-	down_read(&inode->i_rwsem);
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
 	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)
-		return;
+		return 0;
 	up_read(&inode->i_rwsem);
+
 	/* Slow path.... */
-	down_write(&inode->i_rwsem);
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
 	ceph_block_buffered(ci, inode);
 	downgrade_write(&inode->i_rwsem);
+
+	return 0;
 }
 
 /**
diff --git a/fs/ceph/io.h b/fs/ceph/io.h
index fa594cd77348..79029825e8b8 100644
--- a/fs/ceph/io.h
+++ b/fs/ceph/io.h
@@ -2,11 +2,13 @@
 #ifndef _FS_CEPH_IO_H
 #define _FS_CEPH_IO_H
 
-void ceph_start_io_read(struct inode *inode);
+#include <linux/compiler_attributes.h>
+
+int __must_check ceph_start_io_read(struct inode *inode);
 void ceph_end_io_read(struct inode *inode);
-void ceph_start_io_write(struct inode *inode);
+int __must_check ceph_start_io_write(struct inode *inode);
 void ceph_end_io_write(struct inode *inode);
-void ceph_start_io_direct(struct inode *inode);
+int __must_check ceph_start_io_direct(struct inode *inode);
 void ceph_end_io_direct(struct inode *inode);
 
 #endif /* FS_CEPH_IO_H */

From b7ed1e29cfe773d648ca09895b92856bd3a2092d Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Fri, 6 Jun 2025 12:04:32 -0700
Subject: [PATCH 233/352] ceph: add checking of wait_for_completion_killable()
 return value

The Coverity Scan service has detected the calling of
wait_for_completion_killable() without checking the return
value in ceph_lock_wait_for_completion() [1]. The CID 1636232
defect contains explanation: "If the function returns an error
value, the error value may be mistaken for a normal value.
In ceph_lock_wait_for_completion(): Value returned from
a function is not checked for errors before being used. (CWE-252)".

The patch adds the checking of wait_for_completion_killable()
return value and return the error code from
ceph_lock_wait_for_completion().

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1636232

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/locks.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ebf4ac0055dd..dd764f9c64b9 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -221,7 +221,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 	if (err && err != -ERESTARTSYS)
 		return err;
 
-	wait_for_completion_killable(&req->r_safe_completion);
+	err = wait_for_completion_killable(&req->r_safe_completion);
+	if (err)
+		return err;
+
 	return 0;
 }
 

From 1ed4471a4ee6cfa902467332042158ca5ef8ad24 Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Fri, 6 Jun 2025 12:05:21 -0700
Subject: [PATCH 234/352] ceph: fix wrong sizeof argument issue in
 register_session()

The Coverity Scan service has detected the wrong sizeof
argument in register_session() [1]. The CID 1598909 defect
contains explanation: "The wrong sizeof value is used in
an expression or as argument to a function. The result is
an incorrect value that may cause unexpected program behaviors.
In register_session: The sizeof operator is invoked on
the wrong argument (CWE-569)".

The patch introduces a ptr_size variable that is initialized
by sizeof(struct ceph_mds_session *). And this variable is used
instead of sizeof(void *) in the code.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1598909

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3bc72b47fe4d..aa2f74142cf4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -979,14 +979,15 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	if (mds >= mdsc->max_sessions) {
 		int newmax = 1 << get_count_order(mds + 1);
 		struct ceph_mds_session **sa;
+		size_t ptr_size = sizeof(struct ceph_mds_session *);
 
 		doutc(cl, "realloc to %d\n", newmax);
-		sa = kcalloc(newmax, sizeof(void *), GFP_NOFS);
+		sa = kcalloc(newmax, ptr_size, GFP_NOFS);
 		if (!sa)
 			goto fail_realloc;
 		if (mdsc->sessions) {
 			memcpy(sa, mdsc->sessions,
-			       mdsc->max_sessions * sizeof(void *));
+			       mdsc->max_sessions * ptr_size);
 			kfree(mdsc->sessions);
 		}
 		mdsc->sessions = sa;

From 5b2d1377d6cc4147492780b0bd95fb9c4cb28d1b Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Fri, 6 Jun 2025 12:05:45 -0700
Subject: [PATCH 235/352] ceph: fix overflowed constant issue in
 ceph_do_objects_copy()

The Coverity Scan service has detected overflowed constant
issue in ceph_do_objects_copy() [1]. The CID 1624308
defect contains explanation: "The overflowed value due to
arithmetic on constants is too small or unexpectedly
negative, causing incorrect computations. Expression bytes,
which is equal to -95, where ret is known to be equal to -95,
underflows the type that receives it, an unsigned integer
64 bits wide. In ceph_do_objects_copy: Integer overflow occurs
in arithmetic on constant operands (CWE-190)".

The patch changes the type of bytes variable from size_t
to ssize_t with the goal of to be capable to receive
negative values.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1624308

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 08681cf66137..07052f331611 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2880,7 +2880,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 	struct ceph_object_id src_oid, dst_oid;
 	struct ceph_osd_client *osdc;
 	struct ceph_osd_request *req;
-	size_t bytes = 0;
+	ssize_t bytes = 0;
 	u64 src_objnum, src_objoff, dst_objnum, dst_objoff;
 	u32 src_objlen, dst_objlen;
 	u32 object_size = src_ci->i_layout.object_size;
@@ -2930,7 +2930,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 					"OSDs don't support copy-from2; disabling copy offload\n");
 			}
 			doutc(cl, "returned %d\n", ret);
-			if (!bytes)
+			if (bytes <= 0)
 				bytes = ret;
 			goto out;
 		}

From 5824ccba9a39a3ad914fc9b2972a2c1119abaac9 Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Fri, 13 Jun 2025 11:31:08 -0700
Subject: [PATCH 236/352] ceph: fix potential race condition in
 ceph_ioctl_lazyio()

The Coverity Scan service has detected potential
race condition in ceph_ioctl_lazyio() [1].

The CID 1591046 contains explanation: "Check of thread-shared
field evades lock acquisition (LOCK_EVASION). Thread1 sets
fmode to a new value. Now the two threads have an inconsistent
view of fmode and updates to fields correlated with fmode
may be lost. The data guarded by this critical section may
be read while in an inconsistent state or modified by multiple
racing threads. In ceph_ioctl_lazyio: Checking the value of
a thread-shared field outside of a locked region to determine
if a locked operation involving that thread shared field
has completed. (CWE-543)".

The patch places fi->fmode field access under ci->i_ceph_lock
protection. Also, it introduces the is_file_already_lazy
variable that is set under the lock and it is checked later
out of scope of critical section.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1591046

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/ioctl.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index e861de3c79b9..15cde055f3da 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -246,21 +246,28 @@ static long ceph_ioctl_lazyio(struct file *file)
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
 	struct ceph_client *cl = mdsc->fsc->client;
+	bool is_file_already_lazy = false;
 
+	spin_lock(&ci->i_ceph_lock);
 	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
-		spin_lock(&ci->i_ceph_lock);
 		fi->fmode |= CEPH_FILE_MODE_LAZY;
 		ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
 		__ceph_touch_fmode(ci, mdsc, fi->fmode);
-		spin_unlock(&ci->i_ceph_lock);
+	} else {
+		is_file_already_lazy = true;
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (is_file_already_lazy) {
+		doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
+		      ceph_vinop(inode));
+	} else {
 		doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode,
 		      ceph_vinop(inode));
 
 		ceph_check_caps(ci, 0);
-	} else {
-		doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
-		      ceph_vinop(inode));
 	}
+
 	return 0;
 }
 

From 53db6f25ee47cb1265141d31562604e56146919a Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Tue, 8 Jul 2025 12:20:57 -0700
Subject: [PATCH 237/352] ceph: refactor wake_up_bit() pattern of calling

The wake_up_bit() is called in ceph_async_unlink_cb(),
wake_async_create_waiters(), and ceph_finish_async_create().
It makes sense to switch on clear_bit() function, because
it makes the code much cleaner and easier to understand.
More important rework is the adding of smp_mb__after_atomic()
memory barrier after the bit modification and before
wake_up_bit() call. It can prevent potential race condition
of accessing the modified bit in other threads. Luckily,
clear_and_wake_up_bit() already implements the required
functionality pattern:

static inline void clear_and_wake_up_bit(int bit, unsigned long *word)
{
	clear_bit_unlock(bit, word);
	/* See wake_up_bit() for which memory barrier you need to use. */
	smp_mb__after_atomic();
	wake_up_bit(word, bit);
}

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c  | 3 +--
 fs/ceph/file.c | 6 ++----
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 32973c62c1a2..d18c0eaef9b7 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1260,8 +1260,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 	spin_unlock(&fsc->async_unlink_conflict_lock);
 
 	spin_lock(&dentry->d_lock);
-	di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
-	wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT);
+	clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags);
 	spin_unlock(&dentry->d_lock);
 
 	synchronize_rcu();
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 07052f331611..99b30f784ee2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -579,8 +579,7 @@ static void wake_async_create_waiters(struct inode *inode,
 
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
-		ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE;
-		wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT);
+		clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags);
 
 		if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) {
 			ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS;
@@ -762,8 +761,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 	}
 
 	spin_lock(&dentry->d_lock);
-	di->flags &= ~CEPH_DENTRY_ASYNC_CREATE;
-	wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT);
+	clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_CREATE_BIT, &di->flags);
 	spin_unlock(&dentry->d_lock);
 
 	return ret;

From fbeafe782bd986bf75544526fb9c0284e045e0a4 Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Wed, 16 Jul 2025 11:40:49 -0700
Subject: [PATCH 238/352] ceph: fix potential race condition on operations with
 CEPH_I_ODIRECT flag

The Coverity Scan service has detected potential
race conditions in ceph_block_o_direct(), ceph_start_io_read(),
ceph_block_buffered(), and ceph_start_io_direct() [1 - 4].

The CID 1590942, 1590665, 1589664, 1590377 contain explanation:
"The value of the shared data will be determined by
the interleaving of thread execution. Thread shared data is accessed
without holding an appropriate lock, possibly causing
a race condition (CWE-366)".

This patch reworks the pattern of accessing/modification of
CEPH_I_ODIRECT flag by means of adding smp_mb__before_atomic()
before reading the status of CEPH_I_ODIRECT flag and
smp_mb__after_atomic() after clearing set/clear this flag.
Also, it was reworked the pattern of using of ci->i_ceph_lock
in ceph_block_o_direct(), ceph_start_io_read(),
ceph_block_buffered(), and ceph_start_io_direct() methods.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590942
[2] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590665
[3] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1589664
[4] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1590377

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/io.c    | 53 +++++++++++++++++++++++++++++++++++++++----------
 fs/ceph/super.h |  3 ++-
 2 files changed, 44 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/io.c b/fs/ceph/io.c
index e10f44182a4c..2d10f49c93a9 100644
--- a/fs/ceph/io.c
+++ b/fs/ceph/io.c
@@ -21,14 +21,23 @@
 /* Call with exclusively locked inode->i_rwsem */
 static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
 {
+	bool is_odirect;
+
 	lockdep_assert_held_write(&inode->i_rwsem);
 
-	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) {
-		spin_lock(&ci->i_ceph_lock);
-		ci->i_ceph_flags &= ~CEPH_I_ODIRECT;
-		spin_unlock(&ci->i_ceph_lock);
-		inode_dio_wait(inode);
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (is_odirect) {
+		clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
 	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (is_odirect)
+		inode_dio_wait(inode);
 }
 
 /**
@@ -50,6 +59,7 @@ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
 int ceph_start_io_read(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
 	int err;
 
 	/* Be an optimist! */
@@ -57,7 +67,12 @@ int ceph_start_io_read(struct inode *inode)
 	if (err)
 		return err;
 
-	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT))
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (!is_odirect)
 		return 0;
 	up_read(&inode->i_rwsem);
 
@@ -116,12 +131,22 @@ ceph_end_io_write(struct inode *inode)
 /* Call with exclusively locked inode->i_rwsem */
 static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
 {
+	bool is_odirect;
+
 	lockdep_assert_held_write(&inode->i_rwsem);
 
-	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) {
-		spin_lock(&ci->i_ceph_lock);
-		ci->i_ceph_flags |= CEPH_I_ODIRECT;
-		spin_unlock(&ci->i_ceph_lock);
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (!is_odirect) {
+		set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (!is_odirect) {
 		/* FIXME: unmap_mapping_range? */
 		filemap_write_and_wait(inode->i_mapping);
 	}
@@ -146,6 +171,7 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
 int ceph_start_io_direct(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
 	int err;
 
 	/* Be an optimist! */
@@ -153,7 +179,12 @@ int ceph_start_io_direct(struct inode *inode)
 	if (err)
 		return err;
 
-	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (is_odirect)
 		return 0;
 	up_read(&inode->i_rwsem);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index cf176aab0f82..d1e81e11661b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -638,7 +638,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_FLUSH_SNAPS	(1 << 8)  /* need flush snapss */
 #define CEPH_I_ERROR_WRITE	(1 << 9) /* have seen write errors */
 #define CEPH_I_ERROR_FILELOCK	(1 << 10) /* have seen file lock errors */
-#define CEPH_I_ODIRECT		(1 << 11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT_BIT	(11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT		(1 << CEPH_I_ODIRECT_BIT)
 #define CEPH_ASYNC_CREATE_BIT	(12)	  /* async create in flight for this */
 #define CEPH_I_ASYNC_CREATE	(1 << CEPH_ASYNC_CREATE_BIT)
 #define CEPH_I_SHUTDOWN		(1 << 13) /* inode is no longer usable */

From 59699a5a7114f09f890e86c09a6b32afb5eaa64c Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Wed, 6 Aug 2025 11:48:53 +0200
Subject: [PATCH 239/352] libceph: make ceph_con_get_out_msg() return the
 message pointer

The caller in messenger_v1.c loads it anyway, so let's keep the
pointer in the register instead of reloading it from memory.  This
eliminates a tiny bit of unnecessary overhead.

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>
---
 include/linux/ceph/messenger.h | 2 +-
 net/ceph/messenger.c           | 4 ++--
 net/ceph/messenger_v1.c        | 3 +--
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 4b49592a738f..9ebcac2981fd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -550,7 +550,7 @@ void ceph_addr_set_port(struct ceph_entity_addr *addr, int p);
 void ceph_con_process_message(struct ceph_connection *con);
 int ceph_con_in_msg_alloc(struct ceph_connection *con,
 			  struct ceph_msg_header *hdr, int *skip);
-void ceph_con_get_out_msg(struct ceph_connection *con);
+struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con);
 
 /* messenger_v1.c */
 int ceph_con_v1_try_read(struct ceph_connection *con);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9f6d860411cb..b6c7bfc03503 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2110,7 +2110,7 @@ int ceph_con_in_msg_alloc(struct ceph_connection *con,
 	return ret;
 }
 
-void ceph_con_get_out_msg(struct ceph_connection *con)
+struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con)
 {
 	struct ceph_msg *msg;
 
@@ -2141,7 +2141,7 @@ void ceph_con_get_out_msg(struct ceph_connection *con)
 	 * message or in case of a fault.
 	 */
 	WARN_ON(con->out_msg);
-	con->out_msg = ceph_msg_get(msg);
+	return con->out_msg = ceph_msg_get(msg);
 }
 
 /*
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 0cb61c76b9b8..eebe4e19d75a 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -210,8 +210,7 @@ static void prepare_write_message(struct ceph_connection *con)
 			&con->v1.out_temp_ack);
 	}
 
-	ceph_con_get_out_msg(con);
-	m = con->out_msg;
+	m = ceph_con_get_out_msg(con);
 
 	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
 	     m, con->out_seq, le16_to_cpu(m->hdr.type),

From 7399212dcf64d90a6ab239bdd98bd325d922fc7e Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Wed, 6 Aug 2025 11:48:54 +0200
Subject: [PATCH 240/352] libceph: pass the message pointer instead of loading
 con->out_msg

This pointer is in a register anyway, so let's use that instead of
reloading from memory everywhere.

[ idryomov: formatting ]

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>
---
 include/linux/ceph/messenger.h |   4 +-
 net/ceph/messenger.c           |   4 +-
 net/ceph/messenger_v1.c        |  45 +++++----
 net/ceph/messenger_v2.c        | 168 +++++++++++++++++----------------
 4 files changed, 114 insertions(+), 107 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 9ebcac2981fd..6aa4c6478c9f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -555,7 +555,7 @@ struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con);
 /* messenger_v1.c */
 int ceph_con_v1_try_read(struct ceph_connection *con);
 int ceph_con_v1_try_write(struct ceph_connection *con);
-void ceph_con_v1_revoke(struct ceph_connection *con);
+void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg);
 void ceph_con_v1_revoke_incoming(struct ceph_connection *con);
 bool ceph_con_v1_opened(struct ceph_connection *con);
 void ceph_con_v1_reset_session(struct ceph_connection *con);
@@ -564,7 +564,7 @@ void ceph_con_v1_reset_protocol(struct ceph_connection *con);
 /* messenger_v2.c */
 int ceph_con_v2_try_read(struct ceph_connection *con);
 int ceph_con_v2_try_write(struct ceph_connection *con);
-void ceph_con_v2_revoke(struct ceph_connection *con);
+void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg);
 void ceph_con_v2_revoke_incoming(struct ceph_connection *con);
 bool ceph_con_v2_opened(struct ceph_connection *con);
 void ceph_con_v2_reset_session(struct ceph_connection *con);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index b6c7bfc03503..08a6a083609f 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1793,9 +1793,9 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 		WARN_ON(con->state != CEPH_CON_S_OPEN);
 		dout("%s con %p msg %p was sending\n", __func__, con, msg);
 		if (ceph_msgr2(from_msgr(con->msgr)))
-			ceph_con_v2_revoke(con);
+			ceph_con_v2_revoke(con, msg);
 		else
-			ceph_con_v1_revoke(con);
+			ceph_con_v1_revoke(con, msg);
 		ceph_msg_put(con->out_msg);
 		con->out_msg = NULL;
 	} else {
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index eebe4e19d75a..cc4a36ef8462 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -169,10 +169,9 @@ static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
  * Prepare footer for currently outgoing message, and finish things
  * off.  Assumes out_kvec* are already valid.. we just add on to the end.
  */
-static void prepare_write_message_footer(struct ceph_connection *con)
+static void prepare_write_message_footer(struct ceph_connection *con,
+					 struct ceph_msg *m)
 {
-	struct ceph_msg *m = con->out_msg;
-
 	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
 
 	dout("prepare_write_message_footer %p\n", con);
@@ -230,31 +229,31 @@ static void prepare_write_message(struct ceph_connection *con)
 
 	/* fill in hdr crc and finalize hdr */
 	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
-	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	memcpy(&con->v1.out_hdr, &con->out_msg->hdr, sizeof(con->v1.out_hdr));
+	m->hdr.crc = cpu_to_le32(crc);
+	memcpy(&con->v1.out_hdr, &m->hdr, sizeof(con->v1.out_hdr));
 
 	/* fill in front and middle crc, footer */
 	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
-	con->out_msg->footer.front_crc = cpu_to_le32(crc);
+	m->footer.front_crc = cpu_to_le32(crc);
 	if (m->middle) {
 		crc = crc32c(0, m->middle->vec.iov_base,
 				m->middle->vec.iov_len);
-		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
+		m->footer.middle_crc = cpu_to_le32(crc);
 	} else
-		con->out_msg->footer.middle_crc = 0;
+		m->footer.middle_crc = 0;
 	dout("%s front_crc %u middle_crc %u\n", __func__,
-	     le32_to_cpu(con->out_msg->footer.front_crc),
-	     le32_to_cpu(con->out_msg->footer.middle_crc));
-	con->out_msg->footer.flags = 0;
+	     le32_to_cpu(m->footer.front_crc),
+	     le32_to_cpu(m->footer.middle_crc));
+	m->footer.flags = 0;
 
 	/* is there a data payload? */
-	con->out_msg->footer.data_crc = 0;
+	m->footer.data_crc = 0;
 	if (m->data_length) {
-		prepare_message_data(con->out_msg, m->data_length);
+		prepare_message_data(m, m->data_length);
 		con->v1.out_more = 1;  /* data + footer will follow */
 	} else {
 		/* no, queue up footer too and be done */
-		prepare_write_message_footer(con);
+		prepare_write_message_footer(con, m);
 	}
 
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
@@ -461,9 +460,9 @@ out:
  *  0 -> socket full, but more to do
  * <0 -> error
  */
-static int write_partial_message_data(struct ceph_connection *con)
+static int write_partial_message_data(struct ceph_connection *con,
+				      struct ceph_msg *msg)
 {
-	struct ceph_msg *msg = con->out_msg;
 	struct ceph_msg_data_cursor *cursor = &msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
 	u32 crc;
@@ -515,7 +514,7 @@ static int write_partial_message_data(struct ceph_connection *con)
 	else
 		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
 	con_out_kvec_reset(con);
-	prepare_write_message_footer(con);
+	prepare_write_message_footer(con, msg);
 
 	return 1;	/* must return > 0 to indicate success */
 }
@@ -1471,6 +1470,7 @@ bad_tag:
  */
 int ceph_con_v1_try_write(struct ceph_connection *con)
 {
+	struct ceph_msg *msg;
 	int ret = 1;
 
 	dout("try_write start %p state %d\n", con, con->state);
@@ -1517,14 +1517,15 @@ more:
 	}
 
 	/* msg pages? */
-	if (con->out_msg) {
+	msg = con->out_msg;
+	if (msg) {
 		if (con->v1.out_msg_done) {
-			ceph_msg_put(con->out_msg);
+			ceph_msg_put(msg);
 			con->out_msg = NULL;   /* we're done with this one */
 			goto do_next;
 		}
 
-		ret = write_partial_message_data(con);
+		ret = write_partial_message_data(con, msg);
 		if (ret == 1)
 			goto more;  /* we need to send the footer, too! */
 		if (ret == 0)
@@ -1563,10 +1564,8 @@ out:
 	return ret;
 }
 
-void ceph_con_v1_revoke(struct ceph_connection *con)
+void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg)
 {
-	struct ceph_msg *msg = con->out_msg;
-
 	WARN_ON(con->v1.out_skip);
 	/* footer */
 	if (con->v1.out_msg_done) {
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c54c8b5a6526..b44e936f3865 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1560,10 +1560,11 @@ static int prepare_ack(struct ceph_connection *con)
 	return prepare_control(con, FRAME_TAG_ACK, con->v2.out_buf, 8);
 }
 
-static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted)
+static void prepare_epilogue_plain(struct ceph_connection *con,
+				   struct ceph_msg *msg, bool aborted)
 {
 	dout("%s con %p msg %p aborted %d crcs %u %u %u\n", __func__, con,
-	     con->out_msg, aborted, con->v2.out_epil.front_crc,
+	     msg, aborted, con->v2.out_epil.front_crc,
 	     con->v2.out_epil.middle_crc, con->v2.out_epil.data_crc);
 
 	encode_epilogue_plain(con, aborted);
@@ -1574,10 +1575,9 @@ static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted)
  * For "used" empty segments, crc is -1.  For unused (trailing)
  * segments, crc is 0.
  */
-static void prepare_message_plain(struct ceph_connection *con)
+static void prepare_message_plain(struct ceph_connection *con,
+				  struct ceph_msg *msg)
 {
-	struct ceph_msg *msg = con->out_msg;
-
 	prepare_head_plain(con, con->v2.out_buf,
 			   sizeof(struct ceph_msg_header2), NULL, 0, false);
 
@@ -1618,7 +1618,7 @@ static void prepare_message_plain(struct ceph_connection *con)
 		con->v2.out_state = OUT_S_QUEUE_DATA;
 	} else {
 		con->v2.out_epil.data_crc = 0;
-		prepare_epilogue_plain(con, false);
+		prepare_epilogue_plain(con, msg, false);
 		con->v2.out_state = OUT_S_FINISH_MESSAGE;
 	}
 }
@@ -1630,7 +1630,8 @@ static void prepare_message_plain(struct ceph_connection *con)
  * allocate pages for the entire tail of the message (currently up
  * to ~32M) and two sgs arrays (up to ~256K each)...
  */
-static int prepare_message_secure(struct ceph_connection *con)
+static int prepare_message_secure(struct ceph_connection *con,
+				  struct ceph_msg *msg)
 {
 	void *zerop = page_address(ceph_zero_page);
 	struct sg_table enc_sgt = {};
@@ -1645,7 +1646,7 @@ static int prepare_message_secure(struct ceph_connection *con)
 	if (ret)
 		return ret;
 
-	tail_len = tail_onwire_len(con->out_msg, true);
+	tail_len = tail_onwire_len(msg, true);
 	if (!tail_len) {
 		/*
 		 * Empty message: once the head is written,
@@ -1656,7 +1657,7 @@ static int prepare_message_secure(struct ceph_connection *con)
 	}
 
 	encode_epilogue_secure(con, false);
-	ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop,
+	ret = setup_message_sgs(&sgt, msg, zerop, zerop, zerop,
 				&con->v2.out_epil, NULL, 0, false);
 	if (ret)
 		goto out;
@@ -1685,7 +1686,7 @@ static int prepare_message_secure(struct ceph_connection *con)
 		goto out;
 
 	dout("%s con %p msg %p sg_cnt %d enc_page_cnt %d\n", __func__, con,
-	     con->out_msg, sgt.orig_nents, enc_page_cnt);
+	     msg, sgt.orig_nents, enc_page_cnt);
 	con->v2.out_state = OUT_S_QUEUE_ENC_PAGE;
 
 out:
@@ -1694,19 +1695,19 @@ out:
 	return ret;
 }
 
-static int prepare_message(struct ceph_connection *con)
+static int prepare_message(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	int lens[] = {
 		sizeof(struct ceph_msg_header2),
-		front_len(con->out_msg),
-		middle_len(con->out_msg),
-		data_len(con->out_msg)
+		front_len(msg),
+		middle_len(msg),
+		data_len(msg)
 	};
 	struct ceph_frame_desc desc;
 	int ret;
 
 	dout("%s con %p msg %p logical %d+%d+%d+%d\n", __func__, con,
-	     con->out_msg, lens[0], lens[1], lens[2], lens[3]);
+	     msg, lens[0], lens[1], lens[2], lens[3]);
 
 	if (con->in_seq > con->in_seq_acked) {
 		dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con,
@@ -1717,15 +1718,15 @@ static int prepare_message(struct ceph_connection *con)
 	reset_out_kvecs(con);
 	init_frame_desc(&desc, FRAME_TAG_MESSAGE, lens, 4);
 	encode_preamble(&desc, con->v2.out_buf);
-	fill_header2(CTRL_BODY(con->v2.out_buf), &con->out_msg->hdr,
+	fill_header2(CTRL_BODY(con->v2.out_buf), &msg->hdr,
 		     con->in_seq_acked);
 
 	if (con_secure(con)) {
-		ret = prepare_message_secure(con);
+		ret = prepare_message_secure(con, msg);
 		if (ret)
 			return ret;
 	} else {
-		prepare_message_plain(con);
+		prepare_message_plain(con, msg);
 	}
 
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
@@ -3153,20 +3154,20 @@ int ceph_con_v2_try_read(struct ceph_connection *con)
 	}
 }
 
-static void queue_data(struct ceph_connection *con)
+static void queue_data(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	struct bio_vec bv;
 
 	con->v2.out_epil.data_crc = -1;
-	ceph_msg_data_cursor_init(&con->v2.out_cursor, con->out_msg,
-				  data_len(con->out_msg));
+	ceph_msg_data_cursor_init(&con->v2.out_cursor, msg,
+				  data_len(msg));
 
 	get_bvec_at(&con->v2.out_cursor, &bv);
 	set_out_bvec(con, &bv, true);
 	con->v2.out_state = OUT_S_QUEUE_DATA_CONT;
 }
 
-static void queue_data_cont(struct ceph_connection *con)
+static void queue_data_cont(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	struct bio_vec bv;
 
@@ -3187,7 +3188,7 @@ static void queue_data_cont(struct ceph_connection *con)
 	 * we are done.
 	 */
 	reset_out_kvecs(con);
-	prepare_epilogue_plain(con, false);
+	prepare_epilogue_plain(con, msg, false);
 	con->v2.out_state = OUT_S_FINISH_MESSAGE;
 }
 
@@ -3219,7 +3220,7 @@ static void queue_enc_page(struct ceph_connection *con)
 	con->v2.out_state = OUT_S_FINISH_MESSAGE;
 }
 
-static void queue_zeros(struct ceph_connection *con)
+static void queue_zeros(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	dout("%s con %p out_zero %d\n", __func__, con, con->v2.out_zero);
 
@@ -3236,7 +3237,7 @@ static void queue_zeros(struct ceph_connection *con)
 	 * Once it's written, we are done patching up for the revoke.
 	 */
 	reset_out_kvecs(con);
-	prepare_epilogue_plain(con, true);
+	prepare_epilogue_plain(con, msg, true);
 	con->v2.out_state = OUT_S_FINISH_MESSAGE;
 }
 
@@ -3263,6 +3264,7 @@ static void finish_message(struct ceph_connection *con)
 
 static int populate_out_iter(struct ceph_connection *con)
 {
+	struct ceph_msg *msg;
 	int ret;
 
 	dout("%s con %p state %d out_state %d\n", __func__, con, con->state,
@@ -3278,18 +3280,18 @@ static int populate_out_iter(struct ceph_connection *con)
 	switch (con->v2.out_state) {
 	case OUT_S_QUEUE_DATA:
 		WARN_ON(!con->out_msg);
-		queue_data(con);
+		queue_data(con, con->out_msg);
 		goto populated;
 	case OUT_S_QUEUE_DATA_CONT:
 		WARN_ON(!con->out_msg);
-		queue_data_cont(con);
+		queue_data_cont(con, con->out_msg);
 		goto populated;
 	case OUT_S_QUEUE_ENC_PAGE:
 		queue_enc_page(con);
 		goto populated;
 	case OUT_S_QUEUE_ZEROS:
 		WARN_ON(con->out_msg);  /* revoked */
-		queue_zeros(con);
+		queue_zeros(con, con->out_msg);
 		goto populated;
 	case OUT_S_FINISH_MESSAGE:
 		finish_message(con);
@@ -3309,8 +3311,8 @@ static int populate_out_iter(struct ceph_connection *con)
 			return ret;
 		}
 	} else if (!list_empty(&con->out_queue)) {
-		ceph_con_get_out_msg(con);
-		ret = prepare_message(con);
+		msg = ceph_con_get_out_msg(con);
+		ret = prepare_message(con, msg);
 		if (ret) {
 			pr_err("prepare_message failed: %d\n", ret);
 			return ret;
@@ -3422,17 +3424,18 @@ static u32 crc32c_zeros(u32 crc, int zero_len)
 	return crc;
 }
 
-static void prepare_zero_front(struct ceph_connection *con, int resid)
+static void prepare_zero_front(struct ceph_connection *con,
+			       struct ceph_msg *msg, int resid)
 {
 	int sent;
 
-	WARN_ON(!resid || resid > front_len(con->out_msg));
-	sent = front_len(con->out_msg) - resid;
+	WARN_ON(!resid || resid > front_len(msg));
+	sent = front_len(msg) - resid;
 	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
 
 	if (sent) {
 		con->v2.out_epil.front_crc =
-			crc32c(-1, con->out_msg->front.iov_base, sent);
+			crc32c(-1, msg->front.iov_base, sent);
 		con->v2.out_epil.front_crc =
 			crc32c_zeros(con->v2.out_epil.front_crc, resid);
 	} else {
@@ -3443,17 +3446,18 @@ static void prepare_zero_front(struct ceph_connection *con, int resid)
 	out_zero_add(con, resid);
 }
 
-static void prepare_zero_middle(struct ceph_connection *con, int resid)
+static void prepare_zero_middle(struct ceph_connection *con,
+				struct ceph_msg *msg, int resid)
 {
 	int sent;
 
-	WARN_ON(!resid || resid > middle_len(con->out_msg));
-	sent = middle_len(con->out_msg) - resid;
+	WARN_ON(!resid || resid > middle_len(msg));
+	sent = middle_len(msg) - resid;
 	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
 
 	if (sent) {
 		con->v2.out_epil.middle_crc =
-			crc32c(-1, con->out_msg->middle->vec.iov_base, sent);
+			crc32c(-1, msg->middle->vec.iov_base, sent);
 		con->v2.out_epil.middle_crc =
 			crc32c_zeros(con->v2.out_epil.middle_crc, resid);
 	} else {
@@ -3464,61 +3468,64 @@ static void prepare_zero_middle(struct ceph_connection *con, int resid)
 	out_zero_add(con, resid);
 }
 
-static void prepare_zero_data(struct ceph_connection *con)
+static void prepare_zero_data(struct ceph_connection *con,
+			      struct ceph_msg *msg)
 {
 	dout("%s con %p\n", __func__, con);
-	con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(con->out_msg));
-	out_zero_add(con, data_len(con->out_msg));
+	con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(msg));
+	out_zero_add(con, data_len(msg));
 }
 
-static void revoke_at_queue_data(struct ceph_connection *con)
+static void revoke_at_queue_data(struct ceph_connection *con,
+				 struct ceph_msg *msg)
 {
 	int boundary;
 	int resid;
 
-	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!data_len(msg));
 	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
 	resid = iov_iter_count(&con->v2.out_iter);
 
-	boundary = front_len(con->out_msg) + middle_len(con->out_msg);
+	boundary = front_len(msg) + middle_len(msg);
 	if (resid > boundary) {
 		resid -= boundary;
 		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
 		dout("%s con %p was sending head\n", __func__, con);
-		if (front_len(con->out_msg))
-			prepare_zero_front(con, front_len(con->out_msg));
-		if (middle_len(con->out_msg))
-			prepare_zero_middle(con, middle_len(con->out_msg));
-		prepare_zero_data(con);
+		if (front_len(msg))
+			prepare_zero_front(con, msg, front_len(msg));
+		if (middle_len(msg))
+			prepare_zero_middle(con, msg, middle_len(msg));
+		prepare_zero_data(con, msg);
 		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
 		con->v2.out_state = OUT_S_QUEUE_ZEROS;
 		return;
 	}
 
-	boundary = middle_len(con->out_msg);
+	boundary = middle_len(msg);
 	if (resid > boundary) {
 		resid -= boundary;
 		dout("%s con %p was sending front\n", __func__, con);
-		prepare_zero_front(con, resid);
-		if (middle_len(con->out_msg))
-			prepare_zero_middle(con, middle_len(con->out_msg));
-		prepare_zero_data(con);
-		queue_zeros(con);
+		prepare_zero_front(con, msg, resid);
+		if (middle_len(msg))
+			prepare_zero_middle(con, msg, middle_len(msg));
+		prepare_zero_data(con, msg);
+		queue_zeros(con, msg);
 		return;
 	}
 
 	WARN_ON(!resid);
 	dout("%s con %p was sending middle\n", __func__, con);
-	prepare_zero_middle(con, resid);
-	prepare_zero_data(con);
-	queue_zeros(con);
+	prepare_zero_middle(con, msg, resid);
+	prepare_zero_data(con, msg);
+	queue_zeros(con, msg);
 }
 
-static void revoke_at_queue_data_cont(struct ceph_connection *con)
+static void revoke_at_queue_data_cont(struct ceph_connection *con,
+				      struct ceph_msg *msg)
 {
 	int sent, resid;  /* current piece of data */
 
-	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!data_len(msg));
 	WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter));
 	resid = iov_iter_count(&con->v2.out_iter);
 	WARN_ON(!resid || resid > con->v2.out_bvec.bv_len);
@@ -3537,10 +3544,11 @@ static void revoke_at_queue_data_cont(struct ceph_connection *con)
 
 	con->v2.out_iter.count -= resid;
 	out_zero_add(con, con->v2.out_cursor.total_resid);
-	queue_zeros(con);
+	queue_zeros(con, msg);
 }
 
-static void revoke_at_finish_message(struct ceph_connection *con)
+static void revoke_at_finish_message(struct ceph_connection *con,
+				     struct ceph_msg *msg)
 {
 	int boundary;
 	int resid;
@@ -3548,39 +3556,39 @@ static void revoke_at_finish_message(struct ceph_connection *con)
 	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
 	resid = iov_iter_count(&con->v2.out_iter);
 
-	if (!front_len(con->out_msg) && !middle_len(con->out_msg) &&
-	    !data_len(con->out_msg)) {
+	if (!front_len(msg) && !middle_len(msg) &&
+	    !data_len(msg)) {
 		WARN_ON(!resid || resid > MESSAGE_HEAD_PLAIN_LEN);
 		dout("%s con %p was sending head (empty message) - noop\n",
 		     __func__, con);
 		return;
 	}
 
-	boundary = front_len(con->out_msg) + middle_len(con->out_msg) +
+	boundary = front_len(msg) + middle_len(msg) +
 		   CEPH_EPILOGUE_PLAIN_LEN;
 	if (resid > boundary) {
 		resid -= boundary;
 		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
 		dout("%s con %p was sending head\n", __func__, con);
-		if (front_len(con->out_msg))
-			prepare_zero_front(con, front_len(con->out_msg));
-		if (middle_len(con->out_msg))
-			prepare_zero_middle(con, middle_len(con->out_msg));
+		if (front_len(msg))
+			prepare_zero_front(con, msg, front_len(msg));
+		if (middle_len(msg))
+			prepare_zero_middle(con, msg, middle_len(msg));
 		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
 		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
 		con->v2.out_state = OUT_S_QUEUE_ZEROS;
 		return;
 	}
 
-	boundary = middle_len(con->out_msg) + CEPH_EPILOGUE_PLAIN_LEN;
+	boundary = middle_len(msg) + CEPH_EPILOGUE_PLAIN_LEN;
 	if (resid > boundary) {
 		resid -= boundary;
 		dout("%s con %p was sending front\n", __func__, con);
-		prepare_zero_front(con, resid);
-		if (middle_len(con->out_msg))
-			prepare_zero_middle(con, middle_len(con->out_msg));
+		prepare_zero_front(con, msg, resid);
+		if (middle_len(msg))
+			prepare_zero_middle(con, msg, middle_len(msg));
 		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
-		queue_zeros(con);
+		queue_zeros(con, msg);
 		return;
 	}
 
@@ -3588,9 +3596,9 @@ static void revoke_at_finish_message(struct ceph_connection *con)
 	if (resid > boundary) {
 		resid -= boundary;
 		dout("%s con %p was sending middle\n", __func__, con);
-		prepare_zero_middle(con, resid);
+		prepare_zero_middle(con, msg, resid);
 		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
-		queue_zeros(con);
+		queue_zeros(con, msg);
 		return;
 	}
 
@@ -3598,7 +3606,7 @@ static void revoke_at_finish_message(struct ceph_connection *con)
 	dout("%s con %p was sending epilogue - noop\n", __func__, con);
 }
 
-void ceph_con_v2_revoke(struct ceph_connection *con)
+void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	WARN_ON(con->v2.out_zero);
 
@@ -3611,13 +3619,13 @@ void ceph_con_v2_revoke(struct ceph_connection *con)
 
 	switch (con->v2.out_state) {
 	case OUT_S_QUEUE_DATA:
-		revoke_at_queue_data(con);
+		revoke_at_queue_data(con, msg);
 		break;
 	case OUT_S_QUEUE_DATA_CONT:
-		revoke_at_queue_data_cont(con);
+		revoke_at_queue_data_cont(con, msg);
 		break;
 	case OUT_S_FINISH_MESSAGE:
-		revoke_at_finish_message(con);
+		revoke_at_finish_message(con, msg);
 		break;
 	default:
 		WARN(1, "bad out_state %d", con->v2.out_state);

From 6140f1d43ba9425dc55b12bdfd8877b0c5118d9a Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Wed, 6 Aug 2025 11:48:55 +0200
Subject: [PATCH 241/352] libceph: add empty check to ceph_con_get_out_msg()

This moves the list_empty() checks from the two callers (v1 and v2)
into the base messenger.c library.  Now the v1/v2 specializations do
not need to know about con->out_queue; that implementation detail is
now hidden behind the ceph_con_get_out_msg() function.

[ idryomov: instead of changing prepare_write_message() to return
  a bool, move ceph_con_get_out_msg() call out to arrive to the same
  pattern as in messenger_v2.c ]

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>
---
 net/ceph/messenger.c    |  4 +++-
 net/ceph/messenger_v1.c | 10 ++++------
 net/ceph/messenger_v2.c |  3 +--
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 08a6a083609f..878bbfe770b1 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2114,7 +2114,9 @@ struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con)
 {
 	struct ceph_msg *msg;
 
-	BUG_ON(list_empty(&con->out_queue));
+	if (list_empty(&con->out_queue))
+		return NULL;
+
 	msg = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
 	WARN_ON(msg->con != con);
 
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index cc4a36ef8462..c9e002d96319 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -191,9 +191,9 @@ static void prepare_write_message_footer(struct ceph_connection *con,
 /*
  * Prepare headers for the next outgoing message.
  */
-static void prepare_write_message(struct ceph_connection *con)
+static void prepare_write_message(struct ceph_connection *con,
+				  struct ceph_msg *m)
 {
-	struct ceph_msg *m;
 	u32 crc;
 
 	con_out_kvec_reset(con);
@@ -209,8 +209,6 @@ static void prepare_write_message(struct ceph_connection *con)
 			&con->v1.out_temp_ack);
 	}
 
-	m = ceph_con_get_out_msg(con);
-
 	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
 	     m, con->out_seq, le16_to_cpu(m->hdr.type),
 	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
@@ -1545,8 +1543,8 @@ do_next:
 			goto more;
 		}
 		/* is anything else pending? */
-		if (!list_empty(&con->out_queue)) {
-			prepare_write_message(con);
+		if ((msg = ceph_con_get_out_msg(con)) != NULL) {
+			prepare_write_message(con, msg);
 			goto more;
 		}
 		if (con->in_seq > con->in_seq_acked) {
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index b44e936f3865..9e39378eda00 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -3310,8 +3310,7 @@ static int populate_out_iter(struct ceph_connection *con)
 			pr_err("prepare_keepalive2 failed: %d\n", ret);
 			return ret;
 		}
-	} else if (!list_empty(&con->out_queue)) {
-		msg = ceph_con_get_out_msg(con);
+	} else if ((msg = ceph_con_get_out_msg(con)) != NULL) {
 		ret = prepare_message(con, msg);
 		if (ret) {
 			pr_err("prepare_message failed: %d\n", ret);

From 98a2850de49c10a1a09642e17978b925f95e6029 Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Thu, 28 Aug 2025 11:44:42 -0700
Subject: [PATCH 242/352] ceph: fix potential NULL dereference issue in
 ceph_fill_trace()

The Coverity Scan service has detected a potential dereference of
an explicit NULL value in ceph_fill_trace() [1].

The variable in is declared in the beggining of
ceph_fill_trace() [2]:

struct inode *in = NULL;

However, the initialization of the variable is happening under
condition [3]:

if (rinfo->head->is_target) {
    <skipped>
    in = req->r_target_inode;
    <skipped>
}

Potentially, if rinfo->head->is_target == FALSE, then
in variable continues to be NULL and later the dereference of
NULL value could happen in ceph_fill_trace() logic [4,5]:

else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
            req->r_op == CEPH_MDS_OP_MKSNAP) &&
            test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
             !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
<skipped>
     ihold(in);
     err = splice_dentry(&req->r_dentry, in);
     if (err < 0)
         goto done;
}

This patch adds the checking of in variable for NULL value
and it returns -EINVAL error code if it has NULL value.

v2
Alex Markuze suggested to add unlikely macro
in the checking condition.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1141197
[2] https://elixir.bootlin.com/linux/v6.17-rc3/source/fs/ceph/inode.c#L1522
[3] https://elixir.bootlin.com/linux/v6.17-rc3/source/fs/ceph/inode.c#L1629
[4] https://elixir.bootlin.com/linux/v6.17-rc3/source/fs/ceph/inode.c#L1745
[5] https://elixir.bootlin.com/linux/v6.17-rc3/source/fs/ceph/inode.c#L1777

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/inode.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f67025465de0..03a8f2e3341e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1793,6 +1793,11 @@ retry_lookup:
 			goto done;
 		}
 
+		if (unlikely(!in)) {
+			err = -EINVAL;
+			goto done;
+		}
+
 		/* attach proper inode */
 		if (d_really_is_negative(dn)) {
 			ceph_dir_clear_ordered(dir);
@@ -1828,6 +1833,12 @@ retry_lookup:
 		doutc(cl, " linking snapped dir %p to dn %p\n", in,
 		      req->r_dentry);
 		ceph_dir_clear_ordered(dir);
+
+		if (unlikely(!in)) {
+			err = -EINVAL;
+			goto done;
+		}
+
 		ihold(in);
 		err = splice_dentry(&req->r_dentry, in);
 		if (err < 0)

From c66120c84295a0495eb46dcfba829457acd6ef7d Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Tue, 2 Sep 2025 12:08:45 -0700
Subject: [PATCH 243/352] ceph: cleanup in ceph_alloc_readdir_reply_buffer()

The Coverity Scan service has reported potential issue
in ceph_alloc_readdir_reply_buffer() [1]. If order could
be negative one, then it expects the issue in the logic:

num_entries = (PAGE_SIZE << order) / size;

Technically speaking, this logic [2] should prevent from
making the order variable negative:

if (!rinfo->dir_entries)
    return -ENOMEM;

However, the allocation logic requires some cleanup.
This patch makes sure that calculated bytes count
will never exceed ULONG_MAX before get_order()
calculation. And it adds the checking of order
variable on negative value to guarantee that second
half of the function's code will never operate by
negative value of order variable even if something
will be wrong or to be changed in the first half of
the function's logic.

v2
Alex Markuze suggested to add unlikely() macro
for introduced condition checks.

[1] https://scan5.scan.coverity.com/#/project-view/64304/10063?selectedIssue=1198252
[2] https://elixir.bootlin.com/linux/v6.17-rc3/source/fs/ceph/mds_client.c#L2553

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index aa2f74142cf4..8104350b1553 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2533,6 +2533,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
 	struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options;
 	size_t size = sizeof(struct ceph_mds_reply_dir_entry);
 	unsigned int num_entries;
+	u64 bytes_count;
 	int order;
 
 	spin_lock(&ci->i_ceph_lock);
@@ -2541,7 +2542,11 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
 	num_entries = max(num_entries, 1U);
 	num_entries = min(num_entries, opt->max_readdir);
 
-	order = get_order(size * num_entries);
+	bytes_count = (u64)size * num_entries;
+	if (unlikely(bytes_count > ULONG_MAX))
+		bytes_count = ULONG_MAX;
+
+	order = get_order((unsigned long)bytes_count);
 	while (order >= 0) {
 		rinfo->dir_entries = (void*)__get_free_pages(GFP_KERNEL |
 							     __GFP_NOWARN |
@@ -2551,7 +2556,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
 			break;
 		order--;
 	}
-	if (!rinfo->dir_entries)
+	if (!rinfo->dir_entries || unlikely(order < 0))
 		return -ENOMEM;
 
 	num_entries = (PAGE_SIZE << order) / size;

From 22c73d52a6d05c5a2053385c0d6cd9984732799d Mon Sep 17 00:00:00 2001
From: Kotresh HR <khiremat@redhat.com>
Date: Thu, 11 Sep 2025 15:02:35 +0530
Subject: [PATCH 244/352] ceph: fix multifs mds auth caps issue

The mds auth caps check should also validate the
fsname along with the associated caps. Not doing
so would result in applying the mds auth caps of
one fs on to the other fs in a multifs ceph cluster.
The bug causes multiple issues w.r.t user
authentication, following is one such example.

Steps to Reproduce (on vstart cluster):
1. Create two file systems in a cluster, say 'fsname1' and 'fsname2'
2. Authorize read only permission to the user 'client.usr' on fs 'fsname1'
    $ceph fs authorize fsname1 client.usr / r
3. Authorize read and write permission to the same user 'client.usr' on fs 'fsname2'
    $ceph fs authorize fsname2 client.usr / rw
4. Update the keyring
    $ceph auth get client.usr >> ./keyring

With above permssions for the user 'client.usr', following is the
expectation.
  a. The 'client.usr' should be able to only read the contents
     and not allowed to create or delete files on file system 'fsname1'.
  b. The 'client.usr' should be able to read/write on file system 'fsname2'.

But, with this bug, the 'client.usr' is allowed to read/write on file
system 'fsname1'. See below.

5. Mount the file system 'fsname1' with the user 'client.usr'
     $sudo bin/mount.ceph usr@.fsname1=/ /kmnt_fsname1_usr/
6. Try creating a file on file system 'fsname1' with user 'client.usr'. This
   should fail but passes with this bug.
     $touch /kmnt_fsname1_usr/file1
7. Mount the file system 'fsname1' with the user 'client.admin' and create a
   file.
     $sudo bin/mount.ceph admin@.fsname1=/ /kmnt_fsname1_admin
     $echo "data" > /kmnt_fsname1_admin/admin_file1
8. Try removing an existing file on file system 'fsname1' with the user
   'client.usr'. This shoudn't succeed but succeeds with the bug.
     $rm -f /kmnt_fsname1_usr/admin_file1

For more information, please take a look at the corresponding mds/fuse patch
and tests added by looking into the tracker mentioned below.

v2: Fix a possible null dereference in doutc
v3: Don't store fsname from mdsmap, validate against
    ceph_mount_options's fsname and use it
v4: Code refactor, better warning message and
    fix possible compiler warning

[ Slava.Dubeyko: "fsname check failed" -> "fsname mismatch" ]

Link: https://tracker.ceph.com/issues/72167
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c |  8 ++++++++
 fs/ceph/mdsmap.c     | 14 +++++++++++++-
 fs/ceph/super.c      | 14 --------------
 fs/ceph/super.h      | 14 ++++++++++++++
 4 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 8104350b1553..93650508d41a 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5655,11 +5655,19 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc,
 	u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid);
 	u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid);
 	struct ceph_client *cl = mdsc->fsc->client;
+	const char *fs_name = mdsc->fsc->mount_options->mds_namespace;
 	const char *spath = mdsc->fsc->mount_options->server_path;
 	bool gid_matched = false;
 	u32 gid, tlen, len;
 	int i, j;
 
+	doutc(cl, "fsname check fs_name=%s  match.fs_name=%s\n",
+	      fs_name, auth->match.fs_name ? auth->match.fs_name : "");
+	if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) {
+		/* fsname mismatch, try next one */
+		return 0;
+	}
+
 	doutc(cl, "match.uid %lld\n", auth->match.uid);
 	if (auth->match.uid != MDS_AUTH_UID_ANY) {
 		if (auth->match.uid != caller_uid)
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 8109aba66e02..2c7b151a7c95 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -353,10 +353,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
 		__decode_and_drop_type(p, end, u8, bad_ext);
 	}
 	if (mdsmap_ev >= 8) {
+		u32 fsname_len;
 		/* enabled */
 		ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
 		/* fs_name */
-		ceph_decode_skip_string(p, end, bad_ext);
+		ceph_decode_32_safe(p, end, fsname_len, bad_ext);
+
+		/* validate fsname against mds_namespace */
+		if (!namespace_equals(mdsc->fsc->mount_options, *p,
+				      fsname_len)) {
+			pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n",
+				       (int)fsname_len, (char *)*p,
+				       mdsc->fsc->mount_options->mds_namespace);
+			goto bad;
+		}
+		/* skip fsname after validation */
+		ceph_decode_skip_n(p, end, fsname_len, bad);
 	}
 	/* damaged */
 	if (mdsmap_ev >= 9) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c3eb651862c5..ebef5244ae25 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -246,20 +246,6 @@ static void canonicalize_path(char *path)
 	path[j] = '\0';
 }
 
-/*
- * Check if the mds namespace in ceph_mount_options matches
- * the passed in namespace string. First time match (when
- * ->mds_namespace is NULL) is treated specially, since
- * ->mds_namespace needs to be initialized by the caller.
- */
-static int namespace_equals(struct ceph_mount_options *fsopt,
-			    const char *namespace, size_t len)
-{
-	return !(fsopt->mds_namespace &&
-		 (strlen(fsopt->mds_namespace) != len ||
-		  strncmp(fsopt->mds_namespace, namespace, len)));
-}
-
 static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end,
 				 struct fs_context *fc)
 {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d1e81e11661b..de6dce077da1 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -104,6 +104,20 @@ struct ceph_mount_options {
 	struct fscrypt_dummy_policy dummy_enc_policy;
 };
 
+/*
+ * Check if the mds namespace in ceph_mount_options matches
+ * the passed in namespace string. First time match (when
+ * ->mds_namespace is NULL) is treated specially, since
+ * ->mds_namespace needs to be initialized by the caller.
+ */
+static inline int namespace_equals(struct ceph_mount_options *fsopt,
+				   const char *namespace, size_t len)
+{
+	return !(fsopt->mds_namespace &&
+		 (strlen(fsopt->mds_namespace) != len ||
+		  strncmp(fsopt->mds_namespace, namespace, len)));
+}
+
 /* mount state */
 enum {
 	CEPH_MOUNT_MOUNTING,

From d74d6c0e98958aa0bdb6f0a93258a856bda58b97 Mon Sep 17 00:00:00 2001
From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Date: Tue, 2 Sep 2025 13:09:58 -0700
Subject: [PATCH 245/352] ceph: add bug tracking system info to MAINTAINERS

This patch adds information about Ceph bug tracking system.

[ idryomov: add the same for RBD, don't mention include/linux/ceph/
  again ]

Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 97d958c945e4..16e23b76b0bf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5622,6 +5622,7 @@ M:	Xiubo Li <xiubli@redhat.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
+B:	https://tracker.ceph.com/
 T:	git https://github.com/ceph/ceph-client.git
 F:	include/linux/ceph/
 F:	include/linux/crush/
@@ -5633,6 +5634,7 @@ M:	Ilya Dryomov <idryomov@gmail.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
+B:	https://tracker.ceph.com/
 T:	git https://github.com/ceph/ceph-client.git
 F:	Documentation/filesystems/ceph.rst
 F:	fs/ceph/
@@ -20980,6 +20982,7 @@ R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
+B:	https://tracker.ceph.com/
 T:	git https://github.com/ceph/ceph-client.git
 F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c

From de4cbd704731778a2dc833ce5a24b38e5d672c05 Mon Sep 17 00:00:00 2001
From: Ankit Khushwaha <ankitkhushwaha.linux@gmail.com>
Date: Wed, 8 Oct 2025 22:55:16 +0530
Subject: [PATCH 246/352] ring buffer: Propagate __rb_map_vma return value to
 caller

The return value from `__rb_map_vma()`, which rejects writable or
executable mappings (VM_WRITE, VM_EXEC, or !VM_MAYSHARE), was being
ignored. As a result the caller of `__rb_map_vma` always returned 0
even when the mapping had actually failed, allowing it to proceed
with an invalid VMA.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20251008172516.20697-1-ankitkhushwaha.linux@gmail.com
Fixes: 117c39200d9d7 ("ring-buffer: Introducing ring-buffer mapping functions")
Reported-by: syzbot+ddc001b92c083dbf2b97@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?id=194151be8eaebd826005329b2e123aecae714bdb
Signed-off-by: Ankit Khushwaha <ankitkhushwaha.linux@gmail.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 43460949ad3f..1244d2c5c384 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7273,7 +7273,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		atomic_dec(&cpu_buffer->resize_disabled);
 	}
 
-	return 0;
+	return err;
 }
 
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)

From 64cf7d058a005c5c31eb8a0b741f35dc12915d18 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 8 Oct 2025 12:45:10 -0400
Subject: [PATCH 247/352] tracing: Have trace_marker use per-cpu data to read
 user space

It was reported that using __copy_from_user_inatomic() can actually
schedule. Which is bad when preemption is disabled. Even though there's
logic to check in_atomic() is set, but this is a nop when the kernel is
configured with PREEMPT_NONE. This is due to page faulting and the code
could schedule with preemption disabled.

Link: https://lore.kernel.org/all/20250819105152.2766363-1-luogengkun@huaweicloud.com/

The solution was to change the __copy_from_user_inatomic() to
copy_from_user_nofault(). But then it was reported that this caused a
regression in Android. There's several applications writing into
trace_marker() in Android, but now instead of showing the expected data,
it is showing:

  tracing_mark_write: <faulted>

After reverting the conversion to copy_from_user_nofault(), Android was
able to get the data again.

Writes to the trace_marker is a way to efficiently and quickly enter data
into the Linux tracing buffer. It takes no locks and was designed to be as
non-intrusive as possible. This means it cannot allocate memory, and must
use pre-allocated data.

A method that is actively being worked on to have faultable system call
tracepoints read user space data is to allocate per CPU buffers, and use
them in the callback. The method uses a technique similar to seqcount.
That is something like this:

	preempt_disable();
	cpu = smp_processor_id();
	buffer = this_cpu_ptr(&pre_allocated_cpu_buffers, cpu);
	do {
		cnt = nr_context_switches_cpu(cpu);
		migrate_disable();
		preempt_enable();
		ret = copy_from_user(buffer, ptr, size);
		preempt_disable();
		migrate_enable();
	} while (!ret && cnt != nr_context_switches_cpu(cpu));

	if (!ret)
		ring_buffer_write(buffer);
	preempt_enable();

It's a little more involved than that, but the above is the basic logic.
The idea is to acquire the current CPU buffer, disable migration, and then
enable preemption. At this moment, it can safely use copy_from_user().
After reading the data from user space, it disables preemption again. It
then checks to see if there was any new scheduling on this CPU. If there
was, it must assume that the buffer was corrupted by another task. If
there wasn't, then the buffer is still valid as only tasks in preemptable
context can write to this buffer and only those that are running on the
CPU.

By using this method, where trace_marker open allocates the per CPU
buffers, trace_marker writes can access user space and even fault it in,
without having to allocate or take any locks of its own.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Luo Gengkun <luogengkun@huaweicloud.com>
Cc: Wattson CI <wattson-external@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/20251008124510.6dba541a@gandalf.local.home
Fixes: 3d62ab32df065 ("tracing: Fix tracing_marker may trigger page fault during preempt_disable")
Reported-by: Runping Lai <runpinglai@google.com>
Tested-by: Runping Lai <runpinglai@google.com>
Closes: https://lore.kernel.org/linux-trace-kernel/20251007003417.3470979-2-runpinglai@google.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 268 +++++++++++++++++++++++++++++++++++--------
 1 file changed, 220 insertions(+), 48 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b3c94fbaf002..0fd582651293 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4791,12 +4791,6 @@ int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
 	return single_release(inode, filp);
 }
 
-static int tracing_mark_open(struct inode *inode, struct file *filp)
-{
-	stream_open(inode, filp);
-	return tracing_open_generic_tr(inode, filp);
-}
-
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -7163,7 +7157,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 
 #define TRACE_MARKER_MAX_SIZE		4096
 
-static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user *ubuf,
+static ssize_t write_marker_to_buffer(struct trace_array *tr, const char *buf,
 				      size_t cnt, unsigned long ip)
 {
 	struct ring_buffer_event *event;
@@ -7173,20 +7167,11 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user
 	int meta_size;
 	ssize_t written;
 	size_t size;
-	int len;
-
-/* Used in tracing_mark_raw_write() as well */
-#define FAULTED_STR "<faulted>"
-#define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */
 
 	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
  again:
 	size = cnt + meta_size;
 
-	/* If less than "<faulted>", then make sure we can still add that */
-	if (cnt < FAULTED_SIZE)
-		size += FAULTED_SIZE - cnt;
-
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
@@ -7196,9 +7181,6 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user
 		 * make it smaller and try again.
 		 */
 		if (size > ring_buffer_max_event_size(buffer)) {
-			/* cnt < FAULTED size should never be bigger than max */
-			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
-				return -EBADF;
 			cnt = ring_buffer_max_event_size(buffer) - meta_size;
 			/* The above should only happen once */
 			if (WARN_ON_ONCE(cnt + meta_size == size))
@@ -7212,14 +7194,8 @@ 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_nofault(&entry->buf, ubuf, cnt);
-	if (len) {
-		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
-		cnt = FAULTED_SIZE;
-		written = -EFAULT;
-	} else
-		written = cnt;
+	memcpy(&entry->buf, buf, cnt);
+	written = cnt;
 
 	if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) {
 		/* do not add \n before testing triggers, but add \0 */
@@ -7243,6 +7219,169 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user
 	return written;
 }
 
+struct trace_user_buf {
+	char		*buf;
+};
+
+struct trace_user_buf_info {
+	struct trace_user_buf __percpu	*tbuf;
+	int				ref;
+};
+
+
+static DEFINE_MUTEX(trace_user_buffer_mutex);
+static struct trace_user_buf_info *trace_user_buffer;
+
+static void trace_user_fault_buffer_free(struct trace_user_buf_info *tinfo)
+{
+	char *buf;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		buf = per_cpu_ptr(tinfo->tbuf, cpu)->buf;
+		kfree(buf);
+	}
+	free_percpu(tinfo->tbuf);
+	kfree(tinfo);
+}
+
+static int trace_user_fault_buffer_enable(void)
+{
+	struct trace_user_buf_info *tinfo;
+	char *buf;
+	int cpu;
+
+	guard(mutex)(&trace_user_buffer_mutex);
+
+	if (trace_user_buffer) {
+		trace_user_buffer->ref++;
+		return 0;
+	}
+
+	tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+	if (!tinfo)
+		return -ENOMEM;
+
+	tinfo->tbuf = alloc_percpu(struct trace_user_buf);
+	if (!tinfo->tbuf) {
+		kfree(tinfo);
+		return -ENOMEM;
+	}
+
+	tinfo->ref = 1;
+
+	/* Clear each buffer in case of error */
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(tinfo->tbuf, cpu)->buf = NULL;
+	}
+
+	for_each_possible_cpu(cpu) {
+		buf = kmalloc_node(TRACE_MARKER_MAX_SIZE, GFP_KERNEL,
+				   cpu_to_node(cpu));
+		if (!buf) {
+			trace_user_fault_buffer_free(tinfo);
+			return -ENOMEM;
+		}
+		per_cpu_ptr(tinfo->tbuf, cpu)->buf = buf;
+	}
+
+	trace_user_buffer = tinfo;
+
+	return 0;
+}
+
+static void trace_user_fault_buffer_disable(void)
+{
+	struct trace_user_buf_info *tinfo;
+
+	guard(mutex)(&trace_user_buffer_mutex);
+
+	tinfo = trace_user_buffer;
+
+	if (WARN_ON_ONCE(!tinfo))
+		return;
+
+	if (--tinfo->ref)
+		return;
+
+	trace_user_fault_buffer_free(tinfo);
+	trace_user_buffer = NULL;
+}
+
+/* Must be called with preemption disabled */
+static char *trace_user_fault_read(struct trace_user_buf_info *tinfo,
+				   const char __user *ptr, size_t size,
+				   size_t *read_size)
+{
+	int cpu = smp_processor_id();
+	char *buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf;
+	unsigned int cnt;
+	int trys = 0;
+	int ret;
+
+	if (size > TRACE_MARKER_MAX_SIZE)
+		size = TRACE_MARKER_MAX_SIZE;
+	*read_size = 0;
+
+	/*
+	 * This acts similar to a seqcount. The per CPU context switches are
+	 * recorded, migration is disabled and preemption is enabled. The
+	 * read of the user space memory is copied into the per CPU buffer.
+	 * Preemption is disabled again, and if the per CPU context switches count
+	 * is still the same, it means the buffer has not been corrupted.
+	 * If the count is different, it is assumed the buffer is corrupted
+	 * and reading must be tried again.
+	 */
+
+	do {
+		/*
+		 * If for some reason, copy_from_user() always causes a context
+		 * switch, this would then cause an infinite loop.
+		 * If this task is preempted by another user space task, it
+		 * will cause this task to try again. But just in case something
+		 * changes where the copying from user space causes another task
+		 * to run, prevent this from going into an infinite loop.
+		 * 100 tries should be plenty.
+		 */
+		if (WARN_ONCE(trys++ > 100, "Error: Too many tries to read user space"))
+			return NULL;
+
+		/* Read the current CPU context switch counter */
+		cnt = nr_context_switches_cpu(cpu);
+
+		/*
+		 * Preemption is going to be enabled, but this task must
+		 * remain on this CPU.
+		 */
+		migrate_disable();
+
+		/*
+		 * Now preemption is being enabed and another task can come in
+		 * and use the same buffer and corrupt our data.
+		 */
+		preempt_enable_notrace();
+
+		ret = __copy_from_user(buffer, ptr, size);
+
+		preempt_disable_notrace();
+		migrate_enable();
+
+		/* if it faulted, no need to test if the buffer was corrupted */
+		if (ret)
+			return NULL;
+
+		/*
+		 * Preemption is disabled again, now check the per CPU context
+		 * switch counter. If it doesn't match, then another user space
+		 * process may have schedule in and corrupted our buffer. In that
+		 * case the copying must be retried.
+		 */
+	} while (nr_context_switches_cpu(cpu) != cnt);
+
+	*read_size = size;
+	return buffer;
+}
+
 static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7250,6 +7389,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	struct trace_array *tr = filp->private_data;
 	ssize_t written = -ENODEV;
 	unsigned long ip;
+	size_t size;
+	char *buf;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -7263,6 +7404,16 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt > TRACE_MARKER_MAX_SIZE)
 		cnt = TRACE_MARKER_MAX_SIZE;
 
+	/* Must have preemption disabled while having access to the buffer */
+	guard(preempt_notrace)();
+
+	buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, &size);
+	if (!buf)
+		return -EFAULT;
+
+	if (cnt > size)
+		cnt = size;
+
 	/* The selftests expect this function to be the IP address */
 	ip = _THIS_IP_;
 
@@ -7270,32 +7421,27 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tr == &global_trace) {
 		guard(rcu)();
 		list_for_each_entry_rcu(tr, &marker_copies, marker_list) {
-			written = write_marker_to_buffer(tr, ubuf, cnt, ip);
+			written = write_marker_to_buffer(tr, buf, cnt, ip);
 			if (written < 0)
 				break;
 		}
 	} else {
-		written = write_marker_to_buffer(tr, ubuf, cnt, ip);
+		written = write_marker_to_buffer(tr, buf, cnt, ip);
 	}
 
 	return written;
 }
 
 static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
-					  const char __user *ubuf, size_t cnt)
+					  const char *buf, size_t cnt)
 {
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer;
 	struct raw_data_entry *entry;
 	ssize_t written;
-	int size;
-	int len;
-
-#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+	size_t size;
 
 	size = sizeof(*entry) + cnt;
-	if (cnt < FAULT_SIZE_ID)
-		size += FAULT_SIZE_ID - cnt;
 
 	buffer = tr->array_buffer.buffer;
 
@@ -7309,14 +7455,8 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
 		return -EBADF;
 
 	entry = ring_buffer_event_data(event);
-
-	len = copy_from_user_nofault(&entry->id, ubuf, cnt);
-	if (len) {
-		entry->id = -1;
-		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
-		written = -EFAULT;
-	} else
-		written = cnt;
+	memcpy(&entry->id, buf, cnt);
+	written = cnt;
 
 	__buffer_unlock_commit(buffer, event);
 
@@ -7329,8 +7469,8 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 {
 	struct trace_array *tr = filp->private_data;
 	ssize_t written = -ENODEV;
-
-#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+	size_t size;
+	char *buf;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -7342,6 +7482,17 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 	if (cnt < sizeof(unsigned int))
 		return -EINVAL;
 
+	/* Must have preemption disabled while having access to the buffer */
+	guard(preempt_notrace)();
+
+	buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, &size);
+	if (!buf)
+		return -EFAULT;
+
+	/* raw write is all or nothing */
+	if (cnt > size)
+		return -EINVAL;
+
 	/* The global trace_marker_raw can go to multiple instances */
 	if (tr == &global_trace) {
 		guard(rcu)();
@@ -7357,6 +7508,27 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 	return written;
 }
 
+static int tracing_mark_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = trace_user_fault_buffer_enable();
+	if (ret < 0)
+		return ret;
+
+	stream_open(inode, filp);
+	ret = tracing_open_generic_tr(inode, filp);
+	if (ret < 0)
+		trace_user_fault_buffer_disable();
+	return ret;
+}
+
+static int tracing_mark_release(struct inode *inode, struct file *file)
+{
+	trace_user_fault_buffer_disable();
+	return tracing_release_generic_tr(inode, file);
+}
+
 static int tracing_clock_show(struct seq_file *m, void *v)
 {
 	struct trace_array *tr = m->private;
@@ -7764,13 +7936,13 @@ static const struct file_operations tracing_free_buffer_fops = {
 static const struct file_operations tracing_mark_fops = {
 	.open		= tracing_mark_open,
 	.write		= tracing_mark_write,
-	.release	= tracing_release_generic_tr,
+	.release	= tracing_mark_release,
 };
 
 static const struct file_operations tracing_mark_raw_fops = {
 	.open		= tracing_mark_open,
 	.write		= tracing_mark_raw_write,
-	.release	= tracing_release_generic_tr,
+	.release	= tracing_mark_release,
 };
 
 static const struct file_operations trace_clock_fops = {

From 6bb73db6948c2de23e407fe1b7ef94bf02b7529f Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 8 Oct 2025 15:54:20 +0800
Subject: [PATCH 248/352] crypto: essiv - Check ssize for decryption and
 in-place encryption

Move the ssize check to the start in essiv_aead_crypt so that
it's also checked for decryption and in-place encryption.

Reported-by: Muhammad Alifa Ramdhan <ramdhan@starlabs.sg>
Fixes: be1eb7f78aa8 ("crypto: essiv - create wrapper template for ESSIV generation")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/essiv.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/crypto/essiv.c b/crypto/essiv.c
index d003b78fcd85..a47a3eab6935 100644
--- a/crypto/essiv.c
+++ b/crypto/essiv.c
@@ -186,9 +186,14 @@ static int essiv_aead_crypt(struct aead_request *req, bool enc)
 	const struct essiv_tfm_ctx *tctx = crypto_aead_ctx(tfm);
 	struct essiv_aead_request_ctx *rctx = aead_request_ctx(req);
 	struct aead_request *subreq = &rctx->aead_req;
+	int ivsize = crypto_aead_ivsize(tfm);
+	int ssize = req->assoclen - ivsize;
 	struct scatterlist *src = req->src;
 	int err;
 
+	if (ssize < 0)
+		return -EINVAL;
+
 	crypto_cipher_encrypt_one(tctx->essiv_cipher, req->iv, req->iv);
 
 	/*
@@ -198,19 +203,12 @@ static int essiv_aead_crypt(struct aead_request *req, bool enc)
 	 */
 	rctx->assoc = NULL;
 	if (req->src == req->dst || !enc) {
-		scatterwalk_map_and_copy(req->iv, req->dst,
-					 req->assoclen - crypto_aead_ivsize(tfm),
-					 crypto_aead_ivsize(tfm), 1);
+		scatterwalk_map_and_copy(req->iv, req->dst, ssize, ivsize, 1);
 	} else {
 		u8 *iv = (u8 *)aead_request_ctx(req) + tctx->ivoffset;
-		int ivsize = crypto_aead_ivsize(tfm);
-		int ssize = req->assoclen - ivsize;
 		struct scatterlist *sg;
 		int nents;
 
-		if (ssize < 0)
-			return -EINVAL;
-
 		nents = sg_nents_for_len(req->src, ssize);
 		if (nents < 0)
 			return -EINVAL;

From 49836ff2f37dd6d52bfe3153c0bcbd96025a6100 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 9 Oct 2025 08:25:36 +0200
Subject: [PATCH 249/352] can: m_can: replace Dong Aisheng's old email address

Dong Aisheng's old Freescale email is not valid anymore and bounces,
replace it by the new NXP one.

Reviewed-by: Dong Aisheng <aisheng.dong@nxp.com>
Link: https://patch.msgid.link/20251009-m_can-update-email-address-v1-1-30a268587f69@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .mailmap                               | 1 +
 drivers/net/can/m_can/m_can.c          | 4 ++--
 drivers/net/can/m_can/m_can_platform.c | 4 ++--
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/.mailmap b/.mailmap
index d30f9363a4c9..8160c62f11e9 100644
--- a/.mailmap
+++ b/.mailmap
@@ -227,6 +227,7 @@ Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
+Dong Aisheng <aisheng.dong@nxp.com> <b29396@freescale.com>
 Douglas Gilbert <dougg@torque.net>
 Drew Fustini <fustini@kernel.org> <drew@pdp7.com>
 <duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr>
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index f2576e577058..ad4f577c1ef7 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // CAN bus driver for Bosch M_CAN controller
 // Copyright (C) 2014 Freescale Semiconductor, Inc.
-//      Dong Aisheng <b29396@freescale.com>
+//      Dong Aisheng <aisheng.dong@nxp.com>
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
 /* Bosch M_CAN user manual can be obtained from:
@@ -2556,7 +2556,7 @@ int m_can_class_resume(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(m_can_class_resume);
 
-MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>");
+MODULE_AUTHOR("Dong Aisheng <aisheng.dong@nxp.com>");
 MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("CAN bus driver for Bosch M_CAN controller");
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 057eaa7b8b4b..4a412add2b8d 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // IOMapped CAN bus driver for Bosch M_CAN controller
 // Copyright (C) 2014 Freescale Semiconductor, Inc.
-//	Dong Aisheng <b29396@freescale.com>
+//	Dong Aisheng <aisheng.dong@nxp.com>
 //
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
@@ -236,7 +236,7 @@ static struct platform_driver m_can_plat_driver = {
 
 module_platform_driver(m_can_plat_driver);
 
-MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>");
+MODULE_AUTHOR("Dong Aisheng <aisheng.dong@nxp.com>");
 MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("M_CAN driver for IO Mapped Bosch controllers");

From 434689e971955f487355b3f01e84ee269032bc87 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hansg@kernel.org>
Date: Wed, 1 Oct 2025 23:24:16 +0200
Subject: [PATCH 250/352] gpio: usbio: Add ACPI device-id for MTL-CVF devices

Add "INTC10D1" ACPI device-id for MTL-CVF devices, like the Dell Latitude
7450.

Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2368506
Signed-off-by: Hans de Goede <hansg@kernel.org>
Acked-by: Israel Cepeda <israel.a.cepeda.lopez@intel.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-usbio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/gpio-usbio.c b/drivers/gpio/gpio-usbio.c
index e13c120824e3..34d42c743d5b 100644
--- a/drivers/gpio/gpio-usbio.c
+++ b/drivers/gpio/gpio-usbio.c
@@ -29,6 +29,7 @@ static const struct acpi_device_id usbio_gpio_acpi_hids[] = {
 	{ "INTC1007" }, /* MTL */
 	{ "INTC10B2" }, /* ARL */
 	{ "INTC10B5" }, /* LNL */
+	{ "INTC10D1" }, /* MTL-CVF */
 	{ "INTC10E2" }, /* PTL */
 	{ }
 };

From eb4faf6343889fcd7edba3deeae49fc5a06531fd Mon Sep 17 00:00:00 2001
From: Kael D'Alcamo <dev@kael-k.io>
Date: Wed, 8 Oct 2025 22:04:27 +0200
Subject: [PATCH 251/352] dt-bindings: i2c: hisilicon,hix5hd2: convert to DT
 schema

Convert the Devicetree binding documentation for hisilicon,hix5hd2-i2c
from plain text to DT binding schema.

Signed-off-by: Kael D'Alcamo <dev@kael-k.io>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 .../bindings/i2c/hisilicon,hix5hd2-i2c.yaml   | 51 +++++++++++++++++++
 .../devicetree/bindings/i2c/i2c-hix5hd2.txt   | 24 ---------
 2 files changed, 51 insertions(+), 24 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml
 delete mode 100644 Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt

diff --git a/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml b/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml
new file mode 100644
index 000000000000..3faa7954e411
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/i2c/hisilicon,hix5hd2-i2c.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+title: I2C for HiSilicon hix5hd2 chipset platform
+
+maintainers:
+  - Wei Yan <sledge.yanwei@huawei.com>
+
+allOf:
+  - $ref: /schemas/i2c/i2c-controller.yaml#
+
+properties:
+  compatible:
+    enum:
+      - hisilicon,hix5hd2-i2c
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-frequency:
+    description: Desired I2C bus frequency in Hz
+    default: 100000
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/hix5hd2-clock.h>
+
+    i2c@f8b10000 {
+        compatible = "hisilicon,hix5hd2-i2c";
+        reg = <0xf8b10000 0x1000>;
+        interrupts = <0 38 4>;
+        clocks = <&clock HIX5HD2_I2C0_RST>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt b/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt
deleted file mode 100644
index f98b37401e6e..000000000000
--- a/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt
+++ /dev/null
@@ -1,24 +0,0 @@
-I2C for Hisilicon hix5hd2 chipset platform
-
-Required properties:
-- compatible: Must be "hisilicon,hix5hd2-i2c"
-- reg: physical base address of the controller and length of memory mapped
-     region.
-- interrupts: interrupt number to the cpu.
-- #address-cells = <1>;
-- #size-cells = <0>;
-- clocks: phandles to input clocks.
-
-Optional properties:
-- clock-frequency: Desired I2C bus frequency in Hz, otherwise defaults to 100000
-- Child nodes conforming to i2c bus binding
-
-Examples:
-I2C0@f8b10000 {
-	compatible = "hisilicon,hix5hd2-i2c";
-	reg = <0xf8b10000 0x1000>;
-	interrupts = <0 38 4>;
-	clocks = <&clock HIX5HD2_I2C0_RST>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-}

From 1643cd51ba975f484a09bed42d1a2014c42c9e6d Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Thu, 9 Oct 2025 17:00:13 +0200
Subject: [PATCH 252/352] smb: client: Omit an if branch in
 smb2_find_smb_tcon()

Statements from an if branch and the end of this function implementation
were equivalent.
Thus delete duplicate source code.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2transport.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index bc0e92eb2b64..33f33013b392 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -240,11 +240,6 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32  tid)
 		return NULL;
 	}
 	tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
-	if (!tcon) {
-		spin_unlock(&cifs_tcp_ses_lock);
-		cifs_put_smb_ses(ses);
-		return NULL;
-	}
 	spin_unlock(&cifs_tcp_ses_lock);
 	/* tcon already has a ref to ses, so we don't need ses anymore */
 	cifs_put_smb_ses(ses);

From 68d2e2ca1cba9259e943bcd188671b619b9770b4 Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Fri, 3 Oct 2025 23:11:43 -0300
Subject: [PATCH 253/352] smb: client: batch SRV_COPYCHUNK entries to cut round
 trips

smb2_copychunk_range() used to send a single SRV_COPYCHUNK per
SRV_COPYCHUNK_COPY IOCTL.

Implement variable Chunks[] array in struct copychunk_ioctl and fill it
with struct copychunk (MS-SMB2 2.2.31.1.1), bounded by server-advertised
limits.

This reduces the number of IOCTL requests for large copies.

While we are at it, rename a couple variables to follow the terminology
used in the specification.

Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 332 +++++++++++++++++++++++++---------------
 fs/smb/client/smb2pdu.h |  16 +-
 fs/smb/client/trace.h   |   2 +-
 3 files changed, 220 insertions(+), 130 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 058050f744c0..80114292e2c9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1803,140 +1803,226 @@ free_vars:
 	return rc;
 }
 
+/**
+ * calc_chunk_count - calculates the number chunks to be filled in the Chunks[]
+ * array of struct copychunk_ioctl
+ *
+ * @tcon: destination file tcon
+ * @bytes_left: how many bytes are left to copy
+ *
+ * Return: maximum number of chunks with which Chunks[] can be filled.
+ */
+static inline u32
+calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left)
+{
+	u32 max_chunks = READ_ONCE(tcon->max_chunks);
+	u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy);
+	u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk);
+	u64 need;
+	u32 allowed;
+
+	if (!max_bytes_chunk || !max_bytes_copy || !max_chunks)
+		return 0;
+
+	/* chunks needed for the remaining bytes */
+	need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk);
+	/* chunks allowed per cc request */
+	allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk);
+
+	return (u32)umin(need, umin(max_chunks, allowed));
+}
+
+/**
+ * smb2_copychunk_range - server-side copy of data range
+ *
+ * @xid: transaction id
+ * @src_file: source file
+ * @dst_file: destination file
+ * @src_off: source file byte offset
+ * @len: number of bytes to copy
+ * @dst_off: destination file byte offset
+ *
+ * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE
+ * IOCTLs, splitting the request into chunks limited by tcon->max_*.
+ *
+ * Return: @len on success; negative errno on failure.
+ */
 static ssize_t
 smb2_copychunk_range(const unsigned int xid,
-			struct cifsFileInfo *srcfile,
-			struct cifsFileInfo *trgtfile, u64 src_off,
-			u64 len, u64 dest_off)
+		     struct cifsFileInfo *src_file,
+		     struct cifsFileInfo *dst_file,
+		     u64 src_off,
+		     u64 len,
+		     u64 dst_off)
 {
-	int rc;
-	unsigned int ret_data_len;
-	struct copychunk_ioctl *pcchunk;
-	struct copychunk_ioctl_rsp *retbuf = NULL;
+	int rc = 0;
+	unsigned int ret_data_len = 0;
+	struct copychunk_ioctl *cc_req = NULL;
+	struct copychunk_ioctl_rsp *cc_rsp = NULL;
 	struct cifs_tcon *tcon;
-	int chunks_copied = 0;
-	bool chunk_sizes_updated = false;
-	ssize_t bytes_written, total_bytes_written = 0;
+	struct copychunk *chunk;
+	u32 chunks, chunk_count, chunk_bytes;
+	u32 copy_bytes, copy_bytes_left;
+	u32 chunks_written, bytes_written;
+	u64 total_bytes_left = len;
+	u64 src_off_prev, dst_off_prev;
+	u32 retries = 0;
 
-	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
-	if (pcchunk == NULL)
-		return -ENOMEM;
+	tcon = tlink_tcon(dst_file->tlink);
 
-	cifs_dbg(FYI, "%s: about to call request res key\n", __func__);
-	/* Request a key from the server to identify the source of the copy */
-	rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
-				srcfile->fid.persistent_fid,
-				srcfile->fid.volatile_fid, pcchunk);
+	trace_smb3_copychunk_enter(xid, src_file->fid.volatile_fid,
+				   dst_file->fid.volatile_fid, tcon->tid,
+				   tcon->ses->Suid, src_off, dst_off, len);
 
-	/* Note: request_res_key sets res_key null only if rc !=0 */
-	if (rc)
-		goto cchunk_out;
-
-	/* For now array only one chunk long, will make more flexible later */
-	pcchunk->ChunkCount = cpu_to_le32(1);
-	pcchunk->Reserved = 0;
-	pcchunk->Reserved2 = 0;
-
-	tcon = tlink_tcon(trgtfile->tlink);
-
-	trace_smb3_copychunk_enter(xid, srcfile->fid.volatile_fid,
-				   trgtfile->fid.volatile_fid, tcon->tid,
-				   tcon->ses->Suid, src_off, dest_off, len);
-
-	while (len > 0) {
-		pcchunk->SourceOffset = cpu_to_le64(src_off);
-		pcchunk->TargetOffset = cpu_to_le64(dest_off);
-		pcchunk->Length =
-			cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk));
-
-		/* Request server copy to target from src identified by key */
-		kfree(retbuf);
-		retbuf = NULL;
-		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
-			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			(char *)pcchunk, sizeof(struct copychunk_ioctl),
-			CIFSMaxBufSize, (char **)&retbuf, &ret_data_len);
-		if (rc == 0) {
-			if (ret_data_len !=
-					sizeof(struct copychunk_ioctl_rsp)) {
-				cifs_tcon_dbg(VFS, "Invalid cchunk response size\n");
-				rc = -EIO;
-				goto cchunk_out;
-			}
-			if (retbuf->TotalBytesWritten == 0) {
-				cifs_dbg(FYI, "no bytes copied\n");
-				rc = -EIO;
-				goto cchunk_out;
-			}
-			/*
-			 * Check if server claimed to write more than we asked
-			 */
-			if (le32_to_cpu(retbuf->TotalBytesWritten) >
-			    le32_to_cpu(pcchunk->Length)) {
-				cifs_tcon_dbg(VFS, "Invalid copy chunk response\n");
-				rc = -EIO;
-				goto cchunk_out;
-			}
-			if (le32_to_cpu(retbuf->ChunksWritten) != 1) {
-				cifs_tcon_dbg(VFS, "Invalid num chunks written\n");
-				rc = -EIO;
-				goto cchunk_out;
-			}
-			chunks_copied++;
-
-			bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
-			src_off += bytes_written;
-			dest_off += bytes_written;
-			len -= bytes_written;
-			total_bytes_written += bytes_written;
-
-			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
-				le32_to_cpu(retbuf->ChunksWritten),
-				le32_to_cpu(retbuf->ChunkBytesWritten),
-				bytes_written);
-			trace_smb3_copychunk_done(xid, srcfile->fid.volatile_fid,
-				trgtfile->fid.volatile_fid, tcon->tid,
-				tcon->ses->Suid, src_off, dest_off, len);
-		} else if (rc == -EINVAL) {
-			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
-				goto cchunk_out;
-
-			cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n",
-				le32_to_cpu(retbuf->ChunksWritten),
-				le32_to_cpu(retbuf->ChunkBytesWritten),
-				le32_to_cpu(retbuf->TotalBytesWritten));
-
-			/*
-			 * Check if this is the first request using these sizes,
-			 * (ie check if copy succeed once with original sizes
-			 * and check if the server gave us different sizes after
-			 * we already updated max sizes on previous request).
-			 * if not then why is the server returning an error now
-			 */
-			if ((chunks_copied != 0) || chunk_sizes_updated)
-				goto cchunk_out;
-
-			/* Check that server is not asking us to grow size */
-			if (le32_to_cpu(retbuf->ChunkBytesWritten) <
-					tcon->max_bytes_chunk)
-				tcon->max_bytes_chunk =
-					le32_to_cpu(retbuf->ChunkBytesWritten);
-			else
-				goto cchunk_out; /* server gave us bogus size */
-
-			/* No need to change MaxChunks since already set to 1 */
-			chunk_sizes_updated = true;
-		} else
-			goto cchunk_out;
+retry:
+	chunk_count = calc_chunk_count(tcon, total_bytes_left);
+	if (!chunk_count) {
+		rc = -EOPNOTSUPP;
+		goto out;
 	}
 
-cchunk_out:
-	kfree(pcchunk);
-	kfree(retbuf);
+	cc_req = kzalloc(struct_size(cc_req, Chunks, chunk_count), GFP_KERNEL);
+	if (!cc_req) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Request a key from the server to identify the source of the copy */
+	rc = SMB2_request_res_key(xid,
+				  tlink_tcon(src_file->tlink),
+				  src_file->fid.persistent_fid,
+				  src_file->fid.volatile_fid,
+				  cc_req);
+
+	/* Note: request_res_key sets res_key null only if rc != 0 */
 	if (rc)
+		goto out;
+
+	while (total_bytes_left > 0) {
+
+		/* Store previous offsets to allow rewind */
+		src_off_prev = src_off;
+		dst_off_prev = dst_off;
+
+		chunks = 0;
+		copy_bytes = 0;
+		copy_bytes_left = umin(total_bytes_left, tcon->max_bytes_copy);
+		while (copy_bytes_left > 0 && chunks < chunk_count) {
+			chunk = &cc_req->Chunks[chunks++];
+
+			chunk->SourceOffset = cpu_to_le64(src_off);
+			chunk->TargetOffset = cpu_to_le64(dst_off);
+
+			chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk);
+
+			chunk->Length = cpu_to_le32(chunk_bytes);
+			/* Buffer is zeroed, no need to set chunk->Reserved = 0 */
+
+			src_off += chunk_bytes;
+			dst_off += chunk_bytes;
+
+			copy_bytes_left -= chunk_bytes;
+			copy_bytes += chunk_bytes;
+		}
+
+		cc_req->ChunkCount = cpu_to_le32(chunks);
+		/* Buffer is zeroed, no need to set cc_req->Reserved = 0 */
+
+		/* Request server copy to target from src identified by key */
+		kfree(cc_rsp);
+		cc_rsp = NULL;
+		rc = SMB2_ioctl(xid, tcon, dst_file->fid.persistent_fid,
+			dst_file->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
+			(char *)cc_req, struct_size(cc_req, Chunks, chunks),
+			CIFSMaxBufSize, (char **)&cc_rsp, &ret_data_len);
+
+		if (rc && rc != -EINVAL)
+			goto out;
+
+		if (unlikely(ret_data_len != sizeof(*cc_rsp))) {
+			cifs_tcon_dbg(VFS, "Copychunk invalid response: size %u/%zu\n",
+				      ret_data_len, sizeof(*cc_rsp));
+			rc = -EIO;
+			goto out;
+		}
+
+		bytes_written = le32_to_cpu(cc_rsp->TotalBytesWritten);
+		chunks_written = le32_to_cpu(cc_rsp->ChunksWritten);
+		chunk_bytes = le32_to_cpu(cc_rsp->ChunkBytesWritten);
+
+		if (rc == 0) {
+			/* Check if server claimed to write more than we asked */
+			if (unlikely(!bytes_written || bytes_written > copy_bytes ||
+				     !chunks_written || chunks_written > chunks)) {
+				cifs_tcon_dbg(VFS, "Copychunk invalid response: bytes written %u/%u, chunks written %u/%u\n",
+					      bytes_written, copy_bytes, chunks_written, chunks);
+				rc = -EIO;
+				goto out;
+			}
+
+			/* Partial write: rewind */
+			if (bytes_written < copy_bytes) {
+				u32 delta = copy_bytes - bytes_written;
+
+				src_off -= delta;
+				dst_off -= delta;
+			}
+
+			total_bytes_left -= bytes_written;
+			continue;
+		}
+
+		/*
+		 * Check if server is not asking us to reduce size.
+		 *
+		 * Note: As per MS-SMB2 2.2.32.1, the values returned
+		 * in cc_rsp are not strictly lower than what existed
+		 * before.
+		 */
+		if (bytes_written < tcon->max_bytes_copy) {
+			cifs_tcon_dbg(FYI, "Copychunk MaxBytesCopy updated: %u -> %u\n",
+				      tcon->max_bytes_copy, bytes_written);
+			tcon->max_bytes_copy = bytes_written;
+		}
+
+		if (chunks_written < tcon->max_chunks) {
+			cifs_tcon_dbg(FYI, "Copychunk MaxChunks updated: %u -> %u\n",
+				      tcon->max_chunks, chunks_written);
+			tcon->max_chunks = chunks_written;
+		}
+
+		if (chunk_bytes < tcon->max_bytes_chunk) {
+			cifs_tcon_dbg(FYI, "Copychunk MaxBytesChunk updated: %u -> %u\n",
+				      tcon->max_bytes_chunk, chunk_bytes);
+			tcon->max_bytes_chunk = chunk_bytes;
+		}
+
+		/* reset to last offsets */
+		if (retries++ < 2) {
+			src_off = src_off_prev;
+			dst_off = dst_off_prev;
+			kfree(cc_req);
+			cc_req = NULL;
+			goto retry;
+		}
+
+		break;
+	}
+
+out:
+	kfree(cc_req);
+	kfree(cc_rsp);
+	if (rc) {
+		trace_smb3_copychunk_err(xid, src_file->fid.volatile_fid,
+					 dst_file->fid.volatile_fid, tcon->tid,
+					 tcon->ses->Suid, src_off, dst_off, len, rc);
 		return rc;
-	else
-		return total_bytes_written;
+	} else {
+		trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid,
+					  dst_file->fid.volatile_fid, tcon->tid,
+					  tcon->ses->Suid, src_off, dst_off, len);
+		return len;
+	}
 }
 
 static int
diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index 3c09a58dfd07..101024f8f725 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -201,16 +201,20 @@ struct resume_key_req {
 	char	Context[];	/* ignored, Windows sets to 4 bytes of zero */
 } __packed;
 
+
+struct copychunk {
+	__le64 SourceOffset;
+	__le64 TargetOffset;
+	__le32 Length;
+	__le32 Reserved;
+} __packed;
+
 /* this goes in the ioctl buffer when doing a copychunk request */
 struct copychunk_ioctl {
 	char SourceKey[COPY_CHUNK_RES_KEY_SIZE];
-	__le32 ChunkCount; /* we are only sending 1 */
+	__le32 ChunkCount;
 	__le32 Reserved;
-	/* array will only be one chunk long for us */
-	__le64 SourceOffset;
-	__le64 TargetOffset;
-	__le32 Length; /* how many bytes to copy */
-	__u32 Reserved2;
+	struct copychunk Chunks[];
 } __packed;
 
 struct copychunk_ioctl_rsp {
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index fd650e2afc76..28e00c34df1c 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -266,7 +266,7 @@ DEFINE_EVENT(smb3_copy_range_err_class, smb3_##name, \
 	TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len, rc))
 
 DEFINE_SMB3_COPY_RANGE_ERR_EVENT(clone_err);
-/* TODO: Add SMB3_COPY_RANGE_ERR_EVENT(copychunk_err) */
+DEFINE_SMB3_COPY_RANGE_ERR_EVENT(copychunk_err);
 
 DECLARE_EVENT_CLASS(smb3_copy_range_done_class,
 	TP_PROTO(unsigned int xid,

From 0cc380d0e1d36b8f2703379890e90f896f68e9e8 Mon Sep 17 00:00:00 2001
From: Fushuai Wang <wangfushuai@baidu.com>
Date: Tue, 7 Oct 2025 16:26:03 +0800
Subject: [PATCH 254/352] cifs: Fix copy_to_iter return value check

The return value of copy_to_iter() function will never be negative,
it is the number of bytes copied, or zero if nothing was copied.
Update the check to treat 0 as an error, and return -1 in that case.

Fixes: d08089f649a0 ("cifs: Change the I/O paths to use an iterator rather than a page list")
Acked-by: Tom Talpey <tom@talpey.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Signed-off-by: Fushuai Wang <wangfushuai@baidu.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 80114292e2c9..83d9cde8a718 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4736,7 +4736,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 	unsigned int pad_len;
 	struct cifs_io_subrequest *rdata = mid->callback_data;
 	struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
-	int length;
+	size_t copied;
 	bool use_rdma_mr = false;
 
 	if (shdr->Command != SMB2_READ) {
@@ -4849,10 +4849,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 	} else if (buf_len >= data_offset + data_len) {
 		/* read response payload is in buf */
 		WARN_ONCE(buffer, "read data can be either in buf or in buffer");
-		length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter);
-		if (length < 0)
-			return length;
-		rdata->got_bytes = data_len;
+		copied = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter);
+		if (copied == 0)
+			return -EIO;
+		rdata->got_bytes = copied;
 	} else {
 		/* read response payload cannot be in both buf and pages */
 		WARN_ONCE(1, "buf can not contain only a part of read data");

From 110fee6b9bb58a5c50047fc2594d415f741b591e Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 7 Oct 2025 16:23:22 -0300
Subject: [PATCH 255/352] smb: client: fix missing timestamp updates with
 O_TRUNC

Don't call ->set_file_info() on open handle to prevent the server from
stopping [cm]time updates automatically as per MS-FSA 2.1.4.17.

Fix this by checking for ATTR_OPEN bit earlier in cifs_setattr() to
prevent ->set_file_info() from being called when opening a file with
O_TRUNC.  Do the truncation in ->open() instead.

This also saves two roundtrips when opening a file with O_TRUNC and
there are currently no open handles to be reused.

Before patch:

$ mount.cifs //srv/share /mnt -o ...
$ cd /mnt
$ exec 3>foo; stat -c 'old: %z %y' foo; sleep 2; echo test >&3; exec 3>&-; sleep 2; stat -c 'new: %z %y' foo
old: 2025-10-03 13:26:23.151030500 -0300 2025-10-03 13:26:23.151030500 -0300
new: 2025-10-03 13:26:23.151030500 -0300 2025-10-03 13:26:23.151030500 -0300

After patch:

$ mount.cifs //srv/share /mnt -o ...
$ cd /mnt
$ exec 3>foo; stat -c 'old: %z %y' foo; sleep 2; echo test >&3; exec 3>&-; sleep 2; stat -c 'new: %z %y' foo
$ exec 3>foo; stat -c 'old: %z %y' foo; sleep 2; echo test >&3; exec 3>&-; sleep 2; stat -c 'new: %z %y' foo
old: 2025-10-03 13:28:13.911933800 -0300 2025-10-03 13:28:13.911933800 -0300
new: 2025-10-03 13:28:26.647492700 -0300 2025-10-03 13:28:26.647492700 -0300

Reported-by: Frank Sorenson <sorenson@redhat.com>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h |   5 ++
 fs/smb/client/file.c     |  94 +++++++++++++++++-------
 fs/smb/client/inode.c    | 152 ++++++++++++++++++++++-----------------
 3 files changed, 159 insertions(+), 92 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 3ac254e123dc..8f6f567d7474 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1566,6 +1566,11 @@ struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file);
 void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr,
 		       bool offload);
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
+int cifs_file_flush(const unsigned int xid, struct inode *inode,
+		    struct cifsFileInfo *cfile);
+int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
+		       const char *full_path, struct cifsFileInfo *open_file,
+		       loff_t size);
 
 #define CIFS_CACHE_READ_FLG	1
 #define CIFS_CACHE_HANDLE_FLG	2
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index a5ed742afa00..ecbb63e66521 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -952,6 +952,66 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
 	}
 }
 
+int cifs_file_flush(const unsigned int xid, struct inode *inode,
+		    struct cifsFileInfo *cfile)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_tcon *tcon;
+	int rc;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
+		return 0;
+
+	if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) {
+		tcon = tlink_tcon(cfile->tlink);
+		return tcon->ses->server->ops->flush(xid, tcon,
+						     &cfile->fid);
+	}
+	rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
+	if (!rc) {
+		tcon = tlink_tcon(cfile->tlink);
+		rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid);
+		cifsFileInfo_put(cfile);
+	} else if (rc == -EBADF) {
+		rc = 0;
+	}
+	return rc;
+}
+
+static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
+{
+	struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry));
+	struct inode *inode = d_inode(dentry);
+	struct cifsFileInfo *cfile = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon;
+	int rc;
+
+	rc = filemap_write_and_wait(inode->i_mapping);
+	if (is_interrupt_error(rc))
+		return -ERESTARTSYS;
+	mapping_set_error(inode->i_mapping, rc);
+
+	cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+	rc = cifs_file_flush(xid, inode, cfile);
+	if (!rc) {
+		if (cfile) {
+			tcon = tlink_tcon(cfile->tlink);
+			server = tcon->ses->server;
+			rc = server->ops->set_file_size(xid, tcon,
+							cfile, 0, false);
+		}
+		if (!rc) {
+			netfs_resize_file(&cinode->netfs, 0, true);
+			cifs_setsize(inode, 0);
+			inode->i_blocks = 0;
+		}
+	}
+	if (cfile)
+		cifsFileInfo_put(cfile);
+	return rc;
+}
+
 int cifs_open(struct inode *inode, struct file *file)
 
 {
@@ -1004,6 +1064,12 @@ int cifs_open(struct inode *inode, struct file *file)
 			file->f_op = &cifs_file_direct_ops;
 	}
 
+	if (file->f_flags & O_TRUNC) {
+		rc = cifs_do_truncate(xid, file_dentry(file));
+		if (rc)
+			goto out;
+	}
+
 	/* 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,
@@ -2685,13 +2751,10 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync)
 {
-	unsigned int xid;
-	int rc = 0;
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file_inode(file);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int xid;
+	int rc = 0;
 
 	rc = file_write_and_wait_range(file, start, end);
 	if (rc) {
@@ -2712,26 +2775,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 		}
 	}
 
-	tcon = tlink_tcon(smbfile->tlink);
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
-		server = tcon->ses->server;
-		if (server->ops->flush == NULL) {
-			rc = -ENOSYS;
-			goto strict_fsync_exit;
-		}
-
-		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
-			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
-			if (smbfile) {
-				rc = server->ops->flush(xid, tcon, &smbfile->fid);
-				cifsFileInfo_put(smbfile);
-			} else
-				cifs_dbg(FYI, "ignore fsync for file not open for write\n");
-		} else
-			rc = server->ops->flush(xid, tcon, &smbfile->fid);
-	}
-
-strict_fsync_exit:
+	rc = cifs_file_flush(xid, inode, smbfile);
 	free_xid(xid);
 	return rc;
 }
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 8bb544be401e..ce88bef4e44c 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -3007,28 +3007,24 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
 
 void cifs_setsize(struct inode *inode, loff_t offset)
 {
-	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-
 	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
 	spin_unlock(&inode->i_lock);
-
-	/* Cached inode must be refreshed on truncate */
-	cifs_i->time = 0;
+	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	truncate_pagecache(inode, offset);
 }
 
-static int
-cifs_set_file_size(struct inode *inode, struct iattr *attrs,
-		   unsigned int xid, const char *full_path, struct dentry *dentry)
+int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
+		       const char *full_path, struct cifsFileInfo *open_file,
+		       loff_t size)
 {
-	int rc;
-	struct cifsFileInfo *open_file;
-	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct inode *inode = d_inode(dentry);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct tcon_link *tlink = NULL;
 	struct cifs_tcon *tcon = NULL;
 	struct TCP_Server_Info *server;
+	int rc = -EINVAL;
 
 	/*
 	 * To avoid spurious oplock breaks from server, in the case of
@@ -3039,19 +3035,25 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 	 * writebehind data than the SMB timeout for the SetPathInfo
 	 * request would allow
 	 */
-	open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
-	if (open_file) {
+	if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) {
 		tcon = tlink_tcon(open_file->tlink);
 		server = tcon->ses->server;
-		if (server->ops->set_file_size)
-			rc = server->ops->set_file_size(xid, tcon, open_file,
-							attrs->ia_size, false);
-		else
-			rc = -ENOSYS;
-		cifsFileInfo_put(open_file);
-		cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc);
-	} else
-		rc = -EINVAL;
+		rc = server->ops->set_file_size(xid, tcon,
+						open_file,
+						size, false);
+		cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc);
+	} else {
+		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		if (open_file) {
+			tcon = tlink_tcon(open_file->tlink);
+			server = tcon->ses->server;
+			rc = server->ops->set_file_size(xid, tcon,
+							open_file,
+							size, false);
+			cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc);
+			cifsFileInfo_put(open_file);
+		}
+	}
 
 	if (!rc)
 		goto set_size_out;
@@ -3069,20 +3071,15 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 	 * valid, writeable file handle for it was found or because there was
 	 * an error setting it by handle.
 	 */
-	if (server->ops->set_path_size)
-		rc = server->ops->set_path_size(xid, tcon, full_path,
-						attrs->ia_size, cifs_sb, false, dentry);
-	else
-		rc = -ENOSYS;
-	cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc);
-
-	if (tlink)
-		cifs_put_tlink(tlink);
+	rc = server->ops->set_path_size(xid, tcon, full_path, size,
+					cifs_sb, false, dentry);
+	cifs_dbg(FYI, "%s: SetEOF by path (setattrs) rc = %d\n", __func__, rc);
+	cifs_put_tlink(tlink);
 
 set_size_out:
 	if (rc == 0) {
-		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
-		cifs_setsize(inode, attrs->ia_size);
+		netfs_resize_file(&cifsInode->netfs, size, true);
+		cifs_setsize(inode, size);
 		/*
 		 * i_blocks is not related to (i_size / i_blksize), but instead
 		 * 512 byte (2**9) size is required for calculating num blocks.
@@ -3090,15 +3087,7 @@ set_size_out:
 		 * this is best estimate we have for blocks allocated for a file
 		 * Number of blocks must be rounded up so size 1 is not 0 blocks
 		 */
-		inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9;
-
-		/*
-		 * The man page of truncate says if the size changed,
-		 * then the st_ctime and st_mtime fields for the file
-		 * are updated.
-		 */
-		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
-		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+		inode->i_blocks = (512 - 1 + size) >> 9;
 	}
 
 	return rc;
@@ -3118,7 +3107,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	struct cifs_unix_set_info_args *args = NULL;
-	struct cifsFileInfo *open_file;
+	struct cifsFileInfo *open_file = NULL;
 
 	cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n",
 		 direntry, attrs->ia_valid);
@@ -3132,6 +3121,9 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	if (rc < 0)
 		goto out;
 
+	if (attrs->ia_valid & ATTR_FILE)
+		open_file = attrs->ia_file->private_data;
+
 	full_path = build_path_from_dentry(direntry, page);
 	if (IS_ERR(full_path)) {
 		rc = PTR_ERR(full_path);
@@ -3159,9 +3151,17 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	rc = 0;
 
 	if (attrs->ia_valid & ATTR_SIZE) {
-		rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry);
+		rc = cifs_file_set_size(xid, direntry, full_path,
+					open_file, attrs->ia_size);
 		if (rc != 0)
 			goto out;
+		/*
+		 * The man page of truncate says if the size changed,
+		 * then the st_ctime and st_mtime fields for the file
+		 * are updated.
+		 */
+		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 
 	/* skip mode change if it's just for clearing setuid/setgid */
@@ -3206,14 +3206,24 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		args->ctime = NO_CHANGE_64;
 
 	args->device = 0;
-	open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
-	if (open_file) {
-		u16 nfid = open_file->fid.netfid;
-		u32 npid = open_file->pid;
+	rc = -EINVAL;
+	if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) {
 		pTcon = tlink_tcon(open_file->tlink);
-		rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, nfid, npid);
-		cifsFileInfo_put(open_file);
+		rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args,
+					    open_file->fid.netfid,
+					    open_file->pid);
 	} else {
+		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		if (open_file) {
+			pTcon = tlink_tcon(open_file->tlink);
+			rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args,
+						    open_file->fid.netfid,
+						    open_file->pid);
+			cifsFileInfo_put(open_file);
+		}
+	}
+
+	if (rc) {
 		tlink = cifs_sb_tlink(cifs_sb);
 		if (IS_ERR(tlink)) {
 			rc = PTR_ERR(tlink);
@@ -3221,8 +3231,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		}
 		pTcon = tlink_tcon(tlink);
 		rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args,
-				    cifs_sb->local_nls,
-				    cifs_remap(cifs_sb));
+					    cifs_sb->local_nls,
+					    cifs_remap(cifs_sb));
 		cifs_put_tlink(tlink);
 	}
 
@@ -3264,8 +3274,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	struct inode *inode = d_inode(direntry);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-	struct cifsFileInfo *wfile;
-	struct cifs_tcon *tcon;
+	struct cifsFileInfo *cfile = NULL;
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	int rc = -EACCES;
@@ -3285,6 +3294,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if (rc < 0)
 		goto cifs_setattr_exit;
 
+	if (attrs->ia_valid & ATTR_FILE)
+		cfile = attrs->ia_file->private_data;
+
 	full_path = build_path_from_dentry(direntry, page);
 	if (IS_ERR(full_path)) {
 		rc = PTR_ERR(full_path);
@@ -3311,25 +3323,24 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 
 	rc = 0;
 
-	if ((attrs->ia_valid & ATTR_MTIME) &&
-	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
-		rc = cifs_get_writable_file(cifsInode, FIND_WR_ANY, &wfile);
-		if (!rc) {
-			tcon = tlink_tcon(wfile->tlink);
-			rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid);
-			cifsFileInfo_put(wfile);
-			if (rc)
-				goto cifs_setattr_exit;
-		} else if (rc != -EBADF)
+	if (attrs->ia_valid & ATTR_MTIME) {
+		rc = cifs_file_flush(xid, inode, cfile);
+		if (rc)
 			goto cifs_setattr_exit;
-		else
-			rc = 0;
 	}
 
 	if (attrs->ia_valid & ATTR_SIZE) {
-		rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry);
+		rc = cifs_file_set_size(xid, direntry, full_path,
+					cfile, attrs->ia_size);
 		if (rc != 0)
 			goto cifs_setattr_exit;
+		/*
+		 * The man page of truncate says if the size changed,
+		 * then the st_ctime and st_mtime fields for the file
+		 * are updated.
+		 */
+		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 
 	if (attrs->ia_valid & ATTR_UID)
@@ -3459,6 +3470,13 @@ cifs_setattr(struct mnt_idmap *idmap, struct dentry *direntry,
 
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return -EIO;
+	/*
+	 * Avoid setting [cm]time with O_TRUNC to prevent the server from
+	 * disabling automatic timestamp updates as specified in
+	 * MS-FSA 2.1.4.17.
+	 */
+	if (attrs->ia_valid & ATTR_OPEN)
+		return 0;
 
 	do {
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY

From 57ce9f7793b714fb14a97d502ce926162c3b96b1 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 7 Oct 2025 16:23:23 -0300
Subject: [PATCH 256/352] smb: client: fix missing timestamp updates after
 ftruncate(2)

Mask off ATTR_MTIME|ATTR_CTIME bits on ATTR_SIZE (e.g. ftruncate(2))
to prevent the client from sending set info calls and then disabling
automatic timestamp updates on server side as per MS-FSA 2.1.4.17.

---8<---
import os
import time

filename = '/mnt/foo'

def print_stat(prefix):
    st = os.stat(filename)
    print(prefix, ': ', time.ctime(st.st_atime), time.ctime(st.st_ctime))

fd = os.open(filename, os.O_CREAT|os.O_TRUNC|os.O_WRONLY, 0o644)
print_stat('old')
os.ftruncate(fd, 10)
time.sleep(2)
os.write(fd, b'foo')
os.close(fd)
time.sleep(2)
print_stat('new')
---8<---

Before patch:

$ mount.cifs //srv/share /mnt -o ...
$ python3 run.py
old :  Fri Oct  3 13:47:03 2025 Fri Oct  3 13:47:03 2025
new :  Fri Oct  3 13:47:00 2025 Fri Oct  3 13:47:03 2025

After patch:

$ mount.cifs //srv/share /mnt -o ...
$ python3 run.py
old :  Fri Oct  3 13:48:39 2025 Fri Oct  3 13:48:39 2025
new :  Fri Oct  3 13:48:41 2025 Fri Oct  3 13:48:41 2025

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: Frank Sorenson <sorenson@redhat.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/inode.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index ce88bef4e44c..fbfd5b556815 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -3156,12 +3156,11 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		if (rc != 0)
 			goto out;
 		/*
-		 * The man page of truncate says if the size changed,
-		 * then the st_ctime and st_mtime fields for the file
-		 * are updated.
+		 * Avoid setting timestamps on the server for ftruncate(2) to
+		 * prevent it from disabling automatic timestamp updates as per
+		 * MS-FSA 2.1.4.17.
 		 */
-		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
-		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+		attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME);
 	}
 
 	/* skip mode change if it's just for clearing setuid/setgid */
@@ -3335,12 +3334,11 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 		if (rc != 0)
 			goto cifs_setattr_exit;
 		/*
-		 * The man page of truncate says if the size changed,
-		 * then the st_ctime and st_mtime fields for the file
-		 * are updated.
+		 * Avoid setting timestamps on the server for ftruncate(2) to
+		 * prevent it from disabling automatic timestamp updates as per
+		 * MS-FSA 2.1.4.17.
 		 */
-		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
-		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+		attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME);
 	}
 
 	if (attrs->ia_valid & ATTR_UID)

From b95cd1bdf5aa9221c98fc9259014b8bb8d1829d7 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 7 Oct 2025 16:23:24 -0300
Subject: [PATCH 257/352] smb: client: fix missing timestamp updates after
 utime(2)

Don't reuse open handle when changing timestamps to prevent the server
from disabling automatic timestamp updates as per MS-FSA 2.1.4.17.

---8<---
import os
import time

filename = '/mnt/foo'

def print_stat(prefix):
    st = os.stat(filename)
    print(prefix, ': ', time.ctime(st.st_atime), time.ctime(st.st_ctime))

fd = os.open(filename, os.O_CREAT|os.O_TRUNC|os.O_WRONLY, 0o644)
print_stat('old')
os.utime(fd, None)
time.sleep(2)
os.write(fd, b'foo')
os.close(fd)
time.sleep(2)
print_stat('new')
---8<---

Before patch:

$ mount.cifs //srv/share /mnt -o ...
$ python3 run.py
old :  Fri Oct  3 14:01:21 2025 Fri Oct  3 14:01:21 2025
new :  Fri Oct  3 14:01:21 2025 Fri Oct  3 14:01:21 2025

After patch:

$ mount.cifs //srv/share /mnt -o ...
$ python3 run.py
old :  Fri Oct  3 17:03:34 2025 Fri Oct  3 17:03:34 2025
new :  Fri Oct  3 17:03:36 2025 Fri Oct  3 17:03:36 2025

Fixes: b6f2a0f89d7e ("cifs: for compound requests, use open handle if possible")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: Frank Sorenson <sorenson@redhat.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 0985db9f86e5..e441fa2e7689 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1382,31 +1382,33 @@ int
 smb2_set_file_info(struct inode *inode, const char *full_path,
 		   FILE_BASIC_INFO *buf, const unsigned int xid)
 {
-	struct cifs_open_parms oparms;
+	struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), };
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifsFileInfo *cfile = NULL;
+	struct cifs_open_parms oparms;
 	struct tcon_link *tlink;
 	struct cifs_tcon *tcon;
-	struct cifsFileInfo *cfile;
-	struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), };
-	int rc;
-
-	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
-	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) &&
-	    (buf->Attributes == 0))
-		return 0; /* would be a no op, no sense sending this */
+	int rc = 0;
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
 
-	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
+	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) {
+		if (buf->Attributes == 0)
+			goto out; /* would be a no op, no sense sending this */
+		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+	}
+
 	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES,
 			     FILE_OPEN, 0, ACL_NO_MODE);
 	rc = smb2_compound_op(xid, tcon, cifs_sb,
 			      full_path, &oparms, &in_iov,
 			      &(int){SMB2_OP_SET_INFO}, 1,
 			      cfile, NULL, NULL, NULL);
+out:
 	cifs_put_tlink(tlink);
 	return rc;
 }

From dba9f997c9d9a1cade05d006ed0429a63a4eed32 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 7 Oct 2025 16:23:25 -0300
Subject: [PATCH 258/352] smb: client: fix race with fallocate(2) and AIO+DIO

AIO+DIO may extend the file size, hence we need to make sure ->i_size
is stable across the entire fallocate(2) operation, otherwise it would
become a truncate and then inode size reduced back down when it
finishes.

Fix this by calling netfs_wait_for_outstanding_io() right after
acquiring ->i_rwsem exclusively in cifs_fallocate() and then guarantee
a stable ->i_size across fallocate(2).

Also call netfs_wait_for_outstanding_io() after truncating pagecache
to avoid any potential races with writeback.

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Fixes: 210627b0aca9 ("smb: client: fix missing timestamp updates with O_TRUNC")
Cc: Frank Sorenson <sorenson@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c  | 22 +++++++++++++++++++---
 fs/smb/client/inode.c   |  1 +
 fs/smb/client/smb2ops.c | 18 ++++++------------
 3 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 1775c2b7528f..05b1fa76e8cc 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -392,11 +392,27 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
 	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct TCP_Server_Info *server = tcon->ses->server;
+	struct inode *inode = file_inode(file);
+	int rc;
 
-	if (server->ops->fallocate)
-		return server->ops->fallocate(file, tcon, mode, off, len);
+	if (!server->ops->fallocate)
+		return -EOPNOTSUPP;
 
-	return -EOPNOTSUPP;
+	rc = inode_lock_killable(inode);
+	if (rc)
+		return rc;
+
+	netfs_wait_for_outstanding_io(inode);
+
+	rc = file_modified(file);
+	if (rc)
+		goto out_unlock;
+
+	rc = server->ops->fallocate(file, tcon, mode, off, len);
+
+out_unlock:
+	inode_unlock(inode);
+	return rc;
 }
 
 static int cifs_permission(struct mnt_idmap *idmap,
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index fbfd5b556815..239dd84a336f 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -3012,6 +3012,7 @@ void cifs_setsize(struct inode *inode, loff_t offset)
 	spin_unlock(&inode->i_lock);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	truncate_pagecache(inode, offset);
+	netfs_wait_for_outstanding_io(inode);
 }
 
 int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 83d9cde8a718..7c392cf5940b 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3367,7 +3367,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 			      ses->Suid, offset, len);
 
-	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	i_size = i_size_read(inode);
@@ -3385,6 +3384,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	 * first, otherwise the data may be inconsistent with the server.
 	 */
 	truncate_pagecache_range(inode, offset, offset + len - 1);
+	netfs_wait_for_outstanding_io(inode);
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	rc = -EOPNOTSUPP;
@@ -3413,7 +3413,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 
  zero_range_exit:
 	filemap_invalidate_unlock(inode->i_mapping);
-	inode_unlock(inode);
 	free_xid(xid);
 	if (rc)
 		trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid,
@@ -3437,7 +3436,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode_lock(inode);
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
 	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
@@ -3451,6 +3449,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 	 * caches first, otherwise the data may be inconsistent with the server.
 	 */
 	truncate_pagecache_range(inode, offset, offset + len - 1);
+	netfs_wait_for_outstanding_io(inode);
 
 	cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);
 
@@ -3485,7 +3484,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 unlock:
 	filemap_invalidate_unlock(inode->i_mapping);
 out:
-	inode_unlock(inode);
 	free_xid(xid);
 	return rc;
 }
@@ -3749,8 +3747,6 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode_lock(inode);
-
 	old_eof = i_size_read(inode);
 	if ((off >= old_eof) ||
 	    off + len >= old_eof) {
@@ -3765,6 +3761,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 
 	truncate_pagecache_range(inode, off, old_eof);
 	ictx->zero_point = old_eof;
+	netfs_wait_for_outstanding_io(inode);
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
 				  old_eof - off - len, off);
@@ -3785,8 +3782,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 	fscache_resize_cookie(cifs_inode_cookie(inode), new_eof);
 out_2:
 	filemap_invalidate_unlock(inode->i_mapping);
- out:
-	inode_unlock(inode);
+out:
 	free_xid(xid);
 	return rc;
 }
@@ -3803,8 +3799,6 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode_lock(inode);
-
 	old_eof = i_size_read(inode);
 	if (off >= old_eof) {
 		rc = -EINVAL;
@@ -3819,6 +3813,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	if (rc < 0)
 		goto out_2;
 	truncate_pagecache_range(inode, off, old_eof);
+	netfs_wait_for_outstanding_io(inode);
 
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 			  cfile->fid.volatile_fid, cfile->pid, new_eof);
@@ -3841,8 +3836,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	rc = 0;
 out_2:
 	filemap_invalidate_unlock(inode->i_mapping);
- out:
-	inode_unlock(inode);
+out:
 	free_xid(xid);
 	return rc;
 }

From be3898a395f830ef7eaff70df557f57315c61c81 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Thu, 9 Oct 2025 12:41:16 -0300
Subject: [PATCH 259/352] smb: client: remove redudant assignment in
 cifs_strict_fsync()

Remove redudant assignment of @rc as it will be overwritten by the
following cifs_file_flush() call.

Reported-by: Steve French <stfrench@microsoft.com>
Addresses-Coverity: 1665925
Fixes: 210627b0aca9 ("smb: client: fix missing timestamp updates with O_TRUNC")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/file.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index ecbb63e66521..474dadeb1593 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -2754,7 +2754,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file_inode(file);
 	unsigned int xid;
-	int rc = 0;
+	int rc;
 
 	rc = file_write_and_wait_range(file, start, end);
 	if (rc) {
@@ -2762,19 +2762,14 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 		return rc;
 	}
 
-	xid = get_xid();
-
-	cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
-		 file, datasync);
+	cifs_dbg(FYI, "%s: name=%pD datasync=0x%x\n", __func__, file, datasync);
 
 	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
 		rc = cifs_zap_mapping(inode);
-		if (rc) {
-			cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
-			rc = 0; /* don't care about it in fsync */
-		}
+		cifs_dbg(FYI, "%s: invalidate mapping: rc = %d\n", __func__, rc);
 	}
 
+	xid = get_xid();
 	rc = cifs_file_flush(xid, inode, smbfile);
 	free_xid(xid);
 	return rc;

From 7ae6152b78316319b9c935eb17c863fbebf54ea6 Mon Sep 17 00:00:00 2001
From: Enzo Matsumiya <ematsumiya@suse.de>
Date: Sat, 4 Oct 2025 19:56:36 -0500
Subject: [PATCH 260/352] smb: client: remove cfids_invalidation_worker

We can do the same cleanup on laundromat.

On invalidate_all_cached_dirs(), run laundromat worker with 0 timeout
and flush it for immediate + sync cleanup.

Signed-off-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c | 37 +++++++++----------------------------
 fs/smb/client/cached_dir.h |  1 -
 2 files changed, 9 insertions(+), 29 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index b36f9f9340f0..b8ac7b7faf61 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -562,8 +562,8 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon)
 
 	/*
 	 * Mark all the cfids as closed, and move them to the cfids->dying list.
-	 * They'll be cleaned up later by cfids_invalidation_worker. Take
-	 * a reference to each cfid during this process.
+	 * They'll be cleaned up by laundromat.  Take a reference to each cfid
+	 * during this process.
 	 */
 	spin_lock(&cfids->cfid_list_lock);
 	list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
@@ -580,12 +580,11 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon)
 		} else
 			kref_get(&cfid->refcount);
 	}
-	/*
-	 * Queue dropping of the dentries once locks have been dropped
-	 */
-	if (!list_empty(&cfids->dying))
-		queue_work(cfid_put_wq, &cfids->invalidation_work);
 	spin_unlock(&cfids->cfid_list_lock);
+
+	/* run laundromat unconditionally now as there might have been previously queued work */
+	mod_delayed_work(cfid_put_wq, &cfids->laundromat_work, 0);
+	flush_delayed_work(&cfids->laundromat_work);
 }
 
 static void
@@ -715,25 +714,6 @@ static void free_cached_dir(struct cached_fid *cfid)
 	kfree(cfid);
 }
 
-static void cfids_invalidation_worker(struct work_struct *work)
-{
-	struct cached_fids *cfids = container_of(work, struct cached_fids,
-						 invalidation_work);
-	struct cached_fid *cfid, *q;
-	LIST_HEAD(entry);
-
-	spin_lock(&cfids->cfid_list_lock);
-	/* move cfids->dying to the local list */
-	list_cut_before(&entry, &cfids->dying, &cfids->dying);
-	spin_unlock(&cfids->cfid_list_lock);
-
-	list_for_each_entry_safe(cfid, q, &entry, entry) {
-		list_del(&cfid->entry);
-		/* Drop the ref-count acquired in invalidate_all_cached_dirs */
-		kref_put(&cfid->refcount, smb2_close_cached_fid);
-	}
-}
-
 static void cfids_laundromat_worker(struct work_struct *work)
 {
 	struct cached_fids *cfids;
@@ -743,6 +723,9 @@ static void cfids_laundromat_worker(struct work_struct *work)
 	cfids = container_of(work, struct cached_fids, laundromat_work.work);
 
 	spin_lock(&cfids->cfid_list_lock);
+	/* move cfids->dying to the local list */
+	list_cut_before(&entry, &cfids->dying, &cfids->dying);
+
 	list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
 		if (cfid->last_access_time &&
 		    time_after(jiffies, cfid->last_access_time + HZ * dir_cache_timeout)) {
@@ -796,7 +779,6 @@ struct cached_fids *init_cached_dirs(void)
 	INIT_LIST_HEAD(&cfids->entries);
 	INIT_LIST_HEAD(&cfids->dying);
 
-	INIT_WORK(&cfids->invalidation_work, cfids_invalidation_worker);
 	INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker);
 	queue_delayed_work(cfid_put_wq, &cfids->laundromat_work,
 			   dir_cache_timeout * HZ);
@@ -820,7 +802,6 @@ void free_cached_dirs(struct cached_fids *cfids)
 		return;
 
 	cancel_delayed_work_sync(&cfids->laundromat_work);
-	cancel_work_sync(&cfids->invalidation_work);
 
 	spin_lock(&cfids->cfid_list_lock);
 	list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index 31339dc32719..1e383db7c337 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -62,7 +62,6 @@ struct cached_fids {
 	int num_entries;
 	struct list_head entries;
 	struct list_head dying;
-	struct work_struct invalidation_work;
 	struct delayed_work laundromat_work;
 	/* aggregate accounting for all cached dirents under this tcon */
 	atomic_long_t total_dirents_entries;

From 795cda8338eab036013314dbc0b04aae728880ab Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 16 May 2025 09:23:35 +0200
Subject: [PATCH 261/352] rtc: interface: Fix long-standing race when setting
 alarm

As described in the old comment dating back to
commit 6610e0893b8b ("RTC: Rework RTC code to use timerqueue for events")
from 2010, we have been living with a race window when setting alarm
with an expiry in the near future (i.e. next second).
With 1 second resolution, it can happen that the second ticks after the
check for the timer having expired, but before the alarm is actually set.
When this happen, no alarm IRQ is generated, at least not with some RTC
chips (isl12022 is an example of this).

With UIE RTC timer being implemented on top of alarm irq, being re-armed
every second, UIE will occasionally fail to work, as an alarm irq lost
due to this race will stop the re-arming loop.

For now, I have limited the additional expiry check to only be done for
alarms set to next seconds. I expect it should be good enough, although I
don't know if we can now for sure that systems with loads could end up
causing the same problems for alarms set 2 seconds or even longer in the
future.

I haven't been able to reproduce the problem with this check in place.

Cc: stable@vger.kernel.org
Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/r/20250516-rtc-uie-irq-fixes-v2-1-3de8e530a39e@geanix.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/interface.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index dc741ba29fa3..6fafe2a4ae4f 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -443,6 +443,29 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	else
 		err = rtc->ops->set_alarm(rtc->dev.parent, alarm);
 
+	/*
+	 * Check for potential race described above. If the waiting for next
+	 * second, and the second just ticked since the check above, either
+	 *
+	 * 1) It ticked after the alarm was set, and an alarm irq should be
+	 *    generated.
+	 *
+	 * 2) It ticked before the alarm was set, and alarm irq most likely will
+	 * not be generated.
+	 *
+	 * While we cannot easily check for which of these two scenarios we
+	 * are in, we can return -ETIME to signal that the timer has already
+	 * expired, which is true in both cases.
+	 */
+	if ((scheduled - now) <= 1) {
+		err = __rtc_read_time(rtc, &tm);
+		if (err)
+			return err;
+		now = rtc_tm_to_time64(&tm);
+		if (scheduled <= now)
+			return -ETIME;
+	}
+
 	trace_rtc_set_alarm(rtc_tm_to_time64(&alarm->time), err);
 	return err;
 }

From 9ffe06b6ccd7a8eaa31d31625db009ea26a22a3c Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 16 May 2025 09:23:36 +0200
Subject: [PATCH 262/352] rtc: isl12022: Fix initial enable_irq/disable_irq
 balance

Interrupts are automatically enabled when requested, so we need to
initialize irq_enabled accordingly to avoid causing an unbalanced enable
warning.

Fixes: c62d658e5253 ("rtc: isl12022: Add alarm support")
Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/r/20250516-rtc-uie-irq-fixes-v2-2-3de8e530a39e@geanix.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-isl12022.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index 9b44839a7402..5fc52dc64213 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -413,6 +413,7 @@ static int isl12022_setup_irq(struct device *dev, int irq)
 	if (ret)
 		return ret;
 
+	isl12022->irq_enabled = true;
 	ret = devm_request_threaded_irq(dev, irq, NULL,
 					isl12022_rtc_interrupt,
 					IRQF_SHARED | IRQF_ONESHOT,

From e0762fd26ad68f0232979e742e080d73a1388ead Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 16 May 2025 09:23:37 +0200
Subject: [PATCH 263/352] rtc: cpcap: Fix initial enable_irq/disable_irq
 balance

Interrupts are automatically enabled when requested, so we need to
initialize alarm_enabled accordingly to avoid causing an unbalanced enable
warning.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/r/20250516-rtc-uie-irq-fixes-v2-3-3de8e530a39e@geanix.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cpcap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index c170345ac076..8b6b35716f53 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -268,6 +268,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 		return err;
 
 	rtc->alarm_irq = platform_get_irq(pdev, 0);
+	rtc->alarm_enabled = true;
 	err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL,
 					cpcap_rtc_alarm_irq,
 					IRQF_TRIGGER_NONE | IRQF_ONESHOT,

From 1502fe0e97be01d18f2b30fd7fe29bb39def0e7d Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 16 May 2025 09:23:38 +0200
Subject: [PATCH 264/352] rtc: tps6586x: Fix initial enable_irq/disable_irq
 balance

Interrupts are automatically enabled when requested, so we need to
initialize irq_en accordingly to avoid causing an unbalanced enable
warning.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Link: https://lore.kernel.org/r/20250516-rtc-uie-irq-fixes-v2-4-3de8e530a39e@geanix.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-tps6586x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 54c8429b16bf..76ecf7b798f0 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -258,6 +258,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 
 	irq_set_status_flags(rtc->irq, IRQ_NOAUTOEN);
 
+	rtc->irq_en = true;
 	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
 				tps6586x_rtc_irq,
 				IRQF_ONESHOT,

From 9db26d5855d0374d4652487bfb5aacf40821c469 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 16 May 2025 09:23:39 +0200
Subject: [PATCH 265/352] rtc: interface: Ensure alarm irq is enabled when UIE
 is enabled

When setting a normal alarm, user-space is responsible for using
RTC_AIE_ON/RTC_AIE_OFF to control if alarm irq should be enabled.

But when RTC_UIE_ON is used, interrupts must be enabled so that the
requested irq events are generated.
When RTC_UIE_OFF is used, alarm irq is disabled if there are no other
alarms queued, so this commit brings symmetry to that.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250516-rtc-uie-irq-fixes-v2-5-3de8e530a39e@geanix.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/interface.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 6fafe2a4ae4f..b8b298efd9a9 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -617,6 +617,10 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled)
 		rtc->uie_rtctimer.node.expires = ktime_add(now, onesec);
 		rtc->uie_rtctimer.period = ktime_set(1, 0);
 		err = rtc_timer_enqueue(rtc, &rtc->uie_rtctimer);
+		if (!err && rtc->ops && rtc->ops->alarm_irq_enable)
+			err = rtc->ops->alarm_irq_enable(rtc->dev.parent, 1);
+		if (err)
+			goto out;
 	} else {
 		rtc_timer_remove(rtc, &rtc->uie_rtctimer);
 	}

From 44ac7f5c6d4c7fd62784bb2700245dbc4ac7e102 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 9 Oct 2025 23:33:34 +0200
Subject: [PATCH 266/352] parisc: Firmware: Fix returned path for
 PDC_MODULE_FIND on older machines

Older machines (like my 715/64) don't correctly initialize the
device path when returning from the PDC_MODULE_FIND firmware call.
Work around that shortcoming by initializing the path with the
known values.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/firmware.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index c69f6d5946e9..042343492a28 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -464,7 +464,8 @@ int pdc_system_map_find_mods(struct pdc_system_map_mod_info *pdc_mod_info,
 	unsigned long flags;
 
 	spin_lock_irqsave(&pdc_lock, flags);
-	retval = mem_pdc_call(PDC_SYSTEM_MAP, PDC_FIND_MODULE, __pa(pdc_result), 
+	memcpy(pdc_result2, mod_path, sizeof(*mod_path));
+	retval = mem_pdc_call(PDC_SYSTEM_MAP, PDC_FIND_MODULE, __pa(pdc_result),
 			      __pa(pdc_result2), mod_index);
 	convert_to_wide(pdc_result);
 	memcpy(pdc_mod_info, pdc_result, sizeof(*pdc_mod_info));

From f4edb5c52c93b1bc676064472fb517566a3e2129 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 9 Oct 2025 23:37:28 +0200
Subject: [PATCH 267/352] parisc: Fix iodc and device path return values on old
 machines

Older machines may not fully initialize the return values when asking for IODC
and device path data when building the inventory.  Work around possible
firmware leaks by proper initialization of the variables.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/drivers.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 1e793f770f71..1f8936fc2292 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -995,6 +995,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
 	struct pdc_system_map_mod_info pdc_mod_info;
 	struct pdc_module_path mod_path;
 
+	memset(&iodc_data, 0, sizeof(iodc_data));
 	status = pdc_iodc_read(&count, hpa, 0,
 		&iodc_data, sizeof(iodc_data));
 	if (status != PDC_OK) {
@@ -1012,6 +1013,11 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
 
 	mod_index = 0;
 	do {
+		/* initialize device path for old machines */
+		memset(&mod_path, 0xff, sizeof(mod_path));
+		get_node_path(dev->dev.parent, &mod_path.path);
+		mod_path.path.mod = dev->hw_path;
+		memset(&pdc_mod_info, 0, sizeof(pdc_mod_info));
 		status = pdc_system_map_find_mods(&pdc_mod_info,
 				&mod_path, mod_index++);
 	} while (status == PDC_OK && pdc_mod_info.mod_addr != hpa);

From 15df28699b28d6b49dc305040c4e26a9553df07a Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@linux-m68k.org>
Date: Thu, 9 Oct 2025 09:56:25 +1100
Subject: [PATCH 268/352] fbdev: Fix logic error in "offb" name match

A regression was reported to me recently whereby /dev/fb0 had disappeared
from a PowerBook G3 Series "Wallstreet". The problem shows up when the
"video=ofonly" parameter is passed to the kernel, which is what the
bootloader does when "no video driver" is selected. The cause of the
problem is the "offb" string comparison, which got mangled when it got
refactored. Fix it.

Cc: stable@vger.kernel.org
Fixes: 93604a5ade3a ("fbdev: Handle video= parameter in video/cmdline.c")
Reported-and-tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@linux-m68k.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/core/fb_cmdline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/core/fb_cmdline.c b/drivers/video/fbdev/core/fb_cmdline.c
index 4d1634c492ec..594b60424d1c 100644
--- a/drivers/video/fbdev/core/fb_cmdline.c
+++ b/drivers/video/fbdev/core/fb_cmdline.c
@@ -40,7 +40,7 @@ int fb_get_options(const char *name, char **option)
 	bool enabled;
 
 	if (name)
-		is_of = strncmp(name, "offb", 4);
+		is_of = !strncmp(name, "offb", 4);
 
 	enabled = __video_get_options(name, &options, is_of);
 

From 057ac50638bcece64b3b436d3a61b70ed6c01a34 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Sat, 7 Jun 2025 18:11:10 +0200
Subject: [PATCH 269/352] cifs: Query EA $LXMOD in cifs_query_path_info() for
 WSL reparse points
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

EA $LXMOD is required for WSL non-symlink reparse points.

Fixes: ef86ab131d91 ("cifs: Fix querying of WSL CHR and BLK reparse points over SMB1")
Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1ops.c | 62 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index a02d41d1ce4a..3fdbb71036cf 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -651,14 +651,72 @@ static int cifs_query_path_info(const unsigned int xid,
 	}
 
 #ifdef CONFIG_CIFS_XATTR
+	/*
+	 * For non-symlink WSL reparse points it is required to fetch
+	 * EA $LXMOD which contains in its S_DT part the mandatory file type.
+	 */
+	if (!rc && data->reparse_point) {
+		struct smb2_file_full_ea_info *ea;
+		u32 next = 0;
+
+		ea = (struct smb2_file_full_ea_info *)data->wsl.eas;
+		do {
+			ea = (void *)((u8 *)ea + next);
+			next = le32_to_cpu(ea->next_entry_offset);
+		} while (next);
+		if (le16_to_cpu(ea->ea_value_length)) {
+			ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) +
+						ea->ea_name_length + 1 +
+						le16_to_cpu(ea->ea_value_length), 4));
+			ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset));
+		}
+
+		rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_MODE,
+				    &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1],
+				    SMB2_WSL_XATTR_MODE_SIZE, cifs_sb);
+		if (rc == SMB2_WSL_XATTR_MODE_SIZE) {
+			ea->next_entry_offset = cpu_to_le32(0);
+			ea->flags = 0;
+			ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN;
+			ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_MODE_SIZE);
+			memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_MODE, SMB2_WSL_XATTR_NAME_LEN + 1);
+			data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 +
+						   SMB2_WSL_XATTR_MODE_SIZE, 4);
+			rc = 0;
+		} else if (rc >= 0) {
+			/* It is an error if EA $LXMOD has wrong size. */
+			rc = -EINVAL;
+		} else {
+			/*
+			 * In all other cases ignore error if fetching
+			 * of EA $LXMOD failed. It is needed only for
+			 * non-symlink WSL reparse points and wsl_to_fattr()
+			 * handle the case when EA is missing.
+			 */
+			rc = 0;
+		}
+	}
+
 	/*
 	 * For WSL CHR and BLK reparse points it is required to fetch
 	 * EA $LXDEV which contains major and minor device numbers.
 	 */
 	if (!rc && data->reparse_point) {
 		struct smb2_file_full_ea_info *ea;
+		u32 next = 0;
 
 		ea = (struct smb2_file_full_ea_info *)data->wsl.eas;
+		do {
+			ea = (void *)((u8 *)ea + next);
+			next = le32_to_cpu(ea->next_entry_offset);
+		} while (next);
+		if (le16_to_cpu(ea->ea_value_length)) {
+			ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) +
+						ea->ea_name_length + 1 +
+						le16_to_cpu(ea->ea_value_length), 4));
+			ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset));
+		}
+
 		rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_DEV,
 				    &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1],
 				    SMB2_WSL_XATTR_DEV_SIZE, cifs_sb);
@@ -668,8 +726,8 @@ static int cifs_query_path_info(const unsigned int xid,
 			ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN;
 			ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE);
 			memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1);
-			data->wsl.eas_len = sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 +
-					    SMB2_WSL_XATTR_DEV_SIZE;
+			data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 +
+						   SMB2_WSL_XATTR_MODE_SIZE, 4);
 			rc = 0;
 		} else if (rc >= 0) {
 			/* It is an error if EA $LXDEV has wrong size. */

From 88cae132dc0539ad188b787d32a7df4e16b5c1af Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Mon, 30 Dec 2024 21:21:31 +0100
Subject: [PATCH 270/352] cifs: Allow fallback code in smb_set_file_info() also
 for directories
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On NT systems, it is possible to do SMB open call also for directories.
Open argument CREATE_NOT_DIR disallows opening directories. So in fallback
code path in smb_set_file_info() remove CREATE_NOT_DIR restriction to allow
it also for directories.

Similar fallback is implemented also in CIFSSMBSetPathInfoFB() function and
this function already allows to call operation for directories.

Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 3fdbb71036cf..7b17668e2a54 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -1032,7 +1032,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 		.tcon = tcon,
 		.cifs_sb = cifs_sb,
 		.desired_access = SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
-		.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR),
+		.create_options = cifs_create_options(cifs_sb, 0),
 		.disposition = FILE_OPEN,
 		.path = full_path,
 		.fid = &fid,

From 92210ccd877ba577585e420c99cff2b51c4c9fe2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Mon, 30 Dec 2024 22:18:53 +0100
Subject: [PATCH 271/352] cifs: Add fallback code path for cifs_mkdir_setinfo()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use SMBSetInformation() as a fallback function (when CIFSSMBSetPathInfo()
fails) which can set attribudes on the directory, including changing
read-only attribute.

Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1ops.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 7b17668e2a54..ca8f3dd7ff63 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -876,6 +876,11 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path,
 	info.Attributes = cpu_to_le32(dosattrs);
 	rc = CIFSSMBSetPathInfo(xid, tcon, full_path, &info, cifs_sb->local_nls,
 				cifs_sb);
+	if (rc == -EOPNOTSUPP || rc == -EINVAL)
+		rc = SMBSetInformation(xid, tcon, full_path,
+				       info.Attributes,
+				       0 /* do not change write time */,
+				       cifs_sb->local_nls, cifs_sb);
 	if (rc == 0)
 		cifsInode->cifsAttrs = dosattrs;
 }

From fa9fe8715055f8b9bcee38904065b2f1eb9197f0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Sun, 1 Jun 2025 18:01:54 +0200
Subject: [PATCH 272/352] cifs: Add comments for DeletePending assignments in
 open functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On more places is set DeletePending member to 0. Add comments why is 0 the
correct value. Paths in DELETE_PENDING state cannot be opened by new calls.
So if the newly issued open for that path succeed then it means that the
path cannot be in DELETE_PENDING state.

Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifssmb.c   | 4 ++--
 fs/smb/client/smb2inode.c | 2 +-
 fs/smb/client/smb2pdu.c   | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index d20766f664c4..2881efcbe09a 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1163,7 +1163,7 @@ OldOpenRetry:
 				cpu_to_le64(le32_to_cpu(pSMBr->EndOfFile));
 			pfile_info->EndOfFile = pfile_info->AllocationSize;
 			pfile_info->NumberOfLinks = cpu_to_le32(1);
-			pfile_info->DeletePending = 0;
+			pfile_info->DeletePending = 0; /* successful open = not delete pending */
 		}
 	}
 
@@ -1288,7 +1288,7 @@ openRetry:
 		buf->AllocationSize = rsp->AllocationSize;
 		buf->EndOfFile = rsp->EndOfFile;
 		buf->NumberOfLinks = cpu_to_le32(1);
-		buf->DeletePending = 0;
+		buf->DeletePending = 0; /* successful open = not delete pending */
 	}
 
 	cifs_buf_release(req);
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index e441fa2e7689..09e3fc81d7cb 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -676,7 +676,7 @@ finished:
 		idata->fi.EndOfFile = create_rsp->EndofFile;
 		if (le32_to_cpu(idata->fi.NumberOfLinks) == 0)
 			idata->fi.NumberOfLinks = cpu_to_le32(1); /* dummy value */
-		idata->fi.DeletePending = 0;
+		idata->fi.DeletePending = 0; /* successful open = not delete pending */
 		idata->fi.Directory = !!(le32_to_cpu(create_rsp->FileAttributes) & ATTR_DIRECTORY);
 
 		/* smb2_parse_contexts() fills idata->fi.IndexNumber */
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 42e2d4ea344d..b0739a2661bf 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3277,7 +3277,7 @@ replay_again:
 		buf->EndOfFile = rsp->EndofFile;
 		buf->Attributes = rsp->FileAttributes;
 		buf->NumberOfLinks = cpu_to_le32(1);
-		buf->DeletePending = 0;
+		buf->DeletePending = 0; /* successful open = not delete pending */
 	}
 
 

From 4bddf4587c131d7b8ce8952cd32b284dcda0dd1f Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Mon, 25 Aug 2025 23:32:23 +0300
Subject: [PATCH 273/352] tpm: Disable TPM2_TCG_HMAC by default

After reading all the feedback, right now disabling the TPM2_TCG_HMAC
is the right call.

Other views discussed:

A. Having a kernel command-line parameter or refining the feature
   otherwise. This goes to the area of improvements.  E.g., one
   example is my own idea where the null key specific code would be
   replaced with a persistent handle parameter (which can be
   *unambigously* defined as part of attestation process when
   done correctly).

B. Removing the code. I don't buy this because that is same as saying
   that HMAC encryption cannot work at all (if really nitpicking) in
   any form. Also I disagree on the view that the feature could not
   be refined to something more reasoable.

Also, both A and B are worst options in terms of backporting.

Thuss, this is the best possible choice.

Cc: stable@vger.kernel.or # v6.10+
Fixes: d2add27cf2b8 ("tpm: Add NULL primary creation")
Suggested-by: Chris Fenner <cfenn@google.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index ba3924eb13ba..99c6fde28810 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -29,7 +29,7 @@ if TCG_TPM
 
 config TCG_TPM2_HMAC
 	bool "Use HMAC and encrypted transactions on the TPM bus"
-	default X86_64
+	default n
 	select CRYPTO_ECDH
 	select CRYPTO_LIB_AESCFB
 	select CRYPTO_LIB_SHA256

From 2c2615c8423890b5ef8e0a186b65607ef5fdeda1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Fri, 1 Aug 2025 14:24:21 -0700
Subject: [PATCH 274/352] tpm: Compare HMAC values in constant time

In tpm_buf_check_hmac_response(), compare the HMAC values in constant
time using crypto_memneq() instead of in variable time using memcmp().

This is worthwhile to follow best practices and to be consistent with
MAC comparisons elsewhere in the kernel.  However, in this driver the
side channel seems to have been benign: the HMAC input data is
guaranteed to always be unique, which makes the usual MAC forgery via
timing side channel not possible.  Specifically, the HMAC input data in
tpm_buf_check_hmac_response() includes the "our_nonce" field, which was
generated by the kernel earlier, remains under the control of the
kernel, and is unique for each call to tpm_buf_check_hmac_response().

Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/Kconfig         | 1 +
 drivers/char/tpm/tpm2-sessions.c | 6 +++---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index 99c6fde28810..8a8f692b6088 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -33,6 +33,7 @@ config TCG_TPM2_HMAC
 	select CRYPTO_ECDH
 	select CRYPTO_LIB_AESCFB
 	select CRYPTO_LIB_SHA256
+	select CRYPTO_LIB_UTILS
 	help
 	  Setting this causes us to deploy a scheme which uses request
 	  and response HMACs in addition to encryption for
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index bdb119453dfb..5fbd62ee5090 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -71,6 +71,7 @@
 #include <crypto/ecdh.h>
 #include <crypto/hash.h>
 #include <crypto/hmac.h>
+#include <crypto/utils.h>
 
 /* maximum number of names the TPM must remember for authorization */
 #define AUTH_MAX_NAMES	3
@@ -829,12 +830,11 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
 	/* we're done with the rphash, so put our idea of the hmac there */
 	tpm2_hmac_final(&sctx, auth->session_key, sizeof(auth->session_key)
 			+ auth->passphrase_len, rphash);
-	if (memcmp(rphash, &buf->data[offset_s], SHA256_DIGEST_SIZE) == 0) {
-		rc = 0;
-	} else {
+	if (crypto_memneq(rphash, &buf->data[offset_s], SHA256_DIGEST_SIZE)) {
 		dev_err(&chip->dev, "TPM: HMAC check failed\n");
 		goto out;
 	}
+	rc = 0;
 
 	/* now do response decryption */
 	if (auth->attrs & TPM2_SA_ENCRYPT) {

From 64a7cfbcf548bb955220c15c39531befe0611475 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Fri, 1 Aug 2025 14:24:22 -0700
Subject: [PATCH 275/352] tpm: Use HMAC-SHA256 library instead of open-coded
 HMAC

Now that there are easy-to-use HMAC-SHA256 library functions, use these
in tpm2-sessions.c instead of open-coding the HMAC algorithm.

Note that the new implementation correctly handles keys longer than 64
bytes (SHA256_BLOCK_SIZE), whereas the old implementation handled such
keys incorrectly.  But it doesn't appear that such keys were being used.

Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm2-sessions.c | 98 +++++++++-----------------------
 1 file changed, 27 insertions(+), 71 deletions(-)

diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index 5fbd62ee5090..6d03c224e6b2 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -69,8 +69,7 @@
 #include <linux/unaligned.h>
 #include <crypto/kpp.h>
 #include <crypto/ecdh.h>
-#include <crypto/hash.h>
-#include <crypto/hmac.h>
+#include <crypto/sha2.h>
 #include <crypto/utils.h>
 
 /* maximum number of names the TPM must remember for authorization */
@@ -385,51 +384,6 @@ EXPORT_SYMBOL_GPL(tpm_buf_append_hmac_session);
 static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy,
 			       u32 *handle, u8 *name);
 
-/*
- * It turns out the crypto hmac(sha256) is hard for us to consume
- * because it assumes a fixed key and the TPM seems to change the key
- * on every operation, so we weld the hmac init and final functions in
- * here to give it the same usage characteristics as a regular hash
- */
-static void tpm2_hmac_init(struct sha256_ctx *sctx, u8 *key, u32 key_len)
-{
-	u8 pad[SHA256_BLOCK_SIZE];
-	int i;
-
-	sha256_init(sctx);
-	for (i = 0; i < sizeof(pad); i++) {
-		if (i < key_len)
-			pad[i] = key[i];
-		else
-			pad[i] = 0;
-		pad[i] ^= HMAC_IPAD_VALUE;
-	}
-	sha256_update(sctx, pad, sizeof(pad));
-}
-
-static void tpm2_hmac_final(struct sha256_ctx *sctx, u8 *key, u32 key_len,
-			    u8 *out)
-{
-	u8 pad[SHA256_BLOCK_SIZE];
-	int i;
-
-	for (i = 0; i < sizeof(pad); i++) {
-		if (i < key_len)
-			pad[i] = key[i];
-		else
-			pad[i] = 0;
-		pad[i] ^= HMAC_OPAD_VALUE;
-	}
-
-	/* collect the final hash;  use out as temporary storage */
-	sha256_final(sctx, out);
-
-	sha256_init(sctx);
-	sha256_update(sctx, pad, sizeof(pad));
-	sha256_update(sctx, out, SHA256_DIGEST_SIZE);
-	sha256_final(sctx, out);
-}
-
 /*
  * assume hash sha256 and nonces u, v of size SHA256_DIGEST_SIZE but
  * otherwise standard tpm2_KDFa.  Note output is in bytes not bits.
@@ -441,16 +395,16 @@ static void tpm2_KDFa(u8 *key, u32 key_len, const char *label, u8 *u,
 	const __be32 bits = cpu_to_be32(bytes * 8);
 
 	while (bytes > 0) {
-		struct sha256_ctx sctx;
+		struct hmac_sha256_ctx hctx;
 		__be32 c = cpu_to_be32(counter);
 
-		tpm2_hmac_init(&sctx, key, key_len);
-		sha256_update(&sctx, (u8 *)&c, sizeof(c));
-		sha256_update(&sctx, label, strlen(label)+1);
-		sha256_update(&sctx, u, SHA256_DIGEST_SIZE);
-		sha256_update(&sctx, v, SHA256_DIGEST_SIZE);
-		sha256_update(&sctx, (u8 *)&bits, sizeof(bits));
-		tpm2_hmac_final(&sctx, key, key_len, out);
+		hmac_sha256_init_usingrawkey(&hctx, key, key_len);
+		hmac_sha256_update(&hctx, (u8 *)&c, sizeof(c));
+		hmac_sha256_update(&hctx, label, strlen(label) + 1);
+		hmac_sha256_update(&hctx, u, SHA256_DIGEST_SIZE);
+		hmac_sha256_update(&hctx, v, SHA256_DIGEST_SIZE);
+		hmac_sha256_update(&hctx, (u8 *)&bits, sizeof(bits));
+		hmac_sha256_final(&hctx, out);
 
 		bytes -= SHA256_DIGEST_SIZE;
 		counter++;
@@ -594,6 +548,7 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf)
 	u32 attrs;
 	u8 cphash[SHA256_DIGEST_SIZE];
 	struct sha256_ctx sctx;
+	struct hmac_sha256_ctx hctx;
 
 	if (!auth)
 		return;
@@ -705,14 +660,14 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf)
 	sha256_final(&sctx, cphash);
 
 	/* now calculate the hmac */
-	tpm2_hmac_init(&sctx, auth->session_key, sizeof(auth->session_key)
-		       + auth->passphrase_len);
-	sha256_update(&sctx, cphash, sizeof(cphash));
-	sha256_update(&sctx, auth->our_nonce, sizeof(auth->our_nonce));
-	sha256_update(&sctx, auth->tpm_nonce, sizeof(auth->tpm_nonce));
-	sha256_update(&sctx, &auth->attrs, 1);
-	tpm2_hmac_final(&sctx, auth->session_key, sizeof(auth->session_key)
-			+ auth->passphrase_len, hmac);
+	hmac_sha256_init_usingrawkey(&hctx, auth->session_key,
+				     sizeof(auth->session_key) +
+					     auth->passphrase_len);
+	hmac_sha256_update(&hctx, cphash, sizeof(cphash));
+	hmac_sha256_update(&hctx, auth->our_nonce, sizeof(auth->our_nonce));
+	hmac_sha256_update(&hctx, auth->tpm_nonce, sizeof(auth->tpm_nonce));
+	hmac_sha256_update(&hctx, &auth->attrs, 1);
+	hmac_sha256_final(&hctx, hmac);
 }
 EXPORT_SYMBOL(tpm_buf_fill_hmac_session);
 
@@ -752,6 +707,7 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
 	u8 rphash[SHA256_DIGEST_SIZE];
 	u32 attrs, cc;
 	struct sha256_ctx sctx;
+	struct hmac_sha256_ctx hctx;
 	u16 tag = be16_to_cpu(head->tag);
 	int parm_len, len, i, handles;
 
@@ -821,15 +777,15 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
 	sha256_final(&sctx, rphash);
 
 	/* now calculate the hmac */
-	tpm2_hmac_init(&sctx, auth->session_key, sizeof(auth->session_key)
-		       + auth->passphrase_len);
-	sha256_update(&sctx, rphash, sizeof(rphash));
-	sha256_update(&sctx, auth->tpm_nonce, sizeof(auth->tpm_nonce));
-	sha256_update(&sctx, auth->our_nonce, sizeof(auth->our_nonce));
-	sha256_update(&sctx, &auth->attrs, 1);
+	hmac_sha256_init_usingrawkey(&hctx, auth->session_key,
+				     sizeof(auth->session_key) +
+					     auth->passphrase_len);
+	hmac_sha256_update(&hctx, rphash, sizeof(rphash));
+	hmac_sha256_update(&hctx, auth->tpm_nonce, sizeof(auth->tpm_nonce));
+	hmac_sha256_update(&hctx, auth->our_nonce, sizeof(auth->our_nonce));
+	hmac_sha256_update(&hctx, &auth->attrs, 1);
 	/* we're done with the rphash, so put our idea of the hmac there */
-	tpm2_hmac_final(&sctx, auth->session_key, sizeof(auth->session_key)
-			+ auth->passphrase_len, rphash);
+	hmac_sha256_final(&hctx, rphash);
 	if (crypto_memneq(rphash, &buf->data[offset_s], SHA256_DIGEST_SIZE)) {
 		dev_err(&chip->dev, "TPM: HMAC check failed\n");
 		goto out;

From 8a81236f2cb0882c7ea6c621ce357f7f3f601fe5 Mon Sep 17 00:00:00 2001
From: Gunnar Kudrjavets <gunnarku@amazon.com>
Date: Thu, 18 Sep 2025 18:49:40 +0300
Subject: [PATCH 276/352] tpm_tis: Fix incorrect arguments in
 tpm_tis_probe_irq_single

The tpm_tis_write8() call specifies arguments in wrong order. Should be
(data, addr, value) not (data, value, addr). The initial correct order
was changed during the major refactoring when the code was split.

Fixes: 41a5e1cf1fe1 ("tpm/tpm_tis: Split tpm_tis driver into a core and TCG TIS compliant phy")
Signed-off-by: Gunnar Kudrjavets <gunnarku@amazon.com>
Reviewed-by: Justinien Bouron <jbouron@amazon.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm_tis_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 4b12c4b9da8b..8954a8660ffc 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -978,8 +978,8 @@ restore_irqs:
 	 * will call disable_irq which undoes all of the above.
 	 */
 	if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) {
-		tpm_tis_write8(priv, original_int_vec,
-			       TPM_INT_VECTOR(priv->locality));
+		tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality),
+			       original_int_vec);
 		rc = -1;
 	}
 

From 207696b17f38e869e59889b44d395ab24bb678d3 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Thu, 18 Sep 2025 22:30:18 +0300
Subject: [PATCH 277/352] tpm: use a map for tpm2_calc_ordinal_duration()

The current shenanigans for duration calculation introduce too much
complexity for a trivial problem, and further the code is hard to patch and
maintain.

Address these issues with a flat look-up table, which is easy to understand
and patch. If leaf driver specific patching is required in future, it is
easy enough to make a copy of this table during driver initialization and
add the chip parameter back.

'chip->duration' is retained for TPM 1.x.

As the first entry for this new behavior address TCG spec update mentioned
in this issue:

https://github.com/raspberrypi/linux/issues/7054

Therefore, for TPM_SelfTest the duration is set to 3000 ms.

This does not categorize a as bug, given that this is introduced to the
spec after the feature was originally made.

Reviewed-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm-interface.c |   2 +-
 drivers/char/tpm/tpm.h           |   2 +-
 drivers/char/tpm/tpm2-cmd.c      | 127 ++++++++-----------------------
 include/linux/tpm.h              |   5 +-
 4 files changed, 37 insertions(+), 99 deletions(-)

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index b71725827743..c9f173001d0e 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(suspend_pcr,
 unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal)
 {
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
-		return tpm2_calc_ordinal_duration(chip, ordinal);
+		return tpm2_calc_ordinal_duration(ordinal);
 	else
 		return tpm1_calc_ordinal_duration(chip, ordinal);
 }
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 7bb87fa5f7a1..2726bd38e5ac 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -299,7 +299,7 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,
 ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip);
 int tpm2_auto_startup(struct tpm_chip *chip);
 void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type);
-unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
+unsigned long tpm2_calc_ordinal_duration(u32 ordinal);
 int tpm2_probe(struct tpm_chip *chip);
 int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip);
 int tpm2_find_cc(struct tpm_chip *chip, u32 cc);
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 524d802ede26..7d77f6fbc152 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -28,120 +28,57 @@ static struct tpm2_hash tpm2_hash_map[] = {
 
 int tpm2_get_timeouts(struct tpm_chip *chip)
 {
-	/* Fixed timeouts for TPM2 */
 	chip->timeout_a = msecs_to_jiffies(TPM2_TIMEOUT_A);
 	chip->timeout_b = msecs_to_jiffies(TPM2_TIMEOUT_B);
 	chip->timeout_c = msecs_to_jiffies(TPM2_TIMEOUT_C);
 	chip->timeout_d = msecs_to_jiffies(TPM2_TIMEOUT_D);
-
-	/* PTP spec timeouts */
-	chip->duration[TPM_SHORT] = msecs_to_jiffies(TPM2_DURATION_SHORT);
-	chip->duration[TPM_MEDIUM] = msecs_to_jiffies(TPM2_DURATION_MEDIUM);
-	chip->duration[TPM_LONG] = msecs_to_jiffies(TPM2_DURATION_LONG);
-
-	/* Key creation commands long timeouts */
-	chip->duration[TPM_LONG_LONG] =
-		msecs_to_jiffies(TPM2_DURATION_LONG_LONG);
-
 	chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS;
-
 	return 0;
 }
 
-/**
- * tpm2_ordinal_duration_index() - returns an index to the chip duration table
- * @ordinal: TPM command ordinal.
- *
- * The function returns an index to the chip duration table
- * (enum tpm_duration), that describes the maximum amount of
- * time the chip could take to return the result for a  particular ordinal.
- *
- * The values of the MEDIUM, and LONG durations are taken
- * from the PC Client Profile (PTP) specification (750, 2000 msec)
- *
- * LONG_LONG is for commands that generates keys which empirically takes
- * a longer time on some systems.
- *
- * Return:
- * * TPM_MEDIUM
- * * TPM_LONG
- * * TPM_LONG_LONG
- * * TPM_UNDEFINED
+/*
+ * Contains the maximum durations in milliseconds for TPM2 commands.
  */
-static u8 tpm2_ordinal_duration_index(u32 ordinal)
-{
-	switch (ordinal) {
-	/* Startup */
-	case TPM2_CC_STARTUP:                 /* 144 */
-		return TPM_MEDIUM;
-
-	case TPM2_CC_SELF_TEST:               /* 143 */
-		return TPM_LONG;
-
-	case TPM2_CC_GET_RANDOM:              /* 17B */
-		return TPM_LONG;
-
-	case TPM2_CC_SEQUENCE_UPDATE:         /* 15C */
-		return TPM_MEDIUM;
-	case TPM2_CC_SEQUENCE_COMPLETE:       /* 13E */
-		return TPM_MEDIUM;
-	case TPM2_CC_EVENT_SEQUENCE_COMPLETE: /* 185 */
-		return TPM_MEDIUM;
-	case TPM2_CC_HASH_SEQUENCE_START:     /* 186 */
-		return TPM_MEDIUM;
-
-	case TPM2_CC_VERIFY_SIGNATURE:        /* 177 */
-		return TPM_LONG_LONG;
-
-	case TPM2_CC_PCR_EXTEND:              /* 182 */
-		return TPM_MEDIUM;
-
-	case TPM2_CC_HIERARCHY_CONTROL:       /* 121 */
-		return TPM_LONG;
-	case TPM2_CC_HIERARCHY_CHANGE_AUTH:   /* 129 */
-		return TPM_LONG;
-
-	case TPM2_CC_GET_CAPABILITY:          /* 17A */
-		return TPM_MEDIUM;
-
-	case TPM2_CC_NV_READ:                 /* 14E */
-		return TPM_LONG;
-
-	case TPM2_CC_CREATE_PRIMARY:          /* 131 */
-		return TPM_LONG_LONG;
-	case TPM2_CC_CREATE:                  /* 153 */
-		return TPM_LONG_LONG;
-	case TPM2_CC_CREATE_LOADED:           /* 191 */
-		return TPM_LONG_LONG;
-
-	default:
-		return TPM_UNDEFINED;
-	}
-}
+static const struct {
+	unsigned long ordinal;
+	unsigned long duration;
+} tpm2_ordinal_duration_map[] = {
+	{TPM2_CC_STARTUP, 750},
+	{TPM2_CC_SELF_TEST, 3000},
+	{TPM2_CC_GET_RANDOM, 2000},
+	{TPM2_CC_SEQUENCE_UPDATE, 750},
+	{TPM2_CC_SEQUENCE_COMPLETE, 750},
+	{TPM2_CC_EVENT_SEQUENCE_COMPLETE, 750},
+	{TPM2_CC_HASH_SEQUENCE_START, 750},
+	{TPM2_CC_VERIFY_SIGNATURE, 30000},
+	{TPM2_CC_PCR_EXTEND, 750},
+	{TPM2_CC_HIERARCHY_CONTROL, 2000},
+	{TPM2_CC_HIERARCHY_CHANGE_AUTH, 2000},
+	{TPM2_CC_GET_CAPABILITY, 750},
+	{TPM2_CC_NV_READ, 2000},
+	{TPM2_CC_CREATE_PRIMARY, 30000},
+	{TPM2_CC_CREATE, 30000},
+	{TPM2_CC_CREATE_LOADED, 30000},
+};
 
 /**
- * tpm2_calc_ordinal_duration() - calculate the maximum command duration
- * @chip:    TPM chip to use.
+ * tpm2_calc_ordinal_duration() - Calculate the maximum command duration
  * @ordinal: TPM command ordinal.
  *
- * The function returns the maximum amount of time the chip could take
- * to return the result for a particular ordinal in jiffies.
- *
- * Return: A maximal duration time for an ordinal in jiffies.
+ * Returns the maximum amount of time the chip is expected by kernel to
+ * take in jiffies.
  */
-unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal)
+unsigned long tpm2_calc_ordinal_duration(u32 ordinal)
 {
-	unsigned int index;
+	int i;
 
-	index = tpm2_ordinal_duration_index(ordinal);
+	for (i = 0; i < ARRAY_SIZE(tpm2_ordinal_duration_map); i++)
+		if (ordinal == tpm2_ordinal_duration_map[i].ordinal)
+			return msecs_to_jiffies(tpm2_ordinal_duration_map[i].duration);
 
-	if (index != TPM_UNDEFINED)
-		return chip->duration[index];
-	else
-		return msecs_to_jiffies(TPM2_DURATION_DEFAULT);
+	return msecs_to_jiffies(TPM2_DURATION_DEFAULT);
 }
 
-
 struct tpm2_pcr_read_out {
 	__be32	update_cnt;
 	__be32	pcr_selects_cnt;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index b0e9eb5ef022..dc0338a783f3 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -228,10 +228,11 @@ enum tpm2_timeouts {
 	TPM2_TIMEOUT_B          =   4000,
 	TPM2_TIMEOUT_C          =    200,
 	TPM2_TIMEOUT_D          =     30,
+};
+
+enum tpm2_durations {
 	TPM2_DURATION_SHORT     =     20,
-	TPM2_DURATION_MEDIUM    =    750,
 	TPM2_DURATION_LONG      =   2000,
-	TPM2_DURATION_LONG_LONG = 300000,
 	TPM2_DURATION_DEFAULT   = 120000,
 };
 

From a29ad21b988652dc60aa99c6d3b1e3d52dc69c30 Mon Sep 17 00:00:00 2001
From: Denis Aleksandrov <daleksan@redhat.com>
Date: Mon, 15 Sep 2025 17:08:29 -0400
Subject: [PATCH 278/352] tpm: Prevent local DOS via tpm/tpm0/ppi/*operations

Reads on tpm/tpm0/ppi/*operations can become very long on
misconfigured systems. Reading the TPM is a blocking operation,
thus a user could effectively trigger a DOS.

Resolve this by caching the results and avoiding the blocking
operations after the first read.

[ jarkko: fixed atomic sleep:
  sed -i 's/spin_/mutex_/g' drivers/char/tpm/tpm_ppi.c
  sed -i 's/DEFINE_SPINLOCK/DEFINE_MUTEX/g' drivers/char/tpm/tpm_ppi.c ]

Signed-off-by: Denis Aleksandrov <daleksan@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Closes: https://lore.kernel.org/linux-integrity/20250915210829.6661-1-daleksan@redhat.com/T/#u
Suggested-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm_ppi.c | 89 ++++++++++++++++++++++++++++----------
 1 file changed, 66 insertions(+), 23 deletions(-)

diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index d53fce1c9d6f..c9793a3d986d 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -33,6 +33,20 @@ static const guid_t tpm_ppi_guid =
 	GUID_INIT(0x3DDDFAA6, 0x361B, 0x4EB4,
 		  0xA4, 0x24, 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53);
 
+static const char * const tpm_ppi_info[] = {
+	"Not implemented",
+	"BIOS only",
+	"Blocked for OS by system firmware",
+	"User required",
+	"User not required",
+};
+
+/* A spinlock to protect access to the cache from concurrent reads */
+static DEFINE_MUTEX(tpm_ppi_lock);
+
+static u32 ppi_operations_cache[PPI_VS_REQ_END + 1];
+static bool ppi_cache_populated;
+
 static bool tpm_ppi_req_has_parameter(u64 req)
 {
 	return req == 23;
@@ -277,8 +291,7 @@ cleanup:
 	return status;
 }
 
-static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start,
-				   u32 end)
+static ssize_t cache_ppi_operations(acpi_handle dev_handle, char *buf)
 {
 	int i;
 	u32 ret;
@@ -286,34 +299,22 @@ static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start,
 	union acpi_object *obj, tmp;
 	union acpi_object argv = ACPI_INIT_DSM_ARGV4(1, &tmp);
 
-	static char *info[] = {
-		"Not implemented",
-		"BIOS only",
-		"Blocked for OS by BIOS",
-		"User required",
-		"User not required",
-	};
-
 	if (!acpi_check_dsm(dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID_1,
 			    1 << TPM_PPI_FN_GETOPR))
 		return -EPERM;
 
 	tmp.integer.type = ACPI_TYPE_INTEGER;
-	for (i = start; i <= end; i++) {
+	for (i = 0; i <= PPI_VS_REQ_END; i++) {
 		tmp.integer.value = i;
 		obj = tpm_eval_dsm(dev_handle, TPM_PPI_FN_GETOPR,
 				   ACPI_TYPE_INTEGER, &argv,
 				   TPM_PPI_REVISION_ID_1);
-		if (!obj) {
+		if (!obj)
 			return -ENOMEM;
-		} else {
-			ret = obj->integer.value;
-			ACPI_FREE(obj);
-		}
 
-		if (ret > 0 && ret < ARRAY_SIZE(info))
-			len += sysfs_emit_at(buf, len, "%d %d: %s\n",
-					     i, ret, info[ret]);
+		ret = obj->integer.value;
+		ppi_operations_cache[i] = ret;
+		ACPI_FREE(obj);
 	}
 
 	return len;
@@ -324,9 +325,30 @@ static ssize_t tpm_show_ppi_tcg_operations(struct device *dev,
 					   char *buf)
 {
 	struct tpm_chip *chip = to_tpm_chip(dev);
+	ssize_t len = 0;
+	u32 ret;
+	int i;
 
-	return show_ppi_operations(chip->acpi_dev_handle, buf, 0,
-				   PPI_TPM_REQ_MAX);
+	mutex_lock(&tpm_ppi_lock);
+	if (!ppi_cache_populated) {
+		len = cache_ppi_operations(chip->acpi_dev_handle, buf);
+		if (len < 0) {
+			mutex_unlock(&tpm_ppi_lock);
+			return len;
+		}
+
+		ppi_cache_populated = true;
+	}
+
+	for (i = 0; i <= PPI_TPM_REQ_MAX; i++) {
+		ret = ppi_operations_cache[i];
+		if (ret >= 0 && ret < ARRAY_SIZE(tpm_ppi_info))
+			len += sysfs_emit_at(buf, len, "%d %d: %s\n",
+							i, ret, tpm_ppi_info[ret]);
+	}
+	mutex_unlock(&tpm_ppi_lock);
+
+	return len;
 }
 
 static ssize_t tpm_show_ppi_vs_operations(struct device *dev,
@@ -334,9 +356,30 @@ static ssize_t tpm_show_ppi_vs_operations(struct device *dev,
 					  char *buf)
 {
 	struct tpm_chip *chip = to_tpm_chip(dev);
+	ssize_t len = 0;
+	u32 ret;
+	int i;
 
-	return show_ppi_operations(chip->acpi_dev_handle, buf, PPI_VS_REQ_START,
-				   PPI_VS_REQ_END);
+	mutex_lock(&tpm_ppi_lock);
+	if (!ppi_cache_populated) {
+		len = cache_ppi_operations(chip->acpi_dev_handle, buf);
+		if (len < 0) {
+			mutex_unlock(&tpm_ppi_lock);
+			return len;
+		}
+
+		ppi_cache_populated = true;
+	}
+
+	for (i = PPI_VS_REQ_START; i <= PPI_VS_REQ_END; i++) {
+		ret = ppi_operations_cache[i];
+		if (ret >= 0 && ret < ARRAY_SIZE(tpm_ppi_info))
+			len += sysfs_emit_at(buf, len, "%d %d: %s\n",
+							i, ret, tpm_ppi_info[ret]);
+	}
+	mutex_unlock(&tpm_ppi_lock);
+
+	return len;
 }
 
 static DEVICE_ATTR(version, S_IRUGO, tpm_show_ppi_version, NULL);

From f3426ac54c42c3260096ddc50b5470eb179fb06a Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 8 Oct 2025 16:14:18 +0200
Subject: [PATCH 279/352] dpll: zl3073x: Increase maximum size of flash utility

Newer firmware bundles contain a flash utility whose size exceeds
the currently allowed limit. Increase the maximum allowed size
to accommodate the newer utility version.

Without this patch:
 # devlink dev flash i2c/1-0070 file fw_nosplit_v3.hex
 Failed to load firmware
 Flashing failed
 Error: zl3073x: FW load failed: [utility] component is too big (11000 bytes)

Fixes: ca017409da694 ("dpll: zl3073x: Add firmware loading functionality")
Suggested-by: Prathosh Satish <Prathosh.Satish@microchip.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20251008141418.841053-1-ivecera@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/dpll/zl3073x/fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dpll/zl3073x/fw.c b/drivers/dpll/zl3073x/fw.c
index d5418ff74886..def37fe8d9b0 100644
--- a/drivers/dpll/zl3073x/fw.c
+++ b/drivers/dpll/zl3073x/fw.c
@@ -37,7 +37,7 @@ struct zl3073x_fw_component_info {
 static const struct zl3073x_fw_component_info component_info[] = {
 	[ZL_FW_COMPONENT_UTIL] = {
 		.name		= "utility",
-		.max_size	= 0x2300,
+		.max_size	= 0x4000,
 		.load_addr	= 0x20000000,
 		.flash_type	= ZL3073X_FLASH_TYPE_NONE,
 	},

From b5f8aa8d4bde0cf3e4595af5a536da337e5f1c78 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 24 Sep 2025 16:51:29 +0200
Subject: [PATCH 280/352] gpio: wcd934x: mark the GPIO controller as sleeping

The slimbus regmap passed to the GPIO driver down from MFD does not use
fast_io. This means a mutex is used for locking and thus this GPIO chip
must not be used in atomic context. Change the can_sleep switch in
struct gpio_chip to true.

Fixes: 59c324683400 ("gpio: wcd934x: Add support to wcd934x gpio controller")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-wcd934x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c
index 4af504c23e6f..572b85e77370 100644
--- a/drivers/gpio/gpio-wcd934x.c
+++ b/drivers/gpio/gpio-wcd934x.c
@@ -103,7 +103,7 @@ static int wcd_gpio_probe(struct platform_device *pdev)
 	chip->base = -1;
 	chip->ngpio = WCD934X_NPINS;
 	chip->label = dev_name(dev);
-	chip->can_sleep = false;
+	chip->can_sleep = true;
 
 	return devm_gpiochip_add_data(dev, chip, data);
 }

From 4dd5b5ac089bb6ea719b7ffb748707ac9cbce4e4 Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@redhat.com>
Date: Wed, 8 Oct 2025 14:44:17 +0200
Subject: [PATCH 281/352] Revert "fs: make vfs_fileattr_[get|set] return
 -EOPNOTSUPP"

This reverts commit 474b155adf3927d2c944423045757b54aa1ca4de.

This patch caused regression in ioctl_setflags(). Underlying filesystems
use EOPNOTSUPP to indicate that flag is not supported. This error is
also gets converted in ioctl_setflags(). Therefore, for unsupported
flags error changed from EOPNOSUPP to ENOIOCTLCMD.

Link: https://lore.kernel.org/linux-xfs/a622643f-1585-40b0-9441-cf7ece176e83@kernel.org/
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c         | 12 ++----------
 fs/fuse/ioctl.c        |  4 ----
 fs/overlayfs/copy_up.c |  2 +-
 fs/overlayfs/inode.c   |  5 ++++-
 4 files changed, 7 insertions(+), 16 deletions(-)

diff --git a/fs/file_attr.c b/fs/file_attr.c
index 12424d4945d0..460b2dd21a85 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -84,7 +84,7 @@ int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 	int error;
 
 	if (!inode->i_op->fileattr_get)
-		return -EOPNOTSUPP;
+		return -ENOIOCTLCMD;
 
 	error = security_inode_file_getattr(dentry, fa);
 	if (error)
@@ -270,7 +270,7 @@ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
 	int err;
 
 	if (!inode->i_op->fileattr_set)
-		return -EOPNOTSUPP;
+		return -ENOIOCTLCMD;
 
 	if (!inode_owner_or_capable(idmap, inode))
 		return -EPERM;
@@ -312,8 +312,6 @@ int ioctl_getflags(struct file *file, unsigned int __user *argp)
 	int err;
 
 	err = vfs_fileattr_get(file->f_path.dentry, &fa);
-	if (err == -EOPNOTSUPP)
-		err = -ENOIOCTLCMD;
 	if (!err)
 		err = put_user(fa.flags, argp);
 	return err;
@@ -335,8 +333,6 @@ int ioctl_setflags(struct file *file, unsigned int __user *argp)
 			fileattr_fill_flags(&fa, flags);
 			err = vfs_fileattr_set(idmap, dentry, &fa);
 			mnt_drop_write_file(file);
-			if (err == -EOPNOTSUPP)
-				err = -ENOIOCTLCMD;
 		}
 	}
 	return err;
@@ -349,8 +345,6 @@ int ioctl_fsgetxattr(struct file *file, void __user *argp)
 	int err;
 
 	err = vfs_fileattr_get(file->f_path.dentry, &fa);
-	if (err == -EOPNOTSUPP)
-		err = -ENOIOCTLCMD;
 	if (!err)
 		err = copy_fsxattr_to_user(&fa, argp);
 
@@ -371,8 +365,6 @@ int ioctl_fssetxattr(struct file *file, void __user *argp)
 		if (!err) {
 			err = vfs_fileattr_set(idmap, dentry, &fa);
 			mnt_drop_write_file(file);
-			if (err == -EOPNOTSUPP)
-				err = -ENOIOCTLCMD;
 		}
 	}
 	return err;
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 57032eadca6c..fdc175e93f74 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -536,8 +536,6 @@ int fuse_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 cleanup:
 	fuse_priv_ioctl_cleanup(inode, ff);
 
-	if (err == -ENOTTY)
-		err = -EOPNOTSUPP;
 	return err;
 }
 
@@ -574,7 +572,5 @@ int fuse_fileattr_set(struct mnt_idmap *idmap,
 cleanup:
 	fuse_priv_ioctl_cleanup(inode, ff);
 
-	if (err == -ENOTTY)
-		err = -EOPNOTSUPP;
 	return err;
 }
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aac7e34f56c1..604a82acd164 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -178,7 +178,7 @@ static int ovl_copy_fileattr(struct inode *inode, const struct path *old,
 	err = ovl_real_fileattr_get(old, &oldfa);
 	if (err) {
 		/* Ntfs-3g returns -EINVAL for "no fileattr support" */
-		if (err == -EOPNOTSUPP || err == -EINVAL)
+		if (err == -ENOTTY || err == -EINVAL)
 			return 0;
 		pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n",
 			old->dentry, err);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index aaa4cf579561..e11f310ce092 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -720,7 +720,10 @@ int ovl_real_fileattr_get(const struct path *realpath, struct file_kattr *fa)
 	if (err)
 		return err;
 
-	return vfs_fileattr_get(realpath->dentry, fa);
+	err = vfs_fileattr_get(realpath->dentry, fa);
+	if (err == -ENOIOCTLCMD)
+		err = -ENOTTY;
+	return err;
 }
 
 int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa)

From d90ad28e8aa482e397150e22f3762173d918a724 Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@redhat.com>
Date: Wed, 8 Oct 2025 14:44:18 +0200
Subject: [PATCH 282/352] fs: return EOPNOTSUPP from file_setattr/file_getattr
 syscalls

These syscalls call to vfs_fileattr_get/set functions which return
ENOIOCTLCMD if filesystem doesn't support setting file attribute on an
inode. For syscalls EOPNOTSUPP would be more appropriate return error.

Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/file_attr.c b/fs/file_attr.c
index 460b2dd21a85..1dcec88c0680 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -416,6 +416,8 @@ SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
 	}
 
 	error = vfs_fileattr_get(filepath.dentry, &fa);
+	if (error == -ENOIOCTLCMD || error == -ENOTTY)
+		error = -EOPNOTSUPP;
 	if (error)
 		return error;
 
@@ -483,6 +485,8 @@ SYSCALL_DEFINE5(file_setattr, int, dfd, const char __user *, filename,
 	if (!error) {
 		error = vfs_fileattr_set(mnt_idmap(filepath.mnt),
 					 filepath.dentry, &fa);
+		if (error == -ENOIOCTLCMD || error == -ENOTTY)
+			error = -EOPNOTSUPP;
 		mnt_drop_write(filepath.mnt);
 	}
 

From 7933a585d70ee496fa341b50b8b0a95b131867ff Mon Sep 17 00:00:00 2001
From: Seong-Gwang Heo <heo@mykernel.net>
Date: Thu, 9 Oct 2025 13:41:48 +0800
Subject: [PATCH 283/352] ovl: remove redundant IOCB_DIO_CALLER_COMP clearing

The backing_file_write_iter() function, which is called
immediately after this code, already contains identical
logic to clear the IOCB_DIO_CALLER_COMP flag along with
the same explanatory comment. There is no need to duplicate
this operation in the overlayfs code.

Signed-off-by: Seong-Gwang Heo <heo@mykernel.net>
Fixes: a6293b3e285c ("fs: factor out backing_file_{read,write}_iter() helpers")
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/file.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index fc52c796061d..7ab2c9daffd0 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -369,11 +369,6 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
 		ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
 
-	/*
-	 * Overlayfs doesn't support deferred completions, don't copy
-	 * this property in case it is set by the issuer.
-	 */
-	ifl &= ~IOCB_DIO_CALLER_COMP;
 	ret = backing_file_write_iter(realfile, iter, iocb, ifl, &ctx);
 
 out_unlock:

From dc6b724974018c1b3b6fd704899782da3f12f145 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Fri, 10 Oct 2025 08:04:46 -0500
Subject: [PATCH 284/352] MAINTAINERS: Move DT patchwork to kernel.org

The ozlabs.org PW instance is slow due to being geographically far away
from any of the maintainers and seems to have gotten slower as of late
(AI scrapers perhaps). The kernel.org PW also has some additional
features (i.e. pwbot) we want to use.

DT core patches also go into PW, so add the PW link for it.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3c1970f96d99..9ffa6408fa97 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18882,6 +18882,7 @@ M:	Rob Herring <robh@kernel.org>
 M:	Saravana Kannan <saravanak@google.com>
 L:	devicetree@vger.kernel.org
 S:	Maintained
+Q:	http://patchwork.kernel.org/project/devicetree/list/
 W:	http://www.devicetree.org/
 C:	irc://irc.libera.chat/devicetree
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
@@ -18902,7 +18903,7 @@ M:	Krzysztof Kozlowski <krzk+dt@kernel.org>
 M:	Conor Dooley <conor+dt@kernel.org>
 L:	devicetree@vger.kernel.org
 S:	Maintained
-Q:	http://patchwork.ozlabs.org/project/devicetree-bindings/list/
+Q:	http://patchwork.kernel.org/project/devicetree/list/
 C:	irc://irc.libera.chat/devicetree
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
 F:	Documentation/devicetree/

From b30c32c784bf29735dabff15443a5feeafd26d1c Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sat, 4 Oct 2025 19:50:31 -0500
Subject: [PATCH 285/352] cifs: update internal version number

    to 2.57

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 3ce7c614ccc0..e9534258d1ef 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 56
-#define CIFS_VERSION   "2.56"
+#define SMB3_PRODUCT_BUILD 57
+#define CIFS_VERSION   "2.57"
 #endif				/* _CIFSFS_H */

From 4b47a8601b71ad98833b447d465592d847b4dc77 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 11 Sep 2025 11:12:06 -0400
Subject: [PATCH 286/352] NFSD: Define a proc_layoutcommit for the FlexFiles
 layout type

Avoid a crash if a pNFS client should happen to send a LAYOUTCOMMIT
operation on a FlexFiles layout.

Reported-by: Robert Morris <rtm@csail.mit.edu>
Closes: https://lore.kernel.org/linux-nfs/152f99b2-ba35-4dec-93a9-4690e625dccd@oracle.com/T/#t
Cc: Thomas Haynes <loghyr@hammerspace.com>
Cc: stable@vger.kernel.org
Fixes: 9b9960a0ca47 ("nfsd: Add a super simple flex file server")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/flexfilelayout.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
index c318cf74e388..0f1a35400cd5 100644
--- a/fs/nfsd/flexfilelayout.c
+++ b/fs/nfsd/flexfilelayout.c
@@ -125,6 +125,13 @@ nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
 	return 0;
 }
 
+static __be32
+nfsd4_ff_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	return nfs_ok;
+}
+
 const struct nfsd4_layout_ops ff_layout_ops = {
 	.notify_types		=
 			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
@@ -133,4 +140,5 @@ const struct nfsd4_layout_ops ff_layout_ops = {
 	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
 	.proc_layoutget		= nfsd4_ff_proc_layoutget,
 	.encode_layoutget	= nfsd4_ff_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_ff_proc_layoutcommit,
 };

From 07ca98f906a403637fc5e513a872a50ef1247f3b Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 8 Oct 2025 18:56:59 +0200
Subject: [PATCH 287/352] xsk: Harden userspace-supplied xdp_desc validation

Turned out certain clearly invalid values passed in xdp_desc from
userspace can pass xp_{,un}aligned_validate_desc() and then lead
to UBs or just invalid frames to be queued for xmit.

desc->len close to ``U32_MAX`` with a non-zero pool->tx_metadata_len
can cause positive integer overflow and wraparound, the same way low
enough desc->addr with a non-zero pool->tx_metadata_len can cause
negative integer overflow. Both scenarios can then pass the
validation successfully.
This doesn't happen with valid XSk applications, but can be used
to perform attacks.

Always promote desc->len to ``u64`` first to exclude positive
overflows of it. Use explicit check_{add,sub}_overflow() when
validating desc->addr (which is ``u64`` already).

bloat-o-meter reports a little growth of the code size:

add/remove: 0/0 grow/shrink: 2/1 up/down: 60/-16 (44)
Function                                     old     new   delta
xskq_cons_peek_desc                          299     330     +31
xsk_tx_peek_release_desc_batch               973    1002     +29
xsk_generic_xmit                            3148    3132     -16

but hopefully this doesn't hurt the performance much.

Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len")
Cc: stable@vger.kernel.org # 6.8+
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20251008165659.4141318-1-aleksander.lobakin@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk_queue.h | 45 +++++++++++++++++++++++++++++++++++----------
 1 file changed, 35 insertions(+), 10 deletions(-)

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index f16f390370dc..1eb8d9f8b104 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -143,14 +143,24 @@ static inline bool xp_unused_options_set(u32 options)
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
-	u64 addr = desc->addr - pool->tx_metadata_len;
-	u64 len = desc->len + pool->tx_metadata_len;
-	u64 offset = addr & (pool->chunk_size - 1);
+	u64 len = desc->len;
+	u64 addr, offset;
 
-	if (!desc->len)
+	if (!len)
 		return false;
 
-	if (offset + len > pool->chunk_size)
+	/* Can overflow if desc->addr < pool->tx_metadata_len */
+	if (check_sub_overflow(desc->addr, pool->tx_metadata_len, &addr))
+		return false;
+
+	offset = addr & (pool->chunk_size - 1);
+
+	/*
+	 * Can't overflow: @offset is guaranteed to be < ``U32_MAX``
+	 * (pool->chunk_size is ``u32``), @len is guaranteed
+	 * to be <= ``U32_MAX``.
+	 */
+	if (offset + len + pool->tx_metadata_len > pool->chunk_size)
 		return false;
 
 	if (addr >= pool->addrs_cnt)
@@ -158,27 +168,42 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 
 	if (xp_unused_options_set(desc->options))
 		return false;
+
 	return true;
 }
 
 static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 					      struct xdp_desc *desc)
 {
-	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
-	u64 len = desc->len + pool->tx_metadata_len;
+	u64 len = desc->len;
+	u64 addr, end;
 
-	if (!desc->len)
+	if (!len)
 		return false;
 
+	/* Can't overflow: @len is guaranteed to be <= ``U32_MAX`` */
+	len += pool->tx_metadata_len;
 	if (len > pool->chunk_size)
 		return false;
 
-	if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt ||
-	    xp_desc_crosses_non_contig_pg(pool, addr, len))
+	/* Can overflow if desc->addr is close to 0 */
+	if (check_sub_overflow(xp_unaligned_add_offset_to_addr(desc->addr),
+			       pool->tx_metadata_len, &addr))
+		return false;
+
+	if (addr >= pool->addrs_cnt)
+		return false;
+
+	/* Can overflow if pool->addrs_cnt is high enough */
+	if (check_add_overflow(addr, len, &end) || end > pool->addrs_cnt)
+		return false;
+
+	if (xp_desc_crosses_non_contig_pg(pool, addr, len))
 		return false;
 
 	if (xp_unused_options_set(desc->options))
 		return false;
+
 	return true;
 }
 

From 3c652c3a71de1d30d72dc82c3bead8deb48eb749 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Tue, 16 Sep 2025 17:33:36 +0800
Subject: [PATCH 288/352] jbd2: ensure that all ongoing I/O complete before
 freeing blocks

When releasing file system metadata blocks in jbd2_journal_forget(), if
this buffer has not yet been checkpointed, it may have already been
written back, currently be in the process of being written back, or has
not yet written back.  jbd2_journal_forget() calls
jbd2_journal_try_remove_checkpoint() to check the buffer's status and
add it to the current transaction if it has not been written back. This
buffer can only be reallocated after the transaction is committed.

jbd2_journal_try_remove_checkpoint() attempts to lock the buffer and
check its dirty status while holding the buffer lock. If the buffer has
already been written back, everything proceeds normally. However, there
are two issues. First, the function returns immediately if the buffer is
locked by the write-back process. It does not wait for the write-back to
complete. Consequently, until the current transaction is committed and
the block is reallocated, there is no guarantee that the I/O will
complete. This means that ongoing I/O could write stale metadata to the
newly allocated block, potentially corrupting data. Second, the function
unlocks the buffer as soon as it detects that the buffer is still dirty.
If a concurrent write-back occurs immediately after this unlocking and
before clear_buffer_dirty() is called in jbd2_journal_forget(), data
corruption can theoretically still occur.

Although these two issues are unlikely to occur in practice since the
undergoing metadata writeback I/O does not take this long to complete,
it's better to explicitly ensure that all ongoing I/O operations are
completed.

Fixes: 597599268e3b ("jbd2: discard dirty data when forgetting an un-journalled buffer")
Cc: stable@kernel.org
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Message-ID: <20250916093337.3161016-2-yi.zhang@huaweicloud.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/transaction.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index c7867139af69..3e510564de6e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1659,6 +1659,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 	int drop_reserve = 0;
 	int err = 0;
 	int was_modified = 0;
+	int wait_for_writeback = 0;
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
@@ -1782,18 +1783,22 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 		}
 
 		/*
-		 * The buffer is still not written to disk, we should
-		 * attach this buffer to current transaction so that the
-		 * buffer can be checkpointed only after the current
-		 * transaction commits.
+		 * The buffer has not yet been written to disk. We should
+		 * either clear the buffer or ensure that the ongoing I/O
+		 * is completed, and attach this buffer to current
+		 * transaction so that the buffer can be checkpointed only
+		 * after the current transaction commits.
 		 */
 		clear_buffer_dirty(bh);
+		wait_for_writeback = 1;
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
 		spin_unlock(&journal->j_list_lock);
 	}
 drop:
 	__brelse(bh);
 	spin_unlock(&jh->b_state_lock);
+	if (wait_for_writeback)
+		wait_on_buffer(bh);
 	jbd2_journal_put_journal_head(jh);
 	if (drop_reserve) {
 		/* no need to reserve log space for this block -bzzz */

From 4f375ade6aa9f37fd72d7a78682f639772089eed Mon Sep 17 00:00:00 2001
From: KaFai Wan <kafai.wan@linux.dev>
Date: Wed, 8 Oct 2025 18:26:26 +0800
Subject: [PATCH 289/352] bpf: Avoid RCU context warning when unpinning htab
 with internal structs

When unpinning a BPF hash table (htab or htab_lru) that contains internal
structures (timer, workqueue, or task_work) in its values, a BUG warning
is triggered:
 BUG: sleeping function called from invalid context at kernel/bpf/hashtab.c:244
 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 14, name: ksoftirqd/0
 ...

The issue arises from the interaction between BPF object unpinning and
RCU callback mechanisms:
1. BPF object unpinning uses ->free_inode() which schedules cleanup via
   call_rcu(), deferring the actual freeing to an RCU callback that
   executes within the RCU_SOFTIRQ context.
2. During cleanup of hash tables containing internal structures,
   htab_map_free_internal_structs() is invoked, which includes
   cond_resched() or cond_resched_rcu() calls to yield the CPU during
   potentially long operations.

However, cond_resched() or cond_resched_rcu() cannot be safely called from
atomic RCU softirq context, leading to the BUG warning when attempting
to reschedule.

Fix this by changing from ->free_inode() to ->destroy_inode() and rename
bpf_free_inode() to bpf_destroy_inode() for BPF objects (prog, map, link).
This allows direct inode freeing without RCU callback scheduling,
avoiding the invalid context warning.

Reported-by: Le Chen <tom2cat@sjtu.edu.cn>
Closes: https://lore.kernel.org/all/1444123482.1827743.1750996347470.JavaMail.zimbra@sjtu.edu.cn/
Fixes: 68134668c17f ("bpf: Add map side support for bpf timers.")
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: KaFai Wan <kafai.wan@linux.dev>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20251008102628.808045-2-kafai.wan@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index f90bdcc0a047..81780bcf8d25 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -775,7 +775,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
-static void bpf_free_inode(struct inode *inode)
+static void bpf_destroy_inode(struct inode *inode)
 {
 	enum bpf_type type;
 
@@ -790,7 +790,7 @@ const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= inode_just_drop,
 	.show_options	= bpf_show_options,
-	.free_inode	= bpf_free_inode,
+	.destroy_inode	= bpf_destroy_inode,
 };
 
 enum {

From accb9a7e87f096a12eb21256107b9c8e343f8019 Mon Sep 17 00:00:00 2001
From: KaFai Wan <kafai.wan@linux.dev>
Date: Wed, 8 Oct 2025 18:26:27 +0800
Subject: [PATCH 290/352] selftests/bpf: Add test for unpinning htab with
 internal timer struct

Add test to verify that unpinning hash tables containing internal timer
structures does not trigger context warnings.

Each subtest (timer_prealloc and timer_no_prealloc) can trigger the
context warning when unpinning, but the warning cannot be triggered
twice within a short time interval (a HZ), which is expected behavior.

Signed-off-by: KaFai Wan <kafai.wan@linux.dev>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20251008102628.808045-3-kafai.wan@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/pinning_htab.c   | 36 +++++++++++++++++++
 .../selftests/bpf/progs/test_pinning_htab.c   | 25 +++++++++++++
 2 files changed, 61 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/pinning_htab.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_pinning_htab.c

diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_htab.c b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
new file mode 100644
index 000000000000..16bd74be3dbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_pinning_htab.skel.h"
+
+static void unpin_map(const char *map_name, const char *pin_path)
+{
+	struct test_pinning_htab *skel;
+	struct bpf_map *map;
+	int err;
+
+	skel = test_pinning_htab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(map, "bpf_object__find_map_by_name"))
+		goto out;
+
+	err = bpf_map__pin(map, pin_path);
+	if (!ASSERT_OK(err, "bpf_map__pin"))
+		goto out;
+
+	err = bpf_map__unpin(map, pin_path);
+	ASSERT_OK(err, "bpf_map__unpin");
+out:
+	test_pinning_htab__destroy(skel);
+}
+
+void test_pinning_htab(void)
+{
+	if (test__start_subtest("timer_prealloc"))
+		unpin_map("timer_prealloc", "/sys/fs/bpf/timer_prealloc");
+	if (test__start_subtest("timer_no_prealloc"))
+		unpin_map("timer_no_prealloc", "/sys/fs/bpf/timer_no_prealloc");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_htab.c b/tools/testing/selftests/bpf/progs/test_pinning_htab.c
new file mode 100644
index 000000000000..ae227930c73c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning_htab.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct timer_val {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, struct timer_val);
+	__uint(max_entries, 1);
+} timer_prealloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, struct timer_val);
+	__uint(max_entries, 1);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} timer_no_prealloc SEC(".maps");

From 4b47a3aefb29c523ca66f0d28de8db15a10f9352 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 8 Oct 2025 15:46:44 -0700
Subject: [PATCH 291/352] kbuild: Restore pattern to avoid stripping .rela.dyn
 from vmlinux

Commit 0ce5139fd96e ("kbuild: always create intermediate
vmlinux.unstripped") removed the pattern to avoid stripping .rela.dyn
sections added by commit e9d86b8e17e7 ("scripts: Do not strip .rela.dyn
section"). Restore it so that .rela.dyn sections remain in the final
vmlinux.

Fixes: 0ce5139fd96e ("kbuild: always create intermediate vmlinux.unstripped")
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Alexey Gladkov <legion@kernel.org>
Acked-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20251008-kbuild-fix-modinfo-regressions-v1-1-9fc776c5887c@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/Makefile.vmlinux | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index 7c6ae9886f8f..a62639982be5 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -82,7 +82,7 @@ endif
 # ---------------------------------------------------------------------------
 
 remove-section-y                                   := .modinfo
-remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*'
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn'
 
 remove-symbols := -w --strip-symbol='__mod_device_table__*'
 

From 8ec3af916fe3954381cf3555ea03dc5adf4d0e8e Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 8 Oct 2025 15:46:45 -0700
Subject: [PATCH 292/352] kbuild: Add '.rel.*' strip pattern for vmlinux

Prior to binutils commit c12d9fa2afe ("Support objcopy
--remove-section=.relaFOO") [1] in 2.32, stripping relocation sections
required the trailing period (i.e., '.rel.*') to work properly.

After commit 3e86e4d74c04 ("kbuild: keep .modinfo section in
vmlinux.unstripped"), there is an error with binutils 2.31.1 or earlier
because these sections are not properly removed:

  s390-linux-objcopy: st6tO8Ev: symbol `.modinfo' required but not present
  s390-linux-objcopy:st6tO8Ev: no symbols

Add the old pattern to resolve this issue (along with a comment to allow
cleaning this when binutils 2.32 or newer is the minimum supported
version). While the aforementioned kbuild change exposes this, the
pattern was originally changed by commit 71d815bf5dfd ("kbuild: Strip
runtime const RELA sections correctly"), where it would still be
incorrect with binutils older than 2.32.

Fixes: 71d815bf5dfd ("kbuild: Strip runtime const RELA sections correctly")
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7 [1]
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Closes: https://lore.kernel.org/CA+G9fYvVktRhFtZXdNgVOL8j+ArsJDpvMLgCitaQvQmCx=hwOQ@mail.gmail.com/
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Alexey Gladkov <legion@kernel.org>
Acked-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20251008-kbuild-fix-modinfo-regressions-v1-2-9fc776c5887c@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/Makefile.vmlinux | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index a62639982be5..c02f85c2e241 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -83,6 +83,9 @@ endif
 
 remove-section-y                                   := .modinfo
 remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn'
+# for compatibility with binutils < 2.32
+# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel.*'
 
 remove-symbols := -w --strip-symbol='__mod_device_table__*'
 

From 9338d660b79a0dfe4eb3fe9bd748054cded87d4f Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 8 Oct 2025 15:46:46 -0700
Subject: [PATCH 293/352] s390/vmlinux.lds.S: Move .vmlinux.info to end of
 allocatable sections

When building s390 defconfig with binutils older than 2.32, there are
several warnings during the final linking stage:

  s390-linux-ld: .tmp_vmlinux1: warning: allocated section `.got.plt' not in segment
  s390-linux-ld: .tmp_vmlinux2: warning: allocated section `.got.plt' not in segment
  s390-linux-ld: vmlinux.unstripped: warning: allocated section `.got.plt' not in segment
  s390-linux-objcopy: vmlinux: warning: allocated section `.got.plt' not in segment
  s390-linux-objcopy: st7afZyb: warning: allocated section `.got.plt' not in segment

binutils commit afca762f598 ("S/390: Improve partial relro support for
64 bit") [1] in 2.32 changed where .got.plt is emitted, avoiding the
warning.

The :NONE in the .vmlinux.info output section description changes the
segment for subsequent allocated sections. Move .vmlinux.info right
above the discards section to place all other sections in the previously
defined segment, .data.

Fixes: 30226853d6ec ("s390: vmlinux.lds.S: explicitly handle '.got' and '.plt' sections")
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=afca762f598d453c563f244cd3777715b1a0cb72 [1]
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Alexey Gladkov <legion@kernel.org>
Acked-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20251008-kbuild-fix-modinfo-regressions-v1-3-9fc776c5887c@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 arch/s390/kernel/vmlinux.lds.S | 44 +++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index feecf1a6ddb4..d74d4c52ccd0 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -214,6 +214,28 @@ SECTIONS
 	DWARF_DEBUG
 	ELF_DETAILS
 
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the three reserved double words.
+	 */
+	.got.plt : {
+		*(.got.plt)
+	}
+	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+
 	/*
 	 * uncompressed image info used by the decompressor
 	 * it should match struct vmlinux_info
@@ -244,28 +266,6 @@ SECTIONS
 #endif
 	} :NONE
 
-	/*
-	 * Make sure that the .got.plt is either completely empty or it
-	 * contains only the three reserved double words.
-	 */
-	.got.plt : {
-		*(.got.plt)
-	}
-	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
-
-	/*
-	 * Sections that should stay zero sized, which is safer to
-	 * explicitly check instead of blindly discarding.
-	 */
-	.plt : {
-		*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
-	}
-	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
-	.rela.dyn : {
-		*(.rela.*) *(.rela_*)
-	}
-	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
-
 	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {

From 328a782cb138029182e521c08f50eb1587db955d Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Tue, 16 Sep 2025 17:33:37 +0800
Subject: [PATCH 294/352] ext4: wait for ongoing I/O to complete before freeing
 blocks

When freeing metadata blocks in nojournal mode, ext4_forget() calls
bforget() to clear the dirty flag on the buffer_head and remvoe
associated mappings. This is acceptable if the metadata has not yet
begun to be written back. However, if the write-back has already started
but is not yet completed, ext4_forget() will have no effect.
Subsequently, ext4_mb_clear_bb() will immediately return the block to
the mb allocator. This block can then be reallocated immediately,
potentially causing an data corruption issue.

Fix this by clearing the buffer's dirty flag and waiting for the ongoing
I/O to complete, ensuring that no further writes to stale data will
occur.

Fixes: 16e08b14a455 ("ext4: cleanup clean_bdev_aliases() calls")
Cc: stable@kernel.org
Reported-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Closes: https://lore.kernel.org/linux-ext4/a9417096-9549-4441-9878-b1955b899b4e@huaweicloud.com/
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Message-ID: <20250916093337.3161016-3-yi.zhang@huaweicloud.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4_jbd2.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index b3e9b7bd7978..a0e66bc10093 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -280,9 +280,16 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
 		  bh, is_metadata, inode->i_mode,
 		  test_opt(inode->i_sb, DATA_FLAGS));
 
-	/* In the no journal case, we can just do a bforget and return */
+	/*
+	 * In the no journal case, we should wait for the ongoing buffer
+	 * to complete and do a forget.
+	 */
 	if (!ext4_handle_valid(handle)) {
-		bforget(bh);
+		if (bh) {
+			clear_buffer_dirty(bh);
+			wait_on_buffer(bh);
+			__bforget(bh);
+		}
 		return 0;
 	}
 

From 4b471b736ea1ce08113a12bd7dcdaea621b0f65f Mon Sep 17 00:00:00 2001
From: Zeno Endemann <zeno.endemann@mailbox.org>
Date: Thu, 25 Sep 2025 17:24:33 +0200
Subject: [PATCH 295/352] ext4, doc: fix and improve directory hash tree
 description

Some of the details about how directory hash trees work were confusing or
outright wrong, this patch should fix those.

A note on dx_tail's dt_reserved member, as far as I can tell the kernel
never sets this explicitly, so its content is apparently left-overs from
what was there before (for the dx_root I've seen remnants of a
ext4_dir_entry_tail struct from when the dir was not yet a hash dir).

Signed-off-by: Zeno Endemann <zeno.endemann@mailbox.org>
Message-ID: <20250925152435.22749-1-zeno.endemann@mailbox.org>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/directory.rst | 61 ++++++++++----------
 1 file changed, 31 insertions(+), 30 deletions(-)

diff --git a/Documentation/filesystems/ext4/directory.rst b/Documentation/filesystems/ext4/directory.rst
index 6eece8e31df8..9b003a4d453f 100644
--- a/Documentation/filesystems/ext4/directory.rst
+++ b/Documentation/filesystems/ext4/directory.rst
@@ -183,10 +183,10 @@ in the place where the name normally goes. The structure is
      - det_checksum
      - Directory leaf block checksum.
 
-The leaf directory block checksum is calculated against the FS UUID, the
-directory's inode number, the directory's inode generation number, and
-the entire directory entry block up to (but not including) the fake
-directory entry.
+The leaf directory block checksum is calculated against the FS UUID (or
+the checksum seed, if that feature is enabled for the fs), the directory's
+inode number, the directory's inode generation number, and the entire
+directory entry block up to (but not including) the fake directory entry.
 
 Hash Tree Directories
 ~~~~~~~~~~~~~~~~~~~~~
@@ -196,12 +196,12 @@ new feature was added to ext3 to provide a faster (but peculiar)
 balanced tree keyed off a hash of the directory entry name. If the
 EXT4_INDEX_FL (0x1000) flag is set in the inode, this directory uses a
 hashed btree (htree) to organize and find directory entries. For
-backwards read-only compatibility with ext2, this tree is actually
-hidden inside the directory file, masquerading as “empty” directory data
-blocks! It was stated previously that the end of the linear directory
-entry table was signified with an entry pointing to inode 0; this is
-(ab)used to fool the old linear-scan algorithm into thinking that the
-rest of the directory block is empty so that it moves on.
+backwards read-only compatibility with ext2, interior tree nodes are actually
+hidden inside the directory file, masquerading as “empty” directory entries
+spanning the whole block. It was stated previously that directory entries
+with the inode set to 0 are treated as unused entries; this is (ab)used to
+fool the old linear-scan algorithm into skipping over those blocks containing
+the interior tree node data.
 
 The root of the tree always lives in the first data block of the
 directory. By ext2 custom, the '.' and '..' entries must appear at the
@@ -209,24 +209,24 @@ beginning of this first block, so they are put here as two
 ``struct ext4_dir_entry_2`` s and not stored in the tree. The rest of
 the root node contains metadata about the tree and finally a hash->block
 map to find nodes that are lower in the htree. If
-``dx_root.info.indirect_levels`` is non-zero then the htree has two
-levels; the data block pointed to by the root node's map is an interior
-node, which is indexed by a minor hash. Interior nodes in this tree
-contains a zeroed out ``struct ext4_dir_entry_2`` followed by a
-minor_hash->block map to find leafe nodes. Leaf nodes contain a linear
-array of all ``struct ext4_dir_entry_2``; all of these entries
-(presumably) hash to the same value. If there is an overflow, the
-entries simply overflow into the next leaf node, and the
-least-significant bit of the hash (in the interior node map) that gets
-us to this next leaf node is set.
+``dx_root.info.indirect_levels`` is non-zero then the htree has that many
+levels and the blocks pointed to by the root node's map are interior nodes.
+These interior nodes have a zeroed out ``struct ext4_dir_entry_2`` followed by
+a hash->block map to find nodes of the next level. Leaf nodes look like
+classic linear directory blocks, but all of its entries have a hash value
+equal or greater than the indicated hash of the parent node.
 
-To traverse the directory as a htree, the code calculates the hash of
-the desired file name and uses it to find the corresponding block
-number. If the tree is flat, the block is a linear array of directory
-entries that can be searched; otherwise, the minor hash of the file name
-is computed and used against this second block to find the corresponding
-third block number. That third block number will be a linear array of
-directory entries.
+The actual hash value for an entry name is only 31 bits, the least-significant
+bit is set to 0. However, if there is a hash collision between directory
+entries, the least-significant bit may get set to 1 on interior nodes in the
+case where these two (or more) hash-colliding entries do not fit into one leaf
+node and must be split across multiple nodes.
+
+To look up a name in such a htree, the code calculates the hash of the desired
+file name and uses it to find the leaf node with the range of hash values the
+calculated hash falls into (in other words, a lookup works basically the same
+as it would in a B-Tree keyed by the hash value), and possibly also scanning
+the leaf nodes that follow (in tree order) in case of hash collisions.
 
 To traverse the directory as a linear array (such as the old code does),
 the code simply reads every data block in the directory. The blocks used
@@ -319,7 +319,8 @@ of a data block:
    * - 0x24
      - __le32
      - block
-     - The block number (within the directory file) that goes with hash=0.
+     - The block number (within the directory file) that lead to the left-most
+       leaf node, i.e. the leaf containing entries with the lowest hash values.
    * - 0x28
      - struct dx_entry
      - entries[0]
@@ -442,7 +443,7 @@ The dx_tail structure is 8 bytes long and looks like this:
    * - 0x0
      - u32
      - dt_reserved
-     - Zero.
+     - Unused (but still part of the checksum curiously).
    * - 0x4
      - __le32
      - dt_checksum
@@ -450,4 +451,4 @@ The dx_tail structure is 8 bytes long and looks like this:
 
 The checksum is calculated against the FS UUID, the htree index header
 (dx_root or dx_node), all of the htree indices (dx_entry) that are in
-use, and the tail block (dx_tail).
+use, and the tail block (dx_tail) with the dt_checksum initially set to 0.

From f7045387a6816d51d462447af4522785e1c7251c Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 9 Oct 2025 20:37:43 +0200
Subject: [PATCH 296/352] dt-bindings: bus: allwinner,sun50i-a64-de2: don't
 check node names

Node names are already and properly checked by the core schema. No need
to do it again.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
[robh: Also drop [A-F] in unit address]
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml       | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
index 9845a187bdf6..232252e8825e 100644
--- a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
+++ b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
@@ -44,7 +44,7 @@ properties:
 
 patternProperties:
   # All other properties should be child nodes with unit-address and 'reg'
-  "^[a-zA-Z][a-zA-Z0-9,+\\-._]{0,63}@[0-9a-fA-F]+$":
+  "@[0-9a-f]+$":
     type: object
     additionalProperties: true
     properties:

From ce740955b238761ec1d8cf0590d7e6802d3a813a Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 9 Oct 2025 20:34:53 +0200
Subject: [PATCH 297/352] dt-bindings: bus: renesas-bsc: allow additional
 properties

Allow additional properties to enable devices attached to the bus.
Fixes warnings like these:

arch/arm/boot/dts/renesas/sh73a0-kzm9g.dtb: bus@fec10000 (renesas,bsc-sh73a0): Unevaluated properties are not allowed ('ethernet@10000000' was unexpected)
arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dtb: bus@fec10000 (renesas,bsc-r8a73a4): Unevaluated properties are not allowed ('ethernet@8000000', 'flash@0' were unexpected)

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../devicetree/bindings/bus/renesas,bsc.yaml         | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/devicetree/bindings/bus/renesas,bsc.yaml b/Documentation/devicetree/bindings/bus/renesas,bsc.yaml
index f53a37785413..ff3c78317d28 100644
--- a/Documentation/devicetree/bindings/bus/renesas,bsc.yaml
+++ b/Documentation/devicetree/bindings/bus/renesas,bsc.yaml
@@ -41,6 +41,18 @@ properties:
   interrupts:
     maxItems: 1
 
+patternProperties:
+  # All other properties should be child nodes with unit-address and 'reg'
+  "@[0-9a-f]+$":
+    type: object
+    additionalProperties: true
+    properties:
+      reg:
+        maxItems: 1
+
+    required:
+      - reg
+
 required:
   - reg
 

From 1d3ad183943b38eec2acf72a0ae98e635dc8456b Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Tue, 30 Sep 2025 16:58:10 +0530
Subject: [PATCH 298/352] ext4: detect invalid INLINE_DATA + EXTENTS flag
 combination

syzbot reported a BUG_ON in ext4_es_cache_extent() when opening a verity
file on a corrupted ext4 filesystem mounted without a journal.

The issue is that the filesystem has an inode with both the INLINE_DATA
and EXTENTS flags set:

    EXT4-fs error (device loop0): ext4_cache_extents:545: inode #15:
    comm syz.0.17: corrupted extent tree: lblk 0 < prev 66

Investigation revealed that the inode has both flags set:
    DEBUG: inode 15 - flag=1, i_inline_off=164, has_inline=1, extents_flag=1

This is an invalid combination since an inode should have either:
- INLINE_DATA: data stored directly in the inode
- EXTENTS: data stored in extent-mapped blocks

Having both flags causes ext4_has_inline_data() to return true, skipping
extent tree validation in __ext4_iget(). The unvalidated out-of-order
extents then trigger a BUG_ON in ext4_es_cache_extent() due to integer
underflow when calculating hole sizes.

Fix this by detecting this invalid flag combination early in ext4_iget()
and rejecting the corrupted inode.

Cc: stable@kernel.org
Reported-and-tested-by: syzbot+038b7bf43423e132b308@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=038b7bf43423e132b308
Suggested-by: Zhang Yi <yi.zhang@huawei.com>
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Message-ID: <20250930112810.315095-1-kartikey406@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f9e4ac87211e..e99306a8f47c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5319,6 +5319,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
 	ext4_set_inode_flags(inode, true);
+	/* Detect invalid flag combination - can't have both inline data and extents */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		ext4_error_inode(inode, function, line, 0,
+			"inode has both inline data and extents flags");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
 	if (ext4_has_feature_64bit(sb))

From 971843c511c3c2f6eda96c6b03442913bfee6148 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 7 Oct 2025 15:49:37 +0200
Subject: [PATCH 299/352] ext4: free orphan info with kvfree

Orphan info is now getting allocated with kvmalloc_array(). Free it with
kvfree() instead of kfree() to avoid complaints from mm.

Reported-by: Chris Mason <clm@meta.com>
Fixes: 0a6ce20c1564 ("ext4: verify orphan file size is not too big")
Cc: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Message-ID: <20251007134936.7291-2-jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/orphan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c
index 33c3a89396b1..82d5e7501455 100644
--- a/fs/ext4/orphan.c
+++ b/fs/ext4/orphan.c
@@ -513,7 +513,7 @@ void ext4_release_orphan_info(struct super_block *sb)
 		return;
 	for (i = 0; i < oi->of_blocks; i++)
 		brelse(oi->of_binfo[i].ob_bh);
-	kfree(oi->of_binfo);
+	kvfree(oi->of_binfo);
 }
 
 static struct ext4_orphan_block_tail *ext4_orphan_block_tail(
@@ -637,7 +637,7 @@ int ext4_init_orphan_info(struct super_block *sb)
 out_free:
 	for (i--; i >= 0; i--)
 		brelse(oi->of_binfo[i].ob_bh);
-	kfree(oi->of_binfo);
+	kvfree(oi->of_binfo);
 out_put:
 	iput(inode);
 	return ret;

From b0f2942a16017f88395d768afedd7373860968ce Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 10 Oct 2025 14:49:27 -0700
Subject: [PATCH 300/352] kbuild: Use '--strip-unneeded-symbol' for removing
 module device table symbols

After commit 5ab23c7923a1 ("modpost: Create modalias for builtin
modules"), relocatable RISC-V kernels with CONFIG_KASAN=y start failing
when attempting to strip the module device table symbols:

  riscv64-linux-objcopy: not stripping symbol `__mod_device_table__kmod_irq_starfive_jh8100_intc__of__starfive_intc_irqchip_match_table' because it is named in a relocation
  make[4]: *** [scripts/Makefile.vmlinux:97: vmlinux] Error 1

The relocation appears to come from .LASANLOC5 in .data.rel.local:

  $ llvm-objdump --disassemble-symbols=.LASANLOC5 --disassemble-all -r drivers/irqchip/irq-starfive-jh8100-intc.o

  drivers/irqchip/irq-starfive-jh8100-intc.o:   file format elf64-littleriscv

  Disassembly of section .data.rel.local:

  0000000000000180 <.LASANLOC5>:
  ...
       1d0: 0000          unimp
                  00000000000001d0:  R_RISCV_64   __mod_device_table__kmod_irq_starfive_jh8100_intc__of__starfive_intc_irqchip_match_table
  ...

This section appears to come from GCC for including additional
information about global variables that may be protected by KASAN.

There appears to be no way to opt out of the generation of these symbols
through either a flag or attribute. Attempting to remove '.LASANLOC*'
with '--strip-symbol' results in the same error as above because these
symbols may refer to (thus have relocation between) each other.

Avoid this build breakage by switching to '--strip-unneeded-symbol' for
removing __mod_device_table__ symbols, as it will only remove the symbol
when there is no relocation pointing to it. While this may result in a
little more bloat in the symbol table in certain configurations, it is
not as bad as outright build failures.

Fixes: 5ab23c7923a1 ("modpost: Create modalias for builtin modules")
Reported-by: Charles Mirabile <cmirabil@redhat.com>
Closes: https://lore.kernel.org/20251007011637.2512413-1-cmirabil@redhat.com/
Suggested-by: Alexey Gladkov <legion@kernel.org>
Tested-by: Nicolas Schier <nsc@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/Makefile.vmlinux | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index c02f85c2e241..ced4379550d7 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -87,7 +87,7 @@ remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn'
 # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7
 remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel.*'
 
-remove-symbols := -w --strip-symbol='__mod_device_table__*'
+remove-symbols := -w --strip-unneeded-symbol='__mod_device_table__*'
 
 # To avoid warnings: "empty loadable segment detected at ..." from GNU objcopy,
 # it is necessary to remove the PT_LOAD flag from the segment.

From bda745ee8fbb63330d8f2f2ea4157229a5df959e Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 10 Oct 2025 23:51:42 -0400
Subject: [PATCH 301/352] tracing: Fix tracing_mark_raw_write() to use buf and
 not ubuf

The fix to use a per CPU buffer to read user space tested only the writes
to trace_marker. But it appears that the selftests are missing tests to
the trace_maker_raw file. The trace_maker_raw file is used by applications
that writes data structures and not strings into the file, and the tools
read the raw ring buffer to process the structures it writes.

The fix that reads the per CPU buffers passes the new per CPU buffer to
the trace_marker file writes, but the update to the trace_marker_raw write
read the data from user space into the per CPU buffer, but then still used
then passed the user space address to the function that records the data.

Pass in the per CPU buffer and not the user space address.

TODO: Add a test to better test trace_marker_raw.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/20251011035243.386098147@kernel.org
Fixes: 64cf7d058a00 ("tracing: Have trace_marker use per-cpu data to read user space")
Reported-by: syzbot+9a2ede1643175f350105@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68e973f5.050a0220.1186a4.0010.GAE@google.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 0fd582651293..bbb89206a891 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7497,12 +7497,12 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 	if (tr == &global_trace) {
 		guard(rcu)();
 		list_for_each_entry_rcu(tr, &marker_copies, marker_list) {
-			written = write_raw_marker_to_buffer(tr, ubuf, cnt);
+			written = write_raw_marker_to_buffer(tr, buf, cnt);
 			if (written < 0)
 				break;
 		}
 	} else {
-		written = write_raw_marker_to_buffer(tr, ubuf, cnt);
+		written = write_raw_marker_to_buffer(tr, buf, cnt);
 	}
 
 	return written;

From fd6db58867924d2bfbc4ece4b0092f697f9fc31c Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Sat, 11 Oct 2025 10:45:41 +0200
Subject: [PATCH 302/352] slab: fix barn NULL pointer dereference on memoryless
 nodes

Phil reported a boot failure once sheaves become used in commits
59faa4da7cd4 ("maple_tree: use percpu sheaves for maple_node_cache") and
3accabda4da1 ("mm, vma: use percpu sheaves for vm_area_struct cache"):

 BUG: kernel NULL pointer dereference, address: 0000000000000040
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] SMP NOPTI
 CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
 Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
 RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
 Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89
 RSP: 0018:ffffd2d10950bdb0 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: ffff8a775dab74b0 RCX: 00000000ffffffff
 RDX: 0000000000000cc0 RSI: ffff8a6800804000 RDI: ffff8a680004e300
 RBP: ffffd2d10950be40 R08: 0000000000000060 R09: ffffffffb9367388
 R10: 00000000000149e8 R11: ffff8a6f87a38000 R12: 0000000000000cc0
 R13: 0000000000000cc0 R14: ffff8a680004e300 R15: 00000000000000c0
 FS:  0000000000000000(0000) GS:ffff8a77a3541000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000040 CR3: 0000000e1aa24000 CR4: 00000000003506f0
 Call Trace:
  <TASK>
  ? srso_return_thunk+0x5/0x5f
  ? vm_area_alloc+0x1e/0x60
  kmem_cache_alloc_noprof+0x4ec/0x5b0
  vm_area_alloc+0x1e/0x60
  create_init_stack_vma+0x26/0x210
  alloc_bprm+0x139/0x200
  kernel_execve+0x4a/0x140
  call_usermodehelper_exec_async+0xd0/0x190
  ? __pfx_call_usermodehelper_exec_async+0x10/0x10
  ret_from_fork+0xf0/0x110
  ? __pfx_call_usermodehelper_exec_async+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>
 Modules linked in:
 CR2: 0000000000000040
 ---[ end trace 0000000000000000 ]---
 RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
 Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89
 RSP: 0018:ffffd2d10950bdb0 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: ffff8a775dab74b0 RCX: 00000000ffffffff
 RDX: 0000000000000cc0 RSI: ffff8a6800804000 RDI: ffff8a680004e300
 RBP: ffffd2d10950be40 R08: 0000000000000060 R09: ffffffffb9367388
 R10: 00000000000149e8 R11: ffff8a6f87a38000 R12: 0000000000000cc0
 R13: 0000000000000cc0 R14: ffff8a680004e300 R15: 00000000000000c0
 FS:  0000000000000000(0000) GS:ffff8a77a3541000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000040 CR3: 0000000e1aa24000 CR4: 00000000003506f0
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: 0x36a00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
 ---[ end Kernel panic - not syncing: Fatal exception ]---

And noted "this is an AMD EPYC 7401 with 8 NUMA nodes configured such
that memory is only on 2 of them."

 # numactl --hardware
 available: 8 nodes (0-7)
 node 0 cpus: 0 8 16 24 32 40 48 56 64 72 80 88
 node 0 size: 0 MB
 node 0 free: 0 MB
 node 1 cpus: 2 10 18 26 34 42 50 58 66 74 82 90
 node 1 size: 31584 MB
 node 1 free: 30397 MB
 node 2 cpus: 4 12 20 28 36 44 52 60 68 76 84 92
 node 2 size: 0 MB
 node 2 free: 0 MB
 node 3 cpus: 6 14 22 30 38 46 54 62 70 78 86 94
 node 3 size: 0 MB
 node 3 free: 0 MB
 node 4 cpus: 1 9 17 25 33 41 49 57 65 73 81 89
 node 4 size: 0 MB
 node 4 free: 0 MB
 node 5 cpus: 3 11 19 27 35 43 51 59 67 75 83 91
 node 5 size: 32214 MB
 node 5 free: 31625 MB
 node 6 cpus: 5 13 21 29 37 45 53 61 69 77 85 93
 node 6 size: 0 MB
 node 6 free: 0 MB
 node 7 cpus: 7 15 23 31 39 47 55 63 71 79 87 95
 node 7 size: 0 MB
 node 7 free: 0 MB

Linus decoded the stacktrace to get_barn() and get_node() and determined
that kmem_cache->node[numa_mem_id()] is NULL.

The problem is due to a wrong assumption that memoryless nodes only
exist on systems with CONFIG_HAVE_MEMORYLESS_NODES, where numa_mem_id()
points to the nearest node that has memory. SLUB has been allocating its
kmem_cache_node structures only on nodes with memory and so it does with
struct node_barn.

For kmem_cache_node, get_partial_node() checks if get_node() result is
not NULL, which I assumed was for protection from a bogus node id passed
to kmalloc_node() but apparently it's also for systems where
numa_mem_id() (used when no specific node is given) might return a
memoryless node.

Fix the sheaves code the same way by checking the result of get_node()
and bailing out if it's NULL. Note that cpus on such memoryless nodes
will have degraded sheaves performance, which can be improved later,
preferably by making numa_mem_id() work properly on such systems.

Fixes: 2d517aa09bbc ("slab: add opt-in caching layer of percpu sheaves")
Reported-and-tested-by: Phil Auld <pauld@redhat.com>
Closes: https://lore.kernel.org/all/20251010151116.GA436967@pauld.westford.csb/
Analyzed-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/all/CAHk-%3Dwg1xK%2BBr%3DFJ5QipVhzCvq7uQVPt5Prze6HDhQQ%3DQD_BcQ@mail.gmail.com/
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 65 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 51 insertions(+), 14 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 135c408e0515..b1f15598fbfd 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -504,10 +504,18 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 	return s->node[node];
 }
 
-/* Get the barn of the current cpu's memory node */
+/*
+ * Get the barn of the current cpu's closest memory node. It may not exist on
+ * systems with memoryless nodes but without CONFIG_HAVE_MEMORYLESS_NODES
+ */
 static inline struct node_barn *get_barn(struct kmem_cache *s)
 {
-	return get_node(s, numa_mem_id())->barn;
+	struct kmem_cache_node *n = get_node(s, numa_mem_id());
+
+	if (!n)
+		return NULL;
+
+	return n->barn;
 }
 
 /*
@@ -4982,6 +4990,10 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
 
 	full = barn_replace_empty_sheaf(barn, pcs->main);
 
@@ -5153,13 +5165,20 @@ next_batch:
 	if (unlikely(pcs->main->size == 0)) {
 
 		struct slab_sheaf *full;
+		struct node_barn *barn;
 
 		if (pcs->spare && pcs->spare->size > 0) {
 			swap(pcs->main, pcs->spare);
 			goto do_alloc;
 		}
 
-		full = barn_replace_empty_sheaf(get_barn(s), pcs->main);
+		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			return allocated;
+		}
+
+		full = barn_replace_empty_sheaf(barn, pcs->main);
 
 		if (full) {
 			stat(s, BARN_GET);
@@ -5314,6 +5333,7 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 {
 	struct slub_percpu_sheaves *pcs;
 	struct slab_sheaf *sheaf = NULL;
+	struct node_barn *barn;
 
 	if (unlikely(size > s->sheaf_capacity)) {
 
@@ -5355,8 +5375,11 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 		pcs->spare = NULL;
 		stat(s, SHEAF_PREFILL_FAST);
 	} else {
+		barn = get_barn(s);
+
 		stat(s, SHEAF_PREFILL_SLOW);
-		sheaf = barn_get_full_or_empty_sheaf(get_barn(s));
+		if (barn)
+			sheaf = barn_get_full_or_empty_sheaf(barn);
 		if (sheaf && sheaf->size)
 			stat(s, BARN_GET);
 		else
@@ -5426,7 +5449,7 @@ void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
 	 * If the barn has too many full sheaves or we fail to refill the sheaf,
 	 * simply flush and free it.
 	 */
-	if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
+	if (!barn || data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
 	    refill_sheaf(s, sheaf, gfp)) {
 		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
@@ -5943,10 +5966,9 @@ slab_empty:
  * put the full sheaf there.
  */
 static void __pcs_install_empty_sheaf(struct kmem_cache *s,
-		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty)
+		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty,
+		struct node_barn *barn)
 {
-	struct node_barn *barn;
-
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	/* This is what we expect to find if nobody interrupted us. */
@@ -5956,8 +5978,6 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s,
 		return;
 	}
 
-	barn = get_barn(s);
-
 	/*
 	 * Unlikely because if the main sheaf had space, we would have just
 	 * freed to it. Get rid of our empty sheaf.
@@ -6002,6 +6022,11 @@ restart:
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
+
 	put_fail = false;
 
 	if (!pcs->spare) {
@@ -6084,7 +6109,7 @@ got_empty:
 	}
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
-	__pcs_install_empty_sheaf(s, pcs, empty);
+	__pcs_install_empty_sheaf(s, pcs, empty, barn);
 
 	return pcs;
 }
@@ -6121,8 +6146,9 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
 
 static void rcu_free_sheaf(struct rcu_head *head)
 {
+	struct kmem_cache_node *n;
 	struct slab_sheaf *sheaf;
-	struct node_barn *barn;
+	struct node_barn *barn = NULL;
 	struct kmem_cache *s;
 
 	sheaf = container_of(head, struct slab_sheaf, rcu_head);
@@ -6139,7 +6165,11 @@ static void rcu_free_sheaf(struct rcu_head *head)
 	 */
 	__rcu_free_sheaf_prepare(s, sheaf);
 
-	barn = get_node(s, sheaf->node)->barn;
+	n = get_node(s, sheaf->node);
+	if (!n)
+		goto flush;
+
+	barn = n->barn;
 
 	/* due to slab_free_hook() */
 	if (unlikely(sheaf->size == 0))
@@ -6157,11 +6187,12 @@ static void rcu_free_sheaf(struct rcu_head *head)
 		return;
 	}
 
+flush:
 	stat(s, BARN_PUT_FAIL);
 	sheaf_flush_unused(s, sheaf);
 
 empty:
-	if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
+	if (barn && data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
 		barn_put_empty_sheaf(barn, sheaf);
 		return;
 	}
@@ -6191,6 +6222,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
 		}
 
 		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			goto fail;
+		}
 
 		empty = barn_get_empty_sheaf(barn);
 
@@ -6304,6 +6339,8 @@ next_batch:
 		goto do_free;
 
 	barn = get_barn(s);
+	if (!barn)
+		goto no_empty;
 
 	if (!pcs->spare) {
 		empty = barn_get_empty_sheaf(barn);

From 54b91e54b113d4f15ab023a44f508251db6e22e7 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Sat, 11 Oct 2025 11:20:32 -0400
Subject: [PATCH 303/352] tracing: Stop fortify-string from warning in
 tracing_mark_raw_write()

The way tracing_mark_raw_write() records its data is that it has the
following structure:

  struct {
	struct trace_entry;
	int id;
	char buf[];
  };

But memcpy(&entry->id, buf, size) triggers the following warning when the
size is greater than the id:

 ------------[ cut here ]------------
 memcpy: detected field-spanning write (size 6) of single field "&entry->id" at kernel/trace/trace.c:7458 (size 4)
 WARNING: CPU: 7 PID: 995 at kernel/trace/trace.c:7458 write_raw_marker_to_buffer.isra.0+0x1f9/0x2e0
 Modules linked in:
 CPU: 7 UID: 0 PID: 995 Comm: bash Not tainted 6.17.0-test-00007-g60b82183e78a-dirty #211 PREEMPT(voluntary)
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
 RIP: 0010:write_raw_marker_to_buffer.isra.0+0x1f9/0x2e0
 Code: 04 00 75 a7 b9 04 00 00 00 48 89 de 48 89 04 24 48 c7 c2 e0 b1 d1 b2 48 c7 c7 40 b2 d1 b2 c6 05 2d 88 6a 04 01 e8 f7 e8 bd ff <0f> 0b 48 8b 04 24 e9 76 ff ff ff 49 8d 7c 24 04 49 8d 5c 24 08 48
 RSP: 0018:ffff888104c3fc78 EFLAGS: 00010292
 RAX: 0000000000000000 RBX: 0000000000000006 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 1ffffffff6b363b4 RDI: 0000000000000001
 RBP: ffff888100058a00 R08: ffffffffb041d459 R09: ffffed1020987f40
 R10: 0000000000000007 R11: 0000000000000001 R12: ffff888100bb9010
 R13: 0000000000000000 R14: 00000000000003e3 R15: ffff888134800000
 FS:  00007fa61d286740(0000) GS:ffff888286cad000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000560d28d509f1 CR3: 00000001047a4006 CR4: 0000000000172ef0
 Call Trace:
  <TASK>
  tracing_mark_raw_write+0x1fe/0x290
  ? __pfx_tracing_mark_raw_write+0x10/0x10
  ? security_file_permission+0x50/0xf0
  ? rw_verify_area+0x6f/0x4b0
  vfs_write+0x1d8/0xdd0
  ? __pfx_vfs_write+0x10/0x10
  ? __pfx_css_rstat_updated+0x10/0x10
  ? count_memcg_events+0xd9/0x410
  ? fdget_pos+0x53/0x5e0
  ksys_write+0x182/0x200
  ? __pfx_ksys_write+0x10/0x10
  ? do_user_addr_fault+0x4af/0xa30
  do_syscall_64+0x63/0x350
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
 RIP: 0033:0x7fa61d318687
 Code: 48 89 fa 4c 89 df e8 58 b3 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 fa 08 75 de e8 23 ff ff ff
 RSP: 002b:00007ffd87fe0120 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
 RAX: ffffffffffffffda RBX: 00007fa61d286740 RCX: 00007fa61d318687
 RDX: 0000000000000006 RSI: 0000560d28d509f0 RDI: 0000000000000001
 RBP: 0000560d28d509f0 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000006
 R13: 00007fa61d4715c0 R14: 00007fa61d46ee80 R15: 0000000000000000
  </TASK>
 ---[ end trace 0000000000000000 ]---

This is because fortify string sees that the size of entry->id is only 4
bytes, but it is writing more than that. But this is OK as the
dynamic_array is allocated to handle that copy.

The size allocated on the ring buffer was actually a bit too big:

  size = sizeof(*entry) + cnt;

But cnt includes the 'id' and the buffer data, so adding cnt to the size
of *entry actually allocates too much on the ring buffer.

Change the allocation to:

  size = struct_size(entry, buf, cnt - sizeof(entry->id));

and the memcpy() to unsafe_memcpy() with an added justification.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/20251011112032.77be18e4@gandalf.local.home
Fixes: 64cf7d058a00 ("tracing: Have trace_marker use per-cpu data to read user space")
Reported-by: syzbot+9a2ede1643175f350105@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68e973f5.050a0220.1186a4.0010.GAE@google.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bbb89206a891..eb256378e65b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7441,7 +7441,8 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
 	ssize_t written;
 	size_t size;
 
-	size = sizeof(*entry) + cnt;
+	/* cnt includes both the entry->id and the data behind it. */
+	size = struct_size(entry, buf, cnt - sizeof(entry->id));
 
 	buffer = tr->array_buffer.buffer;
 
@@ -7455,7 +7456,10 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
 		return -EBADF;
 
 	entry = ring_buffer_event_data(event);
-	memcpy(&entry->id, buf, cnt);
+	unsafe_memcpy(&entry->id, buf, cnt,
+		      "id and content already reserved on ring buffer"
+		      "'buf' includes the 'id' and the data."
+		      "'entry' was allocated with cnt from 'id'.");
 	written = cnt;
 
 	__buffer_unlock_commit(buffer, event);

From a8482d2c9071d75c920eba0db36428898250ea57 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sat, 11 Oct 2025 12:31:53 +0200
Subject: [PATCH 304/352] Revert "i2c: boardinfo: Annotate code used in init
 phase only"

This reverts commit 1a2b423be6a89dd07d5fc27ea042be68697a6a49 because we
got a regression report and need time to find out the details.

Reported-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Closes: https://lore.kernel.org/r/29ec0082-4dd4-4120-acd2-44b35b4b9487@oss.qualcomm.com
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/i2c-boardinfo.c | 4 ++--
 include/linux/i2c.h         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c
index 338800321f8b..4df8ad092df3 100644
--- a/drivers/i2c/i2c-boardinfo.c
+++ b/drivers/i2c/i2c-boardinfo.c
@@ -22,7 +22,7 @@ EXPORT_SYMBOL_GPL(__i2c_board_lock);
 LIST_HEAD(__i2c_board_list);
 EXPORT_SYMBOL_GPL(__i2c_board_list);
 
-int __i2c_first_dynamic_bus_num __ro_after_init;
+int __i2c_first_dynamic_bus_num;
 EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num);
 
 
@@ -48,7 +48,7 @@ EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num);
  * The board info passed can safely be __initdata, but be careful of embedded
  * pointers (for platform_data, functions, etc) since that won't be copied.
  */
-int __init i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len)
+int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len)
 {
 	int status;
 
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 11a19241e360..20fd41b51d5c 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -499,7 +499,7 @@ static inline struct i2c_client *i2c_verify_client(struct device *dev)
  * Modules for add-on boards must use other calls.
  */
 #ifdef CONFIG_I2C_BOARDINFO
-int __init
+int
 i2c_register_board_info(int busnum, struct i2c_board_info const *info,
 			unsigned n);
 #else

From d5d790ba1558dbb8d179054f514476e2ee970b8e Mon Sep 17 00:00:00 2001
From: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Date: Thu, 9 Oct 2025 11:00:09 +0530
Subject: [PATCH 305/352] net: usb: lan78xx: Fix lost EEPROM write timeout
 error(-ETIMEDOUT) in lan78xx_write_raw_eeprom

The function lan78xx_write_raw_eeprom failed to properly propagate EEPROM
write timeout errors (-ETIMEDOUT). In the timeout  fallthrough path, it first
attempted to restore the pin configuration for LED outputs and then
returned only the status of that restore operation, discarding the
original timeout error saved in ret.

As a result, callers could mistakenly treat EEPROM write operation as
successful even though the EEPROM write had actually timed out with no
or partial data write.

To fix this, handle errors in restoring the LED pin configuration separately.
If the restore succeeds, return any prior EEPROM write timeout error saved
in ret to the caller.

Suggested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Fixes: 8b1b2ca83b20 ("net: usb: lan78xx: Improve error handling in EEPROM and OTP operations")
cc: stable@vger.kernel.org
Signed-off-by: Bhanu Seshu Kumar Valluri <bhanuseshukumar@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 42d35cc6b421..28195d9a8d6b 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1175,10 +1175,13 @@ static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset,
 	}
 
 write_raw_eeprom_done:
-	if (dev->chipid == ID_REV_CHIP_ID_7800_)
-		return lan78xx_write_reg(dev, HW_CFG, saved);
-
-	return 0;
+	if (dev->chipid == ID_REV_CHIP_ID_7800_) {
+		int rc = lan78xx_write_reg(dev, HW_CFG, saved);
+		/* If USB fails, there is nothing to do */
+		if (rc < 0)
+			return rc;
+	}
+	return ret;
 }
 
 static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset,

From 3abc0e55ea1fa2250e52bc860e8f24b2b9a2093a Mon Sep 17 00:00:00 2001
From: Rex Lu <rex.lu@mediatek.com>
Date: Thu, 9 Oct 2025 08:29:34 +0200
Subject: [PATCH 306/352] net: mtk: wed: add dma mask limitation and GFP_DMA32
 for device with more than 4GB DRAM

Limit tx/rx buffer address to 32-bit address space for board with more
than 4GB DRAM.

Fixes: 804775dfc2885 ("net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED)")
Fixes: 6757d345dd7db ("net: ethernet: mtk_wed: introduce hw_rro support for MT7988")
Tested-by: Daniel Pawlik <pawlik.dan@gmail.com>
Tested-by: Matteo Croce <teknoraver@meta.com>
Signed-off-by: Rex Lu <rex.lu@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_wed.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 3dbb113b792c..1ed1f88dd7f8 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -677,7 +677,7 @@ mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev)
 		void *buf;
 		int s;
 
-		page = __dev_alloc_page(GFP_KERNEL);
+		page = __dev_alloc_page(GFP_KERNEL | GFP_DMA32);
 		if (!page)
 			return -ENOMEM;
 
@@ -800,7 +800,7 @@ mtk_wed_hwrro_buffer_alloc(struct mtk_wed_device *dev)
 		struct page *page;
 		int s;
 
-		page = __dev_alloc_page(GFP_KERNEL);
+		page = __dev_alloc_page(GFP_KERNEL | GFP_DMA32);
 		if (!page)
 			return -ENOMEM;
 
@@ -2426,6 +2426,10 @@ mtk_wed_attach(struct mtk_wed_device *dev)
 	dev->version = hw->version;
 	dev->hw->pcie_base = mtk_wed_get_pcie_base(dev);
 
+	ret = dma_set_mask_and_coherent(hw->dev, DMA_BIT_MASK(32));
+	if (ret)
+		goto out;
+
 	if (hw->eth->dma_dev == hw->eth->dev &&
 	    of_dma_is_coherent(hw->eth->dev->of_node))
 		mtk_eth_set_dma_device(hw->eth, hw->dev);

From 65946eac6d888d50ae527c4e5c237dbe5cc3a2f2 Mon Sep 17 00:00:00 2001
From: Yeounsu Moon <yyyynoom@gmail.com>
Date: Fri, 10 Oct 2025 00:57:16 +0900
Subject: [PATCH 307/352] net: dlink: handle dma_map_single() failure properly

There is no error handling for `dma_map_single()` failures.

Add error handling by checking `dma_mapping_error()` and freeing
the `skb` using `dev_kfree_skb()` (process context) when it fails.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Yeounsu Moon <yyyynoom@gmail.com>
Tested-on: D-Link DGE-550T Rev-A3
Suggested-by: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dlink/dl2k.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 1996d2e4e3e2..7077d705e471 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -508,25 +508,34 @@ static int alloc_list(struct net_device *dev)
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		/* Allocated fixed size of skbuff */
 		struct sk_buff *skb;
+		dma_addr_t addr;
 
 		skb = netdev_alloc_skb_ip_align(dev, np->rx_buf_sz);
 		np->rx_skbuff[i] = skb;
-		if (!skb) {
-			free_list(dev);
-			return -ENOMEM;
-		}
+		if (!skb)
+			goto err_free_list;
+
+		addr = dma_map_single(&np->pdev->dev, skb->data,
+				      np->rx_buf_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&np->pdev->dev, addr))
+			goto err_kfree_skb;
 
 		np->rx_ring[i].next_desc = cpu_to_le64(np->rx_ring_dma +
 						((i + 1) % RX_RING_SIZE) *
 						sizeof(struct netdev_desc));
 		/* Rubicon now supports 40 bits of addressing space. */
-		np->rx_ring[i].fraginfo =
-		    cpu_to_le64(dma_map_single(&np->pdev->dev, skb->data,
-					       np->rx_buf_sz, DMA_FROM_DEVICE));
+		np->rx_ring[i].fraginfo = cpu_to_le64(addr);
 		np->rx_ring[i].fraginfo |= cpu_to_le64((u64)np->rx_buf_sz << 48);
 	}
 
 	return 0;
+
+err_kfree_skb:
+	dev_kfree_skb(np->rx_skbuff[i]);
+	np->rx_skbuff[i] = NULL;
+err_free_list:
+	free_list(dev);
+	return -ENOMEM;
 }
 
 static void rio_hw_init(struct net_device *dev)

From 68a052239fc4b351e961f698b824f7654a346091 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 9 Oct 2025 13:56:29 -0700
Subject: [PATCH 308/352] selftests: drv-net: update remaining Python init
 files

Convert remaining __init__ files similar to what we did in
commit b615879dbfea ("selftests: drv-net: make linters happy with our imports")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/hw/lib/py/__init__.py         | 40 ++++++++++++++-----
 .../selftests/drivers/net/lib/py/__init__.py  |  4 +-
 .../testing/selftests/net/lib/py/__init__.py  | 29 ++++++++++++--
 3 files changed, 57 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index 0ceb297e7757..fb010a48a5a1 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -1,5 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0
 
+"""
+Driver test environment (hardware-only tests).
+NetDrvEnv and NetDrvEpEnv are the main environment classes.
+Former is for local host only tests, latter creates / connects
+to a remote endpoint. See NIPA wiki for more information about
+running and writing driver tests.
+"""
+
 import sys
 from pathlib import Path
 
@@ -8,26 +16,36 @@ KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve()
 try:
     sys.path.append(KSFT_DIR.as_posix())
 
-    from net.lib.py import *
-    from drivers.net.lib.py import *
-
     # Import one by one to avoid pylint false positives
+    from net.lib.py import NetNS, NetNSEnter, NetdevSimDev
     from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
         NlError, RtnlFamily, DevlinkFamily, PSPFamily
     from net.lib.py import CmdExitFailure
-    from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \
-        rand_port, tool, wait_port_listen
-    from net.lib.py import fd_read_timeout
+    from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
+        fd_read_timeout, ip, rand_port, wait_port_listen, wait_file
     from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
     from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
         ksft_setup
     from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
         ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
-    from net.lib.py import NetNSEnter
-    from drivers.net.lib.py import GenerateTraffic
+    from drivers.net.lib.py import GenerateTraffic, Remote
     from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv
+
+    __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev",
+               "EthtoolFamily", "NetdevFamily", "NetshaperFamily",
+               "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily",
+               "CmdExitFailure",
+               "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool",
+               "fd_read_timeout", "ip", "rand_port",
+               "wait_port_listen", "wait_file",
+               "KsftSkipEx", "KsftFailEx", "KsftXfailEx",
+               "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run",
+               "ksft_setup",
+               "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt",
+               "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt",
+               "ksft_not_none", "ksft_not_none",
+               "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"]
 except ModuleNotFoundError as e:
-    ksft_pr("Failed importing `net` library from kernel sources")
-    ksft_pr(str(e))
-    ktap_result(True, comment="SKIP")
+    print("Failed importing `net` library from kernel sources")
+    print(str(e))
     sys.exit(4)
diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py
index e6c070f32f51..b0c6300150fb 100644
--- a/tools/testing/selftests/drivers/net/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py
@@ -22,7 +22,7 @@ try:
         NlError, RtnlFamily, DevlinkFamily, PSPFamily
     from net.lib.py import CmdExitFailure
     from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
-        fd_read_timeout, ip, rand_port, tool, wait_port_listen, wait_file
+        fd_read_timeout, ip, rand_port, wait_port_listen, wait_file
     from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
     from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
         ksft_setup
@@ -34,7 +34,7 @@ try:
                "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily",
                "CmdExitFailure",
                "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool",
-               "fd_read_timeout", "ip", "rand_port", "tool",
+               "fd_read_timeout", "ip", "rand_port",
                "wait_port_listen", "wait_file",
                "KsftSkipEx", "KsftFailEx", "KsftXfailEx",
                "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run",
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 997b85cc216a..97b7cf2b20eb 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -1,9 +1,32 @@
 # SPDX-License-Identifier: GPL-2.0
 
+"""
+Python selftest helpers for netdev.
+"""
+
 from .consts import KSRC
-from .ksft import *
+from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \
+    ksft_ne, ksft_true, ksft_not_none, ksft_in, ksft_not_in, ksft_is, \
+    ksft_ge, ksft_gt, ksft_lt, ksft_raises, ksft_busy_wait, \
+    ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit
 from .netns import NetNS, NetNSEnter
-from .nsim import *
-from .utils import *
+from .nsim import NetdevSim, NetdevSimDev
+from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \
+    bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file
 from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
 from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily
+
+__all__ = ["KSRC",
+           "KsftFailEx", "KsftSkipEx", "KsftXfailEx", "ksft_pr", "ksft_eq",
+           "ksft_ne", "ksft_true", "ksft_not_none", "ksft_in", "ksft_not_in",
+           "ksft_is", "ksft_ge", "ksft_gt", "ksft_lt", "ksft_raises",
+           "ksft_busy_wait", "ktap_result", "ksft_disruptive", "ksft_setup",
+           "ksft_run", "ksft_exit",
+           "NetNS", "NetNSEnter",
+           "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer",
+           "bpftool", "ip", "ethtool", "bpftrace", "rand_port",
+           "wait_port_listen", "wait_file",
+           "NetdevSim", "NetdevSimDev",
+           "NetshaperFamily", "DevlinkFamily", "PSPFamily", "NlError",
+           "YnlFamily", "EthtoolFamily", "NetdevFamily", "RtnlFamily",
+           "RtnlAddrFamily"]

From 3a8660878839faadb4f1a6dd72c3179c1df56787 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 12 Oct 2025 13:42:36 -0700
Subject: [PATCH 309/352] Linux 6.18-rc1

---
 Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 6f88b1d3b40d..17cfa11ca716 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 17
+PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 0b4b77eff5f8cd9be062783a1c1e198d46d0a753 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 10 Oct 2025 16:18:59 +0200
Subject: [PATCH 310/352] doc: fix seg6_flowlabel path

This sysctl is not per interface; it's global per netns.

Fixes: 292ecd9f5a94 ("doc: move seg6_flowlabel to seg6-sysctl.rst")
Reported-by: Philippe Guibert <philippe.guibert@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/seg6-sysctl.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/networking/seg6-sysctl.rst b/Documentation/networking/seg6-sysctl.rst
index 07c20e470baf..1b6af4779be1 100644
--- a/Documentation/networking/seg6-sysctl.rst
+++ b/Documentation/networking/seg6-sysctl.rst
@@ -25,6 +25,9 @@ seg6_require_hmac - INTEGER
 
 	Default is 0.
 
+/proc/sys/net/ipv6/seg6_* variables:
+====================================
+
 seg6_flowlabel - INTEGER
 	Controls the behaviour of computing the flowlabel of outer
 	IPv6 header in case of SR T.encaps

From 12d724f2852d094d68dccaf5101e0ef89a971cde Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 9 Oct 2025 19:46:00 +0900
Subject: [PATCH 311/352] ata: libata-core: relax checks in
 ata_read_log_directory()

Commit 6d4405b16d37 ("ata: libata-core: Cache the general purpose log
directory") introduced caching of a device general purpose log directory
to avoid repeated access to this log page during device scan. This
change also added a check on this log page to verify that the log page
version is 0x0001 as mandated by the ACS specifications.

And it turns out that some devices do not bother reporting this version,
instead reporting a version 0, resulting in error messages such as:

ata6.00: Invalid log directory version 0x0000

and to the device being marked as not supporting the general purpose log
directory log page.

Since before commit 6d4405b16d37 the log page version check did not
exist and things were still working correctly for these devices, relax
ata_read_log_directory() version check and only warn about the invalid
log page version number without disabling access to the log directory
page.

Fixes: 6d4405b16d37 ("ata: libata-core: Cache the general purpose log directory")
Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220635
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 11 ++++-------
 include/linux/libata.h    |  6 ++++++
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ff53f5f029b4..2a210719c4ce 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2174,13 +2174,10 @@ static int ata_read_log_directory(struct ata_device *dev)
 	}
 
 	version = get_unaligned_le16(&dev->gp_log_dir[0]);
-	if (version != 0x0001) {
-		ata_dev_err(dev, "Invalid log directory version 0x%04x\n",
-			    version);
-		ata_clear_log_directory(dev);
-		dev->quirks |= ATA_QUIRK_NO_LOG_DIR;
-		return -EINVAL;
-	}
+	if (version != 0x0001)
+		ata_dev_warn_once(dev,
+				  "Invalid log directory version 0x%04x\n",
+				  version);
 
 	return 0;
 }
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 21de0935775d..7a98de1cc995 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1594,6 +1594,12 @@ do {								\
 #define ata_dev_dbg(dev, fmt, ...)				\
 	ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__)
 
+#define ata_dev_warn_once(dev, fmt, ...)			\
+	pr_warn_once("ata%u.%02u: " fmt,			\
+		     (dev)->link->ap->print_id,			\
+		     (dev)->link->pmp + (dev)->devno,		\
+		     ##__VA_ARGS__)
+
 static inline void ata_print_version_once(const struct device *dev,
 					  const char *version)
 {

From c282993ccd97ad627d213645dc485086de034647 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol@kernel.org>
Date: Mon, 13 Oct 2025 19:10:22 +0900
Subject: [PATCH 312/352] can: remove false statement about 1:1 mapping between
 DLC and length

The CAN-FD section of can.rst still states that there is a 1:1 mapping
between the Classical CAN DLC and its length. This is only true for
the DLC values up to 8. Beyond that point, the length remains at 8.

For reference, the mapping between the CAN DLC and the length is given
in below table [1]:

	 DLC value	CBFF and CEFF	FBFF and FEFF
	 [decimal]	    [byte]	    [byte]
	----------------------------------------------
		 0		 0		 0
		 1		 1		 1
		 2		 2		 2
		 3		 3		 3
		 4		 4		 4
		 5		 5		 5
		 6		 6		 6
		 7		 7		 7
		 8		 8		 8
		 9		 8		12
		10		 8		16
		11		 8		20
		12		 8		24
		13		 8		32
		14		 8		48
		15		 8		64

Remove the erroneous statement. Instead just state that the length of
a Classical CAN frame ranges from 0 to 8.

[1] ISO 11898-1:2024, Table 5 -- DLC: coding of the four LSB

Signed-off-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20251013-can-fd-doc-v2-1-5d53bdc8f2ad@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/can.rst | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index 7650c4b5be5f..ccd321d29a8a 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -1398,10 +1398,9 @@ second bit timing has to be specified in order to enable the CAN FD bitrate.
 Additionally CAN FD capable CAN controllers support up to 64 bytes of
 payload. The representation of this length in can_frame.len and
 canfd_frame.len for userspace applications and inside the Linux network
-layer is a plain value from 0 .. 64 instead of the CAN 'data length code'.
-The data length code was a 1:1 mapping to the payload length in the Classical
-CAN frames anyway. The payload length to the bus-relevant DLC mapping is
-only performed inside the CAN drivers, preferably with the helper
+layer is a plain value from 0 .. 64 instead of the Classical CAN length
+which ranges from 0 to 8. The payload length to the bus-relevant DLC mapping
+is only performed inside the CAN drivers, preferably with the helper
 functions can_fd_dlc2len() and can_fd_len2dlc().
 
 The CAN netdevice driver capabilities can be distinguished by the network

From b5746b3e8ea4a8a4df776e0864322028d4f5e4b1 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol@kernel.org>
Date: Mon, 13 Oct 2025 19:10:23 +0900
Subject: [PATCH 313/352] can: add Transmitter Delay Compensation (TDC)
 documentation

Back in 2021, support for CAN TDC was added to the kernel in series [1]
and in iproute2 in series [2]. However, the documentation was never
updated.

Add a new sub-section under CAN-FD driver support to document how to
configure the TDC using the "ip tool".

[1] add the netlink interface for CAN-FD Transmitter Delay Compensation (TDC)
Link: https://lore.kernel.org/all/20210918095637.20108-1-mailhol.vincent@wanadoo.fr/

[2] iplink_can: cleaning, fixes and adding TDC support
Link: https://lore.kernel.org/all/20211103164428.692722-1-mailhol.vincent@wanadoo.fr/

Signed-off-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20251013-can-fd-doc-v2-2-5d53bdc8f2ad@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/can.rst | 64 ++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index ccd321d29a8a..194e305ae973 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -1464,6 +1464,70 @@ Example when 'fd-non-iso on' is added on this switchable CAN FD adapter::
    can <FD,FD-NON-ISO> state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 0
 
 
+Transmitter Delay Compensation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+At high bit rates, the propagation delay from the TX pin to the RX pin of
+the transceiver might become greater than the actual bit time causing
+measurement errors: the RX pin would still be measuring the previous bit.
+
+The Transmitter Delay Compensation (thereafter, TDC) resolves this problem
+by introducing a Secondary Sample Point (SSP) equal to the distance, in
+minimum time quantum, from the start of the bit time on the TX pin to the
+actual measurement on the RX pin. The SSP is calculated as the sum of two
+configurable values: the TDC Value (TDCV) and the TDC offset (TDCO).
+
+TDC, if supported by the device, can be configured together with CAN-FD
+using the ip tool's "tdc-mode" argument as follow:
+
+**omitted**
+	When no "tdc-mode" option is provided, the kernel will automatically
+	decide whether TDC should be turned on, in which case it will
+	calculate a default TDCO and use the TDCV as measured by the
+	device. This is the recommended method to use TDC.
+
+**"tdc-mode off"**
+	TDC is explicitly disabled.
+
+**"tdc-mode auto"**
+	The user must provide the "tdco" argument. The TDCV will be
+	automatically calculated by the device. This option is only
+	available if the device supports the TDC-AUTO CAN controller mode.
+
+**"tdc-mode manual"**
+	The user must provide both the "tdco" and "tdcv" arguments. This
+	option is only available if the device supports the TDC-MANUAL CAN
+	controller mode.
+
+Note that some devices may offer an additional parameter: "tdcf" (TDC Filter
+window). If supported by your device, this can be added as an optional
+argument to either "tdc-mode auto" or "tdc-mode manual".
+
+Example configuring a 500 kbit/s arbitration bitrate, a 5 Mbit/s data
+bitrate, a TDCO of 15 minimum time quantum and a TDCV automatically measured
+by the device::
+
+    $ ip link set can0 up type can bitrate 500000 \
+                                   fd on dbitrate 4000000 \
+				   tdc-mode auto tdco 15
+    $ ip -details link show can0
+    5: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 72 qdisc pfifo_fast state UP \
+             mode DEFAULT group default qlen 10
+        link/can  promiscuity 0 allmulti 0 minmtu 72 maxmtu 72
+        can <FD,TDC-AUTO> state ERROR-ACTIVE restart-ms 0
+          bitrate 500000 sample-point 0.875
+          tq 12 prop-seg 69 phase-seg1 70 phase-seg2 20 sjw 10 brp 1
+          ES582.1/ES584.1: tseg1 2..256 tseg2 2..128 sjw 1..128 brp 1..512 \
+          brp_inc 1
+          dbitrate 4000000 dsample-point 0.750
+          dtq 12 dprop-seg 7 dphase-seg1 7 dphase-seg2 5 dsjw 2 dbrp 1
+          tdco 15 tdcf 0
+          ES582.1/ES584.1: dtseg1 2..32 dtseg2 1..16 dsjw 1..8 dbrp 1..32 \
+          dbrp_inc 1
+          tdco 0..127 tdcf 0..127
+          clock 80000000
+
+
 Supported CAN Hardware
 ----------------------
 

From 93a27b5891b8194a8c083c9a80d2141d4bf47ba8 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sat, 27 Sep 2025 21:11:16 +0900
Subject: [PATCH 314/352] can: j1939: add missing calls in NETDEV_UNREGISTER
 notification handler

Currently NETDEV_UNREGISTER event handler is not calling
j1939_cancel_active_session() and j1939_sk_queue_drop_all().
This will result in these calls being skipped when j1939_sk_release() is
called. And I guess that the reason syzbot is still reporting

  unregister_netdevice: waiting for vcan0 to become free. Usage count = 2

is caused by lack of these calls.

Calling j1939_cancel_active_session(priv, sk) from j1939_sk_release() can
be covered by calling j1939_cancel_active_session(priv, NULL) from
j1939_netdev_notify().

Calling j1939_sk_queue_drop_all() from j1939_sk_release() can be covered
by calling j1939_sk_netdev_event_netdown() from j1939_netdev_notify().

Therefore, we can reuse j1939_cancel_active_session(priv, NULL) and
j1939_sk_netdev_event_netdown(priv) for NETDEV_UNREGISTER event handler.

Fixes: 7fcbe5b2c6a4 ("can: j1939: implement NETDEV_UNREGISTER notification handler")
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/3ad3c7f8-5a74-4b07-a193-cb0725823558@I-love.SAKURA.ne.jp
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 3706a872ecaf..a93af55df5fd 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -378,6 +378,8 @@ static int j1939_netdev_notify(struct notifier_block *nb,
 		j1939_ecu_unmap_all(priv);
 		break;
 	case NETDEV_UNREGISTER:
+		j1939_cancel_active_session(priv, NULL);
+		j1939_sk_netdev_event_netdown(priv);
 		j1939_sk_netdev_event_unregister(priv);
 		break;
 	}

From fcb8b32a68fd40b0440cb9468cf6f6ab9de9f3c5 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 8 Oct 2025 16:14:45 +0200
Subject: [PATCH 315/352] dpll: zl3073x: Handle missing or corrupted flash
 configuration

If the internal flash contains missing or corrupted configuration,
basic communication over the bus still functions, but the device
is not capable of normal operation (for example, using mailboxes).

This condition is indicated in the info register by the ready bit.
If this bit is cleared, the probe procedure times out while fetching
the device state.

Handle this case by checking the ready bit value in zl3073x_dev_start()
and skipping DPLL device and pin registration if it is cleared.
Do not report this condition as an error, allowing the devlink device
to be registered and enabling the user to flash the correct configuration.

Prior this patch:
[   31.112299] zl3073x-i2c 1-0070: Failed to fetch input state: -ETIMEDOUT
[   31.116332] zl3073x-i2c 1-0070: error -ETIMEDOUT: Failed to start device
[   31.136881] zl3073x-i2c 1-0070: probe with driver zl3073x-i2c failed with error -110

After this patch:
[   41.011438] zl3073x-i2c 1-0070: FW not fully ready - missing or corrupted config

Fixes: 75a71ecc24125 ("dpll: zl3073x: Register DPLL devices and pins")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251008141445.841113-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/zl3073x/core.c | 21 +++++++++++++++++++++
 drivers/dpll/zl3073x/regs.h |  3 +++
 2 files changed, 24 insertions(+)

diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c
index 092e7027948a..e42e527813cf 100644
--- a/drivers/dpll/zl3073x/core.c
+++ b/drivers/dpll/zl3073x/core.c
@@ -1038,8 +1038,29 @@ zl3073x_dev_phase_meas_setup(struct zl3073x_dev *zldev)
 int zl3073x_dev_start(struct zl3073x_dev *zldev, bool full)
 {
 	struct zl3073x_dpll *zldpll;
+	u8 info;
 	int rc;
 
+	rc = zl3073x_read_u8(zldev, ZL_REG_INFO, &info);
+	if (rc) {
+		dev_err(zldev->dev, "Failed to read device status info\n");
+		return rc;
+	}
+
+	if (!FIELD_GET(ZL_INFO_READY, info)) {
+		/* The ready bit indicates that the firmware was successfully
+		 * configured and is ready for normal operation. If it is
+		 * cleared then the configuration stored in flash is wrong
+		 * or missing. In this situation the driver will expose
+		 * only devlink interface to give an opportunity to flash
+		 * the correct config.
+		 */
+		dev_info(zldev->dev,
+			 "FW not fully ready - missing or corrupted config\n");
+
+		return 0;
+	}
+
 	if (full) {
 		/* Fetch device state */
 		rc = zl3073x_dev_state_fetch(zldev);
diff --git a/drivers/dpll/zl3073x/regs.h b/drivers/dpll/zl3073x/regs.h
index 19a25325bd9c..d837bee72b17 100644
--- a/drivers/dpll/zl3073x/regs.h
+++ b/drivers/dpll/zl3073x/regs.h
@@ -67,6 +67,9 @@
  * Register Page 0, General
  **************************/
 
+#define ZL_REG_INFO				ZL_REG(0, 0x00, 1)
+#define ZL_INFO_READY				BIT(7)
+
 #define ZL_REG_ID				ZL_REG(0, 0x01, 2)
 #define ZL_REG_REVISION				ZL_REG(0, 0x03, 2)
 #define ZL_REG_FW_VER				ZL_REG(0, 0x05, 2)

From 25718fdcbdd2dadd15fc8b684df59b43970b91ed Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 9 Oct 2025 11:43:38 +0200
Subject: [PATCH 316/352] net: gro_cells: Use nested-BH locking for gro_cell

The gro_cell data structure is per-CPU variable and relies on disabled
BH for its locking. Without per-CPU locking in local_bh_disable() on
PREEMPT_RT this data structure requires explicit locking.

Add a local_lock_t to the data structure and use
local_lock_nested_bh() for locking. This change adds only lockdep
coverage and does not alter the functional behaviour for !PREEMPT_RT.

Reported-by: syzbot+8715dd783e9b0bef43b1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68c6c3b1.050a0220.2ff435.0382.GAE@google.com/
Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20251009094338.j1jyKfjR@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/gro_cells.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index ff8e5b64bf6b..b43911562f4d 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -8,11 +8,13 @@
 struct gro_cell {
 	struct sk_buff_head	napi_skbs;
 	struct napi_struct	napi;
+	local_lock_t		bh_lock;
 };
 
 int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
+	bool have_bh_lock = false;
 	struct gro_cell *cell;
 	int res;
 
@@ -25,6 +27,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 		goto unlock;
 	}
 
+	local_lock_nested_bh(&gcells->cells->bh_lock);
+	have_bh_lock = true;
 	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) {
@@ -39,6 +43,9 @@ drop:
 	if (skb_queue_len(&cell->napi_skbs) == 1)
 		napi_schedule(&cell->napi);
 
+	if (have_bh_lock)
+		local_unlock_nested_bh(&gcells->cells->bh_lock);
+
 	res = NET_RX_SUCCESS;
 
 unlock:
@@ -54,6 +61,7 @@ static int gro_cell_poll(struct napi_struct *napi, int budget)
 	struct sk_buff *skb;
 	int work_done = 0;
 
+	__local_lock_nested_bh(&cell->bh_lock);
 	while (work_done < budget) {
 		skb = __skb_dequeue(&cell->napi_skbs);
 		if (!skb)
@@ -64,6 +72,7 @@ static int gro_cell_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget)
 		napi_complete_done(napi, work_done);
+	__local_unlock_nested_bh(&cell->bh_lock);
 	return work_done;
 }
 
@@ -79,6 +88,7 @@ int gro_cells_init(struct gro_cells *gcells, struct net_device *dev)
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		__skb_queue_head_init(&cell->napi_skbs);
+		local_lock_init(&cell->bh_lock);
 
 		set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state);
 

From 70f92ab97042f243e1c8da1c457ff56b9b3e49f1 Mon Sep 17 00:00:00 2001
From: Linmao Li <lilinmao@kylinos.cn>
Date: Thu, 9 Oct 2025 20:25:49 +0800
Subject: [PATCH 317/352] r8169: fix packet truncation after S4 resume on
 RTL8168H/RTL8111H

After resume from S4 (hibernate), RTL8168H/RTL8111H truncates incoming
packets. Packet captures show messages like "IP truncated-ip - 146 bytes
missing!".

The issue is caused by RxConfig not being properly re-initialized after
resume. Re-initializing the RxConfig register before the chip
re-initialization sequence avoids the truncation and restores correct
packet reception.

This follows the same pattern as commit ef9da46ddef0 ("r8169: fix data
corruption issue on RTL8402").

Fixes: 6e1d0b898818 ("r8169:add support for RTL8168H and RTL8107E")
Signed-off-by: Linmao Li <lilinmao@kylinos.cn>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/20251009122549.3955845-1-lilinmao@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 8903ae90afcb..d18734fe12e4 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4994,8 +4994,9 @@ static int rtl8169_resume(struct device *device)
 	if (!device_may_wakeup(tp_to_dev(tp)))
 		clk_prepare_enable(tp->clk);
 
-	/* Reportedly at least Asus X453MA truncates packets otherwise */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_37)
+	/* Some chip versions may truncate packets without this initialization */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_37 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_46)
 		rtl_init_rxcfg(tp);
 
 	return rtl8169_runtime_resume(device);

From e4d0c909bf8328d986bf3aadba0c33a72b5ae30d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kamil=20Hor=C3=A1k=20-=202N?= <kamilh@axis.com>
Date: Thu, 9 Oct 2025 15:06:56 +0200
Subject: [PATCH 318/352] net: phy: bcm54811: Fix GMII/MII/MII-Lite selection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Broadcom bcm54811 is hardware-strapped to select among RGMII and
GMII/MII/MII-Lite modes. However, the corresponding bit, RGMII Enable
in Miscellaneous Control Register must be also set to select desired
RGMII or MII(-lite)/GMII mode.

Fixes: 3117a11fff5af9e7 ("net: phy: bcm54811: PHY initialization")
Signed-off-by: Kamil Horák - 2N <kamilh@axis.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20251009130656.1308237-2-kamilh@axis.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/broadcom.c | 20 +++++++++++++++++++-
 include/linux/brcmphy.h    |  1 +
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 3459a0e9d8b9..cb306f9e80cc 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -405,7 +405,7 @@ static int bcm5481x_set_brrmode(struct phy_device *phydev, bool on)
 static int bcm54811_config_init(struct phy_device *phydev)
 {
 	struct bcm54xx_phy_priv *priv = phydev->priv;
-	int err, reg, exp_sync_ethernet;
+	int err, reg, exp_sync_ethernet, aux_rgmii_en;
 
 	/* Enable CLK125 MUX on LED4 if ref clock is enabled. */
 	if (!(phydev->dev_flags & PHY_BRCM_RX_REFCLK_UNUSED)) {
@@ -434,6 +434,24 @@ static int bcm54811_config_init(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	/* Enable RGMII if configured */
+	if (phy_interface_is_rgmii(phydev))
+		aux_rgmii_en = MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN |
+			       MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
+	else
+		aux_rgmii_en = 0;
+
+	/* Also writing Reserved bits 6:5 because the documentation requires
+	 * them to be written to 0b11
+	 */
+	err = bcm54xx_auxctl_write(phydev,
+				   MII_BCM54XX_AUXCTL_SHDWSEL_MISC,
+				   MII_BCM54XX_AUXCTL_MISC_WREN |
+				   aux_rgmii_en |
+				   MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RSVD);
+	if (err < 0)
+		return err;
+
 	return bcm5481x_set_brrmode(phydev, priv->brr_mode);
 }
 
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 15c35655f482..115a964f3006 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -137,6 +137,7 @@
 
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC			0x07
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN	0x0010
+#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RSVD		0x0060
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN	0x0080
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN	0x0100
 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX		0x0200

From 21f4d45eba0b2dcae5dbc9e5e0ad08735c993f16 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Thu, 9 Oct 2025 16:02:19 +0100
Subject: [PATCH 319/352] net/ip6_tunnel: Prevent perpetual tunnel growth

Similarly to ipv4 tunnel, ipv6 version updates dev->needed_headroom, too.
While ipv4 tunnel headroom adjustment growth was limited in
commit 5ae1e9922bbd ("net: ip_tunnel: prevent perpetual headroom growth"),
ipv6 tunnel yet increases the headroom without any ceiling.

Reflect ipv4 tunnel headroom adjustment limit on ipv6 version.

Credits to Francesco Ruggeri, who was originally debugging this issue
and wrote local Arista-specific patch and a reproducer.

Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit")
Cc: Florian Westphal <fw@strlen.de>
Cc: Francesco Ruggeri <fruggeri05@gmail.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://patch.msgid.link/20251009-ip6_tunnel-headroom-v2-1-8e4dbd8f7e35@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h | 15 +++++++++++++++
 net/ipv4/ip_tunnel.c     | 14 --------------
 net/ipv6/ip6_tunnel.c    |  3 +--
 3 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 4314a97702ea..ecae35512b9b 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -611,6 +611,21 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 			  int headroom, bool reply);
 
+static inline void ip_tunnel_adj_headroom(struct net_device *dev,
+					  unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
 
 static inline int iptunnel_pull_offloads(struct sk_buff *skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index aaeb5d16f0c9..158a30ae7c5f 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -568,20 +568,6 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
-static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
-{
-	/* we must cap headroom to some upperlimit, else pskb_expand_head
-	 * will overflow header offsets in skb_headers_offset_update().
-	 */
-	static const unsigned int max_allowed = 512;
-
-	if (headroom > max_allowed)
-		headroom = max_allowed;
-
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-}
-
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3262e81223df..6405072050e0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1257,8 +1257,7 @@ route_lookup:
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr)
 			+ dst->header_len + t->hlen;
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
+	ip_tunnel_adj_headroom(dev, max_headroom);
 
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)

From a3f8c0a273120fd2638f03403e786c3de2382e72 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Thu, 9 Oct 2025 17:03:46 -0700
Subject: [PATCH 320/352] idpf: cleanup remaining SKBs in PTP flows

When the driver requests Tx timestamp value, one of the first steps is
to clone SKB using skb_get. It increases the reference counter for that
SKB to prevent unexpected freeing by another component.
However, there may be a case where the index is requested, SKB is
assigned and never consumed by PTP flows - for example due to reset during
running PTP apps.

Add a check in release timestamping function to verify if the SKB
assigned to Tx timestamp latch was freed, and release remaining SKBs.

Fixes: 4901e83a94ef ("idpf: add Tx timestamp capabilities negotiation")
Signed-off-by: Milena Olech <milena.olech@intel.com>
Signed-off-by: Anton Nadezhdin <anton.nadezhdin@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-1-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_ptp.c          | 3 +++
 drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 142823af1f9e..3e1052d070cf 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -863,6 +863,9 @@ static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
 		u64_stats_inc(&vport->tstamp_stats.flushed);
 
 		list_del(&ptp_tx_tstamp->list_member);
+		if (ptp_tx_tstamp->skb)
+			consume_skb(ptp_tx_tstamp->skb);
+
 		kfree(ptp_tx_tstamp);
 	}
 	u64_stats_update_end(&vport->tstamp_stats.stats_sync);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
index 8a2e0f8c5e36..61cedb6f2854 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -517,6 +517,7 @@ idpf_ptp_get_tstamp_value(struct idpf_vport *vport,
 	shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
 	skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps);
 	consume_skb(ptp_tx_tstamp->skb);
+	ptp_tx_tstamp->skb = NULL;
 
 	list_add(&ptp_tx_tstamp->list_member,
 		 &tx_tstamp_caps->latches_free);

From 53f0eb62b4d23d40686f2dd51776b8220f2887bb Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Thu, 9 Oct 2025 17:03:47 -0700
Subject: [PATCH 321/352] ixgbevf: fix getting link speed data for E610 devices

E610 adapters no longer use the VFLINKS register to read PF's link
speed and linkup state. As a result VF driver cannot get actual link
state and it incorrectly reports 10G which is the default option.
It leads to a situation where even 1G adapters print 10G as actual
link speed. The same happens when PF driver set speed different than 10G.

Add new mailbox operation to let the VF driver request a PF driver
to provide actual link data. Update the mailbox api to v1.6.

Incorporate both ways of getting link status within the legacy
ixgbe_check_mac_link_vf() function.

Fixes: 4c44b450c69b ("ixgbevf: Add support for Intel(R) E610 device")
Co-developed-by: Andrzej Wilczynski <andrzejx.wilczynski@intel.com>
Signed-off-by: Andrzej Wilczynski <andrzejx.wilczynski@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-2-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbevf/defines.h  |   1 +
 .../net/ethernet/intel/ixgbevf/ixgbevf_main.c |   6 +-
 drivers/net/ethernet/intel/ixgbevf/mbx.h      |   4 +
 drivers/net/ethernet/intel/ixgbevf/vf.c       | 137 ++++++++++++++----
 4 files changed, 116 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index a9bc96f6399d..e177d1d58696 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -28,6 +28,7 @@
 
 /* Link speed */
 typedef u32 ixgbe_link_speed;
+#define IXGBE_LINK_SPEED_UNKNOWN	0
 #define IXGBE_LINK_SPEED_1GB_FULL	0x0020
 #define IXGBE_LINK_SPEED_10GB_FULL	0x0080
 #define IXGBE_LINK_SPEED_100_FULL	0x0008
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 28e25641b167..92671638b428 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2275,6 +2275,7 @@ static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	static const int api[] = {
+		ixgbe_mbox_api_16,
 		ixgbe_mbox_api_15,
 		ixgbe_mbox_api_14,
 		ixgbe_mbox_api_13,
@@ -2294,7 +2295,8 @@ static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 		idx++;
 	}
 
-	if (hw->api_version >= ixgbe_mbox_api_15) {
+	/* Following is not supported by API 1.6, it is specific for 1.5 */
+	if (hw->api_version == ixgbe_mbox_api_15) {
 		hw->mbx.ops.init_params(hw);
 		memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
 		       sizeof(struct ixgbe_mbx_operations));
@@ -2651,6 +2653,7 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
 		case ixgbe_mbox_api_13:
 		case ixgbe_mbox_api_14:
 		case ixgbe_mbox_api_15:
+		case ixgbe_mbox_api_16:
 			if (adapter->xdp_prog &&
 			    hw->mac.max_tx_queues == rss)
 				rss = rss > 3 ? 2 : 1;
@@ -4645,6 +4648,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
 		netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE -
 				  (ETH_HLEN + ETH_FCS_LEN);
 		break;
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h
index 835bbcc5cc8e..c1494fd1f67b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.h
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h
@@ -66,6 +66,7 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_13,	/* API version 1.3, linux/freebsd VF driver */
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
 	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
+	ixgbe_mbox_api_16,      /* API version 1.6, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -102,6 +103,9 @@ enum ixgbe_pfvf_api_rev {
 
 #define IXGBE_VF_GET_LINK_STATE 0x10 /* get vf link state */
 
+/* mailbox API, version 1.6 VF requests */
+#define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN	4
 /* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index dcaef34b88b6..f05246fb5a74 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -313,6 +313,7 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues)
 	 * is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -382,6 +383,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key)
 	 * or if the operation is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -552,6 +554,7 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode)
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -624,6 +627,48 @@ static s32 ixgbevf_hv_get_link_state_vf(struct ixgbe_hw *hw, bool *link_state)
 	return -EOPNOTSUPP;
 }
 
+/**
+ * ixgbevf_get_pf_link_state - Get PF's link status
+ * @hw: pointer to the HW structure
+ * @speed: link speed
+ * @link_up: indicate if link is up/down
+ *
+ * Ask PF to provide link_up state and speed of the link.
+ *
+ * Return: IXGBE_ERR_MBX in the case of mailbox error,
+ * -EOPNOTSUPP if the op is not supported or 0 on success.
+ */
+static int ixgbevf_get_pf_link_state(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+				     bool *link_up)
+{
+	u32 msgbuf[3] = {};
+	int err;
+
+	switch (hw->api_version) {
+	case ixgbe_mbox_api_16:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	msgbuf[0] = IXGBE_VF_GET_PF_LINK_STATE;
+
+	err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+					 ARRAY_SIZE(msgbuf));
+	if (err || (msgbuf[0] & IXGBE_VT_MSGTYPE_FAILURE)) {
+		err = IXGBE_ERR_MBX;
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+		/* No need to set @link_up to false as it will be done by
+		 * ixgbe_check_mac_link_vf().
+		 */
+	} else {
+		*speed = msgbuf[1];
+		*link_up = msgbuf[2];
+	}
+
+	return err;
+}
+
 /**
  *  ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address
  *  @hw: pointer to the HW structure
@@ -658,6 +703,58 @@ mbx_err:
 	return err;
 }
 
+/**
+ * ixgbe_read_vflinks - Read VFLINKS register
+ * @hw: pointer to the HW structure
+ * @speed: link speed
+ * @link_up: indicate if link is up/down
+ *
+ * Get linkup status and link speed from the VFLINKS register.
+ */
+static void ixgbe_read_vflinks(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			       bool *link_up)
+{
+	u32 vflinks = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+
+	/* if link status is down no point in checking to see if PF is up */
+	if (!(vflinks & IXGBE_LINKS_UP)) {
+		*link_up = false;
+		return;
+	}
+
+	/* for SFP+ modules and DA cables on 82599 it can take up to 500usecs
+	 * before the link status is correct
+	 */
+	if (hw->mac.type == ixgbe_mac_82599_vf) {
+		for (int i = 0; i < 5; i++) {
+			udelay(100);
+			vflinks = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+
+			if (!(vflinks & IXGBE_LINKS_UP)) {
+				*link_up = false;
+				return;
+			}
+		}
+	}
+
+	/* We reached this point so there's link */
+	*link_up = true;
+
+	switch (vflinks & IXGBE_LINKS_SPEED_82599) {
+	case IXGBE_LINKS_SPEED_10G_82599:
+		*speed = IXGBE_LINK_SPEED_10GB_FULL;
+		break;
+	case IXGBE_LINKS_SPEED_1G_82599:
+		*speed = IXGBE_LINK_SPEED_1GB_FULL;
+		break;
+	case IXGBE_LINKS_SPEED_100_82599:
+		*speed = IXGBE_LINK_SPEED_100_FULL;
+		break;
+	default:
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+	}
+}
+
 /**
  * ixgbevf_hv_set_vfta_vf - * Hyper-V variant - just a stub.
  * @hw: unused
@@ -705,7 +802,6 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 	struct ixgbe_mac_info *mac = &hw->mac;
 	s32 ret_val = 0;
-	u32 links_reg;
 	u32 in_msg = 0;
 
 	/* If we were hit with a reset drop the link */
@@ -715,36 +811,14 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	if (!mac->get_link_status)
 		goto out;
 
-	/* if link status is down no point in checking to see if pf is up */
-	links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
-	if (!(links_reg & IXGBE_LINKS_UP))
-		goto out;
-
-	/* for SFP+ modules and DA cables on 82599 it can take up to 500usecs
-	 * before the link status is correct
-	 */
-	if (mac->type == ixgbe_mac_82599_vf) {
-		int i;
-
-		for (i = 0; i < 5; i++) {
-			udelay(100);
-			links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
-
-			if (!(links_reg & IXGBE_LINKS_UP))
-				goto out;
-		}
-	}
-
-	switch (links_reg & IXGBE_LINKS_SPEED_82599) {
-	case IXGBE_LINKS_SPEED_10G_82599:
-		*speed = IXGBE_LINK_SPEED_10GB_FULL;
-		break;
-	case IXGBE_LINKS_SPEED_1G_82599:
-		*speed = IXGBE_LINK_SPEED_1GB_FULL;
-		break;
-	case IXGBE_LINKS_SPEED_100_82599:
-		*speed = IXGBE_LINK_SPEED_100_FULL;
-		break;
+	if (hw->mac.type == ixgbe_mac_e610_vf) {
+		ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up);
+		if (ret_val)
+			goto out;
+	} else {
+		ixgbe_read_vflinks(hw, speed, link_up);
+		if (*link_up == false)
+			goto out;
 	}
 
 	/* if the read failed it could just be a mailbox collision, best wait
@@ -951,6 +1025,7 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
 		break;
 	default:
 		return 0;

From f7f97cbc03a470ce405d48dedb7f135713caa0fa Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Thu, 9 Oct 2025 17:03:48 -0700
Subject: [PATCH 322/352] ixgbe: handle IXGBE_VF_GET_PF_LINK_STATE mailbox
 operation

Update supported API version and provide handler for
IXGBE_VF_GET_PF_LINK_STATE cmd.
Simply put stored values of link speed and link_up from adapter context.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Link: https://lore.kernel.org/stable/20250828095227.1857066-3-jedrzej.jagielski%40intel.com
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-3-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h  |  5 +++
 .../net/ethernet/intel/ixgbe/ixgbe_sriov.c    | 42 +++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index 4af149b63a39..f7256a339c99 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -50,6 +50,8 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_12,	/* API version 1.2, linux/freebsd VF driver */
 	ixgbe_mbox_api_13,	/* API version 1.3, linux/freebsd VF driver */
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
+	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
+	ixgbe_mbox_api_16,	/* API version 1.6, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -86,6 +88,9 @@ enum ixgbe_pfvf_api_rev {
 
 #define IXGBE_VF_GET_LINK_STATE 0x10 /* get vf link state */
 
+/* mailbox API, version 1.6 VF requests */
+#define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN 4
 /* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 32ac1e020d91..b09271d61a4e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -510,6 +510,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf
 		case ixgbe_mbox_api_12:
 		case ixgbe_mbox_api_13:
 		case ixgbe_mbox_api_14:
+		case ixgbe_mbox_api_16:
 			/* Version 1.1 supports jumbo frames on VFs if PF has
 			 * jumbo frames enabled which means legacy VFs are
 			 * disabled
@@ -1046,6 +1047,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
 		adapter->vfinfo[vf].vf_api = api;
 		return 0;
 	default:
@@ -1072,6 +1074,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
 		break;
 	default:
 		return -1;
@@ -1112,6 +1115,7 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
@@ -1145,6 +1149,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
@@ -1174,6 +1179,7 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter,
 		fallthrough;
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1244,6 +1250,7 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1254,6 +1261,38 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
+/**
+ * ixgbe_send_vf_link_status - send link status data to VF
+ * @adapter: pointer to adapter struct
+ * @msgbuf: pointer to message buffers
+ * @vf: VF identifier
+ *
+ * Reply for IXGBE_VF_GET_PF_LINK_STATE mbox command sending link status data.
+ *
+ * Return: 0 on success or -EOPNOTSUPP when operation is not supported.
+ */
+static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter,
+				     u32 *msgbuf, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_16:
+		if (hw->mac.type != ixgbe_mac_e610)
+			return -EOPNOTSUPP;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	/* Simply provide stored values as watchdog & link status events take
+	 * care of its freshness.
+	 */
+	msgbuf[1] = adapter->link_speed;
+	msgbuf[2] = adapter->link_up;
+
+	return 0;
+}
+
 static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 {
 	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
@@ -1328,6 +1367,9 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 	case IXGBE_VF_IPSEC_DEL:
 		retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf);
 		break;
+	case IXGBE_VF_GET_PF_LINK_STATE:
+		retval = ixgbe_send_vf_link_status(adapter, msgbuf, vf);
+		break;
 	default:
 		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
 		retval = -EIO;

From a7075f501bd33c93570af759b6f4302ef0175168 Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Thu, 9 Oct 2025 17:03:49 -0700
Subject: [PATCH 323/352] ixgbevf: fix mailbox API compatibility by negotiating
 supported features

There was backward compatibility in the terms of mailbox API. Various
drivers from various OSes supporting 10G adapters from Intel portfolio
could easily negotiate mailbox API.

This convention has been broken since introducing API 1.4.
Commit 0062e7cc955e ("ixgbevf: add VF IPsec offload code") added support
for IPSec which is specific only for the kernel ixgbe driver. None of the
rest of the Intel 10G PF/VF drivers supports it. And actually lack of
support was not included in the IPSec implementation - there were no such
code paths. No possibility to negotiate support for the feature was
introduced along with introduction of the feature itself.

Commit 339f28964147 ("ixgbevf: Add support for new mailbox communication
between PF and VF") increasing API version to 1.5 did the same - it
introduced code supported specifically by the PF ESX driver. It altered API
version for the VF driver in the same time not touching the version
defined for the PF ixgbe driver. It led to additional discrepancies,
as the code provided within API 1.6 cannot be supported for Linux ixgbe
driver as it causes crashes.

The issue was noticed some time ago and mitigated by Jake within the commit
d0725312adf5 ("ixgbevf: stop attempting IPSEC offload on Mailbox API 1.5").
As a result we have regression for IPsec support and after increasing API
to version 1.6 ixgbevf driver stopped to support ESX MBX.

To fix this mess add new mailbox op asking PF driver about supported
features. Basing on a response determine whether to set support for IPSec
and ESX-specific enhanced mailbox.

New mailbox op, for compatibility purposes, must be added within new API
revision, as API version of OOT PF & VF drivers is already increased to
1.6 and doesn't incorporate features negotiate op.

Features negotiation mechanism gives possibility to be extended with new
features when needed in the future.

Reported-by: Jacob Keller <jacob.e.keller@intel.com>
Closes: https://lore.kernel.org/intel-wired-lan/20241101-jk-ixgbevf-mailbox-v1-5-fixes-v1-0-f556dc9a66ed@intel.com/
Fixes: 0062e7cc955e ("ixgbevf: add VF IPsec offload code")
Fixes: 339f28964147 ("ixgbevf: Add support for new mailbox communication between PF and VF")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-4-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbevf/ipsec.c    | 10 +++++
 drivers/net/ethernet/intel/ixgbevf/ixgbevf.h  |  7 +++
 .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 32 ++++++++++++-
 drivers/net/ethernet/intel/ixgbevf/mbx.h      |  4 ++
 drivers/net/ethernet/intel/ixgbevf/vf.c       | 45 ++++++++++++++++++-
 drivers/net/ethernet/intel/ixgbevf/vf.h       |  1 +
 6 files changed, 96 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index 65580b9cb06f..fce35924ff8b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -273,6 +273,9 @@ static int ixgbevf_ipsec_add_sa(struct net_device *dev,
 	adapter = netdev_priv(dev);
 	ipsec = adapter->ipsec;
 
+	if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+		return -EOPNOTSUPP;
+
 	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol for IPsec offload");
 		return -EINVAL;
@@ -405,6 +408,9 @@ static void ixgbevf_ipsec_del_sa(struct net_device *dev,
 	adapter = netdev_priv(dev);
 	ipsec = adapter->ipsec;
 
+	if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+		return;
+
 	if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) {
 		sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
 
@@ -612,6 +618,10 @@ void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter)
 	size_t size;
 
 	switch (adapter->hw.api_version) {
+	case ixgbe_mbox_api_17:
+		if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+			return;
+		break;
 	case ixgbe_mbox_api_14:
 		break;
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 3a379e6a3a2a..039187607e98 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -363,6 +363,13 @@ struct ixgbevf_adapter {
 	struct ixgbe_hw hw;
 	u16 msg_enable;
 
+	u32 pf_features;
+#define IXGBEVF_PF_SUP_IPSEC		BIT(0)
+#define IXGBEVF_PF_SUP_ESX_MBX		BIT(1)
+
+#define IXGBEVF_SUPPORTED_FEATURES	(IXGBEVF_PF_SUP_IPSEC | \
+					IXGBEVF_PF_SUP_ESX_MBX)
+
 	struct ixgbevf_hw_stats stats;
 
 	unsigned long state;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 92671638b428..d5ce20f47def 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2271,10 +2271,35 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
 	adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
 }
 
+/**
+ * ixgbevf_set_features - Set features supported by PF
+ * @adapter: pointer to the adapter struct
+ *
+ * Negotiate with PF supported features and then set pf_features accordingly.
+ */
+static void ixgbevf_set_features(struct ixgbevf_adapter *adapter)
+{
+	u32 *pf_features = &adapter->pf_features;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	err = hw->mac.ops.negotiate_features(hw, pf_features);
+	if (err && err != -EOPNOTSUPP)
+		netdev_dbg(adapter->netdev,
+			   "PF feature negotiation failed.\n");
+
+	/* Address also pre API 1.7 cases */
+	if (hw->api_version == ixgbe_mbox_api_14)
+		*pf_features |= IXGBEVF_PF_SUP_IPSEC;
+	else if (hw->api_version == ixgbe_mbox_api_15)
+		*pf_features |= IXGBEVF_PF_SUP_ESX_MBX;
+}
+
 static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	static const int api[] = {
+		ixgbe_mbox_api_17,
 		ixgbe_mbox_api_16,
 		ixgbe_mbox_api_15,
 		ixgbe_mbox_api_14,
@@ -2295,8 +2320,9 @@ static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 		idx++;
 	}
 
-	/* Following is not supported by API 1.6, it is specific for 1.5 */
-	if (hw->api_version == ixgbe_mbox_api_15) {
+	ixgbevf_set_features(adapter);
+
+	if (adapter->pf_features & IXGBEVF_PF_SUP_ESX_MBX) {
 		hw->mbx.ops.init_params(hw);
 		memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
 		       sizeof(struct ixgbe_mbx_operations));
@@ -2654,6 +2680,7 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
 		case ixgbe_mbox_api_14:
 		case ixgbe_mbox_api_15:
 		case ixgbe_mbox_api_16:
+		case ixgbe_mbox_api_17:
 			if (adapter->xdp_prog &&
 			    hw->mac.max_tx_queues == rss)
 				rss = rss > 3 ? 2 : 1;
@@ -4649,6 +4676,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE -
 				  (ETH_HLEN + ETH_FCS_LEN);
 		break;
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h
index c1494fd1f67b..a8ed23ee66aa 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.h
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h
@@ -67,6 +67,7 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
 	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
 	ixgbe_mbox_api_16,      /* API version 1.6, linux/freebsd VF driver */
+	ixgbe_mbox_api_17,	/* API version 1.7, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -106,6 +107,9 @@ enum ixgbe_pfvf_api_rev {
 /* mailbox API, version 1.6 VF requests */
 #define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
 
+/* mailbox API, version 1.7 VF requests */
+#define IXGBE_VF_FEATURES_NEGOTIATE	0x12 /* get features supported by PF*/
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN	4
 /* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index f05246fb5a74..74d320879513 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -313,6 +313,7 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues)
 	 * is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
 	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
@@ -383,6 +384,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key)
 	 * or if the operation is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
 	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
@@ -555,6 +557,7 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode)
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -646,6 +649,7 @@ static int ixgbevf_get_pf_link_state(struct ixgbe_hw *hw, ixgbe_link_speed *spee
 
 	switch (hw->api_version) {
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -669,6 +673,42 @@ static int ixgbevf_get_pf_link_state(struct ixgbe_hw *hw, ixgbe_link_speed *spee
 	return err;
 }
 
+/**
+ * ixgbevf_negotiate_features_vf - negotiate supported features with PF driver
+ * @hw: pointer to the HW structure
+ * @pf_features: bitmask of features supported by PF
+ *
+ * Return: IXGBE_ERR_MBX in the  case of mailbox error,
+ * -EOPNOTSUPP if the op is not supported or 0 on success.
+ */
+static int ixgbevf_negotiate_features_vf(struct ixgbe_hw *hw, u32 *pf_features)
+{
+	u32 msgbuf[2] = {};
+	int err;
+
+	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	msgbuf[0] = IXGBE_VF_FEATURES_NEGOTIATE;
+	msgbuf[1] = IXGBEVF_SUPPORTED_FEATURES;
+
+	err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+					 ARRAY_SIZE(msgbuf));
+
+	if (err || (msgbuf[0] & IXGBE_VT_MSGTYPE_FAILURE)) {
+		err = IXGBE_ERR_MBX;
+		*pf_features = 0x0;
+	} else {
+		*pf_features = msgbuf[1];
+	}
+
+	return err;
+}
+
 /**
  *  ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address
  *  @hw: pointer to the HW structure
@@ -799,6 +839,7 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 				     bool *link_up,
 				     bool autoneg_wait_to_complete)
 {
+	struct ixgbevf_adapter *adapter = hw->back;
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 	struct ixgbe_mac_info *mac = &hw->mac;
 	s32 ret_val = 0;
@@ -825,7 +866,7 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	 * until we are called again and don't report an error
 	 */
 	if (mbx->ops.read(hw, &in_msg, 1)) {
-		if (hw->api_version >= ixgbe_mbox_api_15)
+		if (adapter->pf_features & IXGBEVF_PF_SUP_ESX_MBX)
 			mac->get_link_status = false;
 		goto out;
 	}
@@ -1026,6 +1067,7 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs,
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return 0;
@@ -1080,6 +1122,7 @@ static const struct ixgbe_mac_operations ixgbevf_mac_ops = {
 	.setup_link		= ixgbevf_setup_mac_link_vf,
 	.check_link		= ixgbevf_check_mac_link_vf,
 	.negotiate_api_version	= ixgbevf_negotiate_api_version_vf,
+	.negotiate_features	= ixgbevf_negotiate_features_vf,
 	.set_rar		= ixgbevf_set_rar_vf,
 	.update_mc_addr_list	= ixgbevf_update_mc_addr_list_vf,
 	.update_xcast_mode	= ixgbevf_update_xcast_mode,
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h
index 2d791bc26ae4..4f19b8900c29 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.h
@@ -26,6 +26,7 @@ struct ixgbe_mac_operations {
 	s32 (*stop_adapter)(struct ixgbe_hw *);
 	s32 (*get_bus_info)(struct ixgbe_hw *);
 	s32 (*negotiate_api_version)(struct ixgbe_hw *hw, int api);
+	int (*negotiate_features)(struct ixgbe_hw *hw, u32 *pf_features);
 
 	/* Link */
 	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool);

From 823be089f9c8ab136ba382b516aedd3f7ac854bd Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Thu, 9 Oct 2025 17:03:50 -0700
Subject: [PATCH 324/352] ixgbe: handle IXGBE_VF_FEATURES_NEGOTIATE mbox cmd

Send to VF information about features supported by the PF driver.

Increase API version to 1.7.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-5-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h  | 10 +++++
 .../net/ethernet/intel/ixgbe/ixgbe_sriov.c    | 37 +++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index f7256a339c99..0334ed4b8fa3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -52,6 +52,7 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
 	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
 	ixgbe_mbox_api_16,	/* API version 1.6, linux/freebsd VF driver */
+	ixgbe_mbox_api_17,	/* API version 1.7, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -91,6 +92,9 @@ enum ixgbe_pfvf_api_rev {
 /* mailbox API, version 1.6 VF requests */
 #define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
 
+/* mailbox API, version 1.7 VF requests */
+#define IXGBE_VF_FEATURES_NEGOTIATE	0x12 /* get features supported by PF */
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN 4
 /* word in permanent address message with the current multicast type */
@@ -101,6 +105,12 @@ enum ixgbe_pfvf_api_rev {
 #define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */
 #define IXGBE_VF_MBX_INIT_DELAY   500  /* microseconds between retries */
 
+/* features negotiated between PF/VF */
+#define IXGBEVF_PF_SUP_IPSEC		BIT(0)
+#define IXGBEVF_PF_SUP_ESX_MBX		BIT(1)
+
+#define IXGBE_SUPPORTED_FEATURES	IXGBEVF_PF_SUP_IPSEC
+
 struct ixgbe_hw;
 
 int ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index b09271d61a4e..ee133d6749b3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -511,6 +511,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf
 		case ixgbe_mbox_api_13:
 		case ixgbe_mbox_api_14:
 		case ixgbe_mbox_api_16:
+		case ixgbe_mbox_api_17:
 			/* Version 1.1 supports jumbo frames on VFs if PF has
 			 * jumbo frames enabled which means legacy VFs are
 			 * disabled
@@ -1048,6 +1049,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		adapter->vfinfo[vf].vf_api = api;
 		return 0;
 	default:
@@ -1075,6 +1077,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -1;
@@ -1115,6 +1118,7 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
 	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -1149,6 +1153,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
 	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -1180,6 +1185,7 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1251,6 +1257,7 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1278,6 +1285,7 @@ static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter,
 
 	switch (adapter->vfinfo[vf].vf_api) {
 	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		if (hw->mac.type != ixgbe_mac_e610)
 			return -EOPNOTSUPP;
 		break;
@@ -1293,6 +1301,32 @@ static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
+/**
+ * ixgbe_negotiate_vf_features -  negotiate supported features with VF driver
+ * @adapter: pointer to adapter struct
+ * @msgbuf: pointer to message buffers
+ * @vf: VF identifier
+ *
+ * Return: 0 on success or -EOPNOTSUPP when operation is not supported.
+ */
+static int ixgbe_negotiate_vf_features(struct ixgbe_adapter *adapter,
+				       u32 *msgbuf, u32 vf)
+{
+	u32 features = msgbuf[1];
+
+	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	features &= IXGBE_SUPPORTED_FEATURES;
+	msgbuf[1] = features;
+
+	return 0;
+}
+
 static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 {
 	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
@@ -1370,6 +1404,9 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 	case IXGBE_VF_GET_PF_LINK_STATE:
 		retval = ixgbe_send_vf_link_status(adapter, msgbuf, vf);
 		break;
+	case IXGBE_VF_FEATURES_NEGOTIATE:
+		retval = ixgbe_negotiate_vf_features(adapter, msgbuf, vf);
+		break;
 	default:
 		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
 		retval = -EIO;

From 5feef67b646d8f5064bac288e22204ffba2b9a4a Mon Sep 17 00:00:00 2001
From: Koichiro Den <den@valinux.co.jp>
Date: Thu, 9 Oct 2025 17:03:51 -0700
Subject: [PATCH 325/352] ixgbe: fix too early devlink_free() in ixgbe_remove()

Since ixgbe_adapter is embedded in devlink, calling devlink_free()
prematurely in the ixgbe_remove() path can lead to UAF. Move devlink_free()
to the end.

KASAN report:

 BUG: KASAN: use-after-free in ixgbe_reset_interrupt_capability+0x140/0x180 [ixgbe]
 Read of size 8 at addr ffff0000adf813e0 by task bash/2095
 CPU: 1 UID: 0 PID: 2095 Comm: bash Tainted: G S  6.17.0-rc2-tnguy.net-queue+ #1 PREEMPT(full)
 [...]
 Call trace:
  show_stack+0x30/0x90 (C)
  dump_stack_lvl+0x9c/0xd0
  print_address_description.constprop.0+0x90/0x310
  print_report+0x104/0x1f0
  kasan_report+0x88/0x180
  __asan_report_load8_noabort+0x20/0x30
  ixgbe_reset_interrupt_capability+0x140/0x180 [ixgbe]
  ixgbe_clear_interrupt_scheme+0xf8/0x130 [ixgbe]
  ixgbe_remove+0x2d0/0x8c0 [ixgbe]
  pci_device_remove+0xa0/0x220
  device_remove+0xb8/0x170
  device_release_driver_internal+0x318/0x490
  device_driver_detach+0x40/0x68
  unbind_store+0xec/0x118
  drv_attr_store+0x64/0xb8
  sysfs_kf_write+0xcc/0x138
  kernfs_fop_write_iter+0x294/0x440
  new_sync_write+0x1fc/0x588
  vfs_write+0x480/0x6a0
  ksys_write+0xf0/0x1e0
  __arm64_sys_write+0x70/0xc0
  invoke_syscall.constprop.0+0xcc/0x280
  el0_svc_common.constprop.0+0xa8/0x248
  do_el0_svc+0x44/0x68
  el0_svc+0x54/0x160
  el0t_64_sync_handler+0xa0/0xe8
  el0t_64_sync+0x1b0/0x1b8

Fixes: a0285236ab93 ("ixgbe: add initial devlink support")
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Tested-by: Rinitha S <sx.rinitha@intel.com>
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-6-ef32a425b92a@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 90d4e57b1c93..ca1ccc630001 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -12101,7 +12101,6 @@ static void ixgbe_remove(struct pci_dev *pdev)
 
 	devl_port_unregister(&adapter->devlink_port);
 	devl_unlock(adapter->devlink);
-	devlink_free(adapter->devlink);
 
 	ixgbe_stop_ipsec_offload(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
@@ -12137,6 +12136,8 @@ static void ixgbe_remove(struct pci_dev *pdev)
 
 	if (disable_dev)
 		pci_disable_device(pdev);
+
+	devlink_free(adapter->devlink);
 }
 
 /**

From 2c67301584f2671e320236df6bbe75ae09feb4d0 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut@mailbox.org>
Date: Sat, 11 Oct 2025 13:02:49 +0200
Subject: [PATCH 326/352] net: phy: realtek: Avoid PHYCR2 access if PHYCR2 not
 present

The driver is currently checking for PHYCR2 register presence in
rtl8211f_config_init(), but it does so after accessing PHYCR2 to
disable EEE. This was introduced in commit bfc17c165835 ("net:
phy: realtek: disable PHY-mode EEE"). Move the PHYCR2 presence
test before the EEE disablement and simplify the code.

Fixes: bfc17c165835 ("net: phy: realtek: disable PHY-mode EEE")
Signed-off-by: Marek Vasut <marek.vasut@mailbox.org>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20251011110309.12664-1-marek.vasut@mailbox.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/realtek_main.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 82d8e1335215..a724b21b4fe7 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -633,26 +633,25 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 			str_enabled_disabled(val_rxdly));
 	}
 
+	if (!priv->has_phycr2)
+		return 0;
+
 	/* Disable PHY-mode EEE so LPI is passed to the MAC */
 	ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2,
 			       RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0);
 	if (ret)
 		return ret;
 
-	if (priv->has_phycr2) {
-		ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE,
-				       RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN,
-				       priv->phycr2);
-		if (ret < 0) {
-			dev_err(dev, "clkout configuration failed: %pe\n",
-				ERR_PTR(ret));
-			return ret;
-		}
-
-		return genphy_soft_reset(phydev);
+	ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE,
+			       RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN,
+			       priv->phycr2);
+	if (ret < 0) {
+		dev_err(dev, "clkout configuration failed: %pe\n",
+			ERR_PTR(ret));
+		return ret;
 	}
 
-	return 0;
+	return genphy_soft_reset(phydev);
 }
 
 static int rtl821x_suspend(struct phy_device *phydev)

From c065b6046b3493a878c2ceb810aed845431badb4 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Mon, 13 Oct 2025 21:50:40 -0400
Subject: [PATCH 327/352] Use CONFIG_EXT4_FS instead of CONFIG_EXT3_FS in all
 of the defconfigs

Commit d6ace46c82fd ("ext4: remove obsolete EXT3 config options")
removed the obsolete EXT3_CONFIG options, since it had been over a
decade since fs/ext3 had been removed.  Unfortunately, there were a
number of defconfigs that still used CONFIG_EXT3_FS which the cleanup
commit didn't fix up.  This led to a large number of defconfig test
builds to fail.  Oops.

Fixes: d6ace46c82fd ("ext4: remove obsolete EXT3 config options")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 arch/arc/configs/axs101_defconfig           | 2 +-
 arch/arc/configs/axs103_defconfig           | 2 +-
 arch/arc/configs/axs103_smp_defconfig       | 2 +-
 arch/arc/configs/hsdk_defconfig             | 2 +-
 arch/arc/configs/vdk_hs38_defconfig         | 2 +-
 arch/arc/configs/vdk_hs38_smp_defconfig     | 2 +-
 arch/arm/configs/axm55xx_defconfig          | 2 +-
 arch/arm/configs/bcm2835_defconfig          | 4 ++--
 arch/arm/configs/davinci_all_defconfig      | 2 +-
 arch/arm/configs/dove_defconfig             | 4 ++--
 arch/arm/configs/ep93xx_defconfig           | 4 ++--
 arch/arm/configs/imx_v6_v7_defconfig        | 6 +++---
 arch/arm/configs/ixp4xx_defconfig           | 4 ++--
 arch/arm/configs/mmp2_defconfig             | 2 +-
 arch/arm/configs/moxart_defconfig           | 2 +-
 arch/arm/configs/multi_v5_defconfig         | 2 +-
 arch/arm/configs/mv78xx0_defconfig          | 4 ++--
 arch/arm/configs/mvebu_v5_defconfig         | 2 +-
 arch/arm/configs/nhk8815_defconfig          | 2 +-
 arch/arm/configs/omap1_defconfig            | 2 +-
 arch/arm/configs/omap2plus_defconfig        | 2 +-
 arch/arm/configs/orion5x_defconfig          | 4 ++--
 arch/arm/configs/pxa_defconfig              | 6 +++---
 arch/arm/configs/qcom_defconfig             | 2 +-
 arch/arm/configs/rpc_defconfig              | 2 +-
 arch/arm/configs/s3c6400_defconfig          | 6 +++---
 arch/arm/configs/sama7_defconfig            | 2 +-
 arch/arm/configs/socfpga_defconfig          | 2 +-
 arch/arm/configs/spear13xx_defconfig        | 4 ++--
 arch/arm/configs/spear3xx_defconfig         | 4 ++--
 arch/arm/configs/spear6xx_defconfig         | 4 ++--
 arch/arm/configs/spitz_defconfig            | 4 ++--
 arch/arm/configs/stm32_defconfig            | 2 +-
 arch/arm/configs/tegra_defconfig            | 6 +++---
 arch/arm/configs/u8500_defconfig            | 2 +-
 arch/arm/configs/vexpress_defconfig         | 2 +-
 arch/hexagon/configs/comet_defconfig        | 6 +++---
 arch/loongarch/configs/loongson3_defconfig  | 6 +++---
 arch/m68k/configs/stmark2_defconfig         | 6 +++---
 arch/microblaze/configs/mmu_defconfig       | 2 +-
 arch/mips/configs/bigsur_defconfig          | 6 +++---
 arch/mips/configs/cobalt_defconfig          | 6 +++---
 arch/mips/configs/decstation_64_defconfig   | 6 +++---
 arch/mips/configs/decstation_defconfig      | 6 +++---
 arch/mips/configs/decstation_r4k_defconfig  | 6 +++---
 arch/mips/configs/fuloong2e_defconfig       | 2 +-
 arch/mips/configs/ip22_defconfig            | 6 +++---
 arch/mips/configs/ip27_defconfig            | 6 +++---
 arch/mips/configs/ip28_defconfig            | 6 +++---
 arch/mips/configs/ip30_defconfig            | 6 +++---
 arch/mips/configs/ip32_defconfig            | 6 +++---
 arch/mips/configs/jazz_defconfig            | 2 +-
 arch/mips/configs/lemote2f_defconfig        | 6 +++---
 arch/mips/configs/loongson1b_defconfig      | 6 +++---
 arch/mips/configs/loongson1c_defconfig      | 6 +++---
 arch/mips/configs/loongson2k_defconfig      | 6 +++---
 arch/mips/configs/loongson3_defconfig       | 6 +++---
 arch/mips/configs/malta_defconfig           | 2 +-
 arch/mips/configs/malta_kvm_defconfig       | 2 +-
 arch/mips/configs/malta_qemu_32r6_defconfig | 2 +-
 arch/mips/configs/maltaaprp_defconfig       | 2 +-
 arch/mips/configs/maltasmvp_defconfig       | 6 +++---
 arch/mips/configs/maltasmvp_eva_defconfig   | 2 +-
 arch/mips/configs/maltaup_defconfig         | 2 +-
 arch/mips/configs/maltaup_xpa_defconfig     | 2 +-
 arch/mips/configs/mtx1_defconfig            | 6 +++---
 arch/mips/configs/rm200_defconfig           | 2 +-
 arch/openrisc/configs/or1klitex_defconfig   | 2 +-
 arch/openrisc/configs/virt_defconfig        | 4 ++--
 arch/parisc/configs/generic-32bit_defconfig | 4 ++--
 arch/parisc/configs/generic-64bit_defconfig | 4 ++--
 arch/sh/configs/ap325rxa_defconfig          | 6 +++---
 arch/sh/configs/apsh4a3a_defconfig          | 2 +-
 arch/sh/configs/apsh4ad0a_defconfig         | 2 +-
 arch/sh/configs/ecovec24_defconfig          | 6 +++---
 arch/sh/configs/edosk7760_defconfig         | 2 +-
 arch/sh/configs/espt_defconfig              | 2 +-
 arch/sh/configs/landisk_defconfig           | 2 +-
 arch/sh/configs/lboxre2_defconfig           | 2 +-
 arch/sh/configs/magicpanelr2_defconfig      | 4 ++--
 arch/sh/configs/r7780mp_defconfig           | 2 +-
 arch/sh/configs/r7785rp_defconfig           | 2 +-
 arch/sh/configs/rsk7264_defconfig           | 2 +-
 arch/sh/configs/rsk7269_defconfig           | 2 +-
 arch/sh/configs/sdk7780_defconfig           | 4 ++--
 arch/sh/configs/sdk7786_defconfig           | 2 +-
 arch/sh/configs/se7343_defconfig            | 2 +-
 arch/sh/configs/se7712_defconfig            | 2 +-
 arch/sh/configs/se7721_defconfig            | 2 +-
 arch/sh/configs/se7722_defconfig            | 2 +-
 arch/sh/configs/se7724_defconfig            | 6 +++---
 arch/sh/configs/sh03_defconfig              | 4 ++--
 arch/sh/configs/sh2007_defconfig            | 2 +-
 arch/sh/configs/sh7757lcr_defconfig         | 2 +-
 arch/sh/configs/sh7763rdp_defconfig         | 2 +-
 arch/sh/configs/sh7785lcr_32bit_defconfig   | 2 +-
 arch/sh/configs/sh7785lcr_defconfig         | 2 +-
 arch/sh/configs/shx3_defconfig              | 2 +-
 arch/sh/configs/titan_defconfig             | 4 ++--
 arch/sh/configs/ul2_defconfig               | 2 +-
 arch/sh/configs/urquell_defconfig           | 2 +-
 arch/sparc/configs/sparc64_defconfig        | 6 +++---
 arch/xtensa/configs/audio_kc705_defconfig   | 2 +-
 arch/xtensa/configs/cadence_csp_defconfig   | 2 +-
 arch/xtensa/configs/generic_kc705_defconfig | 2 +-
 arch/xtensa/configs/nommu_kc705_defconfig   | 2 +-
 arch/xtensa/configs/smp_lx200_defconfig     | 2 +-
 arch/xtensa/configs/virt_defconfig          | 2 +-
 arch/xtensa/configs/xip_kc705_defconfig     | 2 +-
 109 files changed, 182 insertions(+), 182 deletions(-)

diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index a7cd526dd7ca..f930396d9dae 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -88,7 +88,7 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index afa6a348f444..6b779dee5ea0 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -86,7 +86,7 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 2bfa6371953c..a89b50d5369d 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -88,7 +88,7 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 1558e8e87767..1b8b2a098cda 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -77,7 +77,7 @@ CONFIG_DMADEVICES=y
 CONFIG_DW_AXI_DMAC=y
 CONFIG_IIO=y
 CONFIG_TI_ADC108S102=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index 03d9ac20baa9..b7120523e09a 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -74,7 +74,7 @@ CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_SERIAL=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index c09488992f13..4077abd5980c 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -81,7 +81,7 @@ CONFIG_MMC_DW=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig
index 516689dc6cf1..9b263ea9a878 100644
--- a/arch/arm/configs/axm55xx_defconfig
+++ b/arch/arm/configs/axm55xx_defconfig
@@ -194,7 +194,7 @@ CONFIG_MAILBOX=y
 CONFIG_PL320_MBOX=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_AUTOFS_FS=y
diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig
index 27dc3bf6b124..4a8ac09843d7 100644
--- a/arch/arm/configs/bcm2835_defconfig
+++ b/arch/arm/configs/bcm2835_defconfig
@@ -154,8 +154,8 @@ CONFIG_PWM_BCM2835=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_FANOTIFY=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index e2ddaca0f89d..673408a10888 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -228,7 +228,7 @@ CONFIG_PWM=y
 CONFIG_PWM_TIECAP=m
 CONFIG_PWM_TIEHRPWM=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_XFS_FS=m
 CONFIG_AUTOFS_FS=m
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index d76eb12d29a7..bb6c4748bfc8 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -95,8 +95,8 @@ CONFIG_RTC_DRV_MV=y
 CONFIG_DMADEVICES=y
 CONFIG_MV_XOR=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig
index 2248afaf35b5..7f3756d8b086 100644
--- a/arch/arm/configs/ep93xx_defconfig
+++ b/arch/arm/configs/ep93xx_defconfig
@@ -103,8 +103,8 @@ CONFIG_RTC_DRV_EP93XX=y
 CONFIG_DMADEVICES=y
 CONFIG_EP93XX_DMA=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 9a57763a8d38..0d55056c6f82 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -436,9 +436,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_AUTOFS_FS=y
diff --git a/arch/arm/configs/ixp4xx_defconfig b/arch/arm/configs/ixp4xx_defconfig
index 3cb995b9616a..81199dddcde7 100644
--- a/arch/arm/configs/ixp4xx_defconfig
+++ b/arch/arm/configs/ixp4xx_defconfig
@@ -158,8 +158,8 @@ CONFIG_IXP4XX_NPE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_OVERLAY_FS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
diff --git a/arch/arm/configs/mmp2_defconfig b/arch/arm/configs/mmp2_defconfig
index 842a989baa27..f67e9cda73e2 100644
--- a/arch/arm/configs/mmp2_defconfig
+++ b/arch/arm/configs/mmp2_defconfig
@@ -53,7 +53,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MAX8925=y
 # CONFIG_RESET_CONTROLLER is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_MSDOS_FS=y
diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig
index fa06d98e43fc..e2d9f3610063 100644
--- a/arch/arm/configs/moxart_defconfig
+++ b/arch/arm/configs/moxart_defconfig
@@ -113,7 +113,7 @@ CONFIG_RTC_DRV_MOXART=y
 CONFIG_DMADEVICES=y
 CONFIG_MOXART_DMA=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index b523bc246c09..59b020e66a0b 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -268,7 +268,7 @@ CONFIG_PWM_ATMEL=m
 CONFIG_PWM_ATMEL_HLCDC_PWM=m
 CONFIG_PWM_ATMEL_TCB=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_UDF_FS=m
diff --git a/arch/arm/configs/mv78xx0_defconfig b/arch/arm/configs/mv78xx0_defconfig
index 3343f72de7ea..55f4ab67a306 100644
--- a/arch/arm/configs/mv78xx0_defconfig
+++ b/arch/arm/configs/mv78xx0_defconfig
@@ -91,8 +91,8 @@ CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_EXT4_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig
index 23dbb80fcc2e..d1742a7cae6a 100644
--- a/arch/arm/configs/mvebu_v5_defconfig
+++ b/arch/arm/configs/mvebu_v5_defconfig
@@ -168,7 +168,7 @@ CONFIG_MV_XOR=y
 CONFIG_STAGING=y
 CONFIG_FB_XGI=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_UDF_FS=m
diff --git a/arch/arm/configs/nhk8815_defconfig b/arch/arm/configs/nhk8815_defconfig
index ea28ed8991b4..696b4fbc2412 100644
--- a/arch/arm/configs/nhk8815_defconfig
+++ b/arch/arm/configs/nhk8815_defconfig
@@ -116,7 +116,7 @@ CONFIG_IIO_ST_ACCEL_3AXIS=y
 CONFIG_PWM=y
 CONFIG_PWM_STMPE=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FUSE_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 661e5d6894bd..24c54bf1e243 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -184,7 +184,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_OMAP=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 939913ed9a73..8f443c20872b 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -679,7 +679,7 @@ CONFIG_TWL4030_USB=m
 CONFIG_COUNTER=m
 CONFIG_TI_EQEP=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA=y
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index 62b9c6102789..c28426250ec3 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -115,8 +115,8 @@ CONFIG_RTC_DRV_M48T86=y
 CONFIG_DMADEVICES=y
 CONFIG_MV_XOR=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_EXT4_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 1a80602c1284..4b988a9e2768 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -580,9 +580,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig
index ec52ccece0ca..5a0513290547 100644
--- a/arch/arm/configs/qcom_defconfig
+++ b/arch/arm/configs/qcom_defconfig
@@ -295,7 +295,7 @@ CONFIG_INTERCONNECT_QCOM_MSM8974=m
 CONFIG_INTERCONNECT_QCOM_SDX55=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FUSE_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/rpc_defconfig b/arch/arm/configs/rpc_defconfig
index 24f1fa868230..46df453e224e 100644
--- a/arch/arm/configs/rpc_defconfig
+++ b/arch/arm/configs/rpc_defconfig
@@ -77,7 +77,7 @@ CONFIG_SOUND_VIDC=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PCF8583=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/arm/configs/s3c6400_defconfig b/arch/arm/configs/s3c6400_defconfig
index a37e6ac40825..4c635818973c 100644
--- a/arch/arm/configs/s3c6400_defconfig
+++ b/arch/arm/configs/s3c6400_defconfig
@@ -53,9 +53,9 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_S3C=y
 CONFIG_PWM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_CRAMFS=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index e14720a9a5ac..e2ad9a05566f 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -201,7 +201,7 @@ CONFIG_MCHP_EIC=y
 CONFIG_RESET_CONTROLLER=y
 CONFIG_NVMEM_MICROCHIP_OTPC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_VFAT_FS=y
diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig
index 294906c8f16e..f2e42846b116 100644
--- a/arch/arm/configs/socfpga_defconfig
+++ b/arch/arm/configs/socfpga_defconfig
@@ -136,7 +136,7 @@ CONFIG_FPGA_REGION=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/arm/configs/spear13xx_defconfig b/arch/arm/configs/spear13xx_defconfig
index a8f992fdb30d..8b19af1ea67c 100644
--- a/arch/arm/configs/spear13xx_defconfig
+++ b/arch/arm/configs/spear13xx_defconfig
@@ -84,8 +84,8 @@ CONFIG_DMATEST=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_MSDOS_FS=m
diff --git a/arch/arm/configs/spear3xx_defconfig b/arch/arm/configs/spear3xx_defconfig
index 8dc5a388759c..b4e4b96a98af 100644
--- a/arch/arm/configs/spear3xx_defconfig
+++ b/arch/arm/configs/spear3xx_defconfig
@@ -67,8 +67,8 @@ CONFIG_DMATEST=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
diff --git a/arch/arm/configs/spear6xx_defconfig b/arch/arm/configs/spear6xx_defconfig
index 4e9e1a6ff381..7083b1bd8573 100644
--- a/arch/arm/configs/spear6xx_defconfig
+++ b/arch/arm/configs/spear6xx_defconfig
@@ -53,8 +53,8 @@ CONFIG_DMATEST=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index ac2a0f998c73..395df2f9dc8e 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -193,8 +193,8 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index dcd9c316072e..82190b155b14 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -69,7 +69,7 @@ CONFIG_STM32_MDMA=y
 CONFIG_IIO=y
 CONFIG_STM32_ADC_CORE=y
 CONFIG_STM32_ADC=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_FILE_LOCKING is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index ba863b445417..ab477ca13f89 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -319,9 +319,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index 0f55815eecb3..f3bc967a0f25 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -175,7 +175,7 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig
index cdb6065e04fd..b9454f6954f8 100644
--- a/arch/arm/configs/vexpress_defconfig
+++ b/arch/arm/configs/vexpress_defconfig
@@ -120,7 +120,7 @@ CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig
index c6108f000288..b132752693a9 100644
--- a/arch/hexagon/configs/comet_defconfig
+++ b/arch/hexagon/configs/comet_defconfig
@@ -46,10 +46,10 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 34eaee0384c9..f3e2c588e5df 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -929,9 +929,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig
index 7787a4dd7c3c..f3268fed02fc 100644
--- a/arch/m68k/configs/stmark2_defconfig
+++ b/arch/m68k/configs/stmark2_defconfig
@@ -72,9 +72,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_FILE_LOCKING is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 176314f3c9aa..fbbdcb394ca2 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -73,7 +73,7 @@ CONFIG_FB_XILINX=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=y
 CONFIG_UIO_DMEM_GENIRQ=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index 97d2cd997285..349e9e0b4f54 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -144,9 +144,9 @@ CONFIG_EXT2_FS=m
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=m
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=m
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_QUOTA=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
diff --git a/arch/mips/configs/cobalt_defconfig b/arch/mips/configs/cobalt_defconfig
index b0b551efac7c..6ee9ee391fdc 100644
--- a/arch/mips/configs/cobalt_defconfig
+++ b/arch/mips/configs/cobalt_defconfig
@@ -59,9 +59,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
diff --git a/arch/mips/configs/decstation_64_defconfig b/arch/mips/configs/decstation_64_defconfig
index 85a4472cb058..52a63dd7aac7 100644
--- a/arch/mips/configs/decstation_64_defconfig
+++ b/arch/mips/configs/decstation_64_defconfig
@@ -133,9 +133,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig
index a3b2c8da2dde..59fb7ee5eeb0 100644
--- a/arch/mips/configs/decstation_defconfig
+++ b/arch/mips/configs/decstation_defconfig
@@ -129,9 +129,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig
index a476717b8a6a..8be1cb433e95 100644
--- a/arch/mips/configs/decstation_r4k_defconfig
+++ b/arch/mips/configs/decstation_r4k_defconfig
@@ -129,9 +129,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index cdedbb8a8f53..b6fe3c962464 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -173,7 +173,7 @@ CONFIG_USB_ISIGHTFW=m
 CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=y
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index 2decf8b98d31..e123848f94ab 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -232,9 +232,9 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1286=y
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_QUOTA=y
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index 5d079941fd20..1c10242b148b 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -272,9 +272,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/ip28_defconfig b/arch/mips/configs/ip28_defconfig
index 6db21e498faa..755cbf20f5a5 100644
--- a/arch/mips/configs/ip28_defconfig
+++ b/arch/mips/configs/ip28_defconfig
@@ -49,9 +49,9 @@ CONFIG_WATCHDOG=y
 CONFIG_INDYDOG=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_PROC_KCORE=y
 # CONFIG_PROC_PAGE_MONITOR is not set
diff --git a/arch/mips/configs/ip30_defconfig b/arch/mips/configs/ip30_defconfig
index a4524e785469..718f3060d9fa 100644
--- a/arch/mips/configs/ip30_defconfig
+++ b/arch/mips/configs/ip30_defconfig
@@ -143,9 +143,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig
index d8ac11427f69..7568838eb08b 100644
--- a/arch/mips/configs/ip32_defconfig
+++ b/arch/mips/configs/ip32_defconfig
@@ -89,9 +89,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig
index 65adb538030d..a790c2610fd3 100644
--- a/arch/mips/configs/jazz_defconfig
+++ b/arch/mips/configs/jazz_defconfig
@@ -69,7 +69,7 @@ CONFIG_FB_G364=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 # CONFIG_HWMON is not set
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 5038a27d035f..8d3f20ed19b5 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -226,9 +226,9 @@ CONFIG_MMC=m
 CONFIG_LEDS_CLASS=y
 CONFIG_STAGING=y
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_XFS_FS=m
diff --git a/arch/mips/configs/loongson1b_defconfig b/arch/mips/configs/loongson1b_defconfig
index 68207b31dc20..a64a39447963 100644
--- a/arch/mips/configs/loongson1b_defconfig
+++ b/arch/mips/configs/loongson1b_defconfig
@@ -94,9 +94,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/loongson1c_defconfig b/arch/mips/configs/loongson1c_defconfig
index c3910a9dee9e..86d7f64a164a 100644
--- a/arch/mips/configs/loongson1c_defconfig
+++ b/arch/mips/configs/loongson1c_defconfig
@@ -95,9 +95,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/loongson2k_defconfig b/arch/mips/configs/loongson2k_defconfig
index 0cc665d3ea34..aec1fd1902eb 100644
--- a/arch/mips/configs/loongson2k_defconfig
+++ b/arch/mips/configs/loongson2k_defconfig
@@ -298,9 +298,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 240efff37d98..575aaf242361 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -348,9 +348,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_POSIX_ACL=y
 CONFIG_QUOTA=y
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 9fcbac829920..81704ec67f09 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -313,7 +313,7 @@ CONFIG_RTC_DRV_CMOS=y
 CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 19102386a81c..82a97f58bce1 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -319,7 +319,7 @@ CONFIG_RTC_DRV_CMOS=y
 CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 1b98f6945c2d..accb471a1d93 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -148,7 +148,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index 7b8905cb3400..6bda67c5f68f 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -149,7 +149,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index 8249f6a51895..e4082537f80f 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -148,9 +148,9 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 21cb37668763..58f5af45fa98 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -152,7 +152,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 3df9cd669683..9bfef7de0d1c 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -148,7 +148,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 1dd07c9d1812..0f9ef20744f9 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -319,7 +319,7 @@ CONFIG_RTC_DRV_CMOS=y
 CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index e4bcdb64df6c..b4dc2255a81c 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -594,9 +594,9 @@ CONFIG_EXT2_FS=m
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=m
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=m
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=m
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 39a2419e1f3e..b507dc4dddd4 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -307,7 +307,7 @@ CONFIG_USB_SISUSBVGA=m
 CONFIG_USB_LD=m
 CONFIG_USB_TEST=m
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/openrisc/configs/or1klitex_defconfig b/arch/openrisc/configs/or1klitex_defconfig
index 3e849d25838a..fb1eb9a68bd6 100644
--- a/arch/openrisc/configs/or1klitex_defconfig
+++ b/arch/openrisc/configs/or1klitex_defconfig
@@ -38,7 +38,7 @@ CONFIG_MMC_LITEX=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_LITEX_SOC_CONTROLLER=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_EXFAT_FS=y
diff --git a/arch/openrisc/configs/virt_defconfig b/arch/openrisc/configs/virt_defconfig
index c1b69166c500..01d685f3fb17 100644
--- a/arch/openrisc/configs/virt_defconfig
+++ b/arch/openrisc/configs/virt_defconfig
@@ -94,8 +94,8 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 # CONFIG_DNOTIFY is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index 94928d114d4c..52031bde9f17 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -232,8 +232,8 @@ CONFIG_AUXDISPLAY=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_QFMT_V2=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index d8cd7f858b2a..1aec04c09d0b 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -251,8 +251,8 @@ CONFIG_STAGING=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_BTRFS_FS=m
 CONFIG_QUOTA=y
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index b6f36c938f1d..336dbacd89bd 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -81,10 +81,10 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/apsh4a3a_defconfig b/arch/sh/configs/apsh4a3a_defconfig
index 9c2644443c4d..59daf99ea745 100644
--- a/arch/sh/configs/apsh4a3a_defconfig
+++ b/arch/sh/configs/apsh4a3a_defconfig
@@ -60,7 +60,7 @@ CONFIG_FONT_8x16=y
 CONFIG_LOGO=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
index 137573610ec4..df2a669ea9d8 100644
--- a/arch/sh/configs/apsh4ad0a_defconfig
+++ b/arch/sh/configs/apsh4ad0a_defconfig
@@ -88,7 +88,7 @@ CONFIG_USB_MON=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
index e76694aace25..dd7e54c451d6 100644
--- a/arch/sh/configs/ecovec24_defconfig
+++ b/arch/sh/configs/ecovec24_defconfig
@@ -109,10 +109,10 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig
index f427a95bcd21..711db47b65ba 100644
--- a/arch/sh/configs/edosk7760_defconfig
+++ b/arch/sh/configs/edosk7760_defconfig
@@ -87,7 +87,7 @@ CONFIG_SND_SOC=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index da176f100e00..f8cad1e7a333 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -59,7 +59,7 @@ CONFIG_USB_MON=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_AUTOFS_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index 924bb3233b0b..08342ceee32e 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -93,7 +93,7 @@ CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
 CONFIG_USB_SISUSBVGA=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_ISO9660_FS=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 0307bb2be79f..96a21173522d 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -49,7 +49,7 @@ CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_RTC_CLASS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/magicpanelr2_defconfig b/arch/sh/configs/magicpanelr2_defconfig
index 93b9aa32dc7c..af7f777b20be 100644
--- a/arch/sh/configs/magicpanelr2_defconfig
+++ b/arch/sh/configs/magicpanelr2_defconfig
@@ -64,9 +64,9 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+# CONFIG_EXT4_FS_XATTR is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index f28b8c4181c2..11f210517f76 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -74,7 +74,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_FUSE_FS=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index 3a4239f20ff1..ae367d7a14a8 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -69,7 +69,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_FUSE_FS=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/rsk7264_defconfig b/arch/sh/configs/rsk7264_defconfig
index e4ef259425c4..3aba0102304f 100644
--- a/arch/sh/configs/rsk7264_defconfig
+++ b/arch/sh/configs/rsk7264_defconfig
@@ -59,7 +59,7 @@ CONFIG_USB_R8A66597_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_STORAGE_DEBUG=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_NFS_FS=y
diff --git a/arch/sh/configs/rsk7269_defconfig b/arch/sh/configs/rsk7269_defconfig
index e0d1560b2bfd..f82f280fc55a 100644
--- a/arch/sh/configs/rsk7269_defconfig
+++ b/arch/sh/configs/rsk7269_defconfig
@@ -43,7 +43,7 @@ CONFIG_USB_R8A66597_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_STORAGE_DEBUG=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_NFS_FS=y
diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig
index 9870d16d9711..3b51195bf1b5 100644
--- a/arch/sh/configs/sdk7780_defconfig
+++ b/arch/sh/configs/sdk7780_defconfig
@@ -102,9 +102,9 @@ CONFIG_LEDS_CLASS=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index 07894f13441e..ebb3f4420ae8 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -161,7 +161,7 @@ CONFIG_STAGING=y
 # CONFIG_STAGING_EXCLUDE_BUILD is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index 75db12fb9ad1..6ef546ee8a32 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -84,7 +84,7 @@ CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_ISP116X_HCD=y
 CONFIG_UIO=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_JFFS2_FS=y
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index 8770a72e6a63..4cecf9c06a65 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -83,7 +83,7 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_JFFS2_FS=y
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index b15c6406a0e8..c28057b70ad7 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -107,7 +107,7 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/se7722_defconfig b/arch/sh/configs/se7722_defconfig
index 5327a2f70980..88bfd953ef89 100644
--- a/arch/sh/configs/se7722_defconfig
+++ b/arch/sh/configs/se7722_defconfig
@@ -44,7 +44,7 @@ CONFIG_HW_RANDOM=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig
index 9501e69eb886..e1b2616ef921 100644
--- a/arch/sh/configs/se7724_defconfig
+++ b/arch/sh/configs/se7724_defconfig
@@ -110,10 +110,10 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 4d75c92cac10..306e1661fbf5 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -57,9 +57,9 @@ CONFIG_WATCHDOG=y
 CONFIG_SH_WDT=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig
index cc6292b3235a..889daa5d2faa 100644
--- a/arch/sh/configs/sh2007_defconfig
+++ b/arch/sh/configs/sh2007_defconfig
@@ -95,7 +95,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_DMADEVICES=y
 CONFIG_TIMB_DMA=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig
index 48a0f9beb116..25e9d22779b3 100644
--- a/arch/sh/configs/sh7757lcr_defconfig
+++ b/arch/sh/configs/sh7757lcr_defconfig
@@ -64,7 +64,7 @@ CONFIG_MMC=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_SH_MMCIF=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index b77b3313157e..85ec00b7dbd2 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -61,7 +61,7 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_AUTOFS_FS=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig
index 44f9b2317f09..e860a20d3f0f 100644
--- a/arch/sh/configs/sh7785lcr_32bit_defconfig
+++ b/arch/sh/configs/sh7785lcr_32bit_defconfig
@@ -113,7 +113,7 @@ CONFIG_RTC_DRV_RS5C372=y
 CONFIG_DMADEVICES=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/sh7785lcr_defconfig b/arch/sh/configs/sh7785lcr_defconfig
index aec74b0e7003..33c98b4a2adb 100644
--- a/arch/sh/configs/sh7785lcr_defconfig
+++ b/arch/sh/configs/sh7785lcr_defconfig
@@ -90,7 +90,7 @@ CONFIG_USB_TEST=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
index 9a0df5ea3866..3169e4dc7004 100644
--- a/arch/sh/configs/shx3_defconfig
+++ b/arch/sh/configs/shx3_defconfig
@@ -84,7 +84,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 8ef72b8dbcd3..6bff00038072 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -215,9 +215,9 @@ CONFIG_USB_SERIAL_PL2303=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+# CONFIG_EXT4_FS_XATTR is not set
 CONFIG_XFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_ISO9660_FS=m
diff --git a/arch/sh/configs/ul2_defconfig b/arch/sh/configs/ul2_defconfig
index 103b81ec1ffb..b89eb8f5cc5c 100644
--- a/arch/sh/configs/ul2_defconfig
+++ b/arch/sh/configs/ul2_defconfig
@@ -66,7 +66,7 @@ CONFIG_USB_R8A66597_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
index 00ef62133b04..60cb716ef195 100644
--- a/arch/sh/configs/urquell_defconfig
+++ b/arch/sh/configs/urquell_defconfig
@@ -114,7 +114,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_RTC_DRV_GENERIC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_BTRFS_FS=y
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 7a7c4dec2925..200640b93e05 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -187,10 +187,10 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index f2af1a32c9c7..dc942bbac69f 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -103,7 +103,7 @@ CONFIG_SND_SIMPLE_CARD=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_COMMON_CLK_CDCE706=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index 88ed5284e21c..81a057f25f21 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -80,7 +80,7 @@ CONFIG_SOFT_WATCHDOG=y
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index 4427907becca..3ee7e1c56556 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -90,7 +90,7 @@ CONFIG_SOFT_WATCHDOG=y
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index 5828228522ba..c6e96f0aa700 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -91,7 +91,7 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=y
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 326966ca7831..373d42b9e510 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -94,7 +94,7 @@ CONFIG_SOFT_WATCHDOG=y
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/xtensa/configs/virt_defconfig b/arch/xtensa/configs/virt_defconfig
index e37048985b47..72628d31e87a 100644
--- a/arch/xtensa/configs/virt_defconfig
+++ b/arch/xtensa/configs/virt_defconfig
@@ -76,7 +76,7 @@ CONFIG_LOGO=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_INPUT=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/xtensa/configs/xip_kc705_defconfig b/arch/xtensa/configs/xip_kc705_defconfig
index ee47438f9b51..5d6013ea70fc 100644
--- a/arch/xtensa/configs/xip_kc705_defconfig
+++ b/arch/xtensa/configs/xip_kc705_defconfig
@@ -82,7 +82,7 @@ CONFIG_SOFT_WATCHDOG=y
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y

From 2616222e423398bb374ffcb5d23dea4ba2c3e524 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 10 Oct 2025 12:21:42 +0530
Subject: [PATCH 328/352] amd-xgbe: Avoid spurious link down messages during
 interface toggle

During interface toggle operations (ifdown/ifup), the driver currently
resets the local helper variable 'phy_link' to -1. This causes the link
state machine to incorrectly interpret the state as a link change event,
resulting in spurious "Link is down" messages being logged when the
interface is brought back up.

Preserve the phy_link state across interface toggles to avoid treating
the -1 sentinel value as a legitimate link state transition.

Fixes: 88131a812b16 ("amd-xgbe: Perform phy connect/disconnect at dev open/stop")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Link: https://patch.msgid.link/20251010065142.1189310-1-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c  | 1 -
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index f0989aa01855..4dc631af7933 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1080,7 +1080,6 @@ static void xgbe_free_rx_data(struct xgbe_prv_data *pdata)
 
 static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
 {
-	pdata->phy_link = -1;
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return pdata->phy_if.phy_reset(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 1a37ec45e650..7675bb98f029 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1555,6 +1555,7 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		pdata->phy.duplex = DUPLEX_FULL;
 	}
 
+	pdata->phy_link = 0;
 	pdata->phy.link = 0;
 
 	pdata->phy.pause_autoneg = pdata->pause_autoneg;

From c5705a2a4aa35350e504b72a94b5c71c3754833c Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Fri, 10 Oct 2025 13:42:39 -0700
Subject: [PATCH 329/352] Octeontx2-af: Fix missing error code in cgx_probe()

When CGX fails mapping to NIX, set the error code to -ENODEV, currently
err is zero and that is treated as success path.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/aLAdlCg2_Yv7Y-3h@stanley.mountain/
Fixes: d280233fc866 ("Octeontx2-af: Fix NIX X2P calibration failures")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251010204239.94237-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index d374a4454836..ec0e11c77cbf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1981,6 +1981,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	    !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);
+		err = -ENODEV;
 		goto err_release_regions;
 	}
 

From 327cd4b68b4398b6c24f10eb2b2533ffbfc10185 Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@linux.dev>
Date: Sat, 11 Oct 2025 15:05:18 +0800
Subject: [PATCH 330/352] usbnet: Fix using smp_processor_id() in preemptible
 code warnings

Syzbot reported the following warning:

BUG: using smp_processor_id() in preemptible [00000000] code: dhcpcd/2879
caller is usbnet_skb_return+0x74/0x490 drivers/net/usb/usbnet.c:331
CPU: 1 UID: 0 PID: 2879 Comm: dhcpcd Not tainted 6.15.0-rc4-syzkaller-00098-g615dca38c2ea #0 PREEMPT(voluntary)
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x16c/0x1f0 lib/dump_stack.c:120
 check_preemption_disabled+0xd0/0xe0 lib/smp_processor_id.c:49
 usbnet_skb_return+0x74/0x490 drivers/net/usb/usbnet.c:331
 usbnet_resume_rx+0x4b/0x170 drivers/net/usb/usbnet.c:708
 usbnet_change_mtu+0x1be/0x220 drivers/net/usb/usbnet.c:417
 __dev_set_mtu net/core/dev.c:9443 [inline]
 netif_set_mtu_ext+0x369/0x5c0 net/core/dev.c:9496
 netif_set_mtu+0xb0/0x160 net/core/dev.c:9520
 dev_set_mtu+0xae/0x170 net/core/dev_api.c:247
 dev_ifsioc+0xa31/0x18d0 net/core/dev_ioctl.c:572
 dev_ioctl+0x223/0x10e0 net/core/dev_ioctl.c:821
 sock_do_ioctl+0x19d/0x280 net/socket.c:1204
 sock_ioctl+0x42f/0x6a0 net/socket.c:1311
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:906 [inline]
 __se_sys_ioctl fs/ioctl.c:892 [inline]
 __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xcd/0x260 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

For historical and portability reasons, the netif_rx() is usually
run in the softirq or interrupt context, this commit therefore add
local_bh_disable/enable() protection in the usbnet_resume_rx().

Fixes: 43daa96b166c ("usbnet: Stop RX Q on MTU change")
Link: https://syzkaller.appspot.com/bug?id=81f55dfa587ee544baaaa5a359a060512228c1e1
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Zqiang <qiang.zhang@linux.dev>
Link: https://patch.msgid.link/20251011070518.7095-1-qiang.zhang@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/usbnet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 511c4154cf74..bf01f2728531 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -702,6 +702,7 @@ void usbnet_resume_rx(struct usbnet *dev)
 	struct sk_buff *skb;
 	int num = 0;
 
+	local_bh_disable();
 	clear_bit(EVENT_RX_PAUSED, &dev->flags);
 
 	while ((skb = skb_dequeue(&dev->rxq_pause)) != NULL) {
@@ -710,6 +711,7 @@ void usbnet_resume_rx(struct usbnet *dev)
 	}
 
 	queue_work(system_bh_wq, &dev->bh_work);
+	local_bh_enable();
 
 	netif_dbg(dev, rx_status, dev->net,
 		  "paused rx queue disabled, %d skbs requeued\n", num);

From 75527d61d60d493d1eb064f335071a20ca581f54 Mon Sep 17 00:00:00 2001
From: Yi Cong <yicong@kylinos.cn>
Date: Sat, 11 Oct 2025 16:24:15 +0800
Subject: [PATCH 331/352] r8152: add error handling in rtl8152_driver_init

rtl8152_driver_init() is missing the error handling.
When rtl8152_driver registration fails, rtl8152_cfgselector_driver
should be deregistered.

Fixes: ec51fbd1b8a2 ("r8152: add USB device driver for config selection")
Cc: stable@vger.kernel.org
Signed-off-by: Yi Cong <yicong@kylinos.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251011082415.580740-1-yicongsrfy@163.com
[pabeni@redhat.com: clarified the commit message]
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/r8152.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 44cba7acfe7d..a22d4bb2cf3b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10122,7 +10122,12 @@ static int __init rtl8152_driver_init(void)
 	ret = usb_register_device_driver(&rtl8152_cfgselector_driver, THIS_MODULE);
 	if (ret)
 		return ret;
-	return usb_register(&rtl8152_driver);
+
+	ret = usb_register(&rtl8152_driver);
+	if (ret)
+		usb_deregister_device_driver(&rtl8152_cfgselector_driver);
+
+	return ret;
 }
 
 static void __exit rtl8152_driver_exit(void)

From 295ce1eb36ae47dc862d6c8a1012618a25516208 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 11 Oct 2025 11:57:42 +0000
Subject: [PATCH 332/352] tcp: fix tcp_tso_should_defer() vs large RTT

Neal reported that using neper tcp_stream with TCP_TX_DELAY
set to 50ms would often lead to flows stuck in a small cwnd mode,
regardless of the congestion control.

While tcp_stream sets TCP_TX_DELAY too late after the connect(),
it highlighted two kernel bugs.

The following heuristic in tcp_tso_should_defer() seems wrong
for large RTT:

delta = tp->tcp_clock_cache - head->tstamp;
/* If next ACK is likely to come too late (half srtt), do not defer */
if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
      goto send_now;

If next ACK is expected to come in more than 1 ms, we should
not defer because we prefer a smooth ACK clocking.

While blamed commit was a step in the good direction, it was not
generic enough.

Another patch fixing TCP_TX_DELAY for established flows
will be proposed when net-next reopens.

Fixes: 50c8339e9299 ("tcp: tso: restore IW10 after TSO autosizing")
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20251011115742.1245771-1-edumazet@google.com
[pabeni@redhat.com: fixed whitespace issue]
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/tcp_output.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bb3576ac0ad7..b94efb3050d2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2369,7 +2369,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight, threshold;
+	u64 srtt_in_ns, expected_ack, how_far_is_the_ack;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;
@@ -2431,9 +2432,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	delta = tp->tcp_clock_cache - head->tstamp;
-	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
+
+	srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us;
+	/* When is the ACK expected ? */
+	expected_ack = head->tstamp + srtt_in_ns;
+	/* How far from now is the ACK expected ? */
+	how_far_is_the_ack = expected_ack - tp->tcp_clock_cache;
+
+	/* If next ACK is likely to come too late,
+	 * ie in more than min(1ms, half srtt), do not defer.
+	 */
+	threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC);
+
+	if ((s64)(how_far_is_the_ack - threshold) > 0)
 		goto send_now;
 
 	/* Ok, it looks like it is advisable to defer.

From bd5afca115f181c85f992d42a57cd497bc823ccb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sun, 12 Oct 2025 11:19:44 +0200
Subject: [PATCH 333/352] net: airoha: Take into account out-of-order tx
 completions in airoha_dev_xmit()

Completion napi can free out-of-order tx descriptors if hw QoS is
enabled and packets with different priority are queued to same DMA ring.
Take into account possible out-of-order reports checking if the tx queue
is full using circular buffer head/tail pointer instead of the number of
queued packets.

Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC")
Suggested-by: Simon Horman <horms@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251012-airoha-tx-busy-queue-v2-1-a600b08bab2d@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 833dd911980b..433a646e9831 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1873,6 +1873,20 @@ static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
 #endif
 }
 
+static bool airoha_dev_tx_queue_busy(struct airoha_queue *q, u32 nr_frags)
+{
+	u32 tail = q->tail <= q->head ? q->tail + q->ndesc : q->tail;
+	u32 index = q->head + nr_frags;
+
+	/* completion napi can free out-of-order tx descriptors if hw QoS is
+	 * enabled and packets with different priorities are queued to the same
+	 * DMA ring. Take into account possible out-of-order reports checking
+	 * if the tx queue is full using circular buffer head/tail pointers
+	 * instead of the number of queued packets.
+	 */
+	return index >= tail;
+}
+
 static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
@@ -1926,7 +1940,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	txq = netdev_get_tx_queue(dev, qid);
 	nr_frags = 1 + skb_shinfo(skb)->nr_frags;
 
-	if (q->queued + nr_frags > q->ndesc) {
+	if (airoha_dev_tx_queue_busy(q, nr_frags)) {
 		/* not enough space in the queue */
 		netif_tx_stop_queue(txq);
 		spin_unlock_bh(&q->lock);

From 4f86eb0a38bc719ba966f155071a6f0594327f34 Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Mon, 13 Oct 2025 16:00:39 +0800
Subject: [PATCH 334/352] selftests: net: check jq command is supported

The jq command is used in vlan_bridge_binding.sh, if it is not supported,
the test will spam the following log.

  # ./vlan_bridge_binding.sh: line 51: jq: command not found
  # ./vlan_bridge_binding.sh: line 51: jq: command not found
  # ./vlan_bridge_binding.sh: line 51: jq: command not found
  # ./vlan_bridge_binding.sh: line 51: jq: command not found
  # ./vlan_bridge_binding.sh: line 51: jq: command not found
  # TEST: Test bridge_binding on->off when lower down                   [FAIL]
  #       Got operstate of , expected 0

The rtnetlink.sh has the same problem. It makes sense to check if jq is
installed before running these tests. After this patch, the
vlan_bridge_binding.sh skipped if jq is not supported:

  # timeout set to 3600
  # selftests: net: vlan_bridge_binding.sh
  # TEST: jq not installed                                              [SKIP]

Fixes: dca12e9ab760 ("selftests: net: Add a VLAN bridge binding selftest")
Fixes: 6a414fd77f61 ("selftests: rtnetlink: Add an address proto test")
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20251013080039.3035898-1-wangliang74@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/rtnetlink.sh           | 2 ++
 tools/testing/selftests/net/vlan_bridge_binding.sh | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index dbf77513f617..163a084d525d 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1466,6 +1466,8 @@ usage: ${0##*/} OPTS
 EOF
 }
 
+require_command jq
+
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
 	end_test "SKIP: Need root privileges"
diff --git a/tools/testing/selftests/net/vlan_bridge_binding.sh b/tools/testing/selftests/net/vlan_bridge_binding.sh
index db481af9b6b3..e8c02c64e03a 100755
--- a/tools/testing/selftests/net/vlan_bridge_binding.sh
+++ b/tools/testing/selftests/net/vlan_bridge_binding.sh
@@ -249,6 +249,8 @@ test_binding_toggle_off_when_upper_down()
 	do_test_binding_off : "on->off when upper down"
 }
 
+require_command jq
+
 trap defer_scopes_cleanup EXIT
 setup_prepare
 tests_run

From df5a1f4aeb6ff5e7c5ac47d16a347f03509dd441 Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Mon, 13 Oct 2025 20:03:47 +0200
Subject: [PATCH 335/352] MAINTAINERS: add myself as maintainer for b53

I wrote the original OpenWrt driver that Florian used as the base for
the dsa driver, I might as well take responsibility for it.

Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20251013180347.133246-1-jonas.gorski@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3a27901781c2..8a213950e37e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4804,6 +4804,7 @@ F:	drivers/net/ethernet/broadcom/b44.*
 
 BROADCOM B53/SF2 ETHERNET SWITCH DRIVER
 M:	Florian Fainelli <florian.fainelli@broadcom.com>
+M:	Jonas Gorski <jonas.gorski@gmail.com>
 L:	netdev@vger.kernel.org
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Supported

From 7f0fddd817ba6daebea1445ae9fab4b6d2294fa8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Oct 2025 20:50:52 +0200
Subject: [PATCH 336/352] net: core: fix lockdep splat on device unregister

Since blamed commit, unregister_netdevice_many_notify() takes the netdev
mutex if the device needs it.

If the device list is too long, this will lock more device mutexes than
lockdep can handle:

unshare -n \
 bash -c 'for i in $(seq 1 100);do ip link add foo$i type dummy;done'

BUG: MAX_LOCK_DEPTH too low!
turning off the locking correctness validator.
depth: 48  max: 48!
48 locks held by kworker/u16:1/69:
 #0: ..148 ((wq_completion)netns){+.+.}-{0:0}, at: process_one_work
 #1: ..d40 (net_cleanup_work){+.+.}-{0:0}, at: process_one_work
 #2: ..bd0 (pernet_ops_rwsem){++++}-{4:4}, at: cleanup_net
 #3: ..aa8 (rtnl_mutex){+.+.}-{4:4}, at: default_device_exit_batch
 #4: ..cb0 (&dev_instance_lock_key#3){+.+.}-{4:4}, at: unregister_netdevice_many_notify
[..]

Add a helper to close and then unlock a list of net_devices.
Devices that are not up have to be skipped - netif_close_many always
removes them from the list without any other actions taken, so they'd
remain in locked state.

Close devices whenever we've used up half of the tracking slots or we
processed entire list without hitting the limit.

Fixes: 7e4d784f5810 ("net: hold netdev instance lock during rtnetlink operations")
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20251013185052.14021-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 40 +++++++++++++++++++++++++++++++++++-----
 1 file changed, 35 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index a64cef2c537e..2acfa44927da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12176,6 +12176,35 @@ static void dev_memory_provider_uninstall(struct net_device *dev)
 	}
 }
 
+/* devices must be UP and netdev_lock()'d */
+static void netif_close_many_and_unlock(struct list_head *close_head)
+{
+	struct net_device *dev, *tmp;
+
+	netif_close_many(close_head, false);
+
+	/* ... now unlock them */
+	list_for_each_entry_safe(dev, tmp, close_head, close_list) {
+		netdev_unlock(dev);
+		list_del_init(&dev->close_list);
+	}
+}
+
+static void netif_close_many_and_unlock_cond(struct list_head *close_head)
+{
+#ifdef CONFIG_LOCKDEP
+	/* We can only track up to MAX_LOCK_DEPTH locks per task.
+	 *
+	 * Reserve half the available slots for additional locks possibly
+	 * taken by notifiers and (soft)irqs.
+	 */
+	unsigned int limit = MAX_LOCK_DEPTH / 2;
+
+	if (lockdep_depth(current) > limit)
+		netif_close_many_and_unlock(close_head);
+#endif
+}
+
 void unregister_netdevice_many_notify(struct list_head *head,
 				      u32 portid, const struct nlmsghdr *nlh)
 {
@@ -12208,17 +12237,18 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 	/* If device is running, close it first. Start with ops locked... */
 	list_for_each_entry(dev, head, unreg_list) {
+		if (!(dev->flags & IFF_UP))
+			continue;
 		if (netdev_need_ops_lock(dev)) {
 			list_add_tail(&dev->close_list, &close_head);
 			netdev_lock(dev);
 		}
+		netif_close_many_and_unlock_cond(&close_head);
 	}
-	netif_close_many(&close_head, true);
-	/* ... now unlock them and go over the rest. */
+	netif_close_many_and_unlock(&close_head);
+	/* ... now go over the rest. */
 	list_for_each_entry(dev, head, unreg_list) {
-		if (netdev_need_ops_lock(dev))
-			netdev_unlock(dev);
-		else
+		if (!netdev_need_ops_lock(dev))
 			list_add_tail(&dev->close_list, &close_head);
 	}
 	netif_close_many(&close_head, true);

From 0f5878834d6ce97426219b64c02a2c4081419d53 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Mon, 13 Oct 2025 02:14:22 +0200
Subject: [PATCH 337/352] rust: bitmap: clean Rust 1.92.0 `unused_unsafe`
 warning

Starting with Rust 1.92.0 (expected 2025-12-11), Rust allows to safely
take the address of a union field [1][2]:

      CLIPPY L rust/kernel.o
    error: unnecessary `unsafe` block
       --> rust/kernel/bitmap.rs:169:13
        |
    169 |             unsafe { core::ptr::addr_of!(self.repr.bitmap) }
        |             ^^^^^^ unnecessary `unsafe` block
        |
        = note: `-D unused-unsafe` implied by `-D warnings`
        = help: to override `-D warnings` add `#[allow(unused_unsafe)]`

    error: unnecessary `unsafe` block
       --> rust/kernel/bitmap.rs:185:13
        |
    185 |             unsafe { core::ptr::addr_of_mut!(self.repr.bitmap) }
        |             ^^^^^^ unnecessary `unsafe` block

Thus allow both instances to clean the warning in newer compilers.

Link: https://github.com/rust-lang/rust/issues/141264 [1]
Link: https://github.com/rust-lang/rust/pull/141469 [2]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 rust/kernel/bitmap.rs | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/rust/kernel/bitmap.rs b/rust/kernel/bitmap.rs
index f45915694454..711b8368b38f 100644
--- a/rust/kernel/bitmap.rs
+++ b/rust/kernel/bitmap.rs
@@ -166,6 +166,7 @@ impl core::ops::Deref for BitmapVec {
     fn deref(&self) -> &Bitmap {
         let ptr = if self.nbits <= BITS_PER_LONG {
             // SAFETY: Bitmap is represented inline.
+            #[allow(unused_unsafe, reason = "Safe since Rust 1.92.0")]
             unsafe { core::ptr::addr_of!(self.repr.bitmap) }
         } else {
             // SAFETY: Bitmap is represented as array of `unsigned long`.
@@ -182,6 +183,7 @@ impl core::ops::DerefMut for BitmapVec {
     fn deref_mut(&mut self) -> &mut Bitmap {
         let ptr = if self.nbits <= BITS_PER_LONG {
             // SAFETY: Bitmap is represented inline.
+            #[allow(unused_unsafe, reason = "Safe since Rust 1.92.0")]
             unsafe { core::ptr::addr_of_mut!(self.repr.bitmap) }
         } else {
             // SAFETY: Bitmap is represented as array of `unsigned long`.

From 7e85ac9da1acc591bd5269f2b890ed1994c42e96 Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Mon, 13 Oct 2025 09:34:04 +0200
Subject: [PATCH 338/352] PM / devfreq: rockchip-dfi: switch to FIELD_PREP_WM16
 macro

The era of hand-rolled HIWORD_UPDATE macros is over, at least for those
drivers that use constant masks.

Like many other Rockchip drivers, rockchip-dfi brings with it its own
HIWORD_UPDATE macro. This variant doesn't shift the value (and like the
others, doesn't do any checking).

Remove it, and replace instances of it with hw_bitfield.h's
FIELD_PREP_WM16.  Since FIELD_PREP_WM16 requires contiguous masks and
shifts the value for us, some reshuffling of definitions needs to
happen.

This gives us better compile-time error checking, and in my opinion,
nicer code.

Tested on an RK3568 ODROID-M1 board (LPDDR4X at 1560 MHz, an RK3588
Radxa ROCK 5B board (LPDDR4X at 2112 MHz) and an RK3588 Radxa ROCK 5T
board (LPDDR5 at 2400 MHz). perf measurements were consistent with the
measurements of stress-ng --stream in all cases.

Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 drivers/devfreq/event/rockchip-dfi.c | 45 ++++++++++++++--------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c
index 5a2c9badcc64..5e6e7e900bda 100644
--- a/drivers/devfreq/event/rockchip-dfi.c
+++ b/drivers/devfreq/event/rockchip-dfi.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/bitfield.h>
+#include <linux/hw_bitfield.h>
 #include <linux/bits.h>
 #include <linux/perf_event.h>
 
@@ -30,8 +31,6 @@
 
 #define DMC_MAX_CHANNELS	4
 
-#define HIWORD_UPDATE(val, mask)	((val) | (mask) << 16)
-
 /* DDRMON_CTRL */
 #define DDRMON_CTRL	0x04
 #define DDRMON_CTRL_LPDDR5		BIT(6)
@@ -41,10 +40,6 @@
 #define DDRMON_CTRL_LPDDR23		BIT(2)
 #define DDRMON_CTRL_SOFTWARE_EN		BIT(1)
 #define DDRMON_CTRL_TIMER_CNT_EN	BIT(0)
-#define DDRMON_CTRL_DDR_TYPE_MASK	(DDRMON_CTRL_LPDDR5 | \
-					 DDRMON_CTRL_DDR4 | \
-					 DDRMON_CTRL_LPDDR4 | \
-					 DDRMON_CTRL_LPDDR23)
 #define DDRMON_CTRL_LP5_BANK_MODE_MASK	GENMASK(8, 7)
 
 #define DDRMON_CH0_WR_NUM		0x20
@@ -124,27 +119,31 @@ struct rockchip_dfi {
 	unsigned int count_multiplier;	/* number of data clocks per count */
 };
 
-static int rockchip_dfi_ddrtype_to_ctrl(struct rockchip_dfi *dfi, u32 *ctrl,
-					u32 *mask)
+static int rockchip_dfi_ddrtype_to_ctrl(struct rockchip_dfi *dfi, u32 *ctrl)
 {
 	u32 ddrmon_ver;
 
-	*mask = DDRMON_CTRL_DDR_TYPE_MASK;
-
 	switch (dfi->ddr_type) {
 	case ROCKCHIP_DDRTYPE_LPDDR2:
 	case ROCKCHIP_DDRTYPE_LPDDR3:
-		*ctrl = DDRMON_CTRL_LPDDR23;
+		*ctrl = FIELD_PREP_WM16(DDRMON_CTRL_LPDDR23, 1) |
+			FIELD_PREP_WM16(DDRMON_CTRL_LPDDR4, 0) |
+			FIELD_PREP_WM16(DDRMON_CTRL_LPDDR5, 0);
 		break;
 	case ROCKCHIP_DDRTYPE_LPDDR4:
 	case ROCKCHIP_DDRTYPE_LPDDR4X:
-		*ctrl = DDRMON_CTRL_LPDDR4;
+		*ctrl = FIELD_PREP_WM16(DDRMON_CTRL_LPDDR23, 0) |
+			FIELD_PREP_WM16(DDRMON_CTRL_LPDDR4, 1) |
+			FIELD_PREP_WM16(DDRMON_CTRL_LPDDR5, 0);
 		break;
 	case ROCKCHIP_DDRTYPE_LPDDR5:
 		ddrmon_ver = readl_relaxed(dfi->regs);
 		if (ddrmon_ver < 0x40) {
-			*ctrl = DDRMON_CTRL_LPDDR5 | dfi->lp5_bank_mode;
-			*mask |= DDRMON_CTRL_LP5_BANK_MODE_MASK;
+			*ctrl = FIELD_PREP_WM16(DDRMON_CTRL_LPDDR23, 0) |
+				FIELD_PREP_WM16(DDRMON_CTRL_LPDDR4, 0) |
+				FIELD_PREP_WM16(DDRMON_CTRL_LPDDR5, 1) |
+				FIELD_PREP_WM16(DDRMON_CTRL_LP5_BANK_MODE_MASK,
+						dfi->lp5_bank_mode);
 			break;
 		}
 
@@ -172,7 +171,6 @@ static int rockchip_dfi_enable(struct rockchip_dfi *dfi)
 	void __iomem *dfi_regs = dfi->regs;
 	int i, ret = 0;
 	u32 ctrl;
-	u32 ctrl_mask;
 
 	mutex_lock(&dfi->mutex);
 
@@ -186,7 +184,7 @@ static int rockchip_dfi_enable(struct rockchip_dfi *dfi)
 		goto out;
 	}
 
-	ret = rockchip_dfi_ddrtype_to_ctrl(dfi, &ctrl, &ctrl_mask);
+	ret = rockchip_dfi_ddrtype_to_ctrl(dfi, &ctrl);
 	if (ret)
 		goto out;
 
@@ -196,15 +194,16 @@ static int rockchip_dfi_enable(struct rockchip_dfi *dfi)
 			continue;
 
 		/* clear DDRMON_CTRL setting */
-		writel_relaxed(HIWORD_UPDATE(0, DDRMON_CTRL_TIMER_CNT_EN |
-			       DDRMON_CTRL_SOFTWARE_EN | DDRMON_CTRL_HARDWARE_EN),
+		writel_relaxed(FIELD_PREP_WM16(DDRMON_CTRL_TIMER_CNT_EN, 0) |
+			       FIELD_PREP_WM16(DDRMON_CTRL_SOFTWARE_EN, 0) |
+			       FIELD_PREP_WM16(DDRMON_CTRL_HARDWARE_EN, 0),
 			       dfi_regs + i * dfi->ddrmon_stride + DDRMON_CTRL);
 
-		writel_relaxed(HIWORD_UPDATE(ctrl, ctrl_mask),
-			       dfi_regs + i * dfi->ddrmon_stride + DDRMON_CTRL);
+		writel_relaxed(ctrl, dfi_regs + i * dfi->ddrmon_stride +
+			       DDRMON_CTRL);
 
 		/* enable count, use software mode */
-		writel_relaxed(HIWORD_UPDATE(DDRMON_CTRL_SOFTWARE_EN, DDRMON_CTRL_SOFTWARE_EN),
+		writel_relaxed(FIELD_PREP_WM16(DDRMON_CTRL_SOFTWARE_EN, 1),
 			       dfi_regs + i * dfi->ddrmon_stride + DDRMON_CTRL);
 
 		if (dfi->ddrmon_ctrl_single)
@@ -234,8 +233,8 @@ static void rockchip_dfi_disable(struct rockchip_dfi *dfi)
 		if (!(dfi->channel_mask & BIT(i)))
 			continue;
 
-		writel_relaxed(HIWORD_UPDATE(0, DDRMON_CTRL_SOFTWARE_EN),
-			      dfi_regs + i * dfi->ddrmon_stride + DDRMON_CTRL);
+		writel_relaxed(FIELD_PREP_WM16(DDRMON_CTRL_SOFTWARE_EN, 0),
+			       dfi_regs + i * dfi->ddrmon_stride + DDRMON_CTRL);
 
 		if (dfi->ddrmon_ctrl_single)
 			break;

From 1f4a222b0e334540343fbb5d3eac4584a6bfe180 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 15 Oct 2025 07:57:28 -0700
Subject: [PATCH 339/352] Remove long-stale ext3 defconfig option

Inspired by commit c065b6046b34 ("Use CONFIG_EXT4_FS instead of
CONFIG_EXT3_FS in all of the defconfigs") I looked around for any other
left-over EXT3 config options, and found some old defconfig files still
mentioned CONFIG_EXT3_DEFAULTS_TO_ORDERED.

That config option was removed a decade ago in commit c290ea01abb7 ("fs:
Remove ext3 filesystem driver").  It had a good run, but let's remove it
for good.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/configs/axm55xx_defconfig        | 1 -
 arch/hexagon/configs/comet_defconfig      | 1 -
 arch/sh/configs/ap325rxa_defconfig        | 1 -
 arch/sh/configs/apsh4a3a_defconfig        | 1 -
 arch/sh/configs/apsh4ad0a_defconfig       | 1 -
 arch/sh/configs/ecovec24_defconfig        | 1 -
 arch/sh/configs/edosk7760_defconfig       | 1 -
 arch/sh/configs/espt_defconfig            | 1 -
 arch/sh/configs/landisk_defconfig         | 1 -
 arch/sh/configs/lboxre2_defconfig         | 1 -
 arch/sh/configs/magicpanelr2_defconfig    | 1 -
 arch/sh/configs/r7780mp_defconfig         | 1 -
 arch/sh/configs/r7785rp_defconfig         | 1 -
 arch/sh/configs/rsk7264_defconfig         | 1 -
 arch/sh/configs/rsk7269_defconfig         | 1 -
 arch/sh/configs/sdk7780_defconfig         | 1 -
 arch/sh/configs/sdk7786_defconfig         | 1 -
 arch/sh/configs/se7343_defconfig          | 1 -
 arch/sh/configs/se7712_defconfig          | 1 -
 arch/sh/configs/se7721_defconfig          | 1 -
 arch/sh/configs/se7722_defconfig          | 1 -
 arch/sh/configs/se7724_defconfig          | 1 -
 arch/sh/configs/sh03_defconfig            | 1 -
 arch/sh/configs/sh7763rdp_defconfig       | 1 -
 arch/sh/configs/sh7785lcr_32bit_defconfig | 1 -
 arch/sh/configs/sh7785lcr_defconfig       | 1 -
 arch/sh/configs/shx3_defconfig            | 1 -
 arch/sh/configs/titan_defconfig           | 1 -
 arch/sh/configs/ul2_defconfig             | 1 -
 arch/sh/configs/urquell_defconfig         | 1 -
 arch/sparc/configs/sparc64_defconfig      | 1 -
 31 files changed, 31 deletions(-)

diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig
index 9b263ea9a878..242a61208a0f 100644
--- a/arch/arm/configs/axm55xx_defconfig
+++ b/arch/arm/configs/axm55xx_defconfig
@@ -195,7 +195,6 @@ CONFIG_PL320_MBOX=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=y
diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig
index b132752693a9..22d7f8ac58a3 100644
--- a/arch/hexagon/configs/comet_defconfig
+++ b/arch/hexagon/configs/comet_defconfig
@@ -47,7 +47,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index 336dbacd89bd..48b2e97114f9 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -82,7 +82,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/apsh4a3a_defconfig b/arch/sh/configs/apsh4a3a_defconfig
index 59daf99ea745..85db9ce42d1a 100644
--- a/arch/sh/configs/apsh4a3a_defconfig
+++ b/arch/sh/configs/apsh4a3a_defconfig
@@ -61,7 +61,6 @@ CONFIG_LOGO=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
index df2a669ea9d8..e8b3b720578b 100644
--- a/arch/sh/configs/apsh4ad0a_defconfig
+++ b/arch/sh/configs/apsh4ad0a_defconfig
@@ -89,7 +89,6 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
index dd7e54c451d6..fcca7cc5a75a 100644
--- a/arch/sh/configs/ecovec24_defconfig
+++ b/arch/sh/configs/ecovec24_defconfig
@@ -110,7 +110,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig
index 711db47b65ba..98f4611ba553 100644
--- a/arch/sh/configs/edosk7760_defconfig
+++ b/arch/sh/configs/edosk7760_defconfig
@@ -88,7 +88,6 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_XIP=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_NFS_FS=y
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index f8cad1e7a333..e5d102cbff89 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -60,7 +60,6 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_AUTOFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index 08342ceee32e..22177aa8f961 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -94,7 +94,6 @@ CONFIG_USB_EMI26=m
 CONFIG_USB_SISUSBVGA=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_ISO9660_FS=m
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 96a21173522d..ff992301622b 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -50,7 +50,6 @@ CONFIG_HW_RANDOM=y
 CONFIG_RTC_CLASS=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/magicpanelr2_defconfig b/arch/sh/configs/magicpanelr2_defconfig
index af7f777b20be..a29fb912a242 100644
--- a/arch/sh/configs/magicpanelr2_defconfig
+++ b/arch/sh/configs/magicpanelr2_defconfig
@@ -65,7 +65,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT4_FS_XATTR is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_PROC_KCORE=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index 11f210517f76..58b792dacfec 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -75,7 +75,6 @@ CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_FUSE_FS=m
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index ae367d7a14a8..7edf18451158 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -70,7 +70,6 @@ CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_FUSE_FS=m
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/rsk7264_defconfig b/arch/sh/configs/rsk7264_defconfig
index 3aba0102304f..28a81efefb02 100644
--- a/arch/sh/configs/rsk7264_defconfig
+++ b/arch/sh/configs/rsk7264_defconfig
@@ -60,7 +60,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_STORAGE_DEBUG=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
diff --git a/arch/sh/configs/rsk7269_defconfig b/arch/sh/configs/rsk7269_defconfig
index f82f280fc55a..f8bfa46643ff 100644
--- a/arch/sh/configs/rsk7269_defconfig
+++ b/arch/sh/configs/rsk7269_defconfig
@@ -44,7 +44,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_STORAGE_DEBUG=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig
index 3b51195bf1b5..311817161afb 100644
--- a/arch/sh/configs/sdk7780_defconfig
+++ b/arch/sh/configs/sdk7780_defconfig
@@ -103,7 +103,6 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index ebb3f4420ae8..2433aa5f44a8 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -162,7 +162,6 @@ CONFIG_STAGING=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=y
 CONFIG_BTRFS_FS=y
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index 6ef546ee8a32..b0baa5771c26 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -85,7 +85,6 @@ CONFIG_USB_ISP116X_HCD=y
 CONFIG_UIO=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index 4cecf9c06a65..1078c286a610 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -84,7 +84,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index c28057b70ad7..edb9e0d2dce5 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -108,7 +108,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/se7722_defconfig b/arch/sh/configs/se7722_defconfig
index 88bfd953ef89..33daa0a17a32 100644
--- a/arch/sh/configs/se7722_defconfig
+++ b/arch/sh/configs/se7722_defconfig
@@ -45,7 +45,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig
index e1b2616ef921..d572655f842d 100644
--- a/arch/sh/configs/se7724_defconfig
+++ b/arch/sh/configs/se7724_defconfig
@@ -111,7 +111,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 306e1661fbf5..3d194d81c92b 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -58,7 +58,6 @@ CONFIG_SH_WDT=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=m
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index 85ec00b7dbd2..e7b72ff377a8 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -62,7 +62,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_AUTOFS_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig
index e860a20d3f0f..17d2471d8e51 100644
--- a/arch/sh/configs/sh7785lcr_32bit_defconfig
+++ b/arch/sh/configs/sh7785lcr_32bit_defconfig
@@ -114,7 +114,6 @@ CONFIG_DMADEVICES=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/sh/configs/sh7785lcr_defconfig b/arch/sh/configs/sh7785lcr_defconfig
index 33c98b4a2adb..34c8fe755add 100644
--- a/arch/sh/configs/sh7785lcr_defconfig
+++ b/arch/sh/configs/sh7785lcr_defconfig
@@ -91,7 +91,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
index 3169e4dc7004..52e7a42d66c7 100644
--- a/arch/sh/configs/shx3_defconfig
+++ b/arch/sh/configs/shx3_defconfig
@@ -85,7 +85,6 @@ CONFIG_RTC_DRV_SH=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 6bff00038072..2c474645ec36 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -216,7 +216,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SH=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT4_FS_XATTR is not set
 CONFIG_XFS_FS=m
 CONFIG_FUSE_FS=m
diff --git a/arch/sh/configs/ul2_defconfig b/arch/sh/configs/ul2_defconfig
index b89eb8f5cc5c..b0c2ba478353 100644
--- a/arch/sh/configs/ul2_defconfig
+++ b/arch/sh/configs/ul2_defconfig
@@ -67,7 +67,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
index 60cb716ef195..e6d807f52253 100644
--- a/arch/sh/configs/urquell_defconfig
+++ b/arch/sh/configs/urquell_defconfig
@@ -115,7 +115,6 @@ CONFIG_RTC_DRV_SH=y
 CONFIG_RTC_DRV_GENERIC=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_BTRFS_FS=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 200640b93e05..127940aafc39 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -188,7 +188,6 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_PROC_KCORE=y

From bfdd74166a639930baaba27a8d729edaacd46907 Mon Sep 17 00:00:00 2001
From: Tim Hostetler <thostet@google.com>
Date: Tue, 14 Oct 2025 00:47:39 +0000
Subject: [PATCH 340/352] gve: Check valid ts bit on RX descriptor before hw
 timestamping

The device returns a valid bit in the LSB of the low timestamp byte in
the completion descriptor that the driver should check before
setting the SKB's hardware timestamp. If the timestamp is not valid, do not
hardware timestamp the SKB.

Cc: stable@vger.kernel.org
Fixes: b2c7aeb49056 ("gve: Implement ndo_hwtstamp_get/set for RX timestamping")
Reviewed-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Tim Hostetler <thostet@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20251014004740.2775957-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h          |  2 ++
 drivers/net/ethernet/google/gve/gve_desc_dqo.h |  3 ++-
 drivers/net/ethernet/google/gve/gve_rx_dqo.c   | 16 +++++++++++-----
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index bceaf9b05cb4..4cc6dcbfd367 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -100,6 +100,8 @@
  */
 #define GVE_DQO_QPL_ONDEMAND_ALLOC_THRESHOLD 96
 
+#define GVE_DQO_RX_HWTSTAMP_VALID 0x1
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
diff --git a/drivers/net/ethernet/google/gve/gve_desc_dqo.h b/drivers/net/ethernet/google/gve/gve_desc_dqo.h
index d17da841b5a0..f7786b03c744 100644
--- a/drivers/net/ethernet/google/gve/gve_desc_dqo.h
+++ b/drivers/net/ethernet/google/gve/gve_desc_dqo.h
@@ -236,7 +236,8 @@ struct gve_rx_compl_desc_dqo {
 
 	u8 status_error1;
 
-	__le16 reserved5;
+	u8 reserved5;
+	u8 ts_sub_nsecs_low;
 	__le16 buf_id; /* Buffer ID which was sent on the buffer queue. */
 
 	union {
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 55393b784317..1aff3bbb8cfc 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -456,14 +456,20 @@ static void gve_rx_skb_hash(struct sk_buff *skb,
  * Note that this means if the time delta between packet reception and the last
  * clock read is greater than ~2 seconds, this will provide invalid results.
  */
-static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx, u32 hwts)
+static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx,
+				const struct gve_rx_compl_desc_dqo *desc)
 {
 	u64 last_read = READ_ONCE(rx->gve->last_sync_nic_counter);
 	struct sk_buff *skb = rx->ctx.skb_head;
-	u32 low = (u32)last_read;
-	s32 diff = hwts - low;
+	u32 ts, low;
+	s32 diff;
 
-	skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(last_read + diff);
+	if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID) {
+		ts = le32_to_cpu(desc->ts);
+		low = (u32)last_read;
+		diff = ts - low;
+		skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(last_read + diff);
+	}
 }
 
 static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx)
@@ -944,7 +950,7 @@ static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi,
 		gve_rx_skb_csum(rx->ctx.skb_head, desc, ptype);
 
 	if (rx->gve->ts_config.rx_filter == HWTSTAMP_FILTER_ALL)
-		gve_rx_skb_hwtstamp(rx, le32_to_cpu(desc->ts));
+		gve_rx_skb_hwtstamp(rx, desc);
 
 	/* RSC packets must set gso_size otherwise the TCP stack will complain
 	 * that packets are larger than MTU.

From bc384963bc18e4f21cf8615b57cbbc9c5e0d309a Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 14 Oct 2025 19:06:50 +0200
Subject: [PATCH 341/352] MAINTAINERS: new entry for IPv6 IOAM

Create a maintainer entry for IPv6 IOAM. Add myself as I authored most
if not all of the IPv6 IOAM code in the kernel and actively participate
in the related IETF groups.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20251014170650.27679-1-justin.iurman@uliege.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8a213950e37e..eba5e091a086 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18012,6 +18012,16 @@ X:	net/rfkill/
 X:	net/wireless/
 X:	tools/testing/selftests/net/can/
 
+NETWORKING [IOAM]
+M:	Justin Iurman <justin.iurman@uliege.be>
+S:	Maintained
+F:	Documentation/networking/ioam6*
+F:	include/linux/ioam6*
+F:	include/net/ioam6*
+F:	include/uapi/linux/ioam6*
+F:	net/ipv6/ioam6*
+F:	tools/testing/selftests/net/ioam6*
+
 NETWORKING [IPSEC]
 M:	Steffen Klassert <steffen.klassert@secunet.com>
 M:	Herbert Xu <herbert@gondor.apana.org.au>

From 0c3f2e62815a43628e748b1e4ad97a1c46cce703 Mon Sep 17 00:00:00 2001
From: Alexey Simakov <bigalex934@gmail.com>
Date: Tue, 14 Oct 2025 19:47:38 +0300
Subject: [PATCH 342/352] tg3: prevent use of uninitialized remote_adv and
 local_adv variables

Some execution paths that jump to the fiber_setup_done label
could leave the remote_adv and local_adv variables uninitialized
and then use it.

Initialize this variables at the point of definition to avoid this.

Fixes: 85730a631f0c ("tg3: Add SGMII phy support for 5719/5718 serdes")
Co-developed-by: Alexandr Sapozhnikov <alsp705@gmail.com>
Signed-off-by: Alexandr Sapozhnikov <alsp705@gmail.com>
Signed-off-by: Alexey Simakov <bigalex934@gmail.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://patch.msgid.link/20251014164736.5890-1-bigalex934@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/tg3.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 7f00ec7fd7b9..d78cafdb2094 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -5803,7 +5803,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
-	u32 local_adv, remote_adv, sgsr;
+	u32 local_adv = 0, remote_adv = 0, sgsr;
 
 	if ((tg3_asic_rev(tp) == ASIC_REV_5719 ||
 	     tg3_asic_rev(tp) == ASIC_REV_5720) &&
@@ -5944,9 +5944,6 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 		else
 			current_duplex = DUPLEX_HALF;
 
-		local_adv = 0;
-		remote_adv = 0;
-
 		if (bmcr & BMCR_ANENABLE) {
 			u32 common;
 

From ce5af41e3234425a40974696682163edfd21128c Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:16:56 +0200
Subject: [PATCH 343/352] tls: trim encrypted message to match the plaintext on
 short splice

During tls_sw_sendmsg_locked, we pre-allocate the encrypted message
for the size we're expecting to send during the current iteration, but
we may end up sending less, for example when splicing: if we're
getting the data from small fragments of memory, we may fill up all
the slots in the skmsg with less data than expected.

In this case, we need to trim the encrypted message to only the length
we actually need, to avoid pushing uninitialized bytes down the
underlying TCP socket.

Fixes: fe1e81d4f73b ("tls/sw: Support MSG_SPLICE_PAGES")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/66a0ae99c9efc15f88e9e56c1f58f902f442ce86.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index daac9fd4be7e..36ca3011ab87 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1112,8 +1112,11 @@ alloc_encrypted:
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
 
-			if (sk_msg_full(msg_pl))
+			if (sk_msg_full(msg_pl)) {
 				full_record = true;
+				sk_msg_trim(sk, msg_en,
+					    msg_pl->sg.size + prot->overhead_size);
+			}
 
 			if (full_record || eor)
 				goto copied;

From b014a4e066c555185b7c367efacdc33f16695495 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:16:57 +0200
Subject: [PATCH 344/352] tls: wait for async encrypt in case of error during
 latter iterations of sendmsg

If we hit an error during the main loop of tls_sw_sendmsg_locked (eg
failed allocation), we jump to send_end and immediately
return. Previous iterations may have queued async encryption requests
that are still pending. We should wait for those before returning, as
we could otherwise be reading from memory that userspace believes
we're not using anymore, which would be a sort of use-after-free.

This is similar to what tls_sw_recvmsg already does: failures during
the main loop jump to the "wait for async" code, not straight to the
unlock/return.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/c793efe9673b87f808d84fdefc0f732217030c52.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 36ca3011ab87..1478d515badc 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1054,7 +1054,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			if (ret == -EINPROGRESS)
 				num_async++;
 			else if (ret != -EAGAIN)
-				goto send_end;
+				goto end;
 		}
 	}
 
@@ -1226,8 +1226,9 @@ trim_sgl:
 			goto alloc_encrypted;
 	}
 
+send_end:
 	if (!num_async) {
-		goto send_end;
+		goto end;
 	} else if (num_zc || eor) {
 		int err;
 
@@ -1245,7 +1246,7 @@ trim_sgl:
 		tls_tx_records(sk, msg->msg_flags);
 	}
 
-send_end:
+end:
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
 	return copied > 0 ? copied : ret;
 }

From b6fe4c29bb51cf239ecf48eacf72b924565cb619 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:16:58 +0200
Subject: [PATCH 345/352] tls: always set record_type in tls_process_cmsg

When userspace wants to send a non-DATA record (via the
TLS_SET_RECORD_TYPE cmsg), we need to send any pending data from a
previous MSG_MORE send() as a separate DATA record. If that DATA record
is encrypted asynchronously, tls_handle_open_record will return
-EINPROGRESS. This is currently treated as an error by
tls_process_cmsg, and it will skip setting record_type to the correct
value, but the caller (tls_sw_sendmsg_locked) handles that return
value correctly and proceeds with sending the new message with an
incorrect record_type (DATA instead of whatever was requested in the
cmsg).

Always set record_type before handling the open record. If
tls_handle_open_record returns an error, record_type will be
ignored. If it succeeds, whether with synchronous crypto (returning 0)
or asynchronous (returning -EINPROGRESS), the caller will proceed
correctly.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/0457252e578a10a94e40c72ba6288b3a64f31662.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_main.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a3ccb3135e51..39a2ab47fe72 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -255,12 +255,9 @@ int tls_process_cmsg(struct sock *sk, struct msghdr *msg,
 			if (msg->msg_flags & MSG_MORE)
 				return -EINVAL;
 
-			rc = tls_handle_open_record(sk, msg->msg_flags);
-			if (rc)
-				return rc;
-
 			*record_type = *(unsigned char *)CMSG_DATA(cmsg);
-			rc = 0;
+
+			rc = tls_handle_open_record(sk, msg->msg_flags);
 			break;
 		default:
 			return -EINVAL;

From b8a6ff84abbcbbc445463de58704686011edc8e1 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:16:59 +0200
Subject: [PATCH 346/352] tls: wait for pending async decryptions if
 tls_strp_msg_hold fails

Async decryption calls tls_strp_msg_hold to create a clone of the
input skb to hold references to the memory it uses. If we fail to
allocate that clone, proceeding with async decryption can lead to
various issues (UAF on the skb, writing into userspace memory after
the recv() call has returned).

In this case, wait for all pending decryption requests.

Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/b9fe61dcc07dab15da9b35cf4c7d86382a98caf2.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1478d515badc..e3d852091e7a 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1641,8 +1641,10 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 
 	if (unlikely(darg->async)) {
 		err = tls_strp_msg_hold(&ctx->strp, &ctx->async_hold);
-		if (err)
-			__skb_queue_tail(&ctx->async_hold, darg->skb);
+		if (err) {
+			err = tls_decrypt_async_wait(ctx);
+			darg->async = false;
+		}
 		return err;
 	}
 

From 7f846c65ca11e63d2409868ff039081f80e42ae4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:17:00 +0200
Subject: [PATCH 347/352] tls: don't rely on tx_work during send()

With async crypto, we rely on tx_work to actually transmit records
once encryption completes. But while send() is running, both the
tx_lock and socket lock are held, so tx_work_handler cannot process
the queue of encrypted records, and simply reschedules itself. During
a large send(), this could last a long time, and use a lot of memory.

Transmit any pending encrypted records before restarting the main
loop of tls_sw_sendmsg_locked.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/8396631478f70454b44afb98352237d33f48d34d.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e3d852091e7a..d17135369980 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1152,6 +1152,13 @@ alloc_encrypted:
 				} else if (ret != -EAGAIN)
 					goto send_end;
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
+
 			continue;
 rollback_iter:
 			copied -= try_to_copy;
@@ -1207,6 +1214,12 @@ copied:
 					goto send_end;
 				}
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
 		}
 
 		continue;

From f95fce1e953b8a7af3fbad84aaffe92804196e2d Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:17:01 +0200
Subject: [PATCH 348/352] selftests: net: tls: add tests for cmsg vs MSG_MORE

We don't have a test to check that MSG_MORE won't let us merge records
of different types across sendmsg calls.

Add new tests that check:
 - MSG_MORE is only allowed for DATA records
 - a pending DATA record gets closed and pushed before a non-DATA
   record is processed

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/b34feeadefe8a997f068d5ed5617afd0072df3c0.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 34 +++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index e788b84551ca..77e4e30b46cc 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -564,6 +564,40 @@ TEST_F(tls, msg_more)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, cmsg_msg_more)
+{
+	char *test_str =  "test_read";
+	char record_type = 100;
+	int send_len = 10;
+
+	/* we don't allow MSG_MORE with non-DATA records */
+	EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len,
+				MSG_MORE), -1);
+	EXPECT_EQ(errno, EINVAL);
+}
+
+TEST_F(tls, msg_more_then_cmsg)
+{
+	char *test_str = "test_read";
+	char record_type = 100;
+	int send_len = 10;
+	char buf[10 * 2];
+	int ret;
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+
+	ret = tls_send_cmsg(self->fd, record_type, test_str, send_len, 0);
+	EXPECT_EQ(ret, send_len);
+
+	/* initial DATA record didn't get merged with the non-DATA record */
+	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, 0), send_len);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
+}
+
 TEST_F(tls, msg_more_unsent)
 {
 	char const *test_str = "test_read";

From 3667e9b442b95b021189db793b9156552f918e99 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 Oct 2025 11:17:02 +0200
Subject: [PATCH 349/352] selftests: tls: add test for short splice due to full
 skmsg

We don't have a test triggering a partial splice caused by a full
skmsg. Add one, based on a program by Jann Horn.

Use MAX_FRAGS=48 to make sure the skmsg will be full for any allowed
value of CONFIG_MAX_SKB_FRAGS (17..45).

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/1d129a15f526ea3602f3a2b368aa0b6f7e0d35d5.1760432043.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 77e4e30b46cc..5c6d8215021c 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -946,6 +946,37 @@ TEST_F(tls, peek_and_splice)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+#define MAX_FRAGS 48
+TEST_F(tls, splice_short)
+{
+	struct iovec sendchar_iov;
+	char read_buf[0x10000];
+	char sendbuf[0x100];
+	char sendchar = 'S';
+	int pipefds[2];
+	int i;
+
+	sendchar_iov.iov_base = &sendchar;
+	sendchar_iov.iov_len = 1;
+
+	memset(sendbuf, 's', sizeof(sendbuf));
+
+	ASSERT_GE(pipe2(pipefds, O_NONBLOCK), 0);
+	ASSERT_GE(fcntl(pipefds[0], F_SETPIPE_SZ, (MAX_FRAGS + 1) * 0x1000), 0);
+
+	for (i = 0; i < MAX_FRAGS; i++)
+		ASSERT_GE(vmsplice(pipefds[1], &sendchar_iov, 1, 0), 0);
+
+	ASSERT_EQ(write(pipefds[1], sendbuf, sizeof(sendbuf)), sizeof(sendbuf));
+
+	EXPECT_EQ(splice(pipefds[0], NULL, self->fd, NULL, MAX_FRAGS + 0x1000, 0),
+		  MAX_FRAGS + sizeof(sendbuf));
+	EXPECT_EQ(recv(self->cfd, read_buf, sizeof(read_buf), 0), MAX_FRAGS + sizeof(sendbuf));
+	EXPECT_EQ(recv(self->cfd, read_buf, sizeof(read_buf), MSG_DONTWAIT), -1);
+	EXPECT_EQ(errno, EAGAIN);
+}
+#undef MAX_FRAGS
+
 TEST_F(tls, recvmsg_single)
 {
 	char const *test_str = "test_recvmsg_single";

From 1a8fed52f7be14e45785e8e54d0d0b50fc17dbd8 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 14 Oct 2025 02:17:25 -0700
Subject: [PATCH 350/352] netdevsim: set the carrier when the device goes up

Bringing a linked netdevsim device down and then up causes communication
failure because both interfaces lack carrier. Basically a ifdown/ifup on
the interface make the link broken.

Commit 3762ec05a9fbda ("netdevsim: add NAPI support") added supported
for NAPI, calling netif_carrier_off() in nsim_stop(). This patch
re-enables the carrier symmetrically on nsim_open(), in case the device
is linked and the peer is up.

Signed-off-by: Breno Leitao <leitao@debian.org>
Fixes: 3762ec05a9fbda ("netdevsim: add NAPI support")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20251014-netdevsim_fix-v2-1-53b40590dae1@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index ebc3833e95b4..fa1d97885caa 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -545,6 +545,7 @@ static void nsim_enable_napi(struct netdevsim *ns)
 static int nsim_open(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
+	struct netdevsim *peer;
 	int err;
 
 	netdev_assert_locked(dev);
@@ -555,6 +556,12 @@ static int nsim_open(struct net_device *dev)
 
 	nsim_enable_napi(ns);
 
+	peer = rtnl_dereference(ns->peer);
+	if (peer && netif_running(peer->netdev)) {
+		netif_carrier_on(dev);
+		netif_carrier_on(peer->netdev);
+	}
+
 	return 0;
 }
 

From 8d93ff40d49d70e05c82a74beae31f883fe0eaf8 Mon Sep 17 00:00:00 2001
From: I Viswanath <viswanathiyyappan@gmail.com>
Date: Mon, 13 Oct 2025 23:46:48 +0530
Subject: [PATCH 351/352] net: usb: lan78xx: fix use of improperly initialized
 dev->chipid in lan78xx_reset

dev->chipid is used in lan78xx_init_mac_address before it's initialized:

lan78xx_reset() {
    lan78xx_init_mac_address()
        lan78xx_read_eeprom()
            lan78xx_read_raw_eeprom() <- dev->chipid is used here

    dev->chipid = ... <- dev->chipid is initialized correctly here
}

Reorder initialization so that dev->chipid is set before calling
lan78xx_init_mac_address().

Fixes: a0db7d10b76e ("lan78xx: Add to handle mux control per chip id")
Signed-off-by: I Viswanath <viswanathiyyappan@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Khalid Aziz <khalid@kernel.org>
Link: https://patch.msgid.link/20251013181648.35153-1-viswanathiyyappan@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 28195d9a8d6b..00397a807393 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3250,10 +3250,6 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		}
 	} while (buf & HW_CFG_LRST_);
 
-	ret = lan78xx_init_mac_address(dev);
-	if (ret < 0)
-		return ret;
-
 	/* save DEVID for later usage */
 	ret = lan78xx_read_reg(dev, ID_REV, &buf);
 	if (ret < 0)
@@ -3262,6 +3258,10 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	dev->chipid = (buf & ID_REV_CHIP_ID_MASK_) >> 16;
 	dev->chiprev = buf & ID_REV_CHIP_REV_MASK_;
 
+	ret = lan78xx_init_mac_address(dev);
+	if (ret < 0)
+		return ret;
+
 	/* Respond to the IN token with a NAK */
 	ret = lan78xx_read_reg(dev, USB_CFG0, &buf);
 	if (ret < 0)

From 6de1dec1c166c7f7324ce52ccfdf43e2fa743b19 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Oct 2025 05:27:15 +0000
Subject: [PATCH 352/352] udp: do not use skb_release_head_state() before
 skb_attempt_defer_free()

Michal reported and bisected an issue after recent adoption
of skb_attempt_defer_free() in UDP.

The issue here is that skb_release_head_state() is called twice per skb,
one time from skb_consume_udp(), then a second time from skb_defer_free_flush()
and napi_consume_skb().

As Sabrina suggested, remove skb_release_head_state() call from
skb_consume_udp().

Add a DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb)) in skb_attempt_defer_free()

Many thanks to Michal, Sabrina, Paolo and Florian for their help.

Fixes: 6471658dc66c ("udp: use skb_attempt_defer_free()")
Reported-and-bisected-by: Michal Kubecek <mkubecek@suse.cz>
Closes: https://lore.kernel.org/netdev/gpjh4lrotyephiqpuldtxxizrsg6job7cvhiqrw72saz2ubs3h@g6fgbvexgl3r/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Michal Kubecek <mkubecek@suse.cz>
Cc: Sabrina Dubroca <sd@queasysnail.net>
Cc: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20251015052715.4140493-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/skbuff.c | 1 +
 net/ipv4/udp.c    | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bc12790017b0..6be01454f262 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -7200,6 +7200,7 @@ nodefer:	kfree_skb_napi_cache(skb);
 
 	DEBUG_NET_WARN_ON_ONCE(skb_dst(skb));
 	DEBUG_NET_WARN_ON_ONCE(skb->destructor);
+	DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb));
 
 	sdn = per_cpu_ptr(net_hotdata.skb_defer_nodes, cpu) + numa_node_id();
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 95241093b7f0..30dfbf73729d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1851,8 +1851,6 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		sk_peek_offset_bwd(sk, len);
 
 	if (!skb_shared(skb)) {
-		if (unlikely(udp_skb_has_head_state(skb)))
-			skb_release_head_state(skb);
 		skb_attempt_defer_free(skb);
 		return;
 	}