Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 93 insertions, 89 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f0dae4fb6d..6da73513f0 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -36,7 +36,7 @@ lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
-lib-$(CONFIG_RETPOLINE) += retpoline.o
+lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 obj-y += iomem.o
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 6962df3157..4fb44894ad 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -23,14 +23,14 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	cli
 
 	/* if (*ptr == old) */
-	cmpq	PER_CPU_VAR(0(%rsi)), %rax
+	cmpq	__percpu (%rsi), %rax
 	jne	.Lnot_same
-	cmpq	PER_CPU_VAR(8(%rsi)), %rdx
+	cmpq	__percpu 8(%rsi), %rdx
 	jne	.Lnot_same
 
 	/* *ptr = new */
-	movq	%rbx, PER_CPU_VAR(0(%rsi))
-	movq	%rcx, PER_CPU_VAR(8(%rsi))
+	movq	%rbx, __percpu (%rsi)
+	movq	%rcx, __percpu 8(%rsi)
 
 	/* set ZF in EFLAGS to indicate success */
 	orl	$X86_EFLAGS_ZF, (%rsp)
@@ -42,8 +42,8 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	/* *ptr != old */
 
 	/* old = *ptr */
-	movq	PER_CPU_VAR(0(%rsi)), %rax
-	movq	PER_CPU_VAR(8(%rsi)), %rdx
+	movq	__percpu (%rsi), %rax
+	movq	__percpu 8(%rsi), %rdx
 
 	/* clear ZF in EFLAGS to indicate failure */
 	andl	$(~X86_EFLAGS_ZF), (%rsp)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 873e4ef23e..1c96be769a 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -24,12 +24,12 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	pushfl
 	cli
 
-	cmpl	0(%esi), %eax
+	cmpl	(%esi), %eax
 	jne	.Lnot_same
 	cmpl	4(%esi), %edx
 	jne	.Lnot_same
 
-	movl	%ebx, 0(%esi)
+	movl	%ebx, (%esi)
 	movl	%ecx, 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
@@ -38,7 +38,7 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	RET
 
 .Lnot_same:
-	movl	0(%esi), %eax
+	movl	(%esi), %eax
 	movl	4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
@@ -53,18 +53,30 @@ EXPORT_SYMBOL(cmpxchg8b_emu)
 
 #ifndef CONFIG_UML
 
+/*
+ * Emulate 'cmpxchg8b %fs:(%rsi)'
+ *
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
+ */
 SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 
 	pushfl
 	cli
 
-	cmpl	PER_CPU_VAR(0(%esi)), %eax
+	cmpl	__percpu (%esi), %eax
 	jne	.Lnot_same2
-	cmpl	PER_CPU_VAR(4(%esi)), %edx
+	cmpl	__percpu 4(%esi), %edx
 	jne	.Lnot_same2
 
-	movl	%ebx, PER_CPU_VAR(0(%esi))
-	movl	%ecx, PER_CPU_VAR(4(%esi))
+	movl	%ebx, __percpu (%esi)
+	movl	%ecx, __percpu 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
 
@@ -72,8 +84,8 @@ SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 	RET
 
 .Lnot_same2:
-	movl	PER_CPU_VAR(0(%esi)), %eax
-	movl	PER_CPU_VAR(4(%esi)), %edx
+	movl	__percpu (%esi), %eax
+	movl	__percpu 4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 10d5ed8b59..a1cb3a4e67 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -44,7 +44,11 @@
 	or %rdx, %rax
 .else
 	cmp $TASK_SIZE_MAX-\size+1, %eax
+.if \size != 8
 	jae .Lbad_get_user
+.else
+	jae .Lbad_get_user_8
+.endif
 	sbb %edx, %edx		/* array_index_mask_nospec() */
 	and %edx, %eax
 .endif
@@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception)
 #ifdef CONFIG_X86_32
 SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
 	ASM_CLAC
-bad_get_user_8:
+.Lbad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 558a605929..98631c0e7a 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1129,15 +1129,15 @@ static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs,
  * get_eff_addr_sib() - Obtain referenced effective address via SIB
  * @insn:	Instruction. Must be valid.
  * @regs:	Register values as seen when entering kernel mode
- * @regoff:	Obtained operand offset, in pt_regs, associated with segment
+ * @base_offset: Obtained operand offset, in pt_regs, associated with segment
  * @eff_addr:	Obtained effective address
  *
  * Obtain the effective address referenced by the SIB byte of @insn. After
  * identifying the registers involved in the indexed, register-indirect memory
  * reference, its value is obtained from the operands in @regs. The computed
  * address is stored @eff_addr. Also, the register operand that indicates the
- * associated segment is stored in @regoff, this parameter can later be used to
- * determine such segment.
+ * associated segment is stored in @base_offset; this parameter can later be
+ * used to determine such segment.
  *
  * Returns:
  *
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 55e371cc69..1bb155a095 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 	insn->kaddr = kaddr;
 	insn->end_kaddr = kaddr + buf_len;
 	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->x86_64 = x86_64;
 	insn->opnd_bytes = 4;
 	if (x86_64)
 		insn->addr_bytes = 8;
@@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn)
 	if (opcode->got)
 		return 0;
 
-	if (!insn->prefixes.got) {
-		ret = insn_get_prefixes(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_prefixes(insn);
+	if (ret)
+		return ret;
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
@@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn)
 	if (modrm->got)
 		return 0;
 
-	if (!insn->opcode.got) {
-		ret = insn_get_opcode(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_opcode(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
@@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn)
 	if (!insn->x86_64)
 		return 0;
 
-	if (!modrm->got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return 0;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return 0;
 	/*
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
@@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn)
 	if (insn->sib.got)
 		return 0;
 
-	if (!insn->modrm.got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		modrm = insn->modrm.bytes[0];
@@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn)
 	if (insn->displacement.got)
 		return 0;
 
-	if (!insn->sib.got) {
-		ret = insn_get_sib(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_sib(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		/*
@@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn)
 	if (insn->immediate.got)
 		return 0;
 
-	if (!insn->displacement.got) {
-		ret = insn_get_displacement(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_displacement(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_moffset(insn->attr)) {
 		if (!__get_moffset(insn))
@@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn)
 	if (insn->length)
 		return 0;
 
-	if (!insn->immediate.got) {
-		ret = insn_get_immediate(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_immediate(insn);
+	if (ret)
+		return ret;
 
 	insn->length = (unsigned char)((unsigned long)insn->next_byte
 				     - (unsigned long)insn->kaddr);
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index 40bbe56bde..acd463d887 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -9,10 +9,9 @@ static void __rdmsr_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
+		reg = this_cpu_ptr(rv->msrs);
 	else
 		reg = &rv->reg;
 
@@ -23,10 +22,9 @@ static void __wrmsr_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
+		reg = this_cpu_ptr(rv->msrs);
 	else
 		reg = &rv->reg;
 
@@ -97,7 +95,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 EXPORT_SYMBOL(wrmsrl_on_cpu);
 
 static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
-			    struct msr *msrs,
+			    struct msr __percpu *msrs,
 			    void (*msr_func) (void *info))
 {
 	struct msr_info rv;
@@ -124,7 +122,7 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
  * @msrs:       array of MSR values
  *
  */
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs)
 {
 	__rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
 }
@@ -138,7 +136,7 @@ EXPORT_SYMBOL(rdmsr_on_cpus);
  * @msrs:       array of MSR values
  *
  */
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs)
 {
 	__rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
 }
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 47fd9bd6b9..4bf4fad5b1 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -6,9 +6,9 @@
 #define CREATE_TRACE_POINTS
 #include <asm/msr-trace.h>
 
-struct msr *msrs_alloc(void)
+struct msr __percpu *msrs_alloc(void)
 {
-	struct msr *msrs = NULL;
+	struct msr __percpu *msrs = NULL;
 
 	msrs = alloc_percpu(struct msr);
 	if (!msrs) {
@@ -20,7 +20,7 @@ struct msr *msrs_alloc(void)
 }
 EXPORT_SYMBOL(msrs_alloc);
 
-void msrs_free(struct msr *msrs)
+void msrs_free(struct msr __percpu *msrs)
 {
 	free_percpu(msrs);
 }
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 5b26a952e2..391059b2c6 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -71,7 +71,7 @@ SYM_CODE_END(__x86_indirect_thunk_array)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 .macro CALL_THUNK reg
 	.align RETPOLINE_THUNK_SIZE
 
@@ -127,7 +127,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
 #undef GEN
 #endif
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 
 /*
  * Be careful here: that label cannot really be removed because in
@@ -138,7 +138,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  */
 	.section .text..__x86.return_thunk
 
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
 
 /*
  * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
@@ -225,8 +225,7 @@ SYM_CODE_START(srso_return_thunk)
 SYM_CODE_END(srso_return_thunk)
 
 #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
-#else /* !CONFIG_CPU_SRSO */
-#define JMP_SRSO_UNTRAIN_RET "ud2"
+#else /* !CONFIG_MITIGATION_SRSO */
 /* Dummy for the alternative in CALL_UNTRAIN_RET. */
 SYM_CODE_START(srso_alias_untrain_ret)
 	ANNOTATE_UNRET_SAFE
@@ -235,9 +234,10 @@ SYM_CODE_START(srso_alias_untrain_ret)
 	int3
 SYM_FUNC_END(srso_alias_untrain_ret)
 __EXPORT_THUNK(srso_alias_untrain_ret)
-#endif /* CONFIG_CPU_SRSO */
+#define JMP_SRSO_UNTRAIN_RET "ud2"
+#endif /* CONFIG_MITIGATION_SRSO */
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 
 /*
  * Some generic notes on the untraining sequences:
@@ -319,20 +319,20 @@ SYM_CODE_END(retbleed_return_thunk)
 SYM_FUNC_END(retbleed_untrain_ret)
 
 #define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret"
-#else /* !CONFIG_CPU_UNRET_ENTRY */
+#else /* !CONFIG_MITIGATION_UNRET_ENTRY */
 #define JMP_RETBLEED_UNTRAIN_RET "ud2"
-#endif /* CONFIG_CPU_UNRET_ENTRY */
+#endif /* CONFIG_MITIGATION_UNRET_ENTRY */
 
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
 	ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
 
-#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
+#endif /* CONFIG_MITIGATION_UNRET_ENTRY || CONFIG_MITIGATION_SRSO */
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 
 	.align 64
 SYM_FUNC_START(call_depth_return_thunk)
@@ -364,7 +364,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	int3
 SYM_FUNC_END(call_depth_return_thunk)
 
-#endif /* CONFIG_CALL_DEPTH_TRACKING */
+#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
@@ -374,21 +374,25 @@ SYM_FUNC_END(call_depth_return_thunk)
  * 'JMP __x86_return_thunk' sites are changed to something else by
  * apply_returns().
  *
- * This should be converted eventually to call a warning function which
- * should scream loudly when the default return thunk is called after
- * alternatives have been applied.
- *
- * That warning function cannot BUG() because the bug splat cannot be
- * displayed in all possible configurations, leading to users not really
- * knowing why the machine froze.
+ * The ALTERNATIVE below adds a really loud warning to catch the case
+ * where the insufficient default return thunk ends up getting used for
+ * whatever reason like miscompilation or failure of
+ * objtool/alternatives/etc to patch all the return sites.
  */
 SYM_CODE_START(__x86_return_thunk)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \
+    defined(CONFIG_MITIGATION_SRSO) || \
+    defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)
+	ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \
+		   "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS
+#else
 	ANNOTATE_UNRET_SAFE
 	ret
+#endif
 	int3
 SYM_CODE_END(__x86_return_thunk)
 EXPORT_SYMBOL(__x86_return_thunk)
 
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index d1ccd06c53..da9347552b 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1051,8 +1051,8 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv