16 files changed, 124 insertions, 33 deletions
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 0f63585edf5f..5c15f95b1ba7 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -144,7 +144,7 @@
 	_ASM_PTR (entry);					\
 	.popsection
 
-#else
+#else /* ! __ASSEMBLY__ */
 # define _EXPAND_EXTABLE_HANDLE(x) #x
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
@@ -164,9 +164,7 @@
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
-#endif
 
-#ifndef __ASSEMBLY__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -175,6 +173,6 @@
  */
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
-#endif
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 35460fef39b8..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index fb34ff641e0a..028189575560 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -75,6 +75,12 @@ do {								\
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index dd17c2da1af5..da78ccbd493b 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 02dabc9e77b0..c693ebf32a15 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -96,6 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
+/* free					( 3*32+17) */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -107,6 +108,7 @@
 #define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
 #define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+/* free					( 3*32+29) */
 #define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
 #define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 6722ffcef2e6..3afa990d756b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9b8cb50768c2..b8f1dc0761e4 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -74,16 +74,26 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 #else
 # include <asm-generic/div64.h>
 
-static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+/*
+ * Will generate an #DE when the result doesn't fit u64, could fix with an
+ * __ex_table[] entry when it becomes an issue.
+ */
+static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div)
 {
 	u64 q;
 
 	asm ("mulq %2; divq %3" : "=a" (q)
-				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "a" (a), "rm" (mul), "rm" (div)
 				: "rdx");
 
 	return q;
 }
+#define mul_u64_u64_div_u64 mul_u64_u64_div_u64
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	return mul_u64_u64_div_u64(a, mul, div);
+}
 #define mul_u64_u32_div	mul_u64_u32_div
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index bca4c743de77..aefd53767a5d 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -19,36 +19,63 @@ extern unsigned long x86_gsbase_read_task(struct task_struct *task);
 extern void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase);
 extern void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase);
 
-/* Helper functions for reading/writing FS/GS base */
+/* Must be protected by X86_FEATURE_FSGSBASE check. */
 
-static inline unsigned long x86_fsbase_read_cpu(void)
+static __always_inline unsigned long rdfsbase(void)
 {
 	unsigned long fsbase;
 
-	rdmsrl(MSR_FS_BASE, fsbase);
+	asm volatile("rdfsbase %0" : "=r" (fsbase) :: "memory");
 
 	return fsbase;
 }
 
-static inline unsigned long x86_gsbase_read_cpu_inactive(void)
+static __always_inline unsigned long rdgsbase(void)
 {
 	unsigned long gsbase;
 
-	rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	asm volatile("rdgsbase %0" : "=r" (gsbase) :: "memory");
 
 	return gsbase;
 }
 
-static inline void x86_fsbase_write_cpu(unsigned long fsbase)
+static __always_inline void wrfsbase(unsigned long fsbase)
 {
-	wrmsrl(MSR_FS_BASE, fsbase);
+	asm volatile("wrfsbase %0" :: "r" (fsbase) : "memory");
 }
 
-static inline void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
+static __always_inline void wrgsbase(unsigned long gsbase)
 {
-	wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	asm volatile("wrgsbase %0" :: "r" (gsbase) : "memory");
 }
 
+#include <asm/cpufeature.h>
+
+/* Helper functions for reading/writing FS/GS base */
+
+static inline unsigned long x86_fsbase_read_cpu(void)
+{
+	unsigned long fsbase;
+
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		fsbase = rdfsbase();
+	else
+		rdmsrl(MSR_FS_BASE, fsbase);
+
+	return fsbase;
+}
+
+static inline void x86_fsbase_write_cpu(unsigned long fsbase)
+{
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		wrfsbase(fsbase);
+	else
+		wrmsrl(MSR_FS_BASE, fsbase);
+}
+
+extern unsigned long x86_gsbase_read_cpu_inactive(void);
+extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase);
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index f5a796da07f8..d063841a17e3 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -306,6 +306,21 @@
 	.endif
 	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
 	.endm
+
+.macro RDPID opd
+	REG_TYPE rdpid_opd_type \opd
+	.if rdpid_opd_type == REG_TYPE_R64
+	R64_NUM rdpid_opd \opd
+	.else
+	R32_NUM rdpid_opd \opd
+	.endif
+	.byte 0xf3
+	.if rdpid_opd > 7
+	PFX_REX rdpid_opd 0
+	.endif
+	.byte 0x0f, 0xc7
+	MODRM 0xc0 rdpid_opd 0x7
+.endm
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 073eb7ad2f56..143bc9abe99c 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -66,6 +66,8 @@ struct arch_specific_insn {
 	 */
 	bool boostable;
 	bool if_modifier;
+	/* Number of bytes of text poked */
+	int tp_len;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 848ce43b9040..5049f6c22683 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -43,9 +43,10 @@ void __init sme_enable(struct boot_params *bp);
 int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
 int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
 
+void __init mem_encrypt_free_decrypted_mem(void);
+
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_init(void);
-void __init mem_encrypt_free_decrypted_mem(void);
 
 bool sme_active(void);
 bool sev_active(void);
@@ -77,6 +78,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0;
 static inline int __init
 early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
 
+static inline void mem_encrypt_free_decrypted_mem(void) { }
+
 #define __bss_decrypted
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e8370e64a155..63ed8fe35738 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -418,7 +418,6 @@
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_TSC_RATIO		0xc0000104
 #define MSR_AMD64_NB_CFG		0xc001001f
-#define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD_PERF_CTL		0xc0010062
 #define MSR_AMD_PERF_STATUS		0xc0010063
@@ -427,6 +426,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
 #define MSR_AMD_PPIN			0xc00102f1
+#define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
@@ -466,6 +466,8 @@
 #define MSR_F16H_DR0_ADDR_MASK		0xc0011027
 
 /* Fam 15h MSRs */
+#define MSR_F15H_CU_PWR_ACCUMULATOR     0xc001007a
+#define MSR_F15H_CU_MAX_PWR_ACCUMULATOR 0xc001007b
 #define MSR_F15H_PERF_CTL		0xc0010200
 #define MSR_F15H_PERF_CTL0		MSR_F15H_PERF_CTL
 #define MSR_F15H_PERF_CTL1		(MSR_F15H_PERF_CTL + 2)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 76aa21e8128d..b836138ce852 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -999,15 +999,12 @@ extern int direct_gbpages;
 void init_mem_mapping(void);
 void early_alloc_pgt_buf(void);
 extern void memblock_find_dma_reserve(void);
-
-
-#ifdef CONFIG_X86_64
-extern pgd_t trampoline_pgd_entry;
-
 void __init poking_init(void);
-
 unsigned long init_memory_mapping(unsigned long start,
 				  unsigned long end, pgprot_t prot);
+
+#ifdef CONFIG_X86_64
+extern pgd_t trampoline_pgd_entry;
 #endif
 
 /* local pte updates need not use xchg for locking */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 42cd333616c4..7c2ecdf7e064 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -457,10 +457,8 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
 
-#if IS_ENABLED(CONFIG_KVM)
 /* Save actual FS/GS selectors and bases to current->thread */
-void save_fsgs_for_kvm(void);
-#endif
+void current_save_fsgs(void);
 #else	/* X86_64 */
 #ifdef CONFIG_STACKPROTECTOR
 /*
@@ -575,7 +573,7 @@ native_load_sp0(unsigned long sp0)
 	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
-static inline void native_swapgs(void)
+static __always_inline void native_swapgs(void)
 {
 #ifdef CONFIG_X86_64
 	asm volatile("swapgs" ::: "memory");
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 9804a7957f4e..7fb482f0f25b 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -90,6 +90,15 @@ static __always_inline void boot_init_stack_canary(void)
 #endif
 }
 
+static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
+{
+#ifdef CONFIG_X86_64
+	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
+#else
+	per_cpu(stack_canary.canary, cpu) = idle->stack_canary;
+#endif
+}
+
 static inline void setup_stack_canary_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -119,6 +128,9 @@ static inline void load_stack_canary_segment(void)
 static inline void setup_stack_canary_segment(int cpu)
 { }
 
+static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
+{ }
+
 static inline void load_stack_canary_segment(void)
 {
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 79d8d5496330..f4234575f3fd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -193,7 +193,7 @@ static inline void sched_clear_itmt_support(void)
 }
 #endif /* CONFIG_SCHED_MC_PRIO */
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_X86_64)
 #include <asm/cpufeature.h>
 
 DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key);