Merge tag 'x86_cpu_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpuid updates from Borislav Petkov:

 - Cache the AMD debug registers in per-CPU variables to avoid MSR
   writes where possible, when supporting a debug registers swap feature
   for SEV-ES guests

 - Add support for AMD's version of eIBRS called Automatic IBRS which is
   a set-and-forget control of indirect branch restriction speculation
   resources on privilege change

 - Add support for a new x86 instruction - LKGS - Load kernel GS which
   is part of the FRED infrastructure

 - Reset SPEC_CTRL upon init to accomodate use cases like kexec which
   rediscover

 - Other smaller fixes and cleanups

* tag 'x86_cpu_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/amd: Cache debug register values in percpu variables
  KVM: x86: Propagate the AMD Automatic IBRS feature to the guest
  x86/cpu: Support AMD Automatic IBRS
  x86/cpu, kvm: Add the SMM_CTL MSR not present feature
  x86/cpu, kvm: Add the Null Selector Clears Base feature
  x86/cpu, kvm: Move X86_FEATURE_LFENCE_RDTSC to its native leaf
  x86/cpu, kvm: Add the NO_NESTED_DATA_BP feature
  KVM: x86: Move open-coded CPUID leaf 0x80000021 EAX bit propagation code
  x86/cpu, kvm: Add support for CPUID_80000021_EAX
  x86/gsseg: Add the new <asm/gsseg.h> header to <asm/asm-prototypes.h>
  x86/gsseg: Use the LKGS instruction if available for load_gs_index()
  x86/gsseg: Move load_gs_index() to its own new header file
  x86/gsseg: Make asm_load_gs_index() take an u16
  x86/opcode: Add the LKGS instruction to x86-opcode-map
  x86/cpufeature: Add the CPU feature bit for LKGS
  x86/bugs: Reset speculation control settings on init
  x86/cpu: Remove redundant extern x86_read_arch_cap_msr()

26 files changed, 210 insertions, 88 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 15739a2c0983..7ecd2aeeeffc 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -782,7 +782,7 @@ _ASM_NOKPROBE(common_interrupt_return)
 
 /*
  * Reload gs selector with exception handling
- * edi:  new selector
+ *  di:  new selector
  *
  * Is in entry.text as it shouldn't be instrumented.
  */
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 8f80de627c60..b1a98fa38828 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -12,6 +12,7 @@
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
 #include <asm/asm.h>
+#include <asm/gsseg.h>
 
 #ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1a85e1fb0922..ce0c8f7d3218 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -32,6 +32,7 @@ enum cpuid_leafs
 	CPUID_8000_0007_EBX,
 	CPUID_7_EDX,
 	CPUID_8000_001F_EAX,
+	CPUID_8000_0021_EAX,
 };
 
 #define X86_CAP_FMT_NUM "%d:%d"
@@ -94,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 20))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -118,8 +120,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 20))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 49973061b5bd..389ea336258f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			20	   /* N 32-bit words worth of info */
+#define NCAPINTS			21	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -97,7 +97,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+/* FREE, was #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 */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
@@ -315,6 +315,7 @@
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 #define X86_FEATURE_CMPCCXADD           (12*32+ 7) /* "" CMPccXADD instructions */
 #define X86_FEATURE_ARCH_PERFMON_EXT	(12*32+ 8) /* "" Intel Architectural PerfMon Extension */
+#define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
 
@@ -429,6 +430,13 @@
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 
+/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
+#define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
+#define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
+#define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index ca97442e8d49..66eb5e1ac4fb 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -148,9 +148,14 @@ static __always_inline void local_db_restore(unsigned long dr7)
 }
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern void set_dr_addr_mask(unsigned long mask, int dr);
+extern void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr);
+extern unsigned long amd_get_dr_addr_mask(unsigned int dr);
 #else
-static inline void set_dr_addr_mask(unsigned long mask, int dr) { }
+static inline void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr) { }
+static inline unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+	return 0;
+}
 #endif
 
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index c44b56f7ffba..5dfa4fb76f4b 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -124,6 +124,7 @@
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
 #define DISABLED_MASK19	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define DISABLED_MASK20	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/gsseg.h b/arch/x86/include/asm/gsseg.h
new file mode 100644
index 000000000000..ab6a595cea70
--- /dev/null
+++ b/arch/x86/include/asm/gsseg.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_X86_GSSEG_H
+#define _ASM_X86_GSSEG_H
+
+#include <linux/types.h>
+
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
+#include <asm/processor.h>
+#include <asm/nops.h>
+
+#ifdef CONFIG_X86_64
+
+extern asmlinkage void asm_load_gs_index(u16 selector);
+
+/* Replace with "lkgs %di" once binutils support LKGS instruction */
+#define LKGS_DI _ASM_BYTES(0xf2,0x0f,0x00,0xf7)
+
+static inline void native_lkgs(unsigned int selector)
+{
+	u16 sel = selector;
+	asm_inline volatile("1: " LKGS_DI
+			    _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k[sel])
+			    : [sel] "+D" (sel));
+}
+
+static inline void native_load_gs_index(unsigned int selector)
+{
+	if (cpu_feature_enabled(X86_FEATURE_LKGS)) {
+		native_lkgs(selector);
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		asm_load_gs_index(selector);
+		local_irq_restore(flags);
+	}
+}
+
+#endif /* CONFIG_X86_64 */
+
+static inline void __init lkgs_init(void)
+{
+#ifdef CONFIG_PARAVIRT_XXL
+#ifdef CONFIG_X86_64
+	if (cpu_feature_enabled(X86_FEATURE_LKGS))
+		pv_ops.cpu.load_gs_index = native_lkgs;
+#endif
+#endif
+}
+
+#ifndef CONFIG_PARAVIRT_XXL
+
+static inline void load_gs_index(unsigned int selector)
+{
+#ifdef CONFIG_X86_64
+	native_load_gs_index(selector);
+#else
+	loadsegment(gs, selector);
+#endif
+}
+
+#endif /* CONFIG_PARAVIRT_XXL */
+
+#endif /* _ASM_X86_GSSEG_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index b8d40ddeab00..e01aa74a6de7 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,6 +12,7 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/debugreg.h>
+#include <asm/gsseg.h>
 
 extern atomic64_t last_mm_ctx_id;
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 28d334fa8588..ad35355ee43e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
 #define EFER_LME		(1<<_EFER_LME)
@@ -33,6 +34,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /* Intel MSRs. Some also available on other CPUs */
 
@@ -49,6 +51,10 @@
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
 
+/* A mask for bits which the kernel toggles when controlling mitigations */
+#define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
+							| SPEC_CTRL_RRSBA_DIS_S)
+
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index aff774775c67..7ba1726b71c7 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -98,6 +98,7 @@
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK19	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define REQUIRED_MASK20	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index f358a23f228d..de48d1389936 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -120,17 +120,6 @@ static __always_inline void native_wbinvd(void)
 	asm volatile("wbinvd": : :"memory");
 }
 
-extern asmlinkage void asm_load_gs_index(unsigned int selector);
-
-static inline void native_load_gs_index(unsigned int selector)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	asm_load_gs_index(selector);
-	local_irq_restore(flags);
-}
-
 static inline unsigned long __read_cr4(void)
 {
 	return native_read_cr4();
@@ -184,16 +173,6 @@ static __always_inline void wbinvd(void)
 	native_wbinvd();
 }
 
-
-static inline void load_gs_index(unsigned int selector)
-{
-#ifdef CONFIG_X86_64
-	native_load_gs_index(selector);
-#else
-	loadsegment(gs, selector);
-#endif
-}
-
 #endif /* CONFIG_PARAVIRT_XXL */
 
 static __always_inline void clflush(volatile void *__p)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f769d6d08b43..380753b14cab 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -956,7 +956,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	init_amd_cacheinfo(c);
 
-	if (cpu_has(c, X86_FEATURE_XMM2)) {
+	if (!cpu_has(c, X86_FEATURE_LFENCE_RDTSC) && cpu_has(c, X86_FEATURE_XMM2)) {
 		/*
 		 * Use LFENCE for execution serialization.  On families which
 		 * don't have that MSR, LFENCE is already serializing.
@@ -1158,24 +1158,43 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 	return false;
 }
 
-void set_dr_addr_mask(unsigned long mask, int dr)
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask);
+
+static unsigned int amd_msr_dr_addr_masks[] = {
+	MSR_F16H_DR0_ADDR_MASK,
+	MSR_F16H_DR1_ADDR_MASK,
+	MSR_F16H_DR1_ADDR_MASK + 1,
+	MSR_F16H_DR1_ADDR_MASK + 2
+};
+
+void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
 {
-	if (!boot_cpu_has(X86_FEATURE_BPEXT))
+	int cpu = smp_processor_id();
+
+	if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
 		return;
 
-	switch (dr) {
-	case 0:
-		wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
-		break;
-	case 1:
-	case 2:
-	case 3:
-		wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
-		break;
-	default:
-		break;
-	}
+	if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+		return;
+
+	if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
+		return;
+
+	wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+	per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
+}
+
+unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
+		return 0;
+
+	if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+		return 0;
+
+	return per_cpu(amd_dr_addr_mask[dr], smp_processor_id());
 }
+EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
 
 u32 amd_get_highest_perf(void)
 {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 85168740f76a..cf81848b72f4 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -33,6 +33,7 @@
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
 #include <asm/tlbflush.h>
+#include <asm/cpu.h>
 
 #include "cpu.h"
 
@@ -144,9 +145,17 @@ void __init check_bugs(void)
 	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
 	 * init code as it is not enumerated and depends on the family.
 	 */
-	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+	if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
+		/*
+		 * Previously running kernel (kexec), may have some controls
+		 * turned ON. Clear them and let the mitigations setup below
+		 * rediscover them based on configuration.
+		 */
+		x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK;
+	}
+
 	/* Select the proper CPU mitigations before patching alternatives: */
 	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
@@ -1229,9 +1238,9 @@ static const char * const spectre_v2_strings[] = {
 	[SPECTRE_V2_NONE]			= "Vulnerable",
 	[SPECTRE_V2_RETPOLINE]			= "Mitigation: Retpolines",
 	[SPECTRE_V2_LFENCE]			= "Mitigation: LFENCE",
-	[SPECTRE_V2_EIBRS]			= "Mitigation: Enhanced IBRS",
-	[SPECTRE_V2_EIBRS_LFENCE]		= "Mitigation: Enhanced IBRS + LFENCE",
-	[SPECTRE_V2_EIBRS_RETPOLINE]		= "Mitigation: Enhanced IBRS + Retpolines",
+	[SPECTRE_V2_EIBRS]			= "Mitigation: Enhanced / Automatic IBRS",
+	[SPECTRE_V2_EIBRS_LFENCE]		= "Mitigation: Enhanced / Automatic IBRS + LFENCE",
+	[SPECTRE_V2_EIBRS_RETPOLINE]		= "Mitigation: Enhanced / Automatic IBRS + Retpolines",
 	[SPECTRE_V2_IBRS]			= "Mitigation: IBRS",
 };
 
@@ -1300,7 +1309,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	     cmd == SPECTRE_V2_CMD_EIBRS_LFENCE ||
 	     cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) &&
 	    !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
-		pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n",
+		pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n",
 		       mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
 	}
@@ -1486,8 +1495,12 @@ static void __init spectre_v2_select_mitigation(void)
 		pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
 
 	if (spectre_v2_in_ibrs_mode(mode)) {
-		x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
-		update_spec_ctrl(x86_spec_ctrl_base);
+		if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+			msr_set_bit(MSR_EFER, _EFER_AUTOIBRS);
+		} else {
+			x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+			update_spec_ctrl(x86_spec_ctrl_base);
+		}
 	}
 
 	switch (mode) {
@@ -1571,8 +1584,8 @@ static void __init spectre_v2_select_mitigation(void)
 	/*
 	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
 	 * and Enhanced IBRS protect firmware too, so enable IBRS around
-	 * firmware calls only when IBRS / Enhanced IBRS aren't otherwise
-	 * enabled.
+	 * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't
+	 * otherwise enabled.
 	 *
 	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
 	 * the user might select retpoline on the kernel command line and if
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 65ceabb2e114..a394bbba7a4b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1093,6 +1093,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x8000001f)
 		c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f);
 
+	if (c->extended_cpuid_level >= 0x80000021)
+		c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021);
+
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
 
@@ -1226,8 +1229,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
 
 	/* Zhaoxin Family 7 */
 	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
@@ -1340,8 +1343,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
-	if (ia32_cap & ARCH_CAP_IBRS_ALL)
+	/*
+	 * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature
+	 * flag and protect from vendor-specific bugs via the whitelist.
+	 */
+	if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+		if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
+		    !(ia32_cap & ARCH_CAP_PBRSB_NO))
+			setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
+	}
 
 	if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
 	    !(ia32_cap & ARCH_CAP_MDS_NO)) {
@@ -1403,11 +1414,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_RETBLEED);
 	}
 
-	if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) &&
-	    !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
-	    !(ia32_cap & ARCH_CAP_PBRSB_NO))
-		setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
-
 	if (cpu_matches(cpu_vuln_blacklist, SMT_RSB))
 		setup_force_cpu_bug(X86_BUG_SMT_RSB);
 
@@ -1687,9 +1693,7 @@ void check_null_seg_clears_base(struct cpuinfo_x86 *c)
 	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
-	/* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */
-	if (c->extended_cpuid_level >= 0x80000021 &&
-	    cpuid_eax(0x80000021) & BIT(6))
+	if (cpu_has(c, X86_FEATURE_NULL_SEL_CLR_BASE))
 		return;
 
 	/*
@@ -1964,6 +1968,7 @@ void __init identify_boot_cpu(void)
 	setup_cr_pinning();
 
 	tsx_init();
+	lkgs_init();
 }
 
 void identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 7c9b5893c30a..57a5349e6954 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -83,6 +83,4 @@ unsigned int aperfmperf_get_khz(int cpu);
 extern void x86_spec_ctrl_setup_ap(void);
 extern void update_srbds_msr(void);
 
-extern u64 x86_read_arch_cap_msr(void);
-
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index 8009c8346d8f..b31ee4f1657a 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -11,6 +11,7 @@
 #include <linux/cpufeature.h>
 
 #include <asm/cmdline.h>
+#include <asm/cpu.h>
 
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index bbb0f737aab1..b01644c949b2 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -127,7 +127,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 
 	set_debugreg(*dr7, 7);
 	if (info->mask)
-		set_dr_addr_mask(info->mask, i);
+		amd_set_dr_addr_mask(info->mask, i);
 
 	return 0;
 }
@@ -166,7 +166,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 
 	set_debugreg(dr7, 7);
 	if (info->mask)
-		set_dr_addr_mask(0, i);
+		amd_set_dr_addr_mask(0, i);
 
 	/*
 	 * Ensure the write to cpu_dr7 is after we've set the DR7 register.
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5bf4f0b2f35d..42e182868873 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -32,6 +32,7 @@
 #include <asm/special_insns.h>
 #include <asm/tlb.h>
 #include <asm/io_bitmap.h>
+#include <asm/gsseg.h>
 
 /*
  * nop stub, which must not clobber anything *including the stack* to
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index f042dcdf1f16..9027fc088f97 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -31,6 +31,7 @@
 #include <asm/sigframe.h>
 #include <asm/sighandling.h>
 #include <asm/smap.h>
+#include <asm/gsseg.h>
 
 #ifdef CONFIG_IA32_EMULATION
 #include <asm/ia32_unistd.h>
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 3c883e064242..3ffbab0081f4 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -12,6 +12,7 @@
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
+#include <asm/gsseg.h>
 
 #include "tls.h"
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 596061c1610e..7f1b585f9a67 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -741,6 +741,27 @@ void kvm_set_cpu_caps(void)
 		0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) |
 		F(SME_COHERENT));
 
+	kvm_cpu_cap_mask(CPUID_8000_0021_EAX,
+		F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ |
+		F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */
+	);
+
+	/*
+	 * Synthesize "LFENCE is serializing" into the AMD-defined entry in
+	 * KVM's supported CPUID if the feature is reported as supported by the
+	 * kernel.  LFENCE_RDTSC was a Linux-defined synthetic feature long
+	 * before AMD joined the bandwagon, e.g. LFENCE is serializing on most
+	 * CPUs that support SSE2.  On CPUs that don't support AMD's leaf,
+	 * kvm_cpu_cap_mask() will unfortunately drop the flag due to ANDing
+	 * the mask with the raw host CPUID, and reporting support in AMD's
+	 * leaf can make it easier for userspace to detect the feature.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
+		kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC);
+	if (!static_cpu_has_bug(X86_BUG_NULL_SEG))
+		kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE);
+	kvm_cpu_cap_set(X86_FEATURE_NO_SMM_CTL_MSR);
+
 	kvm_cpu_cap_mask(CPUID_C000_0001_EDX,
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
 		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
@@ -1222,25 +1243,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	case 0x80000021:
 		entry->ebx = entry->ecx = entry->edx = 0;
-		/*
-		 * Pass down these bits:
-		 *    EAX      0      NNDBP, Processor ignores nested data breakpoints
-		 *    EAX      2      LAS, LFENCE always serializing
-		 *    EAX      6      NSCB, Null selector clear base
-		 *
-		 * Other defined bits are for MSRs that KVM does not expose:
-		 *   EAX      3      SPCL, SMM page configuration lock
-		 *   EAX      13     PCMSR, Prefetch control MSR
-		 *
-		 * KVM doesn't support SMM_CTL.
-		 *   EAX       9     SMM_CTL MSR is not supported
-		 */
-		entry->eax &= BIT(0) | BIT(2) | BIT(6);
-		entry->eax |= BIT(9);
-		if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC))
-			entry->eax |= BIT(2);
-		if (!static_cpu_has_bug(X86_BUG_NULL_SEG))
-			entry->eax |= BIT(6);
+		cpuid_entry_override(entry, CPUID_8000_0021_EAX);
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 042d0aca3c92..81f4e9ce0c77 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -68,6 +68,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_12_EAX]        = {0x00000012, 0, CPUID_EAX},
 	[CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX},
 	[CPUID_7_1_EDX]       = {         7, 1, CPUID_EDX},
+	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9a194aa1a75a..60c7c880266b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4969,6 +4969,9 @@ static __init int svm_hardware_setup(void)
 
 	tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
 
+	if (boot_cpu_has(X86_FEATURE_AUTOIBRS))
+		kvm_enable_efer_bits(EFER_AUTOIBRS);
+
 	/* Check for pause filtering support */
 	if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
 		pause_filter_count = 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2c299d47e69..0735fbc9ba8c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1689,6 +1689,9 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 
 static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
+	if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS))
+		return false;
+
 	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
 		return false;
 
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index d12d1358f96d..5168ee0360b2 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1047,6 +1047,7 @@ GrpTable: Grp6
 3: LTR Ew
 4: VERR Ew
 5: VERW Ew
+6: LKGS Ew (F2)
 EndTable
 
 GrpTable: Grp7
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5cacd4890bab..bb59cc6ddb2d 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -276,6 +276,7 @@ static void __init xen_init_capabilities(void)
 	setup_clear_cpu_cap(X86_FEATURE_ACC);
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	setup_clear_cpu_cap(X86_FEATURE_SME);
+	setup_clear_cpu_cap(X86_FEATURE_LKGS);
 
 	/*
 	 * Xen PV would need some work to support PCID: CR3 handling as well