Merge tag 'x86_cpu_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linu…

…x/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()

Documentation/admin-guide/hw-vuln/spectre.rst

@@ -610,9 +610,9 @@ kernel command line.
                 retpoline,generic       Retpolines
                 retpoline,lfence        LFENCE; indirect branch
                 retpoline,amd           alias for retpoline,lfence
-                eibrs                   enhanced IBRS
-                eibrs,retpoline         enhanced IBRS + Retpolines
-                eibrs,lfence            enhanced IBRS + LFENCE
+                eibrs                   Enhanced/Auto IBRS
+                eibrs,retpoline         Enhanced/Auto IBRS + Retpolines
+                eibrs,lfence            Enhanced/Auto IBRS + LFENCE
                 ibrs                    use IBRS to protect kernel
 
 		Not specifying this option is equivalent to

Documentation/admin-guide/kernel-parameters.txt

@@ -5740,9 +5740,9 @@
 			retpoline,generic - Retpolines
 			retpoline,lfence  - LFENCE; indirect branch
 			retpoline,amd     - alias for retpoline,lfence
-			eibrs		  - enhanced IBRS
-			eibrs,retpoline   - enhanced IBRS + Retpolines
-			eibrs,lfence      - enhanced IBRS + LFENCE
+			eibrs		  - Enhanced/Auto IBRS
+			eibrs,retpoline   - Enhanced/Auto IBRS + Retpolines
+			eibrs,lfence      - Enhanced/Auto IBRS + LFENCE
 			ibrs		  - use IBRS to protect kernel
 
 			Not specifying this option is equivalent to

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.
  */

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);

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 :	\

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)
  */

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 */

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 */

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 */

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;
 

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 */
 

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 */

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)

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)
 {