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()

9 files changed, 78 insertions, 39 deletions

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"