Merge tag 'kvm-x86-misc-6.8' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.8:

 - Turn off KVM_WERROR by default for all configs so that it's not
   inadvertantly enabled by non-KVM developers, which can be problematic for
   subsystems that require no regressions for W=1 builds.

 - Advertise all of the host-supported CPUID bits that enumerate IA32_SPEC_CTRL
   "features".

 - Don't force a masterclock update when a vCPU synchronizes to the current TSC
   generation, as updating the masterclock can cause kvmclock's time to "jump"
   unexpectedly, e.g. when userspace hotplugs a pre-created vCPU.

 - Use RIP-relative address to read kvm_rebooting in the VM-Enter fault paths,
   partly as a super minor optimization, but mostly to make KVM play nice with
   position independent executable builds.

6 files changed, 70 insertions, 41 deletions

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b9d35b6b19f7..87e3da7b0439 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -62,13 +62,13 @@ config KVM
 
 config KVM_WERROR
 	bool "Compile KVM with -Werror"
-	# KASAN may cause the build to fail due to larger frames
-	default y if X86_64 && !KASAN
-	# We use the dependency on !COMPILE_TEST to not be enabled
-	# blindly in allmodconfig or allyesconfig configurations
-	depends on KVM
-	depends on (X86_64 && !KASAN) || !COMPILE_TEST
-	depends on EXPERT
+	# Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against
+	# randomized configs from selecting KVM_WERROR=y, which doesn't play
+	# nice with KASAN.  KASAN builds generates warnings for the default
+	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
+	# Building KVM with -Werror and KASAN is still doable via enabling
+	# the kernel-wide WERROR=y.
+	depends on KVM && EXPERT && !KASAN
 	help
 	  Add -Werror to the build flags for KVM.
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index cab20216921b..727b6551e1df 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -685,6 +685,11 @@ void kvm_set_cpu_caps(void)
 		F(AMX_COMPLEX)
 	);
 
+	kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
+		F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) |
+		F(BHI_CTRL) | F(MCDT_NO)
+	);
+
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
 	);
@@ -966,13 +971,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* function 7 has additional index. */
 	case 7:
-		entry->eax = min(entry->eax, 1u);
+		max_idx = entry->eax = min(entry->eax, 2u);
 		cpuid_entry_override(entry, CPUID_7_0_EBX);
 		cpuid_entry_override(entry, CPUID_7_ECX);
 		cpuid_entry_override(entry, CPUID_7_EDX);
 
-		/* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */
-		if (entry->eax == 1) {
+		/* KVM only supports up to 0x7.2, capped above via min(). */
+		if (max_idx >= 1) {
 			entry = do_host_cpuid(array, function, 1);
 			if (!entry)
 				goto out;
@@ -982,6 +987,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->ebx = 0;
 			entry->ecx = 0;
 		}
+		if (max_idx >= 2) {
+			entry = do_host_cpuid(array, function, 2);
+			if (!entry)
+				goto out;
+
+			cpuid_entry_override(entry, CPUID_7_2_EDX);
+			entry->ecx = 0;
+			entry->ebx = 0;
+			entry->eax = 0;
+		}
 		break;
 	case 0xa: { /* Architectural Performance Monitoring */
 		union cpuid10_eax eax;
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index b81650678375..aadefcaa9561 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_7_1_EDX,
 	CPUID_8000_0007_EDX,
 	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
 
+/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */
+#define X86_FEATURE_INTEL_PSFD		KVM_X86_FEATURE(CPUID_7_2_EDX, 0)
+#define X86_FEATURE_IPRED_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
+#define KVM_X86_FEATURE_RRSBA_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
+#define X86_FEATURE_DDPD_U		KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
+#define X86_FEATURE_BHI_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
+
 /* CPUID level 0x80000007 (EDX). */
 #define KVM_X86_FEATURE_CONSTANT_TSC	KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8)
 
@@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX},
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
+	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 };
 
 /*
@@ -106,18 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
  */
 static __always_inline u32 __feature_translate(int x86_feature)
 {
-	if (x86_feature == X86_FEATURE_SGX1)
-		return KVM_X86_FEATURE_SGX1;
-	else if (x86_feature == X86_FEATURE_SGX2)
-		return KVM_X86_FEATURE_SGX2;
-	else if (x86_feature == X86_FEATURE_SGX_EDECCSSA)
-		return KVM_X86_FEATURE_SGX_EDECCSSA;
-	else if (x86_feature == X86_FEATURE_CONSTANT_TSC)
-		return KVM_X86_FEATURE_CONSTANT_TSC;
-	else if (x86_feature == X86_FEATURE_PERFMON_V2)
-		return KVM_X86_FEATURE_PERFMON_V2;
-
-	return x86_feature;
+#define KVM_X86_TRANSLATE_FEATURE(f)	\
+	case X86_FEATURE_##f: return KVM_X86_FEATURE_##f
+
+	switch (x86_feature) {
+	KVM_X86_TRANSLATE_FEATURE(SGX1);
+	KVM_X86_TRANSLATE_FEATURE(SGX2);
+	KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA);
+	KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
+	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
+	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+	default:
+		return x86_feature;
+	}
 }
 
 static __always_inline u32 __feature_leaf(int x86_feature)
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index ef2ebabb059c..9499f9c6b077 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-10:	cmpb $0, kvm_rebooting
+10:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
-30:	cmpb $0, kvm_rebooting
+30:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 4b
 	ud2
-50:	cmpb $0, kvm_rebooting
+50:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 6b
 	ud2
-70:	cmpb $0, kvm_rebooting
+70:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 8b
 	ud2
 
@@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-3:	cmpb $0, kvm_rebooting
+3:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index be275a0410a8..906ecd001511 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -289,7 +289,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
 	RET
 
 .Lfixup:
-	cmpb $0, kvm_rebooting
+	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne .Lvmfail
 	ud2
 .Lvmfail:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b6fca43cb455..4f4248c2941a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2513,26 +2513,29 @@ static inline int gtod_is_based_on_tsc(int mode)
 }
 #endif
 
-static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
+static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
 {
 #ifdef CONFIG_X86_64
-	bool vcpus_matched;
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 
-	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
-			 atomic_read(&vcpu->kvm->online_vcpus));
+	/*
+	 * To use the masterclock, the host clocksource must be based on TSC
+	 * and all vCPUs must have matching TSCs.  Note, the count for matching
+	 * vCPUs doesn't include the reference vCPU, hence "+1".
+	 */
+	bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 ==
+				 atomic_read(&vcpu->kvm->online_vcpus)) &&
+				gtod_is_based_on_tsc(gtod->clock.vclock_mode);
 
 	/*
-	 * Once the masterclock is enabled, always perform request in
-	 * order to update it.
-	 *
-	 * In order to enable masterclock, the host clocksource must be TSC
-	 * and the vcpus need to have matched TSCs.  When that happens,
-	 * perform request to enable masterclock.
+	 * Request a masterclock update if the masterclock needs to be toggled
+	 * on/off, or when starting a new generation and the masterclock is
+	 * enabled (compute_guest_tsc() requires the masterclock snapshot to be
+	 * taken _after_ the new generation is created).
 	 */
-	if (ka->use_master_clock ||
-	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
+	if ((ka->use_master_clock && new_generation) ||
+	    (ka->use_master_clock != use_master_clock))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2709,7 +2712,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	kvm_track_tsc_matching(vcpu);
+	kvm_track_tsc_matching(vcpu, !matched);
 }
 
 static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)