1 files changed, 113 insertions, 73 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0ed07d8d2caa..5d530521f11d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -212,7 +212,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
-	{ "largepages", VM_STAT(lpages) },
+	{ "largepages", VM_STAT(lpages, .mode = 0444) },
+	{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -360,8 +361,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	if (!kvm_rebooting)
-		BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
-
 	if (cr4 & CR4_RESERVED_BITS)
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+		return -EINVAL;
+
+	return 0;
+}
+
+int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long old_cr4 = kvm_read_cr4(vcpu);
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -1125,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
  * may depend on host virtualization features rather than host cpu features.
  */
 
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1161,13 +1171,6 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
 	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
 	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
-	MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19,
-	MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21,
-	MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23,
-	MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25,
-	MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27,
-	MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29,
-	MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31,
 	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
@@ -1177,18 +1180,12 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31,
 };
 
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1227,7 +1224,7 @@ static u32 emulated_msrs[] = {
 	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
 	 * We always support the "true" VMX control MSRs, even if the host
 	 * processor does not, so I am putting these registers here rather
-	 * than in msrs_to_save.
+	 * than in msrs_to_save_all.
 	 */
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@@ -1246,13 +1243,14 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_POLL_CONTROL,
 };
 
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
 static unsigned num_emulated_msrs;
 
 /*
  * List of msr numbers which are used to expose MSR-based features that
  * can be used by a hypervisor to validate requested CPU features.
  */
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
 	MSR_IA32_VMX_PINBASED_CTLS,
@@ -1277,6 +1275,7 @@ static u32 msr_based_features[] = {
 	MSR_IA32_ARCH_CAPABILITIES,
 };
 
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
 static u64 kvm_get_arch_capabilities(void)
@@ -1287,6 +1286,14 @@ static u64 kvm_get_arch_capabilities(void)
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
 
 	/*
+	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+	 * the nested hypervisor runs with NX huge pages.  If it is not,
+	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+	 * L1 guests, so it need not worry about its own (L2) guests.
+	 */
+	data |= ARCH_CAP_PSCHANGE_MC_NO;
+
+	/*
 	 * If we're doing cache flushes (either "always" or "cond")
 	 * we will do one whenever the guest does a vmlaunch/vmresume.
 	 * If an outer hypervisor is doing the cache flush for us
@@ -1305,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void)
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
 
+	/*
+	 * On TAA affected systems, export MDS_NO=0 when:
+	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+	 *	- Updated microcode is present. This is detected by
+	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+	 *	  that VERW clears CPU buffers.
+	 *
+	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+	 * mitigation and don't complain:
+	 *
+	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
+	 *
+	 * If TSX is disabled on the system, guests are also mitigated against
+	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
+	    (data & ARCH_CAP_TSX_CTRL_MSR))
+		data &= ~ARCH_CAP_MDS_NO;
+
 	return data;
 }
 
@@ -2543,6 +2569,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2708,8 +2735,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2723,14 +2748,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -5097,23 +5121,28 @@ out:
 
 static void kvm_init_msr_list(void)
 {
+	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
-	unsigned i, j;
+	unsigned i;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
-			 "Please update the fixed PMCs in msrs_to_save[]");
-	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32,
-			 "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]");
+			 "Please update the fixed PMCs in msrs_to_saved_all[]");
+
+	perf_get_x86_pmu_capability(&x86_pmu);
+
+	num_msrs_to_save = 0;
+	num_emulated_msrs = 0;
+	num_msr_based_features = 0;
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
-		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
 		 * to the guests in some cases.
 		 */
-		switch (msrs_to_save[i]) {
+		switch (msrs_to_save_all[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_mpx_supported())
 				continue;
@@ -5141,43 +5170,43 @@ static void kvm_init_msr_list(void)
 			break;
 		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
 			if (!kvm_x86_ops->pt_supported() ||
-				msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
+			break;
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
 		}
 		default:
 			break;
 		}
 
-		if (j < i)
-			msrs_to_save[j] = msrs_to_save[i];
-		j++;
+		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
 	}
-	num_msrs_to_save = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
 			continue;
 
-		if (j < i)
-			emulated_msrs[j] = emulated_msrs[i];
-		j++;
+		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
 	}
-	num_emulated_msrs = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
 		struct kvm_msr_entry msr;
 
-		msr.index = msr_based_features[i];
+		msr.index = msr_based_features_all[i];
 		if (kvm_get_msr_feature(&msr))
 			continue;
 
-		if (j < i)
-			msr_based_features[j] = msr_based_features[i];
-		j++;
+		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
 	}
-	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -7937,8 +7966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -8714,10 +8747,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			(sregs->cr4 & X86_CR4_OSXSAVE))
-		return  -EINVAL;
-
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
@@ -8736,7 +8765,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 			return -EINVAL;
 	}
 
-	return 0;
+	return kvm_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -9427,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
@@ -9455,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return kvm_x86_ops->vm_init(kvm);
 }
 
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return kvm_mmu_post_init_vm(kvm);
+}
+
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
@@ -9556,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 }
 EXPORT_SYMBOL_GPL(x86_set_memory_region);
 
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+	kvm_mmu_pre_destroy_vm(kvm);
+}
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {