1 files changed, 131 insertions, 32 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index e19dabf1848b..3902c28fb6cb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -32,7 +32,7 @@
 u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_cpu_caps);
 
-static u32 xstate_required_size(u64 xstate_bv, bool compacted)
+u32 xstate_required_size(u64 xstate_bv, bool compacted)
 {
 	int feature_bit = 0;
 	u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
@@ -42,7 +42,11 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 		if (xstate_bv & 0x1) {
 		        u32 eax, ebx, ecx, edx, offset;
 		        cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
-			offset = compacted ? ret : ebx;
+			/* ECX[1]: 64B alignment in compacted form */
+			if (compacted)
+				offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret;
+			else
+				offset = ebx;
 			ret = max(ret, offset + eax);
 		}
 
@@ -80,9 +84,12 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	return NULL;
 }
 
-static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent)
+static int kvm_check_cpuid(struct kvm_vcpu *vcpu,
+			   struct kvm_cpuid_entry2 *entries,
+			   int nent)
 {
 	struct kvm_cpuid_entry2 *best;
+	u64 xfeatures;
 
 	/*
 	 * The existing code assumes virtual address is 48-bit or 57-bit in the
@@ -96,6 +103,41 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent)
 			return -EINVAL;
 	}
 
+	/*
+	 * Exposing dynamic xfeatures to the guest requires additional
+	 * enabling in the FPU, e.g. to expand the guest XSAVE state size.
+	 */
+	best = cpuid_entry2_find(entries, nent, 0xd, 0);
+	if (!best)
+		return 0;
+
+	xfeatures = best->eax | ((u64)best->edx << 32);
+	xfeatures &= XFEATURE_MASK_USER_DYNAMIC;
+	if (!xfeatures)
+		return 0;
+
+	return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures);
+}
+
+/* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */
+static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
+				 int nent)
+{
+	struct kvm_cpuid_entry2 *orig;
+	int i;
+
+	if (nent != vcpu->arch.cpuid_nent)
+		return -EINVAL;
+
+	for (i = 0; i < nent; i++) {
+		orig = &vcpu->arch.cpuid_entries[i];
+		if (e2[i].function != orig->function ||
+		    e2[i].index != orig->index ||
+		    e2[i].eax != orig->eax || e2[i].ebx != orig->ebx ||
+		    e2[i].ecx != orig->ecx || e2[i].edx != orig->edx)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -125,14 +167,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 	}
 }
 
-struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu,
+					      struct kvm_cpuid_entry2 *entries, int nent)
 {
 	u32 base = vcpu->arch.kvm_cpuid_base;
 
 	if (!base)
 		return NULL;
 
-	return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0);
+	return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, 0);
+}
+
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+{
+	return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries,
+					     vcpu->arch.cpuid_nent);
 }
 
 void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
@@ -147,11 +196,12 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
 		vcpu->arch.pv_cpuid.features = best->eax;
 }
 
-void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
+				       int nent)
 {
 	struct kvm_cpuid_entry2 *best;
 
-	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	best = cpuid_entry2_find(entries, nent, 1, 0);
 	if (best) {
 		/* Update OSXSAVE bit */
 		if (boot_cpu_has(X86_FEATURE_XSAVE))
@@ -162,33 +212,38 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 			   vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE);
 	}
 
-	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	best = cpuid_entry2_find(entries, nent, 7, 0);
 	if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7)
 		cpuid_entry_change(best, X86_FEATURE_OSPKE,
 				   kvm_read_cr4_bits(vcpu, X86_CR4_PKE));
 
-	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
+	best = cpuid_entry2_find(entries, nent, 0xD, 0);
 	if (best)
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, false);
 
-	best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
+	best = cpuid_entry2_find(entries, nent, 0xD, 1);
 	if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) ||
 		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	best = kvm_find_kvm_cpuid_features(vcpu);
+	best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
 	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
 	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
-		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+		best = cpuid_entry2_find(entries, nent, 0x1, 0);
 		if (best)
 			cpuid_entry_change(best, X86_FEATURE_MWAIT,
 					   vcpu->arch.ia32_misc_enable_msr &
 					   MSR_IA32_MISC_ENABLE_MWAIT);
 	}
 }
+
+void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+{
+	__kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
+}
 EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -276,21 +331,36 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu)
 static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
                         int nent)
 {
-    int r;
+	int r;
+
+	__kvm_update_cpuid_runtime(vcpu, e2, nent);
+
+	/*
+	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+	 * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with
+	 * the core vCPU model on the fly. It would've been better to forbid any
+	 * KVM_SET_CPUID{,2} calls after KVM_RUN altogether but unfortunately
+	 * some VMMs (e.g. QEMU) reuse vCPU fds for CPU hotplug/unplug and do
+	 * KVM_SET_CPUID{,2} again. To support this legacy behavior, check
+	 * whether the supplied CPUID data is equal to what's already set.
+	 */
+	if (vcpu->arch.last_vmentry_cpu != -1)
+		return kvm_cpuid_check_equal(vcpu, e2, nent);
 
-    r = kvm_check_cpuid(e2, nent);
-    if (r)
-        return r;
+	r = kvm_check_cpuid(vcpu, e2, nent);
+	if (r)
+		return r;
 
-    kvfree(vcpu->arch.cpuid_entries);
-    vcpu->arch.cpuid_entries = e2;
-    vcpu->arch.cpuid_nent = nent;
+	kvfree(vcpu->arch.cpuid_entries);
+	vcpu->arch.cpuid_entries = e2;
+	vcpu->arch.cpuid_nent = nent;
 
-    kvm_update_kvm_cpuid_base(vcpu);
-    kvm_update_cpuid_runtime(vcpu);
-    kvm_vcpu_after_set_cpuid(vcpu);
+	kvm_update_kvm_cpuid_base(vcpu);
+	kvm_vcpu_after_set_cpuid(vcpu);
 
-    return 0;
+	return 0;
 }
 
 /* when an old userspace process fills a new kernel module */
@@ -422,9 +492,11 @@ void kvm_set_cpu_caps(void)
 #ifdef CONFIG_X86_64
 	unsigned int f_gbpages = F(GBPAGES);
 	unsigned int f_lm = F(LM);
+	unsigned int f_xfd = F(XFD);
 #else
 	unsigned int f_gbpages = 0;
 	unsigned int f_lm = 0;
+	unsigned int f_xfd = 0;
 #endif
 	memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps));
 
@@ -492,7 +564,8 @@ void kvm_set_cpu_caps(void)
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
 		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) |
-		F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16)
+		F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) |
+		F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16)
 	);
 
 	/* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */
@@ -511,7 +584,7 @@ void kvm_set_cpu_caps(void)
 	);
 
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
-		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES)
+		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
 	);
 
 	kvm_cpu_cap_init_scattered(CPUID_12_EAX,
@@ -523,7 +596,7 @@ void kvm_set_cpu_caps(void)
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
 		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) |
-		F(TOPOEXT) | F(PERFCTR_CORE)
+		F(TOPOEXT) | 0 /* PERFCTR_CORE */
 	);
 
 	kvm_cpu_cap_mask(CPUID_8000_0001_EDX,
@@ -637,6 +710,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
 	case 0x14:
 	case 0x17:
 	case 0x18:
+	case 0x1d:
+	case 0x1e:
 	case 0x1f:
 	case 0x8000001d:
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -770,10 +845,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		perf_get_x86_pmu_capability(&cap);
 
 		/*
-		 * Only support guest architectural pmu on a host
-		 * with architectural pmu.
+		 * The guest architecture pmu is only supported if the architecture
+		 * pmu exists on the host and the module parameters allow it.
 		 */
-		if (!cap.version)
+		if (!cap.version || !enable_pmu)
 			memset(&cap, 0, sizeof(cap));
 
 		eax.split.version_id = min(cap.version, 2);
@@ -811,11 +886,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 				goto out;
 		}
 		break;
-	case 0xd:
-		entry->eax &= supported_xcr0;
+	case 0xd: {
+		u64 guest_perm = xstate_get_guest_group_perm();
+
+		entry->eax &= supported_xcr0 & guest_perm;
 		entry->ebx = xstate_required_size(supported_xcr0, false);
 		entry->ecx = entry->ebx;
-		entry->edx &= supported_xcr0 >> 32;
+		entry->edx &= (supported_xcr0 & guest_perm) >> 32;
 		if (!supported_xcr0)
 			break;
 
@@ -859,9 +936,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 				--array->nent;
 				continue;
 			}
+
+			if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
+				entry->ecx &= ~BIT_ULL(2);
 			entry->edx = 0;
 		}
 		break;
+	}
 	case 0x12:
 		/* Intel SGX */
 		if (!kvm_cpu_cap_has(X86_FEATURE_SGX)) {
@@ -906,6 +987,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 				goto out;
 		}
 		break;
+	/* Intel AMX TILE */
+	case 0x1d:
+		if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) {
+			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+			break;
+		}
+
+		for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) {
+			if (!do_host_cpuid(array, function, i))
+				goto out;
+		}
+		break;
+	case 0x1e: /* TMUL information */
+		if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) {
+			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+			break;
+		}
+		break;
 	case KVM_CPUID_SIGNATURE: {
 		const u32 *sigptr = (const u32 *)KVM_SIGNATURE;
 		entry->eax = KVM_CPUID_FEATURES;