1 files changed, 68 insertions, 6 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 74674a6e4827..3b711cd261d7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -523,8 +523,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 				       data, offset, len, access);
 }
 
+static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
+{
+	return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) |
+	       rsvd_bits(1, 2);
+}
+
 /*
- * Load the pae pdptrs.  Return true is they are all valid.
+ * Load the pae pdptrs.  Return 1 if they are all valid, 0 otherwise.
  */
 int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 {
@@ -543,8 +549,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
 		if (is_present_gpte(pdpte[i]) &&
-		    (pdpte[i] &
-		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+		    (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
 			ret = 0;
 			goto out;
 		}
@@ -570,7 +575,7 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int r;
 
-	if (is_long_mode(vcpu) || !is_pae(vcpu))
+	if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
 		return false;
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
@@ -990,6 +995,43 @@ static u32 emulated_msrs[] = {
 
 static unsigned num_emulated_msrs;
 
+u64 kvm_get_arch_capabilities(void)
+{
+	u64 data;
+
+	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		data |= ARCH_CAP_RDCL_NO;
+	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		data |= ARCH_CAP_SSB_NO;
+	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;
+}
+
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
 static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & EFER_FFXSR) {
@@ -2065,6 +2107,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_AMD64_BU_CFG2:
 		break;
 
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vcpu->arch.arch_capabilities = data;
+		break;
 	case MSR_EFER:
 		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
@@ -2339,6 +2386,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = 0x100000000ULL;
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_arch_capabilities(vcpu))
+			return 1;
+		msr_info->data = vcpu->arch.arch_capabilities;
+		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -5486,8 +5539,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
 				return EMULATE_DONE;
-			if (ctxt->have_exception && inject_emulated_exception(vcpu))
+			if (ctxt->have_exception) {
+				/*
+				 * #UD should result in just EMULATION_FAILED, and trap-like
+				 * exception should not be encountered during decode.
+				 */
+				WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR ||
+					     exception_type(ctxt->exception.vector) == EXCPT_TRAP);
+				inject_emulated_exception(vcpu);
 				return EMULATE_DONE;
+			}
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
 			return handle_emulation_failure(vcpu);
@@ -7155,7 +7216,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+	if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
@@ -7379,6 +7440,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int r;
 
+	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
 	kvm_vcpu_mtrr_init(vcpu);
 	r = vcpu_load(vcpu);
 	if (r)