1 files changed, 133 insertions, 39 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 858dd0d89b02..8a51442247c5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,8 +90,8 @@ 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)
@@ -191,7 +191,8 @@ 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 }
@@ -275,13 +276,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -306,23 +308,27 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_apic_base);
 
+enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
+{
+	return kvm_apic_mode(kvm_get_apic_base(vcpu));
+}
+EXPORT_SYMBOL_GPL(kvm_get_apic_mode);
+
 int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
-	u64 old_state = vcpu->arch.apic_base &
-		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
-	u64 new_state = msr_info->data &
-		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
+	enum lapic_mode new_mode = kvm_apic_mode(msr_info->data);
 	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff |
 		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
 
-	if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE)
-		return 1;
-	if (!msr_info->host_initiated &&
-	    ((new_state == MSR_IA32_APICBASE_ENABLE &&
-	      old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) ||
-	     (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) &&
-	      old_state == 0)))
+	if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
 		return 1;
+	if (!msr_info->host_initiated) {
+		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
+			return 1;
+		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
+			return 1;
+	}
 
 	kvm_lapic_set_base(vcpu, msr_info->data);
 	return 0;
@@ -563,8 +569,14 @@ 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)
 {
@@ -583,8 +595,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
 		if ((pdpte[i] & PT_PRESENT_MASK) &&
-		    (pdpte[i] &
-		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+		    (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
 			ret = 0;
 			goto out;
 		}
@@ -610,7 +621,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int r;
 
-	if (is_long_mode(vcpu) || !is_pae(vcpu))
+	if (!is_pae_paging(vcpu))
 		return false;
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
@@ -839,8 +850,8 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (is_long_mode(vcpu) &&
 	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
 		return 1;
-	else if (is_pae(vcpu) && is_paging(vcpu) &&
-		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+	else if (is_pae_paging(vcpu) &&
+		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
 		return 1;
 
 	vcpu->arch.cr3 = cr3;
@@ -1061,6 +1072,14 @@ u64 kvm_get_arch_capabilities(void)
 	rdmsrl_safe(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
@@ -1072,8 +1091,40 @@ u64 kvm_get_arch_capabilities(void)
 	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
 		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
 
+	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(X86_FEATURE_RTM))
+		data &= ~ARCH_CAP_TAA_NO;
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
+	else if (data & ARCH_CAP_TSX_CTRL_MSR)
+		data &= ~ARCH_CAP_MDS_NO;
+
+	/* KVM does not emulate MSR_IA32_TSX_CTRL.  */
+	data &= ~ARCH_CAP_TSX_CTRL_MSR;
 	return data;
 }
+
 EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
 
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
@@ -1392,7 +1443,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 			vcpu->arch.tsc_always_catchup = 1;
 			return 0;
 		} else {
-			WARN(1, "user requested TSC rate below hardware speed\n");
+			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
 			return -1;
 		}
 	}
@@ -1402,8 +1453,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 				user_tsc_khz, tsc_khz);
 
 	if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
-		WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
-			  user_tsc_khz);
+		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+			            user_tsc_khz);
 		return -1;
 	}
 
@@ -4721,6 +4772,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
 	/* kvm_write_guest_virt_system can pull in tons of pages. */
 	vcpu->arch.l1tf_flush_l1d = true;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }
@@ -5885,8 +5943,16 @@ 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);
@@ -5954,12 +6020,13 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE && ctxt->tf)
-			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
-		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+			kvm_rip_write(vcpu, ctxt->eip);
+			if (r == EMULATE_DONE && ctxt->tf)
+				kvm_vcpu_do_singlestep(vcpu, &r);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
+		}
 
 		/*
 		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
@@ -6104,17 +6171,17 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
 				continue;
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-			if (vcpu->cpu != smp_processor_id())
+			if (vcpu->cpu != raw_smp_processor_id())
 				send_ipi = 1;
 		}
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -6251,12 +6318,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -6922,10 +6989,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
-static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 {
 	++vcpu->stat.tlb_flush;
-	kvm_x86_ops->tlb_flush(vcpu);
+	kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
 }
 
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
@@ -6996,7 +7063,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			kvm_vcpu_flush_tlb(vcpu);
+			kvm_vcpu_flush_tlb(vcpu, true);
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
@@ -7726,7 +7793,7 @@ 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_pae_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
@@ -8309,6 +8376,7 @@ 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);
 
@@ -8338,6 +8406,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return 0;
 }
 
+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)
 {
 	int r;
@@ -8441,6 +8514,11 @@ 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) {
@@ -8711,6 +8789,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+		return true;
+
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+		kvm_test_request(KVM_REQ_SMI, vcpu) ||
+		 kvm_test_request(KVM_REQ_EVENT, vcpu))
+		return true;
+
+	if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.preempted_in_kernel;