1 files changed, 45 insertions, 80 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f85680b86524..396d41f192ca 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1674,43 +1674,15 @@ static void vmcs_load(struct vmcs *vmcs)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-/*
- * This bitmap is used to indicate whether the vmclear
- * operation is enabled on all cpus. All disabled by
- * default.
- */
-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
-
-static inline void crash_enable_local_vmclear(int cpu)
-{
-	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline void crash_disable_local_vmclear(int cpu)
-{
-	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline int crash_local_vmclear_enabled(int cpu)
-{
-	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
 static void crash_vmclear_local_loaded_vmcss(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
 
-	if (!crash_local_vmclear_enabled(cpu))
-		return;
-
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 }
-#else
-static inline void crash_enable_local_vmclear(int cpu) { }
-static inline void crash_disable_local_vmclear(int cpu) { }
 #endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
@@ -1722,19 +1694,24 @@ static void __loaded_vmcs_clear(void *arg)
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
-	crash_disable_local_vmclear(cpu);
+
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 
 	/*
-	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
-	 * is before setting loaded_vmcs->vcpu to -1 which is done in
-	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
-	 * then adds the vmcs into percpu list before it is deleted.
+	 * Ensure all writes to loaded_vmcs, including deleting it from its
+	 * current percpu list, complete before setting loaded_vmcs->vcpu to
+	 * -1, otherwise a different cpu can see vcpu == -1 first and add
+	 * loaded_vmcs to its percpu list before it's deleted from this cpu's
+	 * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
 	 */
 	smp_wmb();
 
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -2497,18 +2474,17 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!already_loaded) {
 		loaded_vmcs_clear(vmx->loaded_vmcs);
 		local_irq_disable();
-		crash_disable_local_vmclear(cpu);
 
 		/*
-		 * Read loaded_vmcs->cpu should be before fetching
-		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
-		 * See the comments in __loaded_vmcs_clear().
+		 * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
+		 * this cpu's percpu list, otherwise it may not yet be deleted
+		 * from its previous cpu's percpu list.  Pairs with the
+		 * smb_wmb() in __loaded_vmcs_clear().
 		 */
 		smp_rmb();
 
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
-		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 	}
 
@@ -3800,21 +3776,6 @@ static int hardware_enable(void)
 	if (cr4_read_shadow() & X86_CR4_VMXE)
 		return -EBUSY;
 
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
-	/*
-	 * Now we can enable the vmclear operation in kdump
-	 * since the loaded_vmcss_on_cpu list on this cpu
-	 * has been initialized.
-	 *
-	 * Though the cpu is not in VMX operation now, there
-	 * is no problem to enable the vmclear operation
-	 * for the loaded_vmcss_on_cpu list is empty!
-	 */
-	crash_enable_local_vmclear(cpu);
-
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;
@@ -5631,6 +5592,8 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
+	BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
 	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
 	if (enable_ept)
 		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
@@ -6198,8 +6161,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	return (!to_vmx(vcpu)->nested.nested_run_pending &&
-		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return false;
+
+	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+		return true;
+
+	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
 		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
 			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
@@ -6284,7 +6252,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
  */
 static void kvm_machine_check(void)
 {
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_MCE)
 	struct pt_regs regs = {
 		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
 		.flags = X86_EFLAGS_IF,
@@ -8745,7 +8713,7 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
-	switch (exit_reason) {
+	switch ((u16)exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
 		if (is_nmi(intr_info))
 			return false;
@@ -9176,6 +9144,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -9314,15 +9283,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	if (!flexpriority_enabled &&
+	    !cpu_has_vmx_virtualize_x2apic_mode())
+		return;
+
 	/* Postpone execution until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
 		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
 		return;
 	}
 
-	if (!cpu_need_tpr_shadow(vcpu))
-		return;
-
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -11659,7 +11629,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 	}
 }
 
-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
@@ -11697,8 +11667,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
-	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
-	    nested_exit_on_intr(vcpu)) {
+	if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
@@ -12254,17 +12223,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	if (likely(!vmx->fail)) {
-		/*
-		 * TODO: SDM says that with acknowledge interrupt on
-		 * exit, bit 31 of the VM-exit interrupt information
-		 * (valid interrupt) is always set to 1 on
-		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
-		 * need kvm_cpu_has_interrupt().  See the commit
-		 * message for details.
-		 */
-		if (nested_exit_intr_ack_set(vcpu) &&
-		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    kvm_cpu_has_interrupt(vcpu)) {
+		if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+		    nested_exit_intr_ack_set(vcpu)) {
 			int irq = kvm_cpu_get_interrupt(vcpu);
 			WARN_ON(irq < 0);
 			vmcs12->vm_exit_intr_info = irq |
@@ -12505,11 +12465,10 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa;
 	struct page *page = NULL;
 	u64 *pml_address;
 
@@ -12530,7 +12489,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address);
 		if (is_error_page(page))
@@ -12940,7 +12899,7 @@ module_exit(vmx_exit)
 
 static int __init vmx_init(void)
 {
-	int r;
+	int r, cpu;
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
 		     __alignof__(struct vcpu_vmx), THIS_MODULE);
@@ -12962,6 +12921,12 @@ static int __init vmx_init(void)
 		}
 	}
 
+	for_each_possible_cpu(cpu) {
+		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);