Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "The bigger part of the change is a revert for x86 hosts. Here the
  second patch was supposed to fix the first, but in reality it was just
  as broken, so both have to go.

  x86 host:

   - Revert incorrect assumption that cr3 changes come with preempt
     notifier callbacks (they don't when static branches are changed,
     for example)

  ARM host:

   - Correctly synchronise PMR and co on PSCI CPU_SUSPEND

   - Skip tests that depend on GICv3 when the HW isn't available"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: selftests: aarch64: Skip tests if we can't create a vgic-v3
  Revert "KVM: VMX: Save HOST_CR3 in vmx_prepare_switch_to_guest()"
  Revert "KVM: VMX: Save HOST_CR3 in vmx_set_host_fs_gs()"
  KVM: arm64: Don't miss pending interrupts for suspended vCPU

Author: torvalds

arch/arm64/kvm/psci.c

@@ -46,8 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 	 * specification (ARM DEN 0022A). This means all suspend states
 	 * for KVM will preserve the register state.
 	 */
-	kvm_vcpu_halt(vcpu);
-	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
+	kvm_vcpu_wfi(vcpu);
 
 	return PSCI_RET_SUCCESS;
 }

arch/x86/kvm/vmx/nested.c

@@ -246,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 	src = &prev->host_state;
 	dest = &vmx->loaded_vmcs->host_state;
 
-	vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel,
-				src->fs_base, src->gs_base);
+	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
 	dest->ldt_sel = src->ldt_sel;
 #ifdef CONFIG_X86_64
 	dest->ds_sel = src->ds_sel;
@@ -3056,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr4;
+	unsigned long cr3, cr4;
 	bool vm_fail;
 
 	if (!nested_early_check)
@@ -3079,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	 */
 	vmcs_writel(GUEST_RFLAGS, 0);
 
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);

arch/x86/kvm/vmx/vmx.c

@@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
-void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
-			     u16 fs_sel, u16 gs_sel,
-			     unsigned long fs_base, unsigned long gs_base)
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base)
 {
-	if (unlikely(cr3 != host->cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		host->cr3 = cr3;
-	}
 	if (unlikely(fs_sel != host->fs_sel)) {
 		if (!(fs_sel & 7))
 			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
@@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	gs_base = segment_base(gs_sel);
 #endif
 
-	vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(),
-				fs_sel, gs_sel, fs_base, gs_base);
-
+	vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
 	vmx->guest_state_loaded = true;
 }
 
@@ -6791,7 +6784,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr4;
+	unsigned long cr3, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!enable_vnmi &&
@@ -6834,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 	vcpu->arch.regs_dirty = 0;
 
+	/*
+	 * Refresh vmcs.HOST_CR3 if necessary.  This must be done immediately
+	 * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
+	 * it switches back to the current->mm, which can occur in KVM context
+	 * when switching to a temporary mm to patch kernel code, e.g. if KVM
+	 * toggles a static key while handling a VM-Exit.
+	 */
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);

arch/x86/kvm/vmx/vmx.h

@@ -374,9 +374,8 @@ int allocate_vpid(void);
 void free_vpid(int vpid);
 void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
 void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
-void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
-			     u16 fs_sel, u16 gs_sel,
-			     unsigned long fs_base, unsigned long gs_base);
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
 bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);

tools/testing/selftests/kvm/aarch64/arch_timer.c

@@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void)
 {
 	struct kvm_vm *vm;
 	unsigned int i;
+	int ret;
 	int nr_vcpus = test_args.nr_vcpus;
 
 	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void)
 
 	ucall_init(vm, NULL);
 	test_init_timer_irq(vm);
-	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+	ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+	if (ret < 0) {
+		print_skip("Failed to create vgic-v3");
+		exit(KSFT_SKIP);
+	}
 
 	/* Make all the test's cmdline args visible to the guest */
 	sync_global_to_guest(vm, test_args);

tools/testing/selftests/kvm/aarch64/vgic_irq.c

@@ -761,6 +761,10 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 
 	gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
 			GICD_BASE_GPA, GICR_BASE_GPA);
+	if (gic_fd < 0) {
+		print_skip("Failed to create vgic-v3, skipping");
+		exit(KSFT_SKIP);
+	}
 
 	vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT,
 		guest_irq_handlers[args.eoi_split][args.level_sensitive]);

tools/testing/selftests/kvm/lib/aarch64/vgic.c

@@ -52,7 +52,9 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 			nr_vcpus, nr_vcpus_created);
 
 	/* Distributor setup */
-	gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+	if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3,
+			       false, &gic_fd) != 0)
+		return -1;
 
 	kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
 			0, &nr_irqs, true);