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

Pull kvm fixes from Paolo Bonzini:
 "Bugfixes, including the fix for CVE-2020-2732 and a few issues found
  by 'make W=1'"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: s390: rstify new ioctls in api.rst
  KVM: nVMX: Check IO instruction VM-exit conditions
  KVM: nVMX: Refactor IO bitmap checks into helper function
  KVM: nVMX: Don't emulate instructions in guest mode
  KVM: nVMX: Emulate MTF when performing instruction emulation
  KVM: fix error handling in svm_hardware_setup
  KVM: SVM: Fix potential memory leak in svm_cpu_init()
  KVM: apic: avoid calculating pending eoi from an uninitialized val
  KVM: nVMX: clear PIN_BASED_POSTED_INTR from nested pinbased_ctls only when apicv is globally disabled
  KVM: nVMX: handle nested posted interrupts when apicv is disabled for L1
  kvm: x86: svm: Fix NULL pointer dereference when AVIC not enabled
  KVM: VMX: Add VMX_FEATURE_USR_WAIT_PAUSE
  KVM: nVMX: Hold KVM's srcu lock when syncing vmcs12->shadow
  KVM: x86: don't notify userspace IOAPIC on edge-triggered interrupt EOI
  kvm/emulate: fix a -Werror=cast-function-type
  KVM: x86: fix incorrect comparison in trace event
  KVM: nVMX: Fix some obsolete comments and grammar error
  KVM: x86: fix missing prototypes
  KVM: x86: enable -Werror

Documentation/virt/kvm/api.rst

@@ -4611,35 +4611,38 @@ unpins the VPA pages and releases all the device pages that are used to
 track the secure pages by hypervisor.
 
 4.122 KVM_S390_NORMAL_RESET
+---------------------------
 
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the cpu reset definition in the POP (Principles Of Operation).
 
 4.123 KVM_S390_INITIAL_RESET
+----------------------------
 
-Capability: none
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: none
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the initial cpu reset definition in the POP. However, the cpu is not
 put into ESA mode. This reset is a superset of the normal reset.
 
 4.124 KVM_S390_CLEAR_RESET
+--------------------------
 
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
 
 This ioctl resets VCPU registers and control structures according to
 the clear cpu reset definition in the POP. However, the cpu is not put

arch/x86/include/asm/kvm_emulate.h

@@ -292,6 +292,14 @@ enum x86emul_mode {
 #define X86EMUL_SMM_MASK             (1 << 6)
 #define X86EMUL_SMM_INSIDE_NMI_MASK  (1 << 7)
 
+/*
+ * fastop functions are declared as taking a never-defined fastop parameter,
+ * so they can't be called from C directly.
+ */
+struct fastop;
+
+typedef void (*fastop_t)(struct fastop *);
+
 struct x86_emulate_ctxt {
 	const struct x86_emulate_ops *ops;
 
@@ -324,7 +332,10 @@ struct x86_emulate_ctxt {
 	struct operand src;
 	struct operand src2;
 	struct operand dst;
-	int (*execute)(struct x86_emulate_ctxt *ctxt);
+	union {
+		int (*execute)(struct x86_emulate_ctxt *ctxt);
+		fastop_t fop;
+	};
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 	/*
 	 * The following six fields are cleared together,

arch/x86/include/asm/kvm_host.h

@@ -1122,6 +1122,7 @@ struct kvm_x86_ops {
 	int (*handle_exit)(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*update_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
 	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
@@ -1146,7 +1147,7 @@ struct kvm_x86_ops {
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
-	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);

arch/x86/include/asm/vmx.h

@@ -72,7 +72,7 @@
 #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC	VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
 #define SECONDARY_EXEC_PT_USE_GPA		VMCS_CONTROL_BIT(PT_USE_GPA)
 #define SECONDARY_EXEC_TSC_SCALING              VMCS_CONTROL_BIT(TSC_SCALING)
-#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	0x04000000
+#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
 
 #define PIN_BASED_EXT_INTR_MASK                 VMCS_CONTROL_BIT(INTR_EXITING)
 #define PIN_BASED_NMI_EXITING                   VMCS_CONTROL_BIT(NMI_EXITING)

arch/x86/include/asm/vmxfeatures.h

@@ -81,6 +81,7 @@
 #define VMX_FEATURE_MODE_BASED_EPT_EXEC	( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
 #define VMX_FEATURE_PT_USE_GPA		( 2*32+ 24) /* "" Processor Trace logs GPAs */
 #define VMX_FEATURE_TSC_SCALING		( 2*32+ 25) /* Scale hardware TSC when read in guest */
+#define VMX_FEATURE_USR_WAIT_PAUSE	( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
 #define VMX_FEATURE_ENCLV_EXITING	( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
 
 #endif /* _ASM_X86_VMXFEATURES_H */

arch/x86/include/uapi/asm/kvm.h

@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002

arch/x86/kvm/Makefile

 # SPDX-License-Identifier: GPL-2.0
 
 ccflags-y += -Iarch/x86/kvm
+ccflags-y += -Werror
 
 KVM := ../../../virt/kvm
 

arch/x86/kvm/emulate.c

@@ -191,25 +191,6 @@
 #define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
 #define FASTOP_SIZE 8
 
-/*
- * fastop functions have a special calling convention:
- *
- * dst:    rax        (in/out)
- * src:    rdx        (in/out)
- * src2:   rcx        (in)
- * flags:  rflags     (in/out)
- * ex:     rsi        (in:fastop pointer, out:zero if exception)
- *
- * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
- * different operand sizes can be reached by calculation, rather than a jump
- * table (which would be bigger than the code).
- *
- * fastop functions are declared as taking a never-defined fastop parameter,
- * so they can't be called from C directly.
- */
-
-struct fastop;
-
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 #define ON64(x)
 #endif
 
-typedef void (*fastop_t)(struct fastop *);
-
+/*
+ * fastop functions have a special calling convention:
+ *
+ * dst:    rax        (in/out)
+ * src:    rdx        (in/out)
+ * src2:   rcx        (in)
+ * flags:  rflags     (in/out)
+ * ex:     rsi        (in:fastop pointer, out:zero if exception)
+ *
+ * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
+ * different operand sizes can be reached by calculation, rather than a jump
+ * table (which would be bigger than the code).
+ */
 static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
 #define __FOP_FUNC(name) \
@@ -5683,7 +5675,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 	if (ctxt->execute) {
 		if (ctxt->d & Fastop)
-			rc = fastop(ctxt, (fastop_t)ctxt->execute);
+			rc = fastop(ctxt, ctxt->fop);
 		else
 			rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)

arch/x86/kvm/irq_comm.c

@@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level &&
+			if (irq.trig_mode &&
 			    kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);

arch/x86/kvm/lapic.c

@@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu)
 static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 {
 	u8 val;
-	if (pv_eoi_get_user(vcpu, &val) < 0)
+	if (pv_eoi_get_user(vcpu, &val) < 0) {
 		printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return false;
+	}
 	return val & 0x1;
 }
 
@@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 						       apic->regs + APIC_TMR);
 		}
 
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		else {
+		if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
 			kvm_lapic_set_irr(vector, apic);
-
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}

arch/x86/kvm/mmutrace.h

@@ -339,7 +339,7 @@ TRACE_EVENT(
 		/* These depend on page entry type, so compute them now.  */
 		__field(bool, r)
 		__field(bool, x)
-		__field(u8, u)
+		__field(signed char, u)
 	),
 
 	TP_fast_assign(

arch/x86/kvm/svm.c

@@ -1005,33 +1005,32 @@ static void svm_cpu_uninit(int cpu)
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *sd;
-	int r;
 
 	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
 	if (!sd)
 		return -ENOMEM;
 	sd->cpu = cpu;
-	r = -ENOMEM;
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
-		goto err_1;
+		goto free_cpu_data;
 
 	if (svm_sev_enabled()) {
-		r = -ENOMEM;
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
 					      sizeof(void *),
 					      GFP_KERNEL);
 		if (!sd->sev_vmcbs)
-			goto err_1;
+			goto free_save_area;
 	}
 
 	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
-err_1:
+free_save_area:
+	__free_page(sd->save_area);
+free_cpu_data:
 	kfree(sd);
-	return r;
+	return -ENOMEM;
 
 }
 
@@ -1350,6 +1349,24 @@ static __init void svm_adjust_mmio_mask(void)
 	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
 }
 
+static void svm_hardware_teardown(void)
+{
+	int cpu;
+
+	if (svm_sev_enabled()) {
+		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
+
+	for_each_possible_cpu(cpu)
+		svm_cpu_uninit(cpu);
+
+	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
+	iopm_base = 0;
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1463,29 +1480,10 @@ static __init int svm_hardware_setup(void)
 	return 0;
 
 err:
-	__free_pages(iopm_pages, IOPM_ALLOC_ORDER);
-	iopm_base = 0;
+	svm_hardware_teardown();
 	return r;
 }
 
-static __exit void svm_hardware_unsetup(void)
-{
-	int cpu;
-
-	if (svm_sev_enabled()) {
-		bitmap_free(sev_asid_bitmap);
-		bitmap_free(sev_reclaim_asid_bitmap);
-
-		sev_flush_asids();
-	}
-
-	for_each_possible_cpu(cpu)
-		svm_cpu_uninit(cpu);
-
-	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
-	iopm_base = 0;
-}
-
 static void init_seg(struct vmcb_seg *seg)
 {
 	seg->selector = 0;
@@ -5232,6 +5230,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	struct vmcb *vmcb = svm->vmcb;
 	bool activated = kvm_vcpu_apicv_active(vcpu);
 
+	if (!avic)
+		return;
+
 	if (activated) {
 		/**
 		 * During AVIC temporary deactivation, guest could update
@@ -5255,8 +5256,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
@@ -5268,6 +5272,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		put_cpu();
 	} else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -7378,7 +7384,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
 	.hardware_setup = svm_hardware_setup,
-	.hardware_unsetup = svm_hardware_unsetup,
+	.hardware_unsetup = svm_hardware_teardown,
 	.check_processor_compatibility = svm_check_processor_compat,
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
@@ -7433,6 +7439,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.update_emulated_instruction = NULL,
 	.set_interrupt_shadow = svm_set_interrupt_shadow,
 	.get_interrupt_shadow = svm_get_interrupt_shadow,
 	.patch_hypercall = svm_patch_hypercall,

arch/x86/kvm/vmx/capabilities.h

@@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0

arch/x86/kvm/vmx/nested.c

@@ -3161,10 +3161,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
  * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
  *
  * Returns:
- *	NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
- *	NVMX_ENTRY_VMFAIL:  Consistency check VMFail
- *	NVMX_ENTRY_VMEXIT:  Consistency check VMExit
- *	NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
+ *	NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode
+ *	NVMX_VMENTRY_VMFAIL:  Consistency check VMFail
+ *	NVMX_VMENTRY_VMEXIT:  Consistency check VMExit
+ *	NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error
  */
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 							bool from_vmentry)
@@ -3609,8 +3609,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 	unsigned long exit_qual;
 	bool block_nested_events =
 	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
+	bool mtf_pending = vmx->nested.mtf_pending;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/*
+	 * Clear the MTF state. If a higher priority VM-exit is delivered first,
+	 * this state is discarded.
+	 */
+	vmx->nested.mtf_pending = false;
+
 	if (lapic_in_kernel(vcpu) &&
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
@@ -3621,8 +3628,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
+	/*
+	 * Process any exceptions that are not debug traps before MTF.
+	 */
+	if (vcpu->arch.exception.pending &&
+	    !vmx_pending_dbg_trap(vcpu) &&
+	    nested_vmx_check_exception(vcpu, &exit_qual)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+		return 0;
+	}
+
+	if (mtf_pending) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_update_pending_dbg(vcpu);
+		nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0);
+		return 0;
+	}
+
 	if (vcpu->arch.exception.pending &&
-		nested_vmx_check_exception(vcpu, &exit_qual)) {
+	    nested_vmx_check_exception(vcpu, &exit_qual)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
@@ -5285,24 +5312,17 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size)
 {
-	unsigned long exit_qualification;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
 	u8 b;
 
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
 	last_bitmap = (gpa_t)-1;
 	b = -1;
 
@@ -5329,8 +5349,26 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	unsigned short port;
+	int size;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
 /*
- * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
+ * Return 1 if we should exit from L2 to L1 to handle an MSR access,
  * rather than handle it ourselves in L0. I.e., check whether L1 expressed
  * disinterest in the current event (read or write a specific MSR) by using an
  * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
@@ -5712,6 +5750,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 
 			if (vmx->nested.nested_run_pending)
 				kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+
+			if (vmx->nested.mtf_pending)
+				kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING;
 		}
 	}
 
@@ -5892,6 +5933,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	vmx->nested.nested_run_pending =
 		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
 
+	vmx->nested.mtf_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
+
 	ret = -EINVAL;
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != -1ull) {
@@ -5949,8 +5993,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void)
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 {
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in
@@ -5977,7 +6020,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
 		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
+		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
 	msrs->pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;

arch/x86/kvm/vmx/nested.h

@@ -17,8 +17,7 @@ enum nvmx_vmentry_status {
 };
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);
@@ -34,6 +33,8 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
 void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
@@ -175,6 +176,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
+}
+
 static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
 {
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);

arch/x86/kvm/vmx/vmx.c

@@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*
@@ -1175,6 +1175,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 					   vmx->guest_msrs[i].mask);
 
 	}
+
+    	if (vmx->nested.need_vmcs12_to_shadow_sync)
+		nested_sync_vmcs12_to_shadow(vcpu);
+
 	if (vmx->guest_state_loaded)
 		return;
 
@@ -1599,6 +1603,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+
+/*
+ * Recognizes a pending MTF VM-exit and records the nested state for later
+ * delivery.
+ */
+static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!is_guest_mode(vcpu))
+		return;
+
+	/*
+	 * Per the SDM, MTF takes priority over debug-trap exceptions besides
+	 * T-bit traps. As instruction emulation is completed (i.e. at the
+	 * instruction boundary), any #DB exception pending delivery must be a
+	 * debug-trap. Record the pending MTF state to be delivered in
+	 * vmx_check_nested_events().
+	 */
+	if (nested_cpu_has_mtf(vmcs12) &&
+	    (!vcpu->arch.exception.pending ||
+	     vcpu->arch.exception.nr == DB_VECTOR))
+		vmx->nested.mtf_pending = true;
+	else
+		vmx->nested.mtf_pending = false;
+}
+
+static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	vmx_update_emulated_instruction(vcpu);
+	return skip_emulated_instruction(vcpu);
+}
+
 static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -3818,24 +3856,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
  * 2. If target vcpu isn't running(root mode), kick it to pick up the
  * interrupt from PIR in next vmentry.
  */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
 	if (!r)
-		return;
+		return 0;
+
+	if (!vcpu->arch.apicv_active)
+		return -1;
 
 	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
+		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
 	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
+		return 0;
 
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
+
+	return 0;
 }
 
 /*
@@ -6482,8 +6525,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_write32(PLE_WINDOW, vmx->ple_window);
 	}
 
-	if (vmx->nested.need_vmcs12_to_shadow_sync)
-		nested_sync_vmcs12_to_shadow(vcpu);
+	/*
+	 * We did this in prepare_switch_to_guest, because it needs to
+	 * be within srcu_read_lock.
+	 */
+	WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync);
 
 	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
@@ -6757,8 +6803,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -6839,8 +6884,7 @@ static int __init vmx_check_processor_compat(void)
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -7101,6 +7145,39 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
 	to_vmx(vcpu)->req_immediate_exit = true;
 }
 
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned short port;
+	bool intercept;
+	int size;
+
+	if (info->intercept == x86_intercept_in ||
+	    info->intercept == x86_intercept_ins) {
+		port = info->src_val;
+		size = info->dst_bytes;
+	} else {
+		port = info->dst_val;
+		size = info->src_bytes;
+	}
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		intercept = nested_cpu_has(vmcs12,
+					   CPU_BASED_UNCOND_IO_EXITING);
+	else
+		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage)
@@ -7108,19 +7185,31 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 
+	switch (info->intercept) {
 	/*
 	 * RDPID causes #UD if disabled through secondary execution controls.
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
 	 */
-	if (info->intercept == x86_intercept_rdtscp &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-		ctxt->exception.vector = UD_VECTOR;
-		ctxt->exception.error_code_valid = false;
-		return X86EMUL_PROPAGATE_FAULT;
-	}
+	case x86_intercept_rdtscp:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+			ctxt->exception.vector = UD_VECTOR;
+			ctxt->exception.error_code_valid = false;
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+		break;
+
+	case x86_intercept_in:
+	case x86_intercept_ins:
+	case x86_intercept_out:
+	case x86_intercept_outs:
+		return vmx_check_intercept_io(vcpu, info);
 
 	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
+	default:
+		break;
+	}
+
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64
@@ -7702,7 +7791,7 @@ static __init int hardware_setup(void)
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)
@@ -7786,7 +7875,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.run = vmx_vcpu_run,
 	.handle_exit = vmx_handle_exit,
-	.skip_emulated_instruction = skip_emulated_instruction,
+	.skip_emulated_instruction = vmx_skip_emulated_instruction,
+	.update_emulated_instruction = vmx_update_emulated_instruction,
 	.set_interrupt_shadow = vmx_set_interrupt_shadow,
 	.get_interrupt_shadow = vmx_get_interrupt_shadow,
 	.patch_hypercall = vmx_patch_hypercall,

arch/x86/kvm/vmx/vmx.h

@@ -150,6 +150,9 @@ struct nested_vmx {
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 
+	/* Pending MTF VM-exit into L1.  */
+	bool mtf_pending;
+
 	struct loaded_vmcs vmcs02;
 
 	/*

arch/x86/kvm/x86.c

@@ -6891,6 +6891,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			kvm_rip_write(vcpu, ctxt->eip);
 			if (r && ctxt->tf)
 				r = kvm_vcpu_do_singlestep(vcpu);
+			if (kvm_x86_ops->update_emulated_instruction)
+				kvm_x86_ops->update_emulated_instruction(vcpu);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
 		}
 

include/linux/kvm_host.h

@@ -889,6 +889,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_post_init_vm(struct kvm *kvm);
+void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 /*