Merge branch 'kvm-updates/2.6.38' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.38' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (142 commits)
  KVM: Initialize fpu state in preemptible context
  KVM: VMX: when entering real mode align segment base to 16 bytes
  KVM: MMU: handle 'map_writable' in set_spte() function
  KVM: MMU: audit: allow audit more guests at the same time
  KVM: Fetch guest cr3 from hardware on demand
  KVM: Replace reads of vcpu->arch.cr3 by an accessor
  KVM: MMU: only write protect mappings at pagetable level
  KVM: VMX: Correct asm constraint in vmcs_load()/vmcs_clear()
  KVM: MMU: Initialize base_role for tdp mmus
  KVM: VMX: Optimize atomic EFER load
  KVM: VMX: Add definitions for more vm entry/exit control bits
  KVM: SVM: copy instruction bytes from VMCB
  KVM: SVM: implement enhanced INVLPG intercept
  KVM: SVM: enhance mov DR intercept handler
  KVM: SVM: enhance MOV CR intercept handler
  KVM: SVM: add new SVM feature bit names
  KVM: cleanup emulate_instruction
  KVM: move complete_insn_gp() into x86.c
  KVM: x86: fix CR8 handling
  KVM guest: Fix kvm clock initialization when it's configured out
  ...

Documentation/kernel-parameters.txt

@@ -1705,6 +1705,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
 
+	no-kvmapf	[X86,KVM] Disable paravirtualized asynchronous page
+			fault handling.
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.

Documentation/kvm/api.txt

@@ -1085,6 +1085,184 @@ of 4 instructions that make up a hypercall.
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+4.47 KVM_ASSIGN_PCI_DEVICE
+
+Capability: KVM_CAP_DEVICE_ASSIGNMENT
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_pci_dev (in)
+Returns: 0 on success, -1 on error
+
+Assigns a host PCI device to the VM.
+
+struct kvm_assigned_pci_dev {
+	__u32 assigned_dev_id;
+	__u32 busnr;
+	__u32 devfn;
+	__u32 flags;
+	__u32 segnr;
+	union {
+		__u32 reserved[11];
+	};
+};
+
+The PCI device is specified by the triple segnr, busnr, and devfn.
+Identification in succeeding service requests is done via assigned_dev_id. The
+following flags are specified:
+
+/* Depends on KVM_CAP_IOMMU */
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+
+4.48 KVM_DEASSIGN_PCI_DEVICE
+
+Capability: KVM_CAP_DEVICE_DEASSIGNMENT
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_pci_dev (in)
+Returns: 0 on success, -1 on error
+
+Ends PCI device assignment, releasing all associated resources.
+
+See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
+used in kvm_assigned_pci_dev to identify the device.
+
+4.49 KVM_ASSIGN_DEV_IRQ
+
+Capability: KVM_CAP_ASSIGN_DEV_IRQ
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_irq (in)
+Returns: 0 on success, -1 on error
+
+Assigns an IRQ to a passed-through device.
+
+struct kvm_assigned_irq {
+	__u32 assigned_dev_id;
+	__u32 host_irq;
+	__u32 guest_irq;
+	__u32 flags;
+	union {
+		struct {
+			__u32 addr_lo;
+			__u32 addr_hi;
+			__u32 data;
+		} guest_msi;
+		__u32 reserved[12];
+	};
+};
+
+The following flags are defined:
+
+#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
+
+It is not valid to specify multiple types per host or guest IRQ. However, the
+IRQ type of host and guest can differ or can even be null.
+
+4.50 KVM_DEASSIGN_DEV_IRQ
+
+Capability: KVM_CAP_ASSIGN_DEV_IRQ
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_irq (in)
+Returns: 0 on success, -1 on error
+
+Ends an IRQ assignment to a passed-through device.
+
+See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
+by assigned_dev_id, flags must correspond to the IRQ type specified on
+KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
+
+4.51 KVM_SET_GSI_ROUTING
+
+Capability: KVM_CAP_IRQ_ROUTING
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_irq_routing (in)
+Returns: 0 on success, -1 on error
+
+Sets the GSI routing table entries, overwriting any previously set entries.
+
+struct kvm_irq_routing {
+	__u32 nr;
+	__u32 flags;
+	struct kvm_irq_routing_entry entries[0];
+};
+
+No flags are specified so far, the corresponding field must be set to zero.
+
+struct kvm_irq_routing_entry {
+	__u32 gsi;
+	__u32 type;
+	__u32 flags;
+	__u32 pad;
+	union {
+		struct kvm_irq_routing_irqchip irqchip;
+		struct kvm_irq_routing_msi msi;
+		__u32 pad[8];
+	} u;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+
+No flags are specified so far, the corresponding field must be set to zero.
+
+struct kvm_irq_routing_irqchip {
+	__u32 irqchip;
+	__u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 pad;
+};
+
+4.52 KVM_ASSIGN_SET_MSIX_NR
+
+Capability: KVM_CAP_DEVICE_MSIX
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_nr (in)
+Returns: 0 on success, -1 on error
+
+Set the number of MSI-X interrupts for an assigned device. This service can
+only be called once in the lifetime of an assigned device.
+
+struct kvm_assigned_msix_nr {
+	__u32 assigned_dev_id;
+	__u16 entry_nr;
+	__u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV		256
+
+4.53 KVM_ASSIGN_SET_MSIX_ENTRY
+
+Capability: KVM_CAP_DEVICE_MSIX
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_entry (in)
+Returns: 0 on success, -1 on error
+
+Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
+the GSI vector to zero means disabling the interrupt.
+
+struct kvm_assigned_msix_entry {
+	__u32 assigned_dev_id;
+	__u32 gsi;
+	__u16 entry; /* The index of entry in the MSI-X table */
+	__u16 padding[3];
+};
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

Documentation/kvm/cpuid.txt

@@ -36,6 +36,9 @@ KVM_FEATURE_MMU_OP                 ||     2 || deprecated.
 KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
                                    ||       || 0x4b564d00 and 0x4b564d01
 ------------------------------------------------------------------------------
+KVM_FEATURE_ASYNC_PF               ||     4 || async pf can be enabled by
+                                   ||       || writing to msr 0x4b564d02
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.

Documentation/kvm/msr.txt

@@ -3,7 +3,6 @@ Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
 =====================================================
 
 KVM makes use of some custom MSRs to service some requests.
-At present, this facility is only used by kvmclock.
 
 Custom MSRs have a range reserved for them, that goes from
 0x4b564d00 to 0x4b564dff. There are MSRs outside this area,
@@ -151,3 +150,38 @@ MSR_KVM_SYSTEM_TIME: 0x12
 			return PRESENT;
 		} else
 			return NON_PRESENT;
+
+MSR_KVM_ASYNC_PF_EN: 0x4b564d02
+	data: Bits 63-6 hold 64-byte aligned physical address of a
+	64 byte memory area which must be in guest RAM and must be
+	zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1
+	when asynchronous page faults are enabled on the vcpu 0 when
+	disabled. Bit 2 is 1 if asynchronous page faults can be injected
+	when vcpu is in cpl == 0.
+
+	First 4 byte of 64 byte memory location will be written to by
+	the hypervisor at the time of asynchronous page fault (APF)
+	injection to indicate type of asynchronous page fault. Value
+	of 1 means that the page referred to by the page fault is not
+	present. Value 2 means that the page is now available. Disabling
+	interrupt inhibits APFs. Guest must not enable interrupt
+	before the reason is read, or it may be overwritten by another
+	APF. Since APF uses the same exception vector as regular page
+	fault guest must reset the reason to 0 before it does
+	something that can generate normal page fault.  If during page
+	fault APF reason is 0 it means that this is regular page
+	fault.
+
+	During delivery of type 1 APF cr2 contains a token that will
+	be used to notify a guest when missing page becomes
+	available. When page becomes available type 2 APF is sent with
+	cr2 set to the token associated with the page. There is special
+	kind of token 0xffffffff which tells vcpu that it should wake
+	up all processes waiting for APFs and no individual type 2 APFs
+	will be sent.
+
+	If APF is disabled while there are outstanding APFs, they will
+	not be delivered.
+
+	Currently type 2 APF will be always delivered on the same vcpu as
+	type 1 was, but guest should not rely on that.

arch/ia64/include/asm/kvm_host.h

@@ -590,6 +590,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 void kvm_sal_emul(struct kvm_vcpu *vcpu);
 
+#define __KVM_HAVE_ARCH_VM_ALLOC 1
+struct kvm *kvm_arch_alloc_vm(void);
+void kvm_arch_free_vm(struct kvm *kvm);
+
 #endif /* __ASSEMBLY__*/
 
 #endif

arch/ia64/kvm/kvm-ia64.c

@@ -749,7 +749,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return r;
 }
 
-static struct kvm *kvm_alloc_kvm(void)
+struct kvm *kvm_arch_alloc_vm(void)
 {
 
 	struct kvm *kvm;
@@ -760,7 +760,7 @@ static struct kvm *kvm_alloc_kvm(void)
 	vm_base = __get_free_pages(GFP_KERNEL, get_order(KVM_VM_DATA_SIZE));
 
 	if (!vm_base)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
 	kvm = (struct kvm *)(vm_base +
@@ -806,10 +806,12 @@ static void kvm_build_io_pmt(struct kvm *kvm)
 #define GUEST_PHYSICAL_RR4	0x2739
 #define VMM_INIT_RR		0x1660
 
-static void kvm_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm)
 {
 	BUG_ON(!kvm);
 
+	kvm->arch.is_sn2 = ia64_platform_is("sn2");
+
 	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
 	kvm->arch.metaphysical_rr4 = GUEST_PHYSICAL_RR4;
 	kvm->arch.vmm_init_rr = VMM_INIT_RR;
@@ -823,21 +825,8 @@ static void kvm_init_vm(struct kvm *kvm)
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
-}
-
-struct  kvm *kvm_arch_create_vm(void)
-{
-	struct kvm *kvm = kvm_alloc_kvm();
-
-	if (IS_ERR(kvm))
-		return ERR_PTR(-ENOMEM);
-
-	kvm->arch.is_sn2 = ia64_platform_is("sn2");
-
-	kvm_init_vm(kvm);
-
-	return kvm;
 
+	return 0;
 }
 
 static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm,
@@ -962,7 +951,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
+			mutex_lock(&kvm->slots_lock);
 			kvm_ioapic_destroy(kvm);
+			mutex_unlock(&kvm->slots_lock);
 			goto out;
 		}
 		break;
@@ -1357,7 +1348,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-static void free_kvm(struct kvm *kvm)
+void kvm_arch_free_vm(struct kvm *kvm)
 {
 	unsigned long vm_base = kvm->arch.vm_base;
 
@@ -1399,9 +1390,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 #endif
 	kfree(kvm->arch.vioapic);
 	kvm_release_vm_pages(kvm);
-	kvm_free_physmem(kvm);
-	cleanup_srcu_struct(&kvm->srcu);
-	free_kvm(kvm);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/book3s.c

@@ -1307,12 +1307,10 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	int err = -ENOMEM;
 	unsigned long p;
 
-	vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
+	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
 	if (!vcpu_book3s)
 		goto out;
 
-	memset(vcpu_book3s, 0, sizeof(struct kvmppc_vcpu_book3s));
-
 	vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
 		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
 	if (!vcpu_book3s->shadow_vcpu)

arch/powerpc/kvm/powerpc.c

@@ -145,18 +145,12 @@ void kvm_arch_check_processor_compat(void *rtn)
 	*(int *)rtn = kvmppc_core_check_processor_compat();
 }
 
-struct kvm *kvm_arch_create_vm(void)
+int kvm_arch_init_vm(struct kvm *kvm)
 {
-	struct kvm *kvm;
-
-	kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
-	if (!kvm)
-		return ERR_PTR(-ENOMEM);
-
-	return kvm;
+	return 0;
 }
 
-static void kvmppc_free_vcpus(struct kvm *kvm)
+void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	unsigned int i;
 	struct kvm_vcpu *vcpu;
@@ -176,14 +170,6 @@ void kvm_arch_sync_events(struct kvm *kvm)
 {
 }
 
-void kvm_arch_destroy_vm(struct kvm *kvm)
-{
-	kvmppc_free_vcpus(kvm);
-	kvm_free_physmem(kvm);
-	cleanup_srcu_struct(&kvm->srcu);
-	kfree(kvm);
-}
-
 int kvm_dev_ioctl_check_extension(long ext)
 {
 	int r;

arch/s390/kvm/kvm-s390.c

@@ -164,24 +164,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-struct kvm *kvm_arch_create_vm(void)
+int kvm_arch_init_vm(struct kvm *kvm)
 {
-	struct kvm *kvm;
 	int rc;
 	char debug_name[16];
 
 	rc = s390_enable_sie();
 	if (rc)
-		goto out_nokvm;
-
-	rc = -ENOMEM;
-	kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
-	if (!kvm)
-		goto out_nokvm;
+		goto out_err;
 
 	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
-		goto out_nosca;
+		goto out_err;
 
 	sprintf(debug_name, "kvm-%u", current->pid);
 
@@ -195,13 +189,11 @@ struct kvm *kvm_arch_create_vm(void)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
-	return kvm;
+	return 0;
 out_nodbf:
 	free_page((unsigned long)(kvm->arch.sca));
-out_nosca:
-	kfree(kvm);
-out_nokvm:
-	return ERR_PTR(rc);
+out_err:
+	return rc;
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -240,11 +232,8 @@ void kvm_arch_sync_events(struct kvm *kvm)
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
-	kvm_free_physmem(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
-	cleanup_srcu_struct(&kvm->srcu);
-	kfree(kvm);
 }
 
 /* Section: vcpu related */

arch/x86/include/asm/kvm_emulate.h

@@ -15,6 +15,14 @@
 
 struct x86_emulate_ctxt;
 
+struct x86_exception {
+	u8 vector;
+	bool error_code_valid;
+	u16 error_code;
+	bool nested_page_fault;
+	u64 address; /* cr2 or nested page fault gpa */
+};
+
 /*
  * x86_emulate_ops:
  *
@@ -64,7 +72,8 @@ struct x86_emulate_ops {
 	 *  @bytes: [IN ] Number of bytes to read from memory.
 	 */
 	int (*read_std)(unsigned long addr, void *val,
-			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+			unsigned int bytes, struct kvm_vcpu *vcpu,
+			struct x86_exception *fault);
 
 	/*
 	 * write_std: Write bytes of standard (non-emulated/special) memory.
@@ -74,7 +83,8 @@ struct x86_emulate_ops {
 	 *  @bytes: [IN ] Number of bytes to write to memory.
 	 */
 	int (*write_std)(unsigned long addr, void *val,
-			 unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+			 unsigned int bytes, struct kvm_vcpu *vcpu,
+			 struct x86_exception *fault);
 	/*
 	 * fetch: Read bytes of standard (non-emulated/special) memory.
 	 *        Used for instruction fetch.
@@ -83,7 +93,8 @@ struct x86_emulate_ops {
 	 *  @bytes: [IN ] Number of bytes to read from memory.
 	 */
 	int (*fetch)(unsigned long addr, void *val,
-			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+		     unsigned int bytes, struct kvm_vcpu *vcpu,
+		     struct x86_exception *fault);
 
 	/*
 	 * read_emulated: Read bytes from emulated/special memory area.
@@ -94,7 +105,7 @@ struct x86_emulate_ops {
 	int (*read_emulated)(unsigned long addr,
 			     void *val,
 			     unsigned int bytes,
-			     unsigned int *error,
+			     struct x86_exception *fault,
 			     struct kvm_vcpu *vcpu);
 
 	/*
@@ -107,7 +118,7 @@ struct x86_emulate_ops {
 	int (*write_emulated)(unsigned long addr,
 			      const void *val,
 			      unsigned int bytes,
-			      unsigned int *error,
+			      struct x86_exception *fault,
 			      struct kvm_vcpu *vcpu);
 
 	/*
@@ -122,7 +133,7 @@ struct x86_emulate_ops {
 				const void *old,
 				const void *new,
 				unsigned int bytes,
-				unsigned int *error,
+				struct x86_exception *fault,
 				struct kvm_vcpu *vcpu);
 
 	int (*pio_in_emulated)(int size, unsigned short port, void *val,
@@ -159,7 +170,10 @@ struct operand {
 	};
 	union {
 		unsigned long *reg;
-		unsigned long mem;
+		struct segmented_address {
+			ulong ea;
+			unsigned seg;
+		} mem;
 	} addr;
 	union {
 		unsigned long val;
@@ -226,9 +240,8 @@ struct x86_emulate_ctxt {
 
 	bool perm_ok; /* do not check permissions if true */
 
-	int exception; /* exception that happens during emulation or -1 */
-	u32 error_code; /* error code for exception */
-	bool error_code_valid;
+	bool have_exception;
+	struct x86_exception exception;
 
 	/* decode cache */
 	struct decode_cache decode;
@@ -252,7 +265,7 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1

arch/x86/include/asm/kvm_host.h

@@ -83,11 +83,14 @@
 #define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 
+#define ASYNC_PF_PER_VCPU 64
+
 extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_vcpu;
 struct kvm;
+struct kvm_async_pf;
 
 enum kvm_reg {
 	VCPU_REGS_RAX = 0,
@@ -114,6 +117,7 @@ enum kvm_reg {
 
 enum kvm_reg_ex {
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+	VCPU_EXREG_CR3,
 };
 
 enum {
@@ -238,16 +242,18 @@ struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
-	void (*inject_page_fault)(struct kvm_vcpu *vcpu);
+	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+			  bool prefault);
+	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
+				  struct x86_exception *fault);
 	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-			    u32 *error);
+			    struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
-			 struct kvm_mmu_page *sp, bool clear_unsync);
+			 struct kvm_mmu_page *sp);
 	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
 	hpa_t root_hpa;
 	int root_level;
@@ -315,16 +321,6 @@ struct kvm_vcpu_arch {
 	 */
 	struct kvm_mmu *walk_mmu;
 
-	/*
-	 * This struct is filled with the necessary information to propagate a
-	 * page fault into the guest
-	 */
-	struct {
-		u64      address;
-		unsigned error_code;
-		bool     nested;
-	} fault;
-
 	/* only needed in kvm_pv_mmu_op() path, but it's hot so
 	 * put it here to avoid allocation */
 	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -412,6 +408,15 @@ struct kvm_vcpu_arch {
 	u64 hv_vapic;
 
 	cpumask_var_t wbinvd_dirty_mask;
+
+	struct {
+		bool halted;
+		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+		struct gfn_to_hva_cache data;
+		u64 msr_val;
+		u32 id;
+		bool send_user_only;
+	} apf;
 };
 
 struct kvm_arch {
@@ -456,6 +461,10 @@ struct kvm_arch {
 	/* fields used by HYPER-V emulation */
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
+
+	#ifdef CONFIG_KVM_MMU_AUDIT
+	int audit_point;
+	#endif
 };
 
 struct kvm_vm_stat {
@@ -529,6 +538,7 @@ struct kvm_x86_ops {
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
 	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
+	void (*decache_cr3)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -582,9 +592,17 @@ struct kvm_x86_ops {
 
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
+	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 	const struct trace_print_flags *exit_reasons_str;
 };
 
+struct kvm_arch_async_pf {
+	u32 token;
+	gfn_t gfn;
+	unsigned long cr3;
+	bool direct_map;
+};
+
 extern struct kvm_x86_ops *kvm_x86_ops;
 
 int kvm_mmu_module_init(void);
@@ -594,7 +612,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
 int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
-void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
@@ -623,8 +640,15 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
-int emulate_instruction(struct kvm_vcpu *vcpu,
-			unsigned long cr2, u16 error_code, int emulation_type);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+			    int emulation_type, void *insn, int insn_len);
+
+static inline int emulate_instruction(struct kvm_vcpu *vcpu,
+			int emulation_type)
+{
+	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
+
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 
@@ -650,7 +674,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
 int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
@@ -668,11 +692,11 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			    gfn_t gfn, void *data, int offset, int len,
 			    u32 access);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu);
+void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);
@@ -690,16 +714,21 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
+			      struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
+			       struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
+			       struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
+				struct x86_exception *exception);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 
 void kvm_enable_tdp(void);
@@ -766,20 +795,25 @@ enum {
 #define HF_VINTR_MASK		(1 << 2)
 #define HF_NMI_MASK		(1 << 3)
 #define HF_IRET_MASK		(1 << 4)
+#define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
 
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
  * Trap the fault and ignore the instruction if that happens.
  */
-asmlinkage void kvm_handle_fault_on_reboot(void);
+asmlinkage void kvm_spurious_fault(void);
+extern bool kvm_rebooting;
 
 #define __kvm_handle_fault_on_reboot(insn) \
 	"666: " insn "\n\t" \
+	"668: \n\t"                           \
 	".pushsection .fixup, \"ax\" \n" \
 	"667: \n\t" \
+	"cmpb $0, kvm_rebooting \n\t"	      \
+	"jne 668b \n\t"      		      \
 	__ASM_SIZE(push) " $666b \n\t"	      \
-	"jmp kvm_handle_fault_on_reboot \n\t" \
+	"call kvm_spurious_fault \n\t"	      \
 	".popsection \n\t" \
 	".pushsection __ex_table, \"a\" \n\t" \
 	_ASM_PTR " 666b, 667b \n\t" \
@@ -799,4 +833,15 @@ void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+				     struct kvm_async_pf *work);
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+				 struct kvm_async_pf *work);
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+			       struct kvm_async_pf *work);
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+
+void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/kvm_para.h

@@ -20,6 +20,7 @@
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
+#define KVM_FEATURE_ASYNC_PF		4
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -32,9 +33,13 @@
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+#define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 
 #define KVM_MAX_MMU_OP_BATCH           32
 
+#define KVM_ASYNC_PF_ENABLED			(1 << 0)
+#define KVM_ASYNC_PF_SEND_ALWAYS		(1 << 1)
+
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
 #define KVM_MMU_OP_FLUSH_TLB	        2
@@ -61,10 +66,20 @@ struct kvm_mmu_op_release_pt {
 	__u64 pt_phys;
 };
 
+#define KVM_PV_REASON_PAGE_NOT_PRESENT 1
+#define KVM_PV_REASON_PAGE_READY 2
+
+struct kvm_vcpu_pv_apf_data {
+	__u32 reason;
+	__u8 pad[60];
+	__u32 enabled;
+};
+
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
 extern void kvmclock_init(void);
+extern int kvm_register_clock(char *txt);
 
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
@@ -160,8 +175,17 @@ static inline unsigned int kvm_arch_para_features(void)
 
 #ifdef CONFIG_KVM_GUEST
 void __init kvm_guest_init(void);
+void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wake(u32 token);
+u32 kvm_read_and_reset_pf_reason(void);
 #else
 #define kvm_guest_init() do { } while (0)
+#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wake(T) do {} while(0)
+static inline u32 kvm_read_and_reset_pf_reason(void)
+{
+	return 0;
+}
 #endif
 
 #endif /* __KERNEL__ */

arch/x86/include/asm/svm.h

@@ -47,14 +47,13 @@ enum {
 	INTERCEPT_MONITOR,
 	INTERCEPT_MWAIT,
 	INTERCEPT_MWAIT_COND,
+	INTERCEPT_XSETBV,
 };
 
 
 struct __attribute__ ((__packed__)) vmcb_control_area {
-	u16 intercept_cr_read;
-	u16 intercept_cr_write;
-	u16 intercept_dr_read;
-	u16 intercept_dr_write;
+	u32 intercept_cr;
+	u32 intercept_dr;
 	u32 intercept_exceptions;
 	u64 intercept;
 	u8 reserved_1[42];
@@ -81,14 +80,19 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 event_inj_err;
 	u64 nested_cr3;
 	u64 lbr_ctl;
-	u64 reserved_5;
+	u32 clean;
+	u32 reserved_5;
 	u64 next_rip;
-	u8 reserved_6[816];
+	u8 insn_len;
+	u8 insn_bytes[15];
+	u8 reserved_6[800];
 };
 
 
 #define TLB_CONTROL_DO_NOTHING 0
 #define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
 
 #define V_TPR_MASK 0x0f
 
@@ -204,19 +208,31 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
 #define SVM_SELECTOR_CODE_MASK (1 << 3)
 
-#define INTERCEPT_CR0_MASK 1
-#define INTERCEPT_CR3_MASK (1 << 3)
-#define INTERCEPT_CR4_MASK (1 << 4)
-#define INTERCEPT_CR8_MASK (1 << 8)
-
-#define INTERCEPT_DR0_MASK 1
-#define INTERCEPT_DR1_MASK (1 << 1)
-#define INTERCEPT_DR2_MASK (1 << 2)
-#define INTERCEPT_DR3_MASK (1 << 3)
-#define INTERCEPT_DR4_MASK (1 << 4)
-#define INTERCEPT_DR5_MASK (1 << 5)
-#define INTERCEPT_DR6_MASK (1 << 6)
-#define INTERCEPT_DR7_MASK (1 << 7)
+#define INTERCEPT_CR0_READ	0
+#define INTERCEPT_CR3_READ	3
+#define INTERCEPT_CR4_READ	4
+#define INTERCEPT_CR8_READ	8
+#define INTERCEPT_CR0_WRITE	(16 + 0)
+#define INTERCEPT_CR3_WRITE	(16 + 3)
+#define INTERCEPT_CR4_WRITE	(16 + 4)
+#define INTERCEPT_CR8_WRITE	(16 + 8)
+
+#define INTERCEPT_DR0_READ	0
+#define INTERCEPT_DR1_READ	1
+#define INTERCEPT_DR2_READ	2
+#define INTERCEPT_DR3_READ	3
+#define INTERCEPT_DR4_READ	4
+#define INTERCEPT_DR5_READ	5
+#define INTERCEPT_DR6_READ	6
+#define INTERCEPT_DR7_READ	7
+#define INTERCEPT_DR0_WRITE	(16 + 0)
+#define INTERCEPT_DR1_WRITE	(16 + 1)
+#define INTERCEPT_DR2_WRITE	(16 + 2)
+#define INTERCEPT_DR3_WRITE	(16 + 3)
+#define INTERCEPT_DR4_WRITE	(16 + 4)
+#define INTERCEPT_DR5_WRITE	(16 + 5)
+#define INTERCEPT_DR6_WRITE	(16 + 6)
+#define INTERCEPT_DR7_WRITE	(16 + 7)
 
 #define SVM_EVTINJ_VEC_MASK 0xff
 
@@ -246,6 +262,8 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
 #define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
 
+#define SVM_EXITINFO_REG_MASK 0x0F
+
 #define	SVM_EXIT_READ_CR0 	0x000
 #define	SVM_EXIT_READ_CR3 	0x003
 #define	SVM_EXIT_READ_CR4 	0x004
@@ -316,6 +334,7 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EXIT_MONITOR	0x08a
 #define SVM_EXIT_MWAIT		0x08b
 #define SVM_EXIT_MWAIT_COND	0x08c
+#define SVM_EXIT_XSETBV		0x08d
 #define SVM_EXIT_NPF  		0x400
 
 #define SVM_EXIT_ERR		-1

arch/x86/include/asm/traps.h

@@ -30,6 +30,7 @@ asmlinkage void segment_not_present(void);
 asmlinkage void stack_segment(void);
 asmlinkage void general_protection(void);
 asmlinkage void page_fault(void);
+asmlinkage void async_page_fault(void);
 asmlinkage void spurious_interrupt_bug(void);
 asmlinkage void coprocessor_error(void);
 asmlinkage void alignment_check(void);

arch/x86/include/asm/vmx.h

@@ -66,15 +66,23 @@
 #define PIN_BASED_NMI_EXITING                   0x00000008
 #define PIN_BASED_VIRTUAL_NMIS                  0x00000020
 
+#define VM_EXIT_SAVE_DEBUG_CONTROLS             0x00000002
 #define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL      0x00001000
 #define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
 #define VM_EXIT_SAVE_IA32_PAT			0x00040000
 #define VM_EXIT_LOAD_IA32_PAT			0x00080000
+#define VM_EXIT_SAVE_IA32_EFER                  0x00100000
+#define VM_EXIT_LOAD_IA32_EFER                  0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER       0x00400000
 
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS            0x00000002
 #define VM_ENTRY_IA32E_MODE                     0x00000200
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL     0x00002000
 #define VM_ENTRY_LOAD_IA32_PAT			0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER                 0x00008000
 
 /* VMCS Encodings */
 enum vmcs_field {
@@ -239,6 +247,7 @@ enum vmcs_field {
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
 #define EXIT_REASON_HLT                 12
+#define EXIT_REASON_INVD                13
 #define EXIT_REASON_INVLPG              14
 #define EXIT_REASON_RDPMC               15
 #define EXIT_REASON_RDTSC               16
@@ -296,6 +305,12 @@ enum vmcs_field {
 #define GUEST_INTR_STATE_SMI		0x00000004
 #define GUEST_INTR_STATE_NMI		0x00000008
 
+/* GUEST_ACTIVITY_STATE flags */
+#define GUEST_ACTIVITY_ACTIVE		0
+#define GUEST_ACTIVITY_HLT		1
+#define GUEST_ACTIVITY_SHUTDOWN		2
+#define GUEST_ACTIVITY_WAIT_SIPI	3
+
 /*
  * Exit Qualifications for MOV for Control Register Access
  */

arch/x86/kernel/entry_32.S

@@ -1406,6 +1406,16 @@ ENTRY(general_protection)
 	CFI_ENDPROC
 END(general_protection)
 
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+	RING0_EC_FRAME
+	pushl $do_async_page_fault
+	CFI_ADJUST_CFA_OFFSET 4
+	jmp error_code
+	CFI_ENDPROC
+END(apf_page_fault)
+#endif
+
 /*
  * End of kprobes section
  */

arch/x86/kernel/entry_64.S

@@ -1329,6 +1329,9 @@ errorentry xen_stack_segment do_stack_segment
 #endif
 errorentry general_protection do_general_protection
 errorentry page_fault do_page_fault
+#ifdef CONFIG_KVM_GUEST
+errorentry async_page_fault do_async_page_fault
+#endif
 #ifdef CONFIG_X86_MCE
 paranoidzeroentry machine_check *machine_check_vector(%rip)
 #endif

arch/x86/kernel/i387.c

@@ -169,6 +169,7 @@ int init_fpu(struct task_struct *tsk)
 	set_stopped_child_used_math(tsk);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(init_fpu);
 
 /*
  * The xstateregs_active() routine is the same as the fpregs_active() routine,

arch/x86/kernel/kvm.c

@@ -27,16 +27,37 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/hardirq.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/hash.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/kprobes.h>
 #include <asm/timer.h>
+#include <asm/cpu.h>
+#include <asm/traps.h>
+#include <asm/desc.h>
+#include <asm/tlbflush.h>
 
 #define MMU_QUEUE_SIZE 1024
 
+static int kvmapf = 1;
+
+static int parse_no_kvmapf(char *arg)
+{
+        kvmapf = 0;
+        return 0;
+}
+
+early_param("no-kvmapf", parse_no_kvmapf);
+
 struct kvm_para_state {
 	u8 mmu_queue[MMU_QUEUE_SIZE];
 	int mmu_queue_len;
 };
 
 static DEFINE_PER_CPU(struct kvm_para_state, para_state);
+static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 
 static struct kvm_para_state *kvm_para_state(void)
 {
@@ -50,6 +71,195 @@ static void kvm_io_delay(void)
 {
 }
 
+#define KVM_TASK_SLEEP_HASHBITS 8
+#define KVM_TASK_SLEEP_HASHSIZE (1<<KVM_TASK_SLEEP_HASHBITS)
+
+struct kvm_task_sleep_node {
+	struct hlist_node link;
+	wait_queue_head_t wq;
+	u32 token;
+	int cpu;
+	bool halted;
+	struct mm_struct *mm;
+};
+
+static struct kvm_task_sleep_head {
+	spinlock_t lock;
+	struct hlist_head list;
+} async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
+
+static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
+						  u32 token)
+{
+	struct hlist_node *p;
+
+	hlist_for_each(p, &b->list) {
+		struct kvm_task_sleep_node *n =
+			hlist_entry(p, typeof(*n), link);
+		if (n->token == token)
+			return n;
+	}
+
+	return NULL;
+}
+
+void kvm_async_pf_task_wait(u32 token)
+{
+	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
+	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
+	struct kvm_task_sleep_node n, *e;
+	DEFINE_WAIT(wait);
+	int cpu, idle;
+
+	cpu = get_cpu();
+	idle = idle_cpu(cpu);
+	put_cpu();
+
+	spin_lock(&b->lock);
+	e = _find_apf_task(b, token);
+	if (e) {
+		/* dummy entry exist -> wake up was delivered ahead of PF */
+		hlist_del(&e->link);
+		kfree(e);
+		spin_unlock(&b->lock);
+		return;
+	}
+
+	n.token = token;
+	n.cpu = smp_processor_id();
+	n.mm = current->active_mm;
+	n.halted = idle || preempt_count() > 1;
+	atomic_inc(&n.mm->mm_count);
+	init_waitqueue_head(&n.wq);
+	hlist_add_head(&n.link, &b->list);
+	spin_unlock(&b->lock);
+
+	for (;;) {
+		if (!n.halted)
+			prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (hlist_unhashed(&n.link))
+			break;
+
+		if (!n.halted) {
+			local_irq_enable();
+			schedule();
+			local_irq_disable();
+		} else {
+			/*
+			 * We cannot reschedule. So halt.
+			 */
+			native_safe_halt();
+			local_irq_disable();
+		}
+	}
+	if (!n.halted)
+		finish_wait(&n.wq, &wait);
+
+	return;
+}
+EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
+
+static void apf_task_wake_one(struct kvm_task_sleep_node *n)
+{
+	hlist_del_init(&n->link);
+	if (!n->mm)
+		return;
+	mmdrop(n->mm);
+	if (n->halted)
+		smp_send_reschedule(n->cpu);
+	else if (waitqueue_active(&n->wq))
+		wake_up(&n->wq);
+}
+
+static void apf_task_wake_all(void)
+{
+	int i;
+
+	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
+		struct hlist_node *p, *next;
+		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
+		spin_lock(&b->lock);
+		hlist_for_each_safe(p, next, &b->list) {
+			struct kvm_task_sleep_node *n =
+				hlist_entry(p, typeof(*n), link);
+			if (n->cpu == smp_processor_id())
+				apf_task_wake_one(n);
+		}
+		spin_unlock(&b->lock);
+	}
+}
+
+void kvm_async_pf_task_wake(u32 token)
+{
+	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
+	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
+	struct kvm_task_sleep_node *n;
+
+	if (token == ~0) {
+		apf_task_wake_all();
+		return;
+	}
+
+again:
+	spin_lock(&b->lock);
+	n = _find_apf_task(b, token);
+	if (!n) {
+		/*
+		 * async PF was not yet handled.
+		 * Add dummy entry for the token.
+		 */
+		n = kmalloc(sizeof(*n), GFP_ATOMIC);
+		if (!n) {
+			/*
+			 * Allocation failed! Busy wait while other cpu
+			 * handles async PF.
+			 */
+			spin_unlock(&b->lock);
+			cpu_relax();
+			goto again;
+		}
+		n->token = token;
+		n->cpu = smp_processor_id();
+		n->mm = NULL;
+		init_waitqueue_head(&n->wq);
+		hlist_add_head(&n->link, &b->list);
+	} else
+		apf_task_wake_one(n);
+	spin_unlock(&b->lock);
+	return;
+}
+EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
+
+u32 kvm_read_and_reset_pf_reason(void)
+{
+	u32 reason = 0;
+
+	if (__get_cpu_var(apf_reason).enabled) {
+		reason = __get_cpu_var(apf_reason).reason;
+		__get_cpu_var(apf_reason).reason = 0;
+	}
+
+	return reason;
+}
+EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
+
+dotraplinkage void __kprobes
+do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	switch (kvm_read_and_reset_pf_reason()) {
+	default:
+		do_page_fault(regs, error_code);
+		break;
+	case KVM_PV_REASON_PAGE_NOT_PRESENT:
+		/* page is swapped out by the host. */
+		kvm_async_pf_task_wait((u32)read_cr2());
+		break;
+	case KVM_PV_REASON_PAGE_READY:
+		kvm_async_pf_task_wake((u32)read_cr2());
+		break;
+	}
+}
+
 static void kvm_mmu_op(void *buffer, unsigned len)
 {
 	int r;
@@ -231,10 +441,117 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+void __cpuinit kvm_guest_cpu_init(void)
+{
+	if (!kvm_para_available())
+		return;
+
+	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
+		u64 pa = __pa(&__get_cpu_var(apf_reason));
+
+#ifdef CONFIG_PREEMPT
+		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
+#endif
+		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
+		__get_cpu_var(apf_reason).enabled = 1;
+		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
+		       smp_processor_id());
+	}
+}
+
+static void kvm_pv_disable_apf(void *unused)
+{
+	if (!__get_cpu_var(apf_reason).enabled)
+		return;
+
+	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
+	__get_cpu_var(apf_reason).enabled = 0;
+
+	printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
+	       smp_processor_id());
+}
+
+static int kvm_pv_reboot_notify(struct notifier_block *nb,
+				unsigned long code, void *unused)
+{
+	if (code == SYS_RESTART)
+		on_each_cpu(kvm_pv_disable_apf, NULL, 1);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block kvm_pv_reboot_nb = {
+	.notifier_call = kvm_pv_reboot_notify,
+};
+
+#ifdef CONFIG_SMP
+static void __init kvm_smp_prepare_boot_cpu(void)
+{
+#ifdef CONFIG_KVM_CLOCK
+	WARN_ON(kvm_register_clock("primary cpu clock"));
+#endif
+	kvm_guest_cpu_init();
+	native_smp_prepare_boot_cpu();
+}
+
+static void kvm_guest_cpu_online(void *dummy)
+{
+	kvm_guest_cpu_init();
+}
+
+static void kvm_guest_cpu_offline(void *dummy)
+{
+	kvm_pv_disable_apf(NULL);
+	apf_task_wake_all();
+}
+
+static int __cpuinit kvm_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = (unsigned long)hcpu;
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE_FROZEN:
+		smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0);
+		break;
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata kvm_cpu_notifier = {
+        .notifier_call  = kvm_cpu_notify,
+};
+#endif
+
+static void __init kvm_apf_trap_init(void)
+{
+	set_intr_gate(14, &async_page_fault);
+}
+
 void __init kvm_guest_init(void)
 {
+	int i;
+
 	if (!kvm_para_available())
 		return;
 
 	paravirt_ops_setup();
+	register_reboot_notifier(&kvm_pv_reboot_nb);
+	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
+		spin_lock_init(&async_pf_sleepers[i].lock);
+	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
+		x86_init.irqs.trap_init = kvm_apf_trap_init;
+
+#ifdef CONFIG_SMP
+	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+	register_cpu_notifier(&kvm_cpu_notifier);
+#else
+	kvm_guest_cpu_init();
+#endif
 }

arch/x86/kernel/kvmclock.c

@@ -125,7 +125,7 @@ static struct clocksource kvm_clock = {
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(char *txt)
+int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
 	int low, high, ret;
@@ -152,14 +152,6 @@ static void __cpuinit kvm_setup_secondary_clock(void)
 }
 #endif
 
-#ifdef CONFIG_SMP
-static void __init kvm_smp_prepare_boot_cpu(void)
-{
-	WARN_ON(kvm_register_clock("primary cpu clock"));
-	native_smp_prepare_boot_cpu();
-}
-#endif
-
 /*
  * After the clock is registered, the host will keep writing to the
  * registered memory location. If the guest happens to shutdown, this memory
@@ -205,9 +197,6 @@ void __init kvmclock_init(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 	x86_cpuinit.setup_percpu_clockev =
 		kvm_setup_secondary_clock;
-#endif
-#ifdef CONFIG_SMP
-	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
 	machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC

arch/x86/kvm/Kconfig

@@ -28,6 +28,7 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
+	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
 	---help---

arch/x86/kvm/Makefile

 
-EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
+ccflags-y += -Ivirt/kvm -Iarch/x86/kvm
 
 CFLAGS_x86.o := -I.
 CFLAGS_svm.o := -I.
@@ -9,6 +9,7 @@ kvm-y			+= $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
 				coalesced_mmio.o irq_comm.o eventfd.o \
 				assigned-dev.o)
 kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
+kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(addprefix ../../../virt/kvm/, async_pf.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o timer.o

arch/x86/kvm/kvm_cache_regs.h

@@ -73,6 +73,13 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
 	return vcpu->arch.cr4 & mask;
 }
 
+static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu)
+{
+	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		kvm_x86_ops->decache_cr3(vcpu);
+	return vcpu->arch.cr3;
+}
+
 static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, ~0UL);
@@ -84,4 +91,19 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
 }
 
+static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hflags |= HF_GUEST_MASK;
+}
+
+static inline void leave_guest_mode(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hflags &= ~HF_GUEST_MASK;
+}
+
+static inline bool is_guest_mode(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.hflags & HF_GUEST_MASK;
+}
+
 #endif

arch/x86/kvm/lapic.c

@@ -277,7 +277,8 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 
 	if (old_ppr != ppr) {
 		apic_set_reg(apic, APIC_PROCPRI, ppr);
-		kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
+		if (ppr < old_ppr)
+			kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 	}
 }
 

arch/x86/kvm/mmu_audit.c

@@ -19,11 +19,9 @@
 
 #include <linux/ratelimit.h>
 
-static int audit_point;
-
-#define audit_printk(fmt, args...)		\
+#define audit_printk(kvm, fmt, args...)		\
 	printk(KERN_ERR "audit: (%s) error: "	\
-		fmt, audit_point_name[audit_point], ##args)
+		fmt, audit_point_name[kvm->arch.audit_point], ##args)
 
 typedef void (*inspect_spte_fn) (struct kvm_vcpu *vcpu, u64 *sptep, int level);
 
@@ -97,18 +95,21 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 
 	if (sp->unsync) {
 		if (level != PT_PAGE_TABLE_LEVEL) {
-			audit_printk("unsync sp: %p level = %d\n", sp, level);
+			audit_printk(vcpu->kvm, "unsync sp: %p "
+				     "level = %d\n", sp, level);
 			return;
 		}
 
 		if (*sptep == shadow_notrap_nonpresent_pte) {
-			audit_printk("notrap spte in unsync sp: %p\n", sp);
+			audit_printk(vcpu->kvm, "notrap spte in unsync "
+				     "sp: %p\n", sp);
 			return;
 		}
 	}
 
 	if (sp->role.direct && *sptep == shadow_notrap_nonpresent_pte) {
-		audit_printk("notrap spte in direct sp: %p\n", sp);
+		audit_printk(vcpu->kvm, "notrap spte in direct sp: %p\n",
+			     sp);
 		return;
 	}
 
@@ -125,8 +126,9 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 
 	hpa =  pfn << PAGE_SHIFT;
 	if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
-		audit_printk("levels %d pfn %llx hpa %llx ent %llxn",
-				   vcpu->arch.mmu.root_level, pfn, hpa, *sptep);
+		audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
+			     "ent %llxn", vcpu->arch.mmu.root_level, pfn,
+			     hpa, *sptep);
 }
 
 static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
@@ -142,8 +144,8 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 	if (!gfn_to_memslot(kvm, gfn)) {
 		if (!printk_ratelimit())
 			return;
-		audit_printk("no memslot for gfn %llx\n", gfn);
-		audit_printk("index %ld of sp (gfn=%llx)\n",
+		audit_printk(kvm, "no memslot for gfn %llx\n", gfn);
+		audit_printk(kvm, "index %ld of sp (gfn=%llx)\n",
 		       (long int)(sptep - rev_sp->spt), rev_sp->gfn);
 		dump_stack();
 		return;
@@ -153,7 +155,8 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 	if (!*rmapp) {
 		if (!printk_ratelimit())
 			return;
-		audit_printk("no rmap for writable spte %llx\n", *sptep);
+		audit_printk(kvm, "no rmap for writable spte %llx\n",
+			     *sptep);
 		dump_stack();
 	}
 }
@@ -168,8 +171,9 @@ static void audit_spte_after_sync(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 {
 	struct kvm_mmu_page *sp = page_header(__pa(sptep));
 
-	if (audit_point == AUDIT_POST_SYNC && sp->unsync)
-		audit_printk("meet unsync sp(%p) after sync root.\n", sp);
+	if (vcpu->kvm->arch.audit_point == AUDIT_POST_SYNC && sp->unsync)
+		audit_printk(vcpu->kvm, "meet unsync sp(%p) after sync "
+			     "root.\n", sp);
 }
 
 static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -202,8 +206,9 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	spte = rmap_next(kvm, rmapp, NULL);
 	while (spte) {
 		if (is_writable_pte(*spte))
-			audit_printk("shadow page has writable mappings: gfn "
-				     "%llx role %x\n", sp->gfn, sp->role.word);
+			audit_printk(kvm, "shadow page has writable "
+				     "mappings: gfn %llx role %x\n",
+				     sp->gfn, sp->role.word);
 		spte = rmap_next(kvm, rmapp, spte);
 	}
 }
@@ -238,7 +243,7 @@ static void kvm_mmu_audit(void *ignore, struct kvm_vcpu *vcpu, int point)
 	if (!__ratelimit(&ratelimit_state))
 		return;
 
-	audit_point = point;
+	vcpu->kvm->arch.audit_point = point;
 	audit_all_active_sps(vcpu->kvm);
 	audit_vcpu_spte(vcpu);
 }

arch/x86/kvm/paging_tmpl.h

@@ -72,7 +72,7 @@ struct guest_walker {
 	unsigned pt_access;
 	unsigned pte_access;
 	gfn_t gfn;
-	u32 error_code;
+	struct x86_exception fault;
 };
 
 static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
@@ -266,21 +266,23 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	return 1;
 
 error:
-	walker->error_code = 0;
+	walker->fault.vector = PF_VECTOR;
+	walker->fault.error_code_valid = true;
+	walker->fault.error_code = 0;
 	if (present)
-		walker->error_code |= PFERR_PRESENT_MASK;
+		walker->fault.error_code |= PFERR_PRESENT_MASK;
 
-	walker->error_code |= write_fault | user_fault;
+	walker->fault.error_code |= write_fault | user_fault;
 
 	if (fetch_fault && mmu->nx)
-		walker->error_code |= PFERR_FETCH_MASK;
+		walker->fault.error_code |= PFERR_FETCH_MASK;
 	if (rsvd_fault)
-		walker->error_code |= PFERR_RSVD_MASK;
+		walker->fault.error_code |= PFERR_RSVD_MASK;
 
-	vcpu->arch.fault.address    = addr;
-	vcpu->arch.fault.error_code = walker->error_code;
+	walker->fault.address = addr;
+	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
 
-	trace_kvm_mmu_walker_error(walker->error_code);
+	trace_kvm_mmu_walker_error(walker->fault.error_code);
 	return 0;
 }
 
@@ -299,25 +301,42 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 					addr, access);
 }
 
+static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
+				    struct kvm_mmu_page *sp, u64 *spte,
+				    pt_element_t gpte)
+{
+	u64 nonpresent = shadow_trap_nonpresent_pte;
+
+	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
+	if (!is_present_gpte(gpte)) {
+		if (!sp->unsync)
+			nonpresent = shadow_notrap_nonpresent_pte;
+		goto no_present;
+	}
+
+	if (!(gpte & PT_ACCESSED_MASK))
+		goto no_present;
+
+	return false;
+
+no_present:
+	drop_spte(vcpu->kvm, spte, nonpresent);
+	return true;
+}
+
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			      u64 *spte, const void *pte)
 {
 	pt_element_t gpte;
 	unsigned pte_access;
 	pfn_t pfn;
-	u64 new_spte;
 
 	gpte = *(const pt_element_t *)pte;
-	if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
-		if (!is_present_gpte(gpte)) {
-			if (sp->unsync)
-				new_spte = shadow_trap_nonpresent_pte;
-			else
-				new_spte = shadow_notrap_nonpresent_pte;
-			__set_spte(spte, new_spte);
-		}
+	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return;
-	}
+
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
 	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
 	if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn)
@@ -329,7 +348,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return;
 	kvm_get_pfn(pfn);
 	/*
-	 * we call mmu_set_spte() with reset_host_protection = true beacuse that
+	 * we call mmu_set_spte() with host_writable = true beacuse that
 	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
 	 */
 	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
@@ -364,7 +383,6 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 				u64 *sptep)
 {
 	struct kvm_mmu_page *sp;
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
 	pt_element_t *gptep = gw->prefetch_ptes;
 	u64 *spte;
 	int i;
@@ -395,14 +413,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 
 		gpte = gptep[i];
 
-		if (!is_present_gpte(gpte) ||
-		      is_rsvd_bits_set(mmu, gpte, PT_PAGE_TABLE_LEVEL)) {
-			if (!sp->unsync)
-				__set_spte(spte, shadow_notrap_nonpresent_pte);
-			continue;
-		}
-
-		if (!(gpte & PT_ACCESSED_MASK))
+		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 			continue;
 
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
@@ -427,7 +438,8 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int user_fault, int write_fault, int hlevel,
-			 int *ptwrite, pfn_t pfn)
+			 int *ptwrite, pfn_t pfn, bool map_writable,
+			 bool prefault)
 {
 	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *sp = NULL;
@@ -501,7 +513,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access & access,
 		     user_fault, write_fault, dirty, ptwrite, it.level,
-		     gw->gfn, pfn, false, true);
+		     gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
 	return it.sptep;
@@ -527,8 +539,8 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
-			       u32 error_code)
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
 	int user_fault = error_code & PFERR_USER_MASK;
@@ -539,6 +551,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
 	unsigned long mmu_seq;
+	bool map_writable;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -556,8 +569,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	 */
 	if (!r) {
 		pgprintk("%s: guest page fault\n", __func__);
-		inject_page_fault(vcpu);
-		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
+		if (!prefault) {
+			inject_page_fault(vcpu, &walker.fault);
+			/* reset fork detector */
+			vcpu->arch.last_pt_write_count = 0;
+		}
 		return 0;
 	}
 
@@ -568,7 +584,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
-	pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
+
+	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
+			 &map_writable))
+		return 0;
 
 	/* mmio */
 	if (is_error_pfn(pfn))
@@ -581,7 +600,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	kvm_mmu_free_some_pages(vcpu);
 	sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-			     level, &write_pt, pfn);
+			     level, &write_pt, pfn, map_writable, prefault);
 	(void)sptep;
 	pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
 		 sptep, *sptep, write_pt);
@@ -661,7 +680,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
-			       u32 *error)
+			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
@@ -672,14 +691,15 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
 		gpa |= vaddr & ~PAGE_MASK;
-	} else if (error)
-		*error = walker.error_code;
+	} else if (exception)
+		*exception = walker.fault;
 
 	return gpa;
 }
 
 static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
-				      u32 access, u32 *error)
+				      u32 access,
+				      struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
@@ -690,8 +710,8 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
 		gpa |= vaddr & ~PAGE_MASK;
-	} else if (error)
-		*error = walker.error_code;
+	} else if (exception)
+		*exception = walker.fault;
 
 	return gpa;
 }
@@ -730,12 +750,19 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
+ *
+ * Note:
+ *   We should flush all tlbs if spte is dropped even though guest is
+ *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
+ *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
+ *   used by guest then tlbs are not flushed, so guest is allowed to access the
+ *   freed pages.
+ *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
-static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			    bool clear_unsync)
+static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	int i, offset, nr_present;
-	bool reset_host_protection;
+	bool host_writable;
 	gpa_t first_pte_gpa;
 
 	offset = nr_present = 0;
@@ -764,31 +791,27 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			return -EINVAL;
 
 		gfn = gpte_to_gfn(gpte);
-		if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)
-		      || gfn != sp->gfns[i] || !is_present_gpte(gpte)
-		      || !(gpte & PT_ACCESSED_MASK)) {
-			u64 nonpresent;
 
-			if (is_present_gpte(gpte) || !clear_unsync)
-				nonpresent = shadow_trap_nonpresent_pte;
-			else
-				nonpresent = shadow_notrap_nonpresent_pte;
-			drop_spte(vcpu->kvm, &sp->spt[i], nonpresent);
+		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
+			vcpu->kvm->tlbs_dirty++;
+			continue;
+		}
+
+		if (gfn != sp->gfns[i]) {
+			drop_spte(vcpu->kvm, &sp->spt[i],
+				      shadow_trap_nonpresent_pte);
+			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
-		if (!(sp->spt[i] & SPTE_HOST_WRITEABLE)) {
-			pte_access &= ~ACC_WRITE_MASK;
-			reset_host_protection = 0;
-		} else {
-			reset_host_protection = 1;
-		}
+		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
+
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
 			 is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false,
-			 reset_host_protection);
+			 host_writable);
 	}
 
 	return !nr_present;

arch/x86/kvm/trace.h

@@ -178,27 +178,36 @@ TRACE_EVENT(kvm_apic,
 #define trace_kvm_apic_read(reg, val)		trace_kvm_apic(0, reg, val)
 #define trace_kvm_apic_write(reg, val)		trace_kvm_apic(1, reg, val)
 
+#define KVM_ISA_VMX   1
+#define KVM_ISA_SVM   2
+
 /*
  * Tracepoint for kvm guest exit:
  */
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu),
-	TP_ARGS(exit_reason, vcpu),
+	TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu, u32 isa),
+	TP_ARGS(exit_reason, vcpu, isa),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	exit_reason	)
 		__field(	unsigned long,	guest_rip	)
+		__field(	u32,	        isa             )
+		__field(	u64,	        info1           )
+		__field(	u64,	        info2           )
 	),
 
 	TP_fast_assign(
 		__entry->exit_reason	= exit_reason;
 		__entry->guest_rip	= kvm_rip_read(vcpu);
+		__entry->isa            = isa;
+		kvm_x86_ops->get_exit_info(vcpu, &__entry->info1,
+					   &__entry->info2);
 	),
 
-	TP_printk("reason %s rip 0x%lx",
+	TP_printk("reason %s rip 0x%lx info %llx %llx",
 		 ftrace_print_symbols_seq(p, __entry->exit_reason,
 					  kvm_x86_ops->exit_reasons_str),
-		 __entry->guest_rip)
+		 __entry->guest_rip, __entry->info1, __entry->info2)
 );
 
 /*

include/linux/kvm.h

@@ -540,6 +540,7 @@ struct kvm_ppc_pvinfo {
 #endif
 #define KVM_CAP_PPC_GET_PVINFO 57
 #define KVM_CAP_PPC_IRQ_LEVEL 58
+#define KVM_CAP_ASYNC_PF 59
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

include/linux/kvm_types.h

@@ -67,4 +67,11 @@ struct kvm_lapic_irq {
 	u32 dest_id;
 };
 
+struct gfn_to_hva_cache {
+	u64 generation;
+	gpa_t gpa;
+	unsigned long hva;
+	struct kvm_memory_slot *memslot;
+};
+
 #endif /* __KVM_TYPES_H__ */

include/trace/events/kvm.h

@@ -6,6 +6,36 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
 
+#define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x }
+
+#define kvm_trace_exit_reason						\
+	ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL),	\
+	ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN),	\
+	ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR),	\
+	ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
+	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI)
+
+TRACE_EVENT(kvm_userspace_exit,
+	    TP_PROTO(__u32 reason, int errno),
+	    TP_ARGS(reason, errno),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		reason		)
+		__field(	int,		errno		)
+	),
+
+	TP_fast_assign(
+		__entry->reason		= reason;
+		__entry->errno		= errno;
+	),
+
+	TP_printk("reason %s (%d)",
+		  __entry->errno < 0 ?
+		  (__entry->errno == -EINTR ? "restart" : "error") :
+		  __print_symbolic(__entry->reason, kvm_trace_exit_reason),
+		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
+);
+
 #if defined(__KVM_HAVE_IOAPIC)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
@@ -185,6 +215,97 @@ TRACE_EVENT(kvm_age_page,
 		  __entry->referenced ? "YOUNG" : "OLD")
 );
 
+#ifdef CONFIG_KVM_ASYNC_PF
+DECLARE_EVENT_CLASS(kvm_async_get_page_class,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn),
+
+	TP_STRUCT__entry(
+		__field(__u64, gva)
+		__field(u64, gfn)
+	),
+
+	TP_fast_assign(
+		__entry->gva = gva;
+		__entry->gfn = gfn;
+	),
+
+	TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_doublefault,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva),
+
+	TP_STRUCT__entry(
+		__field(__u64, token)
+		__field(__u64, gva)
+	),
+
+	TP_fast_assign(
+		__entry->token = token;
+		__entry->gva = gva;
+	),
+
+	TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva)
+
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva)
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_completed,
+	TP_PROTO(unsigned long address, struct page *page, u64 gva),
+	TP_ARGS(address, page, gva),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, address)
+		__field(pfn_t, pfn)
+		__field(u64, gva)
+		),
+
+	TP_fast_assign(
+		__entry->address = address;
+		__entry->pfn = page ? page_to_pfn(page) : 0;
+		__entry->gva = gva;
+		),
+
+	TP_printk("gva %#llx address %#lx pfn %#llx",  __entry->gva,
+		  __entry->address, __entry->pfn)
+);
+
+#endif
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */

virt/kvm/Kconfig

@@ -15,3 +15,6 @@ config KVM_APIC_ARCHITECTURE
 
 config KVM_MMIO
        bool
+
+config KVM_ASYNC_PF
+       bool

virt/kvm/irq_comm.c

@@ -114,8 +114,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
-static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		       struct kvm *kvm, int irq_source_id, int level)
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id, int level)
 {
 	struct kvm_lapic_irq irq;
 
@@ -409,8 +409,9 @@ int kvm_set_irq_routing(struct kvm *kvm,
 
 	mutex_lock(&kvm->irq_lock);
 	old = kvm->irq_routing;
-	rcu_assign_pointer(kvm->irq_routing, new);
+	kvm_irq_routing_update(kvm, new);
 	mutex_unlock(&kvm->irq_lock);
+
 	synchronize_rcu();
 
 	new = old;