1 files changed, 437 insertions, 201 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cdac9e592aa5..f1e4025f1ae2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -43,6 +43,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <linux/uaccess.h>
+#include <linux/hash.h>
 #include <trace/events/kvm.h>
 
 #define CREATE_TRACE_POINTS
@@ -80,9 +81,10 @@
  * - enable LME and LMA per default on 64 bit KVM
  */
 #ifdef CONFIG_X86_64
-static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL;
+static
+u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 #else
-static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
+static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
 #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
@@ -155,9 +157,11 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 u64 __read_mostly host_xcr0;
 
-static inline u32 bit(int bitno)
+static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
 {
-	return 1 << (bitno & 31);
+	int i;
+	for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++)
+		vcpu->arch.apf.gfns[i] = ~0;
 }
 
 static void kvm_on_user_return(struct user_return_notifier *urn)
@@ -331,29 +335,34 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu)
+void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
-	unsigned error_code = vcpu->arch.fault.error_code;
+	if (err)
+		kvm_inject_gp(vcpu, 0);
+	else
+		kvm_x86_ops->skip_emulated_instruction(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+{
 	++vcpu->stat.pf_guest;
-	vcpu->arch.cr2 = vcpu->arch.fault.address;
-	kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
+	vcpu->arch.cr2 = fault->address;
+	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
 }
 
-void kvm_propagate_fault(struct kvm_vcpu *vcpu)
+void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
-	if (mmu_is_nested(vcpu) && !vcpu->arch.fault.nested)
-		vcpu->arch.nested_mmu.inject_page_fault(vcpu);
+	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
+		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
 	else
-		vcpu->arch.mmu.inject_page_fault(vcpu);
-
-	vcpu->arch.fault.nested = false;
+		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
 }
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu)
 {
+	kvm_make_request(KVM_REQ_NMI, vcpu);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
-	vcpu->arch.nmi_pending = 1;
 }
 EXPORT_SYMBOL_GPL(kvm_inject_nmi);
 
@@ -465,8 +474,8 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
 		      (unsigned long *)&vcpu->arch.regs_avail))
 		return true;
 
-	gfn = (vcpu->arch.cr3 & ~31u) >> PAGE_SHIFT;
-	offset = (vcpu->arch.cr3 & ~31u) & (PAGE_SIZE - 1);
+	gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
+	offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1);
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
@@ -511,12 +520,17 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		} else
 #endif
 		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
-						 vcpu->arch.cr3))
+						 kvm_read_cr3(vcpu)))
 			return 1;
 	}
 
 	kvm_x86_ops->set_cr0(vcpu, cr0);
 
+	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
+		kvm_clear_async_pf_completion_queue(vcpu);
+		kvm_async_pf_hash_reset(vcpu);
+	}
+
 	if ((cr0 ^ old_cr0) & update_bits)
 		kvm_mmu_reset_context(vcpu);
 	return 0;
@@ -600,7 +614,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
-		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))
+		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
+				   kvm_read_cr3(vcpu)))
 		return 1;
 
 	if (cr4 & X86_CR4_VMXE)
@@ -620,7 +635,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
 
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
-	if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
+	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
 		kvm_mmu_sync_roots(vcpu);
 		kvm_mmu_flush_tlb(vcpu);
 		return 0;
@@ -655,12 +670,13 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
 		return 1;
 	vcpu->arch.cr3 = cr3;
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
 	vcpu->arch.mmu.new_cr3(vcpu);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr3);
 
-int __kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
+int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS)
 		return 1;
@@ -670,12 +686,6 @@ int __kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 		vcpu->arch.cr8 = cr8;
 	return 0;
 }
-
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
-{
-	if (__kvm_set_cr8(vcpu, cr8))
-		kvm_inject_gp(vcpu, 0);
-}
 EXPORT_SYMBOL_GPL(kvm_set_cr8);
 
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
@@ -780,12 +790,12 @@ EXPORT_SYMBOL_GPL(kvm_get_dr);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	7
+#define KVM_SAVE_MSRS_BEGIN	8
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
-	HV_X64_MSR_APIC_ASSIST_PAGE,
+	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -835,7 +845,6 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	kvm_x86_ops->set_efer(vcpu, efer);
 
 	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
-	kvm_mmu_reset_context(vcpu);
 
 	/* Update reserved bits */
 	if ((efer ^ old_efer) & EFER_NX)
@@ -981,7 +990,7 @@ static inline u64 nsec_to_cycles(u64 nsec)
 	if (kvm_tsc_changes_freq())
 		printk_once(KERN_WARNING
 		 "kvm: unreliable cycle conversion on adjustable rate TSC\n");
-	ret = nsec * __get_cpu_var(cpu_tsc_khz);
+	ret = nsec * __this_cpu_read(cpu_tsc_khz);
 	do_div(ret, USEC_PER_SEC);
 	return ret;
 }
@@ -1011,7 +1020,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 	unsigned long flags;
 	s64 sdiff;
 
-	spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
+	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = data - native_read_tsc();
 	ns = get_kernel_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
@@ -1044,7 +1053,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 	kvm->arch.last_tsc_write = data;
 	kvm->arch.last_tsc_offset = offset;
 	kvm_x86_ops->write_tsc_offset(vcpu, offset);
-	spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 	/* Reset of TSC must disable overshoot protection below */
 	vcpu->arch.hv_clock.tsc_timestamp = 0;
@@ -1066,7 +1075,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	local_irq_save(flags);
 	kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
 	kernel_ns = get_kernel_ns();
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
 
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
@@ -1423,6 +1432,38 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	return 0;
 }
 
+static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
+{
+	gpa_t gpa = data & ~0x3f;
+
+	/* Bits 2:5 are resrved, Should be zero */
+	if (data & 0x3c)
+		return 1;
+
+	vcpu->arch.apf.msr_val = data;
+
+	if (!(data & KVM_ASYNC_PF_ENABLED)) {
+		kvm_clear_async_pf_completion_queue(vcpu);
+		kvm_async_pf_hash_reset(vcpu);
+		return 0;
+	}
+
+	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+		return 1;
+
+	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+	kvm_async_pf_wakeup_all(vcpu);
+	return 0;
+}
+
+static void kvmclock_reset(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.time_page) {
+		kvm_release_page_dirty(vcpu->arch.time_page);
+		vcpu->arch.time_page = NULL;
+	}
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -1480,10 +1521,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
-		if (vcpu->arch.time_page) {
-			kvm_release_page_dirty(vcpu->arch.time_page);
-			vcpu->arch.time_page = NULL;
-		}
+		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -1504,6 +1542,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		}
 		break;
 	}
+	case MSR_KVM_ASYNC_PF_EN:
+		if (kvm_pv_enable_async_pf(vcpu, data))
+			return 1;
+		break;
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
@@ -1558,6 +1600,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		} else
 			return set_msr_hyperv(vcpu, msr, data);
 		break;
+	case MSR_IA32_BBL_CR_CTL3:
+		/* Drop writes to this legacy MSR -- see rdmsr
+		 * counterpart for further detail.
+		 */
+		pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
+		break;
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
@@ -1780,6 +1828,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_KVM_SYSTEM_TIME_NEW:
 		data = vcpu->arch.time;
 		break;
+	case MSR_KVM_ASYNC_PF_EN:
+		data = vcpu->arch.apf.msr_val;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:
@@ -1809,6 +1860,19 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		} else
 			return get_msr_hyperv(vcpu, msr, pdata);
 		break;
+	case MSR_IA32_BBL_CR_CTL3:
+		/* This legacy MSR exists but isn't fully documented in current
+		 * silicon.  It is however accessed by winxp in very narrow
+		 * scenarios where it sets bit #19, itself documented as
+		 * a "reserved" bit.  Best effort attempt to source coherent
+		 * read data here should the balance of the register be
+		 * interpreted by the guest:
+		 *
+		 * L2 cache control register 3: 64GB range, 256KB size,
+		 * enabled, latency 0x1, configured
+		 */
+		data = 0xbe702111;
+		break;
 	default:
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
@@ -1909,6 +1973,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_SYNC_MMU:
+	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_ASSIGN_DEV_IRQ:
@@ -1927,6 +1992,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 	case KVM_CAP_XSAVE:
+	case KVM_CAP_ASYNC_PF:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2061,8 +2127,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (check_tsc_unstable()) {
 			kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta);
 			vcpu->arch.tsc_catchup = 1;
-			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 		}
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 		if (vcpu->cpu != cpu)
 			kvm_migrate_timers(vcpu);
 		vcpu->cpu = cpu;
@@ -2190,6 +2256,11 @@ out:
 	return r;
 }
 
+static void cpuid_mask(u32 *word, int wordnum)
+{
+	*word &= boot_cpu_data.x86_capability[wordnum];
+}
+
 static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			   u32 index)
 {
@@ -2264,7 +2335,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	case 1:
 		entry->edx &= kvm_supported_word0_x86_features;
+		cpuid_mask(&entry->edx, 0);
 		entry->ecx &= kvm_supported_word4_x86_features;
+		cpuid_mask(&entry->ecx, 4);
 		/* we support x2apic emulation even if host does not support
 		 * it since we emulate x2apic in software */
 		entry->ecx |= F(X2APIC);
@@ -2355,7 +2428,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	case 0x80000001:
 		entry->edx &= kvm_supported_word1_x86_features;
+		cpuid_mask(&entry->edx, 1);
 		entry->ecx &= kvm_supported_word6_x86_features;
+		cpuid_mask(&entry->ecx, 6);
 		break;
 	}
 
@@ -2527,9 +2602,6 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
 	if (mce->status & MCI_STATUS_UC) {
 		if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
 		    !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
-			printk(KERN_DEBUG "kvm: set_mce: "
-			       "injects mce exception while "
-			       "previous one is in progress!\n");
 			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 			return 0;
 		}
@@ -2600,8 +2672,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	vcpu->arch.interrupt.pending = events->interrupt.injected;
 	vcpu->arch.interrupt.nr = events->interrupt.nr;
 	vcpu->arch.interrupt.soft = events->interrupt.soft;
-	if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
-		kvm_pic_clear_isr_ack(vcpu->kvm);
 	if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
 		kvm_x86_ops->set_interrupt_shadow(vcpu,
 						  events->interrupt.shadow);
@@ -3174,20 +3244,18 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		struct kvm_memslots *slots, *old_slots;
 		unsigned long *dirty_bitmap;
 
-		r = -ENOMEM;
-		dirty_bitmap = vmalloc(n);
-		if (!dirty_bitmap)
-			goto out;
+		dirty_bitmap = memslot->dirty_bitmap_head;
+		if (memslot->dirty_bitmap == dirty_bitmap)
+			dirty_bitmap += n / sizeof(long);
 		memset(dirty_bitmap, 0, n);
 
 		r = -ENOMEM;
 		slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
-		if (!slots) {
-			vfree(dirty_bitmap);
+		if (!slots)
 			goto out;
-		}
 		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 		slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;
+		slots->generation++;
 
 		old_slots = kvm->memslots;
 		rcu_assign_pointer(kvm->memslots, slots);
@@ -3200,11 +3268,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		spin_unlock(&kvm->mmu_lock);
 
 		r = -EFAULT;
-		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) {
-			vfree(dirty_bitmap);
+		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
 			goto out;
-		}
-		vfree(dirty_bitmap);
 	} else {
 		r = -EFAULT;
 		if (clear_user(log->dirty_bitmap, n))
@@ -3271,8 +3336,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (vpic) {
 			r = kvm_ioapic_init(kvm);
 			if (r) {
+				mutex_lock(&kvm->slots_lock);
 				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
 							  &vpic->dev);
+				mutex_unlock(&kvm->slots_lock);
 				kfree(vpic);
 				goto create_irqchip_unlock;
 			}
@@ -3283,10 +3350,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		smp_wmb();
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
+			mutex_lock(&kvm->slots_lock);
 			mutex_lock(&kvm->irq_lock);
 			kvm_ioapic_destroy(kvm);
 			kvm_destroy_pic(kvm);
 			mutex_unlock(&kvm->irq_lock);
+			mutex_unlock(&kvm->slots_lock);
 		}
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
@@ -3562,63 +3631,63 @@ static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
 static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
 {
 	gpa_t t_gpa;
-	u32 error;
+	struct x86_exception exception;
 
 	BUG_ON(!mmu_is_nested(vcpu));
 
 	/* NPT walks are always user-walks */
 	access |= PFERR_USER_MASK;
-	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &error);
-	if (t_gpa == UNMAPPED_GVA)
-		vcpu->arch.fault.nested = true;
+	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
 
 	return t_gpa;
 }
 
-gpa_t kvm_mmu_gva_to_gpa_read(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)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
-	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
 }
 
- gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+ gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
+				struct x86_exception *exception)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 	access |= PFERR_FETCH_MASK;
-	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
 }
 
-gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
+			       struct x86_exception *exception)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 	access |= PFERR_WRITE_MASK;
-	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
 }
 
 /* uses this to access any guest's mapped memory without checking CPL */
-gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
+				struct x86_exception *exception)
 {
-	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, error);
+	return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception);
 }
 
 static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 				      struct kvm_vcpu *vcpu, u32 access,
-				      u32 *error)
+				      struct x86_exception *exception)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
 		gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access,
-							    error);
+							    exception);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
 
-		if (gpa == UNMAPPED_GVA) {
-			r = X86EMUL_PROPAGATE_FAULT;
-			goto out;
-		}
+		if (gpa == UNMAPPED_GVA)
+			return X86EMUL_PROPAGATE_FAULT;
 		ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
@@ -3635,31 +3704,35 @@ out:
 
 /* used for instruction fetching */
 static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes,
-				struct kvm_vcpu *vcpu, u32 *error)
+				struct kvm_vcpu *vcpu,
+				struct x86_exception *exception)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
-					  access | PFERR_FETCH_MASK, error);
+					  access | PFERR_FETCH_MASK,
+					  exception);
 }
 
 static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
-			       struct kvm_vcpu *vcpu, u32 *error)
+			       struct kvm_vcpu *vcpu,
+			       struct x86_exception *exception)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
-					  error);
+					  exception);
 }
 
 static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
-			       struct kvm_vcpu *vcpu, u32 *error)
+				      struct kvm_vcpu *vcpu,
+				      struct x86_exception *exception)
 {
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
 }
 
 static int kvm_write_guest_virt_system(gva_t addr, void *val,
 				       unsigned int bytes,
 				       struct kvm_vcpu *vcpu,
-				       u32 *error)
+				       struct x86_exception *exception)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
@@ -3667,15 +3740,13 @@ static int kvm_write_guest_virt_system(gva_t addr, void *val,
 	while (bytes) {
 		gpa_t gpa =  vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
 							     PFERR_WRITE_MASK,
-							     error);
+							     exception);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
 
-		if (gpa == UNMAPPED_GVA) {
-			r = X86EMUL_PROPAGATE_FAULT;
-			goto out;
-		}
+		if (gpa == UNMAPPED_GVA)
+			return X86EMUL_PROPAGATE_FAULT;
 		ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
@@ -3693,7 +3764,7 @@ out:
 static int emulator_read_emulated(unsigned long addr,
 				  void *val,
 				  unsigned int bytes,
-				  unsigned int *error_code,
+				  struct x86_exception *exception,
 				  struct kvm_vcpu *vcpu)
 {
 	gpa_t                 gpa;
@@ -3706,7 +3777,7 @@ static int emulator_read_emulated(unsigned long addr,
 		return X86EMUL_CONTINUE;
 	}
 
-	gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, error_code);
+	gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, exception);
 
 	if (gpa == UNMAPPED_GVA)
 		return X86EMUL_PROPAGATE_FAULT;
@@ -3715,8 +3786,8 @@ static int emulator_read_emulated(unsigned long addr,
 	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
 		goto mmio;
 
-	if (kvm_read_guest_virt(addr, val, bytes, vcpu, NULL)
-				== X86EMUL_CONTINUE)
+	if (kvm_read_guest_virt(addr, val, bytes, vcpu, exception)
+	    == X86EMUL_CONTINUE)
 		return X86EMUL_CONTINUE;
 
 mmio:
@@ -3740,7 +3811,7 @@ mmio:
 }
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
-			  const void *val, int bytes)
+			const void *val, int bytes)
 {
 	int ret;
 
@@ -3754,12 +3825,12 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 static int emulator_write_emulated_onepage(unsigned long addr,
 					   const void *val,
 					   unsigned int bytes,
-					   unsigned int *error_code,
+					   struct x86_exception *exception,
 					   struct kvm_vcpu *vcpu)
 {
 	gpa_t                 gpa;
 
-	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error_code);
+	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception);
 
 	if (gpa == UNMAPPED_GVA)
 		return X86EMUL_PROPAGATE_FAULT;
@@ -3792,7 +3863,7 @@ mmio:
 int emulator_write_emulated(unsigned long addr,
 			    const void *val,
 			    unsigned int bytes,
-			    unsigned int *error_code,
+			    struct x86_exception *exception,
 			    struct kvm_vcpu *vcpu)
 {
 	/* Crossing a page boundary? */
@@ -3800,7 +3871,7 @@ int emulator_write_emulated(unsigned long addr,
 		int rc, now;
 
 		now = -addr & ~PAGE_MASK;
-		rc = emulator_write_emulated_onepage(addr, val, now, error_code,
+		rc = emulator_write_emulated_onepage(addr, val, now, exception,
 						     vcpu);
 		if (rc != X86EMUL_CONTINUE)
 			return rc;
@@ -3808,7 +3879,7 @@ int emulator_write_emulated(unsigned long addr,
 		val += now;
 		bytes -= now;
 	}
-	return emulator_write_emulated_onepage(addr, val, bytes, error_code,
+	return emulator_write_emulated_onepage(addr, val, bytes, exception,
 					       vcpu);
 }
 
@@ -3826,7 +3897,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 				     const void *old,
 				     const void *new,
 				     unsigned int bytes,
-				     unsigned int *error_code,
+				     struct x86_exception *exception,
 				     struct kvm_vcpu *vcpu)
 {
 	gpa_t gpa;
@@ -3884,7 +3955,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 emul_write:
 	printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
 
-	return emulator_write_emulated(addr, new, bytes, error_code, vcpu);
+	return emulator_write_emulated(addr, new, bytes, exception, vcpu);
 }
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
@@ -3909,7 +3980,7 @@ static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
-	trace_kvm_pio(0, port, size, 1);
+	trace_kvm_pio(0, port, size, count);
 
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = 1;
@@ -3937,7 +4008,7 @@ static int emulator_pio_out_emulated(int size, unsigned short port,
 			      const void *val, unsigned int count,
 			      struct kvm_vcpu *vcpu)
 {
-	trace_kvm_pio(1, port, size, 1);
+	trace_kvm_pio(1, port, size, count);
 
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = 0;
@@ -3978,13 +4049,15 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
 		return X86EMUL_CONTINUE;
 
 	if (kvm_x86_ops->has_wbinvd_exit()) {
-		preempt_disable();
+		int cpu = get_cpu();
+
+		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
 		smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
 				wbinvd_ipi, NULL, 1);
-		preempt_enable();
+		put_cpu();
 		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
-	}
-	wbinvd();
+	} else
+		wbinvd();
 	return X86EMUL_CONTINUE;
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
@@ -4024,7 +4097,7 @@ static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu)
 		value = vcpu->arch.cr2;
 		break;
 	case 3:
-		value = vcpu->arch.cr3;
+		value = kvm_read_cr3(vcpu);
 		break;
 	case 4:
 		value = kvm_read_cr4(vcpu);
@@ -4058,7 +4131,7 @@ static int emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu)
 		res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
 		break;
 	case 8:
-		res = __kvm_set_cr8(vcpu, val & 0xfUL);
+		res = kvm_set_cr8(vcpu, val);
 		break;
 	default:
 		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
@@ -4089,8 +4162,8 @@ static unsigned long emulator_get_cached_segment_base(int seg,
 	return get_segment_base(vcpu, seg);
 }
 
-static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
-					   struct kvm_vcpu *vcpu)
+static bool emulator_get_cached_descriptor(struct desc_struct *desc, u32 *base3,
+					   int seg, struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment var;
 
@@ -4103,6 +4176,10 @@ static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
 		var.limit >>= 12;
 	set_desc_limit(desc, var.limit);
 	set_desc_base(desc, (unsigned long)var.base);
+#ifdef CONFIG_X86_64
+	if (base3)
+		*base3 = var.base >> 32;
+#endif
 	desc->type = var.type;
 	desc->s = var.s;
 	desc->dpl = var.dpl;
@@ -4115,8 +4192,8 @@ static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
 	return true;
 }
 
-static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg,
-					   struct kvm_vcpu *vcpu)
+static void emulator_set_cached_descriptor(struct desc_struct *desc, u32 base3,
+					   int seg, struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment var;
 
@@ -4124,6 +4201,9 @@ static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg,
 	kvm_get_segment(vcpu, &var, seg);
 
 	var.base = get_desc_base(desc);
+#ifdef CONFIG_X86_64
+	var.base |= ((u64)base3) << 32;
+#endif
 	var.limit = get_desc_limit(desc);
 	if (desc->g)
 		var.limit = (var.limit << 12) | 0xfff;
@@ -4211,12 +4291,13 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
-	if (ctxt->exception == PF_VECTOR)
-		kvm_propagate_fault(vcpu);
-	else if (ctxt->error_code_valid)
-		kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code);
+	if (ctxt->exception.vector == PF_VECTOR)
+		kvm_propagate_fault(vcpu, &ctxt->exception);
+	else if (ctxt->exception.error_code_valid)
+		kvm_queue_exception_e(vcpu, ctxt->exception.vector,
+				      ctxt->exception.error_code);
 	else
-		kvm_queue_exception(vcpu, ctxt->exception);
+		kvm_queue_exception(vcpu, ctxt->exception.vector);
 }
 
 static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -4272,13 +4353,19 @@ EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);
 
 static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 {
+	int r = EMULATE_DONE;
+
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	vcpu->run->internal.ndata = 0;
+	if (!is_guest_mode(vcpu)) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
+		r = EMULATE_FAIL;
+	}
 	kvm_queue_exception(vcpu, UD_VECTOR);
-	return EMULATE_FAIL;
+
+	return r;
 }
 
 static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
@@ -4307,10 +4394,11 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	return false;
 }
 
-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)
 {
 	int r;
 	struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
@@ -4328,44 +4416,19 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		init_emulate_ctxt(vcpu);
 		vcpu->arch.emulate_ctxt.interruptibility = 0;
-		vcpu->arch.emulate_ctxt.exception = -1;
+		vcpu->arch.emulate_ctxt.have_exception = false;
 		vcpu->arch.emulate_ctxt.perm_ok = false;
 
-		r = x86_decode_insn(&vcpu->arch.emulate_ctxt);
-		if (r == X86EMUL_PROPAGATE_FAULT)
-			goto done;
-
-		trace_kvm_emulate_insn_start(vcpu);
-
-		/* Only allow emulation of specific instructions on #UD
-		 * (namely VMMCALL, sysenter, sysexit, syscall)*/
-		if (emulation_type & EMULTYPE_TRAP_UD) {
-			if (!c->twobyte)
-				return EMULATE_FAIL;
-			switch (c->b) {
-			case 0x01: /* VMMCALL */
-				if (c->modrm_mod != 3 || c->modrm_rm != 1)
-					return EMULATE_FAIL;
-				break;
-			case 0x34: /* sysenter */
-			case 0x35: /* sysexit */
-				if (c->modrm_mod != 0 || c->modrm_rm != 0)
-					return EMULATE_FAIL;
-				break;
-			case 0x05: /* syscall */
-				if (c->modrm_mod != 0 || c->modrm_rm != 0)
-					return EMULATE_FAIL;
-				break;
-			default:
-				return EMULATE_FAIL;
-			}
+		vcpu->arch.emulate_ctxt.only_vendor_specific_insn
+			= emulation_type & EMULTYPE_TRAP_UD;
 
-			if (!(c->modrm_reg == 0 || c->modrm_reg == 3))
-				return EMULATE_FAIL;
-		}
+		r = x86_decode_insn(&vcpu->arch.emulate_ctxt, insn, insn_len);
 
+		trace_kvm_emulate_insn_start(vcpu);
 		++vcpu->stat.insn_emulation;
 		if (r)  {
+			if (emulation_type & EMULTYPE_TRAP_UD)
+				return EMULATE_FAIL;
 			if (reexecute_instruction(vcpu, cr2))
 				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
@@ -4393,8 +4456,7 @@ restart:
 		return handle_emulation_failure(vcpu);
 	}
 
-done:
-	if (vcpu->arch.emulate_ctxt.exception >= 0) {
+	if (vcpu->arch.emulate_ctxt.have_exception) {
 		inject_emulated_exception(vcpu);
 		r = EMULATE_DONE;
 	} else if (vcpu->arch.pio.count) {
@@ -4418,7 +4480,7 @@ done:
 
 	return r;
 }
-EXPORT_SYMBOL_GPL(emulate_instruction);
+EXPORT_SYMBOL_GPL(x86_emulate_instruction);
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 {
@@ -4432,7 +4494,7 @@ EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
 static void tsc_bad(void *info)
 {
-	__get_cpu_var(cpu_tsc_khz) = 0;
+	__this_cpu_write(cpu_tsc_khz, 0);
 }
 
 static void tsc_khz_changed(void *data)
@@ -4446,7 +4508,7 @@ static void tsc_khz_changed(void *data)
 		khz = cpufreq_quick_get(raw_smp_processor_id());
 	if (!khz)
 		khz = tsc_khz;
-	__get_cpu_var(cpu_tsc_khz) = khz;
+	__this_cpu_write(cpu_tsc_khz, khz);
 }
 
 static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
@@ -4503,7 +4565,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
@@ -4513,7 +4575,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 				send_ipi = 1;
 		}
 	}
-	spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -4569,9 +4631,11 @@ static void kvm_timer_init(void)
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
 		memset(&policy, 0, sizeof(policy));
-		cpufreq_get_policy(&policy, get_cpu());
+		cpu = get_cpu();
+		cpufreq_get_policy(&policy, cpu);
 		if (policy.cpuinfo.max_freq)
 			max_tsc_khz = policy.cpuinfo.max_freq;
+		put_cpu();
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
@@ -4656,7 +4720,6 @@ int kvm_arch_init(void *opaque)
 
 	kvm_x86_ops = ops;
 	kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
-	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 
@@ -5119,6 +5182,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu->fpu_active = 0;
 			kvm_x86_ops->fpu_deactivate(vcpu);
 		}
+		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
+			/* Page is swapped out. Do synthetic halt */
+			vcpu->arch.apf.halted = true;
+			r = 1;
+			goto out;
+		}
+		if (kvm_check_request(KVM_REQ_NMI, vcpu))
+			vcpu->arch.nmi_pending = true;
 	}
 
 	r = kvm_mmu_reload(vcpu);
@@ -5147,14 +5218,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_load_guest_fpu(vcpu);
 	kvm_load_guest_xcr0(vcpu);
 
-	atomic_set(&vcpu->guest_mode, 1);
-	smp_wmb();
+	vcpu->mode = IN_GUEST_MODE;
+
+	/* We should set ->mode before check ->requests,
+	 * see the comment in make_all_cpus_request.
+	 */
+	smp_mb();
 
 	local_irq_disable();
 
-	if (!atomic_read(&vcpu->guest_mode) || vcpu->requests
+	if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests
 	    || need_resched() || signal_pending(current)) {
-		atomic_set(&vcpu->guest_mode, 0);
+		vcpu->mode = OUTSIDE_GUEST_MODE;
 		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
@@ -5190,7 +5265,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
 
-	atomic_set(&vcpu->guest_mode, 0);
+	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 	local_irq_enable();
 
@@ -5247,7 +5322,8 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	r = 1;
 	while (r > 0) {
-		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
+		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+		    !vcpu->arch.apf.halted)
 			r = vcpu_enter_guest(vcpu);
 		else {
 			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
@@ -5260,6 +5336,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 					vcpu->arch.mp_state =
 						KVM_MP_STATE_RUNNABLE;
 				case KVM_MP_STATE_RUNNABLE:
+					vcpu->arch.apf.halted = false;
 					break;
 				case KVM_MP_STATE_SIPI_RECEIVED:
 				default:
@@ -5281,6 +5358,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			vcpu->run->exit_reason = KVM_EXIT_INTR;
 			++vcpu->stat.request_irq_exits;
 		}
+
+		kvm_check_async_pf_completion(vcpu);
+
 		if (signal_pending(current)) {
 			r = -EINTR;
 			vcpu->run->exit_reason = KVM_EXIT_INTR;
@@ -5305,6 +5385,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int r;
 	sigset_t sigsaved;
 
+	if (!tsk_used_math(current) && init_fpu(current))
+		return -ENOMEM;
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -5316,8 +5399,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	/* re-sync apic's tpr */
-	if (!irqchip_in_kernel(vcpu->kvm))
-		kvm_set_cr8(vcpu, kvm_run->cr8);
+	if (!irqchip_in_kernel(vcpu->kvm)) {
+		if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) {
+			r = -EINVAL;
+			goto out;
+		}
+	}
 
 	if (vcpu->arch.pio.count || vcpu->mmio_needed) {
 		if (vcpu->mmio_needed) {
@@ -5326,7 +5413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			vcpu->mmio_needed = 0;
 		}
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+		r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r != EMULATE_DONE) {
 			r = 0;
@@ -5439,7 +5526,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
-	sregs->cr3 = vcpu->arch.cr3;
+	sregs->cr3 = kvm_read_cr3(vcpu);
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.efer;
@@ -5496,7 +5583,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
 	int mmu_reset_needed = 0;
-	int pending_vec, max_bits;
+	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
 	dt.size = sregs->idt.limit;
@@ -5507,8 +5594,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->set_gdt(vcpu, &dt);
 
 	vcpu->arch.cr2 = sregs->cr2;
-	mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
+	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -5522,10 +5610,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
+	if (sregs->cr4 & X86_CR4_OSXSAVE)
+		update_cpuid(vcpu);
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
-		load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
+		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
@@ -5536,8 +5629,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (pending_vec < max_bits) {
 		kvm_queue_interrupt(vcpu, pending_vec, false);
 		pr_debug("Set back pending irq %d\n", pending_vec);
-		if (irqchip_in_kernel(vcpu->kvm))
-			kvm_pic_clear_isr_ack(vcpu->kvm);
 	}
 
 	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
@@ -5733,10 +5824,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	kvmclock_reset(vcpu);
 
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	fx_free(vcpu);
@@ -5774,6 +5862,8 @@ free_vcpu:
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.apf.msr_val = 0;
+
 	vcpu_load(vcpu);
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
@@ -5793,6 +5883,13 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.dr7 = DR7_FIXED_1;
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
+	vcpu->arch.apf.msr_val = 0;
+
+	kvmclock_reset(vcpu);
+
+	kvm_clear_async_pf_completion_queue(vcpu);
+	kvm_async_pf_hash_reset(vcpu);
+	vcpu->arch.apf.halted = false;
 
 	return kvm_x86_ops->vcpu_reset(vcpu);
 }
@@ -5882,6 +5979,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
 		goto fail_free_mce_banks;
 
+	kvm_async_pf_hash_reset(vcpu);
+
 	return 0;
 fail_free_mce_banks:
 	kfree(vcpu->arch.mce_banks);
@@ -5907,22 +6006,17 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.pio_data);
 }
 
-struct  kvm *kvm_arch_create_vm(void)
+int kvm_arch_init_vm(struct kvm *kvm)
 {
-	struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
-
-	if (!kvm)
-		return ERR_PTR(-ENOMEM);
-
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
 
-	spin_lock_init(&kvm->arch.tsc_write_lock);
+	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 
-	return kvm;
+	return 0;
 }
 
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
@@ -5940,8 +6034,10 @@ static void kvm_free_vcpus(struct kvm *kvm)
 	/*
 	 * Unpin any mmu pages first.
 	 */
-	kvm_for_each_vcpu(i, vcpu, kvm)
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvm_clear_async_pf_completion_queue(vcpu);
 		kvm_unload_vcpu_mmu(vcpu);
+	}
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_arch_vcpu_free(vcpu);
 
@@ -5965,13 +6061,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
-	kvm_free_physmem(kvm);
 	if (kvm->arch.apic_access_page)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
-	cleanup_srcu_struct(&kvm->srcu);
-	kfree(kvm);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -6019,7 +6112,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				int user_alloc)
 {
 
-	int npages = mem->memory_size >> PAGE_SHIFT;
+	int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
 
 	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
 		int ret;
@@ -6034,12 +6127,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 			       "failed to munmap memory\n");
 	}
 
+	if (!kvm->arch.n_requested_mmu_pages)
+		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
+
 	spin_lock(&kvm->mmu_lock);
-	if (!kvm->arch.n_requested_mmu_pages) {
-		unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
+	if (nr_mmu_pages)
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
-	}
-
 	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	spin_unlock(&kvm->mmu_lock);
 }
@@ -6052,7 +6145,9 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
+	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+		!vcpu->arch.apf.halted)
+		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
 		|| vcpu->arch.nmi_pending ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
@@ -6071,7 +6166,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 
 	me = get_cpu();
 	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (atomic_xchg(&vcpu->guest_mode, 0))
+		if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE)
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
@@ -6111,6 +6206,147 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 }
 EXPORT_SYMBOL_GPL(kvm_set_rflags);
 
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
+{
+	int r;
+
+	if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+	      is_error_page(work->page))
+		return;
+
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r))
+		return;
+
+	if (!vcpu->arch.mmu.direct_map &&
+	      work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+		return;
+
+	vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+}
+
+static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
+{
+	return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU));
+}
+
+static inline u32 kvm_async_pf_next_probe(u32 key)
+{
+	return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1);
+}
+
+static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	u32 key = kvm_async_pf_hash_fn(gfn);
+
+	while (vcpu->arch.apf.gfns[key] != ~0)
+		key = kvm_async_pf_next_probe(key);
+
+	vcpu->arch.apf.gfns[key] = gfn;
+}
+
+static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	int i;
+	u32 key = kvm_async_pf_hash_fn(gfn);
+
+	for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) &&
+		     (vcpu->arch.apf.gfns[key] != gfn &&
+		      vcpu->arch.apf.gfns[key] != ~0); i++)
+		key = kvm_async_pf_next_probe(key);
+
+	return key;
+}
+
+bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn;
+}
+
+static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	u32 i, j, k;
+
+	i = j = kvm_async_pf_gfn_slot(vcpu, gfn);
+	while (true) {
+		vcpu->arch.apf.gfns[i] = ~0;
+		do {
+			j = kvm_async_pf_next_probe(j);
+			if (vcpu->arch.apf.gfns[j] == ~0)
+				return;
+			k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]);
+			/*
+			 * k lies cyclically in ]i,j]
+			 * |    i.k.j |
+			 * |....j i.k.| or  |.k..j i...|
+			 */
+		} while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j));
+		vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j];
+		i = j;
+	}
+}
+
+static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
+{
+
+	return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val,
+				      sizeof(val));
+}
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+				     struct kvm_async_pf *work)
+{
+	struct x86_exception fault;
+
+	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
+
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
+	    (vcpu->arch.apf.send_user_only &&
+	     kvm_x86_ops->get_cpl(vcpu) == 0))
+		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+	else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
+		fault.vector = PF_VECTOR;
+		fault.error_code_valid = true;
+		fault.error_code = 0;
+		fault.nested_page_fault = false;
+		fault.address = work->arch.token;
+		kvm_inject_page_fault(vcpu, &fault);
+	}
+}
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+				 struct kvm_async_pf *work)
+{
+	struct x86_exception fault;
+
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	if (is_error_page(work->page))
+		work->arch.token = ~0; /* broadcast wakeup */
+	else
+		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+
+	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
+	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+		fault.vector = PF_VECTOR;
+		fault.error_code_valid = true;
+		fault.error_code = 0;
+		fault.nested_page_fault = false;
+		fault.address = work->arch.token;
+		kvm_inject_page_fault(vcpu, &fault);
+	}
+	vcpu->arch.apf.halted = false;
+}
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
+		return true;
+	else
+		return !kvm_event_needs_reinjection(vcpu) &&
+			kvm_x86_ops->interrupt_allowed(vcpu);
+}
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);