Merge branch 'master'; commit 'v2.6.38-rc7' into next

7 files changed, 666 insertions, 185 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 7f1178f6b83..f63ccb0a598 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -15,3 +15,6 @@ config KVM_APIC_ARCHITECTURE
 
 config KVM_MMIO
        bool
+
+config KVM_ASYNC_PF
+       bool
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 7c98928b09d..ae72ae604c8 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -55,58 +55,31 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
 	return index;
 }
 
-static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
+static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
 {
-	struct kvm_assigned_dev_kernel *assigned_dev;
-	int i;
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	u32 vector;
+	int index;
 
-	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
-				    interrupt_work);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_INTX) {
+		spin_lock(&assigned_dev->intx_lock);
+		disable_irq_nosync(irq);
+		assigned_dev->host_irq_disabled = true;
+		spin_unlock(&assigned_dev->intx_lock);
+	}
 
-	spin_lock_irq(&assigned_dev->assigned_dev_lock);
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		struct kvm_guest_msix_entry *guest_entries =
-			assigned_dev->guest_msix_entries;
-		for (i = 0; i < assigned_dev->entries_nr; i++) {
-			if (!(guest_entries[i].flags &
-					KVM_ASSIGNED_MSIX_PENDING))
-				continue;
-			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+		index = find_index_from_host_irq(assigned_dev, irq);
+		if (index >= 0) {
+			vector = assigned_dev->
+					guest_msix_entries[index].vector;
 			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id,
-				    guest_entries[i].vector, 1);
+				    assigned_dev->irq_source_id, vector, 1);
 		}
 	} else
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
 			    assigned_dev->guest_irq, 1);
 
-	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
-}
-
-static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
-{
-	unsigned long flags;
-	struct kvm_assigned_dev_kernel *assigned_dev =
-		(struct kvm_assigned_dev_kernel *) dev_id;
-
-	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		int index = find_index_from_host_irq(assigned_dev, irq);
-		if (index < 0)
-			goto out;
-		assigned_dev->guest_msix_entries[index].flags |=
-			KVM_ASSIGNED_MSIX_PENDING;
-	}
-
-	schedule_work(&assigned_dev->interrupt_work);
-
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
-		disable_irq_nosync(irq);
-		assigned_dev->host_irq_disabled = true;
-	}
-
-out:
-	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -114,7 +87,6 @@ out:
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_assigned_dev_kernel *dev;
-	unsigned long flags;
 
 	if (kian->gsi == -1)
 		return;
@@ -127,12 +99,12 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 	/* The guest irq may be shared so this ack may be
 	 * from another device.
 	 */
-	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
+	spin_lock(&dev->intx_lock);
 	if (dev->host_irq_disabled) {
 		enable_irq(dev->host_irq);
 		dev->host_irq_disabled = false;
 	}
-	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
+	spin_unlock(&dev->intx_lock);
 }
 
 static void deassign_guest_irq(struct kvm *kvm,
@@ -141,6 +113,9 @@ static void deassign_guest_irq(struct kvm *kvm,
 	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
 	assigned_dev->ack_notifier.gsi = -1;
 
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+		    assigned_dev->guest_irq, 0);
+
 	if (assigned_dev->irq_source_id != -1)
 		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
 	assigned_dev->irq_source_id = -1;
@@ -152,28 +127,19 @@ static void deassign_host_irq(struct kvm *kvm,
 			      struct kvm_assigned_dev_kernel *assigned_dev)
 {
 	/*
-	 * In kvm_free_device_irq, cancel_work_sync return true if:
-	 * 1. work is scheduled, and then cancelled.
-	 * 2. work callback is executed.
-	 *
-	 * The first one ensured that the irq is disabled and no more events
-	 * would happen. But for the second one, the irq may be enabled (e.g.
-	 * for MSI). So we disable irq here to prevent further events.
+	 * We disable irq here to prevent further events.
 	 *
 	 * Notice this maybe result in nested disable if the interrupt type is
 	 * INTx, but it's OK for we are going to free it.
 	 *
 	 * If this function is a part of VM destroy, please ensure that till
 	 * now, the kvm state is still legal for probably we also have to wait
-	 * interrupt_work done.
+	 * on a currently running IRQ handler.
 	 */
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
 		int i;
 		for (i = 0; i < assigned_dev->entries_nr; i++)
-			disable_irq_nosync(assigned_dev->
-					   host_msix_entries[i].vector);
-
-		cancel_work_sync(&assigned_dev->interrupt_work);
+			disable_irq(assigned_dev->host_msix_entries[i].vector);
 
 		for (i = 0; i < assigned_dev->entries_nr; i++)
 			free_irq(assigned_dev->host_msix_entries[i].vector,
@@ -185,8 +151,7 @@ static void deassign_host_irq(struct kvm *kvm,
 		pci_disable_msix(assigned_dev->dev);
 	} else {
 		/* Deal with MSI and INTx */
-		disable_irq_nosync(assigned_dev->host_irq);
-		cancel_work_sync(&assigned_dev->interrupt_work);
+		disable_irq(assigned_dev->host_irq);
 
 		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
 
@@ -232,7 +197,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 {
 	kvm_free_assigned_irq(kvm, assigned_dev);
 
-	pci_reset_function(assigned_dev->dev);
+	__pci_reset_function(assigned_dev->dev);
+	pci_restore_state(assigned_dev->dev);
 
 	pci_release_regions(assigned_dev->dev);
 	pci_disable_device(assigned_dev->dev);
@@ -265,8 +231,8 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 	 * on the same interrupt line is not a happy situation: there
 	 * are going to be long delays in accepting, acking, etc.
 	 */
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
-			0, "kvm_assigned_intx_device", (void *)dev))
+	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
+				 IRQF_ONESHOT, dev->irq_name, (void *)dev))
 		return -EIO;
 	return 0;
 }
@@ -284,8 +250,8 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 	}
 
 	dev->host_irq = dev->dev->irq;
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
-			"kvm_assigned_msi_device", (void *)dev)) {
+	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
+				 0, dev->irq_name, (void *)dev)) {
 		pci_disable_msi(dev->dev);
 		return -EIO;
 	}
@@ -310,10 +276,9 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 		return r;
 
 	for (i = 0; i < dev->entries_nr; i++) {
-		r = request_irq(dev->host_msix_entries[i].vector,
-				kvm_assigned_dev_intr, 0,
-				"kvm_assigned_msix_device",
-				(void *)dev);
+		r = request_threaded_irq(dev->host_msix_entries[i].vector,
+					 NULL, kvm_assigned_dev_thread,
+					 0, dev->irq_name, (void *)dev);
 		if (r)
 			goto err;
 	}
@@ -370,6 +335,9 @@ static int assign_host_irq(struct kvm *kvm,
 	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
 		return r;
 
+	snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s",
+		 pci_name(dev->dev));
+
 	switch (host_irq_type) {
 	case KVM_DEV_IRQ_HOST_INTX:
 		r = assigned_device_enable_host_intx(kvm, dev);
@@ -547,6 +515,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	}
 
 	pci_reset_function(dev);
+	pci_save_state(dev);
 
 	match->assigned_dev_id = assigned_dev->assigned_dev_id;
 	match->host_segnr = assigned_dev->segnr;
@@ -554,12 +523,10 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	match->host_devfn = assigned_dev->devfn;
 	match->flags = assigned_dev->flags;
 	match->dev = dev;
-	spin_lock_init(&match->assigned_dev_lock);
+	spin_lock_init(&match->intx_lock);
 	match->irq_source_id = -1;
 	match->kvm = kvm;
 	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
-	INIT_WORK(&match->interrupt_work,
-		  kvm_assigned_dev_interrupt_work_handler);
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
@@ -579,6 +546,7 @@ out:
 	mutex_unlock(&kvm->lock);
 	return r;
 out_list_del:
+	pci_restore_state(dev);
 	list_del(&match->list);
 	pci_release_regions(dev);
 out_disable:
@@ -651,9 +619,9 @@ static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
 			r = -ENOMEM;
 			goto msix_nr_out;
 		}
-		adev->guest_msix_entries = kzalloc(
-				sizeof(struct kvm_guest_msix_entry) *
-				entry_nr->entry_nr, GFP_KERNEL);
+		adev->guest_msix_entries =
+			kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr,
+				GFP_KERNEL);
 		if (!adev->guest_msix_entries) {
 			kfree(adev->host_msix_entries);
 			r = -ENOMEM;
@@ -706,7 +674,7 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 				  unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
-	int r = -ENOTTY;
+	int r;
 
 	switch (ioctl) {
 	case KVM_ASSIGN_PCI_DEVICE: {
@@ -724,7 +692,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 		r = -EOPNOTSUPP;
 		break;
 	}
-#ifdef KVM_CAP_ASSIGN_DEV_IRQ
 	case KVM_ASSIGN_DEV_IRQ: {
 		struct kvm_assigned_irq assigned_irq;
 
@@ -747,8 +714,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#endif
-#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
 	case KVM_DEASSIGN_PCI_DEVICE: {
 		struct kvm_assigned_pci_dev assigned_dev;
 
@@ -760,7 +725,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#endif
 #ifdef KVM_CAP_IRQ_ROUTING
 	case KVM_SET_GSI_ROUTING: {
 		struct kvm_irq_routing routing;
@@ -813,6 +777,9 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 		break;
 	}
 #endif
+	default:
+		r = -ENOTTY;
+		break;
 	}
 out:
 	return r;
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
new file mode 100644
index 00000000000..74268b4c2ee
--- /dev/null
+++ b/virt/kvm/async_pf.c
@@ -0,0 +1,216 @@
+/*
+ * kvm asynchronous fault support
+ *
+ * Copyright 2010 Red Hat, Inc.
+ *
+ * Author:
+ *      Gleb Natapov <gleb@redhat.com>
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/mmu_context.h>
+
+#include "async_pf.h"
+#include <trace/events/kvm.h>
+
+static struct kmem_cache *async_pf_cache;
+
+int kvm_async_pf_init(void)
+{
+	async_pf_cache = KMEM_CACHE(kvm_async_pf, 0);
+
+	if (!async_pf_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void kvm_async_pf_deinit(void)
+{
+	if (async_pf_cache)
+		kmem_cache_destroy(async_pf_cache);
+	async_pf_cache = NULL;
+}
+
+void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	INIT_LIST_HEAD(&vcpu->async_pf.done);
+	INIT_LIST_HEAD(&vcpu->async_pf.queue);
+	spin_lock_init(&vcpu->async_pf.lock);
+}
+
+static void async_pf_execute(struct work_struct *work)
+{
+	struct page *page = NULL;
+	struct kvm_async_pf *apf =
+		container_of(work, struct kvm_async_pf, work);
+	struct mm_struct *mm = apf->mm;
+	struct kvm_vcpu *vcpu = apf->vcpu;
+	unsigned long addr = apf->addr;
+	gva_t gva = apf->gva;
+
+	might_sleep();
+
+	use_mm(mm);
+	down_read(&mm->mmap_sem);
+	get_user_pages(current, mm, addr, 1, 1, 0, &page, NULL);
+	up_read(&mm->mmap_sem);
+	unuse_mm(mm);
+
+	spin_lock(&vcpu->async_pf.lock);
+	list_add_tail(&apf->link, &vcpu->async_pf.done);
+	apf->page = page;
+	apf->done = true;
+	spin_unlock(&vcpu->async_pf.lock);
+
+	/*
+	 * apf may be freed by kvm_check_async_pf_completion() after
+	 * this point
+	 */
+
+	trace_kvm_async_pf_completed(addr, page, gva);
+
+	if (waitqueue_active(&vcpu->wq))
+		wake_up_interruptible(&vcpu->wq);
+
+	mmdrop(mm);
+	kvm_put_kvm(vcpu->kvm);
+}
+
+void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
+{
+	/* cancel outstanding work queue item */
+	while (!list_empty(&vcpu->async_pf.queue)) {
+		struct kvm_async_pf *work =
+			list_entry(vcpu->async_pf.queue.next,
+				   typeof(*work), queue);
+		cancel_work_sync(&work->work);
+		list_del(&work->queue);
+		if (!work->done) /* work was canceled */
+			kmem_cache_free(async_pf_cache, work);
+	}
+
+	spin_lock(&vcpu->async_pf.lock);
+	while (!list_empty(&vcpu->async_pf.done)) {
+		struct kvm_async_pf *work =
+			list_entry(vcpu->async_pf.done.next,
+				   typeof(*work), link);
+		list_del(&work->link);
+		if (work->page)
+			put_page(work->page);
+		kmem_cache_free(async_pf_cache, work);
+	}
+	spin_unlock(&vcpu->async_pf.lock);
+
+	vcpu->async_pf.queued = 0;
+}
+
+void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
+{
+	struct kvm_async_pf *work;
+
+	while (!list_empty_careful(&vcpu->async_pf.done) &&
+	      kvm_arch_can_inject_async_page_present(vcpu)) {
+		spin_lock(&vcpu->async_pf.lock);
+		work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
+					      link);
+		list_del(&work->link);
+		spin_unlock(&vcpu->async_pf.lock);
+
+		if (work->page)
+			kvm_arch_async_page_ready(vcpu, work);
+		kvm_arch_async_page_present(vcpu, work);
+
+		list_del(&work->queue);
+		vcpu->async_pf.queued--;
+		if (work->page)
+			put_page(work->page);
+		kmem_cache_free(async_pf_cache, work);
+	}
+}
+
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+		       struct kvm_arch_async_pf *arch)
+{
+	struct kvm_async_pf *work;
+
+	if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
+		return 0;
+
+	/* setup delayed work */
+
+	/*
+	 * do alloc nowait since if we are going to sleep anyway we
+	 * may as well sleep faulting in page
+	 */
+	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
+	if (!work)
+		return 0;
+
+	work->page = NULL;
+	work->done = false;
+	work->vcpu = vcpu;
+	work->gva = gva;
+	work->addr = gfn_to_hva(vcpu->kvm, gfn);
+	work->arch = *arch;
+	work->mm = current->mm;
+	atomic_inc(&work->mm->mm_count);
+	kvm_get_kvm(work->vcpu->kvm);
+
+	/* this can't really happen otherwise gfn_to_pfn_async
+	   would succeed */
+	if (unlikely(kvm_is_error_hva(work->addr)))
+		goto retry_sync;
+
+	INIT_WORK(&work->work, async_pf_execute);
+	if (!schedule_work(&work->work))
+		goto retry_sync;
+
+	list_add_tail(&work->queue, &vcpu->async_pf.queue);
+	vcpu->async_pf.queued++;
+	kvm_arch_async_page_not_present(vcpu, work);
+	return 1;
+retry_sync:
+	kvm_put_kvm(work->vcpu->kvm);
+	mmdrop(work->mm);
+	kmem_cache_free(async_pf_cache, work);
+	return 0;
+}
+
+int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
+{
+	struct kvm_async_pf *work;
+
+	if (!list_empty_careful(&vcpu->async_pf.done))
+		return 0;
+
+	work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
+	if (!work)
+		return -ENOMEM;
+
+	work->page = bad_page;
+	get_page(bad_page);
+	INIT_LIST_HEAD(&work->queue); /* for list_del to work */
+
+	spin_lock(&vcpu->async_pf.lock);
+	list_add_tail(&work->link, &vcpu->async_pf.done);
+	spin_unlock(&vcpu->async_pf.lock);
+
+	vcpu->async_pf.queued++;
+	return 0;
+}
diff --git a/virt/kvm/async_pf.h b/virt/kvm/async_pf.h
new file mode 100644
index 00000000000..e7ef6447cb8
--- /dev/null
+++ b/virt/kvm/async_pf.h
@@ -0,0 +1,36 @@
+/*
+ * kvm asynchronous fault support
+ *
+ * Copyright 2010 Red Hat, Inc.
+ *
+ * Author:
+ *      Gleb Natapov <gleb@redhat.com>
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef __KVM_ASYNC_PF_H__
+#define __KVM_ASYNC_PF_H__
+
+#ifdef CONFIG_KVM_ASYNC_PF
+int kvm_async_pf_init(void);
+void kvm_async_pf_deinit(void);
+void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu);
+#else
+#define kvm_async_pf_init() (0)
+#define kvm_async_pf_deinit() do{}while(0)
+#define kvm_async_pf_vcpu_init(C) do{}while(0)
+#endif
+
+#endif
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index c1f1e3c6298..2ca4535f4fb 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -44,14 +44,19 @@
  */
 
 struct _irqfd {
-	struct kvm               *kvm;
-	struct eventfd_ctx       *eventfd;
-	int                       gsi;
-	struct list_head          list;
-	poll_table                pt;
-	wait_queue_t              wait;
-	struct work_struct        inject;
-	struct work_struct        shutdown;
+	/* Used for MSI fast-path */
+	struct kvm *kvm;
+	wait_queue_t wait;
+	/* Update side is protected by irqfds.lock */
+	struct kvm_kernel_irq_routing_entry __rcu *irq_entry;
+	/* Used for level IRQ fast-path */
+	int gsi;
+	struct work_struct inject;
+	/* Used for setup/shutdown */
+	struct eventfd_ctx *eventfd;
+	struct list_head list;
+	poll_table pt;
+	struct work_struct shutdown;
 };
 
 static struct workqueue_struct *irqfd_cleanup_wq;
@@ -125,14 +130,22 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
 	unsigned long flags = (unsigned long)key;
+	struct kvm_kernel_irq_routing_entry *irq;
+	struct kvm *kvm = irqfd->kvm;
 
-	if (flags & POLLIN)
+	if (flags & POLLIN) {
+		rcu_read_lock();
+		irq = rcu_dereference(irqfd->irq_entry);
 		/* An event has been signaled, inject an interrupt */
-		schedule_work(&irqfd->inject);
+		if (irq)
+			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+		else
+			schedule_work(&irqfd->inject);
+		rcu_read_unlock();
+	}
 
 	if (flags & POLLHUP) {
 		/* The eventfd is closing, detach from KVM */
-		struct kvm *kvm = irqfd->kvm;
 		unsigned long flags;
 
 		spin_lock_irqsave(&kvm->irqfds.lock, flags);
@@ -163,9 +176,31 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 	add_wait_queue(wqh, &irqfd->wait);
 }
 
+/* Must be called under irqfds.lock */
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
+			 struct kvm_irq_routing_table *irq_rt)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	struct hlist_node *n;
+
+	if (irqfd->gsi >= irq_rt->nr_rt_entries) {
+		rcu_assign_pointer(irqfd->irq_entry, NULL);
+		return;
+	}
+
+	hlist_for_each_entry(e, n, &irq_rt->map[irqfd->gsi], link) {
+		/* Only fast-path MSI. */
+		if (e->type == KVM_IRQ_ROUTING_MSI)
+			rcu_assign_pointer(irqfd->irq_entry, e);
+		else
+			rcu_assign_pointer(irqfd->irq_entry, NULL);
+	}
+}
+
 static int
 kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 {
+	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
 	struct file *file = NULL;
 	struct eventfd_ctx *eventfd = NULL;
@@ -215,6 +250,10 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 		goto fail;
 	}
 
+	irq_rt = rcu_dereference_protected(kvm->irq_routing,
+					   lockdep_is_held(&kvm->irqfds.lock));
+	irqfd_update(kvm, irqfd, irq_rt);
+
 	events = file->f_op->poll(file, &irqfd->pt);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
@@ -271,8 +310,17 @@ kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
 	spin_lock_irq(&kvm->irqfds.lock);
 
 	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
-		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi)
+		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi) {
+			/*
+			 * This rcu_assign_pointer is needed for when
+			 * another thread calls kvm_irqfd_update before
+			 * we flush workqueue below.
+			 * It is paired with synchronize_rcu done by caller
+			 * of that function.
+			 */
+			rcu_assign_pointer(irqfd->irq_entry, NULL);
 			irqfd_deactivate(irqfd);
+		}
 	}
 
 	spin_unlock_irq(&kvm->irqfds.lock);
@@ -322,6 +370,25 @@ kvm_irqfd_release(struct kvm *kvm)
 }
 
 /*
+ * Change irq_routing and irqfd.
+ * Caller must invoke synchronize_rcu afterwards.
+ */
+void kvm_irq_routing_update(struct kvm *kvm,
+			    struct kvm_irq_routing_table *irq_rt)
+{
+	struct _irqfd *irqfd;
+
+	spin_lock_irq(&kvm->irqfds.lock);
+
+	rcu_assign_pointer(kvm->irq_routing, irq_rt);
+
+	list_for_each_entry(irqfd, &kvm->irqfds.items, list)
+		irqfd_update(kvm, irqfd, irq_rt);
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+}
+
+/*
  * create a host-wide workqueue for issuing deferred shutdown requests
  * aggregated from all vm* instances. We need our own isolated single-thread
  * queue to prevent deadlock against flushing the normal work-queue.
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 8edca9141b7..9f614b4e365 100644
--- a/virt/kvm/irq_comm.c
+++ b/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;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5225052aebc..f29abeb6a91 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -55,6 +55,7 @@
 #include <asm-generic/bitops/le.h>
 
 #include "coalesced_mmio.h"
+#include "async_pf.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
@@ -89,7 +90,8 @@ static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
-static bool kvm_rebooting;
+bool kvm_rebooting;
+EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
@@ -102,8 +104,26 @@ static pfn_t fault_pfn;
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
-		struct page *page = compound_head(pfn_to_page(pfn));
-		return PageReserved(page);
+		int reserved;
+		struct page *tail = pfn_to_page(pfn);
+		struct page *head = compound_trans_head(tail);
+		reserved = PageReserved(head);
+		if (head != tail) {
+			/*
+			 * "head" is not a dangling pointer
+			 * (compound_trans_head takes care of that)
+			 * but the hugepage may have been splitted
+			 * from under us (and we may not hold a
+			 * reference count on the head page so it can
+			 * be reused before we run PageReferenced), so
+			 * we've to check PageTail before returning
+			 * what we just read.
+			 */
+			smp_rmb();
+			if (PageTail(tail))
+				return reserved;
+		}
+		return PageReserved(tail);
 	}
 
 	return true;
@@ -167,8 +187,12 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
+	int dirty_count = kvm->tlbs_dirty;
+
+	smp_mb();
 	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
+	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
@@ -186,6 +210,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	init_waitqueue_head(&vcpu->wq);
+	kvm_async_pf_vcpu_init(vcpu);
 
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page) {
@@ -247,7 +272,7 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
 	kvm->mmu_notifier_seq++;
-	need_tlb_flush = kvm_unmap_hva(kvm, address);
+	need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -291,6 +316,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	kvm->mmu_notifier_count++;
 	for (; start < end; start += PAGE_SIZE)
 		need_tlb_flush |= kvm_unmap_hva(kvm, start);
+	need_tlb_flush |= kvm->tlbs_dirty;
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -344,6 +370,22 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 	return young;
 }
 
+static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
+				       struct mm_struct *mm,
+				       unsigned long address)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	int young, idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+	young = kvm_test_age_hva(kvm, address);
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return young;
+}
+
 static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 				     struct mm_struct *mm)
 {
@@ -360,6 +402,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
+	.test_young		= kvm_mmu_notifier_test_young,
 	.change_pte		= kvm_mmu_notifier_change_pte,
 	.release		= kvm_mmu_notifier_release,
 };
@@ -381,11 +424,15 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 
 static struct kvm *kvm_create_vm(void)
 {
-	int r = 0, i;
-	struct kvm *kvm = kvm_arch_create_vm();
+	int r, i;
+	struct kvm *kvm = kvm_arch_alloc_vm();
 
-	if (IS_ERR(kvm))
-		goto out;
+	if (!kvm)
+		return ERR_PTR(-ENOMEM);
+
+	r = kvm_arch_init_vm(kvm);
+	if (r)
+		goto out_err_nodisable;
 
 	r = hardware_enable_all();
 	if (r)
@@ -399,23 +446,19 @@ static struct kvm *kvm_create_vm(void)
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
-		goto out_err;
+		goto out_err_nosrcu;
 	if (init_srcu_struct(&kvm->srcu))
-		goto out_err;
+		goto out_err_nosrcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
 					GFP_KERNEL);
-		if (!kvm->buses[i]) {
-			cleanup_srcu_struct(&kvm->srcu);
+		if (!kvm->buses[i])
 			goto out_err;
-		}
 	}
 
 	r = kvm_init_mmu_notifier(kvm);
-	if (r) {
-		cleanup_srcu_struct(&kvm->srcu);
+	if (r)
 		goto out_err;
-	}
 
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
@@ -429,19 +472,35 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
-out:
+
 	return kvm;
 
 out_err:
+	cleanup_srcu_struct(&kvm->srcu);
+out_err_nosrcu:
 	hardware_disable_all();
 out_err_nodisable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
 	kfree(kvm->memslots);
-	kfree(kvm);
+	kvm_arch_free_vm(kvm);
 	return ERR_PTR(r);
 }
 
+static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+	if (!memslot->dirty_bitmap)
+		return;
+
+	if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
+		vfree(memslot->dirty_bitmap_head);
+	else
+		kfree(memslot->dirty_bitmap_head);
+
+	memslot->dirty_bitmap = NULL;
+	memslot->dirty_bitmap_head = NULL;
+}
+
 /*
  * Free any memory in @free but not in @dont.
  */
@@ -454,7 +513,7 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 		vfree(free->rmap);
 
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
-		vfree(free->dirty_bitmap);
+		kvm_destroy_dirty_bitmap(free);
 
 
 	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
@@ -465,7 +524,6 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 	}
 
 	free->npages = 0;
-	free->dirty_bitmap = NULL;
 	free->rmap = NULL;
 }
 
@@ -499,6 +557,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_flush_shadow(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
+	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
+	kvm_arch_free_vm(kvm);
 	hardware_disable_all();
 	mmdrop(mm);
 }
@@ -528,6 +589,27 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 }
 
 /*
+ * Allocation size is twice as large as the actual dirty bitmap size.
+ * This makes it possible to do double buffering: see x86's
+ * kvm_vm_ioctl_get_dirty_log().
+ */
+static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
+
+	if (dirty_bytes > PAGE_SIZE)
+		memslot->dirty_bitmap = vzalloc(dirty_bytes);
+	else
+		memslot->dirty_bitmap = kzalloc(dirty_bytes, GFP_KERNEL);
+
+	if (!memslot->dirty_bitmap)
+		return -ENOMEM;
+
+	memslot->dirty_bitmap_head = memslot->dirty_bitmap;
+	return 0;
+}
+
+/*
  * Allocate some memory and give it an address in the guest physical address
  * space.
  *
@@ -604,13 +686,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Allocate if a slot is being created */
 #ifndef CONFIG_S390
 	if (npages && !new.rmap) {
-		new.rmap = vmalloc(npages * sizeof(*new.rmap));
+		new.rmap = vzalloc(npages * sizeof(*new.rmap));
 
 		if (!new.rmap)
 			goto out_free;
 
-		memset(new.rmap, 0, npages * sizeof(*new.rmap));
-
 		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
 	}
@@ -633,14 +713,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			     >> KVM_HPAGE_GFN_SHIFT(level));
 		lpages -= base_gfn >> KVM_HPAGE_GFN_SHIFT(level);
 
-		new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i]));
+		new.lpage_info[i] = vzalloc(lpages * sizeof(*new.lpage_info[i]));
 
 		if (!new.lpage_info[i])
 			goto out_free;
 
-		memset(new.lpage_info[i], 0,
-		       lpages * sizeof(*new.lpage_info[i]));
-
 		if (base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
 			new.lpage_info[i][0].write_count = 1;
 		if ((base_gfn+npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
@@ -661,12 +738,8 @@ skip_lpage:
 
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
-		unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(&new);
-
-		new.dirty_bitmap = vmalloc(dirty_bytes);
-		if (!new.dirty_bitmap)
+		if (kvm_create_dirty_bitmap(&new) < 0)
 			goto out_free;
-		memset(new.dirty_bitmap, 0, dirty_bytes);
 		/* destroy any largepage mappings for dirty tracking */
 		if (old.npages)
 			flush_shadow = 1;
@@ -685,6 +758,7 @@ skip_lpage:
 		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 		if (mem->slot >= slots->nmemslots)
 			slots->nmemslots = mem->slot + 1;
+		slots->generation++;
 		slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID;
 
 		old_memslots = kvm->memslots;
@@ -719,6 +793,7 @@ skip_lpage:
 	memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 	if (mem->slot >= slots->nmemslots)
 		slots->nmemslots = mem->slot + 1;
+	slots->generation++;
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
 	if (!npages) {
@@ -849,10 +924,10 @@ int kvm_is_error_hva(unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots,
+						gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; ++i) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -863,6 +938,11 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 	}
 	return NULL;
 }
+
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
+}
 EXPORT_SYMBOL_GPL(gfn_to_memslot);
 
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
@@ -925,12 +1005,9 @@ int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return memslot - slots->memslots;
 }
 
-static unsigned long gfn_to_hva_many(struct kvm *kvm, gfn_t gfn,
+static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
 				     gfn_t *nr_pages)
 {
-	struct kvm_memory_slot *slot;
-
-	slot = gfn_to_memslot(kvm, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return bad_hva();
 
@@ -942,28 +1019,61 @@ static unsigned long gfn_to_hva_many(struct kvm *kvm, gfn_t gfn,
 
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
-	return gfn_to_hva_many(kvm, gfn, NULL);
+	return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic)
+static pfn_t get_fault_pfn(void)
+{
+	get_page(fault_page);
+	return fault_pfn;
+}
+
+static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
+			bool *async, bool write_fault, bool *writable)
 {
 	struct page *page[1];
-	int npages;
+	int npages = 0;
 	pfn_t pfn;
 
-	if (atomic)
+	/* we can do it either atomically or asynchronously, not both */
+	BUG_ON(atomic && async);
+
+	BUG_ON(!write_fault && !writable);
+
+	if (writable)
+		*writable = true;
+
+	if (atomic || async)
 		npages = __get_user_pages_fast(addr, 1, 1, page);
-	else {
+
+	if (unlikely(npages != 1) && !atomic) {
 		might_sleep();
-		npages = get_user_pages_fast(addr, 1, 1, page);
+
+		if (writable)
+			*writable = write_fault;
+
+		npages = get_user_pages_fast(addr, 1, write_fault, page);
+
+		/* map read fault as writable if possible */
+		if (unlikely(!write_fault) && npages == 1) {
+			struct page *wpage[1];
+
+			npages = __get_user_pages_fast(addr, 1, 1, wpage);
+			if (npages == 1) {
+				*writable = true;
+				put_page(page[0]);
+				page[0] = wpage[0];
+			}
+			npages = 1;
+		}
 	}
 
 	if (unlikely(npages != 1)) {
 		struct vm_area_struct *vma;
 
 		if (atomic)
-			goto return_fault_page;
+			return get_fault_pfn();
 
 		down_read(&current->mm->mmap_sem);
 		if (is_hwpoison_address(addr)) {
@@ -972,19 +1082,20 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic)
 			return page_to_pfn(hwpoison_page);
 		}
 
-		vma = find_vma(current->mm, addr);
-
-		if (vma == NULL || addr < vma->vm_start ||
-		    !(vma->vm_flags & VM_PFNMAP)) {
-			up_read(&current->mm->mmap_sem);
-return_fault_page:
-			get_page(fault_page);
-			return page_to_pfn(fault_page);
+		vma = find_vma_intersection(current->mm, addr, addr+1);
+
+		if (vma == NULL)
+			pfn = get_fault_pfn();
+		else if ((vma->vm_flags & VM_PFNMAP)) {
+			pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+				vma->vm_pgoff;
+			BUG_ON(!kvm_is_mmio_pfn(pfn));
+		} else {
+			if (async && (vma->vm_flags & VM_WRITE))
+				*async = true;
+			pfn = get_fault_pfn();
 		}
-
-		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 		up_read(&current->mm->mmap_sem);
-		BUG_ON(!kvm_is_mmio_pfn(pfn));
 	} else
 		pfn = page_to_pfn(page[0]);
 
@@ -993,40 +1104,58 @@ return_fault_page:
 
 pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr)
 {
-	return hva_to_pfn(kvm, addr, true);
+	return hva_to_pfn(kvm, addr, true, NULL, true, NULL);
 }
 EXPORT_SYMBOL_GPL(hva_to_pfn_atomic);
 
-static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic)
+static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async,
+			  bool write_fault, bool *writable)
 {
 	unsigned long addr;
 
+	if (async)
+		*async = false;
+
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr)) {
 		get_page(bad_page);
 		return page_to_pfn(bad_page);
 	}
 
-	return hva_to_pfn(kvm, addr, atomic);
+	return hva_to_pfn(kvm, addr, atomic, async, write_fault, writable);
 }
 
 pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
 {
-	return __gfn_to_pfn(kvm, gfn, true);
+	return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
 
+pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
+		       bool write_fault, bool *writable)
+{
+	return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_async);
+
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 {
-	return __gfn_to_pfn(kvm, gfn, false);
+	return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
+pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+		      bool *writable)
+{
+	return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
+
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	unsigned long addr = gfn_to_hva_memslot(slot, gfn);
-	return hva_to_pfn(kvm, addr, false);
+	return hva_to_pfn(kvm, addr, false, NULL, true, NULL);
 }
 
 int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
@@ -1035,7 +1164,7 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 	unsigned long addr;
 	gfn_t entry;
 
-	addr = gfn_to_hva_many(kvm, gfn, &entry);
+	addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry);
 	if (kvm_is_error_hva(addr))
 		return -1;
 
@@ -1219,9 +1348,51 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 	return 0;
 }
 
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			      gpa_t gpa)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	int offset = offset_in_page(gpa);
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+
+	ghc->gpa = gpa;
+	ghc->generation = slots->generation;
+	ghc->memslot = __gfn_to_memslot(slots, gfn);
+	ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
+	if (!kvm_is_error_hva(ghc->hva))
+		ghc->hva += offset;
+	else
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
+
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	int r;
+
+	if (slots->generation != ghc->generation)
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+
+	if (kvm_is_error_hva(ghc->hva))
+		return -EFAULT;
+
+	r = copy_to_user((void __user *)ghc->hva, data, len);
+	if (r)
+		return -EFAULT;
+	mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
+
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
 {
-	return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len);
+	return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
+				    offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
 
@@ -1244,11 +1415,9 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			     gfn_t gfn)
 {
-	struct kvm_memory_slot *memslot;
-
-	memslot = gfn_to_memslot(kvm, gfn);
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
@@ -1256,6 +1425,14 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	}
 }
 
+void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot;
+
+	memslot = gfn_to_memslot(kvm, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
+}
+
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
@@ -1457,6 +1634,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		if (arg)
 			goto out;
 		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
+		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	case KVM_GET_REGS: {
 		struct kvm_regs *kvm_regs;
@@ -1824,7 +2002,7 @@ static struct file_operations kvm_vm_fops = {
 
 static int kvm_dev_ioctl_create_vm(void)
 {
-	int fd, r;
+	int r;
 	struct kvm *kvm;
 
 	kvm = kvm_create_vm();
@@ -1837,11 +2015,11 @@ static int kvm_dev_ioctl_create_vm(void)
 		return r;
 	}
 #endif
-	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
-	if (fd < 0)
+	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	if (r < 0)
 		kvm_put_kvm(kvm);
 
-	return fd;
+	return r;
 }
 
 static long kvm_dev_ioctl_check_extension_generic(long arg)
@@ -1922,7 +2100,7 @@ static struct miscdevice kvm_dev = {
 	&kvm_chardev_ops,
 };
 
-static void hardware_enable(void *junk)
+static void hardware_enable_nolock(void *junk)
 {
 	int cpu = raw_smp_processor_id();
 	int r;
@@ -1942,7 +2120,14 @@ static void hardware_enable(void *junk)
 	}
 }
 
-static void hardware_disable(void *junk)
+static void hardware_enable(void *junk)
+{
+	spin_lock(&kvm_lock);
+	hardware_enable_nolock(junk);
+	spin_unlock(&kvm_lock);
+}
+
+static void hardware_disable_nolock(void *junk)
 {
 	int cpu = raw_smp_processor_id();
 
@@ -1952,13 +2137,20 @@ static void hardware_disable(void *junk)
 	kvm_arch_hardware_disable(NULL);
 }
 
+static void hardware_disable(void *junk)
+{
+	spin_lock(&kvm_lock);
+	hardware_disable_nolock(junk);
+	spin_unlock(&kvm_lock);
+}
+
 static void hardware_disable_all_nolock(void)
 {
 	BUG_ON(!kvm_usage_count);
 
 	kvm_usage_count--;
 	if (!kvm_usage_count)
-		on_each_cpu(hardware_disable, NULL, 1);
+		on_each_cpu(hardware_disable_nolock, NULL, 1);
 }
 
 static void hardware_disable_all(void)
@@ -1977,7 +2169,7 @@ static int hardware_enable_all(void)
 	kvm_usage_count++;
 	if (kvm_usage_count == 1) {
 		atomic_set(&hardware_enable_failed, 0);
-		on_each_cpu(hardware_enable, NULL, 1);
+		on_each_cpu(hardware_enable_nolock, NULL, 1);
 
 		if (atomic_read(&hardware_enable_failed)) {
 			hardware_disable_all_nolock();
@@ -2008,27 +2200,19 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	case CPU_STARTING:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
-		spin_lock(&kvm_lock);
 		hardware_enable(NULL);
-		spin_unlock(&kvm_lock);
 		break;
 	}
 	return NOTIFY_OK;
 }
 
 
-asmlinkage void kvm_handle_fault_on_reboot(void)
+asmlinkage void kvm_spurious_fault(void)
 {
-	if (kvm_rebooting) {
-		/* spin while reset goes on */
-		local_irq_enable();
-		while (true)
-			cpu_relax();
-	}
 	/* Fault while not rebooting.  We want the trace. */
 	BUG();
 }
-EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);
+EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
@@ -2041,7 +2225,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 	 */
 	printk(KERN_INFO "kvm: exiting hardware virtualization\n");
 	kvm_rebooting = true;
-	on_each_cpu(hardware_disable, NULL, 1);
+	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	return NOTIFY_OK;
 }
 
@@ -2211,7 +2395,7 @@ static void kvm_exit_debug(void)
 static int kvm_suspend(struct sys_device *dev, pm_message_t state)
 {
 	if (kvm_usage_count)
-		hardware_disable(NULL);
+		hardware_disable_nolock(NULL);
 	return 0;
 }
 
@@ -2219,7 +2403,7 @@ static int kvm_resume(struct sys_device *dev)
 {
 	if (kvm_usage_count) {
 		WARN_ON(spin_is_locked(&kvm_lock));
-		hardware_enable(NULL);
+		hardware_enable_nolock(NULL);
 	}
 	return 0;
 }
@@ -2336,6 +2520,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		goto out_free_5;
 	}
 
+	r = kvm_async_pf_init();
+	if (r)
+		goto out_free;
+
 	kvm_chardev_ops.owner = module;
 	kvm_vm_fops.owner = module;
 	kvm_vcpu_fops.owner = module;
@@ -2343,7 +2531,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	r = misc_register(&kvm_dev);
 	if (r) {
 		printk(KERN_ERR "kvm: misc device register failed\n");
-		goto out_free;
+		goto out_unreg;
 	}
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
@@ -2353,6 +2541,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	return 0;
 
+out_unreg:
+	kvm_async_pf_deinit();
 out_free:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_5:
@@ -2385,11 +2575,12 @@ void kvm_exit(void)
 	kvm_exit_debug();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
+	kvm_async_pf_deinit();
 	sysdev_unregister(&kvm_sysdev);
 	sysdev_class_unregister(&kvm_sysdev_class);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
-	on_each_cpu(hardware_disable, NULL, 1);
+	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
 	free_cpumask_var(cpus_hardware_enabled);