Merge branch 'linus' into tracing/core

Merge reason: Pick up kernel/softirq.c update for dependent fix.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 963 insertions, 471 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
new file mode 100644
index 00000000000..daece36c0a5
--- /dev/null
+++ b/virt/kvm/Kconfig
@@ -0,0 +1,14 @@
+# KVM common configuration items and defaults
+
+config HAVE_KVM
+       bool
+
+config HAVE_KVM_IRQCHIP
+       bool
+
+config HAVE_KVM_EVENTFD
+       bool
+       select EVENTFD
+
+config KVM_APIC_ARCHITECTURE
+       bool
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 5ae620d32fa..04d69cd7049 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -14,32 +14,28 @@
 
 #include "coalesced_mmio.h"
 
-static int coalesced_mmio_in_range(struct kvm_io_device *this,
-				   gpa_t addr, int len, int is_write)
+static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
+}
+
+static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
+				   gpa_t addr, int len)
 {
-	struct kvm_coalesced_mmio_dev *dev =
-				(struct kvm_coalesced_mmio_dev*)this->private;
 	struct kvm_coalesced_mmio_zone *zone;
-	int next;
+	struct kvm_coalesced_mmio_ring *ring;
+	unsigned avail;
 	int i;
 
-	if (!is_write)
-		return 0;
-
-	/* kvm->lock is taken by the caller and must be not released before
-         * dev.read/write
-         */
-
 	/* Are we able to batch it ? */
 
 	/* last is the first free entry
 	 * check if we don't meet the first used entry
 	 * there is always one unused entry in the buffer
 	 */
-
-	next = (dev->kvm->coalesced_mmio_ring->last + 1) %
-							KVM_COALESCED_MMIO_MAX;
-	if (next == dev->kvm->coalesced_mmio_ring->first) {
+	ring = dev->kvm->coalesced_mmio_ring;
+	avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX;
+	if (avail < KVM_MAX_VCPUS) {
 		/* full */
 		return 0;
 	}
@@ -60,14 +56,15 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 	return 0;
 }
 
-static void coalesced_mmio_write(struct kvm_io_device *this,
-				 gpa_t addr, int len, const void *val)
+static int coalesced_mmio_write(struct kvm_io_device *this,
+				gpa_t addr, int len, const void *val)
 {
-	struct kvm_coalesced_mmio_dev *dev =
-				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+	if (!coalesced_mmio_in_range(dev, addr, len))
+		return -EOPNOTSUPP;
 
-	/* kvm->lock must be taken by caller before call to in_range()*/
+	spin_lock(&dev->lock);
 
 	/* copy data in first free entry of the ring */
 
@@ -76,29 +73,40 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
 	smp_wmb();
 	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
+	spin_unlock(&dev->lock);
+	return 0;
 }
 
 static void coalesced_mmio_destructor(struct kvm_io_device *this)
 {
-	kfree(this);
+	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
+
+	kfree(dev);
 }
 
+static const struct kvm_io_device_ops coalesced_mmio_ops = {
+	.write      = coalesced_mmio_write,
+	.destructor = coalesced_mmio_destructor,
+};
+
 int kvm_coalesced_mmio_init(struct kvm *kvm)
 {
 	struct kvm_coalesced_mmio_dev *dev;
+	int ret;
 
 	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
-	dev->dev.write  = coalesced_mmio_write;
-	dev->dev.in_range  = coalesced_mmio_in_range;
-	dev->dev.destructor  = coalesced_mmio_destructor;
-	dev->dev.private  = dev;
+	spin_lock_init(&dev->lock);
+	kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
 	dev->kvm = kvm;
 	kvm->coalesced_mmio_dev = dev;
-	kvm_io_bus_register_dev(&kvm->mmio_bus, &dev->dev);
 
-	return 0;
+	ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &dev->dev);
+	if (ret < 0)
+		kfree(dev);
+
+	return ret;
 }
 
 int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
@@ -109,16 +117,16 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	down_write(&kvm->slots_lock);
 	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
-		mutex_unlock(&kvm->lock);
+		up_write(&kvm->slots_lock);
 		return -ENOBUFS;
 	}
 
 	dev->zone[dev->nb_zones] = *zone;
 	dev->nb_zones++;
 
-	mutex_unlock(&kvm->lock);
+	up_write(&kvm->slots_lock);
 	return 0;
 }
 
@@ -132,7 +140,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	down_write(&kvm->slots_lock);
 
 	i = dev->nb_zones;
 	while(i) {
@@ -150,7 +158,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 		i--;
 	}
 
-	mutex_unlock(&kvm->lock);
+	up_write(&kvm->slots_lock);
 
 	return 0;
 }
diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h
index 5ac0ec62846..4b49f27fa31 100644
--- a/virt/kvm/coalesced_mmio.h
+++ b/virt/kvm/coalesced_mmio.h
@@ -12,6 +12,7 @@
 struct kvm_coalesced_mmio_dev {
 	struct kvm_io_device dev;
 	struct kvm *kvm;
+	spinlock_t lock;
 	int nb_zones;
 	struct kvm_coalesced_mmio_zone zone[KVM_COALESCED_MMIO_ZONE_MAX];
 };
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
new file mode 100644
index 00000000000..bb4ebd89b9f
--- /dev/null
+++ b/virt/kvm/eventfd.c
@@ -0,0 +1,578 @@
+/*
+ * kvm eventfd support - use eventfd objects to signal various KVM events
+ *
+ * Copyright 2009 Novell.  All Rights Reserved.
+ *
+ * Author:
+ *	Gregory Haskins <ghaskins@novell.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/kvm.h>
+#include <linux/workqueue.h>
+#include <linux/syscalls.h>
+#include <linux/wait.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/list.h>
+#include <linux/eventfd.h>
+#include <linux/kernel.h>
+
+#include "iodev.h"
+
+/*
+ * --------------------------------------------------------------------
+ * irqfd: Allows an fd to be used to inject an interrupt to the guest
+ *
+ * Credit goes to Avi Kivity for the original idea.
+ * --------------------------------------------------------------------
+ */
+
+struct _irqfd {
+	struct kvm               *kvm;
+	struct eventfd_ctx       *eventfd;
+	int                       gsi;
+	struct list_head          list;
+	poll_table                pt;
+	wait_queue_head_t        *wqh;
+	wait_queue_t              wait;
+	struct work_struct        inject;
+	struct work_struct        shutdown;
+};
+
+static struct workqueue_struct *irqfd_cleanup_wq;
+
+static void
+irqfd_inject(struct work_struct *work)
+{
+	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
+	struct kvm *kvm = irqfd->kvm;
+
+	mutex_lock(&kvm->irq_lock);
+	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
+	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+	mutex_unlock(&kvm->irq_lock);
+}
+
+/*
+ * Race-free decouple logic (ordering is critical)
+ */
+static void
+irqfd_shutdown(struct work_struct *work)
+{
+	struct _irqfd *irqfd = container_of(work, struct _irqfd, shutdown);
+
+	/*
+	 * Synchronize with the wait-queue and unhook ourselves to prevent
+	 * further events.
+	 */
+	remove_wait_queue(irqfd->wqh, &irqfd->wait);
+
+	/*
+	 * We know no new events will be scheduled at this point, so block
+	 * until all previously outstanding events have completed
+	 */
+	flush_work(&irqfd->inject);
+
+	/*
+	 * It is now safe to release the object's resources
+	 */
+	eventfd_ctx_put(irqfd->eventfd);
+	kfree(irqfd);
+}
+
+
+/* assumes kvm->irqfds.lock is held */
+static bool
+irqfd_is_active(struct _irqfd *irqfd)
+{
+	return list_empty(&irqfd->list) ? false : true;
+}
+
+/*
+ * Mark the irqfd as inactive and schedule it for removal
+ *
+ * assumes kvm->irqfds.lock is held
+ */
+static void
+irqfd_deactivate(struct _irqfd *irqfd)
+{
+	BUG_ON(!irqfd_is_active(irqfd));
+
+	list_del_init(&irqfd->list);
+
+	queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
+}
+
+/*
+ * Called with wqh->lock held and interrupts disabled
+ */
+static int
+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;
+
+	if (flags & POLLIN)
+		/* An event has been signaled, inject an interrupt */
+		schedule_work(&irqfd->inject);
+
+	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);
+
+		/*
+		 * We must check if someone deactivated the irqfd before
+		 * we could acquire the irqfds.lock since the item is
+		 * deactivated from the KVM side before it is unhooked from
+		 * the wait-queue.  If it is already deactivated, we can
+		 * simply return knowing the other side will cleanup for us.
+		 * We cannot race against the irqfd going away since the
+		 * other side is required to acquire wqh->lock, which we hold
+		 */
+		if (irqfd_is_active(irqfd))
+			irqfd_deactivate(irqfd);
+
+		spin_unlock_irqrestore(&kvm->irqfds.lock, flags);
+	}
+
+	return 0;
+}
+
+static void
+irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
+			poll_table *pt)
+{
+	struct _irqfd *irqfd = container_of(pt, struct _irqfd, pt);
+
+	irqfd->wqh = wqh;
+	add_wait_queue(wqh, &irqfd->wait);
+}
+
+static int
+kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
+{
+	struct _irqfd *irqfd;
+	struct file *file = NULL;
+	struct eventfd_ctx *eventfd = NULL;
+	int ret;
+	unsigned int events;
+
+	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
+	if (!irqfd)
+		return -ENOMEM;
+
+	irqfd->kvm = kvm;
+	irqfd->gsi = gsi;
+	INIT_LIST_HEAD(&irqfd->list);
+	INIT_WORK(&irqfd->inject, irqfd_inject);
+	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
+
+	file = eventfd_fget(fd);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto fail;
+	}
+
+	eventfd = eventfd_ctx_fileget(file);
+	if (IS_ERR(eventfd)) {
+		ret = PTR_ERR(eventfd);
+		goto fail;
+	}
+
+	irqfd->eventfd = eventfd;
+
+	/*
+	 * Install our own custom wake-up handling so we are notified via
+	 * a callback whenever someone signals the underlying eventfd
+	 */
+	init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
+	init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
+
+	events = file->f_op->poll(file, &irqfd->pt);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+	list_add_tail(&irqfd->list, &kvm->irqfds.items);
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+	/*
+	 * Check if there was an event already pending on the eventfd
+	 * before we registered, and trigger it as if we didn't miss it.
+	 */
+	if (events & POLLIN)
+		schedule_work(&irqfd->inject);
+
+	/*
+	 * do not drop the file until the irqfd is fully initialized, otherwise
+	 * we might race against the POLLHUP
+	 */
+	fput(file);
+
+	return 0;
+
+fail:
+	if (eventfd && !IS_ERR(eventfd))
+		eventfd_ctx_put(eventfd);
+
+	if (!IS_ERR(file))
+		fput(file);
+
+	kfree(irqfd);
+	return ret;
+}
+
+void
+kvm_eventfd_init(struct kvm *kvm)
+{
+	spin_lock_init(&kvm->irqfds.lock);
+	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->ioeventfds);
+}
+
+/*
+ * shutdown any irqfd's that match fd+gsi
+ */
+static int
+kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
+{
+	struct _irqfd *irqfd, *tmp;
+	struct eventfd_ctx *eventfd;
+
+	eventfd = eventfd_ctx_fdget(fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+
+	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
+		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi)
+			irqfd_deactivate(irqfd);
+	}
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+	eventfd_ctx_put(eventfd);
+
+	/*
+	 * Block until we know all outstanding shutdown jobs have completed
+	 * so that we guarantee there will not be any more interrupts on this
+	 * gsi once this deassign function returns.
+	 */
+	flush_workqueue(irqfd_cleanup_wq);
+
+	return 0;
+}
+
+int
+kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+{
+	if (flags & KVM_IRQFD_FLAG_DEASSIGN)
+		return kvm_irqfd_deassign(kvm, fd, gsi);
+
+	return kvm_irqfd_assign(kvm, fd, gsi);
+}
+
+/*
+ * This function is called as the kvm VM fd is being released. Shutdown all
+ * irqfds that still remain open
+ */
+void
+kvm_irqfd_release(struct kvm *kvm)
+{
+	struct _irqfd *irqfd, *tmp;
+
+	spin_lock_irq(&kvm->irqfds.lock);
+
+	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list)
+		irqfd_deactivate(irqfd);
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+	/*
+	 * Block until we know all outstanding shutdown jobs have completed
+	 * since we do not take a kvm* reference.
+	 */
+	flush_workqueue(irqfd_cleanup_wq);
+
+}
+
+/*
+ * 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.
+ */
+static int __init irqfd_module_init(void)
+{
+	irqfd_cleanup_wq = create_singlethread_workqueue("kvm-irqfd-cleanup");
+	if (!irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit irqfd_module_exit(void)
+{
+	destroy_workqueue(irqfd_cleanup_wq);
+}
+
+module_init(irqfd_module_init);
+module_exit(irqfd_module_exit);
+
+/*
+ * --------------------------------------------------------------------
+ * ioeventfd: translate a PIO/MMIO memory write to an eventfd signal.
+ *
+ * userspace can register a PIO/MMIO address with an eventfd for receiving
+ * notification when the memory has been touched.
+ * --------------------------------------------------------------------
+ */
+
+struct _ioeventfd {
+	struct list_head     list;
+	u64                  addr;
+	int                  length;
+	struct eventfd_ctx  *eventfd;
+	u64                  datamatch;
+	struct kvm_io_device dev;
+	bool                 wildcard;
+};
+
+static inline struct _ioeventfd *
+to_ioeventfd(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct _ioeventfd, dev);
+}
+
+static void
+ioeventfd_release(struct _ioeventfd *p)
+{
+	eventfd_ctx_put(p->eventfd);
+	list_del(&p->list);
+	kfree(p);
+}
+
+static bool
+ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
+{
+	u64 _val;
+
+	if (!(addr == p->addr && len == p->length))
+		/* address-range must be precise for a hit */
+		return false;
+
+	if (p->wildcard)
+		/* all else equal, wildcard is always a hit */
+		return true;
+
+	/* otherwise, we have to actually compare the data */
+
+	BUG_ON(!IS_ALIGNED((unsigned long)val, len));
+
+	switch (len) {
+	case 1:
+		_val = *(u8 *)val;
+		break;
+	case 2:
+		_val = *(u16 *)val;
+		break;
+	case 4:
+		_val = *(u32 *)val;
+		break;
+	case 8:
+		_val = *(u64 *)val;
+		break;
+	default:
+		return false;
+	}
+
+	return _val == p->datamatch ? true : false;
+}
+
+/* MMIO/PIO writes trigger an event if the addr/val match */
+static int
+ioeventfd_write(struct kvm_io_device *this, gpa_t addr, int len,
+		const void *val)
+{
+	struct _ioeventfd *p = to_ioeventfd(this);
+
+	if (!ioeventfd_in_range(p, addr, len, val))
+		return -EOPNOTSUPP;
+
+	eventfd_signal(p->eventfd, 1);
+	return 0;
+}
+
+/*
+ * This function is called as KVM is completely shutting down.  We do not
+ * need to worry about locking just nuke anything we have as quickly as possible
+ */
+static void
+ioeventfd_destructor(struct kvm_io_device *this)
+{
+	struct _ioeventfd *p = to_ioeventfd(this);
+
+	ioeventfd_release(p);
+}
+
+static const struct kvm_io_device_ops ioeventfd_ops = {
+	.write      = ioeventfd_write,
+	.destructor = ioeventfd_destructor,
+};
+
+/* assumes kvm->slots_lock held */
+static bool
+ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
+{
+	struct _ioeventfd *_p;
+
+	list_for_each_entry(_p, &kvm->ioeventfds, list)
+		if (_p->addr == p->addr && _p->length == p->length &&
+		    (_p->wildcard || p->wildcard ||
+		     _p->datamatch == p->datamatch))
+			return true;
+
+	return false;
+}
+
+static int
+kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
+	struct kvm_io_bus        *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus;
+	struct _ioeventfd        *p;
+	struct eventfd_ctx       *eventfd;
+	int                       ret;
+
+	/* must be natural-word sized */
+	switch (args->len) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* check for range overflow */
+	if (args->addr + args->len < args->addr)
+		return -EINVAL;
+
+	/* check for extra flags that we don't understand */
+	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
+		return -EINVAL;
+
+	eventfd = eventfd_ctx_fdget(args->fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	INIT_LIST_HEAD(&p->list);
+	p->addr    = args->addr;
+	p->length  = args->len;
+	p->eventfd = eventfd;
+
+	/* The datamatch feature is optional, otherwise this is a wildcard */
+	if (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH)
+		p->datamatch = args->datamatch;
+	else
+		p->wildcard = true;
+
+	down_write(&kvm->slots_lock);
+
+	/* Verify that there isnt a match already */
+	if (ioeventfd_check_collision(kvm, p)) {
+		ret = -EEXIST;
+		goto unlock_fail;
+	}
+
+	kvm_iodevice_init(&p->dev, &ioeventfd_ops);
+
+	ret = __kvm_io_bus_register_dev(bus, &p->dev);
+	if (ret < 0)
+		goto unlock_fail;
+
+	list_add_tail(&p->list, &kvm->ioeventfds);
+
+	up_write(&kvm->slots_lock);
+
+	return 0;
+
+unlock_fail:
+	up_write(&kvm->slots_lock);
+
+fail:
+	kfree(p);
+	eventfd_ctx_put(eventfd);
+
+	return ret;
+}
+
+static int
+kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
+	struct kvm_io_bus        *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus;
+	struct _ioeventfd        *p, *tmp;
+	struct eventfd_ctx       *eventfd;
+	int                       ret = -ENOENT;
+
+	eventfd = eventfd_ctx_fdget(args->fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	down_write(&kvm->slots_lock);
+
+	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
+		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
+
+		if (p->eventfd != eventfd  ||
+		    p->addr != args->addr  ||
+		    p->length != args->len ||
+		    p->wildcard != wildcard)
+			continue;
+
+		if (!p->wildcard && p->datamatch != args->datamatch)
+			continue;
+
+		__kvm_io_bus_unregister_dev(bus, &p->dev);
+		ioeventfd_release(p);
+		ret = 0;
+		break;
+	}
+
+	up_write(&kvm->slots_lock);
+
+	eventfd_ctx_put(eventfd);
+
+	return ret;
+}
+
+int
+kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	if (args->flags & KVM_IOEVENTFD_FLAG_DEASSIGN)
+		return kvm_deassign_ioeventfd(kvm, args);
+
+	return kvm_assign_ioeventfd(kvm, args);
+}
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 1150c6d5c7b..9fe140bb38e 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -36,6 +36,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
+#include <trace/events/kvm.h>
 
 #include "ioapic.h"
 #include "lapic.h"
@@ -103,6 +104,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
+	union kvm_ioapic_redirect_entry *e;
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -122,19 +124,20 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
-		mask_before = ioapic->redirtbl[index].fields.mask;
+		e = &ioapic->redirtbl[index];
+		mask_before = e->fields.mask;
 		if (ioapic->ioregsel & 1) {
-			ioapic->redirtbl[index].bits &= 0xffffffff;
-			ioapic->redirtbl[index].bits |= (u64) val << 32;
+			e->bits &= 0xffffffff;
+			e->bits |= (u64) val << 32;
 		} else {
-			ioapic->redirtbl[index].bits &= ~0xffffffffULL;
-			ioapic->redirtbl[index].bits |= (u32) val;
-			ioapic->redirtbl[index].fields.remote_irr = 0;
+			e->bits &= ~0xffffffffULL;
+			e->bits |= (u32) val;
+			e->fields.remote_irr = 0;
 		}
-		mask_after = ioapic->redirtbl[index].fields.mask;
+		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after);
-		if (ioapic->redirtbl[index].fields.trig_mode == IOAPIC_LEVEL_TRIG
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index);
 		break;
@@ -164,7 +167,9 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	/* Always delivery PIT interrupt to vcpu 0 */
 	if (irq == 0) {
 		irqe.dest_mode = 0; /* Physical mode. */
-		irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id;
+		/* need to read apic_id from apic regiest since
+		 * it can be rewritten */
+		irqe.dest_id = ioapic->kvm->bsp_vcpu->vcpu_id;
 	}
 #endif
 	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
@@ -188,7 +193,10 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 			if ((edge && old_irr != ioapic->irr) ||
 			    (!edge && !entry.fields.remote_irr))
 				ret = ioapic_service(ioapic, irq);
+			else
+				ret = 0; /* report coalesced interrupt */
 		}
+		trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	}
 	return ret;
 }
@@ -220,24 +228,29 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 			__kvm_ioapic_update_eoi(ioapic, i, trigger_mode);
 }
 
-static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
-			   int len, int is_write)
+static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	return container_of(dev, struct kvm_ioapic, dev);
+}
 
+static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
+{
 	return ((addr >= ioapic->base_address &&
 		 (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
 }
 
-static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
-			     void *val)
+static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
+			    void *val)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	struct kvm_ioapic *ioapic = to_ioapic(this);
 	u32 result;
+	if (!ioapic_in_range(ioapic, addr))
+		return -EOPNOTSUPP;
 
 	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
+	mutex_lock(&ioapic->kvm->irq_lock);
 	addr &= 0xff;
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
@@ -264,22 +277,28 @@ static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
 	}
+	mutex_unlock(&ioapic->kvm->irq_lock);
+	return 0;
 }
 
-static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
-			      const void *val)
+static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
+			     const void *val)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	struct kvm_ioapic *ioapic = to_ioapic(this);
 	u32 data;
+	if (!ioapic_in_range(ioapic, addr))
+		return -EOPNOTSUPP;
 
 	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
 		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
+
+	mutex_lock(&ioapic->kvm->irq_lock);
 	if (len == 4 || len == 8)
 		data = *(u32 *) val;
 	else {
 		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
-		return;
+		goto unlock;
 	}
 
 	addr &= 0xff;
@@ -300,6 +319,9 @@ static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		break;
 	}
+unlock:
+	mutex_unlock(&ioapic->kvm->irq_lock);
+	return 0;
 }
 
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
@@ -314,21 +336,27 @@ void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->id = 0;
 }
 
+static const struct kvm_io_device_ops ioapic_mmio_ops = {
+	.read     = ioapic_mmio_read,
+	.write    = ioapic_mmio_write,
+};
+
 int kvm_ioapic_init(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic;
+	int ret;
 
 	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
 	if (!ioapic)
 		return -ENOMEM;
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
-	ioapic->dev.read = ioapic_mmio_read;
-	ioapic->dev.write = ioapic_mmio_write;
-	ioapic->dev.in_range = ioapic_in_range;
-	ioapic->dev.private = ioapic;
+	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
 	ioapic->kvm = kvm;
-	kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
-	return 0;
+	ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &ioapic->dev);
+	if (ret < 0)
+		kfree(ioapic);
+
+	return ret;
 }
 
diff --git a/virt/kvm/iodev.h b/virt/kvm/iodev.h
index 55e8846ac3a..12fd3caffd2 100644
--- a/virt/kvm/iodev.h
+++ b/virt/kvm/iodev.h
@@ -17,49 +17,54 @@
 #define __KVM_IODEV_H__
 
 #include <linux/kvm_types.h>
+#include <asm/errno.h>
 
-struct kvm_io_device {
-	void (*read)(struct kvm_io_device *this,
+struct kvm_io_device;
+
+/**
+ * kvm_io_device_ops are called under kvm slots_lock.
+ * read and write handlers return 0 if the transaction has been handled,
+ * or non-zero to have it passed to the next device.
+ **/
+struct kvm_io_device_ops {
+	int (*read)(struct kvm_io_device *this,
+		    gpa_t addr,
+		    int len,
+		    void *val);
+	int (*write)(struct kvm_io_device *this,
 		     gpa_t addr,
 		     int len,
-		     void *val);
-	void (*write)(struct kvm_io_device *this,
-		      gpa_t addr,
-		      int len,
-		      const void *val);
-	int (*in_range)(struct kvm_io_device *this, gpa_t addr, int len,
-			int is_write);
+		     const void *val);
 	void (*destructor)(struct kvm_io_device *this);
+};
 
-	void             *private;
+
+struct kvm_io_device {
+	const struct kvm_io_device_ops *ops;
 };
 
-static inline void kvm_iodevice_read(struct kvm_io_device *dev,
-				     gpa_t addr,
-				     int len,
-				     void *val)
+static inline void kvm_iodevice_init(struct kvm_io_device *dev,
+				     const struct kvm_io_device_ops *ops)
 {
-	dev->read(dev, addr, len, val);
+	dev->ops = ops;
 }
 
-static inline void kvm_iodevice_write(struct kvm_io_device *dev,
-				      gpa_t addr,
-				      int len,
-				      const void *val)
+static inline int kvm_iodevice_read(struct kvm_io_device *dev,
+				    gpa_t addr, int l, void *v)
 {
-	dev->write(dev, addr, len, val);
+	return dev->ops->read ? dev->ops->read(dev, addr, l, v) : -EOPNOTSUPP;
 }
 
-static inline int kvm_iodevice_inrange(struct kvm_io_device *dev,
-				       gpa_t addr, int len, int is_write)
+static inline int kvm_iodevice_write(struct kvm_io_device *dev,
+				     gpa_t addr, int l, const void *v)
 {
-	return dev->in_range(dev, addr, len, is_write);
+	return dev->ops->write ? dev->ops->write(dev, addr, l, v) : -EOPNOTSUPP;
 }
 
 static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
 {
-	if (dev->destructor)
-		dev->destructor(dev);
+	if (dev->ops->destructor)
+		dev->ops->destructor(dev);
 }
 
 #endif /* __KVM_IODEV_H__ */
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index ddc17f0e2f3..001663ff401 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
 #ifdef CONFIG_IA64
@@ -62,14 +63,14 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_is_dm_lowest_prio(irq))
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
-		vcpu = kvm->vcpus[i];
-
-		if (!vcpu || !kvm_apic_present(vcpu))
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
 			continue;
 
 		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
@@ -99,6 +100,8 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 {
 	struct kvm_lapic_irq irq;
 
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
 	irq.dest_id = (e->msi.address_lo &
 			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
 	irq.vector = (e->msi.data &
@@ -113,7 +116,7 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
-/* This should be called with the kvm->lock mutex held
+/* This should be called with the kvm->irq_lock mutex held
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
  *  = 0   Interrupt was coalesced (previous irq is still pending)
@@ -125,6 +128,10 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 	unsigned long *irq_state, sig_level;
 	int ret = -1;
 
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	if (irq < KVM_IOAPIC_NUM_PINS) {
 		irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
 
@@ -134,7 +141,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 		else
 			clear_bit(irq_source_id, irq_state);
 		sig_level = !!(*irq_state);
-	} else /* Deal with MSI/MSI-X */
+	} else if (!level)
+		return ret;
+	else /* Deal with MSI/MSI-X */
 		sig_level = 1;
 
 	/* Not possible to detect if the guest uses the PIC or the
@@ -159,6 +168,8 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 	struct hlist_node *n;
 	unsigned gsi = pin;
 
+	trace_kvm_ack_irq(irqchip, pin);
+
 	list_for_each_entry(e, &kvm->irq_routing, link)
 		if (e->type == KVM_IRQ_ROUTING_IRQCHIP &&
 		    e->irqchip.irqchip == irqchip &&
@@ -175,19 +186,26 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
 }
 
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian)
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				    struct kvm_irq_ack_notifier *kian)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_del_init(&kian->link);
+	mutex_unlock(&kvm->irq_lock);
 }
 
-/* The caller must hold kvm->lock mutex */
 int kvm_request_irq_source_id(struct kvm *kvm)
 {
 	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id = find_first_zero_bit(bitmap,
+	int irq_source_id;
+
+	mutex_lock(&kvm->irq_lock);
+	irq_source_id = find_first_zero_bit(bitmap,
 				sizeof(kvm->arch.irq_sources_bitmap));
 
 	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
@@ -197,6 +215,7 @@ int kvm_request_irq_source_id(struct kvm *kvm)
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 	set_bit(irq_source_id, bitmap);
+	mutex_unlock(&kvm->irq_lock);
 
 	return irq_source_id;
 }
@@ -207,6 +226,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 
+	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
 	    irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
 		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
@@ -215,19 +235,24 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
 		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 				    struct kvm_irq_mask_notifier *kimn)
 {
+	mutex_lock(&kvm->irq_lock);
 	kimn->irq = irq;
 	hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_del(&kimn->link);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
@@ -235,6 +260,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
 	struct kvm_irq_mask_notifier *kimn;
 	struct hlist_node *n;
 
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
 		if (kimn->irq == irq)
 			kimn->func(kimn, mask);
@@ -250,7 +277,9 @@ static void __kvm_free_irq_routing(struct list_head *irq_routing)
 
 void kvm_free_irq_routing(struct kvm *kvm)
 {
+	mutex_lock(&kvm->irq_lock);
 	__kvm_free_irq_routing(&kvm->irq_routing);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
@@ -325,13 +354,13 @@ int kvm_set_irq_routing(struct kvm *kvm,
 		e = NULL;
 	}
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	list_splice(&kvm->irq_routing, &tmp);
 	INIT_LIST_HEAD(&kvm->irq_routing);
 	list_splice(&irq_list, &kvm->irq_routing);
 	INIT_LIST_HEAD(&irq_list);
 	list_splice(&tmp, &irq_list);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->irq_lock);
 
 	r = 0;
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2884baf1d5f..897bff3b7df 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -59,9 +59,18 @@
 #include "irq.h"
 #endif
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kvm.h>
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+/*
+ * Ordering of locks:
+ *
+ * 		kvm->slots_lock --> kvm->lock --> kvm->irq_lock
+ */
+
 DEFINE_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 
@@ -79,6 +88,8 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 
 static bool kvm_rebooting;
 
+static bool largepages_enabled = true;
+
 #ifdef KVM_CAP_DEVICE_ASSIGNMENT
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
 						      int assigned_dev_id)
@@ -120,17 +131,13 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev;
 	struct kvm *kvm;
-	int irq, i;
+	int i;
 
 	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
 				    interrupt_work);
 	kvm = assigned_dev->kvm;
 
-	/* This is taken to safely inject irq inside the guest. When
-	 * the interrupt injection (or the ioapic code) uses a
-	 * finer-grained lock, update this
-	 */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_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 =
@@ -143,23 +150,13 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 			kvm_set_irq(assigned_dev->kvm,
 				    assigned_dev->irq_source_id,
 				    guest_entries[i].vector, 1);
-			irq = assigned_dev->host_msix_entries[i].vector;
-			if (irq != 0)
-				enable_irq(irq);
-			assigned_dev->host_irq_disabled = false;
 		}
-	} else {
+	} else
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
 			    assigned_dev->guest_irq, 1);
-		if (assigned_dev->irq_requested_type &
-				KVM_DEV_IRQ_GUEST_MSI) {
-			enable_irq(assigned_dev->host_irq);
-			assigned_dev->host_irq_disabled = false;
-		}
-	}
 
 	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
-	mutex_unlock(&assigned_dev->kvm->lock);
+	mutex_unlock(&assigned_dev->kvm->irq_lock);
 }
 
 static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
@@ -179,8 +176,10 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 
 	schedule_work(&assigned_dev->interrupt_work);
 
-	disable_irq_nosync(irq);
-	assigned_dev->host_irq_disabled = true;
+	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);
@@ -215,7 +214,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 static void deassign_guest_irq(struct kvm *kvm,
 			       struct kvm_assigned_dev_kernel *assigned_dev)
 {
-	kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
 	assigned_dev->ack_notifier.gsi = -1;
 
 	if (assigned_dev->irq_source_id != -1)
@@ -417,6 +416,7 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif
@@ -427,6 +427,7 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif
@@ -693,11 +694,6 @@ out:
 }
 #endif
 
-static inline int valid_vcpu(int n)
-{
-	return likely(n >= 0 && n < KVM_MAX_VCPUS);
-}
-
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
@@ -745,12 +741,9 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	if (alloc_cpumask_var(&cpus, GFP_ATOMIC))
 		cpumask_clear(cpus);
 
-	me = get_cpu();
 	spin_lock(&kvm->requests_lock);
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		vcpu = kvm->vcpus[i];
-		if (!vcpu)
-			continue;
+	me = smp_processor_id();
+	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (test_and_set_bit(req, &vcpu->requests))
 			continue;
 		cpu = vcpu->cpu;
@@ -764,7 +757,6 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	else
 		called = false;
 	spin_unlock(&kvm->requests_lock);
-	put_cpu();
 	free_cpumask_var(cpus);
 	return called;
 }
@@ -986,7 +978,9 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock_init(&kvm->mmu_lock);
 	spin_lock_init(&kvm->requests_lock);
 	kvm_io_bus_init(&kvm->pio_bus);
+	kvm_eventfd_init(kvm);
 	mutex_init(&kvm->lock);
+	mutex_init(&kvm->irq_lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
 	init_rwsem(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
@@ -1006,19 +1000,25 @@ out:
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
+	int i;
+
 	if (!dont || free->rmap != dont->rmap)
 		vfree(free->rmap);
 
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		vfree(free->dirty_bitmap);
 
-	if (!dont || free->lpage_info != dont->lpage_info)
-		vfree(free->lpage_info);
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		if (!dont || free->lpage_info[i] != dont->lpage_info[i]) {
+			vfree(free->lpage_info[i]);
+			free->lpage_info[i] = NULL;
+		}
+	}
 
 	free->npages = 0;
 	free->dirty_bitmap = NULL;
 	free->rmap = NULL;
-	free->lpage_info = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -1071,6 +1071,8 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 {
 	struct kvm *kvm = filp->private_data;
 
+	kvm_irqfd_release(kvm);
+
 	kvm_put_kvm(kvm);
 	return 0;
 }
@@ -1089,8 +1091,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 {
 	int r;
 	gfn_t base_gfn;
-	unsigned long npages, ugfn;
-	unsigned long largepages, i;
+	unsigned long npages;
+	unsigned long i;
 	struct kvm_memory_slot *memslot;
 	struct kvm_memory_slot old, new;
 
@@ -1164,31 +1166,51 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		else
 			new.userspace_addr = 0;
 	}
-	if (npages && !new.lpage_info) {
-		largepages = 1 + (base_gfn + npages - 1) / KVM_PAGES_PER_HPAGE;
-		largepages -= base_gfn / KVM_PAGES_PER_HPAGE;
+	if (!npages)
+		goto skip_lpage;
 
-		new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		unsigned long ugfn;
+		unsigned long j;
+		int lpages;
+		int level = i + 2;
 
-		if (!new.lpage_info)
+		/* Avoid unused variable warning if no large pages */
+		(void)level;
+
+		if (new.lpage_info[i])
+			continue;
+
+		lpages = 1 + (base_gfn + npages - 1) /
+			     KVM_PAGES_PER_HPAGE(level);
+		lpages -= base_gfn / KVM_PAGES_PER_HPAGE(level);
+
+		new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i]));
+
+		if (!new.lpage_info[i])
 			goto out_free;
 
-		memset(new.lpage_info, 0, largepages * sizeof(*new.lpage_info));
+		memset(new.lpage_info[i], 0,
+		       lpages * sizeof(*new.lpage_info[i]));
 
-		if (base_gfn % KVM_PAGES_PER_HPAGE)
-			new.lpage_info[0].write_count = 1;
-		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
-			new.lpage_info[largepages-1].write_count = 1;
+		if (base_gfn % KVM_PAGES_PER_HPAGE(level))
+			new.lpage_info[i][0].write_count = 1;
+		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE(level))
+			new.lpage_info[i][lpages - 1].write_count = 1;
 		ugfn = new.userspace_addr >> PAGE_SHIFT;
 		/*
 		 * If the gfn and userspace address are not aligned wrt each
-		 * other, disable large page support for this slot
+		 * other, or if explicitly asked to, disable large page
+		 * support for this slot
 		 */
-		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1))
-			for (i = 0; i < largepages; ++i)
-				new.lpage_info[i].write_count = 1;
+		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
+		    !largepages_enabled)
+			for (j = 0; j < lpages; ++j)
+				new.lpage_info[i][j].write_count = 1;
 	}
 
+skip_lpage:
+
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
 		unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8;
@@ -1200,6 +1222,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if (old.npages)
 			kvm_arch_flush_shadow(kvm);
 	}
+#else  /* not defined CONFIG_S390 */
+	new.user_alloc = user_alloc;
+	if (user_alloc)
+		new.userspace_addr = mem->userspace_addr;
 #endif /* not defined CONFIG_S390 */
 
 	if (!npages)
@@ -1299,6 +1325,12 @@ out:
 	return r;
 }
 
+void kvm_disable_largepages(void)
+{
+	largepages_enabled = false;
+}
+EXPORT_SYMBOL_GPL(kvm_disable_largepages);
+
 int is_error_page(struct page *page)
 {
 	return page == bad_page;
@@ -1635,9 +1667,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if ((kvm_arch_interrupt_allowed(vcpu) &&
-					kvm_cpu_has_interrupt(vcpu)) ||
-				kvm_arch_vcpu_runnable(vcpu)) {
+		if (kvm_arch_vcpu_runnable(vcpu)) {
 			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			break;
 		}
@@ -1714,24 +1744,18 @@ static struct file_operations kvm_vcpu_fops = {
  */
 static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 {
-	int fd = anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, 0);
-	if (fd < 0)
-		kvm_put_kvm(vcpu->kvm);
-	return fd;
+	return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, 0);
 }
 
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
  */
-static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
+static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 {
 	int r;
-	struct kvm_vcpu *vcpu;
-
-	if (!valid_vcpu(n))
-		return -EINVAL;
+	struct kvm_vcpu *vcpu, *v;
 
-	vcpu = kvm_arch_vcpu_create(kvm, n);
+	vcpu = kvm_arch_vcpu_create(kvm, id);
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
 
@@ -1742,23 +1766,38 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 		return r;
 
 	mutex_lock(&kvm->lock);
-	if (kvm->vcpus[n]) {
-		r = -EEXIST;
+	if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) {
+		r = -EINVAL;
 		goto vcpu_destroy;
 	}
-	kvm->vcpus[n] = vcpu;
-	mutex_unlock(&kvm->lock);
+
+	kvm_for_each_vcpu(r, v, kvm)
+		if (v->vcpu_id == id) {
+			r = -EEXIST;
+			goto vcpu_destroy;
+		}
+
+	BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]);
 
 	/* Now it's all set up, let userspace reach it */
 	kvm_get_kvm(kvm);
 	r = create_vcpu_fd(vcpu);
-	if (r < 0)
-		goto unlink;
+	if (r < 0) {
+		kvm_put_kvm(kvm);
+		goto vcpu_destroy;
+	}
+
+	kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu;
+	smp_wmb();
+	atomic_inc(&kvm->online_vcpus);
+
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+	if (kvm->bsp_vcpu_id == id)
+		kvm->bsp_vcpu = vcpu;
+#endif
+	mutex_unlock(&kvm->lock);
 	return r;
 
-unlink:
-	mutex_lock(&kvm->lock);
-	kvm->vcpus[n] = NULL;
 vcpu_destroy:
 	mutex_unlock(&kvm->lock);
 	kvm_arch_vcpu_destroy(vcpu);
@@ -2199,6 +2238,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		vfree(entries);
 		break;
 	}
+#endif /* KVM_CAP_IRQ_ROUTING */
 #ifdef __KVM_HAVE_MSIX
 	case KVM_ASSIGN_SET_MSIX_NR: {
 		struct kvm_assigned_msix_nr entry_nr;
@@ -2221,7 +2261,35 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
-#endif /* KVM_CAP_IRQ_ROUTING */
+	case KVM_IRQFD: {
+		struct kvm_irqfd data;
+
+		r = -EFAULT;
+		if (copy_from_user(&data, argp, sizeof data))
+			goto out;
+		r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags);
+		break;
+	}
+	case KVM_IOEVENTFD: {
+		struct kvm_ioeventfd data;
+
+		r = -EFAULT;
+		if (copy_from_user(&data, argp, sizeof data))
+			goto out;
+		r = kvm_ioeventfd(kvm, &data);
+		break;
+	}
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+	case KVM_SET_BOOT_CPU_ID:
+		r = 0;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus) != 0)
+			r = -EBUSY;
+		else
+			kvm->bsp_vcpu_id = arg;
+		mutex_unlock(&kvm->lock);
+		break;
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -2288,6 +2356,9 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+	case KVM_CAP_SET_BOOT_CPU_ID:
+#endif
 		return 1;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQ_ROUTING:
@@ -2335,7 +2406,7 @@ static long kvm_dev_ioctl(struct file *filp,
 	case KVM_TRACE_ENABLE:
 	case KVM_TRACE_PAUSE:
 	case KVM_TRACE_DISABLE:
-		r = kvm_trace_ioctl(ioctl, arg);
+		r = -EOPNOTSUPP;
 		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
@@ -2449,26 +2520,71 @@ void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	}
 }
 
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
-					  gpa_t addr, int len, int is_write)
+/* kvm_io_bus_write - called under kvm->slots_lock */
+int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr,
+		     int len, const void *val)
 {
 	int i;
+	for (i = 0; i < bus->dev_count; i++)
+		if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
+			return 0;
+	return -EOPNOTSUPP;
+}
 
-	for (i = 0; i < bus->dev_count; i++) {
-		struct kvm_io_device *pos = bus->devs[i];
+/* kvm_io_bus_read - called under kvm->slots_lock */
+int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len, void *val)
+{
+	int i;
+	for (i = 0; i < bus->dev_count; i++)
+		if (!kvm_iodevice_read(bus->devs[i], addr, len, val))
+			return 0;
+	return -EOPNOTSUPP;
+}
 
-		if (pos->in_range(pos, addr, len, is_write))
-			return pos;
-	}
+int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus,
+			     struct kvm_io_device *dev)
+{
+	int ret;
 
-	return NULL;
+	down_write(&kvm->slots_lock);
+	ret = __kvm_io_bus_register_dev(bus, dev);
+	up_write(&kvm->slots_lock);
+
+	return ret;
 }
 
-void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev)
+/* An unlocked version. Caller must have write lock on slots_lock. */
+int __kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+			      struct kvm_io_device *dev)
 {
-	BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1));
+	if (bus->dev_count > NR_IOBUS_DEVS-1)
+		return -ENOSPC;
 
 	bus->devs[bus->dev_count++] = dev;
+
+	return 0;
+}
+
+void kvm_io_bus_unregister_dev(struct kvm *kvm,
+			       struct kvm_io_bus *bus,
+			       struct kvm_io_device *dev)
+{
+	down_write(&kvm->slots_lock);
+	__kvm_io_bus_unregister_dev(bus, dev);
+	up_write(&kvm->slots_lock);
+}
+
+/* An unlocked version. Caller must have write lock on slots_lock. */
+void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus,
+				 struct kvm_io_device *dev)
+{
+	int i;
+
+	for (i = 0; i < bus->dev_count; i++)
+		if (bus->devs[i] == dev) {
+			bus->devs[i] = bus->devs[--bus->dev_count];
+			break;
+		}
 }
 
 static struct notifier_block kvm_cpu_notifier = {
@@ -2501,11 +2617,9 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	*val = 0;
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (vcpu)
-				*val += *(u32 *)((void *)vcpu + offset);
-		}
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			*val += *(u32 *)((void *)vcpu + offset);
+
 	spin_unlock(&kvm_lock);
 	return 0;
 }
@@ -2679,15 +2793,15 @@ out_free_0:
 	__free_page(bad_page);
 out:
 	kvm_arch_exit();
-	kvm_exit_debug();
 out_fail:
+	kvm_exit_debug();
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	kvm_trace_cleanup();
+	tracepoint_synchronize_unregister();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	sysdev_unregister(&kvm_sysdev);
diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c
deleted file mode 100644
index f5987444644..00000000000
--- a/virt/kvm/kvm_trace.c
+++ /dev/null
@@ -1,285 +0,0 @@
-/*
- * kvm trace
- *
- * It is designed to allow debugging traces of kvm to be generated
- * on UP / SMP machines.  Each trace entry can be timestamped so that
- * it's possible to reconstruct a chronological record of trace events.
- * The implementation refers to blktrace kernel support.
- *
- * Copyright (c) 2008 Intel Corporation
- * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
- *
- * Authors: Feng(Eric) Liu, eric.e.liu@intel.com
- *
- * Date:    Feb 2008
- */
-
-#include <linux/module.h>
-#include <linux/relay.h>
-#include <linux/debugfs.h>
-#include <linux/ktime.h>
-
-#include <linux/kvm_host.h>
-
-#define KVM_TRACE_STATE_RUNNING 	(1 << 0)
-#define KVM_TRACE_STATE_PAUSE 		(1 << 1)
-#define KVM_TRACE_STATE_CLEARUP 	(1 << 2)
-
-struct kvm_trace {
-	int trace_state;
-	struct rchan *rchan;
-	struct dentry *lost_file;
-	atomic_t lost_records;
-};
-static struct kvm_trace *kvm_trace;
-
-struct kvm_trace_probe {
-	const char *name;
-	const char *format;
-	u32 timestamp_in;
-	marker_probe_func *probe_func;
-};
-
-static inline int calc_rec_size(int timestamp, int extra)
-{
-	int rec_size = KVM_TRC_HEAD_SIZE;
-
-	rec_size += extra;
-	return timestamp ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
-}
-
-static void kvm_add_trace(void *probe_private, void *call_data,
-			  const char *format, va_list *args)
-{
-	struct kvm_trace_probe *p = probe_private;
-	struct kvm_trace *kt = kvm_trace;
-	struct kvm_trace_rec rec;
-	struct kvm_vcpu *vcpu;
-	int    i, size;
-	u32    extra;
-
-	if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING))
-		return;
-
-	rec.rec_val	= TRACE_REC_EVENT_ID(va_arg(*args, u32));
-	vcpu		= va_arg(*args, struct kvm_vcpu *);
-	rec.pid		= current->tgid;
-	rec.vcpu_id	= vcpu->vcpu_id;
-
-	extra   	= va_arg(*args, u32);
-	WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX));
-	extra 		= min_t(u32, extra, KVM_TRC_EXTRA_MAX);
-
-	rec.rec_val |= TRACE_REC_TCS(p->timestamp_in)
-			| TRACE_REC_NUM_DATA_ARGS(extra);
-
-	if (p->timestamp_in) {
-		rec.u.timestamp.timestamp = ktime_to_ns(ktime_get());
-
-		for (i = 0; i < extra; i++)
-			rec.u.timestamp.extra_u32[i] = va_arg(*args, u32);
-	} else {
-		for (i = 0; i < extra; i++)
-			rec.u.notimestamp.extra_u32[i] = va_arg(*args, u32);
-	}
-
-	size = calc_rec_size(p->timestamp_in, extra * sizeof(u32));
-	relay_write(kt->rchan, &rec, size);
-}
-
-static struct kvm_trace_probe kvm_trace_probes[] = {
-	{ "kvm_trace_entryexit", "%u %p %u %u %u %u %u %u", 1, kvm_add_trace },
-	{ "kvm_trace_handler", "%u %p %u %u %u %u %u %u", 0, kvm_add_trace },
-};
-
-static int lost_records_get(void *data, u64 *val)
-{
-	struct kvm_trace *kt = data;
-
-	*val = atomic_read(&kt->lost_records);
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(kvm_trace_lost_ops, lost_records_get, NULL, "%llu\n");
-
-/*
- *  The relay channel is used in "no-overwrite" mode, it keeps trace of how
- *  many times we encountered a full subbuffer, to tell user space app the
- *  lost records there were.
- */
-static int kvm_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
-{
-	struct kvm_trace *kt;
-
-	if (!relay_buf_full(buf)) {
-		if (!prev_subbuf) {
-			/*
-			 * executed only once when the channel is opened
-			 * save metadata as first record
-			 */
-			subbuf_start_reserve(buf, sizeof(u32));
-			*(u32 *)subbuf = 0x12345678;
-		}
-
-		return 1;
-	}
-
-	kt = buf->chan->private_data;
-	atomic_inc(&kt->lost_records);
-
-	return 0;
-}
-
-static struct dentry *kvm_create_buf_file_callack(const char *filename,
-						 struct dentry *parent,
-						 int mode,
-						 struct rchan_buf *buf,
-						 int *is_global)
-{
-	return debugfs_create_file(filename, mode, parent, buf,
-				   &relay_file_operations);
-}
-
-static int kvm_remove_buf_file_callback(struct dentry *dentry)
-{
-	debugfs_remove(dentry);
-	return 0;
-}
-
-static struct rchan_callbacks kvm_relay_callbacks = {
-	.subbuf_start 		= kvm_subbuf_start_callback,
-	.create_buf_file 	= kvm_create_buf_file_callack,
-	.remove_buf_file 	= kvm_remove_buf_file_callback,
-};
-
-static int do_kvm_trace_enable(struct kvm_user_trace_setup *kuts)
-{
-	struct kvm_trace *kt;
-	int i, r = -ENOMEM;
-
-	if (!kuts->buf_size || !kuts->buf_nr)
-		return -EINVAL;
-
-	kt = kzalloc(sizeof(*kt), GFP_KERNEL);
-	if (!kt)
-		goto err;
-
-	r = -EIO;
-	atomic_set(&kt->lost_records, 0);
-	kt->lost_file = debugfs_create_file("lost_records", 0444, kvm_debugfs_dir,
-					    kt, &kvm_trace_lost_ops);
-	if (!kt->lost_file)
-		goto err;
-
-	kt->rchan = relay_open("trace", kvm_debugfs_dir, kuts->buf_size,
-				kuts->buf_nr, &kvm_relay_callbacks, kt);
-	if (!kt->rchan)
-		goto err;
-
-	kvm_trace = kt;
-
-	for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
-		struct kvm_trace_probe *p = &kvm_trace_probes[i];
-
-		r = marker_probe_register(p->name, p->format, p->probe_func, p);
-		if (r)
-			printk(KERN_INFO "Unable to register probe %s\n",
-			       p->name);
-	}
-
-	kvm_trace->trace_state = KVM_TRACE_STATE_RUNNING;
-
-	return 0;
-err:
-	if (kt) {
-		if (kt->lost_file)
-			debugfs_remove(kt->lost_file);
-		if (kt->rchan)
-			relay_close(kt->rchan);
-		kfree(kt);
-	}
-	return r;
-}
-
-static int kvm_trace_enable(char __user *arg)
-{
-	struct kvm_user_trace_setup kuts;
-	int ret;
-
-	ret = copy_from_user(&kuts, arg, sizeof(kuts));
-	if (ret)
-		return -EFAULT;
-
-	ret = do_kvm_trace_enable(&kuts);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int kvm_trace_pause(void)
-{
-	struct kvm_trace *kt = kvm_trace;
-	int r = -EINVAL;
-
-	if (kt == NULL)
-		return r;
-
-	if (kt->trace_state == KVM_TRACE_STATE_RUNNING) {
-		kt->trace_state = KVM_TRACE_STATE_PAUSE;
-		relay_flush(kt->rchan);
-		r = 0;
-	}
-
-	return r;
-}
-
-void kvm_trace_cleanup(void)
-{
-	struct kvm_trace *kt = kvm_trace;
-	int i;
-
-	if (kt == NULL)
-		return;
-
-	if (kt->trace_state == KVM_TRACE_STATE_RUNNING ||
-	    kt->trace_state == KVM_TRACE_STATE_PAUSE) {
-
-		kt->trace_state = KVM_TRACE_STATE_CLEARUP;
-
-		for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
-			struct kvm_trace_probe *p = &kvm_trace_probes[i];
-			marker_probe_unregister(p->name, p->probe_func, p);
-		}
-		marker_synchronize_unregister();
-
-		relay_close(kt->rchan);
-		debugfs_remove(kt->lost_file);
-		kfree(kt);
-	}
-}
-
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	long r = -EINVAL;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (ioctl) {
-	case KVM_TRACE_ENABLE:
-		r = kvm_trace_enable(argp);
-		break;
-	case KVM_TRACE_PAUSE:
-		r = kvm_trace_pause();
-		break;
-	case KVM_TRACE_DISABLE:
-		r = 0;
-		kvm_trace_cleanup();
-		break;
-	}
-
-	return r;
-}