Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost updates from Michael Tsirkin:

 - new vsock device support in host and guest

 - platform IOMMU support in host and guest, including compatibility
   quirks for legacy systems.

 - misc fixes and cleanups.

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  VSOCK: Use kvfree()
  vhost: split out vringh Kconfig
  vhost: detect 32 bit integer wrap around
  vhost: new device IOTLB API
  vhost: drop vringh dependency
  vhost: convert pre sorted vhost memory array to interval tree
  vhost: introduce vhost memory accessors
  VSOCK: Add Makefile and Kconfig
  VSOCK: Introduce vhost_vsock.ko
  VSOCK: Introduce virtio_transport.ko
  VSOCK: Introduce virtio_vsock_common.ko
  VSOCK: defer sock removal to transports
  VSOCK: transport-specific vsock_transport functions
  vhost: drop vringh dependency
  vop: pull in vhost Kconfig
  virtio: new feature to detect IOMMU device quirk
  balloon: check the number of available pages in leak balloon
  vhost: lockless enqueuing
  vhost: simplify work flushing

7 files changed, 1612 insertions, 192 deletions

diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index 533eaf04f12f..40764ecad9ce 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -2,7 +2,6 @@ config VHOST_NET
 	tristate "Host kernel accelerator for virtio net"
 	depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP)
 	select VHOST
-	select VHOST_RING
 	---help---
 	  This kernel module can be loaded in host kernel to accelerate
 	  guest networking with virtio_net. Not to be confused with virtio_net
@@ -15,17 +14,24 @@ config VHOST_SCSI
 	tristate "VHOST_SCSI TCM fabric driver"
 	depends on TARGET_CORE && EVENTFD && m
 	select VHOST
-	select VHOST_RING
 	default n
 	---help---
 	Say M here to enable the vhost_scsi TCM fabric module
 	for use with virtio-scsi guests
 
-config VHOST_RING
-	tristate
+config VHOST_VSOCK
+	tristate "vhost virtio-vsock driver"
+	depends on VSOCKETS && EVENTFD
+	select VIRTIO_VSOCKETS_COMMON
+	select VHOST
+	default n
 	---help---
-	  This option is selected by any driver which needs to access
-	  the host side of a virtio ring.
+	This kernel module can be loaded in the host kernel to provide AF_VSOCK
+	sockets for communicating with guests.  The guests must have the
+	virtio_transport.ko driver loaded to use the virtio-vsock device.
+
+	To compile this driver as a module, choose M here: the module will be called
+	vhost_vsock.
 
 config VHOST
 	tristate
diff --git a/drivers/vhost/Kconfig.vringh b/drivers/vhost/Kconfig.vringh
new file mode 100644
index 000000000000..6a4490c09d7f
--- /dev/null
+++ b/drivers/vhost/Kconfig.vringh
@@ -0,0 +1,5 @@
+config VHOST_RING
+	tristate
+	---help---
+	  This option is selected by any driver which needs to access
+	  the host side of a virtio ring.
diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile
index e0441c34db1c..6b012b986b57 100644
--- a/drivers/vhost/Makefile
+++ b/drivers/vhost/Makefile
@@ -4,5 +4,9 @@ vhost_net-y := net.o
 obj-$(CONFIG_VHOST_SCSI) += vhost_scsi.o
 vhost_scsi-y := scsi.o
 
+obj-$(CONFIG_VHOST_VSOCK) += vhost_vsock.o
+vhost_vsock-y := vsock.o
+
 obj-$(CONFIG_VHOST_RING) += vringh.o
+
 obj-$(CONFIG_VHOST)	+= vhost.o
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e032ca397371..5dc128a8da83 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -61,7 +61,8 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
 enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1ULL << VIRTIO_NET_F_MRG_RXBUF)
+			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
 };
 
 enum {
@@ -334,7 +335,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 {
 	unsigned long uninitialized_var(endtime);
 	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
-				    out_num, in_num, NULL, NULL);
+				  out_num, in_num, NULL, NULL);
 
 	if (r == vq->num && vq->busyloop_timeout) {
 		preempt_disable();
@@ -344,7 +345,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 			cpu_relax_lowlatency();
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
-					out_num, in_num, NULL, NULL);
+				      out_num, in_num, NULL, NULL);
 	}
 
 	return r;
@@ -377,6 +378,9 @@ static void handle_tx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&net->dev, vq);
 
 	hdr_size = nvq->vhost_hlen;
@@ -652,6 +656,10 @@ static void handle_rx(struct vhost_net *net)
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
+
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&net->dev, vq);
 	vhost_net_disable_vq(net, vq);
 
@@ -1052,20 +1060,20 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	struct socket *tx_sock = NULL;
 	struct socket *rx_sock = NULL;
 	long err;
-	struct vhost_memory *memory;
+	struct vhost_umem *umem;
 
 	mutex_lock(&n->dev.mutex);
 	err = vhost_dev_check_owner(&n->dev);
 	if (err)
 		goto done;
-	memory = vhost_dev_reset_owner_prepare();
-	if (!memory) {
+	umem = vhost_dev_reset_owner_prepare();
+	if (!umem) {
 		err = -ENOMEM;
 		goto done;
 	}
 	vhost_net_stop(n, &tx_sock, &rx_sock);
 	vhost_net_flush(n);
-	vhost_dev_reset_owner(&n->dev, memory);
+	vhost_dev_reset_owner(&n->dev, umem);
 	vhost_net_vq_reset(n);
 done:
 	mutex_unlock(&n->dev.mutex);
@@ -1096,10 +1104,14 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	}
 	mutex_lock(&n->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
-	    !vhost_log_access_ok(&n->dev)) {
-		mutex_unlock(&n->dev.mutex);
-		return -EFAULT;
+	    !vhost_log_access_ok(&n->dev))
+		goto out_unlock;
+
+	if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
+		if (vhost_init_device_iotlb(&n->dev, true))
+			goto out_unlock;
 	}
+
 	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
 		mutex_lock(&n->vqs[i].vq.mutex);
 		n->vqs[i].vq.acked_features = features;
@@ -1109,6 +1121,10 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	}
 	mutex_unlock(&n->dev.mutex);
 	return 0;
+
+out_unlock:
+	mutex_unlock(&n->dev.mutex);
+	return -EFAULT;
 }
 
 static long vhost_net_set_owner(struct vhost_net *n)
@@ -1182,9 +1198,40 @@ static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
 }
 #endif
 
+static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+	int noblock = file->f_flags & O_NONBLOCK;
+
+	return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_net_chr_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static unsigned int vhost_net_chr_poll(struct file *file, poll_table *wait)
+{
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+
+	return vhost_chr_poll(file, dev, wait);
+}
+
 static const struct file_operations vhost_net_fops = {
 	.owner          = THIS_MODULE,
 	.release        = vhost_net_release,
+	.read_iter      = vhost_net_chr_read_iter,
+	.write_iter     = vhost_net_chr_write_iter,
+	.poll           = vhost_net_chr_poll,
 	.unlocked_ioctl = vhost_net_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = vhost_net_compat_ioctl,
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 669fef1e2bb6..c6f2d89c0e97 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -27,6 +27,7 @@
 #include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/sort.h>
+#include <linux/interval_tree_generic.h>
 
 #include "vhost.h"
 
@@ -34,6 +35,10 @@ static ushort max_mem_regions = 64;
 module_param(max_mem_regions, ushort, 0444);
 MODULE_PARM_DESC(max_mem_regions,
 	"Maximum number of memory regions in memory map. (default: 64)");
+static int max_iotlb_entries = 2048;
+module_param(max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+	"Maximum number of iotlb entries. (default: 2048)");
 
 enum {
 	VHOST_MEMORY_F_LOG = 0x1,
@@ -42,6 +47,10 @@ enum {
 #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
+INTERVAL_TREE_DEFINE(struct vhost_umem_node,
+		     rb, __u64, __subtree_last,
+		     START, LAST, , vhost_umem_interval_tree);
+
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
 static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
@@ -131,6 +140,19 @@ static void vhost_reset_is_le(struct vhost_virtqueue *vq)
 	vq->is_le = virtio_legacy_is_little_endian();
 }
 
+struct vhost_flush_struct {
+	struct vhost_work work;
+	struct completion wait_event;
+};
+
+static void vhost_flush_work(struct vhost_work *work)
+{
+	struct vhost_flush_struct *s;
+
+	s = container_of(work, struct vhost_flush_struct, work);
+	complete(&s->wait_event);
+}
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -155,11 +177,9 @@ static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
 
 void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
 {
-	INIT_LIST_HEAD(&work->node);
+	clear_bit(VHOST_WORK_QUEUED, &work->flags);
 	work->fn = fn;
 	init_waitqueue_head(&work->done);
-	work->flushing = 0;
-	work->queue_seq = work->done_seq = 0;
 }
 EXPORT_SYMBOL_GPL(vhost_work_init);
 
@@ -211,31 +231,17 @@ void vhost_poll_stop(struct vhost_poll *poll)
 }
 EXPORT_SYMBOL_GPL(vhost_poll_stop);
 
-static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work,
-				unsigned seq)
-{
-	int left;
-
-	spin_lock_irq(&dev->work_lock);
-	left = seq - work->done_seq;
-	spin_unlock_irq(&dev->work_lock);
-	return left <= 0;
-}
-
 void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
 {
-	unsigned seq;
-	int flushing;
+	struct vhost_flush_struct flush;
 
-	spin_lock_irq(&dev->work_lock);
-	seq = work->queue_seq;
-	work->flushing++;
-	spin_unlock_irq(&dev->work_lock);
-	wait_event(work->done, vhost_work_seq_done(dev, work, seq));
-	spin_lock_irq(&dev->work_lock);
-	flushing = --work->flushing;
-	spin_unlock_irq(&dev->work_lock);
-	BUG_ON(flushing < 0);
+	if (dev->worker) {
+		init_completion(&flush.wait_event);
+		vhost_work_init(&flush.work, vhost_flush_work);
+
+		vhost_work_queue(dev, &flush.work);
+		wait_for_completion(&flush.wait_event);
+	}
 }
 EXPORT_SYMBOL_GPL(vhost_work_flush);
 
@@ -249,16 +255,16 @@ EXPORT_SYMBOL_GPL(vhost_poll_flush);
 
 void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
 {
-	unsigned long flags;
+	if (!dev->worker)
+		return;
 
-	spin_lock_irqsave(&dev->work_lock, flags);
-	if (list_empty(&work->node)) {
-		list_add_tail(&work->node, &dev->work_list);
-		work->queue_seq++;
-		spin_unlock_irqrestore(&dev->work_lock, flags);
+	if (!test_and_set_bit(VHOST_WORK_QUEUED, &work->flags)) {
+		/* We can only add the work to the list after we're
+		 * sure it was not in the list.
+		 */
+		smp_mb();
+		llist_add(&work->node, &dev->work_list);
 		wake_up_process(dev->worker);
-	} else {
-		spin_unlock_irqrestore(&dev->work_lock, flags);
 	}
 }
 EXPORT_SYMBOL_GPL(vhost_work_queue);
@@ -266,7 +272,7 @@ EXPORT_SYMBOL_GPL(vhost_work_queue);
 /* A lockless hint for busy polling code to exit the loop */
 bool vhost_has_work(struct vhost_dev *dev)
 {
-	return !list_empty(&dev->work_list);
+	return !llist_empty(&dev->work_list);
 }
 EXPORT_SYMBOL_GPL(vhost_has_work);
 
@@ -300,17 +306,18 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call_ctx = NULL;
 	vq->call = NULL;
 	vq->log_ctx = NULL;
-	vq->memory = NULL;
 	vhost_reset_is_le(vq);
 	vhost_disable_cross_endian(vq);
 	vq->busyloop_timeout = 0;
+	vq->umem = NULL;
+	vq->iotlb = NULL;
 }
 
 static int vhost_worker(void *data)
 {
 	struct vhost_dev *dev = data;
-	struct vhost_work *work = NULL;
-	unsigned uninitialized_var(seq);
+	struct vhost_work *work, *work_next;
+	struct llist_node *node;
 	mm_segment_t oldfs = get_fs();
 
 	set_fs(USER_DS);
@@ -320,35 +327,25 @@ static int vhost_worker(void *data)
 		/* mb paired w/ kthread_stop */
 		set_current_state(TASK_INTERRUPTIBLE);
 
-		spin_lock_irq(&dev->work_lock);
-		if (work) {
-			work->done_seq = seq;
-			if (work->flushing)
-				wake_up_all(&work->done);
-		}
-
 		if (kthread_should_stop()) {
-			spin_unlock_irq(&dev->work_lock);
 			__set_current_state(TASK_RUNNING);
 			break;
 		}
-		if (!list_empty(&dev->work_list)) {
-			work = list_first_entry(&dev->work_list,
-						struct vhost_work, node);
-			list_del_init(&work->node);
-			seq = work->queue_seq;
-		} else
-			work = NULL;
-		spin_unlock_irq(&dev->work_lock);
 
-		if (work) {
+		node = llist_del_all(&dev->work_list);
+		if (!node)
+			schedule();
+
+		node = llist_reverse_order(node);
+		/* make sure flag is seen after deletion */
+		smp_wmb();
+		llist_for_each_entry_safe(work, work_next, node, node) {
+			clear_bit(VHOST_WORK_QUEUED, &work->flags);
 			__set_current_state(TASK_RUNNING);
 			work->fn(work);
 			if (need_resched())
 				schedule();
-		} else
-			schedule();
-
+		}
 	}
 	unuse_mm(dev->mm);
 	set_fs(oldfs);
@@ -407,11 +404,16 @@ void vhost_dev_init(struct vhost_dev *dev,
 	mutex_init(&dev->mutex);
 	dev->log_ctx = NULL;
 	dev->log_file = NULL;
-	dev->memory = NULL;
+	dev->umem = NULL;
+	dev->iotlb = NULL;
 	dev->mm = NULL;
-	spin_lock_init(&dev->work_lock);
-	INIT_LIST_HEAD(&dev->work_list);
 	dev->worker = NULL;
+	init_llist_head(&dev->work_list);
+	init_waitqueue_head(&dev->wait);
+	INIT_LIST_HEAD(&dev->read_list);
+	INIT_LIST_HEAD(&dev->pending_list);
+	spin_lock_init(&dev->iotlb_lock);
+
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		vq = dev->vqs[i];
@@ -512,27 +514,36 @@ err_mm:
 }
 EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
 
-struct vhost_memory *vhost_dev_reset_owner_prepare(void)
+static void *vhost_kvzalloc(unsigned long size)
 {
-	return kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
+	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+
+	if (!n)
+		n = vzalloc(size);
+	return n;
+}
+
+struct vhost_umem *vhost_dev_reset_owner_prepare(void)
+{
+	return vhost_kvzalloc(sizeof(struct vhost_umem));
 }
 EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
 
 /* Caller should have device mutex */
-void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_memory *memory)
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem)
 {
 	int i;
 
 	vhost_dev_cleanup(dev, true);
 
 	/* Restore memory to default empty mapping. */
-	memory->nregions = 0;
-	dev->memory = memory;
+	INIT_LIST_HEAD(&umem->umem_list);
+	dev->umem = umem;
 	/* We don't need VQ locks below since vhost_dev_cleanup makes sure
 	 * VQs aren't running.
 	 */
 	for (i = 0; i < dev->nvqs; ++i)
-		dev->vqs[i]->memory = memory;
+		dev->vqs[i]->umem = umem;
 }
 EXPORT_SYMBOL_GPL(vhost_dev_reset_owner);
 
@@ -549,6 +560,47 @@ void vhost_dev_stop(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_stop);
 
+static void vhost_umem_free(struct vhost_umem *umem,
+			    struct vhost_umem_node *node)
+{
+	vhost_umem_interval_tree_remove(node, &umem->umem_tree);
+	list_del(&node->link);
+	kfree(node);
+	umem->numem--;
+}
+
+static void vhost_umem_clean(struct vhost_umem *umem)
+{
+	struct vhost_umem_node *node, *tmp;
+
+	if (!umem)
+		return;
+
+	list_for_each_entry_safe(node, tmp, &umem->umem_list, link)
+		vhost_umem_free(umem, node);
+
+	kvfree(umem);
+}
+
+static void vhost_clear_msg(struct vhost_dev *dev)
+{
+	struct vhost_msg_node *node, *n;
+
+	spin_lock(&dev->iotlb_lock);
+
+	list_for_each_entry_safe(node, n, &dev->read_list, node) {
+		list_del(&node->node);
+		kfree(node);
+	}
+
+	list_for_each_entry_safe(node, n, &dev->pending_list, node) {
+		list_del(&node->node);
+		kfree(node);
+	}
+
+	spin_unlock(&dev->iotlb_lock);
+}
+
 /* Caller should have device mutex if and only if locked is set */
 void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
 {
@@ -575,9 +627,13 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kvfree(dev->memory);
-	dev->memory = NULL;
-	WARN_ON(!list_empty(&dev->work_list));
+	vhost_umem_clean(dev->umem);
+	dev->umem = NULL;
+	vhost_umem_clean(dev->iotlb);
+	dev->iotlb = NULL;
+	vhost_clear_msg(dev);
+	wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM);
+	WARN_ON(!llist_empty(&dev->work_list));
 	if (dev->worker) {
 		kthread_stop(dev->worker);
 		dev->worker = NULL;
@@ -601,26 +657,34 @@ static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
 			 (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
 }
 
+static bool vhost_overflow(u64 uaddr, u64 size)
+{
+	/* Make sure 64 bit math will not overflow. */
+	return uaddr > ULONG_MAX || size > ULONG_MAX || uaddr > ULONG_MAX - size;
+}
+
 /* Caller should have vq mutex and device mutex. */
-static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem,
+static int vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
 			       int log_all)
 {
-	int i;
+	struct vhost_umem_node *node;
 
-	if (!mem)
+	if (!umem)
 		return 0;
 
-	for (i = 0; i < mem->nregions; ++i) {
-		struct vhost_memory_region *m = mem->regions + i;
-		unsigned long a = m->userspace_addr;
-		if (m->memory_size > ULONG_MAX)
+	list_for_each_entry(node, &umem->umem_list, link) {
+		unsigned long a = node->userspace_addr;
+
+		if (vhost_overflow(node->userspace_addr, node->size))
 			return 0;
-		else if (!access_ok(VERIFY_WRITE, (void __user *)a,
-				    m->memory_size))
+
+
+		if (!access_ok(VERIFY_WRITE, (void __user *)a,
+				    node->size))
 			return 0;
 		else if (log_all && !log_access_ok(log_base,
-						   m->guest_phys_addr,
-						   m->memory_size))
+						   node->start,
+						   node->size))
 			return 0;
 	}
 	return 1;
@@ -628,7 +692,7 @@ static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem,
 
 /* Can we switch to this memory table? */
 /* Caller should have device mutex but not vq mutex */
-static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
+static int memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
 			    int log_all)
 {
 	int i;
@@ -641,7 +705,8 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 		log = log_all || vhost_has_feature(d->vqs[i], VHOST_F_LOG_ALL);
 		/* If ring is inactive, will check when it's enabled. */
 		if (d->vqs[i]->private_data)
-			ok = vq_memory_access_ok(d->vqs[i]->log_base, mem, log);
+			ok = vq_memory_access_ok(d->vqs[i]->log_base,
+						 umem, log);
 		else
 			ok = 1;
 		mutex_unlock(&d->vqs[i]->mutex);
@@ -651,12 +716,385 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 	return 1;
 }
 
+static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
+			  struct iovec iov[], int iov_size, int access);
+
+static int vhost_copy_to_user(struct vhost_virtqueue *vq, void *to,
+			      const void *from, unsigned size)
+{
+	int ret;
+
+	if (!vq->iotlb)
+		return __copy_to_user(to, from, size);
+	else {
+		/* This function should be called after iotlb
+		 * prefetch, which means we're sure that all vq
+		 * could be access through iotlb. So -EAGAIN should
+		 * not happen in this case.
+		 */
+		/* TODO: more fast path */
+		struct iov_iter t;
+		ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov,
+				     ARRAY_SIZE(vq->iotlb_iov),
+				     VHOST_ACCESS_WO);
+		if (ret < 0)
+			goto out;
+		iov_iter_init(&t, WRITE, vq->iotlb_iov, ret, size);
+		ret = copy_to_iter(from, size, &t);
+		if (ret == size)
+			ret = 0;
+	}
+out:
+	return ret;
+}
+
+static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to,
+				void *from, unsigned size)
+{
+	int ret;
+
+	if (!vq->iotlb)
+		return __copy_from_user(to, from, size);
+	else {
+		/* This function should be called after iotlb
+		 * prefetch, which means we're sure that vq
+		 * could be access through iotlb. So -EAGAIN should
+		 * not happen in this case.
+		 */
+		/* TODO: more fast path */
+		struct iov_iter f;
+		ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov,
+				     ARRAY_SIZE(vq->iotlb_iov),
+				     VHOST_ACCESS_RO);
+		if (ret < 0) {
+			vq_err(vq, "IOTLB translation failure: uaddr "
+			       "%p size 0x%llx\n", from,
+			       (unsigned long long) size);
+			goto out;
+		}
+		iov_iter_init(&f, READ, vq->iotlb_iov, ret, size);
+		ret = copy_from_iter(to, size, &f);
+		if (ret == size)
+			ret = 0;
+	}
+
+out:
+	return ret;
+}
+
+static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
+				     void *addr, unsigned size)
+{
+	int ret;
+
+	/* This function should be called after iotlb
+	 * prefetch, which means we're sure that vq
+	 * could be access through iotlb. So -EAGAIN should
+	 * not happen in this case.
+	 */
+	/* TODO: more fast path */
+	ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov,
+			     ARRAY_SIZE(vq->iotlb_iov),
+			     VHOST_ACCESS_RO);
+	if (ret < 0) {
+		vq_err(vq, "IOTLB translation failure: uaddr "
+			"%p size 0x%llx\n", addr,
+			(unsigned long long) size);
+		return NULL;
+	}
+
+	if (ret != 1 || vq->iotlb_iov[0].iov_len != size) {
+		vq_err(vq, "Non atomic userspace memory access: uaddr "
+			"%p size 0x%llx\n", addr,
+			(unsigned long long) size);
+		return NULL;
+	}
+
+	return vq->iotlb_iov[0].iov_base;
+}
+
+#define vhost_put_user(vq, x, ptr) \
+({ \
+	int ret = -EFAULT; \
+	if (!vq->iotlb) { \
+		ret = __put_user(x, ptr); \
+	} else { \
+		__typeof__(ptr) to = \
+			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
+		if (to != NULL) \
+			ret = __put_user(x, to); \
+		else \
+			ret = -EFAULT;	\
+	} \
+	ret; \
+})
+
+#define vhost_get_user(vq, x, ptr) \
+({ \
+	int ret; \
+	if (!vq->iotlb) { \
+		ret = __get_user(x, ptr); \
+	} else { \
+		__typeof__(ptr) from = \
+			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
+		if (from != NULL) \
+			ret = __get_user(x, from); \
+		else \
+			ret = -EFAULT; \
+	} \
+	ret; \
+})
+
+static void vhost_dev_lock_vqs(struct vhost_dev *d)
+{
+	int i = 0;
+	for (i = 0; i < d->nvqs; ++i)
+		mutex_lock(&d->vqs[i]->mutex);
+}
+
+static void vhost_dev_unlock_vqs(struct vhost_dev *d)
+{
+	int i = 0;
+	for (i = 0; i < d->nvqs; ++i)
+		mutex_unlock(&d->vqs[i]->mutex);
+}
+
+static int vhost_new_umem_range(struct vhost_umem *umem,
+				u64 start, u64 size, u64 end,
+				u64 userspace_addr, int perm)
+{
+	struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+
+	if (!node)
+		return -ENOMEM;
+
+	if (umem->numem == max_iotlb_entries) {
+		tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link);
+		vhost_umem_free(umem, tmp);
+	}
+
+	node->start = start;
+	node->size = size;
+	node->last = end;
+	node->userspace_addr = userspace_addr;
+	node->perm = perm;
+	INIT_LIST_HEAD(&node->link);
+	list_add_tail(&node->link, &umem->umem_list);
+	vhost_umem_interval_tree_insert(node, &umem->umem_tree);
+	umem->numem++;
+
+	return 0;
+}
+
+static void vhost_del_umem_range(struct vhost_umem *umem,
+				 u64 start, u64 end)
+{
+	struct vhost_umem_node *node;
+
+	while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
+							   start, end)))
+		vhost_umem_free(umem, node);
+}
+
+static void vhost_iotlb_notify_vq(struct vhost_dev *d,
+				  struct vhost_iotlb_msg *msg)
+{
+	struct vhost_msg_node *node, *n;
+
+	spin_lock(&d->iotlb_lock);
+
+	list_for_each_entry_safe(node, n, &d->pending_list, node) {
+		struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb;
+		if (msg->iova <= vq_msg->iova &&
+		    msg->iova + msg->size - 1 > vq_msg->iova &&
+		    vq_msg->type == VHOST_IOTLB_MISS) {
+			vhost_poll_queue(&node->vq->poll);
+			list_del(&node->node);
+			kfree(node);
+		}
+	}
+
+	spin_unlock(&d->iotlb_lock);
+}
+
+static int umem_access_ok(u64 uaddr, u64 size, int access)
+{
+	unsigned long a = uaddr;
+
+	/* Make sure 64 bit math will not overflow. */
+	if (vhost_overflow(uaddr, size))
+		return -EFAULT;
+
+	if ((access & VHOST_ACCESS_RO) &&
+	    !access_ok(VERIFY_READ, (void __user *)a, size))
+		return -EFAULT;
+	if ((access & VHOST_ACCESS_WO) &&
+	    !access_ok(VERIFY_WRITE, (void __user *)a, size))
+		return -EFAULT;
+	return 0;
+}
+
+int vhost_process_iotlb_msg(struct vhost_dev *dev,
+			    struct vhost_iotlb_msg *msg)
+{
+	int ret = 0;
+
+	vhost_dev_lock_vqs(dev);
+	switch (msg->type) {
+	case VHOST_IOTLB_UPDATE:
+		if (!dev->iotlb) {
+			ret = -EFAULT;
+			break;
+		}
+		if (umem_access_ok(msg->uaddr, msg->size, msg->perm)) {
+			ret = -EFAULT;
+			break;
+		}
+		if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
+					 msg->iova + msg->size - 1,
+					 msg->uaddr, msg->perm)) {
+			ret = -ENOMEM;
+			break;
+		}
+		vhost_iotlb_notify_vq(dev, msg);
+		break;
+	case VHOST_IOTLB_INVALIDATE:
+		vhost_del_umem_range(dev->iotlb, msg->iova,
+				     msg->iova + msg->size - 1);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	vhost_dev_unlock_vqs(dev);
+	return ret;
+}
+ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
+			     struct iov_iter *from)
+{
+	struct vhost_msg_node node;
+	unsigned size = sizeof(struct vhost_msg);
+	size_t ret;
+	int err;
+
+	if (iov_iter_count(from) < size)
+		return 0;
+	ret = copy_from_iter(&node.msg, size, from);
+	if (ret != size)
+		goto done;
+
+	switch (node.msg.type) {
+	case VHOST_IOTLB_MSG:
+		err = vhost_process_iotlb_msg(dev, &node.msg.iotlb);
+		if (err)
+			ret = err;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+done:
+	return ret;
+}
+EXPORT_SYMBOL(vhost_chr_write_iter);
+
+unsigned int vhost_chr_poll(struct file *file, struct vhost_dev *dev,
+			    poll_table *wait)
+{
+	unsigned int mask = 0;
+
+	poll_wait(file, &dev->wait, wait);
+
+	if (!list_empty(&dev->read_list))
+		mask |= POLLIN | POLLRDNORM;
+
+	return mask;
+}
+EXPORT_SYMBOL(vhost_chr_poll);
+
+ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
+			    int noblock)
+{
+	DEFINE_WAIT(wait);
+	struct vhost_msg_node *node;
+	ssize_t ret = 0;
+	unsigned size = sizeof(struct vhost_msg);
+
+	if (iov_iter_count(to) < size)
+		return 0;
+
+	while (1) {
+		if (!noblock)
+			prepare_to_wait(&dev->wait, &wait,
+					TASK_INTERRUPTIBLE);
+
+		node = vhost_dequeue_msg(dev, &dev->read_list);
+		if (node)
+			break;
+		if (noblock) {
+			ret = -EAGAIN;
+			break;
+		}
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+		if (!dev->iotlb) {
+			ret = -EBADFD;
+			break;
+		}
+
+		schedule();
+	}
+
+	if (!noblock)
+		finish_wait(&dev->wait, &wait);
+
+	if (node) {
+		ret = copy_to_iter(&node->msg, size, to);
+
+		if (ret != size || node->msg.type != VHOST_IOTLB_MISS) {
+			kfree(node);
+			return ret;
+		}
+
+		vhost_enqueue_msg(dev, &dev->pending_list, node);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vhost_chr_read_iter);
+
+static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
+{
+	struct vhost_dev *dev = vq->dev;
+	struct vhost_msg_node *node;
+	struct vhost_iotlb_msg *msg;
+
+	node = vhost_new_msg(vq, VHOST_IOTLB_MISS);
+	if (!node)
+		return -ENOMEM;
+
+	msg = &node->msg.iotlb;
+	msg->type = VHOST_IOTLB_MISS;
+	msg->iova = iova;
+	msg->perm = access;
+
+	vhost_enqueue_msg(dev, &dev->read_list, node);
+
+	return 0;
+}
+
 static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			struct vring_desc __user *desc,
 			struct vring_avail __user *avail,
 			struct vring_used __user *used)
+
 {
 	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+
 	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
 	       access_ok(VERIFY_READ, avail,
 			 sizeof *avail + num * sizeof *avail->ring + s) &&
@@ -664,11 +1102,59 @@ static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			sizeof *used + num * sizeof *used->ring + s);
 }
 
+static int iotlb_access_ok(struct vhost_virtqueue *vq,
+			   int access, u64 addr, u64 len)
+{
+	const struct vhost_umem_node *node;
+	struct vhost_umem *umem = vq->iotlb;
+	u64 s = 0, size;
+
+	while (len > s) {
+		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
+							   addr,
+							   addr + len - 1);
+		if (node == NULL || node->start > addr) {
+			vhost_iotlb_miss(vq, addr, access);
+			return false;
+		} else if (!(node->perm & access)) {
+			/* Report the possible access violation by
+			 * request another translation from userspace.
+			 */
+			return false;
+		}
+
+		size = node->size - addr + node->start;
+		s += size;
+		addr += size;
+	}
+
+	return true;
+}
+
+int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
+{
+	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+	unsigned int num = vq->num;
+
+	if (!vq->iotlb)
+		return 1;
+
+	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
+			       num * sizeof *vq->desc) &&
+	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
+			       sizeof *vq->avail +
+			       num * sizeof *vq->avail->ring + s) &&
+	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
+			       sizeof *vq->used +
+			       num * sizeof *vq->used->ring + s);
+}
+EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);