1 files changed, 387 insertions, 226 deletions

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ade0568c07a..c90f4374442 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -4,7 +4,7 @@
  * Author: Michael S. Tsirkin <mst@redhat.com>
  *
  * Inspiration, some code, and most witty comments come from
- * Documentation/lguest/lguest.c, by Rusty Russell
+ * Documentation/virtual/lguest/lguest.c, by Rusty Russell
  *
  * This work is licensed under the terms of the GNU GPL, version 2.
  *
@@ -13,22 +13,18 @@
 
 #include <linux/eventfd.h>
 #include <linux/vhost.h>
-#include <linux/virtio_net.h>
+#include <linux/uio.h>
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
-#include <linux/rcupdate.h>
 #include <linux/poll.h>
 #include <linux/file.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/cgroup.h>
-
-#include <linux/net.h>
-#include <linux/if_packet.h>
-#include <linux/if_arp.h>
+#include <linux/module.h>
 
 #include "vhost.h"
 
@@ -37,12 +33,15 @@ enum {
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
+#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
 	struct vhost_poll *poll;
-	poll = container_of(pt, struct vhost_poll, table);
 
+	poll = container_of(pt, struct vhost_poll, table);
 	poll->wqh = wqh;
 	add_wait_queue(wqh, &poll->wait);
 }
@@ -59,7 +58,7 @@ static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
 	return 0;
 }
 
-static void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
+void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
 {
 	INIT_LIST_HEAD(&work->node);
 	work->fn = fn;
@@ -67,6 +66,7 @@ static void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
 	work->flushing = 0;
 	work->queue_seq = work->done_seq = 0;
 }
+EXPORT_SYMBOL_GPL(vhost_work_init);
 
 /* Init poll structure */
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
@@ -76,38 +76,58 @@ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 	init_poll_funcptr(&poll->table, vhost_poll_func);
 	poll->mask = mask;
 	poll->dev = dev;
+	poll->wqh = NULL;
 
 	vhost_work_init(&poll->work, fn);
 }
+EXPORT_SYMBOL_GPL(vhost_poll_init);
 
 /* Start polling a file. We add ourselves to file's wait queue. The caller must
  * keep a reference to a file until after vhost_poll_stop is called. */
-void vhost_poll_start(struct vhost_poll *poll, struct file *file)
+int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 {
 	unsigned long mask;
+	int ret = 0;
+
+	if (poll->wqh)
+		return 0;
+
 	mask = file->f_op->poll(file, &poll->table);
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
+	if (mask & POLLERR) {
+		if (poll->wqh)
+			remove_wait_queue(poll->wqh, &poll->wait);
+		ret = -EINVAL;
+	}
+
+	return ret;
 }
+EXPORT_SYMBOL_GPL(vhost_poll_start);
 
 /* Stop polling a file. After this function returns, it becomes safe to drop the
  * file reference. You must also flush afterwards. */
 void vhost_poll_stop(struct vhost_poll *poll)
 {
-	remove_wait_queue(poll->wqh, &poll->wait);
+	if (poll->wqh) {
+		remove_wait_queue(poll->wqh, &poll->wait);
+		poll->wqh = NULL;
+	}
 }
+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;
 }
 
-static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
+void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
 {
 	unsigned seq;
 	int flushing;
@@ -122,6 +142,7 @@ static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
 	spin_unlock_irq(&dev->work_lock);
 	BUG_ON(flushing < 0);
 }
+EXPORT_SYMBOL_GPL(vhost_work_flush);
 
 /* Flush any work that has been scheduled. When calling this, don't hold any
  * locks that are also used by the callback. */
@@ -129,9 +150,9 @@ void vhost_poll_flush(struct vhost_poll *poll)
 {
 	vhost_work_flush(poll->dev, &poll->work);
 }
+EXPORT_SYMBOL_GPL(vhost_poll_flush);
 
-static inline void vhost_work_queue(struct vhost_dev *dev,
-				    struct vhost_work *work)
+void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
 {
 	unsigned long flags;
 
@@ -139,15 +160,19 @@ static inline void vhost_work_queue(struct vhost_dev *dev,
 	if (list_empty(&work->node)) {
 		list_add_tail(&work->node, &dev->work_list);
 		work->queue_seq++;
+		spin_unlock_irqrestore(&dev->work_lock, flags);
 		wake_up_process(dev->worker);
+	} else {
+		spin_unlock_irqrestore(&dev->work_lock, flags);
 	}
-	spin_unlock_irqrestore(&dev->work_lock, flags);
 }
+EXPORT_SYMBOL_GPL(vhost_work_queue);
 
 void vhost_poll_queue(struct vhost_poll *poll)
 {
 	vhost_work_queue(poll->dev, &poll->work);
 }
+EXPORT_SYMBOL_GPL(vhost_poll_queue);
 
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
@@ -159,12 +184,13 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->last_avail_idx = 0;
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
+	vq->signalled_used = 0;
+	vq->signalled_used_valid = false;
 	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
-	vq->vhost_hlen = 0;
-	vq->sock_hlen = 0;
 	vq->private_data = NULL;
+	vq->acked_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->error = NULL;
@@ -172,6 +198,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call_ctx = NULL;
 	vq->call = NULL;
 	vq->log_ctx = NULL;
+	vq->memory = NULL;
 }
 
 static int vhost_worker(void *data)
@@ -179,7 +206,9 @@ static int vhost_worker(void *data)
 	struct vhost_dev *dev = data;
 	struct vhost_work *work = NULL;
 	unsigned uninitialized_var(seq);
+	mm_segment_t oldfs = get_fs();
 
+	set_fs(USER_DS);
 	use_mm(dev->mm);
 
 	for (;;) {
@@ -210,56 +239,62 @@ static int vhost_worker(void *data)
 		if (work) {
 			__set_current_state(TASK_RUNNING);
 			work->fn(work);
+			if (need_resched())
+				schedule();
 		} else
 			schedule();
 
 	}
 	unuse_mm(dev->mm);
+	set_fs(oldfs);
 	return 0;
 }
 
+static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
+{
+	kfree(vq->indirect);
+	vq->indirect = NULL;
+	kfree(vq->log);
+	vq->log = NULL;
+	kfree(vq->heads);
+	vq->heads = NULL;
+}
+
 /* Helper to allocate iovec buffers for all vqs. */
 static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 {
+	struct vhost_virtqueue *vq;
 	int i;
+
 	for (i = 0; i < dev->nvqs; ++i) {
-		dev->vqs[i].indirect = kmalloc(sizeof *dev->vqs[i].indirect *
-					       UIO_MAXIOV, GFP_KERNEL);
-		dev->vqs[i].log = kmalloc(sizeof *dev->vqs[i].log * UIO_MAXIOV,
-					  GFP_KERNEL);
-		dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
-					    UIO_MAXIOV, GFP_KERNEL);
-
-		if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
-			!dev->vqs[i].heads)
+		vq = dev->vqs[i];
+		vq->indirect = kmalloc(sizeof *vq->indirect * UIO_MAXIOV,
+				       GFP_KERNEL);
+		vq->log = kmalloc(sizeof *vq->log * UIO_MAXIOV, GFP_KERNEL);
+		vq->heads = kmalloc(sizeof *vq->heads * UIO_MAXIOV, GFP_KERNEL);
+		if (!vq->indirect || !vq->log || !vq->heads)
 			goto err_nomem;
 	}
 	return 0;
+
 err_nomem:
-	for (; i >= 0; --i) {
-		kfree(dev->vqs[i].indirect);
-		kfree(dev->vqs[i].log);
-		kfree(dev->vqs[i].heads);
-	}
+	for (; i >= 0; --i)
+		vhost_vq_free_iovecs(dev->vqs[i]);
 	return -ENOMEM;
 }
 
 static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 {
 	int i;
-	for (i = 0; i < dev->nvqs; ++i) {
-		kfree(dev->vqs[i].indirect);
-		dev->vqs[i].indirect = NULL;
-		kfree(dev->vqs[i].log);
-		dev->vqs[i].log = NULL;
-		kfree(dev->vqs[i].heads);
-		dev->vqs[i].heads = NULL;
-	}
+
+	for (i = 0; i < dev->nvqs; ++i)
+		vhost_vq_free_iovecs(dev->vqs[i]);
 }
 
-long vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue *vqs, int nvqs)
+void vhost_dev_init(struct vhost_dev *dev,
+		    struct vhost_virtqueue **vqs, int nvqs)
 {
+	struct vhost_virtqueue *vq;
 	int i;
 
 	dev->vqs = vqs;
@@ -274,19 +309,19 @@ long vhost_dev_init(struct vhost_dev *dev,
 	dev->worker = NULL;
 
 	for (i = 0; i < dev->nvqs; ++i) {
-		dev->vqs[i].log = NULL;
-		dev->vqs[i].indirect = NULL;
-		dev->vqs[i].heads = NULL;
-		dev->vqs[i].dev = dev;
-		mutex_init(&dev->vqs[i].mutex);
-		vhost_vq_reset(dev, dev->vqs + i);
-		if (dev->vqs[i].handle_kick)
-			vhost_poll_init(&dev->vqs[i].poll,
-					dev->vqs[i].handle_kick, POLLIN, dev);
+		vq = dev->vqs[i];
+		vq->log = NULL;
+		vq->indirect = NULL;
+		vq->heads = NULL;
+		vq->dev = dev;
+		mutex_init(&vq->mutex);
+		vhost_vq_reset(dev, vq);
+		if (vq->handle_kick)
+			vhost_poll_init(&vq->poll, vq->handle_kick,
+					POLLIN, dev);
 	}
-
-	return 0;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_init);
 
 /* Caller should have device mutex */
 long vhost_dev_check_owner(struct vhost_dev *dev)
@@ -294,40 +329,52 @@ long vhost_dev_check_owner(struct vhost_dev *dev)
 	/* Are you the owner? If not, I don't think you mean to do that */
 	return dev->mm == current->mm ? 0 : -EPERM;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_check_owner);
 
 struct vhost_attach_cgroups_struct {
-        struct vhost_work work;
-        struct task_struct *owner;
-        int ret;
+	struct vhost_work work;
+	struct task_struct *owner;
+	int ret;
 };
 
 static void vhost_attach_cgroups_work(struct vhost_work *work)
 {
-        struct vhost_attach_cgroups_struct *s;
-        s = container_of(work, struct vhost_attach_cgroups_struct, work);
-        s->ret = cgroup_attach_task_all(s->owner, current);
+	struct vhost_attach_cgroups_struct *s;
+
+	s = container_of(work, struct vhost_attach_cgroups_struct, work);
+	s->ret = cgroup_attach_task_all(s->owner, current);
 }
 
 static int vhost_attach_cgroups(struct vhost_dev *dev)
 {
-        struct vhost_attach_cgroups_struct attach;
-        attach.owner = current;
-        vhost_work_init(&attach.work, vhost_attach_cgroups_work);
-        vhost_work_queue(dev, &attach.work);
-        vhost_work_flush(dev, &attach.work);
-        return attach.ret;
+	struct vhost_attach_cgroups_struct attach;
+
+	attach.owner = current;
+	vhost_work_init(&attach.work, vhost_attach_cgroups_work);
+	vhost_work_queue(dev, &attach.work);
+	vhost_work_flush(dev, &attach.work);
+	return attach.ret;
+}
+
+/* Caller should have device mutex */
+bool vhost_dev_has_owner(struct vhost_dev *dev)
+{
+	return dev->mm;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_has_owner);
 
 /* Caller should have device mutex */
-static long vhost_dev_set_owner(struct vhost_dev *dev)
+long vhost_dev_set_owner(struct vhost_dev *dev)
 {
 	struct task_struct *worker;
 	int err;
+
 	/* Is there an owner already? */
-	if (dev->mm) {
+	if (vhost_dev_has_owner(dev)) {
 		err = -EBUSY;
 		goto err_mm;
 	}
+
 	/* No owner, become one */
 	dev->mm = get_task_mm(current);
 	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
@@ -358,44 +405,62 @@ err_worker:
 err_mm:
 	return err;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
 
-/* Caller should have device mutex */
-long vhost_dev_reset_owner(struct vhost_dev *dev)
+struct vhost_memory *vhost_dev_reset_owner_prepare(void)
 {
-	struct vhost_memory *memory;
+	return kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
 
-	/* Restore memory to default empty mapping. */
-	memory = kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
-	if (!memory)
-		return -ENOMEM;
+/* Caller should have device mutex */
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_memory *memory)
+{
+	int i;
 
-	vhost_dev_cleanup(dev);
+	vhost_dev_cleanup(dev, true);
 
+	/* Restore memory to default empty mapping. */
 	memory->nregions = 0;
-	RCU_INIT_POINTER(dev->memory, memory);
-	return 0;
+	dev->memory = memory;
+	/* 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;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_reset_owner);
 
-/* Caller should have device mutex */
-void vhost_dev_cleanup(struct vhost_dev *dev)
+void vhost_dev_stop(struct vhost_dev *dev)
 {
 	int i;
+
 	for (i = 0; i < dev->nvqs; ++i) {
-		if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
-			vhost_poll_stop(&dev->vqs[i].poll);
-			vhost_poll_flush(&dev->vqs[i].poll);
+		if (dev->vqs[i]->kick && dev->vqs[i]->handle_kick) {
+			vhost_poll_stop(&dev->vqs[i]->poll);
+			vhost_poll_flush(&dev->vqs[i]->poll);
 		}
-		if (dev->vqs[i].error_ctx)
-			eventfd_ctx_put(dev->vqs[i].error_ctx);
-		if (dev->vqs[i].error)
-			fput(dev->vqs[i].error);
-		if (dev->vqs[i].kick)
-			fput(dev->vqs[i].kick);
-		if (dev->vqs[i].call_ctx)
-			eventfd_ctx_put(dev->vqs[i].call_ctx);
-		if (dev->vqs[i].call)
-			fput(dev->vqs[i].call);
-		vhost_vq_reset(dev, dev->vqs + i);
+	}
+}
+EXPORT_SYMBOL_GPL(vhost_dev_stop);
+
+/* Caller should have device mutex if and only if locked is set */
+void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
+{
+	int i;
+
+	for (i = 0; i < dev->nvqs; ++i) {
+		if (dev->vqs[i]->error_ctx)
+			eventfd_ctx_put(dev->vqs[i]->error_ctx);
+		if (dev->vqs[i]->error)
+			fput(dev->vqs[i]->error);
+		if (dev->vqs[i]->kick)
+			fput(dev->vqs[i]->kick);
+		if (dev->vqs[i]->call_ctx)
+			eventfd_ctx_put(dev->vqs[i]->call_ctx);
+		if (dev->vqs[i]->call)
+			fput(dev->vqs[i]->call);
+		vhost_vq_reset(dev, dev->vqs[i]);
 	}
 	vhost_dev_free_iovecs(dev);
 	if (dev->log_ctx)
@@ -405,9 +470,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kfree(rcu_dereference_protected(dev->memory,
-					lockdep_is_held(&dev->mutex)));
-	RCU_INIT_POINTER(dev->memory, NULL);
+	kfree(dev->memory);
+	dev->memory = NULL;
 	WARN_ON(!list_empty(&dev->work_list));
 	if (dev->worker) {
 		kthread_stop(dev->worker);
@@ -417,10 +481,12 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 		mmput(dev->mm);
 	dev->mm = NULL;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
 
 static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
 {
 	u64 a = addr / VHOST_PAGE_SIZE / 8;
+
 	/* Make sure 64 bit math will not overflow. */
 	if (a > ULONG_MAX - (unsigned long)log_base ||
 	    a + (unsigned long)log_base > ULONG_MAX)
@@ -461,72 +527,75 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 			    int log_all)
 {
 	int i;
+
 	for (i = 0; i < d->nvqs; ++i) {
 		int ok;
-		mutex_lock(&d->vqs[i].mutex);
+		bool log;
+
+		mutex_lock(&d->vqs[i]->mutex);
+		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_all);
+		if (d->vqs[i]->private_data)
+			ok = vq_memory_access_ok(d->vqs[i]->log_base, mem, log);
 		else
 			ok = 1;
-		mutex_unlock(&d->vqs[i].mutex);
+		mutex_unlock(&d->vqs[i]->mutex);
 		if (!ok)
 			return 0;
 	}
 	return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+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) &&
+			 sizeof *avail + num * sizeof *avail->ring + s) &&
 	       access_ok(VERIFY_WRITE, used,
-			sizeof *used + num * sizeof *used->ring);
+			sizeof *used + num * sizeof *used->ring + s);
 }
 
 /* Can we log writes? */
 /* Caller should have device mutex but not vq mutex */
 int vhost_log_access_ok(struct vhost_dev *dev)
 {
-	struct vhost_memory *mp;
-
-	mp = rcu_dereference_protected(dev->memory,
-				       lockdep_is_held(&dev->mutex));
-	return memory_access_ok(dev, mp, 1);
+	return memory_access_ok(dev, dev->memory, 1);
 }
+EXPORT_SYMBOL_GPL(vhost_log_access_ok);
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
+static int vq_log_access_ok(struct vhost_virtqueue *vq,
+			    void __user *log_base)
 {
-	struct vhost_memory *mp;
+	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
-	mp = rcu_dereference_protected(vq->dev->memory,
-				       lockdep_is_held(&vq->mutex));
-	return vq_memory_access_ok(log_base, mp,
-			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
+	return vq_memory_access_ok(log_base, vq->memory,
+				   vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
-					vq->num * sizeof *vq->used->ring));
+					vq->num * sizeof *vq->used->ring + s));
 }
 
 /* Can we start vq? */
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
+	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
 		vq_log_access_ok(vq, vq->log_base);
 }
+EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
 	unsigned long size = offsetof(struct vhost_memory, regions);
+	int i;
+
 	if (copy_from_user(&mem, m, size))
 		return -EFAULT;
 	if (mem.padding)
@@ -544,31 +613,27 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EFAULT;
 	}
 
-	if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) {
+	if (!memory_access_ok(d, newmem, 0)) {
 		kfree(newmem);
 		return -EFAULT;
 	}
-	oldmem = rcu_dereference_protected(d->memory,
-					   lockdep_is_held(&d->mutex));
-	rcu_assign_pointer(d->memory, newmem);
-	synchronize_rcu();
+	oldmem = d->memory;
+	d->memory = newmem;
+
+	/* All memory accesses are done under some VQ mutex. */
+	for (i = 0; i < d->nvqs; ++i) {
+		mutex_lock(&d->vqs[i]->mutex);
+		d->vqs[i]->memory = newmem;
+		mutex_unlock(&d->vqs[i]->mutex);
+	}
 	kfree(oldmem);
 	return 0;
 }
 
-static int init_used(struct vhost_virtqueue *vq,
-		     struct vring_used __user *used)
-{
-	int r = put_user(vq->used_flags, &used->flags);
-	if (r)
-		return r;
-	return get_user(vq->last_used_idx, &used->idx);
-}
-
-static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
+long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 {
-	struct file *eventfp, *filep = NULL,
-		    *pollstart = NULL, *pollstop = NULL;
+	struct file *eventfp, *filep = NULL;
+	bool pollstart = false, pollstop = false;
 	struct eventfd_ctx *ctx = NULL;
 	u32 __user *idxp = argp;
 	struct vhost_virtqueue *vq;
@@ -584,7 +649,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 	if (idx >= d->nvqs)
 		return -ENOBUFS;
 
-	vq = d->vqs + idx;
+	vq = d->vqs[idx];
 
 	mutex_lock(&vq->mutex);
 
@@ -659,7 +724,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		 * If it is not, we don't as size might not have been setup.
 		 * We will verify when backend is configured. */
 		if (vq->private_data) {
-			if (!vq_access_ok(vq->num,
+			if (!vq_access_ok(vq, vq->num,
 				(void __user *)(unsigned long)a.desc_user_addr,
 				(void __user *)(unsigned long)a.avail_user_addr,
 				(void __user *)(unsigned long)a.used_user_addr)) {
@@ -677,10 +742,6 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			}
 		}
 
-		r = init_used(vq, (struct vring_used __user *)(unsigned long)
-			      a.used_user_addr);
-		if (r)
-			break;
 		vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
 		vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
 		vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
@@ -698,8 +759,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			break;
 		}
 		if (eventfp != vq->kick) {
-			pollstop = filep = vq->kick;
-			pollstart = vq->kick = eventfp;
+			pollstop = (filep = vq->kick) != NULL;
+			pollstart = (vq->kick = eventfp) != NULL;
 		} else
 			filep = eventfp;
 		break;
@@ -754,7 +815,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		fput(filep);
 
 	if (pollstart && vq->handle_kick)
-		vhost_poll_start(&vq->poll, vq->kick);
+		r = vhost_poll_start(&vq->poll, vq->kick);
 
 	mutex_unlock(&vq->mutex);
 
@@ -762,11 +823,11 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		vhost_poll_flush(&vq->poll);
 	return r;
 }
+EXPORT_SYMBOL_GPL(vhost_vring_ioctl);
 
 /* Caller must have device mutex */
-long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
+long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 {
-	void __user *argp = (void __user *)arg;
 	struct file *eventfp, *filep = NULL;
 	struct eventfd_ctx *ctx = NULL;
 	u64 p;
@@ -800,7 +861,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 		for (i = 0; i < d->nvqs; ++i) {
 			struct vhost_virtqueue *vq;
 			void __user *base = (void __user *)(unsigned long)p;
-			vq = d->vqs + i;
+			vq = d->vqs[i];
 			mutex_lock(&vq->mutex);
 			/* If ring is inactive, will check when it's enabled. */
 			if (vq->private_data && !vq_log_access_ok(vq, base))
@@ -827,9 +888,9 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 		} else
 			filep = eventfp;
 		for (i = 0; i < d->nvqs; ++i) {
-			mutex_lock(&d->vqs[i].mutex);
-			d->vqs[i].log_ctx = d->log_ctx;
-			mutex_unlock(&d->vqs[i].mutex);
+			mutex_lock(&d->vqs[i]->mutex);
+			d->vqs[i]->log_ctx = d->log_ctx;
+			mutex_unlock(&d->vqs[i]->mutex);
 		}
 		if (ctx)
 			eventfd_ctx_put(ctx);
@@ -837,18 +898,20 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 			fput(filep);
 		break;
 	default:
-		r = vhost_set_vring(d, ioctl, argp);
+		r = -ENOIOCTLCMD;
 		break;
 	}
 done:
 	return r;
 }
+EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
 
 static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
 						     __u64 addr, __u32 len)
 {
 	struct vhost_memory_region *reg;
 	int i;
+
 	/* linear search is not brilliant, but we really have on the order of 6
 	 * regions in practice */
 	for (i = 0; i < mem->nregions; ++i) {
@@ -871,13 +934,14 @@ static int set_bit_to_user(int nr, void __user *addr)
 	void *base;
 	int bit = nr + (log % PAGE_SIZE) * 8;
 	int r;
+
 	r = get_user_pages_fast(log, 1, 1, &page);
 	if (r < 0)
 		return r;
 	BUG_ON(r != 1);
-	base = kmap_atomic(page, KM_USER0);
+	base = kmap_atomic(page);
 	set_bit(bit, base);
-	kunmap_atomic(base, KM_USER0);
+	kunmap_atomic(base);
 	set_page_dirty_lock(page);
 	put_page(page);
 	return 0;
@@ -888,6 +952,7 @@ static int log_write(void __user *log_base,
 {
 	u64 write_page = write_address / VHOST_PAGE_SIZE;
 	int r;
+
 	if (!write_length)
 		return 0;
 	write_length += write_address % VHOST_PAGE_SIZE;
@@ -931,8 +996,61 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 	BUG();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vhost_log_write);
+
+static int vhost_update_used_flags(struct vhost_virtqueue *vq)
+{
+	void __user *used;
+	if (__put_user(vq->used_flags, &vq->used->flags) < 0)
+		return -EFAULT;
+	if (unlikely(vq->log_used)) {
+		/* Make sure the flag is seen before log. */
+		smp_wmb();
+		/* Log used flag write. */
+		used = &vq->used->flags;
+		log_write(vq->log_base, vq->log_addr +
+			  (used - (void __user *)vq->used),
+			  sizeof vq->used->flags);
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return 0;
+}
+
+static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
+{
+	if (__put_user(vq->avail_idx, vhost_avail_event(vq)))
+		return -EFAULT;
+	if (unlikely(vq->log_used)) {
+		void __user *used;
+		/* Make sure the event is seen before log. */
+		smp_wmb();
+		/* Log avail event write */
+		used = vhost_avail_event(vq);
+		log_write(vq->log_base, vq->log_addr +
+			  (used - (void __user *)vq->used),
+			  sizeof *vhost_avail_event(vq));
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return 0;
+}
+
+int vhost_init_used(struct vhost_virtqueue *vq)
+{
+	int r;
+	if (!vq->private_data)
+		return 0;
+
+	r = vhost_update_used_flags(vq);
+	if (r)
+		return r;
+	vq->signalled_used_valid = false;
+	return get_user(vq->last_used_idx, &vq->used->idx);
+}
+EXPORT_SYMBOL_GPL(vhost_init_used);
 
-static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
+static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size)
 {
 	const struct vhost_memory_region *reg;
@@ -941,9 +1059,7 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 	u64 s = 0;
 	int ret = 0;
 
-	rcu_read_lock();
-
-	mem = rcu_dereference(dev->memory);
+	mem = vq->memory;
 	while ((u64)len > s) {
 		u64 size;
 		if (unlikely(ret >= iov_size)) {
@@ -957,7 +1073,7 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 		}
 		_iov = iov + ret;
 		size = reg->memory_size - addr + reg->guest_phys_addr;
-		_iov->iov_len = min((u64)len, size);
+		_iov->iov_len = min((u64)len - s, size);
 		_iov->iov_base = (void __user *)(unsigned long)
 			(reg->userspace_addr + addr - reg->guest_phys_addr);
 		s += size;
@@ -965,7 +1081,6 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 		++ret;
 	}
 
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -990,7 +1105,7 @@ static unsigned next_desc(struct vring_desc *desc)
 	return next;
 }
 
-static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+static int get_indirect(struct vhost_virtqueue *vq,
 			struct iovec iov[], unsigned int iov_size,
 			unsigned int *out_num, unsigned int *in_num,
 			struct vhost_log *log, unsigned int *log_num,
@@ -1009,7 +1124,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 		return -EINVAL;
 	}
 
-	ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
+	ret = translate_desc(vq, indirect->addr, indirect->len, vq->indirect,
 			     UIO_MAXIOV);
 	if (unlikely(ret < 0)) {
 		vq_err(vq, "Translation failure %d in indirect.\n", ret);
@@ -1037,8 +1152,8 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			       i, count);
 			return -EINVAL;
 		}
-		if (unlikely(memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
-					      sizeof desc))) {
+		if (unlikely(memcpy_fromiovec((unsigned char *)&desc,
+					      vq->indirect, sizeof desc))) {
 			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
 			       i, (size_t)indirect->addr + i * sizeof desc);
 			return -EINVAL;
@@ -1049,7 +1164,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			return -EINVAL;
 		}
 
-		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+		ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
 				     iov_size - iov_count);
 		if (unlikely(ret < 0)) {
 			vq_err(vq, "Translation failure %d indirect idx %d\n",
@@ -1086,7 +1201,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
  * This function returns the descriptor number found, or vq->num (which is
  * never a valid descriptor number) if none was found.  A negative code is
  * returned on error. */
-int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 		      struct iovec iov[], unsigned int iov_size,
 		      unsigned int *out_num, unsigned int *in_num,
 		      struct vhost_log *log, unsigned int *log_num)
@@ -1153,14 +1268,14 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			       i, vq->num, head);
 			return -EINVAL;
 		}
-		ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
+		ret = __copy_from_user(&desc, vq->desc + i, sizeof desc);
 		if (unlikely(ret)) {
 			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
 			       i, vq->desc + i);
 			return -EFAULT;
 		}
 		if (desc.flags & VRING_DESC_F_INDIRECT) {
-			ret = get_indirect(dev, vq, iov, iov_size,
+			ret = get_indirect(vq, iov, iov_size,
 					   out_num, in_num,
 					   log, log_num, &desc);
 			if (unlikely(ret < 0)) {
@@ -1171,7 +1286,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			continue;
 		}
 
-		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+		ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
 				     iov_size - iov_count);
 		if (unlikely(ret < 0)) {
 			vq_err(vq, "Translation failure %d descriptor idx %d\n",
@@ -1201,67 +1316,51 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
 	/* On success, increment avail index. */
 	vq->last_avail_idx++;
+
+	/* Assume notifications from guest are disabled at this point,
+	 * if they aren't we would need to update avail_event index. */
+	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
 	return head;
 }
+EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
 
 /* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
 void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
 {
 	vq->last_avail_idx -= n;
 }
+EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);
 
 /* After we've used one of their buffers, we tell them about it.  We'll then
  * want to notify the guest, using eventfd. */
 int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
 {
-	struct vring_used_elem __user *used;
+	struct vring_used_elem heads = { head, len };
 
-	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
-	 * next entry in that used ring. */
-	used = &vq->used->ring[vq->last_used_idx % vq->num];
-	if (__put_user(head, &used->id)) {
-		vq_err(vq, "Failed to write used id");
-		return -EFAULT;
-	}
-	if (__put_user(len, &used->len)) {
-		vq_err(vq, "Failed to write used len");
-		return -EFAULT;
-	}
-	/* Make sure buffer is written before we update index. */
-	smp_wmb();
-	if (__put_user(vq->last_used_idx + 1, &vq->used->idx)) {
-		vq_err(vq, "Failed to increment used idx");
-		return -EFAULT;
-	}
-	if (unlikely(vq->log_used)) {
-		/* Make sure data is seen before log. */
-		smp_wmb();
-		/* Log used ring entry write. */
-		log_write(vq->log_base,
-			  vq->log_addr +
-			   ((void __user *)used - (void __user *)vq->used),
-			  sizeof *used);
-		/* Log used index update. */
-		log_write(vq->log_base,
-			  vq->log_addr + offsetof(struct vring_used, idx),
-			  sizeof vq->used->idx);
-		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
-	}
-	vq->last_used_idx++;
-	return 0;
+	return vhost_add_used_n(vq, &heads, 1);
 }
+EXPORT_SYMBOL_GPL(vhost_add_used);
 
 static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			    struct vring_used_elem *heads,
 			    unsigned count)
 {
 	struct vring_used_elem __user *used;
+	u16 old, new;
 	int start;
 
 	start = vq->last_used_idx % vq->num;
 	used = vq->used->ring + start;
-	if (__copy_to_user(used, heads, count * sizeof *used)) {
+	if (count == 1) {
+		if (__put_user(heads[0].id, &used->id)) {
+			vq_err(vq, "Failed to write used id");
+			return -EFAULT;
+		}
+		if (__put_user(heads[0].len, &used->len)) {
+			vq_err(vq, "Failed to write used len");
+			return -EFAULT;
+		}
+	} else if (__copy_to_user(used, heads, count * sizeof *used)) {
 		vq_err(vq, "Failed to write used");
 		return -EFAULT;
 	}
@@ -1274,7 +1373,14 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			   ((void __user *)used - (void __user *)vq->used),
 			  count * sizeof *used);
 	}
-	vq->last_used_idx += count;
+	old = vq->last_used_idx;
+	new = (vq->last_used_idx += count);
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
@@ -1312,31 +1418,52 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 	}
 	return r;
 }
+EXPORT_SYMBOL_GPL(vhost_add_used_n);
 
-/* This actually signals the guest, using eventfd. */
-void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-	__u16 flags;
+	__u16 old, new, event;
+	bool v;
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
 	smp_mb();
 
-	if (__get_user(flags, &vq->avail->flags)) {
-		vq_err(vq, "Failed to get flags");
-		return;
+	if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+	    unlikely(vq->avail_idx == vq->last_avail_idx))
+		return true;
+
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
+		__u16 flags;
+		if (__get_user(flags, &vq->avail->flags)) {
+			vq_err(vq, "Failed to get flags");
+			return true;
+		}
+		return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
 	}
+	old = vq->signalled_used;
+	v = vq->signalled_used_valid;
+	new = vq->signalled_used = vq->last_used_idx;
+	vq->signalled_used_valid = true;
 
-	/* If they don't want an interrupt, don't signal, unless empty. */
-	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
-	    (vq->avail_idx != vq->last_avail_idx ||
-	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-		return;
+	if (unlikely(!v))
+		return true;
 
+	if (get_user(event, vhost_used_event(vq))) {
+		vq_err(vq, "Failed to get used event idx");
+		return true;
+	}
+	return vring_need_event(event, new, old);
+}
+
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
 	/* Signal the Guest tell them we used something up. */
-	if (vq->call_ctx)
+	if (vq->call_ctx && vhost_notify(dev, vq))
 		eventfd_signal(vq->call_ctx, 1);
 }
+EXPORT_SYMBOL_GPL(vhost_signal);
 
 /* And here's the combo meal deal.  Supersize me! */
 void vhost_add_used_and_signal(struct vhost_dev *dev,
@@ -1346,6 +1473,7 @@ void vhost_add_used_and_signal(struct vhost_dev *dev,
 	vhost_add_used(vq, head, len);
 	vhost_signal(dev, vq);
 }
+EXPORT_SYMBOL_GPL(vhost_add_used_and_signal);
 
 /* multi-buffer version of vhost_add_used_and_signal */
 void vhost_add_used_and_signal_n(struct vhost_dev *dev,
@@ -1355,20 +1483,31 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 	vhost_add_used_n(vq, heads, count);
 	vhost_signal(dev, vq);
 }
+EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
 
 /* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_virtqueue *vq)
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	u16 avail_idx;
 	int r;
+
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r) {
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
-		return false;
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
+		r = vhost_update_used_flags(vq);
+		if (r) {
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+			return false;
+		}
+	} else {
+		r = vhost_update_avail_event(vq, vq->avail_idx);
+		if (r) {
+			vq_err(vq, "Failed to update avail event index at %p: %d\n",
+			       vhost_avail_event(vq), r);
+			return false;
+		}
 	}
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
@@ -1382,16 +1521,38 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 
 	return avail_idx != vq->avail_idx;
 }
+EXPORT_SYMBOL_GPL(vhost_enable_notify);
 
 /* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_virtqueue *vq)
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	int r;
+
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r)
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
+		r = vhost_update_used_flags(vq);
+		if (r)
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+	}
+}
+EXPORT_SYMBOL_GPL(vhost_disable_notify);
+
+static int __init vhost_init(void)
+{
+	return 0;
 }
+
+static void __exit vhost_exit(void)
+{
+}
+
+module_init(vhost_init);
+module_exit(vhost_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Michael S. Tsirkin");
+MODULE_DESCRIPTION("Host kernel accelerator for virtio");