9 files changed, 267 insertions, 82 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ecf89cdf006..079c08808d8a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -6,10 +6,13 @@
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
 
 #define PART_BITS 4
 
 static int major, index;
+struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
@@ -26,6 +29,9 @@ struct virtio_blk
 
         mempool_t *pool;
 
+        /* Process context for config space updates */
+        struct work_struct config_work;
+
         /* What host tells us, plus 2 for header & tailer. */
         unsigned int sg_elems;
 
@@ -141,7 +147,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
         num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
 
         if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-                sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+                sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
                 sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
                            sizeof(vbr->in_hdr));
         }
@@ -291,6 +297,46 @@ static ssize_t virtblk_serial_show(struct device *dev,
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+        struct virtio_blk *vblk =
+                container_of(work, struct virtio_blk, config_work);
+        struct virtio_device *vdev = vblk->vdev;
+        struct request_queue *q = vblk->disk->queue;
+        char cap_str_2[10], cap_str_10[10];
+        u64 capacity, size;
+
+        /* Host must always specify the capacity. */
+        vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+                          &capacity, sizeof(capacity));
+
+        /* If capacity is too big, truncate with warning. */
+        if ((sector_t)capacity != capacity) {
+                dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+                         (unsigned long long)capacity);
+                capacity = (sector_t)-1;
+        }
+
+        size = capacity * queue_logical_block_size(q);
+        string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+        string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+        dev_notice(&vdev->dev,
+                  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+                  (unsigned long long)capacity,
+                  queue_logical_block_size(q),
+                  cap_str_10, cap_str_2);
+
+        set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+        struct virtio_blk *vblk = vdev->priv;
+
+        queue_work(virtblk_wq, &vblk->config_work);
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
         struct virtio_blk *vblk;
@@ -327,6 +373,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
         vblk->vdev = vdev;
         vblk->sg_elems = sg_elems;
         sg_init_table(vblk->sg, vblk->sg_elems);
+        INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
         /* We expect one virtqueue, for output. */
         vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
@@ -477,6 +524,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 {
         struct virtio_blk *vblk = vdev->priv;
 
+        flush_work(&vblk->config_work);
+
         /* Nothing should be pending. */
         BUG_ON(!list_empty(&vblk->reqs));
 
@@ -508,27 +557,47 @@ static unsigned int features[] = {
  * Use __refdata to avoid this warning.
  */
 static struct virtio_driver __refdata virtio_blk = {
-        .feature_table = features,
-        .feature_table_size = ARRAY_SIZE(features),
-        .driver.name =  KBUILD_MODNAME,
-        .driver.owner = THIS_MODULE,
-        .id_table =     id_table,
-        .probe =        virtblk_probe,
-        .remove =       __devexit_p(virtblk_remove),
+        .feature_table          = features,
+        .feature_table_size     = ARRAY_SIZE(features),
+        .driver.name            = KBUILD_MODNAME,
+        .driver.owner           = THIS_MODULE,
+        .id_table               = id_table,
+        .probe                  = virtblk_probe,
+        .remove                 = __devexit_p(virtblk_remove),
+        .config_changed         = virtblk_config_changed,
 };
 
 static int __init init(void)
 {
+        int error;
+
+        virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+        if (!virtblk_wq)
+                return -ENOMEM;
+
         major = register_blkdev(0, "virtblk");
-        if (major < 0)
-                return major;
-        return register_virtio_driver(&virtio_blk);
+        if (major < 0) {
+                error = major;
+                goto out_destroy_workqueue;
+        }
+
+        error = register_virtio_driver(&virtio_blk);
+        if (error)
+                goto out_unregister_blkdev;
+        return 0;
+
+out_unregister_blkdev:
+        unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+        destroy_workqueue(virtblk_wq);
+        return error;
 }
 
 static void __exit fini(void)
 {
         unregister_blkdev(major, "virtblk");
         unregister_virtio_driver(&virtio_blk);
+        destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 838568a7dbf5..fb68b1295373 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1677,17 +1677,12 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
         portdev->config.max_nr_ports = 1;
         if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
                 multiport = true;
-                vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
                 vdev->config->get(vdev, offsetof(struct virtio_console_config,
                                                  max_nr_ports),
                                   &portdev->config.max_nr_ports,
                                   sizeof(portdev->config.max_nr_ports));
         }
 
-        /* Let the Host know we support multiple ports.*/
-        vdev->config->finalize_features(vdev);
-
         err = init_vqs(portdev);
         if (err < 0) {
                 dev_err(&vdev->dev, "Error %d initializing vqs\n", err);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0cb0b0632672..f6853247a620 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -609,7 +609,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
          * before it gets out of hand.  Naturally, this wastes entries. */
         if (capacity < 2+MAX_SKB_FRAGS) {
                 netif_stop_queue(dev);
-                if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+                if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
                         /* More just got used, free them then recheck. */
                         capacity += free_old_xmit_skbs(vi);
                         if (capacity >= 2+MAX_SKB_FRAGS) {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2f7c76a85e53..e224a92baa16 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -144,7 +144,7 @@ static void handle_tx(struct vhost_net *net)
         }
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&net->dev, vq);
 
         if (wmem < sock->sk->sk_sndbuf / 2)
                 tx_poll_stop(net);
@@ -166,8 +166,8 @@ static void handle_tx(struct vhost_net *net)
                                 set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
                                 break;
                         }
-                        if (unlikely(vhost_enable_notify(vq))) {
-                                vhost_disable_notify(vq);
+                        if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+                                vhost_disable_notify(&net->dev, vq);
                                 continue;
                         }
                         break;
@@ -315,7 +315,7 @@ static void handle_rx(struct vhost_net *net)
                 return;
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&net->dev, vq);
         vhost_hlen = vq->vhost_hlen;
         sock_hlen = vq->sock_hlen;
 
@@ -334,10 +334,10 @@ static void handle_rx(struct vhost_net *net)
                         break;
                 /* OK, now we need to know about added descriptors. */
                 if (!headcount) {
-                        if (unlikely(vhost_enable_notify(vq))) {
+                        if (unlikely(vhost_enable_notify(&net->dev, vq))) {
                                 /* They have slipped one in as we were
                                  * doing that: check again. */
-                                vhost_disable_notify(vq);
+                                vhost_disable_notify(&net->dev, vq);
                                 continue;
                         }
                         /* Nothing new?  Wait for eventfd to tell us
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index 099f30230d06..734e1d74ad80 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n)
                 return;
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&n->dev, vq);
 
         for (;;) {
                 head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
@@ -61,8 +61,8 @@ static void handle_vq(struct vhost_test *n)
                         break;
                 /* Nothing new?  Wait for eventfd to tell us they refilled. */
                 if (head == vq->num) {
-                        if (unlikely(vhost_enable_notify(vq))) {
-                                vhost_disable_notify(vq);
+                        if (unlikely(vhost_enable_notify(&n->dev, vq))) {
+                                vhost_disable_notify(&n->dev, vq);
                                 continue;
                         }
                         break;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 7aa4eea930f1..ea966b356352 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -37,6 +37,9 @@ 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)
 {
@@ -161,6 +164,8 @@ 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;
@@ -489,16 +494,17 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
         return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+static int vq_access_ok(struct vhost_dev *d, unsigned int num,
                         struct vring_desc __user *desc,
                         struct vring_avail __user *avail,
                         struct vring_used __user *used)
 {
+        size_t s = vhost_has_feature(d, 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? */
@@ -514,9 +520,11 @@ int vhost_log_access_ok(struct vhost_dev *dev)
 
 /* 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_dev *d, struct vhost_virtqueue *vq,
+                            void __user *log_base)
 {
         struct vhost_memory *mp;
+        size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
         mp = rcu_dereference_protected(vq->dev->memory,
                                        lockdep_is_held(&vq->mutex));
@@ -524,15 +532,15 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
                             vhost_has_feature(vq->dev, 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) &&
-                vq_log_access_ok(vq, vq->log_base);
+        return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
+                vq_log_access_ok(vq->dev, vq, vq->log_base);
 }
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
@@ -577,6 +585,7 @@ static int init_used(struct vhost_virtqueue *vq,
 
         if (r)
                 return r;
+        vq->signalled_used_valid = false;
         return get_user(vq->last_used_idx, &used->idx);
 }
 
@@ -674,7 +683,7 @@ 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(d, 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)) {
@@ -818,7 +827,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
                         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))
+                        if (vq->private_data && !vq_log_access_ok(d, vq, base))
                                 r = -EFAULT;
                         else
                                 vq->log_base = base;
@@ -1219,6 +1228,10 @@ 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;
 }
 
@@ -1267,6 +1280,12 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
                         eventfd_signal(vq->log_ctx, 1);
         }
         vq->last_used_idx++;
+        /* 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(vq->last_used_idx == vq->signalled_used))
+                vq->signalled_used_valid = false;
         return 0;
 }
 
@@ -1275,6 +1294,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
                             unsigned count)
 {
         struct vring_used_elem __user *used;
+        u16 old, new;
         int start;
 
         start = vq->last_used_idx % vq->num;
@@ -1292,7 +1312,14 @@ 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;
 }
 
@@ -1331,29 +1358,47 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
         return r;
 }
 
-/* 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(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+            unlikely(vq->avail_idx == vq->last_avail_idx))
+                return true;
+
+        if (!vhost_has_feature(dev, 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);
 }
 
@@ -1376,7 +1421,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 
 /* 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;
@@ -1384,11 +1429,34 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
         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(dev, VIRTIO_RING_F_EVENT_IDX)) {
+                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;
+                }
+        } else {
+                r = put_user(vq->avail_idx, vhost_avail_event(vq));
+                if (r) {
+                        vq_err(vq, "Failed to update avail event index at %p: %d\n",
+                               vhost_avail_event(vq), r);
+                        return false;
+                }
+        }
+        if (unlikely(vq->log_used)) {
+                void __user *used;
+                /* Make sure data is seen before log. */
+                smp_wmb();
+                used = vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX) ?
+                        &vq->used->flags : vhost_avail_event(vq);
+                /* Log used flags or event index entry write. Both are 16 bit
+                 * fields. */
+                log_write(vq->log_base, vq->log_addr +
+                           (used - (void __user *)vq->used),
+                          sizeof(u16));
+                if (vq->log_ctx)
+                        eventfd_signal(vq->log_ctx, 1);
         }
         /* They could have slipped one in as we were doing that: make
          * sure it's written, then check again. */
@@ -1404,15 +1472,17 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 }
 
 /* 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(dev, VIRTIO_RING_F_EVENT_IDX)) {
+                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);
+        }
 }
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index b3363ae38518..8e03379dd30f 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -84,6 +84,12 @@ struct vhost_virtqueue {
         /* Used flags */
         u16 used_flags;
 
+        /* Last used index value we have signalled on */
+        u16 signalled_used;
+
+        /* Last used index value we have signalled on */
+        bool signalled_used_valid;
+
         /* Log writes to used structure. */
         bool log_used;
         u64 log_addr;
@@ -149,8 +155,8 @@ void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
 void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
                                struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
-void vhost_disable_notify(struct vhost_virtqueue *);
-bool vhost_enable_notify(struct vhost_virtqueue *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
                     unsigned int log_num, u64 len);
@@ -162,11 +168,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
         } while (0)
 
 enum {
-        VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
-                         (1 << VIRTIO_RING_F_INDIRECT_DESC) |
-                         (1 << VHOST_F_LOG_ALL) |
-                         (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
-                         (1 << VIRTIO_NET_F_MRG_RXBUF),
+        VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+                         (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+                         (1ULL << VIRTIO_RING_F_EVENT_IDX) |
+                         (1ULL << VHOST_F_LOG_ALL) |
+                         (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
+                         (1ULL << VIRTIO_NET_F_MRG_RXBUF),
 };
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0f1da45ba47d..e058ace2a4ad 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -40,9 +40,6 @@ struct virtio_balloon
         /* Waiting for host to ack the pages we released. */
         struct completion acked;
 
-        /* Do we have to tell Host *before* we reuse pages? */
-        bool tell_host_first;
-
         /* The pages we've told the Host we're not using. */
         unsigned int num_pages;
         struct list_head pages;
@@ -151,13 +148,14 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
                 vb->num_pages--;
         }
 
-        if (vb->tell_host_first) {
-                tell_host(vb, vb->deflate_vq);
-                release_pages_by_pfn(vb->pfns, vb->num_pfns);
-        } else {
-                release_pages_by_pfn(vb->pfns, vb->num_pfns);
-                tell_host(vb, vb->deflate_vq);
-        }
+
+        /*
+         * Note that if
+         * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+         * is true, we *have* to do it in this order
+         */
+        tell_host(vb, vb->deflate_vq);
+        release_pages_by_pfn(vb->pfns, vb->num_pfns);
 }
 
 static inline void update_stat(struct virtio_balloon *vb, int idx,
@@ -325,9 +323,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
                 goto out_del_vqs;
         }
 
-        vb->tell_host_first
-                = virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
-
         return 0;
 
 out_del_vqs:
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b0043fb26a4d..68b9136847af 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -82,6 +82,9 @@ struct vring_virtqueue
         /* Host supports indirect buffers */
         bool indirect;
 
+        /* Host publishes avail event idx */
+        bool event;
+
         /* Number of free buffers */
         unsigned int num_free;
         /* Head of free buffer list. */
@@ -237,18 +240,22 @@ EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp);
 void virtqueue_kick(struct virtqueue *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
+        u16 new, old;
         START_USE(vq);
         /* Descriptors and available array need to be set before we expose the
          * new available array entries. */
         virtio_wmb();
 
-        vq->vring.avail->idx += vq->num_added;
+        old = vq->vring.avail->idx;
+        new = vq->vring.avail->idx = old + vq->num_added;
         vq->num_added = 0;
 
         /* Need to update avail index before checking if we should notify */
         virtio_mb();
 
-        if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+        if (vq->event ?
+            vring_need_event(vring_avail_event(&vq->vring), new, old) :
+            !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
                 /* Prod other side to tell it about changes. */
                 vq->notify(&vq->vq);
 
@@ -324,6 +331,14 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
         ret = vq->data[i];
         detach_buf(vq, i);
         vq->last_used_idx++;
+        /* If we expect an interrupt for the next entry, tell host
+         * by writing event index and flush out the write before
+         * the read in the next get_buf call. */
+        if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+                vring_used_event(&vq->vring) = vq->last_used_idx;
+                virtio_mb();
+        }
+
         END_USE(vq);
         return ret;
 }
@@ -345,7 +360,11 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 
         /* We optimistically turn back on interrupts, then check if there was
          * more to do. */
+        /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+         * either clear the flags bit or point the event index at the next
+         * entry. Always do both to keep code simple. */
         vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+        vring_used_event(&vq->vring) = vq->last_used_idx;
         virtio_mb();
         if (unlikely(more_used(vq))) {
                 END_USE(vq);
@@ -357,6 +376,33 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+        struct vring_virtqueue *vq = to_vvq(_vq);
+        u16 bufs;
+
+        START_USE(vq);
+
+        /* We optimistically turn back on interrupts, then check if there was
+         * more to do. */
+        /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+         * either clear the flags bit or point the event index at the next
+         * entry. Always do both to keep code simple. */
+        vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+        /* TODO: tune this threshold */
+        bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+        vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+        virtio_mb();
+        if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+                END_USE(vq);
+                return false;
+        }
+
+        END_USE(vq);
+        return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
@@ -438,6 +484,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 #endif
 
         vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+        vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
         /* No callback?  Tell other side not to bother us. */
         if (!callback)
@@ -472,6 +519,8 @@ void vring_transport_features(struct virtio_device *vdev)
                 switch (i) {
                 case VIRTIO_RING_F_INDIRECT_DESC:
                         break;
+                case VIRTIO_RING_F_EVENT_IDX:
+                        break;
                 default:
                         /* We don't understand this bit. */
                         clear_bit(i, vdev->features);