Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
  virtio_net: delay TX callbacks
  virtio: add api for delayed callbacks
  virtio_test: support event index
  vhost: support event index
  virtio_ring: support event idx feature
  virtio ring: inline function to check for events
  virtio: event index interface
  virtio: add full three-clause BSD text to headers.
  virtio balloon: kill tell-host-first logic
  virtio console: don't manually set or finalize VIRTIO_CONSOLE_F_MULTIPORT.
  drivers, block: virtio_blk: Replace cryptic number with the macro
  virtio_blk: allow re-reading config space at runtime
  lguest: remove support for VIRTIO_F_NOTIFY_ON_EMPTY.
  lguest: fix up compilation after move
  lguest: fix timer interrupt setup

Documentation/virtual/lguest/Makefile

@@ -1,5 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../include -I../../arch/x86/include"
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 
 all: lguest

Documentation/virtual/lguest/lguest.c

@@ -49,7 +49,7 @@
 #include <linux/virtio_rng.h>
 #include <linux/virtio_ring.h>
 #include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
+#include "../../../include/linux/lguest_launcher.h"
 /*L:110
  * We can ignore the 42 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
@@ -135,9 +135,6 @@ struct device {
 	/* Is it operational */
 	bool running;
 
-	/* Does Guest want an intrrupt on empty? */
-	bool irq_on_empty;
-
 	/* Device-specific data. */
 	void *priv;
 };
@@ -637,10 +634,7 @@ static void trigger_irq(struct virtqueue *vq)
 
 	/* If they don't want an interrupt, don't send one... */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-		/* ... unless they've asked us to force one on empty. */
+		return;
-		if (!vq->dev->irq_on_empty
-		    || lg_last_avail(vq) != vq->vring.avail->idx)
-			return;
 	}
 
 	/* Send the Guest an interrupt tell them we used something up. */
@@ -1057,15 +1051,6 @@ static void create_thread(struct virtqueue *vq)
 	close(vq->eventfd);
 }
 
-static bool accepted_feature(struct device *dev, unsigned int bit)
-{
-	const u8 *features = get_feature_bits(dev) + dev->feature_len;
-
-	if (dev->feature_len < bit / CHAR_BIT)
-		return false;
-	return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
-}
-
 static void start_device(struct device *dev)
 {
 	unsigned int i;
@@ -1079,8 +1064,6 @@ static void start_device(struct device *dev)
 		verbose(" %02x", get_feature_bits(dev)
 			[dev->feature_len+i]);
 
-	dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
-
 	for (vq = dev->vq; vq; vq = vq->next) {
 		if (vq->service)
 			create_thread(vq);
@@ -1564,7 +1547,6 @@ static void setup_tun_net(char *arg)
 	/* Set up the tun device. */
 	configure_device(ipfd, tapif, ip);
 
-	add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
 	/* Expect Guest to handle everything except UFO */
 	add_feature(dev, VIRTIO_NET_F_CSUM);
 	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);

arch/x86/lguest/boot.c

@@ -993,6 +993,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
+	lguest_setup_irq(0);
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);

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		= features,
-	.feature_table_size = ARRAY_SIZE(features),
+	.feature_table_size	= ARRAY_SIZE(features),
-	.driver.name =	KBUILD_MODNAME,
+	.driver.name		= KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
+	.driver.owner		= THIS_MODULE,
-	.id_table =	id_table,
+	.id_table		= id_table,
-	.probe =	virtblk_probe,
+	.probe			= virtblk_probe,
-	.remove =	__devexit_p(virtblk_remove),
+	.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)
+	if (major < 0) {
-		return major;
+		error = major;
-	return register_virtio_driver(&virtio_blk);
+		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);

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);

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) {

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))) {
+			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
-				vhost_disable_notify(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

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))) {
+			if (unlikely(vhost_enable_notify(&n->dev, vq))) {
-				vhost_disable_notify(vq);
+				vhost_disable_notify(&n->dev, vq);
 				continue;
 			}
 			break;

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) &&
+	return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+		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. */
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
-void vhost_signal(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)) {
+	if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
-		vq_err(vq, "Failed to get flags");
+	    unlikely(vq->avail_idx == vq->last_avail_idx))
-		return;
+		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 (unlikely(!v))
-	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
+		return true;
-	    (vq->avail_idx != vq->last_avail_idx ||
-	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-		return;
 
+	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 (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
-	if (r) {
+		r = put_user(vq->used_flags, &vq->used->flags);
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
+		if (r) {
-		       &vq->used->flags, r);
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
-		return false;
+			       &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 (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
-	if (r)
+		r = put_user(vq->used_flags, &vq->used->flags);
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
+		if (r)
-		       &vq->used->flags, r);
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+	}
 }

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 *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
-bool vhost_enable_notify(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) |
+	VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
-			 (1 << VIRTIO_RING_F_INDIRECT_DESC) |
+			 (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
-			 (1 << VHOST_F_LOG_ALL) |
+			 (1ULL << VIRTIO_RING_F_EVENT_IDX) |
-			 (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
+			 (1ULL << VHOST_F_LOG_ALL) |
-			 (1 << VIRTIO_NET_F_MRG_RXBUF),
+			 (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)

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);
+	 * Note that if
-	} else {
+	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
-		release_pages_by_pfn(vb->pfns, vb->num_pfns);
+	 * is true, we *have* to do it in this order
-		tell_host(vb, vb->deflate_vq);
+	 */
-	}
+	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:

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);

include/linux/virtio.h

@@ -51,6 +51,13 @@ struct virtqueue {
  *	This re-enables callbacks; it returns "false" if there are pending
  *	buffers in the queue, to detect a possible race between the driver
  *	checking for more work, and enabling callbacks.
+ * virtqueue_enable_cb_delayed: restart callbacks after disable_cb.
+ *	vq: the struct virtqueue we're talking about.
+ *	This re-enables callbacks but hints to the other side to delay
+ *	interrupts until most of the available buffers have been processed;
+ *	it returns "false" if there are many pending buffers in the queue,
+ *	to detect a possible race between the driver checking for more work,
+ *	and enabling callbacks.
  * virtqueue_detach_unused_buf: detach first unused buffer
  * 	vq: the struct virtqueue we're talking about.
  * 	Returns NULL or the "data" token handed to add_buf
@@ -86,6 +93,8 @@ void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 /**

include/linux/virtio_9p.h

@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_9P_H
 #define _LINUX_VIRTIO_9P_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_balloon.h

@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BALLOON_H
 #define _LINUX_VIRTIO_BALLOON_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 

include/linux/virtio_blk.h

@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BLK_H
 #define _LINUX_VIRTIO_BLK_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_config.h

@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_CONFIG_H
 #define _LINUX_VIRTIO_CONFIG_H
 /* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers. */
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 /* Virtio devices use a standardized configuration space to define their
  * features and pass configuration information, but each implementation can

include/linux/virtio_console.h

@@ -5,7 +5,31 @@
 #include <linux/virtio_config.h>
 /*
  * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers.
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  *
  * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
  * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011

include/linux/virtio_ids.h

@@ -5,7 +5,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
- */
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 #define VIRTIO_ID_NET		1 /* virtio net */
 #define VIRTIO_ID_BLOCK		2 /* virtio block */

include/linux/virtio_net.h

@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_NET_H
 #define _LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_pci.h

@@ -11,6 +11,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  */
 
 #ifndef _LINUX_VIRTIO_PCI_H

include/linux/virtio_ring.h

@@ -7,6 +7,29 @@
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
  * Copyright Rusty Russell IBM Corporation 2007. */
 #include <linux/types.h>
 
@@ -29,6 +52,12 @@
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX		29
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
@@ -83,6 +112,7 @@ struct vring {
  *	__u16 avail_flags;
  *	__u16 avail_idx;
  *	__u16 available[num];
+ *	__u16 used_event_idx;
  *
  *	// Padding to the next align boundary.
  *	char pad[];
@@ -91,8 +121,14 @@ struct vring {
  *	__u16 used_flags;
  *	__u16 used_idx;
  *	struct vring_used_elem used[num];
+ *	__u16 avail_event_idx;
  * };
  */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 			      unsigned long align)
 {
@@ -107,7 +143,21 @@ static inline unsigned vring_size(unsigned int num, unsigned long align)
 {
 	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
 		 + align - 1) & ~(align - 1))
-		+ sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
+		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other size, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+	/* Note: Xen has similar logic for notification hold-off
+	 * in include/xen/interface/io/ring.h with req_event and req_prod
+	 * corresponding to event_idx + 1 and new_idx respectively.
+	 * Note also that req_event and req_prod in Xen start at 1,
+	 * event indexes in virtio start at 0. */
+	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
 #ifdef __KERNEL__

tools/virtio/virtio_test.c

@@ -197,6 +197,14 @@ const struct option longopts[] = {
 		.name = "help",
 		.val = 'h',
 	},
+	{
+		.name = "event-idx",
+		.val = 'E',
+	},
+	{
+		.name = "no-event-idx",
+		.val = 'e',
+	},
 	{
 		.name = "indirect",
 		.val = 'I',
@@ -211,13 +219,17 @@ const struct option longopts[] = {
 
 static void help()
 {
-	fprintf(stderr, "Usage: virtio_test [--help] [--no-indirect]\n");
+	fprintf(stderr, "Usage: virtio_test [--help]"
+		" [--no-indirect]"
+		" [--no-event-idx]"
+		"\n");
 }
 
 int main(int argc, char **argv)
 {
 	struct vdev_info dev;
-	unsigned long long features = 1ULL << VIRTIO_RING_F_INDIRECT_DESC;
+	unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+		(1ULL << VIRTIO_RING_F_EVENT_IDX);
 	int o;
 
 	for (;;) {
@@ -228,6 +240,9 @@ int main(int argc, char **argv)
 		case '?':
 			help();
 			exit(2);
+		case 'e':
+			features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX);
+			break;
 		case 'h':
 			help();
 			goto done;