Merge commit 'v3.3-rc6' into next

4 files changed, 427 insertions, 69 deletions

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 94fd738a774..958e5129c60 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1,4 +1,5 @@
-/* Virtio balloon implementation, inspired by Dor Loar and Marcelo
+/*
+ * Virtio balloon implementation, inspired by Dor Laor and Marcelo
  * Tosatti's implementations.
  *
  *  Copyright 2008 Rusty Russell IBM Corporation
@@ -17,7 +18,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
-//#define DEBUG
+
 #include <linux/virtio.h>
 #include <linux/virtio_balloon.h>
 #include <linux/swap.h>
@@ -87,7 +88,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 	init_completion(&vb->acked);
 
 	/* We should always be able to add one buffer to an empty queue. */
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0)
+	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 
@@ -149,7 +150,6 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
 		vb->num_pages--;
 	}
 
-
 	/*
 	 * Note that if
 	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
@@ -220,7 +220,7 @@ static void stats_handle_request(struct virtio_balloon *vb)
 
 	vq = vb->stats_vq;
 	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0)
+	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 }
@@ -275,32 +275,21 @@ static int balloon(void *_vballoon)
 	return 0;
 }
 
-static int virtballoon_probe(struct virtio_device *vdev)
+static int init_vqs(struct virtio_balloon *vb)
 {
-	struct virtio_balloon *vb;
 	struct virtqueue *vqs[3];
 	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
 	const char *names[] = { "inflate", "deflate", "stats" };
 	int err, nvqs;
 
-	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
-	if (!vb) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	INIT_LIST_HEAD(&vb->pages);
-	vb->num_pages = 0;
-	init_waitqueue_head(&vb->config_change);
-	vb->vdev = vdev;
-	vb->need_stats_update = 0;
-
-	/* We expect two virtqueues: inflate and deflate,
-	 * and optionally stat. */
+	/*
+	 * We expect two virtqueues: inflate and deflate, and
+	 * optionally stat.
+	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
 	if (err)
-		goto out_free_vb;
+		return err;
 
 	vb->inflate_vq = vqs[0];
 	vb->deflate_vq = vqs[1];
@@ -313,10 +302,34 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		 * use it to signal us later.
 		 */
 		sg_init_one(&sg, vb->stats, sizeof vb->stats);
-		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb) < 0)
+		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL)
+		    < 0)
 			BUG();
 		virtqueue_kick(vb->stats_vq);
 	}
+	return 0;
+}
+
+static int virtballoon_probe(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb;
+	int err;
+
+	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
+	if (!vb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&vb->pages);
+	vb->num_pages = 0;
+	init_waitqueue_head(&vb->config_change);
+	vb->vdev = vdev;
+	vb->need_stats_update = 0;
+
+	err = init_vqs(vb);
+	if (err)
+		goto out_free_vb;
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
@@ -351,6 +364,59 @@ static void __devexit virtballoon_remove(struct virtio_device *vdev)
 	kfree(vb);
 }
 
+#ifdef CONFIG_PM
+static int virtballoon_freeze(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	/*
+	 * The kthread is already frozen by the PM core before this
+	 * function is called.
+	 */
+
+	while (vb->num_pages)
+		leak_balloon(vb, vb->num_pages);
+	update_balloon_size(vb);
+
+	/* Ensure we don't get any more requests from the host */
+	vdev->config->reset(vdev);
+	vdev->config->del_vqs(vdev);
+	return 0;
+}
+
+static int restore_common(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+	int ret;
+
+	ret = init_vqs(vdev->priv);
+	if (ret)
+		return ret;
+
+	fill_balloon(vb, towards_target(vb));
+	update_balloon_size(vb);
+	return 0;
+}
+
+static int virtballoon_thaw(struct virtio_device *vdev)
+{
+	return restore_common(vdev);
+}
+
+static int virtballoon_restore(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	/*
+	 * If a request wasn't complete at the time of freezing, this
+	 * could have been set.
+	 */
+	vb->need_stats_update = 0;
+
+	return restore_common(vdev);
+}
+#endif
+
 static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
@@ -365,6 +431,11 @@ static struct virtio_driver virtio_balloon_driver = {
 	.probe =	virtballoon_probe,
 	.remove =	__devexit_p(virtballoon_remove),
 	.config_changed = virtballoon_changed,
+#ifdef CONFIG_PM
+	.freeze	=	virtballoon_freeze,
+	.restore =	virtballoon_restore,
+	.thaw =		virtballoon_thaw,
+#endif
 };
 
 static int __init init(void)
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 7317dc2ec42..01d6dc250d5 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -310,8 +310,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 			vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 
 	/* Create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN,
-				 vdev, info->queue, vm_notify, callback, name);
+	vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+				 true, info->queue, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto error_new_virtqueue;
@@ -361,7 +361,12 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
+static const char *vm_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 
+	return vm_dev->pdev->name;
+}
 
 static struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
@@ -373,6 +378,7 @@ static struct virtio_config_ops virtio_mmio_config_ops = {
 	.del_vqs	= vm_del_vqs,
 	.get_features	= vm_get_features,
 	.finalize_features = vm_finalize_features,
+	.bus_name	= vm_bus_name,
 };
 
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 03d1984bd36..635e1efb379 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -55,6 +55,10 @@ struct virtio_pci_device
 	unsigned msix_vectors;
 	/* Vectors allocated, excluding per-vq vectors if any */
 	unsigned msix_used_vectors;
+
+	/* Status saved during hibernate/restore */
+	u8 saved_status;
+
 	/* Whether we have vector per vq */
 	bool per_vq_vectors;
 };
@@ -414,8 +418,8 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
 		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
 	/* create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN,
-				 vdev, info->queue, vp_notify, callback, name);
+	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
+				 true, info->queue, vp_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto out_activate_queue;
@@ -598,6 +602,13 @@ static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 				  false, false);
 }
 
+static const char *vp_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return pci_name(vp_dev->pci_dev);
+}
+
 static struct virtio_config_ops virtio_pci_config_ops = {
 	.get		= vp_get,
 	.set		= vp_set,
@@ -608,6 +619,7 @@ static struct virtio_config_ops virtio_pci_config_ops = {
 	.del_vqs	= vp_del_vqs,
 	.get_features	= vp_get_features,
 	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
 };
 
 static void virtio_pci_release_dev(struct device *_d)
@@ -708,19 +720,114 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
 }
 
 #ifdef CONFIG_PM
-static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state)
+static int virtio_pci_suspend(struct device *dev)
 {
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
 	pci_save_state(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D3hot);
 	return 0;
 }
 
-static int virtio_pci_resume(struct pci_dev *pci_dev)
+static int virtio_pci_resume(struct device *dev)
 {
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
 	pci_restore_state(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D0);
 	return 0;
 }
+
+static int virtio_pci_freeze(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = 0;
+	vp_dev->saved_status = vp_get_status(&vp_dev->vdev);
+	if (drv && drv->freeze)
+		ret = drv->freeze(&vp_dev->vdev);
+
+	if (!ret)
+		pci_disable_device(pci_dev);
+	return ret;
+}
+
+static int restore_common(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
+	pci_set_master(pci_dev);
+	vp_finalize_features(&vp_dev->vdev);
+
+	return ret;
+}
+
+static int virtio_pci_thaw(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	ret = restore_common(dev);
+	if (ret)
+		return ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	if (drv && drv->thaw)
+		ret = drv->thaw(&vp_dev->vdev);
+	else if (drv && drv->restore)
+		ret = drv->restore(&vp_dev->vdev);
+
+	/* Finally, tell the device we're all set */
+	if (!ret)
+		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+
+	return ret;
+}
+
+static int virtio_pci_restore(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = restore_common(dev);
+	if (!ret && drv && drv->restore)
+		ret = drv->restore(&vp_dev->vdev);
+
+	/* Finally, tell the device we're all set */
+	if (!ret)
+		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+
+	return ret;
+}
+
+static const struct dev_pm_ops virtio_pci_pm_ops = {
+	.suspend	= virtio_pci_suspend,
+	.resume		= virtio_pci_resume,
+	.freeze		= virtio_pci_freeze,
+	.thaw		= virtio_pci_thaw,
+	.restore	= virtio_pci_restore,
+	.poweroff	= virtio_pci_suspend,
+};
 #endif
 
 static struct pci_driver virtio_pci_driver = {
@@ -729,8 +836,7 @@ static struct pci_driver virtio_pci_driver = {
 	.probe		= virtio_pci_probe,
 	.remove		= __devexit_p(virtio_pci_remove),
 #ifdef CONFIG_PM
-	.suspend	= virtio_pci_suspend,
-	.resume		= virtio_pci_resume,
+	.driver.pm	= &virtio_pci_pm_ops,
 #endif
 };
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index c7a2c208f6e..5aa43c3392a 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -22,23 +22,27 @@
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/hrtimer.h>
 
 /* virtio guest is communicating with a virtual "device" that actually runs on
  * a host processor.  Memory barriers are used to control SMP effects. */
 #ifdef CONFIG_SMP
 /* Where possible, use SMP barriers which are more lightweight than mandatory
  * barriers, because mandatory barriers control MMIO effects on accesses
- * through relaxed memory I/O windows (which virtio does not use). */
-#define virtio_mb() smp_mb()
-#define virtio_rmb() smp_rmb()
-#define virtio_wmb() smp_wmb()
+ * through relaxed memory I/O windows (which virtio-pci does not use). */
+#define virtio_mb(vq) \
+	do { if ((vq)->weak_barriers) smp_mb(); else mb(); } while(0)
+#define virtio_rmb(vq) \
+	do { if ((vq)->weak_barriers) smp_rmb(); else rmb(); } while(0)
+#define virtio_wmb(vq) \
+	do { if ((vq)->weak_barriers) smp_wmb(); else wmb(); } while(0)
 #else
 /* We must force memory ordering even if guest is UP since host could be
  * running on another CPU, but SMP barriers are defined to barrier() in that
  * configuration. So fall back to mandatory barriers instead. */
-#define virtio_mb() mb()
-#define virtio_rmb() rmb()
-#define virtio_wmb() wmb()
+#define virtio_mb(vq) mb()
+#define virtio_rmb(vq) rmb()
+#define virtio_wmb(vq) wmb()
 #endif
 
 #ifdef DEBUG
@@ -77,6 +81,9 @@ struct vring_virtqueue
 	/* Actual memory layout for this queue */
 	struct vring vring;
 
+	/* Can we use weak barriers? */
+	bool weak_barriers;
+
 	/* Other side has made a mess, don't try any more. */
 	bool broken;
 
@@ -102,6 +109,10 @@ struct vring_virtqueue
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
+
+	/* Figure out if their kicks are too delayed. */
+	bool last_add_time_valid;
+	ktime_t last_add_time;
 #endif
 
 	/* Tokens for callbacks. */
@@ -160,12 +171,29 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
-int virtqueue_add_buf_gfp(struct virtqueue *_vq,
-			  struct scatterlist sg[],
-			  unsigned int out,
-			  unsigned int in,
-			  void *data,
-			  gfp_t gfp)
+/**
+ * virtqueue_add_buf - expose buffer to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: the description of the buffer(s).
+ * @out_num: the number of sg readable by other side
+ * @in_num: the number of sg which are writable (after readable ones)
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns remaining capacity of queue or a negative error
+ * (ie. ENOSPC).  Note that it only really makes sense to treat all
+ * positive return values as "available": indirect buffers mean that
+ * we can put an entire sg[] array inside a single queue entry.
+ */
+int virtqueue_add_buf(struct virtqueue *_vq,
+		      struct scatterlist sg[],
+		      unsigned int out,
+		      unsigned int in,
+		      void *data,
+		      gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	unsigned int i, avail, uninitialized_var(prev);
@@ -175,6 +203,19 @@ int virtqueue_add_buf_gfp(struct virtqueue *_vq,
 
 	BUG_ON(data == NULL);
 
+#ifdef DEBUG
+	{
+		ktime_t now = ktime_get();
+
+		/* No kick or get, with .1 second between?  Warn. */
+		if (vq->last_add_time_valid)
+			WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
+					    > 100);
+		vq->last_add_time = now;
+		vq->last_add_time_valid = true;
+	}
+#endif
+
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
 	if (vq->indirect && (out + in) > 1 && vq->num_free) {
@@ -227,40 +268,102 @@ add_head:
 	vq->data[head] = data;
 
 	/* Put entry in available array (but don't update avail->idx until they
-	 * do sync).  FIXME: avoid modulus here? */
-	avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num;
+	 * do sync). */
+	avail = (vq->vring.avail->idx & (vq->vring.num-1));
 	vq->vring.avail->ring[avail] = head;
 
+	/* Descriptors and available array need to be set before we expose the
+	 * new available array entries. */
+	virtio_wmb(vq);
+	vq->vring.avail->idx++;
+	vq->num_added++;
+
+	/* This is very unlikely, but theoretically possible.  Kick
+	 * just in case. */
+	if (unlikely(vq->num_added == (1 << 16) - 1))
+		virtqueue_kick(_vq);
+
 	pr_debug("Added buffer head %i to %p\n", head, vq);
 	END_USE(vq);
 
 	return vq->num_free;
 }
-EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp);
+EXPORT_SYMBOL_GPL(virtqueue_add_buf);
 
-void virtqueue_kick(struct virtqueue *_vq)
+/**
+ * virtqueue_kick_prepare - first half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * Instead of virtqueue_kick(), you can do:
+ *	if (virtqueue_kick_prepare(vq))
+ *		virtqueue_notify(vq);
+ *
+ * This is sometimes useful because the virtqueue_kick_prepare() needs
+ * to be serialized, but the actual virtqueue_notify() call does not.
+ */
+bool virtqueue_kick_prepare(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	u16 new, old;
+	bool needs_kick;
+
 	START_USE(vq);
-	/* Descriptors and available array need to be set before we expose the
-	 * new available array entries. */
-	virtio_wmb();
+	/* We need to expose available array entries before checking avail
+	 * event. */
+	virtio_mb(vq);
 
-	old = vq->vring.avail->idx;
-	new = vq->vring.avail->idx = old + vq->num_added;
+	old = vq->vring.avail->idx - vq->num_added;
+	new = vq->vring.avail->idx;
 	vq->num_added = 0;
 
-	/* Need to update avail index before checking if we should notify */
-	virtio_mb();
-
-	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);
+#ifdef DEBUG
+	if (vq->last_add_time_valid) {
+		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
+					      vq->last_add_time)) > 100);
+	}
+	vq->last_add_time_valid = false;
+#endif
 
+	if (vq->event) {
+		needs_kick = vring_need_event(vring_avail_event(&vq->vring),
+					      new, old);
+	} else {
+		needs_kick = !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY);
+	}
 	END_USE(vq);
+	return needs_kick;
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
+
+/**
+ * virtqueue_notify - second half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * This does not need to be serialized.
+ */
+void virtqueue_notify(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	/* Prod other side to tell it about changes. */
+	vq->notify(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_notify);
+
+/**
+ * virtqueue_kick - update after add_buf
+ * @vq: the struct virtqueue
+ *
+ * After one or more virtqueue_add_buf calls, invoke this to kick
+ * the other side.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+void virtqueue_kick(struct virtqueue *vq)
+{
+	if (virtqueue_kick_prepare(vq))
+		virtqueue_notify(vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
@@ -294,11 +397,28 @@ static inline bool more_used(const struct vring_virtqueue *vq)
 	return vq->last_used_idx != vq->vring.used->idx;
 }
 
+/**
+ * virtqueue_get_buf - get the next used buffer
+ * @vq: the struct virtqueue we're talking about.
+ * @len: the length written into the buffer
+ *
+ * If the driver wrote data into the buffer, @len will be set to the
+ * amount written.  This means you don't need to clear the buffer
+ * beforehand to ensure there's no data leakage in the case of short
+ * writes.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns NULL if there are no used buffers, or the "data" token
+ * handed to virtqueue_add_buf().
+ */
 void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	void *ret;
 	unsigned int i;
+	u16 last_used;
 
 	START_USE(vq);
 
@@ -314,10 +434,11 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	}
 
 	/* Only get used array entries after they have been exposed by host. */
-	virtio_rmb();
+	virtio_rmb(vq);
 
-	i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
-	*len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
+	last_used = (vq->last_used_idx & (vq->vring.num - 1));
+	i = vq->vring.used->ring[last_used].id;
+	*len = vq->vring.used->ring[last_used].len;
 
 	if (unlikely(i >= vq->vring.num)) {
 		BAD_RING(vq, "id %u out of range\n", i);
@@ -337,14 +458,27 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	 * 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();
+		virtio_mb(vq);
 	}
 
+#ifdef DEBUG
+	vq->last_add_time_valid = false;
+#endif
+
 	END_USE(vq);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_buf);
 
+/**
+ * virtqueue_disable_cb - disable callbacks
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Note that this is not necessarily synchronous, hence unreliable and only
+ * useful as an optimization.
+ *
+ * Unlike other operations, this need not be serialized.
+ */
 void virtqueue_disable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -353,6 +487,17 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
+/**
+ * virtqueue_enable_cb - restart callbacks after disable_cb.
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * 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.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
 bool virtqueue_enable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -366,7 +511,7 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 	 * 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();
+	virtio_mb(vq);
 	if (unlikely(more_used(vq))) {
 		END_USE(vq);
 		return false;
@@ -377,6 +522,19 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 
+/**
+ * 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.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
 bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -393,7 +551,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	/* 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();
+	virtio_mb(vq);
 	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
 		END_USE(vq);
 		return false;
@@ -404,6 +562,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
+/**
+ * virtqueue_detach_unused_buf - detach first unused buffer
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Returns NULL or the "data" token handed to virtqueue_add_buf().
+ * This is not valid on an active queue; it is useful only for device
+ * shutdown.
+ */
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -453,6 +619,7 @@ EXPORT_SYMBOL_GPL(vring_interrupt);
 struct virtqueue *vring_new_virtqueue(unsigned int num,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
+				      bool weak_barriers,
 				      void *pages,
 				      void (*notify)(struct virtqueue *),
 				      void (*callback)(struct virtqueue *),
@@ -476,12 +643,14 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
 	vq->notify = notify;
+	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
+	vq->last_add_time_valid = false;
 #endif
 
 	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
@@ -530,7 +699,13 @@ void vring_transport_features(struct virtio_device *vdev)
 }
 EXPORT_SYMBOL_GPL(vring_transport_features);
 
-/* return the size of the vring within the virtqueue */
+/**
+ * virtqueue_get_vring_size - return the size of the virtqueue's vring
+ * @vq: the struct virtqueue containing the vring of interest.
+ *
+ * Returns the size of the vring.  This is mainly used for boasting to
+ * userspace.  Unlike other operations, this need not be serialized.
+ */
 unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
 {