[PATCH v2 1/2] virtio_ring: add virtqueue_enable_cb_delayed_max

["Michael S. Tsirkin" <mst@redhat.com>]

virtqueue_enable_cb_delayed places the used event at 3/4 of the
currently queued buffers, so with VIRTIO_RING_F_EVENT_IDX the device
interrupts early and often - this is a good fit for drivers that poll
and process buffers as they trickle in, like virtio net.

Some drivers queue a batch of buffers and then sleep waiting for the
whole batch to complete.  For these, an interrupt before the last
buffer is used is pure waste.

To fix, add virtqueue_enable_cb_delayed_max: same API, but the used
event is placed at the last currently queued buffer, so the device
only notifies us once it has used everything.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---

Notes (changelog):
    changes since v1:
        fix off-by-one: place the used event one entry before the
        last queued buffer.  The device only signals once it passes
        the event, so with the event at the last buffer it never
        fired and callers waiting for the batch to complete hung.

 drivers/virtio/virtio_ring.c | 127 +++++++++++++++++++++++++++++++++++
 include/linux/virtio.h       |   2 +
 2 files changed, 129 insertions(+)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fbca7ce1c6bf..4c0bb860b703 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -180,6 +180,7 @@ struct virtqueue_ops {
 	bool (*kick_prepare)(struct vring_virtqueue *vq);
 	void (*disable_cb)(struct vring_virtqueue *vq);
 	bool (*enable_cb_delayed)(struct vring_virtqueue *vq);
+	bool (*enable_cb_delayed_max)(struct vring_virtqueue *vq);
 	unsigned int (*enable_cb_prepare)(struct vring_virtqueue *vq);
 	bool (*poll)(const struct vring_virtqueue *vq,
 		     unsigned int last_used_idx);
@@ -1122,6 +1123,43 @@ static bool virtqueue_enable_cb_delayed_split(struct vring_virtqueue *vq)
 	return true;
 }
 
+static bool virtqueue_enable_cb_delayed_max_split(struct vring_virtqueue *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 update the event index to keep code simple. */
+	if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+		if (!vq->event)
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(vq->vq.vdev,
+						vq->split.avail_flags_shadow);
+	}
+	/* Point the used event one entry before the last queued buffer:
+	 * the device signals when it passes the event, so this makes it
+	 * notify us exactly once it has used everything. */
+	bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) - 1;
+
+	virtio_store_mb(vq->weak_barriers,
+			&vring_used_event(&vq->split.vring),
+			cpu_to_virtio16(vq->vq.vdev, vq->last_used_idx + bufs));
+
+	if (unlikely((u16)(virtio16_to_cpu(vq->vq.vdev, vq->split.vring.used->idx)
+						- vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
 static void *virtqueue_detach_unused_buf_split(struct vring_virtqueue *vq)
 {
 	unsigned int i;
@@ -2318,6 +2356,68 @@ static bool virtqueue_enable_cb_delayed_packed(struct vring_virtqueue *vq)
 	return true;
 }
 
+static bool virtqueue_enable_cb_delayed_max_packed(struct vring_virtqueue *vq)
+{
+	u16 used_idx, wrap_counter, last_used_idx;
+	u16 bufs;
+
+	START_USE(vq);
+
+	/*
+	 * We optimistically turn back on interrupts, then check if there was
+	 * more to do.
+	 */
+
+	if (vq->event) {
+		/* Point the event one entry before the last queued buffer:
+		 * the device signals when it passes the event, so this
+		 * makes it notify us exactly once it has used everything. */
+		bufs = vq->packed.vring.num - vq->vq.num_free - 1;
+		last_used_idx = READ_ONCE(vq->last_used_idx);
+		wrap_counter = packed_used_wrap_counter(last_used_idx);
+
+		used_idx = packed_last_used(last_used_idx) + bufs;
+		if (used_idx >= vq->packed.vring.num) {
+			used_idx -= vq->packed.vring.num;
+			wrap_counter ^= 1;
+		}
+
+		vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx |
+			(wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR));
+
+		/*
+		 * We need to update event offset and event wrap
+		 * counter first before updating event flags.
+		 */
+		virtio_wmb(vq->weak_barriers);
+	}
+
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = vq->event ?
+				VRING_PACKED_EVENT_FLAG_DESC :
+				VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.vring.driver->flags =
+				cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	/*
+	 * We need to update event suppression structure first
+	 * before re-checking for more used buffers.
+	 */
+	virtio_mb(vq->weak_barriers);
+
+	last_used_idx = READ_ONCE(vq->last_used_idx);
+	wrap_counter = packed_used_wrap_counter(last_used_idx);
+	used_idx = packed_last_used(last_used_idx);
+	if (is_used_desc_packed(vq, used_idx, wrap_counter)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
 static void *virtqueue_detach_unused_buf_packed(struct vring_virtqueue *vq)
 {
 	unsigned int i;
@@ -2640,6 +2740,7 @@ static const struct virtqueue_ops split_ops = {
 	.kick_prepare = virtqueue_kick_prepare_split,
 	.disable_cb = virtqueue_disable_cb_split,
 	.enable_cb_delayed = virtqueue_enable_cb_delayed_split,
+	.enable_cb_delayed_max = virtqueue_enable_cb_delayed_max_split,
 	.enable_cb_prepare = virtqueue_enable_cb_prepare_split,
 	.poll = virtqueue_poll_split,
 	.detach_unused_buf = virtqueue_detach_unused_buf_split,
@@ -2654,6 +2755,7 @@ static const struct virtqueue_ops packed_ops = {
 	.kick_prepare = virtqueue_kick_prepare_packed,
 	.disable_cb = virtqueue_disable_cb_packed,
 	.enable_cb_delayed = virtqueue_enable_cb_delayed_packed,
+	.enable_cb_delayed_max = virtqueue_enable_cb_delayed_max_packed,
 	.enable_cb_prepare = virtqueue_enable_cb_prepare_packed,
 	.poll = virtqueue_poll_packed,
 	.detach_unused_buf = virtqueue_detach_unused_buf_packed,
@@ -2668,6 +2770,7 @@ static const struct virtqueue_ops split_in_order_ops = {
 	.kick_prepare = virtqueue_kick_prepare_split,
 	.disable_cb = virtqueue_disable_cb_split,
 	.enable_cb_delayed = virtqueue_enable_cb_delayed_split,
+	.enable_cb_delayed_max = virtqueue_enable_cb_delayed_max_split,
 	.enable_cb_prepare = virtqueue_enable_cb_prepare_split,
 	.poll = virtqueue_poll_split,
 	.detach_unused_buf = virtqueue_detach_unused_buf_split,
@@ -2682,6 +2785,7 @@ static const struct virtqueue_ops packed_in_order_ops = {
 	.kick_prepare = virtqueue_kick_prepare_packed,
 	.disable_cb = virtqueue_disable_cb_packed,
 	.enable_cb_delayed = virtqueue_enable_cb_delayed_packed,
+	.enable_cb_delayed_max = virtqueue_enable_cb_delayed_max_packed,
 	.enable_cb_prepare = virtqueue_enable_cb_prepare_packed,
 	.poll = virtqueue_poll_packed,
 	.detach_unused_buf = virtqueue_detach_unused_buf_packed,
@@ -3197,6 +3301,29 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
+/**
+ * virtqueue_enable_cb_delayed_max - callback for all queued buffers
+ * @_vq: the struct virtqueue we're talking about.
+ *
+ * Like virtqueue_enable_cb_delayed, but with VIRTIO_RING_F_EVENT_IDX
+ * the used event is placed at the last currently queued buffer, so the
+ * device only notifies us once it has used everything we queued.
+ *
+ * Returns "true" if the callback is armed and we can sleep waiting
+ * for the notification, or "false" if some buffers were already used
+ * and we should poll instead.
+ */
+bool virtqueue_enable_cb_delayed_max(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->event_triggered)
+		data_race(vq->event_triggered = false);
+
+	return VIRTQUEUE_CALL(vq, enable_cb_delayed_max);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed_max);
+
 /**
  * virtqueue_detach_unused_buf - detach first unused buffer
  * @_vq: the struct virtqueue we're talking about.
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 3bbc4cb6a672..214fa36b8eed 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -114,6 +114,8 @@ bool virtqueue_poll(struct virtqueue *vq, unsigned);
 
 bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
 
+bool virtqueue_enable_cb_delayed_max(struct virtqueue *vq);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 unsigned int virtqueue_get_vring_size(const struct virtqueue *vq);
-- 
MST