vhost: cache used event for better performance

When event index was enabled, we need to fetch used event from
userspace memory each time. This userspace fetch (with memory
barrier) could be saved sometime when 1) caching used event and 2)
if used event is ahead of new and old to new updating does not cross
it, we're sure there's no need to notify guest.

This will be useful for heavy tx load e.g guest pktgen test with Linux
driver shows ~3.5% improvement.

Signed-off-by: Jason Wang <[e-mail]>
Signed-off-by: Michael S. Tsirkin <[e-mail]>

drivers/vhost/vhost.c

···
 	vq->avail = NULL;
 	vq->used = NULL;
 	vq->last_avail_idx = 0;
+	vq->last_used_event = 0;
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
 	vq->signalled_used = 0;
···
 			r = -EINVAL;
 			break;
 		}
-		vq->last_avail_idx = s.num;
+		vq->last_avail_idx = vq->last_used_event = s.num;
 		/* Forget the cached index value. */
 		vq->avail_idx = vq->last_avail_idx;
 		break;
···
 	__u16 old, new;
 	__virtio16 event;
 	bool v;
-	/* Flush out used index updates. This is paired
-	 * with the barrier that the Guest executes when enabling
-	 * interrupts. */
-	smp_mb();
 
 	if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) &&
 	    unlikely(vq->avail_idx == vq->last_avail_idx))
···
 
 	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		__virtio16 flags;
+		/* Flush out used index updates. This is paired
+		 * with the barrier that the Guest executes when enabling
+		 * interrupts. */
+		smp_mb();
 		if (vhost_get_user(vq, flags, &vq->avail->flags)) {
 			vq_err(vq, "Failed to get flags");
 			return true;
···
 	if (unlikely(!v))
 		return true;
 
+	/* We're sure if the following conditions are met, there's no
+	 * need to notify guest:
+	 * 1) cached used event is ahead of new
+	 * 2) old to new updating does not cross cached used event. */
+	if (vring_need_event(vq->last_used_event, new + vq->num, new) &&
+	    !vring_need_event(vq->last_used_event, new, old))
+		return false;
+
+	/* Flush out used index updates. This is paired
+	 * with the barrier that the Guest executes when enabling
+	 * interrupts. */
+	smp_mb();
+
 	if (vhost_get_user(vq, event, vhost_used_event(vq))) {
 		vq_err(vq, "Failed to get used event idx");
 		return true;
 	}
-	return vring_need_event(vhost16_to_cpu(vq, event), new, old);
+	vq->last_used_event = vhost16_to_cpu(vq, event);
+
+	return vring_need_event(vq->last_used_event, new, old);
 }
 
 /* This actually signals the guest, using eventfd. */

drivers/vhost/vhost.h

···
 	/* Last index we used. */
 	u16 last_used_idx;
 
+	/* Last used evet we've seen */
+	u16 last_used_event;
+
 	/* Used flags */
 	u16 used_flags;