vhost: support virtqueue interrupt/notification suppression

The driver can suppress interrupt when VIRTIO_F_EVENT_IDX feature bit is
negotiated. The driver set vring flags to 0, and MAY use used_event in
available ring to advise device interrupt util reach an index specified
by used_event. The device ignore the lower bit of vring flags, and send
an interrupt when index reach used_event.

The device can suppress notification in a manner analogous to the ways
driver suppress interrupt. The device manipulates flags or avail_event in
the used ring in the same way the driver manipulates flags or used_event in
available ring.

Signed-off-by: Junjie Chen <junjie.j.chen@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Tested-by: Lei Yao <lei.a.yao@intel.com>
Acked-by: Yuanhan Liu <yliu@fridaylinux.org>

lib/librte_vhost/vhost.c

@@ -509,7 +509,7 @@ rte_vhost_vring_call(int vid, uint16_t vring_idx)
 	if (!vq)
 		return -1;
 
-	vhost_vring_call(vq);
+	vhost_vring_call(dev, vq);
 	return 0;
 }
 

lib/librte_vhost/vhost.h

@@ -74,6 +74,8 @@ struct vhost_virtqueue {
 
 	uint16_t		last_avail_idx;
 	uint16_t		last_used_idx;
+	/* Last used index we notify to front end. */
+	uint16_t		signalled_used;
 #define VIRTIO_INVALID_EVENTFD		(-1)
 #define VIRTIO_UNINITIALIZED_EVENTFD	(-2)
 
@@ -185,6 +187,7 @@ struct vhost_msg {
 				(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
 				(1ULL << VIRTIO_NET_F_GUEST_UFO) | \
 				(1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \
+				(1ULL << VIRTIO_RING_F_EVENT_IDX) | \
 				(1ULL << VIRTIO_NET_F_MTU) | \
 				(1ULL << VIRTIO_F_IOMMU_PLATFORM))
 
@@ -370,16 +373,47 @@ vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return __vhost_iova_to_vva(dev, vq, iova, size, perm);
 }
 
+#define vhost_used_event(vr) \
+	(*(volatile uint16_t*)&(vr)->avail->ring[(vr)->size])
+
+/*
+ * The following is used with VIRTIO_RING_F_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 __rte_always_inline int
+vhost_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old)
+{
+	return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old);
+}
+
 static __rte_always_inline void
-vhost_vring_call(struct vhost_virtqueue *vq)
+vhost_vring_call(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
 	/* Flush used->idx update before we read avail->flags. */
 	rte_mb();
 
-	/* Kick the guest if necessary. */
-	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
-			&& (vq->callfd >= 0))
-		eventfd_write(vq->callfd, (eventfd_t)1);
+	/* Don't kick guest if we don't reach index specified by guest. */
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX)) {
+		uint16_t old = vq->signalled_used;
+		uint16_t new = vq->last_used_idx;
+
+		LOG_DEBUG(VHOST_DATA, "%s: used_event_idx=%d, old=%d, new=%d\n",
+			__func__,
+			vhost_used_event(vq),
+			old, new);
+		if (vhost_need_event(vhost_used_event(vq), new, old)
+			&& (vq->callfd >= 0)) {
+			vq->signalled_used = vq->last_used_idx;
+			eventfd_write(vq->callfd, (eventfd_t) 1);
+		}
+	} else {
+		/* Kick the guest if necessary. */
+		if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
+				&& (vq->callfd >= 0))
+			eventfd_write(vq->callfd, (eventfd_t)1);
+	}
 }
 
 #endif /* _VHOST_NET_CDEV_H_ */

lib/librte_vhost/virtio_net.c

@@ -384,7 +384,7 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
 		offsetof(struct vring_used, idx),
 		sizeof(vq->used->idx));
 
-	vhost_vring_call(vq);
+	vhost_vring_call(dev, vq);
 out:
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_unlock(vq);
@@ -671,7 +671,7 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
 
 	if (likely(vq->shadow_used_idx)) {
 		flush_shadow_used_ring(dev, vq);
-		vhost_vring_call(vq);
+		vhost_vring_call(dev, vq);
 	}
 
 out:
@@ -1075,7 +1075,7 @@ update_used_idx(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	vq->used->idx += count;
 	vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
 			sizeof(vq->used->idx));
-	vhost_vring_call(vq);
+	vhost_vring_call(dev, vq);
 }
 
 static __rte_always_inline struct zcopy_mbuf *