1 files changed, 84 insertions, 47 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index bfb774c273ea..35ded4330431 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -74,7 +74,8 @@ static const u64 vhost_net_features[VIRTIO_FEATURES_DWORDS] = {
 	(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 	(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
 	(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
-	(1ULL << VIRTIO_F_RING_RESET),
+	(1ULL << VIRTIO_F_RING_RESET) |
+	(1ULL << VIRTIO_F_IN_ORDER),
 	VIRTIO_BIT(VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO) |
 	VIRTIO_BIT(VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO),
 };
@@ -98,6 +99,7 @@ struct vhost_net_ubuf_ref {
 	atomic_t refcount;
 	wait_queue_head_t wait;
 	struct vhost_virtqueue *vq;
+	struct rcu_head rcu;
 };
 
 #define VHOST_NET_BATCH 64
@@ -249,9 +251,13 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 
 static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
 {
-	int r = atomic_sub_return(1, &ubufs->refcount);
+	int r;
+
+	rcu_read_lock();
+	r = atomic_sub_return(1, &ubufs->refcount);
 	if (unlikely(!r))
 		wake_up(&ubufs->wait);
+	rcu_read_unlock();
 	return r;
 }
 
@@ -264,7 +270,7 @@ static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
 static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
 {
 	vhost_net_ubuf_put_and_wait(ubufs);
-	kfree(ubufs);
+	kfree_rcu(ubufs, rcu);
 }
 
 static void vhost_net_clear_ubuf_info(struct vhost_net *n)
@@ -376,7 +382,8 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
 	while (j) {
 		add = min(UIO_MAXIOV - nvq->done_idx, j);
 		vhost_add_used_and_signal_n(vq->dev, vq,
-					    &vq->heads[nvq->done_idx], add);
+					    &vq->heads[nvq->done_idx],
+					    NULL, add);
 		nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV;
 		j -= add;
 	}
@@ -451,7 +458,8 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 	return vhost_poll_start(poll, sock->file);
 }
 
-static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
+static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq,
+				  unsigned int count)
 {
 	struct vhost_virtqueue *vq = &nvq->vq;
 	struct vhost_dev *dev = vq->dev;
@@ -459,7 +467,8 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
 	if (!nvq->done_idx)
 		return;
 
-	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	vhost_add_used_and_signal_n(dev, vq, vq->heads,
+				    vq->nheads, count);
 	nvq->done_idx = 0;
 }
 
@@ -468,6 +477,8 @@ static void vhost_tx_batch(struct vhost_net *net,
 			   struct socket *sock,
 			   struct msghdr *msghdr)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 	struct tun_msg_ctl ctl = {
 		.type = TUN_MSG_PTR,
 		.num = nvq->batched_xdp,
@@ -475,6 +486,11 @@ static void vhost_tx_batch(struct vhost_net *net,
 	};
 	int i, err;
 
+	if (in_order) {
+		vq->heads[0].len = 0;
+		vq->nheads[0] = nvq->done_idx;
+	}
+
 	if (nvq->batched_xdp == 0)
 		goto signal_used;
 
@@ -496,7 +512,7 @@ static void vhost_tx_batch(struct vhost_net *net,
 	}
 
 signal_used:
-	vhost_net_signal_used(nvq);
+	vhost_net_signal_used(nvq, in_order ? 1 : nvq->done_idx);
 	nvq->batched_xdp = 0;
 }
 
@@ -749,10 +765,11 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 	int err;
 	int sent_pkts = 0;
 	bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX);
-	bool busyloop_intr;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 
 	do {
-		busyloop_intr = false;
+		bool busyloop_intr = false;
+
 		if (nvq->done_idx == VHOST_NET_BATCH)
 			vhost_tx_batch(net, nvq, sock, &msg);
 
@@ -763,10 +780,18 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			/* Kicks are disabled at this point, break loop and
-			 * process any remaining batched packets. Queue will
-			 * be re-enabled afterwards.
+			/* Flush batched packets to handle pending RX
+			 * work (if busyloop_intr is set) and to avoid
+			 * unnecessary virtqueue kicks.
 			 */
+			vhost_tx_batch(net, nvq, sock, &msg);
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev,
+								vq))) {
+				vhost_disable_notify(&net->dev, vq);
+				continue;
+			}
 			break;
 		}
 
@@ -786,11 +811,13 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 				break;
 			}
 
-			/* We can't build XDP buff, go for single
-			 * packet path but let's flush batched
-			 * packets.
-			 */
-			vhost_tx_batch(net, nvq, sock, &msg);
+			if (nvq->batched_xdp) {
+				/* We can't build XDP buff, go for single
+				 * packet path but let's flush batched
+				 * packets.
+				 */
+				vhost_tx_batch(net, nvq, sock, &msg);
+			}
 			msg.msg_control = NULL;
 		} else {
 			if (tx_can_batch(vq, total_len))
@@ -811,27 +838,16 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 			pr_debug("Truncated TX packet: len %d != %zd\n",
 				 err, len);
 done:
-		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
-		vq->heads[nvq->done_idx].len = 0;
+		if (in_order) {
+			vq->heads[0].id = cpu_to_vhost32(vq, head);
+		} else {
+			vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
+			vq->heads[nvq->done_idx].len = 0;
+		}
 		++nvq->done_idx;
 	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 
-	/* Kicks are still disabled, dispatch any remaining batched msgs. */
 	vhost_tx_batch(net, nvq, sock, &msg);
-
-	if (unlikely(busyloop_intr))
-		/* If interrupted while doing busy polling, requeue the
-		 * handler to be fair handle_rx as well as other tasks
-		 * waiting on cpu.
-		 */
-		vhost_poll_queue(&vq->poll);
-	else
-		/* All of our work has been completed; however, before
-		 * leaving the TX handler, do one last check for work,
-		 * and requeue handler if necessary. If there is no work,
-		 * queue will be reenabled.
-		 */
-		vhost_net_busy_poll_try_queue(net, vq);
 }
 
 static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
@@ -991,7 +1007,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
 }
 
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
-				      bool *busyloop_intr)
+				      bool *busyloop_intr, unsigned int *count)
 {
 	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -1001,7 +1017,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 	if (!len && rvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_net_signal_used(rnvq);
+		vhost_net_signal_used(rnvq, *count);
+		*count = 0;
 		/* Both tx vq and rx socket were polled here */
 		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true);
 
@@ -1013,7 +1030,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 /* This is a multi-buffer version of vhost_get_desc, that works if
  *	vq has read descriptors only.
- * @vq		- the relevant virtqueue
+ * @nvq		- the relevant vhost_net virtqueue
  * @datalen	- data length we'll be reading
  * @iovcount	- returned count of io vectors we fill
  * @log		- vhost log
@@ -1021,14 +1038,17 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
  * @quota       - headcount quota, 1 for big buffer
  *	returns number of buffer heads allocated, negative on error
  */
-static int get_rx_bufs(struct vhost_virtqueue *vq,
+static int get_rx_bufs(struct vhost_net_virtqueue *nvq,
 		       struct vring_used_elem *heads,
+		       u16 *nheads,
 		       int datalen,
 		       unsigned *iovcount,
 		       struct vhost_log *log,
 		       unsigned *log_num,
 		       unsigned int quota)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 	unsigned int out, in;
 	int seg = 0;
 	int headcount = 0;
@@ -1065,14 +1085,16 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			nlogs += *log_num;
 			log += *log_num;
 		}
-		heads[headcount].id = cpu_to_vhost32(vq, d);
 		len = iov_length(vq->iov + seg, in);
-		heads[headcount].len = cpu_to_vhost32(vq, len);
-		datalen -= len;
+		if (!in_order) {
+			heads[headcount].id = cpu_to_vhost32(vq, d);
+			heads[headcount].len = cpu_to_vhost32(vq, len);
+		}
 		++headcount;
+		datalen -= len;
 		seg += in;
 	}
-	heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
+
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
@@ -1082,6 +1104,15 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 		r = UIO_MAXIOV + 1;
 		goto err;
 	}
+
+	if (!in_order)
+		heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
+	else {
+		heads[0].len = cpu_to_vhost32(vq, len + datalen);
+		heads[0].id = cpu_to_vhost32(vq, d);
+		nheads[0] = headcount;
+	}
+
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -1094,6 +1125,8 @@ static void handle_rx(struct vhost_net *net)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
+	unsigned int count = 0;
 	unsigned in, log;
 	struct vhost_log *vq_log;
 	struct msghdr msg = {
@@ -1141,12 +1174,13 @@ static void handle_rx(struct vhost_net *net)
 
 	do {
 		sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
-						      &busyloop_intr);
+						      &busyloop_intr, &count);
 		if (!sock_len)
 			break;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
-		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+		headcount = get_rx_bufs(nvq, vq->heads + count,
+					vq->nheads + count,
 					vhost_len, &in, vq_log, &log,
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
@@ -1222,8 +1256,11 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		}
 		nvq->done_idx += headcount;
-		if (nvq->done_idx > VHOST_NET_BATCH)
-			vhost_net_signal_used(nvq);
+		count += in_order ? 1 : headcount;
+		if (nvq->done_idx > VHOST_NET_BATCH) {
+			vhost_net_signal_used(nvq, count);
+			count = 0;
+		}
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
@@ -1235,7 +1272,7 @@ static void handle_rx(struct vhost_net *net)
 	else if (!sock_len)
 		vhost_net_enable_vq(net, vq);
 out:
-	vhost_net_signal_used(nvq);
+	vhost_net_signal_used(nvq, count);
 	mutex_unlock(&vq->mutex);
 }