net-next-v3/drivers/vhost/net.c
@@ -130,9 +130,8 @@ static void handle_tx(struct vhost_net *
hdr_size = vq->hdr_size;
for (;;) {
- head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
- ARRAY_SIZE(vq->iov),
- &out, &in,
+ head = vhost_get_desc(&net->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov), &out, &in,
NULL, NULL);
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
@@ -167,8 +166,15 @@ static void handle_tx(struct vhost_net *
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
- vhost_discard_vq_desc(vq);
- tx_poll_start(net, sock);
+ if (err == -EAGAIN) {
+ vhost_discard_desc(vq, 1);
+ tx_poll_start(net, sock);
+ } else {
+ vq_err(vq, "sendmsg: errno %d\n", -err);
+ /* drop packet; do not discard/resend */
+ vhost_add_used_and_signal(&net->dev, vq, head,
+ 0);
+ }
break;
}
if (err != len)
@@ -186,12 +192,25 @@ static void handle_tx(struct vhost_net *
unuse_mm(net->dev.mm);
}
+static int vhost_head_len(struct sock *sk)
+{
+ struct sk_buff *head;
+ int len = 0;
+
+ lock_sock(sk);
+ head = skb_peek(&sk->sk_receive_queue);
+ if (head)
+ len = head->len;
+ release_sock(sk);
+ return len;
+}
+
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
- unsigned head, out, in, log, s;
+ unsigned in, log, s;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
@@ -202,13 +221,14 @@ static void handle_rx(struct vhost_net *
.msg_flags = MSG_DONTWAIT,
};
- struct virtio_net_hdr hdr = {
- .flags = 0,
- .gso_type = VIRTIO_NET_HDR_GSO_NONE
+ struct virtio_net_hdr_mrg_rxbuf hdr = {
+ .hdr.flags = 0,
+ .hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
+ int retries = 0;
size_t len, total_len = 0;
- int err;
+ int err, headcount, datalen;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
@@ -222,31 +242,25 @@ static void handle_rx(struct vhost_net *
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
- for (;;) {
- head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
- ARRAY_SIZE(vq->iov),
- &out, &in,
- vq_log, &log);
+ while ((datalen = vhost_head_len(sock->sk))) {
+ headcount = vhost_get_desc_n(vq, vq->heads, datalen, &in,
+ vq_log, &log);
/* OK, now we need to know about added descriptors. */
- if (head == vq->num) {
- if (unlikely(vhost_enable_notify(vq))) {
+ if (!headcount) {
+ if (retries == 0 && unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
+ retries++;
continue;
}
+ retries = 0;
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
- if (out) {
- vq_err(vq, "Unexpected descriptor format for RX: "
- "out %d, int %d\n",
- out, in);
- break;
- }
- /* Skip header. TODO: support TSO/mergeable rx buffers. */
+ /* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
msg.msg_iovlen = in;
len = iov_length(vq->iov, in);
@@ -261,14 +275,33 @@ static void handle_rx(struct vhost_net *
len, MSG_DONTWAIT | MSG_TRUNC);
/* TODO: Check specific error and bomb out unless EAGAIN? */
if (err < 0) {
- vhost_discard_vq_desc(vq);
+ vhost_discard_desc(vq, headcount);
break;
}
/* TODO: Should check and handle checksum. */
+ if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF)) {
+ struct virtio_net_hdr_mrg_rxbuf *vhdr =
+ (struct virtio_net_hdr_mrg_rxbuf *)
+ vq->iov[0].iov_base;
+ /* add num_buffers */
+ if (vhost_has_feature(&net->dev,
+ VHOST_NET_F_VIRTIO_NET_HDR))
+ hdr.num_buffers = headcount;
+ else if (vq->iov[0].iov_len < sizeof(*vhdr)) {
+ vq_err(vq, "tiny buffers < %d unsupported",
+ vq->iov[0].iov_len);
+ vhost_discard_desc(vq, headcount);
+ break;
+ } else if (put_user(headcount, &vhdr->num_buffers)) {
+ vq_err(vq, "Failed num_buffers write");
+ vhost_discard_desc(vq, headcount);
+ break;
+ }
+ }
if (err > len) {
pr_err("Discarded truncated rx packet: "
" len %d > %zd\n", err, len);
- vhost_discard_vq_desc(vq);
+ vhost_discard_desc(vq, headcount);
continue;
}
len = err;
@@ -279,7 +312,7 @@ static void handle_rx(struct vhost_net *
break;
}
len += hdr_size;
- vhost_add_used_and_signal(&net->dev, vq, head, len);
+ vhost_add_used_and_signal_n(&net->dev, vq, vq->heads, headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, len);
total_len += len;
@@ -560,9 +593,14 @@ done:
static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
- size_t hdr_size = features & (1 << VHOST_NET_F_VIRTIO_NET_HDR) ?
- sizeof(struct virtio_net_hdr) : 0;
+ size_t hdr_size = 0;
int i;
+
+ if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
+ hdr_size = sizeof(struct virtio_net_hdr);
+ if (features & (1 << VIRTIO_NET_F_MRG_RXBUF))
+ hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ }
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {