[PATCH net v5 2/2] vhost_net: fix tx queue stuck when sendmsg fails

[wangyunjian]

From: Yunjian Wang <wangyunj...@huawei.com>

Currently the driver doesn't drop a packet which can't be sent by tun
(e.g bad packet). In this case, the driver will always process the
same packet lead to the tx queue stuck.

To fix this issue:
1. in the case of persistent failure (e.g bad packet), the driver
   can skip this descriptor by ignoring the error.
2. in the case of transient failure (e.g -ENOBUFS, -EAGAIN and -ENOMEM),
   the driver schedules the worker to try again.

Fixes: 3a4d5c94e959 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Yunjian Wang <wangyunj...@huawei.com>
Acked-by: Willem de Bruijn <will...@google.com>
---
 drivers/vhost/net.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c8784dfafdd7..01558fb2c552 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -827,14 +827,13 @@ static void handle_tx_copy(struct vhost_net *net, struct 
socket *sock)
                                msg.msg_flags &= ~MSG_MORE;
                }
 
-               /* TODO: Check specific error and bomb out unless ENOBUFS? */
                err = sock->ops->sendmsg(sock, &msg, len);
-               if (unlikely(err < 0)) {
+               if (unlikely(err == -EAGAIN || err == -ENOMEM || err == 
-ENOBUFS)) {
                        vhost_discard_vq_desc(vq, 1);
                        vhost_net_enable_vq(net, vq);
                        break;
                }
-               if (err != len)
+               if (err >= 0 && err != len)
                        pr_debug("Truncated TX packet: len %d != %zd\n",
                                 err, len);
 done:
@@ -922,7 +921,6 @@ static void handle_tx_zerocopy(struct vhost_net *net, 
struct socket *sock)
                        msg.msg_flags &= ~MSG_MORE;
                }
 
-               /* TODO: Check specific error and bomb out unless ENOBUFS? */
                err = sock->ops->sendmsg(sock, &msg, len);
                if (unlikely(err < 0)) {
                        if (zcopy_used) {
@@ -931,11 +929,13 @@ static void handle_tx_zerocopy(struct vhost_net *net, 
struct socket *sock)
                                nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
                                        % UIO_MAXIOV;
                        }
-                       vhost_discard_vq_desc(vq, 1);
-                       vhost_net_enable_vq(net, vq);
-                       break;
+                       if (err == -EAGAIN || err == -ENOMEM || err == 
-ENOBUFS) {
+                               vhost_discard_vq_desc(vq, 1);
+                               vhost_net_enable_vq(net, vq);
+                               break;
+                       }
                }
-               if (err != len)
+               if (err >= 0 && err != len)
                        pr_debug("Truncated TX packet: "
                                 " len %d != %zd\n", err, len);
                if (!zcopy_used)
-- 
2.23.0