[net,2/2] vhost_net: fix high cpu load when sendmsg fails

Commit Message

wangyunjian Dec. 15, 2020, 1:48 a.m. UTC

From: Yunjian Wang <[e-mail]>

Currently we break the loop and wake up the vhost_worker when
sendmsg fails. When the worker wakes up again, we'll meet the
same error. This will cause high CPU load. To fix this issue,
we can skip this description by ignoring the error. When we
exceeds sndbuf, the return value of sendmsg is -EAGAIN. In
the case we don't skip the description and don't drop packet.

Signed-off-by: Yunjian Wang <[e-mail]>
---
 drivers/vhost/net.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

Comments

Jason Wang Dec. 15, 2020, 4:09 a.m. UTC | #1

On 2020/12/15 上午9:48, wangyunjian wrote:
> From: Yunjian Wang <[e-mail]>
>
> Currently we break the loop and wake up the vhost_worker when
> sendmsg fails. When the worker wakes up again, we'll meet the
> same error. This will cause high CPU load. To fix this issue,
> we can skip this description by ignoring the error. When we
> exceeds sndbuf, the return value of sendmsg is -EAGAIN. In
> the case we don't skip the description and don't drop packet.
>
> Signed-off-by: Yunjian Wang <[e-mail]>
> ---
>   drivers/vhost/net.c | 21 +++++++++------------
>   1 file changed, 9 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index c8784dfafdd7..f966592d8900 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -827,16 +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)) {
>   			vhost_discard_vq_desc(vq, 1);
>   			vhost_net_enable_vq(net, vq);
>   			break;
> -		}


As I've pointed out in last version. If you don't discard descriptor, 
you probably need to add the head to used ring. Otherwise this 
descriptor will be always inflight that may confuse drivers.


> -		if (err != len)
> -			pr_debug("Truncated TX packet: len %d != %zd\n",
> -				 err, len);
> +		} else if (unlikely(err < 0 || err != len))


It looks to me err != len covers err < 0.

Thanks


> +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err, len);
>   done:
>   		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
>   		vq->heads[nvq->done_idx].len = 0;
> @@ -922,7 +919,6 @@ 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) {
> @@ -931,13 +927,14 @@ 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) {
> +				vhost_discard_vq_desc(vq, 1);
> +				vhost_net_enable_vq(net, vq);
> +				break;
> +			}
>   		}
>   		if (err != len)
> -			pr_debug("Truncated TX packet: "
> -				 " len %d != %zd\n", err, len);
> +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err, len);
>   		if (!zcopy_used)
>   			vhost_add_used_and_signal(&net->dev, vq, head, 0);
>   		else

wangyunjian Dec. 15, 2020, 8:03 a.m. UTC | #2

> -----Original Message-----
> From: Jason Wang [mailto:[e-mail]]
> Sent: Tuesday, December 15, 2020 12:10 PM
> To: wangyunjian <[e-mail]>; [e-mail];
> [e-mail]; [e-mail]
> Cc: [e-mail]; Lilijun (Jerry)
> <[e-mail]>; chenchanghu <[e-mail]>;
> xudingke <[e-mail]>; huangbin (J)
> <[e-mail]>
> Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg fails
> 
> 
> On 2020/12/15 上午9:48, wangyunjian wrote:
> > From: Yunjian Wang <[e-mail]>
> >
> > Currently we break the loop and wake up the vhost_worker when sendmsg
> > fails. When the worker wakes up again, we'll meet the same error. This
> > will cause high CPU load. To fix this issue, we can skip this
> > description by ignoring the error. When we exceeds sndbuf, the return
> > value of sendmsg is -EAGAIN. In the case we don't skip the description
> > and don't drop packet.
> >
> > Signed-off-by: Yunjian Wang <[e-mail]>
> > ---
> >   drivers/vhost/net.c | 21 +++++++++------------
> >   1 file changed, 9 insertions(+), 12 deletions(-)
> >
> > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index
> > c8784dfafdd7..f966592d8900 100644
> > --- a/drivers/vhost/net.c
> > +++ b/drivers/vhost/net.c
> > @@ -827,16 +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)) {
> >   			vhost_discard_vq_desc(vq, 1);
> >   			vhost_net_enable_vq(net, vq);
> >   			break;
> > -		}
> 
> 
> As I've pointed out in last version. If you don't discard descriptor, you probably
> need to add the head to used ring. Otherwise this descriptor will be always
> inflight that may confuse drivers.

Sorry for missing the comment.

After deleting discard descriptor and break, the next processing will be the same
as the normal success of sendmsg(), and vhost_zerocopy_signal_used() or
vhost_add_used_and_signal() method will be called to add the head to used ring.

Thanks
> 
> 
> > -		if (err != len)
> > -			pr_debug("Truncated TX packet: len %d != %zd\n",
> > -				 err, len);
> > +		} else if (unlikely(err < 0 || err != len))
> 
> 
> It looks to me err != len covers err < 0.

OK

> 
> Thanks
> 
> 
> > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err,
> > +len);
> >   done:
> >   		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
> >   		vq->heads[nvq->done_idx].len = 0;
> > @@ -922,7 +919,6 @@ 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) {
> > @@ -931,13 +927,14 @@ 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) {
> > +				vhost_discard_vq_desc(vq, 1);
> > +				vhost_net_enable_vq(net, vq);
> > +				break;
> > +			}
> >   		}
> >   		if (err != len)
> > -			pr_debug("Truncated TX packet: "
> > -				 " len %d != %zd\n", err, len);
> > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err,
> > +len);
> >   		if (!zcopy_used)
> >   			vhost_add_used_and_signal(&net->dev, vq, head, 0);
> >   		else

Jason Wang Dec. 16, 2020, 5:56 a.m. UTC | #3

----- Original Message -----
> 
> 
> > -----Original Message-----
> > From: Jason Wang [mailto:[e-mail]]
> > Sent: Tuesday, December 15, 2020 12:10 PM
> > To: wangyunjian <[e-mail]>; [e-mail];
> > [e-mail]; [e-mail]
> > Cc: [e-mail]; Lilijun (Jerry)
> > <[e-mail]>; chenchanghu <[e-mail]>;
> > xudingke <[e-mail]>; huangbin (J)
> > <[e-mail]>
> > Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg
> > fails
> > 
> > 
> > On 2020/12/15 上午9:48, wangyunjian wrote:
> > > From: Yunjian Wang <[e-mail]>
> > >
> > > Currently we break the loop and wake up the vhost_worker when sendmsg
> > > fails. When the worker wakes up again, we'll meet the same error. This
> > > will cause high CPU load. To fix this issue, we can skip this
> > > description by ignoring the error. When we exceeds sndbuf, the return
> > > value of sendmsg is -EAGAIN. In the case we don't skip the description
> > > and don't drop packet.
> > >
> > > Signed-off-by: Yunjian Wang <[e-mail]>
> > > ---
> > >   drivers/vhost/net.c | 21 +++++++++------------
> > >   1 file changed, 9 insertions(+), 12 deletions(-)
> > >
> > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index
> > > c8784dfafdd7..f966592d8900 100644
> > > --- a/drivers/vhost/net.c
> > > +++ b/drivers/vhost/net.c
> > > @@ -827,16 +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)) {
> > >   			vhost_discard_vq_desc(vq, 1);
> > >   			vhost_net_enable_vq(net, vq);
> > >   			break;
> > > -		}
> > 
> > 
> > As I've pointed out in last version. If you don't discard descriptor, you
> > probably
> > need to add the head to used ring. Otherwise this descriptor will be always
> > inflight that may confuse drivers.
> 
> Sorry for missing the comment.
> 
> After deleting discard descriptor and break, the next processing will be the
> same
> as the normal success of sendmsg(), and vhost_zerocopy_signal_used() or
> vhost_add_used_and_signal() method will be called to add the head to used
> ring.

It's the next head not the one that contains the buggy packet?

Thanks

> 
> Thanks
> > 
> > 
> > > -		if (err != len)
> > > -			pr_debug("Truncated TX packet: len %d != %zd\n",
> > > -				 err, len);
> > > +		} else if (unlikely(err < 0 || err != len))
> > 
> > 
> > It looks to me err != len covers err < 0.
> 
> OK
> 
> > 
> > Thanks
> > 
> > 
> > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err,
> > > +len);
> > >   done:
> > >   		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
> > >   		vq->heads[nvq->done_idx].len = 0;
> > > @@ -922,7 +919,6 @@ 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) {
> > > @@ -931,13 +927,14 @@ 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) {
> > > +				vhost_discard_vq_desc(vq, 1);
> > > +				vhost_net_enable_vq(net, vq);
> > > +				break;
> > > +			}
> > >   		}
> > >   		if (err != len)
> > > -			pr_debug("Truncated TX packet: "
> > > -				 " len %d != %zd\n", err, len);
> > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err,
> > > +len);
> > >   		if (!zcopy_used)
> > >   			vhost_add_used_and_signal(&net->dev, vq, head, 0);
> > >   		else
> 
>

wangyunjian Dec. 16, 2020, 7:43 a.m. UTC | #4

> -----Original Message-----
> From: Jason Wang [mailto:[e-mail]]
> Sent: Wednesday, December 16, 2020 1:57 PM
> To: wangyunjian <[e-mail]>
> Cc: [e-mail]; [e-mail]; willemdebruijn kernel
> <[e-mail]>; [e-mail];
> Lilijun (Jerry) <[e-mail]>; chenchanghu
> <[e-mail]>; xudingke <[e-mail]>; huangbin (J)
> <[e-mail]>
> Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg fails
> 
> 
> 
> ----- Original Message -----
> >
> >
> > > -----Original Message-----
> > > From: Jason Wang [mailto:[e-mail]]
> > > Sent: Tuesday, December 15, 2020 12:10 PM
> > > To: wangyunjian <[e-mail]>; [e-mail];
> > > [e-mail]; [e-mail]
> > > Cc: [e-mail]; Lilijun (Jerry)
> > > <[e-mail]>; chenchanghu <[e-mail]>;
> > > xudingke <[e-mail]>; huangbin (J)
> > > <[e-mail]>
> > > Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg
> > > fails
> > >
> > >
> > > On 2020/12/15 上午9:48, wangyunjian wrote:
> > > > From: Yunjian Wang <[e-mail]>
> > > >
> > > > Currently we break the loop and wake up the vhost_worker when
> sendmsg
> > > > fails. When the worker wakes up again, we'll meet the same error. This
> > > > will cause high CPU load. To fix this issue, we can skip this
> > > > description by ignoring the error. When we exceeds sndbuf, the return
> > > > value of sendmsg is -EAGAIN. In the case we don't skip the description
> > > > and don't drop packet.
> > > >
> > > > Signed-off-by: Yunjian Wang <[e-mail]>
> > > > ---
> > > >   drivers/vhost/net.c | 21 +++++++++------------
> > > >   1 file changed, 9 insertions(+), 12 deletions(-)
> > > >
> > > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index
> > > > c8784dfafdd7..f966592d8900 100644
> > > > --- a/drivers/vhost/net.c
> > > > +++ b/drivers/vhost/net.c
> > > > @@ -827,16 +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)) {
> > > >   			vhost_discard_vq_desc(vq, 1);
> > > >   			vhost_net_enable_vq(net, vq);
> > > >   			break;
> > > > -		}
> > >
> > >
> > > As I've pointed out in last version. If you don't discard descriptor, you
> > > probably
> > > need to add the head to used ring. Otherwise this descriptor will be always
> > > inflight that may confuse drivers.
> >
> > Sorry for missing the comment.
> >
> > After deleting discard descriptor and break, the next processing will be the
> > same
> > as the normal success of sendmsg(), and vhost_zerocopy_signal_used() or
> > vhost_add_used_and_signal() method will be called to add the head to used
> > ring.
> 
> It's the next head not the one that contains the buggy packet?

In the modified code logic, the head added to used ring is exectly the
one that contains the buggy packet.

Thanks

> 
> Thanks
> 
> >
> > Thanks
> > >
> > >
> > > > -		if (err != len)
> > > > -			pr_debug("Truncated TX packet: len %d != %zd\n",
> > > > -				 err, len);
> > > > +		} else if (unlikely(err < 0 || err != len))
> > >
> > >
> > > It looks to me err != len covers err < 0.
> >
> > OK
> >
> > >
> > > Thanks
> > >
> > >
> > > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n",
> err,
> > > > +len);
> > > >   done:
> > > >   		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
> > > >   		vq->heads[nvq->done_idx].len = 0;
> > > > @@ -922,7 +919,6 @@ 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) {
> > > > @@ -931,13 +927,14 @@ 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) {
> > > > +				vhost_discard_vq_desc(vq, 1);
> > > > +				vhost_net_enable_vq(net, vq);
> > > > +				break;
> > > > +			}
> > > >   		}
> > > >   		if (err != len)
> > > > -			pr_debug("Truncated TX packet: "
> > > > -				 " len %d != %zd\n", err, len);
> > > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n",
> err,
> > > > +len);
> > > >   		if (!zcopy_used)
> > > >   			vhost_add_used_and_signal(&net->dev, vq, head, 0);
> > > >   		else
> >
> >

Jason Wang Dec. 16, 2020, 7:47 a.m. UTC | #5

----- Original Message -----
> > -----Original Message-----
> > From: Jason Wang [mailto:[e-mail]]
> > Sent: Wednesday, December 16, 2020 1:57 PM
> > To: wangyunjian <[e-mail]>
> > Cc: [e-mail]; [e-mail]; willemdebruijn kernel
> > <[e-mail]>;
> > [e-mail];
> > Lilijun (Jerry) <[e-mail]>; chenchanghu
> > <[e-mail]>; xudingke <[e-mail]>; huangbin (J)
> > <[e-mail]>
> > Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg
> > fails
> > 
> > 
> > 
> > ----- Original Message -----
> > >
> > >
> > > > -----Original Message-----
> > > > From: Jason Wang [mailto:[e-mail]]
> > > > Sent: Tuesday, December 15, 2020 12:10 PM
> > > > To: wangyunjian <[e-mail]>; [e-mail];
> > > > [e-mail]; [e-mail]
> > > > Cc: [e-mail]; Lilijun (Jerry)
> > > > <[e-mail]>; chenchanghu <[e-mail]>;
> > > > xudingke <[e-mail]>; huangbin (J)
> > > > <[e-mail]>
> > > > Subject: Re: [PATCH net 2/2] vhost_net: fix high cpu load when sendmsg
> > > > fails
> > > >
> > > >
> > > > On 2020/12/15 上午9:48, wangyunjian wrote:
> > > > > From: Yunjian Wang <[e-mail]>
> > > > >
> > > > > Currently we break the loop and wake up the vhost_worker when
> > sendmsg
> > > > > fails. When the worker wakes up again, we'll meet the same error.
> > > > > This
> > > > > will cause high CPU load. To fix this issue, we can skip this
> > > > > description by ignoring the error. When we exceeds sndbuf, the return
> > > > > value of sendmsg is -EAGAIN. In the case we don't skip the
> > > > > description
> > > > > and don't drop packet.
> > > > >
> > > > > Signed-off-by: Yunjian Wang <[e-mail]>
> > > > > ---
> > > > >   drivers/vhost/net.c | 21 +++++++++------------
> > > > >   1 file changed, 9 insertions(+), 12 deletions(-)
> > > > >
> > > > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index
> > > > > c8784dfafdd7..f966592d8900 100644
> > > > > --- a/drivers/vhost/net.c
> > > > > +++ b/drivers/vhost/net.c
> > > > > @@ -827,16 +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)) {
> > > > >   			vhost_discard_vq_desc(vq, 1);
> > > > >   			vhost_net_enable_vq(net, vq);
> > > > >   			break;
> > > > > -		}
> > > >
> > > >
> > > > As I've pointed out in last version. If you don't discard descriptor,
> > > > you
> > > > probably
> > > > need to add the head to used ring. Otherwise this descriptor will be
> > > > always
> > > > inflight that may confuse drivers.
> > >
> > > Sorry for missing the comment.
> > >
> > > After deleting discard descriptor and break, the next processing will be
> > > the
> > > same
> > > as the normal success of sendmsg(), and vhost_zerocopy_signal_used() or
> > > vhost_add_used_and_signal() method will be called to add the head to used
> > > ring.
> > 
> > It's the next head not the one that contains the buggy packet?
> 
> In the modified code logic, the head added to used ring is exectly the
> one that contains the buggy packet.

-ENOTEA :( You're right, I misread the code.

Thanks

> 
> Thanks
> 
> > 
> > Thanks
> > 
> > >
> > > Thanks
> > > >
> > > >
> > > > > -		if (err != len)
> > > > > -			pr_debug("Truncated TX packet: len %d != %zd\n",
> > > > > -				 err, len);
> > > > > +		} else if (unlikely(err < 0 || err != len))
> > > >
> > > >
> > > > It looks to me err != len covers err < 0.
> > >
> > > OK
> > >
> > > >
> > > > Thanks
> > > >
> > > >
> > > > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n",
> > err,
> > > > > +len);
> > > > >   done:
> > > > >   		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
> > > > >   		vq->heads[nvq->done_idx].len = 0;
> > > > > @@ -922,7 +919,6 @@ 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) {
> > > > > @@ -931,13 +927,14 @@ 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) {
> > > > > +				vhost_discard_vq_desc(vq, 1);
> > > > > +				vhost_net_enable_vq(net, vq);
> > > > > +				break;
> > > > > +			}
> > > > >   		}
> > > > >   		if (err != len)
> > > > > -			pr_debug("Truncated TX packet: "
> > > > > -				 " len %d != %zd\n", err, len);
> > > > > +			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n",
> > err,
> > > > > +len);
> > > > >   		if (!zcopy_used)
> > > > >   			vhost_add_used_and_signal(&net->dev, vq, head, 0);
> > > > >   		else
> > >
> > >
> 
>

Patch

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c8784dfafdd7..f966592d8900 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -827,16 +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)) {
 			vhost_discard_vq_desc(vq, 1);
 			vhost_net_enable_vq(net, vq);
 			break;
-		}
-		if (err != len)
-			pr_debug("Truncated TX packet: len %d != %zd\n",
-				 err, len);
+		} else if (unlikely(err < 0 || err != len))
+			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err, len);
 done:
 		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
 		vq->heads[nvq->done_idx].len = 0;
@@ -922,7 +919,6 @@  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) {
@@ -931,13 +927,14 @@  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) {
+				vhost_discard_vq_desc(vq, 1);
+				vhost_net_enable_vq(net, vq);
+				break;
+			}
 		}
 		if (err != len)
-			pr_debug("Truncated TX packet: "
-				 " len %d != %zd\n", err, len);
+			vq_err(vq, "Fail to sending packets err : %d, len : %zd\n", err, len);
 		if (!zcopy_used)
 			vhost_add_used_and_signal(&net->dev, vq, head, 0);
 		else