Re: [PATCH net,stable v4 0/3] vhost: fix a few skb leaks

[David Miller]

From: w...@redhat.com
Date: Fri,  1 Dec 2017 05:10:35 -0500

> Matthew found a roughly 40% tcp throughput regression with commit
> c67df11f(vhost_net: try batch dequing from skb array) as discussed
> in the following thread:
> https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html

Series applied and queued up for -stable.
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

[PATCH net,stable v4 0/3] vhost: fix a few skb leaks

[wexu]

From: Wei Xu 

Matthew found a roughly 40% tcp throughput regression with commit
c67df11f(vhost_net: try batch dequing from skb array) as discussed
in the following thread:
https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html

v4:
- fix zero iov iterator count in tap/tap_do_read()(Jason)
- don't put tun in case of EBADFD(Jason)
- Replace msg->msg_control with new 'skb' when calling tun/tap_do_read()

v3:
- move freeing skb from vhost to tun/tap recvmsg() to not
  confuse the callers.

v2:
- add Matthew as the reporter, thanks matthew.
- moving zero headcount check ahead instead of defer consuming skb
  due to jason and mst's comment.
- add freeing skb in favor of recvmsg() fails.

Wei Xu (3):
  vhost: fix skb leak in handle_rx()
  tun: free skb in early errors
  tap: free skb if flags error

 drivers/net/tap.c   | 14 ++
 drivers/net/tun.c   | 24 ++--
 drivers/vhost/net.c | 20 ++--
 3 files changed, 38 insertions(+), 20 deletions(-)

-- 
1.8.3.1

___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net,stable v4 0/3] vhost: fix a few skb leaks

[Matthew Rosato]

On 12/01/2017 09:47 AM, Michael S. Tsirkin wrote:
> On Fri, Dec 01, 2017 at 05:10:35AM -0500, w...@redhat.com wrote:
>> From: Wei Xu 
>>
>> Matthew found a roughly 40% tcp throughput regression with commit
>> c67df11f(vhost_net: try batch dequing from skb array) as discussed
>> in the following thread:
>> https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html
> 
> Series
> 
> Acked-by: Michael S. Tsirkin 

Tested this series on a z13 (s390x) on top of net-next using 4GB/4vcpu
guests.  Verified that both the reported TCP throughput regression and
memory leak are resolved.

net-next:  19.83 Gb/s
net-next+: 35.02 Gb/s

Thanks all!

Matt

> 
> 
>> v4:
>> - fix zero iov iterator count in tap/tap_do_read()(Jason)
>> - don't put tun in case of EBADFD(Jason)
>> - Replace msg->msg_control with new 'skb' when calling tun/tap_do_read()
>>
>> v3:
>> - move freeing skb from vhost to tun/tap recvmsg() to not
>>   confuse the callers.
>>
>> v2:
>> - add Matthew as the reporter, thanks matthew.
>> - moving zero headcount check ahead instead of defer consuming skb
>>   due to jason and mst's comment.
>> - add freeing skb in favor of recvmsg() fails.
>>
>> Wei Xu (3):
>>   vhost: fix skb leak in handle_rx()
>>   tun: free skb in early errors
>>   tap: free skb if flags error
>>
>>  drivers/net/tap.c   | 14 ++
>>  drivers/net/tun.c   | 24 ++--
>>  drivers/vhost/net.c | 20 ++--
>>  3 files changed, 38 insertions(+), 20 deletions(-)
>>
>> -- 
>> 1.8.3.1
> 

___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net,stable v4 0/3] vhost: fix a few skb leaks

[Michael S. Tsirkin]

On Fri, Dec 01, 2017 at 09:54:02AM -0500, Matthew Rosato wrote:
> On 12/01/2017 09:47 AM, Michael S. Tsirkin wrote:
> > On Fri, Dec 01, 2017 at 05:10:35AM -0500, w...@redhat.com wrote:
> >> From: Wei Xu 
> >>
> >> Matthew found a roughly 40% tcp throughput regression with commit
> >> c67df11f(vhost_net: try batch dequing from skb array) as discussed
> >> in the following thread:
> >> https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html
> > 
> > Series
> > 
> > Acked-by: Michael S. Tsirkin 
> 
> Tested this series on a z13 (s390x) on top of net-next using 4GB/4vcpu
> guests.  Verified that both the reported TCP throughput regression and
> memory leak are resolved.
> 
> net-next:  19.83 Gb/s
> net-next+: 35.02 Gb/s
> 
> Thanks all!
> 
> Matt

So we can also add
Tested-by: Matthew Rosato 

Dave, pls take this through the net tree as most changes are
in tun/tap.

Thanks!

> > 
> > 
> >> v4:
> >> - fix zero iov iterator count in tap/tap_do_read()(Jason)
> >> - don't put tun in case of EBADFD(Jason)
> >> - Replace msg->msg_control with new 'skb' when calling tun/tap_do_read()
> >>
> >> v3:
> >> - move freeing skb from vhost to tun/tap recvmsg() to not
> >>   confuse the callers.
> >>
> >> v2:
> >> - add Matthew as the reporter, thanks matthew.
> >> - moving zero headcount check ahead instead of defer consuming skb
> >>   due to jason and mst's comment.
> >> - add freeing skb in favor of recvmsg() fails.
> >>
> >> Wei Xu (3):
> >>   vhost: fix skb leak in handle_rx()
> >>   tun: free skb in early errors
> >>   tap: free skb if flags error
> >>
> >>  drivers/net/tap.c   | 14 ++
> >>  drivers/net/tun.c   | 24 ++--
> >>  drivers/vhost/net.c | 20 ++--
> >>  3 files changed, 38 insertions(+), 20 deletions(-)
> >>
> >> -- 
> >> 1.8.3.1
> > 
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net,stable v4 0/3] vhost: fix a few skb leaks

[Michael S. Tsirkin]

On Fri, Dec 01, 2017 at 05:10:35AM -0500, w...@redhat.com wrote:
> From: Wei Xu 
> 
> Matthew found a roughly 40% tcp throughput regression with commit
> c67df11f(vhost_net: try batch dequing from skb array) as discussed
> in the following thread:
> https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html

Series

Acked-by: Michael S. Tsirkin 


> v4:
> - fix zero iov iterator count in tap/tap_do_read()(Jason)
> - don't put tun in case of EBADFD(Jason)
> - Replace msg->msg_control with new 'skb' when calling tun/tap_do_read()
> 
> v3:
> - move freeing skb from vhost to tun/tap recvmsg() to not
>   confuse the callers.
> 
> v2:
> - add Matthew as the reporter, thanks matthew.
> - moving zero headcount check ahead instead of defer consuming skb
>   due to jason and mst's comment.
> - add freeing skb in favor of recvmsg() fails.
> 
> Wei Xu (3):
>   vhost: fix skb leak in handle_rx()
>   tun: free skb in early errors
>   tap: free skb if flags error
> 
>  drivers/net/tap.c   | 14 ++
>  drivers/net/tun.c   | 24 ++--
>  drivers/vhost/net.c | 20 ++--
>  3 files changed, 38 insertions(+), 20 deletions(-)
> 
> -- 
> 1.8.3.1
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization