lkml.org 
[lkml]   [2013]   [Jun]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [net PATCH] tuntap: set SOCK_ZEROCOPY flag during open
On Sat, Jun 08, 2013 at 02:17:41PM +0800, Jason Wang wrote:
> Commit 54f968d6efdbf7dec36faa44fc11f01b0e4d1990
> (tuntap: move socket to tun_file) forgets to set SOCK_ZEROCOPY flag, which will
> prevent vhost_net from doing zercopy w/ tap. This patch fixes this by setting
> it during file open.
>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Signed-off-by: Jason Wang <jasowang@redhat.com>

I see, and this explains the perf regression we are seeing with 3.9.

Acked-by: Michael S. Tsirkin <mst@redhat.com>

and I think this should go into stable as well.

> ---
> drivers/net/tun.c | 2 ++
> 1 files changed, 2 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index f042b03..d2ddd6d 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -2155,6 +2155,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
> set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags);
> INIT_LIST_HEAD(&tfile->next);
>
> + sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
> +
> return 0;
> }
>
> --
> 1.7.1


\
 
 \ /
  Last update: 2013-06-09 09:41    [W:0.048 / U:0.940 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site