On Fri, 2017-01-27 at 17:24 +, David Laight wrote:
> From: Eric Dumazet
> > Sent: 27 January 2017 14:44
> ...
> > > I'm also guessing that extra headroom can be generated by stealing unused
> > > tailroom.
> >
> > This is already done.
> >
> > Quoting
> > https://git.kernel.org/cgit/linux/ke
From: Eric Dumazet
> Sent: 27 January 2017 14:44
...
> > I'm also guessing that extra headroom can be generated by stealing unused
> > tailroom.
>
> This is already done.
>
> Quoting
> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=87fb4b7b533073eeeaed0b6bf7c
> 232899
On Fri, 2017-01-27 at 15:46 +, David Laight wrote:
> Reads code ...
> My confusion is that the call is specifying the number of EXTRA bytes of
> head/tail
> room rather than the number of bytes needed.
And the fact that @size is changed in existing code (so not visible in
patch diff) to
siz
From: Eric Dumazet [mailto:eric.duma...@gmail.com]
> Sent: 27 January 2017 14:44
> On Fri, 2017-01-27 at 10:49 +, David Laight wrote:
> > From: Eric Dumazet
> > > Sent: 27 January 2017 00:21
> > > Slava Shwartsman reported a warning in skb_try_coalesce(), when we
> > > detect skb->truesize is c
On Fri, 2017-01-27 at 10:49 +, David Laight wrote:
> From: Eric Dumazet
> > Sent: 27 January 2017 00:21
> > Slava Shwartsman reported a warning in skb_try_coalesce(), when we
> > detect skb->truesize is completely wrong.
> >
> > In his case, issue came from IPv6 reassembly coping with maliciou
From: Eric Dumazet
> Sent: 27 January 2017 00:21
> Slava Shwartsman reported a warning in skb_try_coalesce(), when we
> detect skb->truesize is completely wrong.
>
> In his case, issue came from IPv6 reassembly coping with malicious
> datagrams, that forced various pskb_may_pull() to reallocate a
On Fri, 2017-01-27 at 10:22 +0800, kbuild test robot wrote:
> Hi Eric,
>
> [auto build test WARNING on net-next/master]
>
> url:
> https://github.com/0day-ci/linux/commits/Eric-Dumazet/net-adjust-skb-truesize-in-pskb_expand_head/20170127-082517
> config: i386-randconfig-x0-01270914 (attached
Hi Eric,
[auto build test WARNING on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Eric-Dumazet/net-adjust-skb-truesize-in-pskb_expand_head/20170127-082517
config: i386-randconfig-x0-01270914 (attached as .config)
compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
reproduce:
From: Eric Dumazet
Slava Shwartsman reported a warning in skb_try_coalesce(), when we
detect skb->truesize is completely wrong.
In his case, issue came from IPv6 reassembly coping with malicious
datagrams, that forced various pskb_may_pull() to reallocate a bigger
skb->head than the one allocate
