netdev - Re: [Patch net 0/5] net_sched: tc action fixes and updates

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <a79fc4fd-69aa-0af6-bb2d-7729610f97e4@mojatatu.com>
Date:	Wed, 10 Aug 2016 10:34:14 -0400
From:	Jamal Hadi Salim <jhs@...atatu.com>
To:	Cong Wang <xiyou.wangcong@...il.com>
Cc:	netdev@...r.kernel.org, David Miller <davem@...emloft.net>
Subject: Re: [Patch net 0/5] net_sched: tc action fixes and updates

On 16-08-08 04:46 PM, Cong Wang wrote:
> This patchset fixes several regressions caused by the previous
> code refactor. Thanks to Jamal for catching them!
>

Cong,

Good news: oops gone. I havent done more testing than I did
before; but looks good so far.

Bad news: You have introduced a performance regression which is
noticeable at high speed.

tcf_exts_exec() is the culprit - and conversion to from flexarray
to linked list in the fast problem to be specific.
The regression is problematic (and unacceptable). Two options:
a) You fix the regressions - which i think may require changing
what gets passed around an executed on as an array instead of a
list.
b) I am worried #a will take some work. So the second option is
to back out the patch since there are known stability options;
get regression issues resolved and then go back and submit.

cheers,
jamla