linux-kernel - Re: [non] 2aa3847085: will-it-scale.per_process

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20200406083930.GV8179@shao2-debian>
Date:   Mon, 6 Apr 2020 16:39:30 +0800
From:   kernel test robot <rong.a.chen@...el.com>
To:     Al Viro <viro@...iv.linux.org.uk>
Cc:     LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org
Subject: Re: [non] 2aa3847085: will-it-scale.per_process_ops -32.0% regression

On Mon, Apr 06, 2020 at 03:04:51AM +0100, Al Viro wrote:
> On Mon, Apr 06, 2020 at 09:25:39AM +0800, kernel test robot wrote:
> > Greeting,
> > 
> > FYI, we noticed a -32.0% regression of will-it-scale.per_process_ops due to commit:
> > 
> > 
> > commit: 2aa38470853a65dc9b1b4bd0989d34cd3fc57ebd ("non-RCU analogue of the previous commit")
> > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
> 
> Arrgghh...  Could you check if vfs.git#fixes recovers that?  FWIW, proposed fix
> is this:
> 
> commit d98d78cd6ac9eb5ed0506140cc43432d7c7dd480
> Author: Al Viro <viro@...iv.linux.org.uk>
> Date:   Sun Apr 5 21:59:55 2020 -0400
> 
>     fix braino in legitimize_path()
>     
>     brown paperbag time... wrong order of arguments ended up confusing
>     the values to check dentry and mount_lock seqcounts against.
>     
>     Reported-by: kernel test robot <rong.a.chen@...el.com>
>     Fixes: 2aa38470853a ("non-RCU analogue of the previous commit")
>     Signed-off-by: Al Viro <viro@...iv.linux.org.uk>
> 
> diff --git a/fs/namei.c b/fs/namei.c
> index 61fdb77a7d58..a320371899cf 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -610,7 +610,7 @@ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq)
>  static inline bool legitimize_path(struct nameidata *nd,
>  			    struct path *path, unsigned seq)
>  {
> -	return __legitimize_path(path, nd->m_seq, seq);
> +	return __legitimize_path(path, seq, nd->m_seq);
>  }
>  
>  static bool legitimize_links(struct nameidata *nd)


Hi Al,

Yes, the regression can be fixed:

7ef482fa65513b18  2aa38470853a65dc9b1b4bd098  d98d78cd6ac9eb5ed0506140cc  testcase/testparams/testbox
----------------  --------------------------  --------------------------  ---------------------------
         %stddev      change         %stddev      change         %stddev
             \          |                \          |                \  
    449960             -32%     306036                      450924        will-it-scale/performance-open2-ucode=0x21/lkp-ivb-d04
    449959             -32%     306035                      450923        GEO-MEAN will-it-scale.per_process_ops

Best Regards,
Rong Chen