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] [day] [month] [year] [list]
Message-ID: <100cdbe8-4109-053c-7a2e-231e5d572e71@virtuozzo.com>
Date:   Thu, 19 Jul 2018 14:14:58 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Michal Hocko <mhocko@...nel.org>
Cc:     akpm@...ux-foundation.org, vdavydov.dev@...il.com,
        penguin-kernel@...ove.SAKURA.ne.jp, chris@...is-wilson.co.uk,
        gregkh@...uxfoundation.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/2] mm: Keep int fields in struct shrink_control together

On 19.07.2018 14:10, Michal Hocko wrote:
> On Thu 19-07-18 13:51:19, Kirill Tkhai wrote:
>> gfp_t is of unsigned type, so let's move nid to keep
>> them together.
>
> I guess you meant unsigned int so you can fill up a hole in
> shrink_control and as such reduce the stack consumption a bit (at least
> on 64b).

Yes, I mean unsigned as synonym of unsigned int and this is the reason :)
 
> An output from pahole is usually a great tool to visualize this.
> 
> die__process_function: tag not supported (INVALID)!
> struct shrink_control {
> 	gfp_t                      gfp_mask;             /*     0     4 */
> 
> 	/* XXX 4 bytes hole, try to pack */
> 
> 	long unsigned int          nr_to_scan;           /*     8     8 */
> 	long unsigned int          nr_scanned;           /*    16     8 */
> 	int                        nid;                  /*    24     4 */
> 
> 	/* XXX 4 bytes hole, try to pack */
> 
> 	struct mem_cgroup *        memcg;                /*    32     8 */
> 
> 	/* size: 40, cachelines: 1, members: 5 */
> 	/* sum members: 32, holes: 2, sum holes: 8 */
> 	/* last cacheline: 40 bytes */
> };
>>>
>> Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
> 
> Acked-by: Michal Hocko <mhocko@...e.com>
> 
>> ---
>>  include/linux/shrinker.h |    6 +++---
>>  1 file changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
>> index b154fd2b084c..d58aaaed34a4 100644
>> --- a/include/linux/shrinker.h
>> +++ b/include/linux/shrinker.h
>> @@ -12,6 +12,9 @@
>>  struct shrink_control {
>>  	gfp_t gfp_mask;
>>  
>> +	/* current node being shrunk (for NUMA aware shrinkers) */
>> +	int nid;
>> +
>>  	/*
>>  	 * How many objects scan_objects should scan and try to reclaim.
>>  	 * This is reset before every call, so it is safe for callees
>> @@ -26,9 +29,6 @@ struct shrink_control {
>>  	 */
>>  	unsigned long nr_scanned;
>>  
>> -	/* current node being shrunk (for NUMA aware shrinkers) */
>> -	int nid;
>> -
>>  	/* current memcg being shrunk (for memcg aware shrinkers) */
>>  	struct mem_cgroup *memcg;
>>  };
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ