linux-kernel - Re: [PATCH] io-controller: Add io group reference handling for request

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: <4A078051.5060702@cn.fujitsu.com>
Date:	Mon, 11 May 2009 09:33:05 +0800
From:	Gui Jianfeng <guijianfeng@...fujitsu.com>
To:	Nauman Rafique <nauman@...gle.com>
CC:	Vivek Goyal <vgoyal@...hat.com>, dpshah@...gle.com,
	lizf@...fujitsu.com, mikew@...gle.com, fchecconi@...il.com,
	paolo.valente@...more.it, jens.axboe@...cle.com,
	ryov@...inux.co.jp, fernando@....ntt.co.jp, s-uchida@...jp.nec.com,
	taka@...inux.co.jp, jmoyer@...hat.com, dhaval@...ux.vnet.ibm.com,
	balbir@...ux.vnet.ibm.com, linux-kernel@...r.kernel.org,
	containers@...ts.linux-foundation.org, righi.andrea@...il.com,
	agk@...hat.com, dm-devel@...hat.com, snitzer@...hat.com,
	m-ikeda@...jp.nec.com, akpm@...ux-foundation.org
Subject: Re: [PATCH] io-controller: Add io group reference handling for 	request

Nauman Rafique wrote:
> On Fri, May 8, 2009 at 6:57 AM, Vivek Goyal <vgoyal@...hat.com> wrote:
>> On Fri, May 08, 2009 at 05:45:32PM +0800, Gui Jianfeng wrote:
>>> Hi Vivek,
>>>
>>> This patch adds io group reference handling when allocating
>>> and removing a request.
>>>
>> Hi Gui,
>>
>> Thanks for the patch. We were thinking that requests can take a reference
>> on io queues and io queues can take a reference on io groups. That should
>> make sure that io groups don't go away as long as active requests are
>> present.
>>
>> But there seems to be a small window while allocating the new request
>> where request gets allocated from a group first and then later it is
>> mapped to that group and queue is created. IOW, in get_request_wait(),
>> we allocate a request from a particular group and set rq->rl, then
>> drop the queue lock and later call elv_set_request() which again maps
>> the request to the group saves rq->iog and creates new queue. This window
>> is troublesome because request can be mapped to a particular group at the
>> time of allocation and during set_request() it can go to a different
>> group as queue lock was dropped and group might have disappeared.
>>
>> In this case probably it might make sense that request also takes a
>> reference on groups. At the same time it looks too much that request takes
>> a reference on queue as well as group object. Ideas are welcome on how
>> to handle it...
> 
> IMHO a request being allocated on the wrong cgroup should not be a big
> problem as such. All it means is that the request descriptor was
> accounted to the wrong cgroup in this particular corner case. Please
> correct me if I am wrong.
> 
> We can also get rid of rq->iog pointer too. What that means is that
> request is associated with ioq (rq->ioq), and we can use
> ioq_to_io_group() function to get the io_group. So the request would
> only be indirectly associated with an io_group i.e. the request is
> associated with an io_queue and the io_group for the request is the
> io_group associated with io_queue. Do you see any problems with that
> approach?

  That sounds reasonable to get rid of rq->iog, and rq->rl is also dead.
  Hope to see the patch soon. ;)

-- 
Regards
Gui Jianfeng

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/