linux-kernel - Re: [PATCH 1/2] ipc/sem.c: Fix complex

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: <c484baa7-f34d-03b5-c5b9-ad922b1f5a58@colorfullife.com>
Date:	Thu, 23 Jun 2016 20:55:06 +0200
From:	Manfred Spraul <manfred@...orfullife.com>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Stephen Rothwell <sfr@...b.auug.org.au>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...e.hu>, "H. Peter Anvin" <hpa@...or.com>,
	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>, linux-next@...r.kernel.org,
	1vier1@....de, Davidlohr Bueso <dave@...olabs.net>,
	felixh@...ormatik.uni-bremen.de, stable@...r.kernel.org
Subject: Re: [PATCH 1/2] ipc/sem.c: Fix complex_count vs. simple op race

On 06/21/2016 01:04 AM, Andrew Morton wrote:
> On Sat, 18 Jun 2016 22:02:21 +0200 Manfred Spraul <manfred@...orfullife.com> wrote:
>
>> Commit 6d07b68ce16a ("ipc/sem.c: optimize sem_lock()") introduced a race:
>>
>> sem_lock has a fast path that allows parallel simple operations.
>> There are two reasons why a simple operation cannot run in parallel:
>> - a non-simple operations is ongoing (sma->sem_perm.lock held)
>> - a complex operation is sleeping (sma->complex_count != 0)
>>
>> As both facts are stored independently, a thread can bypass the current
>> checks by sleeping in the right positions. See below for more details
>> (or kernel bugzilla 105651).
>>
>> The patch fixes that by creating one variable (complex_mode)
>> that tracks both reasons why parallel operations are not possible.
>>
>> The patch also updates stale documentation regarding the locking.
>>
>> With regards to stable kernels:
>> The patch is required for all kernels that include the commit 6d07b68ce16a
>> ("ipc/sem.c: optimize sem_lock()") (3.10?)
> I've had this in -mm (and -next) since January 4, without issues.  I
> put it on hold because Davidlohr expressed concern about performance
> regressions.
I had several ideas how to fix it. The initial ideas probably had 
performance issue.

The current one doesn't have any issues. It just took longer than 
expected to test it.
> Your [2/2] should prevent those regressions (yes?) so I assume that any
> kernel which has [1/2] really should have [2/2] as well.  But without
> any quantitative information, this is all mad guesswork.
>
> What to do?
[2/2] is an improvement, it handles one case better than the current code.
If you want:
3.10 improved scalability, but it introduced a performance regression 
for one use case.
[with 3.10, simple ops got parallel, but complex ops had to perform a 
"for_each_sem() {spin_unlock_wait()}"]
The patch fixes that.


--
     Manfred