linux-kernel - Re: [PATCH] mutex: Do not spin/queue before performing ww

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]

Date:	Thu, 26 May 2016 13:08:58 +0200
From:	Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>
To:	Chris Wilson <chris@...is-wilson.co.uk>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	intel-gfx@...ts.freedesktop.org,
	Christian König <christian.koenig@....com>,
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH] mutex: Do not spin/queue before performing ww_mutex
 deadlock avoidance

Op 26-05-16 om 12:43 schreef Chris Wilson:
> On Thu, May 26, 2016 at 12:37:30PM +0200, Maarten Lankhorst wrote:
>> The check should also not be for NULL, but for use_ww_ctx.
>> This way the if check is optimized out for the ww_ctx path, where
>> ww_ctx is always non-null.
> The compiler can see use_ww_ctx == false => ww_ctx == NULL just as well
> to do dead-code elimination, i.e. use_ww_ctx is superflouus and does not
> reduce the code size. (gcc 4.7.2, 4.9.1, 5.3.1)
That's true, but it cannot do the same when use_ww_ctx = true.
In this case the function will always be called with ww_ctx != NULL,
but the compiler can't see that, so it will keep the check even if it's always true.

~Maarten