linux-kernel - Re: softlockups in multi_cpu

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: <1425703470.19505.111.camel@stgolabs.net>
Date:	Fri, 06 Mar 2015 20:44:30 -0800
From:	Davidlohr Bueso <dave@...olabs.net>
To:	Jason Low <jason.low2@...com>
Cc:	Linus Torvalds <torvalds@...ux-foundation.org>,
	Ingo Molnar <mingo@...nel.org>, tim.c.chen@...ux.intel.com,
	paulmck@...ux.vnet.ibm.com, Sasha Levin <sasha.levin@...cle.com>,
	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>,
	Dave Jones <davej@...emonkey.org.uk>,
	Ming Lei <ming.lei@...onical.com>
Subject: Re: softlockups in multi_cpu_stop

On Fri, 2015-03-06 at 20:31 -0800, Jason Low wrote:
> On Fri, 2015-03-06 at 13:12 -0800, Jason Low wrote:
> 
> Just in case, here's the updated patch which addresses Linus's comments
> and with a changelog.
> 
> Note: The changelog says that it fixes (locking/rwsem: Avoid deceiving
> lock spinners), though I still haven't seen full confirmation that it
> addresses all of the lockup reports.
> 
> ------
> Subject: [PATCH] rwsem: Avoid spinning when owner is not running
> 
> Fixes tip commmit b3fd4f03ca0b (locking/rwsem: Avoid deceiving lock spinners).
> 
> When doing optimistic spinning in rwsem, threads should stop spinning when
> the lock owner is not running. While a thread is spinning on owner, if
> the owner reschedules, owner->on_cpu returns false and we stop spinning.
> 
> However, commit b3fd4f03ca0b essentially caused the check to get ignored
> because when we break out of the spin loop due to !on_cpu, we continue
> spinning if sem->owner != NULL.

I would mention the actual effects of the bug, either just a "lockup"
and/or a fragment of the trace. But ultimately this comes down to
missing a need_resched() condition.

> 
> This patch fixes this by making sure we stop spinning if the owner is not
> running. Furthermore, just like with mutexes, refactor the code such that
> we don't have separate checks for owner_running(). This makes it more
> straightforward in terms of why we exit the spin on owner loop and we
> would also avoid needing to "guess" why we broke out of the loop to make
> this more readable.
> 
> Cc: Ming Lei <ming.lei@...onical.com>
> Cc: Davidlohr Bueso <dave@...olabs.net>

Acked-by: Davidlohr Bueso <dave@...olabs.net>

--
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/