From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Mason Subject: Re: [PATCH RFC] fs/aio: fix sleeping while TASK_INTERRUPTIBLE Date: Wed, 21 Jan 2015 16:42:28 -0500 Message-ID: <20150121214228.GA26018@ret.masoncoding.com> References: <20141223001619.GA26385@ret.masoncoding.com> <20150121101313.GJ16510@dastard> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: , , Peter Zijlstra To: Dave Chinner Return-path: Content-Disposition: inline In-Reply-To: <20150121101313.GJ16510@dastard> Sender: owner-linux-aio@kvack.org List-Id: linux-fsdevel.vger.kernel.org On Wed, Jan 21, 2015 at 09:13:13PM +1100, Dave Chinner wrote: > On Mon, Dec 22, 2014 at 07:16:25PM -0500, Chris Mason wrote: > > The 3.19 merge window brought in a great new warning to catch someone > > calling might_sleep with their state != TASK_RUNNING. The idea was to > > find buggy code locking mutexes after calling prepare_to_wait(), kind > > of like this: > > > > [ 445.464634] WARNING: CPU: 22 PID: 4367 at kernel/sched/core.c:7303 __might_sleep+0x9a/0xb0() > > [ 445.481699] do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait_event+0x68/0x120 > > Hi Chris, > > This still isn't fixed in -rc5 - I'm hitting it multiple times in > every xfstests run I do. What's the current status of your fix? I worried this is going to have a perf hit, so I talked Jens into double checking it on one of his super high iop boxes. -chris -- To unsubscribe, send a message with 'unsubscribe linux-aio' in the body to majordomo@kvack.org. For more info on Linux AIO, see: http://www.kvack.org/aio/ Don't email: aart@kvack.org