On Wed, Jan 21, 2015 at 10:42 PM, Chris Mason <clm@xxxxxx> wrote: > 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 [<ffffffff81093f68>] 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. > >From reading the log [1] this issue seems to be fixed by... commit 9c9ce763b114e608b5cf3aa6cb69ad9f6e8b6adf aio: annotate aio_read_event_ring for sleep patterns - Sedat - [1] http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=9c9ce763b114e608b5cf3aa6cb69ad9f6e8b6adf -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
