Re: [GIT PULL] aio: fix sleeping while TASK_INTERRUPTIBLE

[Dave Chinner <david@fromorbit.com>]

On Mon, Feb 02, 2015 at 10:45:42AM -0800, Linus Torvalds wrote:
> On Sun, Feb 1, 2015 at 9:54 PM, Dave Chinner <david@fromorbit.com> wrote:
> >
> > Simple enough - the patch below removes the warning from generic/036
> > for me.
> 
> So because this is a debugging thing, I'd actually prefer these
> "sched_annotate_sleep()" calls to always come with short  comments in
> code why they exist and why they are fine.

Ok, I just copied the existing users which don't have any comments.

> In this case, it might be as simple as
> 
>  "If the mutex blocks and wakes us up, the loop in
> wait_event_interruptible_hrtimeout() will just schedule without
> sleeping and repeat. The ting-lock doesn't block often enough for this
> to be a performance issue".
> 
> or perhaps just point to the comment in read_events().

Both. New patch below.

-Dave.
-- 
Dave Chinner
david@fromorbit.com

aio: annotate aio_read_event_ring for sleep patterns

From: Dave Chinner <dchinner@redhat.com>

Under CONFIG_DEBUG_ATOMIC_SLEEP=y, aio_read_event_ring() will throw
warnings like the following due to being called from wait_event
context:

 WARNING: CPU: 0 PID: 16006 at kernel/sched/core.c:7300 __might_sleep+0x7f/0x90()
 do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff810d85a3>] prepare_to_wait_event+0x63/0x110
 Modules linked in:
 CPU: 0 PID: 16006 Comm: aio-dio-fcntl-r Not tainted 3.19.0-rc6-dgc+ #705
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  ffffffff821c0372 ffff88003c117cd8 ffffffff81daf2bd 000000000000d8d8
  ffff88003c117d28 ffff88003c117d18 ffffffff8109beda ffff88003c117cf8
  ffffffff821c115e 0000000000000061 0000000000000000 00007ffffe4aa300
 Call Trace:
  [<ffffffff81daf2bd>] dump_stack+0x4c/0x65
  [<ffffffff8109beda>] warn_slowpath_common+0x8a/0xc0
  [<ffffffff8109bf56>] warn_slowpath_fmt+0x46/0x50
  [<ffffffff810d85a3>] ? prepare_to_wait_event+0x63/0x110
  [<ffffffff810d85a3>] ? prepare_to_wait_event+0x63/0x110
  [<ffffffff810bdfcf>] __might_sleep+0x7f/0x90
  [<ffffffff81db8344>] mutex_lock+0x24/0x45
  [<ffffffff81216b7c>] aio_read_events+0x4c/0x290
  [<ffffffff81216fac>] read_events+0x1ec/0x220
  [<ffffffff810d8650>] ? prepare_to_wait_event+0x110/0x110
  [<ffffffff810fdb10>] ? hrtimer_get_res+0x50/0x50
  [<ffffffff8121899d>] SyS_io_getevents+0x4d/0xb0
  [<ffffffff81dba5a9>] system_call_fastpath+0x12/0x17
 ---[ end trace bde69eaf655a4fea ]---

There is not actually a bug here, so annotate the code to tell the
debug logic that everything is just fine and not to fire a false
positive.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
V2: added comment to explain the annotation.

 fs/aio.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/aio.c b/fs/aio.c
index 1b7893e..327ef6d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1140,6 +1140,13 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	long ret = 0;
 	int copy_ret;
 
+	/*
+	 * The mutex can block and wake us up and that will cause
+	 * wait_event_interruptible_hrtimeout() to schedule without sleeping
+	 * and repeat. This should be rare enough that it doesn't cause
+	 * peformance issues. See the comment in read_events() for more detail.
+	 */
+	sched_annotate_sleep();
 	mutex_lock(&ctx->ring_lock);
 
 	/* Access to ->ring_pages here is protected by ctx->ring_lock. */