On Thu, Feb 5, 2015 at 2:58 AM, Philipp Tölke [off-list ref] wrote:

Hi everybody,

Paul Gortmaker <paul.gortmaker <at> windriver.com> writes:

quoted

 -this patch is against 3.10-rt, but the code for all recent -rt
  that include the recent linux-stable rtmutex changes should have
  the same issue.  [The 3.14-rt has a trivial path change where the
  kernel/rtmutex.c of v3.10 becomes kernel/locking/rtmutex.c but
  aside from that it applies to 3.14 too]

 -I'd got a report of this BUG_ON triggering on a v3.4-rt based
  kernel; that kernel was using my integration of the tglx rtmutex
  stable changes into 3.4-rt as described here:
      https://lkml.org/lkml/2014/9/23/944
  but the related code in rostedt's 3.10.53-rt56 (in linux-stable-rt)
  and in tglx's 3.14.12-rt9 patch queue is AFAICT identical.  So I
  have to conclude that anything using the stable rtmutex changes
  can inadvertently suffer the same BUG trigger.

 -this change gets us back to the pre-rtmutex stable commit behaviour,
  but I suspect that smarter people than me can advise on a way to
  achieve the same end result.  So I'll wait before adding anything
  to the linux-stable-rt branches I'd put here at:
      https://git.kernel.org/cgit/linux/kernel/git/paulg/linux-stable-rt.git

What is the status of this patch? I have a machine here I can get to crash in
about half an hour by doing a bidirectional iperf as proposed in
<http://thread.gmane.org/gmane.linux.rt.user/12681>.

Ffor posterity: The command is "iperf -c 1.2.3.4 -i 10 -d -l 64k -t 50400"
which would normally do a 14 hour-iperf test against 1.2.3.4.

My machine crashes with both 3.10.53-rt56 and 3.14.29-rt26. After
applying your patch to 3.14 the machine has not crashed in 24 hours.

Yeah, FWIW, I've been using it on 3.4, 3.10 and 3.14 since my original post.

Have "smarter people" had a chance to advise about this patch? Is there any
reason not to use it?

1) No, and 2) not AFAIK.   I've added Steve to Cc:  hopefully he can
take a look and decide whether to merge it to stable-rt git repo.  It
seems like the results from you, myself and others do indicate it is
a real issue though... and if this isn't the way to fix it then we will
need some other fix.

Paul.
--

Regards,
Philipp Tölke

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html