All of lore.kernel.org
 help / color / mirror / Atom feed
From: mkl@pengutronix.de (Marc Kleine-Budde)
To: linux-arm-kernel@lists.infradead.org
Subject: BUG: commit "ARM: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW on pre-ARMv6 CPUs" breaks armv5 with CONFIG_PREEMPT
Date: Thu, 20 Jun 2013 10:43:33 +0200	[thread overview]
Message-ID: <51C2C0B5.8020802@pengutronix.de> (raw)

Hello Catalin,

on current linus/master on armv5 we observed stack trashing[1] on high
load. I bisected this problem down to commit:

> b9d4d42ad901cc848ac87f1cb8923fded3645568 is the first bad commit
> commit b9d4d42ad901cc848ac87f1cb8923fded3645568
> Author: Catalin Marinas <catalin.marinas@arm.com>
> Date:   Mon Nov 28 21:57:24 2011 +0000
> 
>     ARM: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW on pre-ARMv6 CPUs
> 
>     This patch removes the __ARCH_WANT_INTERRUPTS_ON_CTXSW definition for
>     ARMv5 and earlier processors. On such processors, the context switch
>     requires a full cache flush. To avoid high interrupt latencies, this
>     patch defers the mm switching to the post-lock switch hook if the
>     interrupts are disabled.
> 
>     Reviewed-by: Will Deacon <will.deacon@arm.com>
>     Tested-by: Will Deacon <will.deacon@arm.com>
>     Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
>     Tested-by: Marc Zyngier <Marc.Zyngier@arm.com>
>     Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
> 
> :040000 040000 034899bdcbc9aa59b5455a85a9d78b646b4cf784 ecc23e33a4ca807d4153f87fbea85a9437ff2928 M      arch

The problem can be reproduced on several mx28 and an at91sam9263 and
only occurs of CONFIG_PREEMPT (Preemptible Kernel (Low-Latency Desktop))
is enabled.

I have the gut feeling that the "if (irqs_disabled())" check in the
above patch is not correct for CONFIG_PREEMPT.

Marc

[1] The test program creating 150 threads in a row crashes like this:
> [8]+  Segmentation fault         ./thread_test_c
> [5]   Illegal instruction        ./thread_test_c
> [4]   Illegal instruction        ./thread_test_c
> [2]   Segmentation fault         ./thread_test_c
> [3]   Illegal instruction        ./thread_test_c
> [1]   Segmentation fault         ./thread_test_c

-- 
Pengutronix e.K.                  | Marc Kleine-Budde           |
Industrial Linux Solutions        | Phone: +49-231-2826-924     |
Vertretung West/Dortmund          | Fax:   +49-5121-206917-5555 |
Amtsgericht Hildesheim, HRA 2686  | http://www.pengutronix.de   |

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 259 bytes
Desc: OpenPGP digital signature
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20130620/11a01756/attachment-0001.sig>

             reply	other threads:[~2013-06-20  8:43 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-20  8:43 Marc Kleine-Budde [this message]
2013-06-20  9:25 ` BUG: commit "ARM: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW on pre-ARMv6 CPUs" breaks armv5 with CONFIG_PREEMPT Will Deacon
2013-06-20  9:51   ` Marc Kleine-Budde
2013-06-20  9:57 ` Catalin Marinas
2013-06-20 10:08   ` Marc Kleine-Budde
2013-06-20 10:14   ` Marc Kleine-Budde
2013-06-20 10:28     ` Catalin Marinas
2013-06-20 11:12       ` Catalin Marinas
2013-06-20 11:35         ` Marc Kleine-Budde
2013-06-20 11:39           ` Marc Kleine-Budde
2013-06-20 11:47             ` Marc Kleine-Budde
2013-06-20 12:48               ` Marc Kleine-Budde
2013-06-20 13:01               ` Catalin Marinas
2013-06-20 13:05                 ` Marc Kleine-Budde
2013-06-21 10:28               ` Marc Kleine-Budde
2013-06-21 13:52                 ` Catalin Marinas
2013-07-17  8:41                   ` Marc Kleine-Budde
2013-07-17  8:51                     ` Russell King - ARM Linux
2013-07-17 11:48                       ` Marc Kleine-Budde
2013-07-17 19:41                       ` Catalin Marinas

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=51C2C0B5.8020802@pengutronix.de \
    --to=mkl@pengutronix.de \
    --cc=linux-arm-kernel@lists.infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.