From: Petr Tesarik <ptesarik@suse.cz>
To: Tony Luck <tony.luck@intel.com>
Cc: "linux-ia64@vger.kernel.org" <linux-ia64@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: Serious problem with ticket spinlocks on ia64
Date: Fri, 03 Sep 2010 14:52:55 +0000 [thread overview]
Message-ID: <201009031652.56476.ptesarik@suse.cz> (raw)
In-Reply-To: <201009031635.25093.ptesarik@suse.cz>
On Friday 03 of September 2010 16:35:23 Petr Tesarik wrote:
> On Friday 03 of September 2010 11:04:37 Petr Tesarik wrote:
> > [...]
> > I'm now trying to modify the lock primitives:
> >
> > 1. replace the fetchadd4.acq with looping over cmpxchg
>
> I did this and I feel dumber than ever.
One more thing - the crash dump I got from that run shows that CPU 2 was just
going through zap_page_range(), so it probably also did a few global TLB
flushes. I'm not sure how this should matter, but any idea is good now, I
think.
Anyway, if a global TLB flush is necessary to trigger the bug, it would also
explain why we couldn't reproduce it in user-space.
OK, I know I'm just wildly guessing (and don't have any explanation for the
wrap-around mystery) ... but does anybody have a better idea?
Petr Tesarik
WARNING: multiple messages have this Message-ID (diff)
From: Petr Tesarik <ptesarik@suse.cz>
To: Tony Luck <tony.luck@intel.com>
Cc: "linux-ia64@vger.kernel.org" <linux-ia64@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: Serious problem with ticket spinlocks on ia64
Date: Fri, 3 Sep 2010 16:52:55 +0200 [thread overview]
Message-ID: <201009031652.56476.ptesarik@suse.cz> (raw)
In-Reply-To: <201009031635.25093.ptesarik@suse.cz>
On Friday 03 of September 2010 16:35:23 Petr Tesarik wrote:
> On Friday 03 of September 2010 11:04:37 Petr Tesarik wrote:
> > [...]
> > I'm now trying to modify the lock primitives:
> >
> > 1. replace the fetchadd4.acq with looping over cmpxchg
>
> I did this and I feel dumber than ever.
One more thing - the crash dump I got from that run shows that CPU 2 was just
going through zap_page_range(), so it probably also did a few global TLB
flushes. I'm not sure how this should matter, but any idea is good now, I
think.
Anyway, if a global TLB flush is necessary to trigger the bug, it would also
explain why we couldn't reproduce it in user-space.
OK, I know I'm just wildly guessing (and don't have any explanation for the
wrap-around mystery) ... but does anybody have a better idea?
Petr Tesarik
next prev parent reply other threads:[~2010-09-03 14:52 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-27 13:37 Serious problem with ticket spinlocks on ia64 Petr Tesarik
2010-08-27 13:37 ` Petr Tesarik
2010-08-27 13:48 ` Hedi Berriche
2010-08-27 13:48 ` Hedi Berriche
2010-08-27 14:09 ` Petr Tesarik
2010-08-27 14:09 ` Petr Tesarik
2010-08-27 14:31 ` Hedi Berriche
2010-08-27 14:31 ` Hedi Berriche
2010-08-27 14:40 ` Petr Tesarik
2010-08-27 14:40 ` Petr Tesarik
2010-08-27 14:52 ` Hedi Berriche
2010-08-27 14:52 ` Hedi Berriche
2010-08-27 16:37 ` Petr Tesarik
2010-08-27 16:37 ` Petr Tesarik
2010-08-27 16:08 ` Luck, Tony
2010-08-27 16:08 ` Luck, Tony
2010-08-27 17:16 ` Petr Tesarik
2010-08-27 17:16 ` Petr Tesarik
2010-08-27 18:20 ` Hedi Berriche
2010-08-27 18:20 ` Hedi Berriche
2010-08-27 19:40 ` Petr Tesarik
2010-08-27 19:40 ` Petr Tesarik
2010-08-27 20:29 ` Luck, Tony
2010-08-27 20:29 ` Luck, Tony
2010-08-27 20:41 ` Petr Tesarik
2010-08-27 20:41 ` Petr Tesarik
2010-08-27 21:03 ` Petr Tesarik
2010-08-27 21:03 ` Petr Tesarik
2010-08-27 21:11 ` Luck, Tony
2010-08-27 21:11 ` Luck, Tony
2010-08-27 22:13 ` Petr Tesarik
2010-08-27 22:13 ` Petr Tesarik
2010-08-27 23:26 ` Luck, Tony
2010-08-27 23:26 ` Luck, Tony
2010-08-27 23:55 ` Luck, Tony
2010-08-27 23:55 ` Luck, Tony
2010-08-28 0:28 ` Hedi Berriche
2010-08-28 0:28 ` Hedi Berriche
2010-08-28 5:01 ` Luck, Tony
2010-08-28 5:01 ` Luck, Tony
2010-08-30 18:17 ` Luck, Tony
2010-08-30 18:17 ` Luck, Tony
2010-08-30 21:41 ` Petr Tesarik
2010-08-30 21:41 ` Petr Tesarik
2010-08-30 22:43 ` Tony Luck
2010-08-30 22:43 ` Tony Luck
2010-08-31 22:17 ` Tony Luck
2010-08-31 22:17 ` Tony Luck
2010-09-01 23:09 ` Tony Luck
2010-09-01 23:09 ` Tony Luck
2010-09-02 0:26 ` Hedi Berriche
2010-09-02 0:26 ` Hedi Berriche
2010-09-03 0:06 ` Tony Luck
2010-09-03 0:06 ` Tony Luck
2010-09-03 9:04 ` Petr Tesarik
2010-09-03 9:04 ` Petr Tesarik
2010-09-03 14:35 ` Petr Tesarik
2010-09-03 14:35 ` Petr Tesarik
2010-09-03 14:52 ` Petr Tesarik [this message]
2010-09-03 14:52 ` Petr Tesarik
2010-09-03 15:50 ` Tony Luck
2010-09-03 15:50 ` Tony Luck
2010-09-06 14:47 ` Petr Tesarik
2010-09-06 14:47 ` Petr Tesarik
2010-09-07 13:17 ` Petr Tesarik
2010-09-07 13:17 ` Petr Tesarik
2010-09-07 17:35 ` Tony Luck
2010-09-07 17:35 ` Tony Luck
2010-09-08 15:55 ` Tony Luck
2010-09-08 15:55 ` Tony Luck
2010-09-10 2:55 ` Dave Jones
2010-09-10 2:55 ` Dave Jones
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=201009031652.56476.ptesarik@suse.cz \
--to=ptesarik@suse.cz \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tony.luck@intel.com \
/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.