From: will.deacon@arm.com (Will Deacon)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] ARM: perf: do not handle deleted counter in irq handler to avoid oops
Date: Tue, 21 Feb 2012 15:57:08 +0000 [thread overview]
Message-ID: <20120221155707.GD23133@mudshark.cambridge.arm.com> (raw)
In-Reply-To: <CACVXFVNrWgeEKjZyrEgugGrKkLz030aeMwwNWd_jwdMA5-=N=Q@mail.gmail.com>
On Tue, Feb 21, 2012 at 03:49:22PM +0000, Ming Lei wrote:
> On Tue, Feb 21, 2012 at 11:40 PM, Will Deacon <will.deacon@arm.com> wrote:
> > Sure they do. When we read-modify-write the pmcr we &= ~mask, so we end up
> > writing the overflow flags back if they are set, which is sufficient to
> > clear them.
>
> Sorry for missing it, but looks xscale uses standalone overflow
> register and does not
> clear its overflow flag.
Hmmm, I don't know very much about the xscale PMUs (the perf code is based
on the old OProfile code). The xscale2 overflow handler is certainly doing
something with some overflow flags though, but then it checks the pmnc again
for each counter...
I'd rather not touch that without knowing *exactly* what I'm doing. It may
be that the current code deals with the flag but, even if it doesn't, the
spurious interrupt isn't the end of the world. I have a board at home that
advertises its PMU as xscale2, so I could test that this patch doesn't cause
breakage.
Will
next prev parent reply other threads:[~2012-02-21 15:57 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-21 4:37 [PATCH] ARM: perf: do not handle deleted counter in irq handler to avoid oops Ming Lei
2012-02-21 13:32 ` Will Deacon
2012-02-21 14:02 ` Ming Lei
2012-02-21 15:19 ` Will Deacon
2012-02-21 15:34 ` Ming Lei
2012-02-21 15:40 ` Will Deacon
2012-02-21 15:49 ` Ming Lei
2012-02-21 15:57 ` Will Deacon [this message]
2012-02-21 17:36 ` Will Deacon
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=20120221155707.GD23133@mudshark.cambridge.arm.com \
--to=will.deacon@arm.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).