linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: tony@atomide.com (Tony Lindgren)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] ARM: implement optimized percpu variable access
Date: Fri, 23 Nov 2012 12:32:27 -0800	[thread overview]
Message-ID: <20121123203226.GF5279@atomide.com> (raw)
In-Reply-To: <20121122113401.GC3113@mudshark.cambridge.arm.com>

* Will Deacon <will.deacon@arm.com> [121122 03:43]:
> Hi Rob,
> 
> On Sun, Nov 11, 2012 at 03:20:40AM +0000, Rob Herring wrote:
> > From: Rob Herring <rob.herring@calxeda.com>
> > 
> > Use the previously unused TPIDRPRW register to store percpu offsets.
> > TPIDRPRW is only accessible in PL1, so it can only be used in the kernel.
> > 
> > This saves 2 loads for each percpu variable access which should yield
> > improved performance, but the improvement has not been quantified.
> > 
> > Signed-off-by: Rob Herring <rob.herring@calxeda.com>
> > ---
> >  arch/arm/include/asm/Kbuild   |    1 -
> >  arch/arm/include/asm/percpu.h |   44 +++++++++++++++++++++++++++++++++++++++++
> >  arch/arm/kernel/smp.c         |    3 +++
> >  3 files changed, 47 insertions(+), 1 deletion(-)
> >  create mode 100644 arch/arm/include/asm/percpu.h
> 
> Russell pointed out to me that this patch will break on v6 CPUs if they don't
> have the thread ID registers and we're running with SMP_ON_UP=y. Looking at
> the TRMs, the only case we care about is 1136 < r1p0, but it does indeed break
> there (I have a board on my desk).

Sounds like it will break all omap2420 based systems like Nokia n8x0 :(

FYI those are booting with omap2plus_defconfig with SMP_ON_UP=y.

Regards,

Tony

  parent reply	other threads:[~2012-11-23 20:32 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-11  3:20 [PATCH] ARM: implement optimized percpu variable access Rob Herring
2012-11-12 10:23 ` Will Deacon
2012-11-12 13:03   ` Rob Herring
2012-11-12 13:28     ` Will Deacon
2012-11-12 14:03       ` Rob Herring
2012-11-27 17:29     ` Nicolas Pitre
2012-11-12 14:21   ` Rob Herring
2012-11-12 14:41     ` Will Deacon
2012-11-12 16:51       ` Will Deacon
2012-11-12 21:01         ` Rob Herring
2012-11-13 10:40           ` Will Deacon
2012-11-22 11:34 ` Will Deacon
2012-11-22 11:39   ` Russell King - ARM Linux
2012-11-23 17:06   ` Rob Herring
2012-11-23 17:12     ` Russell King - ARM Linux
2012-11-23 17:16     ` Will Deacon
2012-11-23 20:34       ` Tony Lindgren
2012-11-23 20:32   ` Tony Lindgren [this message]
2012-11-25 18:46   ` Rob Herring
2012-11-26 11:13     ` Will Deacon
2012-11-26 15:15       ` Will Deacon
2012-11-26 17:30         ` Rob Herring
2012-11-27 13:17           ` Will Deacon
2012-11-27 13:26             ` Russell King - ARM Linux
2012-11-26 21:58         ` Jamie Lokier
2012-11-26 23:50           ` Jamie Lokier
2012-11-27  1:02         ` Jamie Lokier
2012-11-27 22:02           ` Rob Herring
2012-11-28 12:34           ` Will Deacon
2012-11-27 17:35         ` Nicolas Pitre
2012-11-27 19:27           ` Nicolas Pitre
2012-11-27 17:19 ` Nicolas Pitre
2012-11-27 19:37   ` Rob Herring
2012-11-27 20:42     ` Rob Herring
2012-11-27 22:02       ` Nicolas Pitre

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=20121123203226.GF5279@atomide.com \
    --to=tony@atomide.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).