Implement a more optimal mutex fastpath for powerpc, making use of acquire
and release barrier semantics. This takes the mutex lock+unlock benchmark
from 203 to 173 cycles on a G5.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
---
Index: linux-2.6/arch/powerpc/include/asm/mutex.h
===
Speed up generic mutex implementations.
- atomic operations which both modify the variable and return something imply
full smp memory barriers before and after the memory operations involved
(failing atomic_cmpxchg, atomic_add_unless, etc don't imply a barrier because
they don't modify the t
> Would the examples (page copy, page clear) be an okay place to do it?
> These sections can't be preempted anyway (right?), and it's noted that
> doing it with AltiVec is a tad faster than using MMU tricks or standard
> copies?
I think typically page copying and clearing -are- preemptible. I'm n
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hello,
I recently built 2.6.27 with these patches on my PS3.
http://www.kernel.org/pub/linux/kernel/people/geoff/cell/ps3-linux-patches/ps3-wip/ps3vram-driver.patch
http://www.kernel.org/pub/linux/kernel/people/geoff/cell/ps3-linux-patches/ps3-wip/ps
Jon Loeliger wrote:
On Fri, 2008-10-10 at 09:04 -0500, Bill Gatliff wrote:
Jon Smirl wrote:
What do the device tree deities have to say about PWM support?
Dunno. What lists are they on? :)
Perhaps [EMAIL PROTECTED] too.
I thought this was what ePAPR was for.
Why would it need all that
Benjamin Herrenschmidt 写道:
> On Sun, 2008-10-12 at 02:00 +0800, Wang Jian wrote:
>> To avoid adding another rare used ata_port member, new bit is added to
>> ata_port->flags.
>>
>> Originally, I hacked pata_platform to make it 8bit only to support 8bit
>> data wired CF card. This patch is more gene
Benjamin Herrenschmidt wrote:
On Thu, 2008-10-09 at 10:37 -0500, Matt Sealey wrote:
Ahem, but nobody here wants AltiVec in the kernel do they?
It depends. We do use altivec in the kernel for example for
RAID accelerations.
The reason where we require a -real-good- reason to do it is
simply be
Hi,
I always have trouble getting an initial build to boot. Usually
it is with keyboards and video console. Currently, I can't seem to find
the root disk.
With the attached config I get the early messages, a pair of
"penguin" images. And then I think it says system restarting. Ha
On Wed, 2008-10-08 at 12:40 -0500, Scott Wood wrote:
>
> The performance difference most likely comes from the fact that copy
> to/from user can assume that the memory is cacheable, while memcpy is
> occasionally used on cache-inhibited memory -- so dcbz isn't used. We
> may be better off hand
On Thu, 2008-10-09 at 10:37 -0500, Matt Sealey wrote:
>
> Ahem, but nobody here wants AltiVec in the kernel do they?
It depends. We do use altivec in the kernel for example for
RAID accelerations.
The reason where we require a -real-good- reason to do it is
simply because of the drawbacks. The c
On Sun, 2008-10-12 at 02:00 +0800, Wang Jian wrote:
> To avoid adding another rare used ata_port member, new bit is added to
> ata_port->flags.
>
> Originally, I hacked pata_platform to make it 8bit only to support 8bit
> data wired CF card. This patch is more generic.
>
> With this patch, __pata
To avoid adding another rare used ata_port member, new bit is added to
ata_port->flags.
Originally, I hacked pata_platform to make it 8bit only to support 8bit
data wired CF card. This patch is more generic.
With this patch, __pata_platform_probe() interface is changed, and
pata_of_platform is br
On Fri, Oct 10, 2008 at 08:55:01PM +0400, Anton Vorontsov wrote:
> The driver supports very simple GPIO controllers, that is, when a
> controller provides just a 'data' register. Such controllers may be
> found in various BCSRs (Board's FPGAs used to control board's
> switches, LEDs, chip-selects,
13 matches
Mail list logo