powerpc: Improve scheduling of system call entry instructions
commitf5f0307f42d39a51a925ca4841f76a2f2ea330ff
authorAnton Blanchard <anton@samba.org>
Sun, 8 May 2011 21:36:44 +0000 (8 21:36 +0000)
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>
Thu, 19 May 2011 04:30:42 +0000 (19 14:30 +1000)
tree5dbaa4b57f6726537e1fd2ba6eb7c97854d85610
parentba00ce1d6e08ad06f19f2ac53fd5c60bbe3fbeeb
powerpc: Improve scheduling of system call entry instructions

After looking at our system call path, Mary Brown suggested that we
should put all mfspr SRR* instructions before any mtspr SRR*.

To test this I used a very simple null syscall (actually getppid)
testcase at http://ozlabs.org/~anton/junkcode/null_syscall.c

I tested with the following changes against the pseries_defconfig:

CONFIG_VIRT_CPU_ACCOUNTING=n
CONFIG_AUDIT=n

to remove the overhead of virtual CPU accounting and syscall
auditing.

POWER6:
baseline:       mean = 757.2 cycles       sd = 2.108
modified:       mean = 759.1 cycles       sd = 2.020

POWER7:
baseline:       mean = 411.4 cycles       sd = 0.138
modified:       mean = 404.1 cycles       sd = 0.109

So we have 1.77% improvement on POWER7 which looks significant. The
POWER6 suggest a 0.25% slowdown, but the results are within 1
standard deviation and may be in the noise.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
arch/powerpc/kernel/exceptions-64s.S