From a3f952df3c6d205fe3b1e0e4848d3c3db4a28ef0 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Fri, 12 May 2017 13:28:10 +0930 Subject: powerpc: Tweak copy selection parameter in __copy_tofrom_user_power7() Experiments with the netperf benchmark indicated that the size selecting VMX-based copies in __copy_tofrom_user_power7() was suboptimal on POWER8. Measurements showed that parity was in the neighbourhood of 3328 bytes, rather than greater than 4096. The change gives a 1.5-2.0% improvement in performance for 4096-byte buffers, reducing the relative time spent in __copy_tofrom_user_power7() from approximately 7% to approximately 5% in the TCP_RR benchmark. Signed-off-by: Andrew Jeffery Acked-by: Anton Blanchard Signed-off-by: Michael Ellerman --- arch/powerpc/lib/copyuser_power7.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/lib') diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index a24b4039352c..706b7cc19846 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -82,14 +82,14 @@ _GLOBAL(__copy_tofrom_user_power7) #ifdef CONFIG_ALTIVEC cmpldi r5,16 - cmpldi cr1,r5,4096 + cmpldi cr1,r5,3328 std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy - bgt cr1,.Lvmx_copy + bge cr1,.Lvmx_copy #else cmpldi r5,16 -- cgit