From fde69282b7ba2701560764b81ebb756deb98cf2b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 29 May 2012 19:33:12 +0000 Subject: powerpc: POWER7 optimised copy_page using VMX and enhanced prefetch Implement a POWER7 optimised copy_page using VMX and enhanced prefetch instructions. We use enhanced prefetch hints to prefetch both the load and store side. We copy a cacheline at a time and fall back to regular loads and stores if we are unable to use VMX (eg we are in an interrupt). The following microbenchmark was used to assess the impact of the patch: http://ozlabs.org/~anton/junkcode/page_fault_file.c We test MAP_PRIVATE page faults across a 1GB file, 100 times: # time ./page_fault_file -p -l 1G -i 100 Before: 22.25s After: 18.89s 17% faster Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/lib/copypage_64.S | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/powerpc/lib/copypage_64.S') diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 53dcb6b1b708..9f9434a85264 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -17,7 +17,11 @@ PPC64_CACHES: .section ".text" _GLOBAL(copy_page) +BEGIN_FTR_SECTION lis r5,PAGE_SIZE@h +FTR_SECTION_ELSE + b .copypage_power7 +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION ld r10,PPC64_CACHES@toc(r2) -- cgit v1.2.1