diff options
author | Mark Nelson <markn@au1.ibm.com> | 2008-08-22 14:39:00 +1000 |
---|---|---|
committer | Paul Mackerras <paulus@samba.org> | 2008-09-15 11:07:42 -0700 |
commit | 57dda6ef5bd5b9e60410477ad29e654097e2cca1 (patch) | |
tree | 5d9ea334a65752d440e2cef79cb33156fe97d585 | |
parent | 2a9294369bd020db89bfdf78b84c3615b39a5c84 (diff) | |
download | op-kernel-dev-57dda6ef5bd5b9e60410477ad29e654097e2cca1.zip op-kernel-dev-57dda6ef5bd5b9e60410477ad29e654097e2cca1.tar.gz |
powerpc: New copy_4K_page()
This new copy_4K_page() function was originally tuned for the best
performance on the Cell processor, but after testing on more 64bit
powerpc chips it was found that with a small modification it either
matched the performance offered by the current mainline version or
bettered it by a small amount.
It was found that on a Cell-based QS22 blade the amount of system
time measured when compiling a 2.6.26 pseries_defconfig decreased
by 4%. Using the same test, a 4-way 970MP machine saw a decrease of
2% in system time. No noticeable change was seen on Power4, Power5
or Power6.
The 4096 byte page is copied in thirty-two 128 byte strides. An
initial setup loop executes dcbt instructions for the whole source
page and dcbz instructions for the whole destination page. To do
this, the cache line size is retrieved from ppc64_caches.
A new CPU feature bit, CPU_FTR_CP_USE_DCBTZ, (introduced in the
previous patch) is used to make the modification to this new copy
routine - on Power4, 970 and Cell the feature bit is set so the
setup loop is executed, but on all other 64bit chips the setup
loop is nop'ed out.
Signed-off-by: Mark Nelson <markn@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
-rw-r--r-- | arch/powerpc/lib/copypage_64.S | 198 |
1 files changed, 93 insertions, 105 deletions
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index f9837f4..75f3267 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -1,5 +1,5 @@ /* - * Copyright (C) 2002 Paul Mackerras, IBM Corp. + * Copyright (C) 2008 Mark Nelson, IBM Corp. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -8,112 +8,100 @@ */ #include <asm/processor.h> #include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + + .section ".toc","aw" +PPC64_CACHES: + .tc ppc64_caches[TC],ppc64_caches + .section ".text" + _GLOBAL(copy_4K_page) - std r31,-8(1) - std r30,-16(1) - std r29,-24(1) - std r28,-32(1) - std r27,-40(1) - std r26,-48(1) - std r25,-56(1) - std r24,-64(1) - std r23,-72(1) - std r22,-80(1) - std r21,-88(1) - std r20,-96(1) - li r5,4096/32 - 1 + li r5,4096 /* 4K page size */ +BEGIN_FTR_SECTION + ld r10,PPC64_CACHES@toc(r2) + lwz r11,DCACHEL1LOGLINESIZE(r10) /* log2 of cache line size */ + lwz r12,DCACHEL1LINESIZE(r10) /* get cache line size */ + li r9,0 + srd r8,r5,r11 + + mtctr r8 +setup: + dcbt r9,r4 + dcbz r9,r3 + add r9,r9,r12 + bdnz setup +END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ) addi r3,r3,-8 - li r12,5 -0: addi r5,r5,-24 - mtctr r12 - ld r22,640(4) - ld r21,512(4) - ld r20,384(4) - ld r11,256(4) - ld r9,128(4) - ld r7,0(4) - ld r25,648(4) - ld r24,520(4) - ld r23,392(4) - ld r10,264(4) - ld r8,136(4) - ldu r6,8(4) - cmpwi r5,24 -1: std r22,648(3) - std r21,520(3) - std r20,392(3) - std r11,264(3) - std r9,136(3) - std r7,8(3) - ld r28,648(4) - ld r27,520(4) - ld r26,392(4) - ld r31,264(4) - ld r30,136(4) - ld r29,8(4) - std r25,656(3) - std r24,528(3) - std r23,400(3) - std r10,272(3) - std r8,144(3) - std r6,16(3) - ld r22,656(4) - ld r21,528(4) - ld r20,400(4) - ld r11,272(4) - ld r9,144(4) - ld r7,16(4) - std r28,664(3) - std r27,536(3) - std r26,408(3) - std r31,280(3) - std r30,152(3) - stdu r29,24(3) - ld r25,664(4) - ld r24,536(4) - ld r23,408(4) - ld r10,280(4) - ld r8,152(4) - ldu r6,24(4) + srdi r8,r5,7 /* page is copied in 128 byte strides */ + addi r8,r8,-1 /* one stride copied outside loop */ + + mtctr r8 + + ld r5,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ldu r8,24(r4) +1: std r5,8(r3) + ld r9,8(r4) + std r6,16(r3) + ld r10,16(r4) + std r7,24(r3) + ld r11,24(r4) + std r8,32(r3) + ld r12,32(r4) + std r9,40(r3) + ld r5,40(r4) + std r10,48(r3) + ld r6,48(r4) + std r11,56(r3) + ld r7,56(r4) + std r12,64(r3) + ld r8,64(r4) + std r5,72(r3) + ld r9,72(r4) + std r6,80(r3) + ld r10,80(r4) + std r7,88(r3) + ld r11,88(r4) + std r8,96(r3) + ld r12,96(r4) + std r9,104(r3) + ld r5,104(r4) + std r10,112(r3) + ld r6,112(r4) + std r11,120(r3) + ld r7,120(r4) + stdu r12,128(r3) + ldu r8,128(r4) bdnz 1b - std r22,648(3) - std r21,520(3) - std r20,392(3) - std r11,264(3) - std r9,136(3) - std r7,8(3) - addi r4,r4,640 - addi r3,r3,648 - bge 0b - mtctr r5 - ld r7,0(4) - ld r8,8(4) - ldu r9,16(4) -3: ld r10,8(4) - std r7,8(3) - ld r7,16(4) - std r8,16(3) - ld r8,24(4) - std r9,24(3) - ldu r9,32(4) - stdu r10,32(3) - bdnz 3b -4: ld r10,8(4) - std r7,8(3) - std r8,16(3) - std r9,24(3) - std r10,32(3) -9: ld r20,-96(1) - ld r21,-88(1) - ld r22,-80(1) - ld r23,-72(1) - ld r24,-64(1) - ld r25,-56(1) - ld r26,-48(1) - ld r27,-40(1) - ld r28,-32(1) - ld r29,-24(1) - ld r30,-16(1) - ld r31,-8(1) + + std r5,8(r3) + ld r9,8(r4) + std r6,16(r3) + ld r10,16(r4) + std r7,24(r3) + ld r11,24(r4) + std r8,32(r3) + ld r12,32(r4) + std r9,40(r3) + ld r5,40(r4) + std r10,48(r3) + ld r6,48(r4) + std r11,56(r3) + ld r7,56(r4) + std r12,64(r3) + ld r8,64(r4) + std r5,72(r3) + ld r9,72(r4) + std r6,80(r3) + ld r10,80(r4) + std r7,88(r3) + ld r11,88(r4) + std r8,96(r3) + ld r12,96(r4) + std r9,104(r3) + std r10,112(r3) + std r11,120(r3) + std r12,128(r3) blr |