kernel-ark/arch/arm/lib/copy_page.S
Kirill A. Shutemov dca230f00d ARM: 5701/1: ARM: copy_page.S: take into account the size of the cache line
Optimized version of copy_page() was written with assumption that cache
line size is 32 bytes. On Cortex-A8 cache line size is 64 bytes.

This patch tries to generalize copy_page() to work with any cache line
size if cache line size is multiple of 16 and page size is multiple of
two cache line size.

After this optimization we've got ~25% speedup on OMAP3(tested in
userspace).

There is test for kernelspace which trigger copy-on-write after fork():

 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>

 #define BUF_SIZE (10000*4096)
 #define NFORK 200

 int main(int argc, char **argv)
 {
         char *buf = malloc(BUF_SIZE);
         int i;

         memset(buf, 0, BUF_SIZE);

         for(i = 0; i < NFORK; i++) {
                 if (fork()) {
                         wait(NULL);
                 } else {
                         int j;

                         for(j = 0; j < BUF_SIZE; j+= 4096)
                                 buf[j] = (j & 0xFF) + 1;
                         break;
                 }
         }

         free(buf);
         return 0;
 }

Before optimization this test takes ~66 seconds, after optimization
takes ~56 seconds.

Signed-off-by: Siarhei Siamashka <siarhei.siamashka@nokia.com>
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-09-15 22:07:02 +01:00

48 lines
1.3 KiB
ArmAsm

/*
* linux/arch/arm/lib/copypage.S
*
* Copyright (C) 1995-1999 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* ASM optimised string functions
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/cache.h>
#define COPY_COUNT (PAGE_SZ / (2 * L1_CACHE_BYTES) PLD( -1 ))
.text
.align 5
/*
* StrongARM optimised copy_page routine
* now 1.78bytes/cycle, was 1.60 bytes/cycle (50MHz bus -> 89MB/s)
* Note that we probably achieve closer to the 100MB/s target with
* the core clock switching.
*/
ENTRY(copy_page)
stmfd sp!, {r4, lr} @ 2
PLD( pld [r1, #0] )
PLD( pld [r1, #L1_CACHE_BYTES] )
mov r2, #COPY_COUNT @ 1
ldmia r1!, {r3, r4, ip, lr} @ 4+1
1: PLD( pld [r1, #2 * L1_CACHE_BYTES])
PLD( pld [r1, #3 * L1_CACHE_BYTES])
2:
.rept (2 * L1_CACHE_BYTES / 16 - 1)
stmia r0!, {r3, r4, ip, lr} @ 4
ldmia r1!, {r3, r4, ip, lr} @ 4
.endr
subs r2, r2, #1 @ 1
stmia r0!, {r3, r4, ip, lr} @ 4
ldmgtia r1!, {r3, r4, ip, lr} @ 4
bgt 1b @ 1
PLD( ldmeqia r1!, {r3, r4, ip, lr} )
PLD( beq 2b )
ldmfd sp!, {r4, pc} @ 3
ENDPROC(copy_page)