789c299ca2
Here is a patch from Paul Mackerras that improves the ppc64 copy_tofrom_user.
The loop now does 32 bytes at a time and as well as pairing loads and stores.
A quick test case that reads 8kB over and over shows the improvement:
POWER6: 53% faster
POWER7: 51% faster
#define _XOPEN_SOURCE 500
#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/stat.h>
#define BUFSIZE (8 * 1024)
#define ITERATIONS 10000000
int main()
{
char tmpfile[] = "/tmp/copy_to_user_testXXXXXX";
int fd;
char *buf[BUFSIZE];
unsigned long i;
fd = mkstemp(tmpfile);
if (fd < 0) {
perror("open");
exit(1);
}
if (write(fd, buf, BUFSIZE) != BUFSIZE) {
perror("open");
exit(1);
}
for (i = 0; i < 10000000; i++) {
if (pread(fd, buf, BUFSIZE, 0) != BUFSIZE) {
perror("pread");
exit(1);
}
}
unlink(tmpfile);
return 0;
}
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
|
||
|---|---|---|
| .. | ||
| alloc.c | ||
| checksum_32.S | ||
| checksum_64.S | ||
| code-patching.c | ||
| copy_32.S | ||
| copypage_64.S | ||
| copyuser_64.S | ||
| crtsavres.S | ||
| devres.c | ||
| div64.S | ||
| feature-fixups-test.S | ||
| feature-fixups.c | ||
| locks.c | ||
| Makefile | ||
| mem_64.S | ||
| memcpy_64.S | ||
| rheap.c | ||
| sstep.c | ||
| string.S | ||
| usercopy_64.c | ||