linux/tools/perf/bench/mem-memcpy.c
Ian Munsie c055564217 perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR()
Parsing an option from the command line with OPT_BOOLEAN on a
bool data type would not work on a big-endian machine due to the
manner in which the boolean was being cast into an int and
incremented. For example, running 'perf probe --list' on a
PowerPC machine would fail to properly set the list_events bool
and would therefore print out the usage information and
terminate.

This patch makes OPT_BOOLEAN work as expected with a bool
datatype. For cases where the original OPT_BOOLEAN was
intentionally being used to increment an int each time it was
passed in on the command line, this patch introduces OPT_INCR
with the old behaviour of OPT_BOOLEAN (the verbose variable is
currently the only such example of this).

I have reviewed every use of OPT_BOOLEAN to verify that a true
C99 bool was passed. Where integers were used, I verified that
they were only being used for boolean logic and changed them to
bools to ensure that they would not be mistakenly used as ints.
The major exception was the verbose variable which now uses
OPT_INCR instead of OPT_BOOLEAN.

Signed-off-by: Ian Munsie <imunsie@au.ibm.com>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport
Cc: Git development list <git@vger.kernel.org>
Cc: Ian Munsie <imunsie@au1.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Eric B Munson <ebmunson@us.ibm.com>
Cc: Valdis.Kletnieks@vt.edu
Cc: WANG Cong <amwang@redhat.com>
Cc: Thiago Farina <tfransosi@gmail.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: John Kacur <jkacur@redhat.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-14 11:26:44 +02:00

192 lines
4.1 KiB
C

/*
* mem-memcpy.c
*
* memcpy: Simple memory copy in various ways
*
* Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*/
#include <ctype.h>
#include "../perf.h"
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../util/header.h"
#include "bench.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#include <errno.h>
#define K 1024
static const char *length_str = "1MB";
static const char *routine = "default";
static bool use_clock = false;
static int clock_fd;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
"Specify length of memory to copy. "
"available unit: B, MB, GB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
"Specify routine to copy"),
OPT_BOOLEAN('c', "clock", &use_clock,
"Use CPU clock for measuring"),
OPT_END()
};
struct routine {
const char *name;
const char *desc;
void * (*fn)(void *dst, const void *src, size_t len);
};
struct routine routines[] = {
{ "default",
"Default memcpy() provided by glibc",
memcpy },
{ NULL,
NULL,
NULL }
};
static const char * const bench_mem_memcpy_usage[] = {
"perf bench mem memcpy <options>",
NULL
};
static struct perf_event_attr clock_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
static void init_clock(void)
{
clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
if (clock_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
BUG_ON(clock_fd < 0);
}
static u64 get_clock(void)
{
int ret;
u64 clk;
ret = read(clock_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
}
static double timeval2double(struct timeval *ts)
{
return (double)ts->tv_sec +
(double)ts->tv_usec / (double)1000000;
}
int bench_mem_memcpy(int argc, const char **argv,
const char *prefix __used)
{
int i;
void *dst, *src;
size_t length;
double bps = 0.0;
struct timeval tv_start, tv_end, tv_diff;
u64 clock_start, clock_end, clock_diff;
clock_start = clock_end = clock_diff = 0ULL;
argc = parse_options(argc, argv, options,
bench_mem_memcpy_usage, 0);
tv_diff.tv_sec = 0;
tv_diff.tv_usec = 0;
length = (size_t)perf_atoll((char *)length_str);
if ((s64)length <= 0) {
fprintf(stderr, "Invalid length:%s\n", length_str);
return 1;
}
for (i = 0; routines[i].name; i++) {
if (!strcmp(routines[i].name, routine))
break;
}
if (!routines[i].name) {
printf("Unknown routine:%s\n", routine);
printf("Available routines...\n");
for (i = 0; routines[i].name; i++) {
printf("\t%s ... %s\n",
routines[i].name, routines[i].desc);
}
return 1;
}
dst = zalloc(length);
if (!dst)
die("memory allocation failed - maybe length is too large?\n");
src = zalloc(length);
if (!src)
die("memory allocation failed - maybe length is too large?\n");
if (bench_format == BENCH_FORMAT_DEFAULT) {
printf("# Copying %s Bytes from %p to %p ...\n\n",
length_str, src, dst);
}
if (use_clock) {
init_clock();
clock_start = get_clock();
} else {
BUG_ON(gettimeofday(&tv_start, NULL));
}
routines[i].fn(dst, src, length);
if (use_clock) {
clock_end = get_clock();
clock_diff = clock_end - clock_start;
} else {
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
bps = (double)((double)length / timeval2double(&tv_diff));
}
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (use_clock) {
printf(" %14lf Clock/Byte\n",
(double)clock_diff / (double)length);
} else {
if (bps < K)
printf(" %14lf B/Sec\n", bps);
else if (bps < K * K)
printf(" %14lfd KB/Sec\n", bps / 1024);
else if (bps < K * K * K)
printf(" %14lf MB/Sec\n", bps / 1024 / 1024);
else {
printf(" %14lf GB/Sec\n",
bps / 1024 / 1024 / 1024);
}
}
break;
case BENCH_FORMAT_SIMPLE:
if (use_clock) {
printf("%14lf\n",
(double)clock_diff / (double)length);
} else
printf("%lf\n", bps);
break;
default:
/* reaching this means there's some disaster: */
die("unknown format: %d\n", bench_format);
break;
}
return 0;
}