mirror of
https://github.com/torvalds/linux.git
synced 2026-04-18 06:44:00 -04:00
Support for dma_map_sg, add option '-m' to distinguish mode.
i) Users can set option '-m' to select mode:
DMA_MAP_BENCH_SINGLE_MODE=0, DMA_MAP_BENCH_SG_MODE:=1
(The mode is also show in the test result).
ii) Users can set option '-g' to set sg_nents
(total count of entries in scatterlist)
the maximum number is 1024. Each of sg buf size is PAGE_SIZE.
e.g
[root@localhost]# ./dma_map_benchmark -m 1 -g 8 -t 8 -s 30 -d 2
dma mapping mode: DMA_MAP_BENCH_SG_MODE
dma mapping benchmark: threads:8 seconds:30 node:-1
dir:FROM_DEVICE granule/sg_nents: 8
average map latency(us):1.4 standard deviation:0.3
average unmap latency(us):1.3 standard deviation:0.3
[root@localhost]# ./dma_map_benchmark -m 0 -g 8 -t 8 -s 30 -d 2
dma mapping mode: DMA_MAP_BENCH_SINGLE_MODE
dma mapping benchmark: threads:8 seconds:30 node:-1
dir:FROM_DEVICE granule/sg_nents: 8
average map latency(us):1.0 standard deviation:0.3
average unmap latency(us):1.3 standard deviation:0.5
Reviewed-by: Barry Song <baohua@kernel.org>
Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260225093800.3625054-4-xiaqinxin@huawei.com
145 lines
3.2 KiB
C
145 lines
3.2 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2020 HiSilicon Limited.
|
|
*/
|
|
|
|
#include <fcntl.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <unistd.h>
|
|
#include <sys/ioctl.h>
|
|
#include <sys/mman.h>
|
|
#include <linux/map_benchmark.h>
|
|
|
|
#define NSEC_PER_MSEC 1000000L
|
|
|
|
static char *directions[] = {
|
|
"BIDIRECTIONAL",
|
|
"TO_DEVICE",
|
|
"FROM_DEVICE",
|
|
};
|
|
|
|
static char *mode[] = {
|
|
"SINGLE_MODE",
|
|
"SG_MODE",
|
|
};
|
|
|
|
int main(int argc, char **argv)
|
|
{
|
|
struct map_benchmark map;
|
|
int fd, opt;
|
|
/* default single thread, run 20 seconds on NUMA_NO_NODE */
|
|
int threads = 1, seconds = 20, node = -1;
|
|
/* default single map mode */
|
|
int map_mode = DMA_MAP_BENCH_SINGLE_MODE;
|
|
/* default dma mask 32bit, bidirectional DMA */
|
|
int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
|
|
/* default granule 1 PAGESIZE */
|
|
int granule = 1;
|
|
|
|
int cmd = DMA_MAP_BENCHMARK;
|
|
|
|
while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:m:")) != -1) {
|
|
switch (opt) {
|
|
case 't':
|
|
threads = atoi(optarg);
|
|
break;
|
|
case 's':
|
|
seconds = atoi(optarg);
|
|
break;
|
|
case 'n':
|
|
node = atoi(optarg);
|
|
break;
|
|
case 'b':
|
|
bits = atoi(optarg);
|
|
break;
|
|
case 'd':
|
|
dir = atoi(optarg);
|
|
break;
|
|
case 'x':
|
|
xdelay = atoi(optarg);
|
|
break;
|
|
case 'g':
|
|
granule = atoi(optarg);
|
|
break;
|
|
case 'm':
|
|
map_mode = atoi(optarg);
|
|
break;
|
|
default:
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
if (map_mode < 0 || map_mode >= DMA_MAP_BENCH_MODE_MAX) {
|
|
fprintf(stderr, "invalid map mode, SINGLE_MODE:%d, SG_MODE: %d\n",
|
|
DMA_MAP_BENCH_SINGLE_MODE, DMA_MAP_BENCH_SG_MODE);
|
|
exit(1);
|
|
}
|
|
|
|
if (threads <= 0 || threads > DMA_MAP_MAX_THREADS) {
|
|
fprintf(stderr, "invalid number of threads, must be in 1-%d\n",
|
|
DMA_MAP_MAX_THREADS);
|
|
exit(1);
|
|
}
|
|
|
|
if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) {
|
|
fprintf(stderr, "invalid number of seconds, must be in 1-%d\n",
|
|
DMA_MAP_MAX_SECONDS);
|
|
exit(1);
|
|
}
|
|
|
|
if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) {
|
|
fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n",
|
|
DMA_MAP_MAX_TRANS_DELAY);
|
|
exit(1);
|
|
}
|
|
|
|
/* suppose the mininum DMA zone is 1MB in the world */
|
|
if (bits < 20 || bits > 64) {
|
|
fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
|
|
exit(1);
|
|
}
|
|
|
|
if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE &&
|
|
dir != DMA_MAP_FROM_DEVICE) {
|
|
fprintf(stderr, "invalid dma direction\n");
|
|
exit(1);
|
|
}
|
|
|
|
if (granule < 1 || granule > 1024) {
|
|
fprintf(stderr, "invalid granule size\n");
|
|
exit(1);
|
|
}
|
|
|
|
fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
|
|
if (fd == -1) {
|
|
perror("open");
|
|
exit(1);
|
|
}
|
|
|
|
memset(&map, 0, sizeof(map));
|
|
map.seconds = seconds;
|
|
map.threads = threads;
|
|
map.node = node;
|
|
map.dma_bits = bits;
|
|
map.dma_dir = dir;
|
|
map.dma_trans_ns = xdelay;
|
|
map.granule = granule;
|
|
map.map_mode = map_mode;
|
|
|
|
if (ioctl(fd, cmd, &map)) {
|
|
perror("ioctl");
|
|
exit(1);
|
|
}
|
|
|
|
printf("dma mapping benchmark(%s): threads:%d seconds:%d node:%d dir:%s granule:%d\n",
|
|
mode[map_mode], threads, seconds, node, directions[dir], granule);
|
|
printf("average map latency(us):%.1f standard deviation:%.1f\n",
|
|
map.avg_map_100ns/10.0, map.map_stddev/10.0);
|
|
printf("average unmap latency(us):%.1f standard deviation:%.1f\n",
|
|
map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0);
|
|
|
|
return 0;
|
|
}
|