tools/dma: Add dma_map_sg support

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

diff --git a/tools/dma/dma_map_benchmark.c b/tools/dma/dma_map_benchmark.c
index dd0ed528e6dfc9f90c0f1be594098917ea03206b..eab0ac611a23a9ac11ab3fed098237f445394d89 100644 (file)
--- a/tools/dma/dma_map_benchmark.c
+++ b/tools/dma/dma_map_benchmark.c
@@ -20,12 +20,19 @@ static char *directions[] = {
        "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 */
@@ -33,7 +40,7 @@ int main(int argc, char **argv)
 
        int cmd = DMA_MAP_BENCHMARK;
 
-       while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) {
+       while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:m:")) != -1) {
                switch (opt) {
                case 't':
                        threads = atoi(optarg);
@@ -56,11 +63,20 @@ int main(int argc, char **argv)
                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);
@@ -110,14 +126,15 @@ int main(int argc, char **argv)
        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: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
-                       threads, seconds, node, directions[dir], granule);
+       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",