mainline inclusion from mainline-v7.1-rc1 commit 9cc60ec453fe5d58d4faa70829814769a8af24d4 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/9215 CVE: NA Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... ---------------------------------------------------------------------- This patch adjusts the DMA map benchmark framework to make the DMA map benchmark framework more flexible and adaptable to other mapping modes in the future. By abstracting the framework into five interfaces: prepare, unprepare, initialize_data, do_map, and do_unmap. The new map schema can be introduced more easily without major modifications to the existing code structure. 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/20260225093800.3625054-2-xiaqinxin@huawei.com Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> --- include/linux/map_benchmark.h | 8 ++- kernel/dma/map_benchmark.c | 131 ++++++++++++++++++++++++++++------ 2 files changed, 115 insertions(+), 24 deletions(-) diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 48e2ff95332f..bd933874a812 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -15,6 +15,11 @@ #define DMA_MAP_TO_DEVICE 1 #define DMA_MAP_FROM_DEVICE 2 +enum { + DMA_MAP_BENCH_SINGLE_MODE, + DMA_MAP_BENCH_MODE_MAX +}; + struct map_benchmark { __u64 avg_map_100ns; /* average map latency in 100ns */ __u64 map_stddev; /* standard deviation of map latency */ @@ -27,6 +32,7 @@ struct map_benchmark { __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ - __u8 expansion[76]; /* For future use */ + __u8 map_mode; /* the mode of dma map */ + __u8 expansion[75]; /* For future use */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 23aeba267cfa..ebad333b0bf2 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -5,6 +5,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cleanup.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/device.h> @@ -34,17 +35,105 @@ struct map_benchmark_data { atomic64_t loops; }; +struct map_benchmark_ops { + void *(*prepare)(struct map_benchmark_data *map); + void (*unprepare)(void *mparam); + void (*initialize_data)(void *mparam); + int (*do_map)(void *mparam); + void (*do_unmap)(void *mparam); +}; + +struct dma_single_map_param { + struct device *dev; + dma_addr_t addr; + void *xbuf; + u32 npages; + u32 dma_dir; +}; + +static void *dma_single_map_benchmark_prepare(struct map_benchmark_data *map) +{ + struct dma_single_map_param *params __free(kfree) = kzalloc(sizeof(*params), + GFP_KERNEL); + if (!params) + return NULL; + + params->npages = map->bparam.granule; + params->dma_dir = map->bparam.dma_dir; + params->dev = map->dev; + params->xbuf = alloc_pages_exact(params->npages * PAGE_SIZE, GFP_KERNEL); + if (!params->xbuf) + return NULL; + + return_ptr(params); +} + +static void dma_single_map_benchmark_unprepare(void *mparam) +{ + struct dma_single_map_param *params = mparam; + + free_pages_exact(params->xbuf, params->npages * PAGE_SIZE); + kfree(params); +} + +static void dma_single_map_benchmark_initialize_data(void *mparam) +{ + struct dma_single_map_param *params = mparam; + + /* + * for a non-coherent device, if we don't stain them in the + * cache, this will give an underestimate of the real-world + * overhead of BIDIRECTIONAL or TO_DEVICE mappings; + * 66 means everything goes well! 66 is lucky. + */ + if (params->dma_dir != DMA_FROM_DEVICE) + memset(params->xbuf, 0x66, params->npages * PAGE_SIZE); +} + +static int dma_single_map_benchmark_do_map(void *mparam) +{ + struct dma_single_map_param *params = mparam; + + params->addr = dma_map_single(params->dev, params->xbuf, + params->npages * PAGE_SIZE, params->dma_dir); + if (unlikely(dma_mapping_error(params->dev, params->addr))) { + pr_err("dma_map_single failed on %s\n", dev_name(params->dev)); + return -ENOMEM; + } + + return 0; +} + +static void dma_single_map_benchmark_do_unmap(void *mparam) +{ + struct dma_single_map_param *params = mparam; + + dma_unmap_single(params->dev, params->addr, + params->npages * PAGE_SIZE, params->dma_dir); +} + +static struct map_benchmark_ops dma_single_map_benchmark_ops = { + .prepare = dma_single_map_benchmark_prepare, + .unprepare = dma_single_map_benchmark_unprepare, + .initialize_data = dma_single_map_benchmark_initialize_data, + .do_map = dma_single_map_benchmark_do_map, + .do_unmap = dma_single_map_benchmark_do_unmap, +}; + +static struct map_benchmark_ops *dma_map_benchmark_ops[DMA_MAP_BENCH_MODE_MAX] = { + [DMA_MAP_BENCH_SINGLE_MODE] = &dma_single_map_benchmark_ops, +}; + static int map_benchmark_thread(void *data) { - void *buf; - dma_addr_t dma_addr; struct map_benchmark_data *map = data; - int npages = map->bparam.granule; - u64 size = npages * PAGE_SIZE; + __u8 map_mode = map->bparam.map_mode; int ret = 0; - buf = alloc_pages_exact(size, GFP_KERNEL); - if (!buf) + struct map_benchmark_ops *mb_ops = dma_map_benchmark_ops[map_mode]; + void *mparam = mb_ops->prepare(map); + + if (!mparam) return -ENOMEM; while (!kthread_should_stop()) { @@ -52,23 +141,12 @@ static int map_benchmark_thread(void *data) ktime_t map_stime, map_etime, unmap_stime, unmap_etime; ktime_t map_delta, unmap_delta; - /* - * for a non-coherent device, if we don't stain them in the - * cache, this will give an underestimate of the real-world - * overhead of BIDIRECTIONAL or TO_DEVICE mappings; - * 66 means evertything goes well! 66 is lucky. - */ - if (map->dir != DMA_FROM_DEVICE) - memset(buf, 0x66, size); - + mb_ops->initialize_data(mparam); map_stime = ktime_get(); - dma_addr = dma_map_single(map->dev, buf, size, map->dir); - if (unlikely(dma_mapping_error(map->dev, dma_addr))) { - pr_err("dma_map_single failed on %s\n", - dev_name(map->dev)); - ret = -ENOMEM; + ret = mb_ops->do_map(mparam); + if (ret) goto out; - } + map_etime = ktime_get(); map_delta = ktime_sub(map_etime, map_stime); @@ -76,7 +154,8 @@ static int map_benchmark_thread(void *data) ndelay(map->bparam.dma_trans_ns); unmap_stime = ktime_get(); - dma_unmap_single(map->dev, dma_addr, size, map->dir); + mb_ops->do_unmap(mparam); + unmap_etime = ktime_get(); unmap_delta = ktime_sub(unmap_etime, unmap_stime); @@ -111,7 +190,7 @@ static int map_benchmark_thread(void *data) } out: - free_pages_exact(buf, size); + mb_ops->unprepare(mparam); return ret; } @@ -212,6 +291,12 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case DMA_MAP_BENCHMARK: + if (map->bparam.map_mode < 0 || + map->bparam.map_mode >= DMA_MAP_BENCH_MODE_MAX) { + pr_err("invalid map mode\n"); + return -EINVAL; + } + if (map->bparam.threads == 0 || map->bparam.threads > DMA_MAP_MAX_THREADS) { pr_err("invalid thread number\n"); -- 2.33.0

mainline inclusion from mainline-v7.1-rc1 commit a54302ccfd38afba7b297566f0d414b961ca97bf category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/9215 CVE: NA Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... ---------------------------------------------------------------------- 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 Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com> Signed-off-by: Hongye Lin <linhongye@h-partners.com> --- .../testing/selftests/dma/dma_map_benchmark.c | 23 ++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index 5c997f17fcbd..093998caa148 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -21,12 +21,19 @@ 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 */ @@ -35,7 +42,7 @@ int main(int argc, char **argv) int cmd = DMA_MAP_BENCHMARK; char *p; - 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); @@ -58,11 +65,20 @@ 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); @@ -112,14 +128,15 @@ 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, dir[directions], 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", -- 2.33.0