The padding field in the structure was previously reserved to maintain a stable interface for potential new fields, ensuring compatibility with user-space shared data structures. However,it was accidentally removed by tiantao in a prior commit, which may lead to incompatibility between user space and the kernel.

This patch reinstates the padding to restore the original structure layout and preserve compatibility.

Fixes: 8ddde07a3d28 ("dma-mapping: benchmark: extract a common header file for map_benchmark definition") Cc: stable@vger.kernel.org Signed-off-by: Qinxin Xia xiaqinxin@huawei.com --- include/linux/map_benchmark.h | 1 + 1 file changed, 1 insertion(+)

diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 62674c83bde4..2ac2fe52f248 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -27,5 +27,6 @@ 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 */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */

Support for dma scatter-gather mapping and is intended for testing mapping performance. It achieves by introducing the dma_sg_map_param structure and related functions, which enable the implementation of scatter-gather mapping preparation, mapping, and unmapping operations. Additionally, the dma_map_benchmark_ops array is updated to include operations for scatter-gather mapping. This commit aims to provide a wider range of mapping performance test to cater to different scenarios.

Signed-off-by: Qinxin Xia xiaqinxin@huawei.com --- include/linux/map_benchmark.h | 43 ++++++++++---- kernel/dma/map_benchmark.c | 103 ++++++++++++++++++++++++++++++++++ 2 files changed, 134 insertions(+), 12 deletions(-)

diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 5294dfd1870f..bf8c9ade43fd 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -17,22 +17,41 @@

enum { DMA_MAP_SINGLE_MODE, + DMA_MAP_SG_MODE, DMA_MAP_MODE_MAX };

+/** + * struct map_benchmark - Benchmarking data for DMA mapping operations. + * @avg_map_100ns: Average map latency in 100ns. + * @map_stddev: Standard deviation of map latency. + * @avg_unmap_100ns: Average unmap latency in 100ns. + * @unmap_stddev: Standard deviation of unmap latency. + * @threads: Number of threads performing map/unmap operations in parallel. + * @seconds: Duration of the test in seconds. + * @node: NUMA node on which this benchmark will run. + * @dma_bits: DMA addressing capability. + * @dma_dir: DMA data direction. + * @dma_trans_ns: Time for DMA transmission in ns. + * @granule: Number of PAGE_SIZE units to map/unmap at once. + In SG mode, this represents the number of scatterlist entries. + In single mode, this represents the total size of the mapping. + * @map_mode: Mode of DMA mapping. + * @expansion: Reserved for future use. + */ struct map_benchmark { - __u64 avg_map_100ns; /* average map latency in 100ns */ - __u64 map_stddev; /* standard deviation of map latency */ - __u64 avg_unmap_100ns; /* as above */ + __u64 avg_map_100ns; + __u64 map_stddev; + __u64 avg_unmap_100ns; __u64 unmap_stddev; - __u32 threads; /* how many threads will do map/unmap in parallel */ - __u32 seconds; /* how long the test will last */ - __s32 node; /* which numa node this benchmark will run on */ - __u32 dma_bits; /* DMA addressing capability */ - __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 map_mode; /* the mode of dma map */ - __u8 expansion[75]; /* For future use */ + __u32 threads; + __u32 seconds; + __s32 node; + __u32 dma_bits; + __u32 dma_dir; + __u32 dma_trans_ns; + __u32 granule; + __u8 map_mode; + __u8 expansion[75]; }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 47a06b891db8..3a996be9fb22 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/platform_device.h> +#include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/timekeeping.h>

@@ -111,8 +112,110 @@ static struct map_benchmark_ops dma_single_map_benchmark_ops = { .do_unmap = dma_single_map_benchmark_do_unmap, };

+struct dma_sg_map_param { + struct sg_table sgt; + struct device *dev; + void **buf; + u32 npages; + u32 dma_dir; +}; + +static void *dma_sg_map_benchmark_prepare(struct map_benchmark_data *map) +{ + struct scatterlist *sg; + int i; + + struct dma_sg_map_param *params __free(kfree) = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return NULL; + + /* + * Set the number of scatterlist entries based on the granule. + * In SG mode, 'granule' represents the number of scatterlist entries. + * Each scatterlist entry corresponds to a single page. + */ + params->npages = map->bparam.granule; + params->dma_dir = map->bparam.dma_dir; + params->dev = map->dev; + params->buf = kmalloc_array(params->npages, sizeof(*params->buf), + GFP_KERNEL); + if (!params->buf) + goto out; + + if (sg_alloc_table(&params->sgt, params->npages, GFP_KERNEL)) + goto free_buf; + + for_each_sgtable_sg(&params->sgt, sg, i) { + params->buf[i] = (void *)__get_free_page(GFP_KERNEL); + if (!params->buf[i]) + goto free_page; + + if (params->dma_dir != DMA_FROM_DEVICE) + memset(params->buf[i], 0x66, PAGE_SIZE); + + sg_set_buf(sg, params->buf[i], PAGE_SIZE); + } + + return_ptr(params); + +free_page: + while (i-- > 0) + free_page((unsigned long)params->buf[i]); + + sg_free_table(&params->sgt); +free_buf: + kfree(params->buf); +out: + return NULL; +} + +static void dma_sg_map_benchmark_unprepare(void *mparam) +{ + struct dma_sg_map_param *params = mparam; + int i; + + for (i = 0; i < params->npages; i++) + free_page((unsigned long)params->buf[i]); + + sg_free_table(&params->sgt); + + kfree(params->buf); + kfree(params); +} + +static int dma_sg_map_benchmark_do_map(void *mparam) +{ + struct dma_sg_map_param *params = mparam; + int ret = 0; + + int sg_mapped = dma_map_sg(params->dev, params->sgt.sgl, + params->npages, params->dma_dir); + if (!sg_mapped) { + pr_err("dma_map_sg failed on %s\n", dev_name(params->dev)); + ret = -ENOMEM; + } + + return ret; +} + +static void dma_sg_map_benchmark_do_unmap(void *mparam) +{ + struct dma_sg_map_param *params = mparam; + + dma_unmap_sg(params->dev, params->sgt.sgl, params->npages, + params->dma_dir); +} + +static struct map_benchmark_ops dma_sg_map_benchmark_ops = { + .prepare = dma_sg_map_benchmark_prepare, + .unprepare = dma_sg_map_benchmark_unprepare, + .do_map = dma_sg_map_benchmark_do_map, + .do_unmap = dma_sg_map_benchmark_do_unmap, +}; + static struct map_benchmark_ops *dma_map_benchmark_ops[DMA_MAP_MODE_MAX] = { [DMA_MAP_SINGLE_MODE] = &dma_single_map_benchmark_ops, + [DMA_MAP_SG_MODE] = &dma_sg_map_benchmark_ops, };

static int map_benchmark_thread(void *data)

Support for dma_map_sg, add option '-m' to distinguish mode.

i) Users can set option '-m' to select mode: DMA_MAP_SINGLE_MODE=0, DMA_MAP_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_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_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

Signed-off-by: Qinxin Xia xiaqinxin@huawei.com --- tools/testing/selftests/dma/dma_map_benchmark.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index b12f1f9babf8..036ddb5ac862 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -27,6 +27,7 @@ int main(int argc, char **argv) int fd, opt; /* default single thread, run 20 seconds on NUMA_NO_NODE */ int threads = 1, seconds = 20, node = -1; + int map_mode = DMA_MAP_SINGLE_MODE; /* default dma mask 32bit, bidirectional DMA */ int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL; /* default granule 1 PAGESIZE */ @@ -34,7 +35,7 @@ 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); @@ -57,11 +58,20 @@ 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 >= DMA_MAP_MODE_MAX) { + fprintf(stderr, "invalid map mode, DMA_MAP_SINGLE_MODE:%d, DMA_MAP_SG_MODE:%d\n", + DMA_MAP_SINGLE_MODE, DMA_MAP_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); @@ -111,13 +121,15 @@ 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", + printf("dma mapping mode: %d\n", map_mode); + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule/sg_nents: %d\n", threads, seconds, node, dir[directions], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0);