Commit ca947482 authored by Xiang Chen's avatar Xiang Chen Committed by Christoph Hellwig
Browse files

dma-mapping: benchmark: Add support for multi-pages map/unmap 



Currently it only support one page map/unmap once a time for dma-map
benchmark, but there are some other scenaries which need to support for
multi-page map/unmap: for those multi-pages interfaces such as
dma_alloc_coherent() and dma_map_sg(), the time spent on multi-pages
map/unmap is not the time of a single page * npages (not linear) as it
may use block description instead of page description when it is satified
with the size such as 2M/1G, and also it can send a single TLB invalidation
command to invalidate multi-pages instead of multi-times when RIL is
enabled (which will short the time of unmap). So it is necessary to add
support for multi-pages map/unmap.

Add a parameter "-g" to support multi-pages map/unmap.

Signed-off-by: default avatarXiang Chen <chenxiang66@hisilicon.com>
Acked-by: default avatarBarry Song <song.bao.hua@hisilicon.com>
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
parent 42e4eefb

kernel/dma/map_benchmark.c

+14 −7
Original line number Diff line number Diff line
@@ -38,7 +38,8 @@ struct map_benchmark { 
	__u32 dma_bits; /* DMA addressing capability */

	__u32 dma_dir; /* DMA data direction */

	__u32 dma_trans_ns; /* time for DMA transmission in ns */

	__u8 expansion[80];	/* For future use */

	__u32 granule;	/* how many PAGE_SIZE will do map/unmap once a time */

	__u8 expansion[76];	/* For future use */

};



struct map_benchmark_data {
@@ -58,9 +59,11 @@ 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;

	int ret = 0;



	buf = (void *)__get_free_page(GFP_KERNEL);

	buf = alloc_pages_exact(size, GFP_KERNEL);

	if (!buf)

		return -ENOMEM;
@@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data) 
		 * 66 means evertything goes well! 66 is lucky.

		 */

		if (map->dir != DMA_FROM_DEVICE)

			memset(buf, 0x66, PAGE_SIZE);

			memset(buf, 0x66, size);



		map_stime = ktime_get();

		dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir);

		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));
@@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data) 
		ndelay(map->bparam.dma_trans_ns);



		unmap_stime = ktime_get();

		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);

		dma_unmap_single(map->dev, dma_addr, size, map->dir);

		unmap_etime = ktime_get();

		unmap_delta = ktime_sub(unmap_etime, unmap_stime);
@@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data) 
	}



out:

	free_page((unsigned long)buf);

	free_pages_exact(buf, size);

	return ret;

}
@@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, 
	struct map_benchmark_data *map = file->private_data;

	void __user *argp = (void __user *)arg;

	u64 old_dma_mask;



	int ret;



	if (copy_from_user(&map->bparam, argp, sizeof(map->bparam)))
@@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, 
			return -EINVAL;

		}



		if (map->bparam.granule < 1 || map->bparam.granule > 1024) {

			pr_err("invalid granule size\n");

			return -EINVAL;

		}



		switch (map->bparam.dma_dir) {

		case DMA_MAP_BIDIRECTIONAL:

			map->dir = DMA_BIDIRECTIONAL;

tools/testing/selftests/dma/dma_map_benchmark.c

+16 −4
Original line number Diff line number Diff line
@@ -40,7 +40,8 @@ struct map_benchmark { 
	__u32 dma_bits; /* DMA addressing capability */

	__u32 dma_dir; /* DMA data direction */

	__u32 dma_trans_ns; /* time for DMA transmission in ns */

	__u8 expansion[80];	/* For future use */

	__u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */

	__u8 expansion[76];	/* For future use */

};



int main(int argc, char **argv)
@@ -51,11 +52,13 @@ int main(int argc, char **argv) 
	int threads = 1, seconds = 20, node = -1;

	/* 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;

	char *p;



	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) {

	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) {

		switch (opt) {

		case 't':

			threads = atoi(optarg);
@@ -75,6 +78,9 @@ int main(int argc, char **argv) 
		case 'x':

			xdelay = atoi(optarg);

			break;

		case 'g':

			granule = atoi(optarg);

			break;

		default:

			return -1;

		}
@@ -110,6 +116,11 @@ int main(int argc, char **argv) 
		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");
@@ -123,14 +134,15 @@ int main(int argc, char **argv) 
	map.dma_bits = bits;

	map.dma_dir = dir;

	map.dma_trans_ns = xdelay;

	map.granule = granule;



	if (ioctl(fd, cmd, &map)) {

		perror("ioctl");

		exit(1);

	}



	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n",

			threads, seconds, node, dir[directions]);

	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %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);

	printf("average unmap latency(us):%.1f standard deviation:%.1f\n",