[PATCH v3 1/2] dma-mapping: benchmark: use u8 for reserved field in uAPI structure

[PATCH v3 1/2] dma-mapping: benchmark: use u8 for reserved field in uAPI structure

[Barry Song]

The original code put five u32 before a u64 expansion[10] array. Five is
odd, this will cause trouble in the extension of the structure by adding
new features. This patch moves to use u8 for reserved field to avoid
future alignment risk.
Meanwhile, it also clears the memory of struct map_benchmark in tools,
otherwise, if users use old version to run on newer kernel, the random
expansion value will cause side effect on newer kernel.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
---
 kernel/dma/map_benchmark.c                      | 2 +-
 tools/testing/selftests/dma/dma_map_benchmark.c | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 1b1b8ff875cb..da95df381483 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -36,7 +36,7 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u64 expansion[10];	/* For future use */
+	__u8 expansion[84];	/* For future use */
 };
 
 struct map_benchmark_data {
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index 7065163a8388..537d65968c48 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -6,6 +6,7 @@
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <unistd.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
@@ -35,7 +36,7 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u64 expansion[10];	/* For future use */
+	__u8 expansion[84];	/* For future use */
 };
 
 int main(int argc, char **argv)
@@ -102,6 +103,7 @@ int main(int argc, char **argv)
 		exit(1);
 	}
 
+	memset(&map, 0, sizeof(map));
 	map.seconds = seconds;
 	map.threads = threads;
 	map.node = node;
-- 
2.25.1

[PATCH v3 2/2] dma-mapping: benchmark: pretend DMA is transmitting

[Barry Song]

In a real dma mapping user case, after dma_map is done, data will be
transmit. Thus, in multi-threaded user scenario, IOMMU contention
should not be that severe. For example, if users enable multiple
threads to send network packets through 1G/10G/100Gbps NIC, usually
the steps will be: map -> transmission -> unmap.  Transmission delay
reduces the contention of IOMMU.

Here a delay is added to simulate the transmission between map and unmap
so that the tested result could be more accurate for TX and simple RX.
A typical TX transmission for NIC would be like: map -> TX -> unmap
since the socket buffers come from OS. Simple RX model eg. disk driver,
is also map -> RX -> unmap, but real RX model in a NIC could be more
complicated considering packets can come spontaneously and many drivers
are using pre-mapped buffers pool. This is in the TBD list.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
---
 kernel/dma/map_benchmark.c                    | 12 ++++++++++-
 .../testing/selftests/dma/dma_map_benchmark.c | 21 ++++++++++++++++---
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index da95df381483..e0e64f8b0739 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -21,6 +21,7 @@
 #define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
 #define DMA_MAP_MAX_THREADS	1024
 #define DMA_MAP_MAX_SECONDS	300
+#define DMA_MAP_MAX_TRANS_DELAY	(10 * NSEC_PER_MSEC)
 
 #define DMA_MAP_BIDIRECTIONAL	0
 #define DMA_MAP_TO_DEVICE	1
@@ -36,7 +37,8 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u8 expansion[84];	/* For future use */
+	__u32 dma_trans_ns; /* time for DMA transmission in ns */
+	__u8 expansion[80];	/* For future use */
 };
 
 struct map_benchmark_data {
@@ -87,6 +89,9 @@ static int map_benchmark_thread(void *data)
 		map_etime = ktime_get();
 		map_delta = ktime_sub(map_etime, map_stime);
 
+		/* Pretend DMA is transmitting */
+		ndelay(map->bparam.dma_trans_ns);
+
 		unmap_stime = ktime_get();
 		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
 		unmap_etime = ktime_get();
@@ -218,6 +223,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		}
 
+		if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) {
+			pr_err("invalid transmission delay\n");
+			return -EINVAL;
+		}
+
 		if (map->bparam.node != NUMA_NO_NODE &&
 		    !node_possible(map->bparam.node)) {
 			pr_err("invalid numa node\n");
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index 537d65968c48..fb23ce9617ea 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -12,9 +12,12 @@
 #include <sys/mman.h>
 #include <linux/types.h>
 
+#define NSEC_PER_MSEC	1000000L
+
 #define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
 #define DMA_MAP_MAX_THREADS	1024
 #define DMA_MAP_MAX_SECONDS     300
+#define DMA_MAP_MAX_TRANS_DELAY	(10 * NSEC_PER_MSEC)
 
 #define DMA_MAP_BIDIRECTIONAL	0
 #define DMA_MAP_TO_DEVICE	1
@@ -36,7 +39,8 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u8 expansion[84];	/* For future use */
+	__u32 dma_trans_ns; /* time for DMA transmission in ns */
+	__u8 expansion[80];	/* For future use */
 };
 
 int main(int argc, char **argv)
@@ -46,12 +50,12 @@ int main(int argc, char **argv)
 	/* default single thread, run 20 seconds on NUMA_NO_NODE */
 	int threads = 1, seconds = 20, node = -1;
 	/* default dma mask 32bit, bidirectional DMA */
-	int bits = 32, dir = DMA_MAP_BIDIRECTIONAL;
+	int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
 
 	int cmd = DMA_MAP_BENCHMARK;
 	char *p;
 
-	while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) {
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) {
 		switch (opt) {
 		case 't':
 			threads = atoi(optarg);
@@ -68,6 +72,9 @@ int main(int argc, char **argv)
 		case 'd':
 			dir = atoi(optarg);
 			break;
+		case 'x':
+			xdelay = atoi(optarg);
+			break;
 		default:
 			return -1;
 		}
@@ -85,6 +92,12 @@ int main(int argc, char **argv)
 		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");
@@ -109,6 +122,8 @@ int main(int argc, char **argv)
 	map.node = node;
 	map.dma_bits = bits;
 	map.dma_dir = dir;
+	map.dma_trans_ns = xdelay;
+
 	if (ioctl(fd, cmd, &map)) {
 		perror("ioctl");
 		exit(1);
-- 
2.25.1

Re: [PATCH v3 1/2] dma-mapping: benchmark: use u8 for reserved field in uAPI structure

[Christoph Hellwig]

Thanks,

applied.