selftests/dma: add test application for DMA_MAP_BENCHMARK

This patch provides the test application for DMA_MAP_BENCHMARK.

Before running the test application, we need to bind a device to dma_map_
benchmark driver. For example, unbind "xxx" from its original driver and
bind to dma_map_benchmark:

echo dma_map_benchmark > /sys/bus/platform/devices/xxx/driver_override
echo xxx > /sys/bus/platform/drivers/xxx/unbind
echo xxx > /sys/bus/platform/drivers/dma_map_benchmark/bind

Another example for PCI devices:
echo dma_map_benchmark > /sys/bus/pci/devices/0000:00:01.0/driver_override
echo 0000:00:01.0 > /sys/bus/pci/drivers/xxx/unbind
echo 0000:00:01.0 > /sys/bus/pci/drivers/dma_map_benchmark/bind

The below command will run 16 threads on numa node 0 for 10 seconds on
the device bound to dma_map_benchmark platform_driver or pci_driver:
./dma_map_benchmark -t 16 -s 10 -n 0
dma mapping benchmark: threads:16 seconds:10
average map latency(us):1.1 standard deviation:1.9
average unmap latency(us):0.5 standard deviation:0.8

Cc: Will Deacon <will@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

MAINTAINERS

@@ -5237,6 +5237,12 @@ F:	include/linux/dma-mapping.h
 F:	include/linux/dma-map-ops.h
 F:	kernel/dma/
 
+DMA MAPPING BENCHMARK
+M:	Barry Song <song.bao.hua@hisilicon.com>
+L:	iommu@lists.linux-foundation.org
+F:	kernel/dma/map_benchmark.c
+F:	tools/testing/selftests/dma/
+
 DMA-BUF HEAPS FRAMEWORK
 M:	Sumit Semwal <sumit.semwal@linaro.org>
 R:	Benjamin Gaignard <benjamin.gaignard@linaro.org>

tools/testing/selftests/dma/Makefile

+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -I../../../../usr/include/
+
+TEST_GEN_PROGS := dma_map_benchmark
+
+include ../lib.mk

tools/testing/selftests/dma/config

+CONFIG_DMA_MAP_BENCHMARK=y

tools/testing/selftests/dma/dma_map_benchmark.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Hisilicon Limited.
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <linux/types.h>
+
+#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_BIDIRECTIONAL	0
+#define DMA_MAP_TO_DEVICE	1
+#define DMA_MAP_FROM_DEVICE	2
+
+static char *directions[] = {
+	"BIDIRECTIONAL",
+	"TO_DEVICE",
+	"FROM_DEVICE",
+};
+
+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 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 */
+	__u64 expansion[10];	/* For future use */
+};
+
+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 dma mask 32bit, bidirectional DMA */
+	int bits = 32, dir = DMA_MAP_BIDIRECTIONAL;
+
+	int cmd = DMA_MAP_BENCHMARK;
+	char *p;
+
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) {
+		switch (opt) {
+		case 't':
+			threads = atoi(optarg);
+			break;
+		case 's':
+			seconds = atoi(optarg);
+			break;
+		case 'n':
+			node = atoi(optarg);
+			break;
+		case 'b':
+			bits = atoi(optarg);
+			break;
+		case 'd':
+			dir = atoi(optarg);
+			break;
+		default:
+			return -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);
+		exit(1);
+	}
+
+	if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) {
+		fprintf(stderr, "invalid number of seconds, must be in 1-%d\n",
+			DMA_MAP_MAX_SECONDS);
+		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");
+		exit(1);
+	}
+
+	if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE &&
+			dir != DMA_MAP_FROM_DEVICE) {
+		fprintf(stderr, "invalid dma direction\n");
+		exit(1);
+	}
+
+	fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
+	if (fd == -1) {
+		perror("open");
+		exit(1);
+	}
+
+	map.seconds = seconds;
+	map.threads = threads;
+	map.node = node;
+	map.dma_bits = bits;
+	map.dma_dir = dir;
+	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("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",
+			map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0);
+
+	return 0;
+}