[PATCH v10] app/dma-perf: introduce dma-perf application

[Cheng Jiang <cheng1.jiang@intel.com>]

There are many high-performance DMA devices supported in DPDK now, and
these DMA devices can also be integrated into other modules of DPDK as
accelerators, such as Vhost. Before integrating DMA into applications,
developers need to know the performance of these DMA devices in various
scenarios and the performance of CPUs in the same scenario, such as
different buffer lengths. Only in this way can we know the target
performance of the application accelerated by using them. This patch
introduces a high-performance testing tool, which supports comparing the
performance of CPU and DMA in different scenarios automatically with a
pre-set config file. Memory Copy performance test are supported for now.

Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Chenbo Xia <chenbo.xia@intel.com>
---
v10:
  rebased code from 23.07-rc2;
v9:
  improved error handling;
  improved lcore_params structure;
  improved mbuf api calling;
  improved exit process;
  fixed some typos;
  added scenario summary data display;
  removed unnecessary include;
v8:
  fixed string copy issue in parse_lcore();
  improved some data display format;
  added doc in doc/guides/tools;
  updated release notes;
v7:
  fixed some strcpy issues;
  removed cache setup in calling rte_pktmbuf_pool_create();
  fixed some typos;
  added some memory free and null set operations;
  improved result calculation;
v6:
  improved code based on Anoob's comments;
  fixed some code structure issues;
v5:
  fixed some LONG_LINE warnings;
v4:
  fixed inaccuracy of the memory footprint display;
v3:
  fixed some typos;
v2:
  added lcore/dmadev designation;
  added error case process;
  removed worker_threads parameter from config.ini;
  improved the logs;
  improved config file;

 app/meson.build                        |   1 +
 app/test-dma-perf/benchmark.c          | 508 ++++++++++++++++++++
 app/test-dma-perf/config.ini           |  61 +++
 app/test-dma-perf/main.c               | 616 +++++++++++++++++++++++++
 app/test-dma-perf/main.h               |  64 +++
 app/test-dma-perf/meson.build          |  17 +
 doc/guides/rel_notes/release_23_07.rst |   6 +
 doc/guides/tools/dmaperf.rst           | 103 +++++
 doc/guides/tools/index.rst             |   1 +
 9 files changed, 1377 insertions(+)
 create mode 100644 app/test-dma-perf/benchmark.c
 create mode 100644 app/test-dma-perf/config.ini
 create mode 100644 app/test-dma-perf/main.c
 create mode 100644 app/test-dma-perf/main.h
 create mode 100644 app/test-dma-perf/meson.build
 create mode 100644 doc/guides/tools/dmaperf.rst

diff --git a/app/meson.build b/app/meson.build
index 74d2420f67..4fc1a83eba 100644
--- a/app/meson.build
+++ b/app/meson.build
@@ -19,6 +19,7 @@ apps = [
         'test-cmdline',
         'test-compress-perf',
         'test-crypto-perf',
+        'test-dma-perf',
         'test-eventdev',
         'test-fib',
         'test-flow-perf',
diff --git a/app/test-dma-perf/benchmark.c b/app/test-dma-perf/benchmark.c
new file mode 100644
index 0000000000..0601e0d171
--- /dev/null
+++ b/app/test-dma-perf/benchmark.c
@@ -0,0 +1,508 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2023 Intel Corporation
+ */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <rte_time.h>
+#include <rte_mbuf.h>
+#include <rte_dmadev.h>
+#include <rte_malloc.h>
+#include <rte_lcore.h>
+
+#include "main.h"
+
+#define MAX_DMA_CPL_NB 255
+
+#define TEST_WAIT_U_SECOND 10000
+#define POLL_MAX 1000
+
+#define CSV_LINE_DMA_FMT "Scenario %u,%u,%s,%u,%u,%u,%u,%.2lf,%" PRIu64 ",%.3lf,%.3lf\n"
+#define CSV_LINE_CPU_FMT "Scenario %u,%u,NA,NA,NA,%u,%u,%.2lf,%" PRIu64 ",%.3lf,%.3lf\n"
+
+#define CSV_TOTAL_LINE_FMT "Scenario %u Summary, , , , , ,%u,%.2lf,%u,%.3lf,%.3lf\n"
+
+struct worker_info {
+	bool ready_flag;
+	bool start_flag;
+	bool stop_flag;
+	uint32_t total_cpl;
+	uint32_t test_cpl;
+};
+
+struct lcore_params {
+	uint8_t scenario_id;
+	unsigned int lcore_id;
+	char *dma_name;
+	uint16_t worker_id;
+	uint16_t dev_id;
+	uint32_t nr_buf;
+	uint16_t kick_batch;
+	uint32_t buf_size;
+	uint16_t test_secs;
+	struct rte_mbuf **srcs;
+	struct rte_mbuf **dsts;
+	volatile struct worker_info worker_info;
+};
+
+static struct rte_mempool *src_pool;
+static struct rte_mempool *dst_pool;
+
+static struct lcore_params *lcores[MAX_WORKER_NB];
+
+#define PRINT_ERR(...) print_err(__func__, __LINE__, __VA_ARGS__)
+
+static inline int
+__rte_format_printf(3, 4)
+print_err(const char *func, int lineno, const char *format, ...)
+{
+	va_list ap;
+	int ret;
+
+	ret = fprintf(stderr, "In %s:%d - ", func, lineno);
+	va_start(ap, format);
+	ret += vfprintf(stderr, format, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+static inline void
+calc_result(uint32_t buf_size, uint32_t nr_buf, uint16_t nb_workers, uint16_t test_secs,
+				uint32_t total_cnt, float *memory, uint32_t *ave_cycle,
+				float *bandwidth, float *mops)
+{
+	float ops;
+
+	*memory = (float)(buf_size * (nr_buf / nb_workers) * 2) / (1024 * 1024);
+	*ave_cycle = test_secs * rte_get_timer_hz() / total_cnt;
+	ops = (float)total_cnt / test_secs;
+	*mops = ops / (1000 * 1000);
+	*bandwidth = (ops * buf_size * 8) / (1000 * 1000 * 1000);
+}
+
+static void
+output_result(uint8_t scenario_id, uint32_t lcore_id, char *dma_name, uint16_t ring_size,
+			uint16_t kick_batch, uint64_t ave_cycle, uint32_t buf_size, uint32_t nr_buf,
+			float memory, float bandwidth, float mops, bool is_dma)
+{
+	if (is_dma)
+		printf("lcore %u, DMA %s, DMA Ring Size: %u, Kick Batch Size: %u.\n",
+				lcore_id, dma_name, ring_size, kick_batch);
+	else
+		printf("lcore %u\n", lcore_id);
+
+	printf("Average Cycles/op: %" PRIu64 ", Buffer Size: %u B, Buffer Number: %u, Memory: %.2lf MB, Frequency: %.3lf Ghz.\n",
+			ave_cycle, buf_size, nr_buf, memory, rte_get_timer_hz()/1000000000.0);
+	printf("Average Bandwidth: %.3lf Gbps, MOps: %.3lf\n", bandwidth, mops);
+
+	if (is_dma)
+		snprintf(output_str[lcore_id], MAX_OUTPUT_STR_LEN, CSV_LINE_DMA_FMT,
+			scenario_id, lcore_id, dma_name, ring_size, kick_batch, buf_size,
+			nr_buf, memory, ave_cycle, bandwidth, mops);
+	else
+		snprintf(output_str[lcore_id], MAX_OUTPUT_STR_LEN, CSV_LINE_CPU_FMT,
+			scenario_id, lcore_id, buf_size,
+			nr_buf, memory, ave_cycle, bandwidth, mops);
+}
+
+static inline void
+cache_flush_buf(__rte_unused struct rte_mbuf **array,
+		__rte_unused uint32_t buf_size,
+		__rte_unused uint32_t nr_buf)
+{
+#ifdef RTE_ARCH_X86_64
+	char *data;
+	struct rte_mbuf **srcs = array;
+	uint32_t i, offset;
+
+	for (i = 0; i < nr_buf; i++) {
+		data = rte_pktmbuf_mtod(srcs[i], char *);
+		for (offset = 0; offset < buf_size; offset += 64)
+			__builtin_ia32_clflush(data + offset);
+	}
+#endif
+}
+
+/* Configuration of device. */
+static void
+configure_dmadev_queue(uint32_t dev_id, uint32_t ring_size)
+{
+	uint16_t vchan = 0;
+	struct rte_dma_info info;
+	struct rte_dma_conf dev_config = { .nb_vchans = 1 };
+	struct rte_dma_vchan_conf qconf = {
+		.direction = RTE_DMA_DIR_MEM_TO_MEM,
+		.nb_desc = ring_size
+	};
+
+	if (rte_dma_configure(dev_id, &dev_config) != 0)
+		rte_exit(EXIT_FAILURE, "Error with dma configure.\n");
+
+	if (rte_dma_vchan_setup(dev_id, vchan, &qconf) != 0)
+		rte_exit(EXIT_FAILURE, "Error with queue configuration.\n");
+
+	if (rte_dma_info_get(dev_id, &info) != 0)
+		rte_exit(EXIT_FAILURE, "Error with getting device info.\n");
+
+	if (info.nb_vchans != 1)
+		rte_exit(EXIT_FAILURE, "Error, no configured queues reported on device id. %u\n",
+				dev_id);
+
+	if (rte_dma_start(dev_id) != 0)
+		rte_exit(EXIT_FAILURE, "Error with dma start.\n");
+}
+
+static int
+config_dmadevs(struct test_configure *cfg)
+{
+	uint32_t ring_size = cfg->ring_size.cur;
+	struct lcore_dma_map_t *ldm = &cfg->lcore_dma_map;
+	uint32_t nb_workers = ldm->cnt;
+	uint32_t i;
+	int dev_id;
+	uint16_t nb_dmadevs = 0;
+	char *dma_name;
+
+	for (i = 0; i < ldm->cnt; i++) {
+		dma_name = ldm->dma_names[i];
+		dev_id = rte_dma_get_dev_id_by_name(dma_name);
+		if (dev_id < 0) {
+			fprintf(stderr, "Error: Fail to find DMA %s.\n", dma_name);
+			goto end;
+		}
+
+		ldm->dma_ids[i] = dev_id;
+		configure_dmadev_queue(dev_id, ring_size);
+		++nb_dmadevs;
+	}
+
+end:
+	if (nb_dmadevs < nb_workers) {
+		printf("Not enough dmadevs (%u) for all workers (%u).\n", nb_dmadevs, nb_workers);
+		return -1;
+	}
+
+	printf("Number of used dmadevs: %u.\n", nb_dmadevs);
+
+	return 0;
+}
+
+static void
+error_exit(int dev_id)
+{
+	rte_dma_stop(dev_id);
+	rte_dma_close(dev_id);
+	rte_exit(EXIT_FAILURE, "DMA error\n");
+}
+
+static inline void
+do_dma_submit_and_poll(uint16_t dev_id, uint64_t *async_cnt,
+			volatile struct worker_info *worker_info)
+{
+	int ret;
+	uint16_t nr_cpl;
+
+	ret = rte_dma_submit(dev_id, 0);
+	if (ret < 0)
+		error_exit(dev_id);
+
+	nr_cpl = rte_dma_completed(dev_id, 0, MAX_DMA_CPL_NB, NULL, NULL);
+	*async_cnt -= nr_cpl;
+	worker_info->total_cpl += nr_cpl;
+}
+
+static inline int
+do_dma_mem_copy(void *p)
+{
+	struct lcore_params *para = (struct lcore_params *)p;
+	volatile struct worker_info *worker_info = &(para->worker_info);
+	const uint16_t dev_id = para->dev_id;
+	const uint32_t nr_buf = para->nr_buf;
+	const uint16_t kick_batch = para->kick_batch;
+	const uint32_t buf_size = para->buf_size;
+	struct rte_mbuf **srcs = para->srcs;
+	struct rte_mbuf **dsts = para->dsts;
+	uint16_t nr_cpl;
+	uint64_t async_cnt = 0;
+	uint32_t i;
+	uint32_t poll_cnt = 0;
+	int ret;
+
+	worker_info->stop_flag = false;
+	worker_info->ready_flag = true;
+
+	while (!worker_info->start_flag)
+		;
+
+	while (1) {
+		for (i = 0; i < nr_buf; i++) {
+dma_copy:
+			ret = rte_dma_copy(dev_id, 0, rte_mbuf_data_iova(srcs[i]),
+				rte_mbuf_data_iova(dsts[i]), buf_size, 0);
+			if (unlikely(ret < 0)) {
+				if (ret == -ENOSPC) {
+					do_dma_submit_and_poll(dev_id, &async_cnt, worker_info);
+					goto dma_copy;
+				} else
+					error_exit(dev_id);
+			}
+			async_cnt++;
+
+			if ((async_cnt % kick_batch) == 0)
+				do_dma_submit_and_poll(dev_id, &async_cnt, worker_info);
+		}
+
+		if (worker_info->stop_flag)
+			break;
+	}
+
+	rte_dma_submit(dev_id, 0);
+	while ((async_cnt > 0) && (poll_cnt++ < POLL_MAX)) {
+		nr_cpl = rte_dma_completed(dev_id, 0, MAX_DMA_CPL_NB, NULL, NULL);
+		async_cnt -= nr_cpl;
+	}
+
+	return 0;
+}
+
+static inline int
+do_cpu_mem_copy(void *p)
+{
+	struct lcore_params *para = (struct lcore_params *)p;
+	volatile struct worker_info *worker_info = &(para->worker_info);
+	const uint32_t nr_buf = para->nr_buf;
+	const uint32_t buf_size = para->buf_size;
+	struct rte_mbuf **srcs = para->srcs;
+	struct rte_mbuf **dsts = para->dsts;
+	uint32_t i;
+
+	worker_info->stop_flag = false;
+	worker_info->ready_flag = true;
+
+	while (!worker_info->start_flag)
+		;
+
+	while (1) {
+		for (i = 0; i < nr_buf; i++) {
+			/* copy buffer form src to dst */
+			rte_memcpy((void *)(uintptr_t)rte_mbuf_data_iova(dsts[i]),
+				(void *)(uintptr_t)rte_mbuf_data_iova(srcs[i]),
+				(size_t)buf_size);
+			worker_info->total_cpl++;
+		}
+		if (worker_info->stop_flag)
+			break;
+	}
+
+	return 0;
+}
+
+static int
+setup_memory_env(struct test_configure *cfg, struct rte_mbuf ***srcs,
+			struct rte_mbuf ***dsts)
+{
+	unsigned int buf_size = cfg->buf_size.cur;
+	unsigned int nr_sockets;
+	uint32_t nr_buf = cfg->nr_buf;
+
+	nr_sockets = rte_socket_count();
+	if (cfg->src_numa_node >= nr_sockets ||
+		cfg->dst_numa_node >= nr_sockets) {
+		printf("Error: Source or destination numa exceeds the acture numa nodes.\n");
+		return -1;
+	}
+
+	src_pool = rte_pktmbuf_pool_create("Benchmark_DMA_SRC",
+			nr_buf,
+			0,
+			0,
+			buf_size + RTE_PKTMBUF_HEADROOM,
+			cfg->src_numa_node);
+	if (src_pool == NULL) {
+		PRINT_ERR("Error with source mempool creation.\n");
+		return -1;
+	}
+
+	dst_pool = rte_pktmbuf_pool_create("Benchmark_DMA_DST",
+			nr_buf,
+			0,
+			0,
+			buf_size + RTE_PKTMBUF_HEADROOM,
+			cfg->dst_numa_node);
+	if (dst_pool == NULL) {
+		PRINT_ERR("Error with destination mempool creation.\n");
+		return -1;
+	}
+
+	*srcs = rte_malloc(NULL, nr_buf * sizeof(struct rte_mbuf *), 0);
+	if (*srcs == NULL) {
+		printf("Error: srcs malloc failed.\n");
+		return -1;
+	}
+
+	*dsts = rte_malloc(NULL, nr_buf * sizeof(struct rte_mbuf *), 0);
+	if (*dsts == NULL) {
+		printf("Error: dsts malloc failed.\n");
+		return -1;
+	}
+
+	if (rte_pktmbuf_alloc_bulk(src_pool, *srcs, nr_buf) != 0) {
+		printf("alloc src mbufs failed.\n");
+		return -1;
+	}
+
+	if (rte_pktmbuf_alloc_bulk(dst_pool, *dsts, nr_buf) != 0) {
+		printf("alloc dst mbufs failed.\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+void
+mem_copy_benchmark(struct test_configure *cfg, bool is_dma)
+{
+	uint16_t i;
+	uint32_t offset;
+	unsigned int lcore_id = 0;
+	struct rte_mbuf **srcs = NULL, **dsts = NULL;
+	struct lcore_dma_map_t *ldm = &cfg->lcore_dma_map;
+	unsigned int buf_size = cfg->buf_size.cur;
+	uint16_t kick_batch = cfg->kick_batch.cur;
+	uint32_t nr_buf = cfg->nr_buf = (cfg->mem_size.cur * 1024 * 1024) / (cfg->buf_size.cur * 2);
+	uint16_t nb_workers = ldm->cnt;
+	uint16_t test_secs = cfg->test_secs;
+	float memory = 0;
+	uint32_t avg_cycles = 0;
+	uint32_t avg_cycles_total;
+	float mops, mops_total;
+	float bandwidth, bandwidth_total;
+
+	if (setup_memory_env(cfg, &srcs, &dsts) < 0)
+		goto out;
+
+	if (is_dma)
+		if (config_dmadevs(cfg) < 0)
+			goto out;
+
+	if (cfg->cache_flush == 1) {
+		cache_flush_buf(srcs, buf_size, nr_buf);
+		cache_flush_buf(dsts, buf_size, nr_buf);
+		rte_mb();
+	}
+
+	printf("Start testing....\n");
+
+	for (i = 0; i < nb_workers; i++) {
+		lcore_id = ldm->lcores[i];
+		offset = nr_buf / nb_workers * i;
+		lcores[i] = rte_malloc(NULL, sizeof(struct lcore_params), 0);
+		if (lcores[i] == NULL) {
+			printf("lcore parameters malloc failure for lcore %d\n", lcore_id);
+			break;
+		}
+		if (is_dma) {
+			lcores[i]->dma_name = ldm->dma_names[i];
+			lcores[i]->dev_id = ldm->dma_ids[i];
+			lcores[i]->kick_batch = kick_batch;
+		}
+		lcores[i]->worker_id = i;
+		lcores[i]->nr_buf = (uint32_t)(nr_buf / nb_workers);
+		lcores[i]->buf_size = buf_size;
+		lcores[i]->test_secs = test_secs;
+		lcores[i]->srcs = srcs + offset;
+		lcores[i]->dsts = dsts + offset;
+		lcores[i]->scenario_id = cfg->scenario_id;
+		lcores[i]->lcore_id = lcore_id;
+
+		if (is_dma)
+			rte_eal_remote_launch(do_dma_mem_copy, (void *)(lcores[i]), lcore_id);
+		else
+			rte_eal_remote_launch(do_cpu_mem_copy, (void *)(lcores[i]), lcore_id);
+	}
+
+	while (1) {
+		bool ready = true;
+		for (i = 0; i < nb_workers; i++) {
+			if (lcores[i]->worker_info.ready_flag == false) {
+				ready = 0;
+				break;
+			}
+		}
+		if (ready)
+			break;
+	}
+
+	for (i = 0; i < nb_workers; i++)
+		lcores[i]->worker_info.start_flag = true;
+
+	usleep(TEST_WAIT_U_SECOND);
+	for (i = 0; i < nb_workers; i++)
+		lcores[i]->worker_info.test_cpl = lcores[i]->worker_info.total_cpl;
+
+	usleep(test_secs * 1000 * 1000);
+	for (i = 0; i < nb_workers; i++)
+		lcores[i]->worker_info.test_cpl = lcores[i]->worker_info.total_cpl -
+						lcores[i]->worker_info.test_cpl;
+
+	for (i = 0; i < nb_workers; i++)
+		lcores[i]->worker_info.stop_flag = true;
+
+	rte_eal_mp_wait_lcore();
+
+	mops_total = 0;
+	bandwidth_total = 0;
+	avg_cycles_total = 0;
+	for (i = 0; i < nb_workers; i++) {
+		calc_result(buf_size, nr_buf, nb_workers, test_secs,
+			lcores[i]->worker_info.test_cpl,
+			&memory, &avg_cycles, &bandwidth, &mops);
+		output_result(cfg->scenario_id, lcores[i]->lcore_id,
+					lcores[i]->dma_name, cfg->ring_size.cur, kick_batch,
+					avg_cycles, buf_size, nr_buf / nb_workers, memory,
+					bandwidth, mops, is_dma);
+		mops_total += mops;
+		bandwidth_total += bandwidth;
+		avg_cycles_total += avg_cycles;
+	}
+	printf("\nTotal Bandwidth: %.3lf Gbps, Total MOps: %.3lf\n", bandwidth_total, mops_total);
+	snprintf(output_str[MAX_WORKER_NB], MAX_OUTPUT_STR_LEN, CSV_TOTAL_LINE_FMT,
+			cfg->scenario_id, nr_buf, memory * nb_workers,
+			avg_cycles_total / nb_workers, bandwidth_total, mops_total);
+
+out:
+	/* free mbufs used in the test */
+	if (srcs != NULL)
+		rte_pktmbuf_free_bulk(srcs, nr_buf);
+	if (dsts != NULL)
+		rte_pktmbuf_free_bulk(dsts, nr_buf);
+
+	/* free the points for the mbufs */
+	rte_free(srcs);
+	srcs = NULL;
+	rte_free(dsts);
+	dsts = NULL;
+
+	rte_mempool_free(src_pool);
+	src_pool = NULL;
+
+	rte_mempool_free(dst_pool);
+	dst_pool = NULL;
+
+	/* free the worker parameters */
+	for (i = 0; i < nb_workers; i++) {
+		rte_free(lcores[i]);
+		lcores[i] = NULL;
+	}
+
+	if (is_dma) {
+		for (i = 0; i < nb_workers; i++) {
+			printf("Stopping dmadev %d\n", ldm->dma_ids[i]);
+			rte_dma_stop(ldm->dma_ids[i]);
+		}
+	}
+}
diff --git a/app/test-dma-perf/config.ini b/app/test-dma-perf/config.ini
new file mode 100644
index 0000000000..b550f4b23f
--- /dev/null
+++ b/app/test-dma-perf/config.ini
@@ -0,0 +1,61 @@
+
+; This is an example configuration file for dma-perf, which details the meanings of each parameter
+; and instructions on how to use dma-perf.
+
+; Supported test types are DMA_MEM_COPY and CPU_MEM_COPY.
+
+; Parameters:
+; "mem_size" denotes the size of the memory footprint.
+; "buf_size" denotes the memory size of a single operation.
+; "dma_ring_size" denotes the dma ring buffer size. It should be must be a power of two, and between
+;  64 and 4096.
+; "kick_batch" denotes the dma operation batch size, and should be greater than 1 normally.
+
+; The format for variables is variable=first,last,increment,ADD|MUL.
+
+; src_numa_node is used to control the numa node where the source memory is allocated.
+; dst_numa_node is used to control the numa node where the destination memory is allocated.
+
+; cache_flush is used to determine whether or not the cache should be flushed, with 1 indicating to
+; flush and 0 indicating to not flush.
+
+; test_seconds controls the test time of the whole case.
+
+; To use DMA for a test, please specify the "lcore_dma" parameter.
+; If you have already set the "-l" and "-a" parameters using EAL,
+; make sure that the value of "lcore_dma" falls within their range of the values.
+; We have to ensure a 1:1 mapping between the core and DMA device.
+
+; To use CPU for a test, please specify the "lcore" parameter.
+; If you have already set the "-l" and "-a" parameters using EAL,
+; make sure that the value of "lcore" falls within their range of values.
+
+; To specify a configuration file, use the "--config" flag followed by the path to the file.
+
+; To specify a result file, use the "--result" flag followed by the path to the file.
+; If you do not specify a result file, one will be generated with the same name as the configuration
+; file, with the addition of "_result.csv" at the end.
+
+[case1]
+type=DMA_MEM_COPY
+mem_size=10
+buf_size=64,8192,2,MUL
+dma_ring_size=1024
+kick_batch=32
+src_numa_node=0
+dst_numa_node=0
+cache_flush=0
+test_seconds=2
+lcore_dma=lcore10@0000:00:04.2, lcore11@0000:00:04.3
+eal_args=--in-memory --file-prefix=test
+
+[case2]
+type=CPU_MEM_COPY
+mem_size=10
+buf_size=64,8192,2,MUL
+src_numa_node=0
+dst_numa_node=1
+cache_flush=0
+test_seconds=2
+lcore = 3, 4
+eal_args=--in-memory --no-pci
diff --git a/app/test-dma-perf/main.c b/app/test-dma-perf/main.c
new file mode 100644
index 0000000000..de37120df6
--- /dev/null
+++ b/app/test-dma-perf/main.c
@@ -0,0 +1,616 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2023 Intel Corporation
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <getopt.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <inttypes.h>
+#include <libgen.h>
+
+#include <rte_eal.h>
+#include <rte_cfgfile.h>
+#include <rte_string_fns.h>
+#include <rte_lcore.h>
+
+#include "main.h"
+
+#define CSV_HDR_FMT "Case %u : %s,lcore,DMA,DMA ring size,kick batch size,buffer size(B),number of buffers,memory(MB),average cycle,bandwidth(Gbps),MOps\n"
+
+#define MAX_EAL_PARAM_NB 100
+#define MAX_EAL_PARAM_LEN 1024
+
+#define DMA_MEM_COPY "DMA_MEM_COPY"
+#define CPU_MEM_COPY "CPU_MEM_COPY"
+
+#define CMDLINE_CONFIG_ARG "--config"
+#define CMDLINE_RESULT_ARG "--result"
+
+#define MAX_PARAMS_PER_ENTRY 4
+
+#define MAX_LONG_OPT_SZ 64
+
+enum {
+	TEST_TYPE_NONE = 0,
+	TEST_TYPE_DMA_MEM_COPY,
+	TEST_TYPE_CPU_MEM_COPY
+};
+
+#define MAX_TEST_CASES 16
+static struct test_configure test_cases[MAX_TEST_CASES];
+
+char output_str[MAX_WORKER_NB + 1][MAX_OUTPUT_STR_LEN];
+
+static FILE *fd;
+
+static void
+output_csv(bool need_blankline)
+{
+	uint32_t i;
+
+	if (need_blankline) {
+		fprintf(fd, ",,,,,,,,\n");
+		fprintf(fd, ",,,,,,,,\n");
+	}
+
+	for (i = 0; i < RTE_DIM(output_str); i++) {
+		if (output_str[i][0]) {
+			fprintf(fd, "%s", output_str[i]);
+			output_str[i][0] = '\0';
+		}
+	}
+
+	fflush(fd);
+}
+
+static void
+output_env_info(void)
+{
+	snprintf(output_str[0], MAX_OUTPUT_STR_LEN, "Test Environment:\n");
+	snprintf(output_str[1], MAX_OUTPUT_STR_LEN, "CPU frequency,%.3lf Ghz",
+			rte_get_timer_hz() / 1000000000.0);
+
+	output_csv(true);
+}
+
+static void
+output_header(uint32_t case_id, struct test_configure *case_cfg)
+{
+	snprintf(output_str[0], MAX_OUTPUT_STR_LEN,
+			CSV_HDR_FMT, case_id, case_cfg->test_type_str);
+
+	output_csv(true);
+}
+
+static void
+run_test_case(struct test_configure *case_cfg)
+{
+	switch (case_cfg->test_type) {
+	case TEST_TYPE_DMA_MEM_COPY:
+		mem_copy_benchmark(case_cfg, true);
+		break;
+	case TEST_TYPE_CPU_MEM_COPY:
+		mem_copy_benchmark(case_cfg, false);
+		break;
+	default:
+		printf("Unknown test type. %s\n", case_cfg->test_type_str);
+		break;
+	}
+}
+
+static void
+run_test(uint32_t case_id, struct test_configure *case_cfg)
+{
+	uint32_t i;
+	uint32_t nb_lcores = rte_lcore_count();
+	struct test_configure_entry *mem_size = &case_cfg->mem_size;
+	struct test_configure_entry *buf_size = &case_cfg->buf_size;
+	struct test_configure_entry *ring_size = &case_cfg->ring_size;
+	struct test_configure_entry *kick_batch = &case_cfg->kick_batch;
+	struct test_configure_entry dummy = { 0 };
+	struct test_configure_entry *var_entry = &dummy;
+
+	for (i = 0; i < RTE_DIM(output_str); i++)
+		memset(output_str[i], 0, MAX_OUTPUT_STR_LEN);
+
+	if (nb_lcores <= case_cfg->lcore_dma_map.cnt) {
+		printf("Case %u: Not enough lcores.\n", case_id);
+		return;
+	}
+
+	printf("Number of used lcores: %u.\n", nb_lcores);
+
+	if (mem_size->incr != 0)
+		var_entry = mem_size;
+
+	if (buf_size->incr != 0)
+		var_entry = buf_size;
+
+	if (ring_size->incr != 0)
+		var_entry = ring_size;
+
+	if (kick_batch->incr != 0)
+		var_entry = kick_batch;
+
+	case_cfg->scenario_id = 0;
+
+	output_header(case_id, case_cfg);
+
+	for (var_entry->cur = var_entry->first; var_entry->cur <= var_entry->last;) {
+		case_cfg->scenario_id++;
+		printf("\nRunning scenario %d\n", case_cfg->scenario_id);
+
+		run_test_case(case_cfg);
+		output_csv(false);
+
+		if (var_entry->op == OP_ADD)
+			var_entry->cur += var_entry->incr;
+		else if (var_entry->op == OP_MUL)
+			var_entry->cur *= var_entry->incr;
+		else {
+			printf("No proper operation for variable entry.\n");
+			break;
+		}
+	}
+}
+
+static int
+parse_lcore(struct test_configure *test_case, const char *value)
+{
+	uint16_t len;
+	char *input;
+	struct lcore_dma_map_t *lcore_dma_map;
+
+	if (test_case == NULL || value == NULL)
+		return -1;
+
+	len = strlen(value);
+	input = (char *)malloc((len + 1) * sizeof(char));
+	strlcpy(input, value, len + 1);
+	lcore_dma_map = &(test_case->lcore_dma_map);
+
+	memset(lcore_dma_map, 0, sizeof(struct lcore_dma_map_t));
+
+	char *token = strtok(input, ", ");
+	while (token != NULL) {
+		if (lcore_dma_map->cnt >= MAX_LCORE_NB) {
+			free(input);
+			return -1;
+		}
+
+		uint16_t lcore_id = atoi(token);
+		lcore_dma_map->lcores[lcore_dma_map->cnt++] = lcore_id;
+
+		token = strtok(NULL, ", ");
+	}
+
+	free(input);
+	return 0;
+}
+
+static int
+parse_lcore_dma(struct test_configure *test_case, const char *value)
+{
+	struct lcore_dma_map_t *lcore_dma_map;
+	char *input, *addrs;
+	char *ptrs[2];
+	char *start, *end, *substr;
+	uint16_t lcore_id;
+	int ret = 0;
+
+	if (test_case == NULL || value == NULL)
+		return -1;
+
+	input = strndup(value, strlen(value) + 1);
+	addrs = input;
+
+	while (*addrs == '\0')
+		addrs++;
+	if (*addrs == '\0') {
+		fprintf(stderr, "No input DMA addresses\n");
+		ret = -1;
+		goto out;
+	}
+
+	substr = strtok(addrs, ",");
+	if (substr == NULL) {
+		fprintf(stderr, "No input DMA address\n");
+		ret = -1;
+		goto out;
+	}
+
+	memset(&test_case->lcore_dma_map, 0, sizeof(struct lcore_dma_map_t));
+
+	do {
+		if (rte_strsplit(substr, strlen(substr), ptrs, 2, '@') < 0) {
+			fprintf(stderr, "Illegal DMA address\n");
+			ret = -1;
+			break;
+		}
+
+		start = strstr(ptrs[0], "lcore");
+		if (start == NULL) {
+			fprintf(stderr, "Illegal lcore\n");
+			ret = -1;
+			break;
+		}
+
+		start += 5;
+		lcore_id = strtol(start, &end, 0);
+		if (end == start) {
+			fprintf(stderr, "No input lcore ID or ID %d is wrong\n", lcore_id);
+			ret = -1;
+			break;
+		}
+
+		lcore_dma_map = &test_case->lcore_dma_map;
+		if (lcore_dma_map->cnt >= MAX_LCORE_NB) {
+			fprintf(stderr, "lcores count error\n");
+			ret = -1;
+			break;
+		}
+
+		lcore_dma_map->lcores[lcore_dma_map->cnt] = lcore_id;
+		strlcpy(lcore_dma_map->dma_names[lcore_dma_map->cnt], ptrs[1],
+				RTE_DEV_NAME_MAX_LEN);
+		lcore_dma_map->cnt++;
+		substr = strtok(NULL, ",");
+	} while (substr != NULL);
+
+out:
+	free(input);
+	return ret;
+}
+
+static int
+parse_entry(const char *value, struct test_configure_entry *entry)
+{
+	char input[255] = {0};
+	char *args[MAX_PARAMS_PER_ENTRY];
+	int args_nr = -1;
+	int ret;
+
+	if (value == NULL || entry == NULL)
+		goto out;
+
+	strncpy(input, value, 254);
+	if (*input == '\0')
+		goto out;
+
+	ret = rte_strsplit(input, strlen(input), args, MAX_PARAMS_PER_ENTRY, ',');
+	if (ret != 1 && ret != 4)
+		goto out;
+
+	entry->cur = entry->first = (uint32_t)atoi(args[0]);
+
+	if (ret == 4) {
+		args_nr = 4;
+		entry->last = (uint32_t)atoi(args[1]);
+		entry->incr = (uint32_t)atoi(args[2]);
+		if (!strcmp(args[3], "MUL"))
+			entry->op = OP_MUL;
+		else if (!strcmp(args[3], "ADD"))
+			entry->op = OP_ADD;
+		else {
+			args_nr = -1;
+			printf("Invalid op %s.\n", args[3]);
+		}
+
+	} else {
+		args_nr = 1;
+		entry->op = OP_NONE;
+		entry->last = 0;
+		entry->incr = 0;
+	}
+out:
+	return args_nr;
+}
+
+static uint16_t
+load_configs(const char *path)
+{
+	struct rte_cfgfile *cfgfile;
+	int nb_sections, i;
+	struct test_configure *test_case;
+	char section_name[CFG_NAME_LEN];
+	const char *case_type;
+	const char *lcore_dma;
+	const char *mem_size_str, *buf_size_str, *ring_size_str, *kick_batch_str;
+	int args_nr, nb_vp;
+	bool is_dma;
+
+	printf("config file parsing...\n");
+	cfgfile = rte_cfgfile_load(path, 0);
+	if (!cfgfile) {
+		printf("Open configure file error.\n");
+		exit(1);
+	}
+
+	nb_sections = rte_cfgfile_num_sections(cfgfile, NULL, 0);
+	if (nb_sections > MAX_TEST_CASES) {
+		printf("Error: The maximum number of cases is %d.\n", MAX_TEST_CASES);
+		exit(1);
+	}
+
+	for (i = 0; i < nb_sections; i++) {
+		snprintf(section_name, CFG_NAME_LEN, "case%d", i + 1);
+		test_case = &test_cases[i];
+		case_type = rte_cfgfile_get_entry(cfgfile, section_name, "type");
+		if (case_type == NULL) {
+			printf("Error: No case type in case %d, the test will be finished here.\n",
+				i + 1);
+			test_case->is_valid = false;
+			continue;
+		}
+
+		if (strcmp(case_type, DMA_MEM_COPY) == 0) {
+			test_case->test_type = TEST_TYPE_DMA_MEM_COPY;
+			test_case->test_type_str = DMA_MEM_COPY;
+			is_dma = true;
+		} else if (strcmp(case_type, CPU_MEM_COPY) == 0) {
+			test_case->test_type = TEST_TYPE_CPU_MEM_COPY;
+			test_case->test_type_str = CPU_MEM_COPY;
+			is_dma = false;
+		} else {
+			printf("Error: Wrong test case type %s in case%d.\n", case_type, i + 1);
+			test_case->is_valid = false;
+			continue;
+		}
+
+		test_case->src_numa_node = (int)atoi(rte_cfgfile_get_entry(cfgfile,
+								section_name, "src_numa_node"));
+		test_case->dst_numa_node = (int)atoi(rte_cfgfile_get_entry(cfgfile,
+								section_name, "dst_numa_node"));
+		nb_vp = 0;
+		mem_size_str = rte_cfgfile_get_entry(cfgfile, section_name, "mem_size");
+		args_nr = parse_entry(mem_size_str, &test_case->mem_size);
+		if (args_nr < 0) {
+			printf("parse error in case %d.\n", i + 1);
+			test_case->is_valid = false;
+			continue;
+		} else if (args_nr == 4)
+			nb_vp++;
+
+		buf_size_str = rte_cfgfile_get_entry(cfgfile, section_name, "buf_size");
+		args_nr = parse_entry(buf_size_str, &test_case->buf_size);
+		if (args_nr < 0) {
+			printf("parse error in case %d.\n", i + 1);
+			test_case->is_valid = false;
+			continue;
+		} else if (args_nr == 4)
+			nb_vp++;
+
+		if (is_dma) {
+			ring_size_str = rte_cfgfile_get_entry(cfgfile, section_name,
+								"dma_ring_size");
+			args_nr = parse_entry(ring_size_str, &test_case->ring_size);
+			if (args_nr < 0) {
+				printf("parse error in case %d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			} else if (args_nr == 4)
+				nb_vp++;
+
+			kick_batch_str = rte_cfgfile_get_entry(cfgfile, section_name, "kick_batch");
+			args_nr = parse_entry(kick_batch_str, &test_case->kick_batch);
+			if (args_nr < 0) {
+				printf("parse error in case %d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			} else if (args_nr == 4)
+				nb_vp++;
+
+			lcore_dma = rte_cfgfile_get_entry(cfgfile, section_name, "lcore_dma");
+			int lcore_ret = parse_lcore_dma(test_case, lcore_dma);
+			if (lcore_ret < 0) {
+				printf("parse lcore dma error in case %d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+		} else {
+			lcore_dma = rte_cfgfile_get_entry(cfgfile, section_name, "lcore");
+			int lcore_ret = parse_lcore(test_case, lcore_dma);
+			if (lcore_ret < 0) {
+				printf("parse lcore error in case %d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+		}
+
+		if (nb_vp > 1) {
+			printf("Case %d error, each section can only have a single variable parameter.\n",
+					i + 1);
+			test_case->is_valid = false;
+			continue;
+		}
+
+		test_case->cache_flush =
+			(uint8_t)atoi(rte_cfgfile_get_entry(cfgfile, section_name, "cache_flush"));
+		test_case->test_secs = (uint16_t)atoi(rte_cfgfile_get_entry(cfgfile,
+					section_name, "test_seconds"));
+
+		test_case->eal_args = rte_cfgfile_get_entry(cfgfile, section_name, "eal_args");
+		test_case->is_valid = true;
+	}
+
+	rte_cfgfile_close(cfgfile);
+	printf("config file parsing complete.\n\n");
+	return i;
+}
+
+/* Parse the argument given in the command line of the application */
+static int
+append_eal_args(int argc, char **argv, const char *eal_args, char **new_argv)
+{
+	int i;
+	char *tokens[MAX_EAL_PARAM_NB];
+	char args[MAX_EAL_PARAM_LEN] = {0};
+	int token_nb, new_argc = 0;
+
+	for (i = 0; i < argc; i++) {
+		if ((strcmp(argv[i], CMDLINE_CONFIG_ARG) == 0) ||
+				(strcmp(argv[i], CMDLINE_RESULT_ARG) == 0)) {
+			i++;
+			continue;
+		}
+		strlcpy(new_argv[new_argc], argv[i], MAX_EAL_PARAM_LEN);
+		new_argc++;
+	}
+
+	if (eal_args) {
+		strlcpy(args, eal_args, MAX_EAL_PARAM_LEN);
+		token_nb = rte_strsplit(args, strlen(args),
+					tokens, MAX_EAL_PARAM_NB, ' ');
+		for (i = 0; i < token_nb; i++)
+			strlcpy(new_argv[new_argc++], tokens[i], MAX_EAL_PARAM_LEN);
+	}
+
+	return new_argc;
+}
+
+int
+main(int argc, char *argv[])
+{
+	int ret;
+	uint16_t case_nb;
+	uint32_t i, nb_lcores;
+	pid_t cpid, wpid;
+	int wstatus;
+	char args[MAX_EAL_PARAM_NB][MAX_EAL_PARAM_LEN];
+	char *pargs[MAX_EAL_PARAM_NB];
+	char *cfg_path_ptr = NULL;
+	char *rst_path_ptr = NULL;
+	char rst_path[PATH_MAX];
+	int new_argc;
+
+	memset(args, 0, sizeof(args));
+
+	for (i = 0; i < RTE_DIM(pargs); i++)
+		pargs[i] = args[i];
+
+	for (i = 0; i < (uint32_t)argc; i++) {
+		if (strncmp(argv[i], CMDLINE_CONFIG_ARG, MAX_LONG_OPT_SZ) == 0)
+			cfg_path_ptr = argv[i + 1];
+		if (strncmp(argv[i], CMDLINE_RESULT_ARG, MAX_LONG_OPT_SZ) == 0)
+			rst_path_ptr = argv[i + 1];
+	}
+	if (cfg_path_ptr == NULL) {
+		printf("Config file not assigned.\n");
+		return -1;
+	}
+	if (rst_path_ptr == NULL) {
+		strlcpy(rst_path, cfg_path_ptr, PATH_MAX);
+		char *token = strtok(basename(rst_path), ".");
+		if (token == NULL) {
+			printf("Config file error.\n");
+			return -1;
+		}
+		strcat(token, "_result.csv");
+		rst_path_ptr = rst_path;
+	}
+
+	case_nb = load_configs(cfg_path_ptr);
+	fd = fopen(rst_path_ptr, "w");
+	if (fd == NULL) {
+		printf("Open output CSV file error.\n");
+		return -1;
+	}
+	fclose(fd);
+
+	printf("Running cases...\n");
+	for (i = 0; i < case_nb; i++) {
+		if (!test_cases[i].is_valid) {
+			printf("Invalid test case %d.\n\n", i + 1);
+			snprintf(output_str[0], MAX_OUTPUT_STR_LEN, "Invalid case %d\n", i + 1);
+
+			fd = fopen(rst_path_ptr, "a");
+			if (!fd) {
+				printf("Open output CSV file error.\n");
+				return 0;
+			}
+			output_csv(true);
+			fclose(fd);
+			continue;
+		}
+
+		if (test_cases[i].test_type == TEST_TYPE_NONE) {
+			printf("No valid test type in test case %d.\n\n", i + 1);
+			snprintf(output_str[0], MAX_OUTPUT_STR_LEN, "Invalid case %d\n", i + 1);
+
+			fd = fopen(rst_path_ptr, "a");
+			if (!fd) {
+				printf("Open output CSV file error.\n");
+				return 0;
+			}
+			output_csv(true);
+			fclose(fd);
+			continue;
+		}
+
+		cpid = fork();
+		if (cpid < 0) {
+			printf("Fork case %d failed.\n", i + 1);
+			exit(EXIT_FAILURE);
+		} else if (cpid == 0) {
+			printf("\nRunning case %u\n\n", i + 1);
+
+			new_argc = append_eal_args(argc, argv, test_cases[i].eal_args, pargs);
+			ret = rte_eal_init(new_argc, pargs);
+			if (ret < 0)
+				rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n");
+
+			/* Check lcores. */
+			nb_lcores = rte_lcore_count();
+			if (nb_lcores < 2)
+				rte_exit(EXIT_FAILURE,
+					"There should be at least 2 worker lcores.\n");
+
+			fd = fopen(rst_path_ptr, "a");
+			if (!fd) {
+				printf("Open output CSV file error.\n");
+				return 0;
+			}
+
+			output_env_info();
+
+			run_test(i + 1, &test_cases[i]);
+
+			/* clean up the EAL */
+			rte_eal_cleanup();
+
+			fclose(fd);
+
+			printf("\nCase %u completed.\n\n", i + 1);
+
+			exit(EXIT_SUCCESS);
+		} else {
+			wpid = waitpid(cpid, &wstatus, 0);
+			if (wpid == -1) {
+				printf("waitpid error.\n");
+				exit(EXIT_FAILURE);
+			}
+
+			if (WIFEXITED(wstatus))
+				printf("Case process exited. status %d\n\n",
+					WEXITSTATUS(wstatus));
+			else if (WIFSIGNALED(wstatus))
+				printf("Case process killed by signal %d\n\n",
+					WTERMSIG(wstatus));
+			else if (WIFSTOPPED(wstatus))
+				printf("Case process stopped by signal %d\n\n",
+					WSTOPSIG(wstatus));
+			else if (WIFCONTINUED(wstatus))
+				printf("Case process continued.\n\n");
+			else
+				printf("Case process unknown terminated.\n\n");
+		}
+	}
+
+	printf("Bye...\n");
+	return 0;
+}
+
diff --git a/app/test-dma-perf/main.h b/app/test-dma-perf/main.h
new file mode 100644
index 0000000000..12bc3f4e3f
--- /dev/null
+++ b/app/test-dma-perf/main.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2023 Intel Corporation
+ */
+
+#ifndef _MAIN_H_
+#define _MAIN_H_
+
+
+#include <rte_common.h>
+#include <rte_cycles.h>
+#include <rte_dev.h>
+
+#define MAX_WORKER_NB 128
+#define MAX_OUTPUT_STR_LEN 512
+
+#define MAX_DMA_NB 128
+#define MAX_LCORE_NB 256
+
+extern char output_str[MAX_WORKER_NB + 1][MAX_OUTPUT_STR_LEN];
+
+typedef enum {
+	OP_NONE = 0,
+	OP_ADD,
+	OP_MUL
+} alg_op_type;
+
+struct test_configure_entry {
+	uint32_t first;
+	uint32_t last;
+	uint32_t incr;
+	alg_op_type op;
+	uint32_t cur;
+};
+
+struct lcore_dma_map_t {
+	uint32_t lcores[MAX_WORKER_NB];
+	char dma_names[MAX_WORKER_NB][RTE_DEV_NAME_MAX_LEN];
+	int16_t dma_ids[MAX_WORKER_NB];
+	uint16_t cnt;
+};
+
+struct test_configure {
+	bool is_valid;
+	uint8_t test_type;
+	const char *test_type_str;
+	uint16_t src_numa_node;
+	uint16_t dst_numa_node;
+	uint16_t opcode;
+	bool is_dma;
+	struct lcore_dma_map_t lcore_dma_map;
+	struct test_configure_entry mem_size;
+	struct test_configure_entry buf_size;
+	struct test_configure_entry ring_size;
+	struct test_configure_entry kick_batch;
+	uint8_t cache_flush;
+	uint32_t nr_buf;
+	uint16_t test_secs;
+	const char *eal_args;
+	uint8_t scenario_id;
+};
+
+void mem_copy_benchmark(struct test_configure *cfg, bool is_dma);
+
+#endif /* _MAIN_H_ */
diff --git a/app/test-dma-perf/meson.build b/app/test-dma-perf/meson.build
new file mode 100644
index 0000000000..bd6c264002
--- /dev/null
+++ b/app/test-dma-perf/meson.build
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2019-2023 Intel Corporation
+
+# meson file, for building this app as part of a main DPDK build.
+
+if is_windows
+    build = false
+    reason = 'not supported on Windows'
+    subdir_done()
+endif
+
+deps += ['dmadev', 'mbuf', 'cfgfile']
+
+sources = files(
+        'main.c',
+        'benchmark.c',
+)
diff --git a/doc/guides/rel_notes/release_23_07.rst b/doc/guides/rel_notes/release_23_07.rst
index 4459144140..796cc5517d 100644
--- a/doc/guides/rel_notes/release_23_07.rst
+++ b/doc/guides/rel_notes/release_23_07.rst
@@ -200,6 +200,12 @@ New Features

   Enhanced the GRO library to support TCP packets over IPv6 network.

+* **Added DMA device performance test application.**
+
+  Added an new application to test the performance of DMA device and CPU.
+
+  See the :doc:`../tools/dmaperf` for more details.
+

 Removed Items
 -------------
diff --git a/doc/guides/tools/dmaperf.rst b/doc/guides/tools/dmaperf.rst
new file mode 100644
index 0000000000..c5f8a9406f
--- /dev/null
+++ b/doc/guides/tools/dmaperf.rst
@@ -0,0 +1,103 @@
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright(c) 2023 Intel Corporation.
+
+dpdk-test-dma-perf Application
+==============================
+
+The ``dpdk-test-dma-perf`` tool is a Data Plane Development Kit (DPDK) application that enables
+testing the performance of DMA (Direct Memory Access) devices available within DPDK. It provides a
+test framework to assess the performance of CPU and DMA devices under various scenarios, such as
+varying buffer lengths. Doing so provides insight into the potential performance when using these
+DMA devices for acceleration in DPDK applications. It supports memory copy performance tests for
+now, comparing the performance of CPU and DMA automatically in various conditions with the help of a
+pre-set configuration file.
+
+
+Configuration
+-------------
+This application uses inherent DPDK EAL command-line options as well as custom command-line options
+in the application. An example configuration file for the application is provided and gives the
+meanings for each parameter.
+
+Here is an extracted sample from the configuration file (the complete sample can be found in the
+application source directory):
+
+.. code-block:: ini
+
+   [case1]
+   type=DMA_MEM_COPY
+   mem_size=10
+   buf_size=64,8192,2,MUL
+   dma_ring_size=1024
+   kick_batch=32
+   src_numa_node=0
+   dst_numa_node=0
+   cache_flush=0
+   test_seconds=2
+   lcore_dma=lcore10@0000:00:04.2, lcore11@0000:00:04.3
+   eal_args=--in-memory --file-prefix=test
+
+   [case2]
+   type=CPU_MEM_COPY
+   mem_size=10
+   buf_size=64,8192,2,MUL
+   src_numa_node=0
+   dst_numa_node=1
+   cache_flush=0
+   test_seconds=2
+   lcore = 3, 4
+   eal_args=--in-memory --no-pci
+
+The configuration file is divided into multiple sections, each section represents a test case.
+The four variables mem_size, buf_size, dma_ring_size, and kick_batch can vary in each test case.
+The format for this is ``variable=first,last,increment,ADD\|MUL``. This means that the first value
+of the variable is 'first', the last value is 'last', 'increment' is the step size, and ADD|MUL
+indicates whether the change is by addition or multiplication. Each case can only have one variable
+change, and each change will generate a scenario, so each case can have multiple scenarios.
+
+Parameter Definitions
+---------------------
+
+- **type**: The type of the test. Currently supported types are `DMA_MEM_COPY` and `CPU_MEM_COPY`.
+- **mem_size**: The size of the memory footprint.
+- **buf_size**: The memory size of a single operation.
+- **dma_ring_size**: The DMA ring buffer size. Must be a power of two, and between 64 and 4096.
+- **kick_batch**: The DMA operation batch size, should be greater than 1 normally.
+- **src_numa_node**: Controls the NUMA node where the source memory is allocated.
+- **dst_numa_node**: Controls the NUMA node where the destination memory is allocated.
+- **cache_flush**: Determines whether the cache should be flushed. `1` indicates to flush and `0` to not flush.
+- **test_seconds**: Controls the test time for each scenario.
+- **lcore_dma**: Specifies the lcore/DMA mapping.
+- **lcore**: Specifies the lcore for CPU testing.
+- **eal_args**: Specifies the EAL arguments.
+
+.. Note::
+
+	The mapping of lcore to DMA must be one-to-one and cannot be duplicated.
+
+To specify a configuration file, use the "\-\-config" flag followed by the path to the file.
+
+To specify a result file, use the "\-\-result" flag followed by the path to the file. If you do not
+specify a result file, one will be generated with the same name as the configuration file, with the
+addition of "_result.csv" at the end.
+
+
+Running the Application
+-----------------------
+
+Typical command-line invocation to execute the application:
+
+.. code-block:: console
+
+   dpdk-test-dma-perf --config=./config_dma.ini --result=./res_dma.csv
+
+Where `config_dma.ini` is the configuration file, and `res_dma.csv` will be the generated result
+file.
+
+After the tests, you can find the results in the `res_dma.csv` file.
+
+Limitations
+-----------
+
+Currently, this tool only supports memory copy performance tests. Additional enhancements are
+possible in the future to support more types of tests for DMA devices and CPUs.
diff --git a/doc/guides/tools/index.rst b/doc/guides/tools/index.rst
index 6f84fc31ff..857572da96 100644
--- a/doc/guides/tools/index.rst
+++ b/doc/guides/tools/index.rst
@@ -23,3 +23,4 @@ DPDK Tools User Guides
     testregex
     testmldev
     dts
+    dmaperf
--
2.40.1