[v3] app/dma-perf: support bi-directional transfer

Message ID 20240229141426.4188428-1-amitprakashs@marvell.com (mailing list archive)
State New
Delegated to: Thomas Monjalon
Headers
Series [v3] app/dma-perf: support bi-directional transfer |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/loongarch-compilation warning apply patch failure
ci/Intel-compilation warning apply issues
ci/github-robot: build success github build: passed
ci/iol-testing warning apply patch failure

Commit Message

Amit Prakash Shukla Feb. 29, 2024, 2:14 p.m. UTC
  Adds bi-directional DMA transfer support to test performance.
One DMA device on one core will do mem2dev transfer and another
DMA device on another core will do dev2mem transfer.

Depends-on: series-31298 ("PCI Dev and SG copy support")

Signed-off-by: Amit Prakash Shukla <amitprakashs@marvell.com>
---
v3:
- Rebased with dependent series.

 app/test-dma-perf/benchmark.c | 65 +++++++++++++++++++++++++++--------
 app/test-dma-perf/config.ini  |  5 +++
 app/test-dma-perf/main.c      | 18 +++++++++-
 app/test-dma-perf/main.h      |  1 +
 4 files changed, 74 insertions(+), 15 deletions(-)
  

Patch

diff --git a/app/test-dma-perf/benchmark.c b/app/test-dma-perf/benchmark.c
index d821af8532..79de80499f 100644
--- a/app/test-dma-perf/benchmark.c
+++ b/app/test-dma-perf/benchmark.c
@@ -148,12 +148,19 @@  cache_flush_buf(__rte_unused struct rte_mbuf **array,
 
 static int
 vchan_data_populate(uint32_t dev_id, struct rte_dma_vchan_conf *qconf,
-		    struct test_configure *cfg)
+		    struct test_configure *cfg, uint16_t dev_num)
 {
 	struct rte_dma_info info;
 
 	qconf->direction = cfg->transfer_dir;
 
+	/* If its a bi-directional test, configure odd device for inbound dma
+	 * transfer and even device for outbound dma transfer.
+	 */
+	if (cfg->is_bidir)
+		qconf->direction = (dev_num % 2) ? RTE_DMA_DIR_MEM_TO_DEV :
+				   RTE_DMA_DIR_DEV_TO_MEM;
+
 	rte_dma_info_get(dev_id, &info);
 	if (!(RTE_BIT64(qconf->direction) & info.dev_capa))
 		return -1;
@@ -185,14 +192,15 @@  vchan_data_populate(uint32_t dev_id, struct rte_dma_vchan_conf *qconf,
 
 /* Configuration of device. */
 static void
-configure_dmadev_queue(uint32_t dev_id, struct test_configure *cfg, uint8_t sges_max)
+configure_dmadev_queue(uint32_t dev_id, struct test_configure *cfg, uint8_t sges_max,
+		       uint16_t dev_num)
 {
 	uint16_t vchan = 0;
 	struct rte_dma_info info;
 	struct rte_dma_conf dev_config = { .nb_vchans = 1 };
 	struct rte_dma_vchan_conf qconf = { 0 };
 
-	if (vchan_data_populate(dev_id, &qconf, cfg) != 0)
+	if (vchan_data_populate(dev_id, &qconf, cfg, dev_num) != 0)
 		rte_exit(EXIT_FAILURE, "Error with vchan data populate.\n");
 
 	if (rte_dma_configure(dev_id, &dev_config) != 0)
@@ -239,7 +247,7 @@  config_dmadevs(struct test_configure *cfg)
 		}
 
 		ldm->dma_ids[i] = dev_id;
-		configure_dmadev_queue(dev_id, cfg, nb_sges);
+		configure_dmadev_queue(dev_id, cfg, nb_sges, nb_dmadevs);
 		++nb_dmadevs;
 	}
 
@@ -508,7 +516,7 @@  setup_memory_env(struct test_configure *cfg,
 		}
 	}
 
-	if (cfg->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
+	if (cfg->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM && !cfg->is_bidir) {
 		ext_buf_info->free_cb = dummy_free_ext_buf;
 		ext_buf_info->fcb_opaque = NULL;
 		for (i = 0; i < nr_buf; i++) {
@@ -521,7 +529,7 @@  setup_memory_env(struct test_configure *cfg,
 		}
 	}
 
-	if (cfg->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV) {
+	if (cfg->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV && !cfg->is_bidir) {
 		ext_buf_info->free_cb = dummy_free_ext_buf;
 		ext_buf_info->fcb_opaque = NULL;
 		for (i = 0; i < nr_buf; i++) {
@@ -534,6 +542,19 @@  setup_memory_env(struct test_configure *cfg,
 		}
 	}
 
+	if (cfg->is_bidir) {
+		ext_buf_info->free_cb = dummy_free_ext_buf;
+		ext_buf_info->fcb_opaque = NULL;
+		for (i = 0; i < nr_buf; i++) {
+			/* Using mbuf structure to hold remote iova address. */
+			rte_pktmbuf_attach_extbuf((*srcs)[i],
+				(void *)(cfg->vchan_dev.raddr + (i * buf_size)),
+				(rte_iova_t)(cfg->vchan_dev.raddr + (i * buf_size)),
+				0, ext_buf_info);
+			rte_mbuf_ext_refcnt_update(ext_buf_info, 1);
+		}
+	}
+
 	if (cfg->is_sg) {
 		uint8_t nb_src_sges = cfg->nb_src_sges;
 		uint8_t nb_dst_sges = cfg->nb_dst_sges;
@@ -676,16 +697,30 @@  mem_copy_benchmark(struct test_configure *cfg)
 		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 (cfg->is_sg) {
-			lcores[i]->sge.nb_srcs = cfg->nb_src_sges;
-			lcores[i]->sge.nb_dsts = cfg->nb_dst_sges;
-			lcores[i]->sge.srcs = src_sges + (nr_sgsrc / nb_workers * i);
-			lcores[i]->sge.dsts = dst_sges + (nr_sgdst / nb_workers * i);
+		/* Number of workers is equal to number of devices. In case of bi-directional
+		 * dma, use 1 device for mem-to-dev and 1 device for dev-to-mem.
+		 */
+		if (cfg->is_dma && cfg->is_bidir && (i % 2 != 0)) {
+			lcores[i]->dsts = srcs + offset;
+			lcores[i]->srcs = dsts + offset;
+			if (cfg->is_sg) {
+				lcores[i]->sge.nb_dsts = cfg->nb_src_sges;
+				lcores[i]->sge.nb_srcs = cfg->nb_dst_sges;
+				lcores[i]->sge.dsts = src_sges + (nr_sgsrc / nb_workers * i);
+				lcores[i]->sge.srcs = dst_sges + (nr_sgdst / nb_workers * i);
+			}
+		} else {
+			lcores[i]->srcs = srcs + offset;
+			lcores[i]->dsts = dsts + offset;
+			if (cfg->is_sg) {
+				lcores[i]->sge.nb_srcs = cfg->nb_src_sges;
+				lcores[i]->sge.nb_dsts = cfg->nb_dst_sges;
+				lcores[i]->sge.srcs = src_sges + (nr_sgsrc / nb_workers * i);
+				lcores[i]->sge.dsts = dst_sges + (nr_sgdst / nb_workers * i);
+			}
 		}
 
 		rte_eal_remote_launch(get_work_function(cfg), (void *)(lcores[i]),
@@ -778,6 +813,8 @@  mem_copy_benchmark(struct test_configure *cfg)
 		calc_result(buf_size, nr_buf, nb_workers, test_secs,
 			lcores[i]->worker_info.test_cpl,
 			&memory, &avg_cycles, &bandwidth, &mops);
+		if (cfg->is_bidir)
+			printf("%s direction\n", i % 2 ? "MEM-to-DEV" : "DEV-to-MEM");
 		output_result(cfg, lcores[i], kick_batch, avg_cycles, buf_size,
 			nr_buf / nb_workers, memory, bandwidth, mops);
 		mops_total += mops;
@@ -791,7 +828,7 @@  mem_copy_benchmark(struct test_configure *cfg)
 
 out:
 
-	if (cfg->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM)
+	if (cfg->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM || cfg->is_bidir)
 		m = srcs;
 	else if (cfg->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV)
 		m = dsts;
diff --git a/app/test-dma-perf/config.ini b/app/test-dma-perf/config.ini
index 2a7e2567d3..541885e34e 100644
--- a/app/test-dma-perf/config.ini
+++ b/app/test-dma-perf/config.ini
@@ -47,6 +47,10 @@ 
 ;    "vfid" denotes VF-id of PF-id to be used for data transfer.
 ;    Example: vchan_dev=raddr=0x400000,coreid=1,pfid=2,vfid=3
 
+; "xfer_mode" denotes mode of data transfer. It can take 2 values:
+;    0 - unidirection transfer based on direction configured (default).
+;    1 - Bi-directional transfer based on direction configured (mem-to-dev and dev-to-mem).
+
 ; Parameters for DMA scatter-gather memory copy:
 ;
 ; "dma_src_sge" denotes number of source segments.
@@ -93,6 +97,7 @@  eal_args=--in-memory --file-prefix=test
 skip=1
 type=DMA_MEM_COPY
 direction=dev2mem
+xfer_mode=0
 vchan_dev=raddr=0x200000000,coreid=1,pfid=2,vfid=3
 mem_size=10
 buf_size=64,4096,2,MUL
diff --git a/app/test-dma-perf/main.c b/app/test-dma-perf/main.c
index 18219918cc..b67f8380b2 100644
--- a/app/test-dma-perf/main.c
+++ b/app/test-dma-perf/main.c
@@ -368,6 +368,7 @@  load_configs(const char *path)
 	const char *skip;
 	struct rte_kvargs *kvlist;
 	const char *vchan_dev;
+	const char *xfer_mode;
 	int args_nr, nb_vp;
 	bool is_dma;
 
@@ -421,6 +422,21 @@  load_configs(const char *path)
 					test_case->transfer_dir = RTE_DMA_DIR_MEM_TO_MEM;
 				}
 			}
+
+			xfer_mode = rte_cfgfile_get_entry(cfgfile, section_name, "xfer_mode");
+			if (xfer_mode) {
+				int xmode = atoi(xfer_mode);
+				if (xmode == 1) {
+					if (test_case->transfer_dir == RTE_DMA_DIR_MEM_TO_MEM) {
+						printf("Error: Invalid configuration. For mem to"
+						       " mem dma transfer bi-directional cannot be"
+						       " configured.\n");
+						test_case->is_valid = false;
+						continue;
+					}
+					test_case->is_bidir = true;
+				}
+			}
 			is_dma = true;
 		} else if (strcmp(case_type, CPU_MEM_COPY) == 0) {
 			test_case->test_type = TEST_TYPE_CPU_MEM_COPY;
@@ -433,7 +449,7 @@  load_configs(const char *path)
 		}
 
 		if (test_case->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV ||
-			test_case->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
+		    test_case->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
 			vchan_dev = rte_cfgfile_get_entry(cfgfile, section_name, "vchan_dev");
 			if (vchan_dev == NULL) {
 				printf("Transfer direction mem2dev and dev2mem"
diff --git a/app/test-dma-perf/main.h b/app/test-dma-perf/main.h
index e88d72f54f..e6fe9c7f0b 100644
--- a/app/test-dma-perf/main.h
+++ b/app/test-dma-perf/main.h
@@ -67,6 +67,7 @@  struct test_configure {
 	const char *eal_args;
 	uint8_t scenario_id;
 	struct test_vchan_dev_config vchan_dev;
+	bool is_bidir;
 };
 
 int mem_copy_benchmark(struct test_configure *cfg);