[PATCH 2/2] app/dma-perf: add PCI device support

[Amit Prakash Shukla <amitprakashs@marvell.com>]

Add support to test performance for "device to memory" and
"memory to device" data transfer.

Signed-off-by: Amit Prakash Shukla <amitprakashs@marvell.com>
---
 app/test-dma-perf/benchmark.c | 67 +++++++++++++++++++++++++++++++----
 app/test-dma-perf/config.ini  | 37 +++++++++++++++++++
 app/test-dma-perf/main.c      | 67 +++++++++++++++++++++++++++++++++++
 app/test-dma-perf/main.h      |  6 ++++
 4 files changed, 170 insertions(+), 7 deletions(-)

diff --git a/app/test-dma-perf/benchmark.c b/app/test-dma-perf/benchmark.c
index 0601e0d171..523f2fbb5a 100644
--- a/app/test-dma-perf/benchmark.c
+++ b/app/test-dma-perf/benchmark.c
@@ -127,17 +127,54 @@ cache_flush_buf(__rte_unused struct rte_mbuf **array,
 #endif
 }
 
+static int
+vchan_data_populate(uint32_t dev_id, struct rte_dma_vchan_conf *qconf,
+		    struct test_configure *cfg)
+{
+	struct rte_dma_info info;
+
+	qconf->direction = cfg->transfer_dir;
+
+	rte_dma_info_get(dev_id, &info);
+	if (!(RTE_BIT64(qconf->direction) & info.dev_capa))
+		return -1;
+
+	qconf->nb_desc = cfg->ring_size.cur;
+
+	switch (qconf->direction) {
+	case RTE_DMA_DIR_MEM_TO_DEV:
+		qconf->dst_port.pcie.vfen = 1;
+		qconf->dst_port.port_type = RTE_DMA_PORT_PCIE;
+		qconf->dst_port.pcie.coreid = cfg->dcoreid;
+		qconf->dst_port.pcie.vfid = cfg->vfid;
+		qconf->dst_port.pcie.pfid = cfg->pfid;
+		break;
+	case RTE_DMA_DIR_DEV_TO_MEM:
+		qconf->src_port.pcie.vfen = 1;
+		qconf->src_port.port_type = RTE_DMA_PORT_PCIE;
+		qconf->src_port.pcie.coreid = cfg->scoreid;
+		qconf->src_port.pcie.vfid = cfg->vfid;
+		qconf->src_port.pcie.pfid = cfg->pfid;
+		break;
+	case RTE_DMA_DIR_MEM_TO_MEM:
+	case RTE_DMA_DIR_DEV_TO_DEV:
+		break;
+	}
+
+	return 0;
+}
+
 /* Configuration of device. */
 static void
-configure_dmadev_queue(uint32_t dev_id, uint32_t ring_size)
+configure_dmadev_queue(uint32_t dev_id, struct test_configure *cfg)
 {
 	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
-	};
+	struct rte_dma_vchan_conf qconf = { 0 };
+
+	if (vchan_data_populate(dev_id, &qconf, cfg) != 0)
+		rte_exit(EXIT_FAILURE, "Error with vchan data populate.\n");
 
 	if (rte_dma_configure(dev_id, &dev_config) != 0)
 		rte_exit(EXIT_FAILURE, "Error with dma configure.\n");
@@ -159,7 +196,6 @@ configure_dmadev_queue(uint32_t dev_id, uint32_t ring_size)
 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;
@@ -176,7 +212,7 @@ config_dmadevs(struct test_configure *cfg)
 		}
 
 		ldm->dma_ids[i] = dev_id;
-		configure_dmadev_queue(dev_id, ring_size);
+		configure_dmadev_queue(dev_id, cfg);
 		++nb_dmadevs;
 	}
 
@@ -308,6 +344,7 @@ setup_memory_env(struct test_configure *cfg, struct rte_mbuf ***srcs,
 	unsigned int buf_size = cfg->buf_size.cur;
 	unsigned int nr_sockets;
 	uint32_t nr_buf = cfg->nr_buf;
+	uint32_t i;
 
 	nr_sockets = rte_socket_count();
 	if (cfg->src_numa_node >= nr_sockets ||
@@ -360,6 +397,22 @@ setup_memory_env(struct test_configure *cfg, struct rte_mbuf ***srcs,
 		return -1;
 	}
 
+	if (cfg->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
+		for (i = 0; i < nr_buf; i++) {
+			/* Using mbuf structure to hold remote iova address. */
+			rte_mbuf_iova_set(*srcs[i], (rte_iova_t)cfg->raddr);
+			((*srcs)[i])->data_off = 0;
+		}
+	}
+
+	if (cfg->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV) {
+		for (i = 0; i < nr_buf; i++) {
+			/* Using mbuf structure to hold remote iova address. */
+			rte_mbuf_iova_set(*dsts[i], (rte_iova_t)cfg->raddr);
+			((*dsts)[i])->data_off = 0;
+		}
+	}
+
 	return 0;
 }
 
diff --git a/app/test-dma-perf/config.ini b/app/test-dma-perf/config.ini
index 4d59234b2a..cddcf93c6e 100644
--- a/app/test-dma-perf/config.ini
+++ b/app/test-dma-perf/config.ini
@@ -38,6 +38,23 @@
 
 ; "skip" To skip a test-case set skip to 1.
 
+; Parameters to be configured for data transfers from "mem to dev" and "dev to mem":
+; ==================================================================================
+; "direction" denotes the direction of data transfer. It can take 3 values:
+;    0 - mem to mem transfer
+;    1 - mem to dev transfer
+;    2 - dev to mem transfer
+; If not specified the default value is 0 (mem to mem transfer).
+
+; "raddr" remote iova address for "mem to dev" and "dev to mem" transfer.
+
+; "scoreid" denotes source PCIe core index.
+; "dcoreid" denotes destination PCIe core index.
+; "pfid" denotes PF-id to be used for data transfer
+; "vfid" denotes VF-id of PF-id to be used for data transfer.
+
+; =========== End of "mem to dev" and "dev to mem" config parameters. ==============
+
 [case1]
 type=DMA_MEM_COPY
 mem_size=10
@@ -52,6 +69,26 @@ lcore_dma=lcore10@0000:00:04.2, lcore11@0000:00:04.3
 eal_args=--in-memory --file-prefix=test
 
 [case2]
+skip=1
+type=DMA_MEM_COPY
+direction=2
+raddr=0x200000000
+scoreid=0
+dcoreid=0
+pfid=0
+vfid=0
+mem_size=10
+buf_size=64,4096,2,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
+
+[case3]
 type=CPU_MEM_COPY
 mem_size=10
 buf_size=64,8192,2,MUL
diff --git a/app/test-dma-perf/main.c b/app/test-dma-perf/main.c
index 61260fa072..9640356592 100644
--- a/app/test-dma-perf/main.c
+++ b/app/test-dma-perf/main.c
@@ -16,6 +16,7 @@
 #include <rte_cfgfile.h>
 #include <rte_string_fns.h>
 #include <rte_lcore.h>
+#include <rte_dmadev.h>
 
 #include "main.h"
 
@@ -318,9 +319,11 @@ load_configs(const char *path)
 	struct test_configure *test_case;
 	char section_name[CFG_NAME_LEN];
 	const char *case_type;
+	const char *transfer_dir;
 	const char *lcore_dma;
 	const char *mem_size_str, *buf_size_str, *ring_size_str, *kick_batch_str;
 	const char *skip;
+	const char *raddr, *scoreid, *dcoreid, *vfid, *pfid;
 	int args_nr, nb_vp;
 	bool is_dma;
 
@@ -358,6 +361,20 @@ load_configs(const char *path)
 		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;
+
+			transfer_dir = rte_cfgfile_get_entry(cfgfile, section_name, "direction");
+			if (transfer_dir == NULL) {
+				printf("Transfer direction not configured."
+					" Defaulting it to MEM to MEM transfer.\n");
+				test_case->transfer_dir = RTE_DMA_DIR_MEM_TO_MEM;
+			} else
+				test_case->transfer_dir = (uint8_t)atoi(transfer_dir);
+
+			if (test_case->transfer_dir >= RTE_DMA_DIR_DEV_TO_DEV) {
+				printf("Error: Invalid transfer direction configured.\n");
+				test_case->is_valid = false;
+				continue;
+			}
 			is_dma = true;
 		} else if (strcmp(case_type, CPU_MEM_COPY) == 0) {
 			test_case->test_type = TEST_TYPE_CPU_MEM_COPY;
@@ -369,6 +386,56 @@ load_configs(const char *path)
 			continue;
 		}
 
+		if (test_case->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV ||
+			test_case->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
+			char *endptr;
+
+			raddr = rte_cfgfile_get_entry(cfgfile, section_name, "raddr");
+			if (raddr == NULL) {
+				printf("Error: No raddr configured for case%d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+			test_case->raddr = strtoull(raddr, &endptr, 16);
+
+			vfid = rte_cfgfile_get_entry(cfgfile, section_name, "vfid");
+			if (vfid == NULL) {
+				printf("Error: No vfid configured for case%d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+			test_case->vfid = (uint16_t)atoi(vfid);
+
+			pfid = rte_cfgfile_get_entry(cfgfile, section_name, "pfid");
+			if (pfid == NULL) {
+				printf("Error: No pfid configured for case%d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+			test_case->pfid = (uint8_t)atoi(pfid);
+
+		}
+
+		if (test_case->transfer_dir == RTE_DMA_DIR_DEV_TO_MEM) {
+			scoreid = rte_cfgfile_get_entry(cfgfile, section_name, "scoreid");
+			if (scoreid == NULL) {
+				printf("Error: No scoreid configured for case%d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+			test_case->scoreid = (uint8_t)atoi(scoreid);
+		}
+
+		if (test_case->transfer_dir == RTE_DMA_DIR_MEM_TO_DEV) {
+			dcoreid = rte_cfgfile_get_entry(cfgfile, section_name, "dcoreid");
+			if (dcoreid == NULL) {
+				printf("Error: No dcoreid configured for case%d.\n", i + 1);
+				test_case->is_valid = false;
+				continue;
+			}
+			test_case->dcoreid = (uint8_t)atoi(dcoreid);
+		}
+
 		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,
diff --git a/app/test-dma-perf/main.h b/app/test-dma-perf/main.h
index be89cb2b65..617f62f085 100644
--- a/app/test-dma-perf/main.h
+++ b/app/test-dma-perf/main.h
@@ -43,6 +43,7 @@ struct test_configure {
 	bool is_valid;
 	bool is_skip;
 	uint8_t test_type;
+	uint8_t transfer_dir;
 	const char *test_type_str;
 	uint16_t src_numa_node;
 	uint16_t dst_numa_node;
@@ -58,6 +59,11 @@ struct test_configure {
 	uint16_t test_secs;
 	const char *eal_args;
 	uint8_t scenario_id;
+	uint8_t scoreid;
+	uint8_t dcoreid;
+	uint8_t pfid;
+	uint16_t vfid;
+	uint64_t raddr;
 };
 
 void mem_copy_benchmark(struct test_configure *cfg, bool is_dma);
-- 
2.25.1