[dpdk-dev] [PATCH 2/4] net/mlx5: modify net PMD to use common multi-process APIs

[Vu Pham <vuhuoong@mellanox.com>]

From: Vu Pham <vuhuong@mellanox.com>

Modify net PMD to use multi-process IPC APIs from common driver.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
---
 drivers/common/mlx5/Makefile    |   3 +-
 drivers/common/mlx5/meson.build |   1 +
 drivers/net/mlx5/mlx5.c         |  15 ++-
 drivers/net/mlx5/mlx5.h         |  43 +-------
 drivers/net/mlx5/mlx5_mp.c      | 234 +++-------------------------------------
 drivers/net/mlx5/mlx5_mr.c      |   2 +-
 drivers/net/mlx5/mlx5_rxtx.c    |   3 +-
 7 files changed, 37 insertions(+), 264 deletions(-)

diff --git a/drivers/common/mlx5/Makefile b/drivers/common/mlx5/Makefile
index f32933d592..2a88492731 100644
--- a/drivers/common/mlx5/Makefile
+++ b/drivers/common/mlx5/Makefile
@@ -17,6 +17,7 @@ endif
 SRCS-y += mlx5_devx_cmds.c
 SRCS-y += mlx5_common.c
 SRCS-y += mlx5_nl.c
+SRCS-y += mlx5_common_mp.c
 ifeq ($(CONFIG_RTE_IBVERBS_LINK_DLOPEN),y)
 INSTALL-y-lib += $(LIB_GLUE)
 endif
@@ -46,7 +47,7 @@ endif
 LDLIBS += -lrte_eal -lrte_pci -lrte_kvargs -lrte_net
 
 # A few warnings cannot be avoided in external headers.
-CFLAGS += -Wno-error=cast-qual -UPEDANTIC
+CFLAGS += -Wno-error=cast-qual  -UPEDANTIC -DALLOW_EXPERIMENTAL_API
 
 EXPORT_MAP := rte_common_mlx5_version.map
 
diff --git a/drivers/common/mlx5/meson.build b/drivers/common/mlx5/meson.build
index f671710714..83671861c9 100644
--- a/drivers/common/mlx5/meson.build
+++ b/drivers/common/mlx5/meson.build
@@ -55,6 +55,7 @@ sources = files(
 	'mlx5_devx_cmds.c',
 	'mlx5_common.c',
 	'mlx5_nl.c',
+	'mlx5_common_mp.c',
 )
 if not dlopen_ibverbs
 	sources += files('mlx5_glue.c')
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 94aaa60579..f802bcee3d 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -38,6 +38,7 @@
 #include <mlx5_glue.h>
 #include <mlx5_devx_cmds.h>
 #include <mlx5_common.h>
+#include <mlx5_common_mp.h>
 
 #include "mlx5_defs.h"
 #include "mlx5.h"
@@ -1694,7 +1695,8 @@ mlx5_init_once(void)
 		rte_rwlock_init(&sd->mem_event_rwlock);
 		rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
 						mlx5_mr_mem_event_cb, NULL);
-		ret = mlx5_mp_init_primary();
+		ret = mlx5_mp_init_primary(MLX5_MP_NAME,
+					   mlx5_mp_primary_handle);
 		if (ret)
 			goto out;
 		sd->init_done = true;
@@ -1702,7 +1704,8 @@ mlx5_init_once(void)
 	case RTE_PROC_SECONDARY:
 		if (ld->init_done)
 			break;
-		ret = mlx5_mp_init_secondary();
+		ret = mlx5_mp_init_secondary(MLX5_MP_NAME,
+					     mlx5_mp_secondary_handle);
 		if (ret)
 			goto out;
 		++sd->secondary_cnt;
@@ -2177,6 +2180,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	}
 	DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+		struct mlx5_mp_id mp_id;
+
 		eth_dev = rte_eth_dev_attach_secondary(name);
 		if (eth_dev == NULL) {
 			DRV_LOG(ERR, "can not attach rte ethdev");
@@ -2188,8 +2193,10 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		err = mlx5_proc_priv_init(eth_dev);
 		if (err)
 			return NULL;
+		mp_id.port_id = eth_dev->data->port_id;
+		strlcpy(mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
 		/* Receive command fd from primary process */
-		err = mlx5_mp_req_verbs_cmd_fd(eth_dev);
+		err = mlx5_mp_req_verbs_cmd_fd(&mp_id);
 		if (err < 0)
 			return NULL;
 		/* Remap UAR for Tx queues. */
@@ -2353,6 +2360,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	priv->ibv_port = spawn->ibv_port;
 	priv->pci_dev = spawn->pci_dev;
 	priv->mtu = RTE_ETHER_MTU;
+	priv->mp_id.port_id = port_id;
+	strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
 #ifndef RTE_ARCH_64
 	/* Initialize UAR access locks for 32bit implementations. */
 	rte_spinlock_init(&priv->uar_lock_cq);
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index d7c519bae0..dc02e148c3 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -36,43 +36,13 @@
 #include <mlx5_devx_cmds.h>
 #include <mlx5_prm.h>
 #include <mlx5_nl.h>
+#include <mlx5_common_mp.h>
 
 #include "mlx5_defs.h"
 #include "mlx5_utils.h"
 #include "mlx5_mr.h"
 #include "mlx5_autoconf.h"
 
-/* Request types for IPC. */
-enum mlx5_mp_req_type {
-	MLX5_MP_REQ_VERBS_CMD_FD = 1,
-	MLX5_MP_REQ_CREATE_MR,
-	MLX5_MP_REQ_START_RXTX,
-	MLX5_MP_REQ_STOP_RXTX,
-	MLX5_MP_REQ_QUEUE_STATE_MODIFY,
-};
-
-struct mlx5_mp_arg_queue_state_modify {
-	uint8_t is_wq; /* Set if WQ. */
-	uint16_t queue_id; /* DPDK queue ID. */
-	enum ibv_wq_state state; /* WQ requested state. */
-};
-
-/* Pameters for IPC. */
-struct mlx5_mp_param {
-	enum mlx5_mp_req_type type;
-	int port_id;
-	int result;
-	RTE_STD_C11
-	union {
-		uintptr_t addr; /* MLX5_MP_REQ_CREATE_MR */
-		struct mlx5_mp_arg_queue_state_modify state_modify;
-		/* MLX5_MP_REQ_QUEUE_STATE_MODIFY */
-	} args;
-};
-
-/** Request timeout for IPC. */
-#define MLX5_MP_REQ_TIMEOUT_SEC 5
-
 /** Key string for IPC. */
 #define MLX5_MP_NAME "net_mlx5_mp"
 
@@ -555,6 +525,7 @@ struct mlx5_priv {
 #endif
 	uint8_t skip_default_rss_reta; /* Skip configuration of default reta. */
 	uint8_t fdb_def_rule; /* Whether fdb jump to table 1 is configured. */
+	struct mlx5_mp_id mp_id; /* ID of a multi-process process */
 };
 
 #define PORT_ID(priv) ((priv)->dev_data->port_id)
@@ -750,16 +721,10 @@ int mlx5_flow_dev_dump(struct rte_eth_dev *dev, FILE *file,
 		       struct rte_flow_error *error);
 
 /* mlx5_mp.c */
+int mlx5_mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer);
+int mlx5_mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer);
 void mlx5_mp_req_start_rxtx(struct rte_eth_dev *dev);
 void mlx5_mp_req_stop_rxtx(struct rte_eth_dev *dev);
-int mlx5_mp_req_mr_create(struct rte_eth_dev *dev, uintptr_t addr);
-int mlx5_mp_req_verbs_cmd_fd(struct rte_eth_dev *dev);
-int mlx5_mp_req_queue_state_modify(struct rte_eth_dev *dev,
-				   struct mlx5_mp_arg_queue_state_modify *sm);
-int mlx5_mp_init_primary(void);
-void mlx5_mp_uninit_primary(void);
-int mlx5_mp_init_secondary(void);
-void mlx5_mp_uninit_secondary(void);
 
 /* mlx5_socket.c */
 
diff --git a/drivers/net/mlx5/mlx5_mp.c b/drivers/net/mlx5/mlx5_mp.c
index 55d408fe95..43684dbc3a 100644
--- a/drivers/net/mlx5/mlx5_mp.c
+++ b/drivers/net/mlx5/mlx5_mp.c
@@ -10,46 +10,14 @@
 #include <rte_ethdev_driver.h>
 #include <rte_string_fns.h>
 
+#include <mlx5_common_mp.h>
+
 #include "mlx5.h"
 #include "mlx5_rxtx.h"
 #include "mlx5_utils.h"
 
-/**
- * Initialize IPC message.
- *
- * @param[in] dev
- *   Pointer to Ethernet structure.
- * @param[out] msg
- *   Pointer to message to fill in.
- * @param[in] type
- *   Message type.
- */
-static inline void
-mp_init_msg(struct rte_eth_dev *dev, struct rte_mp_msg *msg,
-	    enum mlx5_mp_req_type type)
-{
-	struct mlx5_mp_param *param = (struct mlx5_mp_param *)msg->param;
-
-	memset(msg, 0, sizeof(*msg));
-	strlcpy(msg->name, MLX5_MP_NAME, sizeof(msg->name));
-	msg->len_param = sizeof(*param);
-	param->type = type;
-	param->port_id = dev->data->port_id;
-}
-
-/**
- * IPC message handler of primary process.
- *
- * @param[in] dev
- *   Pointer to Ethernet structure.
- * @param[in] peer
- *   Pointer to the peer socket path.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
+int
+mlx5_mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 {
 	struct rte_mp_msg mp_res;
 	struct mlx5_mp_param *res = (struct mlx5_mp_param *)mp_res.param;
@@ -71,21 +39,21 @@ mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 	priv = dev->data->dev_private;
 	switch (param->type) {
 	case MLX5_MP_REQ_CREATE_MR:
-		mp_init_msg(dev, &mp_res, param->type);
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		lkey = mlx5_mr_create_primary(dev, &entry, param->args.addr);
 		if (lkey == UINT32_MAX)
 			res->result = -rte_errno;
 		ret = rte_mp_reply(&mp_res, peer);
 		break;
 	case MLX5_MP_REQ_VERBS_CMD_FD:
-		mp_init_msg(dev, &mp_res, param->type);
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		mp_res.num_fds = 1;
 		mp_res.fds[0] = priv->sh->ctx->cmd_fd;
 		res->result = 0;
 		ret = rte_mp_reply(&mp_res, peer);
 		break;
 	case MLX5_MP_REQ_QUEUE_STATE_MODIFY:
-		mp_init_msg(dev, &mp_res, param->type);
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		res->result = mlx5_queue_state_modify_primary
 					(dev, &param->args.state_modify);
 		ret = rte_mp_reply(&mp_res, peer);
@@ -110,14 +78,15 @@ mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-static int
-mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
+int
+mlx5_mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 {
 	struct rte_mp_msg mp_res;
 	struct mlx5_mp_param *res = (struct mlx5_mp_param *)mp_res.param;
 	const struct mlx5_mp_param *param =
 		(const struct mlx5_mp_param *)mp_msg->param;
 	struct rte_eth_dev *dev;
+	struct mlx5_priv *priv;
 	int ret;
 
 	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
@@ -127,13 +96,14 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 		return -rte_errno;
 	}
 	dev = &rte_eth_devices[param->port_id];
+	priv = dev->data->dev_private;
 	switch (param->type) {
 	case MLX5_MP_REQ_START_RXTX:
 		DRV_LOG(INFO, "port %u starting datapath", dev->data->port_id);
 		rte_mb();
 		dev->rx_pkt_burst = mlx5_select_rx_function(dev);
 		dev->tx_pkt_burst = mlx5_select_tx_function(dev);
-		mp_init_msg(dev, &mp_res, param->type);
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		res->result = 0;
 		ret = rte_mp_reply(&mp_res, peer);
 		break;
@@ -142,7 +112,7 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 		dev->rx_pkt_burst = removed_rx_burst;
 		dev->tx_pkt_burst = removed_tx_burst;
 		rte_mb();
-		mp_init_msg(dev, &mp_res, param->type);
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		res->result = 0;
 		ret = rte_mp_reply(&mp_res, peer);
 		break;
@@ -171,6 +141,7 @@ mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx5_mp_req_type type)
 	struct rte_mp_reply mp_rep;
 	struct mlx5_mp_param *res;
 	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
+	struct mlx5_priv *priv = dev->data->dev_private;
 	int ret;
 	int i;
 
@@ -182,7 +153,7 @@ mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx5_mp_req_type type)
 			dev->data->port_id, type);
 		return;
 	}
-	mp_init_msg(dev, &mp_req, type);
+	mp_init_msg(&priv->mp_id, &mp_req, type);
 	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
 	if (ret) {
 		if (rte_errno != ENOTSUP)
@@ -234,178 +205,3 @@ mlx5_mp_req_stop_rxtx(struct rte_eth_dev *dev)
 {
 	mp_req_on_rxtx(dev, MLX5_MP_REQ_STOP_RXTX);
 }
-
-/**
- * Request Memory Region creation to the primary process.
- *
- * @param[in] dev
- *   Pointer to Ethernet structure.
- * @param addr
- *   Target virtual address to register.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_mp_req_mr_create(struct rte_eth_dev *dev, uintptr_t addr)
-{
-	struct rte_mp_msg mp_req;
-	struct rte_mp_msg *mp_res;
-	struct rte_mp_reply mp_rep;
-	struct mlx5_mp_param *req = (struct mlx5_mp_param *)mp_req.param;
-	struct mlx5_mp_param *res;
-	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
-	int ret;
-
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	mp_init_msg(dev, &mp_req, MLX5_MP_REQ_CREATE_MR);
-	req->args.addr = addr;
-	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
-	if (ret) {
-		DRV_LOG(ERR, "port %u request to primary process failed",
-			dev->data->port_id);
-		return -rte_errno;
-	}
-	MLX5_ASSERT(mp_rep.nb_received == 1);
-	mp_res = &mp_rep.msgs[0];
-	res = (struct mlx5_mp_param *)mp_res->param;
-	ret = res->result;
-	if (ret)
-		rte_errno = -ret;
-	free(mp_rep.msgs);
-	return ret;
-}
-
-/**
- * Request Verbs queue state modification to the primary process.
- *
- * @param[in] dev
- *   Pointer to Ethernet structure.
- * @param sm
- *   State modify parameters.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_mp_req_queue_state_modify(struct rte_eth_dev *dev,
-			       struct mlx5_mp_arg_queue_state_modify *sm)
-{
-	struct rte_mp_msg mp_req;
-	struct rte_mp_msg *mp_res;
-	struct rte_mp_reply mp_rep;
-	struct mlx5_mp_param *req = (struct mlx5_mp_param *)mp_req.param;
-	struct mlx5_mp_param *res;
-	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
-	int ret;
-
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	mp_init_msg(dev, &mp_req, MLX5_MP_REQ_QUEUE_STATE_MODIFY);
-	req->args.state_modify = *sm;
-	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
-	if (ret) {
-		DRV_LOG(ERR, "port %u request to primary process failed",
-			dev->data->port_id);
-		return -rte_errno;
-	}
-	MLX5_ASSERT(mp_rep.nb_received == 1);
-	mp_res = &mp_rep.msgs[0];
-	res = (struct mlx5_mp_param *)mp_res->param;
-	ret = res->result;
-	free(mp_rep.msgs);
-	return ret;
-}
-
-/**
- * Request Verbs command file descriptor for mmap to the primary process.
- *
- * @param[in] dev
- *   Pointer to Ethernet structure.
- *
- * @return
- *   fd on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_mp_req_verbs_cmd_fd(struct rte_eth_dev *dev)
-{
-	struct rte_mp_msg mp_req;
-	struct rte_mp_msg *mp_res;
-	struct rte_mp_reply mp_rep;
-	struct mlx5_mp_param *res;
-	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
-	int ret;
-
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	mp_init_msg(dev, &mp_req, MLX5_MP_REQ_VERBS_CMD_FD);
-	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
-	if (ret) {
-		DRV_LOG(ERR, "port %u request to primary process failed",
-			dev->data->port_id);
-		return -rte_errno;
-	}
-	MLX5_ASSERT(mp_rep.nb_received == 1);
-	mp_res = &mp_rep.msgs[0];
-	res = (struct mlx5_mp_param *)mp_res->param;
-	if (res->result) {
-		rte_errno = -res->result;
-		DRV_LOG(ERR,
-			"port %u failed to get command FD from primary process",
-			dev->data->port_id);
-		ret = -rte_errno;
-		goto exit;
-	}
-	MLX5_ASSERT(mp_res->num_fds == 1);
-	ret = mp_res->fds[0];
-	DRV_LOG(DEBUG, "port %u command FD from primary is %d",
-		dev->data->port_id, ret);
-exit:
-	free(mp_rep.msgs);
-	return ret;
-}
-
-/**
- * Initialize by primary process.
- */
-int
-mlx5_mp_init_primary(void)
-{
-	int ret;
-
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
-
-	/* primary is allowed to not support IPC */
-	ret = rte_mp_action_register(MLX5_MP_NAME, mp_primary_handle);
-	if (ret && rte_errno != ENOTSUP)
-		return -1;
-	return 0;
-}
-
-/**
- * Un-initialize by primary process.
- */
-void
-mlx5_mp_uninit_primary(void)
-{
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
-	rte_mp_action_unregister(MLX5_MP_NAME);
-}
-
-/**
- * Initialize by secondary process.
- */
-int
-mlx5_mp_init_secondary(void)
-{
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	return rte_mp_action_register(MLX5_MP_NAME, mp_secondary_handle);
-}
-
-/**
- * Un-initialize by secondary process.
- */
-void
-mlx5_mp_uninit_secondary(void)
-{
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	rte_mp_action_unregister(MLX5_MP_NAME);
-}
diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
index 6aa578646f..8097211b55 100644
--- a/drivers/net/mlx5/mlx5_mr.c
+++ b/drivers/net/mlx5/mlx5_mr.c
@@ -540,7 +540,7 @@ mlx5_mr_create_secondary(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry,
 
 	DEBUG("port %u requesting MR creation for address (%p)",
 	      dev->data->port_id, (void *)addr);
-	ret = mlx5_mp_req_mr_create(dev, addr);
+	ret = mlx5_mp_req_mr_create(&priv->mp_id, addr);
 	if (ret) {
 		DEBUG("port %u fail to request MR creation for address (%p)",
 		      dev->data->port_id, (void *)addr);
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index f3bf763769..fc7591c2b0 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -1000,6 +1000,7 @@ static int
 mlx5_queue_state_modify(struct rte_eth_dev *dev,
 			struct mlx5_mp_arg_queue_state_modify *sm)
 {
+	struct mlx5_priv *priv = dev->data->dev_private;
 	int ret = 0;
 
 	switch (rte_eal_process_type()) {
@@ -1007,7 +1008,7 @@ mlx5_queue_state_modify(struct rte_eth_dev *dev,
 		ret = mlx5_queue_state_modify_primary(dev, sm);
 		break;
 	case RTE_PROC_SECONDARY:
-		ret = mlx5_mp_req_queue_state_modify(dev, sm);
+		ret = mlx5_mp_req_queue_state_modify(&priv->mp_id, sm);
 		break;
 	default:
 		break;
-- 
2.16.6