mlx5: sharing global MR cache between drivers

index 149253d174..459414d5c2 100644
@@ -122,8 +122,21 @@ mlx5_init_shared_data(void)
 static int
 mlx5_init_once(void)
 {
+	struct mlx5_shared_data *sd;
+
 	if (mlx5_init_shared_data())
 		return -rte_errno;
+	sd = mlx5_shared_data;
+	rte_spinlock_lock(&sd->lock);
+	MLX5_ASSERT(sd);
+	if (!sd->init_done) {
+		LIST_INIT(&sd->mem_event_cb_list);
+		rte_rwlock_init(&sd->mem_event_rwlock);
+		rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
+						mlx5_mr_mem_event_cb, NULL);
+		sd->init_done = true;
+	}
+	rte_spinlock_unlock(&sd->lock);
 	return 0;
 }
 

index 6885bbb1d2..91de7b3e2c 100644
@@ -241,7 +241,7 @@ drivers_remove(struct mlx5_common_device *dev, uint32_t enabled_classes)
 	while (enabled_classes) {
 		driver = driver_get(RTE_BIT64(i));
 		if (driver != NULL) {
-			local_ret = driver->remove(dev->dev);
+			local_ret = driver->remove(dev);
 			if (local_ret == 0)
 				dev->classes_loaded &= ~RTE_BIT64(i);
 			else if (ret == 0)

@@ -275,7 +275,7 @@ drivers_probe(struct mlx5_common_device *dev, uint32_t user_classes)
 			ret = -EEXIST;
 			goto probe_err;
 		}
-		ret = driver->probe(dev->dev);
+		ret = driver->probe(dev);
 		if (ret < 0) {
 			DRV_LOG(ERR, "Failed to load driver %s",
 				driver->name);

index a772371200..b7e2ad1a82 100644
@@ -324,15 +324,21 @@ void mlx5_common_init(void);
  *   from devargs, locating target RDMA device and probing with it.
  */
 
+struct mlx5_common_device {
+	struct rte_device *dev;
+	TAILQ_ENTRY(mlx5_common_device) next;
+	uint32_t classes_loaded;
+};
+
 /**
  * Initialization function for the driver called during device probing.
  */
-typedef int (mlx5_class_driver_probe_t)(struct rte_device *dev);
+typedef int (mlx5_class_driver_probe_t)(struct mlx5_common_device *dev);
 
 /**
  * Uninitialization function for the driver called during hot-unplugging.
  */
-typedef int (mlx5_class_driver_remove_t)(struct rte_device *dev);
+typedef int (mlx5_class_driver_remove_t)(struct mlx5_common_device *dev);
 
 /**
  * Driver-specific DMA mapping. After a successful call the device

index a038330375..04c0af3763 100644
@@ -16,12 +16,6 @@ extern "C" {
 
 /* Common bus driver: */
 
-struct mlx5_common_device {
-	struct rte_device *dev;
-	TAILQ_ENTRY(mlx5_common_device) next;
-	uint32_t classes_loaded;
-};
-
 int mlx5_common_dev_probe(struct rte_device *eal_dev);
 int mlx5_common_dev_remove(struct rte_device *eal_dev);
 int mlx5_common_dev_dma_map(struct rte_device *dev, void *addr, uint64_t iova,

index c5e0a83a8c..afb63e9b8f 100644
@@ -36,7 +36,7 @@ struct mlx5_compress_xform {
 struct mlx5_compress_priv {
 	TAILQ_ENTRY(mlx5_compress_priv) next;
 	struct ibv_context *ctx; /* Device context. */
-	struct rte_compressdev *cdev;
+	struct rte_compressdev *compressdev;
 	void *uar;
 	uint32_t pdn; /* Protection Domain number. */
 	uint8_t min_block_size;

@@ -786,16 +786,16 @@ mlx5_compress_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
 }
 
 static int
-mlx5_compress_dev_probe(struct rte_device *dev)
+mlx5_compress_dev_probe(struct mlx5_common_device *cdev)
 {
 	struct ibv_device *ibv;
-	struct rte_compressdev *cdev;
+	struct rte_compressdev *compressdev;
 	struct ibv_context *ctx;
 	struct mlx5_compress_priv *priv;
 	struct mlx5_hca_attr att = { 0 };
 	struct rte_compressdev_pmd_init_params init_params = {
 		.name = "",
-		.socket_id = dev->numa_node,
+		.socket_id = cdev->dev->numa_node,
 	};
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {

@@ -803,7 +803,7 @@ mlx5_compress_dev_probe(struct rte_device *dev)
 		rte_errno = ENOTSUP;
 		return -rte_errno;
 	}
-	ibv = mlx5_os_get_ibv_dev(dev);
+	ibv = mlx5_os_get_ibv_dev(cdev->dev);
 	if (ibv == NULL)
 		return -rte_errno;
 	ctx = mlx5_glue->dv_open_device(ibv);

@@ -821,26 +821,26 @@ mlx5_compress_dev_probe(struct rte_device *dev)
 		rte_errno = ENOTSUP;
 		return -ENOTSUP;
 	}
-	cdev = rte_compressdev_pmd_create(ibv->name, dev,
-					  sizeof(*priv), &init_params);
-	if (cdev == NULL) {
+	compressdev = rte_compressdev_pmd_create(ibv->name, cdev->dev,
+						 sizeof(*priv), &init_params);
+	if (compressdev == NULL) {
 		DRV_LOG(ERR, "Failed to create device \"%s\".", ibv->name);
 		claim_zero(mlx5_glue->close_device(ctx));
 		return -ENODEV;
 	}
 	DRV_LOG(INFO,
 		"Compress device %s was created successfully.", ibv->name);
-	cdev->dev_ops = &mlx5_compress_ops;
-	cdev->dequeue_burst = mlx5_compress_dequeue_burst;
-	cdev->enqueue_burst = mlx5_compress_enqueue_burst;
-	cdev->feature_flags = RTE_COMPDEV_FF_HW_ACCELERATED;
-	priv = cdev->data->dev_private;
+	compressdev->dev_ops = &mlx5_compress_ops;
+	compressdev->dequeue_burst = mlx5_compress_dequeue_burst;
+	compressdev->enqueue_burst = mlx5_compress_enqueue_burst;
+	compressdev->feature_flags = RTE_COMPDEV_FF_HW_ACCELERATED;
+	priv = compressdev->data->dev_private;
 	priv->ctx = ctx;
-	priv->cdev = cdev;
+	priv->compressdev = compressdev;
 	priv->min_block_size = att.compress_min_block_size;
 	priv->sq_ts_format = att.sq_ts_format;
 	if (mlx5_compress_hw_global_prepare(priv) != 0) {
-		rte_compressdev_pmd_destroy(priv->cdev);
+		rte_compressdev_pmd_destroy(priv->compressdev);
 		claim_zero(mlx5_glue->close_device(priv->ctx));
 		return -1;
 	}

@@ -848,7 +848,7 @@ mlx5_compress_dev_probe(struct rte_device *dev)
 			     MLX5_MR_BTREE_CACHE_N * 2, rte_socket_id()) != 0) {
 		DRV_LOG(ERR, "Failed to allocate shared cache MR memory.");
 		mlx5_compress_hw_global_release(priv);
-		rte_compressdev_pmd_destroy(priv->cdev);
+		rte_compressdev_pmd_destroy(priv->compressdev);
 		claim_zero(mlx5_glue->close_device(priv->ctx));
 		rte_errno = ENOMEM;
 		return -rte_errno;

@@ -867,13 +867,13 @@ mlx5_compress_dev_probe(struct rte_device *dev)
 }
 
 static int
-mlx5_compress_dev_remove(struct rte_device *dev)
+mlx5_compress_dev_remove(struct mlx5_common_device *cdev)
 {
 	struct mlx5_compress_priv *priv = NULL;
 
 	pthread_mutex_lock(&priv_list_lock);
 	TAILQ_FOREACH(priv, &mlx5_compress_priv_list, next)
-		if (priv->cdev->device == dev)
+		if (priv->compressdev->device == cdev->dev)
 			break;
 	if (priv)
 		TAILQ_REMOVE(&mlx5_compress_priv_list, priv, next);

@@ -884,7 +884,7 @@ mlx5_compress_dev_remove(struct rte_device *dev)
 							  NULL);
 		mlx5_mr_release_cache(&priv->mr_scache);
 		mlx5_compress_hw_global_release(priv);
-		rte_compressdev_pmd_destroy(priv->cdev);
+		rte_compressdev_pmd_destroy(priv->compressdev);
 		claim_zero(mlx5_glue->close_device(priv->ctx));
 	}
 	return 0;

index 682cf8b607..b07cff40f1 100644
@@ -1001,7 +1001,7 @@ mlx5_crypto_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
 }
 
 static int
-mlx5_crypto_dev_probe(struct rte_device *dev)
+mlx5_crypto_dev_probe(struct mlx5_common_device *cdev)
 {
 	struct ibv_device *ibv;
 	struct rte_cryptodev *crypto_dev;

@@ -1013,7 +1013,7 @@ mlx5_crypto_dev_probe(struct rte_device *dev)
 	struct rte_cryptodev_pmd_init_params init_params = {
 		.name = "",
 		.private_data_size = sizeof(struct mlx5_crypto_priv),
-		.socket_id = dev->numa_node,
+		.socket_id = cdev->dev->numa_node,
 		.max_nb_queue_pairs =
 				RTE_CRYPTODEV_PMD_DEFAULT_MAX_NB_QUEUE_PAIRS,
 	};

@@ -1025,7 +1025,7 @@ mlx5_crypto_dev_probe(struct rte_device *dev)
 		rte_errno = ENOTSUP;
 		return -rte_errno;
 	}
-	ibv = mlx5_os_get_ibv_dev(dev);
+	ibv = mlx5_os_get_ibv_dev(cdev->dev);
 	if (ibv == NULL)
 		return -rte_errno;
 	ctx = mlx5_glue->dv_open_device(ibv);

@@ -1042,7 +1042,7 @@ mlx5_crypto_dev_probe(struct rte_device *dev)
 		rte_errno = ENOTSUP;
 		return -ENOTSUP;
 	}
-	ret = mlx5_crypto_parse_devargs(dev->devargs, &devarg_prms);
+	ret = mlx5_crypto_parse_devargs(cdev->dev->devargs, &devarg_prms);
 	if (ret) {
 		DRV_LOG(ERR, "Failed to parse devargs.");
 		claim_zero(mlx5_glue->close_device(ctx));

@@ -1055,8 +1055,8 @@ mlx5_crypto_dev_probe(struct rte_device *dev)
 		claim_zero(mlx5_glue->close_device(ctx));
 		return -rte_errno;
 	}
-	crypto_dev = rte_cryptodev_pmd_create(ibv->name, dev,
-					&init_params);
+	crypto_dev = rte_cryptodev_pmd_create(ibv->name, cdev->dev,
+					      &init_params);
 	if (crypto_dev == NULL) {
 		DRV_LOG(ERR, "Failed to create device \"%s\".", ibv->name);
 		claim_zero(mlx5_glue->close_device(ctx));

@@ -1115,13 +1115,13 @@ mlx5_crypto_dev_probe(struct rte_device *dev)
 }
 
 static int
-mlx5_crypto_dev_remove(struct rte_device *dev)
+mlx5_crypto_dev_remove(struct mlx5_common_device *cdev)
 {
 	struct mlx5_crypto_priv *priv = NULL;
 
 	pthread_mutex_lock(&priv_list_lock);
 	TAILQ_FOREACH(priv, &mlx5_crypto_priv_list, next)
-		if (priv->crypto_dev->device == dev)
+		if (priv->crypto_dev->device == cdev->dev)
 			break;
 	if (priv)
 		TAILQ_REMOVE(&mlx5_crypto_priv_list, priv, next);

154 lines not on this page · raw message

index 1e1b8b736b..e39e77aa9d 100644
@@ -1279,7 +1279,8 @@ mlx5_alloc_shared_dev_ctx(const struct mlx5_dev_spawn_data *spawn,
 		rte_errno  = ENOMEM;
 		goto exit;
 	}
-	sh->numa_node = spawn->numa_node;
+	sh->numa_node = spawn->cdev->dev->numa_node;
+	sh->cdev = spawn->cdev;
 	if (spawn->bond_info)
 		sh->bond = *spawn->bond_info;
 	err = mlx5_os_open_device(spawn, config, sh);

@@ -2537,19 +2538,19 @@ mlx5_eth_find_next(uint16_t port_id, struct rte_device *odev)
  *
  * This function removes all Ethernet devices belong to a given device.
  *
- * @param[in] dev
+ * @param[in] cdev
  *   Pointer to the generic device.
  *
  * @return
  *   0 on success, the function cannot fail.
  */
 int
-mlx5_net_remove(struct rte_device *dev)
+mlx5_net_remove(struct mlx5_common_device *cdev)
 {
 	uint16_t port_id;
 	int ret = 0;
 
-	RTE_ETH_FOREACH_DEV_OF(port_id, dev) {
+	RTE_ETH_FOREACH_DEV_OF(port_id, cdev->dev) {
 		/*
 		 * mlx5_dev_close() is not registered to secondary process,
 		 * call the close function explicitly for secondary process.

index fe533fcc81..f441352a63 100644
@@ -134,11 +134,11 @@ struct mlx5_dev_spawn_data {
 	uint32_t max_port; /**< Device maximal port index. */
 	uint32_t phys_port; /**< Device physical port index. */
 	int pf_bond; /**< bonding device PF index. < 0 - no bonding */
-	int numa_node; /**< Device numa node. */
 	struct mlx5_switch_info info; /**< Switch information. */
 	void *phys_dev; /**< Associated physical device. */
 	struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
 	struct rte_pci_device *pci_dev; /**< Backend PCI device. */
+	struct mlx5_common_device *cdev; /**< Backend common device. */
 	struct mlx5_bond_info *bond_info;
 };
 

@@ -1148,6 +1148,7 @@ struct mlx5_dev_ctx_shared {
 	uint32_t reclaim_mode:1; /* Reclaim memory. */
 	uint32_t max_port; /* Maximal IB device port index. */
 	struct mlx5_bond_info bond; /* Bonding information. */
+	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
 	void *ctx; /* Verbs/DV/DevX context. */
 	void *pd; /* Protection Domain. */
 	uint32_t pdn; /* Protection Domain number. */

@@ -1492,7 +1493,7 @@ int mlx5_udp_tunnel_port_add(struct rte_eth_dev *dev,
 			      struct rte_eth_udp_tunnel *udp_tunnel);
 uint16_t mlx5_eth_find_next(uint16_t port_id, struct rte_device *odev);
 int mlx5_dev_close(struct rte_eth_dev *dev);
-int mlx5_net_remove(struct rte_device *dev);
+int mlx5_net_remove(struct mlx5_common_device *cdev);
 bool mlx5_is_hpf(struct rte_eth_dev *dev);
 bool mlx5_is_sf_repr(struct rte_eth_dev *dev);
 void mlx5_age_event_prepare(struct mlx5_dev_ctx_shared *sh);

@@ -1782,7 +1783,7 @@ int mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
 			 const struct mlx5_dev_config *config,
 			 struct mlx5_dev_ctx_shared *sh);
 int mlx5_os_get_pdn(void *pd, uint32_t *pdn);
-int mlx5_os_net_probe(struct rte_device *dev);
+int mlx5_os_net_probe(struct mlx5_common_device *cdev);
 void mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh);
 void mlx5_os_dev_shared_handler_uninstall(struct mlx5_dev_ctx_shared *sh);
 void mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,

index 459414d5c2..8ffbb9ff54 100644
@@ -337,7 +337,7 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
 }
 
 /**
- * Spawn an Ethernet device from Verbs information.
+ * Spawn an Ethernet device from DevX information.
  *
  * @param dpdk_dev
  *   Backing DPDK device.

@@ -982,15 +982,15 @@ mlx5_match_devx_devices_to_addr(struct devx_device_bdf *devx_bdf,
  * This function spawns Ethernet devices out of a given device.
  *
  * @param[in] dev
- *   Pointer to the generic device.
+ *   Pointer to the common device.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 int
-mlx5_os_net_probe(struct rte_device *dev)
+mlx5_os_net_probe(struct mlx5_common_device *cdev)
 {
-	struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev);
+	struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(cdev->dev);
 	struct devx_device_bdf *devx_bdf_devs, *orig_devx_bdf_devs;
 	/*
 	 * Number of found IB Devices matching with requested PCI BDF.

@@ -1092,6 +1092,7 @@ mlx5_os_net_probe(struct rte_device *dev)
 	list[ns].phys_dev = devx_bdf_match[ns];
 	list[ns].eth_dev = NULL;
 	list[ns].pci_dev = pci_dev;
+	list[ns].cdev = cdev;
 	list[ns].pf_bond = bd;
 	list[ns].ifindex = -1; /* Spawn will assign */
 	list[ns].info =

@@ -1136,10 +1137,7 @@ mlx5_os_net_probe(struct rte_device *dev)
 	dev_config.dv_flow_en = 1;
 	dev_config.decap_en = 0;
 	dev_config.log_hp_size = MLX5_ARG_UNSET;
-	list[ns].numa_node = pci_dev->device.numa_node;
-	list[ns].eth_dev = mlx5_dev_spawn(&pci_dev->device,
-					  &list[ns],
-					  &dev_config);
+	list[ns].eth_dev = mlx5_dev_spawn(cdev->dev, &list[ns], &dev_config);
 	if (!list[ns].eth_dev)
 		goto exit;
 	restore = list[ns].eth_dev->data->dev_flags;

index 8866a4d0c6..5e27645c84 100644
@@ -121,7 +121,7 @@ mlx5_regex_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
 }
 
 static int
-mlx5_regex_dev_probe(struct rte_device *rte_dev)
+mlx5_regex_dev_probe(struct mlx5_common_device *cdev)
 {
 	struct ibv_device *ibv;
 	struct mlx5_regex_priv *priv = NULL;

@@ -131,7 +131,7 @@ mlx5_regex_dev_probe(struct rte_device *rte_dev)
 	int ret;
 	uint32_t val;
 
-	ibv = mlx5_os_get_ibv_dev(rte_dev);
+	ibv = mlx5_os_get_ibv_dev(cdev->dev);
 	if (ibv == NULL)
 		return -rte_errno;
 	DRV_LOG(INFO, "Probe device \"%s\".", ibv->name);

@@ -177,7 +177,7 @@ mlx5_regex_dev_probe(struct rte_device *rte_dev)
 		priv->is_bf2 = 1;
 	/* Default RXP programming mode to Shared. */
 	priv->prog_mode = MLX5_RXP_SHARED_PROG_MODE;
-	mlx5_regex_get_name(name, rte_dev);
+	mlx5_regex_get_name(name, cdev->dev);
 	priv->regexdev = rte_regexdev_register(name);
 	if (priv->regexdev == NULL) {
 		DRV_LOG(ERR, "Failed to register RegEx device.");

@@ -211,7 +211,7 @@ mlx5_regex_dev_probe(struct rte_device *rte_dev)
 		priv->regexdev->enqueue = mlx5_regexdev_enqueue_gga;
 #endif
 	priv->regexdev->dequeue = mlx5_regexdev_dequeue;
-	priv->regexdev->device = rte_dev;
+	priv->regexdev->device = cdev->dev;
 	priv->regexdev->data->dev_private = priv;
 	priv->regexdev->state = RTE_REGEXDEV_READY;
 	priv->mr_scache.reg_mr_cb = mlx5_common_verbs_reg_mr;

@@ -253,13 +253,13 @@ mlx5_regex_dev_probe(struct rte_device *rte_dev)
 }
 
 static int
-mlx5_regex_dev_remove(struct rte_device *rte_dev)
+mlx5_regex_dev_remove(struct mlx5_common_device *cdev)
 {
 	char name[RTE_REGEXDEV_NAME_MAX_LEN];
 	struct rte_regexdev *dev;
 	struct mlx5_regex_priv *priv = NULL;
 
-	mlx5_regex_get_name(name, rte_dev);
+	mlx5_regex_get_name(name, cdev->dev);
 	dev = rte_regexdev_get_device_by_name(name);
 	if (!dev)
 		return 0;

index 6d17d7a6f3..d7ef303cfe 100644
@@ -630,7 +630,7 @@ mlx5_vdpa_config_get(struct rte_devargs *devargs, struct mlx5_vdpa_priv *priv)
 }
 
 static int
-mlx5_vdpa_dev_probe(struct rte_device *dev)
+mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev)
 {
 	struct ibv_device *ibv;
 	struct mlx5_vdpa_priv *priv = NULL;

@@ -639,14 +639,14 @@ mlx5_vdpa_dev_probe(struct rte_device *dev)
 	int retry;
 	int ret;
 
-	if (mlx5_vdpa_roce_disable(dev) != 0) {
+	if (mlx5_vdpa_roce_disable(cdev->dev) != 0) {
 		DRV_LOG(WARNING, "Failed to disable ROCE for \"%s\".",
-			dev->name);
+			cdev->dev->name);
 		return -rte_errno;
 	}
 	/* Wait for the IB device to appear again after reload. */
 	for (retry = MLX5_VDPA_MAX_RETRIES; retry > 0; --retry) {
-		ibv = mlx5_os_get_ibv_dev(dev);
+		ibv = mlx5_os_get_ibv_dev(cdev->dev);
 		if (ibv != NULL)
 			break;
 		usleep(MLX5_VDPA_USEC);

@@ -654,7 +654,7 @@ mlx5_vdpa_dev_probe(struct rte_device *dev)
 	if (ibv == NULL) {
 		DRV_LOG(ERR, "Cannot get IB device after disabling RoCE for "
 				"\"%s\", retries exceed %d.",
-				dev->name, MLX5_VDPA_MAX_RETRIES);
+				cdev->dev->name, MLX5_VDPA_MAX_RETRIES);
 		rte_errno = EAGAIN;
 		return -rte_errno;
 	}

@@ -698,13 +698,13 @@ mlx5_vdpa_dev_probe(struct rte_device *dev)
 		DRV_LOG(ERR, "Failed to allocate VAR %u.", errno);
 		goto error;
 	}
-	priv->vdev = rte_vdpa_register_device(dev, &mlx5_vdpa_ops);
+	priv->vdev = rte_vdpa_register_device(cdev->dev, &mlx5_vdpa_ops);
 	if (priv->vdev == NULL) {
 		DRV_LOG(ERR, "Failed to register vDPA device.");
 		rte_errno = rte_errno ? rte_errno : EINVAL;
 		goto error;
 	}
-	mlx5_vdpa_config_get(dev->devargs, priv);
+	mlx5_vdpa_config_get(cdev->dev->devargs, priv);
 	SLIST_INIT(&priv->mr_list);
 	pthread_mutex_init(&priv->vq_config_lock, NULL);
 	pthread_mutex_lock(&priv_list_lock);

@@ -724,14 +724,14 @@ mlx5_vdpa_dev_probe(struct rte_device *dev)
 }
 
 static int
-mlx5_vdpa_dev_remove(struct rte_device *dev)
+mlx5_vdpa_dev_remove(struct mlx5_common_device *cdev)
 {
 	struct mlx5_vdpa_priv *priv = NULL;
 	int found = 0;
 
 	pthread_mutex_lock(&priv_list_lock);
 	TAILQ_FOREACH(priv, &priv_list, next) {
-		if (priv->vdev->device == dev) {
+		if (priv->vdev->device == cdev->dev) {
 			found = 1;
 			break;
 		}

index 91de7b3e2c..8e3ea073e3 100644
@@ -14,6 +14,7 @@
 #include "mlx5_common.h"
 #include "mlx5_common_os.h"
 #include "mlx5_common_log.h"
+#include "mlx5_common_defs.h"
 #include "mlx5_common_private.h"
 
 uint8_t haswell_broadwell_cpu;

42 lines not on this page · raw message

index 685ac98e08..15489cd399 100644
@@ -18,10 +18,7 @@
 
 #include "mlx5_glue.h"
 #include "mlx5_common_mp.h"
-
-/* Size of per-queue MR cache array for linear search. */
-#define MLX5_MR_CACHE_N 8
-#define MLX5_MR_BTREE_CACHE_N 256
+#include "mlx5_common_defs.h"
 
 /* mlx5 PMD MR struct. */
 struct mlx5_pmd_mr {

index e576e30f24..a7c92c9e40 100644
@@ -5,18 +5,10 @@
 #ifndef RTE_PMD_MLX5_DEVX_CMDS_H_
 #define RTE_PMD_MLX5_DEVX_CMDS_H_
 
-#include "mlx5_glue.h"
-#include "mlx5_prm.h"
 #include <rte_compat.h>
 
-/*
- * Defines the amount of retries to allocate the first UAR in the page.
- * OFED 5.0.x and Upstream rdma_core before v29 returned the NULL as
- * UAR base address if UAR was not the first object in the UAR page.
- * It caused the PMD failure and we should try to get another UAR
- * till we get the first one with non-NULL base address returned.
- */
-#define MLX5_ALLOC_UAR_RETRY 32
+#include "mlx5_glue.h"
+#include "mlx5_prm.h"
 
 /* This is limitation of libibverbs: in length variable type is u16. */
 #define MLX5_DEVX_MAX_KLM_ENTRIES ((UINT16_MAX - \

index f441352a63..2e93ce2a3e 100644
@@ -27,6 +27,7 @@
 #include <mlx5_common_mp.h>
 #include <mlx5_common_mr.h>
 #include <mlx5_common_devx.h>
+#include <mlx5_common_defs.h>
 
 #include "mlx5_defs.h"
 #include "mlx5_utils.h"

@@ -214,9 +215,6 @@ struct mlx5_stats_ctrl {
 	uint64_t imissed;
 };
 
-/* Default PMD specific parameter value. */
-#define MLX5_ARG_UNSET (-1)
-
 #define MLX5_LRO_SUPPORTED(dev) \
 	(((struct mlx5_priv *)((dev)->data->dev_private))->config.lro.supported)
 

index fe86bb40d3..376e34a946 100644
@@ -9,6 +9,8 @@
 #include <ethdev_driver.h>
 #include <rte_vxlan.h>
 
+#include <mlx5_common_defs.h>
+
 #include "mlx5_autoconf.h"
 
 /* Maximum number of simultaneous VLAN filters. */

@@ -33,13 +35,6 @@
  */
 #define MLX5_TX_COMP_MAX_CQE 2u
 
-
-/* Size of per-queue MR cache array for linear search. */
-#define MLX5_MR_CACHE_N 8
-
-/* Size of MR cache table for binary search. */
-#define MLX5_MR_BTREE_CACHE_N 256
-
 /*
  * If defined, only use software counters. The PMD will never ask the hardware
  * for these, and many of them won't be available.

@@ -121,14 +116,6 @@
 #define MLX5_UAR_MMAP_CMD_SHIFT 8
 #define MLX5_UAR_MMAP_CMD_MASK 0xff
 
-/* Environment variable to control the doorbell register mapping. */
-#define MLX5_SHUT_UP_BF "MLX5_SHUT_UP_BF"
-#if defined(RTE_ARCH_ARM64)
-#define MLX5_SHUT_UP_BF_DEFAULT "0"
-#else
-#define MLX5_SHUT_UP_BF_DEFAULT "1"
-#endif
-
 #ifndef HAVE_MLX5DV_MMAP_GET_NC_PAGES_CMD
 #define MLX5_MMAP_GET_NC_PAGES_CMD 3
 #endif

@@ -161,11 +148,6 @@
 /* Provide info on patrial hw miss. Implies MLX5_XMETA_MODE_META16 */
 #define MLX5_XMETA_MODE_MISS_INFO 3
 
-/* MLX5_TX_DB_NC supported values. */
-#define MLX5_TXDB_CACHED 0
-#define MLX5_TXDB_NCACHED 1
-#define MLX5_TXDB_HEURISTIC 2
-
 /* Tx accurate scheduling on timestamps parameters. */
 #define MLX5_TXPP_WAIT_INIT_TS 1000ul /* How long to wait timestamp. */
 #define MLX5_TXPP_CLKQ_SIZE 1

index 8e3ea073e3..0ad9e09972 100644
@@ -90,6 +90,93 @@ driver_get(uint32_t class)
 	return NULL;
 }
 
+/**
+ * Verify and store value for devargs.
+ *
+ * @param[in] key
+ *   Key argument to verify.
+ * @param[in] val
+ *   Value associated with key.
+ * @param opaque
+ *   User data.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_common_args_check_handler(const char *key, const char *val, void *opaque)
+{
+	struct mlx5_common_dev_config *config = opaque;
+	signed long tmp;
+
+	errno = 0;
+	tmp = strtol(val, NULL, 0);
+	if (errno) {
+		rte_errno = errno;
+		DRV_LOG(WARNING, "%s: \"%s\" is an invalid integer.", key, val);
+		return -rte_errno;
+	}
+	if (strcmp(key, "tx_db_nc") == 0) {
+		if (tmp != MLX5_TXDB_CACHED &&
+		    tmp != MLX5_TXDB_NCACHED &&
+		    tmp != MLX5_TXDB_HEURISTIC) {
+			DRV_LOG(ERR, "Invalid Tx doorbell mapping parameter.");
+			rte_errno = EINVAL;
+			return -rte_errno;
+		}
+		config->dbnc = tmp;
+	} else if (strcmp(key, "mr_ext_memseg_en") == 0) {
+		config->mr_ext_memseg_en = !!tmp;
+	} else if (strcmp(key, "mr_mempool_reg_en") == 0) {
+		config->mr_mempool_reg_en = !!tmp;
+	} else if (strcmp(key, "sys_mem_en") == 0) {
+		config->sys_mem_en = !!tmp;
+	}
+	return 0;
+}
+
+/**
+ * Parse common device parameters.
+ *
+ * @param devargs
+ *   Device arguments structure.
+ * @param config
+ *   Pointer to device configuration structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_common_config_get(struct rte_devargs *devargs,
+		       struct mlx5_common_dev_config *config)
+{
+	struct rte_kvargs *kvlist;
+	int ret = 0;
+
+	/* Set defaults. */
+	config->mr_ext_memseg_en = 1;
+	config->mr_mempool_reg_en = 1;
+	config->sys_mem_en = 0;
+	config->dbnc = MLX5_ARG_UNSET;
+	if (devargs == NULL)
+		return 0;
+	kvlist = rte_kvargs_parse(devargs->args, NULL);
+	if (kvlist == NULL) {
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	ret = rte_kvargs_process(kvlist, NULL, mlx5_common_args_check_handler,
+				 config);
+	if (ret)
+		ret = -rte_errno;
+	rte_kvargs_free(kvlist);
+	DRV_LOG(DEBUG, "mr_ext_memseg_en is %u.", config->mr_ext_memseg_en);
+	DRV_LOG(DEBUG, "mr_mempool_reg_en is %u.", config->mr_mempool_reg_en);
+	DRV_LOG(DEBUG, "sys_mem_en is %u.", config->sys_mem_en);
+	DRV_LOG(DEBUG, "Tx doorbell mapping parameter is %d.", config->dbnc);
+	return ret;
+}
+
 static int
 devargs_class_handler(__rte_unused const char *key,
 		      const char *class_names, void *opaque)

@@ -189,11 +276,11 @@ mlx5_bus_match(const struct mlx5_class_driver *drv,
 static struct mlx5_common_device *
 to_mlx5_device(const struct rte_device *rte_dev)
 {
-	struct mlx5_common_device *dev;
+	struct mlx5_common_device *cdev;
 
-	TAILQ_FOREACH(dev, &devices_list, next) {
-		if (rte_dev == dev->dev)
-			return dev;
+	TAILQ_FOREACH(cdev, &devices_list, next) {
+		if (rte_dev == cdev->dev)
+			return cdev;
 	}
 	return NULL;
 }

@@ -222,29 +309,60 @@ mlx5_dev_to_pci_str(const struct rte_device *dev, char *addr, size_t size)
 }
 
 static void
-dev_release(struct mlx5_common_device *dev)
+mlx5_common_dev_release(struct mlx5_common_device *cdev)
+{
+	pthread_mutex_lock(&devices_list_lock);
+	TAILQ_REMOVE(&devices_list, cdev, next);
+	pthread_mutex_unlock(&devices_list_lock);
+	rte_free(cdev);
+}
+
+static struct mlx5_common_device *
+mlx5_common_dev_create(struct rte_device *eal_dev)
 {
+	struct mlx5_common_device *cdev;
+	int ret;
+
+	cdev = rte_zmalloc("mlx5_common_device", sizeof(*cdev), 0);
+	if (!cdev) {
+		DRV_LOG(ERR, "Device allocation failure.");
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+	cdev->dev = eal_dev;
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+		goto exit;
+	/* Parse device parameters. */
+	ret = mlx5_common_config_get(eal_dev->devargs, &cdev->config);
+	if (ret < 0) {
+		DRV_LOG(ERR, "Failed to process device arguments: %s",
+			strerror(rte_errno));
+		rte_free(cdev);
+		return NULL;
+	}
+	mlx5_malloc_mem_select(cdev->config.sys_mem_en);
+exit:
 	pthread_mutex_lock(&devices_list_lock);
-	TAILQ_REMOVE(&devices_list, dev, next);
+	TAILQ_INSERT_HEAD(&devices_list, cdev, next);
 	pthread_mutex_unlock(&devices_list_lock);
-	rte_free(dev);
+	return cdev;
 }
 
 static int
-drivers_remove(struct mlx5_common_device *dev, uint32_t enabled_classes)
+drivers_remove(struct mlx5_common_device *cdev, uint32_t enabled_classes)
 {
 	struct mlx5_class_driver *driver;
 	int local_ret = -ENODEV;
 	unsigned int i = 0;
 	int ret = 0;
 
-	enabled_classes &= dev->classes_loaded;
+	enabled_classes &= cdev->classes_loaded;
 	while (enabled_classes) {
 		driver = driver_get(RTE_BIT64(i));
 		if (driver != NULL) {
-			local_ret = driver->remove(dev);
+			local_ret = driver->remove(cdev);
 			if (local_ret == 0)
-				dev->classes_loaded &= ~RTE_BIT64(i);
+				cdev->classes_loaded &= ~RTE_BIT64(i);
 			else if (ret == 0)
 				ret = local_ret;
 		}

@@ -257,7 +375,7 @@ drivers_remove(struct mlx5_common_device *dev, uint32_t enabled_classes)
 }
 
 static int
-drivers_probe(struct mlx5_common_device *dev, uint32_t user_classes)
+drivers_probe(struct mlx5_common_device *cdev, uint32_t user_classes)
 {
 	struct mlx5_class_driver *driver;
 	uint32_t enabled_classes = 0;

@@ -267,16 +385,16 @@ drivers_probe(struct mlx5_common_device *dev, uint32_t user_classes)
 	TAILQ_FOREACH(driver, &drivers_list, next) {
 		if ((driver->drv_class & user_classes) == 0)
 			continue;
-		if (!mlx5_bus_match(driver, dev->dev))
+		if (!mlx5_bus_match(driver, cdev->dev))
 			continue;
-		already_loaded = dev->classes_loaded & driver->drv_class;
+		already_loaded = cdev->classes_loaded & driver->drv_class;
 		if (already_loaded && driver->probe_again == 0) {
 			DRV_LOG(ERR, "Device %s is already probed",
-				dev->dev->name);
+				cdev->dev->name);
 			ret = -EEXIST;
 			goto probe_err;
 		}
-		ret = driver->probe(dev);
+		ret = driver->probe(cdev);
 		if (ret < 0) {
 			DRV_LOG(ERR, "Failed to load driver %s",
 				driver->name);

@@ -284,20 +402,20 @@ drivers_probe(struct mlx5_common_device *dev, uint32_t user_classes)
 		}
 		enabled_classes |= driver->drv_class;
 	}
-	dev->classes_loaded |= enabled_classes;
+	cdev->classes_loaded |= enabled_classes;
 	return 0;
 probe_err:
 	/* Only unload drivers which are enabled which were enabled
 	 * in this probe instance.
 	 */
-	drivers_remove(dev, enabled_classes);
+	drivers_remove(cdev, enabled_classes);
 	return ret;
 }
 
 int
 mlx5_common_dev_probe(struct rte_device *eal_dev)
 {
-	struct mlx5_common_device *dev;
+	struct mlx5_common_device *cdev;
 	uint32_t classes = 0;
 	bool new_device = false;
 	int ret;

@@ -313,15 +431,11 @@ mlx5_common_dev_probe(struct rte_device *eal_dev)
 	if (classes == 0)
 		/* Default to net class. */
 		classes = MLX5_CLASS_ETH;
-	dev = to_mlx5_device(eal_dev);
-	if (!dev) {
-		dev = rte_zmalloc("mlx5_common_device", sizeof(*dev), 0);
-		if (!dev)
+	cdev = to_mlx5_device(eal_dev);
+	if (!cdev) {
+		cdev = mlx5_common_dev_create(eal_dev);
+		if (!cdev)
 			return -ENOMEM;
-		dev->dev = eal_dev;
-		pthread_mutex_lock(&devices_list_lock);
-		TAILQ_INSERT_HEAD(&devices_list, dev, next);
-		pthread_mutex_unlock(&devices_list_lock);
 		new_device = true;
 	}
 	/*

@@ -329,34 +443,34 @@ mlx5_common_dev_probe(struct rte_device *eal_dev)
 	 * For new device, the classes_loaded field is 0 and it check only
 	 * the classes given as user device arguments.
 	 */
-	ret = is_valid_class_combination(classes | dev->classes_loaded);
+	ret = is_valid_class_combination(classes | cdev->classes_loaded);
 	if (ret != 0) {
 		DRV_LOG(ERR, "Unsupported mlx5 classes combination.");
 		goto class_err;
 	}
-	ret = drivers_probe(dev, classes);
+	ret = drivers_probe(cdev, classes);
 	if (ret)
 		goto class_err;
 	return 0;
 class_err:
 	if (new_device)
-		dev_release(dev);
+		mlx5_common_dev_release(cdev);
 	return ret;
 }
 
 int
 mlx5_common_dev_remove(struct rte_device *eal_dev)
 {
-	struct mlx5_common_device *dev;
+	struct mlx5_common_device *cdev;
 	int ret;
 
-	dev = to_mlx5_device(eal_dev);
-	if (!dev)
+	cdev = to_mlx5_device(eal_dev);
+	if (!cdev)
 		return -ENODEV;
 	/* Matching device found, cleanup and unload drivers. */
-	ret = drivers_remove(dev, dev->classes_loaded);
+	ret = drivers_remove(cdev, cdev->classes_loaded);
 	if (ret == 0)
-		dev_release(dev);
+		mlx5_common_dev_release(cdev);
 	return ret;
 }
 

index b7e2ad1a82..f922757da1 100644
@@ -324,10 +324,28 @@ void mlx5_common_init(void);
  *   from devargs, locating target RDMA device and probing with it.
  */
 
+/*
+ * Device configuration structure.
+ *
+ * Merged configuration from:
+ *
+ *  - Device capabilities,
+ *  - User device parameters disabled features.
+ */
+struct mlx5_common_dev_config {
+	int dbnc; /* Skip doorbell register write barrier. */
+	unsigned int sys_mem_en:1; /* The default memory allocator. */
+	unsigned int mr_mempool_reg_en:1;
+	/* Allow/prevent implicit mempool memory registration. */
+	unsigned int mr_ext_memseg_en:1;
+	/* Whether memseg should be extended for MR creation. */
+};
+
 struct mlx5_common_device {
 	struct rte_device *dev;
 	TAILQ_ENTRY(mlx5_common_device) next;
 	uint32_t classes_loaded;
+	struct mlx5_common_dev_config config; /* Device configuration. */
 };
 
 /**

index 8aea414635..74b7eeb26e 100644
@@ -38,7 +38,6 @@ enum mlx5_mem_flags {
  * @param sys_mem_en
  *   Use system memory or not.
  */
-__rte_internal
 void mlx5_malloc_mem_select(uint32_t sys_mem_en);
 
 /**

index d2ac375a47..b0996813dc 100644
@@ -68,6 +68,7 @@ mlx5_mp_os_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 		(const struct mlx5_mp_param *)mp_msg->param;
 	struct rte_eth_dev *dev;
 	struct mlx5_priv *priv;
+	struct mlx5_common_device *cdev;
 	struct mr_cache_entry entry;
 	uint32_t lkey;
 	int ret;

@@ -85,13 +86,14 @@ mlx5_mp_os_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 	}
 	dev = &rte_eth_devices[param->port_id];
 	priv = dev->data->dev_private;
+	cdev = priv->sh->cdev;
 	switch (param->type) {
 	case MLX5_MP_REQ_CREATE_MR:
 		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		lkey = mlx5_mr_create_primary(priv->sh->pd,
 					      &priv->sh->share_cache,
 					      &entry, param->args.addr,
-					      priv->config.mr_ext_memseg_en);
+					      cdev->config.mr_ext_memseg_en);
 		if (lkey == UINT32_MAX)
 			res->result = -rte_errno;
 		ret = rte_mp_reply(&mp_res, peer);

index 0aad08aba4..a808325412 100644
@@ -1072,7 +1072,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		if (switch_info->master || switch_info->representor)
 			config->dv_xmeta_en = MLX5_XMETA_MODE_META16;
 	}
-	mlx5_malloc_mem_select(config->sys_mem_en);
 	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
 	if (!sh)
 		return NULL;

@@ -2124,15 +2123,12 @@ mlx5_os_config_default(struct mlx5_dev_config *config)
 {
 	memset(config, 0, sizeof(*config));
 	config->mps = MLX5_ARG_UNSET;
-	config->dbnc = MLX5_ARG_UNSET;
 	config->rx_vec_en = 1;
 	config->txq_inline_max = MLX5_ARG_UNSET;
 	config->txq_inline_min = MLX5_ARG_UNSET;
 	config->txq_inline_mpw = MLX5_ARG_UNSET;
 	config->txqs_inline = MLX5_ARG_UNSET;
 	config->vf_nl_en = 1;
-	config->mr_ext_memseg_en = 1;
-	config->mr_mempool_reg_en = 1;
 	config->mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
 	config->mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
 	config->dv_esw_en = 1;

@@ -2796,7 +2792,7 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 }
 
 static int
-mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config)
+mlx5_config_doorbell_mapping_env(const struct mlx5_common_dev_config *config)
 {
 	char *env;
 	int value;

@@ -2866,8 +2862,6 @@ mlx5_os_get_pdn(void *pd, uint32_t *pdn)
  *
  * @param[in] spawn
  *   Pointer to the IB device attributes (name, port, etc).
- * @param[out] config
- *   Pointer to device configuration structure.
  * @param[out] sh
  *   Pointer to shared context structure.
  *

@@ -2876,7 +2870,6 @@ mlx5_os_get_pdn(void *pd, uint32_t *pdn)
  */
 int
 mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
-		     const struct mlx5_dev_config *config,
 		     struct mlx5_dev_ctx_shared *sh)
 {
 	int dbmap_env;

@@ -2889,7 +2882,7 @@ mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
 	 * checks the variable at device creation and
 	 * stores the result internally.
 	 */
-	dbmap_env = mlx5_config_doorbell_mapping_env(config);
+	dbmap_env = mlx5_config_doorbell_mapping_env(&spawn->mlx5_dev->config);
 	/* Try to open IB device with DV first, then usual Verbs. */
 	errno = 0;
 	sh->ctx = mlx5_glue->dv_open_device(spawn->phys_dev);

index e39e77aa9d..b5af21b0f6 100644
@@ -968,7 +968,7 @@ mlx5_flex_parser_ecpri_release(struct rte_eth_dev *dev)
  */
 static int
 mlx5_alloc_rxtx_uars(struct mlx5_dev_ctx_shared *sh,
-		     const struct mlx5_dev_config *config)
+		     const struct mlx5_common_dev_config *config)
 {
 	uint32_t uar_mapping, retry;
 	int err = 0;

@@ -1210,7 +1210,7 @@ mlx5_dev_ctx_shared_mempool_subscribe(struct rte_eth_dev *dev)
 	int ret;
 
 	/* Check if we only need to track Rx mempool destruction. */
-	if (!priv->config.mr_mempool_reg_en) {
+	if (!sh->cdev->config.mr_mempool_reg_en) {
 		ret = rte_mempool_event_callback_register
 				(mlx5_dev_ctx_shared_rx_mempool_event_cb, sh);
 		return ret == 0 || rte_errno == EEXIST ? 0 : ret;

@@ -1283,7 +1283,7 @@ mlx5_alloc_shared_dev_ctx(const struct mlx5_dev_spawn_data *spawn,
 	sh->cdev = spawn->cdev;
 	if (spawn->bond_info)
 		sh->bond = *spawn->bond_info;
-	err = mlx5_os_open_device(spawn, config, sh);
+	err = mlx5_os_open_device(spawn, sh);
 	if (!sh->ctx)
 		goto error;
 	err = mlx5_os_get_dev_attr(sh->ctx, &sh->device_attr);

@@ -1332,7 +1332,7 @@ mlx5_alloc_shared_dev_ctx(const struct mlx5_dev_spawn_data *spawn,
 			err = ENOMEM;
 			goto error;
 		}
-		err = mlx5_alloc_rxtx_uars(sh, config);
+		err = mlx5_alloc_rxtx_uars(sh, &sh->cdev->config);
 		if (err)
 			goto error;
 		MLX5_ASSERT(sh->tx_uar);

@@ -2016,7 +2016,10 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
 	signed long tmp;
 
 	/* No-op, port representors are processed in mlx5_dev_spawn(). */
-	if (!strcmp(MLX5_DRIVER_KEY, key) || !strcmp(MLX5_REPRESENTOR, key))
+	if (!strcmp(MLX5_DRIVER_KEY, key) || !strcmp(MLX5_REPRESENTOR, key) ||
+	    !strcmp(MLX5_SYS_MEM_EN, key) || !strcmp(MLX5_TX_DB_NC, key) ||
+	    !strcmp(MLX5_MR_MEMPOOL_REG_EN, key) ||
+	    !strcmp(MLX5_MR_EXT_MEMSEG_EN, key))
 		return 0;
 	errno = 0;
 	tmp = strtol(val, NULL, 0);

@@ -2069,16 +2072,6 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
 		DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
 	} else if (strcmp(MLX5_TXQ_MPW_EN, key) == 0) {
 		config->mps = !!tmp;
-	} else if (strcmp(MLX5_TX_DB_NC, key) == 0) {
-		if (tmp != MLX5_TXDB_CACHED &&
-		    tmp != MLX5_TXDB_NCACHED &&
-		    tmp != MLX5_TXDB_HEURISTIC) {
-			DRV_LOG(ERR, "invalid Tx doorbell "
-				     "mapping parameter");
-			rte_errno = EINVAL;
-			return -rte_errno;
-		}
-		config->dbnc = tmp;
 	} else if (strcmp(MLX5_TXQ_MPW_HDR_DSEG_EN, key) == 0) {
 		DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
 	} else if (strcmp(MLX5_TXQ_MAX_INLINE_LEN, key) == 0) {

@@ -2122,8 +2115,6 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
 			config->dv_miss_info = 1;
 	} else if (strcmp(MLX5_LACP_BY_USER, key) == 0) {
 		config->lacp_by_user = !!tmp;
-	} else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) {
-		config->mr_ext_memseg_en = !!tmp;
 	} else if (strcmp(MLX5_MAX_DUMP_FILES_NUM, key) == 0) {
 		config->max_dump_files_num = tmp;
 	} else if (strcmp(MLX5_LRO_TIMEOUT_USEC, key) == 0) {

@@ -2141,14 +2132,10 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
 			return -rte_errno;
 		}
 		config->reclaim_mode = tmp;
-	} else if (strcmp(MLX5_SYS_MEM_EN, key) == 0) {
-		config->sys_mem_en = !!tmp;
 	} else if (strcmp(MLX5_DECAP_EN, key) == 0) {
 		config->decap_en = !!tmp;
 	} else if (strcmp(MLX5_ALLOW_DUPLICATE_PATTERN, key) == 0) {
 		config->allow_duplicate_pattern = !!tmp;
-	} else if (strcmp(MLX5_MR_MEMPOOL_REG_EN, key) == 0) {
-		config->mr_mempool_reg_en = !!tmp;
 	} else {
 		DRV_LOG(WARNING, "%s: unknown parameter", key);
 		rte_errno = EINVAL;

index 2e93ce2a3e..4c8e633fb6 100644
@@ -256,8 +256,6 @@ struct mlx5_dev_config {
 	unsigned int cqe_comp_fmt:3; /* CQE compression format. */
 	unsigned int tso:1; /* Whether TSO is supported. */
 	unsigned int rx_vec_en:1; /* Rx vector is enabled. */
-	unsigned int mr_ext_memseg_en:1;
-	/* Whether memseg should be extended for MR creation. */
 	unsigned int l3_vxlan_en:1; /* Enable L3 VXLAN flow creation. */
 	unsigned int vf_nl_en:1; /* Enable Netlink requests in VF mode. */
 	unsigned int dv_esw_en:1; /* Enable E-Switch DV flow. */

@@ -270,13 +268,10 @@ struct mlx5_dev_config {
 	unsigned int dest_tir:1; /* Whether advanced DR API is available. */
 	unsigned int reclaim_mode:2; /* Memory reclaim mode. */
 	unsigned int rt_timestamp:1; /* realtime timestamp format. */
-	unsigned int sys_mem_en:1; /* The default memory allocator. */
 	unsigned int decap_en:1; /* Whether decap will be used or not. */
 	unsigned int dv_miss_info:1; /* restore packet after partial hw miss */
 	unsigned int allow_duplicate_pattern:1;
 	/* Allow/Prevent the duplicate rules pattern. */
-	unsigned int mr_mempool_reg_en:1;
-	/* Allow/prevent implicit mempool memory registration. */
 	struct {
 		unsigned int enabled:1; /* Whether MPRQ is enabled. */
 		unsigned int stride_num_n; /* Number of strides. */

@@ -289,7 +284,6 @@ struct mlx5_dev_config {
 		/* Rx queue count threshold to enable MPRQ. */
 	} mprq; /* Configurations for Multi-Packet RQ. */
 	int mps; /* Multi-packet send supported mode. */
-	int dbnc; /* Skip doorbell register write barrier. */
 	unsigned int flow_prio; /* Number of flow priorities. */
 	enum modify_reg flow_mreg_c[MLX5_MREG_C_NUM];
 	/* Availibility of mreg_c's. */

@@ -1778,7 +1772,6 @@ struct rte_pci_driver;
 int mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *dev_attr);
 void mlx5_os_free_shared_dr(struct mlx5_priv *priv);
 int mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
-			 const struct mlx5_dev_config *config,
 			 struct mlx5_dev_ctx_shared *sh);
 int mlx5_os_get_pdn(void *pd, uint32_t *pdn);
 int mlx5_os_net_probe(struct mlx5_common_device *cdev);

index 55d27b50b9..f16f4f6a67 100644
@@ -86,7 +86,7 @@ mlx5_tx_addr2mr_bh(struct mlx5_txq_data *txq, uintptr_t addr)
 
 	return mlx5_mr_addr2mr_bh(priv->sh->pd, &priv->mp_id,
 				  &priv->sh->share_cache, mr_ctrl, addr,
-				  priv->config.mr_ext_memseg_en);
+				  priv->sh->cdev->config.mr_ext_memseg_en);
 }
 
 /**

@@ -111,7 +111,7 @@ mlx5_tx_mb2mr_bh(struct mlx5_txq_data *txq, struct rte_mbuf *mb)
 	uintptr_t addr = (uintptr_t)mb->buf_addr;
 	uint32_t lkey;
 
-	if (priv->config.mr_mempool_reg_en) {
+	if (priv->sh->cdev->config.mr_mempool_reg_en) {
 		struct rte_mempool *mp = NULL;
 		struct mlx5_mprq_buf *buf;
 

@@ -196,8 +196,8 @@ mlx5_mr_update_ext_mp_cb(struct rte_mempool *mp, void *opaque,
 	mlx5_mr_insert_cache(&sh->share_cache, mr);
 	rte_rwlock_write_unlock(&sh->share_cache.rwlock);
 	/* Insert to the local cache table */
-	mlx5_mr_addr2mr_bh(sh->pd, &priv->mp_id, &sh->share_cache,
-			   mr_ctrl, addr, priv->config.mr_ext_memseg_en);
+	mlx5_mr_addr2mr_bh(sh->pd, &priv->mp_id, &sh->share_cache, mr_ctrl,
+			   addr, priv->sh->cdev->config.mr_ext_memseg_en);
 }
 
 /**

index eb4d34ca55..a9c8ce52c9 100644
@@ -505,10 +505,10 @@ mlx5_tx_queue_release(void *dpdk_txq)
 static void
 txq_uar_ncattr_init(struct mlx5_txq_ctrl *txq_ctrl, size_t page_size)
 {
-	struct mlx5_priv *priv = txq_ctrl->priv;
+	struct mlx5_common_device *cdev = txq_ctrl->priv->sh->cdev;
 	off_t cmd;
 
-	txq_ctrl->txq.db_heu = priv->config.dbnc == MLX5_TXDB_HEURISTIC;
+	txq_ctrl->txq.db_heu = cdev->config.dbnc == MLX5_TXDB_HEURISTIC;
 	txq_ctrl->txq.db_nc = 0;
 	/* Check the doorbell register mapping type. */
 	cmd = txq_ctrl->uar_mmap_offset / page_size;

index 8ffbb9ff54..ea2d45bbce 100644
@@ -260,8 +260,6 @@ mlx5_os_set_nonblock_channel_fd(int fd)
  *
  * @param[in] spawn
  *   Pointer to the device attributes (name, port, etc).
- * @param[out] config
- *   Pointer to device configuration structure.
  * @param[out] sh
  *   Pointer to shared context structure.
  *

@@ -270,10 +268,8 @@ mlx5_os_set_nonblock_channel_fd(int fd)
  */
 int
 mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
-		 const struct mlx5_dev_config *config,
 		 struct mlx5_dev_ctx_shared *sh)
 {
-	RTE_SET_USED(config);
 	int err = 0;
 	struct mlx5_context *mlx5_ctx;
 

@@ -390,7 +386,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 			strerror(rte_errno));
 		goto error;
 	}
-	mlx5_malloc_mem_select(config->sys_mem_en);
 	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
 	if (!sh)
 		return NULL;

@@ -1122,15 +1117,12 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 	memset(&dev_config, 0, sizeof(struct mlx5_dev_config));
 	dev_config.vf = dev_config_vf;
 	dev_config.mps = 0;
-	dev_config.dbnc = MLX5_ARG_UNSET;
 	dev_config.rx_vec_en = 1;
 	dev_config.txq_inline_max = MLX5_ARG_UNSET;
 	dev_config.txq_inline_min = MLX5_ARG_UNSET;
 	dev_config.txq_inline_mpw = MLX5_ARG_UNSET;
 	dev_config.txqs_inline = MLX5_ARG_UNSET;
 	dev_config.vf_nl_en = 0;
-	dev_config.mr_ext_memseg_en = 1;
-	dev_config.mr_mempool_reg_en = 1;
 	dev_config.mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
 	dev_config.mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
 	dev_config.dv_esw_en = 0;

index ea2d45bbce..90e21479e3 100644
@@ -956,9 +956,9 @@ mlx5_match_devx_devices_to_addr(struct devx_device_bdf *devx_bdf,
 
 	if (mlx5_match_devx_bdf_to_addr(devx_bdf, addr))
 		return 1;
-	/**
-	 * Didn't match on Native/PF BDF, could still
-	 * Match a VF BDF, check it next
+	/*
+	 * Didn't match on Native/PF BDF, could still match a VF BDF,
+	 * check it next.
 	 */
 	err = mlx5_glue->query_device(devx_bdf, &mlx5_dev);
 	if (err) {

@@ -971,6 +971,52 @@ mlx5_match_devx_devices_to_addr(struct devx_device_bdf *devx_bdf,
 	return 0;
 }
 
+/**
+ * Look for DevX device that match to given rte_device.
+ *
+ * @param dev
+ *   Pointer to the generic device.
+ * @param orig_devx_list
+ *   Pointer to head of DevX devices list.
+ * @param n
+ *   Number of devices in given DevX devices list.
+ *
+ * @return
+ *   A device match on success, NULL otherwise and rte_errno is set.
+ */
+static struct devx_device_bdf *
+mlx5_os_get_devx_device(struct rte_device *dev,
+			struct devx_device_bdf *orig_devx_list, int n)
+{
+	struct devx_device_bdf *devx_list = orig_devx_list;
+	struct devx_device_bdf *devx_match = NULL;
+	struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev);
+	struct rte_pci_addr *addr = &pci_dev->addr;
+
+	while (n-- > 0) {
+		int ret = mlx5_match_devx_devices_to_addr(devx_list, addr);
+		if (!ret) {
+			devx_list++;
+			continue;
+		}
+		if (ret != 1) {
+			rte_errno = ret;
+			return NULL;
+		}
+		devx_match = devx_list;
+		break;
+	}
+	if (devx_match == NULL) {
+		/* No device matches, just complain and bail out. */
+		DRV_LOG(WARNING,
+			"No DevX device matches PCI device " PCI_PRI_FMT ","
+			" is DevX Configured?",
+			addr->domain, addr->bus, addr->devid, addr->function);
+		rte_errno = ENOENT;
+	}
+	return devx_match;
+}
+
 /**
  * DPDK callback to register a PCI device.
  *

@@ -986,37 +1032,34 @@ int
 mlx5_os_net_probe(struct mlx5_common_device *cdev)
 {
 	struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(cdev->dev);
-	struct devx_device_bdf *devx_bdf_devs, *orig_devx_bdf_devs;
-	/*
-	 * Number of found IB Devices matching with requested PCI BDF.
-	 * nd != 1 means there are multiple IB devices over the same
-	 * PCI device and we have representors and master.
-	 */
-	unsigned int nd = 0;
-	/*
-	 * Number of found IB device Ports. nd = 1 and np = 1..n means
-	 * we have the single multiport IB device, and there may be
-	 * representors attached to some of found ports.
-	 * Currently not supported.
-	 * unsigned int np = 0;
-	 */
-
-	/*
-	 * Number of DPDK ethernet devices to Spawn - either over
-	 * multiple IB devices or multiple ports of single IB device.
-	 * Actually this is the number of iterations to spawn.
-	 */
-	unsigned int ns = 0;
-	/*
-	 * Bonding device
-	 *   < 0 - no bonding device (single one)
-	 *  >= 0 - bonding device (value is slave PF index)
-	 */
-	int bd = -1;
-	struct mlx5_dev_spawn_data *list = NULL;
-	struct mlx5_dev_config dev_config;
-	unsigned int dev_config_vf;
-	int ret, err;
+	struct devx_device_bdf *devx_list;
+	struct devx_device_bdf *devx_bdf_match;
+	struct mlx5_dev_spawn_data spawn = {
+		.pf_bond = -1,
+		.max_port = 1,
+		.phys_port = 1,
+		.pci_dev = pci_dev,
+		.cdev = cdev,
+		.ifindex = -1, /* Spawn will assign */
+		.info = (struct mlx5_switch_info){
+			.name_type = MLX5_PHYS_PORT_NAME_TYPE_UPLINK,
+		},
+	};
+	struct mlx5_dev_config dev_config = {
+		.rx_vec_en = 1,
+		.txq_inline_max = MLX5_ARG_UNSET,
+		.txq_inline_min = MLX5_ARG_UNSET,
+		.txq_inline_mpw = MLX5_ARG_UNSET,
+		.txqs_inline = MLX5_ARG_UNSET,
+		.mprq = {
+			.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN,
+			.min_rxqs_num = MLX5_MPRQ_MIN_RXQS,
+		},
+		.dv_flow_en = 1,
+		.log_hp_size = MLX5_ARG_UNSET,
+	};
+	int ret;
+	int n;
 	uint32_t restore;
 
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {

@@ -1030,74 +1073,18 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 		return -rte_errno;
 	}
 	errno = 0;
-	devx_bdf_devs = mlx5_glue->get_device_list(&ret);
-	orig_devx_bdf_devs = devx_bdf_devs;
-	if (!devx_bdf_devs) {
+	devx_list = mlx5_glue->get_device_list(&n);
+	if (devx_list == NULL) {
 		rte_errno = errno ? errno : ENOSYS;
-		DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?");
+		DRV_LOG(ERR, "Cannot list devices, is DevX enabled?");
 		return -rte_errno;
 	}
-	/*
-	 * First scan the list of all Infiniband devices to find
-	 * matching ones, gathering into the list.
-	 */
-	struct devx_device_bdf *devx_bdf_match[ret + 1];
-
-	while (ret-- > 0) {
-		err = mlx5_match_devx_devices_to_addr(devx_bdf_devs,
-		    &pci_dev->addr);
-		if (!err) {
-			devx_bdf_devs++;
-			continue;
-		}
-		if (err != 1) {
-			ret = -err;
-			goto exit;
-		}
-		devx_bdf_match[nd++] = devx_bdf_devs;
-	}
-	devx_bdf_match[nd] = NULL;
-	if (!nd) {
-		/* No device matches, just complain and bail out. */
-		DRV_LOG(WARNING,
-			"no DevX device matches PCI device " PCI_PRI_FMT ","
-			" is DevX Configured?",
-			pci_dev->addr.domain, pci_dev->addr.bus,
-			pci_dev->addr.devid, pci_dev->addr.function);
-		rte_errno = ENOENT;
+	devx_bdf_match = mlx5_os_get_devx_device(cdev->dev, devx_list, n);
+	if (devx_bdf_match == NULL) {
 		ret = -rte_errno;
 		goto exit;
 	}
-	/*
-	 * Now we can determine the maximal
-	 * amount of devices to be spawned.
-	 */
-	list = mlx5_malloc(MLX5_MEM_ZERO,
-			   sizeof(struct mlx5_dev_spawn_data),
-			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
-	if (!list) {
-		DRV_LOG(ERR, "spawn data array allocation failure");
-		rte_errno = ENOMEM;
-		ret = -rte_errno;
-		goto exit;
-	}
-	memset(&list[ns].info, 0, sizeof(list[ns].info));
-	list[ns].max_port = 1;
-	list[ns].phys_port = 1;
-	list[ns].phys_dev = devx_bdf_match[ns];
-	list[ns].eth_dev = NULL;
-	list[ns].pci_dev = pci_dev;
-	list[ns].cdev = cdev;
-	list[ns].pf_bond = bd;
-	list[ns].ifindex = -1; /* Spawn will assign */
-	list[ns].info =
-		(struct mlx5_switch_info){
-			.master = 0,
-			.representor = 0,
-			.name_type = MLX5_PHYS_PORT_NAME_TYPE_UPLINK,
-			.port_name = 0,
-			.switch_id = 0,
-		};
+	spawn.phys_dev = devx_bdf_match;
 	/* Device specific configuration. */
 	switch (pci_dev->id.device_id) {
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:

@@ -1107,47 +1094,24 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF:
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF:
 	case PCI_DEVICE_ID_MELLANOX_CONNECTXVF:
-		dev_config_vf = 1;
+		dev_config.vf = 1;
 		break;
 	default:
-		dev_config_vf = 0;
+		dev_config.vf = 0;
 		break;
 	}
-	/* Default configuration. */
-	memset(&dev_config, 0, sizeof(struct mlx5_dev_config));
-	dev_config.vf = dev_config_vf;
-	dev_config.mps = 0;
-	dev_config.rx_vec_en = 1;
-	dev_config.txq_inline_max = MLX5_ARG_UNSET;
-	dev_config.txq_inline_min = MLX5_ARG_UNSET;
-	dev_config.txq_inline_mpw = MLX5_ARG_UNSET;
-	dev_config.txqs_inline = MLX5_ARG_UNSET;
-	dev_config.vf_nl_en = 0;
-	dev_config.mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
-	dev_config.mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
-	dev_config.dv_esw_en = 0;
-	dev_config.dv_flow_en = 1;
-	dev_config.decap_en = 0;
-	dev_config.log_hp_size = MLX5_ARG_UNSET;
-	list[ns].eth_dev = mlx5_dev_spawn(cdev->dev, &list[ns], &dev_config);
-	if (!list[ns].eth_dev)
+	spawn.eth_dev = mlx5_dev_spawn(cdev->dev, &spawn, &dev_config);
+	if (!spawn.eth_dev) {
+		ret = -rte_errno;
 		goto exit;
-	restore = list[ns].eth_dev->data->dev_flags;
-	rte_eth_copy_pci_info(list[ns].eth_dev, pci_dev);
+	}
+	restore = spawn.eth_dev->data->dev_flags;
+	rte_eth_copy_pci_info(spawn.eth_dev, pci_dev);
 	/* Restore non-PCI flags cleared by the above call. */
-	list[ns].eth_dev->data->dev_flags |= restore;
-	rte_eth_dev_probing_finish(list[ns].eth_dev);
-	ret = 0;
+	spawn.eth_dev->data->dev_flags |= restore;
+	rte_eth_dev_probing_finish(spawn.eth_dev);
 exit:
-	/*
-	 * Do the routine cleanup:
-	 * - free allocated spawn data array
-	 * - free the device list
-	 */
-	if (list)
-		mlx5_free(list);
-	MLX5_ASSERT(orig_devx_bdf_devs);
-	mlx5_glue->free_device_list(orig_devx_bdf_devs);
+	mlx5_glue->free_device_list(devx_list);
 	return ret;
 }
 

index 9e0c823c97..2aa5684b05 100644
@@ -16,6 +16,7 @@
 
 #include "mlx5_common.h"
 #include "mlx5_common_log.h"
+#include "mlx5_common_defs.h"
 #include "mlx5_common_os.h"
 #include "mlx5_glue.h"
 

@@ -428,3 +429,88 @@ mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
 	mlx5_glue->free_device_list(ibv_list);
 	return ibv_match;
 }
+
+static int
+mlx5_config_doorbell_mapping_env(int dbnc)
+{
+	char *env;
+	int value;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	/* Get environment variable to store. */
+	env = getenv(MLX5_SHUT_UP_BF);
+	value = env ? !!strcmp(env, "0") : MLX5_ARG_UNSET;
+	if (dbnc == MLX5_ARG_UNSET)
+		setenv(MLX5_SHUT_UP_BF, MLX5_SHUT_UP_BF_DEFAULT, 1);
+	else
+		setenv(MLX5_SHUT_UP_BF,
+		       dbnc == MLX5_TXDB_NCACHED ? "1" : "0", 1);
+	return value;
+}
+
+static void
+mlx5_restore_doorbell_mapping_env(int value)
+{
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	/* Restore the original environment variable state. */
+	if (value == MLX5_ARG_UNSET)
+		unsetenv(MLX5_SHUT_UP_BF);
+	else
+		setenv(MLX5_SHUT_UP_BF, value ? "1" : "0", 1);
+}
+
+/**
+ * Function API to open IB device.
+ *
+ *
+ * @param cdev
+ *   Pointer to the mlx5 device.
+ * @param ctx_ptr
+ *   Pointer to fill inside pointer to device context.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx_ptr)
+{
+	struct ibv_device *ibv;
+	struct ibv_context *ctx = NULL;
+	int dbmap_env;
+
+	ibv = mlx5_os_get_ibv_dev(cdev->dev);
+	if (!ibv)
+		return -rte_errno;
+	DRV_LOG(INFO, "Dev information matches for device \"%s\".", ibv->name);
+	/*
+	 * Configure environment variable "MLX5_BF_SHUT_UP" before the device
+	 * creation. The rdma_core library checks the variable at device
+	 * creation and stores the result internally.
+	 */
+	dbmap_env = mlx5_config_doorbell_mapping_env(cdev->config.dbnc);
+	/* Try to open IB device with DV first, then usual Verbs. */
+	errno = 0;
+	ctx = mlx5_glue->dv_open_device(ibv);
+	if (ctx) {
+		cdev->config.devx = 1;
+		DRV_LOG(DEBUG, "DevX is supported.");
+	} else {
+		/* The environment variable is still configured. */
+		ctx = mlx5_glue->open_device(ibv);
+		if (ctx == NULL)
+			goto error;
+		DRV_LOG(DEBUG, "DevX is NOT supported.");
+	}
+	/* The device is created, no need for environment. */
+	mlx5_restore_doorbell_mapping_env(dbmap_env);
+	/* Hint libmlx5 to use PMD allocator for data plane resources */
+	mlx5_set_context_attr(cdev->dev, ctx);
+	*ctx_ptr = (void *)ctx;
+	return 0;
+error:
+	rte_errno = errno ? errno : ENODEV;
+	/* The device creation is failed, no need for environment. */
+	mlx5_restore_doorbell_mapping_env(dbmap_env);
+	DRV_LOG(ERR, "Failed to open IB device \"%s\".", ibv->name);
+	return -rte_errno;
+}

index c3202b6786..05c8ae1ba5 100644
@@ -296,4 +296,7 @@ __rte_internal
 struct ibv_device *
 mlx5_os_get_ibv_dev(const struct rte_device *dev);
 
+void
+mlx5_set_context_attr(struct rte_device *dev, struct ibv_context *ctx);
+
 #endif /* RTE_PMD_MLX5_COMMON_OS_H_ */

88 lines not on this page · raw message

index f922757da1..f36791f24e 100644
@@ -334,6 +334,7 @@ void mlx5_common_init(void);
  */
 struct mlx5_common_dev_config {
 	int dbnc; /* Skip doorbell register write barrier. */
+	unsigned int devx:1; /* Whether devx interface is available or not. */
 	unsigned int sys_mem_en:1; /* The default memory allocator. */
 	unsigned int mr_mempool_reg_en:1;
 	/* Allow/prevent implicit mempool memory registration. */

@@ -443,4 +444,9 @@ __rte_internal
 bool
 mlx5_dev_is_pci(const struct rte_device *dev);
 
+/* mlx5_common_os.c */
+
+__rte_internal
+int mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx);
+
 #endif /* RTE_PMD_MLX5_COMMON_H_ */

167 lines not on this page · raw message

494 lines not on this page · raw message

index b5af21b0f6..bfdce8da72 100644
@@ -1262,7 +1262,7 @@ mlx5_alloc_shared_dev_ctx(const struct mlx5_dev_spawn_data *spawn,
 	/* Search for IB context by device name. */
 	LIST_FOREACH(sh, &mlx5_dev_ctx_list, next) {
 		if (!strcmp(sh->ibdev_name,
-			mlx5_os_get_dev_device_name(spawn->phys_dev))) {
+			mlx5_os_get_ctx_device_name(spawn->ctx))) {
 			sh->refcnt++;
 			goto exit;
 		}

@@ -1279,13 +1279,13 @@ mlx5_alloc_shared_dev_ctx(const struct mlx5_dev_spawn_data *spawn,
 		rte_errno  = ENOMEM;
 		goto exit;
 	}
+	pthread_mutex_init(&sh->txpp.mutex, NULL);
 	sh->numa_node = spawn->cdev->dev->numa_node;
 	sh->cdev = spawn->cdev;
+	sh->devx = sh->cdev->config.devx;
+	sh->ctx = spawn->ctx;
 	if (spawn->bond_info)
 		sh->bond = *spawn->bond_info;
-	err = mlx5_os_open_device(spawn, sh);
-	if (!sh->ctx)
-		goto error;
 	err = mlx5_os_get_dev_attr(sh->ctx, &sh->device_attr);
 	if (err) {
 		DRV_LOG(DEBUG, "mlx5_os_get_dev_attr() failed");

index 4c8e633fb6..becd8722de 100644
@@ -136,7 +136,8 @@ struct mlx5_dev_spawn_data {
 	uint32_t phys_port; /**< Device physical port index. */
 	int pf_bond; /**< bonding device PF index. < 0 - no bonding */
 	struct mlx5_switch_info info; /**< Switch information. */
-	void *phys_dev; /**< Associated physical device. */
+	const char *phys_dev_name; /**< Name of physical device. */
+	void *ctx; /**< Associated physical device context. */
 	struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
 	struct rte_pci_device *pci_dev; /**< Backend PCI device. */
 	struct mlx5_common_device *cdev; /**< Backend common device. */

@@ -1771,8 +1772,6 @@ void mlx5_flow_meter_rxq_flush(struct rte_eth_dev *dev);
 struct rte_pci_driver;
 int mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *dev_attr);
 void mlx5_os_free_shared_dr(struct mlx5_priv *priv);
-int mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
-			 struct mlx5_dev_ctx_shared *sh);
 int mlx5_os_get_pdn(void *pd, uint32_t *pdn);
 int mlx5_os_net_probe(struct mlx5_common_device *cdev);
 void mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh);

230 lines not on this page · raw message

index c1b828a422..07ba0ff43b 100644
@@ -718,7 +718,7 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
 	fallback = true;
 #else
 	fallback = false;
-	if (!priv->config.devx || !priv->config.dv_flow_en ||
+	if (!sh->devx || !priv->config.dv_flow_en ||
 	    !priv->config.hca_attr.flow_counters_dump ||
 	    !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) ||
 	    (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP))

@@ -1025,7 +1025,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
 	if (!sh)
 		return NULL;
-	config->devx = sh->devx;
 #ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
 	config->dest_tir = 1;
 #endif

@@ -1325,7 +1324,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		config->mps == MLX5_MPW_ENHANCED ? "enhanced " :
 		config->mps == MLX5_MPW ? "legacy " : "",
 		config->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
-	if (config->devx) {
+	if (sh->devx) {
 		err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
 		if (err) {
 			err = -err;

@@ -1468,13 +1467,13 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		config->cqe_comp = 0;
 	}
 	if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_FTAG_STRIDX &&
-	    (!config->devx || !config->hca_attr.mini_cqe_resp_flow_tag)) {
+	    (!sh->devx || !config->hca_attr.mini_cqe_resp_flow_tag)) {
 		DRV_LOG(WARNING, "Flow Tag CQE compression"
 				 " format isn't supported.");
 		config->cqe_comp = 0;
 	}
 	if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_L34H_STRIDX &&
-	    (!config->devx || !config->hca_attr.mini_cqe_resp_l3_l4_tag)) {
+	    (!sh->devx || !config->hca_attr.mini_cqe_resp_l3_l4_tag)) {
 		DRV_LOG(WARNING, "L3/L4 Header CQE compression"
 				 " format isn't supported.");
 		config->cqe_comp = 0;

@@ -1497,7 +1496,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 			config->hca_attr.log_max_static_sq_wq);
 		DRV_LOG(DEBUG, "WQE rate PP mode is %ssupported",
 			config->hca_attr.qos.wqe_rate_pp ? "" : "not ");
-		if (!config->devx) {
+		if (!sh->devx) {
 			DRV_LOG(ERR, "DevX is required for packet pacing");
 			err = ENODEV;
 			goto error;

@@ -1544,7 +1543,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		goto error;
 #endif
 	}
-	if (config->devx) {
+	if (sh->devx) {
 		uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
 
 		err = config->hca_attr.access_register_user ?

@@ -1722,7 +1721,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		if (err)
 			goto error;
 	}
-	if (config->devx && config->dv_flow_en && config->dest_tir) {
+	if (sh->devx && config->dv_flow_en && config->dest_tir) {
 		priv->obj_ops = devx_obj_ops;
 		priv->obj_ops.drop_action_create =
 						ibv_obj_ops.drop_action_create;

index becd8722de..d2eabe04a5 100644
@@ -265,7 +265,6 @@ struct mlx5_dev_config {
 	unsigned int lacp_by_user:1;
 	/* Enable user to manage LACP traffic. */
 	unsigned int swp:1; /* Tx generic tunnel checksum and TSO offload. */
-	unsigned int devx:1; /* Whether devx interface is available or not. */
 	unsigned int dest_tir:1; /* Whether advanced DR API is available. */
 	unsigned int reclaim_mode:2; /* Memory reclaim mode. */
 	unsigned int rt_timestamp:1; /* realtime timestamp format. */

index b610ad3ef4..0f3288df96 100644
@@ -3350,7 +3350,7 @@ flow_dv_validate_action_count(struct rte_eth_dev *dev, bool shared,
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
 
-	if (!priv->config.devx)
+	if (!priv->sh->devx)
 		goto notsup_err;
 	if (action_flags & MLX5_FLOW_ACTION_COUNT)
 		return rte_flow_error_set(error, EINVAL,

@@ -5297,7 +5297,7 @@ flow_dv_validate_action_age(uint64_t action_flags,
 	struct mlx5_priv *priv = dev->data->dev_private;
 	const struct rte_flow_action_age *age = action->conf;
 
-	if (!priv->config.devx || (priv->sh->cmng.counter_fallback &&
+	if (!priv->sh->devx || (priv->sh->cmng.counter_fallback &&
 	    !priv->sh->aso_age_mng))
 		return rte_flow_error_set(error, ENOTSUP,
 					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED,

@@ -5582,7 +5582,7 @@ flow_dv_validate_action_sample(uint64_t *action_flags,
 		return rte_flow_error_set(error, EINVAL,
 					  RTE_FLOW_ERROR_TYPE_ACTION, action,
 					  "ratio value starts from 1");
-	if (!priv->config.devx || (sample->ratio > 0 && !priv->sampler_en))
+	if (!priv->sh->devx || (sample->ratio > 0 && !priv->sampler_en))
 		return rte_flow_error_set(error, ENOTSUP,
 					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
 					  NULL,

@@ -6166,7 +6166,7 @@ flow_dv_counter_alloc(struct rte_eth_dev *dev, uint32_t age)
 			age ? MLX5_COUNTER_TYPE_AGE : MLX5_COUNTER_TYPE_ORIGIN;
 	uint32_t cnt_idx;
 
-	if (!priv->config.devx) {
+	if (!priv->sh->devx) {
 		rte_errno = ENOTSUP;
 		return 0;
 	}

@@ -6553,7 +6553,7 @@ flow_dv_mtr_alloc(struct rte_eth_dev *dev)
 	struct mlx5_aso_mtr_pool *pool;
 	uint32_t mtr_idx = 0;
 
-	if (!priv->config.devx) {
+	if (!priv->sh->devx) {
 		rte_errno = ENOTSUP;
 		return 0;
 	}

@@ -12438,7 +12438,7 @@ flow_dv_aso_ct_alloc(struct rte_eth_dev *dev, struct rte_flow_error *error)
 	uint32_t ct_idx;
 
 	MLX5_ASSERT(mng);
-	if (!priv->config.devx) {
+	if (!priv->sh->devx) {
 		rte_errno = ENOTSUP;
 		return 0;
 	}

@@ -12874,7 +12874,7 @@ flow_dv_translate(struct rte_eth_dev *dev,
 			}
 			break;
 		case RTE_FLOW_ACTION_TYPE_COUNT:
-			if (!dev_conf->devx) {
+			if (!priv->sh->devx) {
 				return rte_flow_error_set
 					      (error, ENOTSUP,
 					       RTE_FLOW_ERROR_TYPE_UNSPECIFIED,

@@ -15718,7 +15718,7 @@ flow_dv_query_count(struct rte_eth_dev *dev, uint32_t cnt_idx, void *data,
 	struct mlx5_priv *priv = dev->data->dev_private;
 	struct rte_flow_query_count *qc = data;
 
-	if (!priv->config.devx)
+	if (!priv->sh->devx)
 		return rte_flow_error_set(error, ENOTSUP,
 					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
 					  NULL,

@@ -17331,7 +17331,7 @@ flow_dv_counter_query(struct rte_eth_dev *dev, uint32_t counter, bool clear,
 	uint64_t inn_pkts, inn_bytes;
 	int ret;
 
-	if (!priv->config.devx)
+	if (!priv->sh->devx)
 		return -1;
 
 	ret = _flow_dv_query_count(dev, counter, &inn_pkts, &inn_bytes);

index 3cbf5816a1..e93647aafd 100644
@@ -1112,7 +1112,7 @@ mlx5_dev_start(struct rte_eth_dev *dev)
 			dev->data->port_id, strerror(rte_errno));
 		goto error;
 	}
-	if ((priv->config.devx && priv->config.dv_flow_en &&
+	if ((priv->sh->devx && priv->config.dv_flow_en &&
 	    priv->config.dest_tir) && priv->obj_ops.lb_dummy_queue_create) {
 		ret = priv->obj_ops.lb_dummy_queue_create(dev);
 		if (ret)

index 1e76f63fc1..a882a18439 100644
@@ -272,7 +272,7 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
 	fallback = true;
 #else
 	fallback = false;
-	if (!priv->config.devx || !priv->config.dv_flow_en ||
+	if (!sh->devx || !priv->config.dv_flow_en ||
 	    !priv->config.hca_attr.flow_counters_dump ||
 	    !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) ||
 	    (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP))

@@ -349,7 +349,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
 	if (!sh)
 		return NULL;
-	config->devx = sh->devx;
 	/* Initialize the shutdown event in mlx5_dev_spawn to
 	 * support mlx5_is_removed for Windows.
 	 */

@@ -452,7 +451,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		DRV_LOG(WARNING, "Rx CQE compression isn't supported.");
 		config->cqe_comp = 0;
 	}
-	if (config->devx) {
+	if (sh->devx) {
 		err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
 		if (err) {
 			err = -err;

@@ -471,7 +470,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		DRV_LOG(DEBUG, "checksum offloading is %ssupported",
 		    (config->hw_csum ? "" : "not "));
 	}
-	if (config->devx) {
+	if (sh->devx) {
 		uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
 
 		err = config->hca_attr.access_register_user ?

@@ -642,7 +641,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 			goto error;
 		}
 	}
-	if (config->devx && config->dv_flow_en) {
+	if (sh->devx && config->dv_flow_en) {
 		priv->obj_ops = devx_obj_ops;
 	} else {
 		DRV_LOG(ERR, "Flow mode %u is not supported "

index 2aa5684b05..1589212172 100644
@@ -424,8 +424,13 @@ mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
 		ibv_match = ibv_list[n];
 		break;
 	}
-	if (ibv_match == NULL)
+	if (ibv_match == NULL) {
+		DRV_LOG(WARNING,
+			"No Verbs device matches PCI device " PCI_PRI_FMT ","
+			" are kernel drivers loaded?",
+			addr->domain, addr->bus, addr->devid, addr->function);
 		rte_errno = ENOENT;
+	}
 	mlx5_glue->free_device_list(ibv_list);
 	return ibv_match;
 }

@@ -465,14 +470,14 @@ mlx5_restore_doorbell_mapping_env(int value)
  *
  * @param cdev
  *   Pointer to the mlx5 device.
- * @param ctx_ptr
- *   Pointer to fill inside pointer to device context.
+ * @param classes
+ *   Chosen classes come from device arguments.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 int
-mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx_ptr)
+mlx5_os_open_device(struct mlx5_common_device *cdev, uint32_t classes)
 {
 	struct ibv_device *ibv;
 	struct ibv_context *ctx = NULL;

@@ -494,18 +499,20 @@ mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx_ptr)
 	if (ctx) {
 		cdev->config.devx = 1;
 		DRV_LOG(DEBUG, "DevX is supported.");
-	} else {
+	} else if (classes == MLX5_CLASS_ETH) {
 		/* The environment variable is still configured. */
 		ctx = mlx5_glue->open_device(ibv);
 		if (ctx == NULL)
 			goto error;
 		DRV_LOG(DEBUG, "DevX is NOT supported.");
+	} else {
+		goto error;
 	}
 	/* The device is created, no need for environment. */
 	mlx5_restore_doorbell_mapping_env(dbmap_env);
 	/* Hint libmlx5 to use PMD allocator for data plane resources */
 	mlx5_set_context_attr(cdev->dev, ctx);
-	*ctx_ptr = (void *)ctx;
+	cdev->ctx = ctx;
 	return 0;
 error:
 	rte_errno = errno ? errno : ENODEV;

82 lines not on this page · raw message

index f36791f24e..d7d9e43a4d 100644
@@ -346,6 +346,7 @@ struct mlx5_common_device {
 	struct rte_device *dev;
 	TAILQ_ENTRY(mlx5_common_device) next;
 	uint32_t classes_loaded;
+	void *ctx; /* Verbs/DV/DevX context. */
 	struct mlx5_common_dev_config config; /* Device configuration. */
 };
 

@@ -446,7 +447,6 @@ mlx5_dev_is_pci(const struct rte_device *dev);
 
 /* mlx5_common_os.c */
 
-__rte_internal
-int mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx);
+int mlx5_os_open_device(struct mlx5_common_device *cdev, uint32_t classes);
 
 #endif /* RTE_PMD_MLX5_COMMON_H_ */

index e426a955ff..b7178cbbcf 100644
@@ -7,6 +7,7 @@
 #include <stdio.h>
 
 #include <rte_mempool.h>
+#include <rte_bus_pci.h>
 #include <rte_malloc.h>
 #include <rte_errno.h>
 

@@ -17,7 +18,7 @@
 #include "mlx5_malloc.h"
 
 /**
- * Initialization routine for run-time dependency on external lib
+ * Initialization routine for run-time dependency on external lib.
  */
 void
 mlx5_glue_constructor(void)

@@ -25,7 +26,7 @@ mlx5_glue_constructor(void)
 }
 
 /**
- * Allocate PD. Given a devx context object
+ * Allocate PD. Given a DevX context object
  * return an mlx5-pd object.
  *
  * @param[in] ctx

@@ -37,8 +38,8 @@ mlx5_glue_constructor(void)
 void *
 mlx5_os_alloc_pd(void *ctx)
 {
-	struct mlx5_pd *ppd =  mlx5_malloc(MLX5_MEM_ZERO,
-		sizeof(struct mlx5_pd), 0, SOCKET_ID_ANY);
+	struct mlx5_pd *ppd = mlx5_malloc(MLX5_MEM_ZERO, sizeof(struct mlx5_pd),
+					  0, SOCKET_ID_ANY);
 	if (!ppd)
 		return NULL;
 

@@ -60,7 +61,7 @@ mlx5_os_alloc_pd(void *ctx)
  *   Pointer to mlx5_pd.
  *
  * @return
- *    Zero if pd is released successfully, negative number otherwise.
+ *   Zero if pd is released successfully, negative number otherwise.
  */
 int
 mlx5_os_dealloc_pd(void *pd)

@@ -184,22 +185,28 @@ mlx5_os_get_devx_device(struct rte_device *dev,
  *
  * This function calls the Windows glue APIs to open a device.
  *
- * @param dev
+ * @param cdev
  *   Pointer to mlx5 device structure.
- * @param ctx
- *   Pointer to fill inside pointer to device context.
+ * @param classes
+ *   Chosen classes come from user device arguments.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 int
-mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx)
+mlx5_os_open_device(struct mlx5_common_device *cdev, uint32_t classes)
 {
 	struct devx_device_bdf *devx_bdf_dev = NULL;
 	struct devx_device_bdf *devx_list;
 	struct mlx5_context *mlx5_ctx = NULL;
 	int n;
 
+	if (classes != MLX5_CLASS_ETH) {
+		DRV_LOG(ERR,
+			"The chosen classes are not supported on Windows.");
+		rte_errno = ENOTSUP;
+		return -rte_errno;
+	}
 	errno = 0;
 	devx_list = mlx5_glue->get_device_list(&n);
 	if (devx_list == NULL) {

@@ -223,7 +230,7 @@ mlx5_os_open_device(struct mlx5_common_device *cdev, void **ctx)
 		goto error;
 	}
 	cdev->config.devx = 1;
-	*ctx = (void *)mlx5_ctx;
+	cdev->ctx = mlx5_ctx;
 	mlx5_glue->free_device_list(devx_list);
 	return 0;
 error:

index afb63e9b8f..4967e71c96 100644
@@ -35,8 +35,8 @@ struct mlx5_compress_xform {
 
 struct mlx5_compress_priv {
 	TAILQ_ENTRY(mlx5_compress_priv) next;
-	struct ibv_context *ctx; /* Device context. */
 	struct rte_compressdev *compressdev;
+	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
 	void *uar;
 	uint32_t pdn; /* Protection Domain number. */
 	uint8_t min_block_size;

@@ -236,7 +236,7 @@ mlx5_compress_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
 		rte_errno = ENOMEM;
 		goto err;
 	}
-	ret = mlx5_devx_cq_create(priv->ctx, &qp->cq, log_ops_n, &cq_attr,
+	ret = mlx5_devx_cq_create(priv->cdev->ctx, &qp->cq, log_ops_n, &cq_attr,
 				  socket_id);
 	if (ret != 0) {
 		DRV_LOG(ERR, "Failed to create CQ.");

@@ -244,7 +244,7 @@ mlx5_compress_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
 	}
 	sq_attr.cqn = qp->cq.cq->id;
 	sq_attr.ts_format = mlx5_ts_format_conv(priv->sq_ts_format);
-	ret = mlx5_devx_sq_create(priv->ctx, &qp->sq, log_ops_n, &sq_attr,
+	ret = mlx5_devx_sq_create(priv->cdev->ctx, &qp->sq, log_ops_n, &sq_attr,
 				  socket_id);
 	if (ret != 0) {
 		DRV_LOG(ERR, "Failed to create SQ.");

@@ -707,7 +707,7 @@ mlx5_compress_pd_create(struct mlx5_compress_priv *priv)
 	struct mlx5dv_pd pd_info;
 	int ret;
 
-	priv->pd = mlx5_glue->alloc_pd(priv->ctx);
+	priv->pd = mlx5_glue->alloc_pd(priv->cdev->ctx);
 	if (priv->pd == NULL) {
 		DRV_LOG(ERR, "Failed to allocate PD.");
 		return errno ? -errno : -ENOMEM;

@@ -735,7 +735,7 @@ mlx5_compress_hw_global_prepare(struct mlx5_compress_priv *priv)
 {
 	if (mlx5_compress_pd_create(priv) != 0)
 		return -1;
-	priv->uar = mlx5_devx_alloc_uar(priv->ctx, -1);
+	priv->uar = mlx5_devx_alloc_uar(priv->cdev->ctx, -1);
 	if (priv->uar == NULL || mlx5_os_get_devx_uar_reg_addr(priv->uar) ==
 	    NULL) {
 		rte_errno = errno;

@@ -775,7 +775,8 @@ mlx5_compress_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
 		/* Iterate all the existing mlx5 devices. */
 		TAILQ_FOREACH(priv, &mlx5_compress_priv_list, next)
 			mlx5_free_mr_by_addr(&priv->mr_scache,
-					     priv->ctx->device->name,
+					     mlx5_os_get_ctx_device_name
+							      (priv->cdev->ctx),
 					     addr, len);
 		pthread_mutex_unlock(&priv_list_lock);
 		break;

@@ -788,60 +789,47 @@ mlx5_compress_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
 static int
 mlx5_compress_dev_probe(struct mlx5_common_device *cdev)
 {
-	struct ibv_device *ibv;
 	struct rte_compressdev *compressdev;
-	struct ibv_context *ctx;
 	struct mlx5_compress_priv *priv;
 	struct mlx5_hca_attr att = { 0 };
 	struct rte_compressdev_pmd_init_params init_params = {
 		.name = "",
 		.socket_id = cdev->dev->numa_node,
 	};
+	const char *ibdev_name = mlx5_os_get_ctx_device_name(cdev->ctx);
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
 		DRV_LOG(ERR, "Non-primary process type is not supported.");
 		rte_errno = ENOTSUP;
 		return -rte_errno;
 	}
-	ibv = mlx5_os_get_ibv_dev(cdev->dev);
-	if (ibv == NULL)
-		return -rte_errno;
-	ctx = mlx5_glue->dv_open_device(ibv);
-	if (ctx == NULL) {
-		DRV_LOG(ERR, "Failed to open IB device \"%s\".", ibv->name);
-		rte_errno = ENODEV;
-		return -rte_errno;
-	}
-	if (mlx5_devx_cmd_query_hca_attr(ctx, &att) != 0 ||
+	if (mlx5_devx_cmd_query_hca_attr(cdev->ctx, &att) != 0 ||
 	    att.mmo_compress_en == 0 || att.mmo_decompress_en == 0 ||
 	    att.mmo_dma_en == 0) {
 		DRV_LOG(ERR, "Not enough capabilities to support compress "
 			"operations, maybe old FW/OFED version?");
-		claim_zero(mlx5_glue->close_device(ctx));
 		rte_errno = ENOTSUP;
 		return -ENOTSUP;
 	}
-	compressdev = rte_compressdev_pmd_create(ibv->name, cdev->dev,
+	compressdev = rte_compressdev_pmd_create(ibdev_name, cdev->dev,
 						 sizeof(*priv), &init_params);
 	if (compressdev == NULL) {
-		DRV_LOG(ERR, "Failed to create device \"%s\".", ibv->name);
-		claim_zero(mlx5_glue->close_device(ctx));
+		DRV_LOG(ERR, "Failed to create device \"%s\".", ibdev_name);
 		return -ENODEV;
 	}
 	DRV_LOG(INFO,
-		"Compress device %s was created successfully.", ibv->name);
+		"Compress device %s was created successfully.", ibdev_name);
 	compressdev->dev_ops = &mlx5_compress_ops;
 	compressdev->dequeue_burst = mlx5_compress_dequeue_burst;
 	compressdev->enqueue_burst = mlx5_compress_enqueue_burst;
 	compressdev->feature_flags = RTE_COMPDEV_FF_HW_ACCELERATED;
 	priv = compressdev->data->dev_private;
-	priv->ctx = ctx;
+	priv->cdev = cdev;
 	priv->compressdev = compressdev;
 	priv->min_block_size = att.compress_min_block_size;
 	priv->sq_ts_format = att.sq_ts_format;
 	if (mlx5_compress_hw_global_prepare(priv) != 0) {
 		rte_compressdev_pmd_destroy(priv->compressdev);
-		claim_zero(mlx5_glue->close_device(priv->ctx));
 		return -1;
 	}
 	if (mlx5_mr_btree_init(&priv->mr_scache.cache,

@@ -849,7 +837,6 @@ mlx5_compress_dev_probe(struct mlx5_common_device *cdev)
 		DRV_LOG(ERR, "Failed to allocate shared cache MR memory.");
 		mlx5_compress_hw_global_release(priv);
 		rte_compressdev_pmd_destroy(priv->compressdev);
-		claim_zero(mlx5_glue->close_device(priv->ctx));
 		rte_errno = ENOMEM;
 		return -rte_errno;
 	}

@@ -885,7 +872,6 @@ mlx5_compress_dev_remove(struct mlx5_common_device *cdev)
 		mlx5_mr_release_cache(&priv->mr_scache);
 		mlx5_compress_hw_global_release(priv);
 		rte_compressdev_pmd_destroy(priv->compressdev);
-		claim_zero(mlx5_glue->close_device(priv->ctx));
 	}
 	return 0;
 }

151 lines not on this page · raw message

index d589e0ac3d..238881c584 100644
@@ -19,7 +19,7 @@
 
 struct mlx5_crypto_priv {
 	TAILQ_ENTRY(mlx5_crypto_priv) next;
-	struct ibv_context *ctx; /* Device context. */
+	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
 	struct rte_cryptodev *crypto_dev;
 	void *uar; /* User Access Region. */
 	volatile uint64_t *uar_addr;

index 67b1fa3819..94f21ec036 100644
@@ -117,7 +117,8 @@ mlx5_crypto_dek_create_cb(void *tool_ctx __rte_unused, void *cb_ctx)
 		return NULL;
 	}
 	memcpy(&dek_attr.key, cipher_ctx->key.data, cipher_ctx->key.length);
-	dek->obj = mlx5_devx_cmd_create_dek_obj(ctx->priv->ctx, &dek_attr);
+	dek->obj = mlx5_devx_cmd_create_dek_obj(ctx->priv->cdev->ctx,
+						&dek_attr);
 	if (dek->obj == NULL) {
 		rte_free(dek);
 		return NULL;

index f34133e2c6..471c3f1bdc 100644
@@ -324,7 +324,7 @@ int
 mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	struct ibv_context *ctx = priv->sh->ctx;
+	struct ibv_context *ctx = priv->sh->cdev->ctx;
 	struct ibv_values_ex values;
 	int err = 0;
 

@@ -778,7 +778,7 @@ mlx5_dev_interrupt_handler(void *cb_arg)
 		struct rte_eth_dev *dev;
 		uint32_t tmp;
 
-		if (mlx5_glue->get_async_event(sh->ctx, &event))
+		if (mlx5_glue->get_async_event(sh->cdev->ctx, &event))
 			break;
 		/* Retrieve and check IB port index. */
 		tmp = (uint32_t)event.element.port_num;

@@ -990,7 +990,7 @@ mlx5_is_removed(struct rte_eth_dev *dev)
 	struct ibv_device_attr device_attr;
 	struct mlx5_priv *priv = dev->data->dev_private;
 
-	if (mlx5_glue->query_device(priv->sh->ctx, &device_attr) == EIO)
+	if (mlx5_glue->query_device(priv->sh->cdev->ctx, &device_attr) == EIO)
 		return 1;
 	return 0;
 }

index b0996813dc..35b2dfd3b2 100644
@@ -101,7 +101,7 @@ mlx5_mp_os_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 	case MLX5_MP_REQ_VERBS_CMD_FD:
 		mp_init_msg(&priv->mp_id, &mp_res, param->type);
 		mp_res.num_fds = 1;
-		mp_res.fds[0] = ((struct ibv_context *)priv->sh->ctx)->cmd_fd;
+		mp_res.fds[0] = ((struct ibv_context *)cdev->ctx)->cmd_fd;
 		res->result = 0;
 		ret = rte_mp_reply(&mp_res, peer);
 		break;

@@ -248,7 +248,8 @@ mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx5_mp_req_type type)
 	mp_init_msg(&priv->mp_id, &mp_req, type);
 	if (type == MLX5_MP_REQ_START_RXTX) {
 		mp_req.num_fds = 1;
-		mp_req.fds[0] = ((struct ibv_context *)priv->sh->ctx)->cmd_fd;
+		mp_req.fds[0] =
+			((struct ibv_context *)priv->sh->cdev->ctx)->cmd_fd;
 	}
 	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
 	if (ret) {

327 lines not on this page · raw message

117 lines not on this page · raw message

144 lines not on this page · raw message

index d2eabe04a5..2c92b2ce13 100644
@@ -137,7 +137,6 @@ struct mlx5_dev_spawn_data {
 	int pf_bond; /**< bonding device PF index. < 0 - no bonding */
 	struct mlx5_switch_info info; /**< Switch information. */
 	const char *phys_dev_name; /**< Name of physical device. */
-	void *ctx; /**< Associated physical device context. */
 	struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
 	struct rte_pci_device *pci_dev; /**< Backend PCI device. */
 	struct mlx5_common_device *cdev; /**< Backend common device. */

@@ -1141,7 +1140,6 @@ struct mlx5_dev_ctx_shared {
 	uint32_t max_port; /* Maximal IB device port index. */
 	struct mlx5_bond_info bond; /* Bonding information. */
 	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
-	void *ctx; /* Verbs/DV/DevX context. */
 	void *pd; /* Protection Domain. */
 	uint32_t pdn; /* Protection Domain number. */
 	uint32_t tdn; /* Transport Domain number. */

index a1db53577a..1fb835cb0d 100644
@@ -279,7 +279,7 @@ mlx5_rxq_create_devx_rq_resources(struct rte_eth_dev *dev, uint16_t idx)
 	rq_attr.wq_attr.pd = priv->sh->pdn;
 	rq_attr.counter_set_id = priv->counter_set_id;
 	/* Create RQ using DevX API. */
-	return mlx5_devx_rq_create(priv->sh->ctx, &rxq_ctrl->obj->rq_obj,
+	return mlx5_devx_rq_create(priv->sh->cdev->ctx, &rxq_ctrl->obj->rq_obj,
 				   wqe_size, log_desc_n, &rq_attr,
 				   rxq_ctrl->socket);
 }

@@ -365,8 +365,8 @@ mlx5_rxq_create_devx_cq_resources(struct rte_eth_dev *dev, uint16_t idx)
 	cq_attr.uar_page_id = mlx5_os_get_devx_uar_page_id(sh->devx_rx_uar);
 	log_cqe_n = log2above(cqe_n);
 	/* Create CQ using DevX API. */
-	ret = mlx5_devx_cq_create(sh->ctx, &rxq_ctrl->obj->cq_obj, log_cqe_n,
-				  &cq_attr, sh->numa_node);
+	ret = mlx5_devx_cq_create(sh->cdev->ctx, &rxq_ctrl->obj->cq_obj,
+				  log_cqe_n, &cq_attr, sh->numa_node);
 	if (ret)
 		return ret;
 	cq_obj = &rxq_ctrl->obj->cq_obj;

@@ -442,7 +442,7 @@ mlx5_rxq_obj_hairpin_new(struct rte_eth_dev *dev, uint16_t idx)
 			attr.wq_attr.log_hairpin_data_sz -
 			MLX5_HAIRPIN_QUEUE_STRIDE;
 	attr.counter_set_id = priv->counter_set_id;
-	tmpl->rq = mlx5_devx_cmd_create_rq(priv->sh->ctx, &attr,
+	tmpl->rq = mlx5_devx_cmd_create_rq(priv->sh->cdev->ctx, &attr,
 					   rxq_ctrl->socket);
 	if (!tmpl->rq) {
 		DRV_LOG(ERR,

@@ -486,8 +486,8 @@ mlx5_rxq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
 			  MLX5DV_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA;
 
 		tmpl->devx_channel = mlx5_os_devx_create_event_channel
-								(priv->sh->ctx,
-								 devx_ev_flag);
+							(priv->sh->cdev->ctx,
+							 devx_ev_flag);
 		if (!tmpl->devx_channel) {
 			rte_errno = errno;
 			DRV_LOG(ERR, "Failed to create event channel %d.",

@@ -602,7 +602,7 @@ mlx5_devx_ind_table_new(struct rte_eth_dev *dev, const unsigned int log_n,
 							ind_tbl->queues_n);
 	if (!rqt_attr)
 		return -rte_errno;
-	ind_tbl->rqt = mlx5_devx_cmd_create_rqt(priv->sh->ctx, rqt_attr);
+	ind_tbl->rqt = mlx5_devx_cmd_create_rqt(priv->sh->cdev->ctx, rqt_attr);
 	mlx5_free(rqt_attr);
 	if (!ind_tbl->rqt) {
 		DRV_LOG(ERR, "Port %u cannot create DevX RQT.",

@@ -770,7 +770,7 @@ mlx5_devx_hrxq_new(struct rte_eth_dev *dev, struct mlx5_hrxq *hrxq,
 
 	mlx5_devx_tir_attr_set(dev, hrxq->rss_key, hrxq->hash_fields,
 			       hrxq->ind_table, tunnel, &tir_attr);
-	hrxq->tir = mlx5_devx_cmd_create_tir(priv->sh->ctx, &tir_attr);
+	hrxq->tir = mlx5_devx_cmd_create_tir(priv->sh->cdev->ctx, &tir_attr);
 	if (!hrxq->tir) {
 		DRV_LOG(ERR, "Port %u cannot create DevX TIR.",
 			dev->data->port_id);

@@ -936,7 +936,7 @@ mlx5_txq_obj_hairpin_new(struct rte_eth_dev *dev, uint16_t idx)
 			attr.wq_attr.log_hairpin_data_sz -
 			MLX5_HAIRPIN_QUEUE_STRIDE;
 	attr.tis_num = priv->sh->tis->id;
-	tmpl->sq = mlx5_devx_cmd_create_sq(priv->sh->ctx, &attr);
+	tmpl->sq = mlx5_devx_cmd_create_sq(priv->sh->cdev->ctx, &attr);
 	if (!tmpl->sq) {
 		DRV_LOG(ERR,
 			"Port %u tx hairpin queue %u can't create SQ object.",

@@ -1001,8 +1001,8 @@ mlx5_txq_create_devx_sq_resources(struct rte_eth_dev *dev, uint16_t idx,
 		.ts_format = mlx5_ts_format_conv(priv->sh->sq_ts_format),
 	};
 	/* Create Send Queue object with DevX. */
-	return mlx5_devx_sq_create(priv->sh->ctx, &txq_obj->sq_obj, log_desc_n,
-				   &sq_attr, priv->sh->numa_node);
+	return mlx5_devx_sq_create(priv->sh->cdev->ctx, &txq_obj->sq_obj,
+				   log_desc_n, &sq_attr, priv->sh->numa_node);
 }
 #endif
 

@@ -1058,7 +1058,7 @@ mlx5_txq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
 		return 0;
 	}
 	/* Create completion queue object with DevX. */
-	ret = mlx5_devx_cq_create(sh->ctx, &txq_obj->cq_obj, log_desc_n,
+	ret = mlx5_devx_cq_create(sh->cdev->ctx, &txq_obj->cq_obj, log_desc_n,
 				  &cq_attr, priv->sh->numa_node);
 	if (ret) {
 		DRV_LOG(ERR, "Port %u Tx queue %u CQ creation failure.",

index c914a7120c..abe8a0d7fe 100644
@@ -7628,7 +7628,7 @@ mlx5_flow_create_counter_stat_mem_mng(struct mlx5_dev_ctx_shared *sh)
 	}
 	mem_mng = (struct mlx5_counter_stats_mem_mng *)(mem + size) - 1;
 	size = sizeof(*raw_data) * MLX5_COUNTERS_PER_POOL * raws_n;
-	mem_mng->umem = mlx5_os_umem_reg(sh->ctx, mem, size,
+	mem_mng->umem = mlx5_os_umem_reg(sh->cdev->ctx, mem, size,
 						 IBV_ACCESS_LOCAL_WRITE);
 	if (!mem_mng->umem) {
 		rte_errno = errno;

@@ -7642,7 +7642,7 @@ mlx5_flow_create_counter_stat_mem_mng(struct mlx5_dev_ctx_shared *sh)
 	mkey_attr.pd = sh->pdn;
 	mkey_attr.relaxed_ordering_write = sh->cmng.relaxed_ordering_write;
 	mkey_attr.relaxed_ordering_read = sh->cmng.relaxed_ordering_read;
-	mem_mng->dm = mlx5_devx_cmd_mkey_create(sh->ctx, &mkey_attr);
+	mem_mng->dm = mlx5_devx_cmd_mkey_create(sh->cdev->ctx, &mkey_attr);
 	if (!mem_mng->dm) {
 		mlx5_os_umem_dereg(mem_mng->umem);
 		rte_errno = errno;

index e11327a11b..49eec7a6b6 100644
@@ -309,13 +309,14 @@ mlx5_aso_queue_init(struct mlx5_dev_ctx_shared *sh,
 		    enum mlx5_access_aso_opc_mod aso_opc_mod)
 {
 	uint32_t sq_desc_n = 1 << MLX5_ASO_QUEUE_LOG_DESC;
+	struct mlx5_common_device *cdev = sh->cdev;
 
 	switch (aso_opc_mod) {
 	case ASO_OPC_MOD_FLOW_HIT:
 		if (mlx5_aso_reg_mr(sh, (MLX5_ASO_AGE_ACTIONS_PER_POOL / 8) *
 				    sq_desc_n, &sh->aso_age_mng->aso_sq.mr, 0))
 			return -1;
-		if (mlx5_aso_sq_create(sh->ctx, &sh->aso_age_mng->aso_sq, 0,
+		if (mlx5_aso_sq_create(cdev->ctx, &sh->aso_age_mng->aso_sq, 0,
 				  sh->tx_uar, sh->pdn, MLX5_ASO_QUEUE_LOG_DESC,
 				  sh->sq_ts_format)) {
 			mlx5_aso_dereg_mr(sh, &sh->aso_age_mng->aso_sq.mr);

@@ -324,7 +325,7 @@ mlx5_aso_queue_init(struct mlx5_dev_ctx_shared *sh,
 		mlx5_aso_age_init_sq(&sh->aso_age_mng->aso_sq);
 		break;
 	case ASO_OPC_MOD_POLICER:
-		if (mlx5_aso_sq_create(sh->ctx, &sh->mtrmng->pools_mng.sq, 0,
+		if (mlx5_aso_sq_create(cdev->ctx, &sh->mtrmng->pools_mng.sq, 0,
 				  sh->tx_uar, sh->pdn, MLX5_ASO_QUEUE_LOG_DESC,
 				  sh->sq_ts_format))
 			return -1;

@@ -335,7 +336,7 @@ mlx5_aso_queue_init(struct mlx5_dev_ctx_shared *sh,
 		if (mlx5_aso_reg_mr(sh, 64 * sq_desc_n,
 				    &sh->ct_mng->aso_sq.mr, 0))
 			return -1;
-		if (mlx5_aso_sq_create(sh->ctx, &sh->ct_mng->aso_sq, 0,
+		if (mlx5_aso_sq_create(cdev->ctx, &sh->ct_mng->aso_sq, 0,
 				sh->tx_uar, sh->pdn, MLX5_ASO_QUEUE_LOG_DESC,
 				sh->sq_ts_format)) {
 			mlx5_aso_dereg_mr(sh, &sh->ct_mng->aso_sq.mr);

index 0f3288df96..ac97cd717a 100644
@@ -3678,8 +3678,8 @@ flow_dv_encap_decap_create_cb(void *tool_ctx, void *cb_ctx)
 	}
 	*resource = *ctx_resource;
 	resource->idx = idx;
-	ret = mlx5_flow_os_create_flow_action_packet_reformat(sh->ctx, domain,
-							      resource,
+	ret = mlx5_flow_os_create_flow_action_packet_reformat(sh->cdev->ctx,
+							      domain, resource,
 							     &resource->action);
 	if (ret) {
 		mlx5_ipool_free(sh->ipool[MLX5_IPOOL_DECAP_ENCAP], idx);

@@ -5479,7 +5479,7 @@ flow_dv_modify_create_cb(void *tool_ctx, void *cb_ctx)
 	else
 		ns = sh->rx_domain;
 	ret = mlx5_flow_os_create_flow_action_modify_header
-					(sh->ctx, ns, entry,
+					(sh->cdev->ctx, ns, entry,
 					 data_len, &entry->action);
 	if (ret) {
 		mlx5_ipool_free(sh->mdh_ipools[ref->actions_num - 1], idx);

@@ -6101,7 +6101,7 @@ flow_dv_counter_pool_prepare(struct rte_eth_dev *dev,
 
 	if (fallback) {
 		/* bulk_bitmap must be 0 for single counter allocation. */
-		dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0);
+		dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->cdev->ctx, 0);
 		if (!dcs)
 			return NULL;
 		pool = flow_dv_find_pool_by_id(cmng, dcs->id);

@@ -6119,7 +6119,7 @@ flow_dv_counter_pool_prepare(struct rte_eth_dev *dev,
 		*cnt_free = cnt;
 		return pool;
 	}
-	dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0x4);
+	dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->cdev->ctx, 0x4);
 	if (!dcs) {
 		rte_errno = ENODATA;
 		return NULL;

@@ -6479,7 +6479,7 @@ flow_dv_mtr_pool_create(struct rte_eth_dev *dev,
 	uint32_t log_obj_size;
 
 	log_obj_size = rte_log2_u32(MLX5_ASO_MTRS_PER_POOL >> 1);
-	dcs = mlx5_devx_cmd_create_flow_meter_aso_obj(priv->sh->ctx,
+	dcs = mlx5_devx_cmd_create_flow_meter_aso_obj(priv->sh->cdev->ctx,
 			priv->sh->pdn, log_obj_size);
 	if (!dcs) {
 		rte_errno = ENODATA;

@@ -9175,7 +9175,7 @@ flow_dev_geneve_tlv_option_resource_register(struct rte_eth_dev *dev,
 		}
 	} else {
 		/* Create a GENEVE TLV object and resource. */
-		obj = mlx5_devx_cmd_create_geneve_tlv_option(sh->ctx,
+		obj = mlx5_devx_cmd_create_geneve_tlv_option(sh->cdev->ctx,
 				geneve_opt_v->option_class,
 				geneve_opt_v->option_type,
 				geneve_opt_v->option_len);

@@ -10535,7 +10535,8 @@ flow_dv_matcher_create_cb(void *tool_ctx, void *cb_ctx)
 	dv_attr.priority = ref->priority;
 	if (tbl->is_egress)
 		dv_attr.flags |= IBV_FLOW_ATTR_FLAGS_EGRESS;
-	ret = mlx5_flow_os_create_flow_matcher(sh->ctx, &dv_attr, tbl->tbl.obj,
+	ret = mlx5_flow_os_create_flow_matcher(sh->cdev->ctx, &dv_attr,
+					       tbl->tbl.obj,
 					       &resource->matcher_object);
 	if (ret) {
 		mlx5_free(resource);

@@ -11954,7 +11955,7 @@ flow_dv_age_pool_create(struct rte_eth_dev *dev,
 	struct mlx5_devx_obj *obj = NULL;
 	uint32_t i;
 
-	obj = mlx5_devx_cmd_create_flow_hit_aso_obj(priv->sh->ctx,
+	obj = mlx5_devx_cmd_create_flow_hit_aso_obj(priv->sh->cdev->ctx,
 						    priv->sh->pdn);
 	if (!obj) {
 		rte_errno = ENODATA;

@@ -12382,7 +12383,7 @@ flow_dv_ct_pool_create(struct rte_eth_dev *dev,
 	uint32_t i;
 	uint32_t log_obj_size = rte_log2_u32(MLX5_ASO_CT_ACTIONS_PER_POOL);
 
-	obj = mlx5_devx_cmd_create_conn_track_offload_obj(priv->sh->ctx,
+	obj = mlx5_devx_cmd_create_conn_track_offload_obj(priv->sh->cdev->ctx,
 						priv->sh->pdn, log_obj_size);
 	if (!obj) {
 		rte_errno = ENODATA;

@@ -17188,8 +17189,8 @@ mlx5_flow_discover_dr_action_support(struct rte_eth_dev *dev)
 		goto err;
 	dv_attr.match_criteria_enable = flow_dv_matcher_enable(mask.buf);
 	__flow_dv_adjust_buf_size(&mask.size, dv_attr.match_criteria_enable);
-	ret = mlx5_flow_os_create_flow_matcher(sh->ctx, &dv_attr, tbl->obj,
-					       &matcher);
+	ret = mlx5_flow_os_create_flow_matcher(sh->cdev->ctx, &dv_attr,
+					       tbl->obj, &matcher);
 	if (ret)
 		goto err;
 	__flow_dv_adjust_buf_size(&value.size, dv_attr.match_criteria_enable);

@@ -17257,7 +17258,7 @@ mlx5_flow_dv_discover_counter_offset_support(struct rte_eth_dev *dev)
 					0, 0, 0, NULL);
 	if (!tbl)
 		goto err;
-	dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0x4);
+	dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->cdev->ctx, 0x4);
 	if (!dcs)
 		goto err;
 	ret = mlx5_flow_os_create_flow_action_count(dcs->obj, UINT16_MAX,

@@ -17266,8 +17267,8 @@ mlx5_flow_dv_discover_counter_offset_support(struct rte_eth_dev *dev)
 		goto err;
 	dv_attr.match_criteria_enable = flow_dv_matcher_enable(mask.buf);
 	__flow_dv_adjust_buf_size(&mask.size, dv_attr.match_criteria_enable);
-	ret = mlx5_flow_os_create_flow_matcher(sh->ctx, &dv_attr, tbl->obj,
-					       &matcher);
+	ret = mlx5_flow_os_create_flow_matcher(sh->cdev->ctx, &dv_attr,
+					       tbl->obj, &matcher);
 	if (ret)
 		goto err;
 	__flow_dv_adjust_buf_size(&value.size, dv_attr.match_criteria_enable);

index b93fd4d2c9..2df63b6cac 100644
@@ -198,7 +198,7 @@ flow_verbs_counter_create(struct rte_eth_dev *dev,
 {
 #if defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42)
 	struct mlx5_priv *priv = dev->data->dev_private;
-	struct ibv_context *ctx = priv->sh->ctx;
+	struct ibv_context *ctx = priv->sh->cdev->ctx;
 	struct ibv_counter_set_init_attr init = {
 			 .counter_set_id = counter->shared_info.id};
 

@@ -210,7 +210,7 @@ flow_verbs_counter_create(struct rte_eth_dev *dev,
 	return 0;
 #elif defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
 	struct mlx5_priv *priv = dev->data->dev_private;
-	struct ibv_context *ctx = priv->sh->ctx;
+	struct ibv_context *ctx = priv->sh->cdev->ctx;
 	struct ibv_counters_init_attr init = {0};
 	struct ibv_counter_attach_attr attach;
 	int ret;

index 4f6da9f2d1..baf6015d89 100644
@@ -49,7 +49,7 @@ static int
 mlx5_txpp_create_event_channel(struct mlx5_dev_ctx_shared *sh)
 {
 	MLX5_ASSERT(!sh->txpp.echan);
-	sh->txpp.echan = mlx5_os_devx_create_event_channel(sh->ctx,
+	sh->txpp.echan = mlx5_os_devx_create_event_channel(sh->cdev->ctx,
 			MLX5DV_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA);
 	if (!sh->txpp.echan) {
 		rte_errno = errno;

@@ -104,7 +104,7 @@ mlx5_txpp_alloc_pp_index(struct mlx5_dev_ctx_shared *sh)
 	MLX5_SET(set_pp_rate_limit_context, &pp, rate_mode,
 		 sh->txpp.test ? MLX5_DATA_RATE : MLX5_WQE_RATE);
 	sh->txpp.pp = mlx5_glue->dv_alloc_pp
-				(sh->ctx, sizeof(pp), &pp,
+				(sh->cdev->ctx, sizeof(pp), &pp,
 				 MLX5DV_PP_ALLOC_FLAGS_DEDICATED_INDEX);
 	if (sh->txpp.pp == NULL) {
 		DRV_LOG(ERR, "Failed to allocate packet pacing index.");

@@ -245,7 +245,7 @@ mlx5_txpp_create_rearm_queue(struct mlx5_dev_ctx_shared *sh)
 	int ret;
 
 	/* Create completion queue object for Rearm Queue. */
-	ret = mlx5_devx_cq_create(sh->ctx, &wq->cq_obj,
+	ret = mlx5_devx_cq_create(sh->cdev->ctx, &wq->cq_obj,
 				  log2above(MLX5_TXPP_REARM_CQ_SIZE), &cq_attr,
 				  sh->numa_node);
 	if (ret) {

@@ -259,7 +259,7 @@ mlx5_txpp_create_rearm_queue(struct mlx5_dev_ctx_shared *sh)
 	/* Create send queue object for Rearm Queue. */
 	sq_attr.cqn = wq->cq_obj.cq->id;
 	/* There should be no WQE leftovers in the cyclic queue. */
-	ret = mlx5_devx_sq_create(sh->ctx, &wq->sq_obj,
+	ret = mlx5_devx_sq_create(sh->cdev->ctx, &wq->sq_obj,
 				  log2above(MLX5_TXPP_REARM_SQ_SIZE), &sq_attr,
 				  sh->numa_node);
 	if (ret) {

@@ -409,7 +409,7 @@ mlx5_txpp_create_clock_queue(struct mlx5_dev_ctx_shared *sh)
 	sh->txpp.ts_p = 0;
 	sh->txpp.ts_n = 0;
 	/* Create completion queue object for Clock Queue. */
-	ret = mlx5_devx_cq_create(sh->ctx, &wq->cq_obj,
+	ret = mlx5_devx_cq_create(sh->cdev->ctx, &wq->cq_obj,
 				  log2above(MLX5_TXPP_CLKQ_SIZE), &cq_attr,
 				  sh->numa_node);
 	if (ret) {

@@ -446,7 +446,8 @@ mlx5_txpp_create_clock_queue(struct mlx5_dev_ctx_shared *sh)
 	sq_attr.wq_attr.uar_page = mlx5_os_get_devx_uar_page_id(sh->tx_uar);
 	sq_attr.wq_attr.pd = sh->pdn;
 	sq_attr.ts_format = mlx5_ts_format_conv(sh->sq_ts_format);
-	ret = mlx5_devx_sq_create(sh->ctx, &wq->sq_obj, log2above(wq->sq_size),
+	ret = mlx5_devx_sq_create(sh->cdev->ctx, &wq->sq_obj,
+				  log2above(wq->sq_size),
 				  &sq_attr, sh->numa_node);
 	if (ret) {
 		rte_errno = errno;

index c709dd19be..fddc7a6b12 100644
@@ -38,7 +38,7 @@ mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN])
 		return -rte_errno;
 	}
 	priv = dev->data->dev_private;
-	context_obj = (mlx5_context_st *)priv->sh->ctx;
+	context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 	memcpy(mac, context_obj->mlx5_dev.eth_mac, RTE_ETHER_ADDR_LEN);
 	return 0;
 }

@@ -66,7 +66,7 @@ mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[MLX5_NAMESIZE])
 		return -rte_errno;
 	}
 	priv = dev->data->dev_private;
-	context_obj = (mlx5_context_st *)priv->sh->ctx;
+	context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 	strncpy(*ifname, context_obj->mlx5_dev.name, MLX5_NAMESIZE);
 	return 0;
 }

@@ -93,7 +93,7 @@ mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu)
 		return -rte_errno;
 	}
 	priv = dev->data->dev_private;
-	context_obj = (mlx5_context_st *)priv->sh->ctx;
+	context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 	*mtu = context_obj->mlx5_dev.mtu_bytes;
 	return 0;
 }

@@ -253,7 +253,7 @@ mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
 		return -rte_errno;
 	}
 	priv = dev->data->dev_private;
-	context_obj = (mlx5_context_st *)priv->sh->ctx;
+	context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 	dev_link.link_speed = context_obj->mlx5_dev.link_speed / (1000 * 1000);
 	dev_link.link_status =
 	      (context_obj->mlx5_dev.link_state == 1 && !mlx5_is_removed(dev))

@@ -359,7 +359,7 @@ mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
 	int err;
 	struct mlx5_devx_clock mlx5_clock;
 	struct mlx5_priv *priv = dev->data->dev_private;
-	mlx5_context_st *context_obj = (mlx5_context_st *)priv->sh->ctx;
+	mlx5_context_st *context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 
 	err = mlx5_glue->query_rt_values(context_obj, &mlx5_clock);
 	if (err != 0) {

@@ -383,7 +383,7 @@ int
 mlx5_is_removed(struct rte_eth_dev *dev)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	mlx5_context_st *context_obj = (mlx5_context_st *)priv->sh->ctx;
+	mlx5_context_st *context_obj = (mlx5_context_st *)priv->sh->cdev->ctx;
 
 	if (*context_obj->shutdown_event_obj.p_flag)
 		return 1;

index a882a18439..e1010beeb5 100644
@@ -352,14 +352,14 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	/* Initialize the shutdown event in mlx5_dev_spawn to
 	 * support mlx5_is_removed for Windows.
 	 */
-	err = mlx5_glue->devx_init_showdown_event(sh->ctx);
+	err = mlx5_glue->devx_init_showdown_event(sh->cdev->ctx);
 	if (err) {
 		DRV_LOG(ERR, "failed to init showdown event: %s",
 			strerror(errno));
 		goto error;
 	}
 	DRV_LOG(DEBUG, "MPW isn't supported");
-	mlx5_os_get_dev_attr(sh->ctx, &device_attr);
+	mlx5_os_get_dev_attr(sh->cdev->ctx, &device_attr);
 	config->swp = 0;
 	config->ind_table_max_size =
 		sh->device_attr.max_rwq_indirection_table_size;

@@ -452,7 +452,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		config->cqe_comp = 0;
 	}
 	if (sh->devx) {
-		err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
+		err = mlx5_devx_cmd_query_hca_attr(sh->cdev->ctx,
+						   &config->hca_attr);
 		if (err) {
 			err = -err;
 			goto error;

@@ -475,7 +476,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 
 		err = config->hca_attr.access_register_user ?
 			mlx5_devx_cmd_register_read
-				(sh->ctx, MLX5_REGISTER_ID_MTUTC, 0,
+				(sh->cdev->ctx, MLX5_REGISTER_ID_MTUTC, 0,
 				reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP;
 		if (!err) {
 			uint32_t ts_mode;

@@ -887,6 +888,7 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 		.pf_bond = -1,
 		.max_port = 1,
 		.phys_port = 1,
+		.phys_dev_name = mlx5_os_get_ctx_device_name(cdev->ctx),
 		.pci_dev = pci_dev,
 		.cdev = cdev,
 		.ifindex = -1, /* Spawn will assign */

@@ -907,7 +909,6 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 		.dv_flow_en = 1,
 		.log_hp_size = MLX5_ARG_UNSET,
 	};
-	void *ctx;
 	int ret;
 	uint32_t restore;
 

@@ -915,20 +916,12 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 		DRV_LOG(ERR, "Secondary process is not supported on Windows.");
 		return -ENOTSUP;
 	}
-	ret = mlx5_os_open_device(cdev, &ctx);
-	if (ret) {
-		DRV_LOG(ERR, "Fail to open DevX device %s", cdev->dev->name);
-		return -rte_errno;
-	}
 	ret = mlx5_init_once();
 	if (ret) {
 		DRV_LOG(ERR, "unable to init PMD global data: %s",
 			strerror(rte_errno));
-		claim_zero(mlx5_glue->close_device(ctx));
 		return -rte_errno;
 	}
-	spawn.ctx = ctx;
-	spawn.phys_dev_name = mlx5_os_get_ctx_device_name(ctx);
 	/* Device specific configuration. */
 	switch (pci_dev->id.device_id) {
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:

@@ -945,10 +938,8 @@ mlx5_os_net_probe(struct mlx5_common_device *cdev)
 		break;
 	}
 	spawn.eth_dev = mlx5_dev_spawn(cdev->dev, &spawn, &dev_config);
-	if (!spawn.eth_dev) {
-		claim_zero(mlx5_glue->close_device(ctx));
+	if (!spawn.eth_dev)
 		return -rte_errno;
-	}
 	restore = spawn.eth_dev->data->dev_flags;
 	rte_eth_copy_pci_info(spawn.eth_dev, pci_dev);
 	/* Restore non-PCI flags cleared by the above call. */

107 lines not on this page · raw message

index 514f3408f9..a9a010c437 100644
@@ -58,7 +58,7 @@ struct mlx5_regex_db {
 
 struct mlx5_regex_priv {
 	TAILQ_ENTRY(mlx5_regex_priv) next;
-	struct ibv_context *ctx; /* Device context. */
+	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
 	struct rte_regexdev *regexdev; /* Pointer to the RegEx dev. */
 	uint16_t nb_queues; /* Number of queues. */
 	struct mlx5_regex_qp *qps; /* Pointer to the qp array. */

index 8ce2dabb55..1580a51ccb 100644
@@ -83,7 +83,7 @@ regex_ctrl_create_cq(struct mlx5_regex_priv *priv, struct mlx5_regex_cq *cq)
 	int ret;
 
 	cq->ci = 0;
-	ret = mlx5_devx_cq_create(priv->ctx, &cq->cq_obj, cq->log_nb_desc,
+	ret = mlx5_devx_cq_create(priv->cdev->ctx, &cq->cq_obj, cq->log_nb_desc,
 				  &attr, SOCKET_ID_ANY);
 	if (ret) {
 		DRV_LOG(ERR, "Can't create CQ object.");

@@ -158,7 +158,7 @@ regex_ctrl_create_sq(struct mlx5_regex_priv *priv, struct mlx5_regex_qp *qp,
 	if (ret)
 		return ret;
 	attr.wq_attr.pd = pd_num;
-	ret = mlx5_devx_sq_create(priv->ctx, &sq->sq_obj,
+	ret = mlx5_devx_sq_create(priv->cdev->ctx, &sq->sq_obj,
 			MLX5_REGEX_WQE_LOG_NUM(priv->has_umr, log_nb_desc),
 			&attr, SOCKET_ID_ANY);
 	if (ret) {

index c79445ce7d..7b3e209714 100644
@@ -752,8 +752,8 @@ mlx5_regexdev_setup_fastpath(struct mlx5_regex_priv *priv, uint32_t qp_id)
 		for (i = 0; i < qp->nb_desc; i++) {
 			attr.klm_num = MLX5_REGEX_MAX_KLM_NUM;
 			attr.klm_array = qp->jobs[i].imkey_array;
-			qp->jobs[i].imkey = mlx5_devx_cmd_mkey_create(priv->ctx,
-								      &attr);
+			qp->jobs[i].imkey = mlx5_devx_cmd_mkey_create
+						       (priv->cdev->ctx, &attr);
 			if (!qp->jobs[i].imkey) {
 				err = -rte_errno;
 				DRV_LOG(ERR, "Failed to allocate imkey.");

203 lines not on this page · raw message

index 1589212172..341822cf71 100644
@@ -13,9 +13,13 @@
 
 #include <rte_errno.h>
 #include <rte_string_fns.h>
+#include <rte_bus_pci.h>
+#include <rte_bus_auxiliary.h>
 
 #include "mlx5_common.h"
+#include "mlx5_nl.h"
 #include "mlx5_common_log.h"
+#include "mlx5_common_private.h"
 #include "mlx5_common_defs.h"
 #include "mlx5_common_os.h"
 #include "mlx5_glue.h"

@@ -402,7 +406,7 @@ mlx5_glue_constructor(void)
 	mlx5_glue = NULL;
 }
 
-struct ibv_device *
+static struct ibv_device *
 mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
 {
 	int n;

@@ -435,6 +439,139 @@ mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
 	return ibv_match;
 }
 
+/* Try to disable ROCE by Netlink\Devlink. */
+static int
+mlx5_nl_roce_disable(const char *addr)
+{
+	int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC);
+	int devlink_id;
+	int enable;
+	int ret;
+
+	if (nlsk_fd < 0)
+		return nlsk_fd;
+	devlink_id = mlx5_nl_devlink_family_id_get(nlsk_fd);
+	if (devlink_id < 0) {
+		ret = devlink_id;
+		DRV_LOG(DEBUG,
+			"Failed to get devlink id for ROCE operations by Netlink.");
+		goto close;
+	}
+	ret = mlx5_nl_enable_roce_get(nlsk_fd, devlink_id, addr, &enable);
+	if (ret) {
+		DRV_LOG(DEBUG, "Failed to get ROCE enable by Netlink: %d.",
+			ret);
+		goto close;
+	} else if (!enable) {
+		DRV_LOG(INFO, "ROCE has already disabled(Netlink).");
+		goto close;
+	}
+	ret = mlx5_nl_enable_roce_set(nlsk_fd, devlink_id, addr, 0);
+	if (ret)
+		DRV_LOG(DEBUG, "Failed to disable ROCE by Netlink: %d.", ret);
+	else
+		DRV_LOG(INFO, "ROCE is disabled by Netlink successfully.");
+close:
+	close(nlsk_fd);
+	return ret;
+}
+
+/* Try to disable ROCE by sysfs. */
+static int
+mlx5_sys_roce_disable(const char *addr)
+{
+	FILE *file_o;
+	int enable;
+	int ret;
+
+	MKSTR(file_p, "/sys/bus/pci/devices/%s/roce_enable", addr);
+	file_o = fopen(file_p, "rb");
+	if (!file_o) {
+		rte_errno = ENOTSUP;
+		return -ENOTSUP;
+	}
+	ret = fscanf(file_o, "%d", &enable);
+	if (ret != 1) {
+		rte_errno = EINVAL;
+		ret = EINVAL;
+		goto close;
+	} else if (!enable) {
+		ret = 0;
+		DRV_LOG(INFO, "ROCE has already disabled(sysfs).");
+		goto close;
+	}
+	fclose(file_o);
+	file_o = fopen(file_p, "wb");
+	if (!file_o) {
+		rte_errno = ENOTSUP;
+		return -ENOTSUP;
+	}
+	fprintf(file_o, "0\n");
+	ret = 0;
+close:
+	if (ret)
+		DRV_LOG(DEBUG, "Failed to disable ROCE by sysfs: %d.", ret);
+	else
+		DRV_LOG(INFO, "ROCE is disabled by sysfs successfully.");
+	fclose(file_o);
+	return ret;
+}
+
+static int
+mlx5_roce_disable(const struct rte_device *dev)
+{
+	char pci_addr[PCI_PRI_STR_SIZE] = { 0 };
+
+	if (mlx5_dev_to_pci_str(dev, pci_addr, sizeof(pci_addr)) < 0)
+		return -rte_errno;
+	/* Firstly try to disable ROCE by Netlink and fallback to sysfs. */
+	if (mlx5_nl_roce_disable(pci_addr) != 0 &&
+	    mlx5_sys_roce_disable(pci_addr) != 0)
+		return -rte_errno;
+	return 0;
+}
+
+static struct ibv_device *
+mlx5_os_get_ibv_dev(const struct rte_device *dev)
+{
+	struct ibv_device *ibv;
+
+	if (mlx5_dev_is_pci(dev))
+		ibv = mlx5_os_get_ibv_device(&RTE_DEV_TO_PCI_CONST(dev)->addr);
+	else
+		ibv = mlx5_get_aux_ibv_device(RTE_DEV_TO_AUXILIARY_CONST(dev));
+	if (ibv == NULL) {
+		rte_errno = ENODEV;
+		DRV_LOG(ERR, "Verbs device not found: %s", dev->name);
+	}
+	return ibv;
+}
+
+static struct ibv_device *
+mlx5_vdpa_get_ibv_dev(const struct rte_device *dev)
+{
+	struct ibv_device *ibv;
+	int retry;
+
+	if (mlx5_roce_disable(dev) != 0) {
+		DRV_LOG(WARNING, "Failed to disable ROCE for \"%s\".",
+			dev->name);
+		return NULL;
+	}
+	/* Wait for the IB device to appear again after reload. */
+	for (retry = MLX5_VDPA_MAX_RETRIES; retry > 0; --retry) {
+		ibv = mlx5_os_get_ibv_dev(dev);
+		if (ibv != NULL)
+			return ibv;
+		usleep(MLX5_VDPA_USEC);
+	}
+	DRV_LOG(ERR,
+		"Cannot get IB device after disabling RoCE for \"%s\", retries exceed %d.",
+		dev->name, MLX5_VDPA_MAX_RETRIES);
+	rte_errno = EAGAIN;
+	return NULL;
+}
+
 static int
 mlx5_config_doorbell_mapping_env(int dbnc)
 {

@@ -483,7 +620,10 @@ mlx5_os_open_device(struct mlx5_common_device *cdev, uint32_t classes)
 	struct ibv_context *ctx = NULL;
 	int dbmap_env;
 
-	ibv = mlx5_os_get_ibv_dev(cdev->dev);
+	if (classes & MLX5_CLASS_VDPA)
+		ibv = mlx5_vdpa_get_ibv_dev(cdev->dev);
+	else
+		ibv = mlx5_os_get_ibv_dev(cdev->dev);
 	if (!ibv)
 		return -rte_errno;
 	DRV_LOG(INFO, "Dev information matches for device \"%s\".", ibv->name);

index 05c8ae1ba5..0e605c3a9e 100644
@@ -289,13 +289,6 @@ mlx5_os_free(void *addr)
 	free(addr);
 }
 
-struct ibv_device *
-mlx5_os_get_ibv_device(const struct rte_pci_addr *addr);
-
-__rte_internal
-struct ibv_device *
-mlx5_os_get_ibv_dev(const struct rte_device *dev);
-
 void
 mlx5_set_context_attr(struct rte_device *dev, struct ibv_context *ctx);
 

index e5a1244867..519cb8d056 100644
@@ -11,35 +11,16 @@
 #include <inttypes.h>
 
 #include <rte_errno.h>
-#include <rte_bus_pci.h>
 #include <rte_eal_paging.h>
-#include <rte_bus_auxiliary.h>
 
 #include "mlx5_common_utils.h"
 #include "mlx5_common_log.h"
-#include "mlx5_common_private.h"
 #include "mlx5_autoconf.h"
 #include <mlx5_glue.h>
 #include <mlx5_malloc.h>
 #include <mlx5_common.h>
 #include <mlx5_common_mr.h>
 
-struct ibv_device *
-mlx5_os_get_ibv_dev(const struct rte_device *dev)
-{
-	struct ibv_device *ibv;
-
-	if (mlx5_dev_is_pci(dev))
-		ibv = mlx5_os_get_ibv_device(&RTE_DEV_TO_PCI_CONST(dev)->addr);
-	else
-		ibv = mlx5_get_aux_ibv_device(RTE_DEV_TO_AUXILIARY_CONST(dev));
-	if (ibv == NULL) {
-		rte_errno = ENODEV;
-		DRV_LOG(ERR, "Verbs device not found: %s", dev->name);
-	}
-	return ibv;
-}
-
 /**
  * Verbs callback to allocate a memory. This function should allocate the space
  * according to the size provided residing inside a huge page.

index 9120a697fd..530d491b66 100644
@@ -1700,7 +1700,7 @@ mlx5_nl_enable_roce_get(int nlsk_fd, int family_id, const char *pci_addr,
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-int
+static int
 mlx5_nl_driver_reload(int nlsk_fd, int family_id, const char *pci_addr)
 {
 	struct nlmsghdr *nlh;

index 15129ffdc8..202849f52a 100644
@@ -66,14 +66,10 @@ void mlx5_nl_vlan_vmwa_delete(struct mlx5_nl_vlan_vmwa_context *vmwa,
 __rte_internal
 uint32_t mlx5_nl_vlan_vmwa_create(struct mlx5_nl_vlan_vmwa_context *vmwa,
 				  uint32_t ifindex, uint16_t tag);
-__rte_internal
+
 int mlx5_nl_devlink_family_id_get(int nlsk_fd);
-__rte_internal
 int mlx5_nl_enable_roce_get(int nlsk_fd, int family_id, const char *pci_addr,
 			    int *enable);
-__rte_internal
-int mlx5_nl_driver_reload(int nlsk_fd, int family_id, const char *pci_addr);
-__rte_internal
 int mlx5_nl_enable_roce_set(int nlsk_fd, int family_id, const char *pci_addr,
 			    int enable);
 

index d7d9e43a4d..066860045a 100644
@@ -218,7 +218,6 @@ check_cqe(volatile struct mlx5_cqe *cqe, const uint16_t cqes_n,
  *   - 0 on success.
  *   - Negative value and rte_errno is set otherwise.
  */
-__rte_internal
 int mlx5_dev_to_pci_str(const struct rte_device *dev, char *addr, size_t size);
 
 /*

index 6fd30f2c97..8f43b8e8ad 100644
@@ -39,4 +39,7 @@
 #define MLX5_TXDB_NCACHED 1
 #define MLX5_TXDB_HEURISTIC 2
 
+#define MLX5_VDPA_MAX_RETRIES 20
+#define MLX5_VDPA_USEC 1000
+
 #endif /* RTE_PMD_MLX5_COMMON_DEFS_H_ */

224 lines not on this page · raw message

index 2a04e36607..830592ed5c 100644
@@ -131,8 +131,8 @@ struct mlx5_vdpa_priv {
 	uint16_t hw_max_latency_us; /* Hardware CQ moderation period in usec. */
 	uint16_t hw_max_pending_comp; /* Hardware CQ moderation counter. */
 	struct rte_vdpa_device *vdev; /* vDPA device. */
+	struct mlx5_common_device *cdev; /* Backend mlx5 device. */
 	int vid; /* vhost device id. */
-	struct ibv_context *ctx; /* Device context. */
 	struct mlx5_hca_vdpa_attr caps;
 	uint32_t pdn; /* Protection Domain number. */
 	struct ibv_pd *pd;

index 3541c652ce..118a147eac 100644
@@ -48,7 +48,7 @@ mlx5_vdpa_event_qp_global_prepare(struct mlx5_vdpa_priv *priv)
 {
 	if (priv->eventc)
 		return 0;
-	priv->eventc = mlx5_os_devx_create_event_channel(priv->ctx,
+	priv->eventc = mlx5_os_devx_create_event_channel(priv->cdev->ctx,
 			   MLX5DV_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA);
 	if (!priv->eventc) {
 		rte_errno = errno;

@@ -61,7 +61,7 @@ mlx5_vdpa_event_qp_global_prepare(struct mlx5_vdpa_priv *priv)
 	 * registers writings, it is safe to allocate UAR with any
 	 * memory mapping type.
 	 */
-	priv->uar = mlx5_devx_alloc_uar(priv->ctx, -1);
+	priv->uar = mlx5_devx_alloc_uar(priv->cdev->ctx, -1);
 	if (!priv->uar) {
 		rte_errno = errno;
 		DRV_LOG(ERR, "Failed to allocate UAR.");

@@ -115,8 +115,8 @@ mlx5_vdpa_cq_create(struct mlx5_vdpa_priv *priv, uint16_t log_desc_n,
 	uint16_t event_nums[1] = {0};
 	int ret;
 
-	ret = mlx5_devx_cq_create(priv->ctx, &cq->cq_obj, log_desc_n, &attr,
-				  SOCKET_ID_ANY);
+	ret = mlx5_devx_cq_create(priv->cdev->ctx, &cq->cq_obj, log_desc_n,
+				  &attr, SOCKET_ID_ANY);
 	if (ret)
 		goto error;
 	cq->cq_ci = 0;

@@ -397,7 +397,8 @@ mlx5_vdpa_err_event_setup(struct mlx5_vdpa_priv *priv)
 	int flags;
 
 	/* Setup device event channel. */
-	priv->err_chnl = mlx5_glue->devx_create_event_channel(priv->ctx, 0);
+	priv->err_chnl = mlx5_glue->devx_create_event_channel(priv->cdev->ctx,
+							      0);
 	if (!priv->err_chnl) {
 		rte_errno = errno;
 		DRV_LOG(ERR, "Failed to create device event channel %d.",

@@ -600,7 +601,7 @@ mlx5_vdpa_event_qp_create(struct mlx5_vdpa_priv *priv, uint16_t desc_n,
 		return -1;
 	attr.pd = priv->pdn;
 	attr.ts_format = mlx5_ts_format_conv(priv->qp_ts_format);
-	eqp->fw_qp = mlx5_devx_cmd_create_qp(priv->ctx, &attr);
+	eqp->fw_qp = mlx5_devx_cmd_create_qp(priv->cdev->ctx, &attr);
 	if (!eqp->fw_qp) {
 		DRV_LOG(ERR, "Failed to create FW QP(%u).", rte_errno);
 		goto error;

@@ -611,7 +612,7 @@ mlx5_vdpa_event_qp_create(struct mlx5_vdpa_priv *priv, uint16_t desc_n,
 		rte_errno = ENOMEM;
 		goto error;
 	}
-	eqp->umem_obj = mlx5_glue->devx_umem_reg(priv->ctx,
+	eqp->umem_obj = mlx5_glue->devx_umem_reg(priv->cdev->ctx,
 					       (void *)(uintptr_t)eqp->umem_buf,
 					       umem_size,
 					       IBV_ACCESS_LOCAL_WRITE);

@@ -631,7 +632,7 @@ mlx5_vdpa_event_qp_create(struct mlx5_vdpa_priv *priv, uint16_t desc_n,
 	attr.dbr_umem_id = eqp->umem_obj->umem_id;
 	attr.ts_format = mlx5_ts_format_conv(priv->qp_ts_format);
 	attr.dbr_address = RTE_BIT64(log_desc_n) * MLX5_WSEG_SIZE;
-	eqp->sw_qp = mlx5_devx_cmd_create_qp(priv->ctx, &attr);
+	eqp->sw_qp = mlx5_devx_cmd_create_qp(priv->cdev->ctx, &attr);
 	if (!eqp->sw_qp) {
 		DRV_LOG(ERR, "Failed to create SW QP(%u).", rte_errno);
 		goto error;

index f391813745..0b0ffeb07d 100644
@@ -54,7 +54,7 @@ mlx5_vdpa_dirty_bitmap_set(struct mlx5_vdpa_priv *priv, uint64_t log_base,
 		DRV_LOG(ERR, "Failed to allocate mem for lm mr.");
 		return -1;
 	}
-	mr->umem = mlx5_glue->devx_umem_reg(priv->ctx,
+	mr->umem = mlx5_glue->devx_umem_reg(priv->cdev->ctx,
 					    (void *)(uintptr_t)log_base,
 					    log_size, IBV_ACCESS_LOCAL_WRITE);
 	if (!mr->umem) {

@@ -62,7 +62,7 @@ mlx5_vdpa_dirty_bitmap_set(struct mlx5_vdpa_priv *priv, uint64_t log_base,
 		goto err;
 	}
 	mkey_attr.umem_id = mr->umem->umem_id;
-	mr->mkey = mlx5_devx_cmd_mkey_create(priv->ctx, &mkey_attr);
+	mr->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
 	if (!mr->mkey) {
 		DRV_LOG(ERR, "Failed to create Mkey for lm.");
 		goto err;

index a06681b494..c5cdb3abd7 100644
@@ -209,7 +209,7 @@ mlx5_vdpa_mem_register(struct mlx5_vdpa_priv *priv)
 			DRV_LOG(ERR, "Failed to allocate mem entry memory.");
 			goto error;
 		}
-		entry->umem = mlx5_glue->devx_umem_reg(priv->ctx,
+		entry->umem = mlx5_glue->devx_umem_reg(priv->cdev->ctx,
 					 (void *)(uintptr_t)reg->host_user_addr,
 					     reg->size, IBV_ACCESS_LOCAL_WRITE);
 		if (!entry->umem) {

@@ -222,7 +222,8 @@ mlx5_vdpa_mem_register(struct mlx5_vdpa_priv *priv)
 		mkey_attr.umem_id = entry->umem->umem_id;
 		mkey_attr.pd = priv->pdn;
 		mkey_attr.pg_access = 1;
-		entry->mkey = mlx5_devx_cmd_mkey_create(priv->ctx, &mkey_attr);
+		entry->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx,
+							&mkey_attr);
 		if (!entry->mkey) {
 			DRV_LOG(ERR, "Failed to create direct Mkey.");
 			ret = -rte_errno;

@@ -281,7 +282,7 @@ mlx5_vdpa_mem_register(struct mlx5_vdpa_priv *priv)
 		ret = -ENOMEM;
 		goto error;
 	}
-	entry->mkey = mlx5_devx_cmd_mkey_create(priv->ctx, &mkey_attr);
+	entry->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
 	if (!entry->mkey) {
 		DRV_LOG(ERR, "Failed to create indirect Mkey.");
 		ret = -rte_errno;

index 383f003966..a0fd2776e5 100644
@@ -98,7 +98,8 @@ mlx5_vdpa_rqt_prepare(struct mlx5_vdpa_priv *priv)
 	attr->rqt_max_size = rqt_n;
 	attr->rqt_actual_size = rqt_n;
 	if (!priv->steer.rqt) {
-		priv->steer.rqt = mlx5_devx_cmd_create_rqt(priv->ctx, attr);
+		priv->steer.rqt = mlx5_devx_cmd_create_rqt(priv->cdev->ctx,
+							   attr);
 		if (!priv->steer.rqt) {
 			DRV_LOG(ERR, "Failed to create RQT.");
 			ret = -rte_errno;

@@ -204,13 +205,13 @@ mlx5_vdpa_rss_flows_create(struct mlx5_vdpa_priv *priv)
 		tir_att.rx_hash_field_selector_outer.selected_fields =
 								  vars[i][HASH];
 		priv->steer.rss[i].matcher = mlx5_glue->dv_create_flow_matcher
-					 (priv->ctx, &dv_attr, priv->steer.tbl);
+				   (priv->cdev->ctx, &dv_attr, priv->steer.tbl);
 		if (!priv->steer.rss[i].matcher) {
 			DRV_LOG(ERR, "Failed to create matcher %d.", i);
 			goto error;
 		}
-		priv->steer.rss[i].tir = mlx5_devx_cmd_create_tir(priv->ctx,
-								  &tir_att);
+		priv->steer.rss[i].tir = mlx5_devx_cmd_create_tir
+						    (priv->cdev->ctx, &tir_att);
 		if (!priv->steer.rss[i].tir) {
 			DRV_LOG(ERR, "Failed to create TIR %d.", i);
 			goto error;

@@ -268,7 +269,7 @@ int
 mlx5_vdpa_steer_setup(struct mlx5_vdpa_priv *priv)
 {
 #ifdef HAVE_MLX5DV_DR
-	priv->steer.domain = mlx5_glue->dr_create_domain(priv->ctx,
+	priv->steer.domain = mlx5_glue->dr_create_domain(priv->cdev->ctx,
 						  MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
 	if (!priv->steer.domain) {
 		DRV_LOG(ERR, "Failed to create Rx domain.");