common/mlx5: use new port query API if available

[ upstream commit d0cf77e ]

In order to get E-Switch vport identifiers the mlx5 PMD relies
on two approaches:
  [a] use port query API if it is provided by rdma-core library
  [b] otherwise, deduce vport ids from the related VF index
The latter is not reliable and may not work with newer kernel
drivers and in some configurations (LAG), causing E-Switch
malfunction. Hence, engaging the port query API is highly
desirable.

Depending on rdma-core version the port query API is:
  - very old OFED versions have no query API (approach [b])
  - rdma-core OFED < 5.5 provides mlx5dv_query_devx_port,
    HAVE_MLX5DV_DR_DEVX_PORT flag is defined (approach [a])
  - rdma-core OFED >= 5.5 has mlx5dv_query_port, flag
    HAVE_MLX5DV_DR_DEVX_PORT_V35 is defined (approach [a])
  - future OFED versions might remove mlx5dv_query_devx_port
    and HAVE_MLX5DV_DR_DEVX_PORT will not be defined
  - Upstream rdma-core < v35 has no port query API (approach [b])
  - Upstream rdma-core >= v35 has  mlx5dv_query_port, flag
    HAVE_MLX5DV_DR_DEVX_PORT_V35 is defined (approach [a])

In order to support the new mlx5dv_query_port routine, the
conditional compilation flag HAVE_MLX5DV_DR_DEVX_PORT_V35
is introduced by this patch. The flag HAVE_MLX5DV_DR_DEVX_PORT
is kept for compatibility with previous rdma-core versions.

Despite this patch is not a bugfix (it follows the introduced API
variation in underlying library), it resolves the compatibility
issue and is highly desired to be ported to DPDK LTS.

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>

drivers/common/mlx5/linux/meson.build

@@ -94,6 +94,8 @@ has_sym_args = [
 	'IBV_WQ_FLAG_RX_END_PADDING' ],
 	[ 'HAVE_MLX5DV_DR_DEVX_PORT', 'infiniband/mlx5dv.h',
 	'mlx5dv_query_devx_port' ],
+	[ 'HAVE_MLX5DV_DR_DEVX_PORT_V35', 'infiniband/mlx5dv.h',
+	'mlx5dv_query_port' ],
 	[ 'HAVE_IBV_DEVX_OBJ', 'infiniband/mlx5dv.h',
 	'mlx5dv_devx_obj_create' ],
 	[ 'HAVE_IBV_FLOW_DEVX_COUNTERS', 'infiniband/mlx5dv.h',

drivers/common/mlx5/linux/mlx5_glue.c

@@ -1087,17 +1087,54 @@ mlx5_glue_devx_wq_query(struct ibv_wq *wq, const void *in, size_t inlen,
 static int
 mlx5_glue_devx_port_query(struct ibv_context *ctx,
 			  uint32_t port_num,
-			  struct mlx5dv_devx_port *mlx5_devx_port)
-{
+			  struct mlx5_port_info *info)
+{
+	int err = 0;
+
+	info->query_flags = 0;
+#ifdef HAVE_MLX5DV_DR_DEVX_PORT_V35
+	/* The DevX port query API is implemented (rdma-core v35 and above). */
+	struct mlx5_ib_uapi_query_port devx_port;
+
+	memset(&devx_port, 0, sizeof(devx_port));
+	err = mlx5dv_query_port(ctx, port_num, &devx_port);
+	if (err)
+		return err;
+	if (devx_port.flags & MLX5DV_QUERY_PORT_VPORT_REG_C0) {
+		info->vport_meta_tag = devx_port.reg_c0.value;
+		info->vport_meta_mask = devx_port.reg_c0.mask;
+		info->query_flags |= MLX5_PORT_QUERY_REG_C0;
+	}
+	if (devx_port.flags & MLX5DV_QUERY_PORT_VPORT) {
+		info->vport_id = devx_port.vport;
+		info->query_flags |= MLX5_PORT_QUERY_VPORT;
+	}
+#else
 #ifdef HAVE_MLX5DV_DR_DEVX_PORT
-	return mlx5dv_query_devx_port(ctx, port_num, mlx5_devx_port);
+	/* The legacy DevX port query API is implemented (prior v35). */
+	struct mlx5dv_devx_port devx_port = {
+		.comp_mask = MLX5DV_DEVX_PORT_VPORT |
+			     MLX5DV_DEVX_PORT_MATCH_REG_C_0
+	};
+
+	err = mlx5dv_query_devx_port(ctx, port_num, &devx_port);
+	if (err)
+		return err;
+	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_MATCH_REG_C_0) {
+		info->vport_meta_tag = devx_port.reg_c_0.value;
+		info->vport_meta_mask = devx_port.reg_c_0.mask;
+		info->query_flags |= MLX5_PORT_QUERY_REG_C0;
+	}
+	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) {
+		info->vport_id = devx_port.vport_num;
+		info->query_flags |= MLX5_PORT_QUERY_VPORT;
+	}
 #else
-	(void)ctx;
-	(void)port_num;
-	(void)mlx5_devx_port;
-	errno = ENOTSUP;
-	return errno;
-#endif
+	RTE_SET_USED(ctx);
+	RTE_SET_USED(port_num);
+#endif /* HAVE_MLX5DV_DR_DEVX_PORT */
+#endif /* HAVE_MLX5DV_DR_DEVX_PORT_V35 */
+	return err;
 }
 
 static int

drivers/common/mlx5/linux/mlx5_glue.h

@@ -84,6 +84,20 @@ struct mlx5dv_dr_action;
 struct mlx5dv_devx_port;
 #endif
 
+#ifndef HAVE_MLX5DV_DR_DEVX_PORT_V35
+struct mlx5dv_port;
+#endif
+
+#define MLX5_PORT_QUERY_VPORT (1u << 0)
+#define MLX5_PORT_QUERY_REG_C0 (1u << 1)
+
+struct mlx5_port_info {
+	uint16_t query_flags;
+	uint16_t vport_id; /* Associated VF vport index (if any). */
+	uint32_t vport_meta_tag; /* Used for vport index match ove VF LAG. */
+	uint32_t vport_meta_mask; /* Used for vport index field match mask. */
+};
+
 #ifndef HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER
 struct mlx5dv_dr_flow_meter_attr;
 #endif
@@ -311,7 +325,7 @@ struct mlx5_glue {
 			     void *out, size_t outlen);
 	int (*devx_port_query)(struct ibv_context *ctx,
 			       uint32_t port_num,
-			       struct mlx5dv_devx_port *mlx5_devx_port);
+			       struct mlx5_port_info *info);
 	int (*dr_dump_domain)(FILE *file, void *domain);
 	int (*devx_query_eqn)(struct ibv_context *context, uint32_t cpus,
 			      uint32_t *eqn);

drivers/net/mlx5/linux/mlx5_os.c

@@ -695,9 +695,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	int own_domain_id = 0;
 	uint16_t port_id;
 	unsigned int i;
-#ifdef HAVE_MLX5DV_DR_DEVX_PORT
-	struct mlx5dv_devx_port devx_port = { .comp_mask = 0 };
-#endif
+	struct mlx5_port_info vport_info = { .query_flags = 0 };
 
 	/* Determine if this port representor is supposed to be spawned. */
 	if (switch_info->representor && dpdk_dev->devargs) {
@@ -940,29 +938,27 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	priv->vport_meta_tag = 0;
 	priv->vport_meta_mask = 0;
 	priv->pf_bond = spawn->pf_bond;
-#ifdef HAVE_MLX5DV_DR_DEVX_PORT
 	/*
-	 * The DevX port query API is implemented. E-Switch may use
-	 * either vport or reg_c[0] metadata register to match on
-	 * vport index. The engaged part of metadata register is
-	 * defined by mask.
+	 * If we have E-Switch we should determine the vport attributes.
+	 * E-Switch may use either source vport field or reg_c[0] metadata
+	 * register to match on vport index. The engaged part of metadata
+	 * register is defined by mask.
 	 */
 	if (switch_info->representor || switch_info->master) {
-		devx_port.comp_mask = MLX5DV_DEVX_PORT_VPORT |
-				      MLX5DV_DEVX_PORT_MATCH_REG_C_0;
-		err = mlx5_glue->devx_port_query(sh->ctx, spawn->phys_port,
-						 &devx_port);
+		err = mlx5_glue->devx_port_query(sh->ctx,
+						 spawn->phys_port,
+						 &vport_info);
 		if (err) {
 			DRV_LOG(WARNING,
 				"can't query devx port %d on device %s",
 				spawn->phys_port,
 				mlx5_os_get_dev_device_name(spawn->phys_dev));
-			devx_port.comp_mask = 0;
+			vport_info.query_flags = 0;
 		}
 	}
-	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_MATCH_REG_C_0) {
-		priv->vport_meta_tag = devx_port.reg_c_0.value;
-		priv->vport_meta_mask = devx_port.reg_c_0.mask;
+	if (vport_info.query_flags & MLX5_PORT_QUERY_REG_C0) {
+		priv->vport_meta_tag = vport_info.vport_meta_tag;
+		priv->vport_meta_mask = vport_info.vport_meta_mask;
 		if (!priv->vport_meta_mask) {
 			DRV_LOG(ERR, "vport zero mask for port %d"
 				     " on bonding device %s",
@@ -982,8 +978,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 			goto error;
 		}
 	}
-	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) {
-		priv->vport_id = devx_port.vport_num;
+	if (vport_info.query_flags & MLX5_PORT_QUERY_VPORT) {
+		priv->vport_id = vport_info.vport_id;
 	} else if (spawn->pf_bond >= 0 &&
 		   (switch_info->representor || switch_info->master)) {
 		DRV_LOG(ERR, "can't deduce vport index for port %d"
@@ -993,25 +989,21 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 		err = ENOTSUP;
 		goto error;
 	} else {
-		/* Suppose vport index in compatible way. */
+		/*
+		 * Suppose vport index in compatible way. Kernel/rdma_core
+		 * support single E-Switch per PF configurations only and
+		 * vport_id field contains the vport index for associated VF,
+		 * which is deduced from representor port name.
+		 * For example, let's have the IB device port 10, it has
+		 * attached network device eth0, which has port name attribute
+		 * pf0vf2, we can deduce the VF number as 2, and set vport index
+		 * as 3 (2+1). This assigning schema should be changed if the
+		 * multiple E-Switch instances per PF configurations or/and PCI
+		 * subfunctions are added.
+		 */
 		priv->vport_id = switch_info->representor ?
 				 switch_info->port_name + 1 : -1;
 	}
-#else
-	/*
-	 * Kernel/rdma_core support single E-Switch per PF configurations
-	 * only and vport_id field contains the vport index for
-	 * associated VF, which is deduced from representor port name.
-	 * For example, let's have the IB device port 10, it has
-	 * attached network device eth0, which has port name attribute
-	 * pf0vf2, we can deduce the VF number as 2, and set vport index
-	 * as 3 (2+1). This assigning schema should be changed if the
-	 * multiple E-Switch instances per PF configurations or/and PCI
-	 * subfunctions are added.
-	 */
-	priv->vport_id = switch_info->representor ?
-			 switch_info->port_name + 1 : -1;
-#endif
 	/* representor_id field keeps the unmodified VF index. */
 	priv->representor_id = switch_info->representor ?
 			       switch_info->port_name : -1;