net/mlx5: fix memory region cache init

MR cache init takes place on the device configuration.
When the device is re-configured multiple times, for example when
changing the number of queue on the flight, deadlock can happen.

This patch moved MR cache init from device configuration function to
probe function to make sure init only once.

Fixes: 974f1e7ef146 ("net/mlx5: add new memory region support")
Signed-off-by: Xueming Li <xuemingl@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index dae8474937dc63a2cd034afa47dce8e128aaf2ec..3ef02e2d20aa2e35881c580e39ca10ab80dd415f 100644 (file)
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -1193,6 +1193,19 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
                        goto port_error;
                }
                priv->config.max_verbs_prio = verb_priorities;
+               /*
+                * Once the device is added to the list of memory event
+                * callback, its global MR cache table cannot be expanded
+                * on the fly because of deadlock. If it overflows, lookup
+                * should be done by searching MR list linearly, which is slow.
+                */
+               err = mlx5_mr_btree_init(&priv->mr.cache,
+                                        MLX5_MR_BTREE_CACHE_N * 2,
+                                        eth_dev->device->numa_node);
+               if (err) {
+                       err = rte_errno;
+                       goto port_error;
+               }
                /* Add device to memory callback list. */
                rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
                LIST_INSERT_HEAD(&mlx5_shared_data->mem_event_cb_list,

diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c
index f6cebae41d5e344681e2d3447b13ba027564dd8f..90488af33b81e70f1e5c8a184084c1984af93081 100644 (file)
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -392,17 +392,6 @@ mlx5_dev_configure(struct rte_eth_dev *dev)
                if (++j == rxqs_n)
                        j = 0;
        }
-       /*
-        * Once the device is added to the list of memory event callback, its
-        * global MR cache table cannot be expanded on the fly because of
-        * deadlock. If it overflows, lookup should be done by searching MR list
-        * linearly, which is slow.
-        */
-       if (mlx5_mr_btree_init(&priv->mr.cache, MLX5_MR_BTREE_CACHE_N * 2,
-                              dev->device->numa_node)) {
-               /* rte_errno is already set. */
-               return -rte_errno;
-       }
        return 0;
 }
 

diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
index abb1f51799fd3704ed94a864ef1923e3eb61cca8..08105a4430d7fe85f2dbaf25a1e8b74dd7f8cc6b 100644 (file)
--- a/drivers/net/mlx5/mlx5_mr.c
+++ b/drivers/net/mlx5/mlx5_mr.c
@@ -191,6 +191,7 @@ mlx5_mr_btree_init(struct mlx5_mr_btree *bt, int n, int socket)
                rte_errno = EINVAL;
                return -rte_errno;
        }
+       assert(!bt->table && !bt->size);
        memset(bt, 0, sizeof(*bt));
        bt->table = rte_calloc_socket("B-tree table",
                                      n, sizeof(struct mlx5_mr_cache),