net/mlx5: fix crash on secondary process port close

When secondary process starts, in rte_eth_dev_attach_secondary()
function, the secondary process port device data in struct rte_eth_dev
will be initialized to be shared with primary process port.

When failsafe sub-port hot-plug happens, both primary and secondary
process will release the sub-port, and primary process will clear the
sub-port device data in fs_dev_remove() deactivate stage first before
request secondary process to release the sub-port. In this case, the
secondary process will not be able to get the priv memory pointer from
the shared device data memory anymore, since the device data memory
has been cleared.

Since what secondary process needs in port detach is the UAR table size
to unmap the UAR addresses. It used Tx queue number as size of UAR table
in priv. In fact the uar_table_sz in struct mlx5_proc_priv means the
size of UAR register table - the number of UAR records. However, the
code set this field incorrectly to the size of mlx5_proc_priv structure.

This commit fixes UAR table size to match with relevant Tx queue number,
uses the UAR table size directly to avoid the secondary process to
access the priv pointer in the shared device data memory when unmapping
the UAR address.

Fixes: 120dc4a7dcd3 ("net/mlx5: remove device register remap")
Cc: stable@dpdk.org
Signed-off-by: Suanming Mou <suanmingm@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 50a6d2b19f33504ef12fa569147a3132048211df..93629e5b0585d511564c5c9dbeccc8fc1883ec76 100644 (file)
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -1251,13 +1251,13 @@ mlx5_proc_priv_init(struct rte_eth_dev *dev)
         */
        ppriv_size =
                sizeof(struct mlx5_proc_priv) + priv->txqs_n * sizeof(void *);
-       ppriv = mlx5_malloc(MLX5_MEM_RTE, ppriv_size, RTE_CACHE_LINE_SIZE,
-                           dev->device->numa_node);
+       ppriv = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, ppriv_size,
+                           RTE_CACHE_LINE_SIZE, dev->device->numa_node);
        if (!ppriv) {
                rte_errno = ENOMEM;
                return -rte_errno;
        }
-       ppriv->uar_table_sz = ppriv_size;
+       ppriv->uar_table_sz = priv->txqs_n;
        dev->process_private = ppriv;
        return 0;
 }

diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 5142e50858f562242dc43737edfefac494a7ae6c..15624428aae28b3923826a69a77c9b7fad16b414 100644 (file)
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -634,18 +634,23 @@ txq_uar_uninit_secondary(struct mlx5_txq_ctrl *txq_ctrl)
 void
 mlx5_tx_uar_uninit_secondary(struct rte_eth_dev *dev)
 {
-       struct mlx5_priv *priv = dev->data->dev_private;
-       struct mlx5_txq_data *txq;
-       struct mlx5_txq_ctrl *txq_ctrl;
+       struct mlx5_proc_priv *ppriv = (struct mlx5_proc_priv *)
+                                       dev->process_private;
+       const size_t page_size = rte_mem_page_size();
+       void *addr;
        unsigned int i;
 
+       if (page_size == (size_t)-1) {
+               DRV_LOG(ERR, "Failed to get mem page size");
+               return;
+       }
        MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-       for (i = 0; i != priv->txqs_n; ++i) {
-               if (!(*priv->txqs)[i])
+       for (i = 0; i != ppriv->uar_table_sz; ++i) {
+               if (!ppriv->uar_table[i])
                        continue;
-               txq = (*priv->txqs)[i];
-               txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
-               txq_uar_uninit_secondary(txq_ctrl);
+               addr = ppriv->uar_table[i];
+               rte_mem_unmap(RTE_PTR_ALIGN_FLOOR(addr, page_size), page_size);
+
        }
 }