net/mlx4: fix port attach in secondary process

Currently, the secondary process port UAR register mapping used by Tx
queue is done during port initializing.

Unluckily, in port hot-plug case, the secondary process will be
requested to initialize the port when primary process probe the port.
At that time, the port Tx queue number is still not configured, the
secondary process get Tx queue number as 0. This causes the UAR register
not be mapped as secondary process get Tx queue number 0.

This commit adds the check of Tx queue number in secondary process when
port starts is requested. Once the Tx queue number is not matching, do
UAR mapping with the latest Tx queue number.

Fixes: 0203d33a1059 ("net/mlx4: support secondary process")
Cc: stable@dpdk.org
Signed-off-by: Suanming Mou <suanmingm@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>

diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index 284dcb9..041c193 100644 (file)
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -195,7 +195,7 @@ mlx4_free_verbs_buf(void *ptr, void *data __rte_unused)
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-static int
+int
 mlx4_proc_priv_init(struct rte_eth_dev *dev)
 {
        struct mlx4_proc_priv *ppriv;
@@ -207,13 +207,13 @@ mlx4_proc_priv_init(struct rte_eth_dev *dev)
         */
        ppriv_size = sizeof(struct mlx4_proc_priv) +
                     dev->data->nb_tx_queues * sizeof(void *);
-       ppriv = rte_malloc_socket("mlx4_proc_priv", ppriv_size,
-                                 RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+       ppriv = rte_zmalloc_socket("mlx4_proc_priv", 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 = dev->data->nb_tx_queues;
        dev->process_private = ppriv;
        return 0;
 }
@@ -224,7 +224,7 @@ mlx4_proc_priv_init(struct rte_eth_dev *dev)
  * @param dev
  *   Pointer to Ethernet device structure.
  */
-static void
+void
 mlx4_proc_priv_uninit(struct rte_eth_dev *dev)
 {
        if (!dev->process_private)

diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 63df8fc..e07b1d2 100644 (file)
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -197,6 +197,10 @@ struct mlx4_priv {
 #define PORT_ID(priv) ((priv)->dev_data->port_id)
 #define ETH_DEV(priv) (&rte_eth_devices[PORT_ID(priv)])
 
+int mlx4_proc_priv_init(struct rte_eth_dev *dev);
+void mlx4_proc_priv_uninit(struct rte_eth_dev *dev);
+
+
 /* mlx4_ethdev.c */
 
 int mlx4_get_ifname(const struct mlx4_priv *priv, char (*ifname)[IF_NAMESIZE]);

diff --git a/drivers/net/mlx4/mlx4_mp.c b/drivers/net/mlx4/mlx4_mp.c
index e05da89..ddf7bdb 100644 (file)
--- a/drivers/net/mlx4/mlx4_mp.c
+++ b/drivers/net/mlx4/mlx4_mp.c
@@ -111,6 +111,9 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
        const struct mlx4_mp_param *param =
                (const struct mlx4_mp_param *)mp_msg->param;
        struct rte_eth_dev *dev;
+#ifdef HAVE_IBV_MLX4_UAR_MMAP_OFFSET
+       struct mlx4_proc_priv *ppriv;
+#endif
        int ret;
 
        MLX4_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
@@ -126,6 +129,21 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
                rte_mb();
                dev->tx_pkt_burst = mlx4_tx_burst;
                dev->rx_pkt_burst = mlx4_rx_burst;
+#ifdef HAVE_IBV_MLX4_UAR_MMAP_OFFSET
+               ppriv = (struct mlx4_proc_priv *)dev->process_private;
+               if (ppriv->uar_table_sz != dev->data->nb_tx_queues) {
+                       mlx4_tx_uar_uninit_secondary(dev);
+                       mlx4_proc_priv_uninit(dev);
+                       ret = mlx4_proc_priv_init(dev);
+                       if (ret)
+                               return -rte_errno;
+                       ret = mlx4_tx_uar_init_secondary(dev, mp_msg->fds[0]);
+                       if (ret) {
+                               mlx4_proc_priv_uninit(dev);
+                               return -rte_errno;
+                       }
+               }
+#endif
                mp_init_msg(dev, &mp_res, param->type);
                res->result = 0;
                ret = rte_mp_reply(&mp_res, peer);
@@ -163,6 +181,7 @@ mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx4_mp_req_type type)
        struct rte_mp_reply mp_rep;
        struct mlx4_mp_param *res __rte_unused;
        struct timespec ts = {.tv_sec = MLX4_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
+       struct mlx4_priv *priv;
        int ret;
        int i;
 
@@ -175,6 +194,11 @@ mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx4_mp_req_type type)
                return;
        }
        mp_init_msg(dev, &mp_req, type);
+       if (type == MLX4_MP_REQ_START_RXTX) {
+               priv = dev->data->dev_private;
+               mp_req.num_fds = 1;
+               mp_req.fds[0] = priv->ctx->cmd_fd;
+       }
        ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
        if (ret) {
                if (rte_errno != ENOTSUP)

diff --git a/drivers/net/mlx4/mlx4_rxtx.h b/drivers/net/mlx4/mlx4_rxtx.h
index 7c72ce6..c838afc 100644 (file)
--- a/drivers/net/mlx4/mlx4_rxtx.h
+++ b/drivers/net/mlx4/mlx4_rxtx.h
@@ -157,6 +157,7 @@ uint16_t mlx4_rx_burst_removed(void *dpdk_rxq, struct rte_mbuf **pkts,
 /* mlx4_txq.c */
 
 int mlx4_tx_uar_init_secondary(struct rte_eth_dev *dev, int fd);
+void mlx4_tx_uar_uninit_secondary(struct rte_eth_dev *dev);
 uint64_t mlx4_get_tx_port_offloads(struct mlx4_priv *priv);
 int mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx,
                        uint16_t desc, unsigned int socket,

diff --git a/drivers/net/mlx4/mlx4_txq.c b/drivers/net/mlx4/mlx4_txq.c
index 8262071..31ab308 100644 (file)
--- a/drivers/net/mlx4/mlx4_txq.c
+++ b/drivers/net/mlx4/mlx4_txq.c
@@ -157,6 +157,27 @@ error:
        } while (i--);
        return -rte_errno;
 }
+
+void
+mlx4_tx_uar_uninit_secondary(struct rte_eth_dev *dev)
+{
+       struct mlx4_proc_priv *ppriv =
+                       (struct mlx4_proc_priv *)dev->process_private;
+       const size_t page_size = sysconf(_SC_PAGESIZE);
+       void *addr;
+       size_t i;
+
+       if (page_size == (size_t)-1) {
+               ERROR("Failed to get mem page size");
+               return;
+       }
+       for (i = 0; i < ppriv->uar_table_sz; i++) {
+               addr = ppriv->uar_table[i];
+               if (addr)
+                       munmap(RTE_PTR_ALIGN_FLOOR(addr, page_size), page_size);
+       }
+}
+
 #else
 int
 mlx4_tx_uar_init_secondary(struct rte_eth_dev *dev __rte_unused,
@@ -167,6 +188,13 @@ mlx4_tx_uar_init_secondary(struct rte_eth_dev *dev __rte_unused,
        rte_errno = ENOTSUP;
        return -rte_errno;
 }
+
+void
+mlx4_tx_uar_uninit_secondary(struct rte_eth_dev *dev __rte_unused)
+{
+       assert(rte_eal_process_type() == RTE_PROC_SECONDARY);
+       ERROR("UAR remap is not supported");
+}
 #endif
 
 /**