[3/3] net/mlx5: fix initial link status detection
Checks
Commit Message
Link status change takes time that depends on the HW and the kernel.
It was checked immediately after the change was issued at probing.
If the port had beed down before probing, a "down" state may be read,
while the port would be "up" imminently.
After that, DPDK reported the port as "down" mistakenly
and "ifconfig $DEV up" did not trigger an LSC event,
because from the system's perspective the port was "up" already.
Install Netlink event handler at port probe before requesting the port
to come up in order to receive LSC event even if it comes up
between probe and start.
Fixes: b6499434b83e ("net/mlx5: fix link status initialization")
Cc: stable@dpdk.org
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Reviewed-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
drivers/net/mlx5/linux/mlx5_os.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
@@ -1645,13 +1645,10 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
/* Bring Ethernet device up. */
DRV_LOG(DEBUG, "port %u forcing Ethernet interface up",
eth_dev->data->port_id);
+ /* Watch LSC interrupts between port probe and port start. */
+ priv->sh->port[priv->dev_port - 1].nl_ih_port_id =
+ eth_dev->data->port_id;
mlx5_set_link_up(eth_dev);
- /*
- * Even though the interrupt handler is not installed yet,
- * interrupts will still trigger on the async_fd from
- * Verbs context returned by ibv_open_device().
- */
- mlx5_link_update(eth_dev, 0);
#ifdef HAVE_MLX5DV_DR_ESWITCH
if (!(config->hca_attr.eswitch_manager && config->dv_flow_en &&
(switch_info->representor || switch_info->master)))