[PATCH 19.11] net/mlx5: fix port event cleaning order

[Christian Ehrhardt]

On Wed, Nov 16, 2022 at 1:13 PM Michael Baum <michaelba at nvidia.com> wrote:
>
> [ upstream commit 7ba5320baa3285bf8beca96cc025ff56b494060d ]

Applied, thanks!

> The shared IB device (sh) has per port data with filed for interrupt
> handler port_id. It used by shared interrupt handler to find the
> corresponding rte_eth device by IB port index.
> If value is equal or greater RTE_MAX_ETHPORTS it means there is no
> subhandler installed for specified IB port index.
>
> When a few ports are created under same sh, the sh is created with the
> first port and the interrupt handler port_id is initialized to
> RTE_MAX_ETHPORTS for each port.
> In port creation, the interrupt handler port_id is updated with the
> correct value. Since this updating, the mlx5_dev_interrupt_nl_cb
> function uses this port and its priv structure.
> However, when the ports are closed, this filed isn't updated and the
> interrupt handler continue working until it is uninstalled in SH
> destruction.
> If mlx5_dev_interrupt_nl_cb is called between port closing and SH
> destruction, it uses invalid port causing a crash.
>
> This patch adds interrupt handler port_id updating to the close function
> and add memory barrier to make sure it is done before priv reset.
>
> Fixes: 0906b984ff1f ("net/mlx5: fix initial link status detection")
>
> Signed-off-by: Michael Baum <michaelba at nvidia.com>
> Acked-by: Matan Azrad <matan at nvidia.com>
> ---
>  drivers/net/mlx5/mlx5.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
>
> diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
> index dee018bbba..ae3ba1885e 100644
> --- a/drivers/net/mlx5/mlx5.c
> +++ b/drivers/net/mlx5/mlx5.c
> @@ -1458,6 +1458,12 @@ mlx5_dev_close(struct rte_eth_dev *dev)
>                 if (!c)
>                         claim_zero(rte_eth_switch_domain_free(priv->domain_id));
>         }
> +       priv->sh->port[priv->ibv_port - 1].nl_ih_port_id = RTE_MAX_ETHPORTS;
> +       /*
> +        * The interrupt handler port id must be reset before priv is reset
> +        * since 'mlx5_dev_interrupt_nl_cb' uses priv.
> +        */
> +       rte_io_wmb();
>         memset(priv, 0, sizeof(*priv));
>         priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
>         /*
> @@ -2883,6 +2889,9 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
>         return eth_dev;
>  error:
>         if (priv) {
> +               priv->sh->port[priv->ibv_port - 1].nl_ih_port_id =
> +                                                              RTE_MAX_ETHPORTS;
> +               rte_io_wmb();
>                 if (priv->mreg_cp_tbl)
>                         mlx5_hlist_destroy(priv->mreg_cp_tbl, NULL, NULL);
>                 if (priv->sh)
> --
> 2.25.1
>


-- 
Christian Ehrhardt
Senior Staff Engineer, Ubuntu Server
Canonical Ltd