[dpdk-dev] [PATCH v2] net/mlx5: fix flow creation on port start
Nélio Laranjeiro
nelio.laranjeiro at 6wind.com
Mon Nov 6 15:32:03 CET 2017
On Mon, Nov 06, 2017 at 04:00:25PM +0200, Shahaf Shuler wrote:
> While the PMD avoids from creating hash RXQ with no hash fields and
> array of queues after the port was allready started, it lacks such
> protection when re-creating the flows after the port restarts.
>
> This may lead to inconsist behaviour for flows depending if they were
> created before or after the port start.
>
> Fixes: 8086cf08b2f0 ("net/mlx5: handle RSS hash configuration in RSS flow")
> Cc: nelio.laranjeiro at 6wind.com
>
> Signed-off-by: Shahaf Shuler <shahafs at mellanox.com>
> ---
> On v2:
> - Fixing the issue from the hrxq_get and hrxq_new functions.
> ---
> drivers/net/mlx5/mlx5_flow.c | 4 ++--
> drivers/net/mlx5/mlx5_rxq.c | 8 ++++++--
> 2 files changed, 8 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
> index 5f49bf5ff..bcb06f84a 100644
> --- a/drivers/net/mlx5/mlx5_flow.c
> +++ b/drivers/net/mlx5/mlx5_flow.c
> @@ -1781,7 +1781,7 @@ priv_flow_create_action_queue_rss(struct priv *priv,
> parser->rss_conf.rss_key_len,
> hash_fields,
> parser->queues,
> - hash_fields ? parser->queues_n : 1);
> + parser->queues_n);
> if (flow->frxq[i].hrxq)
> continue;
> flow->frxq[i].hrxq =
> @@ -1790,7 +1790,7 @@ priv_flow_create_action_queue_rss(struct priv *priv,
> parser->rss_conf.rss_key_len,
> hash_fields,
> parser->queues,
> - hash_fields ? parser->queues_n : 1);
> + parser->queues_n);
> if (!flow->frxq[i].hrxq) {
> rte_flow_error_set(error, ENOMEM,
> RTE_FLOW_ERROR_TYPE_HANDLE,
> diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
> index a1f382b1f..18c13b3c7 100644
> --- a/drivers/net/mlx5/mlx5_rxq.c
> +++ b/drivers/net/mlx5/mlx5_rxq.c
> @@ -1265,7 +1265,8 @@ mlx5_priv_ind_table_ibv_verify(struct priv *priv)
> * @param hash_fields
> * Verbs protocol hash field to make the RSS on.
> * @param queues
> - * Queues entering in hash queue.
> + * Queues entering in hash queue. In case of empty hash_fields only the
> + * first queue index will be taken for the indirection table.
> * @param queues_n
> * Number of queues.
> *
> @@ -1280,6 +1281,7 @@ mlx5_priv_hrxq_new(struct priv *priv, uint8_t *rss_key, uint8_t rss_key_len,
> struct mlx5_ind_table_ibv *ind_tbl;
> struct ibv_qp *qp;
>
> + queues_n = hash_fields ? queues_n : 1;
> ind_tbl = mlx5_priv_ind_table_ibv_get(priv, queues, queues_n);
> if (!ind_tbl)
> ind_tbl = mlx5_priv_ind_table_ibv_new(priv, queues, queues_n);
> @@ -1332,7 +1334,8 @@ mlx5_priv_hrxq_new(struct priv *priv, uint8_t *rss_key, uint8_t rss_key_len,
> * @param rss_conf
> * RSS configuration for the Rx hash queue.
> * @param queues
> - * Queues entering in hash queue.
> + * Queues entering in hash queue. In case of empty hash_fields only the
> + * first queue index will be taken for the indirection table.
> * @param queues_n
> * Number of queues.
> *
> @@ -1345,6 +1348,7 @@ mlx5_priv_hrxq_get(struct priv *priv, uint8_t *rss_key, uint8_t rss_key_len,
> {
> struct mlx5_hrxq *hrxq;
>
> + queues_n = hash_fields ? queues_n : 1;
> LIST_FOREACH(hrxq, &priv->hrxqs, next) {
> struct mlx5_ind_table_ibv *ind_tbl;
>
> --
> 2.12.0
Acked-by: Nelio Laranjeiro <nelio.laranjeiro at 6wind.com>
--
Nélio Laranjeiro
6WIND
More information about the dev
mailing list