[dpdk-dev] [PATCH v2 13/15] net/mlx5: setup RSS flow regardless of queue count
Xueming(Steven) Li
xuemingl at mellanox.com
Wed Apr 11 15:01:13 CEST 2018
Hi Nelio,
> -----Original Message-----
> From: Nélio Laranjeiro <nelio.laranjeiro at 6wind.com>
> Sent: Wednesday, April 11, 2018 8:37 PM
> To: Xueming(Steven) Li <xuemingl at mellanox.com>
> Cc: Shahaf Shuler <shahafs at mellanox.com>; dev at dpdk.org
> Subject: Re: [PATCH v2 13/15] net/mlx5: setup RSS flow regardless of queue
> count
>
> On Tue, Apr 10, 2018 at 09:34:13PM +0800, Xueming Li wrote:
> > In some environments it is desirable to have the NIC perform RSS
> > normally on the packet regardless of the number of queues configured.
> > The RSS hash result that is stored in the mbuf can then be used by the
> > application to make decisions about how to distribute workloads to
> > threads, secondary processes, or even virtual machines if the
> > application is a virtual switch.
> >
> > Signed-off-by: Xueming Li <xuemingl at mellanox.com>
> > ---
> > drivers/net/mlx5/mlx5_flow.c | 71
> > +++++++++++++++++++-------------------------
> > 1 file changed, 30 insertions(+), 41 deletions(-)
> >
> > diff --git a/drivers/net/mlx5/mlx5_flow.c
> > b/drivers/net/mlx5/mlx5_flow.c index 5784f2ee0..9efe00086 100644
> > --- a/drivers/net/mlx5/mlx5_flow.c
> > +++ b/drivers/net/mlx5/mlx5_flow.c
> > @@ -1252,48 +1252,37 @@ mlx5_flow_convert_rss(struct rte_eth_dev *dev,
> struct mlx5_flow_parse *parser)
> > parser->queue[i].ibv_attr = NULL;
> > }
> > }
> > - if (parser->rss_conf.types) {
> > - /* Remove impossible flow according to the RSS configuration.
> */
> > - for (i = hmin; i != (hmax + 1); ++i) {
> > - if (!parser->queue[i].ibv_attr)
> > - continue;
> > - if (parser->rss_conf.types &
> > - hash_rxq_init[i].dpdk_rss_hf) {
> > - parser->queue[i].hash_fields =
> > - hash_rxq_init[i].hash_fields;
> > - found = 1;
> > - continue;
> > - }
> > - /* L4 flow could be used for L3 RSS. */
> > - if (i == parser->layer && i < ip &&
> > - (hash_rxq_init[ip].dpdk_rss_hf &
> > - parser->rss_conf.types)) {
> > - parser->queue[i].hash_fields =
> > - hash_rxq_init[ip].hash_fields;
> > - found = 1;
> > - continue;
> > - }
> > - /* L3 flow and L4 hash: non-rss L3 flow. */
> > - if (i == parser->layer && i == ip && found)
> > - /* IP pattern and L4 HF. */
> > - continue;
> > - rte_free(parser->queue[i].ibv_attr);
> > - parser->queue[i].ibv_attr = NULL;
> > + /* Remove impossible flow according to the RSS configuration. */
> > + for (i = hmin; i != (hmax + 1); ++i) {
> > + if (!parser->queue[i].ibv_attr)
> > + continue;
> > + if (parser->rss_conf.types &
> > + hash_rxq_init[i].dpdk_rss_hf) {
> > + parser->queue[i].hash_fields =
> > + hash_rxq_init[i].hash_fields;
> > + found = 1;
> > + continue;
> > }
> > - if (!found)
> > - DRV_LOG(WARNING,
> > - "port %u rss hash function doesn't match "
> > - "pattern", dev->data->port_id);
> > - } else {
> > - /* Remove any other flow. */
> > - for (i = hmin; i != (hmax + 1); ++i) {
> > - if (i == parser->layer || !parser->queue[i].ibv_attr)
> > - continue;
> > - rte_free(parser->queue[i].ibv_attr);
> > - parser->queue[i].ibv_attr = NULL;
> > + /* L4 flow could be used for L3 RSS. */
> > + if (i == parser->layer && i < ip &&
> > + (hash_rxq_init[ip].dpdk_rss_hf &
> > + parser->rss_conf.types)) {
> > + parser->queue[i].hash_fields =
> > + hash_rxq_init[ip].hash_fields;
> > + found = 1;
> > + continue;
> > }
> > - parser->rss_conf.queue_num = 1;
> > + /* L3 flow and L4 hash: non-rss L3 flow. */
> > + if (i == parser->layer && i == ip && found)
> > + /* IP pattern and L4 HF. */
> > + continue;
> > + rte_free(parser->queue[i].ibv_attr);
> > + parser->queue[i].ibv_attr = NULL;
> > }
> > + if (!found)
> > + DRV_LOG(WARNING,
> > + "port %u rss hash function doesn't match "
> > + "pattern", dev->data->port_id);
> > return 0;
> > }
> >
> > @@ -2326,8 +2315,8 @@ mlx5_flow_dump(struct rte_eth_dev *dev
> __rte_unused,
> > (void *)flow->frxq[i].hrxq->ind_table,
> > flow->frxq[i].hash_fields |
> > (flow->tunnel &&
> > - flow->rss_conf.rss_level ? (uint32_t)IBV_RX_HASH_INNER : 0),
> > - flow->queues_n,
> > + flow->rss_conf.level ? (uint32_t)IBV_RX_HASH_INNER : 0),
> > + flow->rss_conf.queue_num,
> > flow->frxq[i].ibv_attr->num_of_specs,
> > flow->frxq[i].ibv_attr->size,
> > flow->frxq[i].ibv_attr->priority,
> > --
> > 2.13.3
>
> Seems, this code should make part of
> "[PATCH v2 07/15] net/mlx5: support tunnel RSS level", as it re-works the
> code added there, in addition this feature is already present in tree for
> non tunnel packets.
>
> Any reason why it is not merged in the previous commit?
This feature is developed much later than the patch 7/15, but I think you are
right, will merge them together.
>
> Thanks,
>
> --
> Nélio Laranjeiro
> 6WIND
More information about the dev
mailing list