From: "Nélio Laranjeiro" <nelio.laranjeiro@6wind.com>
To: Shahaf Shuler <shahafs@mellanox.com>
Cc: yskoh@mellanox.com, adrien.mazarguil@6wind.com, dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] net/mlx5: fix flow creation on port start
Date: Mon, 6 Nov 2017 08:43:40 +0100 [thread overview]
Message-ID: <20171106074340.hltazlvyshmivoir@laranjeiro-vm> (raw)
In-Reply-To: <20171105154449.93962-1-shahafs@mellanox.com>
Hi Shahaf,
On Sun, Nov 05, 2017 at 05:44:49PM +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@6wind.com
>
> Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
> ---
> drivers/net/mlx5/mlx5_flow.c | 13 +++++++++----
> 1 file changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
> index 5f49bf5ff..b0a196a4b 100644
> --- a/drivers/net/mlx5/mlx5_flow.c
> +++ b/drivers/net/mlx5/mlx5_flow.c
> @@ -2290,22 +2290,27 @@ priv_flow_start(struct priv *priv, struct mlx5_flows *list)
> continue;
> }
> for (i = 0; i != hash_rxq_init_n; ++i) {
> + uint64_t hash_fields = hash_rxq_init[i].hash_fields;
> if (!flow->frxq[i].ibv_attr)
> continue;
> flow->frxq[i].hrxq =
> mlx5_priv_hrxq_get(priv, flow->rss_conf.rss_key,
> flow->rss_conf.rss_key_len,
> - hash_rxq_init[i].hash_fields,
> + hash_fields,
> (*flow->queues),
> - flow->queues_n);
> + hash_fields ?
> + flow->queues_n :
> + 1);
> if (flow->frxq[i].hrxq)
> goto flow_create;
> flow->frxq[i].hrxq =
> mlx5_priv_hrxq_new(priv, flow->rss_conf.rss_key,
> flow->rss_conf.rss_key_len,
> - hash_rxq_init[i].hash_fields,
> + hash_fields,
> (*flow->queues),
> - flow->queues_n);
> + hash_fields ?
> + flow->queues_n :
> + 1);
> if (!flow->frxq[i].hrxq) {
> DEBUG("Flow %p cannot be applied",
> (void *)flow);
> --
> 2.12.0
I would suggest to modify directly the mlx5_priv_hrxq_get() and
mlx5_priv_hrxq_new() to handle this and update the comment of both
functions, as the two places where those are called are tricking the
queue numbers the same way, it can be directly handled by the function
itself.
Thanks,
--
Nélio Laranjeiro
6WIND
next prev parent reply other threads:[~2017-11-06 7:43 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-05 15:44 Shahaf Shuler
2017-11-06 7:43 ` Nélio Laranjeiro [this message]
2017-11-06 14:00 ` [dpdk-dev] [PATCH v2] " Shahaf Shuler
2017-11-06 14:32 ` Nélio Laranjeiro
2017-11-07 5:44 ` Ferruh Yigit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171106074340.hltazlvyshmivoir@laranjeiro-vm \
--to=nelio.laranjeiro@6wind.com \
--cc=adrien.mazarguil@6wind.com \
--cc=dev@dpdk.org \
--cc=shahafs@mellanox.com \
--cc=yskoh@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).