From: "Nélio Laranjeiro" <nelio.laranjeiro@6wind.com>
To: Shahaf Shuler <shahafs@mellanox.com>
Cc: adrien.mazarguil@6wind.com, dev@dpdk.org, stable@dpdk.org
Subject: Re: [dpdk-stable] [PATCH v2 1/2] net/mlx5: fix num seg assumption on vPMD
Date: Mon, 4 Sep 2017 16:57:48 +0200 [thread overview]
Message-ID: <20170904145748.fjd3mwroy2pwwdw4@localhost> (raw)
In-Reply-To: <1e7320c4ee4162c9e509b7560be215077f43ca87.1504076528.git.shahafs@mellanox.com>
On Wed, Aug 30, 2017 at 10:07:07AM +0300, Shahaf Shuler wrote:
> vPMD Tx function assumes that after the scatter of the
> multi-segment packets the next packet will be a single segment packet.
>
> This is not current as the function can return due to lack of resources
> without sending all of the multi-segment mbufs sequence.
>
> Fixes: 6cb559d67b83 ("net/mlx5: add vectorized Rx/Tx burst for x86")
> Cc: stable@dpdk.org
>
> Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
> Acked-by: Yongseok Koh <yskoh@mellanox.com>
> ---
> This patch should be applied only after the series:
> http://dpdk.org/dev/patchwork/patch/27367/
>
> on v2:
> - different approach to fix the issue.
> ---
> drivers/net/mlx5/mlx5_rxtx_vec_sse.c | 6 ++----
> 1 file changed, 2 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.c b/drivers/net/mlx5/mlx5_rxtx_vec_sse.c
> index 37854a73b..f89762ff8 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.c
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.c
> @@ -112,8 +112,7 @@ txq_wr_dseg_v(struct txq *txq, __m128i *dseg,
> }
>
> /**
> - * Count the number of continuous single segment packets. The first packet must
> - * be a single segment packet.
> + * Count the number of continuous single segment packets.
> *
> * @param pkts
> * Pointer to array of packets.
> @@ -130,9 +129,8 @@ txq_check_multiseg(struct rte_mbuf **pkts, uint16_t pkts_n)
>
> if (!pkts_n)
> return 0;
> - assert(NB_SEGS(pkts[0]) == 1);
> /* Count the number of continuous single segment packets. */
> - for (pos = 1; pos < pkts_n; ++pos)
> + for (pos = 0; pos < pkts_n; ++pos)
> if (NB_SEGS(pkts[pos]) > 1)
> break;
> return pos;
> --
> 2.12.0
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
--
Nélio Laranjeiro
6WIND
next prev parent reply other threads:[~2017-09-04 14:57 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-23 7:33 [dpdk-stable] [PATCH " Shahaf Shuler
2017-08-23 7:33 ` [dpdk-stable] [PATCH 2/2] net/mlx5: enforce Tx num of segments limitation Shahaf Shuler
2017-08-24 13:28 ` Nélio Laranjeiro
2017-08-24 13:23 ` [dpdk-stable] [PATCH 1/2] net/mlx5: fix num seg assumption on vPMD Nélio Laranjeiro
2017-08-30 7:07 ` [dpdk-stable] [PATCH v2 " Shahaf Shuler
2017-09-04 14:57 ` Nélio Laranjeiro [this message]
2017-09-11 12:50 ` [dpdk-stable] [PATCH v3 1/3] " Shahaf Shuler
2017-09-13 10:50 ` [dpdk-stable] [PATCH v4 1/4] " Shahaf Shuler
2017-09-14 10:50 ` [dpdk-stable] [PATCH v5 " Shahaf Shuler
2017-09-15 10:51 ` Ferruh Yigit
2017-09-14 10:50 ` [dpdk-stable] [PATCH v5 2/4] net/mlx5: fix Tx stats error counter definition Shahaf Shuler
2017-09-14 10:50 ` [dpdk-stable] [PATCH v5 3/4] net/mlx5: fix Tx stats error counter logic Shahaf Shuler
2017-09-14 10:50 ` [dpdk-stable] [PATCH v5 4/4] net/mlx5: enforce Tx num of segments limitation Shahaf Shuler
2017-09-14 19:21 ` Yongseok Koh
2017-09-15 8:11 ` Nélio Laranjeiro
2017-09-13 10:50 ` [dpdk-stable] [PATCH v4 2/4] net/mlx5: fix Tx stats error counter definition Shahaf Shuler
2017-09-13 17:59 ` Yongseok Koh
2017-09-14 8:11 ` Nélio Laranjeiro
2017-09-13 10:50 ` [dpdk-stable] [PATCH v4 3/4] net/mlx5: fix Tx stats error counter logic Shahaf Shuler
2017-09-13 18:17 ` Yongseok Koh
2017-09-14 8:12 ` Nélio Laranjeiro
2017-09-13 10:50 ` [dpdk-stable] [PATCH v4 4/4] net/mlx5: enforce Tx num of segments limitation Shahaf Shuler
2017-09-13 19:51 ` Yongseok Koh
2017-09-14 5:23 ` Shahaf Shuler
2017-09-14 8:05 ` Yongseok Koh
2017-09-11 12:50 ` [dpdk-stable] [PATCH v3 2/3] net/mlx5: fix Tx stats error counter Shahaf Shuler
2017-09-11 12:50 ` [dpdk-stable] [PATCH v3 3/3] net/mlx5: enforce Tx num of segments limitation Shahaf Shuler
2017-08-30 7:07 ` [dpdk-stable] [PATCH v2 2/2] " Shahaf Shuler
2017-09-04 14:57 ` Nélio Laranjeiro
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=20170904145748.fjd3mwroy2pwwdw4@localhost \
--to=nelio.laranjeiro@6wind.com \
--cc=adrien.mazarguil@6wind.com \
--cc=dev@dpdk.org \
--cc=shahafs@mellanox.com \
--cc=stable@dpdk.org \
/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).