From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Deng, KaiwenX" <kaiwenx.deng@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "stable@dpdk.org" <stable@dpdk.org>,
"Yang, Qiming" <qiming.yang@intel.com>,
"Zhou, YidingX" <yidingx.zhou@intel.com>,
"Deng, KaiwenX" <kaiwenx.deng@intel.com>,
"Wu, Jingjing" <jingjing.wu@intel.com>,
"Xing, Beilei" <beilei.xing@intel.com>,
"Zeng, ZhichaoX" <zhichaox.zeng@intel.com>
Subject: RE: [PATCH v3] net/iavf: fix mbuf release API selection
Date: Wed, 8 Nov 2023 09:33:02 +0000 [thread overview]
Message-ID: <DM4PR11MB59945BBD4094F35FDC0CDF23D7A8A@DM4PR11MB5994.namprd11.prod.outlook.com> (raw)
In-Reply-To: <20231102044316.541458-1-kaiwenx.deng@intel.com>
> -----Original Message-----
> From: Kaiwen Deng <kaiwenx.deng@intel.com>
> Sent: Thursday, November 2, 2023 12:43 PM
> To: dev@dpdk.org
> Cc: stable@dpdk.org; Yang, Qiming <qiming.yang@intel.com>; Zhou, YidingX
> <yidingx.zhou@intel.com>; Deng, KaiwenX <kaiwenx.deng@intel.com>; Wu,
> Jingjing <jingjing.wu@intel.com>; Xing, Beilei <beilei.xing@intel.com>; Zeng,
> ZhichaoX <zhichaox.zeng@intel.com>
> Subject: [PATCH v3] net/iavf: fix mbuf release API selection
>
> When AVX2 is forcibly selected and outer checksum offload is configured, the
> basic Tx path will be selected. Also, the txq mbuf release API is incorrectly set
> to iavf_tx_queue_release_mbufs_sse. This causes coredump.
>
> This commit selects release_txq_mbufs to releasing txq mbufs when selecting
> the basic Tx path.
>
> Fixes: 22f1e7608ebc ("net/iavf: fix AVX2 Tx selection")
> Cc: stable@dpdk.org
>
> Signed-off-by: Kaiwen Deng <kaiwenx.deng@intel.com>
> ---
> drivers/net/iavf/iavf_rxtx.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c index
> 610912f635..a16e03d88c 100644
> --- a/drivers/net/iavf/iavf_rxtx.c
> +++ b/drivers/net/iavf/iavf_rxtx.c
> @@ -4022,6 +4022,7 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
> PMD_DRV_LOG(DEBUG,
> "AVX2 does not support outer
> checksum offload, using Basic Tx (port %d).",
> dev->data->port_id);
> + return;
This make the execution routing not consistent between avx2 and avx512.
I think it will be a better solution if we reset the use_avx2 flag here, and use this flag to decide if need to overwrite the release function later.
> } else {
> dev->tx_pkt_burst =
> iavf_xmit_pkts_vec_avx2_offload;
> dev->tx_pkt_prepare = iavf_prep_pkts;
> --
> 2.34.1
next prev parent reply other threads:[~2023-11-08 9:33 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-26 8:54 [PATCH] net/iavf: fix core dump when exiting testpmd Kaiwen Deng
2023-10-31 8:15 ` Zhang, Qi Z
2023-11-01 1:34 ` [PATCH v2] net/iavf: fix coredump " Kaiwen Deng
2023-11-01 7:53 ` Lu, Wenzhuo
2023-11-01 9:32 ` Deng, KaiwenX
2023-11-01 11:00 ` Zhang, Qi Z
2023-11-02 4:43 ` [PATCH v3] net/iavf: fix mbuf release API selection Kaiwen Deng
2023-11-08 9:33 ` Zhang, Qi Z [this message]
2023-11-08 12:02 ` Zhang, Qi Z
2023-11-09 1:42 ` Deng, KaiwenX
2023-11-09 4:58 ` [PATCH v4] " Kaiwen Deng
2023-11-09 12:23 ` Zhang, Qi Z
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=DM4PR11MB59945BBD4094F35FDC0CDF23D7A8A@DM4PR11MB5994.namprd11.prod.outlook.com \
--to=qi.z.zhang@intel.com \
--cc=beilei.xing@intel.com \
--cc=dev@dpdk.org \
--cc=jingjing.wu@intel.com \
--cc=kaiwenx.deng@intel.com \
--cc=qiming.yang@intel.com \
--cc=stable@dpdk.org \
--cc=yidingx.zhou@intel.com \
--cc=zhichaox.zeng@intel.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).