From: Stephen Hemminger <stephen@networkplumber.org>
To: Sriram Yagnaraman <sriram.yagnaraman@ericsson.com>
Cc: <jgrajcia@cisco.com>, <dev@dpdk.org>, <stable@dpdk.org>,
<bly454@gmail.com>
Subject: Re: [PATCH v2] net/memif: fix multi-segment Rx corruption
Date: Tue, 24 Mar 2026 09:25:36 -0700 [thread overview]
Message-ID: <20260324092503.69899293@phoenix.local> (raw)
In-Reply-To: <20260324161436.2816927-1-sriram.yagnaraman@ericsson.com>
On Tue, 24 Mar 2026 17:14:36 +0100
Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> wrote:
> Fix dst_off being reset per-descriptor instead of per-packet in the Rx
> slow path. When processing chained descriptors (MEMIF_DESC_FLAG_NEXT),
> goto next_slot2 reset dst_off to 0, overwriting the beginning of the
> current mbuf with data from subsequent descriptors. Move dst_off
> initialization before the next_slot2 label so it is only reset once
> per packet.
>
> Add boundary check in both Rx paths before processing next segment.
> If MEMIF_DESC_FLAG_NEXT is set but n_slots is 0, free the incomplete
> mbuf chain and exit gracefully to prevent reading beyond available
> descriptors.
>
> Bugzilla ID: 1609
> Fixes: aa17df860891 ("net/memif: add a Rx fast path")
> Cc: stable@dpdk.org
>
> Reported-by: Mike Bly <bly454@gmail.com>
> Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@ericsson.com>
> ---
This version go clean review from AI.
Applied to next-net
prev parent reply other threads:[~2026-03-24 16:25 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-16 15:59 [PATCH] net/memif: fix multi-segment RX data corruption and truncation Sriram Yagnaraman
2026-03-23 23:33 ` Stephen Hemminger
2026-03-24 16:16 ` Sriram Yagnaraman
2026-03-24 16:14 ` [PATCH v2] net/memif: fix multi-segment Rx corruption Sriram Yagnaraman
2026-03-24 16:25 ` Stephen Hemminger [this message]
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=20260324092503.69899293@phoenix.local \
--to=stephen@networkplumber.org \
--cc=bly454@gmail.com \
--cc=dev@dpdk.org \
--cc=jgrajcia@cisco.com \
--cc=sriram.yagnaraman@ericsson.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