From: Jakub Kicinski <kuba@kernel•org>
To: Til Kaiser <mail@tk154•de>
Cc: Marcin Wojtas <marcin.s.wojtas@gmail•com>,
Russell King <linux@armlinux•org.uk>,
Andrew Lunn <andrew+netdev@lunn•ch>,
"David S . Miller" <davem@davemloft•net>,
Eric Dumazet <edumazet@google•com>,
Paolo Abeni <pabeni@redhat•com>,
Alexei Starovoitov <ast@kernel•org>,
Daniel Borkmann <daniel@iogearbox•net>,
Jesper Dangaard Brouer <hawk@kernel•org>,
John Fastabend <john.fastabend@gmail•com>,
Stanislav Fomichev <sdf@fomichev•me>,
Matteo Croce <mcroce@redhat•com>,
Sven Auhagen <sven.auhagen@voleatech•de>,
Lorenzo Bianconi <lorenzo@kernel•org>,
netdev@vger•kernel.org, bpf@vger•kernel.org,
linux-kernel@vger•kernel.org
Subject: Re: [PATCH net v2 3/4] net: mvpp2: do not return retired RX buffers to BM
Date: Thu, 4 Jun 2026 08:45:06 -0700 [thread overview]
Message-ID: <20260604084506.274d0ead@kernel.org> (raw)
In-Reply-To: <20260602164635.62517-4-mail@tk154.de>
On Tue, 2 Jun 2026 18:46:34 +0200 Til Kaiser wrote:
> The RX refill failure path jumps to err_drop_frame, which returns the
> descriptor buffer to the hardware BM pool. That is only valid while the
> driver still owns the buffer.
>
> After a non-PASS XDP verdict, mvpp2_run_xdp() may already have recycled,
> redirected, or queued the page for XDP_TX. After build_skb(), freeing the
> skb on refill failure also retires the data buffer. Returning either of
> those buffers to BM lets hardware DMA into memory that is no longer owned
> by the RX ring.
>
> Split the error handling so buffers are returned to BM only while still
> owned by the driver. Once XDP or an skb owns the buffer, only account the
> RX error. Mark page-pool skbs for recycle before they can be freed on the
> refill failure path, and unmap non-page-pool buffers before freeing them.
As Gemini points out the driver seems to be following the "if I can't
allocate a new buffer I'll drop the packet and give the current buffer
back to the HW" flow. So after your change on allocation error we're
permanently leaking a slot on in the buffer pool. Leaking as in it will
never be filled, if it happens enough times the pool will be empty,
and no Rx can happen.
--
pw-bot: cr
next prev parent reply other threads:[~2026-06-04 15:45 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-02 16:46 [PATCH net v2 0/4] net: mvpp2: fix XDP RX buffer handling Til Kaiser
2026-06-02 16:46 ` [PATCH net v2 1/4] net: mvpp2: sync RX data at the hardware packet offset Til Kaiser
2026-06-02 16:46 ` [PATCH net v2 2/4] net: mvpp2: limit XDP frame size to the RX buffer Til Kaiser
2026-06-02 16:46 ` [PATCH net v2 3/4] net: mvpp2: do not return retired RX buffers to BM Til Kaiser
2026-06-04 15:45 ` Jakub Kicinski [this message]
2026-06-02 16:46 ` [PATCH net v2 4/4] net: mvpp2: build skb from XDP-adjusted data on XDP_PASS Til Kaiser
2026-06-03 13:55 ` [PATCH net v2 0/4] net: mvpp2: fix XDP RX buffer handling Alexander Lobakin
2026-06-04 11:30 ` Marcin Wojtas
2026-06-05 12:13 ` [PATCH net v3 " Til Kaiser
2026-06-05 12:13 ` [PATCH net v3 1/4] net: mvpp2: sync RX data at the hardware packet offset Til Kaiser
2026-06-05 12:13 ` [PATCH net v3 2/4] net: mvpp2: limit XDP frame size to the RX buffer Til Kaiser
2026-06-05 12:13 ` [PATCH net v3 3/4] net: mvpp2: refill RX buffers before XDP or skb use Til Kaiser
2026-06-05 12:13 ` [PATCH net v3 4/4] net: mvpp2: build skb from XDP-adjusted data on XDP_PASS Til Kaiser
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=20260604084506.274d0ead@kernel.org \
--to=kuba@kernel$(echo .)org \
--cc=andrew+netdev@lunn$(echo .)ch \
--cc=ast@kernel$(echo .)org \
--cc=bpf@vger$(echo .)kernel.org \
--cc=daniel@iogearbox$(echo .)net \
--cc=davem@davemloft$(echo .)net \
--cc=edumazet@google$(echo .)com \
--cc=hawk@kernel$(echo .)org \
--cc=john.fastabend@gmail$(echo .)com \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linux@armlinux$(echo .)org.uk \
--cc=lorenzo@kernel$(echo .)org \
--cc=mail@tk154$(echo .)de \
--cc=marcin.s.wojtas@gmail$(echo .)com \
--cc=mcroce@redhat$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=pabeni@redhat$(echo .)com \
--cc=sdf@fomichev$(echo .)me \
--cc=sven.auhagen@voleatech$(echo .)de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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