From mboxrd@z Thu Jan  1 00:00:00 1970
Authentication-Results: mail.toke.dk; dkim=none; arc=none (Message is not ARC signed); dmarc=fail (Used From Domain Record) header.from=toke.dk policy.dmarc=none
From: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
To: Yuchao Zhang <ndaugoing@gmail.com>, "David S . Miller"
 <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski
 <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>, Jamal Hadi Salim <jhs@mojatatu.com>,
 Jiri Pirko <jiri@resnulli.us>, cake@lists.bufferbloat.net,
 netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
 stable@vger.kernel.org, Yuchao Zhang <ndaugoing@gmail.com>
In-Reply-To: <20260927131009.24250-2-ndaugoing@gmail.com>
References: <20260927131009.24250-1-ndaugoing@gmail.com>
 <20260927131009.24250-2-ndaugoing@gmail.com>
Date: Mon, 28 Sep 2026 14:30:39 +0200
X-Clacks-Overhead: GNU Terry Pratchett
Message-ID: <877bk5lfrk.fsf@toke.dk>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Message-ID-Hash: SF6LAZRHDH4SSZTVBI4GDXAYZDDB3K44
X-Message-ID-Hash: SF6LAZRHDH4SSZTVBI4GDXAYZDDB3K44
X-MailFrom: toke@toke.dk
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header
X-Mailman-Version: 3.3.10
Precedence: list
Subject: [Cake] Re: [PATCH net v3 1/2] net/sched: sch_cake: fix shaper stall on segs == 0 in cake_overhead()
List-Id: Cake - FQ_codel the next generation <cake.lists.bufferbloat.net>
Archived-At: <https://lists.bufferbloat.net/cake/877bk5lfrk.fsf@toke.dk/>
List-Archive: <https://lists.bufferbloat.net/cake/>
List-Help: <mailto:cake-request@lists.bufferbloat.net?subject=help>
List-Owner: <mailto:cake-owner@lists.bufferbloat.net>
List-Post: <mailto:cake@lists.bufferbloat.net>
List-Subscribe: <mailto:cake-join@lists.bufferbloat.net>
List-Unsubscribe: <mailto:cake-leave@lists.bufferbloat.net>

Yuchao Zhang <ndaugoing@gmail.com> writes:

> In cake_overhead(), packets with a single segment bypass multi-segment
> overhead calculations:
>
> 	if (segs =3D=3D 1)
> 		return cake_calc_overhead(q, len, off);
>
> Commit c5d34f4583ea ("net_sched: cake: use qdisc_pkt_segs()") switched
> cake to retrieve the cached segmentation count via qdisc_pkt_segs(skb)
> instead of calculating it locally for dodgy GSO packets. If an skb with
> segs =3D=3D 0 reaches cake_overhead(), it skips the segs =3D=3D 1 early r=
eturn
> and enters the multi-segment arithmetic:
>
> 	len =3D shinfo->gso_size + hdr_len;
> 	last_len =3D skb->len - shinfo->gso_size * (segs - 1);
>
> 	return (cake_calc_overhead(q, len, off) * (segs - 1) +
> 		cake_calc_overhead(q, last_len, off));
>
> Because segs is an unsigned 16-bit integer, (segs - 1) underflows to
> 65535 (and is promoted to 4294967295 in the 32-bit unsigned arithmetic
> above). This multiplies the per-segment overhead by UINT32_MAX, so
> cake_overhead() returns a length close to 4.29 GB. cake_advance_shaper()
> then charges that length to the shaper, stalling the CAKE dequeue path
> for tens of seconds at 1 Gbit/s, and for minutes to hours at lower rates.
>
> Fix this by returning early with cake_calc_overhead(q, len, off) whenever
> segs <=3D 1.
>
> Fixes: c5d34f4583ea ("net_sched: cake: use qdisc_pkt_segs()")
> Cc: stable@vger.kernel.org
> Signed-off-by: Yuchao Zhang <ndaugoing@gmail.com>

Acked-by: Toke H=C3=B8iland-J=C3=B8rgensen <toke@toke.dk>