From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: jiri@resnulli.us, jhs@mojatatu.com, willsroot@protonmail.com,
savy@syst3mfailure.io, Cong Wang <xiyou.wangcong@gmail.com>
Subject: [Patch net 1/2] net_sched: Flush gso_skb list too during ->change()
Date: Mon, 5 May 2025 17:15:48 -0700 [thread overview]
Message-ID: <20250506001549.65391-2-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20250506001549.65391-1-xiyou.wangcong@gmail.com>
Previously, when reducing a qdisc's limit via the ->change() operation, only
the main skb queue was trimmed, potentially leaving packets in the gso_skb
list. This could result in NULL pointer dereference when we only check
sch->q.qlen against sch->limit.
This patch introduces a new helper, qdisc_dequeue_internal(), which ensures
both the gso_skb list and the main queue are properly flushed when trimming
excess packets. All relevant qdiscs (codel, fq, fq_codel, fq_pie, hhf, pie)
are updated to use this helper in their ->change() routines.
Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM")
Fixes: 4b549a2ef4be ("fq_codel: Fair Queue Codel AQM")
Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler")
Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler")
Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Fixes: d4b36210c2e6 ("net: pkt_sched: PIE AQM scheme")
Reported-by: Will <willsroot@protonmail.com>
Reported-by: Savy <savy@syst3mfailure.io>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
include/net/sch_generic.h | 14 ++++++++++++++
net/sched/sch_codel.c | 2 +-
net/sched/sch_fq.c | 2 +-
net/sched/sch_fq_codel.c | 2 +-
net/sched/sch_fq_pie.c | 2 +-
net/sched/sch_hhf.c | 2 +-
net/sched/sch_pie.c | 2 +-
7 files changed, 20 insertions(+), 6 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d48c657191cd..81523a4fb01b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1031,6 +1031,20 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh)
return skb;
}
+static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct)
+{
+ struct sk_buff *skb;
+
+ skb = __skb_dequeue(&sch->gso_skb);
+ if (!skb) {
+ if (direct)
+ skb = __qdisc_dequeue_head(&sch->q);
+ else
+ skb = sch->dequeue(sch);
+ }
+ return skb;
+}
+
static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
{
struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 12dd71139da3..c93761040c6e 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -144,7 +144,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt,
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2ca5332cfcc5..902ff5470607 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1136,7 +1136,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
sch_tree_lock(sch);
}
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = fq_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
if (!skb)
break;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6c9029f71e88..2a0f3a513bfa 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -441,7 +441,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
while (sch->q.qlen > sch->limit ||
q->memory_usage > q->memory_limit) {
- struct sk_buff *skb = fq_codel_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
q->cstats.drop_len += qdisc_pkt_len(skb);
rtnl_kfree_skbs(skb, skb);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index f3b8203d3e85..a04554d01960 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -366,7 +366,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
/* Drop excess packets if new limit is lower */
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
len_dropped += qdisc_pkt_len(skb);
num_dropped += 1;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 44d9efe1a96a..f4c2bebd3780 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -564,7 +564,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
qlen = sch->q.qlen;
prev_backlog = sch->qstats.backlog;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = hhf_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
rtnl_kfree_skbs(skb, skb);
}
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 3771d000b30d..ff49a6c97033 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -195,7 +195,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
/* Drop excess packets if new limit is lower */
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
--
2.34.1
next prev parent reply other threads:[~2025-05-06 0:15 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-06 0:15 [Patch net 0/2] net_sched: Fix gso_skb flushing during qdisc change Cong Wang
2025-05-06 0:15 ` Cong Wang [this message]
2025-05-06 14:00 ` [Patch net 1/2] net_sched: Flush gso_skb list too during ->change() Savy
2025-05-06 20:40 ` Cong Wang
2025-05-06 0:15 ` [Patch net 2/2] selftests/tc-testing: Add qdisc limit trimming tests Cong Wang
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=20250506001549.65391-2-xiyou.wangcong@gmail.com \
--to=xiyou.wangcong@gmail.com \
--cc=jhs@mojatatu.com \
--cc=jiri@resnulli.us \
--cc=netdev@vger.kernel.org \
--cc=savy@syst3mfailure.io \
--cc=willsroot@protonmail.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