From 709f34f7c28dc4dd6c40343d101850f11e172312 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:04 -0400 Subject: [PATCH 1/6] net/sched: fq: add overflow bounds to quantum and initial quantum fq_init() computes quantum = 2 * psched_mtu() and initial_quantum = 10 * psched_mtu() with no overflow check. A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes psched_mtu() return 0x80000000; the 2 * and 10 * multiplications wrap to 0 in 32-bit arithmetic, so q->quantum == 0. Then in fq_dequeue() the credit-refill loop adds 0 to f->credit (which stays <= 0) and goto begin loops forever under the qdisc lock, creating a soft lockup. Clamp psched_mtu() to [1, 1 << 20] before multiplying so the product cannot wrap, then cap the result at 1 << 20, matching the bound already enforced on TCA_FQ_QUANTUM in fq_change(). Conditions to recreate the bug: a device whose MTU (plus hard_header_len) is large enough that 2 * psched_mtu() wraps (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-2-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_fq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4b5f6d896c6d..6144b5686f13 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1226,12 +1226,14 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); + u32 mtu; int i, err; sch->limit = 10000; q->flow_plimit = 100; - q->quantum = 2 * psched_mtu(qdisc_dev(sch)); - q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); + mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); + q->quantum = min_t(u32, 2 * mtu, 1 << 20); + q->initial_quantum = min_t(u32, 10 * mtu, 1 << 20); q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; From d9ebd8f9aa8b2773235889cb903fafd61f2d8585 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:05 -0400 Subject: [PATCH 2/6] net/sched: fq_codel: clamp default quantum and mtu fq_codel_init() sets q->quantum = psched_mtu(qdisc_dev(sch)) without clamping. A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes psched_mtu() return 0x80000000, which overflows the signed flow->deficit to INT_MIN in fq_codel_dequeue(), causing an infinite loop and soft lockup. Emulate fq_codel_change() and constrain to [256, FQ_CODEL_QUANTUM_MAX]. The same unclamped psched_mtu() is assigned to q->cparams.mtu a bit below, and fq_codel_change() never updates it. codel_should_drop() tests "*backlog <= params->mtu"; with mtu == 0x80000000 (~2 GiB) and the default 32 MiB memory_limit, the test is always true, so CoDel is silently and completely disabled (no drops, no ECN). Declare a single clamped mtu and assign both q->quantum and q->cparams.mtu from it, which also removes the double psched_mtu() call. Conditions to recreate the bug: a device whose MTU (plus hard_header_len) wraps psched_mtu() into the sign bit (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: 4b549a2ef4be ("fq_codel: Fair Queue Codel AQM") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-3-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_fq_codel.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6cce86ba383c..969b2510b0b8 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -509,6 +509,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); + u32 mtu; int i; int err; @@ -516,13 +517,14 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, q->flows_cnt = 1024; q->memory_limit = 32 << 20; /* 32 MBytes */ q->drop_batch_size = 64; - q->quantum = psched_mtu(qdisc_dev(sch)); + mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 256, FQ_CODEL_QUANTUM_MAX); + q->quantum = mtu; INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); codel_params_init(&q->cparams); codel_stats_init(&q->cstats); q->cparams.ecn = true; - q->cparams.mtu = psched_mtu(qdisc_dev(sch)); + q->cparams.mtu = mtu; if (opt) { err = fq_codel_change(sch, opt, extack); From 6439461f1618ae176c048673ad28bdb6c68efbfc Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:06 -0400 Subject: [PATCH 3/6] net/sched: sch_codel: clamp default mtu to avoid disabling CoDel codel_init() sets q->params.mtu = psched_mtu(qdisc_dev(sch)) without clamping. A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes psched_mtu() return 0x80000000. In codel_should_drop() the test "*backlog <= params->mtu" then compares the backlog against ~2 GiB; with the default sch->limit of DEFAULT_CODEL_LIMIT (1000) packets the backlog can never reach it, so the test is always true and CoDel is silently and completely disabled i.e no drops, no ECN marking, codel degrades to a tail-drop FIFO. codel_change() never updates params.mtu, so the init path is the only place to clamp it. Constrain to [256, 1 << 20], matching the fq_codel bound; 256 is a sane floor that only makes CoDel slightly more willing to act on very small queues, which is the safe direction. Conditions to recreate the bug: a device whose MTU (plus hard_header_len) wraps psched_mtu() into the sign bit (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-4-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_codel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index cacf5244958e..6aa5829d6961 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -205,7 +205,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt, codel_params_init(&q->params); codel_vars_init(&q->vars); codel_stats_init(&q->stats); - q->params.mtu = psched_mtu(qdisc_dev(sch)); + q->params.mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 256, 1 << 20); if (opt) { int err = codel_change(sch, opt, extack); From c86cd7ed0b0e44779a3d1683f03e4353baf4bdc9 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:07 -0400 Subject: [PATCH 4/6] net/sched: fq_pie: clamp default quantum to avoid signed overflow fq_pie_init() sets q->quantum = psched_mtu(qdisc_dev(sch)) without clamping. A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes psched_mtu() return 0x80000000, which overflows the signed flow->deficit to INT_MIN in fq_pie_qdisc_dequeue(), causing an infinite loop and soft lockup. Emulate fq_pie_policy which is already bounded to [1, 1 << 20]; clamp the default to [256, 1 << 20]. 256 matches fq_codel's floor and is a sane minimum for a DRR quantum. Conditions to recreate the bug: a device whose MTU (plus hard_header_len) wraps psched_mtu() into the sign bit (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-5-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_fq_pie.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 069e1facd413..b27d95418707 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -427,7 +427,8 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, pie_params_init(&q->p_params); sch->limit = 10 * 1024; q->p_params.limit = sch->limit; - q->quantum = psched_mtu(qdisc_dev(sch)); + q->quantum = clamp_t(u32, psched_mtu(qdisc_dev(sch)), + 256, 1 << 20); q->sch = sch; q->ecn_prob = 10; q->flows_cnt = 1024; From 2164b512b97bb053e8ce4d6e95576f11bed6a005 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:08 -0400 Subject: [PATCH 5/6] net/sched: hhf: clamp quantum before hhf_change() to avoid overflow hhf_init() sets q->quantum = psched_mtu(qdisc_dev(sch)) with no overflow check. A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes weight * quantum overflow the signed deficit in hhf_dequeue(), spinning forever. Clamp q->quantum before hhf_change() so both the opt and !opt paths see a sane quantum. Without this, bare "tc qdisc add ... hhf" succeeds with a clamped quantum but "tc qdisc add ... hhf limit 1000" (any option present) fails with -EINVAL because hhf_change() re-validates the unclamped default (sch_hhf.c:559). 256 matches fq_codel's floor and is a sane minimum for a DRR quantum. Conditions to recreate the bug: a device whose MTU (plus hard_header_len) wraps psched_mtu() into the sign bit (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-6-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_hhf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index d85cb0263b67..96acab6a8da0 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -624,6 +624,10 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, q->hhf_evict_timeout = HZ; /* 1 sec */ q->hhf_non_hh_weight = 2; + if ((int)q->quantum <= 0 || + (u64)q->quantum * q->hhf_non_hh_weight > INT_MAX) + q->quantum = 256; + if (opt) { int err = hhf_change(sch, opt, extack); From 816e90057ab1879562a5b7cc688e35bb9027ae97 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 22 Aug 2026 15:55:09 -0400 Subject: [PATCH 6/6] net/sched: sfq: clamp quantum to avoid signed overflow soft lockup sfq_init() sets q->quantum = psched_mtu(qdisc_dev(sch)) (unsigned). A device with a huge MTU (e.g. dummy with max_mtu == 0 accepting MTU 2147483634) makes psched_mtu() return 0x80000000, so slot->allot = INT_MIN and INT_MIN + INT_MIN toggles between INT_MIN and 0 forever, spinning sfq_dequeue() under the qdisc lock. Clamp the quantum to [256, 1 << 20] so the refill loop terminates. The lower bound also covers q->quantum == 0 (psched_mtu() returning 0), which spins sfq_dequeue() identically. sfq_change() already rejects a negative quantum, so only the init path was exposed. Conditions to recreate the bug: a device whose MTU (plus hard_header_len) wraps psched_mtu() into the sign bit (e.g. a dummy device with max_mtu == 0 accepting MTU 2147483634). Requires CAP_NET_ADMIN in a user namespace. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260822195509.112717-7-jhs@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/sch_sfq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 77675f9a4c46..187d3ed578f2 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -799,7 +799,8 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt, q->tail = NULL; q->divisor = SFQ_DEFAULT_HASH_DIVISOR; q->maxflows = SFQ_DEFAULT_FLOWS; - q->quantum = psched_mtu(qdisc_dev(sch)); + q->quantum = clamp_t(u32, psched_mtu(qdisc_dev(sch)), + 256, 1 << 20); q->perturb_period = 0; get_random_bytes(&q->perturbation, sizeof(q->perturbation));