From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-dl1-f45.google.com (mail-dl1-f45.google.com [74.125.82.45]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 504873A75B6 for ; Sat, 28 Mar 2026 18:23:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.45 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774722229; cv=none; b=JyoAd1L4SvLorOAjU9qhsJPm43UreLMDYfx9y5E7OfIc3NnjyDo+5zx73JG3Kc+KOKuxXhf4T1h/jNDsrjacGvWQCzJHnNrYCfG8O8biXyfUPRCzvJ3PHNPEYM+WVwTv5IcxDoOBsRa8tA17LW+1cZZGH23b3XrINmnOqPUZiG4= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774722229; c=relaxed/simple; bh=TOAKlDfWzkgQtJ9z1HH1Fm0oFhes+H4PHDuXFVXaQj8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=DFaB/r7NMk1u0Y29QwsRi8/3LrdF2JxAn9NUj3ezZZWwyTicMRL0l4Y7bYvx0DU8/6tph5A1Y8ul32OKcRBgJbN0liOIXuGwoHN+jV5x8I109EouM+1TW5ynngUp4CXjisB4zgspHL7vfxcRkjjvVjyb/XtkZKQ4wgrrRAjKssk= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=networkplumber.org; spf=pass smtp.mailfrom=networkplumber.org; dkim=pass (2048-bit key) header.d=networkplumber-org.20230601.gappssmtp.com header.i=@networkplumber-org.20230601.gappssmtp.com header.b=iwQZr9dB; arc=none smtp.client-ip=74.125.82.45 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=networkplumber.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=networkplumber.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=networkplumber-org.20230601.gappssmtp.com header.i=@networkplumber-org.20230601.gappssmtp.com header.b="iwQZr9dB" Received: by mail-dl1-f45.google.com with SMTP id a92af1059eb24-126ea4e9694so3705569c88.1 for ; Sat, 28 Mar 2026 11:23:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1774722225; x=1775327025; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=muqqZpGr47aKejirv9NV6VhTuEnxkRoIgVczQSZpOIU=; b=iwQZr9dBx57bWYQuPp7yK5lTCiZfqOrhEmIy/S26qHcifWMFAXFcIVJ5GRRaaQ6Xt1 fsZ4NsQW3vifRgILWQLuHqnwkAC+OEr9vuLSrWtiTLffs9FEblFhx485Lc1tR43xjOZQ HZJv6Cgn6ldz48PRt1ZJpVvtXGA5CqervvL5WtRZkKe+xXtSUYqWccsXSkVPQJDbWOSq v83NhK9HIP7D8masXBsJ07TIbfF9RncLwc3bdBpMMXA5dqlsj39a0svpYa+Tei+owXJ+ DQUCY8dSrZNfdV8XIhyL75KsjHO96VzAVPOeicdhdThsdPHztef1J6Ovlpyj5WraJK6j aekw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1774722225; x=1775327025; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=muqqZpGr47aKejirv9NV6VhTuEnxkRoIgVczQSZpOIU=; b=mdiFSA2njkbC9ynnskvfd8usKu+S4XsrDfztH1OQcf8tIYmdRwVhJRQEvgaVuCMbRk 6neRB/NoOGrUXUwlaKLWMz8mcxTS9qJN2KHBeD2Cwc3bQGfxHmq5X9Zf4WchfWL1/W95 fXT0vlZ+Myx+yBvFCJkEtnZRBVR+oM9KeQ3LX4WbgvOYTM73joGs2ES0zbomJMaaUH/E DcZLHRRL+g+3iq97u3dq9ykG73o+0S94rv78UfnXIbD+6T8rvtDAUqC37JkiWU+3L75q QEpj/TFrN/jBMzPiqcfDoOYttTxSl4Q+aAMQp9ENe/zEu5yERS/VSCXioXPaNKmF92H/ Wblg== X-Forwarded-Encrypted: i=1; AJvYcCVLmAr3a2dPCpc9+HqJrYHQNogBqX6amGl6JiANaH7nxl0PBwiC78ykolKFxT1yNh8W4K+wFDtX8MNwxdc=@vger.kernel.org X-Gm-Message-State: AOJu0YzQqUoyJGDRt+fhelwP4AvxNMIBk+kiHE8137cvB3oU291Pgstk CLoOOV+U+5w/zkda9aebdbew3MhjhnOt9NIxiYFzL3yEffUKOocNHOUeu0H1XntZqAI= X-Gm-Gg: ATEYQzws4gGb/iGASpAyyLEIb/nzarb+KmjnSKczEwI1wzHEc6DbkajUN1P/Yz4M70s FO9L2BRk3+iki0fgAyQqUEngV05uobUuEtbYbRN+FMfK0B1LdiGrkL1vvl/y5krd4WSG6wtTzaL 2s12ZsYSe65EsE7tcL55IjODRIH3zDAFRrUOJibY7P/9cgVK40BaaFr/b53CuIURe+/JPm84eZx hIHgAiE8moIqUWJREq9oLavYItKEiMDnByBLDh2R+ND7+m5c0BIenjdRlqQQPXKbjfQtuxxf74D OaPTQq9nXrqVqnImwGx4qm+d+2Za3uictNF69Ndv/x/SPMy7gwPm6O7qrIIOd1PLuAA4CiLvws+ Ol0Hnyej+8M8l8KUgSdzH67qb/kCaQ84B4M8Kt1D5wF/vfTi9PQeteqYJ0gdF5+11El6aK7Zj0m ox6KKzPtiMkxhxDJBYBtWwn7VevgojV39w X-Received: by 2002:a05:7022:b98:b0:128:d967:466c with SMTP id a92af1059eb24-12ab28e4c8amr3659107c88.24.1774722225390; Sat, 28 Mar 2026 11:23:45 -0700 (PDT) Received: from phoenix.lan ([104.202.29.139]) by smtp.gmail.com with ESMTPSA id a92af1059eb24-12aba581027sm3133008c88.4.2026.03.28.11.23.44 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 28 Mar 2026 11:23:45 -0700 (PDT) From: Stephen Hemminger To: netdev@vger.kernel.org Cc: Stephen Hemminger , Jamal Hadi Salim , Jiri Pirko , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , linux-kernel@vger.kernel.org (open list) Subject: [PATCH net 4/5] net/sched: netem: restructure dequeue to avoid re-entrancy with child qdisc Date: Sat, 28 Mar 2026 11:21:48 -0700 Message-ID: <20260328182336.392817-5-stephen@networkplumber.org> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260328182336.392817-1-stephen@networkplumber.org> References: <20260328182336.392817-1-stephen@networkplumber.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit netem_dequeue() enqueues packets into its child qdisc while being called from the parent's dequeue path. This causes two problems: - HFSC tracks class active/inactive state on qlen transitions. A child enqueue during dequeue causes double-insertion into the eltree (CVE-2025-37890, CVE-2025-38001). - Non-work-conserving children like TBF may refuse to dequeue packets just enqueued, causing netem to return NULL despite having backlog. Parents like DRR then incorrectly deactivate the class. Split the dequeue into helpers: netem_pull_tfifo() - remove head packet from tfifo netem_slot_account() - update slot pacing counters netem_dequeue_child() - batch-transfer ready packets to the child, then dequeue from the child netem_dequeue_direct()- dequeue from tfifo when no child When a child qdisc is present, all time-ready packets are moved into the child before calling its dequeue. This separates the enqueue and dequeue phases so the parent sees consistent qlen transitions. Fixes: 50612537e9ab ("netem: fix classful handling") Signed-off-by: Stephen Hemminger --- net/sched/sch_netem.c | 201 +++++++++++++++++++++++++++--------------- 1 file changed, 128 insertions(+), 73 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 448097fc88a4..ce12b64603b2 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -688,99 +688,154 @@ static struct sk_buff *netem_peek(struct netem_sched_data *q) return q->t_head; } -static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) +/* + * Pop the head packet from the tfifo and prepare it for delivery. + * skb->dev shares the rbnode area and must be restored after removal. + */ +static struct sk_buff *netem_pull_tfifo(struct netem_sched_data *q, + struct Qdisc *sch) { - if (skb == q->t_head) { + struct sk_buff *skb; + + if (q->t_head) { + skb = q->t_head; q->t_head = skb->next; if (!q->t_head) q->t_tail = NULL; } else { - rb_erase(&skb->rbnode, &q->t_root); + struct rb_node *p = rb_first(&q->t_root); + + if (!p) + return NULL; + skb = rb_to_skb(p); + rb_erase(p, &q->t_root); } + + q->t_len--; + skb->next = NULL; + skb->prev = NULL; + skb->dev = qdisc_dev(sch); + + return skb; } -static struct sk_buff *netem_dequeue(struct Qdisc *sch) +/* Update slot pacing counters after releasing a packet */ +static void netem_slot_account(struct netem_sched_data *q, + const struct sk_buff *skb, u64 now) +{ + if (!q->slot.slot_next) + return; + + q->slot.packets_left--; + q->slot.bytes_left -= qdisc_pkt_len(skb); + if (q->slot.packets_left <= 0 || q->slot.bytes_left <= 0) + get_slot_next(q, now); +} + +/* + * Transfer all time-ready packets from the tfifo into the child qdisc, + * then dequeue from the child. Batching the transfers avoids calling + * qdisc_enqueue() inside the parent's dequeue path, which confuses + * parents that track active/inactive state on qlen transitions (HFSC). + */ +static struct sk_buff *netem_dequeue_child(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); + u64 now = ktime_get_ns(); struct sk_buff *skb; -tfifo_dequeue: - skb = __qdisc_dequeue_head(&sch->q); - if (skb) { -deliver: - qdisc_qstats_backlog_dec(sch, skb); - qdisc_bstats_update(sch, skb); - return skb; - } - skb = netem_peek(q); - if (skb) { - u64 time_to_send; - u64 now = ktime_get_ns(); - - /* if more time remaining? */ - time_to_send = netem_skb_cb(skb)->time_to_send; - if (q->slot.slot_next && q->slot.slot_next < time_to_send) - get_slot_next(q, now); - - if (time_to_send <= now && q->slot.slot_next <= now) { - netem_erase_head(q, skb); - q->t_len--; - skb->next = NULL; - skb->prev = NULL; - /* skb->dev shares skb->rbnode area, - * we need to restore its value. - */ - skb->dev = qdisc_dev(sch); - - if (q->slot.slot_next) { - q->slot.packets_left--; - q->slot.bytes_left -= qdisc_pkt_len(skb); - if (q->slot.packets_left <= 0 || - q->slot.bytes_left <= 0) - get_slot_next(q, now); - } + while ((skb = netem_peek(q)) != NULL) { + struct sk_buff *to_free = NULL; + unsigned int pkt_len; + int err; - if (q->qdisc) { - unsigned int pkt_len = qdisc_pkt_len(skb); - struct sk_buff *to_free = NULL; - int err; - - err = qdisc_enqueue(skb, q->qdisc, &to_free); - kfree_skb_list(to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - sch->qstats.backlog -= pkt_len; - sch->q.qlen--; - qdisc_tree_reduce_backlog(sch, 1, pkt_len); - } - goto tfifo_dequeue; - } + if (netem_skb_cb(skb)->time_to_send > now) + break; + if (q->slot.slot_next && q->slot.slot_next > now) + break; + + skb = netem_pull_tfifo(q, sch); + netem_slot_account(q, skb, now); + + pkt_len = qdisc_pkt_len(skb); + err = qdisc_enqueue(skb, q->qdisc, &to_free); + kfree_skb_list(to_free); + if (unlikely(err != NET_XMIT_SUCCESS)) { + if (net_xmit_drop_count(err)) + qdisc_qstats_drop(sch); + sch->qstats.backlog -= pkt_len; sch->q.qlen--; - goto deliver; + qdisc_tree_reduce_backlog(sch, 1, pkt_len); } + } - if (q->qdisc) { - skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) { - sch->q.qlen--; - goto deliver; - } - } + skb = q->qdisc->ops->dequeue(q->qdisc); + if (skb) + sch->q.qlen--; - qdisc_watchdog_schedule_ns(&q->watchdog, - max(time_to_send, - q->slot.slot_next)); - } + return skb; +} - if (q->qdisc) { - skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) { - sch->q.qlen--; - goto deliver; - } +/* Dequeue directly from the tfifo when no child qdisc is configured. */ +static struct sk_buff *netem_dequeue_direct(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + u64 time_to_send; + u64 now; + + skb = netem_peek(q); + if (!skb) + return NULL; + + now = ktime_get_ns(); + time_to_send = netem_skb_cb(skb)->time_to_send; + + if (q->slot.slot_next && q->slot.slot_next < time_to_send) + get_slot_next(q, now); + + if (time_to_send > now || q->slot.slot_next > now) + return NULL; + + skb = netem_pull_tfifo(q, sch); + netem_slot_account(q, skb, now); + sch->q.qlen--; + + return skb; +} + +static struct sk_buff *netem_dequeue(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + /* First check the reorder queue */ + skb = __qdisc_dequeue_head(&sch->q); + if (skb) + goto deliver; + + if (q->qdisc) + skb = netem_dequeue_child(sch); + else + skb = netem_dequeue_direct(sch); + + if (skb) + goto deliver; + + /* Nothing ready — schedule watchdog for next packet */ + skb = netem_peek(q); + if (skb) { + u64 time_to_send = netem_skb_cb(skb)->time_to_send; + + qdisc_watchdog_schedule_ns(&q->watchdog, + max(time_to_send, q->slot.slot_next)); } return NULL; + +deliver: + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + return skb; } static void netem_reset(struct Qdisc *sch) -- 2.53.0