linux-kernel - [PATCH v2 net] net: sch_generic: aviod concurrent reset and enqueue op for lockless qdisc

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1599562954-87257-1-git-send-email-linyunsheng@huawei.com>
Date:   Tue, 8 Sep 2020 19:02:34 +0800
From:   Yunsheng Lin <linyunsheng@...wei.com>
To:     <jhs@...atatu.com>, <xiyou.wangcong@...il.com>, <jiri@...nulli.us>,
        <davem@...emloft.net>, <kuba@...nel.org>
CC:     <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <linuxarm@...wei.com>, <john.fastabend@...il.com>,
        <eric.dumazet@...il.com>
Subject: [PATCH v2 net] net: sch_generic: aviod concurrent reset and enqueue op for lockless qdisc

Currently there is concurrent reset and enqueue operation for the
same lockless qdisc when there is no lock to synchronize the
q->enqueue() in __dev_xmit_skb() with the qdisc reset operation in
qdisc_deactivate() called by dev_deactivate_queue(), which may cause
out-of-bounds access for priv->ring[] in hns3 driver if user has
requested a smaller queue num when __dev_xmit_skb() still enqueue a
skb with a larger queue_mapping after the corresponding qdisc is
reset, and call hns3_nic_net_xmit() with that skb later.

Reused the existing synchronize_net() in dev_deactivate_many() to
make sure skb with larger queue_mapping enqueued to old qdisc(which
is saved in dev_queue->qdisc_sleeping) will always be reset when
dev_reset_queue() is called.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Signed-off-by: Yunsheng Lin <linyunsheng@...wei.com>
---
ChangeLog V2:
	Reuse existing synchronize_net().
---
 net/sched/sch_generic.c | 48 +++++++++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 15 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 265a61d..54c4172 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate);
 
 static void qdisc_deactivate(struct Qdisc *qdisc)
 {
-	bool nolock = qdisc->flags & TCQ_F_NOLOCK;
-
 	if (qdisc->flags & TCQ_F_BUILTIN)
 		return;
-	if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state))
-		return;
-
-	if (nolock)
-		spin_lock_bh(&qdisc->seqlock);
-	spin_lock_bh(qdisc_lock(qdisc));
 
 	set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
-
-	qdisc_reset(qdisc);
-
-	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock)
-		spin_unlock_bh(&qdisc->seqlock);
 }
 
 static void dev_deactivate_queue(struct net_device *dev,
@@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev,
 	}
 }
 
+static void dev_reset_queue(struct net_device *dev,
+			    struct netdev_queue *dev_queue,
+			    void *_unused)
+{
+	struct Qdisc *qdisc;
+	bool nolock;
+
+	qdisc = dev_queue->qdisc_sleeping;
+	if (!qdisc)
+		return;
+
+	nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+	if (nolock)
+		spin_lock_bh(&qdisc->seqlock);
+	spin_lock_bh(qdisc_lock(qdisc));
+
+	qdisc_reset(qdisc);
+
+	spin_unlock_bh(qdisc_lock(qdisc));
+	if (nolock)
+		spin_unlock_bh(&qdisc->seqlock);
+}
+
 static bool some_qdisc_is_busy(struct net_device *dev)
 {
 	unsigned int i;
@@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head)
 		dev_watchdog_down(dev);
 	}
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls or
+	 * outstanding qdisc enqueuing calls.
 	 * This is avoided if all devices are in dismantle phase :
 	 * Caller will call synchronize_net() for us
 	 */
 	synchronize_net();
 
+	list_for_each_entry(dev, head, close_list) {
+		netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
+
+		if (dev_ingress_queue(dev))
+			dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
+	}
+
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, close_list) {
 		while (some_qdisc_is_busy(dev)) {
-- 
2.8.1