When a TAPRIO child qdisc is deleted via RTM_DELQDISC, taprio_graft()
is called with new == NULL and stores NULL into q->qdiscs[cl - 1].
Subsequent RTM_GETTCLASS dump operations walk all classes via
taprio_walk() and call taprio_dump_class(), which calls taprio_leaf()
returning the NULL pointer, then dereferences it to read child->handle,
causing a kernel NULL pointer dereference.
The bug is reachable with namespace-scoped CAP_NET_ADMIN on any kernel
with CONFIG_NET_SCH_TAPRIO enabled. On systems with unprivileged user
namespaces enabled, an unprivileged local user can trigger a kernel
panic by creating a taprio qdisc inside a new network namespace,
grafting an explicit child qdisc, deleting it, and requesting a class
dump. The RTM_GETTCLASS dump itself requires no capability.
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000007: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f]
RIP: 0010:taprio_dump_class (net/sched/sch_taprio.c:2475)
Call Trace:
tc_fill_tclass (net/sched/sch_api.c:1966)
qdisc_class_dump (net/sched/sch_api.c:2329)
taprio_walk (net/sched/sch_taprio.c:2510)
tc_dump_tclass_qdisc (net/sched/sch_api.c:2353)
tc_dump_tclass_root (net/sched/sch_api.c:2370)
tc_dump_tclass (net/sched/sch_api.c:2431)
rtnl_dumpit (net/core/rtnetlink.c:6827)
netlink_dump (net/netlink/af_netlink.c:2325)
rtnetlink_rcv_msg (net/core/rtnetlink.c:6927)
netlink_rcv_skb (net/netlink/af_netlink.c:2550)
Fix this by substituting &noop_qdisc when new is NULL in
taprio_graft(), following the same pattern used by multiq_graft() and
prio_graft(). This ensures q->qdiscs[] slots are never NULL, making
control-plane dump paths safe without requiring individual NULL checks.
Since the data-plane paths (taprio_enqueue and taprio_dequeue_from_txq)
previously had explicit NULL guards that would drop/skip the packet
cleanly, update those checks to test for &noop_qdisc instead. Without
this, packets would reach taprio_enqueue_one() which increments the root
qdisc's qlen and backlog before calling the child's enqueue; noop_qdisc
drops the packet but those counters are never rolled back, permanently
inflating the root qdisc's statistics.
Fixes: 665338b2a7a0 ("net/sched: taprio: dump class stats for the actual q->qdiscs[]")
Reported-by: Xiang Mei
Signed-off-by: Weiming Shi
---
v3: fix broken patch
v2: Also update NULL guards in taprio_enqueue() and
taprio_dequeue_from_txq() to avoid qlen/backlog inflation (Paolo).
---
net/sched/sch_taprio.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index f721c03514f60..07723b156c5b3 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -634,7 +634,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
queue = skb_get_queue_mapping(skb);
child = q->qdiscs[queue];
- if (unlikely(!child))
+ if (unlikely(child == &noop_qdisc))
return qdisc_drop(skb, sch, to_free);
if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) {
@@ -717,7 +717,7 @@ static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq,
int len;
u8 tc;
- if (unlikely(!child))
+ if (unlikely(child == &noop_qdisc))
return NULL;
if (TXTIME_ASSIST_IS_ENABLED(q->flags))
@@ -2183,6 +2183,9 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
if (!dev_queue)
return -EINVAL;
+ if (!new)
+ new = &noop_qdisc;
+
if (dev->flags & IFF_UP)
dev_deactivate(dev);
@@ -2196,14 +2199,14 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
*old = q->qdiscs[cl - 1];
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old);
- if (new)
+ if (new != &noop_qdisc)
qdisc_refcount_inc(new);
if (*old)
qdisc_put(*old);
}
q->qdiscs[cl - 1] = new;
- if (new)
+ if (new != &noop_qdisc)
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
--
2.43.0