net: sched: add rcu annotations around qdisc->qdisc_sleeping

syzbot reported a race around qdisc->qdisc_sleeping [1]

It is time we add proper annotations to reads and writes to/from
qdisc->qdisc_sleeping.

[1]
BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu

read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1:
qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331
__tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174
tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547
rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
____sys_sendmsg+0x375/0x4c0 net/socket.c:2503
___sys_sendmsg net/socket.c:2557 [inline]
__sys_sendmsg+0x1e3/0x270 net/socket.c:2586
__do_sys_sendmsg net/socket.c:2595 [inline]
__se_sys_sendmsg net/socket.c:2593 [inline]
__x64_sys_sendmsg+0x46/0x50 net/socket.c:2593
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0:
dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115
qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103
tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693
rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
____sys_sendmsg+0x375/0x4c0 net/socket.c:2503
___sys_sendmsg net/socket.c:2557 [inline]
__sys_sendmsg+0x1e3/0x270 net/socket.c:2586
__do_sys_sendmsg net/socket.c:2595 [inline]
__se_sys_sendmsg net/socket.c:2593 [inline]
__x64_sys_sendmsg+0x46/0x50 net/socket.c:2593
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023

Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu")
Reported-by: syzbot <[email protected]>
Signed-off-by: Eric Dumazet <[email protected]>
Cc: Vlad Buslov <[email protected]>
Acked-by: Jamal Hadi Salim<[email protected]>
Signed-off-by: David S. Miller <[email protected]>
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index d0bc660..c860119 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -141,7 +141,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	 * qdisc totals are added at end.
 	 */
 	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
-		qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
+		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping);
 		spin_lock_bh(qdisc_lock(qdisc));
 
 		gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats,
@@ -202,7 +202,7 @@ static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl)
 {
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
-	return dev_queue->qdisc_sleeping;
+	return rtnl_dereference(dev_queue->qdisc_sleeping);
 }
 
 static unsigned long mq_find(struct Qdisc *sch, u32 classid)
@@ -221,7 +221,7 @@ static int mq_dump_class(struct Qdisc *sch, unsigned long cl,
 
 	tcm->tcm_parent = TC_H_ROOT;
 	tcm->tcm_handle |= TC_H_MIN(cl);
-	tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
+	tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle;
 	return 0;
 }
 
@@ -230,7 +230,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 {
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
-	sch = dev_queue->qdisc_sleeping;
+	sch = rtnl_dereference(dev_queue->qdisc_sleeping);
 	if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 ||
 	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;