sch_netem: acquire qdisc lock in netem_change()

syzbot managed to trigger a divide error [1] in netem.

It could happen if q->rate changes while netem_enqueue()
is running, since q->rate is read twice.

It turns out netem_change() always lacked proper synchronization.

[1]
divide error: 0000 [#1] SMP KASAN
CPU: 1 PID: 7867 Comm: syz-executor.1 Not tainted 6.1.30-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023
RIP: 0010:div64_u64 include/linux/math64.h:69 [inline]
RIP: 0010:packet_time_ns net/sched/sch_netem.c:357 [inline]
RIP: 0010:netem_enqueue+0x2067/0x36d0 net/sched/sch_netem.c:576
Code: 89 e2 48 69 da 00 ca 9a 3b 42 80 3c 28 00 4c 8b a4 24 88 00 00 00 74 0d 4c 89 e7 e8 c3 4f 3b fd 48 8b 4c 24 18 48 89 d8 31 d2 <49> f7 34 24 49 01 c7 4c 8b 64 24 48 4d 01 f7 4c 89 e3 48 c1 eb 03
RSP: 0018:ffffc9000dccea60 EFLAGS: 00010246
RAX: 000001a442624200 RBX: 000001a442624200 RCX: ffff888108a4f000
RDX: 0000000000000000 RSI: 000000000000070d RDI: 000000000000070d
RBP: ffffc9000dcceb90 R08: ffffffff849c5e26 R09: fffffbfff10e1297
R10: 0000000000000000 R11: dffffc0000000001 R12: ffff888108a4f358
R13: dffffc0000000000 R14: 0000001a8cd9a7ec R15: 0000000000000000
FS: 00007fa73fe18700(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa73fdf7718 CR3: 000000011d36e000 CR4: 0000000000350ee0
Call Trace:
<TASK>
[<ffffffff84714385>] __dev_xmit_skb net/core/dev.c:3931 [inline]
[<ffffffff84714385>] __dev_queue_xmit+0xcf5/0x3370 net/core/dev.c:4290
[<ffffffff84d22df2>] dev_queue_xmit include/linux/netdevice.h:3030 [inline]
[<ffffffff84d22df2>] neigh_hh_output include/net/neighbour.h:531 [inline]
[<ffffffff84d22df2>] neigh_output include/net/neighbour.h:545 [inline]
[<ffffffff84d22df2>] ip_finish_output2+0xb92/0x10d0 net/ipv4/ip_output.c:235
[<ffffffff84d21e63>] __ip_finish_output+0xc3/0x2b0
[<ffffffff84d10a81>] ip_finish_output+0x31/0x2a0 net/ipv4/ip_output.c:323
[<ffffffff84d10f14>] NF_HOOK_COND include/linux/netfilter.h:298 [inline]
[<ffffffff84d10f14>] ip_output+0x224/0x2a0 net/ipv4/ip_output.c:437
[<ffffffff84d123b5>] dst_output include/net/dst.h:444 [inline]
[<ffffffff84d123b5>] ip_local_out net/ipv4/ip_output.c:127 [inline]
[<ffffffff84d123b5>] __ip_queue_xmit+0x1425/0x2000 net/ipv4/ip_output.c:542
[<ffffffff84d12fdc>] ip_queue_xmit+0x4c/0x70 net/ipv4/ip_output.c:556

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230620184425.1179809-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 6ef3021..e79be1b 100644 (file)
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -966,6 +966,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
        if (ret < 0)
                return ret;
 
+       sch_tree_lock(sch);
        /* backup q->clg and q->loss_model */
        old_clg = q->clg;
        old_loss_model = q->loss_model;
@@ -974,7 +975,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
                ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
                if (ret) {
                        q->loss_model = old_loss_model;
-                       return ret;
+                       goto unlock;
                }
        } else {
                q->loss_model = CLG_RANDOM;
@@ -1041,6 +1042,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
        /* capping jitter to the range acceptable by tabledist() */
        q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
 
+unlock:
+       sch_tree_unlock(sch);
        return ret;
 
 get_table_failure:
@@ -1050,7 +1053,8 @@ get_table_failure:
         */
        q->clg = old_clg;
        q->loss_model = old_loss_model;
-       return ret;
+
+       goto unlock;
 }
 
 static int netem_init(struct Qdisc *sch, struct nlattr *opt,