summaryrefslogtreecommitdiff
path: root/include/net/neighbour.h
diff options
context:
space:
mode:
authorDaniel Borkmann <daniel@iogearbox.net>2022-02-01 22:39:42 +0300
committerJakub Kicinski <kuba@kernel.org>2022-02-03 07:30:18 +0300
commit4a81f6da9cb2d1ef911131a6fd8bd15cb61fc772 (patch)
treef048a6818f99690b8d84a3558a38df135dae74ed /include/net/neighbour.h
parentb67985be400969578d4d4b17299714c0e5d2c07b (diff)
downloadlinux-4a81f6da9cb2d1ef911131a6fd8bd15cb61fc772.tar.xz
net, neigh: Do not trigger immediate probes on NUD_FAILED from neigh_managed_work
syzkaller was able to trigger a deadlock for NTF_MANAGED entries [0]: kworker/0:16/14617 is trying to acquire lock: ffffffff8d4dd370 (&tbl->lock){++-.}-{2:2}, at: ___neigh_create+0x9e1/0x2990 net/core/neighbour.c:652 [...] but task is already holding lock: ffffffff8d4dd370 (&tbl->lock){++-.}-{2:2}, at: neigh_managed_work+0x35/0x250 net/core/neighbour.c:1572 The neighbor entry turned to NUD_FAILED state, where __neigh_event_send() triggered an immediate probe as per commit cd28ca0a3dd1 ("neigh: reduce arp latency") via neigh_probe() given table lock was held. One option to fix this situation is to defer the neigh_probe() back to the neigh_timer_handler() similarly as pre cd28ca0a3dd1. For the case of NTF_MANAGED, this deferral is acceptable given this only happens on actual failure state and regular / expected state is NUD_VALID with the entry already present. The fix adds a parameter to __neigh_event_send() in order to communicate whether immediate probe is allowed or disallowed. Existing call-sites of neigh_event_send() default as-is to immediate probe. However, the neigh_managed_work() disables it via use of neigh_event_send_probe(). [0] <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2956 [inline] check_deadlock kernel/locking/lockdep.c:2999 [inline] validate_chain kernel/locking/lockdep.c:3788 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5027 lock_acquire kernel/locking/lockdep.c:5639 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5604 __raw_write_lock_bh include/linux/rwlock_api_smp.h:202 [inline] _raw_write_lock_bh+0x2f/0x40 kernel/locking/spinlock.c:334 ___neigh_create+0x9e1/0x2990 net/core/neighbour.c:652 ip6_finish_output2+0x1070/0x14f0 net/ipv6/ip6_output.c:123 __ip6_finish_output net/ipv6/ip6_output.c:191 [inline] __ip6_finish_output+0x61e/0xe90 net/ipv6/ip6_output.c:170 ip6_finish_output+0x32/0x200 net/ipv6/ip6_output.c:201 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:224 dst_output include/net/dst.h:451 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ndisc_send_skb+0xa99/0x17f0 net/ipv6/ndisc.c:508 ndisc_send_ns+0x3a9/0x840 net/ipv6/ndisc.c:650 ndisc_solicit+0x2cd/0x4f0 net/ipv6/ndisc.c:742 neigh_probe+0xc2/0x110 net/core/neighbour.c:1040 __neigh_event_send+0x37d/0x1570 net/core/neighbour.c:1201 neigh_event_send include/net/neighbour.h:470 [inline] neigh_managed_work+0x162/0x250 net/core/neighbour.c:1574 process_one_work+0x9ac/0x1650 kernel/workqueue.c:2307 worker_thread+0x657/0x1110 kernel/workqueue.c:2454 kthread+0x2e9/0x3a0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 </TASK> Fixes: 7482e3841d52 ("net, neigh: Add NTF_MANAGED flag for managed neighbor entries") Reported-by: syzbot+5239d0e1778a500d477a@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Roopa Prabhu <roopa@nvidia.com> Tested-by: syzbot+5239d0e1778a500d477a@syzkaller.appspotmail.com Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/20220201193942.5055-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net/neighbour.h')
-rw-r--r--include/net/neighbour.h18
1 files changed, 13 insertions, 5 deletions
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 937389e04c8e..87419f7f5421 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -350,7 +350,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl,
return __neigh_create(tbl, pkey, dev, true);
}
void neigh_destroy(struct neighbour *neigh);
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+ const bool immediate_ok);
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
u32 nlmsg_pid);
void __neigh_set_probe_once(struct neighbour *neigh);
@@ -460,17 +461,24 @@ static inline struct neighbour * neigh_clone(struct neighbour *neigh)
#define neigh_hold(n) refcount_inc(&(n)->refcnt)
-static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+static __always_inline int neigh_event_send_probe(struct neighbour *neigh,
+ struct sk_buff *skb,
+ const bool immediate_ok)
{
unsigned long now = jiffies;
-
+
if (READ_ONCE(neigh->used) != now)
WRITE_ONCE(neigh->used, now);
- if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
- return __neigh_event_send(neigh, skb);
+ if (!(neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)))
+ return __neigh_event_send(neigh, skb, immediate_ok);
return 0;
}
+static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+{
+ return neigh_event_send_probe(neigh, skb, true);
+}
+
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
{