tipc: fix potential deadlock when all links are reset

[   60.988363] ======================================================
[   60.988754] [ INFO: possible circular locking dependency detected ]
[   60.989152] 3.19.0+ #194 Not tainted
[   60.989377] -------------------------------------------------------
[   60.989781] swapper/3/0 is trying to acquire lock:
[   60.990079]  (&(&n_ptr->lock)->rlock){+.-...}, at: [<ffffffffa0006dca>] tipc_link_retransmit+0x1aa/0x240 [tipc]
[   60.990743]
[   60.990743] but task is already holding lock:
[   60.991106]  (&(&bclink->lock)->rlock){+.-...}, at: [<ffffffffa00004be>] tipc_bclink_lock+0x8e/0xa0 [tipc]
[   60.991738]
[   60.991738] which lock already depends on the new lock.
[   60.991738]
[   60.992174]
[   60.992174] the existing dependency chain (in reverse order) is:
[   60.992174]
-> #1 (&(&bclink->lock)->rlock){+.-...}:
[   60.992174]        [<ffffffff810a9c0c>] lock_acquire+0x9c/0x140
[   60.992174]        [<ffffffff8179c41f>] _raw_spin_lock_bh+0x3f/0x50
[   60.992174]        [<ffffffffa00004be>] tipc_bclink_lock+0x8e/0xa0 [tipc]
[   60.992174]        [<ffffffffa0000f57>] tipc_bclink_add_node+0x97/0xf0 [tipc]
[   60.992174]        [<ffffffffa0011815>] tipc_node_link_up+0xf5/0x110 [tipc]
[   60.992174]        [<ffffffffa0007783>] link_state_event+0x2b3/0x4f0 [tipc]
[   60.992174]        [<ffffffffa00193c0>] tipc_link_proto_rcv+0x24c/0x418 [tipc]
[   60.992174]        [<ffffffffa0008857>] tipc_rcv+0x827/0xac0 [tipc]
[   60.992174]        [<ffffffffa0002ca3>] tipc_l2_rcv_msg+0x73/0xd0 [tipc]
[   60.992174]        [<ffffffff81646e66>] __netif_receive_skb_core+0x746/0x980
[   60.992174]        [<ffffffff816470c1>] __netif_receive_skb+0x21/0x70
[   60.992174]        [<ffffffff81647295>] netif_receive_skb_internal+0x35/0x130
[   60.992174]        [<ffffffff81648218>] napi_gro_receive+0x158/0x1d0
[   60.992174]        [<ffffffff81559e05>] e1000_clean_rx_irq+0x155/0x490
[   60.992174]        [<ffffffff8155c1b7>] e1000_clean+0x267/0x990
[   60.992174]        [<ffffffff81647b60>] net_rx_action+0x150/0x360
[   60.992174]        [<ffffffff8105ec43>] __do_softirq+0x123/0x360
[   60.992174]        [<ffffffff8105f12e>] irq_exit+0x8e/0xb0
[   60.992174]        [<ffffffff8179f9f5>] do_IRQ+0x65/0x110
[   60.992174]        [<ffffffff8179da6f>] ret_from_intr+0x0/0x13
[   60.992174]        [<ffffffff8100de9f>] arch_cpu_idle+0xf/0x20
[   60.992174]        [<ffffffff8109dfa6>] cpu_startup_entry+0x2f6/0x3f0
[   60.992174]        [<ffffffff81033cda>] start_secondary+0x13a/0x150
[   60.992174]
-> #0 (&(&n_ptr->lock)->rlock){+.-...}:
[   60.992174]        [<ffffffff810a8f7d>] __lock_acquire+0x163d/0x1ca0
[   60.992174]        [<ffffffff810a9c0c>] lock_acquire+0x9c/0x140
[   60.992174]        [<ffffffff8179c41f>] _raw_spin_lock_bh+0x3f/0x50
[   60.992174]        [<ffffffffa0006dca>] tipc_link_retransmit+0x1aa/0x240 [tipc]
[   60.992174]        [<ffffffffa0001e11>] tipc_bclink_rcv+0x611/0x640 [tipc]
[   60.992174]        [<ffffffffa0008646>] tipc_rcv+0x616/0xac0 [tipc]
[   60.992174]        [<ffffffffa0002ca3>] tipc_l2_rcv_msg+0x73/0xd0 [tipc]
[   60.992174]        [<ffffffff81646e66>] __netif_receive_skb_core+0x746/0x980
[   60.992174]        [<ffffffff816470c1>] __netif_receive_skb+0x21/0x70
[   60.992174]        [<ffffffff81647295>] netif_receive_skb_internal+0x35/0x130
[   60.992174]        [<ffffffff81648218>] napi_gro_receive+0x158/0x1d0
[   60.992174]        [<ffffffff81559e05>] e1000_clean_rx_irq+0x155/0x490
[   60.992174]        [<ffffffff8155c1b7>] e1000_clean+0x267/0x990
[   60.992174]        [<ffffffff81647b60>] net_rx_action+0x150/0x360
[   60.992174]        [<ffffffff8105ec43>] __do_softirq+0x123/0x360
[   60.992174]        [<ffffffff8105f12e>] irq_exit+0x8e/0xb0
[   60.992174]        [<ffffffff8179f9f5>] do_IRQ+0x65/0x110
[   60.992174]        [<ffffffff8179da6f>] ret_from_intr+0x0/0x13
[   60.992174]        [<ffffffff8100de9f>] arch_cpu_idle+0xf/0x20
[   60.992174]        [<ffffffff8109dfa6>] cpu_startup_entry+0x2f6/0x3f0
[   60.992174]        [<ffffffff81033cda>] start_secondary+0x13a/0x150
[   60.992174]
[   60.992174] other info that might help us debug this:
[   60.992174]
[   60.992174]  Possible unsafe locking scenario:
[   60.992174]
[   60.992174]        CPU0                    CPU1
[   60.992174]        ----                    ----
[   60.992174]   lock(&(&bclink->lock)->rlock);
[   60.992174]                                lock(&(&n_ptr->lock)->rlock);
[   60.992174]                                lock(&(&bclink->lock)->rlock);
[   60.992174]   lock(&(&n_ptr->lock)->rlock);
[   60.992174]
[   60.992174]  *** DEADLOCK ***
[   60.992174]
[   60.992174] 3 locks held by swapper/3/0:
[   60.992174]  #0:  (rcu_read_lock){......}, at: [<ffffffff81646791>] __netif_receive_skb_core+0x71/0x980
[   60.992174]  #1:  (rcu_read_lock){......}, at: [<ffffffffa0002c35>] tipc_l2_rcv_msg+0x5/0xd0 [tipc]
[   60.992174]  #2:  (&(&bclink->lock)->rlock){+.-...}, at: [<ffffffffa00004be>] tipc_bclink_lock+0x8e/0xa0 [tipc]
[   60.992174]

The correct the sequence of grabbing n_ptr->lock and bclink->lock
should be that the former is first held and the latter is then taken,
which exactly happened on CPU1. But especially when the retransmission
of broadcast link is failed, bclink->lock is first held in
tipc_bclink_rcv(), and n_ptr->lock is taken in link_retransmit_failure()
called by tipc_link_retransmit() subsequently, which is demonstrated on
CPU0. As a result, deadlock occurs.

If the order of holding the two locks happening on CPU0 is reversed, the
deadlock risk will be relieved. Therefore, the node lock taken in
link_retransmit_failure() originally is moved to tipc_bclink_rcv()
so that it's obtained before bclink lock. But the precondition of
the adjustment of node lock is that responding to bclink reset event
must be moved from tipc_bclink_unlock() to tipc_node_unlock().

Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 1 insertions, 22 deletions

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 7935553..4289dd6 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -62,21 +62,8 @@ static void tipc_bclink_lock(struct net *net)
 static void tipc_bclink_unlock(struct net *net)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct tipc_node *node = NULL;
 
-	if (likely(!tn->bclink->flags)) {
-		spin_unlock_bh(&tn->bclink->lock);
-		return;
-	}
-
-	if (tn->bclink->flags & TIPC_BCLINK_RESET) {
-		tn->bclink->flags &= ~TIPC_BCLINK_RESET;
-		node = tipc_bclink_retransmit_to(net);
-	}
 	spin_unlock_bh(&tn->bclink->lock);
-
-	if (node)
-		tipc_link_reset_all(node);
 }
 
 void tipc_bclink_input(struct net *net)
@@ -91,13 +78,6 @@ uint  tipc_bclink_get_mtu(void)
 	return MAX_PKT_DEFAULT_MCAST;
 }
 
-void tipc_bclink_set_flags(struct net *net, unsigned int flags)
-{
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-
-	tn->bclink->flags |= flags;
-}
-
 static u32 bcbuf_acks(struct sk_buff *buf)
 {
 	return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle;
@@ -156,7 +136,6 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno)
 						seqno : node->bclink.last_sent;
 }
 
-
 /**
  * tipc_bclink_retransmit_to - get most recent node to request retransmission
  *
@@ -476,13 +455,13 @@ void tipc_bclink_rcv(struct net *net, struct sk_buff *buf)
 			goto unlock;
 		if (msg_destnode(msg) == tn->own_addr) {
 			tipc_bclink_acknowledge(node, msg_bcast_ack(msg));
-			tipc_node_unlock(node);
 			tipc_bclink_lock(net);
 			bcl->stats.recv_nacks++;
 			tn->bclink->retransmit_to = node;
 			bclink_retransmit_pkt(tn, msg_bcgap_after(msg),
 					      msg_bcgap_to(msg));
 			tipc_bclink_unlock(net);
+			tipc_node_unlock(node);
 		} else {
 			tipc_node_unlock(node);
 			bclink_peek_nack(net, msg);