[PATCH 4.19 12/42] tipc: fix lockdep warning when reinitilaizing sockets

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



4.19-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jon Maloy <donmalo99@xxxxxxxxx>

[ Upstream commit adba75be0d23cca92a028749d92c60c8909bbdb3 ]

We get the following warning:

[   47.926140] 32-bit node address hash set to 2010a0a
[   47.927202]
[   47.927433] ================================
[   47.928050] WARNING: inconsistent lock state
[   47.928661] 4.19.0+ #37 Tainted: G            E
[   47.929346] --------------------------------
[   47.929954] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[   47.930116] swapper/3/0 [HC0[0]:SC1[3]:HE1:SE0] takes:
[   47.930116] 00000000af8bc31e (&(&ht->lock)->rlock){+.?.}, at: rhashtable_walk_enter+0x36/0xb0
[   47.930116] {SOFTIRQ-ON-W} state was registered at:
[   47.930116]   _raw_spin_lock+0x29/0x60
[   47.930116]   rht_deferred_worker+0x556/0x810
[   47.930116]   process_one_work+0x1f5/0x540
[   47.930116]   worker_thread+0x64/0x3e0
[   47.930116]   kthread+0x112/0x150
[   47.930116]   ret_from_fork+0x3a/0x50
[   47.930116] irq event stamp: 14044
[   47.930116] hardirqs last  enabled at (14044): [<ffffffff9a07fbba>] __local_bh_enable_ip+0x7a/0xf0
[   47.938117] hardirqs last disabled at (14043): [<ffffffff9a07fb81>] __local_bh_enable_ip+0x41/0xf0
[   47.938117] softirqs last  enabled at (14028): [<ffffffff9a0803ee>] irq_enter+0x5e/0x60
[   47.938117] softirqs last disabled at (14029): [<ffffffff9a0804a5>] irq_exit+0xb5/0xc0
[   47.938117]
[   47.938117] other info that might help us debug this:
[   47.938117]  Possible unsafe locking scenario:
[   47.938117]
[   47.938117]        CPU0
[   47.938117]        ----
[   47.938117]   lock(&(&ht->lock)->rlock);
[   47.938117]   <Interrupt>
[   47.938117]     lock(&(&ht->lock)->rlock);
[   47.938117]
[   47.938117]  *** DEADLOCK ***
[   47.938117]
[   47.938117] 2 locks held by swapper/3/0:
[   47.938117]  #0: 0000000062c64f90 ((&d->timer)){+.-.}, at: call_timer_fn+0x5/0x280
[   47.938117]  #1: 00000000ee39619c (&(&d->lock)->rlock){+.-.}, at: tipc_disc_timeout+0xc8/0x540 [tipc]
[   47.938117]
[   47.938117] stack backtrace:
[   47.938117] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G            E     4.19.0+ #37
[   47.938117] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[   47.938117] Call Trace:
[   47.938117]  <IRQ>
[   47.938117]  dump_stack+0x5e/0x8b
[   47.938117]  print_usage_bug+0x1ed/0x1ff
[   47.938117]  mark_lock+0x5b5/0x630
[   47.938117]  __lock_acquire+0x4c0/0x18f0
[   47.938117]  ? lock_acquire+0xa6/0x180
[   47.938117]  lock_acquire+0xa6/0x180
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  _raw_spin_lock+0x29/0x60
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  rhashtable_walk_enter+0x36/0xb0
[   47.938117]  tipc_sk_reinit+0xb0/0x410 [tipc]
[   47.938117]  ? mark_held_locks+0x6f/0x90
[   47.938117]  ? __local_bh_enable_ip+0x7a/0xf0
[   47.938117]  ? lockdep_hardirqs_on+0x20/0x1a0
[   47.938117]  tipc_net_finalize+0xbf/0x180 [tipc]
[   47.938117]  tipc_disc_timeout+0x509/0x540 [tipc]
[   47.938117]  ? call_timer_fn+0x5/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  call_timer_fn+0xa1/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  run_timer_softirq+0x1f2/0x4d0
[   47.938117]  __do_softirq+0xfc/0x413
[   47.938117]  irq_exit+0xb5/0xc0
[   47.938117]  smp_apic_timer_interrupt+0xac/0x210
[   47.938117]  apic_timer_interrupt+0xf/0x20
[   47.938117]  </IRQ>
[   47.938117] RIP: 0010:default_idle+0x1c/0x140
[   47.938117] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 54 55 53 65 8b 2d d8 2b 74 65 0f 1f 44 00 00 e8 c6 2c 8b ff fb f4 <65> 8b 2d c5 2b 74 65 0f 1f 44 00 00 5b 5d 41 5c c3 65 8b 05 b4 2b
[   47.938117] RSP: 0018:ffffaf6ac0207ec8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
[   47.938117] RAX: ffff8f5b3735e200 RBX: 0000000000000003 RCX: 0000000000000001
[   47.938117] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff8f5b3735e200
[   47.938117] RBP: 0000000000000003 R08: 0000000000000001 R09: 0000000000000000
[   47.938117] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[   47.938117] R13: 0000000000000000 R14: ffff8f5b3735e200 R15: ffff8f5b3735e200
[   47.938117]  ? default_idle+0x1a/0x140
[   47.938117]  do_idle+0x1bc/0x280
[   47.938117]  cpu_startup_entry+0x19/0x20
[   47.938117]  start_secondary+0x187/0x1c0
[   47.938117]  secondary_startup_64+0xa4/0xb0

The reason seems to be that tipc_net_finalize()->tipc_sk_reinit() is
calling the function rhashtable_walk_enter() within a timer interrupt.
We fix this by executing tipc_net_finalize() in work queue context.

Acked-by: Ying Xue <ying.xue@xxxxxxxxxxxxx>
Signed-off-by: Jon Maloy <jon.maloy@xxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 net/tipc/discover.c |   19 ++++++++++---------
 net/tipc/net.c      |   45 +++++++++++++++++++++++++++++++++++++--------
 net/tipc/net.h      |    2 +-
 3 files changed, 48 insertions(+), 18 deletions(-)

--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(str
 
 	/* Apply trial address if we just left trial period */
 	if (!trial && !self) {
-		tipc_net_finalize(net, tn->trial_addr);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
@@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct tim
 		goto exit;
 	}
 
-	/* Trial period over ? */
-	if (!time_before(jiffies, tn->addr_trial_end)) {
-		/* Did we just leave it ? */
-		if (!tipc_own_addr(net))
-			tipc_net_finalize(net, tn->trial_addr);
-
-		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
-		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		return;
 	}
 
 	/* Adjust timeout interval according to discovery phase */
@@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct tim
 			d->timer_intv = TIPC_DISC_SLOW;
 		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
 			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 	}
 
 	mod_timer(&d->timer, jiffies + d->timer_intv);
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -104,6 +104,14 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
+struct tipc_net_work {
+	struct work_struct work;
+	struct net *net;
+	u32 addr;
+};
+
+static void tipc_net_finalize(struct net *net, u32 addr);
+
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 {
 	if (tipc_own_id(net)) {
@@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *n
 	return 0;
 }
 
-void tipc_net_finalize(struct net *net, u32 addr)
+static void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	if (!cmpxchg(&tn->node_addr, 0, addr)) {
-		tipc_set_node_addr(net, addr);
-		tipc_named_reinit(net);
-		tipc_sk_reinit(net);
-		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-				     TIPC_CLUSTER_SCOPE, 0, addr);
-	}
+	if (cmpxchg(&tn->node_addr, 0, addr))
+		return;
+	tipc_set_node_addr(net, addr);
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+			     TIPC_CLUSTER_SCOPE, 0, addr);
+}
+
+static void tipc_net_finalize_work(struct work_struct *work)
+{
+	struct tipc_net_work *fwork;
+
+	fwork = container_of(work, struct tipc_net_work, work);
+	tipc_net_finalize(fwork->net, fwork->addr);
+	kfree(fwork);
+}
+
+void tipc_sched_net_finalize(struct net *net, u32 addr)
+{
+	struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC);
+
+	if (!fwork)
+		return;
+	INIT_WORK(&fwork->work, tipc_net_finalize_work);
+	fwork->net = net;
+	fwork->addr = addr;
+	schedule_work(&fwork->work);
 }
 
 void tipc_net_stop(struct net *net)
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -42,7 +42,7 @@
 extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
-void tipc_net_finalize(struct net *net, u32 addr);
+void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);





[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux