rcu: Fix deadlock in TREE_PREEMPT_RCU CPU stall detection

Under TREE_PREEMPT_RCU, print_other_cpu_stall() invokes
rcu_print_task_stall() with the root rcu_node structure's ->lock
held, and rcu_print_task_stall() acquires that same lock for
self-deadlock. Fix this by removing the lock acquisition from
rcu_print_task_stall(), and making all callers acquire the lock
instead.

Tested-by: John Kacur <jkacur@redhat.com>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Located-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-19-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 65a807b..b07be37 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -476,7 +476,9 @@
 
 	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rcu_print_task_stall(rnp);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		if (rnp->qsmask == 0)
 			continue;
 		for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index a8b2e83..aecfe37 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -318,18 +318,15 @@
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
-	unsigned long flags;
 	struct list_head *lp;
 	int phase;
 	struct task_struct *t;
 
 	if (rcu_preempted_readers(rnp)) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
 		phase = rnp->gpnum & 0x1;
 		lp = &rnp->blocked_tasks[phase];
 		list_for_each_entry(t, lp, rcu_node_entry)
 			printk(" P%d", t->pid);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 }