summaryrefslogtreecommitdiff
path: root/kernel/rcu/tree.c
diff options
context:
space:
mode:
authorPaul E. McKenney <paulmck@linux.vnet.ibm.com>2016-11-29 05:49:06 -0800
committerPaul E. McKenney <paulmck@linux.vnet.ibm.com>2017-01-23 11:37:12 -0800
commit7aa92230c9e86b2150f718185f70e0af592e290b (patch)
treea0402e24bc7048f590a7bffce9953845dfdc5fb9 /kernel/rcu/tree.c
parentb201fa67371862229f27a1f022196423aa5c7381 (diff)
rcu: Once again use NMI-based stack traces in stall warnings
This commit is for all intents and purposes a revert of bc1dce514e9b ("rcu: Don't use NMIs to dump other CPUs' stacks"). The reason to suppose that this can now safely be reverted is the presence of 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI"), which is said to have made NMI-based stack dumps safe. However, this reversion keeps one nice property of bc1dce514e9b ("rcu: Don't use NMIs to dump other CPUs' stacks"), namely that only those CPUs blocking the grace period are dumped. The new trigger_single_cpu_backtrace() is used to make this happen, as suggested by Josh Poimboeuf. Reported-by: Vince Weaver <vincent.weaver@maine.edu> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Diffstat (limited to 'kernel/rcu/tree.c')
-rw-r--r--kernel/rcu/tree.c12
1 files changed, 7 insertions, 5 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5a4aaad75e76..d7b63b88434b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1278,7 +1278,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
}
/*
- * Dump stacks of all tasks running on stalled CPUs.
+ * Dump stacks of all tasks running on stalled CPUs. First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps. The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
*/
static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
{
@@ -1288,11 +1291,10 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rnp->qsmask != 0) {
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+ for_each_leaf_node_possible_cpu(rnp, cpu)
+ if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+ if (!trigger_single_cpu_backtrace(cpu))
dump_cpu_task(cpu);
- }
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}