The only thing that prevented an rdp leader from being de-offloaded was
the nocb_bypass_timer that used to lock the nocb_lock of the rdp leader.
If an rdp gets de-offloaded, it will subtely ignore rcu_nocb_lock()
calls and do its job in the timer unsafely. Worse yet: if it gets
re-offloaded in the middle of the timer, rcu_nocb_unlock() would try to
unlock, leaving it imbalanced.
Now that the nocb_bypass_timer doesn't use the nocb_lock anymore, we can
safely allow rdp leader to be de-offloaded.
Reported-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
Cc: Lai Jiangshan <jiangshanlai@xxxxxxxxx>
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
Cc: Neeraj Upadhyay <neeraju@xxxxxxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
---
kernel/rcu/tree_plugin.h | 4 ----
1 file changed, 4 deletions(-)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c80b214a86bb..0fdf0223f08f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2500,10 +2500,6 @@ int rcu_nocb_cpu_deoffload(int cpu)
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
int ret = 0;
- if (rdp == rdp->nocb_gp_rdp) {
- pr_info("Can't deoffload an rdp GP leader (yet)\n");
- return -EINVAL;
- }
mutex_lock(&rcu_state.barrier_mutex);
cpus_read_lock();
if (rcu_rdp_is_offloaded(rdp)) {
--
2.25.1
