It was possible that sync_rcu_exp_select_cpus() enqueued something on
CPU0 while CPU0 was offline. Such a work item wouldn't be processed
until CPU0 gets back online. This problem was addressed in commit
fcc6354365015 ("rcu: Make expedited GPs handle CPU 0 being offline"). I
don't think the issue fully addressed.
Assume grplo = 0 and grphi = 7 and sync_rcu_exp_select_cpus() is invoked
on CPU1. The preempt_disable() section on CPU1 won't ensure that CPU0
remains online between looking at cpu_online_mask and invoking
queue_work_on() on CPU1.
Use cpus_read_lock() to ensure that `cpu' is not going down between
looking at cpu_online_mask at invoking queue_work_on() and waiting for
its completion. It is added around the loop + flush_work() which is
similar to work_on_cpu_safe() (and we can have multiple jobs running on
NUMA systems).
Fixes: fcc6354365015 ("rcu: Make expedited GPs handle CPU 0 being
offline")
Signed-off-by: Sebastian Andrzej Siewior <bige...@linutronix.de>
---
kernel/rcu/tree_exp.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 01b6ddeb4f050..a104cf91e6b90 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -479,6 +479,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
sync_exp_reset_tree(rsp);
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp),
TPS("select"));
+ cpus_read_lock();
/* Schedule work for each leaf rcu_node structure. */
rcu_for_each_leaf_node(rsp, rnp) {
rnp->exp_need_flush = false;
@@ -493,13 +494,11 @@ static void sync_rcu_exp_select_cpus(struct rcu_state
*rsp,
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
- preempt_disable();
cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
/* If all offline, queue the work on an unbound CPU. */
if (unlikely(cpu > rnp->grphi))
cpu = WORK_CPU_UNBOUND;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
- preempt_enable();
rnp->exp_need_flush = true;
}
@@ -507,6 +506,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
rcu_for_each_leaf_node(rsp, rnp)
if (rnp->exp_need_flush)
flush_work(&rnp->rew.rew_work);
+ cpus_read_unlock();
}
static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
--
2.19.0.rc2
