From f757fe9192aaa91e552288749401fd39e6619dbf Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Sat, 18 Sep 2021 20:40:48 -0700
Subject: [PATCH] rcu-tasks: Don't remove tasks with pending IPIs from holdout
list
References: bnc#1189998 (PREEMPT_RT prerequisite backports)
Patch-mainline: v5.17-rc0
Git-commit: f5dbc594b5bac1fa694174032b8d3d0249945fd3
Currently, the check_all_holdout_tasks_trace() function removes all tasks
marked with ->trc_reader_checked from the holdout list, including those
with IPIs pending. This means that the IPI handler might arrive at
a task that has already been removed from the list, which is at best
an accident waiting to happen.
This commit therefore avoids removing tasks with IPIs pending from
the holdout list. This in turn means that the "if" condition in the
for_each_online_cpu() loop in rcu_tasks_trace_postgp() should always
evaluate to false, so a WARN_ON_ONCE() is added to check that.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/rcu/tasks.h | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index e410d62202f7..db2a148ce0c8 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1121,7 +1121,8 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
trc_wait_for_one_reader(t, hop);
// If check succeeded, remove this task from the list.
- if (READ_ONCE(t->trc_reader_checked))
+ if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 &&
+ READ_ONCE(t->trc_reader_checked))
trc_del_holdout(t);
else if (needreport)
show_stalled_task_trace(t, firstreport);
@@ -1156,7 +1157,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
// Yes, this assumes that CPUs process IPIs in order. If that ever
// changes, there will need to be a recheck and/or timed wait.
for_each_online_cpu(cpu)
- if (smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu)))
+ if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu))))
smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
// Remove the safety count.