Entering RCU idle mode may cause a deferred wake up of an RCU NOCB_GP
kthread (rcuog) to be serviced.
Usually a local wake up happening while running the idle task is handled
in one of the need_resched() checks carefully placed within the idle
loop that can break to the scheduler.
Unfortunately the call to rcu_idle_enter() is already beyond the last
generic need_resched() check and we may halt the CPU with a resched
request unhandled, leaving the task hanging.
Fix this with splitting the rcuog wakeup handling from rcu_idle_enter()
and place it before the last generic need_resched() check in the idle
loop. It is then assumed that no call to call_rcu() will be performed
after that in the idle loop until the CPU is put in low power mode.
Reported-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Fixes: 96d3fd0d315a (rcu: Break call_rcu() deadlock involving scheduler and perf)
Cc: stable@xxxxxxxxxxxxxxx
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
---
include/linux/rcupdate.h | 2 ++
kernel/rcu/tree.c | 3 ---
kernel/rcu/tree_plugin.h | 5 +++++
kernel/sched/idle.c | 3 +++
4 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index fd02c5fa60cb..36c2119de702 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -110,8 +110,10 @@ static inline void rcu_user_exit(void) { }
#ifdef CONFIG_RCU_NOCB_CPU
void rcu_init_nohz(void);
+void rcu_nocb_flush_deferred_wakeup(void);
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
static inline void rcu_init_nohz(void) { }
+static inline void rcu_nocb_flush_deferred_wakeup(void) { }
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
/**
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 63032e5620b9..82838e93b498 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -671,10 +671,7 @@ static noinstr void rcu_eqs_enter(bool user)
*/
void rcu_idle_enter(void)
{
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
lockdep_assert_irqs_disabled();
- do_nocb_deferred_wakeup(rdp);
rcu_eqs_enter(false);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7e291ce0a1d6..d5b38c28abd1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2187,6 +2187,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
do_nocb_deferred_wakeup_common(rdp);
}
+void rcu_nocb_flush_deferred_wakeup(void)
+{
+ do_nocb_deferred_wakeup(this_cpu_ptr(&rcu_data));
+}
+
void __init rcu_init_nohz(void)
{
int cpu;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 305727ea0677..b601a3aa2152 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -55,6 +55,7 @@ __setup("hlt", cpu_idle_nopoll_setup);
static noinline int __cpuidle cpu_idle_poll(void)
{
trace_cpu_idle(0, smp_processor_id());
+ rcu_nocb_flush_deferred_wakeup();
stop_critical_timings();
rcu_idle_enter();
local_irq_enable();
@@ -173,6 +174,8 @@ static void cpuidle_idle_call(void)
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
+ rcu_nocb_flush_deferred_wakeup();
+
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
--
2.25.1
