@@ -104,8 +104,10 @@ 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 */
/**
@@ -670,10 +670,7 @@ 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);
@@ -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;
@@ -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.
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. Further debug code will help spotting the offenders. Reported-by: Paul E. McKenney <paulmck@kernel.org> Fixes: 96d3fd0d315a (rcu: Break call_rcu() deadlock involving scheduler and perf) Cc: stable@vger.kernel.org Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar<mingo@kernel.org> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> --- 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(-)