hrtimer: Report offline hrtimer enqueue

The hrtimers migration on CPU-down hotplug process has been moved
earlier, before the CPU actually goes to die. This leaves a small window
of opportunity to queue an hrtimer in a blind spot, leaving it ignored.

For example a practical case has been reported with RCU waking up a
SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that
way a sched/rt timer to the local offline CPU.

Make sure such situations never go unnoticed and warn when that happens.

Fixes: 5c0930c ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Reported-by: Paul E. McKenney <[email protected]>
Signed-off-by: Frederic Weisbecker <[email protected]>
Signed-off-by: Paul E. McKenney <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]

Author: Frederic Weisbecker

include/linux/hrtimer.h

@@ -157,6 +157,7 @@ enum  hrtimer_base_type {
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
  *			 expired
+ * @online:		CPU is online from an hrtimers point of view
  * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
  *			callback to finish.
  * @expires_next:	absolute time of the next event, is required for remote
@@ -179,7 +180,8 @@ struct hrtimer_cpu_base {
 	unsigned int			hres_active		: 1,
 					in_hrtirq		: 1,
 					hang_detected		: 1,
-					softirq_activated       : 1;
+					softirq_activated       : 1,
+					online			: 1;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	unsigned int			nr_events;
 	unsigned short			nr_retries;

kernel/time/hrtimer.c

@@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 			   enum hrtimer_mode mode)
 {
 	debug_activate(timer, mode);
+	WARN_ON_ONCE(!base->cpu_base->online);
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
@@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+	cpu_base->online = 1;
 	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
@@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
 	raw_spin_unlock(&new_base->lock);
+	old_base->online = 0;
 	raw_spin_unlock(&old_base->lock);
 
 	return 0;