[PATCH v3 25/36] hrtimer: Use irqsave/irqrestore around __run_hrtimer()

[Anna-Maria Gleixner]

__run_hrtimer() is called with the hrtimer_cpu_base.lock held and
interrupts disabled. Before invoking the timer callback the base lock is
dropped, but interrupts stay disabled.

The upcoming support for softirq based hrtimers requires that interrupts
are enabled before the timer callback is invoked.

To avoid code duplication, take hrtimer_cpu_base.lock with
raw_spin_lock_irqsave(flags) at the call site and hand in the flags as
argument. So raw_spin_unlock_irqrestore() before the callback invocation
will either keep interrupts disabled in interrupt context or restore to
interrupt enabled state when called from softirq context.

Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
---
 kernel/time/hrtimer.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 1bb369b1accf..afb54c47e81c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1161,7 +1161,8 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
 
 static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 			  struct hrtimer_clock_base *base,
-			  struct hrtimer *timer, ktime_t *now)
+			  struct hrtimer *timer, ktime_t *now,
+			  unsigned long flags)
 {
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
@@ -1196,11 +1197,11 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	 * protected against migration to a different CPU even if the lock
 	 * is dropped.
 	 */
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 	trace_hrtimer_expire_entry(timer, now);
 	restart = fn(timer);
 	trace_hrtimer_expire_exit(timer);
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irq(&cpu_base->lock);
 
 	/*
 	 * Note: We clear the running state after enqueue_hrtimer and
@@ -1228,7 +1229,8 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	base->running = NULL;
 }
 
-static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
+				 unsigned long flags)
 {
 	struct hrtimer_clock_base *base;
 	unsigned int active = cpu_base->active_bases;
@@ -1259,7 +1261,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 			if (basenow < hrtimer_get_softexpires_tv64(timer))
 				break;
 
-			__run_hrtimer(cpu_base, base, timer, &basenow);
+			__run_hrtimer(cpu_base, base, timer, &basenow, flags);
 		}
 	}
 }
@@ -1274,13 +1276,14 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires_next, now, entry_time, delta;
+	unsigned long flags;
 	int retries = 0;
 
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
 	dev->next_event = KTIME_MAX;
 
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	cpu_base->in_hrtirq = 1;
@@ -1293,7 +1296,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	 */
 	cpu_base->expires_next = KTIME_MAX;
 
-	__hrtimer_run_queues(cpu_base, now);
+	__hrtimer_run_queues(cpu_base, now, flags);
 
 	/* Reevaluate the clock bases for the next expiry */
 	expires_next = __hrtimer_get_next_event(cpu_base);
@@ -1303,7 +1306,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	 */
 	cpu_base->expires_next = expires_next;
 	cpu_base->in_hrtirq = 0;
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
 	/* Reprogramming necessary ? */
 	if (!tick_program_event(expires_next, 0)) {
@@ -1324,7 +1327,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	 * Acquire base lock for updating the offsets and retrieving
 	 * the current time.
 	 */
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
@@ -1337,7 +1340,8 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	 */
 	cpu_base->nr_hangs++;
 	cpu_base->hang_detected = 1;
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+
 	delta = ktime_sub(now, entry_time);
 	if ((unsigned int)delta > cpu_base->max_hang_time)
 		cpu_base->max_hang_time = (unsigned int) delta;
@@ -1379,6 +1383,7 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 void hrtimer_run_queues(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	unsigned long flags;
 	ktime_t now;
 
 	if (__hrtimer_hres_active(cpu_base))
@@ -1396,10 +1401,10 @@ void hrtimer_run_queues(void)
 		return;
 	}
 
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	now = hrtimer_update_base(cpu_base);
-	__hrtimer_run_queues(cpu_base, now);
-	raw_spin_unlock(&cpu_base->lock);
+	__hrtimer_run_queues(cpu_base, now, flags);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 }
 
 /*
-- 
2.11.0