[PATCH v5] hrtimer: avoid retrigger_next_event IPI

[Marcelo Tosatti <mtosatti@redhat.com>]

Setting the realtime clock triggers an IPI to all CPUs to reprogram
the clock event device.

However, only realtime and TAI clocks have their offsets updated
(and therefore potentially require a reprogram).

Instead of sending an IPI unconditionally, check each per CPU hrtimer base
whether it has active timers in the CLOCK_REALTIME and CLOCK_TAI bases. If
that's not the case, update the realtime and TAI base offsets remotely and
skip the IPI. This ensures that any subsequently armed timers on
CLOCK_REALTIME and CLOCK_TAI are evaluated with the correct offsets.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

---

v5:
  - Add missing hrtimer_update_base (Peter Xu).

v4:
   - Drop unused code (Thomas).

v3:
   - Nicer changelog  (Thomas).
   - Code style fixes (Thomas).
   - Compilation warning with CONFIG_HIGH_RES_TIMERS=n (Thomas).
   - Shrink preemption disabled section (Thomas).

v2:
   - Only REALTIME and TAI bases are affected by offset-to-monotonic changes (Thomas).
   - Don't special case nohz_full CPUs (Thomas).


diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 5c9d968187ae..06fcc272e28d 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -871,6 +871,19 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
 	tick_program_event(expires, 1);
 }
 
+#define CLOCK_SET_BASES ((1U << HRTIMER_BASE_REALTIME) |	\
+			 (1U << HRTIMER_BASE_REALTIME_SOFT) |	\
+			 (1U << HRTIMER_BASE_TAI) |		\
+			 (1U << HRTIMER_BASE_TAI_SOFT))
+
+static bool need_reprogram_timer(struct hrtimer_cpu_base *cpu_base)
+{
+	if (cpu_base->softirq_activated)
+		return true;
+
+	return (cpu_base->active_bases & CLOCK_SET_BASES) != 0;
+}
+
 /*
  * Clock realtime was set
  *
@@ -885,8 +898,34 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
 void clock_was_set(void)
 {
 #ifdef CONFIG_HIGH_RES_TIMERS
-	/* Retrigger the CPU local events everywhere */
-	on_each_cpu(retrigger_next_event, NULL, 1);
+	cpumask_var_t mask;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+		on_each_cpu(retrigger_next_event, NULL, 1);
+		goto set_timerfd;
+	}
+
+	/* Avoid interrupting CPUs if possible */
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		unsigned long flags;
+		struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+
+		raw_spin_lock_irqsave(&cpu_base->lock, flags);
+		if (need_reprogram_timer(cpu_base))
+			cpumask_set_cpu(cpu, mask);
+		else
+			hrtimer_update_base(cpu_base);
+		raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+	}
+
+	preempt_disable();
+	smp_call_function_many(mask, retrigger_next_event, NULL, 1);
+	preempt_enable();
+	cpus_read_unlock();
+	free_cpumask_var(mask);
+set_timerfd:
 #endif
 	timerfd_clock_was_set();
 }