hrtimer: Avoid unnecessary SMP function calls in clock_was_set()

Setting of clocks triggers an unconditional SMP function call on all online
CPUs to reprogram the clock event device.

However, only some clocks have their offsets updated and therefore
potentially require a reprogram. That's CLOCK_REALTIME and CLOCK_TAI and in
the case of resume (delayed sleep time injection) also CLOCK_BOOTTIME.

Instead of sending an IPI unconditionally, check each per CPU hrtimer base
whether it has active timers in the affected clock bases which are
indicated by the caller in the @bases argument of clock_was_set().

If that's not the case, skip the IPI and update the offsets remotely which
ensures that any subsequently armed timers on the affected clocks are
evaluated with the correct offsets.

[ tglx: Adopted to the new bases argument, removed the softirq_active
  	check, added comment, fixed up stale comment ]

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210713135158.787536542@linutronix.de

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c8af165..5d44c90 100644 (file)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -882,11 +882,42 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
  */
 void clock_was_set(unsigned int bases)
 {
+       cpumask_var_t mask;
+       int cpu;
+
        if (!hrtimer_hres_active() && !tick_nohz_active)
                goto out_timerfd;
 
-       /* Retrigger the CPU local events everywhere */
-       on_each_cpu(retrigger_next_event, NULL, 1);
+       if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+               on_each_cpu(retrigger_next_event, NULL, 1);
+               goto out_timerfd;
+       }
+
+       /* Avoid interrupting CPUs if possible */
+       cpus_read_lock();
+       for_each_online_cpu(cpu) {
+               struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+               unsigned long flags;
+
+               raw_spin_lock_irqsave(&cpu_base->lock, flags);
+               /*
+                * Only send the IPI when there are timers queued in one of
+                * the affected clock bases. Otherwise update the base
+                * remote to ensure that the next enqueue of a timer on
+                * such a clock base will see the correct offsets.
+                */
+               if (cpu_base->active_bases & bases)
+                       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);
 
 out_timerfd:
        timerfd_clock_was_set();