hrtimer: Avoid unnecessary SMP function calls in clock_was_set()
authorMarcelo Tosatti <mtosatti@redhat.com>
Tue, 13 Jul 2021 13:39:54 +0000 (15:39 +0200)
committerThomas Gleixner <tglx@linutronix.de>
Tue, 10 Aug 2021 15:57:23 +0000 (17:57 +0200)
commit81d741d3460ca422843ce0ec8351083f259c6166
tree885541bd7b985d8840bee06752a764dd88d07678
parent17a1b8826b451c80e7999a7c68e06b70579b2b8f
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
kernel/time/hrtimer.c