tick/nohz_full: Don't abuse smp_call_function_single() in tick_setup_device()

After the recent commit 5097cbcb38e6 ("sched/isolation: Prevent boot crash
when the boot CPU is nohz_full") the kernel no longer crashes, but there is
another problem.

In this case tick_setup_device() calls tick_take_do_timer_from_boot() to
update tick_do_timer_cpu and this triggers the WARN_ON_ONCE(irqs_disabled)
in smp_call_function_single().

Kill tick_take_do_timer_from_boot() and just use WRITE_ONCE(), the new
comment explains why this is safe (thanks Thomas!).

Fixes: 08ae95f4fd3b ("nohz_full: Allow the boot CPU to be nohz_full")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240528122019.GA28794@redhat.com
Link: https://lore.kernel.org/all/20240522151742.GA10400@redhat.com

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index d88b13076b7944e54fefb2802d914f8f7fe1abf5..a47bcf71defcf5afdf4edae01d27287e73f1d56a 100644 (file)
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -178,26 +178,6 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
        }
 }
 
-#ifdef CONFIG_NO_HZ_FULL
-static void giveup_do_timer(void *info)
-{
-       int cpu = *(unsigned int *)info;
-
-       WARN_ON(tick_do_timer_cpu != smp_processor_id());
-
-       tick_do_timer_cpu = cpu;
-}
-
-static void tick_take_do_timer_from_boot(void)
-{
-       int cpu = smp_processor_id();
-       int from = tick_do_timer_boot_cpu;
-
-       if (from >= 0 && from != cpu)
-               smp_call_function_single(from, giveup_do_timer, &cpu, 1);
-}
-#endif
-
 /*
  * Setup the tick device
  */
@@ -221,19 +201,25 @@ static void tick_setup_device(struct tick_device *td,
                        tick_next_period = ktime_get();
 #ifdef CONFIG_NO_HZ_FULL
                        /*
-                        * The boot CPU may be nohz_full, in which case set
-                        * tick_do_timer_boot_cpu so the first housekeeping
-                        * secondary that comes up will take do_timer from
-                        * us.
+                        * The boot CPU may be nohz_full, in which case the
+                        * first housekeeping secondary will take do_timer()
+                        * from it.
                         */
                        if (tick_nohz_full_cpu(cpu))
                                tick_do_timer_boot_cpu = cpu;
 
-               } else if (tick_do_timer_boot_cpu != -1 &&
-                                               !tick_nohz_full_cpu(cpu)) {
-                       tick_take_do_timer_from_boot();
+               } else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) {
                        tick_do_timer_boot_cpu = -1;
-                       WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu);
+                       /*
+                        * The boot CPU will stay in periodic (NOHZ disabled)
+                        * mode until clocksource_done_booting() called after
+                        * smp_init() selects a high resolution clocksource and
+                        * timekeeping_notify() kicks the NOHZ stuff alive.
+                        *
+                        * So this WRITE_ONCE can only race with the READ_ONCE
+                        * check in tick_periodic() but this race is harmless.
+                        */
+                       WRITE_ONCE(tick_do_timer_cpu, cpu);
 #endif
                }