Merge: sched/isolation: Prevent boot crash when the boot CPU is nohz_full

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/4811

sched/isolation: Prevent boot crash when the boot CPU is nohz_full

JIRA: https://issues.redhat.com/browse/RHEL-30589

Signed-off-by: Oleg Nesterov <oleg@redhat.com>

Approved-by: Valentin Schneider <vschneid@redhat.com>
Approved-by: Chris von Recklinghausen <crecklin@redhat.com>
Approved-by: Phil Auld <pauld@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Lucas Zampieri <lzampier@redhat.com>

Author: zampierilucas

Documentation/timers/no_hz.rst

@@ -129,11 +129,8 @@ adaptive-tick CPUs:  At least one non-adaptive-tick CPU must remain
 online to handle timekeeping tasks in order to ensure that system
 calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
 (This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
-user processes to observe slight drifts in clock rate.)  Therefore, the
-boot CPU is prohibited from entering adaptive-ticks mode.  Specifying a
-"nohz_full=" mask that includes the boot CPU will result in a boot-time
-error message, and the boot CPU will be removed from the mask.  Note that
-this means that your system must have at least two CPUs in order for
+user processes to observe slight drifts in clock rate.) Note that this
+means that your system must have at least two CPUs in order for
 CONFIG_NO_HZ_FULL=y to do anything for you.
 
 Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded.

kernel/sched/isolation.c

@@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type)
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			if (likely(cpu < nr_cpu_ids))
+				return cpu;
+			/*
+			 * Unless we have another problem this can only happen
+			 * at boot time before start_secondary() brings the 1st
+			 * housekeeping CPU up.
+			 */
+			WARN_ON_ONCE(system_state == SYSTEM_RUNNING ||
+				     type != HK_TYPE_TIMER);
 		}
 	}
 	return smp_processor_id();
@@ -109,6 +118,7 @@ static void __init housekeeping_setup_type(enum hk_type type,
 static int __init housekeeping_setup(char *str, unsigned long flags)
 {
 	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+	unsigned int first_cpu;
 	int err = 0;
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
@@ -129,7 +139,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 	cpumask_andnot(housekeeping_staging,
 		       cpu_possible_mask, non_housekeeping_mask);
 
-	if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+	first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging);
+	if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) {
 		__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
 		__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		if (!housekeeping.flags) {
@@ -138,6 +149,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 		}
 	}
 
+	if (cpumask_empty(non_housekeeping_mask))
+		goto free_housekeeping_staging;
+
 	if (!housekeeping.flags) {
 		/* First setup call ("nohz_full=" or "isolcpus=") */
 		enum hk_type type;

kernel/time/tick-common.c

@@ -179,26 +179,6 @@ 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
  */
@@ -222,19 +202,25 @@ 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(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
 		}