[PATCH v5 4/6] sched/isolation: Force housekeeping if isolcpus and nohz_full don't leave any

[Gabriele Monaco]

Currently the user can set up isolcpus and nohz_full in such a way that
leaves no housekeeping CPU (i.e. no CPU that is neither domain isolated
nor nohz full). This can be a problem for other subsystems (e.g. the
timer wheel imgration).

Prevent this configuration by setting the boot CPU as housekeeping if
the union of isolcpus and nohz_full covers all CPUs. In a similar
fashion as it already happens if either of them covers all CPUs.

Signed-off-by: Gabriele Monaco <gmonaco@xxxxxxxxxx>
---
 include/linux/tick.h     |  2 ++
 kernel/sched/isolation.c | 20 ++++++++++++++++++++
 kernel/time/tick-sched.c |  7 +++++++
 3 files changed, 29 insertions(+)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index b8ddc8e631a3..0b32c0bd3512 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -278,6 +278,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void __tick_nohz_task_switch(void);
 extern void __init tick_nohz_full_setup(cpumask_var_t cpumask);
+extern void __init tick_nohz_full_clear_cpu(unsigned int cpu);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
@@ -304,6 +305,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void __tick_nohz_task_switch(void) { }
 static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { }
+static inline void tick_nohz_full_clear_cpu(unsigned int cpu) { }
 #endif
 
 static inline void tick_nohz_task_switch(void)
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 81bc8b329ef1..27b65b401534 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -165,6 +165,26 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 			}
 		}
 
+		/* Check in combination with the previously set cpumask */
+		type = find_first_bit(&housekeeping.flags, HK_TYPE_MAX);
+		first_cpu = cpumask_first_and_and(cpu_present_mask,
+						  housekeeping_staging,
+						  housekeeping.cpumasks[type]);
+		if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) {
+			pr_warn("Housekeeping: must include one present CPU neither "
+				"in nohz_full= nor in isolcpus=, using boot CPU:%d\n",
+				smp_processor_id());
+			for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX)
+				__cpumask_set_cpu(smp_processor_id(),
+						  housekeeping.cpumasks[type]);
+			__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+			tick_nohz_full_clear_cpu(smp_processor_id());
+
+			if (cpumask_empty(non_housekeeping_mask))
+				goto free_housekeeping_staging;
+		}
+
 		iter_flags = flags & ~housekeeping.flags;
 
 		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c527b421c865..2969ed13d1f4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -604,6 +604,13 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 	tick_nohz_full_running = true;
 }
 
+/* Called if boot-time nohz CPU list changes during initialisation. */
+void __init tick_nohz_full_clear_cpu(unsigned int cpu)
+{
+	if (tick_nohz_full_running)
+		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+}
+
 bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
 {
 	/*
-- 
2.49.0