sched/isolation: Handle the nohz_full= parameter

We want to centralize the isolation management, done by the housekeeping
subsystem. Therefore we need to handle the nohz_full= parameter from
there.

Since nohz_full= so far has involved unbound timers, watchdog, RCU
and tilegx NAPI isolation, we keep that default behaviour.

nohz_full= will be deprecated in the future. We want to control
the isolation features from the isolcpus= parameter.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Wanpeng Li <kernellwp@gmail.com>
Link: http://lkml.kernel.org/r/1509072159-31808-10-git-send-email-frederic@kernel.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched/isolation.h

@@ -10,6 +10,7 @@ enum hk_flags {
 	HK_FLAG_RCU		= (1 << 1),
 	HK_FLAG_MISC		= (1 << 2),
 	HK_FLAG_SCHED		= (1 << 3),
+	HK_FLAG_TICK		= (1 << 4),
 };
 
 #ifdef CONFIG_CPU_ISOLATION

include/linux/tick.h

@@ -228,6 +228,7 @@ 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);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
@@ -248,6 +249,7 @@ 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) { }
 #endif
 
 static inline void tick_nohz_task_switch(void)

init/Kconfig

@@ -474,7 +474,6 @@ endmenu # "CPU/Task time and stats accounting"
 
 config CPU_ISOLATION
 	bool "CPU isolation"
-	depends on NO_HZ_FULL
 	help
 	  Make sure that CPUs running critical tasks are not disturbed by
 	  any source of "noise" such as unbound workqueues, timers, kthreads...

kernel/sched/isolation.c

@@ -54,23 +54,41 @@ EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
 
 void __init housekeeping_init(void)
 {
-	if (!tick_nohz_full_enabled())
+	if (!housekeeping_flags)
 		return;
 
-	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
-		WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n");
-		cpumask_clear(tick_nohz_full_mask);
-		tick_nohz_full_running = false;
-		return;
+	static_branch_enable(&housekeeping_overriden);
+
+	/* We need at least one CPU to handle housekeeping work */
+	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+static int __init housekeeping_nohz_full_setup(char *str)
+{
+	cpumask_var_t non_housekeeping_mask;
+
+	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
+	if (cpulist_parse(str, non_housekeeping_mask) < 0) {
+		pr_warn("Housekeeping: Incorrect nohz_full cpumask\n");
+		free_bootmem_cpumask_var(non_housekeeping_mask);
+		return 0;
 	}
 
-	cpumask_andnot(housekeeping_mask,
-		       cpu_possible_mask, tick_nohz_full_mask);
+	alloc_bootmem_cpumask_var(&housekeeping_mask);
+	cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask);
 
-	housekeeping_flags = HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+	if (cpumask_empty(housekeeping_mask))
+		cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
 
-	static_branch_enable(&housekeeping_overriden);
+	housekeeping_flags = HK_FLAG_TICK | HK_FLAG_TIMER |
+				HK_FLAG_RCU | HK_FLAG_MISC;
 
-	/* We need at least one CPU to handle housekeeping work */
-	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
+	tick_nohz_full_setup(non_housekeeping_mask);
+
+	free_bootmem_cpumask_var(non_housekeeping_mask);
+
+	return 1;
 }
+__setup("nohz_full=", housekeeping_nohz_full_setup);
+#endif

kernel/time/tick-sched.c

@@ -385,20 +385,13 @@ void __tick_nohz_task_switch(void)
 	local_irq_restore(flags);
 }
 
-/* Parse the boot-time nohz CPU list from the kernel parameters. */
-static int __init tick_nohz_full_setup(char *str)
+/* Get the boot-time nohz CPU list from the kernel parameters. */
+void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 {
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
-	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
-		pr_warn("NO_HZ: Incorrect nohz_full cpumask\n");
-		free_bootmem_cpumask_var(tick_nohz_full_mask);
-		return 1;
-	}
+	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
-
-	return 1;
 }
-__setup("nohz_full=", tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down(unsigned int cpu)
 {