patches/add_migrate_disable.patch

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Sat, 27 May 2017 19:02:06 +0200
Subject: kernel/sched/core: add migrate_disable()

---
 include/linux/preempt.h |   23 ++++++++
 include/linux/sched.h   |    7 ++
 include/linux/smp.h     |    3 +
 kernel/sched/core.c     |  130 +++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/debug.c    |    4 +
 5 files changed, 165 insertions(+), 2 deletions(-)

--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -184,6 +184,22 @@ do { \
 
 #define preemptible()	(preempt_count() == 0 && !irqs_disabled())
 
+#ifdef CONFIG_SMP
+
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+
+int __migrate_disabled(struct task_struct *p);
+
+#else
+#define migrate_disable()		barrier()
+#define migrate_enable()		barrier()
+static inline int __migrate_disabled(struct task_struct *p)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_PREEMPT
 #define preempt_enable() \
 do { \
@@ -252,6 +268,13 @@ do { \
 #define preempt_enable_notrace()		barrier()
 #define preemptible()				0
 
+#define migrate_disable()			barrier()
+#define migrate_enable()			barrier()
+
+static inline int __migrate_disabled(struct task_struct *p)
+{
+	return 0;
+}
 #endif /* CONFIG_PREEMPT_COUNT */
 
 #ifdef MODULE
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -537,6 +537,13 @@ struct task_struct {
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+	int				migrate_disable;
+	int				migrate_disable_update;
+# ifdef CONFIG_SCHED_DEBUG
+	int				migrate_disable_atomic;
+# endif
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -197,6 +197,9 @@ static inline int get_boot_cpu_id(void)
 #define get_cpu()		({ preempt_disable(); smp_processor_id(); })
 #define put_cpu()		preempt_enable()
 
+#define get_cpu_light()		({ migrate_disable(); smp_processor_id(); })
+#define put_cpu_light()		migrate_enable()
+
 /*
  * Callback to arch code if there's nosmp or maxcpus=0 on the
  * boot command line:
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1047,7 +1047,15 @@ void set_cpus_allowed_common(struct task
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+int __migrate_disabled(struct task_struct *p)
+{
+	return p->migrate_disable;
+}
+#endif
+
+static void __do_set_cpus_allowed_tail(struct task_struct *p,
+				       const struct cpumask *new_mask)
 {
 	struct rq *rq = task_rq(p);
 	bool queued, running;
@@ -1076,6 +1084,20 @@ void do_set_cpus_allowed(struct task_str
 		set_curr_task(rq, p);
 }
 
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+	if (__migrate_disabled(p)) {
+		lockdep_assert_held(&p->pi_lock);
+
+		cpumask_copy(&p->cpus_mask, new_mask);
+		p->migrate_disable_update = 1;
+		return;
+	}
+#endif
+	__do_set_cpus_allowed_tail(p, new_mask);
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -1134,9 +1156,16 @@ static int __set_cpus_allowed_ptr(struct
 	}
 
 	/* Can the task run on the task's current CPU? If so, we're done */
-	if (cpumask_test_cpu(task_cpu(p), new_mask))
+	if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
 		goto out;
 
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+	if (__migrate_disabled(p)) {
+		p->migrate_disable_update = 1;
+		goto out;
+	}
+#endif
+
 	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
 	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
@@ -7357,3 +7386,100 @@ const u32 sched_prio_to_wmult[40] = {
  /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
+
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+
+void migrate_disable(void)
+{
+	struct task_struct *p = current;
+
+	if (in_atomic() || irqs_disabled()) {
+#ifdef CONFIG_SCHED_DEBUG
+		p->migrate_disable_atomic++;
+#endif
+		return;
+	}
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(p->migrate_disable_atomic);
+#endif
+
+	if (p->migrate_disable) {
+		p->migrate_disable++;
+		return;
+	}
+
+	preempt_disable();
+	p->migrate_disable = 1;
+
+	p->cpus_ptr = cpumask_of(smp_processor_id());
+	p->nr_cpus_allowed = 1;
+
+	preempt_enable();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+void migrate_enable(void)
+{
+	struct task_struct *p = current;
+
+	if (in_atomic() || irqs_disabled()) {
+#ifdef CONFIG_SCHED_DEBUG
+		p->migrate_disable_atomic--;
+#endif
+		return;
+	}
+
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(p->migrate_disable_atomic);
+#endif
+
+	WARN_ON_ONCE(p->migrate_disable <= 0);
+	if (p->migrate_disable > 1) {
+		p->migrate_disable--;
+		return;
+	}
+
+	preempt_disable();
+
+	p->cpus_ptr = &p->cpus_mask;
+	p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask);
+	p->migrate_disable = 0;
+
+	if (p->migrate_disable_update) {
+		struct rq *rq;
+		struct rq_flags rf;
+
+		rq = task_rq_lock(p, &rf);
+		update_rq_clock(rq);
+
+		__do_set_cpus_allowed_tail(p, &p->cpus_mask);
+		task_rq_unlock(rq, p, &rf);
+
+		p->migrate_disable_update = 0;
+
+		WARN_ON(smp_processor_id() != task_cpu(p));
+		if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
+			const struct cpumask *cpu_valid_mask = cpu_active_mask;
+			struct migration_arg arg;
+			unsigned int dest_cpu;
+
+			if (p->flags & PF_KTHREAD) {
+				/*
+				 * Kernel threads are allowed on online && !active CPUs
+				 */
+				cpu_valid_mask = cpu_online_mask;
+			}
+			dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask);
+			arg.task = p;
+			arg.dest_cpu = dest_cpu;
+
+			preempt_enable();
+			stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
+			tlb_migrate_finish(p->mm);
+			return;
+		}
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL(migrate_enable);
+#endif
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -958,6 +958,10 @@ void proc_sched_show_task(struct task_st
 		P(dl.runtime);
 		P(dl.deadline);
 	}
+#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP)
+	P(migrate_disable);
+#endif
+	P(nr_cpus_allowed);
 #undef PN_SCHEDSTAT
 #undef PN
 #undef __PN