1 files changed, 123 insertions, 65 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..bfa7452ca92e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,7 +26,10 @@
 #include <linux/topology.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/cond_resched.h>
+#include <linux/sched/cputime.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/init.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
@@ -145,12 +148,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8;
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 #endif
 
-/*
- * period over which we measure -rt task CPU usage in us.
- * default: 1s
- */
-unsigned int sysctl_sched_rt_period = 1000000;
-
 __read_mostly int scheduler_running;
 
 #ifdef CONFIG_SCHED_CORE
@@ -445,13 +442,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
 #endif /* CONFIG_SCHED_CORE */
 
 /*
- * part of the period that we allow rt tasks to run in us.
- * default: 0.95s
- */
-int sysctl_sched_rt_runtime = 950000;
-
-
-/*
  * Serialization rules:
  *
  * Lock order:
@@ -610,10 +600,10 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 		swap(rq1, rq2);
 
 	raw_spin_rq_lock(rq1);
-	if (__rq_lockp(rq1) == __rq_lockp(rq2))
-		return;
+	if (__rq_lockp(rq1) != __rq_lockp(rq2))
+		raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
 
-	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+	double_rq_clock_clear_update(rq1, rq2);
 }
 #endif
 
@@ -1319,10 +1309,10 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 static DEFINE_MUTEX(uclamp_mutex);
 
 /* Max allowed minimum utilization */
-unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 
 /* Max allowed maximum utilization */
-unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
 /*
  * By default RT tasks run at the maximum performance point/capacity of the
@@ -1339,7 +1329,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
  * This knob will not override the system default sched_util_clamp_min defined
  * above.
  */
-unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
 
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
@@ -1469,33 +1459,6 @@ static void uclamp_update_util_min_rt_default(struct task_struct *p)
 	task_rq_unlock(rq, p, &rf);
 }
 
-static void uclamp_sync_util_min_rt_default(void)
-{
-	struct task_struct *g, *p;
-
-	/*
-	 * copy_process()			sysctl_uclamp
-	 *					  uclamp_min_rt = X;
-	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
-	 *   // link thread			  smp_mb__after_spinlock()
-	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
-	 *   sched_post_fork()			  for_each_process_thread()
-	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
-	 *
-	 * Ensures that either sched_post_fork() will observe the new
-	 * uclamp_min_rt or for_each_process_thread() will observe the new
-	 * task.
-	 */
-	read_lock(&tasklist_lock);
-	smp_mb__after_spinlock();
-	read_unlock(&tasklist_lock);
-
-	rcu_read_lock();
-	for_each_process_thread(g, p)
-		uclamp_update_util_min_rt_default(p);
-	rcu_read_unlock();
-}
-
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -1775,6 +1738,11 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css)
 }
 
 static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+#endif
+
+#ifdef CONFIG_SYSCTL
+#ifdef CONFIG_UCLAMP_TASK
+#ifdef CONFIG_UCLAMP_TASK_GROUP
 static void uclamp_update_root_tg(void)
 {
 	struct task_group *tg = &root_task_group;
@@ -1792,7 +1760,34 @@ static void uclamp_update_root_tg(void)
 static void uclamp_update_root_tg(void) { }
 #endif
 
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	for_each_process_thread(g, p)
+		uclamp_update_util_min_rt_default(p);
+	rcu_read_unlock();
+}
+
+static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
@@ -1856,6 +1851,8 @@ done:
 
 	return result;
 }
+#endif
+#endif
 
 static int uclamp_validate(struct task_struct *p,
 			   const struct sched_attr *attr)
@@ -2190,7 +2187,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	else if (p->sched_class > rq->curr->sched_class)
+	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
 		resched_curr(rq);
 
 	/*
@@ -2408,7 +2405,7 @@ static int migration_cpu_stop(void *data)
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
-	flush_smp_call_function_from_idle();
+	flush_smp_call_function_queue();
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
@@ -4430,7 +4427,7 @@ out:
 __setup("schedstats=", setup_schedstats);
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -4452,6 +4449,52 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 #endif /* CONFIG_PROC_SYSCTL */
 #endif /* CONFIG_SCHEDSTATS */
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_core_sysctls[] = {
+#ifdef CONFIG_SCHEDSTATS
+	{
+		.procname       = "sched_schedstats",
+		.data           = NULL,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_schedstats,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_UCLAMP_TASK
+	{
+		.procname       = "sched_util_clamp_min",
+		.data           = &sysctl_sched_uclamp_util_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_max",
+		.data           = &sysctl_sched_uclamp_util_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_min_rt_default",
+		.data           = &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+#endif /* CONFIG_UCLAMP_TASK */
+	{}
+};
+static int __init sched_core_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_core_sysctls);
+	return 0;
+}
+late_initcall(sched_core_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * fork()/clone()-time setup:
  */
@@ -5689,7 +5732,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those lose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(prev->sched_class <= &fair_sched_class &&
+	if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
@@ -5752,6 +5795,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
 
 extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
 
+static void queue_core_balance(struct rq *rq);
+
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
@@ -5801,7 +5846,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 
 		rq->core_pick = NULL;
-		return next;
+		goto out;
 	}
 
 	put_prev_task_balance(rq, prev, rf);
@@ -5851,7 +5896,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			 */
 			WARN_ON_ONCE(fi_before);
 			task_vruntime_update(rq, next, false);
-			goto done;
+			goto out_set_next;
 		}
 	}
 
@@ -5970,8 +6015,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		resched_curr(rq_i);
 	}
 
-done:
+out_set_next:
 	set_next_task(rq, next);
+out:
+	if (rq->core->core_forceidle_count && next == rq->idle)
+		queue_core_balance(rq);
+
 	return next;
 }
 
@@ -6000,7 +6049,7 @@ static bool try_steal_cookie(int this, int that)
 		if (p == src->core_pick || p == src->curr)
 			goto next;
 
-		if (!cpumask_test_cpu(this, &p->cpus_mask))
+		if (!is_cpu_allowed(p, this))
 			goto next;
 
 		if (p->core_occupation > dst->idle->core_occupation)
@@ -6066,7 +6115,7 @@ static void sched_core_balance(struct rq *rq)
 
 static DEFINE_PER_CPU(struct callback_head, core_balance_head);
 
-void queue_core_balance(struct rq *rq)
+static void queue_core_balance(struct rq *rq)
 {
 	if (!sched_core_enabled(rq))
 		return;
@@ -6304,10 +6353,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
-	 * that:
-	 *
-	 *  - we form a control dependency vs deactivate_task() below.
-	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
+	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
 	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
@@ -6376,7 +6422,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -8409,6 +8455,18 @@ static void __init preempt_dynamic_init(void)
 	}
 }
 
+#define PREEMPT_MODEL_ACCESSOR(mode) \
+	bool preempt_model_##mode(void)						 \
+	{									 \
+		WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
+		return preempt_dynamic_mode == preempt_dynamic_##mode;		 \
+	}									 \
+	EXPORT_SYMBOL_GPL(preempt_model_##mode)
+
+PREEMPT_MODEL_ACCESSOR(none);
+PREEMPT_MODEL_ACCESSOR(voluntary);
+PREEMPT_MODEL_ACCESSOR(full);
+
 #else /* !CONFIG_PREEMPT_DYNAMIC */
 
 static inline void preempt_dynamic_init(void) { }
@@ -9451,11 +9509,11 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
-	       &fair_sched_class + 1 != &rt_sched_class ||
-	       &rt_sched_class + 1   != &dl_sched_class);
+	BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
+	       &fair_sched_class != &rt_sched_class + 1 ||
+	       &rt_sched_class   != &dl_sched_class + 1);
 #ifdef CONFIG_SMP
-	BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
 #endif
 
 	wait_bit_init();