1 files changed, 534 insertions, 98 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8f360326861e..84758f34cdb0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,10 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
@@ -23,9 +27,6 @@
 #include "pelt.h"
 #include "smp.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
  * associated with them) to allow external modules to probe them.
@@ -36,6 +37,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -75,6 +79,100 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+
+/*
+ * Serialization rules:
+ *
+ * Lock order:
+ *
+ *   p->pi_lock
+ *     rq->lock
+ *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
+ *
+ *  rq1->lock
+ *    rq2->lock  where: rq1 < rq2
+ *
+ * Regular state:
+ *
+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
+ * always looks at the local rq data structures to find the most elegible task
+ * to run next.
+ *
+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
+ * the local CPU to avoid bouncing the runqueue state around [ see
+ * ttwu_queue_wakelist() ]
+ *
+ * Task wakeup, specifically wakeups that involve migration, are horribly
+ * complicated to avoid having to take two rq->locks.
+ *
+ * Special state:
+ *
+ * System-calls and anything external will use task_rq_lock() which acquires
+ * both p->pi_lock and rq->lock. As a consequence the state they change is
+ * stable while holding either lock:
+ *
+ *  - sched_setaffinity()/
+ *    set_cpus_allowed_ptr():	p->cpus_ptr, p->nr_cpus_allowed
+ *  - set_user_nice():		p->se.load, p->*prio
+ *  - __sched_setscheduler():	p->sched_class, p->policy, p->*prio,
+ *				p->se.load, p->rt_priority,
+ *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
+ *  - sched_setnuma():		p->numa_preferred_nid
+ *  - sched_move_task()/
+ *    cpu_cgroup_fork():	p->sched_task_group
+ *  - uclamp_update_active()	p->uclamp*
+ *
+ * p->state <- TASK_*:
+ *
+ *   is changed locklessly using set_current_state(), __set_current_state() or
+ *   set_special_state(), see their respective comments, or by
+ *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
+ *   concurrent self.
+ *
+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
+ *
+ *   is set by activate_task() and cleared by deactivate_task(), under
+ *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   ON_RQ_MIGRATING state is used for migration without holding both
+ *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
+ *
+ * p->on_cpu <- { 0, 1 }:
+ *
+ *   is set by prepare_task() and cleared by finish_task() such that it will be
+ *   set before p is scheduled-in and cleared after p is scheduled-out, both
+ *   under rq->lock. Non-zero indicates the task is running on its CPU.
+ *
+ *   [ The astute reader will observe that it is possible for two tasks on one
+ *     CPU to have ->on_cpu = 1 at the same time. ]
+ *
+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
+ *
+ *  - Don't call set_task_cpu() on a blocked task:
+ *
+ *    We don't care what CPU we're not running on, this simplifies hotplug,
+ *    the CPU assignment of blocked tasks isn't required to be valid.
+ *
+ *  - for try_to_wake_up(), called under p->pi_lock:
+ *
+ *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
+ *
+ *  - for migration called under rq->lock:
+ *    [ see task_on_rq_migrating() in task_rq_lock() ]
+ *
+ *    o move_queued_task()
+ *    o detach_task()
+ *
+ *  - for migration called under double_rq_lock():
+ *
+ *    o __migrate_swap_task()
+ *    o push_rt_task() / pull_rt_task()
+ *    o push_dl_task() / pull_dl_task()
+ *    o dl_task_offline_migration()
+ *
+ */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -791,9 +889,46 @@ unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 /* Max allowed maximum utilization */
 unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
+/*
+ * By default RT tasks run at the maximum performance point/capacity of the
+ * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
+ * SCHED_CAPACITY_SCALE.
+ *
+ * This knob allows admins to change the default behavior when uclamp is being
+ * used. In battery powered devices, particularly, running at the maximum
+ * capacity and frequency will increase energy consumption and shorten the
+ * battery life.
+ *
+ * This knob only affects RT tasks that their uclamp_se->user_defined == false.
+ *
+ * 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;
+
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
+/*
+ * This static key is used to reduce the uclamp overhead in the fast path. It
+ * primarily disables the call to uclamp_rq_{inc, dec}() in
+ * enqueue/dequeue_task().
+ *
+ * This allows users to continue to enable uclamp in their kernel config with
+ * minimum uclamp overhead in the fast path.
+ *
+ * As soon as userspace modifies any of the uclamp knobs, the static key is
+ * enabled, since we have an actual users that make use of uclamp
+ * functionality.
+ *
+ * The knobs that would enable this static key are:
+ *
+ *   * A task modifying its uclamp value with sched_setattr().
+ *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
+ *   * An admin modifying the cgroup cpu.uclamp.{min, max}
+ */
+DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
+
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
 
@@ -873,6 +1008,64 @@ unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static void __uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	unsigned int default_util_min;
+	struct uclamp_se *uc_se;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	uc_se = &p->uclamp_req[UCLAMP_MIN];
+
+	/* Only sync if user didn't override the default */
+	if (uc_se->user_defined)
+		return;
+
+	default_util_min = sysctl_sched_uclamp_util_min_rt_default;
+	uclamp_se_set(uc_se, default_util_min, false);
+}
+
+static void uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	if (!rt_task(p))
+		return;
+
+	/* Protect updates to p->uclamp_* */
+	rq = task_rq_lock(p, &rf);
+	__uclamp_update_util_min_rt_default(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)
 {
@@ -990,10 +1183,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 	lockdep_assert_held(&rq->lock);
 
+	/*
+	 * If sched_uclamp_used was enabled after task @p was enqueued,
+	 * we could end up with unbalanced call to uclamp_rq_dec_id().
+	 *
+	 * In this case the uc_se->active flag should be false since no uclamp
+	 * accounting was performed at enqueue time and we can just return
+	 * here.
+	 *
+	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * problem too
+	 *
+	 *	enqueue(taskA)
+	 *	// sched_uclamp_used gets enabled
+	 *	enqueue(taskB)
+	 *	dequeue(taskA)
+	 *	// Must not decrement bukcet->tasks here
+	 *	dequeue(taskB)
+	 *
+	 * where we could end up with stale data in uc_se and
+	 * bucket[uc_se->bucket_id].
+	 *
+	 * The following check here eliminates the possibility of such race.
+	 */
+	if (unlikely(!uc_se->active))
+		return;
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
+
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+
 	uc_se->active = false;
 
 	/*
@@ -1021,6 +1242,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1036,6 +1266,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1114,12 +1353,13 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
-	int old_min, old_max;
+	int old_min, old_max, old_min_rt;
 	int result;
 
 	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
+	old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
 
 	result = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (result)
@@ -1128,7 +1368,9 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		goto done;
 
 	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
-	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
+	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
+
 		result = -EINVAL;
 		goto undo;
 	}
@@ -1144,8 +1386,15 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		update_root_tg = true;
 	}
 
-	if (update_root_tg)
+	if (update_root_tg) {
+		static_branch_enable(&sched_uclamp_used);
 		uclamp_update_root_tg();
+	}
+
+	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
+		static_branch_enable(&sched_uclamp_used);
+		uclamp_sync_util_min_rt_default();
+	}
 
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
@@ -1158,6 +1407,7 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
+	sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
 done:
 	mutex_unlock(&uclamp_mutex);
 
@@ -1180,6 +1430,15 @@ static int uclamp_validate(struct task_struct *p,
 	if (upper_bound > SCHED_CAPACITY_SCALE)
 		return -EINVAL;
 
+	/*
+	 * We have valid uclamp attributes; make sure uclamp is enabled.
+	 *
+	 * We need to do that here, because enabling static branches is a
+	 * blocking operation which obviously cannot be done while holding
+	 * scheduler locks.
+	 */
+	static_branch_enable(&sched_uclamp_used);
+
 	return 0;
 }
 
@@ -1194,17 +1453,20 @@ static void __setscheduler_uclamp(struct task_struct *p,
 	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
-		unsigned int clamp_value = uclamp_none(clamp_id);
 
 		/* Keep using defined clamps across class changes */
 		if (uc_se->user_defined)
 			continue;
 
-		/* By default, RT tasks always get 100% boost */
+		/*
+		 * RT by default have a 100% boost value that could be modified
+		 * at runtime.
+		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+			__uclamp_update_util_min_rt_default(p);
+		else
+			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 
-		uclamp_se_set(uc_se, clamp_value, false);
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
@@ -1225,6 +1487,10 @@ static void uclamp_fork(struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * We don't need to hold task_rq_lock() when updating p->uclamp_* here
+	 * as the task is still at its early fork stages.
+	 */
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
 
@@ -1237,19 +1503,33 @@ static void uclamp_fork(struct task_struct *p)
 	}
 }
 
+static void uclamp_post_fork(struct task_struct *p)
+{
+	uclamp_update_util_min_rt_default(p);
+}
+
+static void __init init_uclamp_rq(struct rq *rq)
+{
+	enum uclamp_id clamp_id;
+	struct uclamp_rq *uc_rq = rq->uclamp;
+
+	for_each_clamp_id(clamp_id) {
+		uc_rq[clamp_id] = (struct uclamp_rq) {
+			.value = uclamp_none(clamp_id)
+		};
+	}
+
+	rq->uclamp_flags = 0;
+}
+
 static void __init init_uclamp(void)
 {
 	struct uclamp_se uc_max = {};
 	enum uclamp_id clamp_id;
 	int cpu;
 
-	mutex_init(&uclamp_mutex);
-
-	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0,
-				sizeof(struct uclamp_rq)*UCLAMP_CNT);
-		cpu_rq(cpu)->uclamp_flags = 0;
-	}
+	for_each_possible_cpu(cpu)
+		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
@@ -1278,6 +1558,7 @@ static inline int uclamp_validate(struct task_struct *p,
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
+static inline void uclamp_post_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -1311,9 +1592,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1323,9 +1601,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
 
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -1410,20 +1685,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
-	const struct sched_class *class;
-
-	if (p->sched_class == rq->curr->sched_class) {
+	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	} else {
-		for_each_class(class) {
-			if (class == rq->curr->sched_class)
-				break;
-			if (class == p->sched_class) {
-				resched_curr(rq);
-				break;
-			}
-		}
-	}
+	else if (p->sched_class > rq->curr->sched_class)
+		resched_curr(rq);
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -1474,8 +1739,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
+	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
 
@@ -1483,8 +1747,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 
 	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
-	enqueue_task(rq, p, 0);
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1637,7 +1900,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	/*
@@ -2236,10 +2499,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2249,12 +2512,31 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 }
 
 /*
- * Called in case the task @p isn't fully descheduled from its runqueue,
- * in this case we must do a remote wakeup. Its a 'light' wakeup though,
- * since all we need to do is flip p->state to TASK_RUNNING, since
- * the task is still ->on_rq.
+ * Consider @p being inside a wait loop:
+ *
+ *   for (;;) {
+ *      set_current_state(TASK_UNINTERRUPTIBLE);
+ *
+ *      if (CONDITION)
+ *         break;
+ *
+ *      schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * between set_current_state() and schedule(). In this case @p is still
+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
+ * an atomic manner.
+ *
+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
+ * then schedule() must still happen and p->state can be changed to
+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
+ * need to do a full wakeup with enqueue.
+ *
+ * Returns: %true when the wakeup is done,
+ *          %false otherwise.
  */
-static int ttwu_remote(struct task_struct *p, int wake_flags)
+static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -2293,8 +2575,15 @@ void sched_ttwu_pending(void *arg)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -2322,7 +2611,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	__smp_call_single_queue(cpu, &p->wake_entry);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2369,7 +2658,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	 * the soon-to-be-idle CPU as the current CPU is likely busy.
 	 * nr_running is checked to avoid unnecessary task stacking.
 	 */
-	if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1)
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
 		return true;
 
 	return false;
@@ -2378,6 +2667,9 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -2385,6 +2677,14 @@ static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 
 	return false;
 }
+
+#else /* !CONFIG_SMP */
+
+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2392,10 +2692,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
-#if defined(CONFIG_SMP)
 	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
-#endif
 
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
@@ -2451,8 +2749,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * migration. However the means are completely different as there is no lock
  * chain to provide order. Instead we do:
  *
- *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_load_acquire(!X->on_cpu)
+ *   1) smp_store_release(X->on_cpu, 0)   -- finish_task()
+ *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
  *
  * Example:
  *
@@ -2492,15 +2790,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * If (@state & @p->state) @p->state = TASK_RUNNING.
+ * Conceptually does:
+ *
+ *   If (@state & @p->state) @p->state = TASK_RUNNING.
  *
  * If the task was not queued/runnable, also place it back on a runqueue.
  *
- * Atomic against schedule() which would dequeue a task, also see
- * set_current_state().
+ * This function is atomic against schedule() which would dequeue the task.
+ *
+ * It issues a full memory barrier before accessing @p->state, see the comment
+ * with set_current_state().
+ *
+ * Uses p->pi_lock to serialize against concurrent wake-ups.
+ *
+ * Relies on p->pi_lock stabilizing:
+ *  - p->sched_class
+ *  - p->cpus_ptr
+ *  - p->sched_task_group
+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
+ *
+ * Tries really hard to only take one task_rq(p)->lock for performance.
+ * Takes rq->lock in:
+ *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
+ *  - ttwu_queue()       -- new rq, for enqueue of the task;
+ *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
  *
- * This function executes a full memory barrier before accessing the task
- * state; see set_current_state().
+ * As a consequence we race really badly with just about everything. See the
+ * many memory barriers and their comments for details.
  *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
@@ -2516,7 +2832,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
-		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
 		 * In particular:
@@ -2528,7 +2844,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2538,8 +2853,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
-	 * reordered with p->state check below. This pairs with mb() in
-	 * set_current_state() the waiting thread does.
+	 * reordered with p->state check below. This pairs with smp_store_mb()
+	 * in set_current_state() that the waiting thread does.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
@@ -2550,7 +2865,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2575,7 +2889,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -2584,9 +2898,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 
 #ifdef CONFIG_SMP
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
 	 * possible to, falsely, observe p->on_cpu == 0.
@@ -2605,8 +2916,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2614,8 +2937,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * which potentially sends an IPI instead of spinning on p->on_cpu to
 	 * let the waker make forward progress. This is safe because IRQs are
 	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
 	 */
-	if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ))
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
 		goto unlock;
 
 	/*
@@ -2635,6 +2971,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2642,7 +2980,7 @@ unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
@@ -2763,7 +3101,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
-	p->wake_entry_type = CSD_TYPE_TTWU;
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 #endif
 }
 
@@ -2939,6 +3277,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -2963,6 +3302,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
+void sched_post_fork(struct task_struct *p)
+{
+	uclamp_post_fork(p);
+}
+
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -3003,6 +3347,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -3119,8 +3464,10 @@ static inline void prepare_task(struct task_struct *next)
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
+	 *
+	 * See the ttwu() WF_ON_CPU case and its ordering comment.
 	 */
-	next->on_cpu = 1;
+	WRITE_ONCE(next->on_cpu, 1);
 #endif
 }
 
@@ -3128,8 +3475,9 @@ static inline void finish_task(struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
+	 * This must be the very last reference to @prev from this CPU. After
+	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
+	 * must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
 	 * In particular, the load of prev->state in finish_task_switch() must
@@ -3628,17 +3976,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
-DEFINE_PER_CPU(unsigned long, thermal_pressure);
-
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure)
-{
-	int cpu;
-
-	for_each_cpu(cpu, cpus)
-		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
-}
-
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
@@ -4001,8 +4338,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those loose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely((prev->sched_class == &idle_sched_class ||
-		    prev->sched_class == &fair_sched_class) &&
+	if (likely(prev->sched_class <= &fair_sched_class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
@@ -4074,6 +4410,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4093,9 +4430,16 @@ static void __sched notrace __schedule(bool preempt)
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
+	 *
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4106,10 +4450,38 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+
+	/*
+	 * 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.
+	 */
+	prev_state = prev->state;
+	if (!preempt && prev_state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;    if (p->on_rq && ...)
+			 *   if (prev_state)		    goto out;
+			 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
+			 *				  p->state = TASK_WAKING
+			 *
+			 * Where __schedule() and ttwu() have matching control dependencies.
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
@@ -4421,6 +4793,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
@@ -4533,7 +4906,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
@@ -5122,6 +5496,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Use sched_set_fifo(), read its comment.
+ *
  * Return: 0 on success. An error code otherwise.
  *
  * NOTE that the task may be already dead.
@@ -5131,13 +5507,11 @@ int sched_setscheduler(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, true);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler);
 
 int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, true, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr);
 
 int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
@@ -5162,7 +5536,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
+
+/*
+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
+ * incapable of resource management, which is the one thing an OS really should
+ * be doing.
+ *
+ * This is of course the reason it is limited to privileged users only.
+ *
+ * Worse still; it is fundamentally impossible to compose static priority
+ * workloads. You cannot take two correctly working static prio workloads
+ * and smash them together and still expect them to work.
+ *
+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
+ *
+ *   MAX_RT_PRIO / 2
+ *
+ * The administrator _MUST_ configure the system, the kernel simply doesn't
+ * know enough information to make a sensible choice.
+ */
+void sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo);
+
+/*
+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
+ */
+void sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+void sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
@@ -5453,6 +5871,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
+	/*
+	 * This could race with another potential updater, but this is fine
+	 * because it'll correctly read the old or the new value. We don't need
+	 * to guarantee who wins the race as long as it doesn't return garbage.
+	 */
 	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
 	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
@@ -5810,7 +6233,7 @@ again:
 	if (task_running(p_rq, p) || p->state)
 		goto out_unlock;
 
-	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	yielded = curr->sched_class->yield_to_task(rq, p);
 	if (yielded) {
 		schedstat_inc(rq->yld_count);
 		/*
@@ -6644,6 +7067,14 @@ void __init sched_init(void)
 	unsigned long ptr = 0;
 	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);
+#ifdef CONFIG_SMP
+	BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+#endif
+
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -7365,6 +7796,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	if (req.ret)
 		return req.ret;
 
+	static_branch_enable(&sched_uclamp_used);
+
 	mutex_lock(&uclamp_mutex);
 	rcu_read_lock();
 
@@ -8052,4 +8485,7 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}