Merge branch 'sched/core'

include/linux/cpuset.h

@@ -15,6 +15,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/jump_label.h>
 
 #ifdef CONFIG_CPUSETS
@@ -58,7 +59,7 @@ extern void cpuset_wait_for_hotplug(void);
 extern void cpuset_read_lock(void);
 extern void cpuset_read_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -184,11 +185,12 @@ static inline void cpuset_read_unlock(void) { }
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
-	cpumask_copy(mask, cpu_possible_mask);
+	cpumask_copy(mask, task_cpu_possible_mask(p));
 }
 
-static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)
+static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
+	return false;
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)

include/linux/mmu_context.h

@@ -14,4 +14,18 @@
 static inline void leave_mm(int cpu) { }
 #endif
 
+/*
+ * CPUs that are capable of running user task @p. Must contain at least one
+ * active CPU. It is assumed that the kernel can run on all CPUs, so calling
+ * this for a kernel thread is pointless.
+ *
+ * By default, we assume a sane, homogeneous system.
+ */
+#ifndef task_cpu_possible_mask
+# define task_cpu_possible_mask(p)	cpu_possible_mask
+# define task_cpu_possible(cpu, p)	true
+#else
+# define task_cpu_possible(cpu, p)	cpumask_test_cpu((cpu), task_cpu_possible_mask(p))
+#endif
+
 #endif

include/linux/sched.h

@@ -748,6 +748,7 @@ struct task_struct {
 	unsigned int			policy;
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
+	cpumask_t			*user_cpus_ptr;
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
 #ifdef CONFIG_SMP
@@ -1705,6 +1706,11 @@ extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
+extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node);
+extern void release_user_cpus_ptr(struct task_struct *p);
+extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask);
+extern void force_compatible_cpus_allowed_ptr(struct task_struct *p);
+extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p);
 #else
 static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
@@ -1715,6 +1721,21 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma
 		return -EINVAL;
 	return 0;
 }
+static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
+{
+	if (src->user_cpus_ptr)
+		return -EINVAL;
+	return 0;
+}
+static inline void release_user_cpus_ptr(struct task_struct *p)
+{
+	WARN_ON(p->user_cpus_ptr);
+}
+
+static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
+{
+	return 0;
+}
 #endif
 
 extern int yield_to(struct task_struct *p, bool preempt);

include/linux/sched/sysctl.h

@@ -28,30 +28,12 @@ enum { sysctl_hung_task_timeout_secs = 0 };
 
 extern unsigned int sysctl_sched_child_runs_first;
 
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
-
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
 	SCHED_TUNABLESCALING_LINEAR,
 	SCHED_TUNABLESCALING_END,
 };
-extern unsigned int sysctl_sched_tunable_scaling;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_size;
-
-#ifdef CONFIG_SCHED_DEBUG
-extern __read_mostly unsigned int sysctl_sched_migration_cost;
-extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-
-extern int sysctl_resched_latency_warn_ms;
-extern int sysctl_resched_latency_warn_once;
-#endif
 
 /*
  *  control realtime throttling:

include/linux/wait.h

@@ -56,7 +56,7 @@ struct task_struct;
 
 #define __WAIT_QUEUE_HEAD_INITIALIZER(name) {					\
 	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),			\
-	.head		= { &(name).head, &(name).head } }
+	.head		= LIST_HEAD_INIT(name.head) }
 
 #define DECLARE_WAIT_QUEUE_HEAD(name) \
 	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)

init/init_task.c

@@ -80,6 +80,7 @@ struct task_struct init_task
 	.normal_prio	= MAX_PRIO - 20,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
+	.user_cpus_ptr	= NULL,
 	.cpus_mask	= CPU_MASK_ALL,
 	.nr_cpus_allowed= NR_CPUS,
 	.mm		= NULL,

kernel/cgroup/cpuset.c

@@ -372,18 +372,29 @@ static inline bool is_in_v2_mode(void)
 }
 
 /*
- * Return in pmask the portion of a cpusets's cpus_allowed that
- * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.
+ * Return in pmask the portion of a task's cpusets's cpus_allowed that
+ * are online and are capable of running the task.  If none are found,
+ * walk up the cpuset hierarchy until we find one that does have some
+ * appropriate cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
  *
  * Call with callback_lock or cpuset_mutex held.
  */
-static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
+static void guarantee_online_cpus(struct task_struct *tsk,
+				  struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	struct cpuset *cs;
+
+	if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
+		cpumask_copy(pmask, cpu_online_mask);
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+
+	while (!cpumask_intersects(cs->effective_cpus, pmask)) {
 		cs = parent_cs(cs);
 		if (unlikely(!cs)) {
 			/*
@@ -393,11 +404,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 			 * cpuset's effective_cpus is on its way to be
 			 * identical to cpu_online_mask.
 			 */
-			cpumask_copy(pmask, cpu_online_mask);
-			return;
+			goto out_unlock;
 		}
 	}
-	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
+	cpumask_and(pmask, pmask, cs->effective_cpus);
+
+out_unlock:
+	rcu_read_unlock();
 }
 
 /*
@@ -2199,15 +2212,13 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 
 	percpu_down_write(&cpuset_rwsem);
 
-	/* prepare for attach */
-	if (cs == &top_cpuset)
-		cpumask_copy(cpus_attach, cpu_possible_mask);
-	else
-		guarantee_online_cpus(cs, cpus_attach);
-
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
 	cgroup_taskset_for_each(task, css, tset) {
+		if (cs != &top_cpuset)
+			guarantee_online_cpus(task, cpus_attach);
+		else
+			cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -3302,9 +3313,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	unsigned long flags;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	rcu_read_lock();
-	guarantee_online_cpus(task_cs(tsk), pmask);
-	rcu_read_unlock();
+	guarantee_online_cpus(tsk, pmask);
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
@@ -3318,13 +3327,22 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
  * which will not contain a sane cpumask during cases such as cpu hotplugging.
  * This is the absolute last resort for the scheduler and it is only used if
  * _every_ other avenue has been traveled.
+ *
+ * Returns true if the affinity of @tsk was changed, false otherwise.
  **/
 
-void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+bool cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	const struct cpumask *cs_mask;
+	bool changed = false;
+
 	rcu_read_lock();
-	do_set_cpus_allowed(tsk, is_in_v2_mode() ?
-		task_cs(tsk)->cpus_allowed : cpu_possible_mask);
+	cs_mask = task_cs(tsk)->cpus_allowed;
+	if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) {
+		do_set_cpus_allowed(tsk, cs_mask);
+		changed = true;
+	}
 	rcu_read_unlock();
 
 	/*
@@ -3344,6 +3362,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	 * select_fallback_rq() will fix things ups and set cpu_possible_mask
 	 * if required.
 	 */
+	return changed;
 }
 
 void __init cpuset_init_current_mems_allowed(void)

kernel/fork.c

@@ -446,6 +446,7 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+	release_user_cpus_ptr(tsk);
 	scs_release(tsk);
 
 #ifndef CONFIG_THREAD_INFO_IN_TASK
@@ -924,6 +925,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #endif
 	if (orig->cpus_ptr == &orig->cpus_mask)
 		tsk->cpus_ptr = &tsk->cpus_mask;
+	dup_user_cpus_ptr(tsk, orig, node);
 
 	/*
 	 * One for the user space visible state that goes away when reaped.

kernel/sched/core.c

@@ -993,6 +993,7 @@ int get_nohz_timer_target(void)
 {
 	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
+	const struct cpumask *hk_mask;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
 		if (!idle_cpu(cpu))
@@ -1000,10 +1001,11 @@ int get_nohz_timer_target(void)
 		default_cpu = cpu;
 	}
 
+	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu_and(i, sched_domain_span(sd),
-			housekeeping_cpumask(HK_FLAG_TIMER)) {
+		for_each_cpu_and(i, sched_domain_span(sd), hk_mask) {
 			if (cpu == i)
 				continue;
 
@@ -1619,6 +1621,23 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
+static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p,
+				      enum uclamp_id clamp_id)
+{
+	if (!p->uclamp[clamp_id].active)
+		return;
+
+	uclamp_rq_dec_id(rq, p, clamp_id);
+	uclamp_rq_inc_id(rq, p, clamp_id);
+
+	/*
+	 * Make sure to clear the idle flag if we've transiently reached 0
+	 * active tasks on rq.
+	 */
+	if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE))
+		rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
+}
+
 static inline void
 uclamp_update_active(struct task_struct *p)
 {
@@ -1642,12 +1661,8 @@ uclamp_update_active(struct task_struct *p)
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
-	for_each_clamp_id(clamp_id) {
-		if (p->uclamp[clamp_id].active) {
-			uclamp_rq_dec_id(rq, p, clamp_id);
-			uclamp_rq_inc_id(rq, p, clamp_id);
-		}
-	}
+	for_each_clamp_id(clamp_id)
+		uclamp_rq_reinc_id(rq, p, clamp_id);
 
 	task_rq_unlock(rq, p, &rf);
 }
@@ -2161,7 +2176,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 
 	/* Non kernel threads are not allowed during either online or offline. */
 	if (!(p->flags & PF_KTHREAD))
-		return cpu_active(cpu);
+		return cpu_active(cpu) && task_cpu_possible(cpu, p);
 
 	/* KTHREAD_IS_PER_CPU is always allowed. */
 	if (kthread_is_per_cpu(p))
@@ -2468,6 +2483,34 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	__do_set_cpus_allowed(p, new_mask, 0);
 }
 
+int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
+		      int node)
+{
+	if (!src->user_cpus_ptr)
+		return 0;
+
+	dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+	if (!dst->user_cpus_ptr)
+		return -ENOMEM;
+
+	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	return 0;
+}
+
+static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
+{
+	struct cpumask *user_mask = NULL;
+
+	swap(p->user_cpus_ptr, user_mask);
+
+	return user_mask;
+}
+
+void release_user_cpus_ptr(struct task_struct *p)
+{
+	kfree(clear_user_cpus_ptr(p));
+}
+
 /*
  * This function is wildly self concurrent; here be dragons.
  *
@@ -2685,28 +2728,26 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 }
 
 /*
- * 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
- * is removed from the allowed bitmask.
- *
- * NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely. The
- * call is not atomic; no spinlocks may be held.
+ * Called with both p->pi_lock and rq->lock held; drops both before returning.
  */
-static int __set_cpus_allowed_ptr(struct task_struct *p,
-				  const struct cpumask *new_mask,
-				  u32 flags)
+static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
+					 const struct cpumask *new_mask,
+					 u32 flags,
+					 struct rq *rq,
+					 struct rq_flags *rf)
+	__releases(rq->lock)
+	__releases(p->pi_lock)
 {
+	const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
 	const struct cpumask *cpu_valid_mask = cpu_active_mask;
+	bool kthread = p->flags & PF_KTHREAD;
+	struct cpumask *user_mask = NULL;
 	unsigned int dest_cpu;
-	struct rq_flags rf;
-	struct rq *rq;
 	int ret = 0;
 
-	rq = task_rq_lock(p, &rf);
 	update_rq_clock(rq);
 
-	if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
+	if (kthread || is_migration_disabled(p)) {
 		/*
 		 * Kernel threads are allowed on online && !active CPUs,
 		 * however, during cpu-hot-unplug, even these might get pushed
@@ -2720,6 +2761,11 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		cpu_valid_mask = cpu_online_mask;
 	}
 
+	if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	/*
 	 * Must re-check here, to close a race against __kthread_bind(),
 	 * sched_setaffinity() is not guaranteed to observe the flag.
@@ -2754,20 +2800,178 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 
 	__do_set_cpus_allowed(p, new_mask, flags);
 
-	return affine_move_task(rq, p, &rf, dest_cpu, flags);
+	if (flags & SCA_USER)
+		user_mask = clear_user_cpus_ptr(p);
+
+	ret = affine_move_task(rq, p, rf, dest_cpu, flags);
+
+	kfree(user_mask);
+
+	return ret;
 
 out:
-	task_rq_unlock(rq, p, &rf);
+	task_rq_unlock(rq, p, rf);
 
 	return ret;
 }
 
+/*
+ * 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
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask, u32 flags)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &rf);
+	return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf);
+}
+
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
 	return __set_cpus_allowed_ptr(p, new_mask, 0);
 }
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
+/*
+ * Change a given task's CPU affinity to the intersection of its current
+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask
+ * and pointing @p->user_cpus_ptr to a copy of the old mask.
+ * If the resulting mask is empty, leave the affinity unchanged and return
+ * -EINVAL.
+ */
+static int restrict_cpus_allowed_ptr(struct task_struct *p,
+				     struct cpumask *new_mask,
+				     const struct cpumask *subset_mask)
+{
+	struct cpumask *user_mask = NULL;
+	struct rq_flags rf;
+	struct rq *rq;
+	int err;
+
+	if (!p->user_cpus_ptr) {
+		user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+		if (!user_mask)
+			return -ENOMEM;
+	}
+
+	rq = task_rq_lock(p, &rf);
+
+	/*
+	 * Forcefully restricting the affinity of a deadline task is
+	 * likely to cause problems, so fail and noisily override the
+	 * mask entirely.
+	 */
+	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
+		err = -EPERM;
+		goto err_unlock;
+	}
+
+	if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
+	/*
+	 * We're about to butcher the task affinity, so keep track of what
+	 * the user asked for in case we're able to restore it later on.
+	 */
+	if (user_mask) {
+		cpumask_copy(user_mask, p->cpus_ptr);
+		p->user_cpus_ptr = user_mask;
+	}
+
+	return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);
+
+err_unlock:
+	task_rq_unlock(rq, p, &rf);
+	kfree(user_mask);
+	return err;
+}
+
+/*
+ * Restrict the CPU affinity of task @p so that it is a subset of
+ * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the
+ * old affinity mask. If the resulting mask is empty, we warn and walk
+ * up the cpuset hierarchy until we find a suitable mask.
+ */
+void force_compatible_cpus_allowed_ptr(struct task_struct *p)
+{
+	cpumask_var_t new_mask;
+	const struct cpumask *override_mask = task_cpu_possible_mask(p);
+
+	alloc_cpumask_var(&new_mask, GFP_KERNEL);
+
+	/*
+	 * __migrate_task() can fail silently in the face of concurrent
+	 * offlining of the chosen destination CPU, so take the hotplug
+	 * lock to ensure that the migration succeeds.
+	 */
+	cpus_read_lock();
+	if (!cpumask_available(new_mask))
+		goto out_set_mask;
+
+	if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
+		goto out_free_mask;
+
+	/*
+	 * We failed to find a valid subset of the affinity mask for the
+	 * task, so override it based on its cpuset hierarchy.
+	 */
+	cpuset_cpus_allowed(p, new_mask);
+	override_mask = new_mask;
+
+out_set_mask:
+	if (printk_ratelimit()) {
+		printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
+				task_pid_nr(p), p->comm,
+				cpumask_pr_args(override_mask));
+	}
+
+	WARN_ON(set_cpus_allowed_ptr(p, override_mask));
+out_free_mask:
+	cpus_read_unlock();
+	free_cpumask_var(new_mask);
+}
+
+static int
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);
+
+/*
+ * Restore the affinity of a task @p which was previously restricted by a
+ * call to force_compatible_cpus_allowed_ptr(). This will clear (and free)
+ * @p->user_cpus_ptr.
+ *
+ * It is the caller's responsibility to serialise this with any calls to
+ * force_compatible_cpus_allowed_ptr(@p).
+ */
+void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
+{
+	struct cpumask *user_mask = p->user_cpus_ptr;
+	unsigned long flags;
+
+	/*
+	 * Try to restore the old affinity mask. If this fails, then
+	 * we free the mask explicitly to avoid it being inherited across
+	 * a subsequent fork().
+	 */
+	if (!user_mask || !__sched_setaffinity(p, user_mask))
+		return;
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	user_mask = clear_user_cpus_ptr(p);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	kfree(user_mask);
+}
+
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 #ifdef CONFIG_SCHED_DEBUG
@@ -3112,9 +3316,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 
 		/* Look for allowed, online CPU in same node. */
 		for_each_cpu(dest_cpu, nodemask) {
-			if (!cpu_active(dest_cpu))
-				continue;
-			if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
+			if (is_cpu_allowed(p, dest_cpu))
 				return dest_cpu;
 		}
 	}
@@ -3131,8 +3333,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		/* No more Mr. Nice Guy. */
 		switch (state) {
 		case cpuset:
-			if (IS_ENABLED(CONFIG_CPUSETS)) {
-				cpuset_cpus_allowed_fallback(p);
+			if (cpuset_cpus_allowed_fallback(p)) {
 				state = possible;
 				break;
 			}
@@ -3144,10 +3345,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			 *
 			 * More yuck to audit.
 			 */
-			do_set_cpus_allowed(p, cpu_possible_mask);
+			do_set_cpus_allowed(p, task_cpu_possible_mask(p));
 			state = fail;
 			break;
-
 		case fail:
 			BUG();
 			break;
@@ -5660,11 +5860,9 @@ static bool try_steal_cookie(int this, int that)
 		if (p->core_occupation > dst->idle->core_occupation)
 			goto next;
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src, p, 0);
 		set_task_cpu(p, this);
 		activate_task(dst, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 
 		resched_curr(dst);
 
@@ -7300,6 +7498,16 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	return -E2BIG;
 }
 
+static void get_params(struct task_struct *p, struct sched_attr *attr)
+{
+	if (task_has_dl_policy(p))
+		__getparam_dl(p, attr);
+	else if (task_has_rt_policy(p))
+		attr->sched_priority = p->rt_priority;
+	else
+		attr->sched_nice = task_nice(p);
+}
+
 /**
  * sys_sched_setscheduler - set/change the scheduler policy and RT priority
  * @pid: the pid in question.
@@ -7361,6 +7569,8 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	rcu_read_unlock();
 
 	if (likely(p)) {
+		if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
+			get_params(p, &attr);
 		retval = sched_setattr(p, &attr);
 		put_task_struct(p);
 	}
@@ -7509,12 +7719,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	kattr.sched_policy = p->policy;
 	if (p->sched_reset_on_fork)
 		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-	if (task_has_dl_policy(p))
-		__getparam_dl(p, &kattr);
-	else if (task_has_rt_policy(p))
-		kattr.sched_priority = p->rt_priority;
-	else
-		kattr.sched_nice = task_nice(p);
+	get_params(p, &kattr);
+	kattr.sched_flags &= SCHED_FLAG_ALL;
 
 #ifdef CONFIG_UCLAMP_TASK
 	/*
@@ -7535,9 +7741,76 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	return retval;
 }
 
-long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+#ifdef CONFIG_SMP
+int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 {
+	int ret = 0;
+
+	/*
+	 * If the task isn't a deadline task or admission control is
+	 * disabled then we don't care about affinity changes.
+	 */
+	if (!task_has_dl_policy(p) || !dl_bandwidth_enabled())
+		return 0;
+
+	/*
+	 * Since bandwidth control happens on root_domain basis,
+	 * if admission test is enabled, we only admit -deadline
+	 * tasks allowed to run on all the CPUs in the task's
+	 * root_domain.
+	 */
+	rcu_read_lock();
+	if (!cpumask_subset(task_rq(p)->rd->span, mask))
+		ret = -EBUSY;
+	rcu_read_unlock();
+	return ret;
+}
+#endif
+
+static int
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
+{
+	int retval;
 	cpumask_var_t cpus_allowed, new_mask;
+
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, mask, cpus_allowed);
+
+	retval = dl_task_check_affinity(p, new_mask);
+	if (retval)
+		goto out_free_new_mask;
+again:
+	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER);
+	if (retval)
+		goto out_free_new_mask;
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	if (!cpumask_subset(new_mask, cpus_allowed)) {
+		/*
+		 * We must have raced with a concurrent cpuset update.
+		 * Just reset the cpumask to the cpuset's cpus_allowed.
+		 */
+		cpumask_copy(new_mask, cpus_allowed);
+		goto again;
+	}
+
+out_free_new_mask:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
 	struct task_struct *p;
 	int retval;
 
@@ -7557,68 +7830,22 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		retval = -EINVAL;
 		goto out_put_task;
 	}
-	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
-		retval = -ENOMEM;
-		goto out_put_task;
-	}
-	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
-		retval = -ENOMEM;
-		goto out_free_cpus_allowed;
-	}
-	retval = -EPERM;
+
 	if (!check_same_owner(p)) {
 		rcu_read_lock();
 		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
 			rcu_read_unlock();
-			goto out_free_new_mask;
+			retval = -EPERM;
+			goto out_put_task;
 		}
 		rcu_read_unlock();
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_free_new_mask;
-
-
-	cpuset_cpus_allowed(p, cpus_allowed);
-	cpumask_and(new_mask, in_mask, cpus_allowed);
-
-	/*
-	 * Since bandwidth control happens on root_domain basis,
-	 * if admission test is enabled, we only admit -deadline
-	 * tasks allowed to run on all the CPUs in the task's
-	 * root_domain.
-	 */
-#ifdef CONFIG_SMP
-	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
-		rcu_read_lock();
-		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
-			retval = -EBUSY;
-			rcu_read_unlock();
-			goto out_free_new_mask;
-		}
-		rcu_read_unlock();
-	}
-#endif
-again:
-	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);
+		goto out_put_task;
 
-	if (!retval) {
-		cpuset_cpus_allowed(p, cpus_allowed);
-		if (!cpumask_subset(new_mask, cpus_allowed)) {
-			/*
-			 * We must have raced with a concurrent cpuset
-			 * update. Just reset the cpus_allowed to the
-			 * cpuset's cpus_allowed
-			 */
-			cpumask_copy(new_mask, cpus_allowed);
-			goto again;
-		}
-	}
-out_free_new_mask:
-	free_cpumask_var(new_mask);
-out_free_cpus_allowed:
-	free_cpumask_var(cpus_allowed);
+	retval = __sched_setaffinity(p, in_mask);
 out_put_task:
 	put_task_struct(p);
 	return retval;
@@ -9804,7 +10031,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	mutex_lock(&cfs_constraints_mutex);
 	ret = __cfs_schedulable(tg, period, quota);
 	if (ret)
@@ -9848,7 +10075,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -10099,6 +10326,20 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	return css_tg(css)->idle;
+}
+
+static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
+				struct cftype *cft, s64 idle)
+{
+	return sched_group_set_idle(css_tg(css), idle);
+}
+#endif
+
 static struct cftype cpu_legacy_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
@@ -10106,6 +10347,11 @@ static struct cftype cpu_legacy_files[] = {
 		.read_u64 = cpu_shares_read_u64,
 		.write_u64 = cpu_shares_write_u64,
 	},
+	{
+		.name = "idle",
+		.read_s64 = cpu_idle_read_s64,
+		.write_s64 = cpu_idle_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
@@ -10313,6 +10559,12 @@ static struct cftype cpu_files[] = {
 		.read_s64 = cpu_weight_nice_read_s64,
 		.write_s64 = cpu_weight_nice_write_s64,
 	},
+	{
+		.name = "idle",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_idle_read_s64,
+		.write_s64 = cpu_idle_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{

kernel/sched/deadline.c

@@ -1733,6 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 */
 	raw_spin_rq_lock(rq);
 	if (p->dl.dl_non_contending) {
+		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
 		p->dl.dl_non_contending = 0;
 		/*
@@ -2741,7 +2742,7 @@ void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
+	dl_se->flags = attr->sched_flags & SCHED_DL_FLAGS;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
 }
@@ -2754,7 +2755,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_runtime = dl_se->dl_runtime;
 	attr->sched_deadline = dl_se->dl_deadline;
 	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
+	attr->sched_flags &= ~SCHED_DL_FLAGS;
+	attr->sched_flags |= dl_se->flags;
 }
 
 /*
@@ -2851,7 +2853,7 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 	if (dl_se->dl_runtime != attr->sched_runtime ||
 	    dl_se->dl_deadline != attr->sched_deadline ||
 	    dl_se->dl_period != attr->sched_period ||
-	    dl_se->flags != attr->sched_flags)
+	    dl_se->flags != (attr->sched_flags & SCHED_DL_FLAGS))
 		return true;
 
 	return false;

kernel/sched/debug.c

@@ -388,6 +388,13 @@ void update_sched_domain_debugfs(void)
 {
 	int cpu, i;
 
+	/*
+	 * This can unfortunately be invoked before sched_debug_init() creates
+	 * the debug directory. Don't touch sd_sysctl_cpus until then.
+	 */
+	if (!debugfs_sched)
+		return;
+
 	if (!cpumask_available(sd_sysctl_cpus)) {
 		if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
 			return;
@@ -600,6 +607,9 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "idle_h_nr_running",
+			cfs_rq->idle_h_nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",

kernel/sched/fair.c

@@ -431,6 +431,23 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 	}
 }
 
+static int tg_is_idle(struct task_group *tg)
+{
+	return tg->idle > 0;
+}
+
+static int cfs_rq_is_idle(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->idle > 0;
+}
+
+static int se_is_idle(struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		return task_has_idle_policy(task_of(se));
+	return cfs_rq_is_idle(group_cfs_rq(se));
+}
+
 #else	/* !CONFIG_FAIR_GROUP_SCHED */
 
 #define for_each_sched_entity(se) \
@@ -468,6 +485,21 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
 }
 
+static int tg_is_idle(struct task_group *tg)
+{
+	return 0;
+}
+
+static int cfs_rq_is_idle(struct cfs_rq *cfs_rq)
+{
+	return 0;
+}
+
+static int se_is_idle(struct sched_entity *se)
+{
+	return 0;
+}
+
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
 static __always_inline
@@ -1486,7 +1518,7 @@ static inline bool is_core_idle(int cpu)
 		if (cpu == sibling)
 			continue;
 
-		if (!idle_cpu(cpu))
+		if (!idle_cpu(sibling))
 			return false;
 	}
 #endif
@@ -4841,6 +4873,9 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 
+		if (cfs_rq_is_idle(group_cfs_rq(se)))
+			idle_task_delta = cfs_rq->h_nr_running;
+
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
@@ -4860,6 +4895,9 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		update_load_avg(qcfs_rq, se, 0);
 		se_update_runnable(se);
 
+		if (cfs_rq_is_idle(group_cfs_rq(se)))
+			idle_task_delta = cfs_rq->h_nr_running;
+
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 	}
@@ -4904,39 +4942,45 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+
 		if (se->on_rq)
 			break;
-		cfs_rq = cfs_rq_of(se);
-		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+		enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP);
+
+		if (cfs_rq_is_idle(group_cfs_rq(se)))
+			idle_task_delta = cfs_rq->h_nr_running;
 
-		cfs_rq->h_nr_running += task_delta;
-		cfs_rq->idle_h_nr_running += idle_task_delta;
+		qcfs_rq->h_nr_running += task_delta;
+		qcfs_rq->idle_h_nr_running += idle_task_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
-		if (cfs_rq_throttled(cfs_rq))
+		if (cfs_rq_throttled(qcfs_rq))
 			goto unthrottle_throttle;
 	}
 
 	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
+		update_load_avg(qcfs_rq, se, UPDATE_TG);
 		se_update_runnable(se);
 
-		cfs_rq->h_nr_running += task_delta;
-		cfs_rq->idle_h_nr_running += idle_task_delta;
+		if (cfs_rq_is_idle(group_cfs_rq(se)))
+			idle_task_delta = cfs_rq->h_nr_running;
 
+		qcfs_rq->h_nr_running += task_delta;
+		qcfs_rq->idle_h_nr_running += idle_task_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
-		if (cfs_rq_throttled(cfs_rq))
+		if (cfs_rq_throttled(qcfs_rq))
 			goto unthrottle_throttle;
 
 		/*
 		 * One parent has been throttled and cfs_rq removed from the
 		 * list. Add it back to not break the leaf list.
 		 */
-		if (throttled_hierarchy(cfs_rq))
-			list_add_leaf_cfs_rq(cfs_rq);
+		if (throttled_hierarchy(qcfs_rq))
+			list_add_leaf_cfs_rq(qcfs_rq);
 	}
 
 	/* At this point se is NULL and we are at root level*/
@@ -4949,9 +4993,9 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	 * assertion below.
 	 */
 	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
-		if (list_add_leaf_cfs_rq(cfs_rq))
+		if (list_add_leaf_cfs_rq(qcfs_rq))
 			break;
 	}
 
@@ -5574,6 +5618,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		if (cfs_rq_is_idle(cfs_rq))
+			idle_h_nr_running = 1;
+
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto enqueue_throttle;
@@ -5591,6 +5638,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		if (cfs_rq_is_idle(cfs_rq))
+			idle_h_nr_running = 1;
+
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto enqueue_throttle;
@@ -5668,6 +5718,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		if (cfs_rq_is_idle(cfs_rq))
+			idle_h_nr_running = 1;
+
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto dequeue_throttle;
@@ -5697,6 +5750,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		if (cfs_rq_is_idle(cfs_rq))
+			idle_h_nr_running = 1;
+
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto dequeue_throttle;
@@ -6249,7 +6305,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		time = cpu_clock(this);
 	}
 
-	for_each_cpu_wrap(cpu, cpus, target) {
+	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);
 			if ((unsigned int)i < nr_cpumask_bits)
@@ -6376,6 +6432,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
+	p->recent_used_cpu = prev;
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
@@ -6902,9 +6959,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
 		/* Fast path */
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
-
-		if (want_affine)
-			current->recent_used_cpu = cpu;
 	}
 	rcu_read_unlock();
 
@@ -7041,24 +7095,22 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
-		return;
-
 	for_each_sched_entity(se) {
 		if (SCHED_WARN_ON(!se->on_rq))
 			return;
+		if (se_is_idle(se))
+			return;
 		cfs_rq_of(se)->last = se;
 	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
-		return;
-
 	for_each_sched_entity(se) {
 		if (SCHED_WARN_ON(!se->on_rq))
 			return;
+		if (se_is_idle(se))
+			return;
 		cfs_rq_of(se)->next = se;
 	}
 }
@@ -7079,6 +7131,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 	int next_buddy_marked = 0;
+	int cse_is_idle, pse_is_idle;
 
 	if (unlikely(se == pse))
 		return;
@@ -7123,8 +7176,21 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	find_matching_se(&se, &pse);
-	update_curr(cfs_rq_of(se));
 	BUG_ON(!pse);
+
+	cse_is_idle = se_is_idle(se);
+	pse_is_idle = se_is_idle(pse);
+
+	/*
+	 * Preempt an idle group in favor of a non-idle group (and don't preempt
+	 * in the inverse case).
+	 */
+	if (cse_is_idle && !pse_is_idle)
+		goto preempt;
+	if (cse_is_idle != pse_is_idle)
+		return;
+
+	update_curr(cfs_rq_of(se));
 	if (wakeup_preempt_entity(se, pse) == 1) {
 		/*
 		 * Bias pick_next to pick the sched entity that is
@@ -10217,9 +10283,11 @@ static inline int on_null_domain(struct rq *rq)
 static inline int find_new_ilb(void)
 {
 	int ilb;
+	const struct cpumask *hk_mask;
+
+	hk_mask = housekeeping_cpumask(HK_FLAG_MISC);
 
-	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
-			      housekeeping_cpumask(HK_FLAG_MISC)) {
+	for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
 
 		if (ilb == smp_processor_id())
 			continue;
@@ -11416,10 +11484,12 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 
 static DEFINE_MUTEX(shares_mutex);
 
-int sched_group_set_shares(struct task_group *tg, unsigned long shares)
+static int __sched_group_set_shares(struct task_group *tg, unsigned long shares)
 {
 	int i;
 
+	lockdep_assert_held(&shares_mutex);
+
 	/*
 	 * We can't change the weight of the root cgroup.
 	 */
@@ -11428,9 +11498,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 
 	shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
 
-	mutex_lock(&shares_mutex);
 	if (tg->shares == shares)
-		goto done;
+		return 0;
 
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
@@ -11448,10 +11517,88 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		rq_unlock_irqrestore(rq, &rf);
 	}
 
-done:
+	return 0;
+}
+
+int sched_group_set_shares(struct task_group *tg, unsigned long shares)
+{
+	int ret;
+
+	mutex_lock(&shares_mutex);
+	if (tg_is_idle(tg))
+		ret = -EINVAL;
+	else
+		ret = __sched_group_set_shares(tg, shares);
+	mutex_unlock(&shares_mutex);
+
+	return ret;
+}
+
+int sched_group_set_idle(struct task_group *tg, long idle)
+{
+	int i;
+
+	if (tg == &root_task_group)
+		return -EINVAL;
+
+	if (idle < 0 || idle > 1)
+		return -EINVAL;
+
+	mutex_lock(&shares_mutex);
+
+	if (tg->idle == idle) {
+		mutex_unlock(&shares_mutex);
+		return 0;
+	}
+
+	tg->idle = idle;
+
+	for_each_possible_cpu(i) {
+		struct rq *rq = cpu_rq(i);
+		struct sched_entity *se = tg->se[i];
+		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
+		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
+		long idle_task_delta;
+		struct rq_flags rf;
+
+		rq_lock_irqsave(rq, &rf);
+
+		grp_cfs_rq->idle = idle;
+		if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq)))
+			goto next_cpu;
+
+		idle_task_delta = grp_cfs_rq->h_nr_running -
+				  grp_cfs_rq->idle_h_nr_running;
+		if (!cfs_rq_is_idle(grp_cfs_rq))
+			idle_task_delta *= -1;
+
+		for_each_sched_entity(se) {
+			struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+			if (!se->on_rq)
+				break;
+
+			cfs_rq->idle_h_nr_running += idle_task_delta;
+
+			/* Already accounted at parent level and above. */
+			if (cfs_rq_is_idle(cfs_rq))
+				break;
+		}
+
+next_cpu:
+		rq_unlock_irqrestore(rq, &rf);
+	}
+
+	/* Idle groups have minimum weight. */
+	if (tg_is_idle(tg))
+		__sched_group_set_shares(tg, scale_load(WEIGHT_IDLEPRIO));
+	else
+		__sched_group_set_shares(tg, NICE_0_LOAD);
+
 	mutex_unlock(&shares_mutex);
 	return 0;
 }
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 void free_fair_sched_group(struct task_group *tg) { }

kernel/sched/sched.h

@@ -227,6 +227,8 @@ static inline void update_avg(u64 *avg, u64 sample)
  */
 #define SCHED_FLAG_SUGOV	0x10000000
 
+#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV)
+
 static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
 {
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
@@ -394,6 +396,9 @@ struct task_group {
 	struct cfs_rq		**cfs_rq;
 	unsigned long		shares;
 
+	/* A positive value indicates that this is a SCHED_IDLE group. */
+	int			idle;
+
 #ifdef	CONFIG_SMP
 	/*
 	 * load_avg can be heavily contended at clock tick time, so put
@@ -503,6 +508,8 @@ extern void sched_move_task(struct task_struct *tsk);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
+extern int sched_group_set_idle(struct task_group *tg, long idle);
+
 #ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);
@@ -599,6 +606,9 @@ struct cfs_rq {
 	struct list_head	leaf_cfs_rq_list;
 	struct task_group	*tg;	/* group that "owns" this runqueue */
 
+	/* Locally cached copy of our task_group's idle value */
+	int			idle;
+
 #ifdef CONFIG_CFS_BANDWIDTH
 	int			runtime_enabled;
 	s64			runtime_remaining;
@@ -2234,6 +2244,7 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq);
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
 #define SCA_MIGRATE_ENABLE	0x04
+#define SCA_USER		0x08
 
 #ifdef CONFIG_SMP
 
@@ -2385,6 +2396,21 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
+#ifdef CONFIG_SCHED_DEBUG
+extern unsigned int sysctl_sched_latency;
+extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_wakeup_granularity;
+extern int sysctl_resched_latency_warn_ms;
+extern int sysctl_resched_latency_warn_once;
+
+extern unsigned int sysctl_sched_tunable_scaling;
+
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_size;
+#endif
+
 #ifdef CONFIG_SCHED_HRTICK
 
 /*

kernel/sched/topology.c

@@ -1482,6 +1482,8 @@ int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
 static struct cpumask		***sched_domains_numa_masks;
 int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
+
+static unsigned long __read_mostly *sched_numa_onlined_nodes;
 #endif
 
 /*
@@ -1833,6 +1835,16 @@ void sched_init_numa(void)
 			sched_domains_numa_masks[i][j] = mask;
 
 			for_each_node(k) {
+				/*
+				 * Distance information can be unreliable for
+				 * offline nodes, defer building the node
+				 * masks to its bringup.
+				 * This relies on all unique distance values
+				 * still being visible at init time.
+				 */
+				if (!node_online(j))
+					continue;
+
 				if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
 					sched_numa_warn("Node-distance not symmetric");
 
@@ -1886,6 +1898,53 @@ void sched_init_numa(void)
 	sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
 
 	init_numa_topology_type();
+
+	sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL);
+	if (!sched_numa_onlined_nodes)
+		return;
+
+	bitmap_zero(sched_numa_onlined_nodes, nr_node_ids);
+	for_each_online_node(i)
+		bitmap_set(sched_numa_onlined_nodes, i, 1);
+}
+
+static void __sched_domains_numa_masks_set(unsigned int node)
+{
+	int i, j;
+
+	/*
+	 * NUMA masks are not built for offline nodes in sched_init_numa().
+	 * Thus, when a CPU of a never-onlined-before node gets plugged in,
+	 * adding that new CPU to the right NUMA masks is not sufficient: the
+	 * masks of that CPU's node must also be updated.
+	 */
+	if (test_bit(node, sched_numa_onlined_nodes))
+		return;
+
+	bitmap_set(sched_numa_onlined_nodes, node, 1);
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			if (!node_online(j) || node == j)
+				continue;
+
+			if (node_distance(j, node) > sched_domains_numa_distance[i])
+				continue;
+
+			/* Add remote nodes in our masks */
+			cpumask_or(sched_domains_numa_masks[i][node],
+				   sched_domains_numa_masks[i][node],
+				   sched_domains_numa_masks[0][j]);
+		}
+	}
+
+	/*
+	 * A new node has been brought up, potentially changing the topology
+	 * classification.
+	 *
+	 * Note that this is racy vs any use of sched_numa_topology_type :/
+	 */
+	init_numa_topology_type();
 }
 
 void sched_domains_numa_masks_set(unsigned int cpu)
@@ -1893,8 +1952,14 @@ void sched_domains_numa_masks_set(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	int i, j;
 
+	__sched_domains_numa_masks_set(node);
+
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		for (j = 0; j < nr_node_ids; j++) {
+			if (!node_online(j))
+				continue;
+
+			/* Set ourselves in the remote node's masks */
 			if (node_distance(j, node) <= sched_domains_numa_distance[i])
 				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
 		}