Merge tag 'sched-core-2022-12-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Implement persistent user-requested affinity: introduce
   affinity_context::user_mask and unconditionally preserve the
   user-requested CPU affinity masks, for long-lived tasks to better
   interact with cpusets & CPU hotplug events over longer timespans,
   without destroying the original affinity intent if the underlying
   topology changes.

 - Uclamp updates: fix relationship between uclamp and fits_capacity()

 - PSI fixes

 - Misc fixes & updates

* tag 'sched-core-2022-12-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Clear ttwu_pending after enqueue_task()
  sched/psi: Use task->psi_flags to clear in CPU migration
  sched/psi: Stop relying on timer_pending() for poll_work rescheduling
  sched/psi: Fix avgs_work re-arm in psi_avgs_work()
  sched/psi: Fix possible missing or delayed pending event
  sched: Always clear user_cpus_ptr in do_set_cpus_allowed()
  sched: Enforce user requested affinity
  sched: Always preserve the user requested cpumask
  sched: Introduce affinity_context
  sched: Add __releases annotations to affine_move_task()
  sched/fair: Check if prev_cpu has highest spare cap in feec()
  sched/fair: Consider capacity inversion in util_fits_cpu()
  sched/fair: Detect capacity inversion
  sched/uclamp: Cater for uclamp in find_energy_efficient_cpu()'s early exit condition
  sched/uclamp: Make cpu_overutilized() use util_fits_cpu()
  sched/uclamp: Make asym_fits_capacity() use util_fits_cpu()
  sched/uclamp: Make select_idle_capacity() use util_fits_cpu()
  sched/uclamp: Fix fits_capacity() check in feec()
  sched/uclamp: Make task_fits_capacity() use util_fits_cpu()
  sched/uclamp: Fix relationship between uclamp and migration margin

8 files changed, 607 insertions, 183 deletions

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 6e437273506892..1e0a0d7ace3af2 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -72,6 +72,9 @@ enum psi_states {
 /* Use one bit in the state mask to track TSK_ONCPU */
 #define PSI_ONCPU	(1 << NR_PSI_STATES)
 
+/* Flag whether to re-arm avgs_work, see details in get_recent_times() */
+#define PSI_STATE_RESCHEDULE	(1 << (NR_PSI_STATES + 1))
+
 enum psi_aggregators {
 	PSI_AVGS = 0,
 	PSI_POLL,
@@ -177,6 +180,7 @@ struct psi_group {
 	struct timer_list poll_timer;
 	wait_queue_head_t poll_wait;
 	atomic_t poll_wakeup;
+	atomic_t poll_scheduled;
 
 	/* Protects data used by the monitor */
 	struct mutex trigger_lock;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4e03f1dcbe52ac..5affff14993dff 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -888,9 +888,6 @@ struct task_struct {
 	unsigned			sched_reset_on_fork:1;
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
-#ifdef CONFIG_PSI
-	unsigned			sched_psi_wake_requeue:1;
-#endif
 
 	/* Force alignment to the next boundary: */
 	unsigned			:0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index daff72f003858d..78b2d5cabcc5dd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1392,7 +1392,7 @@ static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
 	if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
 		return;
 
-	WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
+	uclamp_rq_set(rq, clamp_id, clamp_value);
 }
 
 static inline
@@ -1543,8 +1543,8 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
 	if (bucket->tasks == 1 || uc_se->value > bucket->value)
 		bucket->value = uc_se->value;
 
-	if (uc_se->value > READ_ONCE(uc_rq->value))
-		WRITE_ONCE(uc_rq->value, uc_se->value);
+	if (uc_se->value > uclamp_rq_get(rq, clamp_id))
+		uclamp_rq_set(rq, clamp_id, uc_se->value);
 }
 
 /*
@@ -1610,7 +1610,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	if (likely(bucket->tasks))
 		return;
 
-	rq_clamp = READ_ONCE(uc_rq->value);
+	rq_clamp = uclamp_rq_get(rq, clamp_id);
 	/*
 	 * Defensive programming: this should never happen. If it happens,
 	 * e.g. due to future modification, warn and fixup the expected value.
@@ -1618,7 +1618,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	SCHED_WARN_ON(bucket->value > rq_clamp);
 	if (bucket->value >= rq_clamp) {
 		bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
-		WRITE_ONCE(uc_rq->value, bkt_clamp);
+		uclamp_rq_set(rq, clamp_id, bkt_clamp);
 	}
 }
 
@@ -2053,7 +2053,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!(flags & ENQUEUE_RESTORE)) {
 		sched_info_enqueue(rq, p);
-		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+		psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
 	}
 
 	uclamp_rq_inc(rq, p);
@@ -2189,14 +2189,18 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 #ifdef CONFIG_SMP
 
 static void
-__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
 
 static int __set_cpus_allowed_ptr(struct task_struct *p,
-				  const struct cpumask *new_mask,
-				  u32 flags);
+				  struct affinity_context *ctx);
 
 static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 {
+	struct affinity_context ac = {
+		.new_mask  = cpumask_of(rq->cpu),
+		.flags     = SCA_MIGRATE_DISABLE,
+	};
+
 	if (likely(!p->migration_disabled))
 		return;
 
@@ -2206,7 +2210,7 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 	/*
 	 * Violates locking rules! see comment in __do_set_cpus_allowed().
 	 */
-	__do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
+	__do_set_cpus_allowed(p, &ac);
 }
 
 void migrate_disable(void)
@@ -2228,6 +2232,10 @@ EXPORT_SYMBOL_GPL(migrate_disable);
 void migrate_enable(void)
 {
 	struct task_struct *p = current;
+	struct affinity_context ac = {
+		.new_mask  = &p->cpus_mask,
+		.flags     = SCA_MIGRATE_ENABLE,
+	};
 
 	if (p->migration_disabled > 1) {
 		p->migration_disabled--;
@@ -2243,7 +2251,7 @@ void migrate_enable(void)
 	 */
 	preempt_disable();
 	if (p->cpus_ptr != &p->cpus_mask)
-		__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+		__set_cpus_allowed_ptr(p, &ac);
 	/*
 	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
 	 * regular cpus_mask, otherwise things that race (eg.
@@ -2523,19 +2531,25 @@ out_unlock:
  * sched_class::set_cpus_allowed must do the below, but is not required to
  * actually call this function.
  */
-void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
+void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
 {
-	if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
-		p->cpus_ptr = new_mask;
+	if (ctx->flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
+		p->cpus_ptr = ctx->new_mask;
 		return;
 	}
 
-	cpumask_copy(&p->cpus_mask, new_mask);
-	p->nr_cpus_allowed = cpumask_weight(new_mask);
+	cpumask_copy(&p->cpus_mask, ctx->new_mask);
+	p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
+
+	/*
+	 * Swap in a new user_cpus_ptr if SCA_USER flag set
+	 */
+	if (ctx->flags & SCA_USER)
+		swap(p->user_cpus_ptr, ctx->user_mask);
 }
 
 static void
-__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
 {
 	struct rq *rq = task_rq(p);
 	bool queued, running;
@@ -2552,7 +2566,7 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
 	 *
 	 * XXX do further audits, this smells like something putrid.
 	 */
-	if (flags & SCA_MIGRATE_DISABLE)
+	if (ctx->flags & SCA_MIGRATE_DISABLE)
 		SCHED_WARN_ON(!p->on_cpu);
 	else
 		lockdep_assert_held(&p->pi_lock);
@@ -2571,7 +2585,7 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
 	if (running)
 		put_prev_task(rq, p);
 
-	p->sched_class->set_cpus_allowed(p, new_mask, flags);
+	p->sched_class->set_cpus_allowed(p, ctx);
 
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
@@ -2579,14 +2593,27 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
 		set_next_task(rq, p);
 }
 
+/*
+ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
+ * affinity (if any) should be destroyed too.
+ */
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-	__do_set_cpus_allowed(p, new_mask, 0);
+	struct affinity_context ac = {
+		.new_mask  = new_mask,
+		.user_mask = NULL,
+		.flags     = SCA_USER,	/* clear the user requested mask */
+	};
+
+	__do_set_cpus_allowed(p, &ac);
+	kfree(ac.user_mask);
 }
 
 int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 		      int node)
 {
+	unsigned long flags;
+
 	if (!src->user_cpus_ptr)
 		return 0;
 
@@ -2594,7 +2621,10 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 	if (!dst->user_cpus_ptr)
 		return -ENOMEM;
 
+	/* Use pi_lock to protect content of user_cpus_ptr */
+	raw_spin_lock_irqsave(&src->pi_lock, flags);
 	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	raw_spin_unlock_irqrestore(&src->pi_lock, flags);
 	return 0;
 }
 
@@ -2690,6 +2720,8 @@ void release_user_cpus_ptr(struct task_struct *p)
  */
 static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
 			    int dest_cpu, unsigned int flags)
+	__releases(rq->lock)
+	__releases(p->pi_lock)
 {
 	struct set_affinity_pending my_pending = { }, *pending = NULL;
 	bool stop_pending, complete = false;
@@ -2832,8 +2864,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
  * Called with both p->pi_lock and rq->lock held; drops both before returning.
  */
 static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
-					 const struct cpumask *new_mask,
-					 u32 flags,
+					 struct affinity_context *ctx,
 					 struct rq *rq,
 					 struct rq_flags *rf)
 	__releases(rq->lock)
@@ -2842,7 +2873,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 	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;
 	int ret = 0;
 
@@ -2862,7 +2892,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 		cpu_valid_mask = cpu_online_mask;
 	}
 
-	if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) {
+	if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -2871,18 +2901,18 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 	 * Must re-check here, to close a race against __kthread_bind(),
 	 * sched_setaffinity() is not guaranteed to observe the flag.
 	 */
-	if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
+	if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (!(flags & SCA_MIGRATE_ENABLE)) {
-		if (cpumask_equal(&p->cpus_mask, new_mask))
+	if (!(ctx->flags & SCA_MIGRATE_ENABLE)) {
+		if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
 			goto out;
 
 		if (WARN_ON_ONCE(p == current &&
 				 is_migration_disabled(p) &&
-				 !cpumask_test_cpu(task_cpu(p), new_mask))) {
+				 !cpumask_test_cpu(task_cpu(p), ctx->new_mask))) {
 			ret = -EBUSY;
 			goto out;
 		}
@@ -2893,22 +2923,15 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 	 * for groups of tasks (ie. cpuset), so that load balancing is not
 	 * immediately required to distribute the tasks within their new mask.
 	 */
-	dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
+	dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, ctx->new_mask);
 	if (dest_cpu >= nr_cpu_ids) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	__do_set_cpus_allowed(p, new_mask, flags);
-
-	if (flags & SCA_USER)
-		user_mask = clear_user_cpus_ptr(p);
-
-	ret = affine_move_task(rq, p, rf, dest_cpu, flags);
+	__do_set_cpus_allowed(p, ctx);
 
-	kfree(user_mask);
-
-	return ret;
+	return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
 
 out:
 	task_rq_unlock(rq, p, rf);
@@ -2926,25 +2949,41 @@ out:
  * 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 affinity_context *ctx)
 {
 	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);
+	/*
+	 * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
+	 * flags are set.
+	 */
+	if (p->user_cpus_ptr &&
+	    !(ctx->flags & (SCA_USER | SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) &&
+	    cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
+		ctx->new_mask = rq->scratch_mask;
+
+	return __set_cpus_allowed_ptr_locked(p, ctx, 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);
+	struct affinity_context ac = {
+		.new_mask  = new_mask,
+		.flags     = 0,
+	};
+
+	return __set_cpus_allowed_ptr(p, &ac);
 }
 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.
+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
+ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
+ * affinity or use cpu_online_mask instead.
+ *
  * If the resulting mask is empty, leave the affinity unchanged and return
  * -EINVAL.
  */
@@ -2952,17 +2991,14 @@ 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 affinity_context ac = {
+		.new_mask  = new_mask,
+		.flags     = 0,
+	};
 	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);
 
 	/*
@@ -2975,31 +3011,21 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
 		goto err_unlock;
 	}
 
-	if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) {
+	if (!cpumask_and(new_mask, task_user_cpus(p), 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);
+	return __set_cpus_allowed_ptr_locked(p, &ac, 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
+ * task_cpu_possible_mask() and point @p->user_cpus_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.
  */
@@ -3043,34 +3069,29 @@ out_free_mask:
 }
 
 static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);
+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
 
 /*
  * 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.
+ * call to force_compatible_cpus_allowed_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;
+	struct affinity_context ac = {
+		.new_mask  = task_user_cpus(p),
+		.flags     = 0,
+	};
+	int ret;
 
 	/*
-	 * 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().
+	 * Try to restore the old affinity mask with __sched_setaffinity().
+	 * Cpuset masking will be done there too.
 	 */
-	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);
+	ret = __sched_setaffinity(p, &ac);
+	WARN_ON_ONCE(ret);
 }
 
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
@@ -3548,10 +3569,9 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
 #else /* CONFIG_SMP */
 
 static inline int __set_cpus_allowed_ptr(struct task_struct *p,
-					 const struct cpumask *new_mask,
-					 u32 flags)
+					 struct affinity_context *ctx)
 {
-	return set_cpus_allowed_ptr(p, new_mask);
+	return set_cpus_allowed_ptr(p, ctx->new_mask);
 }
 
 static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
@@ -3719,13 +3739,6 @@ void sched_ttwu_pending(void *arg)
 	if (!llist)
 		return;
 
-	/*
-	 * rq::ttwu_pending racy indication of out-standing wakeups.
-	 * Races such that false-negatives are possible, since they
-	 * are shorter lived that false-positives would be.
-	 */
-	WRITE_ONCE(rq->ttwu_pending, 0);
-
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
@@ -3739,6 +3752,17 @@ void sched_ttwu_pending(void *arg)
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
 	}
 
+	/*
+	 * Must be after enqueueing at least once task such that
+	 * idle_cpu() does not observe a false-negative -- if it does,
+	 * it is possible for select_idle_siblings() to stack a number
+	 * of tasks on this CPU during that window.
+	 *
+	 * It is ok to clear ttwu_pending when another task pending.
+	 * We will receive IPI after local irq enabled and then enqueue it.
+	 * Since now nr_running > 0, idle_cpu() will always get correct result.
+	 */
+	WRITE_ONCE(rq->ttwu_pending, 0);
 	rq_unlock_irqrestore(rq, &rf);
 }
 
@@ -8106,7 +8130,7 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 #endif
 
 static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
 {
 	int retval;
 	cpumask_var_t cpus_allowed, new_mask;
@@ -8120,13 +8144,16 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
 	}
 
 	cpuset_cpus_allowed(p, cpus_allowed);
-	cpumask_and(new_mask, mask, cpus_allowed);
+	cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
+
+	ctx->new_mask = new_mask;
+	ctx->flags |= SCA_CHECK;
 
 	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);
+
+	retval = __set_cpus_allowed_ptr(p, ctx);
 	if (retval)
 		goto out_free_new_mask;
 
@@ -8137,7 +8164,24 @@ again:
 		 * Just reset the cpumask to the cpuset's cpus_allowed.
 		 */
 		cpumask_copy(new_mask, cpus_allowed);
-		goto again;
+
+		/*
+		 * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
+		 * will restore the previous user_cpus_ptr value.
+		 *
+		 * In the unlikely event a previous user_cpus_ptr exists,
+		 * we need to further restrict the mask to what is allowed
+		 * by that old user_cpus_ptr.
+		 */
+		if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
+			bool empty = !cpumask_and(new_mask, new_mask,
+						  ctx->user_mask);
+
+			if (WARN_ON_ONCE(empty))
+				cpumask_copy(new_mask, cpus_allowed);
+		}
+		__set_cpus_allowed_ptr(p, ctx);
+		retval = -EINVAL;
 	}
 
 out_free_new_mask:
@@ -8149,6 +8193,8 @@ out_free_cpus_allowed:
 
 long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
+	struct affinity_context ac;
+	struct cpumask *user_mask;
 	struct task_struct *p;
 	int retval;
 
@@ -8183,7 +8229,21 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_put_task;
 
-	retval = __sched_setaffinity(p, in_mask);
+	user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+	if (!user_mask) {
+		retval = -ENOMEM;
+		goto out_put_task;
+	}
+	cpumask_copy(user_mask, in_mask);
+	ac = (struct affinity_context){
+		.new_mask  = in_mask,
+		.user_mask = user_mask,
+		.flags     = SCA_USER,
+	};
+
+	retval = __sched_setaffinity(p, &ac);
+	kfree(ac.user_mask);
+
 out_put_task:
 	put_task_struct(p);
 	return retval;
@@ -8964,6 +9024,12 @@ void show_state_filter(unsigned int state_filter)
  */
 void __init init_idle(struct task_struct *idle, int cpu)
 {
+#ifdef CONFIG_SMP
+	struct affinity_context ac = (struct affinity_context) {
+		.new_mask  = cpumask_of(cpu),
+		.flags     = 0,
+	};
+#endif
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
@@ -8988,7 +9054,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	 *
 	 * And since this is boot we can forgo the serialization.
 	 */
-	set_cpus_allowed_common(idle, cpumask_of(cpu), 0);
+	set_cpus_allowed_common(idle, &ac);
 #endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
@@ -9775,6 +9841,7 @@ void __init sched_init(void)
 
 		rq->core_cookie = 0UL;
 #endif
+		zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
 	}
 
 	set_load_weight(&init_task, false);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9ae8f41e3372f3..0d97d54276cc83 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2485,8 +2485,7 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 }
 
 static void set_cpus_allowed_dl(struct task_struct *p,
-				const struct cpumask *new_mask,
-				u32 flags)
+				struct affinity_context *ctx)
 {
 	struct root_domain *src_rd;
 	struct rq *rq;
@@ -2501,7 +2500,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	 * update. We already made space for us in the destination
 	 * domain (see cpuset_can_attach()).
 	 */
-	if (!cpumask_intersects(src_rd->span, new_mask)) {
+	if (!cpumask_intersects(src_rd->span, ctx->new_mask)) {
 		struct dl_bw *src_dl_b;
 
 		src_dl_b = dl_bw_of(cpu_of(rq));
@@ -2515,7 +2514,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	set_cpus_allowed_common(p, new_mask, flags);
+	set_cpus_allowed_common(p, ctx);
 }
 
 /* Assumes rq->lock is held */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e4a0b8bd941c78..4cc56c91e06e61 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4280,14 +4280,16 @@ static inline unsigned long task_util_est(struct task_struct *p)
 }
 
 #ifdef CONFIG_UCLAMP_TASK
-static inline unsigned long uclamp_task_util(struct task_struct *p)
+static inline unsigned long uclamp_task_util(struct task_struct *p,
+					     unsigned long uclamp_min,
+					     unsigned long uclamp_max)
 {
-	return clamp(task_util_est(p),
-		     uclamp_eff_value(p, UCLAMP_MIN),
-		     uclamp_eff_value(p, UCLAMP_MAX));
+	return clamp(task_util_est(p), uclamp_min, uclamp_max);
 }
 #else
-static inline unsigned long uclamp_task_util(struct task_struct *p)
+static inline unsigned long uclamp_task_util(struct task_struct *p,
+					     unsigned long uclamp_min,
+					     unsigned long uclamp_max)
 {
 	return task_util_est(p);
 }
@@ -4426,10 +4428,139 @@ done:
 	trace_sched_util_est_se_tp(&p->se);
 }
 
-static inline int task_fits_capacity(struct task_struct *p,
-				     unsigned long capacity)
+static inline int util_fits_cpu(unsigned long util,
+				unsigned long uclamp_min,
+				unsigned long uclamp_max,
+				int cpu)
 {
-	return fits_capacity(uclamp_task_util(p), capacity);
+	unsigned long capacity_orig, capacity_orig_thermal;
+	unsigned long capacity = capacity_of(cpu);
+	bool fits, uclamp_max_fits;
+
+	/*
+	 * Check if the real util fits without any uclamp boost/cap applied.
+	 */
+	fits = fits_capacity(util, capacity);
+
+	if (!uclamp_is_used())
+		return fits;
+
+	/*
+	 * We must use capacity_orig_of() for comparing against uclamp_min and
+	 * uclamp_max. We only care about capacity pressure (by using
+	 * capacity_of()) for comparing against the real util.
+	 *
+	 * If a task is boosted to 1024 for example, we don't want a tiny
+	 * pressure to skew the check whether it fits a CPU or not.
+	 *
+	 * Similarly if a task is capped to capacity_orig_of(little_cpu), it
+	 * should fit a little cpu even if there's some pressure.
+	 *
+	 * Only exception is for thermal pressure since it has a direct impact
+	 * on available OPP of the system.
+	 *
+	 * We honour it for uclamp_min only as a drop in performance level
+	 * could result in not getting the requested minimum performance level.
+	 *
+	 * For uclamp_max, we can tolerate a drop in performance level as the
+	 * goal is to cap the task. So it's okay if it's getting less.
+	 *
+	 * In case of capacity inversion we should honour the inverted capacity
+	 * for both uclamp_min and uclamp_max all the time.
+	 */
+	capacity_orig = cpu_in_capacity_inversion(cpu);
+	if (capacity_orig) {
+		capacity_orig_thermal = capacity_orig;
+	} else {
+		capacity_orig = capacity_orig_of(cpu);
+		capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
+	}
+
+	/*
+	 * We want to force a task to fit a cpu as implied by uclamp_max.
+	 * But we do have some corner cases to cater for..
+	 *
+	 *
+	 *                                 C=z
+	 *   |                             ___
+	 *   |                  C=y       |   |
+	 *   |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _  uclamp_max
+	 *   |      C=x        |   |      |   |
+	 *   |      ___        |   |      |   |
+	 *   |     |   |       |   |      |   |    (util somewhere in this region)
+	 *   |     |   |       |   |      |   |
+	 *   |     |   |       |   |      |   |
+	 *   +----------------------------------------
+	 *         cpu0        cpu1       cpu2
+	 *
+	 *   In the above example if a task is capped to a specific performance
+	 *   point, y, then when:
+	 *
+	 *   * util = 80% of x then it does not fit on cpu0 and should migrate
+	 *     to cpu1
+	 *   * util = 80% of y then it is forced to fit on cpu1 to honour
+	 *     uclamp_max request.
+	 *
+	 *   which is what we're enforcing here. A task always fits if
+	 *   uclamp_max <= capacity_orig. But when uclamp_max > capacity_orig,
+	 *   the normal upmigration rules should withhold still.
+	 *
+	 *   Only exception is when we are on max capacity, then we need to be
+	 *   careful not to block overutilized state. This is so because:
+	 *
+	 *     1. There's no concept of capping at max_capacity! We can't go
+	 *        beyond this performance level anyway.
+	 *     2. The system is being saturated when we're operating near
+	 *        max capacity, it doesn't make sense to block overutilized.
+	 */
+	uclamp_max_fits = (capacity_orig == SCHED_CAPACITY_SCALE) && (uclamp_max == SCHED_CAPACITY_SCALE);
+	uclamp_max_fits = !uclamp_max_fits && (uclamp_max <= capacity_orig);
+	fits = fits || uclamp_max_fits;
+
+	/*
+	 *
+	 *                                 C=z
+	 *   |                             ___       (region a, capped, util >= uclamp_max)
+	 *   |                  C=y       |   |
+	 *   |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max
+	 *   |      C=x        |   |      |   |
+	 *   |      ___        |   |      |   |      (region b, uclamp_min <= util <= uclamp_max)
+	 *   |_ _ _|_ _|_ _ _ _| _ | _ _ _| _ | _ _ _ _ _ uclamp_min
+	 *   |     |   |       |   |      |   |
+	 *   |     |   |       |   |      |   |      (region c, boosted, util < uclamp_min)
+	 *   +----------------------------------------
+	 *         cpu0        cpu1       cpu2
+	 *
+	 * a) If util > uclamp_max, then we're capped, we don't care about
+	 *    actual fitness value here. We only care if uclamp_max fits
+	 *    capacity without taking margin/pressure into account.
+	 *    See comment above.
+	 *
+	 * b) If uclamp_min <= util <= uclamp_max, then the normal
+	 *    fits_capacity() rules apply. Except we need to ensure that we
+	 *    enforce we remain within uclamp_max, see comment above.
+	 *
+	 * c) If util < uclamp_min, then we are boosted. Same as (b) but we
+	 *    need to take into account the boosted value fits the CPU without
+	 *    taking margin/pressure into account.
+	 *
+	 * Cases (a) and (b) are handled in the 'fits' variable already. We
+	 * just need to consider an extra check for case (c) after ensuring we
+	 * handle the case uclamp_min > uclamp_max.
+	 */
+	uclamp_min = min(uclamp_min, uclamp_max);
+	if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE)
+		fits = fits && (uclamp_min <= capacity_orig_thermal);
+
+	return fits;
+}
+
+static inline int task_fits_cpu(struct task_struct *p, int cpu)
+{
+	unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN);
+	unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX);
+	unsigned long util = task_util_est(p);
+	return util_fits_cpu(util, uclamp_min, uclamp_max, cpu);
 }
 
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
@@ -4442,7 +4573,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) {
+	if (task_fits_cpu(p, cpu_of(rq))) {
 		rq->misfit_task_load = 0;
 		return;
 	}
@@ -5862,7 +5993,10 @@ static inline void hrtick_update(struct rq *rq)
 #ifdef CONFIG_SMP
 static inline bool cpu_overutilized(int cpu)
 {
-	return !fits_capacity(cpu_util_cfs(cpu), capacity_of(cpu));
+	unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+	unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+
+	return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
 }
 
 static inline void update_overutilized_status(struct rq *rq)
@@ -6654,21 +6788,23 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	unsigned long task_util, best_cap = 0;
+	unsigned long task_util, util_min, util_max, best_cap = 0;
 	int cpu, best_cpu = -1;
 	struct cpumask *cpus;
 
 	cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
-	task_util = uclamp_task_util(p);
+	task_util = task_util_est(p);
+	util_min = uclamp_eff_value(p, UCLAMP_MIN);
+	util_max = uclamp_eff_value(p, UCLAMP_MAX);
 
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
 			continue;
-		if (fits_capacity(task_util, cpu_cap))
+		if (util_fits_cpu(task_util, util_min, util_max, cpu))
 			return cpu;
 
 		if (cpu_cap > best_cap) {
@@ -6680,10 +6816,13 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	return best_cpu;
 }
 
-static inline bool asym_fits_capacity(unsigned long task_util, int cpu)
+static inline bool asym_fits_cpu(unsigned long util,
+				 unsigned long util_min,
+				 unsigned long util_max,
+				 int cpu)
 {
 	if (sched_asym_cpucap_active())
-		return fits_capacity(task_util, capacity_of(cpu));
+		return util_fits_cpu(util, util_min, util_max, cpu);
 
 	return true;
 }
@@ -6695,7 +6834,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	bool has_idle_core = false;
 	struct sched_domain *sd;
-	unsigned long task_util;
+	unsigned long task_util, util_min, util_max;
 	int i, recent_used_cpu;
 
 	/*
@@ -6704,7 +6843,9 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 */
 	if (sched_asym_cpucap_active()) {
 		sync_entity_load_avg(&p->se);
-		task_util = uclamp_task_util(p);
+		task_util = task_util_est(p);
+		util_min = uclamp_eff_value(p, UCLAMP_MIN);
+		util_max = uclamp_eff_value(p, UCLAMP_MAX);
 	}
 
 	/*
@@ -6713,7 +6854,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	lockdep_assert_irqs_disabled();
 
 	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
-	    asym_fits_capacity(task_util, target))
+	    asym_fits_cpu(task_util, util_min, util_max, target))
 		return target;
 
 	/*
@@ -6721,7 +6862,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
-	    asym_fits_capacity(task_util, prev))
+	    asym_fits_cpu(task_util, util_min, util_max, prev))
 		return prev;
 
 	/*
@@ -6736,7 +6877,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    in_task() &&
 	    prev == smp_processor_id() &&
 	    this_rq()->nr_running <= 1 &&
-	    asym_fits_capacity(task_util, prev)) {
+	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
 		return prev;
 	}
 
@@ -6748,7 +6889,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
-	    asym_fits_capacity(task_util, recent_used_cpu)) {
+	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 		return recent_used_cpu;
 	}
 
@@ -7044,6 +7185,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
 	unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
+	unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0;
+	unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024;
 	struct root_domain *rd = this_rq()->rd;
 	int cpu, best_energy_cpu, target = -1;
 	struct sched_domain *sd;
@@ -7068,7 +7211,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	target = prev_cpu;
 
 	sync_entity_load_avg(&p->se);
-	if (!task_util_est(p))
+	if (!uclamp_task_util(p, p_util_min, p_util_max))
 		goto unlock;
 
 	eenv_task_busy_time(&eenv, p, prev_cpu);
@@ -7076,7 +7219,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	for (; pd; pd = pd->next) {
 		unsigned long cpu_cap, cpu_thermal_cap, util;
 		unsigned long cur_delta, max_spare_cap = 0;
-		bool compute_prev_delta = false;
+		unsigned long rq_util_min, rq_util_max;
+		unsigned long util_min, util_max;
+		unsigned long prev_spare_cap = 0;
 		int max_spare_cap_cpu = -1;
 		unsigned long base_energy;
 
@@ -7112,26 +7257,45 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * much capacity we can get out of the CPU; this is
 			 * aligned with sched_cpu_util().
 			 */
-			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
-			if (!fits_capacity(util, cpu_cap))
+			if (uclamp_is_used()) {
+				if (uclamp_rq_is_idle(cpu_rq(cpu))) {
+					util_min = p_util_min;
+					util_max = p_util_max;
+				} else {
+					/*
+					 * Open code uclamp_rq_util_with() except for
+					 * the clamp() part. Ie: apply max aggregation
+					 * only. util_fits_cpu() logic requires to
+					 * operate on non clamped util but must use the
+					 * max-aggregated uclamp_{min, max}.
+					 */
+					rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+					rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+
+					util_min = max(rq_util_min, p_util_min);
+					util_max = max(rq_util_max, p_util_max);
+				}
+			}
+			if (!util_fits_cpu(util, util_min, util_max, cpu))
 				continue;
 
 			lsub_positive(&cpu_cap, util);
 
 			if (cpu == prev_cpu) {
 				/* Always use prev_cpu as a candidate. */
-				compute_prev_delta = true;
+				prev_spare_cap = cpu_cap;
 			} else if (cpu_cap > max_spare_cap) {
 				/*
 				 * Find the CPU with the maximum spare capacity
-				 * in the performance domain.
+				 * among the remaining CPUs in the performance
+				 * domain.
 				 */
 				max_spare_cap = cpu_cap;
 				max_spare_cap_cpu = cpu;
 			}
 		}
 
-		if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+		if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
 			continue;
 
 		eenv_pd_busy_time(&eenv, cpus, p);
@@ -7139,7 +7303,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		base_energy = compute_energy(&eenv, pd, cpus, p, -1);
 
 		/* Evaluate the energy impact of using prev_cpu. */
-		if (compute_prev_delta) {
+		if (prev_spare_cap > 0) {
 			prev_delta = compute_energy(&eenv, pd, cpus, p,
 						    prev_cpu);
 			/* CPU utilization has changed */
@@ -7150,7 +7314,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		}
 
 		/* Evaluate the energy impact of using max_spare_cap_cpu. */
-		if (max_spare_cap_cpu >= 0) {
+		if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
 			cur_delta = compute_energy(&eenv, pd, cpus, p,
 						   max_spare_cap_cpu);
 			/* CPU utilization has changed */
@@ -8276,7 +8440,7 @@ static int detach_tasks(struct lb_env *env)
 
 		case migrate_misfit:
 			/* This is not a misfit task */
-			if (task_fits_capacity(p, capacity_of(env->src_cpu)))
+			if (task_fits_cpu(p, env->src_cpu))
 				goto next;
 
 			env->imbalance = 0;
@@ -8665,16 +8829,73 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
+	unsigned long capacity_orig = arch_scale_cpu_capacity(cpu);
 	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
+	struct rq *rq = cpu_rq(cpu);
 
-	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
+	rq->cpu_capacity_orig = capacity_orig;
 
 	if (!capacity)
 		capacity = 1;
 
-	cpu_rq(cpu)->cpu_capacity = capacity;
-	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+	rq->cpu_capacity = capacity;
+
+	/*
+	 * Detect if the performance domain is in capacity inversion state.
+	 *
+	 * Capacity inversion happens when another perf domain with equal or
+	 * lower capacity_orig_of() ends up having higher capacity than this
+	 * domain after subtracting thermal pressure.
+	 *
+	 * We only take into account thermal pressure in this detection as it's
+	 * the only metric that actually results in *real* reduction of
+	 * capacity due to performance points (OPPs) being dropped/become
+	 * unreachable due to thermal throttling.
+	 *
+	 * We assume:
+	 *   * That all cpus in a perf domain have the same capacity_orig
+	 *     (same uArch).
+	 *   * Thermal pressure will impact all cpus in this perf domain
+	 *     equally.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
+		struct perf_domain *pd = rcu_dereference(rq->rd->pd);
+
+		rq->cpu_capacity_inverted = 0;
+
+		for (; pd; pd = pd->next) {
+			struct cpumask *pd_span = perf_domain_span(pd);
+			unsigned long pd_cap_orig, pd_cap;
+
+			cpu = cpumask_any(pd_span);
+			pd_cap_orig = arch_scale_cpu_capacity(cpu);
+
+			if (capacity_orig < pd_cap_orig)
+				continue;
+
+			/*
+			 * handle the case of multiple perf domains have the
+			 * same capacity_orig but one of them is under higher
+			 * thermal pressure. We record it as capacity
+			 * inversion.
+			 */
+			if (capacity_orig == pd_cap_orig) {
+				pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu));
+
+				if (pd_cap > inv_cap) {
+					rq->cpu_capacity_inverted = inv_cap;
+					break;
+				}
+			} else if (pd_cap_orig > inv_cap) {
+				rq->cpu_capacity_inverted = inv_cap;
+				break;
+			}
+		}
+	}
+
+	trace_sched_cpu_capacity_tp(rq);
 
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
@@ -9281,6 +9502,10 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 	memset(sgs, 0, sizeof(*sgs));
 
+	/* Assume that task can't fit any CPU of the group */
+	if (sd->flags & SD_ASYM_CPUCAPACITY)
+		sgs->group_misfit_task_load = 1;
+
 	for_each_cpu(i, sched_group_span(group)) {
 		struct rq *rq = cpu_rq(i);
 		unsigned int local;
@@ -9300,12 +9525,12 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 		if (!nr_running && idle_cpu_without(i, p))
 			sgs->idle_cpus++;
 
-	}
+		/* Check if task fits in the CPU */
+		if (sd->flags & SD_ASYM_CPUCAPACITY &&
+		    sgs->group_misfit_task_load &&
+		    task_fits_cpu(p, i))
+			sgs->group_misfit_task_load = 0;
 
-	/* Check if task fits in the group */
-	if (sd->flags & SD_ASYM_CPUCAPACITY &&
-	    !task_fits_capacity(p, group->sgc->max_capacity)) {
-		sgs->group_misfit_task_load = 1;
 	}
 
 	sgs->group_capacity = group->sgc->capacity;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ee2ecc081422ea..8ac8b81bfee65d 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -189,6 +189,7 @@ static void group_init(struct psi_group *group)
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
+	atomic_set(&group->poll_scheduled, 0);
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
 	group->poll_min_period = U32_MAX;
@@ -242,6 +243,8 @@ static void get_recent_times(struct psi_group *group, int cpu,
 			     u32 *pchanged_states)
 {
 	struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+	int current_cpu = raw_smp_processor_id();
+	unsigned int tasks[NR_PSI_TASK_COUNTS];
 	u64 now, state_start;
 	enum psi_states s;
 	unsigned int seq;
@@ -256,6 +259,8 @@ static void get_recent_times(struct psi_group *group, int cpu,
 		memcpy(times, groupc->times, sizeof(groupc->times));
 		state_mask = groupc->state_mask;
 		state_start = groupc->state_start;
+		if (cpu == current_cpu)
+			memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
 	} while (read_seqcount_retry(&groupc->seq, seq));
 
 	/* Calculate state time deltas against the previous snapshot */
@@ -280,6 +285,28 @@ static void get_recent_times(struct psi_group *group, int cpu,
 		if (delta)
 			*pchanged_states |= (1 << s);
 	}
+
+	/*
+	 * When collect_percpu_times() from the avgs_work, we don't want to
+	 * re-arm avgs_work when all CPUs are IDLE. But the current CPU running
+	 * this avgs_work is never IDLE, cause avgs_work can't be shut off.
+	 * So for the current CPU, we need to re-arm avgs_work only when
+	 * (NR_RUNNING > 1 || NR_IOWAIT > 0 || NR_MEMSTALL > 0), for other CPUs
+	 * we can just check PSI_NONIDLE delta.
+	 */
+	if (current_work() == &group->avgs_work.work) {
+		bool reschedule;
+
+		if (cpu == current_cpu)
+			reschedule = tasks[NR_RUNNING] +
+				     tasks[NR_IOWAIT] +
+				     tasks[NR_MEMSTALL] > 1;
+		else
+			reschedule = *pchanged_states & (1 << PSI_NONIDLE);
+
+		if (reschedule)
+			*pchanged_states |= PSI_STATE_RESCHEDULE;
+	}
 }
 
 static void calc_avgs(unsigned long avg[3], int missed_periods,
@@ -415,7 +442,6 @@ static void psi_avgs_work(struct work_struct *work)
 	struct delayed_work *dwork;
 	struct psi_group *group;
 	u32 changed_states;
-	bool nonidle;
 	u64 now;
 
 	dwork = to_delayed_work(work);
@@ -426,7 +452,6 @@ static void psi_avgs_work(struct work_struct *work)
 	now = sched_clock();
 
 	collect_percpu_times(group, PSI_AVGS, &changed_states);
-	nonidle = changed_states & (1 << PSI_NONIDLE);
 	/*
 	 * If there is task activity, periodically fold the per-cpu
 	 * times and feed samples into the running averages. If things
@@ -437,7 +462,7 @@ static void psi_avgs_work(struct work_struct *work)
 	if (now >= group->avg_next_update)
 		group->avg_next_update = update_averages(group, now);
 
-	if (nonidle) {
+	if (changed_states & PSI_STATE_RESCHEDULE) {
 		schedule_delayed_work(dwork, nsecs_to_jiffies(
 				group->avg_next_update - now) + 1);
 	}
@@ -539,10 +564,12 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 
 			/* Calculate growth since last update */
 			growth = window_update(&t->win, now, total[t->state]);
-			if (growth < t->threshold)
-				continue;
+			if (!t->pending_event) {
+				if (growth < t->threshold)
+					continue;
 
-			t->pending_event = true;
+				t->pending_event = true;
+			}
 		}
 		/* Limit event signaling to once per window */
 		if (now < t->last_event_time + t->win.size)
@@ -563,18 +590,17 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	return now + group->poll_min_period;
 }
 
-/* Schedule polling if it's not already scheduled. */
-static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
+/* Schedule polling if it's not already scheduled or forced. */
+static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay,
+				   bool force)
 {
 	struct task_struct *task;
 
 	/*
-	 * Do not reschedule if already scheduled.
-	 * Possible race with a timer scheduled after this check but before
-	 * mod_timer below can be tolerated because group->polling_next_update
-	 * will keep updates on schedule.
+	 * atomic_xchg should be called even when !force to provide a
+	 * full memory barrier (see the comment inside psi_poll_work).
 	 */
-	if (timer_pending(&group->poll_timer))
+	if (atomic_xchg(&group->poll_scheduled, 1) && !force)
 		return;
 
 	rcu_read_lock();
@@ -586,12 +612,15 @@ static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
 	 */
 	if (likely(task))
 		mod_timer(&group->poll_timer, jiffies + delay);
+	else
+		atomic_set(&group->poll_scheduled, 0);
 
 	rcu_read_unlock();
 }
 
 static void psi_poll_work(struct psi_group *group)
 {
+	bool force_reschedule = false;
 	u32 changed_states;
 	u64 now;
 
@@ -599,6 +628,43 @@ static void psi_poll_work(struct psi_group *group)
 
 	now = sched_clock();
 
+	if (now > group->polling_until) {
+		/*
+		 * We are either about to start or might stop polling if no
+		 * state change was recorded. Resetting poll_scheduled leaves
+		 * a small window for psi_group_change to sneak in and schedule
+		 * an immediate poll_work before we get to rescheduling. One
+		 * potential extra wakeup at the end of the polling window
+		 * should be negligible and polling_next_update still keeps
+		 * updates correctly on schedule.
+		 */
+		atomic_set(&group->poll_scheduled, 0);
+		/*
+		 * A task change can race with the poll worker that is supposed to
+		 * report on it. To avoid missing events, ensure ordering between
+		 * poll_scheduled and the task state accesses, such that if the poll
+		 * worker misses the state update, the task change is guaranteed to
+		 * reschedule the poll worker:
+		 *
+		 * poll worker:
+		 *   atomic_set(poll_scheduled, 0)
+		 *   smp_mb()
+		 *   LOAD states
+		 *
+		 * task change:
+		 *   STORE states
+		 *   if atomic_xchg(poll_scheduled, 1) == 0:
+		 *     schedule poll worker
+		 *
+		 * The atomic_xchg() implies a full barrier.
+		 */
+		smp_mb();
+	} else {
+		/* Polling window is not over, keep rescheduling */
+		force_reschedule = true;
+	}
+
+
 	collect_percpu_times(group, PSI_POLL, &changed_states);
 
 	if (changed_states & group->poll_states) {
@@ -624,7 +690,8 @@ static void psi_poll_work(struct psi_group *group)
 		group->polling_next_update = update_triggers(group, now);
 
 	psi_schedule_poll_work(group,
-		nsecs_to_jiffies(group->polling_next_update - now) + 1);
+		nsecs_to_jiffies(group->polling_next_update - now) + 1,
+		force_reschedule);
 
 out:
 	mutex_unlock(&group->trigger_lock);
@@ -785,7 +852,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
 	write_seqcount_end(&groupc->seq);
 
 	if (state_mask & group->poll_states)
-		psi_schedule_poll_work(group, 1);
+		psi_schedule_poll_work(group, 1, false);
 
 	if (wake_clock && !delayed_work_pending(&group->avgs_work))
 		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
@@ -939,7 +1006,7 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
 		write_seqcount_end(&groupc->seq);
 
 		if (group->poll_states & (1 << PSI_IRQ_FULL))
-			psi_schedule_poll_work(group, 1);
+			psi_schedule_poll_work(group, 1, false);
 	} while ((group = group->parent));
 }
 #endif
@@ -1325,6 +1392,7 @@ void psi_trigger_destroy(struct psi_trigger *t)
 		 * can no longer be found through group->poll_task.
 		 */
 		kthread_stop(task_to_destroy);
+		atomic_set(&group->poll_scheduled, 0);
 	}
 	kfree(t);
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a4a20046e586e0..771f8ddb705337 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1041,6 +1041,7 @@ struct rq {
 
 	unsigned long		cpu_capacity;
 	unsigned long		cpu_capacity_orig;
+	unsigned long		cpu_capacity_inverted;
 
 	struct balance_callback *balance_callback;
 
@@ -1150,6 +1151,9 @@ struct rq {
 	unsigned int		core_forceidle_occupation;
 	u64			core_forceidle_start;
 #endif
+
+	/* Scratch cpumask to be temporarily used under rq_lock */
+	cpumask_var_t		scratch_mask;
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1877,6 +1881,13 @@ static inline void dirty_sched_domain_sysctl(int cpu)
 #endif
 
 extern int sched_update_scaling(void);
+
+static inline const struct cpumask *task_user_cpus(struct task_struct *p)
+{
+	if (!p->user_cpus_ptr)
+		return cpu_possible_mask; /* &init_task.cpus_mask */
+	return p->user_cpus_ptr;
+}
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -2144,6 +2155,12 @@ extern const u32		sched_prio_to_wmult[40];
 
 #define RETRY_TASK		((void *)-1UL)
 
+struct affinity_context {
+	const struct cpumask *new_mask;
+	struct cpumask *user_mask;
+	unsigned int flags;
+};
+
 struct sched_class {
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -2172,9 +2189,7 @@ struct sched_class {
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
 
-	void (*set_cpus_allowed)(struct task_struct *p,
-				 const struct cpumask *newmask,
-				 u32 flags);
+	void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
 
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
@@ -2285,7 +2300,7 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx);
 
 static inline struct task_struct *get_push_task(struct rq *rq)
 {
@@ -2878,6 +2893,24 @@ static inline unsigned long capacity_orig_of(int cpu)
 	return cpu_rq(cpu)->cpu_capacity_orig;
 }
 
+/*
+ * Returns inverted capacity if the CPU is in capacity inversion state.
+ * 0 otherwise.
+ *
+ * Capacity inversion detection only considers thermal impact where actual
+ * performance points (OPPs) gets dropped.
+ *
+ * Capacity inversion state happens when another performance domain that has
+ * equal or lower capacity_orig_of() becomes effectively larger than the perf
+ * domain this CPU belongs to due to thermal pressure throttling it hard.
+ *
+ * See comment in update_cpu_capacity().
+ */
+static inline unsigned long cpu_in_capacity_inversion(int cpu)
+{
+	return cpu_rq(cpu)->cpu_capacity_inverted;
+}
+
 /**
  * enum cpu_util_type - CPU utilization type
  * @FREQUENCY_UTIL:	Utilization used to select frequency
@@ -2979,6 +3012,23 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 #ifdef CONFIG_UCLAMP_TASK
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+					  enum uclamp_id clamp_id)
+{
+	return READ_ONCE(rq->uclamp[clamp_id].value);
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+				 unsigned int value)
+{
+	WRITE_ONCE(rq->uclamp[clamp_id].value, value);
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+	return rq->uclamp_flags & UCLAMP_FLAG_IDLE;
+}
+
 /**
  * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
  * @rq:		The rq to clamp against. Must not be NULL.
@@ -3014,12 +3064,12 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 		 * Ignore last runnable task's max clamp, as this task will
 		 * reset it. Similarly, no need to read the rq's min clamp.
 		 */
-		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+		if (uclamp_rq_is_idle(rq))
 			goto out;
 	}
 
-	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
-	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+	min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN));
+	max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX));
 out:
 	/*
 	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
@@ -3060,6 +3110,15 @@ static inline bool uclamp_is_used(void)
 	return static_branch_likely(&sched_uclamp_used);
 }
 #else /* CONFIG_UCLAMP_TASK */
+static inline unsigned long uclamp_eff_value(struct task_struct *p,
+					     enum uclamp_id clamp_id)
+{
+	if (clamp_id == UCLAMP_MIN)
+		return 0;
+
+	return SCHED_CAPACITY_SCALE;
+}
+
 static inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 				  struct task_struct *p)
@@ -3073,6 +3132,25 @@ static inline bool uclamp_is_used(void)
 {
 	return false;
 }
+
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+					  enum uclamp_id clamp_id)
+{
+	if (clamp_id == UCLAMP_MIN)
+		return 0;
+
+	return SCHED_CAPACITY_SCALE;
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+				 unsigned int value)
+{
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 84a188913cc9d0..38f3698f5e5b31 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -128,11 +128,9 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
 	if (p->in_memstall)
 		set |= TSK_MEMSTALL_RUNNING;
 
-	if (!wakeup || p->sched_psi_wake_requeue) {
+	if (!wakeup) {
 		if (p->in_memstall)
 			set |= TSK_MEMSTALL;
-		if (p->sched_psi_wake_requeue)
-			p->sched_psi_wake_requeue = 0;
 	} else {
 		if (p->in_iowait)
 			clear |= TSK_IOWAIT;
@@ -143,8 +141,6 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
 
 static inline void psi_dequeue(struct task_struct *p, bool sleep)
 {
-	int clear = TSK_RUNNING;
-
 	if (static_branch_likely(&psi_disabled))
 		return;
 
@@ -157,10 +153,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep)
 	if (sleep)
 		return;
 
-	if (p->in_memstall)
-		clear |= (TSK_MEMSTALL | TSK_MEMSTALL_RUNNING);
-
-	psi_task_change(p, clear, 0);
+	psi_task_change(p, p->psi_flags, 0);
 }
 
 static inline void psi_ttwu_dequeue(struct task_struct *p)
@@ -172,19 +165,12 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
 	 * deregister its sleep-persistent psi states from the old
 	 * queue, and let psi_enqueue() know it has to requeue.
 	 */
-	if (unlikely(p->in_iowait || p->in_memstall)) {
+	if (unlikely(p->psi_flags)) {
 		struct rq_flags rf;
 		struct rq *rq;
-		int clear = 0;
-
-		if (p->in_iowait)
-			clear |= TSK_IOWAIT;
-		if (p->in_memstall)
-			clear |= TSK_MEMSTALL;
 
 		rq = __task_rq_lock(p, &rf);
-		psi_task_change(p, clear, 0);
-		p->sched_psi_wake_requeue = 1;
+		psi_task_change(p, p->psi_flags, 0);
 		__task_rq_unlock(rq, &rf);
 	}
 }