Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler udpates from Ingo Molnar:

 - Changes to core scheduling facilities:

    - Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
      coordinated scheduling across SMT siblings. This is a much
      requested feature for cloud computing platforms, to allow the
      flexible utilization of SMT siblings, without exposing untrusted
      domains to information leaks & side channels, plus to ensure more
      deterministic computing performance on SMT systems used by
      heterogenous workloads.

      There are new prctls to set core scheduling groups, which allows
      more flexible management of workloads that can share siblings.

    - Fix task->state access anti-patterns that may result in missed
      wakeups and rename it to ->__state in the process to catch new
      abuses.

 - Load-balancing changes:

    - Tweak newidle_balance for fair-sched, to improve 'memcache'-like
      workloads.

    - "Age" (decay) average idle time, to better track & improve
      workloads such as 'tbench'.

    - Fix & improve energy-aware (EAS) balancing logic & metrics.

    - Fix & improve the uclamp metrics.

    - Fix task migration (taskset) corner case on !CONFIG_CPUSET.

    - Fix RT and deadline utilization tracking across policy changes

    - Introduce a "burstable" CFS controller via cgroups, which allows
      bursty CPU-bound workloads to borrow a bit against their future
      quota to improve overall latencies & batching. Can be tweaked via
      /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.

    - Rework assymetric topology/capacity detection & handling.

 - Scheduler statistics & tooling:

    - Disable delayacct by default, but add a sysctl to enable it at
      runtime if tooling needs it. Use static keys and other
      optimizations to make it more palatable.

    - Use sched_clock() in delayacct, instead of ktime_get_ns().

 - Misc cleanups and fixes.

* tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/doc: Update the CPU capacity asymmetry bits
  sched/topology: Rework CPU capacity asymmetry detection
  sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
  psi: Fix race between psi_trigger_create/destroy
  sched/fair: Introduce the burstable CFS controller
  sched/uclamp: Fix uclamp_tg_restrict()
  sched/rt: Fix Deadline utilization tracking during policy change
  sched/rt: Fix RT utilization tracking during policy change
  sched: Change task_struct::state
  sched,arch: Remove unused TASK_STATE offsets
  sched,timer: Use __set_current_state()
  sched: Add get_current_state()
  sched,perf,kvm: Fix preemption condition
  sched: Introduce task_is_running()
  sched: Unbreak wakeups
  sched/fair: Age the average idle time
  sched/cpufreq: Consider reduced CPU capacity in energy calculation
  sched/fair: Take thermal pressure into account while estimating energy
  thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure
  sched/fair: Return early from update_tg_cfs_load() if delta == 0
  ...

1 files changed, 314 insertions, 126 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 23663318fb81..e6d1dd4e9d68 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -268,33 +268,11 @@ const struct sched_class fair_sched_class;
  */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
-	SCHED_WARN_ON(!entity_is_task(se));
-	return container_of(se, struct task_struct, se);
-}
 
 /* Walk up scheduling entities hierarchy */
 #define for_each_sched_entity(se) \
 		for (; se; se = se->parent)
 
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
-	return p->se.cfs_rq;
-}
-
-/* runqueue on which this entity is (to be) queued */
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
-	return se->cfs_rq;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
-	return grp->my_q;
-}
-
 static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
 {
 	if (!path)
@@ -455,33 +433,9 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 
 #else	/* !CONFIG_FAIR_GROUP_SCHED */
 
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
-	return container_of(se, struct task_struct, se);
-}
-
 #define for_each_sched_entity(se) \
 		for (; se; se = NULL)
 
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
-	return &task_rq(p)->cfs;
-}
-
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
-	struct task_struct *p = task_of(se);
-	struct rq *rq = task_rq(p);
-
-	return &rq->cfs;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
-	return NULL;
-}
-
 static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
 {
 	if (path)
@@ -1039,11 +993,14 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
 		struct task_struct *tsk = task_of(se);
+		unsigned int state;
 
-		if (tsk->state & TASK_INTERRUPTIBLE)
+		/* XXX racy against TTWU */
+		state = READ_ONCE(tsk->__state);
+		if (state & TASK_INTERRUPTIBLE)
 			__schedstat_set(se->statistics.sleep_start,
 				      rq_clock(rq_of(cfs_rq)));
-		if (tsk->state & TASK_UNINTERRUPTIBLE)
+		if (state & TASK_UNINTERRUPTIBLE)
 			__schedstat_set(se->statistics.block_start,
 				      rq_clock(rq_of(cfs_rq)));
 	}
@@ -1107,7 +1064,7 @@ struct numa_group {
 static struct numa_group *deref_task_numa_group(struct task_struct *p)
 {
 	return rcu_dereference_check(p->numa_group, p == current ||
-		(lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+		(lockdep_is_held(__rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu)));
 }
 
 static struct numa_group *deref_curr_numa_group(struct task_struct *p)
@@ -3139,7 +3096,7 @@ void reweight_task(struct task_struct *p, int prio)
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = -----------------------------               (1)
- *			  \Sum grq->load.weight
+ *                       \Sum grq->load.weight
  *
  * Now, because computing that sum is prohibitively expensive to compute (been
  * there, done that) we approximate it with this average stuff. The average
@@ -3153,7 +3110,7 @@ void reweight_task(struct task_struct *p, int prio)
  *
  *                     tg->weight * grq->avg.load_avg
  *   ge->load.weight = ------------------------------              (3)
- *				tg->load_avg
+ *                             tg->load_avg
  *
  * Where: tg->load_avg ~= \Sum grq->avg.load_avg
  *
@@ -3169,7 +3126,7 @@ void reweight_task(struct task_struct *p, int prio)
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = ----------------------------- = tg->weight   (4)
- *			    grp->load.weight
+ *                         grp->load.weight
  *
  * That is, the sum collapses because all other CPUs are idle; the UP scenario.
  *
@@ -3188,7 +3145,7 @@ void reweight_task(struct task_struct *p, int prio)
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = -----------------------------		   (6)
- *				tg_load_avg'
+ *                             tg_load_avg'
  *
  * Where:
  *
@@ -3341,6 +3298,15 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (child_cfs_rq_on_list(cfs_rq))
 		return false;
 
+	/*
+	 * _avg must be null when _sum are null because _avg = _sum / divider
+	 * Make sure that rounding and/or propagation of PELT values never
+	 * break this.
+	 */
+	SCHED_WARN_ON(cfs_rq->avg.load_avg ||
+		      cfs_rq->avg.util_avg ||
+		      cfs_rq->avg.runnable_avg);
+
 	return true;
 }
 
@@ -3594,9 +3560,12 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, divider);
 
+	se->avg.load_sum = runnable_sum;
+
 	delta = load_avg - se->avg.load_avg;
+	if (!delta)
+		return;
 
-	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
 
 	add_positive(&cfs_rq->avg.load_avg, delta);
@@ -4476,6 +4445,8 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 static void
 set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	clear_buddies(cfs_rq, se);
+
 	/* 'current' is not kept within the tree. */
 	if (se->on_rq) {
 		/*
@@ -4535,7 +4506,7 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	 * Avoid running the skip buddy, if running something else can
 	 * be done without getting too unfair.
 	 */
-	if (cfs_rq->skip == se) {
+	if (cfs_rq->skip && cfs_rq->skip == se) {
 		struct sched_entity *second;
 
 		if (se == curr) {
@@ -4562,8 +4533,6 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		se = cfs_rq->last;
 	}
 
-	clear_buddies(cfs_rq, se);
-
 	return se;
 }
 
@@ -4685,8 +4654,11 @@ static inline u64 sched_cfs_bandwidth_slice(void)
  */
 void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 {
-	if (cfs_b->quota != RUNTIME_INF)
-		cfs_b->runtime = cfs_b->quota;
+	if (unlikely(cfs_b->quota == RUNTIME_INF))
+		return;
+
+	cfs_b->runtime += cfs_b->quota;
+	cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -5047,6 +5019,9 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
 	throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 	cfs_b->nr_periods += overrun;
 
+	/* Refill extra burst quota even if cfs_b->idle */
+	__refill_cfs_bandwidth_runtime(cfs_b);
+
 	/*
 	 * idle depends on !throttled (for the case of a large deficit), and if
 	 * we're going inactive then everything else can be deferred
@@ -5054,8 +5029,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
 	if (cfs_b->idle && !throttled)
 		goto out_deactivate;
 
-	__refill_cfs_bandwidth_runtime(cfs_b);
-
 	if (!throttled) {
 		/* mark as potentially idle for the upcoming period */
 		cfs_b->idle = 1;
@@ -5305,6 +5278,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 			if (new < max_cfs_quota_period) {
 				cfs_b->period = ns_to_ktime(new);
 				cfs_b->quota *= 2;
+				cfs_b->burst *= 2;
 
 				pr_warn_ratelimited(
 	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
@@ -5336,6 +5310,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->runtime = 0;
 	cfs_b->quota = RUNTIME_INF;
 	cfs_b->period = ns_to_ktime(default_cfs_period());
+	cfs_b->burst = 0;
 
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
 	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
@@ -5385,7 +5360,7 @@ static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
 	struct task_group *tg;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
@@ -5404,7 +5379,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
 	struct task_group *tg;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
@@ -5992,11 +5967,15 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
+		struct rq *rq = cpu_rq(i);
+
+		if (!sched_core_cookie_match(rq, p))
+			continue;
+
 		if (sched_idle_cpu(i))
 			return i;
 
 		if (available_idle_cpu(i)) {
-			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
 			if (idle && idle->exit_latency < min_exit_latency) {
 				/*
@@ -6082,9 +6061,10 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 	return new_cpu;
 }
 
-static inline int __select_idle_cpu(int cpu)
+static inline int __select_idle_cpu(int cpu, struct task_struct *p)
 {
-	if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
+	if ((available_idle_cpu(cpu) || sched_idle_cpu(cpu)) &&
+	    sched_cpu_cookie_match(cpu_rq(cpu), p))
 		return cpu;
 
 	return -1;
@@ -6154,7 +6134,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 	int cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
-		return __select_idle_cpu(core);
+		return __select_idle_cpu(core, p);
 
 	for_each_cpu(cpu, cpu_smt_mask(core)) {
 		if (!available_idle_cpu(cpu)) {
@@ -6210,7 +6190,7 @@ static inline bool test_idle_cores(int cpu, bool def)
 
 static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
 {
-	return __select_idle_cpu(core);
+	return __select_idle_cpu(core, p);
 }
 
 static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
@@ -6229,9 +6209,10 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	int i, cpu, idle_cpu = -1, nr = INT_MAX;
+	struct rq *this_rq = this_rq();
 	int this = smp_processor_id();
 	struct sched_domain *this_sd;
-	u64 time;
+	u64 time = 0;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -6241,12 +6222,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 
 	if (sched_feat(SIS_PROP) && !has_idle_core) {
 		u64 avg_cost, avg_idle, span_avg;
+		unsigned long now = jiffies;
 
 		/*
-		 * Due to large variance we need a large fuzz factor;
-		 * hackbench in particularly is sensitive here.
+		 * If we're busy, the assumption that the last idle period
+		 * predicts the future is flawed; age away the remaining
+		 * predicted idle time.
 		 */
-		avg_idle = this_rq()->avg_idle / 512;
+		if (unlikely(this_rq->wake_stamp < now)) {
+			while (this_rq->wake_stamp < now && this_rq->wake_avg_idle) {
+				this_rq->wake_stamp++;
+				this_rq->wake_avg_idle >>= 1;
+			}
+		}
+
+		avg_idle = this_rq->wake_avg_idle;
 		avg_cost = this_sd->avg_scan_cost + 1;
 
 		span_avg = sd->span_weight * avg_idle;
@@ -6267,7 +6257,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		} else {
 			if (!--nr)
 				return -1;
-			idle_cpu = __select_idle_cpu(cpu);
+			idle_cpu = __select_idle_cpu(cpu, p);
 			if ((unsigned int)idle_cpu < nr_cpumask_bits)
 				break;
 		}
@@ -6278,6 +6268,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 
 	if (sched_feat(SIS_PROP) && !has_idle_core) {
 		time = cpu_clock(this) - time;
+
+		/*
+		 * Account for the scan cost of wakeups against the average
+		 * idle time.
+		 */
+		this_rq->wake_avg_idle -= min(this_rq->wake_avg_idle, time);
+
 		update_avg(&this_sd->avg_scan_cost, time);
 	}
 
@@ -6345,6 +6342,11 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		task_util = uclamp_task_util(p);
 	}
 
+	/*
+	 * per-cpu select_idle_mask usage
+	 */
+	lockdep_assert_irqs_disabled();
+
 	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
 	    asym_fits_capacity(task_util, target))
 		return target;
@@ -6620,8 +6622,11 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 	struct cpumask *pd_mask = perf_domain_span(pd);
 	unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask));
 	unsigned long max_util = 0, sum_util = 0;
+	unsigned long _cpu_cap = cpu_cap;
 	int cpu;
 
+	_cpu_cap -= arch_scale_thermal_pressure(cpumask_first(pd_mask));
+
 	/*
 	 * The capacity state of CPUs of the current rd can be driven by CPUs
 	 * of another rd if they belong to the same pd. So, account for the
@@ -6657,8 +6662,10 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * is already enough to scale the EM reported power
 		 * consumption at the (eventually clamped) cpu_capacity.
 		 */
-		sum_util += effective_cpu_util(cpu, util_running, cpu_cap,
-					       ENERGY_UTIL, NULL);
+		cpu_util = effective_cpu_util(cpu, util_running, cpu_cap,
+					      ENERGY_UTIL, NULL);
+
+		sum_util += min(cpu_util, _cpu_cap);
 
 		/*
 		 * Performance domain frequency: utilization clamping
@@ -6669,10 +6676,10 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 */
 		cpu_util = effective_cpu_util(cpu, util_freq, cpu_cap,
 					      FREQUENCY_UTIL, tsk);
-		max_util = max(max_util, cpu_util);
+		max_util = max(max_util, min(cpu_util, _cpu_cap));
 	}
 
-	return em_cpu_energy(pd->em_pd, max_util, sum_util);
+	return em_cpu_energy(pd->em_pd, max_util, sum_util, _cpu_cap);
 }
 
 /*
@@ -6718,15 +6725,15 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 {
 	unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	int cpu, best_energy_cpu = prev_cpu, target = -1;
 	unsigned long cpu_cap, util, base_energy = 0;
-	int cpu, best_energy_cpu = prev_cpu;
 	struct sched_domain *sd;
 	struct perf_domain *pd;
 
 	rcu_read_lock();
 	pd = rcu_dereference(rd->pd);
 	if (!pd || READ_ONCE(rd->overutilized))
-		goto fail;
+		goto unlock;
 
 	/*
 	 * Energy-aware wake-up happens on the lowest sched_domain starting
@@ -6736,7 +6743,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
 		sd = sd->parent;
 	if (!sd)
-		goto fail;
+		goto unlock;
+
+	target = prev_cpu;
 
 	sync_entity_load_avg(&p->se);
 	if (!task_util_est(p))
@@ -6744,13 +6753,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 
 	for (; pd; pd = pd->next) {
 		unsigned long cur_delta, spare_cap, max_spare_cap = 0;
+		bool compute_prev_delta = false;
 		unsigned long base_energy_pd;
 		int max_spare_cap_cpu = -1;
 
-		/* Compute the 'base' energy of the pd, without @p */
-		base_energy_pd = compute_energy(p, -1, pd);
-		base_energy += base_energy_pd;
-
 		for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
 			if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 				continue;
@@ -6771,26 +6777,40 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (!fits_capacity(util, cpu_cap))
 				continue;
 
-			/* Always use prev_cpu as a candidate. */
 			if (cpu == prev_cpu) {
-				prev_delta = compute_energy(p, prev_cpu, pd);
-				prev_delta -= base_energy_pd;
-				best_delta = min(best_delta, prev_delta);
-			}
-
-			/*
-			 * Find the CPU with the maximum spare capacity in
-			 * the performance domain
-			 */
-			if (spare_cap > max_spare_cap) {
+				/* Always use prev_cpu as a candidate. */
+				compute_prev_delta = true;
+			} else if (spare_cap > max_spare_cap) {
+				/*
+				 * Find the CPU with the maximum spare capacity
+				 * in the performance domain.
+				 */
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
 			}
 		}
 
-		/* Evaluate the energy impact of using this CPU. */
-		if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) {
+		if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+			continue;
+
+		/* Compute the 'base' energy of the pd, without @p */
+		base_energy_pd = compute_energy(p, -1, pd);
+		base_energy += base_energy_pd;
+
+		/* Evaluate the energy impact of using prev_cpu. */
+		if (compute_prev_delta) {
+			prev_delta = compute_energy(p, prev_cpu, pd);
+			if (prev_delta < base_energy_pd)
+				goto unlock;
+			prev_delta -= base_energy_pd;
+			best_delta = min(best_delta, prev_delta);
+		}
+
+		/* Evaluate the energy impact of using max_spare_cap_cpu. */
+		if (max_spare_cap_cpu >= 0) {
 			cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
+			if (cur_delta < base_energy_pd)
+				goto unlock;
 			cur_delta -= base_energy_pd;
 			if (cur_delta < best_delta) {
 				best_delta = cur_delta;
@@ -6798,25 +6818,22 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			}
 		}
 	}
-unlock:
 	rcu_read_unlock();
 
 	/*
 	 * Pick the best CPU if prev_cpu cannot be used, or if it saves at
 	 * least 6% of the energy used by prev_cpu.
 	 */
-	if (prev_delta == ULONG_MAX)
-		return best_energy_cpu;
-
-	if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4))
-		return best_energy_cpu;
+	if ((prev_delta == ULONG_MAX) ||
+	    (prev_delta - best_delta) > ((prev_delta + base_energy) >> 4))
+		target = best_energy_cpu;
 
-	return prev_cpu;
+	return target;
 
-fail:
+unlock:
 	rcu_read_unlock();
 
-	return -1;
+	return target;
 }
 
 /*
@@ -6828,8 +6845,6 @@ fail:
  * certain conditions an idle sibling CPU if the domain has SD_WAKE_AFFINE set.
  *
  * Returns the target CPU number.
- *
- * preempt must be disabled.
  */
 static int
 select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
@@ -6842,6 +6857,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 	/* SD_flags and WF_flags share the first nibble */
 	int sd_flag = wake_flags & 0xF;
 
+	/*
+	 * required for stable ->cpus_allowed
+	 */
+	lockdep_assert_held(&p->pi_lock);
 	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
 
@@ -6906,7 +6925,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 	 * min_vruntime -- the latter is done by enqueue_entity() when placing
 	 * the task on the new runqueue.
 	 */
-	if (p->state == TASK_WAKING) {
+	if (READ_ONCE(p->__state) == TASK_WAKING) {
 		struct sched_entity *se = &p->se;
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 		u64 min_vruntime;
@@ -6931,7 +6950,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 		 * In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old'
 		 * rq->lock and can modify state directly.
 		 */
-		lockdep_assert_held(&task_rq(p)->lock);
+		lockdep_assert_rq_held(task_rq(p));
 		detach_entity_cfs_rq(&p->se);
 
 	} else {
@@ -7135,6 +7154,39 @@ preempt:
 		set_last_buddy(se);
 }
 
+#ifdef CONFIG_SMP
+static struct task_struct *pick_task_fair(struct rq *rq)
+{
+	struct sched_entity *se;
+	struct cfs_rq *cfs_rq;
+
+again:
+	cfs_rq = &rq->cfs;
+	if (!cfs_rq->nr_running)
+		return NULL;
+
+	do {
+		struct sched_entity *curr = cfs_rq->curr;
+
+		/* When we pick for a remote RQ, we'll not have done put_prev_entity() */
+		if (curr) {
+			if (curr->on_rq)
+				update_curr(cfs_rq);
+			else
+				curr = NULL;
+
+			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+				goto again;
+		}
+
+		se = pick_next_entity(cfs_rq, curr);
+		cfs_rq = group_cfs_rq(se);
+	} while (cfs_rq);
+
+	return task_of(se);
+}
+#endif
+
 struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
@@ -7558,7 +7610,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 {
 	s64 delta;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	if (p->sched_class != &fair_sched_class)
 		return 0;
@@ -7580,6 +7632,14 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 
 	if (sysctl_sched_migration_cost == -1)
 		return 1;
+
+	/*
+	 * Don't migrate task if the task's cookie does not match
+	 * with the destination CPU's core cookie.
+	 */
+	if (!sched_core_cookie_match(cpu_rq(env->dst_cpu), p))
+		return 1;
+
 	if (sysctl_sched_migration_cost == 0)
 		return 0;
 
@@ -7656,7 +7716,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 {
 	int tsk_cache_hot;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	/*
 	 * We do not migrate tasks that are:
@@ -7745,7 +7805,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
  */
 static void detach_task(struct task_struct *p, struct lb_env *env)
 {
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
@@ -7761,7 +7821,7 @@ static struct task_struct *detach_one_task(struct lb_env *env)
 {
 	struct task_struct *p;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	list_for_each_entry_reverse(p,
 			&env->src_rq->cfs_tasks, se.group_node) {
@@ -7797,7 +7857,7 @@ static int detach_tasks(struct lb_env *env)
 	struct task_struct *p;
 	int detached = 0;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	/*
 	 * Source run queue has been emptied by another CPU, clear
@@ -7927,7 +7987,7 @@ next:
  */
 static void attach_task(struct rq *rq, struct task_struct *p)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	BUG_ON(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
@@ -8893,6 +8953,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 					p->cpus_ptr))
 			continue;
 
+		/* Skip over this group if no cookie matched */
+		if (!sched_group_cookie_match(cpu_rq(this_cpu), p, group))
+			continue;
+
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_span(group));
 
@@ -9821,7 +9885,7 @@ more_balance:
 		if (need_active_balance(&env)) {
 			unsigned long flags;
 
-			raw_spin_lock_irqsave(&busiest->lock, flags);
+			raw_spin_rq_lock_irqsave(busiest, flags);
 
 			/*
 			 * Don't kick the active_load_balance_cpu_stop,
@@ -9829,8 +9893,7 @@ more_balance:
 			 * moved to this_cpu:
 			 */
 			if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
-				raw_spin_unlock_irqrestore(&busiest->lock,
-							    flags);
+				raw_spin_rq_unlock_irqrestore(busiest, flags);
 				goto out_one_pinned;
 			}
 
@@ -9847,7 +9910,7 @@ more_balance:
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
-			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+			raw_spin_rq_unlock_irqrestore(busiest, flags);
 
 			if (active_balance) {
 				stop_one_cpu_nowait(cpu_of(busiest),
@@ -10632,6 +10695,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	u64 curr_cost = 0;
 
 	update_misfit_status(NULL, this_rq);
+
+	/*
+	 * There is a task waiting to run. No need to search for one.
+	 * Return 0; the task will be enqueued when switching to idle.
+	 */
+	if (this_rq->ttwu_pending)
+		return 0;
+
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -10664,7 +10735,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		goto out;
 	}
 
-	raw_spin_unlock(&this_rq->lock);
+	raw_spin_rq_unlock(this_rq);
 
 	update_blocked_averages(this_cpu);
 	rcu_read_lock();
@@ -10697,12 +10768,13 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		 * Stop searching for tasks to pull if there are
 		 * now runnable tasks on this rq.
 		 */
-		if (pulled_task || this_rq->nr_running > 0)
+		if (pulled_task || this_rq->nr_running > 0 ||
+		    this_rq->ttwu_pending)
 			break;
 	}
 	rcu_read_unlock();
 
-	raw_spin_lock(&this_rq->lock);
+	raw_spin_rq_lock(this_rq);
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
@@ -10795,6 +10867,119 @@ static void rq_offline_fair(struct rq *rq)
 
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_SCHED_CORE
+static inline bool
+__entity_slice_used(struct sched_entity *se, int min_nr_tasks)
+{
+	u64 slice = sched_slice(cfs_rq_of(se), se);
+	u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+
+	return (rtime * min_nr_tasks > slice);
+}
+
+#define MIN_NR_TASKS_DURING_FORCEIDLE	2
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
+{
+	if (!sched_core_enabled(rq))
+		return;
+
+	/*
+	 * If runqueue has only one task which used up its slice and
+	 * if the sibling is forced idle, then trigger schedule to
+	 * give forced idle task a chance.
+	 *
+	 * sched_slice() considers only this active rq and it gets the
+	 * whole slice. But during force idle, we have siblings acting
+	 * like a single runqueue and hence we need to consider runnable
+	 * tasks on this CPU and the forced idle CPU. Ideally, we should
+	 * go through the forced idle rq, but that would be a perf hit.
+	 * We can assume that the forced idle CPU has at least
+	 * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check
+	 * if we need to give up the CPU.
+	 */
+	if (rq->core->core_forceidle && rq->cfs.nr_running == 1 &&
+	    __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE))
+		resched_curr(rq);
+}
+
+/*
+ * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed.
+ */
+static void se_fi_update(struct sched_entity *se, unsigned int fi_seq, bool forceidle)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		if (forceidle) {
+			if (cfs_rq->forceidle_seq == fi_seq)
+				break;
+			cfs_rq->forceidle_seq = fi_seq;
+		}
+
+		cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime;
+	}
+}
+
+void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi)
+{
+	struct sched_entity *se = &p->se;
+
+	if (p->sched_class != &fair_sched_class)
+		return;
+
+	se_fi_update(se, rq->core->core_forceidle_seq, in_fi);
+}
+
+bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
+{
+	struct rq *rq = task_rq(a);
+	struct sched_entity *sea = &a->se;
+	struct sched_entity *seb = &b->se;
+	struct cfs_rq *cfs_rqa;
+	struct cfs_rq *cfs_rqb;
+	s64 delta;
+
+	SCHED_WARN_ON(task_rq(b)->core != rq->core);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * Find an se in the hierarchy for tasks a and b, such that the se's
+	 * are immediate siblings.
+	 */
+	while (sea->cfs_rq->tg != seb->cfs_rq->tg) {
+		int sea_depth = sea->depth;
+		int seb_depth = seb->depth;
+
+		if (sea_depth >= seb_depth)
+			sea = parent_entity(sea);
+		if (sea_depth <= seb_depth)
+			seb = parent_entity(seb);
+	}
+
+	se_fi_update(sea, rq->core->core_forceidle_seq, in_fi);
+	se_fi_update(seb, rq->core->core_forceidle_seq, in_fi);
+
+	cfs_rqa = sea->cfs_rq;
+	cfs_rqb = seb->cfs_rq;
+#else
+	cfs_rqa = &task_rq(a)->cfs;
+	cfs_rqb = &task_rq(b)->cfs;
+#endif
+
+	/*
+	 * Find delta after normalizing se's vruntime with its cfs_rq's
+	 * min_vruntime_fi, which would have been updated in prior calls
+	 * to se_fi_update().
+	 */
+	delta = (s64)(sea->vruntime - seb->vruntime) +
+		(s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi);
+
+	return delta > 0;
+}
+#else
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
+#endif
+
 /*
  * scheduler tick hitting a task of our scheduling class.
  *
@@ -10818,6 +11003,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	update_misfit_status(curr, rq);
 	update_overutilized_status(task_rq(curr));
+
+	task_tick_core(rq, curr);
 }
 
 /*
@@ -10903,7 +11090,7 @@ static inline bool vruntime_normalized(struct task_struct *p)
 	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 */
 	if (!se->sum_exec_runtime ||
-	    (p->state == TASK_WAKING && p->sched_remote_wakeup))
+	    (READ_ONCE(p->__state) == TASK_WAKING && p->sched_remote_wakeup))
 		return true;
 
 	return false;
@@ -11189,9 +11376,9 @@ void unregister_fair_sched_group(struct task_group *tg)
 
 		rq = cpu_rq(cpu);
 
-		raw_spin_lock_irqsave(&rq->lock, flags);
+		raw_spin_rq_lock_irqsave(rq, flags);
 		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		raw_spin_rq_unlock_irqrestore(rq, flags);
 	}
 }
 
@@ -11313,6 +11500,7 @@ DEFINE_SCHED_CLASS(fair) = {
 
 #ifdef CONFIG_SMP
 	.balance		= balance_fair,
+	.pick_task		= pick_task_fair,
 	.select_task_rq		= select_task_rq_fair,
 	.migrate_task_rq	= migrate_task_rq_fair,