Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar: "The main updates in this cycle were: - Group balancing enhancements and cleanups (Brendan Jackman) - Move CPU isolation related functionality into its separate kernel/sched/isolation.c file, with related 'housekeeping_*()' namespace and nomenclature et al. (Frederic Weisbecker) - Improve the interactive/cpu-intense fairness calculation (Josef Bacik) - Improve the PELT code and related cleanups (Peter Zijlstra) - Improve the logic of pick_next_task_fair() (Uladzislau Rezki) - Improve the RT IPI based balancing logic (Steven Rostedt) - Various micro-optimizations: - better !CONFIG_SCHED_DEBUG optimizations (Patrick Bellasi) - better idle loop (Cheng Jian) - ... plus misc fixes, cleanups and updates" * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits) sched/core: Optimize sched_feat() for !CONFIG_SCHED_DEBUG builds sched/sysctl: Fix attributes of some extern declarations sched/isolation: Document isolcpus= boot parameter flags, mark it deprecated sched/isolation: Add basic isolcpus flags sched/isolation: Move isolcpus= handling to the housekeeping code sched/isolation: Handle the nohz_full= parameter sched/isolation: Introduce housekeeping flags sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu() sched/isolation: Use its own static key sched/isolation: Make the housekeeping cpumask private sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu() sched/isolation, watchdog: Use housekeeping_cpumask() instead of ad-hoc version sched/isolation: Move housekeeping related code to its own file sched/idle: Micro-optimize the idle loop sched/isolcpus: Fix "isolcpus=" boot parameter handling when !CONFIG_CPUMASK_OFFSTACK x86/tsc: Append the 'tsc=' description for the 'tsc=unstable' boot parameter sched/rt: Simplify the IPI based RT balancing logic block/ioprio: Use a helper to check for RT prio sched/rt: Add a helper to test for a RT task ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2017-11-13 22:37:52 +0100
committer: Linus Torvalds <torvalds@linux-foundation.org> 2017-11-13 22:37:52 +0100
commit: 3e2014637c50e5d6a77cd63d5db6c209fe29d1b1 (patch)
tree: a672ed603262aeddda4490056b27b09791d0cbbb /kernel/sched
parent: Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kerne... (diff)
parent: sched/core: Optimize sched_feat() for !CONFIG_SCHED_DEBUG builds (diff)
download: linux-3e2014637c50e5d6a77cd63d5db6c209fe29d1b1.tar.xz
linux-3e2014637c50e5d6a77cd63d5db6c209fe29d1b1.zip
10 files changed, 1094 insertions, 648 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index a9ee16bbc693..e2f9d4feff40 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -27,3 +27,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
 obj-$(CONFIG_MEMBARRIER) += membarrier.o
+obj-$(CONFIG_CPU_ISOLATION) += isolation.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9446b2e5eac5..5b82a0073532 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,6 +26,7 @@
 #include <linux/profile.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/sched/isolation.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -42,18 +43,21 @@
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
 /*
  * Debugging: various feature bits
+ *
+ * If SCHED_DEBUG is disabled, each compilation unit has its own copy of
+ * sysctl_sched_features, defined in sched.h, to allow constants propagation
+ * at compile time and compiler optimization based on features default.
  */
-
 #define SCHED_FEAT(name, enabled)	\
 	(1UL << __SCHED_FEAT_##name) * enabled |
-
 const_debug unsigned int sysctl_sched_features =
 #include "features.h"
 	0;
-
 #undef SCHED_FEAT
+#endif
 
 /*
  * Number of tasks to iterate in a single balance run.
@@ -83,9 +87,6 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-/* CPUs with isolated domains */
-cpumask_var_t cpu_isolated_map;
-
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -525,7 +526,7 @@ int get_nohz_timer_target(void)
 	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
+	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
 		return cpu;
 
 	rcu_read_lock();
@@ -534,15 +535,15 @@ int get_nohz_timer_target(void)
 			if (cpu == i)
 				continue;
 
-			if (!idle_cpu(i) && is_housekeeping_cpu(i)) {
+			if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
 
-	if (!is_housekeeping_cpu(cpu))
-		cpu = housekeeping_any_cpu();
+	if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
+		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -732,7 +733,7 @@ int tg_nop(struct task_group *tg, void *data)
 }
 #endif
 
-static void set_load_weight(struct task_struct *p)
+static void set_load_weight(struct task_struct *p, bool update_load)
 {
 	int prio = p->static_prio - MAX_RT_PRIO;
 	struct load_weight *load = &p->se.load;
@@ -746,8 +747,16 @@ static void set_load_weight(struct task_struct *p)
 		return;
 	}
 
-	load->weight = scale_load(sched_prio_to_weight[prio]);
-	load->inv_weight = sched_prio_to_wmult[prio];
+	/*
+	 * SCHED_OTHER tasks have to update their load when changing their
+	 * weight
+	 */
+	if (update_load && p->sched_class == &fair_sched_class) {
+		reweight_task(p, prio);
+	} else {
+		load->weight = scale_load(sched_prio_to_weight[prio]);
+		load->inv_weight = sched_prio_to_wmult[prio];
+	}
 }
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -2357,7 +2366,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 			p->static_prio = NICE_TO_PRIO(0);
 
 		p->prio = p->normal_prio = __normal_prio(p);
-		set_load_weight(p);
+		set_load_weight(p, false);
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -3804,7 +3813,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		put_prev_task(rq, p);
 
 	p->static_prio = NICE_TO_PRIO(nice);
-	set_load_weight(p);
+	set_load_weight(p, true);
 	old_prio = p->prio;
 	p->prio = effective_prio(p);
 	delta = p->prio - old_prio;
@@ -3961,7 +3970,7 @@ static void __setscheduler_params(struct task_struct *p,
 	 */
 	p->rt_priority = attr->sched_priority;
 	p->normal_prio = normal_prio(p);
-	set_load_weight(p);
+	set_load_weight(p, true);
 }
 
 /* Actually do priority change: must hold pi & rq lock. */
@@ -5727,10 +5736,6 @@ static inline void sched_init_smt(void) { }
 
 void __init sched_init_smp(void)
 {
-	cpumask_var_t non_isolated_cpus;
-
-	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
-
 	sched_init_numa();
 
 	/*
@@ -5740,16 +5745,12 @@ void __init sched_init_smp(void)
 	 */
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
-	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
-	if (cpumask_empty(non_isolated_cpus))
-		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
 	mutex_unlock(&sched_domains_mutex);
 
 	/* Move init over to a non-isolated CPU */
-	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
+	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
 		BUG();
 	sched_init_granularity();
-	free_cpumask_var(non_isolated_cpus);
 
 	init_sched_rt_class();
 	init_sched_dl_class();
@@ -5934,7 +5935,7 @@ void __init sched_init(void)
 		atomic_set(&rq->nr_iowait, 0);
 	}
 
-	set_load_weight(&init_task);
+	set_load_weight(&init_task, false);
 
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
@@ -5953,9 +5954,6 @@ void __init sched_init(void)
 	calc_load_update = jiffies + LOAD_FREQ;
 
 #ifdef CONFIG_SMP
-	/* May be allocated at isolcpus cmdline parse time */
-	if (cpu_isolated_map == NULL)
-		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 	idle_thread_set_boot_cpu();
 	set_cpu_rq_start_time(smp_processor_id());
 #endif
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4ae5c1ea90e2..f349f7e98dec 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -243,7 +243,7 @@ static void task_non_contending(struct task_struct *p)
 			if (p->state == TASK_DEAD)
 				sub_rq_bw(p->dl.dl_bw, &rq->dl);
 			raw_spin_lock(&dl_b->lock);
-			__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+			__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 			__dl_clear_params(p);
 			raw_spin_unlock(&dl_b->lock);
 		}
@@ -1210,7 +1210,7 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 		}
 
 		raw_spin_lock(&dl_b->lock);
-		__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+		__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 		raw_spin_unlock(&dl_b->lock);
 		__dl_clear_params(p);
 
@@ -1365,6 +1365,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 		update_dl_entity(dl_se, pi_se);
 	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se, pi_se);
+	} else if ((flags & ENQUEUE_RESTORE) &&
+		  dl_time_before(dl_se->deadline,
+				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
+		setup_new_dl_entity(dl_se);
 	}
 
 	__enqueue_dl_entity(dl_se);
@@ -2167,7 +2171,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		 * until we complete the update.
 		 */
 		raw_spin_lock(&src_dl_b->lock);
-		__dl_clear(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+		__dl_sub(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
@@ -2256,13 +2260,6 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 
 		return;
 	}
-	/*
-	 * If p is boosted we already updated its params in
-	 * rt_mutex_setprio()->enqueue_task(..., ENQUEUE_REPLENISH),
-	 * p's deadline being now already after rq_clock(rq).
-	 */
-	if (dl_time_before(p->dl.deadline, rq_clock(rq)))
-		setup_new_dl_entity(&p->dl);
 
 	if (rq->curr != p) {
 #ifdef CONFIG_SMP
@@ -2452,7 +2449,7 @@ int sched_dl_overflow(struct task_struct *p, int policy,
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
 	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
 		if (hrtimer_active(&p->dl.inactive_timer))
-			__dl_clear(dl_b, p->dl.dl_bw, cpus);
+			__dl_sub(dl_b, p->dl.dl_bw, cpus);
 		__dl_add(dl_b, new_bw, cpus);
 		err = 0;
 	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
@@ -2464,7 +2461,7 @@ int sched_dl_overflow(struct task_struct *p, int policy,
 		 * But this would require to set the task's "inactive
 		 * timer" when the task is not inactive.
 		 */
-		__dl_clear(dl_b, p->dl.dl_bw, cpus);
+		__dl_sub(dl_b, p->dl.dl_bw, cpus);
 		__dl_add(dl_b, new_bw, cpus);
 		dl_change_utilization(p, new_bw);
 		err = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2f93e4a2d9f6..1ca0130ed4f9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -441,9 +441,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 		P_SCHEDSTAT(se->statistics.wait_count);
 	}
 	P(se->load.weight);
+	P(se->runnable_weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
+	P(se->avg.runnable_load_avg);
 #endif
 
 #undef PN_SCHEDSTAT
@@ -558,16 +560,19 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
+	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight);
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
 			cfs_rq->avg.load_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_load_avg",
-			cfs_rq->runnable_load_avg);
+			cfs_rq->avg.runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "removed_load_avg",
-			atomic_long_read(&cfs_rq->removed_load_avg));
-	SEQ_printf(m, "  .%-30s: %ld\n", "removed_util_avg",
-			atomic_long_read(&cfs_rq->removed_util_avg));
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed.load_avg",
+			cfs_rq->removed.load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed.util_avg",
+			cfs_rq->removed.util_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed.runnable_sum",
+			cfs_rq->removed.runnable_sum);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "  .%-30s: %lu\n", "tg_load_avg_contrib",
 			cfs_rq->tg_load_avg_contrib);
@@ -1004,10 +1009,13 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		   "nr_involuntary_switches", (long long)p->nivcsw);
 
 	P(se.load.weight);
+	P(se.runnable_weight);
 #ifdef CONFIG_SMP
 	P(se.avg.load_sum);
+	P(se.avg.runnable_load_sum);
 	P(se.avg.util_sum);
 	P(se.avg.load_avg);
+	P(se.avg.runnable_load_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5c09ddf8c832..0989676c50e9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -33,6 +33,7 @@
 #include <linux/mempolicy.h>
 #include <linux/migrate.h>
 #include <linux/task_work.h>
+#include <linux/sched/isolation.h>
 
 #include <trace/events/sched.h>
 
@@ -717,13 +718,8 @@ void init_entity_runnable_average(struct sched_entity *se)
 {
 	struct sched_avg *sa = &se->avg;
 
-	sa->last_update_time = 0;
-	/*
-	 * sched_avg's period_contrib should be strictly less then 1024, so
-	 * we give it 1023 to make sure it is almost a period (1024us), and
-	 * will definitely be update (after enqueue).
-	 */
-	sa->period_contrib = 1023;
+	memset(sa, 0, sizeof(*sa));
+
 	/*
 	 * Tasks are intialized with full load to be seen as heavy tasks until
 	 * they get a chance to stabilize to their real load level.
@@ -731,13 +727,10 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * nothing has been attached to the task group yet.
 	 */
 	if (entity_is_task(se))
-		sa->load_avg = scale_load_down(se->load.weight);
-	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
-	/*
-	 * At this point, util_avg won't be used in select_task_rq_fair anyway
-	 */
-	sa->util_avg = 0;
-	sa->util_sum = 0;
+		sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
+
+	se->runnable_weight = se->load.weight;
+
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
@@ -785,7 +778,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		} else {
 			sa->util_avg = cap;
 		}
-		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
 
 	if (entity_is_task(se)) {
@@ -2026,7 +2018,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
 	} else {
-		delta = p->se.avg.load_sum / p->se.load.weight;
+		delta = p->se.avg.load_sum;
 		*period = LOAD_AVG_MAX;
 	}
 
@@ -2693,18 +2685,226 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->nr_running--;
 }
 
+/*
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do {                           \
+	typeof(_ptr) ptr = (_ptr);                              \
+	typeof(_val) val = (_val);                              \
+	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
+								\
+	res = var + val;                                        \
+								\
+	if (val < 0 && res > var)                               \
+		res = 0;                                        \
+								\
+	WRITE_ONCE(*ptr, res);                                  \
+} while (0)
+
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
+#ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return scale_load_down(se->runnable_weight);
+}
+
+static inline void
+enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	cfs_rq->runnable_weight += se->runnable_weight;
+
+	cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
+	cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
+}
+
+static inline void
+dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	cfs_rq->runnable_weight -= se->runnable_weight;
+
+	sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
+	sub_positive(&cfs_rq->avg.runnable_load_sum,
+		     se_runnable(se) * se->avg.runnable_load_sum);
+}
+
+static inline void
+enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	cfs_rq->avg.load_avg += se->avg.load_avg;
+	cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
+}
+
+static inline void
+dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
+}
+#else
+static inline void
+enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+static inline void
+dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
+#endif
+
+static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			    unsigned long weight, unsigned long runnable)
+{
+	if (se->on_rq) {
+		/* commit outstanding execution time */
+		if (cfs_rq->curr == se)
+			update_curr(cfs_rq);
+		account_entity_dequeue(cfs_rq, se);
+		dequeue_runnable_load_avg(cfs_rq, se);
+	}
+	dequeue_load_avg(cfs_rq, se);
+
+	se->runnable_weight = runnable;
+	update_load_set(&se->load, weight);
+
+#ifdef CONFIG_SMP
+	do {
+		u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib;
+
+		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
+		se->avg.runnable_load_avg =
+			div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
+	} while (0);
+#endif
+
+	enqueue_load_avg(cfs_rq, se);
+	if (se->on_rq) {
+		account_entity_enqueue(cfs_rq, se);
+		enqueue_runnable_load_avg(cfs_rq, se);
+	}
+}
+
+void reweight_task(struct task_struct *p, int prio)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	struct load_weight *load = &se->load;
+	unsigned long weight = scale_load(sched_prio_to_weight[prio]);
+
+	reweight_entity(cfs_rq, se, weight, weight);
+	load->inv_weight = sched_prio_to_wmult[prio];
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 # ifdef CONFIG_SMP
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
+/*
+ * All this does is approximate the hierarchical proportion which includes that
+ * global sum we all love to hate.
+ *
+ * That is, the weight of a group entity, is the proportional share of the
+ * group weight based on the group runqueue weights. That is:
+ *
+ *                     tg->weight * grq->load.weight
+ *   ge->load.weight = -----------------------------               (1)
+ *			  \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
+ * moves slower and therefore the approximation is cheaper and more stable.
+ *
+ * So instead of the above, we substitute:
+ *
+ *   grq->load.weight -> grq->avg.load_avg                         (2)
+ *
+ * which yields the following:
+ *
+ *                     tg->weight * grq->avg.load_avg
+ *   ge->load.weight = ------------------------------              (3)
+ *				tg->load_avg
+ *
+ * Where: tg->load_avg ~= \Sum grq->avg.load_avg
+ *
+ * That is shares_avg, and it is right (given the approximation (2)).
+ *
+ * The problem with it is that because the average is slow -- it was designed
+ * to be exactly that of course -- this leads to transients in boundary
+ * conditions. In specific, the case where the group was idle and we start the
+ * one task. It takes time for our CPU's grq->avg.load_avg to build up,
+ * yielding bad latency etc..
+ *
+ * Now, in that special case (1) reduces to:
+ *
+ *                     tg->weight * grq->load.weight
+ *   ge->load.weight = ----------------------------- = tg->weight   (4)
+ *			    grp->load.weight
+ *
+ * That is, the sum collapses because all other CPUs are idle; the UP scenario.
+ *
+ * So what we do is modify our approximation (3) to approach (4) in the (near)
+ * UP case, like:
+ *
+ *   ge->load.weight =
+ *
+ *              tg->weight * grq->load.weight
+ *     ---------------------------------------------------         (5)
+ *     tg->load_avg - grq->avg.load_avg + grq->load.weight
+ *
+ * But because grq->load.weight can drop to 0, resulting in a divide by zero,
+ * we need to use grq->avg.load_avg as its lower bound, which then gives:
+ *
+ *
+ *                     tg->weight * grq->load.weight
+ *   ge->load.weight = -----------------------------		   (6)
+ *				tg_load_avg'
+ *
+ * Where:
+ *
+ *   tg_load_avg' = tg->load_avg - grq->avg.load_avg +
+ *                  max(grq->load.weight, grq->avg.load_avg)
+ *
+ * And that is shares_weight and is icky. In the (near) UP case it approaches
+ * (4) while in the normal case it approaches (3). It consistently
+ * overestimates the ge->load.weight and therefore:
+ *
+ *   \Sum ge->load.weight >= tg->weight
+ *
+ * hence icky!
+ */
+static long calc_group_shares(struct cfs_rq *cfs_rq)
 {
-	long tg_weight, load, shares;
+	long tg_weight, tg_shares, load, shares;
+	struct task_group *tg = cfs_rq->tg;
 
-	/*
-	 * This really should be: cfs_rq->avg.load_avg, but instead we use
-	 * cfs_rq->load.weight, which is its upper bound. This helps ramp up
-	 * the shares for small weight interactive tasks.
-	 */
-	load = scale_load_down(cfs_rq->load.weight);
+	tg_shares = READ_ONCE(tg->shares);
+
+	load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg);
 
 	tg_weight = atomic_long_read(&tg->load_avg);
 
@@ -2712,7 +2912,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	tg_weight -= cfs_rq->tg_load_avg_contrib;
 	tg_weight += load;
 
-	shares = (tg->shares * load);
+	shares = (tg_shares * load);
 	if (tg_weight)
 		shares /= tg_weight;
 
@@ -2728,63 +2928,86 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	 * case no task is runnable on a CPU MIN_SHARES=2 should be returned
 	 * instead of 0.
 	 */
-	if (shares < MIN_SHARES)
-		shares = MIN_SHARES;
-	if (shares > tg->shares)
-		shares = tg->shares;
-
-	return shares;
-}
-# else /* CONFIG_SMP */
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
-	return tg->shares;
+	return clamp_t(long, shares, MIN_SHARES, tg_shares);
 }
-# endif /* CONFIG_SMP */
 
-static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
-			    unsigned long weight)
+/*
+ * This calculates the effective runnable weight for a group entity based on
+ * the group entity weight calculated above.
+ *
+ * Because of the above approximation (2), our group entity weight is
+ * an load_avg based ratio (3). This means that it includes blocked load and
+ * does not represent the runnable weight.
+ *
+ * Approximate the group entity's runnable weight per ratio from the group
+ * runqueue:
+ *
+ *					     grq->avg.runnable_load_avg
+ *   ge->runnable_weight = ge->load.weight * -------------------------- (7)
+ *						 grq->avg.load_avg
+ *
+ * However, analogous to above, since the avg numbers are slow, this leads to
+ * transients in the from-idle case. Instead we use:
+ *
+ *   ge->runnable_weight = ge->load.weight *
+ *
+ *		max(grq->avg.runnable_load_avg, grq->runnable_weight)
+ *		-----------------------------------------------------	(8)
+ *		      max(grq->avg.load_avg, grq->load.weight)
+ *
+ * Where these max() serve both to use the 'instant' values to fix the slow
+ * from-idle and avoid the /0 on to-idle, similar to (6).
+ */
+static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
 {
-	if (se->on_rq) {
-		/* commit outstanding execution time */
-		if (cfs_rq->curr == se)
-			update_curr(cfs_rq);
-		account_entity_dequeue(cfs_rq, se);
-	}
+	long runnable, load_avg;
 
-	update_load_set(&se->load, weight);
+	load_avg = max(cfs_rq->avg.load_avg,
+		       scale_load_down(cfs_rq->load.weight));
 
-	if (se->on_rq)
-		account_entity_enqueue(cfs_rq, se);
+	runnable = max(cfs_rq->avg.runnable_load_avg,
+		       scale_load_down(cfs_rq->runnable_weight));
+
+	runnable *= shares;
+	if (load_avg)
+		runnable /= load_avg;
+
+	return clamp_t(long, runnable, MIN_SHARES, shares);
 }
+# endif /* CONFIG_SMP */
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 
-static void update_cfs_shares(struct sched_entity *se)
+/*
+ * Recomputes the group entity based on the current state of its group
+ * runqueue.
+ */
+static void update_cfs_group(struct sched_entity *se)
 {
-	struct cfs_rq *cfs_rq = group_cfs_rq(se);
-	struct task_group *tg;
-	long shares;
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+	long shares, runnable;
 
-	if (!cfs_rq)
+	if (!gcfs_rq)
 		return;
 
-	if (throttled_hierarchy(cfs_rq))
+	if (throttled_hierarchy(gcfs_rq))
 		return;
 
-	tg = cfs_rq->tg;
-
 #ifndef CONFIG_SMP
-	if (likely(se->load.weight == tg->shares))
+	runnable = shares = READ_ONCE(gcfs_rq->tg->shares);
+
+	if (likely(se->load.weight == shares))
 		return;
+#else
+	shares   = calc_group_shares(gcfs_rq);
+	runnable = calc_group_runnable(gcfs_rq, shares);
 #endif
-	shares = calc_cfs_shares(cfs_rq, tg);
 
-	reweight_entity(cfs_rq_of(se), se, shares);
+	reweight_entity(cfs_rq_of(se), se, shares, runnable);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct sched_entity *se)
+static inline void update_cfs_group(struct sched_entity *se)
 {
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2893,7 +3116,7 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
  */
 static __always_inline u32
 accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
-	       unsigned long weight, int running, struct cfs_rq *cfs_rq)
+	       unsigned long load, unsigned long runnable, int running)
 {
 	unsigned long scale_freq, scale_cpu;
 	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
@@ -2910,10 +3133,8 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
 	 */
 	if (periods) {
 		sa->load_sum = decay_load(sa->load_sum, periods);
-		if (cfs_rq) {
-			cfs_rq->runnable_load_sum =
-				decay_load(cfs_rq->runnable_load_sum, periods);
-		}
+		sa->runnable_load_sum =
+			decay_load(sa->runnable_load_sum, periods);
 		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
 
 		/*
@@ -2926,11 +3147,10 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
 	sa->period_contrib = delta;
 
 	contrib = cap_scale(contrib, scale_freq);
-	if (weight) {
-		sa->load_sum += weight * contrib;
-		if (cfs_rq)
-			cfs_rq->runnable_load_sum += weight * contrib;
-	}
+	if (load)
+		sa->load_sum += load * contrib;
+	if (runnable)
+		sa->runnable_load_sum += runnable * contrib;
 	if (running)
 		sa->util_sum += contrib * scale_cpu;
 
@@ -2966,8 +3186,8 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
 static __always_inline int
-___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
-		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+		  unsigned long load, unsigned long runnable, int running)
 {
 	u64 delta;
 
@@ -3000,8 +3220,8 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	 * this happens during idle_balance() which calls
 	 * update_blocked_averages()
 	 */
-	if (!weight)
-		running = 0;
+	if (!load)
+		runnable = running = 0;
 
 	/*
 	 * Now we know we crossed measurement unit boundaries. The *_avg
@@ -3010,63 +3230,96 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	 * Step 1: accumulate *_sum since last_update_time. If we haven't
 	 * crossed period boundaries, finish.
 	 */
-	if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq))
+	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
 		return 0;
 
+	return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
 	/*
 	 * Step 2: update *_avg.
 	 */
-	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
-	if (cfs_rq) {
-		cfs_rq->runnable_load_avg =
-			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
-	}
-	sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
-
-	return 1;
+	sa->load_avg = div_u64(load * sa->load_sum, divider);
+	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	sa->util_avg = sa->util_sum / divider;
 }
 
+/*
+ * sched_entity:
+ *
+ *   task:
+ *     se_runnable() == se_weight()
+ *
+ *   group: [ see update_cfs_group() ]
+ *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
+ *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ *   load_sum := runnable_sum
+ *   load_avg = se_weight(se) * runnable_avg
+ *
+ *   runnable_load_sum := runnable_sum
+ *   runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rs:
+ *
+ *   load_sum = \Sum se_weight(se) * se->avg.load_sum
+ *   load_avg = \Sum se->avg.load_avg
+ *
+ *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ *   runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
 static int
 __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
 {
-	return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL);
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		return 1;
+	}
+
+	return 0;
 }
 
 static int
 __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	return ___update_load_avg(now, cpu, &se->avg,
-				  se->on_rq * scale_load_down(se->load.weight),
-				  cfs_rq->curr == se, NULL);
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+				cfs_rq->curr == se)) {
+
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		return 1;
+	}
+
+	return 0;
 }
 
 static int
 __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
 {
-	return ___update_load_avg(now, cpu, &cfs_rq->avg,
-			scale_load_down(cfs_rq->load.weight),
-			cfs_rq->curr != NULL, cfs_rq);
-}
+	if (___update_load_sum(now, cpu, &cfs_rq->avg,
+				scale_load_down(cfs_rq->load.weight),
+				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->curr != NULL)) {
 
-/*
- * Signed add and clamp on underflow.
- *
- * Explicitly do a load-store to ensure the intermediate value never hits
- * memory. This allows lockless observations without ever seeing the negative
- * values.
- */
-#define add_positive(_ptr, _val) do {                           \
-	typeof(_ptr) ptr = (_ptr);                              \
-	typeof(_val) val = (_val);                              \
-	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
-								\
-	res = var + val;                                        \
-								\
-	if (val < 0 && res > var)                               \
-		res = 0;                                        \
-								\
-	WRITE_ONCE(*ptr, res);                                  \
-} while (0)
+		___update_load_avg(&cfs_rq->avg, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
@@ -3149,11 +3402,77 @@ void set_task_rq_fair(struct sched_entity *se,
 	se->avg.last_update_time = n_last_update_time;
 }
 
-/* Take into account change of utilization of a child task group */
+
+/*
+ * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
+ * propagate its contribution. The key to this propagation is the invariant
+ * that for each group:
+ *
+ *   ge->avg == grq->avg						(1)
+ *
+ * _IFF_ we look at the pure running and runnable sums. Because they
+ * represent the very same entity, just at different points in the hierarchy.
+ *
+ *
+ * Per the above update_tg_cfs_util() is trivial (and still 'wrong') and
+ * simply copies the running sum over.
+ *
+ * However, update_tg_cfs_runnable() is more complex. So we have:
+ *
+ *   ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg		(2)
+ *
+ * And since, like util, the runnable part should be directly transferable,
+ * the following would _appear_ to be the straight forward approach:
+ *
+ *   grq->avg.load_avg = grq->load.weight * grq->avg.running_avg	(3)
+ *
+ * And per (1) we have:
+ *
+ *   ge->avg.running_avg == grq->avg.running_avg
+ *
+ * Which gives:
+ *
+ *                      ge->load.weight * grq->avg.load_avg
+ *   ge->avg.load_avg = -----------------------------------		(4)
+ *                               grq->load.weight
+ *
+ * Except that is wrong!
+ *
+ * Because while for entities historical weight is not important and we
+ * really only care about our future and therefore can consider a pure
+ * runnable sum, runqueues can NOT do this.
+ *
+ * We specifically want runqueues to have a load_avg that includes
+ * historical weights. Those represent the blocked load, the load we expect
+ * to (shortly) return to us. This only works by keeping the weights as
+ * integral part of the sum. We therefore cannot decompose as per (3).
+ *
+ * OK, so what then?
+ *
+ *
+ * Another way to look at things is:
+ *
+ *   grq->avg.load_avg = \Sum se->avg.load_avg
+ *
+ * Therefore, per (2):
+ *
+ *   grq->avg.load_avg = \Sum se->load.weight * se->avg.runnable_avg
+ *
+ * And the very thing we're propagating is a change in that sum (someone
+ * joined/left). So we can easily know the runnable change, which would be, per
+ * (2) the already tracked se->load_avg divided by the corresponding
+ * se->weight.
+ *
+ * Basically (4) but in differential form:
+ *
+ *   d(runnable_avg) += se->avg.load_avg / se->load.weight
+ *								   (5)
+ *   ge->avg.load_avg += ge->load.weight * d(runnable_avg)
+ */
+
 static inline void
-update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
 	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
 
 	/* Nothing to update */
@@ -3169,102 +3488,65 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
 }
 
-/* Take into account change of load of a child task group */
 static inline void
-update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
-	long delta, load = gcfs_rq->avg.load_avg;
+	long runnable_sum = gcfs_rq->prop_runnable_sum;
+	long runnable_load_avg, load_avg;
+	s64 runnable_load_sum, load_sum;
 
-	/*
-	 * If the load of group cfs_rq is null, the load of the
-	 * sched_entity will also be null so we can skip the formula
-	 */
-	if (load) {
-		long tg_load;
+	if (!runnable_sum)
+		return;
 
-		/* Get tg's load and ensure tg_load > 0 */
-		tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
+	gcfs_rq->prop_runnable_sum = 0;
 
-		/* Ensure tg_load >= load and updated with current load*/
-		tg_load -= gcfs_rq->tg_load_avg_contrib;
-		tg_load += load;
+	load_sum = (s64)se_weight(se) * runnable_sum;
+	load_avg = div_s64(load_sum, LOAD_AVG_MAX);
 
-		/*
-		 * We need to compute a correction term in the case that the
-		 * task group is consuming more CPU than a task of equal
-		 * weight. A task with a weight equals to tg->shares will have
-		 * a load less or equal to scale_load_down(tg->shares).
-		 * Similarly, the sched_entities that represent the task group
-		 * at parent level, can't have a load higher than
-		 * scale_load_down(tg->shares). And the Sum of sched_entities'
-		 * load must be <= scale_load_down(tg->shares).
-		 */
-		if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
-			/* scale gcfs_rq's load into tg's shares*/
-			load *= scale_load_down(gcfs_rq->tg->shares);
-			load /= tg_load;
-		}
-	}
+	add_positive(&se->avg.load_sum, runnable_sum);
+	add_positive(&se->avg.load_avg, load_avg);
 
-	delta = load - se->avg.load_avg;
+	add_positive(&cfs_rq->avg.load_avg, load_avg);
+	add_positive(&cfs_rq->avg.load_sum, load_sum);
 
-	/* Nothing to update */
-	if (!delta)
-		return;
-
-	/* Set new sched_entity's load */
-	se->avg.load_avg = load;
-	se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
+	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
+	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
 
-	/* Update parent cfs_rq load */
-	add_positive(&cfs_rq->avg.load_avg, delta);
-	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+	add_positive(&se->avg.runnable_load_sum, runnable_sum);
+	add_positive(&se->avg.runnable_load_avg, runnable_load_avg);
 
-	/*
-	 * If the sched_entity is already enqueued, we also have to update the
-	 * runnable load avg.
-	 */
 	if (se->on_rq) {
-		/* Update parent cfs_rq runnable_load_avg */
-		add_positive(&cfs_rq->runnable_load_avg, delta);
-		cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
+		add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg);
+		add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum);
 	}
 }
 
-static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
-{
-	cfs_rq->propagate_avg = 1;
-}
-
-static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
+static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
 {
-	struct cfs_rq *cfs_rq = group_cfs_rq(se);
-
-	if (!cfs_rq->propagate_avg)
-		return 0;
-
-	cfs_rq->propagate_avg = 0;
-	return 1;
+	cfs_rq->propagate = 1;
+	cfs_rq->prop_runnable_sum += runnable_sum;
 }
 
 /* Update task and its cfs_rq load average */
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *gcfs_rq;
 
 	if (entity_is_task(se))
 		return 0;
 
-	if (!test_and_clear_tg_cfs_propagate(se))
+	gcfs_rq = group_cfs_rq(se);
+	if (!gcfs_rq->propagate)
 		return 0;
 
+	gcfs_rq->propagate = 0;
+
 	cfs_rq = cfs_rq_of(se);
 
-	set_tg_cfs_propagate(cfs_rq);
+	add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum);
 
-	update_tg_cfs_util(cfs_rq, se);
-	update_tg_cfs_load(cfs_rq, se);
+	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
+	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
 
 	return 1;
 }
@@ -3288,7 +3570,7 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 	 * If there is a pending propagation, we have to update the load and
 	 * the utilization of the sched_entity:
 	 */
-	if (gcfs_rq->propagate_avg)
+	if (gcfs_rq->propagate)
 		return false;
 
 	/*
@@ -3308,27 +3590,10 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 	return 0;
 }
 
-static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
+static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) {}
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-/*
- * Unsigned subtract and clamp on underflow.
- *
- * Explicitly do a load-store to ensure the intermediate value never hits
- * memory. This allows lockless observations without ever seeing the negative
- * values.
- */
-#define sub_positive(_ptr, _val) do {				\
-	typeof(_ptr) ptr = (_ptr);				\
-	typeof(*ptr) val = (_val);				\
-	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
-	res = var - val;					\
-	if (res > var)						\
-		res = 0;					\
-	WRITE_ONCE(*ptr, res);					\
-} while (0)
-
 /**
  * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
  * @now: current time, as per cfs_rq_clock_task()
@@ -3348,65 +3613,45 @@ static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
+	unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
 	struct sched_avg *sa = &cfs_rq->avg;
-	int decayed, removed_load = 0, removed_util = 0;
+	int decayed = 0;
 
-	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
-		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
+	if (cfs_rq->removed.nr) {
+		unsigned long r;
+		u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+		raw_spin_lock(&cfs_rq->removed.lock);
+		swap(cfs_rq->removed.util_avg, removed_util);
+		swap(cfs_rq->removed.load_avg, removed_load);
+		swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+		cfs_rq->removed.nr = 0;
+		raw_spin_unlock(&cfs_rq->removed.lock);
+
+		r = removed_load;
 		sub_positive(&sa->load_avg, r);
-		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
-		removed_load = 1;
-		set_tg_cfs_propagate(cfs_rq);
-	}
+		sub_positive(&sa->load_sum, r * divider);
 
-	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
-		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
+		r = removed_util;
 		sub_positive(&sa->util_avg, r);
-		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
-		removed_util = 1;
-		set_tg_cfs_propagate(cfs_rq);
+		sub_positive(&sa->util_sum, r * divider);
+
+		add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+
+		decayed = 1;
 	}
 
-	decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
+	decayed |= __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
 
 #ifndef CONFIG_64BIT
 	smp_wmb();
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
-	if (decayed || removed_util)
+	if (decayed)
 		cfs_rq_util_change(cfs_rq);
 
-	return decayed || removed_load;
-}
-
-/*
- * Optional action to be done while updating the load average
- */
-#define UPDATE_TG	0x1
-#define SKIP_AGE_LOAD	0x2
-
-/* Update task and its cfs_rq load average */
-static inline void update_load_avg(struct sched_entity *se, int flags)
-{
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 now = cfs_rq_clock_task(cfs_rq);
-	struct rq *rq = rq_of(cfs_rq);
-	int cpu = cpu_of(rq);
-	int decayed;
-
-	/*
-	 * Track task load average for carrying it to new CPU after migrated, and
-	 * track group sched_entity load average for task_h_load calc in migration
-	 */
-	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
-		__update_load_avg_se(now, cpu, cfs_rq, se);
-
-	decayed  = update_cfs_rq_load_avg(now, cfs_rq);
-	decayed |= propagate_entity_load_avg(se);
-
-	if (decayed && (flags & UPDATE_TG))
-		update_tg_load_avg(cfs_rq, 0);
+	return decayed;
 }
 
 /**
@@ -3419,12 +3664,39 @@ static inline void update_load_avg(struct sched_entity *se, int flags)
  */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib;
+
+	/*
+	 * When we attach the @se to the @cfs_rq, we must align the decay
+	 * window because without that, really weird and wonderful things can
+	 * happen.
+	 *
+	 * XXX illustrate
+	 */
 	se->avg.last_update_time = cfs_rq->avg.last_update_time;
-	cfs_rq->avg.load_avg += se->avg.load_avg;
-	cfs_rq->avg.load_sum += se->avg.load_sum;
+	se->avg.period_contrib = cfs_rq->avg.period_contrib;
+
+	/*
+	 * Hell(o) Nasty stuff.. we need to recompute _sum based on the new
+	 * period_contrib. This isn't strictly correct, but since we're
+	 * entirely outside of the PELT hierarchy, nobody cares if we truncate
+	 * _sum a little.
+	 */
+	se->avg.util_sum = se->avg.util_avg * divider;
+
+	se->avg.load_sum = divider;
+	if (se_weight(se)) {
+		se->avg.load_sum =
+			div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
+	}
+
+	se->avg.runnable_load_sum = se->avg.load_sum;
+
+	enqueue_load_avg(cfs_rq, se);
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
-	set_tg_cfs_propagate(cfs_rq);
+
+	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3439,39 +3711,47 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-
-	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
-	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	dequeue_load_avg(cfs_rq, se);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
-	set_tg_cfs_propagate(cfs_rq);
+
+	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
 	cfs_rq_util_change(cfs_rq);
 }
 
-/* Add the load generated by se into cfs_rq's load average */
-static inline void
-enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+/*
+ * Optional action to be done while updating the load average
+ */
+#define UPDATE_TG	0x1
+#define SKIP_AGE_LOAD	0x2
+#define DO_ATTACH	0x4
+
+/* Update task and its cfs_rq load average */
+static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	struct sched_avg *sa = &se->avg;
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	struct rq *rq = rq_of(cfs_rq);
+	int cpu = cpu_of(rq);
+	int decayed;
+
+	/*
+	 * Track task load average for carrying it to new CPU after migrated, and
+	 * track group sched_entity load average for task_h_load calc in migration
+	 */
+	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
+		__update_load_avg_se(now, cpu, cfs_rq, se);
 
-	cfs_rq->runnable_load_avg += sa->load_avg;
-	cfs_rq->runnable_load_sum += sa->load_sum;
+	decayed  = update_cfs_rq_load_avg(now, cfs_rq);
+	decayed |= propagate_entity_load_avg(se);
+
+	if (!se->avg.last_update_time && (flags & DO_ATTACH)) {
 
-	if (!sa->last_update_time) {
 		attach_entity_load_avg(cfs_rq, se);
 		update_tg_load_avg(cfs_rq, 0);
-	}
-}
 
-/* Remove the runnable load generated by se from cfs_rq's runnable load average */
-static inline void
-dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_load_avg =
-		max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
-	cfs_rq->runnable_load_sum =
-		max_t(s64,  cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
+	} else if (decayed && (flags & UPDATE_TG))
+		update_tg_load_avg(cfs_rq, 0);
 }
 
 #ifndef CONFIG_64BIT
@@ -3515,6 +3795,7 @@ void sync_entity_load_avg(struct sched_entity *se)
 void remove_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	unsigned long flags;
 
 	/*
 	 * tasks cannot exit without having gone through wake_up_new_task() ->
@@ -3527,13 +3808,18 @@ void remove_entity_load_avg(struct sched_entity *se)
 	 */
 
 	sync_entity_load_avg(se);
-	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
-	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
+
+	raw_spin_lock_irqsave(&cfs_rq->removed.lock, flags);
+	++cfs_rq->removed.nr;
+	cfs_rq->removed.util_avg	+= se->avg.util_avg;
+	cfs_rq->removed.load_avg	+= se->avg.load_avg;
+	cfs_rq->removed.runnable_sum	+= se->avg.load_sum; /* == runnable_sum */
+	raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
 }
 
 static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
 {
-	return cfs_rq->runnable_load_avg;
+	return cfs_rq->avg.runnable_load_avg;
 }
 
 static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
@@ -3553,16 +3839,13 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
+#define DO_ATTACH	0x0
 
-static inline void update_load_avg(struct sched_entity *se, int not_used1)
+static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int not_used1)
 {
-	cfs_rq_util_change(cfs_rq_of(se));
+	cfs_rq_util_change(cfs_rq);
 }
 
-static inline void
-enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-static inline void
-dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
 
 static inline void
@@ -3707,9 +3990,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *     its group cfs_rq
 	 *   - Add its new weight to cfs_rq->load.weight
 	 */
-	update_load_avg(se, UPDATE_TG);
-	enqueue_entity_load_avg(cfs_rq, se);
-	update_cfs_shares(se);
+	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+	update_cfs_group(se);
+	enqueue_runnable_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
@@ -3791,8 +4074,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *   - For group entity, update its weight to reflect the new share
 	 *     of its group cfs_rq.
 	 */
-	update_load_avg(se, UPDATE_TG);
-	dequeue_entity_load_avg(cfs_rq, se);
+	update_load_avg(cfs_rq, se, UPDATE_TG);
+	dequeue_runnable_load_avg(cfs_rq, se);
 
 	update_stats_dequeue(cfs_rq, se, flags);
 
@@ -3815,7 +4098,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/* return excess runtime on last dequeue */
 	return_cfs_rq_runtime(cfs_rq);
 
-	update_cfs_shares(se);
+	update_cfs_group(se);
 
 	/*
 	 * Now advance min_vruntime if @se was the entity holding it back,
@@ -3879,7 +4162,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
-		update_load_avg(se, UPDATE_TG);
+		update_load_avg(cfs_rq, se, UPDATE_TG);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -3981,7 +4264,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
-		update_load_avg(prev, 0);
+		update_load_avg(cfs_rq, prev, 0);
 	}
 	cfs_rq->curr = NULL;
 }
@@ -3997,8 +4280,8 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	/*
 	 * Ensure that runnable average is periodically updated.
 	 */
-	update_load_avg(curr, UPDATE_TG);
-	update_cfs_shares(curr);
+	update_load_avg(cfs_rq, curr, UPDATE_TG);
+	update_cfs_group(curr);
 
 #ifdef CONFIG_SCHED_HRTICK
 	/*
@@ -4915,8 +5198,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
-		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(se);
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		update_cfs_group(se);
 	}
 
 	if (!se)
@@ -4974,8 +5257,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
-		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(se);
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		update_cfs_group(se);
 	}
 
 	if (!se)
@@ -5449,6 +5732,8 @@ static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
 /*
  * find_idlest_group finds and returns the least busy CPU group within the
  * domain.
+ *
+ * Assumes p is allowed on at least one CPU in sd.
  */
 static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
@@ -5456,8 +5741,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	struct sched_group *most_spare_sg = NULL;
-	unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0;
-	unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0;
+	unsigned long min_runnable_load = ULONG_MAX;
+	unsigned long this_runnable_load = ULONG_MAX;
+	unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
 	unsigned long most_spare = 0, this_spare = 0;
 	int load_idx = sd->forkexec_idx;
 	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
@@ -5578,10 +5864,10 @@ skip_spare:
 }
 
 /*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ * find_idlest_group_cpu - find the idlest cpu among the cpus in group.
  */
 static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
 	unsigned int min_exit_latency = UINT_MAX;
@@ -5630,6 +5916,53 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
+static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
+				  int cpu, int prev_cpu, int sd_flag)
+{
+	int new_cpu = cpu;
+
+	if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+		return prev_cpu;
+
+	while (sd) {
+		struct sched_group *group;
+		struct sched_domain *tmp;
+		int weight;
+
+		if (!(sd->flags & sd_flag)) {
+			sd = sd->child;
+			continue;
+		}
+
+		group = find_idlest_group(sd, p, cpu, sd_flag);
+		if (!group) {
+			sd = sd->child;
+			continue;
+		}
+
+		new_cpu = find_idlest_group_cpu(group, p, cpu);
+		if (new_cpu == cpu) {
+			/* Now try balancing at a lower domain level of cpu */
+			sd = sd->child;
+			continue;
+		}
+
+		/* Now try balancing at a lower domain level of new_cpu */
+		cpu = new_cpu;
+		weight = sd->span_weight;
+		sd = NULL;
+		for_each_domain(cpu, tmp) {
+			if (weight <= tmp->span_weight)
+				break;
+			if (tmp->flags & sd_flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
+	}
+
+	return new_cpu;
+}
+
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5982,50 +6315,30 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			new_cpu = cpu;
 	}
 
+	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
+		/*
+		 * We're going to need the task's util for capacity_spare_wake
+		 * in find_idlest_group. Sync it up to prev_cpu's
+		 * last_update_time.
+		 */
+		sync_entity_load_avg(&p->se);
+	}
+
 	if (!sd) {
- pick_cpu:
+pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
-	} else while (sd) {
-		struct sched_group *group;
-		int weight;
-
-		if (!(sd->flags & sd_flag)) {
-			sd = sd->child;
-			continue;
-		}
-
-		group = find_idlest_group(sd, p, cpu, sd_flag);
-		if (!group) {
-			sd = sd->child;
-			continue;
-		}
-
-		new_cpu = find_idlest_cpu(group, p, cpu);
-		if (new_cpu == -1 || new_cpu == cpu) {
-			/* Now try balancing at a lower domain level of cpu */
-			sd = sd->child;
-			continue;
-		}
-
-		/* Now try balancing at a lower domain level of new_cpu */
-		cpu = new_cpu;
-		weight = sd->span_weight;
-		sd = NULL;
-		for_each_domain(cpu, tmp) {
-			if (weight <= tmp->span_weight)
-				break;
-			if (tmp->flags & sd_flag)
-				sd = tmp;
-		}
-		/* while loop will break here if sd == NULL */
+	} else {
+		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
 	}
 	rcu_read_unlock();
 
 	return new_cpu;
 }
 
+static void detach_entity_cfs_rq(struct sched_entity *se);
+
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -6059,14 +6372,25 @@ static void migrate_task_rq_fair(struct task_struct *p)
 		se->vruntime -= min_vruntime;
 	}
 
-	/*
-	 * We are supposed to update the task to "current" time, then its up to date
-	 * and ready to go to new CPU/cfs_rq. But we have difficulty in getting
-	 * what current time is, so simply throw away the out-of-date time. This
-	 * will result in the wakee task is less decayed, but giving the wakee more
-	 * load sounds not bad.
-	 */
-	remove_entity_load_avg(&p->se);
+	if (p->on_rq == TASK_ON_RQ_MIGRATING) {
+		/*
+		 * 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);
+		detach_entity_cfs_rq(&p->se);
+
+	} else {
+		/*
+		 * We are supposed to update the task to "current" time, then
+		 * its up to date and ready to go to new CPU/cfs_rq. But we
+		 * have difficulty in getting what current time is, so simply
+		 * throw away the out-of-date time. This will result in the
+		 * wakee task is less decayed, but giving the wakee more load
+		 * sounds not bad.
+		 */
+		remove_entity_load_avg(&p->se);
+	}
 
 	/* Tell new CPU we are migrated */
 	p->se.avg.last_update_time = 0;
@@ -6334,10 +6658,7 @@ again:
 		set_next_entity(cfs_rq, se);
 	}
 
-	if (hrtick_enabled(rq))
-		hrtick_start_fair(rq, p);
-
-	return p;
+	goto done;
 simple:
 #endif
 
@@ -6351,6 +6672,16 @@ simple:
 
 	p = task_of(se);
 
+done: __maybe_unused
+#ifdef CONFIG_SMP
+	/*
+	 * Move the next running task to the front of
+	 * the list, so our cfs_tasks list becomes MRU
+	 * one.
+	 */
+	list_move(&p->se.group_node, &rq->cfs_tasks);
+#endif
+
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
@@ -6786,11 +7117,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
  */
 static struct task_struct *detach_one_task(struct lb_env *env)
 {
-	struct task_struct *p, *n;
+	struct task_struct *p;
 
 	lockdep_assert_held(&env->src_rq->lock);
 
-	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+	list_for_each_entry_reverse(p,
+			&env->src_rq->cfs_tasks, se.group_node) {
 		if (!can_migrate_task(p, env))
 			continue;
 
@@ -6836,7 +7168,7 @@ static int detach_tasks(struct lb_env *env)
 		if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
 			break;
 
-		p = list_first_entry(tasks, struct task_struct, se.group_node);
+		p = list_last_entry(tasks, struct task_struct, se.group_node);
 
 		env->loop++;
 		/* We've more or less seen every task there is, call it quits */
@@ -6886,7 +7218,7 @@ static int detach_tasks(struct lb_env *env)
 
 		continue;
 next:
-		list_move_tail(&p->se.group_node, tasks);
+		list_move(&p->se.group_node, tasks);
 	}
 
 	/*
@@ -6962,7 +7294,7 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (cfs_rq->avg.util_sum)
 		return false;
 
-	if (cfs_rq->runnable_load_sum)
+	if (cfs_rq->avg.runnable_load_sum)
 		return false;
 
 	return true;
@@ -6994,7 +7326,7 @@ static void update_blocked_averages(int cpu)
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
-			update_load_avg(se, 0);
+			update_load_avg(cfs_rq_of(se), se, 0);
 
 		/*
 		 * There can be a lot of idle CPU cgroups.  Don't let fully
@@ -7875,8 +8207,11 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	if (busiest->group_type == group_imbalanced)
 		goto force_balance;
 
-	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
-	if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+	/*
+	 * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
+	 * capacities from resulting in underutilization due to avg_load.
+	 */
+	if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
 	    busiest->group_no_capacity)
 		goto force_balance;
 
@@ -8693,7 +9028,7 @@ void nohz_balance_enter_idle(int cpu)
 		return;
 
 	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
-	if (!is_housekeeping_cpu(cpu))
+	if (!housekeeping_cpu(cpu, HK_FLAG_SCHED))
 		return;
 
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
@@ -9158,7 +9493,7 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
-		update_load_avg(se, UPDATE_TG);
+		update_load_avg(cfs_rq, se, UPDATE_TG);
 	}
 }
 #else
@@ -9170,7 +9505,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/* Catch up with the cfs_rq and remove our load when we leave */
-	update_load_avg(se, 0);
+	update_load_avg(cfs_rq, se, 0);
 	detach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
 	propagate_entity_cfs_rq(se);
@@ -9189,7 +9524,7 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 #endif
 
 	/* Synchronize entity with its cfs_rq */
-	update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
+	update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
 	attach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
 	propagate_entity_cfs_rq(se);
@@ -9271,11 +9606,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
 #ifdef CONFIG_SMP
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	cfs_rq->propagate_avg = 0;
-#endif
-	atomic_long_set(&cfs_rq->removed_load_avg, 0);
-	atomic_long_set(&cfs_rq->removed_util_avg, 0);
+	raw_spin_lock_init(&cfs_rq->removed.lock);
 #endif
 }
 
@@ -9473,8 +9804,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		rq_lock_irqsave(rq, &rf);
 		update_rq_clock(rq);
 		for_each_sched_entity(se) {
-			update_load_avg(se, UPDATE_TG);
-			update_cfs_shares(se);
+			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
+			update_cfs_group(se);
 		}
 		rq_unlock_irqrestore(rq, &rf);
 	}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 257f4f0b4532..7dae9eb8c042 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -209,6 +209,7 @@ exit_idle:
  */
 static void do_idle(void)
 {
+	int cpu = smp_processor_id();
 	/*
 	 * If the arch has a polling bit, we maintain an invariant:
 	 *
@@ -219,14 +220,13 @@ static void do_idle(void)
 	 */
 
 	__current_set_polling();
-	quiet_vmstat();
 	tick_nohz_idle_enter();
 
 	while (!need_resched()) {
 		check_pgt_cache();
 		rmb();
 
-		if (cpu_is_offline(smp_processor_id())) {
+		if (cpu_is_offline(cpu)) {
 			cpuhp_report_idle_dead();
 			arch_cpu_idle_dead();
 		}
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
new file mode 100644
index 000000000000..b71b436f59f2
--- /dev/null
+++ b/kernel/sched/isolation.c
@@ -0,0 +1,155 @@
+/*
+ *  Housekeeping management. Manage the targets for routine code that can run on
+ *  any CPU: unbound workqueues, timers, kthreads and any offloadable work.
+ *
+ * Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker
+ *
+ */
+
+#include <linux/sched/isolation.h>
+#include <linux/tick.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/static_key.h>
+#include <linux/ctype.h>
+
+DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
+EXPORT_SYMBOL_GPL(housekeeping_overriden);
+static cpumask_var_t housekeeping_mask;
+static unsigned int housekeeping_flags;
+
+int housekeeping_any_cpu(enum hk_flags flags)
+{
+	if (static_branch_unlikely(&housekeeping_overriden))
+		if (housekeeping_flags & flags)
+			return cpumask_any_and(housekeeping_mask, cpu_online_mask);
+	return smp_processor_id();
+}
+EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
+
+const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+{
+	if (static_branch_unlikely(&housekeeping_overriden))
+		if (housekeeping_flags & flags)
+			return housekeeping_mask;
+	return cpu_possible_mask;
+}
+EXPORT_SYMBOL_GPL(housekeeping_cpumask);
+
+void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
+{
+	if (static_branch_unlikely(&housekeeping_overriden))
+		if (housekeeping_flags & flags)
+			set_cpus_allowed_ptr(t, housekeeping_mask);
+}
+EXPORT_SYMBOL_GPL(housekeeping_affine);
+
+bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
+{
+	if (static_branch_unlikely(&housekeeping_overriden))
+		if (housekeeping_flags & flags)
+			return cpumask_test_cpu(cpu, housekeeping_mask);
+	return true;
+}
+EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
+
+void __init housekeeping_init(void)
+{
+	if (!housekeeping_flags)
+		return;
+
+	static_branch_enable(&housekeeping_overriden);
+
+	/* We need at least one CPU to handle housekeeping work */
+	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
+}
+
+static int __init housekeeping_setup(char *str, enum hk_flags flags)
+{
+	cpumask_var_t non_housekeeping_mask;
+	int err;
+
+	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
+	err = cpulist_parse(str, non_housekeeping_mask);
+	if (err < 0 || cpumask_last(non_housekeeping_mask) >= nr_cpu_ids) {
+		pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
+		free_bootmem_cpumask_var(non_housekeeping_mask);
+		return 0;
+	}
+
+	if (!housekeeping_flags) {
+		alloc_bootmem_cpumask_var(&housekeeping_mask);
+		cpumask_andnot(housekeeping_mask,
+			       cpu_possible_mask, non_housekeeping_mask);
+		if (cpumask_empty(housekeeping_mask))
+			cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+	} else {
+		cpumask_var_t tmp;
+
+		alloc_bootmem_cpumask_var(&tmp);
+		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
+		if (!cpumask_equal(tmp, housekeeping_mask)) {
+			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
+			free_bootmem_cpumask_var(tmp);
+			free_bootmem_cpumask_var(non_housekeeping_mask);
+			return 0;
+		}
+		free_bootmem_cpumask_var(tmp);
+	}
+
+	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
+		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+			tick_nohz_full_setup(non_housekeeping_mask);
+		} else {
+			pr_warn("Housekeeping: nohz unsupported."
+				" Build with CONFIG_NO_HZ_FULL\n");
+			free_bootmem_cpumask_var(non_housekeeping_mask);
+			return 0;
+		}
+	}
+
+	housekeeping_flags |= flags;
+
+	free_bootmem_cpumask_var(non_housekeeping_mask);
+
+	return 1;
+}
+
+static int __init housekeeping_nohz_full_setup(char *str)
+{
+	unsigned int flags;
+
+	flags = HK_FLAG_TICK | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+
+	return housekeeping_setup(str, flags);
+}
+__setup("nohz_full=", housekeeping_nohz_full_setup);
+
+static int __init housekeeping_isolcpus_setup(char *str)
+{
+	unsigned int flags = 0;
+
+	while (isalpha(*str)) {
+		if (!strncmp(str, "nohz,", 5)) {
+			str += 5;
+			flags |= HK_FLAG_TICK;
+			continue;
+		}
+
+		if (!strncmp(str, "domain,", 7)) {
+			str += 7;
+			flags |= HK_FLAG_DOMAIN;
+			continue;
+		}
+
+		pr_warn("isolcpus: Error, unknown flag\n");
+		return 0;
+	}
+
+	/* Default behaviour for isolcpus without flags */
+	if (!flags)
+		flags |= HK_FLAG_DOMAIN;
+
+	return housekeeping_setup(str, flags);
+}
+__setup("isolcpus=", housekeeping_isolcpus_setup);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3c96c80e0992..d8c43d73e078 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -74,10 +74,6 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
-static void push_irq_work_func(struct irq_work *work);
-#endif
-
 void init_rt_rq(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array;
@@ -97,13 +93,6 @@ void init_rt_rq(struct rt_rq *rt_rq)
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
-
-#ifdef HAVE_RT_PUSH_IPI
-	rt_rq->push_flags = 0;
-	rt_rq->push_cpu = nr_cpu_ids;
-	raw_spin_lock_init(&rt_rq->push_lock);
-	init_irq_work(&rt_rq->push_work, push_irq_work_func);
-#endif
 #endif /* CONFIG_SMP */
 	/* We start is dequeued state, because no RT tasks are queued */
 	rt_rq->rt_queued = 0;
@@ -1876,241 +1865,166 @@ static void push_rt_tasks(struct rq *rq)
 }
 
 #ifdef HAVE_RT_PUSH_IPI
+
 /*
- * The search for the next cpu always starts at rq->cpu and ends
- * when we reach rq->cpu again. It will never return rq->cpu.
- * This returns the next cpu to check, or nr_cpu_ids if the loop
- * is complete.
+ * When a high priority task schedules out from a CPU and a lower priority
+ * task is scheduled in, a check is made to see if there's any RT tasks
+ * on other CPUs that are waiting to run because a higher priority RT task
+ * is currently running on its CPU. In this case, the CPU with multiple RT
+ * tasks queued on it (overloaded) needs to be notified that a CPU has opened
+ * up that may be able to run one of its non-running queued RT tasks.
+ *
+ * All CPUs with overloaded RT tasks need to be notified as there is currently
+ * no way to know which of these CPUs have the highest priority task waiting
+ * to run. Instead of trying to take a spinlock on each of these CPUs,
+ * which has shown to cause large latency when done on machines with many
+ * CPUs, sending an IPI to the CPUs to have them push off the overloaded
+ * RT tasks waiting to run.
+ *
+ * Just sending an IPI to each of the CPUs is also an issue, as on large
+ * count CPU machines, this can cause an IPI storm on a CPU, especially
+ * if its the only CPU with multiple RT tasks queued, and a large number
+ * of CPUs scheduling a lower priority task at the same time.
+ *
+ * Each root domain has its own irq work function that can iterate over
+ * all CPUs with RT overloaded tasks. Since all CPUs with overloaded RT
+ * tassk must be checked if there's one or many CPUs that are lowering
+ * their priority, there's a single irq work iterator that will try to
+ * push off RT tasks that are waiting to run.
+ *
+ * When a CPU schedules a lower priority task, it will kick off the
+ * irq work iterator that will jump to each CPU with overloaded RT tasks.
+ * As it only takes the first CPU that schedules a lower priority task
+ * to start the process, the rto_start variable is incremented and if
+ * the atomic result is one, then that CPU will try to take the rto_lock.
+ * This prevents high contention on the lock as the process handles all
+ * CPUs scheduling lower priority tasks.
+ *
+ * All CPUs that are scheduling a lower priority task will increment the
+ * rt_loop_next variable. This will make sure that the irq work iterator
+ * checks all RT overloaded CPUs whenever a CPU schedules a new lower
+ * priority task, even if the iterator is in the middle of a scan. Incrementing
+ * the rt_loop_next will cause the iterator to perform another scan.
  *
- * rq->rt.push_cpu holds the last cpu returned by this function,
- * or if this is the first instance, it must hold rq->cpu.
  */
 static int rto_next_cpu(struct rq *rq)
 {
-	int prev_cpu = rq->rt.push_cpu;
+	struct root_domain *rd = rq->rd;
+	int next;
 	int cpu;
 
-	cpu = cpumask_next(prev_cpu, rq->rd->rto_mask);
-
 	/*
-	 * If the previous cpu is less than the rq's CPU, then it already
-	 * passed the end of the mask, and has started from the beginning.
-	 * We end if the next CPU is greater or equal to rq's CPU.
+	 * When starting the IPI RT pushing, the rto_cpu is set to -1,
+	 * rt_next_cpu() will simply return the first CPU found in
+	 * the rto_mask.
+	 *
+	 * If rto_next_cpu() is called with rto_cpu is a valid cpu, it
+	 * will return the next CPU found in the rto_mask.
+	 *
+	 * If there are no more CPUs left in the rto_mask, then a check is made
+	 * against rto_loop and rto_loop_next. rto_loop is only updated with
+	 * the rto_lock held, but any CPU may increment the rto_loop_next
+	 * without any locking.
 	 */
-	if (prev_cpu < rq->cpu) {
-		if (cpu >= rq->cpu)
-			return nr_cpu_ids;
+	for (;;) {
 
-	} else if (cpu >= nr_cpu_ids) {
-		/*
-		 * We passed the end of the mask, start at the beginning.
-		 * If the result is greater or equal to the rq's CPU, then
-		 * the loop is finished.
-		 */
-		cpu = cpumask_first(rq->rd->rto_mask);
-		if (cpu >= rq->cpu)
-			return nr_cpu_ids;
-	}
-	rq->rt.push_cpu = cpu;
+		/* When rto_cpu is -1 this acts like cpumask_first() */
+		cpu = cpumask_next(rd->rto_cpu, rd->rto_mask);
 
-	/* Return cpu to let the caller know if the loop is finished or not */
-	return cpu;
-}
+		rd->rto_cpu = cpu;
 
-static int find_next_push_cpu(struct rq *rq)
-{
-	struct rq *next_rq;
-	int cpu;
+		if (cpu < nr_cpu_ids)
+			return cpu;
 
-	while (1) {
-		cpu = rto_next_cpu(rq);
-		if (cpu >= nr_cpu_ids)
-			break;
-		next_rq = cpu_rq(cpu);
+		rd->rto_cpu = -1;
+
+		/*
+		 * ACQUIRE ensures we see the @rto_mask changes
+		 * made prior to the @next value observed.
+		 *
+		 * Matches WMB in rt_set_overload().
+		 */
+		next = atomic_read_acquire(&rd->rto_loop_next);
 
-		/* Make sure the next rq can push to this rq */
-		if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr)
+		if (rd->rto_loop == next)
 			break;
+
+		rd->rto_loop = next;
 	}
 
-	return cpu;
+	return -1;
 }
 
-#define RT_PUSH_IPI_EXECUTING		1
-#define RT_PUSH_IPI_RESTART		2
+static inline bool rto_start_trylock(atomic_t *v)
+{
+	return !atomic_cmpxchg_acquire(v, 0, 1);
+}
 
-/*
- * When a high priority task schedules out from a CPU and a lower priority
- * task is scheduled in, a check is made to see if there's any RT tasks
- * on other CPUs that are waiting to run because a higher priority RT task
- * is currently running on its CPU. In this case, the CPU with multiple RT
- * tasks queued on it (overloaded) needs to be notified that a CPU has opened
- * up that may be able to run one of its non-running queued RT tasks.
- *
- * On large CPU boxes, there's the case that several CPUs could schedule
- * a lower priority task at the same time, in which case it will look for
- * any overloaded CPUs that it could pull a task from. To do this, the runqueue
- * lock must be taken from that overloaded CPU. Having 10s of CPUs all fighting
- * for a single overloaded CPU's runqueue lock can produce a large latency.
- * (This has actually been observed on large boxes running cyclictest).
- * Instead of taking the runqueue lock of the overloaded CPU, each of the
- * CPUs that scheduled a lower priority task simply sends an IPI to the
- * overloaded CPU. An IPI is much cheaper than taking an runqueue lock with
- * lots of contention. The overloaded CPU will look to push its non-running
- * RT task off, and if it does, it can then ignore the other IPIs coming
- * in, and just pass those IPIs off to any other overloaded CPU.
- *
- * When a CPU schedules a lower priority task, it only sends an IPI to
- * the "next" CPU that has overloaded RT tasks. This prevents IPI storms,
- * as having 10 CPUs scheduling lower priority tasks and 10 CPUs with
- * RT overloaded tasks, would cause 100 IPIs to go out at once.
- *
- * The overloaded RT CPU, when receiving an IPI, will try to push off its
- * overloaded RT tasks and then send an IPI to the next CPU that has
- * overloaded RT tasks. This stops when all CPUs with overloaded RT tasks
- * have completed. Just because a CPU may have pushed off its own overloaded
- * RT task does not mean it should stop sending the IPI around to other
- * overloaded CPUs. There may be another RT task waiting to run on one of
- * those CPUs that are of higher priority than the one that was just
- * pushed.
- *
- * An optimization that could possibly be made is to make a CPU array similar
- * to the cpupri array mask of all running RT tasks, but for the overloaded
- * case, then the IPI could be sent to only the CPU with the highest priority
- * RT task waiting, and that CPU could send off further IPIs to the CPU with
- * the next highest waiting task. Since the overloaded case is much less likely
- * to happen, the complexity of this implementation may not be worth it.
- * Instead, just send an IPI around to all overloaded CPUs.
- *
- * The rq->rt.push_flags holds the status of the IPI that is going around.
- * A run queue can only send out a single IPI at a time. The possible flags
- * for rq->rt.push_flags are:
- *
- *    (None or zero):		No IPI is going around for the current rq
- *    RT_PUSH_IPI_EXECUTING:	An IPI for the rq is being passed around
- *    RT_PUSH_IPI_RESTART:	The priority of the running task for the rq
- *				has changed, and the IPI should restart
- *				circulating the overloaded CPUs again.
- *
- * rq->rt.push_cpu contains the CPU that is being sent the IPI. It is updated
- * before sending to the next CPU.
- *
- * Instead of having all CPUs that schedule a lower priority task send
- * an IPI to the same "first" CPU in the RT overload mask, they send it
- * to the next overloaded CPU after their own CPU. This helps distribute
- * the work when there's more than one overloaded CPU and multiple CPUs
- * scheduling in lower priority tasks.
- *
- * When a rq schedules a lower priority task than what was currently
- * running, the next CPU with overloaded RT tasks is examined first.
- * That is, if CPU 1 and 5 are overloaded, and CPU 3 schedules a lower
- * priority task, it will send an IPI first to CPU 5, then CPU 5 will
- * send to CPU 1 if it is still overloaded. CPU 1 will clear the
- * rq->rt.push_flags if RT_PUSH_IPI_RESTART is not set.
- *
- * The first CPU to notice IPI_RESTART is set, will clear that flag and then
- * send an IPI to the next overloaded CPU after the rq->cpu and not the next
- * CPU after push_cpu. That is, if CPU 1, 4 and 5 are overloaded when CPU 3
- * schedules a lower priority task, and the IPI_RESTART gets set while the
- * handling is being done on CPU 5, it will clear the flag and send it back to
- * CPU 4 instead of CPU 1.
- *
- * Note, the above logic can be disabled by turning off the sched_feature
- * RT_PUSH_IPI. Then the rq lock of the overloaded CPU will simply be
- * taken by the CPU requesting a pull and the waiting RT task will be pulled
- * by that CPU. This may be fine for machines with few CPUs.
- */
-static void tell_cpu_to_push(struct rq *rq)
+static inline void rto_start_unlock(atomic_t *v)
 {
-	int cpu;
+	atomic_set_release(v, 0);
+}
 
-	if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
-		raw_spin_lock(&rq->rt.push_lock);
-		/* Make sure it's still executing */
-		if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
-			/*
-			 * Tell the IPI to restart the loop as things have
-			 * changed since it started.
-			 */
-			rq->rt.push_flags |= RT_PUSH_IPI_RESTART;
-			raw_spin_unlock(&rq->rt.push_lock);
-			return;
-		}
-		raw_spin_unlock(&rq->rt.push_lock);
-	}
+static void tell_cpu_to_push(struct rq *rq)
+{
+	int cpu = -1;
 
-	/* When here, there's no IPI going around */
+	/* Keep the loop going if the IPI is currently active */
+	atomic_inc(&rq->rd->rto_loop_next);
 
-	rq->rt.push_cpu = rq->cpu;
-	cpu = find_next_push_cpu(rq);
-	if (cpu >= nr_cpu_ids)
+	/* Only one CPU can initiate a loop at a time */
+	if (!rto_start_trylock(&rq->rd->rto_loop_start))
 		return;
 
-	rq->rt.push_flags = RT_PUSH_IPI_EXECUTING;
+	raw_spin_lock(&rq->rd->rto_lock);
+
+	/*
+	 * The rto_cpu is updated under the lock, if it has a valid cpu
+	 * then the IPI is still running and will continue due to the
+	 * update to loop_next, and nothing needs to be done here.
+	 * Otherwise it is finishing up and an ipi needs to be sent.
+	 */
+	if (rq->rd->rto_cpu < 0)
+		cpu = rto_next_cpu(rq);
 
-	irq_work_queue_on(&rq->rt.push_work, cpu);
+	raw_spin_unlock(&rq->rd->rto_lock);
+
+	rto_start_unlock(&rq->rd->rto_loop_start);
+
+	if (cpu >= 0)
+		irq_work_queue_on(&rq->rd->rto_push_work, cpu);
 }
 
 /* Called from hardirq context */
-static void try_to_push_tasks(void *arg)
+void rto_push_irq_work_func(struct irq_work *work)
 {
-	struct rt_rq *rt_rq = arg;
-	struct rq *rq, *src_rq;
-	int this_cpu;
+	struct rq *rq;
 	int cpu;
 
-	this_cpu = rt_rq->push_cpu;
+	rq = this_rq();
 
-	/* Paranoid check */
-	BUG_ON(this_cpu != smp_processor_id());
-
-	rq = cpu_rq(this_cpu);
-	src_rq = rq_of_rt_rq(rt_rq);
-
-again:
+	/*
+	 * We do not need to grab the lock to check for has_pushable_tasks.
+	 * When it gets updated, a check is made if a push is possible.
+	 */
 	if (has_pushable_tasks(rq)) {
 		raw_spin_lock(&rq->lock);
-		push_rt_task(rq);
+		push_rt_tasks(rq);
 		raw_spin_unlock(&rq->lock);
 	}
 
-	/* Pass the IPI to the next rt overloaded queue */
-	raw_spin_lock(&rt_rq->push_lock);
-	/*
-	 * If the source queue changed since the IPI went out,
-	 * we need to restart the search from that CPU again.
-	 */
-	if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) {
-		rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART;
-		rt_rq->push_cpu = src_rq->cpu;
-	}
+	raw_spin_lock(&rq->rd->rto_lock);
 
-	cpu = find_next_push_cpu(src_rq);
+	/* Pass the IPI to the next rt overloaded queue */
+	cpu = rto_next_cpu(rq);
 
-	if (cpu >= nr_cpu_ids)
-		rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING;
-	raw_spin_unlock(&rt_rq->push_lock);
+	raw_spin_unlock(&rq->rd->rto_lock);
 
-	if (cpu >= nr_cpu_ids)
+	if (cpu < 0)
 		return;
 
-	/*
-	 * It is possible that a restart caused this CPU to be
-	 * chosen again. Don't bother with an IPI, just see if we
-	 * have more to push.
-	 */
-	if (unlikely(cpu == rq->cpu))
-		goto again;
-
 	/* Try the next RT overloaded CPU */
-	irq_work_queue_on(&rt_rq->push_work, cpu);
-}
-
-static void push_irq_work_func(struct irq_work *work)
-{
-	struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work);
-
-	try_to_push_tasks(rt_rq);
+	irq_work_queue_on(&rq->rd->rto_push_work, cpu);
 }
 #endif /* HAVE_RT_PUSH_IPI */
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3b448ba82225..45ab0bf564e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -227,7 +227,7 @@ struct dl_bw {
 static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
 
 static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
+void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw -= tsk_bw;
 	__dl_update(dl_b, (s32)tsk_bw / cpus);
@@ -256,7 +256,6 @@ extern int sched_dl_overflow(struct task_struct *p, int policy,
 extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
 extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
-extern void __dl_clear_params(struct task_struct *p);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int dl_task_can_attach(struct task_struct *p,
 			      const struct cpumask *cs_cpus_allowed);
@@ -419,6 +418,7 @@ struct cfs_bandwidth { };
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
+	unsigned long runnable_weight;
 	unsigned int nr_running, h_nr_running;
 
 	u64 exec_clock;
@@ -444,18 +444,22 @@ struct cfs_rq {
 	 * CFS load tracking
 	 */
 	struct sched_avg avg;
-	u64 runnable_load_sum;
-	unsigned long runnable_load_avg;
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	unsigned long tg_load_avg_contrib;
-	unsigned long propagate_avg;
-#endif
-	atomic_long_t removed_load_avg, removed_util_avg;
 #ifndef CONFIG_64BIT
 	u64 load_last_update_time_copy;
 #endif
+	struct {
+		raw_spinlock_t	lock ____cacheline_aligned;
+		int		nr;
+		unsigned long	load_avg;
+		unsigned long	util_avg;
+		unsigned long	runnable_sum;
+	} removed;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	unsigned long tg_load_avg_contrib;
+	long propagate;
+	long prop_runnable_sum;
+
 	/*
 	 *   h_load = weight * f(tg)
 	 *
@@ -502,7 +506,7 @@ static inline int rt_bandwidth_enabled(void)
 }
 
 /* RT IPI pull logic requires IRQ_WORK */
-#ifdef CONFIG_IRQ_WORK
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_SMP)
 # define HAVE_RT_PUSH_IPI
 #endif
 
@@ -524,12 +528,6 @@ struct rt_rq {
 	unsigned long rt_nr_total;
 	int overloaded;
 	struct plist_head pushable_tasks;
-#ifdef HAVE_RT_PUSH_IPI
-	int push_flags;
-	int push_cpu;
-	struct irq_work push_work;
-	raw_spinlock_t push_lock;
-#endif
 #endif /* CONFIG_SMP */
 	int rt_queued;
 
@@ -638,6 +636,19 @@ struct root_domain {
 	struct dl_bw dl_bw;
 	struct cpudl cpudl;
 
+#ifdef HAVE_RT_PUSH_IPI
+	/*
+	 * For IPI pull requests, loop across the rto_mask.
+	 */
+	struct irq_work rto_push_work;
+	raw_spinlock_t rto_lock;
+	/* These are only updated and read within rto_lock */
+	int rto_loop;
+	int rto_cpu;
+	/* These atomics are updated outside of a lock */
+	atomic_t rto_loop_next;
+	atomic_t rto_loop_start;
+#endif
 	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
@@ -655,6 +666,9 @@ extern void init_defrootdomain(void);
 extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
+#ifdef HAVE_RT_PUSH_IPI
+extern void rto_push_irq_work_func(struct irq_work *work);
+#endif
 #endif /* CONFIG_SMP */
 
 /*
@@ -1219,8 +1233,6 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 # define const_debug const
 #endif
 
-extern const_debug unsigned int sysctl_sched_features;
-
 #define SCHED_FEAT(name, enabled)	\
 	__SCHED_FEAT_##name ,
 
@@ -1232,6 +1244,13 @@ enum {
 #undef SCHED_FEAT
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
+
+/*
+ * To support run-time toggling of sched features, all the translation units
+ * (but core.c) reference the sysctl_sched_features defined in core.c.
+ */
+extern const_debug unsigned int sysctl_sched_features;
+
 #define SCHED_FEAT(name, enabled)					\
 static __always_inline bool static_branch_##name(struct static_key *key) \
 {									\
@@ -1239,13 +1258,27 @@ static __always_inline bool static_branch_##name(struct static_key *key) \
 }
 
 #include "features.h"
-
 #undef SCHED_FEAT
 
 extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
+
 #else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
+
+/*
+ * Each translation unit has its own copy of sysctl_sched_features to allow
+ * constants propagation at compile time and compiler optimization based on
+ * features default.
+ */
+#define SCHED_FEAT(name, enabled)	\
+	(1UL << __SCHED_FEAT_##name) * enabled |
+static const_debug __maybe_unused unsigned int sysctl_sched_features =
+#include "features.h"
+	0;
+#undef SCHED_FEAT
+
 #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
 extern struct static_key_false sched_numa_balancing;
@@ -1530,6 +1563,8 @@ extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
+extern void reweight_task(struct task_struct *p, int prio);
+
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 6798276d29af..034cbed7f88b 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -4,6 +4,7 @@
  */
 #include <linux/sched.h>
 #include <linux/mutex.h>
+#include <linux/sched/isolation.h>
 
 #include "sched.h"
 
@@ -269,6 +270,12 @@ static int init_rootdomain(struct root_domain *rd)
 	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_dlo_mask;
 
+#ifdef HAVE_RT_PUSH_IPI
+	rd->rto_cpu = -1;
+	raw_spin_lock_init(&rd->rto_lock);
+	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+#endif
+
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -464,21 +471,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	update_top_cache_domain(cpu);
 }
 
-/* Setup the mask of CPUs configured for isolated domains */
-static int __init isolated_cpu_setup(char *str)
-{
-	int ret;
-
-	alloc_bootmem_cpumask_var(&cpu_isolated_map);
-	ret = cpulist_parse(str, cpu_isolated_map);
-	if (ret) {
-		pr_err("sched: Error, all isolcpus= values must be between 0 and %u\n", nr_cpu_ids);
-		return 0;
-	}
-	return 1;
-}
-__setup("isolcpus=", isolated_cpu_setup);
-
 struct s_data {
 	struct sched_domain ** __percpu sd;
 	struct root_domain	*rd;
@@ -1158,6 +1150,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd->smt_gain = 1178; /* ~15% */
 
 	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 117;
 		sd->cache_nice_tries = 1;
 		sd->busy_idx = 2;
@@ -1332,6 +1325,10 @@ void sched_init_numa(void)
 	if (!sched_domains_numa_distance)
 		return;
 
+	/* Includes NUMA identity node at level 0. */
+	sched_domains_numa_distance[level++] = curr_distance;
+	sched_domains_numa_levels = level;
+
 	/*
 	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
 	 * unique distances in the node_distance() table.
@@ -1379,8 +1376,7 @@ void sched_init_numa(void)
 		return;
 
 	/*
-	 * 'level' contains the number of unique distances, excluding the
-	 * identity distance node_distance(i,i).
+	 * 'level' contains the number of unique distances
 	 *
 	 * The sched_domains_numa_distance[] array includes the actual distance
 	 * numbers.
@@ -1442,9 +1438,18 @@ void sched_init_numa(void)
 		tl[i] = sched_domain_topology[i];
 
 	/*
+	 * Add the NUMA identity distance, aka single NODE.
+	 */
+	tl[i++] = (struct sched_domain_topology_level){
+		.mask = sd_numa_mask,
+		.numa_level = 0,
+		SD_INIT_NAME(NODE)
+	};
+
+	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
-	for (j = 0; j < level; i++, j++) {
+	for (j = 1; j < level; i++, j++) {
 		tl[i] = (struct sched_domain_topology_level){
 			.mask = sd_numa_mask,
 			.sd_flags = cpu_numa_flags,
@@ -1774,7 +1779,7 @@ int sched_init_domains(const struct cpumask *cpu_map)
 	doms_cur = alloc_sched_domains(ndoms_cur);
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
-	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
+	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN));
 	err = build_sched_domains(doms_cur[0], NULL);
 	register_sched_domain_sysctl();
 
@@ -1857,7 +1862,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 		doms_new = alloc_sched_domains(1);
 		if (doms_new) {
 			n = 1;
-			cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+			cpumask_and(doms_new[0], cpu_active_mask,
+				    housekeeping_cpumask(HK_FLAG_DOMAIN));
 		}
 	} else {
 		n = ndoms_new;
@@ -1880,7 +1886,8 @@ match1:
 	if (!doms_new) {
 		n = 0;
 		doms_new = &fallback_doms;
-		cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+		cpumask_and(doms_new[0], cpu_active_mask,
+			    housekeeping_cpumask(HK_FLAG_DOMAIN));
 	}
 
 	/* Build new domains: */
author	Linus Torvalds <torvalds@linux-foundation.org>	2017-11-13 22:37:52 +0100
committer	Linus Torvalds <torvalds@linux-foundation.org>	2017-11-13 22:37:52 +0100
commit	3e2014637c50e5d6a77cd63d5db6c209fe29d1b1 (patch)
tree	a672ed603262aeddda4490056b27b09791d0cbbb /kernel/sched
parent	Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kerne... (diff)
parent	sched/core: Optimize sched_feat() for !CONFIG_SCHED_DEBUG builds (diff)
download	linux-3e2014637c50e5d6a77cd63d5db6c209fe29d1b1.tar.xz linux-3e2014637c50e5d6a77cd63d5db6c209fe29d1b1.zip