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
  ...

17 files changed, 1123 insertions, 706 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4657e2924ecb..f7efa7b4d825 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -57,7 +57,7 @@
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
 #include <linux/oom.h>
-
+#include <linux/sched/isolation.h>
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/mutex.h>
@@ -656,7 +656,6 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
 	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
-	cpumask_var_t non_isolated_cpus;  /* load balanced CPUs */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -666,10 +665,6 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	dattr = NULL;
 	csa = NULL;
 
-	if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
-		goto done;
-	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
-
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
 		ndoms = 1;
@@ -683,7 +678,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
 		cpumask_and(doms[0], top_cpuset.effective_cpus,
-				     non_isolated_cpus);
+			    housekeeping_cpumask(HK_FLAG_DOMAIN));
 
 		goto done;
 	}
@@ -707,7 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
-		      cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
+		      cpumask_intersects(cp->cpus_allowed,
+					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -789,7 +785,7 @@ restart:
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
-				cpumask_and(dp, dp, non_isolated_cpus);
+				cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN));
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -802,7 +798,6 @@ restart:
 	BUG_ON(nslot != ndoms);
 
 done:
-	free_cpumask_var(non_isolated_cpus);
 	kfree(csa);
 
 	/*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index dd4d0d390e5b..910405dc6e5c 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -29,6 +29,7 @@
 #include <linux/oom.h>
 #include <linux/sched/debug.h>
 #include <linux/smpboot.h>
+#include <linux/sched/isolation.h>
 #include <uapi/linux/sched/types.h>
 #include "../time/tick-internal.h"
 
@@ -2587,7 +2588,7 @@ static void rcu_bind_gp_kthread(void)
 
 	if (!tick_nohz_full_enabled())
 		return;
-	housekeeping_affine(current);
+	housekeeping_affine(current, HK_FLAG_RCU);
 }
 
 /* Record the current task on dyntick-idle entry. */
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 27694561f769..fbd56d6e575b 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -51,6 +51,7 @@
 #include <linux/kthread.h>
 #include <linux/tick.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/sched/isolation.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -714,7 +715,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	LIST_HEAD(rcu_tasks_holdouts);
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current);
+	housekeeping_affine(current, HK_FLAG_RCU);
 
 	/*
 	 * Each pass through the following loop makes one check for
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