7 files changed, 489 insertions, 103 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 5a5cc33e4999..d42992bccdfa 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -426,9 +426,7 @@ struct root_domain {
          */
         cpumask_var_t rto_mask;
         atomic_t rto_count;
-#ifdef CONFIG_SMP
         struct cpupri cpupri;
-#endif
 };
 
 /*
@@ -437,7 +435,7 @@ struct root_domain {
  */
 static struct root_domain def_root_domain;
 
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * This is the main, per-CPU runqueue data structure.
@@ -488,11 +486,12 @@ struct rq {
          */
         unsigned long nr_uninterruptible;
 
-        struct task_struct *curr, *idle;
+        struct task_struct *curr, *idle, *stop;
         unsigned long next_balance;
         struct mm_struct *prev_mm;
 
         u64 clock;
+        u64 clock_task;
 
         atomic_t nr_iowait;
 
@@ -520,6 +519,10 @@ struct rq {
         u64 avg_idle;
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+        u64 prev_irq_time;
+#endif
+
         /* calc_load related fields */
         unsigned long calc_load_update;
         long calc_load_active;
@@ -643,10 +646,22 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
+static u64 irq_time_cpu(int cpu);
+static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+
 inline void update_rq_clock(struct rq *rq)
 {
-        if (!rq->skip_clock_update)
-                rq->clock = sched_clock_cpu(cpu_of(rq));
+        if (!rq->skip_clock_update) {
+                int cpu = cpu_of(rq);
+                u64 irq_time;
+
+                rq->clock = sched_clock_cpu(cpu);
+                irq_time = irq_time_cpu(cpu);
+                if (rq->clock - irq_time > rq->clock_task)
+                        rq->clock_task = rq->clock - irq_time;
+
+                sched_irq_time_avg_update(rq, irq_time);
+        }
 }
 
 /*
@@ -723,7 +738,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 size_t cnt, loff_t *ppos)
 {
         char buf[64];
-        char *cmp = buf;
+        char *cmp;
         int neg = 0;
         int i;
 
@@ -734,6 +749,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 return -EFAULT;
 
         buf[cnt] = 0;
+        cmp = strstrip(buf);
 
         if (strncmp(buf, "NO_", 3) == 0) {
                 neg = 1;
@@ -741,9 +757,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
         }
 
         for (i = 0; sched_feat_names[i]; i++) {
-                int len = strlen(sched_feat_names[i]);
-
-                if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+                if (strcmp(cmp, sched_feat_names[i]) == 0) {
                         if (neg)
                                 sysctl_sched_features &= ~(1UL << i);
                         else
@@ -1840,7 +1854,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 static const struct sched_class rt_sched_class;
 
-#define sched_class_highest (&rt_sched_class)
+#define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1858,12 +1872,6 @@ static void dec_nr_running(struct rq *rq)
 
 static void set_load_weight(struct task_struct *p)
 {
-        if (task_has_rt_policy(p)) {
-                p->se.load.weight = 0;
-                p->se.load.inv_weight = WMULT_CONST;
-                return;
-        }
-
         /*
          * SCHED_IDLE tasks get minimal weight:
          */
@@ -1917,13 +1925,132 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
         dec_nr_running(rq);
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value (or semi updated value on 32 bit) with a side effect of
+ * accounting a slice of irq time to wrong task when irq is in progress
+ * while we read rq->clock. That is a worthy compromise in place of having
+ * locks on each irq in account_system_time.
+ */
+static DEFINE_PER_CPU(u64, cpu_hardirq_time);
+static DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+        sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+        sched_clock_irqtime = 0;
+}
+
+static u64 irq_time_cpu(int cpu)
+{
+        if (!sched_clock_irqtime)
+                return 0;
+
+        return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+
+void account_system_vtime(struct task_struct *curr)
+{
+        unsigned long flags;
+        int cpu;
+        u64 now, delta;
+
+        if (!sched_clock_irqtime)
+                return;
+
+        local_irq_save(flags);
+
+        cpu = smp_processor_id();
+        now = sched_clock_cpu(cpu);
+        delta = now - per_cpu(irq_start_time, cpu);
+        per_cpu(irq_start_time, cpu) = now;
+        /*
+         * We do not account for softirq time from ksoftirqd here.
+         * We want to continue accounting softirq time to ksoftirqd thread
+         * in that case, so as not to confuse scheduler with a special task
+         * that do not consume any time, but still wants to run.
+         */
+        if (hardirq_count())
+                per_cpu(cpu_hardirq_time, cpu) += delta;
+        else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+                per_cpu(cpu_softirq_time, cpu) += delta;
+
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+{
+        if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
+                u64 delta_irq = curr_irq_time - rq->prev_irq_time;
+                rq->prev_irq_time = curr_irq_time;
+                sched_rt_avg_update(rq, delta_irq);
+        }
+}
+
+#else
+
+static u64 irq_time_cpu(int cpu)
+{
+        return 0;
+}
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
+
+#endif
+
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
 #endif
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+        struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+        if (stop) {
+                /*
+                 * Make it appear like a SCHED_FIFO task, its something
+                 * userspace knows about and won't get confused about.
+                 *
+                 * Also, it will make PI more or less work without too
+                 * much confusion -- but then, stop work should not
+                 * rely on PI working anyway.
+                 */
+                sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+                stop->sched_class = &stop_sched_class;
+        }
+
+        cpu_rq(cpu)->stop = stop;
+
+        if (old_stop) {
+                /*
+                 * Reset it back to a normal scheduling class so that
+                 * it can die in pieces.
+                 */
+                old_stop->sched_class = &rt_sched_class;
+        }
+}
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -2003,6 +2130,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         if (p->sched_class != &fair_sched_class)
                 return 0;
 
+        if (unlikely(p->policy == SCHED_IDLE))
+                return 0;
+
         /*
          * Buddy candidates are cache hot:
          */
@@ -2852,14 +2982,14 @@ context_switch(struct rq *rq, struct task_struct *prev,
          */
         arch_start_context_switch(prev);
 
-        if (likely(!mm)) {
+        if (!mm) {
                 next->active_mm = oldmm;
                 atomic_inc(&oldmm->mm_count);
                 enter_lazy_tlb(oldmm, next);
         } else
                 switch_mm(oldmm, mm, next);
 
-        if (likely(!prev->mm)) {
+        if (!prev->mm) {
                 prev->active_mm = NULL;
                 rq->prev_mm = oldmm;
         }
@@ -3248,7 +3378,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
 
         if (task_current(rq, p)) {
                 update_rq_clock(rq);
-                ns = rq->clock - p->se.exec_start;
+                ns = rq->clock_task - p->se.exec_start;
                 if ((s64)ns < 0)
                         ns = 0;
         }
@@ -3397,7 +3527,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         tmp = cputime_to_cputime64(cputime);
         if (hardirq_count() - hardirq_offset)
                 cpustat->irq = cputime64_add(cpustat->irq, tmp);
-        else if (softirq_count())
+        else if (in_serving_softirq())
                 cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
         else
                 cpustat->system = cputime64_add(cpustat->system, tmp);
@@ -3723,17 +3853,13 @@ pick_next_task(struct rq *rq)
                         return p;
         }
 
-        class = sched_class_highest;
-        for ( ; ; ) {
+        for_each_class(class) {
                 p = class->pick_next_task(rq);
                 if (p)
                         return p;
-                /*
-                 * Will never be NULL as the idle class always
-                 * returns a non-NULL p:
-                 */
-                class = class->next;
         }
+
+        BUG(); /* the idle class will always have a runnable task */
 }
 
 /*
@@ -4358,6 +4484,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
         rq = task_rq_lock(p, &flags);
 
+        trace_sched_pi_setprio(p, prio);
         oldprio = p->prio;
         prev_class = p->sched_class;
         on_rq = p->se.on_rq;
@@ -4661,6 +4788,15 @@ recheck:
          */
         rq = __task_rq_lock(p);
 
+        /*
+         * Changing the policy of the stop threads its a very bad idea
+         */
+        if (p == rq->stop) {
+                __task_rq_unlock(rq);
+                raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+                return -EINVAL;
+        }
+
 #ifdef CONFIG_RT_GROUP_SCHED
         if (user) {
                 /*
@@ -4893,7 +5029,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 
         cpuset_cpus_allowed(p, cpus_allowed);
         cpumask_and(new_mask, in_mask, cpus_allowed);
- again:
+again:
         retval = set_cpus_allowed_ptr(p, new_mask);
 
         if (!retval) {
@@ -6526,6 +6662,7 @@ struct s_data {
         cpumask_var_t           nodemask;
         cpumask_var_t           this_sibling_map;
         cpumask_var_t           this_core_map;
+        cpumask_var_t           this_book_map;
         cpumask_var_t           send_covered;
         cpumask_var_t           tmpmask;
         struct sched_group      **sched_group_nodes;
@@ -6537,6 +6674,7 @@ enum s_alloc {
         sa_rootdomain,
         sa_tmpmask,
         sa_send_covered,
+        sa_this_book_map,
         sa_this_core_map,
         sa_this_sibling_map,
         sa_nodemask,
@@ -6572,31 +6710,48 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
                   struct sched_group **sg, struct cpumask *mask)
 {
         int group;
-
+#ifdef CONFIG_SCHED_SMT
         cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
         group = cpumask_first(mask);
+#else
+        group = cpu;
+#endif
         if (sg)
                 *sg = &per_cpu(sched_group_core, group).sg;
         return group;
 }
-#elif defined(CONFIG_SCHED_MC)
+#endif /* CONFIG_SCHED_MC */
+
+/*
+ * book sched-domains:
+ */
+#ifdef CONFIG_SCHED_BOOK
+static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
 static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-                  struct sched_group **sg, struct cpumask *unused)
+cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+                  struct sched_group **sg, struct cpumask *mask)
 {
+        int group = cpu;
+#ifdef CONFIG_SCHED_MC
+        cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+        cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#endif
         if (sg)
-                *sg = &per_cpu(sched_group_core, cpu).sg;
-        return cpu;
+                *sg = &per_cpu(sched_group_book, group).sg;
+        return group;
 }
-#endif
+#endif /* CONFIG_SCHED_BOOK */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
@@ -6606,7 +6761,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
                   struct sched_group **sg, struct cpumask *mask)
 {
         int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_BOOK
+        cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_MC)
         cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
         group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -6867,6 +7025,9 @@ SD_INIT_FUNC(CPU)
 #ifdef CONFIG_SCHED_MC
  SD_INIT_FUNC(MC)
 #endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
 
 static int default_relax_domain_level = -1;
 
@@ -6916,6 +7077,8 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
                 free_cpumask_var(d->tmpmask); /* fall through */
         case sa_send_covered:
                 free_cpumask_var(d->send_covered); /* fall through */
+        case sa_this_book_map:
+                free_cpumask_var(d->this_book_map); /* fall through */
         case sa_this_core_map:
                 free_cpumask_var(d->this_core_map); /* fall through */
         case sa_this_sibling_map:
@@ -6962,8 +7125,10 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
                 return sa_nodemask;
         if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
                 return sa_this_sibling_map;
-        if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+        if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
                 return sa_this_core_map;
+        if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+                return sa_this_book_map;
         if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
                 return sa_send_covered;
         d->rd = alloc_rootdomain();
@@ -7021,6 +7186,23 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
         return sd;
 }
 
+static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+        const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+        struct sched_domain *parent, int i)
+{
+        struct sched_domain *sd = parent;
+#ifdef CONFIG_SCHED_BOOK
+        sd = &per_cpu(book_domains, i).sd;
+        SD_INIT(sd, BOOK);
+        set_domain_attribute(sd, attr);
+        cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+        sd->parent = parent;
+        parent->child = sd;
+        cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+#endif
+        return sd;
+}
+
 static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
         const struct cpumask *cpu_map, struct sched_domain_attr *attr,
         struct sched_domain *parent, int i)
@@ -7078,6 +7260,15 @@ static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
                                                 d->send_covered, d->tmpmask);
                 break;
 #endif
+#ifdef CONFIG_SCHED_BOOK
+        case SD_LV_BOOK: /* set up book groups */
+                cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+                if (cpu == cpumask_first(d->this_book_map))
+                        init_sched_build_groups(d->this_book_map, cpu_map,
+                                                &cpu_to_book_group,
+                                                d->send_covered, d->tmpmask);
+                break;
+#endif
         case SD_LV_CPU: /* set up physical groups */
                 cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
                 if (!cpumask_empty(d->nodemask))
@@ -7125,12 +7316,14 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 
                 sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
                 sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+                sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
                 sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
                 sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
         }
 
         for_each_cpu(i, cpu_map) {
                 build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+                build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
                 build_sched_groups(&d, SD_LV_MC, cpu_map, i);
         }
 
@@ -7161,6 +7354,12 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 init_sched_groups_power(i, sd);
         }
 #endif
+#ifdef CONFIG_SCHED_BOOK
+        for_each_cpu(i, cpu_map) {
+                sd = &per_cpu(book_domains, i).sd;
+                init_sched_groups_power(i, sd);
+        }
+#endif
 
         for_each_cpu(i, cpu_map) {
                 sd = &per_cpu(phys_domains, i).sd;
@@ -7186,6 +7385,8 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
                 sd = &per_cpu(core_domains, i).sd;
+#elif defined(CONFIG_SCHED_BOOK)
+                sd = &per_cpu(book_domains, i).sd;
 #else
                 sd = &per_cpu(phys_domains, i).sd;
 #endif
@@ -8090,9 +8291,9 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 
         return 1;
 
- err_free_rq:
+err_free_rq:
         kfree(cfs_rq);
- err:
+err:
         return 0;
 }
 
@@ -8180,9 +8381,9 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
         return 1;
 
- err_free_rq:
+err_free_rq:
         kfree(rt_rq);
- err:
+err:
         return 0;
 }
 
@@ -8540,7 +8741,7 @@ static int tg_set_bandwidth(struct task_group *tg,
                 raw_spin_unlock(&rt_rq->rt_runtime_lock);
         }
         raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- unlock:
+unlock:
         read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5f996d36ac5d..933f3d1b62ea 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,7 +25,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -52,7 +52,7 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 750000ULL;
 unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
@@ -519,7 +519,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *curr = cfs_rq->curr;
-        u64 now = rq_of(cfs_rq)->clock;
+        u64 now = rq_of(cfs_rq)->clock_task;
         unsigned long delta_exec;
 
         if (unlikely(!curr))
@@ -602,7 +602,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
         /*
          * We are starting a new run period:
          */
-        se->exec_start = rq_of(cfs_rq)->clock;
+        se->exec_start = rq_of(cfs_rq)->clock_task;
 }
 
 /**************************************************
@@ -1764,6 +1764,10 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
         set_task_cpu(p, this_cpu);
         activate_task(this_rq, p, 0);
         check_preempt_curr(this_rq, p, 0);
+
+        /* re-arm NEWIDLE balancing when moving tasks */
+        src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
+        this_rq->idle_stamp = 0;
 }
 
 /*
@@ -1798,7 +1802,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
          * 2) too many balance attempts have failed.
          */
 
-        tsk_cache_hot = task_hot(p, rq->clock, sd);
+        tsk_cache_hot = task_hot(p, rq->clock_task, sd);
         if (!tsk_cache_hot ||
                 sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
@@ -2030,12 +2034,14 @@ struct sd_lb_stats {
         unsigned long this_load;
         unsigned long this_load_per_task;
         unsigned long this_nr_running;
+        unsigned long this_has_capacity;
 
         /* Statistics of the busiest group */
         unsigned long max_load;
         unsigned long busiest_load_per_task;
         unsigned long busiest_nr_running;
         unsigned long busiest_group_capacity;
+        unsigned long busiest_has_capacity;
 
         int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2058,6 +2064,7 @@ struct sg_lb_stats {
         unsigned long sum_weighted_load; /* Weighted load of group's tasks */
         unsigned long group_capacity;
         int group_imb; /* Is there an imbalance in the group ? */
+        int group_has_capacity; /* Is there extra capacity in the group? */
 };
 
 /**
@@ -2268,7 +2275,13 @@ unsigned long scale_rt_power(int cpu)
         u64 total, available;
 
         total = sched_avg_period() + (rq->clock - rq->age_stamp);
-        available = total - rq->rt_avg;
+
+        if (unlikely(total < rq->rt_avg)) {
+                /* Ensures that power won't end up being negative */
+                available = 0;
+        } else {
+                available = total - rq->rt_avg;
+        }
 
         if (unlikely((s64)total < SCHED_LOAD_SCALE))
                 total = SCHED_LOAD_SCALE;
@@ -2378,7 +2391,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         int local_group, const struct cpumask *cpus,
                         int *balance, struct sg_lb_stats *sgs)
 {
-        unsigned long load, max_cpu_load, min_cpu_load;
+        unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
         int i;
         unsigned int balance_cpu = -1, first_idle_cpu = 0;
         unsigned long avg_load_per_task = 0;
@@ -2389,6 +2402,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         /* Tally up the load of all CPUs in the group */
         max_cpu_load = 0;
         min_cpu_load = ~0UL;
+        max_nr_running = 0;
 
         for_each_cpu_and(i, sched_group_cpus(group), cpus) {
                 struct rq *rq = cpu_rq(i);
@@ -2406,8 +2420,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         load = target_load(i, load_idx);
                 } else {
                         load = source_load(i, load_idx);
-                        if (load > max_cpu_load)
+                        if (load > max_cpu_load) {
                                 max_cpu_load = load;
+                                max_nr_running = rq->nr_running;
+                        }
                         if (min_cpu_load > load)
                                 min_cpu_load = load;
                 }
@@ -2447,13 +2463,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         if (sgs->sum_nr_running)
                 avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
                 sgs->group_imb = 1;
 
-        sgs->group_capacity =
-                DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+        sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
         if (!sgs->group_capacity)
                 sgs->group_capacity = fix_small_capacity(sd, group);
+
+        if (sgs->group_capacity > sgs->sum_nr_running)
+                sgs->group_has_capacity = 1;
 }
 
 /**
@@ -2542,9 +2560,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                 /*
                  * In case the child domain prefers tasks go to siblings
                  * first, lower the sg capacity to one so that we'll try
-                 * and move all the excess tasks away.
+                 * and move all the excess tasks away. We lower the capacity
+                 * of a group only if the local group has the capacity to fit
+                 * these excess tasks, i.e. nr_running < group_capacity. The
+                 * extra check prevents the case where you always pull from the
+                 * heaviest group when it is already under-utilized (possible
+                 * with a large weight task outweighs the tasks on the system).
                  */
-                if (prefer_sibling)
+                if (prefer_sibling && !local_group && sds->this_has_capacity)
                         sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
                 if (local_group) {
@@ -2552,12 +2575,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->this = sg;
                         sds->this_nr_running = sgs.sum_nr_running;
                         sds->this_load_per_task = sgs.sum_weighted_load;
+                        sds->this_has_capacity = sgs.group_has_capacity;
                 } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
                         sds->max_load = sgs.avg_load;
                         sds->busiest = sg;
                         sds->busiest_nr_running = sgs.sum_nr_running;
                         sds->busiest_group_capacity = sgs.group_capacity;
                         sds->busiest_load_per_task = sgs.sum_weighted_load;
+                        sds->busiest_has_capacity = sgs.group_has_capacity;
                         sds->group_imb = sgs.group_imb;
                 }
 
@@ -2754,6 +2779,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                 return fix_small_imbalance(sds, this_cpu, imbalance);
 
 }
+
 /******* find_busiest_group() helpers end here *********************/
 
 /**
@@ -2805,6 +2831,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * 4) This group is more busy than the avg busieness at this
          *    sched_domain.
          * 5) The imbalance is within the specified limit.
+         *
+         * Note: when doing newidle balance, if the local group has excess
+         * capacity (i.e. nr_running < group_capacity) and the busiest group
+         * does not have any capacity, we force a load balance to pull tasks
+         * to the local group. In this case, we skip past checks 3, 4 and 5.
          */
         if (!(*balance))
                 goto ret;
@@ -2816,6 +2847,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!sds.busiest || sds.busiest_nr_running == 0)
                 goto out_balanced;
 
+        /*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+        if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+                        !sds.busiest_has_capacity)
+                goto force_balance;
+
         if (sds.this_load >= sds.max_load)
                 goto out_balanced;
 
@@ -2827,6 +2863,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
                 goto out_balanced;
 
+force_balance:
         /* Looks like there is an imbalance. Compute it */
         calculate_imbalance(&sds, this_cpu, imbalance);
         return sds.busiest;
@@ -3031,7 +3068,14 @@ redo:
 
         if (!ld_moved) {
                 schedstat_inc(sd, lb_failed[idle]);
-                sd->nr_balance_failed++;
+                /*
+                 * Increment the failure counter only on periodic balance.
+                 * We do not want newidle balance, which can be very
+                 * frequent, pollute the failure counter causing
+                 * excessive cache_hot migrations and active balances.
+                 */
+                if (idle != CPU_NEWLY_IDLE)
+                        sd->nr_balance_failed++;
 
                 if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
                                         this_cpu)) {
@@ -3153,10 +3197,8 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
                         next_balance = sd->last_balance + interval;
-                if (pulled_task) {
-                        this_rq->idle_stamp = 0;
+                if (pulled_task)
                         break;
-                }
         }
 
         raw_spin_lock(&this_rq->lock);
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 83c66e8ad3ee..185f920ec1a2 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -61,3 +61,8 @@ SCHED_FEAT(ASYM_EFF_LOAD, 1)
  * release the lock. Decreases scheduling overhead.
  */
 SCHED_FEAT(OWNER_SPIN, 1)
+
+/*
+ * Decrement CPU power based on irq activity
+ */
+SCHED_FEAT(NONIRQ_POWER, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d10c80ebb67a..bea7d79f7e9c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -609,7 +609,7 @@ static void update_curr_rt(struct rq *rq)
         if (!task_has_rt_policy(curr))
                 return;
 
-        delta_exec = rq->clock - curr->se.exec_start;
+        delta_exec = rq->clock_task - curr->se.exec_start;
         if (unlikely((s64)delta_exec < 0))
                 delta_exec = 0;
 
@@ -618,7 +618,7 @@ static void update_curr_rt(struct rq *rq)
         curr->se.sum_exec_runtime += delta_exec;
         account_group_exec_runtime(curr, delta_exec);
 
-        curr->se.exec_start = rq->clock;
+        curr->se.exec_start = rq->clock_task;
         cpuacct_charge(curr, delta_exec);
 
         sched_rt_avg_update(rq, delta_exec);
@@ -960,18 +960,19 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
          * runqueue. Otherwise simply start this RT task
          * on its current runqueue.
          *
-         * We want to avoid overloading runqueues. Even if
-         * the RT task is of higher priority than the current RT task.
-         * RT tasks behave differently than other tasks. If
-         * one gets preempted, we try to push it off to another queue.
-         * So trying to keep a preempting RT task on the same
-         * cache hot CPU will force the running RT task to
-         * a cold CPU. So we waste all the cache for the lower
-         * RT task in hopes of saving some of a RT task
-         * that is just being woken and probably will have
-         * cold cache anyway.
+         * We want to avoid overloading runqueues. If the woken
+         * task is a higher priority, then it will stay on this CPU
+         * and the lower prio task should be moved to another CPU.
+         * Even though this will probably make the lower prio task
+         * lose its cache, we do not want to bounce a higher task
+         * around just because it gave up its CPU, perhaps for a
+         * lock?
+         *
+         * For equal prio tasks, we just let the scheduler sort it out.
          */
         if (unlikely(rt_task(rq->curr)) &&
+            (rq->curr->rt.nr_cpus_allowed < 2 ||
+             rq->curr->prio < p->prio) &&
             (p->rt.nr_cpus_allowed > 1)) {
                 int cpu = find_lowest_rq(p);
 
@@ -1074,7 +1075,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
         } while (rt_rq);
 
         p = rt_task_of(rt_se);
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         return p;
 }
@@ -1139,7 +1140,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
         for_each_leaf_rt_rq(rt_rq, rq) {
                 array = &rt_rq->active;
                 idx = sched_find_first_bit(array->bitmap);
- next_idx:
+next_idx:
                 if (idx >= MAX_RT_PRIO)
                         continue;
                 if (next && next->prio < idx)
@@ -1315,7 +1316,7 @@ static int push_rt_task(struct rq *rq)
         if (!next_task)
                 return 0;
 
- retry:
+retry:
         if (unlikely(next_task == rq->curr)) {
                 WARN_ON(1);
                 return 0;
@@ -1463,7 +1464,7 @@ static int pull_rt_task(struct rq *this_rq)
                          * but possible)
                          */
                 }
- skip:
+skip:
                 double_unlock_balance(this_rq, src_rq);
         }
 
@@ -1491,7 +1492,10 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
         if (!task_running(rq, p) &&
             !test_tsk_need_resched(rq->curr) &&
             has_pushable_tasks(rq) &&
-            p->rt.nr_cpus_allowed > 1)
+            p->rt.nr_cpus_allowed > 1 &&
+            rt_task(rq->curr) &&
+            (rq->curr->rt.nr_cpus_allowed < 2 ||
+             rq->curr->prio < p->prio))
                 push_rt_tasks(rq);
 }
 
@@ -1709,7 +1713,7 @@ static void set_curr_task_rt(struct rq *rq)
 {
         struct task_struct *p = rq->curr;
 
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         /* The running task is never eligible for pushing */
         dequeue_pushable_task(rq, p);
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
new file mode 100644
index 000000000000..45bddc0c1048
--- /dev/null
+++ b/kernel/sched_stoptask.c
@@ -0,0 +1,108 @@
+/*
+ * stop-task scheduling class.
+ *
+ * The stop task is the highest priority task in the system, it preempts
+ * everything and will be preempted by nothing.
+ *
+ * See kernel/stop_machine.c
+ */
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_stop(struct rq *rq, struct task_struct *p,
+                    int sd_flag, int flags)
+{
+        return task_cpu(p); /* stop tasks as never migrate */
+}
+#endif /* CONFIG_SMP */
+
+static void
+check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+        resched_task(rq->curr); /* we preempt everything */
+}
+
+static struct task_struct *pick_next_task_stop(struct rq *rq)
+{
+        struct task_struct *stop = rq->stop;
+
+        if (stop && stop->state == TASK_RUNNING)
+                return stop;
+
+        return NULL;
+}
+
+static void
+enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void
+dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void yield_task_stop(struct rq *rq)
+{
+        BUG(); /* the stop task should never yield, its pointless. */
+}
+
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_stop(struct rq *rq)
+{
+}
+
+static void switched_to_stop(struct rq *rq, struct task_struct *p,
+                             int running)
+{
+        BUG(); /* its impossible to change to this class */
+}
+
+static void prio_changed_stop(struct rq *rq, struct task_struct *p,
+                              int oldprio, int running)
+{
+        BUG(); /* how!?, what priority? */
+}
+
+static unsigned int
+get_rr_interval_stop(struct rq *rq, struct task_struct *task)
+{
+        return 0;
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU stop tasks:
+ */
+static const struct sched_class stop_sched_class = {
+        .next                   = &rt_sched_class,
+
+        .enqueue_task           = enqueue_task_stop,
+        .dequeue_task           = dequeue_task_stop,
+        .yield_task             = yield_task_stop,
+
+        .check_preempt_curr     = check_preempt_curr_stop,
+
+        .pick_next_task         = pick_next_task_stop,
+        .put_prev_task          = put_prev_task_stop,
+
+#ifdef CONFIG_SMP
+        .select_task_rq         = select_task_rq_stop,
+#endif
+
+        .set_curr_task          = set_curr_task_stop,
+        .task_tick              = task_tick_stop,
+
+        .get_rr_interval        = get_rr_interval_stop,
+
+        .prio_changed           = prio_changed_stop,
+        .switched_to            = switched_to_stop,
+
+        /* no .task_new for stop tasks */
+};
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 07b4f1b1a73a..79ee8f1fc0e7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -77,11 +77,21 @@ void wakeup_softirqd(void)
 }
 
 /*
+ * preempt_count and SOFTIRQ_OFFSET usage:
+ * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
+ *   softirq processing.
+ * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ *   on local_bh_disable or local_bh_enable.
+ * This lets us distinguish between whether we are currently processing
+ * softirq and whether we just have bh disabled.
+ */
+
+/*
  * This one is for softirq.c-internal use,
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip)
+static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
         unsigned long flags;
 
@@ -95,32 +105,43 @@ static void __local_bh_disable(unsigned long ip)
          * We must manually increment preempt_count here and manually
          * call the trace_preempt_off later.
          */
-        preempt_count() += SOFTIRQ_OFFSET;
+        preempt_count() += cnt;
         /*
          * Were softirqs turned off above:
          */
-        if (softirq_count() == SOFTIRQ_OFFSET)
+        if (softirq_count() == cnt)
                 trace_softirqs_off(ip);
         raw_local_irq_restore(flags);
 
-        if (preempt_count() == SOFTIRQ_OFFSET)
+        if (preempt_count() == cnt)
                 trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 #else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip)
+static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
-        add_preempt_count(SOFTIRQ_OFFSET);
+        add_preempt_count(cnt);
         barrier();
 }
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
 void local_bh_disable(void)
 {
-        __local_bh_disable((unsigned long)__builtin_return_address(0));
+        __local_bh_disable((unsigned long)__builtin_return_address(0),
+                                SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(local_bh_disable);
 
+static void __local_bh_enable(unsigned int cnt)
+{
+        WARN_ON_ONCE(in_irq());
+        WARN_ON_ONCE(!irqs_disabled());
+
+        if (softirq_count() == cnt)
+                trace_softirqs_on((unsigned long)__builtin_return_address(0));
+        sub_preempt_count(cnt);
+}
+
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
@@ -128,12 +149,7 @@ EXPORT_SYMBOL(local_bh_disable);
  */
 void _local_bh_enable(void)
 {
-        WARN_ON_ONCE(in_irq());
-        WARN_ON_ONCE(!irqs_disabled());
-
-        if (softirq_count() == SOFTIRQ_OFFSET)
-                trace_softirqs_on((unsigned long)__builtin_return_address(0));
-        sub_preempt_count(SOFTIRQ_OFFSET);
+        __local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(_local_bh_enable);
@@ -147,13 +163,13 @@ static inline void _local_bh_enable_ip(unsigned long ip)
         /*
          * Are softirqs going to be turned on now:
          */
-        if (softirq_count() == SOFTIRQ_OFFSET)
+        if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
                 trace_softirqs_on(ip);
         /*
          * Keep preemption disabled until we are done with
          * softirq processing:
          */
-        sub_preempt_count(SOFTIRQ_OFFSET - 1);
+        sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
 
         if (unlikely(!in_interrupt() && local_softirq_pending()))
                 do_softirq();
@@ -198,7 +214,8 @@ asmlinkage void __do_softirq(void)
         pending = local_softirq_pending();
         account_system_vtime(current);
 
-        __local_bh_disable((unsigned long)__builtin_return_address(0));
+        __local_bh_disable((unsigned long)__builtin_return_address(0),
+                                SOFTIRQ_OFFSET);
         lockdep_softirq_enter();
 
         cpu = smp_processor_id();
@@ -245,7 +262,7 @@ restart:
         lockdep_softirq_exit();
 
         account_system_vtime(current);
-        _local_bh_enable();
+        __local_bh_enable(SOFTIRQ_OFFSET);
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ
@@ -279,10 +296,16 @@ void irq_enter(void)
 
         rcu_irq_enter();
         if (idle_cpu(cpu) && !in_interrupt()) {
-                __irq_enter();
+                /*
+                 * Prevent raise_softirq from needlessly waking up ksoftirqd
+                 * here, as softirq will be serviced on return from interrupt.
+                 */
+                local_bh_disable();
                 tick_check_idle(cpu);
-        } else
-                __irq_enter();
+                _local_bh_enable();
+        }
+
+        __irq_enter();
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -696,6 +719,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 {
         set_current_state(TASK_INTERRUPTIBLE);
 
+        current->flags |= PF_KSOFTIRQD;
         while (!kthread_should_stop()) {
                 preempt_disable();
                 if (!local_softirq_pending()) {
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 4372ccb25127..090c28812ce1 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -287,11 +287,12 @@ repeat:
         goto repeat;
 }
 
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
 /* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
 static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
                                            unsigned long action, void *hcpu)
 {
-        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
         unsigned int cpu = (unsigned long)hcpu;
         struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
         struct task_struct *p;
@@ -304,13 +305,13 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
                                    cpu);
                 if (IS_ERR(p))
                         return NOTIFY_BAD;
-                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
                 get_task_struct(p);
+                kthread_bind(p, cpu);
+                sched_set_stop_task(cpu, p);
                 stopper->thread = p;
                 break;
 
         case CPU_ONLINE:
-                kthread_bind(stopper->thread, cpu);
                 /* strictly unnecessary, as first user will wake it */
                 wake_up_process(stopper->thread);
                 /* mark enabled */
@@ -325,6 +326,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
         {
                 struct cpu_stop_work *work;
 
+                sched_set_stop_task(cpu, NULL);
                 /* kill the stopper */
                 kthread_stop(stopper->thread);
                 /* drain remaining works */