4 files changed, 70 insertions, 350 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index f06950c8a6ce..dcd553cc4ee8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -174,41 +174,6 @@ struct task_group {
         struct sched_entity **se;
         /* runqueue "owned" by this group on each cpu */
         struct cfs_rq **cfs_rq;
-
-        /*
-         * shares assigned to a task group governs how much of cpu bandwidth
-         * is allocated to the group. The more shares a group has, the more is
-         * the cpu bandwidth allocated to it.
-         *
-         * For ex, lets say that there are three task groups, A, B and C which
-         * have been assigned shares 1000, 2000 and 3000 respectively. Then,
-         * cpu bandwidth allocated by the scheduler to task groups A, B and C
-         * should be:
-         *
-         *      Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
-         *      Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
-         *      Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
-         *
-         * The weight assigned to a task group's schedulable entities on every
-         * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
-         * group's shares. For ex: lets say that task group A has been
-         * assigned shares of 1000 and there are two CPUs in a system. Then,
-         *
-         *  tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
-         *
-         * Note: It's not necessary that each of a task's group schedulable
-         *       entity have the same weight on all CPUs. If the group
-         *       has 2 of its tasks on CPU0 and 1 task on CPU1, then a
-         *       better distribution of weight could be:
-         *
-         *      tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
-         *      tg_A->se[1]->load.weight = 1/2 * 2000 =  667
-         *
-         * rebalance_shares() is responsible for distributing the shares of a
-         * task groups like this among the group's schedulable entities across
-         * cpus.
-         *
-         */
         unsigned long shares;
 #endif
 
@@ -250,22 +215,12 @@ static DEFINE_SPINLOCK(task_group_lock);
 static DEFINE_MUTEX(doms_cur_mutex);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-/* kernel thread that runs rebalance_shares() periodically */
-static struct task_struct *lb_monitor_task;
-static int load_balance_monitor(void *unused);
-#endif
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares);
-
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
 #else
 # define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
 #endif
 
-#define MIN_GROUP_SHARES        2
-
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
 
@@ -1245,16 +1200,6 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 #endif
 
-static inline void inc_cpu_load(struct rq *rq, unsigned long load)
-{
-        update_load_add(&rq->load, load);
-}
-
-static inline void dec_cpu_load(struct rq *rq, unsigned long load)
-{
-        update_load_sub(&rq->load, load);
-}
-
 #ifdef CONFIG_SMP
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1272,14 +1217,26 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
 #define sched_class_highest (&rt_sched_class)
 
-static void inc_nr_running(struct rq *rq)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_add(&rq->load, p->se.load.weight);
+}
+
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_sub(&rq->load, p->se.load.weight);
+}
+
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running++;
+        inc_load(rq, p);
 }
 
-static void dec_nr_running(struct rq *rq)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running--;
+        dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -1371,7 +1328,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
                 rq->nr_uninterruptible--;
 
         enqueue_task(rq, p, wakeup);
-        inc_nr_running(rq);
+        inc_nr_running(p, rq);
 }
 
 /*
@@ -1383,7 +1340,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
                 rq->nr_uninterruptible++;
 
         dequeue_task(rq, p, sleep);
-        dec_nr_running(rq);
+        dec_nr_running(p, rq);
 }
 
 /**
@@ -2023,7 +1980,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                  * management (if any):
                  */
                 p->sched_class->task_new(rq, p);
-                inc_nr_running(rq);
+                inc_nr_running(p, rq);
         }
         check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP
@@ -4362,8 +4319,10 @@ void set_user_nice(struct task_struct *p, long nice)
                 goto out_unlock;
         }
         on_rq = p->se.on_rq;
-        if (on_rq)
+        if (on_rq) {
                 dequeue_task(rq, p, 0);
+                dec_load(rq, p);
+        }
 
         p->static_prio = NICE_TO_PRIO(nice);
         set_load_weight(p);
@@ -4373,6 +4332,7 @@ void set_user_nice(struct task_struct *p, long nice)
 
         if (on_rq) {
                 enqueue_task(rq, p, 0);
+                inc_load(rq, p);
                 /*
                  * If the task increased its priority or is running and
                  * lowered its priority, then reschedule its CPU:
@@ -7087,21 +7047,6 @@ void __init sched_init_smp(void)
         if (set_cpus_allowed(current, non_isolated_cpus) < 0)
                 BUG();
         sched_init_granularity();
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-        if (nr_cpu_ids == 1)
-                return;
-
-        lb_monitor_task = kthread_create(load_balance_monitor, NULL,
-                                         "group_balance");
-        if (!IS_ERR(lb_monitor_task)) {
-                lb_monitor_task->flags |= PF_NOFREEZE;
-                wake_up_process(lb_monitor_task);
-        } else {
-                printk(KERN_ERR "Could not create load balance monitor thread"
-                        "(error = %ld) \n", PTR_ERR(lb_monitor_task));
-        }
-#endif
 }
 #else
 void __init sched_init_smp(void)
@@ -7424,157 +7369,6 @@ void set_curr_task(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_GROUP_SCHED
 
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
-/*
- * distribute shares of all task groups among their schedulable entities,
- * to reflect load distribution across cpus.
- */
-static int rebalance_shares(struct sched_domain *sd, int this_cpu)
-{
-        struct cfs_rq *cfs_rq;
-        struct rq *rq = cpu_rq(this_cpu);
-        cpumask_t sdspan = sd->span;
-        int balanced = 1;
-
-        /* Walk thr' all the task groups that we have */
-        for_each_leaf_cfs_rq(rq, cfs_rq) {
-                int i;
-                unsigned long total_load = 0, total_shares;
-                struct task_group *tg = cfs_rq->tg;
-
-                /* Gather total task load of this group across cpus */
-                for_each_cpu_mask(i, sdspan)
-                        total_load += tg->cfs_rq[i]->load.weight;
-
-                /* Nothing to do if this group has no load */
-                if (!total_load)
-                        continue;
-
-                /*
-                 * tg->shares represents the number of cpu shares the task group
-                 * is eligible to hold on a single cpu. On N cpus, it is
-                 * eligible to hold (N * tg->shares) number of cpu shares.
-                 */
-                total_shares = tg->shares * cpus_weight(sdspan);
-
-                /*
-                 * redistribute total_shares across cpus as per the task load
-                 * distribution.
-                 */
-                for_each_cpu_mask(i, sdspan) {
-                        unsigned long local_load, local_shares;
-
-                        local_load = tg->cfs_rq[i]->load.weight;
-                        local_shares = (local_load * total_shares) / total_load;
-                        if (!local_shares)
-                                local_shares = MIN_GROUP_SHARES;
-                        if (local_shares == tg->se[i]->load.weight)
-                                continue;
-
-                        spin_lock_irq(&cpu_rq(i)->lock);
-                        set_se_shares(tg->se[i], local_shares);
-                        spin_unlock_irq(&cpu_rq(i)->lock);
-                        balanced = 0;
-                }
-        }
-
-        return balanced;
-}
-
-/*
- * How frequently should we rebalance_shares() across cpus?
- *
- * The more frequently we rebalance shares, the more accurate is the fairness
- * of cpu bandwidth distribution between task groups. However higher frequency
- * also implies increased scheduling overhead.
- *
- * sysctl_sched_min_bal_int_shares represents the minimum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * sysctl_sched_max_bal_int_shares represents the maximum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * These settings allows for the appropriate trade-off between accuracy of
- * fairness and the associated overhead.
- *
- */
-
-/* default: 8ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_min_bal_int_shares = 8;
-
-/* default: 128ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_max_bal_int_shares = 128;
-
-/* kernel thread that runs rebalance_shares() periodically */
-static int load_balance_monitor(void *unused)
-{
-        unsigned int timeout = sysctl_sched_min_bal_int_shares;
-        struct sched_param schedparm;
-        int ret;
-
-        /*
-         * We don't want this thread's execution to be limited by the shares
-         * assigned to default group (init_task_group). Hence make it run
-         * as a SCHED_RR RT task at the lowest priority.
-         */
-        schedparm.sched_priority = 1;
-        ret = sched_setscheduler(current, SCHED_RR, &schedparm);
-        if (ret)
-                printk(KERN_ERR "Couldn't set SCHED_RR policy for load balance"
-                                " monitor thread (error = %d) \n", ret);
-
-        while (!kthread_should_stop()) {
-                int i, cpu, balanced = 1;
-
-                /* Prevent cpus going down or coming up */
-                get_online_cpus();
-                /* lockout changes to doms_cur[] array */
-                lock_doms_cur();
-                /*
-                 * Enter a rcu read-side critical section to safely walk rq->sd
-                 * chain on various cpus and to walk task group list
-                 * (rq->leaf_cfs_rq_list) in rebalance_shares().
-                 */
-                rcu_read_lock();
-
-                for (i = 0; i < ndoms_cur; i++) {
-                        cpumask_t cpumap = doms_cur[i];
-                        struct sched_domain *sd = NULL, *sd_prev = NULL;
-
-                        cpu = first_cpu(cpumap);
-
-                        /* Find the highest domain at which to balance shares */
-                        for_each_domain(cpu, sd) {
-                                if (!(sd->flags & SD_LOAD_BALANCE))
-                                        continue;
-                                sd_prev = sd;
-                        }
-
-                        sd = sd_prev;
-                        /* sd == NULL? No load balance reqd in this domain */
-                        if (!sd)
-                                continue;
-
-                        balanced &= rebalance_shares(sd, cpu);
-                }
-
-                rcu_read_unlock();
-
-                unlock_doms_cur();
-                put_online_cpus();
-
-                if (!balanced)
-                        timeout = sysctl_sched_min_bal_int_shares;
-                else if (timeout < sysctl_sched_max_bal_int_shares)
-                        timeout *= 2;
-
-                msleep_interruptible(timeout);
-        }
-
-        return 0;
-}
-#endif  /* CONFIG_SMP */
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void free_fair_sched_group(struct task_group *tg)
 {
@@ -7841,29 +7635,25 @@ void sched_move_task(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-/* rq->lock to be locked by caller */
 static void set_se_shares(struct sched_entity *se, unsigned long shares)
 {
         struct cfs_rq *cfs_rq = se->cfs_rq;
         struct rq *rq = cfs_rq->rq;
         int on_rq;
 
-        if (!shares)
-                shares = MIN_GROUP_SHARES;
+        spin_lock_irq(&rq->lock);
 
         on_rq = se->on_rq;
-        if (on_rq) {
+        if (on_rq)
                 dequeue_entity(cfs_rq, se, 0);
-                dec_cpu_load(rq, se->load.weight);
-        }
 
         se->load.weight = shares;
         se->load.inv_weight = div64_64((1ULL<<32), shares);
 
-        if (on_rq) {
+        if (on_rq)
                 enqueue_entity(cfs_rq, se, 0);
-                inc_cpu_load(rq, se->load.weight);
-        }
+
+        spin_unlock_irq(&rq->lock);
 }
 
 static DEFINE_MUTEX(shares_mutex);
@@ -7873,18 +7663,18 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
         int i;
         unsigned long flags;
 
+        /*
+         * A weight of 0 or 1 can cause arithmetics problems.
+         * (The default weight is 1024 - so there's no practical
+         *  limitation from this.)
+         */
+        if (shares < 2)
+                shares = 2;
+
         mutex_lock(&shares_mutex);
         if (tg->shares == shares)
                 goto done;
 
-        if (shares < MIN_GROUP_SHARES)
-                shares = MIN_GROUP_SHARES;
-
-        /*
-         * Prevent any load balance activity (rebalance_shares,
-         * load_balance_fair) from referring to this group first,
-         * by taking it off the rq->leaf_cfs_rq_list on each cpu.
-         */
         spin_lock_irqsave(&task_group_lock, flags);
         for_each_possible_cpu(i)
                 unregister_fair_sched_group(tg, i);
@@ -7898,11 +7688,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
          * w/o tripping rebalance_share or load_balance_fair.
          */
         tg->shares = shares;
-        for_each_possible_cpu(i) {
-                spin_lock_irq(&cpu_rq(i)->lock);
+        for_each_possible_cpu(i)
                 set_se_shares(tg->se[i], shares);
-                spin_unlock_irq(&cpu_rq(i)->lock);
-        }
 
         /*
          * Enable load balance activity on this group, by inserting it back on
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c8e6492c5925..3df4d46994ca 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -727,8 +727,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
         return se->parent;
 }
 
-#define GROUP_IMBALANCE_PCT     20
-
 #else   /* CONFIG_FAIR_GROUP_SCHED */
 
 #define for_each_sched_entity(se) \
@@ -819,26 +817,15 @@ hrtick_start_fair(struct rq *rq, struct task_struct *p)
 static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 {
         struct cfs_rq *cfs_rq;
-        struct sched_entity *se = &p->se,
-                            *topse = NULL;      /* Highest schedulable entity */
-        int incload = 1;
+        struct sched_entity *se = &p->se;
 
         for_each_sched_entity(se) {
-                topse = se;
-                if (se->on_rq) {
-                        incload = 0;
+                if (se->on_rq)
                         break;
-                }
                 cfs_rq = cfs_rq_of(se);
                 enqueue_entity(cfs_rq, se, wakeup);
                 wakeup = 1;
         }
-        /* Increment cpu load if we just enqueued the first task of a group on
-         * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
-         * at the highest grouping level.
-         */
-        if (incload)
-                inc_cpu_load(rq, topse->load.weight);
 
         hrtick_start_fair(rq, rq->curr);
 }
@@ -851,28 +838,16 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 {
         struct cfs_rq *cfs_rq;
-        struct sched_entity *se = &p->se,
-                            *topse = NULL;      /* Highest schedulable entity */
-        int decload = 1;
+        struct sched_entity *se = &p->se;
 
         for_each_sched_entity(se) {
-                topse = se;
                 cfs_rq = cfs_rq_of(se);
                 dequeue_entity(cfs_rq, se, sleep);
                 /* Don't dequeue parent if it has other entities besides us */
-                if (cfs_rq->load.weight) {
-                        if (parent_entity(se))
-                                decload = 0;
+                if (cfs_rq->load.weight)
                         break;
-                }
                 sleep = 1;
         }
-        /* Decrement cpu load if we just dequeued the last task of a group on
-         * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
-         * at the highest grouping level.
-         */
-        if (decload)
-                dec_cpu_load(rq, topse->load.weight);
 
         hrtick_start_fair(rq, rq->curr);
 }
@@ -1186,6 +1161,25 @@ static struct task_struct *load_balance_next_fair(void *arg)
         return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
+{
+        struct sched_entity *curr;
+        struct task_struct *p;
+
+        if (!cfs_rq->nr_running || !first_fair(cfs_rq))
+                return MAX_PRIO;
+
+        curr = cfs_rq->curr;
+        if (!curr)
+                curr = __pick_next_entity(cfs_rq);
+
+        p = task_of(curr);
+
+        return p->prio;
+}
+#endif
+
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
                   unsigned long max_load_move,
@@ -1195,45 +1189,28 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
         struct cfs_rq *busy_cfs_rq;
         long rem_load_move = max_load_move;
         struct rq_iterator cfs_rq_iterator;
-        unsigned long load_moved;
 
         cfs_rq_iterator.start = load_balance_start_fair;
         cfs_rq_iterator.next = load_balance_next_fair;
 
         for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
 #ifdef CONFIG_FAIR_GROUP_SCHED
-                struct cfs_rq *this_cfs_rq = busy_cfs_rq->tg->cfs_rq[this_cpu];
-                unsigned long maxload, task_load, group_weight;
-                unsigned long thisload, per_task_load;
-                struct sched_entity *se = busy_cfs_rq->tg->se[busiest->cpu];
-
-                task_load = busy_cfs_rq->load.weight;
-                group_weight = se->load.weight;
+                struct cfs_rq *this_cfs_rq;
+                long imbalance;
+                unsigned long maxload;
 
-                /*
-                 * 'group_weight' is contributed by tasks of total weight
-                 * 'task_load'. To move 'rem_load_move' worth of weight only,
-                 * we need to move a maximum task load of:
-                 *
-                 *      maxload = (remload / group_weight) * task_load;
-                 */
-                maxload = (rem_load_move * task_load) / group_weight;
+                this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
 
-                if (!maxload || !task_load)
+                imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
+                /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
+                if (imbalance <= 0)
                         continue;
 
-                per_task_load = task_load / busy_cfs_rq->nr_running;
-                /*
-                 * balance_tasks will try to forcibly move atleast one task if
-                 * possible (because of SCHED_LOAD_SCALE_FUZZ). Avoid that if
-                 * maxload is less than GROUP_IMBALANCE_FUZZ% the per_task_load.
-                 */
-                 if (100 * maxload < GROUP_IMBALANCE_PCT * per_task_load)
-                        continue;
+                /* Don't pull more than imbalance/2 */
+                imbalance /= 2;
+                maxload = min(rem_load_move, imbalance);
 
-                /* Disable priority-based load balance */
-                *this_best_prio = 0;
-                thisload = this_cfs_rq->load.weight;
+                *this_best_prio = cfs_rq_best_prio(this_cfs_rq);
 #else
 # define maxload rem_load_move
 #endif
@@ -1242,33 +1219,11 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
                  * load_balance_[start|next]_fair iterators
                  */
                 cfs_rq_iterator.arg = busy_cfs_rq;
-                load_moved = balance_tasks(this_rq, this_cpu, busiest,
+                rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
                                                maxload, sd, idle, all_pinned,
                                                this_best_prio,
                                                &cfs_rq_iterator);
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-                /*
-                 * load_moved holds the task load that was moved. The
-                 * effective (group) weight moved would be:
-                 *      load_moved_eff = load_moved/task_load * group_weight;
-                 */
-                load_moved = (group_weight * load_moved) / task_load;
-
-                /* Adjust shares on both cpus to reflect load_moved */
-                group_weight -= load_moved;
-                set_se_shares(se, group_weight);
-
-                se = busy_cfs_rq->tg->se[this_cpu];
-                if (!thisload)
-                        group_weight = load_moved;
-                else
-                        group_weight = se->load.weight + load_moved;
-                set_se_shares(se, group_weight);
-#endif
-
-                rem_load_move -= load_moved;
-
                 if (rem_load_move <= 0)
                         break;
         }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index f54792b175b2..76e828517541 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -393,8 +393,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
          */
         for_each_sched_rt_entity(rt_se)
                 enqueue_rt_entity(rt_se);
-
-        inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -414,8 +412,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
                 if (rt_rq && rt_rq->rt_nr_running)
                         enqueue_rt_entity(rt_se);
         }
-
-        dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8b7e95411795..b2a2d6889bab 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -311,24 +311,6 @@ static struct ctl_table kern_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
-        {
-                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "sched_min_bal_int_shares",
-                .data           = &sysctl_sched_min_bal_int_shares,
-                .maxlen         = sizeof(unsigned int),
-                .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-        },
-        {
-                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "sched_max_bal_int_shares",
-                .data           = &sysctl_sched_max_bal_int_shares,
-                .maxlen         = sizeof(unsigned int),
-                .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-        },
-#endif
 #endif
         {
                 .ctl_name       = CTL_UNNUMBERED,