5 files changed, 136 insertions, 86 deletions

diff --git a/kernel/relay.c b/kernel/relay.c
index d080b9d161a7..4c035a8a248c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1066,7 +1066,7 @@ static int subbuf_splice_actor(struct file *in,
                                unsigned int flags,
                                int *nonpad_ret)
 {
-        unsigned int pidx, poff, total_len, subbuf_pages, ret;
+        unsigned int pidx, poff, total_len, subbuf_pages, nr_pages, ret;
         struct rchan_buf *rbuf = in->private_data;
         unsigned int subbuf_size = rbuf->chan->subbuf_size;
         uint64_t pos = (uint64_t) *ppos;
@@ -1097,8 +1097,9 @@ static int subbuf_splice_actor(struct file *in,
         subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
         pidx = (read_start / PAGE_SIZE) % subbuf_pages;
         poff = read_start & ~PAGE_MASK;
+        nr_pages = min_t(unsigned int, subbuf_pages, PIPE_BUFFERS);
 
-        for (total_len = 0; spd.nr_pages < subbuf_pages; spd.nr_pages++) {
+        for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
                 unsigned int this_len, this_end, private;
                 unsigned int cur_pos = read_start + total_len;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index d1ad69b270ca..3f7c5eb254e2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1396,6 +1396,12 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 {
         s64 delta;
 
+        /*
+         * Buddy candidates are cache hot:
+         */
+        if (&p->se == cfs_rq_of(&p->se)->next)
+                return 1;
+
         if (p->sched_class != &fair_sched_class)
                 return 0;
 
@@ -1855,10 +1861,11 @@ out_activate:
                 schedstat_inc(p, se.nr_wakeups_remote);
         update_rq_clock(rq);
         activate_task(rq, p, 1);
-        check_preempt_curr(rq, p);
         success = 1;
 
 out_running:
+        check_preempt_curr(rq, p);
+
         p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
@@ -1892,6 +1899,8 @@ static void __sched_fork(struct task_struct *p)
         p->se.exec_start                = 0;
         p->se.sum_exec_runtime          = 0;
         p->se.prev_sum_exec_runtime     = 0;
+        p->se.last_wakeup               = 0;
+        p->se.avg_overlap               = 0;
 
 #ifdef CONFIG_SCHEDSTATS
         p->se.wait_start                = 0;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4b5e24cf2f4a..ef358ba07683 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -288,6 +288,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
         PN(se.exec_start);
         PN(se.vruntime);
         PN(se.sum_exec_runtime);
+        PN(se.avg_overlap);
 
         nr_switches = p->nvcsw + p->nivcsw;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f2cc59080efa..b85cac4b5e25 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,13 +73,13 @@ unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -556,6 +556,21 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
         account_entity_enqueue(cfs_rq, se);
 }
 
+static void update_avg(u64 *avg, u64 sample)
+{
+        s64 diff = sample - *avg;
+        *avg += diff >> 3;
+}
+
+static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+        if (!se->last_wakeup)
+                return;
+
+        update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
+        se->last_wakeup = 0;
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -566,6 +581,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
         update_stats_dequeue(cfs_rq, se);
         if (sleep) {
+                update_avg_stats(cfs_rq, se);
 #ifdef CONFIG_SCHEDSTATS
                 if (entity_is_task(se)) {
                         struct task_struct *tsk = task_of(se);
@@ -980,96 +996,121 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
-static int select_task_rq_fair(struct task_struct *p, int sync)
+
+static const struct sched_class fair_sched_class;
+
+static int
+wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+            struct task_struct *p, int prev_cpu, int this_cpu, int sync,
+            int idx, unsigned long load, unsigned long this_load,
+            unsigned int imbalance)
 {
-        int cpu, this_cpu;
-        struct rq *rq;
-        struct sched_domain *sd, *this_sd = NULL;
-        int new_cpu;
+        struct task_struct *curr = this_rq->curr;
+        unsigned long tl = this_load;
+        unsigned long tl_per_task;
+
+        if (!(this_sd->flags & SD_WAKE_AFFINE))
+                return 0;
+
+        /*
+         * If the currently running task will sleep within
+         * a reasonable amount of time then attract this newly
+         * woken task:
+         */
+        if (sync && curr->sched_class == &fair_sched_class) {
+                if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+                                p->se.avg_overlap < sysctl_sched_migration_cost)
+                        return 1;
+        }
 
-        cpu      = task_cpu(p);
-        rq       = task_rq(p);
-        this_cpu = smp_processor_id();
-        new_cpu  = cpu;
+        schedstat_inc(p, se.nr_wakeups_affine_attempts);
+        tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-        if (cpu == this_cpu)
-                goto out_set_cpu;
+        /*
+         * If sync wakeup then subtract the (maximum possible)
+         * effect of the currently running task from the load
+         * of the current CPU:
+         */
+        if (sync)
+                tl -= current->se.load.weight;
+
+        if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+                        100*(tl + p->se.load.weight) <= imbalance*load) {
+                /*
+                 * This domain has SD_WAKE_AFFINE and
+                 * p is cache cold in this domain, and
+                 * there is no bad imbalance.
+                 */
+                schedstat_inc(this_sd, ttwu_move_affine);
+                schedstat_inc(p, se.nr_wakeups_affine);
 
+                return 1;
+        }
+        return 0;
+}
+
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+        struct sched_domain *sd, *this_sd = NULL;
+        int prev_cpu, this_cpu, new_cpu;
+        unsigned long load, this_load;
+        struct rq *rq, *this_rq;
+        unsigned int imbalance;
+        int idx;
+
+        prev_cpu        = task_cpu(p);
+        rq              = task_rq(p);
+        this_cpu        = smp_processor_id();
+        this_rq         = cpu_rq(this_cpu);
+        new_cpu         = prev_cpu;
+
+        /*
+         * 'this_sd' is the first domain that both
+         * this_cpu and prev_cpu are present in:
+         */
         for_each_domain(this_cpu, sd) {
-                if (cpu_isset(cpu, sd->span)) {
+                if (cpu_isset(prev_cpu, sd->span)) {
                         this_sd = sd;
                         break;
                 }
         }
 
         if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
-                goto out_set_cpu;
+                goto out;
 
         /*
          * Check for affine wakeup and passive balancing possibilities.
          */
-        if (this_sd) {
-                int idx = this_sd->wake_idx;
-                unsigned int imbalance;
-                unsigned long load, this_load;
-
-                imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
-                load = source_load(cpu, idx);
-                this_load = target_load(this_cpu, idx);
-
-                new_cpu = this_cpu; /* Wake to this CPU if we can */
-
-                if (this_sd->flags & SD_WAKE_AFFINE) {
-                        unsigned long tl = this_load;
-                        unsigned long tl_per_task;
-
-                        /*
-                         * Attract cache-cold tasks on sync wakeups:
-                         */
-                        if (sync && !task_hot(p, rq->clock, this_sd))
-                                goto out_set_cpu;
-
-                        schedstat_inc(p, se.nr_wakeups_affine_attempts);
-                        tl_per_task = cpu_avg_load_per_task(this_cpu);
-
-                        /*
-                         * If sync wakeup then subtract the (maximum possible)
-                         * effect of the currently running task from the load
-                         * of the current CPU:
-                         */
-                        if (sync)
-                                tl -= current->se.load.weight;
-
-                        if ((tl <= load &&
-                                tl + target_load(cpu, idx) <= tl_per_task) ||
-                               100*(tl + p->se.load.weight) <= imbalance*load) {
-                                /*
-                                 * This domain has SD_WAKE_AFFINE and
-                                 * p is cache cold in this domain, and
-                                 * there is no bad imbalance.
-                                 */
-                                schedstat_inc(this_sd, ttwu_move_affine);
-                                schedstat_inc(p, se.nr_wakeups_affine);
-                                goto out_set_cpu;
-                        }
-                }
+        if (!this_sd)
+                goto out;
 
-                /*
-                 * Start passive balancing when half the imbalance_pct
-                 * limit is reached.
-                 */
-                if (this_sd->flags & SD_WAKE_BALANCE) {
-                        if (imbalance*this_load <= 100*load) {
-                                schedstat_inc(this_sd, ttwu_move_balance);
-                                schedstat_inc(p, se.nr_wakeups_passive);
-                                goto out_set_cpu;
-                        }
+        idx = this_sd->wake_idx;
+
+        imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+        load = source_load(prev_cpu, idx);
+        this_load = target_load(this_cpu, idx);
+
+        if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+                                     load, this_load, imbalance))
+                return this_cpu;
+
+        if (prev_cpu == this_cpu)
+                goto out;
+
+        /*
+         * Start passive balancing when half the imbalance_pct
+         * limit is reached.
+         */
+        if (this_sd->flags & SD_WAKE_BALANCE) {
+                if (imbalance*this_load <= 100*load) {
+                        schedstat_inc(this_sd, ttwu_move_balance);
+                        schedstat_inc(p, se.nr_wakeups_passive);
+                        return this_cpu;
                 }
         }
 
-        new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
+out:
         return wake_idle(new_cpu, p);
 }
 #endif /* CONFIG_SMP */
@@ -1092,6 +1133,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
                 return;
         }
 
+        se->last_wakeup = se->sum_exec_runtime;
+        if (unlikely(se == pse))
+                return;
+
         cfs_rq_of(pse)->next = pse;
 
         /*
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 548c436a776b..278534bbca95 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -141,13 +141,8 @@ static void clocksource_watchdog(unsigned long data)
         }
 
         if (!list_empty(&watchdog_list)) {
-                /* Cycle through CPUs to check if the CPUs stay synchronized to
-                 * each other. */
-                int next_cpu = next_cpu(raw_smp_processor_id(), cpu_online_map);
-                if (next_cpu >= NR_CPUS)
-                        next_cpu = first_cpu(cpu_online_map);
-                watchdog_timer.expires += WATCHDOG_INTERVAL;
-                add_timer_on(&watchdog_timer, next_cpu);
+                __mod_timer(&watchdog_timer,
+                            watchdog_timer.expires + WATCHDOG_INTERVAL);
         }
         spin_unlock(&watchdog_lock);
 }
@@ -169,7 +164,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                 if (!started && watchdog) {
                         watchdog_last = watchdog->read();
                         watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
-                        add_timer_on(&watchdog_timer, first_cpu(cpu_online_map));
+                        add_timer(&watchdog_timer);
                 }
         } else {
                 if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
@@ -190,8 +185,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                                 watchdog_last = watchdog->read();
                                 watchdog_timer.expires =
                                         jiffies + WATCHDOG_INTERVAL;
-                                add_timer_on(&watchdog_timer,
-                                                first_cpu(cpu_online_map));
+                                add_timer(&watchdog_timer);
                         }
                 }
         }