Clean up duplicate includes in fs/ecryptfs/

[cascardo/linux.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 410b77a..a17b785 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,14 +25,12 @@
  * (default: 20ms, units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS are of variable length.
- * (to see the precise effective timeslice length of your workload,
- *  run vmstat and monitor the context-switches field)
+ * 'timeslice length' - timeslices in CFS are of variable length
+ * and have no persistent notion like in traditional, time-slice
+ * based scheduling concepts.
  *
- * On SMP systems the value of this is multiplied by the log2 of the
- * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
- * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
- * Targeted preemption latency for CPU-bound tasks:
+ * (to see the precise effective timeslice length of your workload,
+ *  run vmstat and monitor the context-switches (cs) field)
  */
 const_debug unsigned int sysctl_sched_latency = 20000000ULL;
 
@@ -76,6 +74,8 @@ const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
  */
 const_debug unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
 
+const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -381,15 +381,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
        se->exec_start = rq_of(cfs_rq)->clock;
 }
 
-/*
- * We are descheduling a task - update its stats:
- */
-static inline void
-update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-       se->exec_start = 0;
-}
-
 /**************************************************
  * Scheduling class queueing methods:
  */
@@ -485,9 +476,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
                vruntime += sched_vslice_add(cfs_rq, se);
 
        if (!initial) {
-               struct task_struct *p = container_of(se, struct task_struct, se);
-
-               if (sched_feat(NEW_FAIR_SLEEPERS) && p->policy != SCHED_BATCH)
+               if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) &&
+                               task_of(se)->policy != SCHED_BATCH)
                        vruntime -= sysctl_sched_latency;
 
                vruntime = max_t(s64, vruntime, se->vruntime);
@@ -527,6 +517,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
        update_stats_dequeue(cfs_rq, se);
        if (sleep) {
+               se->peer_preempt = 0;
 #ifdef CONFIG_SCHEDSTATS
                if (entity_is_task(se)) {
                        struct task_struct *tsk = task_of(se);
@@ -554,8 +545,10 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
        ideal_runtime = sched_slice(cfs_rq, curr);
        delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-       if (delta_exec > ideal_runtime)
+       if (delta_exec > ideal_runtime ||
+                       (sched_feat(PREEMPT_RESTRICT) && curr->peer_preempt))
                resched_task(rq_of(cfs_rq)->curr);
+       curr->peer_preempt = 0;
 }
 
 static void
@@ -609,8 +602,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
        if (prev->on_rq)
                update_curr(cfs_rq);
 
-       update_stats_curr_end(cfs_rq, prev);
-
        check_spread(cfs_rq, prev);
        if (prev->on_rq) {
                update_stats_wait_start(cfs_rq, prev);
@@ -627,7 +618,7 @@ static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
         */
        update_curr(cfs_rq);
 
-       if (cfs_rq->nr_running > 1)
+       if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
                check_preempt_tick(cfs_rq, curr);
 }
 
@@ -828,19 +819,31 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
                resched_task(curr);
                return;
        }
+       /*
+        * Batch tasks do not preempt (their preemption is driven by
+        * the tick):
+        */
+       if (unlikely(p->policy == SCHED_BATCH))
+               return;
 
-       while (!is_same_group(se, pse)) {
-               se = parent_entity(se);
-               pse = parent_entity(pse);
-       }
+       if (sched_feat(WAKEUP_PREEMPT)) {
+               while (!is_same_group(se, pse)) {
+                       se = parent_entity(se);
+                       pse = parent_entity(pse);
+               }
 
-       delta = se->vruntime - pse->vruntime;
-       gran = sysctl_sched_wakeup_granularity;
-       if (unlikely(se->load.weight != NICE_0_LOAD))
-               gran = calc_delta_fair(gran, &se->load);
+               delta = se->vruntime - pse->vruntime;
+               gran = sysctl_sched_wakeup_granularity;
+               if (unlikely(se->load.weight != NICE_0_LOAD))
+                       gran = calc_delta_fair(gran, &se->load);
 
-       if (delta > gran)
-               resched_task(curr);
+               if (delta > gran) {
+                       int now = !sched_feat(PREEMPT_RESTRICT);
+
+                       if (now || p->prio < curr->prio || !se->peer_preempt++)
+                               resched_task(curr);
+               }
+       }
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1033,6 +1036,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
        check_spread(cfs_rq, curr);
        __enqueue_entity(cfs_rq, se);
        account_entity_enqueue(cfs_rq, se);
+       se->peer_preempt = 0;
        resched_task(rq->curr);
 }