For one, the migration bits don't really make sense. We typically do not
call migration code local on both cpus, typically just one, but possibly
neither. That means you cannot actually update the relevant CPU state
from these sites anyway.

quoted

The scheduler hooks for utilization-based cpufreq operation deserve a
lot more debate I think. They could quite possibly have different
requirements than hooks which are chosen just to guarantee periodic
callbacks into sampling-based governors.

I'll repeat what Rafael said, the periodic callback nature is a
'temporary' hack, simply because current cpufreq depends on that.

The idea is to wane cpufreq off of that requirement and then drop that
part.

Very-much-not-signed-off-by: Peter Zijlstra
---
 kernel/sched/fair.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce24a456322..f3e95d8b65c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -2528,6 +2528,17 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */

+enum load_update_type {
+       LOAD_NONE,
+       LOAD_TICK,
+       LOAD_PUT,
+       LOAD_SET,
+       LOAD_ENQUEUE,
+       LOAD_DEQUEUE,
+       LOAD_ENQUEUE_MOVE = LOAD_ENQUEUE + 2,
+       LOAD_DEQUEUE_MOVE = LOAD_DEQUEUE + 2,
+};
+
 #ifdef CONFIG_SMP
 /* Precomputed fixed inverse multiplies for multiplication by y^n */
 static const u32 runnable_avg_yN_inv[] = {

@@ -2852,7 +2863,8 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 }

 /* Update task and its cfs_rq load average */
-static inline void update_load_avg(struct sched_entity *se, int update_tg)
+static inline void update_load_avg(struct sched_entity *se, int update_tg,
+                                  enum load_update_type type)
 {
        struct cfs_rq *cfs_rq = cfs_rq_of(se);
        u64 now = cfs_rq_clock_task(cfs_rq);

@@ -2940,7 +2952,7 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static inline void
 dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-       update_load_avg(se, 1);
+       update_load_avg(se, 1, LOAD_DEQUEUE);

        cfs_rq->runnable_load_avg =
                max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);

@@ -3006,7 +3018,8 @@ static int idle_balance(struct rq *this_rq);

 #else /* CONFIG_SMP */

-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline void update_load_avg(struct sched_entity *se, int update_tg,
+                                  enum load_update_type type) {}
 static inline void
 enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void

@@ -3327,7 +3340,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
                if (schedstat_enabled())
                        update_stats_wait_end(cfs_rq, se);
                __dequeue_entity(cfs_rq, se);
-               update_load_avg(se, 1);
+               update_load_avg(se, 1, LOAD_SET);
        }

        update_stats_curr_start(cfs_rq, se);

@@ -3431,7 +3444,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
                /* Put 'current' back into the tree. */
                __enqueue_entity(cfs_rq, prev);
                /* in !on_rq case, update occurred at dequeue */
-               update_load_avg(prev, 0);
+               update_load_avg(prev, 0, LOAD_PUT);
        }
        cfs_rq->curr = NULL;
 }

@@ -3447,7 +3460,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
        /*
         * Ensure that runnable average is periodically updated.
         */
-       update_load_avg(curr, 1);
+       update_load_avg(curr, 1, LOAD_TICK);
        update_cfs_shares(cfs_rq);

 #ifdef CONFIG_SCHED_HRTICK

@@ -4320,7 +4333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                if (cfs_rq_throttled(cfs_rq))
                        break;

-               update_load_avg(se, 1);
+               update_load_avg(se, 1, LOAD_ENQUEUE + (p->on_rq & TASK_ON_RQ_MIGRATING));
                update_cfs_shares(cfs_rq);
        }

@@ -4380,7 +4393,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                if (cfs_rq_throttled(cfs_rq))
                        break;

-               update_load_avg(se, 1);
+               update_load_avg(se, 1, LOAD_DEQUEUE + (p->on_rq & TASK_ON_RQ_MIGRATING));
                update_cfs_shares(cfs_rq);
        }

--

To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html