sched/fair: use util_est in LB and WU paths

When the scheduler looks at the CPU utilization, the current PELT value
for a CPU is returned straight away. In certain scenarios this can have
undesired side effects on task placement.

For example, since the task utilization is decayed at wakeup time, when
a long sleeping big task is enqueued it does not add immediately a
significant contribution to the target CPU.
As a result we generate a race condition where other tasks can be placed
on the same CPU while it is still considered relatively empty.

In order to reduce this kind of race conditions, this patch introduces the
required support to integrate the usage of the CPU's estimated utilization
in the wakeup path, via cpu_util_wake(), as well as in the load-balance
path, via cpu_util() which is used by update_sg_lb_stats().

The estimated utilization of a CPU is defined to be the maximum between
its PELT's utilization and the sum of the estimated utilization (at
previous dequeue time) of all the tasks currently RUNNABLE on that CPU.
This allows to properly represent the spare capacity of a CPU which, for
example, has just got a big task running since a long sleep period.

Change-Id: Iab14de2d509a15974c3176f091c0d5197cdbd081
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Paul Turner <pjt@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-pm@vger.kernel.org

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f05596eec7ccea9f017ee738dddacc7b6b314323..7de4797f152da6ea06ebfaa4a1fd99b7271c829e 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6920,7 +6920,8 @@ static inline unsigned long task_util(struct task_struct *p)
  */
 static int cpu_util_wake(int cpu, struct task_struct *p)
 {
-       unsigned long util, capacity;
+       struct cfs_rq *cfs_rq;
+       unsigned int util;
 
 #ifdef CONFIG_SCHED_WALT
        /*
@@ -6933,13 +6934,50 @@ static int cpu_util_wake(int cpu, struct task_struct *p)
                return cpu_util(cpu);
 #endif
        /* Task has no contribution or is new */
-       if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
+       if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
                return cpu_util(cpu);
 
-       capacity = capacity_orig_of(cpu);
-       util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0);
+       cfs_rq = &cpu_rq(cpu)->cfs;
+       util = READ_ONCE(cfs_rq->avg.util_avg);
+
+       /* Discount task's blocked util from CPU's util */
+       util -= min_t(unsigned int, util, task_util(p));
 
-       return (util >= capacity) ? capacity : util;
+       /*
+        * Covered cases:
+        *
+        * a) if *p is the only task sleeping on this CPU, then:
+        *      cpu_util (== task_util) > util_est (== 0)
+        *    and thus we return:
+        *      cpu_util_wake = (cpu_util - task_util) = 0
+        *
+        * b) if other tasks are SLEEPING on this CPU, which is now exiting
+        *    IDLE, then:
+        *      cpu_util >= task_util
+        *      cpu_util > util_est (== 0)
+        *    and thus we discount *p's blocked utilization to return:
+        *      cpu_util_wake = (cpu_util - task_util) >= 0
+        *
+        * c) if other tasks are RUNNABLE on that CPU and
+        *      util_est > cpu_util
+        *    then we use util_est since it returns a more restrictive
+        *    estimation of the spare capacity on that CPU, by just
+        *    considering the expected utilization of tasks already
+        *    runnable on that CPU.
+        *
+        * Cases a) and b) are covered by the above code, while case c) is
+        * covered by the following code when estimated utilization is
+        * enabled.
+        */
+       if (sched_feat(UTIL_EST))
+               util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+
+       /*
+        * Utilization (estimated) can exceed the CPU capacity, thus let's
+        * clamp to the maximum CPU capacity to ensure consistency with
+        * the cpu_util call.
+        */
+       return min_t(unsigned long, util, capacity_orig_of(cpu));
 }
 
 static inline int task_fits_capacity(struct task_struct *p, long capacity)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f41f94c00bc3cfa1dbbd9d9e04b7ddf4f75b45f1..dd9c84dd60563273b76e9b32dde7973883754d25 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1821,11 +1821,14 @@ extern bool walt_disabled;
        util_var = (typeof(util_var))sum;\
        }
 #endif
-/*
- * cpu_util returns the amount of capacity of a CPU that is used by CFS
- * tasks. The unit of the return value must be the one of capacity so we can
- * compare the utilization with the capacity of the CPU that is available for
- * CFS task (ie cpu_capacity).
+
+/**
+ * Amount of capacity of a CPU that is (estimated to be) used by CFS tasks
+ * @cpu: the CPU to get the utilization of
+ *
+ * The unit of the return value must be the one of capacity so we can compare
+ * the utilization with the capacity of the CPU that is available for CFS task
+ * (ie cpu_capacity).
  *
  * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
  * recent utilization of currently non-runnable tasks on a CPU. It represents
@@ -1836,6 +1839,14 @@ extern bool walt_disabled;
  * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
  * the running time on this CPU scaled by capacity_curr.
  *
+ * The estimated utilization of a CPU is defined to be the maximum between its
+ * cfs_rq.avg.util_avg and the sum of the estimated utilization of the tasks
+ * currently RUNNABLE on that CPU.
+ * This allows to properly represent the expected utilization of a CPU which
+ * has just got a big task running since a long sleep period. At the same time
+ * however it preserves the benefits of the "blocked utilization" in
+ * describing the potential for other tasks waking up on the same CPU.
+ *
  * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
  * higher than capacity_orig because of unfortunate rounding in
  * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
@@ -1846,22 +1857,30 @@ extern bool walt_disabled;
  * available capacity. We allow utilization to overshoot capacity_curr (but not
  * capacity_orig) as it useful for predicting the capacity required after task
  * migrations (scheduler-driven DVFS).
+ *
+ * Return: the (estimated) utilization for the specified CPU
  */
 static inline unsigned long __cpu_util(int cpu, int delta)
 {
-       unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
-       unsigned long capacity = capacity_orig_of(cpu);
+       struct cfs_rq *cfs_rq;
+       unsigned int util;
+
+       cfs_rq = &cpu_rq(cpu)->cfs;
+       util = READ_ONCE(cfs_rq->avg.util_avg);
 
 #ifdef CONFIG_SCHED_WALT
        if (!walt_disabled && sysctl_sched_use_walt_cpu_util) {
                walt_util(util, cpu_rq(cpu)->cumulative_runnable_avg);
        }
 #endif
+       if (sched_feat(UTIL_EST))
+               util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+
        delta += util;
        if (delta < 0)
                return 0;
 
-       return (delta >= capacity) ? capacity : delta;
+       return min_t(unsigned long, delta, capacity_orig_of(cpu));
 }
 
 static inline unsigned long cpu_util(int cpu)