#include <linux/mempolicy.h>
#include <linux/migrate.h>
#include <linux/task_work.h>
+#include <linux/module.h>
#include <trace/events/sched.h>
#include "sched.h"
+#include "tune.h"
+#include "walt.h"
/*
* Targeted preemption latency for CPU-bound tasks:
unsigned int sysctl_sched_latency = 6000000ULL;
unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+unsigned int sysctl_sched_sync_hint_enable = 1;
+unsigned int sysctl_sched_initial_task_util = 0;
+unsigned int sysctl_sched_cstate_aware = 1;
+
+#ifdef CONFIG_SCHED_WALT
+unsigned int sysctl_sched_use_walt_cpu_util = 1;
+unsigned int sysctl_sched_use_walt_task_util = 1;
+__read_mostly unsigned int sysctl_sched_walt_cpu_high_irqload =
+ (10 * NSEC_PER_MSEC);
+#endif
/*
* The initial- and re-scaling of tunables is configurable
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
+/*
+ * The margin used when comparing utilization with CPU capacity:
+ * util * margin < capacity * 1024
+ */
+unsigned int capacity_margin = 1280; /* ~20% */
+
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (!cfs_rq->on_list) {
+ struct rq *rq = rq_of(cfs_rq);
+ int cpu = cpu_of(rq);
/*
* Ensure we either appear before our parent (if already
* enqueued) or force our parent to appear after us when it is
- * enqueued. The fact that we always enqueue bottom-up
- * reduces this to two cases.
+ * enqueued. The fact that we always enqueue bottom-up
+ * reduces this to two cases and a special case for the root
+ * cfs_rq. Furthermore, it also means that we will always reset
+ * tmp_alone_branch either when the branch is connected
+ * to a tree or when we reach the beg of the tree
*/
if (cfs_rq->tg->parent &&
- cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
- list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
- } else {
+ cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+ /*
+ * If parent is already on the list, we add the child
+ * just before. Thanks to circular linked property of
+ * the list, this means to put the child at the tail
+ * of the list that starts by parent.
+ */
+ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+ &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+ /*
+ * The branch is now connected to its tree so we can
+ * reset tmp_alone_branch to the beginning of the
+ * list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else if (!cfs_rq->tg->parent) {
+ /*
+ * cfs rq without parent should be put
+ * at the tail of the list.
+ */
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
+ &rq->leaf_cfs_rq_list);
+ /*
+ * We have reach the beg of a tree so we can reset
+ * tmp_alone_branch to the beginning of the list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else {
+ /*
+ * The parent has not already been added so we want to
+ * make sure that it will be put after us.
+ * tmp_alone_branch points to the beg of the branch
+ * where we will add parent.
+ */
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+ rq->tmp_alone_branch);
+ /*
+ * update tmp_alone_branch to points to the new beg
+ * of the branch
+ */
+ rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
}
cfs_rq->on_list = 1;
}
#ifdef CONFIG_SMP
-static int select_idle_sibling(struct task_struct *p, int cpu);
+static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
/*
sa->period_contrib = 1023;
sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
- sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
- sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ /*
+ * In previous Android versions, we used to have:
+ * sa->util_avg = sched_freq() ?
+ * sysctl_sched_initial_task_util :
+ * scale_load_down(SCHED_LOAD_SCALE);
+ * sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ * However, that functionality has been moved to enqueue.
+ * It is unclear if we should restore this in enqueue.
+ */
+ /*
+ * At this point, util_avg won't be used in select_task_rq_fair anyway
+ */
+ sa->util_avg = 0;
+ sa->util_sum = 0;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+static void attach_entity_cfs_rq(struct sched_entity *se);
+
+/*
+ * With new tasks being created, their initial util_avgs are extrapolated
+ * based on the cfs_rq's current util_avg:
+ *
+ * util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
+ *
+ * However, in many cases, the above util_avg does not give a desired
+ * value. Moreover, the sum of the util_avgs may be divergent, such
+ * as when the series is a harmonic series.
+ *
+ * To solve this problem, we also cap the util_avg of successive tasks to
+ * only 1/2 of the left utilization budget:
+ *
+ * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *
+ * where n denotes the nth task.
+ *
+ * For example, a simplest series from the beginning would be like:
+ *
+ * task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
+ * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
+ *
+ * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
+ * if util_avg > util_avg_cap.
+ */
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ struct sched_avg *sa = &se->avg;
+ long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+
+ if (cap > 0) {
+ if (cfs_rq->avg.util_avg != 0) {
+ sa->util_avg = cfs_rq->avg.util_avg * se->load.weight;
+ sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+ if (sa->util_avg > cap)
+ sa->util_avg = cap;
+ } else {
+ sa->util_avg = cap;
+ }
+ /*
+ * If we wish to restore tuning via setting initial util,
+ * this is where we should do it.
+ */
+ sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ }
+
+ if (entity_is_task(se)) {
+ struct task_struct *p = task_of(se);
+ if (p->sched_class != &fair_sched_class) {
+ /*
+ * For !fair tasks do:
+ *
+ update_cfs_rq_load_avg(now, cfs_rq, false);
+ attach_entity_load_avg(cfs_rq, se);
+ switched_from_fair(rq, p);
+ *
+ * such that the next switched_to_fair() has the
+ * expected state.
+ */
+ se->avg.last_update_time = cfs_rq_clock_task(cfs_rq);
+ return;
+ }
+ }
+
+ attach_entity_cfs_rq(se);
+}
+
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
#else
void init_entity_runnable_average(struct sched_entity *se)
{
}
-#endif
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+}
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+{
+}
+#endif /* CONFIG_SMP */
/*
* Update the current task's runtime statistics.
* Call select_idle_sibling to maybe find a better one.
*/
if (!cur)
- env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
+ env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
+ env->dst_cpu);
assign:
assigned = true;
scale_freq = arch_scale_freq_capacity(NULL, cpu);
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+ trace_sched_contrib_scale_f(cpu, scale_freq, scale_cpu);
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->period_contrib;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * Updating tg's load_avg is necessary before update_cfs_share (which is done)
- * and effective_load (which is not done because it is too costly).
+/**
+ * update_tg_load_avg - update the tg's load avg
+ * @cfs_rq: the cfs_rq whose avg changed
+ * @force: update regardless of how small the difference
+ *
+ * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
+ * However, because tg->load_avg is a global value there are performance
+ * considerations.
+ *
+ * In order to avoid having to look at the other cfs_rq's, we use a
+ * differential update where we store the last value we propagated. This in
+ * turn allows skipping updates if the differential is 'small'.
+ *
+ * Updating tg's load_avg is necessary before update_cfs_share() (which is
+ * done) and effective_load() (which is not done because it is too costly).
*/
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
#endif /* CONFIG_FAIR_GROUP_SCHED */
+static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
+{
+ if (&this_rq()->cfs == cfs_rq) {
+ /*
+ * There are a few boundary cases this might miss but it should
+ * get called often enough that that should (hopefully) not be
+ * a real problem -- added to that it only calls on the local
+ * CPU, so if we enqueue remotely we'll miss an update, but
+ * the next tick/schedule should update.
+ *
+ * It will not get called when we go idle, because the idle
+ * thread is a different class (!fair), nor will the utilization
+ * number include things like RT tasks.
+ *
+ * As is, the util number is not freq-invariant (we'd have to
+ * implement arch_scale_freq_capacity() for that).
+ *
+ * See cpu_util().
+ */
+ cpufreq_update_util(rq_of(cfs_rq), 0);
+ }
+}
+
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
/*
WRITE_ONCE(*ptr, res); \
} while (0)
-/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
-static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+/**
+ * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
+ * @now: current time, as per cfs_rq_clock_task()
+ * @cfs_rq: cfs_rq to update
+ * @update_freq: should we call cfs_rq_util_change() or will the call do so
+ *
+ * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
+ * avg. The immediate corollary is that all (fair) tasks must be attached, see
+ * post_init_entity_util_avg().
+ *
+ * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
+ *
+ * Returns true if the load decayed or we removed load.
+ *
+ * Since both these conditions indicate a changed cfs_rq->avg.load we should
+ * call update_tg_load_avg() when this function returns true.
+ */
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
{
struct sched_avg *sa = &cfs_rq->avg;
- int decayed, removed = 0;
+ int decayed, removed = 0, removed_util = 0;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
+ removed_util = 1;
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
+ /* Trace CPU load, unless cfs_rq belongs to a non-root task_group */
+ if (cfs_rq == &rq_of(cfs_rq)->cfs)
+ trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
+
+ if (update_freq && (decayed || removed_util))
+ cfs_rq_util_change(cfs_rq);
+
return decayed || removed;
}
+/*
+ * Optional action to be done while updating the load average
+ */
+#define UPDATE_TG 0x1
+#define SKIP_AGE_LOAD 0x2
+
/* 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 flags)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 now = cfs_rq_clock_task(cfs_rq);
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
- __update_load_avg(now, cpu, &se->avg,
+ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
+ __update_load_avg(now, cpu, &se->avg,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
+ }
- if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
+ if (update_cfs_rq_load_avg(now, cfs_rq, true) && (flags & UPDATE_TG))
update_tg_load_avg(cfs_rq, 0);
+
+ if (entity_is_task(se))
+ trace_sched_load_avg_task(task_of(se), &se->avg);
}
+/**
+ * attach_entity_load_avg - attach this entity to its cfs_rq load avg
+ * @cfs_rq: cfs_rq to attach to
+ * @se: sched_entity to attach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (!sched_feat(ATTACH_AGE_LOAD))
- goto skip_aging;
-
- /*
- * If we got migrated (either between CPUs or between cgroups) we'll
- * have aged the average right before clearing @last_update_time.
- */
- if (se->avg.last_update_time) {
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, 0, 0, NULL);
-
- /*
- * XXX: we could have just aged the entire load away if we've been
- * absent from the fair class for too long.
- */
- }
-
-skip_aging:
se->avg.last_update_time = cfs_rq->avg.last_update_time;
cfs_rq->avg.load_avg += se->avg.load_avg;
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+
+ cfs_rq_util_change(cfs_rq);
}
+/**
+ * detach_entity_load_avg - detach this entity from its cfs_rq load avg
+ * @cfs_rq: cfs_rq to detach from
+ * @se: sched_entity to detach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+
+ cfs_rq_util_change(cfs_rq);
}
/* Add the load generated by se into cfs_rq's load average */
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct sched_avg *sa = &se->avg;
- u64 now = cfs_rq_clock_task(cfs_rq);
- int migrated, decayed;
-
- migrated = !sa->last_update_time;
- if (!migrated) {
- __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
- se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
- }
-
- decayed = update_cfs_rq_load_avg(now, cfs_rq);
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
- if (migrated)
+ if (!sa->last_update_time) {
attach_entity_load_avg(cfs_rq, se);
-
- if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
+ }
}
/* Remove the runnable load generated by se from cfs_rq's runnable load average */
static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- update_load_avg(se, 1);
-
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
}
-/*
- * Task first catches up with cfs_rq, and then subtract
- * itself from the cfs_rq (task must be off the queue now).
- */
-void remove_entity_load_avg(struct sched_entity *se)
-{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 last_update_time;
-
#ifndef CONFIG_64BIT
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
u64 last_update_time_copy;
+ u64 last_update_time;
do {
last_update_time_copy = cfs_rq->load_last_update_time_copy;
smp_rmb();
last_update_time = cfs_rq->avg.last_update_time;
} while (last_update_time != last_update_time_copy);
+
+ return last_update_time;
+}
#else
- last_update_time = cfs_rq->avg.last_update_time;
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->avg.last_update_time;
+}
#endif
+/*
+ * Synchronize entity load avg of dequeued entity without locking
+ * the previous rq.
+ */
+void sync_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 last_update_time;
+
+ last_update_time = cfs_rq_last_update_time(cfs_rq);
__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+}
+
+/*
+ * Task first catches up with cfs_rq, and then subtract
+ * itself from the cfs_rq (task must be off the queue now).
+ */
+void remove_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * Newly created task or never used group entity should not be removed
+ * from its (source) cfs_rq
+ */
+ if (se->avg.last_update_time == 0)
+ return;
+
+ sync_entity_load_avg(se);
atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
}
#else /* CONFIG_SMP */
-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+{
+ return 0;
+}
+
+#define UPDATE_TG 0x0
+#define SKIP_AGE_LOAD 0x0
+
+static inline void update_load_avg(struct sched_entity *se, int not_used1){}
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
}
trace_sched_stat_blocked(tsk, delta);
+ trace_sched_blocked_reason(tsk);
/*
* Blocking time is in units of nanosecs, so shift by
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
enqueue_entity_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
update_cfs_shares(cfs_rq);
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
dequeue_entity_load_avg(cfs_rq, se);
update_stats_dequeue(cfs_rq, se);
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
- update_load_avg(se, 1);
+ update_load_avg(se, UPDATE_TG);
}
update_stats_curr_start(cfs_rq, se);
/*
* Ensure that runnable average is periodically updated.
*/
- update_load_avg(curr, 1);
+ update_load_avg(curr, UPDATE_TG);
update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
}
#endif
+#ifdef CONFIG_SMP
+static bool cpu_overutilized(int cpu);
+unsigned long boosted_cpu_util(int cpu);
+#else
+#define boosted_cpu_util(cpu) cpu_util(cpu)
+#endif
+
+#ifdef CONFIG_SMP
+static void update_capacity_of(int cpu)
+{
+ unsigned long req_cap;
+
+ if (!sched_freq())
+ return;
+
+ /* Convert scale-invariant capacity to cpu. */
+ req_cap = boosted_cpu_util(cpu);
+ req_cap = req_cap * SCHED_CAPACITY_SCALE / capacity_orig_of(cpu);
+ set_cfs_cpu_capacity(cpu, true, req_cap);
+}
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+#ifdef CONFIG_SMP
+ int task_new = flags & ENQUEUE_WAKEUP_NEW;
+ int task_wakeup = flags & ENQUEUE_WAKEUP;
+#endif
+
+ /*
+ * If in_iowait is set, the code below may not trigger any cpufreq
+ * utilization updates, so do it here explicitly with the IOWAIT flag
+ * passed.
+ */
+ if (p->in_iowait)
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
for_each_sched_entity(se) {
if (se->on_rq)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
flags = ENQUEUE_WAKEUP;
}
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
+ update_load_avg(se, UPDATE_TG);
update_cfs_shares(cfs_rq);
}
if (!se)
add_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting.
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ *
+ * We do it also in the case where we enqueue a throttled task;
+ * we could argue that a throttled task should not boost a CPU,
+ * however:
+ * a) properly implementing CPU boosting considering throttled
+ * tasks will increase a lot the complexity of the solution
+ * b) it's not easy to quantify the benefits introduced by
+ * such a more complex solution.
+ * Thus, for the time being we go for the simple solution and boost
+ * also for throttled RQs.
+ */
+ schedtune_enqueue_task(p, cpu_of(rq));
+
+ if (!se) {
+ walt_inc_cumulative_runnable_avg(rq, p);
+ if (!task_new && !rq->rd->overutilized &&
+ cpu_overutilized(rq->cpu)) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+
+ /*
+ * We want to potentially trigger a freq switch
+ * request only for tasks that are waking up; this is
+ * because we get here also during load balancing, but
+ * in these cases it seems wise to trigger as single
+ * request after load balancing is done.
+ */
+ if (task_new || task_wakeup)
+ update_capacity_of(cpu_of(rq));
+ }
+
+#endif /* CONFIG_SMP */
hrtick_update(rq);
}
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
+ update_load_avg(se, UPDATE_TG);
update_cfs_shares(cfs_rq);
}
if (!se)
sub_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ */
+ schedtune_dequeue_task(p, cpu_of(rq));
+
+ if (!se) {
+ walt_dec_cumulative_runnable_avg(rq, p);
+
+ /*
+ * We want to potentially trigger a freq switch
+ * request only for tasks that are going to sleep;
+ * this is because we get here also during load
+ * balancing, but in these cases it seems wise to
+ * trigger as single request after load balancing is
+ * done.
+ */
+ if (task_sleep) {
+ if (rq->cfs.nr_running)
+ update_capacity_of(cpu_of(rq));
+ else if (sched_freq())
+ set_cfs_cpu_capacity(cpu_of(rq), false, 0);
+ }
+ }
+
+#endif /* CONFIG_SMP */
+
hrtick_update(rq);
}
return max(rq->cpu_load[type-1], total);
}
-static unsigned long capacity_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity;
-}
-
-static unsigned long capacity_orig_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity_orig;
-}
static unsigned long cpu_avg_load_per_task(int cpu)
{
#endif
/*
- * Detect M:N waker/wakee relationships via a switching-frequency heuristic.
- * A waker of many should wake a different task than the one last awakened
- * at a frequency roughly N times higher than one of its wakees. In order
- * to determine whether we should let the load spread vs consolodating to
- * shared cache, we look for a minimum 'flip' frequency of llc_size in one
- * partner, and a factor of lls_size higher frequency in the other. With
- * both conditions met, we can be relatively sure that the relationship is
- * non-monogamous, with partner count exceeding socket size. Waker/wakee
- * being client/server, worker/dispatcher, interrupt source or whatever is
- * irrelevant, spread criteria is apparent partner count exceeds socket size.
+ * Returns the current capacity of cpu after applying both
+ * cpu and freq scaling.
*/
-static int wake_wide(struct task_struct *p)
+unsigned long capacity_curr_of(int cpu)
{
- unsigned int master = current->wakee_flips;
- unsigned int slave = p->wakee_flips;
- int factor = this_cpu_read(sd_llc_size);
+ return cpu_rq(cpu)->cpu_capacity_orig *
+ arch_scale_freq_capacity(NULL, cpu)
+ >> SCHED_CAPACITY_SHIFT;
+}
- if (master < slave)
- swap(master, slave);
- if (slave < factor || master < slave * factor)
- return 0;
- return 1;
+static inline bool energy_aware(void)
+{
+ return sched_feat(ENERGY_AWARE);
}
-static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
+struct energy_env {
+ struct sched_group *sg_top;
+ struct sched_group *sg_cap;
+ int cap_idx;
+ int util_delta;
+ int src_cpu;
+ int dst_cpu;
+ int energy;
+ int payoff;
+ struct task_struct *task;
+ struct {
+ int before;
+ int after;
+ int delta;
+ int diff;
+ } nrg;
+ struct {
+ int before;
+ int after;
+ int delta;
+ } cap;
+};
+
+/*
+ * __cpu_norm_util() returns the cpu util relative to a specific capacity,
+ * i.e. it's busy ratio, in the range [0..SCHED_LOAD_SCALE] which is useful for
+ * energy calculations. Using the scale-invariant util returned by
+ * cpu_util() and approximating scale-invariant util by:
+ *
+ * util ~ (curr_freq/max_freq)*1024 * capacity_orig/1024 * running_time/time
+ *
+ * the normalized util can be found using the specific capacity.
+ *
+ * capacity = capacity_orig * curr_freq/max_freq
+ *
+ * norm_util = running_time/time ~ util/capacity
+ */
+static unsigned long __cpu_norm_util(int cpu, unsigned long capacity, int delta)
{
- s64 this_load, load;
- s64 this_eff_load, prev_eff_load;
- int idx, this_cpu, prev_cpu;
- struct task_group *tg;
- unsigned long weight;
- int balanced;
+ int util = __cpu_util(cpu, delta);
- idx = sd->wake_idx;
- this_cpu = smp_processor_id();
- prev_cpu = task_cpu(p);
- load = source_load(prev_cpu, idx);
- this_load = target_load(this_cpu, idx);
+ if (util >= capacity)
+ return SCHED_CAPACITY_SCALE;
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync) {
- tg = task_group(current);
- weight = current->se.avg.load_avg;
+ return (util << SCHED_CAPACITY_SHIFT)/capacity;
+}
- this_load += effective_load(tg, this_cpu, -weight, -weight);
+static int calc_util_delta(struct energy_env *eenv, int cpu)
+{
+ if (cpu == eenv->src_cpu)
+ return -eenv->util_delta;
+ if (cpu == eenv->dst_cpu)
+ return eenv->util_delta;
+ return 0;
+}
+
+static
+unsigned long group_max_util(struct energy_env *eenv)
+{
+ int i, delta;
+ unsigned long max_util = 0;
+
+ for_each_cpu(i, sched_group_cpus(eenv->sg_cap)) {
+ delta = calc_util_delta(eenv, i);
+ max_util = max(max_util, __cpu_util(i, delta));
+ }
+
+ return max_util;
+}
+
+/*
+ * group_norm_util() returns the approximated group util relative to it's
+ * current capacity (busy ratio) in the range [0..SCHED_LOAD_SCALE] for use in
+ * energy calculations. Since task executions may or may not overlap in time in
+ * the group the true normalized util is between max(cpu_norm_util(i)) and
+ * sum(cpu_norm_util(i)) when iterating over all cpus in the group, i. The
+ * latter is used as the estimate as it leads to a more pessimistic energy
+ * estimate (more busy).
+ */
+static unsigned
+long group_norm_util(struct energy_env *eenv, struct sched_group *sg)
+{
+ int i, delta;
+ unsigned long util_sum = 0;
+ unsigned long capacity = sg->sge->cap_states[eenv->cap_idx].cap;
+
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ delta = calc_util_delta(eenv, i);
+ util_sum += __cpu_norm_util(i, capacity, delta);
+ }
+
+ if (util_sum > SCHED_CAPACITY_SCALE)
+ return SCHED_CAPACITY_SCALE;
+ return util_sum;
+}
+
+static int find_new_capacity(struct energy_env *eenv,
+ const struct sched_group_energy * const sge)
+{
+ int idx;
+ unsigned long util = group_max_util(eenv);
+
+ for (idx = 0; idx < sge->nr_cap_states; idx++) {
+ if (sge->cap_states[idx].cap >= util)
+ break;
+ }
+
+ eenv->cap_idx = idx;
+
+ return idx;
+}
+
+static int group_idle_state(struct sched_group *sg)
+{
+ int i, state = INT_MAX;
+
+ /* Find the shallowest idle state in the sched group. */
+ for_each_cpu(i, sched_group_cpus(sg))
+ state = min(state, idle_get_state_idx(cpu_rq(i)));
+
+ /* Take non-cpuidle idling into account (active idle/arch_cpu_idle()) */
+ state++;
+
+ return state;
+}
+
+/*
+ * sched_group_energy(): Computes the absolute energy consumption of cpus
+ * belonging to the sched_group including shared resources shared only by
+ * members of the group. Iterates over all cpus in the hierarchy below the
+ * sched_group starting from the bottom working it's way up before going to
+ * the next cpu until all cpus are covered at all levels. The current
+ * implementation is likely to gather the same util statistics multiple times.
+ * This can probably be done in a faster but more complex way.
+ * Note: sched_group_energy() may fail when racing with sched_domain updates.
+ */
+static int sched_group_energy(struct energy_env *eenv)
+{
+ struct sched_domain *sd;
+ int cpu, total_energy = 0;
+ struct cpumask visit_cpus;
+ struct sched_group *sg;
+
+ WARN_ON(!eenv->sg_top->sge);
+
+ cpumask_copy(&visit_cpus, sched_group_cpus(eenv->sg_top));
+
+ while (!cpumask_empty(&visit_cpus)) {
+ struct sched_group *sg_shared_cap = NULL;
+
+ cpu = cpumask_first(&visit_cpus);
+
+ /*
+ * Is the group utilization affected by cpus outside this
+ * sched_group?
+ */
+ sd = rcu_dereference(per_cpu(sd_scs, cpu));
+
+ if (!sd)
+ /*
+ * We most probably raced with hotplug; returning a
+ * wrong energy estimation is better than entering an
+ * infinite loop.
+ */
+ return -EINVAL;
+
+ if (sd->parent)
+ sg_shared_cap = sd->parent->groups;
+
+ for_each_domain(cpu, sd) {
+ sg = sd->groups;
+
+ /* Has this sched_domain already been visited? */
+ if (sd->child && group_first_cpu(sg) != cpu)
+ break;
+
+ do {
+ unsigned long group_util;
+ int sg_busy_energy, sg_idle_energy;
+ int cap_idx, idle_idx;
+
+ if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
+ eenv->sg_cap = sg_shared_cap;
+ else
+ eenv->sg_cap = sg;
+
+ cap_idx = find_new_capacity(eenv, sg->sge);
+
+ if (sg->group_weight == 1) {
+ /* Remove capacity of src CPU (before task move) */
+ if (eenv->util_delta == 0 &&
+ cpumask_test_cpu(eenv->src_cpu, sched_group_cpus(sg))) {
+ eenv->cap.before = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta -= eenv->cap.before;
+ }
+ /* Add capacity of dst CPU (after task move) */
+ if (eenv->util_delta != 0 &&
+ cpumask_test_cpu(eenv->dst_cpu, sched_group_cpus(sg))) {
+ eenv->cap.after = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta += eenv->cap.after;
+ }
+ }
+
+ idle_idx = group_idle_state(sg);
+ group_util = group_norm_util(eenv, sg);
+ sg_busy_energy = (group_util * sg->sge->cap_states[cap_idx].power)
+ >> SCHED_CAPACITY_SHIFT;
+ sg_idle_energy = ((SCHED_LOAD_SCALE-group_util)
+ * sg->sge->idle_states[idle_idx].power)
+ >> SCHED_CAPACITY_SHIFT;
+
+ total_energy += sg_busy_energy + sg_idle_energy;
+
+ if (!sd->child)
+ cpumask_xor(&visit_cpus, &visit_cpus, sched_group_cpus(sg));
+
+ if (cpumask_equal(sched_group_cpus(sg), sched_group_cpus(eenv->sg_top)))
+ goto next_cpu;
+
+ } while (sg = sg->next, sg != sd->groups);
+ }
+next_cpu:
+ cpumask_clear_cpu(cpu, &visit_cpus);
+ continue;
+ }
+
+ eenv->energy = total_energy;
+ return 0;
+}
+
+static inline bool cpu_in_sg(struct sched_group *sg, int cpu)
+{
+ return cpu != -1 && cpumask_test_cpu(cpu, sched_group_cpus(sg));
+}
+
+/*
+ * energy_diff(): Estimate the energy impact of changing the utilization
+ * distribution. eenv specifies the change: utilisation amount, source, and
+ * destination cpu. Source or destination cpu may be -1 in which case the
+ * utilization is removed from or added to the system (e.g. task wake-up). If
+ * both are specified, the utilization is migrated.
+ */
+static inline int __energy_diff(struct energy_env *eenv)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int sd_cpu = -1, energy_before = 0, energy_after = 0;
+ int diff, margin;
+
+ struct energy_env eenv_before = {
+ .util_delta = 0,
+ .src_cpu = eenv->src_cpu,
+ .dst_cpu = eenv->dst_cpu,
+ .nrg = { 0, 0, 0, 0},
+ .cap = { 0, 0, 0 },
+ };
+
+ if (eenv->src_cpu == eenv->dst_cpu)
+ return 0;
+
+ sd_cpu = (eenv->src_cpu != -1) ? eenv->src_cpu : eenv->dst_cpu;
+ sd = rcu_dereference(per_cpu(sd_ea, sd_cpu));
+
+ if (!sd)
+ return 0; /* Error */
+
+ sg = sd->groups;
+
+ do {
+ if (cpu_in_sg(sg, eenv->src_cpu) || cpu_in_sg(sg, eenv->dst_cpu)) {
+ eenv_before.sg_top = eenv->sg_top = sg;
+
+ if (sched_group_energy(&eenv_before))
+ return 0; /* Invalid result abort */
+ energy_before += eenv_before.energy;
+
+ /* Keep track of SRC cpu (before) capacity */
+ eenv->cap.before = eenv_before.cap.before;
+ eenv->cap.delta = eenv_before.cap.delta;
+
+ if (sched_group_energy(eenv))
+ return 0; /* Invalid result abort */
+ energy_after += eenv->energy;
+ }
+ } while (sg = sg->next, sg != sd->groups);
+
+ eenv->nrg.before = energy_before;
+ eenv->nrg.after = energy_after;
+ eenv->nrg.diff = eenv->nrg.after - eenv->nrg.before;
+ eenv->payoff = 0;
+
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ eenv->nrg.delta, eenv->payoff);
+
+ /*
+ * Dead-zone margin preventing too many migrations.
+ */
+
+ margin = eenv->nrg.before >> 6; /* ~1.56% */
+
+ diff = eenv->nrg.after - eenv->nrg.before;
+
+ eenv->nrg.diff = (abs(diff) < margin) ? 0 : eenv->nrg.diff;
+
+ return eenv->nrg.diff;
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+struct target_nrg schedtune_target_nrg;
+
+/*
+ * System energy normalization
+ * Returns the normalized value, in the range [0..SCHED_LOAD_SCALE],
+ * corresponding to the specified energy variation.
+ */
+static inline int
+normalize_energy(int energy_diff)
+{
+ u32 normalized_nrg;
+#ifdef CONFIG_SCHED_DEBUG
+ int max_delta;
+
+ /* Check for boundaries */
+ max_delta = schedtune_target_nrg.max_power;
+ max_delta -= schedtune_target_nrg.min_power;
+ WARN_ON(abs(energy_diff) >= max_delta);
+#endif
+
+ /* Do scaling using positive numbers to increase the range */
+ normalized_nrg = (energy_diff < 0) ? -energy_diff : energy_diff;
+
+ /* Scale by energy magnitude */
+ normalized_nrg <<= SCHED_LOAD_SHIFT;
+
+ /* Normalize on max energy for target platform */
+ normalized_nrg = reciprocal_divide(
+ normalized_nrg, schedtune_target_nrg.rdiv);
+
+ return (energy_diff < 0) ? -normalized_nrg : normalized_nrg;
+}
+
+static inline int
+energy_diff(struct energy_env *eenv)
+{
+ int boost = schedtune_task_boost(eenv->task);
+ int nrg_delta;
+
+ /* Conpute "absolute" energy diff */
+ __energy_diff(eenv);
+
+ /* Return energy diff when boost margin is 0 */
+ if (boost == 0)
+ return eenv->nrg.diff;
+
+ /* Compute normalized energy diff */
+ nrg_delta = normalize_energy(eenv->nrg.diff);
+ eenv->nrg.delta = nrg_delta;
+
+ eenv->payoff = schedtune_accept_deltas(
+ eenv->nrg.delta,
+ eenv->cap.delta,
+ eenv->task);
+
+ /*
+ * When SchedTune is enabled, the energy_diff() function will return
+ * the computed energy payoff value. Since the energy_diff() return
+ * value is expected to be negative by its callers, this evaluation
+ * function return a negative value each time the evaluation return a
+ * positive payoff, which is the condition for the acceptance of
+ * a scheduling decision
+ */
+ return -eenv->payoff;
+}
+#else /* CONFIG_SCHED_TUNE */
+#define energy_diff(eenv) __energy_diff(eenv)
+#endif
+
+/*
+ * Detect M:N waker/wakee relationships via a switching-frequency heuristic.
+ * A waker of many should wake a different task than the one last awakened
+ * at a frequency roughly N times higher than one of its wakees. In order
+ * to determine whether we should let the load spread vs consolodating to
+ * shared cache, we look for a minimum 'flip' frequency of llc_size in one
+ * partner, and a factor of lls_size higher frequency in the other. With
+ * both conditions met, we can be relatively sure that the relationship is
+ * non-monogamous, with partner count exceeding socket size. Waker/wakee
+ * being client/server, worker/dispatcher, interrupt source or whatever is
+ * irrelevant, spread criteria is apparent partner count exceeds socket size.
+ */
+static int wake_wide(struct task_struct *p)
+{
+ unsigned int master = current->wakee_flips;
+ unsigned int slave = p->wakee_flips;
+ int factor = this_cpu_read(sd_llc_size);
+
+ if (master < slave)
+ swap(master, slave);
+ if (slave < factor || master < slave * factor)
+ return 0;
+ return 1;
+}
+
+static int wake_affine(struct sched_domain *sd, struct task_struct *p,
+ int prev_cpu, int sync)
+{
+ s64 this_load, load;
+ s64 this_eff_load, prev_eff_load;
+ int idx, this_cpu;
+ struct task_group *tg;
+ unsigned long weight;
+ int balanced;
+
+ idx = sd->wake_idx;
+ this_cpu = smp_processor_id();
+ load = source_load(prev_cpu, idx);
+ this_load = target_load(this_cpu, idx);
+
+ /*
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ if (sync) {
+ tg = task_group(current);
+ weight = current->se.avg.load_avg;
+
+ this_load += effective_load(tg, this_cpu, -weight, -weight);
load += effective_load(tg, prev_cpu, 0, -weight);
}
return 1;
}
+static inline unsigned long task_util(struct task_struct *p)
+{
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_task_util) {
+ unsigned long demand = p->ravg.demand;
+ return (demand << 10) / walt_ravg_window;
+ }
+#endif
+ return p->se.avg.util_avg;
+}
+
+static inline unsigned long boosted_task_util(struct task_struct *task);
+
+static inline bool __task_fits(struct task_struct *p, int cpu, int util)
+{
+ unsigned long capacity = capacity_of(cpu);
+
+ util += boosted_task_util(p);
+
+ return (capacity * 1024) > (util * capacity_margin);
+}
+
+static inline bool task_fits_max(struct task_struct *p, int cpu)
+{
+ unsigned long capacity = capacity_of(cpu);
+ unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+ if (capacity == max_capacity)
+ return true;
+
+ if (capacity * capacity_margin > max_capacity * 1024)
+ return true;
+
+ return __task_fits(p, cpu, 0);
+}
+
+static bool cpu_overutilized(int cpu)
+{
+ return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+static long
+schedtune_margin(unsigned long signal, long boost)
+{
+ long long margin = 0;
+
+ /*
+ * Signal proportional compensation (SPC)
+ *
+ * The Boost (B) value is used to compute a Margin (M) which is
+ * proportional to the complement of the original Signal (S):
+ * M = B * (SCHED_LOAD_SCALE - S), if B is positive
+ * M = B * S, if B is negative
+ * The obtained M could be used by the caller to "boost" S.
+ */
+ if (boost >= 0) {
+ margin = SCHED_LOAD_SCALE - signal;
+ margin *= boost;
+ } else
+ margin = -signal * boost;
+ /*
+ * Fast integer division by constant:
+ * Constant : (C) = 100
+ * Precision : 0.1% (P) = 0.1
+ * Reference : C * 100 / P (R) = 100000
+ *
+ * Thus:
+ * Shift bits : ceil(log(R,2)) (S) = 17
+ * Mult const : round(2^S/C) (M) = 1311
+ *
+ *
+ */
+ margin *= 1311;
+ margin >>= 17;
+
+ if (boost < 0)
+ margin *= -1;
+ return margin;
+}
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ int boost = schedtune_cpu_boost(cpu);
+
+ if (boost == 0)
+ return 0;
+
+ return schedtune_margin(util, boost);
+}
+
+static inline long
+schedtune_task_margin(struct task_struct *task)
+{
+ int boost = schedtune_task_boost(task);
+ unsigned long util;
+ long margin;
+
+ if (boost == 0)
+ return 0;
+
+ util = task_util(task);
+ margin = schedtune_margin(util, boost);
+
+ return margin;
+}
+
+#else /* CONFIG_SCHED_TUNE */
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ return 0;
+}
+
+static inline int
+schedtune_task_margin(struct task_struct *task)
+{
+ return 0;
+}
+
+#endif /* CONFIG_SCHED_TUNE */
+
+unsigned long
+boosted_cpu_util(int cpu)
+{
+ unsigned long util = cpu_util(cpu);
+ long margin = schedtune_cpu_margin(util, cpu);
+
+ trace_sched_boost_cpu(cpu, util, margin);
+
+ return util + margin;
+}
+
+static inline unsigned long
+boosted_task_util(struct task_struct *task)
+{
+ unsigned long util = task_util(task);
+ long margin = schedtune_task_margin(task);
+
+ trace_sched_boost_task(task, util, margin);
+
+ return util + margin;
+}
+
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+ return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+}
+
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
+ struct sched_group *most_spare_sg = NULL;
unsigned long min_load = ULONG_MAX, this_load = 0;
+ unsigned long most_spare = 0, this_spare = 0;
int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
load_idx = sd->wake_idx;
do {
- unsigned long load, avg_load;
+ unsigned long load, avg_load, spare_cap, max_spare_cap;
int local_group;
int i;
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
- /* Tally up the load of all CPUs in the group */
+ /*
+ * Tally up the load of all CPUs in the group and find
+ * the group containing the CPU with most spare capacity.
+ */
avg_load = 0;
+ max_spare_cap = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
load = target_load(i, load_idx);
avg_load += load;
+
+ spare_cap = capacity_spare_wake(i, p);
+
+ if (spare_cap > max_spare_cap)
+ max_spare_cap = spare_cap;
}
/* Adjust by relative CPU capacity of the group */
if (local_group) {
this_load = avg_load;
- } else if (avg_load < min_load) {
- min_load = avg_load;
- idlest = group;
+ this_spare = max_spare_cap;
+ } else {
+ if (avg_load < min_load) {
+ min_load = avg_load;
+ idlest = group;
+ }
+
+ if (most_spare < max_spare_cap) {
+ most_spare = max_spare_cap;
+ most_spare_sg = group;
+ }
}
} while (group = group->next, group != sd->groups);
+ /*
+ * The cross-over point between using spare capacity or least load
+ * is too conservative for high utilization tasks on partially
+ * utilized systems if we require spare_capacity > task_util(p),
+ * so we allow for some task stuffing by using
+ * spare_capacity > task_util(p)/2.
+ */
+ if (this_spare > task_util(p) / 2 &&
+ imbalance*this_spare > 100*most_spare)
+ return NULL;
+ else if (most_spare > task_util(p) / 2)
+ return most_spare_sg;
+
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
int shallowest_idle_cpu = -1;
int i;
+ /* Check if we have any choice: */
+ if (group->group_weight == 1)
+ return cpumask_first(sched_group_cpus(group));
+
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
if (idle_cpu(i)) {
/*
* Try and locate an idle CPU in the sched_domain.
*/
-static int select_idle_sibling(struct task_struct *p, int target)
+static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
struct sched_domain *sd;
struct sched_group *sg;
- int i = task_cpu(p);
+ int best_idle_cpu = -1;
+ int best_idle_cstate = INT_MAX;
+ unsigned long best_idle_capacity = ULONG_MAX;
- if (idle_cpu(target))
- return target;
+ if (!sysctl_sched_cstate_aware) {
+ if (idle_cpu(target))
+ return target;
- /*
- * If the prevous cpu is cache affine and idle, don't be stupid.
- */
- if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
- return i;
+ /*
+ * If the prevous cpu is cache affine and idle, don't be stupid.
+ */
+ if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+ return prev;
+ }
/*
* Otherwise, iterate the domains and find an elegible idle cpu.
for_each_lower_domain(sd) {
sg = sd->groups;
do {
+ int i;
if (!cpumask_intersects(sched_group_cpus(sg),
tsk_cpus_allowed(p)))
goto next;
- for_each_cpu(i, sched_group_cpus(sg)) {
- if (i == target || !idle_cpu(i))
- goto next;
- }
+ if (sysctl_sched_cstate_aware) {
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+ unsigned long new_usage = boosted_task_util(p);
+ unsigned long capacity_orig = capacity_orig_of(i);
+
+ if (new_usage > capacity_orig || !idle_cpu(i))
+ goto next;
+
+ if (i == target && new_usage <= capacity_curr_of(target))
+ return target;
+
+ if (idle_idx < best_idle_cstate &&
+ capacity_orig <= best_idle_capacity) {
+ best_idle_cpu = i;
+ best_idle_cstate = idle_idx;
+ best_idle_capacity = capacity_orig;
+ }
+ }
+ } else {
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ if (i == target || !idle_cpu(i))
+ goto next;
+ }
- target = cpumask_first_and(sched_group_cpus(sg),
+ target = cpumask_first_and(sched_group_cpus(sg),
tsk_cpus_allowed(p));
- goto done;
+ goto done;
+ }
next:
sg = sg->next;
} while (sg != sd->groups);
}
+
+ if (best_idle_cpu >= 0)
+ target = best_idle_cpu;
+
done:
return target;
}
+static int start_cpu(bool boosted)
+{
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+
+ RCU_LOCKDEP_WARN(rcu_read_lock_sched_held(),
+ "sched RCU must be held");
+
+ return boosted ? rd->max_cap_orig_cpu : rd->min_cap_orig_cpu;
+}
+
+static inline int find_best_target(struct task_struct *p, bool boosted, bool prefer_idle)
+{
+ int target_cpu = -1;
+ unsigned long target_util = prefer_idle ? ULONG_MAX : 0;
+ unsigned long backup_capacity = ULONG_MAX;
+ int best_idle_cpu = -1;
+ int best_idle_cstate = INT_MAX;
+ int backup_cpu = -1;
+ unsigned long min_util = boosted_task_util(p);
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int cpu = start_cpu(boosted);
+
+ if (cpu < 0)
+ return target_cpu;
+
+ sd = rcu_dereference(per_cpu(sd_ea, cpu));
+
+ if (!sd)
+ return target_cpu;
+
+ sg = sd->groups;
+
+ do {
+ int i;
+
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ unsigned long cur_capacity, new_util;
+
+ if (!cpu_online(i))
+ continue;
+
+ /*
+ * p's blocked utilization is still accounted for on prev_cpu
+ * so prev_cpu will receive a negative bias due to the double
+ * accounting. However, the blocked utilization may be zero.
+ */
+ new_util = cpu_util(i) + task_util(p);
+
+ /*
+ * Ensure minimum capacity to grant the required boost.
+ * The target CPU can be already at a capacity level higher
+ * than the one required to boost the task.
+ */
+ new_util = max(min_util, new_util);
+
+ if (new_util > capacity_orig_of(i))
+ continue;
+
+#ifdef CONFIG_SCHED_WALT
+ if (walt_cpu_high_irqload(i))
+ continue;
+#endif
+
+ /*
+ * Unconditionally favoring tasks that prefer idle cpus to
+ * improve latency.
+ */
+ if (idle_cpu(i) && prefer_idle)
+ return i;
+
+ cur_capacity = capacity_curr_of(i);
+
+ if (new_util < cur_capacity) {
+ if (cpu_rq(i)->nr_running) {
+ /*
+ * Find a target cpu with the lowest/highest
+ * utilization if prefer_idle/!prefer_idle.
+ */
+ if ((prefer_idle && target_util > new_util) ||
+ (!prefer_idle && target_util < new_util)) {
+ target_util = new_util;
+ target_cpu = i;
+ }
+ } else if (!prefer_idle) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+
+ if (best_idle_cpu < 0 ||
+ (sysctl_sched_cstate_aware &&
+ best_idle_cstate > idle_idx)) {
+ best_idle_cstate = idle_idx;
+ best_idle_cpu = i;
+ }
+ }
+ } else if (backup_capacity > cur_capacity) {
+ /* Find a backup cpu with least capacity. */
+ backup_capacity = cur_capacity;
+ backup_cpu = i;
+ }
+ }
+ } while (sg = sg->next, sg != sd->groups);
+
+ if (target_cpu < 0)
+ target_cpu = best_idle_cpu >= 0 ? best_idle_cpu : backup_cpu;
+
+ return target_cpu;
+}
+
/*
- * 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).
- *
- * 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
- * the amount of utilization of a CPU in the range [0..capacity_orig] where
- * capacity_orig is the cpu_capacity available at the highest frequency
- * (arch_scale_freq_capacity()).
- * The utilization of a CPU converges towards a sum equal to or less than the
- * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
- * the running time on this CPU scaled by capacity_curr.
- *
- * 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
- * the average stabilizes with the new running time. We need to check that the
- * utilization stays within the range of [0..capacity_orig] and cap it if
- * necessary. Without utilization capping, a group could be seen as overloaded
- * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
- * 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).
- */
-static int cpu_util(int cpu)
-{
- unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
- unsigned long capacity = capacity_orig_of(cpu);
+ * cpu_util_wake: Compute cpu utilization with any contributions from
+ * the waking task p removed.
+ */
+static int cpu_util_wake(int cpu, struct task_struct *p)
+{
+ unsigned long util, capacity;
+
+ /* Task has no contribution or is new */
+ if (cpu != task_cpu(p) || !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);
return (util >= capacity) ? capacity : util;
}
+/*
+ * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
+ * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
+ *
+ * In that case WAKE_AFFINE doesn't make sense and we'll let
+ * BALANCE_WAKE sort things out.
+ */
+static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
+{
+ long min_cap, max_cap;
+
+ min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
+ max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+ /* Minimum capacity is close to max, no need to abort wake_affine */
+ if (max_cap - min_cap < max_cap >> 3)
+ return 0;
+
+ /* Bring task utilization in sync with prev_cpu */
+ sync_entity_load_avg(&p->se);
+
+ return min_cap * 1024 < task_util(p) * capacity_margin;
+}
+
+static int select_energy_cpu_brute(struct task_struct *p, int prev_cpu, int sync)
+{
+ struct sched_domain *sd;
+ int target_cpu = prev_cpu, tmp_target;
+ bool boosted, prefer_idle;
+
+ if (sysctl_sched_sync_hint_enable && sync) {
+ int cpu = smp_processor_id();
+
+ if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+ return cpu;
+ }
+
+ rcu_read_lock();
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ boosted = schedtune_task_boost(p) > 0;
+ prefer_idle = schedtune_prefer_idle(p) > 0;
+#else
+ boosted = get_sysctl_sched_cfs_boost() > 0;
+ prefer_idle = 0;
+#endif
+
+ sd = rcu_dereference(per_cpu(sd_ea, prev_cpu));
+ /* Find a cpu with sufficient capacity */
+ tmp_target = find_best_target(p, boosted, prefer_idle);
+
+ if (!sd)
+ goto unlock;
+ if (tmp_target >= 0) {
+ target_cpu = tmp_target;
+ if ((boosted || prefer_idle) && idle_cpu(target_cpu))
+ goto unlock;
+ }
+
+ if (target_cpu != prev_cpu) {
+ struct energy_env eenv = {
+ .util_delta = task_util(p),
+ .src_cpu = prev_cpu,
+ .dst_cpu = target_cpu,
+ .task = p,
+ };
+
+ /* Not enough spare capacity on previous cpu */
+ if (cpu_overutilized(prev_cpu))
+ goto unlock;
+
+ if (energy_diff(&eenv) >= 0)
+ target_cpu = prev_cpu;
+ }
+
+unlock:
+ rcu_read_unlock();
+ return target_cpu;
+}
+
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
int sync = wake_flags & WF_SYNC;
if (sd_flag & SD_BALANCE_WAKE)
- want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+ want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
+ && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+
+ if (energy_aware() && !(cpu_rq(prev_cpu)->rd->overutilized))
+ return select_energy_cpu_brute(p, prev_cpu, sync);
rcu_read_lock();
for_each_domain(cpu, tmp) {
if (affine_sd) {
sd = NULL; /* Prefer wake_affine over balance flags */
- if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
+ if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
new_cpu = cpu;
}
if (!sd) {
if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
- new_cpu = select_idle_sibling(p, new_cpu);
+ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
} else while (sd) {
struct sched_group *group;
{
remove_entity_load_avg(&p->se);
}
+#else
+#define task_fits_max(p, cpu) true
#endif /* CONFIG_SMP */
static unsigned long
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
simple:
cfs_rq = &rq->cfs;
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
idle:
+ rq->misfit_task = 0;
/*
* This is OK, because current is on_cpu, which avoids it being picked
* for load-balance and preemption/IRQs are still disabled avoiding
enum fbq_type { regular, remote, all };
+enum group_type {
+ group_other = 0,
+ group_misfit_task,
+ group_imbalanced,
+ group_overloaded,
+};
+
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
#define LBF_DST_PINNED 0x04
int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
+ unsigned int src_grp_nr_running;
/* The set of CPUs under consideration for load-balancing */
struct cpumask *cpus;
unsigned int loop_max;
enum fbq_type fbq_type;
+ enum group_type busiest_group_type;
struct list_head tasks;
};
deactivate_task(env->src_rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
+ double_lock_balance(env->src_rq, env->dst_rq);
set_task_cpu(p, env->dst_cpu);
+ double_unlock_balance(env->src_rq, env->dst_rq);
}
/*
{
raw_spin_lock(&rq->lock);
attach_task(rq, p);
+ /*
+ * We want to potentially raise target_cpu's OPP.
+ */
+ update_capacity_of(cpu_of(rq));
raw_spin_unlock(&rq->lock);
}
attach_task(env->dst_rq, p);
}
+ /*
+ * We want to potentially raise env.dst_cpu's OPP.
+ */
+ update_capacity_of(env->dst_cpu);
+
raw_spin_unlock(&env->dst_rq->lock);
}
if (throttled_hierarchy(cfs_rq))
continue;
- if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
+ if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq,
+ true))
update_tg_load_avg(cfs_rq, 0);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/********** Helpers for find_busiest_group ************************/
-enum group_type {
- group_other = 0,
- group_imbalanced,
- group_overloaded,
-};
-
/*
* sg_lb_stats - stats of a sched_group required for load_balancing
*/
unsigned int group_weight;
enum group_type group_type;
int group_no_capacity;
+ int group_misfit_task; /* A cpu has a task too big for its capacity */
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
used = div_u64(avg, total);
+ /*
+ * deadline bandwidth is defined at system level so we must
+ * weight this bandwidth with the max capacity of the system.
+ * As a reminder, avg_bw is 20bits width and
+ * scale_cpu_capacity is 10 bits width
+ */
+ used += div_u64(rq->dl.avg_bw, arch_scale_cpu_capacity(NULL, cpu));
+
if (likely(used < SCHED_CAPACITY_SCALE))
return SCHED_CAPACITY_SCALE - used;
return 1;
}
+void init_max_cpu_capacity(struct max_cpu_capacity *mcc)
+{
+ raw_spin_lock_init(&mcc->lock);
+ mcc->val = 0;
+ mcc->cpu = -1;
+}
+
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
+ struct max_cpu_capacity *mcc;
+ unsigned long max_capacity;
+ int max_cap_cpu;
+ unsigned long flags;
cpu_rq(cpu)->cpu_capacity_orig = capacity;
+ mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;
+
+ raw_spin_lock_irqsave(&mcc->lock, flags);
+ max_capacity = mcc->val;
+ max_cap_cpu = mcc->cpu;
+
+ if ((max_capacity > capacity && max_cap_cpu == cpu) ||
+ (max_capacity < capacity)) {
+ mcc->val = capacity;
+ mcc->cpu = cpu;
+#ifdef CONFIG_SCHED_DEBUG
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+ printk_deferred(KERN_INFO "CPU%d: update max cpu_capacity %lu\n",
+ cpu, capacity);
+ goto skip_unlock;
+#endif
+ }
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+
+skip_unlock: __attribute__ ((unused));
capacity *= scale_rt_capacity(cpu);
capacity >>= SCHED_CAPACITY_SHIFT;
cpu_rq(cpu)->cpu_capacity = capacity;
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = capacity;
+ sdg->sgc->min_capacity = capacity;
}
void update_group_capacity(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long capacity;
+ unsigned long capacity, max_capacity, min_capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
}
capacity = 0;
+ max_capacity = 0;
+ min_capacity = ULONG_MAX;
if (child->flags & SD_OVERLAP) {
/*
*/
if (unlikely(!rq->sd)) {
capacity += capacity_of(cpu);
- continue;
+ } else {
+ sgc = rq->sd->groups->sgc;
+ capacity += sgc->capacity;
}
- sgc = rq->sd->groups->sgc;
- capacity += sgc->capacity;
+ max_capacity = max(capacity, max_capacity);
+ min_capacity = min(capacity, min_capacity);
}
} else {
/*
group = child->groups;
do {
- capacity += group->sgc->capacity;
+ struct sched_group_capacity *sgc = group->sgc;
+
+ capacity += sgc->capacity;
+ max_capacity = max(sgc->max_capacity, max_capacity);
+ min_capacity = min(sgc->min_capacity, min_capacity);
group = group->next;
} while (group != child->groups);
}
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = max_capacity;
+ sdg->sgc->min_capacity = min_capacity;
}
/*
return false;
}
+
+/*
+ * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-cpu capacity than sched_group ref.
+ */
+static inline bool
+group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+ return sg->sgc->max_capacity + capacity_margin - SCHED_LOAD_SCALE <
+ ref->sgc->max_capacity;
+}
+
static inline enum
group_type group_classify(struct sched_group *group,
struct sg_lb_stats *sgs)
if (sg_imbalanced(group))
return group_imbalanced;
+ if (sgs->group_misfit_task)
+ return group_misfit_task;
+
return group_other;
}
* @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
* @overload: Indicate more than one runnable task for any CPU.
+ * @overutilized: Indicate overutilization for any CPU.
*/
static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs,
- bool *overload)
+ bool *overload, bool *overutilized)
{
unsigned long load;
- int i;
+ int i, nr_running;
memset(sgs, 0, sizeof(*sgs));
sgs->group_util += cpu_util(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
- if (rq->nr_running > 1)
+ nr_running = rq->nr_running;
+ if (nr_running > 1)
*overload = true;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
sgs->sum_weighted_load += weighted_cpuload(i);
- if (idle_cpu(i))
+ /*
+ * No need to call idle_cpu() if nr_running is not 0
+ */
+ if (!nr_running && idle_cpu(i))
sgs->idle_cpus++;
+
+ if (cpu_overutilized(i)) {
+ *overutilized = true;
+ if (!sgs->group_misfit_task && rq->misfit_task)
+ sgs->group_misfit_task = capacity_of(i);
+ }
}
/* Adjust by relative CPU capacity of the group */
if (sgs->group_type < busiest->group_type)
return false;
+ /*
+ * Candidate sg doesn't face any serious load-balance problems
+ * so don't pick it if the local sg is already filled up.
+ */
+ if (sgs->group_type == group_other &&
+ !group_has_capacity(env, &sds->local_stat))
+ return false;
+
if (sgs->avg_load <= busiest->avg_load)
return false;
+ if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
+ goto asym_packing;
+
+ /*
+ * Candidate sg has no more than one task per CPU and
+ * has higher per-CPU capacity. Migrating tasks to less
+ * capable CPUs may harm throughput. Maximize throughput,
+ * power/energy consequences are not considered.
+ */
+ if (sgs->sum_nr_running <= sgs->group_weight &&
+ group_smaller_cpu_capacity(sds->local, sg))
+ return false;
+
+asym_packing:
/* This is the busiest node in its class. */
if (!(env->sd->flags & SD_ASYM_PACKING))
return true;
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
- bool overload = false;
+ bool overload = false, overutilized = false;
if (child && child->flags & SD_PREFER_SIBLING)
prefer_sibling = 1;
}
update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
- &overload);
+ &overload, &overutilized);
if (local_group)
goto next_group;
sgs->group_type = group_classify(sg, sgs);
}
+ /*
+ * Ignore task groups with misfit tasks if local group has no
+ * capacity or if per-cpu capacity isn't higher.
+ */
+ if (sgs->group_type == group_misfit_task &&
+ (!group_has_capacity(env, &sds->local_stat) ||
+ !group_smaller_cpu_capacity(sg, sds->local)))
+ sgs->group_type = group_other;
+
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
sds->busiest = sg;
sds->busiest_stat = *sgs;
if (env->sd->flags & SD_NUMA)
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
+ env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;
+
if (!env->sd->parent) {
/* update overload indicator if we are at root domain */
if (env->dst_rq->rd->overload != overload)
env->dst_rq->rd->overload = overload;
+
+ /* Update over-utilization (tipping point, U >= 0) indicator */
+ if (env->dst_rq->rd->overutilized != overutilized) {
+ env->dst_rq->rd->overutilized = overutilized;
+ trace_sched_overutilized(overutilized);
+ }
+ } else {
+ if (!env->dst_rq->rd->overutilized && overutilized) {
+ env->dst_rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
}
}
*/
if (busiest->avg_load <= sds->avg_load ||
local->avg_load >= sds->avg_load) {
+ /* Misfitting tasks should be migrated in any case */
+ if (busiest->group_type == group_misfit_task) {
+ env->imbalance = busiest->group_misfit_task;
+ return;
+ }
+
+ /*
+ * Busiest group is overloaded, local is not, use the spare
+ * cycles to maximize throughput
+ */
+ if (busiest->group_type == group_overloaded &&
+ local->group_type <= group_misfit_task) {
+ env->imbalance = busiest->load_per_task;
+ return;
+ }
+
env->imbalance = 0;
return fix_small_imbalance(env, sds);
}
(sds->avg_load - local->avg_load) * local->group_capacity
) / SCHED_CAPACITY_SCALE;
+ /* Boost imbalance to allow misfit task to be balanced. */
+ if (busiest->group_type == group_misfit_task)
+ env->imbalance = max_t(long, env->imbalance,
+ busiest->group_misfit_task);
+
/*
* if *imbalance is less than the average load per runnable task
* there is no guarantee that any tasks will be moved so we'll have
* this level.
*/
update_sd_lb_stats(env, &sds);
+
+ if (energy_aware() && !env->dst_rq->rd->overutilized)
+ goto out_balanced;
+
local = &sds.local_stat;
busiest = &sds.busiest_stat;
busiest->group_no_capacity)
goto force_balance;
+ /* Misfitting tasks should be dealt with regardless of the avg load */
+ if (busiest->group_type == group_misfit_task) {
+ goto force_balance;
+ }
+
/*
* If the local group is busier than the selected busiest group
* don't try and pull any tasks.
* might end up to just move the imbalance on another group
*/
if ((busiest->group_type != group_overloaded) &&
- (local->idle_cpus <= (busiest->idle_cpus + 1)))
+ (local->idle_cpus <= (busiest->idle_cpus + 1)) &&
+ !group_smaller_cpu_capacity(sds.busiest, sds.local))
goto out_balanced;
} else {
/*
}
force_balance:
+ env->busiest_group_type = busiest->group_type;
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(env, &sds);
return sds.busiest;
*/
if (rq->nr_running == 1 && wl > env->imbalance &&
- !check_cpu_capacity(rq, env->sd))
+ !check_cpu_capacity(rq, env->sd) &&
+ env->busiest_group_type != group_misfit_task)
continue;
/*
return 1;
}
+ if ((capacity_of(env->src_cpu) < capacity_of(env->dst_cpu)) &&
+ env->src_rq->cfs.h_nr_running == 1 &&
+ cpu_overutilized(env->src_cpu) &&
+ !cpu_overutilized(env->dst_cpu)) {
+ return 1;
+ }
+
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}
* ld_moved - cumulative load moved across iterations
*/
cur_ld_moved = detach_tasks(&env);
+ /*
+ * We want to potentially lower env.src_cpu's OPP.
+ */
+ if (cur_ld_moved)
+ update_capacity_of(env.src_cpu);
/*
* We've detached some tasks from busiest_rq. Every
* excessive cache_hot migrations and active balances.
*/
if (idle != CPU_NEWLY_IDLE)
- sd->nr_balance_failed++;
+ if (env.src_grp_nr_running > 1)
+ sd->nr_balance_failed++;
if (need_active_balance(&env)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
struct sched_domain *sd;
int pulled_task = 0;
u64 curr_cost = 0;
+ long removed_util=0;
idle_enter_fair(this_rq);
*/
this_rq->idle_stamp = rq_clock(this_rq);
- if (this_rq->avg_idle < sysctl_sched_migration_cost ||
- !this_rq->rd->overload) {
+ if (!energy_aware() &&
+ (this_rq->avg_idle < sysctl_sched_migration_cost ||
+ !this_rq->rd->overload)) {
rcu_read_lock();
sd = rcu_dereference_check_sched_domain(this_rq->sd);
if (sd)
raw_spin_unlock(&this_rq->lock);
+ /*
+ * If removed_util_avg is !0 we most probably migrated some task away
+ * from this_cpu. In this case we might be willing to trigger an OPP
+ * update, but we want to do so if we don't find anybody else to pull
+ * here (we will trigger an OPP update with the pulled task's enqueue
+ * anyway).
+ *
+ * Record removed_util before calling update_blocked_averages, and use
+ * it below (before returning) to see if an OPP update is required.
+ */
+ removed_util = atomic_long_read(&(this_rq->cfs).removed_util_avg);
update_blocked_averages(this_cpu);
rcu_read_lock();
for_each_domain(this_cpu, sd) {
if (pulled_task) {
idle_exit_fair(this_rq);
this_rq->idle_stamp = 0;
+ } else if (removed_util) {
+ /*
+ * No task pulled and someone has been migrated away.
+ * Good case to trigger an OPP update.
+ */
+ update_capacity_of(this_cpu);
}
return pulled_task;
schedstat_inc(sd, alb_count);
p = detach_one_task(&env);
- if (p)
+ if (p) {
schedstat_inc(sd, alb_pushed);
+ /*
+ * We want to potentially lower env.src_cpu's OPP.
+ */
+ update_capacity_of(env.src_cpu);
+ }
else
schedstat_inc(sd, alb_failed);
}
if (time_before(now, nohz.next_balance))
return false;
- if (rq->nr_running >= 2)
+ if (rq->nr_running >= 2 &&
+ (!energy_aware() || cpu_overutilized(cpu)))
return true;
rcu_read_lock();
sd = rcu_dereference(per_cpu(sd_busy, cpu));
- if (sd) {
+ if (sd && !energy_aware()) {
sgc = sd->groups->sgc;
nr_busy = atomic_read(&sgc->nr_busy_cpus);
if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
+
+#ifdef CONFIG_SMP
+ if (!rq->rd->overutilized && cpu_overutilized(task_cpu(curr))) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+
+ rq->misfit_task = !task_fits_max(curr, rq->cpu);
+#endif
+
}
/*
return false;
}
+static void detach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /* Catch up with the cfs_rq and remove our load when we leave */
+ update_load_avg(se, 0);
+ detach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+}
+
+static void attach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * Since the real-depth could have been changed (only FAIR
+ * class maintain depth value), reset depth properly.
+ */
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+
+ /* Synchronize entity with its cfs_rq */
+ update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
+ attach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+}
+
static void detach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
se->vruntime -= cfs_rq->min_vruntime;
}
- /* Catch up with the cfs_rq and remove our load when we leave */
- detach_entity_load_avg(cfs_rq, se);
+ detach_entity_cfs_rq(se);
}
static void attach_task_cfs_rq(struct task_struct *p)
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
-#ifdef CONFIG_FAIR_GROUP_SCHED
- /*
- * Since the real-depth could have been changed (only FAIR
- * class maintain depth value), reset depth properly.
- */
- se->depth = se->parent ? se->parent->depth + 1 : 0;
-#endif
-
- /* Synchronize task with its cfs_rq */
- attach_entity_load_avg(cfs_rq, se);
+ attach_entity_cfs_rq(se);
if (!vruntime_normalized(p))
se->vruntime += cfs_rq->min_vruntime;
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
- struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
init_entity_runnable_average(se);
+
+ raw_spin_lock_irq(&rq->lock);
+ post_init_entity_util_avg(se);
+ raw_spin_unlock_irq(&rq->lock);
}
return 1;