#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
-#include <asm/mmu_context.h>
+#include <linux/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/binfmts.h>
#include <linux/context_tracking.h>
#include <linux/compiler.h>
+#include <linux/cpufreq_times.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
+#include "walt.h"
DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
/* cpus with isolated domains */
cpumask_var_t cpu_isolated_map;
+struct rq *
+lock_rq_of(struct task_struct *p, unsigned long *flags)
+{
+ return task_rq_lock(p, flags);
+}
+
+void
+unlock_rq_of(struct rq *rq, struct task_struct *p, unsigned long *flags)
+{
+ task_rq_unlock(rq, p, flags);
+}
+
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
return;
+ head->count++;
+
get_task_struct(task);
/*
head->lastp = &node->next;
}
+static int
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
+ int sibling_count_hint);
+
void wake_up_q(struct wake_q_head *head)
{
struct wake_q_node *node = head->first;
task->wake_q.next = NULL;
/*
- * wake_up_process() implies a wmb() to pair with the queueing
+ * try_to_wake_up() implies a wmb() to pair with the queueing
* in wake_q_add() so as not to miss wakeups.
*/
- wake_up_process(task);
+ try_to_wake_up(task, TASK_NORMAL, 0, head->count);
put_task_struct(task);
}
}
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
- resched_curr(rq);
+ if (cpu_online(cpu) || cpu == smp_processor_id())
+ resched_curr(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
dequeue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
+ double_lock_balance(rq, cpu_rq(new_cpu));
set_task_cpu(p, new_cpu);
+ double_unlock_balance(rq, cpu_rq(new_cpu));
raw_spin_unlock(&rq->lock);
rq = cpu_rq(new_cpu);
p->sched_class->migrate_task_rq(p);
p->se.nr_migrations++;
perf_event_task_migrate(p);
+
+ walt_fixup_busy_time(p, new_cpu);
}
__set_task_cpu(p, new_cpu);
dst_rq = cpu_rq(cpu);
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(dst_rq, p, 0);
check_preempt_curr(dst_rq, p, 0);
} else {
* The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
*/
static inline
-int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags,
+ int sibling_count_hint)
{
lockdep_assert_held(&p->pi_lock);
if (p->nr_cpus_allowed > 1)
- cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
+ cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags,
+ sibling_count_hint);
/*
* In order not to call set_task_cpu() on a blocking task we need
* @p: the thread to be awakened
* @state: the mask of task states that can be woken
* @wake_flags: wake modifier flags (WF_*)
+ * @sibling_count_hint: A hint at the number of threads that are being woken up
+ * in this event.
*
* Put it on the run-queue if it's not already there. The "current"
* thread is always on the run-queue (except when the actual
* or @state didn't match @p's state.
*/
static int
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
+ int sibling_count_hint)
{
unsigned long flags;
int cpu, success = 0;
+#ifdef CONFIG_SMP
+ struct rq *rq;
+ u64 wallclock;
+#endif
/*
* If we are going to wake up a thread waiting for CONDITION we
*/
smp_rmb();
+ rq = cpu_rq(task_cpu(p));
+
+ raw_spin_lock(&rq->lock);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
+ raw_spin_unlock(&rq->lock);
+
p->sched_contributes_to_load = !!task_contributes_to_load(p);
p->state = TASK_WAKING;
if (p->sched_class->task_waking)
p->sched_class->task_waking(p);
- cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags,
+ sibling_count_hint);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
set_task_cpu(p, cpu);
}
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu);
trace_sched_waking(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ u64 wallclock = walt_ktime_clock();
+
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
ttwu_do_wakeup(rq, p, 0);
ttwu_stat(p, smp_processor_id(), 0);
*/
int wake_up_process(struct task_struct *p)
{
- return try_to_wake_up(p, TASK_NORMAL, 0);
+ return try_to_wake_up(p, TASK_NORMAL, 0, 1);
}
EXPORT_SYMBOL(wake_up_process);
int wake_up_state(struct task_struct *p, unsigned int state)
{
- return try_to_wake_up(p, state, 0);
+ return try_to_wake_up(p, state, 0, 1);
}
/*
dl_se->dl_period = 0;
dl_se->flags = 0;
dl_se->dl_bw = 0;
+ dl_se->dl_density = 0;
dl_se->dl_throttled = 0;
dl_se->dl_new = 1;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+#ifdef CONFIG_SCHED_WALT
+ p->last_sleep_ts = 0;
+#endif
+
INIT_LIST_HEAD(&p->se.group_node);
+ walt_init_new_task_load(p);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ p->se.cfs_rq = NULL;
+#endif
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
init_dl_task_timer(&p->dl);
__dl_clear_params(p);
+ init_rt_schedtune_timer(&p->rt);
INIT_LIST_HEAD(&p->rt.run_list);
#ifdef CONFIG_PREEMPT_NOTIFIERS
__sched_fork(clone_flags, p);
/*
- * We mark the process as running here. This guarantees that
+ * We mark the process as NEW here. This guarantees that
* nobody will actually run it, and a signal or other external
* event cannot wake it up and insert it on the runqueue either.
*/
- p->state = TASK_RUNNING;
+ p->state = TASK_NEW;
/*
* Make sure we do not leak PI boosting priority to the child.
p->sched_class = &fair_sched_class;
}
- if (p->sched_class->task_fork)
- p->sched_class->task_fork(p);
+ init_entity_runnable_average(&p->se);
/*
* The child is not yet in the pid-hash so no cgroup attach races,
* Silence PROVE_RCU.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
- set_task_cpu(p, cpu);
+ /*
+ * We're setting the cpu for the first time, we don't migrate,
+ * so use __set_task_cpu().
+ */
+ __set_task_cpu(p, cpu);
+ if (p->sched_class->task_fork)
+ p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
#ifdef CONFIG_SCHED_INFO
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, flags);
+ p->state = TASK_RUNNING;
+
+ walt_init_new_task_load(p);
+
/* Initialize new task's runnable average */
init_entity_runnable_average(&p->se);
#ifdef CONFIG_SMP
* Fork balancing, do it here and not earlier because:
* - cpus_allowed can change in the fork path
* - any previously selected cpu might disappear through hotplug
+ *
+ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
+ * as we're not fully set-up yet.
*/
- set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
+ __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0, 1));
#endif
-
rq = __task_rq_lock(p);
- activate_task(rq, p, 0);
+ update_rq_clock(rq);
+ post_init_entity_util_avg(&p->se);
+
+ walt_mark_task_starting(p);
+ activate_task(rq, p, ENQUEUE_WAKEUP_NEW);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
- switch_mm(oldmm, mm, next);
+ switch_mm_irqs_off(oldmm, mm, next);
if (!prev->mm) {
prev->active_mm = NULL;
return atomic_read(&this->nr_iowait);
}
+#ifdef CONFIG_CPU_QUIET
+u64 nr_running_integral(unsigned int cpu)
+{
+ unsigned int seqcnt;
+ u64 integral;
+ struct rq *q;
+
+ if (cpu >= nr_cpu_ids)
+ return 0;
+
+ q = cpu_rq(cpu);
+
+ /*
+ * Update average to avoid reading stalled value if there were
+ * no run-queue changes for a long time. On the other hand if
+ * the changes are happening right now, just read current value
+ * directly.
+ */
+
+ seqcnt = read_seqcount_begin(&q->ave_seqcnt);
+ integral = do_nr_running_integral(q);
+ if (read_seqcount_retry(&q->ave_seqcnt, seqcnt)) {
+ read_seqcount_begin(&q->ave_seqcnt);
+ integral = q->nr_running_integral;
+ }
+
+ return integral;
+}
+#endif
+
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
struct rq *rq = this_rq();
int dest_cpu;
raw_spin_lock_irqsave(&p->pi_lock, flags);
- dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
+ dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0, 1);
if (dest_cpu == smp_processor_id())
goto unlock;
sched_clock_tick();
raw_spin_lock(&rq->lock);
+ walt_set_window_start(rq);
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE,
+ walt_ktime_clock(), 0);
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
update_cpu_load_active(rq);
trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
+
+ if (curr->sched_class == &fair_sched_class)
+ check_for_migration(rq, curr);
}
#ifdef CONFIG_NO_HZ_FULL
unsigned long *switch_count;
struct rq *rq;
int cpu;
+ u64 wallclock;
cpu = smp_processor_id();
rq = cpu_rq(cpu);
update_rq_clock(rq);
next = pick_next_task(rq, prev);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(prev, rq, PUT_PREV_TASK, wallclock, 0);
+ walt_update_task_ravg(next, rq, PICK_NEXT_TASK, wallclock, 0);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq->clock_skip_update = 0;
if (likely(prev != next)) {
+#ifdef CONFIG_SCHED_WALT
+ if (!prev->on_rq)
+ prev->last_sleep_ts = wallclock;
+#endif
rq->nr_switches++;
rq->curr = next;
++*switch_count;
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
void *key)
{
- return try_to_wake_up(curr->private, mode, wake_flags);
+ return try_to_wake_up(curr->private, mode, wake_flags, 1);
}
EXPORT_SYMBOL(default_wake_function);
BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p);
+ update_rq_clock(rq);
/*
* Idle task boosting is a nono in general. There is one
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
+
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
dl_se->flags = attr->sched_flags;
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
/*
* Changing the parameters of a task is 'tricky' and we're not doing
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
/*
* Changing the policy of the stop threads its a very bad idea
raw_spin_lock(&rq->lock);
__sched_fork(0, idle);
+
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
}
static struct ctl_table *
+sd_alloc_ctl_energy_table(struct sched_group_energy *sge)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(5);
+
+ if (table == NULL)
+ return NULL;
+
+ set_table_entry(&table[0], "nr_idle_states", &sge->nr_idle_states,
+ sizeof(int), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[1], "idle_states", &sge->idle_states[0].power,
+ sge->nr_idle_states*sizeof(struct idle_state), 0644,
+ proc_doulongvec_minmax, false);
+ set_table_entry(&table[2], "nr_cap_states", &sge->nr_cap_states,
+ sizeof(int), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[3], "cap_states", &sge->cap_states[0].cap,
+ sge->nr_cap_states*sizeof(struct capacity_state), 0644,
+ proc_doulongvec_minmax, false);
+
+ return table;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_group_table(struct sched_group *sg)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(2);
+
+ if (table == NULL)
+ return NULL;
+
+ table->procname = kstrdup("energy", GFP_KERNEL);
+ table->mode = 0555;
+ table->child = sd_alloc_ctl_energy_table((struct sched_group_energy *)sg->sge);
+
+ return table;
+}
+
+static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
- struct ctl_table *table = sd_alloc_ctl_entry(14);
+ struct ctl_table *table;
+ unsigned int nr_entries = 14;
+
+ int i = 0;
+ struct sched_group *sg = sd->groups;
+
+ if (sg->sge) {
+ int nr_sgs = 0;
+
+ do {} while (nr_sgs++, sg = sg->next, sg != sd->groups);
+
+ nr_entries += nr_sgs;
+ }
+
+ table = sd_alloc_ctl_entry(nr_entries);
if (table == NULL)
return NULL;
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[12], "name", sd->name,
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
- /* &table[13] is terminator */
+ sg = sd->groups;
+ if (sg->sge) {
+ char buf[32];
+ struct ctl_table *entry = &table[13];
+
+ do {
+ snprintf(buf, 32, "group%d", i);
+ entry->procname = kstrdup(buf, GFP_KERNEL);
+ entry->mode = 0555;
+ entry->child = sd_alloc_ctl_group_table(sg);
+ } while (entry++, i++, sg = sg->next, sg != sd->groups);
+ }
+ /* &table[nr_entries-1] is terminator */
return table;
}
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ walt_set_window_start(rq);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
rq->calc_load_update = calc_load_update;
break;
sched_ttwu_pending();
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
+ walt_migrate_sync_cpu(cpu);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
- if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
- " has parent");
return -1;
}
printk(KERN_CONT " %*pbl",
cpumask_pr_args(sched_group_cpus(group)));
if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
- printk(KERN_CONT " (cpu_capacity = %d)",
+ printk(KERN_CONT " (cpu_capacity = %lu)",
group->sgc->capacity);
}
static int sd_degenerate(struct sched_domain *sd)
{
- if (cpumask_weight(sched_domain_span(sd)) == 1)
- return 1;
+ if (cpumask_weight(sched_domain_span(sd)) == 1) {
+ if (sd->groups->sge)
+ sd->flags &= ~SD_LOAD_BALANCE;
+ else
+ return 1;
+ }
/* Following flags need at least 2 groups */
if (sd->flags & (SD_LOAD_BALANCE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_SHARE_CPUCAPACITY |
+ SD_ASYM_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
- SD_SHARE_POWERDOMAIN)) {
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES)) {
if (sd->groups != sd->groups->next)
return 0;
}
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
+ SD_ASYM_CPUCAPACITY |
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_PREFER_SIBLING |
- SD_SHARE_POWERDOMAIN);
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES);
+ if (parent->groups->sge) {
+ parent->flags &= ~SD_LOAD_BALANCE;
+ return 0;
+ }
if (nr_node_ids == 1)
pflags &= ~SD_SERIALIZE;
}
call_rcu_sched(&old_rd->rcu, free_rootdomain);
}
+void sched_get_rd(struct root_domain *rd)
+{
+ atomic_inc(&rd->refcount);
+}
+
+void sched_put_rd(struct root_domain *rd)
+{
+ if (!atomic_dec_and_test(&rd->refcount))
+ return;
+
+ call_rcu_sched(&rd->rcu, free_rootdomain);
+}
+
static int init_rootdomain(struct root_domain *rd)
{
memset(rd, 0, sizeof(*rd));
if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_dlo_mask;
+#ifdef HAVE_RT_PUSH_IPI
+ rd->rto_cpu = -1;
+ raw_spin_lock_init(&rd->rto_lock);
+ init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+#endif
+
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
+
+ init_max_cpu_capacity(&rd->max_cpu_capacity);
+
+ rd->max_cap_orig_cpu = rd->min_cap_orig_cpu = -1;
+
return 0;
free_rto_mask:
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_busy);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_ea);
+DEFINE_PER_CPU(struct sched_domain *, sd_scs);
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
- struct sched_domain *busy_sd = NULL;
+ struct sched_domain *busy_sd = NULL, *ea_sd = NULL;
int id = cpu;
int size = 1;
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+
+ for_each_domain(cpu, sd) {
+ if (sd->groups->sge)
+ ea_sd = sd;
+ else
+ break;
+ }
+ rcu_assign_pointer(per_cpu(sd_ea, cpu), ea_sd);
+
+ sd = highest_flag_domain(cpu, SD_SHARE_CAP_STATES);
+ rcu_assign_pointer(per_cpu(sd_scs, cpu), sd);
}
/*
* die on a /0 trap.
*/
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+ sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
+ sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
/*
* Make sure the first group of this domain contains the
}
/*
+ * Check that the per-cpu provided sd energy data is consistent for all cpus
+ * within the mask.
+ */
+static inline void check_sched_energy_data(int cpu, sched_domain_energy_f fn,
+ const struct cpumask *cpumask)
+{
+ const struct sched_group_energy * const sge = fn(cpu);
+ struct cpumask mask;
+ int i;
+
+ if (cpumask_weight(cpumask) <= 1)
+ return;
+
+ cpumask_xor(&mask, cpumask, get_cpu_mask(cpu));
+
+ for_each_cpu(i, &mask) {
+ const struct sched_group_energy * const e = fn(i);
+ int y;
+
+ BUG_ON(e->nr_idle_states != sge->nr_idle_states);
+
+ for (y = 0; y < (e->nr_idle_states); y++) {
+ BUG_ON(e->idle_states[y].power !=
+ sge->idle_states[y].power);
+ }
+
+ BUG_ON(e->nr_cap_states != sge->nr_cap_states);
+
+ for (y = 0; y < (e->nr_cap_states); y++) {
+ BUG_ON(e->cap_states[y].cap != sge->cap_states[y].cap);
+ BUG_ON(e->cap_states[y].power !=
+ sge->cap_states[y].power);
+ }
+ }
+}
+
+static void init_sched_energy(int cpu, struct sched_domain *sd,
+ sched_domain_energy_f fn)
+{
+ if (!(fn && fn(cpu)))
+ return;
+
+ if (cpu != group_balance_cpu(sd->groups))
+ return;
+
+ if (sd->child && !sd->child->groups->sge) {
+ pr_err("BUG: EAS setup broken for CPU%d\n", cpu);
+#ifdef CONFIG_SCHED_DEBUG
+ pr_err(" energy data on %s but not on %s domain\n",
+ sd->name, sd->child->name);
+#endif
+ return;
+ }
+
+ check_sched_energy_data(cpu, fn, sched_group_cpus(sd->groups));
+
+ sd->groups->sge = fn(cpu);
+}
+
+/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
/*
* SD_flags allowed in topology descriptions.
*
- * SD_SHARE_CPUCAPACITY - describes SMT topologies
- * SD_SHARE_PKG_RESOURCES - describes shared caches
- * SD_NUMA - describes NUMA topologies
- * SD_SHARE_POWERDOMAIN - describes shared power domain
+ * These flags are purely descriptive of the topology and do not prescribe
+ * behaviour. Behaviour is artificial and mapped in the below sd_init()
+ * function:
+ *
+ * SD_SHARE_CPUCAPACITY - describes SMT topologies
+ * SD_SHARE_PKG_RESOURCES - describes shared caches
+ * SD_NUMA - describes NUMA topologies
+ * SD_SHARE_POWERDOMAIN - describes shared power domain
+ * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies
+ * SD_SHARE_CAP_STATES - describes shared capacity states
+ *
+ * Odd one out, which beside describing the topology has a quirk also
+ * prescribes the desired behaviour that goes along with it:
*
* Odd one out:
* SD_ASYM_PACKING - describes SMT quirks
SD_SHARE_PKG_RESOURCES | \
SD_NUMA | \
SD_ASYM_PACKING | \
- SD_SHARE_POWERDOMAIN)
+ SD_ASYM_CPUCAPACITY | \
+ SD_SHARE_POWERDOMAIN | \
+ SD_SHARE_CAP_STATES)
static struct sched_domain *
-sd_init(struct sched_domain_topology_level *tl, int cpu)
+sd_init(struct sched_domain_topology_level *tl,
+ struct sched_domain *child, int cpu)
{
struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
int sd_weight, sd_flags = 0;
.smt_gain = 0,
.max_newidle_lb_cost = 0,
.next_decay_max_lb_cost = jiffies,
+ .child = child,
#ifdef CONFIG_SCHED_DEBUG
.name = tl->name,
#endif
* Convert topological properties into behaviour.
*/
+ if (sd->flags & SD_ASYM_CPUCAPACITY) {
+ struct sched_domain *t = sd;
+
+ for_each_lower_domain(t)
+ t->flags |= SD_BALANCE_WAKE;
+ }
+
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->flags |= SD_PREFER_SIBLING;
sd->imbalance_pct = 110;
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
struct sched_domain *child, int cpu)
{
- struct sched_domain *sd = sd_init(tl, cpu);
- if (!sd)
- return child;
+ struct sched_domain *sd = sd_init(tl, child, cpu);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
sched_domain_level_max = max(sched_domain_level_max, sd->level);
child->parent = sd;
- sd->child = child;
if (!cpumask_subset(sched_domain_span(child),
sched_domain_span(sd))) {
*per_cpu_ptr(d.sd, i) = sd;
if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
sd->flags |= SD_OVERLAP;
- if (cpumask_equal(cpu_map, sched_domain_span(sd)))
- break;
}
}
/* Calculate CPU capacity for physical packages and nodes */
for (i = nr_cpumask_bits-1; i >= 0; i--) {
+ struct sched_domain_topology_level *tl = sched_domain_topology;
+
if (!cpumask_test_cpu(i, cpu_map))
continue;
- for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent, tl++) {
+ init_sched_energy(i, sd, tl->energy);
claim_allocations(i, sd);
init_sched_groups_capacity(i, sd);
}
/* Attach the domains */
rcu_read_lock();
for_each_cpu(i, cpu_map) {
+ int max_cpu = READ_ONCE(d.rd->max_cap_orig_cpu);
+ int min_cpu = READ_ONCE(d.rd->min_cap_orig_cpu);
+
+ if ((max_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig >
+ cpu_rq(max_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->max_cap_orig_cpu, i);
+
+ if ((min_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig <
+ cpu_rq(min_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->min_cap_orig_cpu, i);
+
sd = *per_cpu_ptr(d.sd, i);
+
cpu_attach_domain(sd, d.rd, i);
}
rcu_read_unlock();
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
* How much cpu bandwidth does root_task_group get?
*
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
+ rq->push_task = NULL;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
+#ifdef CONFIG_SCHED_WALT
+ rq->cur_irqload = 0;
+ rq->avg_irqload = 0;
+ rq->irqload_ts = 0;
+#endif
INIT_LIST_HEAD(&rq->cfs_tasks);
return (nested == preempt_offset);
}
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+ __might_sleep_init_called = 1;
+ return 0;
+}
+early_initcall(__might_sleep_init);
+
void __might_sleep(const char *file, int line, int preempt_offset)
{
/*
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
- !is_idle_task(current)) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ !is_idle_task(current)) || oops_in_progress)
+ return;
+ if (system_state != SYSTEM_RUNNING &&
+ (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
- int i;
/* end participation in shares distribution */
- for_each_possible_cpu(i)
- unregister_fair_sched_group(tg, i);
+ unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
spin_unlock_irqrestore(&task_group_lock, flags);
}
-/* change task's runqueue when it moves between groups.
- * The caller of this function should have put the task in its new group
- * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
- * reflect its new group.
- */
-void sched_move_task(struct task_struct *tsk)
+static void sched_change_group(struct task_struct *tsk, int type)
{
struct task_group *tg;
- int queued, running;
- unsigned long flags;
- struct rq *rq;
-
- rq = task_rq_lock(tsk, &flags);
-
- running = task_current(rq, tsk);
- queued = task_on_rq_queued(tsk);
-
- if (queued)
- dequeue_task(rq, tsk, DEQUEUE_SAVE);
- if (unlikely(running))
- put_prev_task(rq, tsk);
/*
* All callers are synchronized by task_rq_lock(); we do not use RCU
tsk->sched_task_group = tg;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (tsk->sched_class->task_move_group)
- tsk->sched_class->task_move_group(tsk);
+ if (tsk->sched_class->task_change_group)
+ tsk->sched_class->task_change_group(tsk, type);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
+}
+
+/*
+ * Change task's runqueue when it moves between groups.
+ *
+ * The caller of this function should have put the task in its new group by
+ * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
+ * its new group.
+ */
+void sched_move_task(struct task_struct *tsk)
+{
+ int queued, running;
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(tsk, &flags);
+
+ running = task_current(rq, tsk);
+ queued = task_on_rq_queued(tsk);
+
+ if (queued)
+ dequeue_task(rq, tsk, DEQUEUE_SAVE);
+ if (unlikely(running))
+ put_prev_task(rq, tsk);
+
+ sched_change_group(tsk, TASK_MOVE_GROUP);
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
sched_free_group(tg);
}
+/*
+ * This is called before wake_up_new_task(), therefore we really only
+ * have to set its group bits, all the other stuff does not apply.
+ */
static void cpu_cgroup_fork(struct task_struct *task, void *private)
{
- sched_move_task(task);
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(task, &flags);
+
+ update_rq_clock(rq);
+ sched_change_group(task, TASK_SET_GROUP);
+
+ task_rq_unlock(rq, task, &flags);
}
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
+ int ret = 0;
cgroup_taskset_for_each(task, css, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
if (task->sched_class != &fair_sched_class)
return -EINVAL;
#endif
+ /*
+ * Serialize against wake_up_new_task() such that if its
+ * running, we're sure to observe its full state.
+ */
+ raw_spin_lock_irq(&task->pi_lock);
+ /*
+ * Avoid calling sched_move_task() before wake_up_new_task()
+ * has happened. This would lead to problems with PELT, due to
+ * move wanting to detach+attach while we're not attached yet.
+ */
+ if (task->state == TASK_NEW)
+ ret = -EINVAL;
+ raw_spin_unlock_irq(&task->pi_lock);
+
+ if (ret)
+ break;
}
- return 0;
+ return ret;
}
static void cpu_cgroup_attach(struct cgroup_taskset *tset)