DEFINE_TRACE(sched_migrate_task);
#ifdef CONFIG_SMP
+
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
/*
* Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
* Since cpu_power is a 'constant', we can use a reciprocal divide.
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rt_b->rt_period_timer.function = sched_rt_period_timer;
- rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
}
static inline int rt_bandwidth_enabled(void)
struct cgroup_subsys_state css;
#endif
+#ifdef CONFIG_USER_SCHED
+ uid_t uid;
+#endif
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
#ifdef CONFIG_USER_SCHED
+/* Helper function to pass uid information to create_sched_user() */
+void set_tg_uid(struct user_struct *user)
+{
+ user->tg->uid = user->uid;
+}
+
/*
* Root task group.
* Every UID task group (including init_task_group aka UID-0) will
struct task_group *tg;
#ifdef CONFIG_USER_SCHED
- tg = p->user->tg;
+ rcu_read_lock();
+ tg = __task_cred(p)->user->tg;
+ rcu_read_unlock();
#elif defined(CONFIG_CGROUP_SCHED)
tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
struct task_group, css);
#ifdef CONFIG_SMP
struct cpupri cpupri;
#endif
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+ /*
+ * Preferred wake up cpu nominated by sched_mc balance that will be
+ * used when most cpus are idle in the system indicating overall very
+ * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
+ */
+ unsigned int sched_mc_preferred_wakeup_cpu;
+#endif
};
/*
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
+ unsigned long long rq_cpu_time;
+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_exp_empty;
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rq->hrtick_timer.function = hrtick;
- rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
}
#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
* slice expiry etc.
*/
-#define WEIGHT_IDLEPRIO 2
-#define WMULT_IDLEPRIO (1 << 31)
+#define WEIGHT_IDLEPRIO 3
+#define WMULT_IDLEPRIO 1431655765
/*
* Nice levels are multiplicative, with a gentle 10% change for every
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
+ unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
- if (rq->nr_running)
- rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+ if (nr_running)
+ rq->avg_load_per_task = rq->load.weight / nr_running;
else
rq->avg_load_per_task = 0;
#endif
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+{
+ int ret = 0;
+
+ if (unlikely(!irqs_disabled())) {
+ /* printk() doesn't work good under rq->lock */
+ spin_unlock(&this_rq->lock);
+ BUG_ON(1);
+ }
+ if (unlikely(!spin_trylock(&busiest->lock))) {
+ if (busiest < this_rq) {
+ spin_unlock(&this_rq->lock);
+ spin_lock(&busiest->lock);
+ spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+ ret = 1;
+ } else
+ spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+ }
+ return ret;
+}
+
+static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(busiest->lock)
+{
+ spin_unlock(&busiest->lock);
+ lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
clock_offset = old_rq->clock - new_rq->clock;
+ trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
p->se.wait_start -= clock_offset;
if (!sched_feat(SYNC_WAKEUPS))
sync = 0;
+ if (!sync) {
+ if (current->se.avg_overlap < sysctl_sched_migration_cost &&
+ p->se.avg_overlap < sysctl_sched_migration_cost)
+ sync = 1;
+ } else {
+ if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
+ p->se.avg_overlap >= sysctl_sched_migration_cost)
+ sync = 0;
+ }
+
#ifdef CONFIG_SMP
if (sched_feat(LB_WAKEUP_UPDATE)) {
struct sched_domain *sd;
smp_wmb();
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
old_state = p->state;
if (!(old_state & state))
goto out;
schedstat_inc(p, se.nr_wakeups_local);
else
schedstat_inc(p, se.nr_wakeups_remote);
- update_rq_clock(rq);
activate_task(rq, p, 1);
success = 1;
out_running:
- trace_sched_wakeup(rq, p);
+ trace_sched_wakeup(rq, p, success);
check_preempt_curr(rq, p, sync);
p->state = TASK_RUNNING;
p->sched_class->task_new(rq, p);
inc_nr_running(rq);
}
- trace_sched_wakeup_new(rq, p);
+ trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, 0);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
}
/*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
- */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
- __releases(this_rq->lock)
- __acquires(busiest->lock)
- __acquires(this_rq->lock)
-{
- int ret = 0;
-
- if (unlikely(!irqs_disabled())) {
- /* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
- BUG_ON(1);
- }
- if (unlikely(!spin_trylock(&busiest->lock))) {
- if (busiest < this_rq) {
- spin_unlock(&this_rq->lock);
- spin_lock(&busiest->lock);
- spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
- ret = 1;
- } else
- spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
- }
- return ret;
-}
-
-static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
- __releases(busiest->lock)
-{
- spin_unlock(&busiest->lock);
- lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
-}
-
-/*
* If dest_cpu is allowed for this process, migrate the task to it.
* This is accomplished by forcing the cpu_allowed mask to only
* allow dest_cpu, which will force the cpu onto dest_cpu. Then
struct rq *rq;
rq = task_rq_lock(p, &flags);
- if (!cpu_isset(dest_cpu, p->cpus_allowed)
+ if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
|| unlikely(!cpu_active(dest_cpu)))
goto out;
- trace_sched_migrate_task(rq, p, dest_cpu);
/* force the process onto the specified CPU */
if (migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
* 2) cannot be migrated to this CPU due to cpus_allowed, or
* 3) are cache-hot on their current CPU.
*/
- if (!cpu_isset(this_cpu, p->cpus_allowed)) {
+ if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
schedstat_inc(p, se.nr_failed_migrations_affine);
return 0;
}
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const cpumask_t *cpus, int *balance)
+ int *sd_idle, const struct cpumask *cpus, int *balance)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
*/
if ((sum_nr_running < min_nr_running) ||
(sum_nr_running == min_nr_running &&
- cpumask_first(sched_group_cpus(group)) <
+ cpumask_first(sched_group_cpus(group)) >
cpumask_first(sched_group_cpus(group_min)))) {
group_min = group;
min_nr_running = sum_nr_running;
if (sum_nr_running <= group_capacity - 1) {
if (sum_nr_running > leader_nr_running ||
(sum_nr_running == leader_nr_running &&
- cpumask_first(sched_group_cpus(group)) >
+ cpumask_first(sched_group_cpus(group)) <
cpumask_first(sched_group_cpus(group_leader)))) {
group_leader = group;
leader_nr_running = sum_nr_running;
if (this == group_leader && group_leader != group_min) {
*imbalance = min_load_per_task;
+ if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+ cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+ cpumask_first(sched_group_cpus(group_leader));
+ }
return group_min;
}
#endif
*/
static struct rq *
find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
- unsigned long imbalance, const cpumask_t *cpus)
+ unsigned long imbalance, const struct cpumask *cpus)
{
struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
for_each_cpu(i, sched_group_cpus(group)) {
unsigned long wl;
- if (!cpu_isset(i, *cpus))
+ if (!cpumask_test_cpu(i, cpus))
continue;
rq = cpu_rq(i);
*/
static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *balance, cpumask_t *cpus)
+ int *balance, struct cpumask *cpus)
{
int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
- cpus_setall(*cpus);
+ cpumask_setall(cpus);
/*
* When power savings policy is enabled for the parent domain, idle
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(all_pinned)) {
- cpu_clear(cpu_of(busiest), *cpus);
- if (!cpus_empty(*cpus))
+ cpumask_clear_cpu(cpu_of(busiest), cpus);
+ if (!cpumask_empty(cpus))
goto redo;
goto out_balanced;
}
/* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
- if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+ if (!cpumask_test_cpu(this_cpu,
+ &busiest->curr->cpus_allowed)) {
spin_unlock_irqrestore(&busiest->lock, flags);
all_pinned = 1;
goto out_one_pinned;
*/
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
- cpumask_t *cpus)
+ struct cpumask *cpus)
{
struct sched_group *group;
struct rq *busiest = NULL;
int sd_idle = 0;
int all_pinned = 0;
- cpus_setall(*cpus);
+ cpumask_setall(cpus);
/*
* When power savings policy is enabled for the parent domain, idle
double_unlock_balance(this_rq, busiest);
if (unlikely(all_pinned)) {
- cpu_clear(cpu_of(busiest), *cpus);
- if (!cpus_empty(*cpus))
+ cpumask_clear_cpu(cpu_of(busiest), cpus);
+ if (!cpumask_empty(cpus))
goto redo;
}
}
if (!ld_moved) {
+ int active_balance = 0;
+
schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
+
+ if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+ return -1;
+
+ if (sd->nr_balance_failed++ < 2)
+ return -1;
+
+ /*
+ * The only task running in a non-idle cpu can be moved to this
+ * cpu in an attempt to completely freeup the other CPU
+ * package. The same method used to move task in load_balance()
+ * have been extended for load_balance_newidle() to speedup
+ * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
+ *
+ * The package power saving logic comes from
+ * find_busiest_group(). If there are no imbalance, then
+ * f_b_g() will return NULL. However when sched_mc={1,2} then
+ * f_b_g() will select a group from which a running task may be
+ * pulled to this cpu in order to make the other package idle.
+ * If there is no opportunity to make a package idle and if
+ * there are no imbalance, then f_b_g() will return NULL and no
+ * action will be taken in load_balance_newidle().
+ *
+ * Under normal task pull operation due to imbalance, there
+ * will be more than one task in the source run queue and
+ * move_tasks() will succeed. ld_moved will be true and this
+ * active balance code will not be triggered.
+ */
+
+ /* Lock busiest in correct order while this_rq is held */
+ double_lock_balance(this_rq, busiest);
+
+ /*
+ * don't kick the migration_thread, if the curr
+ * task on busiest cpu can't be moved to this_cpu
+ */
+ if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+ double_unlock_balance(this_rq, busiest);
+ all_pinned = 1;
+ return ld_moved;
+ }
+
+ if (!busiest->active_balance) {
+ busiest->active_balance = 1;
+ busiest->push_cpu = this_cpu;
+ active_balance = 1;
+ }
+
+ double_unlock_balance(this_rq, busiest);
+ /*
+ * Should not call ttwu while holding a rq->lock
+ */
+ spin_unlock(&this_rq->lock);
+ if (active_balance)
+ wake_up_process(busiest->migration_thread);
+ spin_lock(&this_rq->lock);
+
} else
sd->nr_balance_failed = 0;
static void idle_balance(int this_cpu, struct rq *this_rq)
{
struct sched_domain *sd;
- int pulled_task = -1;
+ int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
- cpumask_t tmpmask;
+ cpumask_var_t tmpmask;
+
+ if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+ return;
for_each_domain(this_cpu, sd) {
unsigned long interval;
if (sd->flags & SD_BALANCE_NEWIDLE)
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu, this_rq,
- sd, &tmpmask);
+ sd, tmpmask);
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
*/
this_rq->next_balance = next_balance;
}
+ free_cpumask_var(tmpmask);
}
/*
#ifdef CONFIG_NO_HZ
static struct {
atomic_t load_balancer;
- cpumask_t cpu_mask;
+ cpumask_var_t cpu_mask;
} nohz ____cacheline_aligned = {
.load_balancer = ATOMIC_INIT(-1),
- .cpu_mask = CPU_MASK_NONE,
};
/*
int cpu = smp_processor_id();
if (stop_tick) {
- cpu_set(cpu, nohz.cpu_mask);
+ cpumask_set_cpu(cpu, nohz.cpu_mask);
cpu_rq(cpu)->in_nohz_recently = 1;
/*
}
/* time for ilb owner also to sleep */
- if (cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
+ if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu)
atomic_set(&nohz.load_balancer, -1);
return 0;
} else if (atomic_read(&nohz.load_balancer) == cpu)
return 1;
} else {
- if (!cpu_isset(cpu, nohz.cpu_mask))
+ if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
return 0;
- cpu_clear(cpu, nohz.cpu_mask);
+ cpumask_clear_cpu(cpu, nohz.cpu_mask);
if (atomic_read(&nohz.load_balancer) == cpu)
if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
int need_serialize;
- cpumask_t tmp;
+ cpumask_var_t tmp;
+
+ /* Fails alloc? Rebalancing probably not a priority right now. */
+ if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
+ return;
for_each_domain(cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
}
if (time_after_eq(jiffies, sd->last_balance + interval)) {
- if (load_balance(cpu, rq, sd, idle, &balance, &tmp)) {
+ if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
/*
* We've pulled tasks over so either we're no
* longer idle, or one of our SMT siblings is
*/
if (likely(update_next_balance))
rq->next_balance = next_balance;
+
+ free_cpumask_var(tmp);
}
/*
*/
if (this_rq->idle_at_tick &&
atomic_read(&nohz.load_balancer) == this_cpu) {
- cpumask_t cpus = nohz.cpu_mask;
struct rq *rq;
int balance_cpu;
- cpu_clear(this_cpu, cpus);
- for_each_cpu(balance_cpu, &cpus) {
+ for_each_cpu(balance_cpu, nohz.cpu_mask) {
+ if (balance_cpu == this_cpu)
+ continue;
+
/*
* If this cpu gets work to do, stop the load balancing
* work being done for other cpus. Next load
rq->in_nohz_recently = 0;
if (atomic_read(&nohz.load_balancer) == cpu) {
- cpu_clear(cpu, nohz.cpu_mask);
+ cpumask_clear_cpu(cpu, nohz.cpu_mask);
atomic_set(&nohz.load_balancer, -1);
}
* TBD: Traverse the sched domains and nominate
* the nearest cpu in the nohz.cpu_mask.
*/
- int ilb = first_cpu(nohz.cpu_mask);
+ int ilb = cpumask_first(nohz.cpu_mask);
if (ilb < nr_cpu_ids)
resched_cpu(ilb);
* cpus with ticks stopped, is it time for that to stop?
*/
if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
- cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
+ cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
resched_cpu(cpu);
return;
}
* someone else, then no need raise the SCHED_SOFTIRQ
*/
if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
- cpu_isset(cpu, nohz.cpu_mask))
+ cpumask_test_cpu(cpu, nohz.cpu_mask))
return;
#endif
if (time_after_eq(jiffies, rq->next_balance))
* Account user cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
cputime64_t tmp;
+ /* Add user time to process. */
p->utime = cputime_add(p->utime, cputime);
+ p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
account_group_user_time(p, cputime);
/* Add user time to cpustat. */
* Account guest cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
{
cputime64_t tmp;
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
tmp = cputime_to_cputime64(cputime);
+ /* Add guest time to process. */
p->utime = cputime_add(p->utime, cputime);
+ p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
account_group_user_time(p, cputime);
p->gtime = cputime_add(p->gtime, cputime);
+ /* Add guest time to cpustat. */
cpustat->user = cputime64_add(cpustat->user, tmp);
cpustat->guest = cputime64_add(cpustat->guest, tmp);
}
/*
- * Account scaled user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- */
-void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
-{
- p->utimescaled = cputime_add(p->utimescaled, cputime);
-}
-
-/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @hardirq_offset: the offset to subtract from hardirq_count()
* @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
void account_system_time(struct task_struct *p, int hardirq_offset,
- cputime_t cputime)
+ cputime_t cputime, cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- struct rq *rq = this_rq();
cputime64_t tmp;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
- account_guest_time(p, cputime);
+ account_guest_time(p, cputime, cputime_scaled);
return;
}
+ /* Add system time to process. */
p->stime = cputime_add(p->stime, cputime);
+ p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
cpustat->irq = cputime64_add(cpustat->irq, tmp);
else if (softirq_count())
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
- else if (p != rq->idle)
- cpustat->system = cputime64_add(cpustat->system, tmp);
- else if (atomic_read(&rq->nr_iowait) > 0)
- cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
- cpustat->idle = cputime64_add(cpustat->idle, tmp);
+ cpustat->system = cputime64_add(cpustat->system, tmp);
+
/* Account for system time used */
acct_update_integrals(p);
}
/*
- * Account scaled system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
*/
-void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+void account_steal_time(cputime_t cputime)
{
- p->stimescaled = cputime_add(p->stimescaled, cputime);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+ cpustat->steal = cputime64_add(cpustat->steal, cputime64);
}
/*
- * Account for involuntary wait time.
- * @p: the process from which the cpu time has been stolen
- * @steal: the cpu time spent in involuntary wait
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
*/
-void account_steal_time(struct task_struct *p, cputime_t steal)
+void account_idle_time(cputime_t cputime)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- cputime64_t tmp = cputime_to_cputime64(steal);
+ cputime64_t cputime64 = cputime_to_cputime64(cputime);
struct rq *rq = this_rq();
- if (p == rq->idle) {
- p->stime = cputime_add(p->stime, steal);
- if (atomic_read(&rq->nr_iowait) > 0)
- cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
- else
- cpustat->idle = cputime64_add(cpustat->idle, tmp);
- } else
- cpustat->steal = cputime64_add(cpustat->steal, tmp);
+ if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+ else
+ cpustat->idle = cputime64_add(cpustat->idle, cputime64);
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+ cputime_t one_jiffy = jiffies_to_cputime(1);
+ cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+ struct rq *rq = this_rq();
+
+ if (user_tick)
+ account_user_time(p, one_jiffy, one_jiffy_scaled);
+ else if (p != rq->idle)
+ account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+ one_jiffy_scaled);
+ else
+ account_idle_time(one_jiffy);
}
/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+ account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+ account_idle_time(jiffies_to_cputime(ticks));
+}
+
+#endif
+
+/*
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
#endif
}
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
- defined(CONFIG_PREEMPT_TRACER))
-
-static inline unsigned long get_parent_ip(unsigned long addr)
+unsigned long get_parent_ip(unsigned long addr)
{
if (in_lock_functions(addr)) {
addr = CALLER_ADDR2;
return addr;
}
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+ defined(CONFIG_PREEMPT_TRACER))
+
void __kprobes add_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
/*
* Underflow?
*/
- if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
return;
/*
* Is the spinlock portion underflowing?
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int sync, void *key)
{
wait_queue_t *curr, *next;
* sys_setpriority is a more generic, but much slower function that
* does similar things.
*/
-asmlinkage long sys_nice(int increment)
+SYSCALL_DEFINE1(nice, int, increment)
{
long nice, retval;
set_load_weight(p);
}
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+ const struct cred *cred = current_cred(), *pcred;
+ bool match;
+
+ rcu_read_lock();
+ pcred = __task_cred(p);
+ match = (cred->euid == pcred->euid ||
+ cred->euid == pcred->uid);
+ rcu_read_unlock();
+ return match;
+}
+
static int __sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param, bool user)
{
return -EPERM;
/* can't change other user's priorities */
- if ((current->euid != p->euid) &&
- (current->euid != p->uid))
+ if (!check_same_owner(p))
return -EPERM;
}
* @policy: new policy.
* @param: structure containing the new RT priority.
*/
-asmlinkage long
-sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
+ struct sched_param __user *, param)
{
/* negative values for policy are not valid */
if (policy < 0)
* @pid: the pid in question.
* @param: structure containing the new RT priority.
*/
-asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
return do_sched_setscheduler(pid, -1, param);
}
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
*/
-asmlinkage long sys_sched_getscheduler(pid_t pid)
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
struct task_struct *p;
int retval;
* @pid: the pid in question.
* @param: structure containing the RT priority.
*/
-asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
struct sched_param lp;
struct task_struct *p;
return retval;
}
-long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
- cpumask_t cpus_allowed;
- cpumask_t new_mask = *in_mask;
+ cpumask_var_t cpus_allowed, new_mask;
struct task_struct *p;
int retval;
get_task_struct(p);
read_unlock(&tasklist_lock);
+ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+ retval = -ENOMEM;
+ goto out_put_task;
+ }
+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+ retval = -ENOMEM;
+ goto out_free_cpus_allowed;
+ }
retval = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
+ if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
goto out_unlock;
retval = security_task_setscheduler(p, 0, NULL);
if (retval)
goto out_unlock;
- cpuset_cpus_allowed(p, &cpus_allowed);
- cpus_and(new_mask, new_mask, cpus_allowed);
+ cpuset_cpus_allowed(p, cpus_allowed);
+ cpumask_and(new_mask, in_mask, cpus_allowed);
again:
- retval = set_cpus_allowed_ptr(p, &new_mask);
+ retval = set_cpus_allowed_ptr(p, new_mask);
if (!retval) {
- cpuset_cpus_allowed(p, &cpus_allowed);
- if (!cpus_subset(new_mask, cpus_allowed)) {
+ cpuset_cpus_allowed(p, cpus_allowed);
+ if (!cpumask_subset(new_mask, cpus_allowed)) {
/*
* We must have raced with a concurrent cpuset
* update. Just reset the cpus_allowed to the
* cpuset's cpus_allowed
*/
- new_mask = cpus_allowed;
+ cpumask_copy(new_mask, cpus_allowed);
goto again;
}
}
out_unlock:
+ free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+ free_cpumask_var(cpus_allowed);
+out_put_task:
put_task_struct(p);
put_online_cpus();
return retval;
}
static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
- cpumask_t *new_mask)
+ struct cpumask *new_mask)
{
- if (len < sizeof(cpumask_t)) {
- memset(new_mask, 0, sizeof(cpumask_t));
- } else if (len > sizeof(cpumask_t)) {
- len = sizeof(cpumask_t);
- }
+ if (len < cpumask_size())
+ cpumask_clear(new_mask);
+ else if (len > cpumask_size())
+ len = cpumask_size();
+
return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to the new cpu mask
*/
-asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
- unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+ unsigned long __user *, user_mask_ptr)
{
- cpumask_t new_mask;
+ cpumask_var_t new_mask;
int retval;
- retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
- if (retval)
- return retval;
+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+ return -ENOMEM;
- return sched_setaffinity(pid, &new_mask);
+ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
+ if (retval == 0)
+ retval = sched_setaffinity(pid, new_mask);
+ free_cpumask_var(new_mask);
+ return retval;
}
-long sched_getaffinity(pid_t pid, cpumask_t *mask)
+long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
int retval;
if (retval)
goto out_unlock;
- cpus_and(*mask, p->cpus_allowed, cpu_online_map);
+ cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
out_unlock:
read_unlock(&tasklist_lock);
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to hold the current cpu mask
*/
-asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
- unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+ unsigned long __user *, user_mask_ptr)
{
int ret;
- cpumask_t mask;
+ cpumask_var_t mask;
- if (len < sizeof(cpumask_t))
+ if (len < cpumask_size())
return -EINVAL;
- ret = sched_getaffinity(pid, &mask);
- if (ret < 0)
- return ret;
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
- if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
- return -EFAULT;
+ ret = sched_getaffinity(pid, mask);
+ if (ret == 0) {
+ if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+ ret = -EFAULT;
+ else
+ ret = cpumask_size();
+ }
+ free_cpumask_var(mask);
- return sizeof(cpumask_t);
+ return ret;
}
/**
* This function yields the current CPU to other tasks. If there are no
* other threads running on this CPU then this function will return.
*/
-asmlinkage long sys_sched_yield(void)
+SYSCALL_DEFINE0(sched_yield)
{
struct rq *rq = this_rq_lock();
* this syscall returns the maximum rt_priority that can be used
* by a given scheduling class.
*/
-asmlinkage long sys_sched_get_priority_max(int policy)
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
int ret = -EINVAL;
* this syscall returns the minimum rt_priority that can be used
* by a given scheduling class.
*/
-asmlinkage long sys_sched_get_priority_min(int policy)
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
int ret = -EINVAL;
* this syscall writes the default timeslice value of a given process
* into the user-space timespec buffer. A value of '0' means infinity.
*/
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+ struct timespec __user *, interval)
{
struct task_struct *p;
unsigned int time_slice;
idle->se.exec_start = sched_clock();
idle->prio = idle->normal_prio = MAX_PRIO;
- idle->cpus_allowed = cpumask_of_cpu(cpu);
+ cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
__set_task_cpu(idle, cpu);
rq->curr = rq->idle = idle;
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
- ftrace_retfunc_init_task(idle);
+ ftrace_graph_init_task(idle);
}
/*
* task must not exit() & deallocate itself prematurely. The
* call is not atomic; no spinlocks may be held.
*/
-int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
struct migration_req req;
unsigned long flags;
int ret = 0;
rq = task_rq_lock(p, &flags);
- if (!cpus_intersects(*new_mask, cpu_online_map)) {
+ if (!cpumask_intersects(new_mask, cpu_online_mask)) {
ret = -EINVAL;
goto out;
}
if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
- !cpus_equal(p->cpus_allowed, *new_mask))) {
+ !cpumask_equal(&p->cpus_allowed, new_mask))) {
ret = -EINVAL;
goto out;
}
if (p->sched_class->set_cpus_allowed)
p->sched_class->set_cpus_allowed(p, new_mask);
else {
- p->cpus_allowed = *new_mask;
- p->rt.nr_cpus_allowed = cpus_weight(*new_mask);
+ cpumask_copy(&p->cpus_allowed, new_mask);
+ p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
}
/* Can the task run on the task's current CPU? If so, we're done */
- if (cpu_isset(task_cpu(p), *new_mask))
+ if (cpumask_test_cpu(task_cpu(p), new_mask))
goto out;
if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
if (task_cpu(p) != src_cpu)
goto done;
/* Affinity changed (again). */
- if (!cpu_isset(dest_cpu, p->cpus_allowed))
+ if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
goto fail;
on_rq = p->se.on_rq;
*/
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
- unsigned long flags;
- cpumask_t mask;
- struct rq *rq;
int dest_cpu;
+ const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
- do {
- /* On same node? */
- node_to_cpumask_ptr(pnodemask, cpu_to_node(dead_cpu));
-
- cpus_and(mask, *pnodemask, p->cpus_allowed);
- dest_cpu = cpumask_any_and(cpu_online_mask, &mask);
+again:
+ /* Look for allowed, online CPU in same node. */
+ for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+ goto move;
- /* On any allowed CPU? */
- if (dest_cpu >= nr_cpu_ids)
- dest_cpu = cpumask_any_and(cpu_online_mask,
- &p->cpus_allowed);
+ /* Any allowed, online CPU? */
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+ if (dest_cpu < nr_cpu_ids)
+ goto move;
- /* No more Mr. Nice Guy. */
- if (dest_cpu >= nr_cpu_ids) {
- cpumask_t cpus_allowed;
+ /* No more Mr. Nice Guy. */
+ if (dest_cpu >= nr_cpu_ids) {
+ cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
+ dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
- cpuset_cpus_allowed_locked(p, &cpus_allowed);
- /*
- * Try to stay on the same cpuset, where the
- * current cpuset may be a subset of all cpus.
- * The cpuset_cpus_allowed_locked() variant of
- * cpuset_cpus_allowed() will not block. It must be
- * called within calls to cpuset_lock/cpuset_unlock.
- */
- rq = task_rq_lock(p, &flags);
- p->cpus_allowed = cpus_allowed;
- dest_cpu = cpumask_any_and(cpu_online_mask,
- &p->cpus_allowed);
- task_rq_unlock(rq, &flags);
-
- /*
- * Don't tell them about moving exiting tasks or
- * kernel threads (both mm NULL), since they never
- * leave kernel.
- */
- if (p->mm && printk_ratelimit()) {
- printk(KERN_INFO "process %d (%s) no "
- "longer affine to cpu%d\n",
- task_pid_nr(p), p->comm, dead_cpu);
- }
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit()) {
+ printk(KERN_INFO "process %d (%s) no "
+ "longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, dead_cpu);
}
- } while (!__migrate_task_irq(p, dead_cpu, dest_cpu));
+ }
+
+move:
+ /* It can have affinity changed while we were choosing. */
+ if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
+ goto again;
}
/*
req = list_entry(rq->migration_queue.next,
struct migration_req, list);
list_del_init(&req->list);
+ spin_unlock_irq(&rq->lock);
complete(&req->done);
+ spin_lock_irq(&rq->lock);
}
spin_unlock_irq(&rq->lock);
break;
#ifdef CONFIG_SCHED_DEBUG
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
- cpumask_t *groupmask)
+ struct cpumask *groupmask)
{
struct sched_group *group = sd->groups;
char str[256];
- cpulist_scnprintf(str, sizeof(str), *sched_domain_span(sd));
- cpus_clear(*groupmask);
+ cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
+ cpumask_clear(groupmask);
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
- cpulist_scnprintf(str, sizeof(str), *sched_group_cpus(group));
+ cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
printk(KERN_CONT " %s", str);
group = group->next;
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
- cpumask_t *groupmask;
+ cpumask_var_t groupmask;
int level = 0;
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
- groupmask = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
- if (!groupmask) {
+ if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
return;
}
if (!sd)
break;
}
- kfree(groupmask);
+ free_cpumask_var(groupmask);
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
SD_BALANCE_EXEC |
SD_SHARE_CPUPOWER |
SD_SHARE_PKG_RESOURCES);
+ if (nr_node_ids == 1)
+ pflags &= ~SD_SERIALIZE;
}
if (~cflags & pflags)
return 0;
static void free_rootdomain(struct root_domain *rd)
{
+ cpupri_cleanup(&rd->cpupri);
+
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
spin_unlock_irqrestore(&rq->lock, flags);
}
-static int init_rootdomain(struct root_domain *rd, bool bootmem)
+static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
{
memset(rd, 0, sizeof(*rd));
alloc_bootmem_cpumask_var(&def_root_domain.span);
alloc_bootmem_cpumask_var(&def_root_domain.online);
alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
- cpupri_init(&rd->cpupri);
+ cpupri_init(&rd->cpupri, true);
return 0;
}
if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
- goto free_rd;
+ goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_online;
- cpupri_init(&rd->cpupri);
+ if (cpupri_init(&rd->cpupri, false) != 0)
+ goto free_rto_mask;
return 0;
+free_rto_mask:
+ free_cpumask_var(rd->rto_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
free_cpumask_var(rd->span);
-free_rd:
- kfree(rd);
+out:
return -ENOMEM;
}
}
/* cpus with isolated domains */
-static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
+static cpumask_var_t cpu_isolated_map;
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
- static int __initdata ints[NR_CPUS];
- int i;
-
- str = get_options(str, ARRAY_SIZE(ints), ints);
- cpus_clear(cpu_isolated_map);
- for (i = 1; i <= ints[0]; i++)
- if (ints[i] < NR_CPUS)
- cpu_set(ints[i], cpu_isolated_map);
+ cpulist_parse(str, cpu_isolated_map);
return 1;
}
/*
* init_sched_build_groups takes the cpumask we wish to span, and a pointer
* to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < NR_CPUS
- * (due to the fact that we keep track of groups covered with a cpumask_t).
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
*
* init_sched_build_groups will build a circular linked list of the groups
* covered by the given span, and will set each group's ->cpumask correctly,
* and ->cpu_power to 0.
*/
static void
-init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
- int (*group_fn)(int cpu, const cpumask_t *cpu_map,
+init_sched_build_groups(const struct cpumask *span,
+ const struct cpumask *cpu_map,
+ int (*group_fn)(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg,
- cpumask_t *tmpmask),
- cpumask_t *covered, cpumask_t *tmpmask)
+ struct cpumask *tmpmask),
+ struct cpumask *covered, struct cpumask *tmpmask)
{
struct sched_group *first = NULL, *last = NULL;
int i;
- cpus_clear(*covered);
+ cpumask_clear(covered);
for_each_cpu(i, span) {
struct sched_group *sg;
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
continue;
- cpu_set(j, *covered);
+ cpumask_set_cpu(j, covered);
cpumask_set_cpu(j, sched_group_cpus(sg));
}
if (!first)
* should be one that prevents unnecessary balancing, but also spreads tasks
* out optimally.
*/
-static void sched_domain_node_span(int node, cpumask_t *span)
+static void sched_domain_node_span(int node, struct cpumask *span)
{
nodemask_t used_nodes;
- node_to_cpumask_ptr(nodemask, node);
int i;
- cpus_clear(*span);
+ cpumask_clear(span);
nodes_clear(used_nodes);
- cpus_or(*span, *span, *nodemask);
+ cpumask_or(span, span, cpumask_of_node(node));
node_set(node, used_nodes);
for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
int next_node = find_next_best_node(node, &used_nodes);
- node_to_cpumask_ptr_next(nodemask, next_node);
- cpus_or(*span, *span, *nodemask);
+ cpumask_or(span, span, cpumask_of_node(next_node));
}
}
#endif /* CONFIG_NUMA */
static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
static int
-cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
- cpumask_t *unused)
+cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg, struct cpumask *unused)
{
if (sg)
*sg = &per_cpu(sched_group_cpus, cpu).sg;
#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int
-cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
- cpumask_t *mask)
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg, struct cpumask *mask)
{
int group;
- *mask = per_cpu(cpu_sibling_map, cpu);
- cpus_and(*mask, *mask, *cpu_map);
- group = first_cpu(*mask);
+ cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+ group = cpumask_first(mask);
if (sg)
*sg = &per_cpu(sched_group_core, group).sg;
return group;
}
#elif defined(CONFIG_SCHED_MC)
static int
-cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
- cpumask_t *unused)
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg, struct cpumask *unused)
{
if (sg)
*sg = &per_cpu(sched_group_core, cpu).sg;
static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
static int
-cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
- cpumask_t *mask)
+cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg, struct cpumask *mask)
{
int group;
#ifdef CONFIG_SCHED_MC
- *mask = cpu_coregroup_map(cpu);
- cpus_and(*mask, *mask, *cpu_map);
- group = first_cpu(*mask);
+ cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+ group = cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
- *mask = per_cpu(cpu_sibling_map, cpu);
- cpus_and(*mask, *mask, *cpu_map);
- group = first_cpu(*mask);
+ cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+ group = cpumask_first(mask);
#else
group = cpu;
#endif
* groups, so roll our own. Now each node has its own list of groups which
* gets dynamically allocated.
*/
-static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
static struct sched_group ***sched_group_nodes_bycpu;
-static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
-static int cpu_to_allnodes_group(int cpu, const cpumask_t *cpu_map,
- struct sched_group **sg, cpumask_t *nodemask)
+static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg,
+ struct cpumask *nodemask)
{
int group;
- node_to_cpumask_ptr(pnodemask, cpu_to_node(cpu));
- cpus_and(*nodemask, *pnodemask, *cpu_map);
- group = first_cpu(*nodemask);
+ cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
+ group = cpumask_first(nodemask);
if (sg)
*sg = &per_cpu(sched_group_allnodes, group).sg;
#ifdef CONFIG_NUMA
/* Free memory allocated for various sched_group structures */
-static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
+static void free_sched_groups(const struct cpumask *cpu_map,
+ struct cpumask *nodemask)
{
int cpu, i;
for (i = 0; i < nr_node_ids; i++) {
struct sched_group *oldsg, *sg = sched_group_nodes[i];
- node_to_cpumask_ptr(pnodemask, i);
- cpus_and(*nodemask, *pnodemask, *cpu_map);
- if (cpus_empty(*nodemask))
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+ if (cpumask_empty(nodemask))
continue;
if (sg == NULL)
}
}
#else /* !CONFIG_NUMA */
-static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
+static void free_sched_groups(const struct cpumask *cpu_map,
+ struct cpumask *nodemask)
{
}
#endif /* CONFIG_NUMA */
* Build sched domains for a given set of cpus and attach the sched domains
* to the individual cpus
*/
-static int __build_sched_domains(const cpumask_t *cpu_map,
+static int __build_sched_domains(const struct cpumask *cpu_map,
struct sched_domain_attr *attr)
{
int i, err = -ENOMEM;
}
#ifdef CONFIG_NUMA
- sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
+ sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
#endif
/*
for_each_cpu(i, cpu_map) {
struct sched_domain *sd = NULL, *p;
- *nodemask = node_to_cpumask(cpu_to_node(i));
- cpus_and(*nodemask, *nodemask, *cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
#ifdef CONFIG_NUMA
- if (cpus_weight(*cpu_map) >
- SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) {
- sd = &per_cpu(allnodes_domains, i);
+ if (cpumask_weight(cpu_map) >
+ SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
+ sd = &per_cpu(allnodes_domains, i).sd;
SD_INIT(sd, ALLNODES);
set_domain_attribute(sd, attr);
cpumask_copy(sched_domain_span(sd), cpu_map);
} else
p = NULL;
- sd = &per_cpu(node_domains, i);
+ sd = &per_cpu(node_domains, i).sd;
SD_INIT(sd, NODE);
set_domain_attribute(sd, attr);
sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
sd = &per_cpu(core_domains, i).sd;
SD_INIT(sd, MC);
set_domain_attribute(sd, attr);
- *sched_domain_span(sd) = cpu_coregroup_map(i);
- cpumask_and(sched_domain_span(sd),
- sched_domain_span(sd), cpu_map);
+ cpumask_and(sched_domain_span(sd), cpu_map,
+ cpu_coregroup_mask(i));
sd->parent = p;
p->child = sd;
cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
#ifdef CONFIG_SCHED_SMT
/* Set up CPU (sibling) groups */
for_each_cpu(i, cpu_map) {
- *this_sibling_map = per_cpu(cpu_sibling_map, i);
- cpus_and(*this_sibling_map, *this_sibling_map, *cpu_map);
- if (i != first_cpu(*this_sibling_map))
+ cpumask_and(this_sibling_map,
+ &per_cpu(cpu_sibling_map, i), cpu_map);
+ if (i != cpumask_first(this_sibling_map))
continue;
init_sched_build_groups(this_sibling_map, cpu_map,
#ifdef CONFIG_SCHED_MC
/* Set up multi-core groups */
for_each_cpu(i, cpu_map) {
- *this_core_map = cpu_coregroup_map(i);
- cpus_and(*this_core_map, *this_core_map, *cpu_map);
- if (i != first_cpu(*this_core_map))
+ cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
+ if (i != cpumask_first(this_core_map))
continue;
init_sched_build_groups(this_core_map, cpu_map,
/* Set up physical groups */
for (i = 0; i < nr_node_ids; i++) {
- *nodemask = node_to_cpumask(i);
- cpus_and(*nodemask, *nodemask, *cpu_map);
- if (cpus_empty(*nodemask))
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+ if (cpumask_empty(nodemask))
continue;
init_sched_build_groups(nodemask, cpu_map,
struct sched_group *sg, *prev;
int j;
- *nodemask = node_to_cpumask(i);
- cpus_clear(*covered);
-
- cpus_and(*nodemask, *nodemask, *cpu_map);
- if (cpus_empty(*nodemask)) {
+ cpumask_clear(covered);
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+ if (cpumask_empty(nodemask)) {
sched_group_nodes[i] = NULL;
continue;
}
sched_domain_node_span(i, domainspan);
- cpus_and(*domainspan, *domainspan, *cpu_map);
+ cpumask_and(domainspan, domainspan, cpu_map);
sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, i);
for_each_cpu(j, nodemask) {
struct sched_domain *sd;
- sd = &per_cpu(node_domains, j);
+ sd = &per_cpu(node_domains, j).sd;
sd->groups = sg;
}
sg->__cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), nodemask);
sg->next = sg;
- cpus_or(*covered, *covered, *nodemask);
+ cpumask_or(covered, covered, nodemask);
prev = sg;
for (j = 0; j < nr_node_ids; j++) {
int n = (i + j) % nr_node_ids;
- node_to_cpumask_ptr(pnodemask, n);
- cpus_complement(*notcovered, *covered);
- cpus_and(*tmpmask, *notcovered, *cpu_map);
- cpus_and(*tmpmask, *tmpmask, *domainspan);
- if (cpus_empty(*tmpmask))
+ cpumask_complement(notcovered, covered);
+ cpumask_and(tmpmask, notcovered, cpu_map);
+ cpumask_and(tmpmask, tmpmask, domainspan);
+ if (cpumask_empty(tmpmask))
break;
- cpus_and(*tmpmask, *tmpmask, *pnodemask);
- if (cpus_empty(*tmpmask))
+ cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
+ if (cpumask_empty(tmpmask))
continue;
sg = kmalloc_node(sizeof(struct sched_group) +
sg->__cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), tmpmask);
sg->next = prev->next;
- cpus_or(*covered, *covered, *tmpmask);
+ cpumask_or(covered, covered, tmpmask);
prev->next = sg;
prev = sg;
}
if (sd_allnodes) {
struct sched_group *sg;
- cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg,
+ cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
tmpmask);
init_numa_sched_groups_power(sg);
}
#endif
}
-static int build_sched_domains(const cpumask_t *cpu_map)
+static int build_sched_domains(const struct cpumask *cpu_map)
{
return __build_sched_domains(cpu_map, NULL);
}
-static cpumask_t *doms_cur; /* current sched domains */
+static struct cpumask *doms_cur; /* current sched domains */
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
/* attribues of custom domains in 'doms_cur' */
/*
* Special case: If a kmalloc of a doms_cur partition (array of
- * cpumask_t) fails, then fallback to a single sched domain,
- * as determined by the single cpumask_t fallback_doms.
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
*/
-static cpumask_t fallback_doms;
+static cpumask_var_t fallback_doms;
-void __attribute__((weak)) arch_update_cpu_topology(void)
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
{
+ return 0;
}
/*
* For now this just excludes isolated cpus, but could be used to
* exclude other special cases in the future.
*/
-static int arch_init_sched_domains(const cpumask_t *cpu_map)
+static int arch_init_sched_domains(const struct cpumask *cpu_map)
{
int err;
arch_update_cpu_topology();
ndoms_cur = 1;
- doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+ doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
if (!doms_cur)
- doms_cur = &fallback_doms;
- cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+ doms_cur = fallback_doms;
+ cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
dattr_cur = NULL;
err = build_sched_domains(doms_cur);
register_sched_domain_sysctl();
return err;
}
-static void arch_destroy_sched_domains(const cpumask_t *cpu_map,
- cpumask_t *tmpmask)
+static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
+ struct cpumask *tmpmask)
{
free_sched_groups(cpu_map, tmpmask);
}
* Detach sched domains from a group of cpus specified in cpu_map
* These cpus will now be attached to the NULL domain
*/
-static void detach_destroy_domains(const cpumask_t *cpu_map)
+static void detach_destroy_domains(const struct cpumask *cpu_map)
{
- cpumask_t tmpmask;
+ /* Save because hotplug lock held. */
+ static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
int i;
for_each_cpu(i, cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
- arch_destroy_sched_domains(cpu_map, &tmpmask);
+ arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
}
/* handle null as "default" */
* doms_new[] to the current sched domain partitioning, doms_cur[].
* It destroys each deleted domain and builds each new domain.
*
- * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
* The masks don't intersect (don't overlap.) We should setup one
* sched domain for each mask. CPUs not in any of the cpumasks will
* not be load balanced. If the same cpumask appears both in the
* the single partition 'fallback_doms', it also forces the domains
* to be rebuilt.
*
- * If doms_new == NULL it will be replaced with cpu_online_map.
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
* ndoms_new == 0 is a special case for destroying existing domains,
* and it will not create the default domain.
*
* Call with hotplug lock held
*/
-void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+/* FIXME: Change to struct cpumask *doms_new[] */
+void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
struct sched_domain_attr *dattr_new)
{
int i, j, n;
+ int new_topology;
mutex_lock(&sched_domains_mutex);
/* always unregister in case we don't destroy any domains */
unregister_sched_domain_sysctl();
+ /* Let architecture update cpu core mappings. */
+ new_topology = arch_update_cpu_topology();
+
n = doms_new ? ndoms_new : 0;
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
- for (j = 0; j < n; j++) {
- if (cpus_equal(doms_cur[i], doms_new[j])
+ for (j = 0; j < n && !new_topology; j++) {
+ if (cpumask_equal(&doms_cur[i], &doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
if (doms_new == NULL) {
ndoms_cur = 0;
- doms_new = &fallback_doms;
- cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+ doms_new = fallback_doms;
+ cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
WARN_ON_ONCE(dattr_new);
}
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
- for (j = 0; j < ndoms_cur; j++) {
- if (cpus_equal(doms_new[i], doms_cur[j])
+ for (j = 0; j < ndoms_cur && !new_topology; j++) {
+ if (cpumask_equal(&doms_new[i], &doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
}
/* Remember the new sched domains */
- if (doms_cur != &fallback_doms)
+ if (doms_cur != fallback_doms)
kfree(doms_cur);
kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-int arch_reinit_sched_domains(void)
+static void arch_reinit_sched_domains(void)
{
get_online_cpus();
rebuild_sched_domains();
put_online_cpus();
-
- return 0;
}
static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
{
- int ret;
+ unsigned int level = 0;
- if (buf[0] != '0' && buf[0] != '1')
+ if (sscanf(buf, "%u", &level) != 1)
+ return -EINVAL;
+
+ /*
+ * level is always be positive so don't check for
+ * level < POWERSAVINGS_BALANCE_NONE which is 0
+ * What happens on 0 or 1 byte write,
+ * need to check for count as well?
+ */
+
+ if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
return -EINVAL;
if (smt)
- sched_smt_power_savings = (buf[0] == '1');
+ sched_smt_power_savings = level;
else
- sched_mc_power_savings = (buf[0] == '1');
+ sched_mc_power_savings = level;
- ret = arch_reinit_sched_domains();
+ arch_reinit_sched_domains();
- return ret ? ret : count;
+ return count;
}
#ifdef CONFIG_SCHED_MC
sched_smt_power_savings_store);
#endif
-int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
{
int err = 0;
void __init sched_init_smp(void)
{
- cpumask_t non_isolated_cpus;
+ cpumask_var_t non_isolated_cpus;
+
+ alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
#if defined(CONFIG_NUMA)
sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
#endif
get_online_cpus();
mutex_lock(&sched_domains_mutex);
- arch_init_sched_domains(&cpu_online_map);
- cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
- if (cpus_empty(non_isolated_cpus))
- cpu_set(smp_processor_id(), non_isolated_cpus);
+ arch_init_sched_domains(cpu_online_mask);
+ cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+ if (cpumask_empty(non_isolated_cpus))
+ cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
mutex_unlock(&sched_domains_mutex);
put_online_cpus();
init_hrtick();
/* Move init over to a non-isolated CPU */
- if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0)
+ if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
BUG();
sched_init_granularity();
+ free_cpumask_var(non_isolated_cpus);
+
+ alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+ init_sched_rt_class();
}
#else
void __init sched_init_smp(void)
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+ alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+#endif
+ alloc_bootmem_cpumask_var(&cpu_isolated_map);
+#endif /* SMP */
scheduler_running = 1;
}
runtime = d->rt_runtime;
}
+#ifdef CONFIG_USER_SCHED
+ if (tg == &root_task_group) {
+ period = global_rt_period();
+ runtime = global_rt_runtime();
+ }
+#endif
+
/*
* Cannot have more runtime than the period.
*/
kfree(ca);
}
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+ u64 data;
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ data = *cpuusage;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ data = *cpuusage;
+#endif
+
+ return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ *cpuusage = val;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ *cpuusage = val;
+#endif
+}
+
/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
{
u64 totalcpuusage = 0;
int i;
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
- /*
- * Take rq->lock to make 64-bit addition safe on 32-bit
- * platforms.
- */
- spin_lock_irq(&cpu_rq(i)->lock);
- totalcpuusage += *cpuusage;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
+ for_each_present_cpu(i)
+ totalcpuusage += cpuacct_cpuusage_read(ca, i);
return totalcpuusage;
}
goto out;
}
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+ for_each_present_cpu(i)
+ cpuacct_cpuusage_write(ca, i, 0);
- spin_lock_irq(&cpu_rq(i)->lock);
- *cpuusage = 0;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
out:
return err;
}
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct cpuacct *ca = cgroup_ca(cgroup);
+ u64 percpu;
+ int i;
+
+ for_each_present_cpu(i) {
+ percpu = cpuacct_cpuusage_read(ca, i);
+ seq_printf(m, "%llu ", (unsigned long long) percpu);
+ }
+ seq_printf(m, "\n");
+ return 0;
+}
+
static struct cftype files[] = {
{
.name = "usage",
.read_u64 = cpuusage_read,
.write_u64 = cpuusage_write,
},
+ {
+ .name = "usage_percpu",
+ .read_seq_string = cpuacct_percpu_seq_read,
+ },
+
};
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)