#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
+#include <linux/pid_namespace.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
+#include <linux/cpu_acct.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#ifdef CONFIG_FAIR_GROUP_SCHED
+#include <linux/cgroup.h>
+
struct cfs_rq;
/* task group related information */
struct task_group {
+#ifdef CONFIG_FAIR_CGROUP_SCHED
+ struct cgroup_subsys_state css;
+#endif
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
#ifdef CONFIG_FAIR_USER_SCHED
tg = p->user->tg;
+#elif defined(CONFIG_FAIR_CGROUP_SCHED)
+ tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
+ struct task_group, css);
#else
tg = &init_task_group;
#endif
* acquire operations must be ordered by ascending &runqueue.
*/
struct rq {
- spinlock_t lock; /* runqueue lock */
+ /* runqueue lock: */
+ spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
#ifdef CONFIG_NO_HZ
unsigned char in_nohz_recently;
#endif
- struct load_weight load; /* capture load from *all* tasks on this cpu */
+ /* capture load from *all* tasks on this cpu: */
+ struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
struct cfs_rq cfs;
#ifdef CONFIG_FAIR_GROUP_SCHED
- struct list_head leaf_cfs_rq_list; /* list of leaf cfs_rq on this cpu */
+ /* list of leaf cfs_rq on this cpu: */
+ struct list_head leaf_cfs_rq_list;
#endif
struct rt_rq rt;
/* For active balancing */
int active_balance;
int push_cpu;
- int cpu; /* cpu of this runqueue */
+ /* cpu of this runqueue: */
+ int cpu;
struct task_struct *migration_thread;
struct list_head migration_queue;
struct sched_info rq_sched_info;
/* sys_sched_yield() stats */
- unsigned long yld_exp_empty;
- unsigned long yld_act_empty;
- unsigned long yld_both_empty;
- unsigned long yld_count;
+ unsigned int yld_exp_empty;
+ unsigned int yld_act_empty;
+ unsigned int yld_both_empty;
+ unsigned int yld_count;
/* schedule() stats */
- unsigned long sched_switch;
- unsigned long sched_count;
- unsigned long sched_goidle;
+ unsigned int sched_switch;
+ unsigned int sched_count;
+ unsigned int sched_goidle;
/* try_to_wake_up() stats */
- unsigned long ttwu_count;
- unsigned long ttwu_local;
+ unsigned int ttwu_count;
+ unsigned int ttwu_local;
/* BKL stats */
- unsigned long bkl_count;
+ unsigned int bkl_count;
#endif
struct lock_class_key rq_lock_key;
};
#endif
}
-static inline int is_migration_thread(struct task_struct *p, struct rq *rq)
-{
-#ifdef CONFIG_SMP
- return p == rq->migration_thread;
-#else
- return 0;
-#endif
-}
-
/*
* Update the per-runqueue clock, as finegrained as the platform can give
* us, but without assuming monotonicity, etc.:
};
const_debug unsigned int sysctl_sched_features =
- SCHED_FEAT_NEW_FAIR_SLEEPERS *1 |
- SCHED_FEAT_START_DEBIT *1 |
- SCHED_FEAT_TREE_AVG *0 |
- SCHED_FEAT_APPROX_AVG *0 |
- SCHED_FEAT_WAKEUP_PREEMPT *1 |
- SCHED_FEAT_PREEMPT_RESTRICT *1;
+ SCHED_FEAT_NEW_FAIR_SLEEPERS * 1 |
+ SCHED_FEAT_START_DEBIT * 1 |
+ SCHED_FEAT_TREE_AVG * 0 |
+ SCHED_FEAT_APPROX_AVG * 0 |
+ SCHED_FEAT_WAKEUP_PREEMPT * 1 |
+ SCHED_FEAT_PREEMPT_RESTRICT * 1;
#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)
#ifdef CONFIG_SMP
+/*
+ * Is this task likely cache-hot:
+ */
+static inline int
+task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+{
+ s64 delta;
+
+ if (p->sched_class != &fair_sched_class)
+ return 0;
+
+ if (sysctl_sched_migration_cost == -1)
+ return 1;
+ if (sysctl_sched_migration_cost == 0)
+ return 0;
+
+ delta = now - p->se.exec_start;
+
+ return delta < (s64)sysctl_sched_migration_cost;
+}
+
+
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
int old_cpu = task_cpu(p);
p->se.sleep_start -= clock_offset;
if (p->se.block_start)
p->se.block_start -= clock_offset;
+ if (old_cpu != new_cpu) {
+ schedstat_inc(p, se.nr_migrations);
+ if (task_hot(p, old_rq->clock, NULL))
+ schedstat_inc(p, se.nr_forced2_migrations);
+ }
#endif
p->se.vruntime -= old_cfsrq->min_vruntime -
new_cfsrq->min_vruntime;
if (sd->flags & SD_WAKE_IDLE) {
cpus_and(tmp, sd->span, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
- if (idle_cpu(i))
+ if (idle_cpu(i)) {
+ if (i != task_cpu(p)) {
+ schedstat_inc(p,
+ se.nr_wakeups_idle);
+ }
return i;
+ }
}
} else {
break;
*/
static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
- int cpu, this_cpu, success = 0;
+ int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
long old_state;
struct rq *rq;
goto out_running;
cpu = task_cpu(p);
+ orig_cpu = cpu;
this_cpu = smp_processor_id();
#ifdef CONFIG_SMP
unsigned long tl = this_load;
unsigned long tl_per_task;
+ /*
+ * Attract cache-cold tasks on sync wakeups:
+ */
+ if (sync && !task_hot(p, rq->clock, this_sd))
+ goto out_set_cpu;
+
+ schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
/*
* there is no bad imbalance.
*/
schedstat_inc(this_sd, ttwu_move_affine);
+ schedstat_inc(p, se.nr_wakeups_affine);
goto out_set_cpu;
}
}
if (this_sd->flags & SD_WAKE_BALANCE) {
if (imbalance*this_load <= 100*load) {
schedstat_inc(this_sd, ttwu_move_balance);
+ schedstat_inc(p, se.nr_wakeups_passive);
goto out_set_cpu;
}
}
out_activate:
#endif /* CONFIG_SMP */
+ schedstat_inc(p, se.nr_wakeups);
+ if (sync)
+ schedstat_inc(p, se.nr_wakeups_sync);
+ if (orig_cpu != cpu)
+ schedstat_inc(p, se.nr_wakeups_migrate);
+ if (cpu == this_cpu)
+ schedstat_inc(p, se.nr_wakeups_local);
+ else
+ schedstat_inc(p, se.nr_wakeups_remote);
update_rq_clock(rq);
activate_task(rq, p, 1);
- /*
- * Sync wakeups (i.e. those types of wakeups where the waker
- * has indicated that it will leave the CPU in short order)
- * don't trigger a preemption, if the woken up task will run on
- * this cpu. (in this case the 'I will reschedule' promise of
- * the waker guarantees that the freshly woken up task is going
- * to be considered on this CPU.)
- */
- if (!sync || cpu != this_cpu)
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p);
success = 1;
out_running:
p->prio = effective_prio(p);
- if (!p->sched_class->task_new || !current->se.on_rq || !rq->cfs.curr) {
+ if (!p->sched_class->task_new || !current->se.on_rq) {
activate_task(rq, p, 0);
} else {
/*
preempt_enable();
#endif
if (current->set_child_tid)
- put_user(current->pid, current->set_child_tid);
+ put_user(task_pid_vnr(current), current->set_child_tid);
}
/*
* 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 (!cpu_isset(this_cpu, p->cpus_allowed)) {
+ schedstat_inc(p, se.nr_failed_migrations_affine);
return 0;
+ }
*all_pinned = 0;
- if (task_running(rq, p))
+ if (task_running(rq, p)) {
+ schedstat_inc(p, se.nr_failed_migrations_running);
return 0;
+ }
+ /*
+ * Aggressive migration if:
+ * 1) task is cache cold, or
+ * 2) too many balance attempts have failed.
+ */
+
+ if (!task_hot(p, rq->clock, sd) ||
+ sd->nr_balance_failed > sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+ if (task_hot(p, rq->clock, sd)) {
+ schedstat_inc(sd, lb_hot_gained[idle]);
+ schedstat_inc(p, se.nr_forced_migrations);
+ }
+#endif
+ return 1;
+ }
+
+ if (task_hot(p, rq->clock, sd)) {
+ schedstat_inc(p, se.nr_failed_migrations_hot);
+ return 0;
+ }
return 1;
}
unsigned long max_pull;
unsigned long busiest_load_per_task, busiest_nr_running;
unsigned long this_load_per_task, this_nr_running;
- int load_idx;
+ int load_idx, group_imb = 0;
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
int power_savings_balance = 1;
unsigned long leader_nr_running = 0, min_load_per_task = 0;
load_idx = sd->idle_idx;
do {
- unsigned long load, group_capacity;
+ unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
int local_group;
int i;
+ int __group_imb = 0;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long sum_nr_running, sum_weighted_load;
/* Tally up the load of all CPUs in the group */
sum_weighted_load = sum_nr_running = avg_load = 0;
+ max_cpu_load = 0;
+ min_cpu_load = ~0UL;
for_each_cpu_mask(i, group->cpumask) {
struct rq *rq;
}
load = target_load(i, load_idx);
- } else
+ } else {
load = source_load(i, load_idx);
+ if (load > max_cpu_load)
+ max_cpu_load = load;
+ if (min_cpu_load > load)
+ min_cpu_load = load;
+ }
avg_load += load;
sum_nr_running += rq->nr_running;
avg_load = sg_div_cpu_power(group,
avg_load * SCHED_LOAD_SCALE);
+ if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE)
+ __group_imb = 1;
+
group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
if (local_group) {
this_nr_running = sum_nr_running;
this_load_per_task = sum_weighted_load;
} else if (avg_load > max_load &&
- sum_nr_running > group_capacity) {
+ (sum_nr_running > group_capacity || __group_imb)) {
max_load = avg_load;
busiest = group;
busiest_nr_running = sum_nr_running;
busiest_load_per_task = sum_weighted_load;
+ group_imb = __group_imb;
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
goto out_balanced;
busiest_load_per_task /= busiest_nr_running;
+ if (group_imb)
+ busiest_load_per_task = min(busiest_load_per_task, avg_load);
+
/*
* We're trying to get all the cpus to the average_load, so we don't
* want to push ourselves above the average load, nor do we wish to
/*
* Account user 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 user space since the last update
*/
void account_user_time(struct task_struct *p, cputime_t cputime)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
cputime64_t tmp;
+ struct rq *rq = this_rq();
p->utime = cputime_add(p->utime, cputime);
+ if (p != rq->idle)
+ cpuacct_charge(p, cputime);
+
/* Add user time to cpustat. */
tmp = cputime_to_cputime64(cputime);
if (TASK_NICE(p) > 0)
cpustat->user = cputime64_add(cpustat->user, tmp);
}
+/*
+ * 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
+ */
+void account_guest_time(struct task_struct *p, cputime_t cputime)
+{
+ cputime64_t tmp;
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+ tmp = cputime_to_cputime64(cputime);
+
+ p->utime = cputime_add(p->utime, cputime);
+ p->gtime = cputime_add(p->gtime, cputime);
+
+ 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
struct rq *rq = this_rq();
cputime64_t tmp;
+ if (p->flags & PF_VCPU) {
+ account_guest_time(p, cputime);
+ p->flags &= ~PF_VCPU;
+ return;
+ }
+
p->stime = cputime_add(p->stime, 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)
+ else if (p != rq->idle) {
cpustat->system = cputime64_add(cpustat->system, tmp);
- else if (atomic_read(&rq->nr_iowait) > 0)
+ cpuacct_charge(p, cputime);
+ } else if (atomic_read(&rq->nr_iowait) > 0)
cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
cpustat->idle = cputime64_add(cpustat->idle, tmp);
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
+ */
+void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+{
+ p->stimescaled = cputime_add(p->stimescaled, cputime);
+}
+
/*
* Account for involuntary wait time.
* @p: the process from which the cpu time has been stolen
cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
cpustat->idle = cputime64_add(cpustat->idle, tmp);
- } else
+ } else {
cpustat->steal = cputime64_add(cpustat->steal, tmp);
+ cpuacct_charge(p, -tmp);
+ }
}
/*
static noinline void __schedule_bug(struct task_struct *prev)
{
printk(KERN_ERR "BUG: scheduling while atomic: %s/0x%08x/%d\n",
- prev->comm, preempt_count(), prev->pid);
+ prev->comm, preempt_count(), task_pid_nr(prev));
debug_show_held_locks(prev);
if (irqs_disabled())
print_irqtrace_events(prev);
int __sched wait_for_completion_interruptible(struct completion *x)
{
- return wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+ if (t == -ERESTARTSYS)
+ return t;
+ return 0;
}
EXPORT_SYMBOL(wait_for_completion_interruptible);
*/
static struct task_struct *find_process_by_pid(pid_t pid)
{
- return pid ? find_task_by_pid(pid) : current;
+ return pid ? find_task_by_vpid(pid) : current;
}
/* Actually do priority change: must hold rq lock. */
cpus_allowed = cpuset_cpus_allowed(p);
cpus_and(new_mask, new_mask, cpus_allowed);
+ again:
retval = set_cpus_allowed(p, new_mask);
+ if (!retval) {
+ cpus_allowed = cpuset_cpus_allowed(p);
+ if (!cpus_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;
+ goto again;
+ }
+ }
out_unlock:
put_task_struct(p);
mutex_unlock(&sched_hotcpu_mutex);
unsigned state;
state = p->state ? __ffs(p->state) + 1 : 0;
- printk("%-13.13s %c", p->comm,
+ printk(KERN_INFO "%-13.13s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
if (state == TASK_RUNNING)
- printk(" running ");
+ printk(KERN_CONT " running ");
else
- printk(" %08lx ", thread_saved_pc(p));
+ printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
if (state == TASK_RUNNING)
- printk(" running task ");
+ printk(KERN_CONT " running task ");
else
- printk(" %016lx ", thread_saved_pc(p));
+ printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
{
free = (unsigned long)n - (unsigned long)end_of_stack(p);
}
#endif
- printk("%5lu %5d %6d\n", free, p->pid, p->parent->pid);
+ printk(KERN_CONT "%5lu %5d %6d\n", free,
+ task_pid_nr(p), task_pid_nr(p->parent));
if (state != TASK_RUNNING)
show_stack(p, NULL);
}
#ifdef CONFIG_HOTPLUG_CPU
+
+static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+ int ret;
+
+ local_irq_disable();
+ ret = __migrate_task(p, src_cpu, dest_cpu);
+ local_irq_enable();
+ return ret;
+}
+
/*
- * Figure out where task on dead CPU should go, use force if neccessary.
+ * Figure out where task on dead CPU should go, use force if necessary.
* NOTE: interrupts should be disabled by the caller
*/
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
/* No more Mr. Nice Guy. */
if (dest_cpu == NR_CPUS) {
+ cpumask_t cpus_allowed = cpuset_cpus_allowed_locked(p);
+ /*
+ * 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);
- cpus_setall(p->cpus_allowed);
+ p->cpus_allowed = cpus_allowed;
dest_cpu = any_online_cpu(p->cpus_allowed);
task_rq_unlock(rq, &flags);
if (p->mm && printk_ratelimit())
printk(KERN_INFO "process %d (%s) no "
"longer affine to cpu%d\n",
- p->pid, p->comm, dead_cpu);
+ task_pid_nr(p), p->comm, dead_cpu);
}
- } while (!__migrate_task(p, dead_cpu, dest_cpu));
+ } while (!__migrate_task_irq(p, dead_cpu, dest_cpu));
}
/*
{
struct task_struct *p, *t;
- write_lock_irq(&tasklist_lock);
+ read_lock(&tasklist_lock);
do_each_thread(t, p) {
if (p == current)
move_task_off_dead_cpu(src_cpu, p);
} while_each_thread(t, p);
- write_unlock_irq(&tasklist_lock);
+ read_unlock(&tasklist_lock);
}
/*
struct rq *rq = cpu_rq(dead_cpu);
/* Must be exiting, otherwise would be on tasklist. */
- BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
+ BUG_ON(!p->exit_state);
/* Cannot have done final schedule yet: would have vanished. */
BUG_ON(p->state == TASK_DEAD);
* Drop lock around migration; if someone else moves it,
* that's OK. No task can be added to this CPU, so iteration is
* fine.
- * NOTE: interrupts should be left disabled --dev@
*/
- spin_unlock(&rq->lock);
+ spin_unlock_irq(&rq->lock);
move_task_off_dead_cpu(dead_cpu, p);
- spin_lock(&rq->lock);
+ spin_lock_irq(&rq->lock);
put_task_struct(p);
}
static struct ctl_table *sd_alloc_ctl_entry(int n)
{
struct ctl_table *entry =
- kmalloc(n * sizeof(struct ctl_table), GFP_KERNEL);
-
- BUG_ON(!entry);
- memset(entry, 0, n * sizeof(struct ctl_table));
+ kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
return entry;
}
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+ struct ctl_table *entry;
+
+ /*
+ * In the intermediate directories, both the child directory and
+ * procname are dynamically allocated and could fail but the mode
+ * will always be set. In the lowest directory the names are
+ * static strings and all have proc handlers.
+ */
+ for (entry = *tablep; entry->mode; entry++) {
+ if (entry->child)
+ sd_free_ctl_entry(&entry->child);
+ if (entry->proc_handler == NULL)
+ kfree(entry->procname);
+ }
+
+ kfree(*tablep);
+ *tablep = NULL;
+}
+
static void
set_table_entry(struct ctl_table *entry,
const char *procname, void *data, int maxlen,
{
struct ctl_table *table = sd_alloc_ctl_entry(12);
+ if (table == NULL)
+ return NULL;
+
set_table_entry(&table[0], "min_interval", &sd->min_interval,
sizeof(long), 0644, proc_doulongvec_minmax);
set_table_entry(&table[1], "max_interval", &sd->max_interval,
sizeof(int), 0644, proc_dointvec_minmax);
set_table_entry(&table[10], "flags", &sd->flags,
sizeof(int), 0644, proc_dointvec_minmax);
+ /* &table[11] is terminator */
return table;
}
-static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+static ctl_table * sd_alloc_ctl_cpu_table(int cpu)
{
struct ctl_table *entry, *table;
struct sched_domain *sd;
for_each_domain(cpu, sd)
domain_num++;
entry = table = sd_alloc_ctl_entry(domain_num + 1);
+ if (table == NULL)
+ return NULL;
i = 0;
for_each_domain(cpu, sd) {
}
static struct ctl_table_header *sd_sysctl_header;
-static void init_sched_domain_sysctl(void)
+static void register_sched_domain_sysctl(void)
{
int i, cpu_num = num_online_cpus();
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
+ if (entry == NULL)
+ return;
+
sd_ctl_dir[0].child = entry;
- for (i = 0; i < cpu_num; i++, entry++) {
+ for_each_online_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
entry->child = sd_alloc_ctl_cpu_table(i);
+ entry++;
}
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
}
+
+static void unregister_sched_domain_sysctl(void)
+{
+ unregister_sysctl_table(sd_sysctl_header);
+ sd_sysctl_header = NULL;
+ sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
#else
-static void init_sched_domain_sysctl(void)
+static void register_sched_domain_sysctl(void)
+{
+}
+static void unregister_sched_domain_sysctl(void)
{
}
#endif
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- /* Strictly unneccessary, as first user will wake it. */
+ /* Strictly unnecessary, as first user will wake it. */
wake_up_process(cpu_rq(cpu)->migration_thread);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
+ cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
migrate_live_tasks(cpu);
rq = cpu_rq(cpu);
kthread_stop(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
- rq = task_rq_lock(rq->idle, &flags);
+ spin_lock_irq(&rq->lock);
update_rq_clock(rq);
deactivate_task(rq, rq->idle, 0);
rq->idle->static_prio = MAX_PRIO;
__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
rq->idle->sched_class = &idle_sched_class;
migrate_dead_tasks(cpu);
- task_rq_unlock(rq, &flags);
+ spin_unlock_irq(&rq->lock);
+ cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
}
if (!group->__cpu_power) {
- printk("\n");
+ printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
break;
}
if (!cpus_weight(group->cpumask)) {
- printk("\n");
+ printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: empty group\n");
break;
}
if (cpus_intersects(groupmask, group->cpumask)) {
- printk("\n");
+ printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
}
cpus_or(groupmask, groupmask, group->cpumask);
cpumask_scnprintf(str, NR_CPUS, group->cpumask);
- printk(" %s", str);
+ printk(KERN_CONT " %s", str);
group = group->next;
} while (group != sd->groups);
- printk("\n");
+ printk(KERN_CONT "\n");
if (!cpus_equal(sd->span, groupmask))
printk(KERN_ERR "ERROR: groups don't span "
struct sched_group **sg)
{
int group;
- cpumask_t mask = cpu_sibling_map[cpu];
+ cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
if (sg)
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
#elif defined(CONFIG_SCHED_SMT)
- cpumask_t mask = cpu_sibling_map[cpu];
+ cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
#else
/*
* Allocate the per-node list of sched groups
*/
- sched_group_nodes = kzalloc(sizeof(struct sched_group *)*MAX_NUMNODES,
+ sched_group_nodes = kcalloc(MAX_NUMNODES, sizeof(struct sched_group *),
GFP_KERNEL);
if (!sched_group_nodes) {
printk(KERN_WARNING "Can not alloc sched group node list\n");
p = sd;
sd = &per_cpu(cpu_domains, i);
*sd = SD_SIBLING_INIT;
- sd->span = cpu_sibling_map[i];
+ sd->span = per_cpu(cpu_sibling_map, i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
p->child = sd;
#ifdef CONFIG_SCHED_SMT
/* Set up CPU (sibling) groups */
for_each_cpu_mask(i, *cpu_map) {
- cpumask_t this_sibling_map = cpu_sibling_map[i];
+ cpumask_t 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))
continue;
return -ENOMEM;
#endif
}
+
+static cpumask_t *doms_cur; /* current sched domains */
+static int ndoms_cur; /* number of sched 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.
+ */
+static cpumask_t fallback_doms;
+
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * 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)
{
- cpumask_t cpu_default_map;
- int err;
-
- /*
- * Setup mask for cpus without special case scheduling requirements.
- * For now this just excludes isolated cpus, but could be used to
- * exclude other special cases in the future.
- */
- cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
-
- err = build_sched_domains(&cpu_default_map);
-
- return err;
+ ndoms_cur = 1;
+ doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+ if (!doms_cur)
+ doms_cur = &fallback_doms;
+ cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+ register_sched_domain_sysctl();
+ return build_sched_domains(doms_cur);
}
static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
{
int i;
+ unregister_sched_domain_sysctl();
+
for_each_cpu_mask(i, *cpu_map)
cpu_attach_domain(NULL, i);
synchronize_sched();
}
/*
- * Partition sched domains as specified by the cpumasks below.
- * This attaches all cpus from the cpumasks to the NULL domain,
- * waits for a RCU quiescent period, recalculates sched
- * domain information and then attaches them back to the
- * correct sched domains
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * 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'.
+ * 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
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be kmalloc'd. This routine takes
+ * ownership of it and will kfree it when done with it. If the caller
+ * failed the kmalloc call, then it can pass in doms_new == NULL,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms'.
+ *
* Call with hotplug lock held
*/
-int partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
+void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
{
- cpumask_t change_map;
- int err = 0;
+ int i, j;
- cpus_and(*partition1, *partition1, cpu_online_map);
- cpus_and(*partition2, *partition2, cpu_online_map);
- cpus_or(change_map, *partition1, *partition2);
+ if (doms_new == NULL) {
+ ndoms_new = 1;
+ doms_new = &fallback_doms;
+ cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+ }
- /* Detach sched domains from all of the affected cpus */
- detach_destroy_domains(&change_map);
- if (!cpus_empty(*partition1))
- err = build_sched_domains(partition1);
- if (!err && !cpus_empty(*partition2))
- err = build_sched_domains(partition2);
+ /* Destroy deleted domains */
+ for (i = 0; i < ndoms_cur; i++) {
+ for (j = 0; j < ndoms_new; j++) {
+ if (cpus_equal(doms_cur[i], doms_new[j]))
+ goto match1;
+ }
+ /* no match - a current sched domain not in new doms_new[] */
+ detach_destroy_domains(doms_cur + i);
+match1:
+ ;
+ }
- return err;
+ /* 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]))
+ goto match2;
+ }
+ /* no match - add a new doms_new */
+ build_sched_domains(doms_new + i);
+match2:
+ ;
+ }
+
+ /* Remember the new sched domains */
+ if (doms_cur != &fallback_doms)
+ kfree(doms_cur);
+ doms_cur = doms_new;
+ ndoms_cur = ndoms_new;
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
- init_sched_domain_sysctl();
-
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed(current, non_isolated_cpus) < 0)
BUG();
read_lock_irq(&tasklist_lock);
do_each_thread(g, p) {
+ /*
+ * Only normalize user tasks:
+ */
+ if (!p->mm)
+ continue;
+
p->se.exec_start = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
spin_lock_irqsave(&p->pi_lock, flags);
rq = __task_rq_lock(p);
- if (!is_migration_thread(p, rq))
- normalize_task(rq, p);
+ normalize_task(rq, p);
__task_rq_unlock(rq);
spin_unlock_irqrestore(&p->pi_lock, flags);
if (tg->shares == shares)
goto done;
- /* return -EINVAL if the new value is not sane */
-
tg->shares = shares;
for_each_possible_cpu(i)
set_se_shares(tg->se[i], shares);
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_FAIR_CGROUP_SCHED
+
+/* return corresponding task_group object of a cgroup */
+static inline struct task_group *cgroup_tg(struct cgroup *cont)
+{
+ return container_of(cgroup_subsys_state(cont, cpu_cgroup_subsys_id),
+ struct task_group, css);
+}
+
+static struct cgroup_subsys_state *
+cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct task_group *tg;
+
+ if (!cont->parent) {
+ /* This is early initialization for the top cgroup */
+ init_task_group.css.cgroup = cont;
+ return &init_task_group.css;
+ }
+
+ /* we support only 1-level deep hierarchical scheduler atm */
+ if (cont->parent->parent)
+ return ERR_PTR(-EINVAL);
+
+ tg = sched_create_group();
+ if (IS_ERR(tg))
+ return ERR_PTR(-ENOMEM);
+
+ /* Bind the cgroup to task_group object we just created */
+ tg->css.cgroup = cont;
+
+ return &tg->css;
+}
+
+static void cpu_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ struct task_group *tg = cgroup_tg(cont);
+
+ sched_destroy_group(tg);
+}
+
+static int cpu_cgroup_can_attach(struct cgroup_subsys *ss,
+ struct cgroup *cont, struct task_struct *tsk)
+{
+ /* We don't support RT-tasks being in separate groups */
+ if (tsk->sched_class != &fair_sched_class)
+ return -EINVAL;
+
+ return 0;
+}
+
+static void
+cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+ struct cgroup *old_cont, struct task_struct *tsk)
+{
+ sched_move_task(tsk);
+}
+
+static ssize_t cpu_shares_write(struct cgroup *cont, struct cftype *cftype,
+ struct file *file, const char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ unsigned long shareval;
+ struct task_group *tg = cgroup_tg(cont);
+ char buffer[2*sizeof(unsigned long) + 1];
+ int rc;
+
+ if (nbytes > 2*sizeof(unsigned long)) /* safety check */
+ return -E2BIG;
+
+ if (copy_from_user(buffer, userbuf, nbytes))
+ return -EFAULT;
+
+ buffer[nbytes] = 0; /* nul-terminate */
+ shareval = simple_strtoul(buffer, NULL, 10);
+
+ rc = sched_group_set_shares(tg, shareval);
+
+ return (rc < 0 ? rc : nbytes);
+}
+
+static u64 cpu_shares_read_uint(struct cgroup *cont, struct cftype *cft)
+{
+ struct task_group *tg = cgroup_tg(cont);
+
+ return (u64) tg->shares;
+}
+
+static struct cftype cpu_shares = {
+ .name = "shares",
+ .read_uint = cpu_shares_read_uint,
+ .write = cpu_shares_write,
+};
+
+static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_file(cont, ss, &cpu_shares);
+}
+
+struct cgroup_subsys cpu_cgroup_subsys = {
+ .name = "cpu",
+ .create = cpu_cgroup_create,
+ .destroy = cpu_cgroup_destroy,
+ .can_attach = cpu_cgroup_can_attach,
+ .attach = cpu_cgroup_attach,
+ .populate = cpu_cgroup_populate,
+ .subsys_id = cpu_cgroup_subsys_id,
+ .early_init = 1,
+};
+
+#endif /* CONFIG_FAIR_CGROUP_SCHED */