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.
struct rt_prio_array active;
unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- int highest_prio; /* highest queued rt task prio */
+ struct {
+ int curr; /* highest queued rt task prio */
+#ifdef CONFIG_SMP
+ int next; /* next highest */
+#endif
+ } highest_prio;
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
int overloaded;
+ struct plist_head pushable_tasks;
#endif
int rt_throttled;
u64 rt_time;
* 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
#endif
+#ifdef CONFIG_PREEMPT
+
/*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations. This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below. However, it
+ * also adds more overhead and therefore may reduce throughput.
*/
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+{
+ spin_unlock(&this_rq->lock);
+ double_rq_lock(this_rq, busiest);
+
+ return 1;
+}
+
+#else
+/*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry. This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+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);
return ret;
}
+#endif /* CONFIG_PREEMPT */
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+{
+ if (unlikely(!irqs_disabled())) {
+ /* printk() doesn't work good under rq->lock */
+ spin_unlock(&this_rq->lock);
+ BUG_ON(1);
+ }
+
+ return _double_lock_balance(this_rq, busiest);
+}
+
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
+ if (wakeup)
+ p->se.start_runtime = p->se.sum_exec_runtime;
+
sched_info_queued(p);
p->sched_class->enqueue_task(rq, p, wakeup);
p->se.on_rq = 1;
static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
- if (sleep && p->se.last_wakeup) {
- update_avg(&p->se.avg_overlap,
- p->se.sum_exec_runtime - p->se.last_wakeup);
- p->se.last_wakeup = 0;
+ if (sleep) {
+ if (p->se.last_wakeup) {
+ update_avg(&p->se.avg_overlap,
+ p->se.sum_exec_runtime - p->se.last_wakeup);
+ p->se.last_wakeup = 0;
+ } else {
+ update_avg(&p->se.avg_wakeup,
+ sysctl_sched_wakeup_granularity);
+ }
}
sched_info_dequeued(p);
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;
activate_task(rq, p, 1);
success = 1;
+ /*
+ * Only attribute actual wakeups done by this task.
+ */
+ if (!in_interrupt()) {
+ struct sched_entity *se = ¤t->se;
+ u64 sample = se->sum_exec_runtime;
+
+ if (se->last_wakeup)
+ sample -= se->last_wakeup;
+ else
+ sample -= se->start_runtime;
+ update_avg(&se->avg_wakeup, sample);
+
+ se->last_wakeup = se->sum_exec_runtime;
+ }
+
out_running:
trace_sched_wakeup(rq, p, success);
check_preempt_curr(rq, p, sync);
p->sched_class->task_wake_up(rq, p);
#endif
out:
- current->se.last_wakeup = current->se.sum_exec_runtime;
-
task_rq_unlock(rq, &flags);
return success;
p->se.prev_sum_exec_runtime = 0;
p->se.last_wakeup = 0;
p->se.avg_overlap = 0;
+ p->se.start_runtime = 0;
+ p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
+ plist_node_init(&p->pushable_tasks, MAX_PRIO);
+
put_cpu();
}
{
struct mm_struct *mm = rq->prev_mm;
long prev_state;
+#ifdef CONFIG_SMP
+ int post_schedule = 0;
+
+ if (current->sched_class->needs_post_schedule)
+ post_schedule = current->sched_class->needs_post_schedule(rq);
+#endif
rq->prev_mm = NULL;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
- if (current->sched_class->post_schedule)
+ if (post_schedule)
current->sched_class->post_schedule(rq);
#endif
pulled++;
rem_load_move -= p->se.load.weight;
+#ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible kernels
+ * will stop after the first task is pulled to minimize the critical
+ * section.
+ */
+ if (idle == CPU_NEWLY_IDLE)
+ goto out;
+#endif
+
/*
* We only want to steal up to the prescribed amount of weighted load.
*/
sd, idle, all_pinned, &this_best_prio);
class = class->next;
+#ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible
+ * kernels will stop after the first task is pulled to minimize
+ * the critical section.
+ */
if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
break;
-
+#endif
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
int cpu = smp_processor_id();
if (stop_tick) {
- cpumask_set_cpu(cpu, nohz.cpu_mask);
cpu_rq(cpu)->in_nohz_recently = 1;
- /*
- * If we are going offline and still the leader, give up!
- */
- if (!cpu_active(cpu) &&
- atomic_read(&nohz.load_balancer) == cpu) {
+ if (!cpu_active(cpu)) {
+ if (atomic_read(&nohz.load_balancer) != cpu)
+ return 0;
+
+ /*
+ * If we are going offline and still the leader,
+ * give up!
+ */
if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
BUG();
+
return 0;
}
+ cpumask_set_cpu(cpu, nohz.cpu_mask);
+
/* time for ilb owner also to sleep */
if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu)
/*
* 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?
* 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;
* @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;
* @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_var_t new_mask;
int retval;
* @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_var_t mask;
* 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;
* 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 struct cpumask *cpu_map,
#ifdef CONFIG_NUMA
if (cpumask_weight(cpu_map) >
SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
- sd = &per_cpu(allnodes_domains, i);
+ 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));
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;
__set_bit(MAX_RT_PRIO, array->bitmap);
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- rt_rq->highest_prio = MAX_RT_PRIO;
+ rt_rq->highest_prio.curr = MAX_RT_PRIO;
+#ifdef CONFIG_SMP
+ rt_rq->highest_prio.next = MAX_RT_PRIO;
+#endif
#endif
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
+ plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
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.
*/