#define SCALE_PRIO(x, prio) \
max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)
-static inline unsigned int task_timeslice(task_t *p)
+static unsigned int task_timeslice(task_t *p)
{
if (p->static_prio < NICE_TO_PRIO(0))
return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
static DEFINE_PER_CPU(struct runqueue, runqueues);
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
#define for_each_domain(cpu, domain) \
- for (domain = cpu_rq(cpu)->sd; domain; domain = domain->parent)
+for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-/*
- * Default context-switch locking:
- */
#ifndef prepare_arch_switch
-# define prepare_arch_switch(rq, next) do { } while (0)
-# define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock)
-# define task_running(rq, p) ((rq)->curr == (p))
+# define prepare_arch_switch(next) do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev) do { } while (0)
+#endif
+
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline int task_running(runqueue_t *rq, task_t *p)
+{
+ return rq->curr == p;
+}
+
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+{
+}
+
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+{
+ spin_unlock_irq(&rq->lock);
+}
+
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+static inline int task_running(runqueue_t *rq, task_t *p)
+{
+#ifdef CONFIG_SMP
+ return p->oncpu;
+#else
+ return rq->curr == p;
+#endif
+}
+
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+{
+#ifdef CONFIG_SMP
+ /*
+ * We can optimise this out completely for !SMP, because the
+ * SMP rebalancing from interrupt is the only thing that cares
+ * here.
+ */
+ next->oncpu = 1;
+#endif
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ spin_unlock_irq(&rq->lock);
+#else
+ spin_unlock(&rq->lock);
#endif
+}
+
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+{
+#ifdef CONFIG_SMP
+ /*
+ * After ->oncpu is cleared, the task can be moved to a different CPU.
+ * We must ensure this doesn't happen until the switch is completely
+ * finished.
+ */
+ smp_wmb();
+ prev->oncpu = 0;
+#endif
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
/*
* task_rq_lock - lock the runqueue a given task resides on and disable
* bump this up when changing the output format or the meaning of an existing
* format, so that tools can adapt (or abort)
*/
-#define SCHEDSTAT_VERSION 11
+#define SCHEDSTAT_VERSION 12
static int show_schedstat(struct seq_file *seq, void *v)
{
#ifdef CONFIG_SMP
/* domain-specific stats */
+ preempt_disable();
for_each_domain(cpu, sd) {
enum idle_type itype;
char mask_str[NR_CPUS];
sd->lb_nobusyq[itype],
sd->lb_nobusyg[itype]);
}
- seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu\n",
+ seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
- sd->sbe_pushed, sd->sbe_attempts,
+ sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
+ sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
}
+ preempt_enable();
#endif
}
return 0;
return rq;
}
-#ifdef CONFIG_SCHED_SMT
-static int cpu_and_siblings_are_idle(int cpu)
-{
- int sib;
- for_each_cpu_mask(sib, cpu_sibling_map[cpu]) {
- if (idle_cpu(sib))
- continue;
- return 0;
- }
-
- return 1;
-}
-#else
-#define cpu_and_siblings_are_idle(A) idle_cpu(A)
-#endif
-
#ifdef CONFIG_SCHEDSTATS
/*
* Called when a process is dequeued from the active array and given
rq->nr_running++;
}
-static void recalc_task_prio(task_t *p, unsigned long long now)
+static int recalc_task_prio(task_t *p, unsigned long long now)
{
/* Caller must always ensure 'now >= p->timestamp' */
unsigned long long __sleep_time = now - p->timestamp;
}
}
- p->prio = effective_prio(p);
+ return effective_prio(p);
}
/*
}
#endif
- recalc_task_prio(p, now);
+ p->prio = recalc_task_prio(p, now);
/*
* This checks to make sure it's not an uninterruptible task
}
#ifdef CONFIG_SMP
-enum request_type {
- REQ_MOVE_TASK,
- REQ_SET_DOMAIN,
-};
-
typedef struct {
struct list_head list;
- enum request_type type;
- /* For REQ_MOVE_TASK */
task_t *task;
int dest_cpu;
- /* For REQ_SET_DOMAIN */
- struct sched_domain *sd;
-
struct completion done;
} migration_req_t;
}
init_completion(&req->done);
- req->type = REQ_MOVE_TASK;
req->task = p;
req->dest_cpu = dest_cpu;
list_add(&req->list, &rq->migration_queue);
return max(rq->cpu_load[type-1], load_now);
}
-#endif
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+{
+ struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+ unsigned long min_load = ULONG_MAX, this_load = 0;
+ int load_idx = sd->forkexec_idx;
+ int imbalance = 100 + (sd->imbalance_pct-100)/2;
+
+ do {
+ unsigned long load, avg_load;
+ int local_group;
+ int i;
+
+ local_group = cpu_isset(this_cpu, group->cpumask);
+ /* XXX: put a cpus allowed check */
+
+ /* Tally up the load of all CPUs in the group */
+ avg_load = 0;
+
+ for_each_cpu_mask(i, group->cpumask) {
+ /* Bias balancing toward cpus of our domain */
+ if (local_group)
+ load = source_load(i, load_idx);
+ else
+ load = target_load(i, load_idx);
+
+ avg_load += load;
+ }
+
+ /* Adjust by relative CPU power of the group */
+ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+ if (local_group) {
+ this_load = avg_load;
+ this = group;
+ } else if (avg_load < min_load) {
+ min_load = avg_load;
+ idlest = group;
+ }
+ group = group->next;
+ } while (group != sd->groups);
+
+ if (!idlest || 100*this_load < imbalance*min_load)
+ return NULL;
+ return idlest;
+}
+
+/*
+ * find_idlest_queue - find the idlest runqueue among the cpus in group.
+ */
+static int find_idlest_cpu(struct sched_group *group, int this_cpu)
+{
+ unsigned long load, min_load = ULONG_MAX;
+ int idlest = -1;
+ int i;
+
+ for_each_cpu_mask(i, group->cpumask) {
+ load = source_load(i, 0);
+
+ if (load < min_load || (load == min_load && i == this_cpu)) {
+ min_load = load;
+ idlest = i;
+ }
+ }
+
+ return idlest;
+}
+
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int sched_balance_self(int cpu, int flag)
+{
+ struct task_struct *t = current;
+ struct sched_domain *tmp, *sd = NULL;
+
+ for_each_domain(cpu, tmp)
+ if (tmp->flags & flag)
+ sd = tmp;
+
+ while (sd) {
+ cpumask_t span;
+ struct sched_group *group;
+ int new_cpu;
+ int weight;
+
+ span = sd->span;
+ group = find_idlest_group(sd, t, cpu);
+ if (!group)
+ goto nextlevel;
+
+ new_cpu = find_idlest_cpu(group, cpu);
+ if (new_cpu == -1 || new_cpu == cpu)
+ goto nextlevel;
+
+ /* Now try balancing at a lower domain level */
+ cpu = new_cpu;
+nextlevel:
+ sd = NULL;
+ weight = cpus_weight(span);
+ for_each_domain(cpu, tmp) {
+ if (weight <= cpus_weight(tmp->span))
+ break;
+ if (tmp->flags & flag)
+ sd = tmp;
+ }
+ /* while loop will break here if sd == NULL */
+ }
+
+ return cpu;
+}
+
+#endif /* CONFIG_SMP */
/*
* wake_idle() will wake a task on an idle cpu if task->cpu is
return try_to_wake_up(p, state, 0);
}
-#ifdef CONFIG_SMP
-static int find_idlest_cpu(struct task_struct *p, int this_cpu,
- struct sched_domain *sd);
-#endif
-
/*
* Perform scheduler related setup for a newly forked process p.
* p is forked by current.
*/
-void fastcall sched_fork(task_t *p)
+void fastcall sched_fork(task_t *p, int clone_flags)
{
+ int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+ cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
+#endif
+ set_task_cpu(p, cpu);
+
/*
* We mark the process as running here, but have not actually
* inserted it onto the runqueue yet. This guarantees that
p->state = TASK_RUNNING;
INIT_LIST_HEAD(&p->run_list);
p->array = NULL;
- spin_lock_init(&p->switch_lock);
#ifdef CONFIG_SCHEDSTATS
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ p->oncpu = 0;
+#endif
#ifdef CONFIG_PREEMPT
- /*
- * During context-switch we hold precisely one spinlock, which
- * schedule_tail drops. (in the common case it's this_rq()->lock,
- * but it also can be p->switch_lock.) So we compensate with a count
- * of 1. Also, we want to start with kernel preemption disabled.
- */
+ /* Want to start with kernel preemption disabled. */
p->thread_info->preempt_count = 1;
#endif
/*
* runqueue lock is not a problem.
*/
current->time_slice = 1;
- preempt_disable();
scheduler_tick();
- local_irq_enable();
- preempt_enable();
- } else
- local_irq_enable();
+ }
+ local_irq_enable();
+ put_cpu();
}
/*
runqueue_t *rq, *this_rq;
rq = task_rq_lock(p, &flags);
- cpu = task_cpu(p);
- this_cpu = smp_processor_id();
-
BUG_ON(p->state != TASK_RUNNING);
+ this_cpu = smp_processor_id();
+ cpu = task_cpu(p);
/*
* We decrease the sleep average of forking parents
task_rq_unlock(rq, &flags);
}
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void prepare_task_switch(runqueue_t *rq, task_t *next)
+{
+ prepare_lock_switch(rq, next);
+ prepare_arch_switch(next);
+}
+
/**
* finish_task_switch - clean up after a task-switch
* @prev: the thread we just switched away from.
*
- * We enter this with the runqueue still locked, and finish_arch_switch()
- * will unlock it along with doing any other architecture-specific cleanup
- * actions.
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
*
* Note that we may have delayed dropping an mm in context_switch(). If
* so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
-static inline void finish_task_switch(task_t *prev)
+static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
__releases(rq->lock)
{
- runqueue_t *rq = this_rq();
struct mm_struct *mm = rq->prev_mm;
unsigned long prev_task_flags;
* Manfred Spraul <manfred@colorfullife.com>
*/
prev_task_flags = prev->flags;
- finish_arch_switch(rq, prev);
+ finish_arch_switch(prev);
+ finish_lock_switch(rq, prev);
if (mm)
mmdrop(mm);
if (unlikely(prev_task_flags & PF_DEAD))
asmlinkage void schedule_tail(task_t *prev)
__releases(rq->lock)
{
- finish_task_switch(prev);
-
+ runqueue_t *rq = this_rq();
+ finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+ /* In this case, finish_task_switch does not reenable preemption */
+ preempt_enable();
+#endif
if (current->set_child_tid)
put_user(current->pid, current->set_child_tid);
}
}
}
-/*
- * find_idlest_cpu - find the least busy runqueue.
- */
-static int find_idlest_cpu(struct task_struct *p, int this_cpu,
- struct sched_domain *sd)
-{
- unsigned long load, min_load, this_load;
- int i, min_cpu;
- cpumask_t mask;
-
- min_cpu = UINT_MAX;
- min_load = ULONG_MAX;
-
- cpus_and(mask, sd->span, p->cpus_allowed);
-
- for_each_cpu_mask(i, mask) {
- load = target_load(i, sd->wake_idx);
-
- if (load < min_load) {
- min_cpu = i;
- min_load = load;
-
- /* break out early on an idle CPU: */
- if (!min_load)
- break;
- }
- }
-
- /* add +1 to account for the new task */
- this_load = source_load(this_cpu, sd->wake_idx) + SCHED_LOAD_SCALE;
-
- /*
- * Would with the addition of the new task to the
- * current CPU there be an imbalance between this
- * CPU and the idlest CPU?
- *
- * Use half of the balancing threshold - new-context is
- * a good opportunity to balance.
- */
- if (min_load*(100 + (sd->imbalance_pct-100)/2) < this_load*100)
- return min_cpu;
-
- return this_cpu;
-}
-
/*
* If dest_cpu is allowed for this process, migrate the task to it.
* This is accomplished by forcing the cpu_allowed mask to only
}
/*
- * sched_exec(): find the highest-level, exec-balance-capable
- * domain and try to migrate the task to the least loaded CPU.
- *
- * execve() is a valuable balancing opportunity, because at this point
- * the task has the smallest effective memory and cache footprint.
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
*/
void sched_exec(void)
{
- struct sched_domain *tmp, *sd = NULL;
int new_cpu, this_cpu = get_cpu();
-
- /* Prefer the current CPU if there's only this task running */
- if (this_rq()->nr_running <= 1)
- goto out;
-
- for_each_domain(this_cpu, tmp)
- if (tmp->flags & SD_BALANCE_EXEC)
- sd = tmp;
-
- if (sd) {
- schedstat_inc(sd, sbe_attempts);
- new_cpu = find_idlest_cpu(current, this_cpu, sd);
- if (new_cpu != this_cpu) {
- schedstat_inc(sd, sbe_pushed);
- put_cpu();
- sched_migrate_task(current, new_cpu);
- return;
- }
- }
-out:
+ new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
put_cpu();
+ if (new_cpu != this_cpu)
+ sched_migrate_task(current, new_cpu);
}
/*
/*
* Aggressive migration if:
- * 1) the [whole] cpu is idle, or
+ * 1) task is cache cold, or
* 2) too many balance attempts have failed.
*/
- if (cpu_and_siblings_are_idle(this_cpu) || \
- sd->nr_balance_failed > sd->cache_nice_tries)
+ if (sd->nr_balance_failed > sd->cache_nice_tries)
return 1;
if (task_hot(p, rq->timestamp_last_tick, sd))
if (local_group) {
this_load = avg_load;
this = group;
- goto nextgroup;
} else if (avg_load > max_load) {
max_load = avg_load;
busiest = group;
}
-nextgroup:
group = group->next;
} while (group != sd->groups);
return busiest;
}
+/*
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
+ */
+#define MAX_PINNED_INTERVAL 512
+
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
struct sched_group *group;
runqueue_t *busiest;
unsigned long imbalance;
- int nr_moved, all_pinned;
+ int nr_moved, all_pinned = 0;
int active_balance = 0;
spin_lock(&this_rq->lock);
sd->nr_balance_failed = 0;
/* tune up the balancing interval */
- if (sd->balance_interval < sd->max_interval)
+ if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+ (sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
return 0;
#ifdef CONFIG_SCHED_SMT
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
- struct sched_domain *sd = this_rq->sd;
+ struct sched_domain *tmp, *sd = NULL;
cpumask_t sibling_map;
int i;
- if (!(sd->flags & SD_SHARE_CPUPOWER))
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
+
+ if (!sd)
return;
/*
static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
- struct sched_domain *sd = this_rq->sd;
+ struct sched_domain *tmp, *sd = NULL;
cpumask_t sibling_map;
prio_array_t *array;
int ret = 0, i;
task_t *p;
- if (!(sd->flags & SD_SHARE_CPUPOWER))
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
+
+ if (!sd)
return 0;
/*
struct list_head *queue;
unsigned long long now;
unsigned long run_time;
- int cpu, idx;
+ int cpu, idx, new_prio;
/*
* Test if we are atomic. Since do_exit() needs to call into
delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
array = next->array;
- dequeue_task(next, array);
- recalc_task_prio(next, next->timestamp + delta);
- enqueue_task(next, array);
+ new_prio = recalc_task_prio(next, next->timestamp + delta);
+
+ if (unlikely(next->prio != new_prio)) {
+ dequeue_task(next, array);
+ next->prio = new_prio;
+ enqueue_task(next, array);
+ } else
+ requeue_task(next, array);
}
next->activated = 0;
switch_tasks:
rq->curr = next;
++*switch_count;
- prepare_arch_switch(rq, next);
+ prepare_task_switch(rq, next);
prev = context_switch(rq, prev, next);
barrier();
-
- finish_task_switch(prev);
+ /*
+ * this_rq must be evaluated again because prev may have moved
+ * CPUs since it called schedule(), thus the 'rq' on its stack
+ * frame will be invalid.
+ */
+ finish_task_switch(this_rq(), prev);
} else
spin_unlock_irq(&rq->lock);
{
return TASK_NICE(p);
}
-
-/*
- * The only users of task_nice are binfmt_elf and binfmt_elf32.
- * binfmt_elf is no longer modular, but binfmt_elf32 still is.
- * Therefore, task_nice is needed if there is a compat_mode.
- */
-#ifdef CONFIG_COMPAT
EXPORT_SYMBOL_GPL(task_nice);
-#endif
/**
* idle_cpu - is a given cpu idle currently?
if ((policy == SCHED_NORMAL) != (param->sched_priority == 0))
return -EINVAL;
- if ((policy == SCHED_FIFO || policy == SCHED_RR) &&
- param->sched_priority > p->signal->rlim[RLIMIT_RTPRIO].rlim_cur &&
- !capable(CAP_SYS_NICE))
- return -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
- return -EPERM;
+ /*
+ * Allow unprivileged RT tasks to decrease priority:
+ */
+ if (!capable(CAP_SYS_NICE)) {
+ /* can't change policy */
+ if (policy != p->policy)
+ return -EPERM;
+ /* can't increase priority */
+ if (policy != SCHED_NORMAL &&
+ param->sched_priority > p->rt_priority &&
+ param->sched_priority >
+ p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
+ return -EPERM;
+ /* can't change other user's priorities */
+ if ((current->euid != p->euid) &&
+ (current->euid != p->uid))
+ return -EPERM;
+ }
retval = security_task_setscheduler(p, policy, param);
if (retval)
spin_lock_irqsave(&rq->lock, flags);
rq->curr = rq->idle = idle;
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ idle->oncpu = 1;
+#endif
set_tsk_need_resched(idle);
spin_unlock_irqrestore(&rq->lock, flags);
struct list_head *head;
migration_req_t *req;
- if (current->flags & PF_FREEZE)
- refrigerator(PF_FREEZE);
+ try_to_freeze();
spin_lock_irq(&rq->lock);
req = list_entry(head->next, migration_req_t, list);
list_del_init(head->next);
- if (req->type == REQ_MOVE_TASK) {
- spin_unlock(&rq->lock);
- __migrate_task(req->task, cpu, req->dest_cpu);
- local_irq_enable();
- } else if (req->type == REQ_SET_DOMAIN) {
- rq->sd = req->sd;
- spin_unlock_irq(&rq->lock);
- } else {
- spin_unlock_irq(&rq->lock);
- WARN_ON(1);
- }
+ spin_unlock(&rq->lock);
+ __migrate_task(req->task, cpu, req->dest_cpu);
+ local_irq_enable();
complete(&req->done);
}
migration_req_t *req;
req = list_entry(rq->migration_queue.next,
migration_req_t, list);
- BUG_ON(req->type != REQ_MOVE_TASK);
list_del_init(&req->list);
complete(&req->done);
}
#endif
#ifdef CONFIG_SMP
-#define SCHED_DOMAIN_DEBUG
+#undef SCHED_DOMAIN_DEBUG
#ifdef SCHED_DOMAIN_DEBUG
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
int level = 0;
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
+ }
+
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
do {
#define sched_domain_debug(sd, cpu) {}
#endif
+static int sd_degenerate(struct sched_domain *sd)
+{
+ if (cpus_weight(sd->span) == 1)
+ return 1;
+
+ /* Following flags need at least 2 groups */
+ if (sd->flags & (SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC)) {
+ if (sd->groups != sd->groups->next)
+ return 0;
+ }
+
+ /* Following flags don't use groups */
+ if (sd->flags & (SD_WAKE_IDLE |
+ SD_WAKE_AFFINE |
+ SD_WAKE_BALANCE))
+ return 0;
+
+ return 1;
+}
+
+static int sd_parent_degenerate(struct sched_domain *sd,
+ struct sched_domain *parent)
+{
+ unsigned long cflags = sd->flags, pflags = parent->flags;
+
+ if (sd_degenerate(parent))
+ return 1;
+
+ if (!cpus_equal(sd->span, parent->span))
+ return 0;
+
+ /* Does parent contain flags not in child? */
+ /* WAKE_BALANCE is a subset of WAKE_AFFINE */
+ if (cflags & SD_WAKE_AFFINE)
+ pflags &= ~SD_WAKE_BALANCE;
+ /* Flags needing groups don't count if only 1 group in parent */
+ if (parent->groups == parent->groups->next) {
+ pflags &= ~(SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC);
+ }
+ if (~cflags & pflags)
+ return 0;
+
+ return 1;
+}
+
/*
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
*/
-void __devinit cpu_attach_domain(struct sched_domain *sd, int cpu)
+void cpu_attach_domain(struct sched_domain *sd, int cpu)
{
- migration_req_t req;
- unsigned long flags;
runqueue_t *rq = cpu_rq(cpu);
- int local = 1;
-
- sched_domain_debug(sd, cpu);
-
- spin_lock_irqsave(&rq->lock, flags);
+ struct sched_domain *tmp;
- if (cpu == smp_processor_id() || !cpu_online(cpu)) {
- rq->sd = sd;
- } else {
- init_completion(&req.done);
- req.type = REQ_SET_DOMAIN;
- req.sd = sd;
- list_add(&req.list, &rq->migration_queue);
- local = 0;
+ /* Remove the sched domains which do not contribute to scheduling. */
+ for (tmp = sd; tmp; tmp = tmp->parent) {
+ struct sched_domain *parent = tmp->parent;
+ if (!parent)
+ break;
+ if (sd_parent_degenerate(tmp, parent))
+ tmp->parent = parent->parent;
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ if (sd && sd_degenerate(sd))
+ sd = sd->parent;
- if (!local) {
- wake_up_process(rq->migration_thread);
- wait_for_completion(&req.done);
- }
+ sched_domain_debug(sd, cpu);
+
+ rcu_assign_pointer(rq->sd, sd);
}
/* cpus with isolated domains */
* covered by the given span, and will set each group's ->cpumask correctly,
* and ->cpu_power to 0.
*/
-void __devinit init_sched_build_groups(struct sched_group groups[],
+void init_sched_build_groups(struct sched_group groups[],
cpumask_t span, int (*group_fn)(int cpu))
{
struct sched_group *first = NULL, *last = NULL;
#ifdef ARCH_HAS_SCHED_DOMAIN
-extern void __devinit arch_init_sched_domains(void);
-extern void __devinit arch_destroy_sched_domains(void);
+extern void build_sched_domains(const cpumask_t *cpu_map);
+extern void arch_init_sched_domains(const cpumask_t *cpu_map);
+extern void arch_destroy_sched_domains(const cpumask_t *cpu_map);
#else
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static struct sched_group sched_group_cpus[NR_CPUS];
-static int __devinit cpu_to_cpu_group(int cpu)
+static int cpu_to_cpu_group(int cpu)
{
return cpu;
}
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static struct sched_group sched_group_phys[NR_CPUS];
-static int __devinit cpu_to_phys_group(int cpu)
+static int cpu_to_phys_group(int cpu)
{
#ifdef CONFIG_SCHED_SMT
return first_cpu(cpu_sibling_map[cpu]);
static DEFINE_PER_CPU(struct sched_domain, node_domains);
static struct sched_group sched_group_nodes[MAX_NUMNODES];
-static int __devinit cpu_to_node_group(int cpu)
+static int cpu_to_node_group(int cpu)
{
return cpu_to_node(cpu);
}
#endif
/*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
*/
-static void __devinit arch_init_sched_domains(void)
+static void build_sched_domains(const cpumask_t *cpu_map)
{
int i;
- cpumask_t cpu_default_map;
-
-#if defined(CONFIG_SCHED_SMT) && defined(CONFIG_NUMA)
- check_sibling_maps();
-#endif
- /*
- * 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_complement(cpu_default_map, cpu_isolated_map);
- cpus_and(cpu_default_map, cpu_default_map, cpu_online_map);
/*
- * Set up domains. Isolated domains just stay on the dummy domain.
+ * Set up domains for cpus specified by the cpu_map.
*/
- for_each_cpu_mask(i, cpu_default_map) {
+ for_each_cpu_mask(i, *cpu_map) {
int group;
struct sched_domain *sd = NULL, *p;
cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
- cpus_and(nodemask, nodemask, cpu_default_map);
+ cpus_and(nodemask, nodemask, *cpu_map);
#ifdef CONFIG_NUMA
sd = &per_cpu(node_domains, i);
group = cpu_to_node_group(i);
*sd = SD_NODE_INIT;
- sd->span = cpu_default_map;
+ sd->span = *cpu_map;
sd->groups = &sched_group_nodes[group];
#endif
group = cpu_to_cpu_group(i);
*sd = SD_SIBLING_INIT;
sd->span = cpu_sibling_map[i];
- cpus_and(sd->span, sd->span, cpu_default_map);
+ cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
sd->groups = &sched_group_cpus[group];
#endif
/* Set up CPU (sibling) groups */
for_each_online_cpu(i) {
cpumask_t this_sibling_map = cpu_sibling_map[i];
- cpus_and(this_sibling_map, this_sibling_map, cpu_default_map);
+ cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
if (i != first_cpu(this_sibling_map))
continue;
for (i = 0; i < MAX_NUMNODES; i++) {
cpumask_t nodemask = node_to_cpumask(i);
- cpus_and(nodemask, nodemask, cpu_default_map);
+ cpus_and(nodemask, nodemask, *cpu_map);
if (cpus_empty(nodemask))
continue;
#ifdef CONFIG_NUMA
/* Set up node groups */
- init_sched_build_groups(sched_group_nodes, cpu_default_map,
+ init_sched_build_groups(sched_group_nodes, *cpu_map,
&cpu_to_node_group);
#endif
/* Calculate CPU power for physical packages and nodes */
- for_each_cpu_mask(i, cpu_default_map) {
+ for_each_cpu_mask(i, *cpu_map) {
int power;
struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
}
/* Attach the domains */
- for_each_online_cpu(i) {
+ for_each_cpu_mask(i, *cpu_map) {
struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i);
cpu_attach_domain(sd, i);
}
}
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ */
+static void arch_init_sched_domains(cpumask_t *cpu_map)
+{
+ cpumask_t cpu_default_map;
-#ifdef CONFIG_HOTPLUG_CPU
-static void __devinit arch_destroy_sched_domains(void)
+#if defined(CONFIG_SCHED_SMT) && defined(CONFIG_NUMA)
+ check_sibling_maps();
+#endif
+ /*
+ * 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);
+
+ build_sched_domains(&cpu_default_map);
+}
+
+static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
{
/* Do nothing: everything is statically allocated. */
}
-#endif
#endif /* ARCH_HAS_SCHED_DOMAIN */
/*
- * Initial dummy domain for early boot and for hotplug cpu. Being static,
- * it is initialized to zero, so all balancing flags are cleared which is
- * what we want.
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
*/
-static struct sched_domain sched_domain_dummy;
+static inline void detach_destroy_domains(const cpumask_t *cpu_map)
+{
+ int i;
+
+ for_each_cpu_mask(i, *cpu_map)
+ cpu_attach_domain(NULL, i);
+ synchronize_sched();
+ arch_destroy_sched_domains(cpu_map);
+}
+
+/*
+ * 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
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
+{
+ cpumask_t change_map;
+
+ cpus_and(*partition1, *partition1, cpu_online_map);
+ cpus_and(*partition2, *partition2, cpu_online_map);
+ cpus_or(change_map, *partition1, *partition2);
+
+ /* Detach sched domains from all of the affected cpus */
+ detach_destroy_domains(&change_map);
+ if (!cpus_empty(*partition1))
+ build_sched_domains(partition1);
+ if (!cpus_empty(*partition2))
+ build_sched_domains(partition2);
+}
#ifdef CONFIG_HOTPLUG_CPU
/*
* Force a reinitialization of the sched domains hierarchy. The domains
* and groups cannot be updated in place without racing with the balancing
- * code, so we temporarily attach all running cpus to a "dummy" domain
+ * code, so we temporarily attach all running cpus to the NULL domain
* which will prevent rebalancing while the sched domains are recalculated.
*/
static int update_sched_domains(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- int i;
-
switch (action) {
case CPU_UP_PREPARE:
case CPU_DOWN_PREPARE:
- for_each_online_cpu(i)
- cpu_attach_domain(&sched_domain_dummy, i);
- arch_destroy_sched_domains();
+ detach_destroy_domains(&cpu_online_map);
return NOTIFY_OK;
case CPU_UP_CANCELED:
}
/* The hotplug lock is already held by cpu_up/cpu_down */
- arch_init_sched_domains();
+ arch_init_sched_domains(&cpu_online_map);
return NOTIFY_OK;
}
void __init sched_init_smp(void)
{
lock_cpu_hotplug();
- arch_init_sched_domains();
+ arch_init_sched_domains(&cpu_online_map);
unlock_cpu_hotplug();
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
rq->best_expired_prio = MAX_PRIO;
#ifdef CONFIG_SMP
- rq->sd = &sched_domain_dummy;
+ rq->sd = NULL;
for (j = 1; j < 3; j++)
rq->cpu_load[j] = 0;
rq->active_balance = 0;
git.openpandora.org / pandora-kernel.git / blobdiff