* by Peter Williams
* 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
+ * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
+ * Thomas Gleixner, Mike Kravetz
*/
#include <linux/mm.h>
#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/reciprocal_div.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
+#include <linux/hrtimer.h>
#include <asm/tlb.h>
+#include <asm/irq_regs.h>
/*
* Scheduler clock - returns current time in nanosec units.
*/
unsigned long long __attribute__((weak)) sched_clock(void)
{
- return (unsigned long long)jiffies * (1000000000 / HZ);
+ return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
}
/*
#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
/*
- * Some helpers for converting nanosecond timing to jiffy resolution
+ * Helpers for converting nanosecond timing to jiffy resolution
*/
-#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (1000000000 / HZ))
-#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ))
+#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
#define NICE_0_LOAD SCHED_LOAD_SCALE
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
#ifdef CONFIG_FAIR_GROUP_SCHED
+#include <linux/cgroup.h>
+
struct cfs_rq;
+static LIST_HEAD(task_groups);
+
/* 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 */
struct cfs_rq **cfs_rq;
+
+ struct sched_rt_entity **rt_se;
+ struct rt_rq **rt_rq;
+
+ unsigned int rt_ratio;
+
+ /*
+ * shares assigned to a task group governs how much of cpu bandwidth
+ * is allocated to the group. The more shares a group has, the more is
+ * the cpu bandwidth allocated to it.
+ *
+ * For ex, lets say that there are three task groups, A, B and C which
+ * have been assigned shares 1000, 2000 and 3000 respectively. Then,
+ * cpu bandwidth allocated by the scheduler to task groups A, B and C
+ * should be:
+ *
+ * Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
+ * Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
+ * Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
+ *
+ * The weight assigned to a task group's schedulable entities on every
+ * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
+ * group's shares. For ex: lets say that task group A has been
+ * assigned shares of 1000 and there are two CPUs in a system. Then,
+ *
+ * tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
+ *
+ * Note: It's not necessary that each of a task's group schedulable
+ * entity have the same weight on all CPUs. If the group
+ * has 2 of its tasks on CPU0 and 1 task on CPU1, then a
+ * better distribution of weight could be:
+ *
+ * tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
+ * tg_A->se[1]->load.weight = 1/2 * 2000 = 667
+ *
+ * rebalance_shares() is responsible for distributing the shares of a
+ * task groups like this among the group's schedulable entities across
+ * cpus.
+ *
+ */
unsigned long shares;
- /* spinlock to serialize modification to shares */
- spinlock_t lock;
+
+ struct rcu_head rcu;
+ struct list_head list;
};
/* Default task group's sched entity on each cpu */
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
+static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+
static struct sched_entity *init_sched_entity_p[NR_CPUS];
static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
+static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
+static struct rt_rq *init_rt_rq_p[NR_CPUS];
+
+/* task_group_mutex serializes add/remove of task groups and also changes to
+ * a task group's cpu shares.
+ */
+static DEFINE_MUTEX(task_group_mutex);
+
+/* doms_cur_mutex serializes access to doms_cur[] array */
+static DEFINE_MUTEX(doms_cur_mutex);
+
+#ifdef CONFIG_SMP
+/* kernel thread that runs rebalance_shares() periodically */
+static struct task_struct *lb_monitor_task;
+static int load_balance_monitor(void *unused);
+#endif
+
+static void set_se_shares(struct sched_entity *se, unsigned long shares);
+
/* Default task group.
* Every task in system belong to this group at bootup.
*/
struct task_group init_task_group = {
- .se = init_sched_entity_p,
+ .se = init_sched_entity_p,
.cfs_rq = init_cfs_rq_p,
+
+ .rt_se = init_sched_rt_entity_p,
+ .rt_rq = init_rt_rq_p,
};
#ifdef CONFIG_FAIR_USER_SCHED
-# define INIT_TASK_GRP_LOAD 2*NICE_0_LOAD
+# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else
-# define INIT_TASK_GRP_LOAD NICE_0_LOAD
+# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
#endif
-static int init_task_group_load = INIT_TASK_GRP_LOAD;
+#define MIN_GROUP_SHARES 2
+
+static int init_task_group_load = INIT_TASK_GROUP_LOAD;
/* return group to which a task belongs */
static inline struct task_group *task_group(struct task_struct *p)
#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;
+ tg = &init_task_group;
#endif
-
return tg;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
-static inline void set_task_cfs_rq(struct task_struct *p)
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
- p->se.cfs_rq = task_group(p)->cfs_rq[task_cpu(p)];
- p->se.parent = task_group(p)->se[task_cpu(p)];
+ p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+ p->se.parent = task_group(p)->se[cpu];
+
+ p->rt.rt_rq = task_group(p)->rt_rq[cpu];
+ p->rt.parent = task_group(p)->rt_se[cpu];
+}
+
+static inline void lock_task_group_list(void)
+{
+ mutex_lock(&task_group_mutex);
+}
+
+static inline void unlock_task_group_list(void)
+{
+ mutex_unlock(&task_group_mutex);
+}
+
+static inline void lock_doms_cur(void)
+{
+ mutex_lock(&doms_cur_mutex);
+}
+
+static inline void unlock_doms_cur(void)
+{
+ mutex_unlock(&doms_cur_mutex);
}
#else
-static inline void set_task_cfs_rq(struct task_struct *p) { }
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+static inline void lock_task_group_list(void) { }
+static inline void unlock_task_group_list(void) { }
+static inline void lock_doms_cur(void) { }
+static inline void unlock_doms_cur(void) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_FAIR_GROUP_SCHED
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
- /* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
+ /*
+ * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
* a hierarchy). Non-leaf lrqs hold other higher schedulable entities
* (like users, containers etc.)
*
* leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
* list is used during load balance.
*/
- struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
- struct task_group *tg; /* group that "owns" this runqueue */
- struct rcu_head rcu;
+ struct list_head leaf_cfs_rq_list;
+ struct task_group *tg; /* group that "owns" this runqueue */
#endif
};
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
struct rt_prio_array active;
- int rt_load_balance_idx;
- struct list_head *rt_load_balance_head, *rt_load_balance_curr;
+ unsigned long rt_nr_running;
+#if defined CONFIG_SMP || defined CONFIG_FAIR_GROUP_SCHED
+ int highest_prio; /* highest queued rt task prio */
+#endif
+#ifdef CONFIG_SMP
+ unsigned long rt_nr_migratory;
+ int overloaded;
+#endif
+ int rt_throttled;
+ u64 rt_time;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct rq *rq;
+ struct list_head leaf_rt_rq_list;
+ struct task_group *tg;
+ struct sched_rt_entity *rt_se;
+#endif
+};
+
+#ifdef CONFIG_SMP
+
+/*
+ * We add the notion of a root-domain which will be used to define per-domain
+ * variables. Each exclusive cpuset essentially defines an island domain by
+ * fully partitioning the member cpus from any other cpuset. Whenever a new
+ * exclusive cpuset is created, we also create and attach a new root-domain
+ * object.
+ *
+ */
+struct root_domain {
+ atomic_t refcount;
+ cpumask_t span;
+ cpumask_t online;
+
+ /*
+ * The "RT overload" flag: it gets set if a CPU has more than
+ * one runnable RT task.
+ */
+ cpumask_t rto_mask;
+ atomic_t rto_count;
};
/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+static struct root_domain def_root_domain;
+
+#endif
+
+/*
* This is the main, per-CPU runqueue data structure.
*
* Locking rule: those places that want to lock multiple runqueues
* 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;
+ struct rt_rq rt;
+ u64 rt_period_expire;
+ int rt_throttled;
+
#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;
+ struct list_head leaf_rt_rq_list;
#endif
- struct rt_rq rt;
/*
* This is part of a global counter where only the total sum
u64 clock, prev_clock_raw;
s64 clock_max_delta;
- unsigned int clock_warps, clock_overflows;
+ unsigned int clock_warps, clock_overflows, clock_underflows;
u64 idle_clock;
unsigned int clock_deep_idle_events;
u64 tick_timestamp;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
+ struct root_domain *rd;
struct sched_domain *sd;
/* 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;
#endif
+#ifdef CONFIG_SCHED_HRTICK
+ unsigned long hrtick_flags;
+ ktime_t hrtick_expire;
+ struct hrtimer hrtick_timer;
+#endif
+
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
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;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static DEFINE_MUTEX(sched_hotcpu_mutex);
static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
{
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+unsigned long rt_needs_cpu(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ u64 delta;
+
+ if (!rq->rt_throttled)
+ return 0;
+
+ if (rq->clock > rq->rt_period_expire)
+ return 1;
+
+ delta = rq->rt_period_expire - rq->clock;
+ do_div(delta, NSEC_PER_SEC / HZ);
+
+ return (unsigned long)delta;
+}
+
/*
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
*/
enum {
SCHED_FEAT_NEW_FAIR_SLEEPERS = 1,
- SCHED_FEAT_START_DEBIT = 2,
- SCHED_FEAT_TREE_AVG = 4,
- SCHED_FEAT_APPROX_AVG = 8,
- SCHED_FEAT_WAKEUP_PREEMPT = 16,
- SCHED_FEAT_PREEMPT_RESTRICT = 32,
+ SCHED_FEAT_WAKEUP_PREEMPT = 2,
+ SCHED_FEAT_START_DEBIT = 4,
+ SCHED_FEAT_TREE_AVG = 8,
+ SCHED_FEAT_APPROX_AVG = 16,
+ SCHED_FEAT_HRTICK = 32,
+ SCHED_FEAT_DOUBLE_TICK = 64,
};
const_debug unsigned int sysctl_sched_features =
SCHED_FEAT_NEW_FAIR_SLEEPERS * 1 |
+ SCHED_FEAT_WAKEUP_PREEMPT * 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_HRTICK * 1 |
+ SCHED_FEAT_DOUBLE_TICK * 0;
#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)
/*
+ * Number of tasks to iterate in a single balance run.
+ * Limited because this is done with IRQs disabled.
+ */
+const_debug unsigned int sysctl_sched_nr_migrate = 32;
+
+/*
+ * period over which we measure -rt task cpu usage in ms.
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_rt_period = 1000;
+
+#define SCHED_RT_FRAC_SHIFT 16
+#define SCHED_RT_FRAC (1UL << SCHED_RT_FRAC_SHIFT)
+
+/*
+ * ratio of time -rt tasks may consume.
+ * default: 95%
+ */
+const_debug unsigned int sysctl_sched_rt_ratio = 62259;
+
+/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
*/
local_irq_save(flags);
rq = cpu_rq(cpu);
- update_rq_clock(rq);
+ /*
+ * Only call sched_clock() if the scheduler has already been
+ * initialized (some code might call cpu_clock() very early):
+ */
+ if (rq->idle)
+ update_rq_clock(rq);
now = rq->clock;
local_irq_restore(flags);
# define finish_arch_switch(prev) do { } while (0)
#endif
+static inline int task_current(struct rq *rq, struct task_struct *p)
+{
+ return rq->curr == p;
+}
+
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
- return rq->curr == p;
+ return task_current(rq, p);
}
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
#ifdef CONFIG_SMP
return p->oncpu;
#else
- return rq->curr == p;
+ return task_current(rq, p);
#endif
}
/*
* task_rq_lock - lock the runqueue a given task resides on and disable
- * interrupts. Note the ordering: we can safely lookup the task_rq without
+ * interrupts. Note the ordering: we can safely lookup the task_rq without
* explicitly disabling preemption.
*/
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
rq->prev_clock_raw = now;
rq->clock += delta_ns;
spin_unlock(&rq->lock);
+ touch_softlockup_watchdog();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+static void __resched_task(struct task_struct *p, int tif_bit);
+
+static inline void resched_task(struct task_struct *p)
+{
+ __resched_task(p, TIF_NEED_RESCHED);
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+/*
+ * Use HR-timers to deliver accurate preemption points.
+ *
+ * Its all a bit involved since we cannot program an hrt while holding the
+ * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
+ * reschedule event.
+ *
+ * When we get rescheduled we reprogram the hrtick_timer outside of the
+ * rq->lock.
+ */
+static inline void resched_hrt(struct task_struct *p)
+{
+ __resched_task(p, TIF_HRTICK_RESCHED);
+}
+
+static inline void resched_rq(struct rq *rq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ resched_task(rq->curr);
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+enum {
+ HRTICK_SET, /* re-programm hrtick_timer */
+ HRTICK_RESET, /* not a new slice */
+};
+
+/*
+ * Use hrtick when:
+ * - enabled by features
+ * - hrtimer is actually high res
+ */
+static inline int hrtick_enabled(struct rq *rq)
+{
+ if (!sched_feat(HRTICK))
+ return 0;
+ return hrtimer_is_hres_active(&rq->hrtick_timer);
+}
+
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay, int reset)
+{
+ assert_spin_locked(&rq->lock);
+
+ /*
+ * preempt at: now + delay
+ */
+ rq->hrtick_expire =
+ ktime_add_ns(rq->hrtick_timer.base->get_time(), delay);
+ /*
+ * indicate we need to program the timer
+ */
+ __set_bit(HRTICK_SET, &rq->hrtick_flags);
+ if (reset)
+ __set_bit(HRTICK_RESET, &rq->hrtick_flags);
+
+ /*
+ * New slices are called from the schedule path and don't need a
+ * forced reschedule.
+ */
+ if (reset)
+ resched_hrt(rq->curr);
+}
+
+static void hrtick_clear(struct rq *rq)
+{
+ if (hrtimer_active(&rq->hrtick_timer))
+ hrtimer_cancel(&rq->hrtick_timer);
+}
+
+/*
+ * Update the timer from the possible pending state.
+ */
+static void hrtick_set(struct rq *rq)
+{
+ ktime_t time;
+ int set, reset;
+ unsigned long flags;
+
+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+
+ spin_lock_irqsave(&rq->lock, flags);
+ set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags);
+ reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags);
+ time = rq->hrtick_expire;
+ clear_thread_flag(TIF_HRTICK_RESCHED);
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ if (set) {
+ hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS);
+ if (reset && !hrtimer_active(&rq->hrtick_timer))
+ resched_rq(rq);
+ } else
+ hrtick_clear(rq);
+}
+
+/*
+ * High-resolution timer tick.
+ * Runs from hardirq context with interrupts disabled.
+ */
+static enum hrtimer_restart hrtick(struct hrtimer *timer)
+{
+ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+
+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+
+ spin_lock(&rq->lock);
+ __update_rq_clock(rq);
+ rq->curr->sched_class->task_tick(rq, rq->curr, 1);
+ spin_unlock(&rq->lock);
+
+ return HRTIMER_NORESTART;
+}
+
+static inline void init_rq_hrtick(struct rq *rq)
+{
+ rq->hrtick_flags = 0;
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ rq->hrtick_timer.function = hrtick;
+ rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+}
+
+void hrtick_resched(void)
+{
+ struct rq *rq;
+ unsigned long flags;
+
+ if (!test_thread_flag(TIF_HRTICK_RESCHED))
+ return;
+
+ local_irq_save(flags);
+ rq = cpu_rq(smp_processor_id());
+ hrtick_set(rq);
+ local_irq_restore(flags);
+}
+#else
+static inline void hrtick_clear(struct rq *rq)
+{
+}
+
+static inline void hrtick_set(struct rq *rq)
+{
+}
+
+static inline void init_rq_hrtick(struct rq *rq)
+{
+}
+
+void hrtick_resched(void)
+{
+}
+#endif
+
/*
* resched_task - mark a task 'to be rescheduled now'.
*
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif
-static void resched_task(struct task_struct *p)
+static void __resched_task(struct task_struct *p, int tif_bit)
{
int cpu;
assert_spin_locked(&task_rq(p)->lock);
- if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+ if (unlikely(test_tsk_thread_flag(p, tif_bit)))
return;
- set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+ set_tsk_thread_flag(p, tif_bit);
cpu = task_cpu(p);
if (cpu == smp_processor_id())
spin_unlock_irqrestore(&rq->lock, flags);
}
#else
-static inline void resched_task(struct task_struct *p)
+static void __resched_task(struct task_struct *p, int tif_bit)
{
assert_spin_locked(&task_rq(p)->lock);
- set_tsk_need_resched(p);
+ set_tsk_thread_flag(p, tif_bit);
}
#endif
* To aid in avoiding the subversion of "niceness" due to uneven distribution
* of tasks with abnormal "nice" values across CPUs the contribution that
* each task makes to its run queue's load is weighted according to its
- * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
+ * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
* scaled version of the new time slice allocation that they receive on time
* slice expiry etc.
*/
struct task_struct *(*next)(void *);
};
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator);
+#ifdef CONFIG_SMP
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move, struct sched_domain *sd,
+ enum cpu_idle_type idle, int *all_pinned,
+ int *this_best_prio, struct rq_iterator *iterator);
+
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ struct rq_iterator *iterator);
+#endif
+
+#ifdef CONFIG_CGROUP_CPUACCT
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+#else
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
+#endif
+
+static inline void inc_cpu_load(struct rq *rq, unsigned long load)
+{
+ update_load_add(&rq->load, load);
+}
+
+static inline void dec_cpu_load(struct rq *rq, unsigned long load)
+{
+ update_load_sub(&rq->load, load);
+}
+
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long cpu_avg_load_per_task(int cpu);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+#endif /* CONFIG_SMP */
#include "sched_stats.h"
#include "sched_idletask.c"
#define sched_class_highest (&rt_sched_class)
-/*
- * Update delta_exec, delta_fair fields for rq.
- *
- * delta_fair clock advances at a rate inversely proportional to
- * total load (rq->load.weight) on the runqueue, while
- * delta_exec advances at the same rate as wall-clock (provided
- * cpu is not idle).
- *
- * delta_exec / delta_fair is a measure of the (smoothened) load on this
- * runqueue over any given interval. This (smoothened) load is used
- * during load balance.
- *
- * This function is called /before/ updating rq->load
- * and when switching tasks.
- */
-static inline void inc_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_add(&rq->load, p->se.load.weight);
-}
-
-static inline void dec_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_sub(&rq->load, p->se.load.weight);
-}
-
static void inc_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running++;
- inc_load(rq, p);
}
static void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
- dec_load(rq, p);
}
static void set_load_weight(struct task_struct *p)
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
+ set_task_rq(p, cpu);
#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+ * successfuly executed on another CPU. We must ensure that updates of
+ * per-task data have been completed by this moment.
+ */
+ smp_wmb();
task_thread_info(p)->cpu = cpu;
#endif
- set_task_cfs_rq(p);
+}
+
+static inline void check_class_changed(struct rq *rq, struct task_struct *p,
+ const struct sched_class *prev_class,
+ int oldprio, int running)
+{
+ if (prev_class != p->sched_class) {
+ if (prev_class->switched_from)
+ prev_class->switched_from(rq, p, running);
+ p->sched_class->switched_to(rq, p, running);
+ } else
+ p->sched_class->prio_changed(rq, p, oldprio, running);
}
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
*/
-static inline int
+static int
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
{
s64 delta;
/*
* Return the average load per task on the cpu's run queue
*/
-static inline unsigned long cpu_avg_load_per_task(int cpu)
+static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
#endif /* CONFIG_SMP */
-/*
- * wake_idle() will wake a task on an idle cpu if task->cpu is
- * not idle and an idle cpu is available. The span of cpus to
- * search starts with cpus closest then further out as needed,
- * so we always favor a closer, idle cpu.
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @sync: do a synchronous wakeup?
*
- * Returns the CPU we should wake onto.
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * returns failure only if the task is already active.
*/
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-static int wake_idle(int cpu, struct task_struct *p)
-{
- cpumask_t tmp;
- struct sched_domain *sd;
- int i;
-
- /*
- * If it is idle, then it is the best cpu to run this task.
- *
- * This cpu is also the best, if it has more than one task already.
- * Siblings must be also busy(in most cases) as they didn't already
- * pickup the extra load from this cpu and hence we need not check
- * sibling runqueue info. This will avoid the checks and cache miss
- * penalities associated with that.
- */
- if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
- return cpu;
-
- for_each_domain(cpu, sd) {
- 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 (i != task_cpu(p)) {
- schedstat_inc(p,
- se.nr_wakeups_idle);
- }
- return i;
- }
- }
- } else {
- break;
- }
- }
- return cpu;
-}
-#else
-static inline int wake_idle(int cpu, struct task_struct *p)
-{
- return cpu;
-}
-#endif
-
-/***
- * try_to_wake_up - wake up a thread
- * @p: the to-be-woken-up thread
- * @state: the mask of task states that can be woken
- * @sync: do a synchronous wakeup?
- *
- * Put it on the run-queue if it's not already there. The "current"
- * thread is always on the run-queue (except when the actual
- * re-schedule is in progress), and as such you're allowed to do
- * the simpler "current->state = TASK_RUNNING" to mark yourself
- * runnable without the overhead of this.
- *
- * returns failure only if the task is already active.
- */
-static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
+static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
long old_state;
struct rq *rq;
-#ifdef CONFIG_SMP
- struct sched_domain *sd, *this_sd = NULL;
- unsigned long load, this_load;
- int new_cpu;
-#endif
rq = task_rq_lock(p, &flags);
old_state = p->state;
if (unlikely(task_running(rq, p)))
goto out_activate;
- new_cpu = cpu;
-
- schedstat_inc(rq, ttwu_count);
- if (cpu == this_cpu) {
- schedstat_inc(rq, ttwu_local);
- goto out_set_cpu;
- }
-
- for_each_domain(this_cpu, sd) {
- if (cpu_isset(cpu, sd->span)) {
- schedstat_inc(sd, ttwu_wake_remote);
- this_sd = sd;
- break;
- }
- }
-
- if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
- goto out_set_cpu;
-
- /*
- * Check for affine wakeup and passive balancing possibilities.
- */
- if (this_sd) {
- int idx = this_sd->wake_idx;
- unsigned int imbalance;
-
- imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
- load = source_load(cpu, idx);
- this_load = target_load(this_cpu, idx);
-
- new_cpu = this_cpu; /* Wake to this CPU if we can */
-
- if (this_sd->flags & SD_WAKE_AFFINE) {
- 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);
-
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync)
- tl -= current->se.load.weight;
-
- if ((tl <= load &&
- tl + target_load(cpu, idx) <= tl_per_task) ||
- 100*(tl + p->se.load.weight) <= imbalance*load) {
- /*
- * This domain has SD_WAKE_AFFINE and
- * p is cache cold in this domain, and
- * there is no bad imbalance.
- */
- schedstat_inc(this_sd, ttwu_move_affine);
- schedstat_inc(p, se.nr_wakeups_affine);
- goto out_set_cpu;
- }
- }
-
- /*
- * Start passive balancing when half the imbalance_pct
- * limit is reached.
- */
- 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;
- }
- }
- }
-
- new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
- new_cpu = wake_idle(new_cpu, p);
- if (new_cpu != cpu) {
- set_task_cpu(p, new_cpu);
+ cpu = p->sched_class->select_task_rq(p, sync);
+ if (cpu != orig_cpu) {
+ set_task_cpu(p, cpu);
task_rq_unlock(rq, &flags);
/* might preempt at this point */
rq = task_rq_lock(p, &flags);
cpu = task_cpu(p);
}
+#ifdef CONFIG_SCHEDSTATS
+ schedstat_inc(rq, ttwu_count);
+ if (cpu == this_cpu)
+ schedstat_inc(rq, ttwu_local);
+ else {
+ struct sched_domain *sd;
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(cpu, sd->span)) {
+ schedstat_inc(sd, ttwu_wake_remote);
+ break;
+ }
+ }
+ }
+#endif
+
out_activate:
#endif /* CONFIG_SMP */
schedstat_inc(p, se.nr_wakeups);
out_running:
p->state = TASK_RUNNING;
+#ifdef CONFIG_SMP
+ if (p->sched_class->task_wake_up)
+ p->sched_class->task_wake_up(rq, p);
+#endif
out:
task_rq_unlock(rq, &flags);
p->se.wait_max = 0;
#endif
- INIT_LIST_HEAD(&p->run_list);
+ INIT_LIST_HEAD(&p->rt.run_list);
p->se.on_rq = 0;
#ifdef CONFIG_PREEMPT_NOTIFIERS
inc_nr_running(p, rq);
}
check_preempt_curr(rq, p);
+#ifdef CONFIG_SMP
+ if (p->sched_class->task_wake_up)
+ p->sched_class->task_wake_up(rq, p);
+#endif
task_rq_unlock(rq, &flags);
}
* 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
+ * so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
prev_state = prev->state;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
+#ifdef CONFIG_SMP
+ if (current->sched_class->post_schedule)
+ current->sched_class->post_schedule(rq);
+#endif
+
fire_sched_in_preempt_notifiers(current);
if (mm)
mmdrop(mm);
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);
}
/*
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
-static void double_lock_balance(struct rq *this_rq, struct rq *busiest)
+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);
spin_unlock(&this_rq->lock);
spin_lock(&busiest->lock);
spin_lock(&this_rq->lock);
+ ret = 1;
} else
spin_lock(&busiest->lock);
}
+ return ret;
}
/*
* 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
+ * allow dest_cpu, which will force the cpu onto dest_cpu. Then
* the cpu_allowed mask is restored.
*/
static void sched_migrate_task(struct task_struct *p, int dest_cpu)
return 1;
}
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator)
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move, struct sched_domain *sd,
+ enum cpu_idle_type idle, int *all_pinned,
+ int *this_best_prio, struct rq_iterator *iterator)
{
- int pulled = 0, pinned = 0, skip_for_load;
+ int loops = 0, pulled = 0, pinned = 0, skip_for_load;
struct task_struct *p;
long rem_load_move = max_load_move;
- if (max_nr_move == 0 || max_load_move == 0)
+ if (max_load_move == 0)
goto out;
pinned = 1;
*/
p = iterator->start(iterator->arg);
next:
- if (!p)
+ if (!p || loops++ > sysctl_sched_nr_migrate)
goto out;
/*
- * To help distribute high priority tasks accross CPUs we don't
+ * To help distribute high priority tasks across CPUs we don't
* skip a task if it will be the highest priority task (i.e. smallest
* prio value) on its new queue regardless of its load weight
*/
rem_load_move -= p->se.load.weight;
/*
- * We only want to steal up to the prescribed number of tasks
- * and the prescribed amount of weighted load.
+ * We only want to steal up to the prescribed amount of weighted load.
*/
- if (pulled < max_nr_move && rem_load_move > 0) {
+ if (rem_load_move > 0) {
if (p->prio < *this_best_prio)
*this_best_prio = p->prio;
p = iterator->next(iterator->arg);
}
out:
/*
- * Right now, this is the only place pull_task() is called,
+ * Right now, this is one of only two places pull_task() is called,
* so we can safely collect pull_task() stats here rather than
* inside pull_task().
*/
if (all_pinned)
*all_pinned = pinned;
- *load_moved = max_load_move - rem_load_move;
- return pulled;
+
+ return max_load_move - rem_load_move;
}
/*
do {
total_load_moved +=
class->load_balance(this_rq, this_cpu, busiest,
- ULONG_MAX, max_load_move - total_load_moved,
+ max_load_move - total_load_moved,
sd, idle, all_pinned, &this_best_prio);
class = class->next;
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
}
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ struct rq_iterator *iterator)
+{
+ struct task_struct *p = iterator->start(iterator->arg);
+ int pinned = 0;
+
+ while (p) {
+ if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+ pull_task(busiest, p, this_rq, this_cpu);
+ /*
+ * Right now, this is only the second place pull_task()
+ * is called, so we can safely collect pull_task()
+ * stats here rather than inside pull_task().
+ */
+ schedstat_inc(sd, lb_gained[idle]);
+
+ return 1;
+ }
+ p = iterator->next(iterator->arg);
+ }
+
+ return 0;
+}
+
/*
* move_one_task tries to move exactly one task from busiest to this_rq, as
* part of active balancing operations within "domain".
struct sched_domain *sd, enum cpu_idle_type idle)
{
const struct sched_class *class;
- int this_best_prio = MAX_PRIO;
for (class = sched_class_highest; class; class = class->next)
- if (class->load_balance(this_rq, this_cpu, busiest,
- 1, ULONG_MAX, sd, idle, NULL,
- &this_best_prio))
+ if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
return 1;
return 0;
* tasks around. Thus we look for the minimum possible imbalance.
* Negative imbalances (*we* are more loaded than anyone else) will
* be counted as no imbalance for these purposes -- we can't fix that
- * by pulling tasks to us. Be careful of negative numbers as they'll
+ * by pulling tasks to us. Be careful of negative numbers as they'll
* appear as very large values with unsigned longs.
*/
if (max_load <= busiest_load_per_task)
/*
* This condition is "impossible", if it occurs
- * we need to fix it. Originally reported by
+ * we need to fix it. Originally reported by
* Bjorn Helgaas on a 128-cpu setup.
*/
BUG_ON(busiest_rq == target_rq);
#ifdef CONFIG_NO_HZ
static struct {
atomic_t load_balancer;
- cpumask_t cpu_mask;
+ cpumask_t cpu_mask;
} nohz ____cacheline_aligned = {
.load_balancer = ATOMIC_INIT(-1),
.cpu_mask = CPU_MASK_NONE,
{
}
-/* Avoid "used but not defined" warning on UP */
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator)
-{
- *load_moved = 0;
-
- return 0;
-}
-
#endif
DEFINE_PER_CPU(struct kernel_stat, kstat);
rq = task_rq_lock(p, &flags);
ns = p->se.sum_exec_runtime;
- if (rq->curr == p) {
+ if (task_current(rq, p)) {
update_rq_clock(rq);
delta_exec = rq->clock - p->se.exec_start;
if ((s64)delta_exec > 0)
/*
* 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)
* @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)
+static void account_guest_time(struct task_struct *p, cputime_t cputime)
{
cputime64_t tmp;
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
}
/*
+ * 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()
struct rq *rq = this_rq();
cputime64_t tmp;
- if (p->flags & PF_VCPU) {
- account_guest_time(p, cputime);
- p->flags &= ~PF_VCPU;
- return;
- }
+ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
+ return account_guest_time(p, cputime);
p->stime = cputime_add(p->stime, cputime);
}
/*
+ * 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
* @steal: the cpu time spent in involuntary wait
/*
* Let rq->clock advance by at least TICK_NSEC:
*/
- if (unlikely(rq->clock < next_tick))
+ if (unlikely(rq->clock < next_tick)) {
rq->clock = next_tick;
+ rq->clock_underflows++;
+ }
rq->tick_timestamp = rq->clock;
update_cpu_load(rq);
- if (curr != rq->idle) /* FIXME: needed? */
- curr->sched_class->task_tick(rq, curr);
+ curr->sched_class->task_tick(rq, curr, 0);
+ update_sched_rt_period(rq);
spin_unlock(&rq->lock);
#ifdef CONFIG_SMP
*/
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);
+ struct pt_regs *regs = get_irq_regs();
+
+ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
+ prev->comm, prev->pid, preempt_count());
+
debug_show_held_locks(prev);
if (irqs_disabled())
print_irqtrace_events(prev);
- dump_stack();
+
+ if (regs)
+ show_regs(regs);
+ else
+ dump_stack();
}
/*
static inline void schedule_debug(struct task_struct *prev)
{
/*
- * Test if we are atomic. Since do_exit() needs to call into
+ * Test if we are atomic. Since do_exit() needs to call into
* schedule() atomically, we ignore that path for now.
* Otherwise, whine if we are scheduling when we should not be.
*/
schedule_debug(prev);
+ hrtick_clear(rq);
+
/*
* Do the rq-clock update outside the rq lock:
*/
switch_count = &prev->nvcsw;
}
+#ifdef CONFIG_SMP
+ if (prev->sched_class->pre_schedule)
+ prev->sched_class->pre_schedule(rq, prev);
+#endif
+
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
++*switch_count;
context_switch(rq, prev, next); /* unlocks the rq */
+ /*
+ * the context switch might have flipped the stack from under
+ * us, hence refresh the local variables.
+ */
+ cpu = smp_processor_id();
+ rq = cpu_rq(cpu);
} else
spin_unlock_irq(&rq->lock);
- if (unlikely(reacquire_kernel_lock(current) < 0)) {
- cpu = smp_processor_id();
- rq = cpu_rq(cpu);
+ hrtick_set(rq);
+
+ if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
- }
+
preempt_enable_no_resched();
if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
goto need_resched;
#ifdef CONFIG_PREEMPT
/*
* this is the entry point to schedule() from in-kernel preemption
- * off of preempt_enable. Kernel preemptions off return from interrupt
+ * off of preempt_enable. Kernel preemptions off return from interrupt
* occur there and call schedule directly.
*/
asmlinkage void __sched preempt_schedule(void)
{
struct thread_info *ti = current_thread_info();
-#ifdef CONFIG_PREEMPT_BKL
struct task_struct *task = current;
int saved_lock_depth;
-#endif
+
/*
* If there is a non-zero preempt_count or interrupts are disabled,
- * we do not want to preempt the current task. Just return..
+ * we do not want to preempt the current task. Just return..
*/
if (likely(ti->preempt_count || irqs_disabled()))
return;
* clear ->lock_depth so that schedule() doesnt
* auto-release the semaphore:
*/
-#ifdef CONFIG_PREEMPT_BKL
saved_lock_depth = task->lock_depth;
task->lock_depth = -1;
-#endif
schedule();
-#ifdef CONFIG_PREEMPT_BKL
task->lock_depth = saved_lock_depth;
-#endif
sub_preempt_count(PREEMPT_ACTIVE);
/*
asmlinkage void __sched preempt_schedule_irq(void)
{
struct thread_info *ti = current_thread_info();
-#ifdef CONFIG_PREEMPT_BKL
struct task_struct *task = current;
int saved_lock_depth;
-#endif
+
/* Catch callers which need to be fixed */
BUG_ON(ti->preempt_count || !irqs_disabled());
* clear ->lock_depth so that schedule() doesnt
* auto-release the semaphore:
*/
-#ifdef CONFIG_PREEMPT_BKL
saved_lock_depth = task->lock_depth;
task->lock_depth = -1;
-#endif
local_irq_enable();
schedule();
local_irq_disable();
-#ifdef CONFIG_PREEMPT_BKL
task->lock_depth = saved_lock_depth;
-#endif
sub_preempt_count(PREEMPT_ACTIVE);
/*
EXPORT_SYMBOL(default_wake_function);
/*
- * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
- * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake all the non-exclusive tasks and one exclusive task.
*
* There are circumstances in which we can try to wake a task which has already
- * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
+ * 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,
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
-void fastcall complete(struct completion *x)
+void complete(struct completion *x)
{
unsigned long flags;
}
EXPORT_SYMBOL(complete);
-void fastcall complete_all(struct completion *x)
+void complete_all(struct completion *x)
{
unsigned long flags;
return timeout;
}
-void fastcall __sched wait_for_completion(struct completion *x)
+void __sched wait_for_completion(struct completion *x)
{
wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion);
-unsigned long fastcall __sched
+unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_interruptible);
-unsigned long fastcall __sched
+unsigned long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
unsigned long timeout)
{
unsigned long flags;
int oldprio, on_rq, running;
struct rq *rq;
+ const struct sched_class *prev_class = p->sched_class;
BUG_ON(prio < 0 || prio > MAX_PRIO);
oldprio = p->prio;
on_rq = p->se.on_rq;
- running = task_running(rq, p);
+ running = task_current(rq, p);
if (on_rq) {
dequeue_task(rq, p, 0);
if (running)
if (on_rq) {
if (running)
p->sched_class->set_curr_task(rq);
+
enqueue_task(rq, p, 0);
- /*
- * Reschedule if we are currently running on this runqueue and
- * our priority decreased, or if we are not currently running on
- * this runqueue and our priority is higher than the current's
- */
- if (running) {
- if (p->prio > oldprio)
- resched_task(rq->curr);
- } else {
- check_preempt_curr(rq, p);
- }
+
+ check_class_changed(rq, p, prev_class, oldprio, running);
}
task_rq_unlock(rq, &flags);
}
goto out_unlock;
}
on_rq = p->se.on_rq;
- if (on_rq) {
+ if (on_rq)
dequeue_task(rq, p, 0);
- dec_load(rq, p);
- }
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p);
if (on_rq) {
enqueue_task(rq, p, 0);
- inc_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
*/
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. */
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
+ const struct sched_class *prev_class = p->sched_class;
struct rq *rq;
/* may grab non-irq protected spin_locks */
}
update_rq_clock(rq);
on_rq = p->se.on_rq;
- running = task_running(rq, p);
+ running = task_current(rq, p);
if (on_rq) {
deactivate_task(rq, p, 0);
if (running)
if (on_rq) {
if (running)
p->sched_class->set_curr_task(rq);
+
activate_task(rq, p, 0);
- /*
- * Reschedule if we are currently running on this runqueue and
- * our priority decreased, or if we are not currently running on
- * this runqueue and our priority is higher than the current's
- */
- if (running) {
- if (p->prio > oldprio)
- resched_task(rq->curr);
- } else {
- check_preempt_curr(rq, p);
- }
+
+ check_class_changed(rq, p, prev_class, oldprio, running);
}
__task_rq_unlock(rq);
spin_unlock_irqrestore(&p->pi_lock, flags);
* @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)
+asmlinkage long
+sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
/* negative values for policy are not valid */
if (policy < 0)
struct task_struct *p;
int retval;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
read_lock(&tasklist_lock);
p = find_process_by_pid(pid);
if (!p) {
read_unlock(&tasklist_lock);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return -ESRCH;
}
/*
* It is not safe to call set_cpus_allowed with the
- * tasklist_lock held. We will bump the task_struct's
+ * tasklist_lock held. We will bump the task_struct's
* usage count and then drop tasklist_lock.
*/
get_task_struct(p);
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);
+ put_online_cpus();
return retval;
}
struct task_struct *p;
int retval;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
read_lock(&tasklist_lock);
retval = -ESRCH;
out_unlock:
read_unlock(&tasklist_lock);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return retval;
}
} while (need_resched());
}
-int __sched cond_resched(void)
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY)
+int __sched _cond_resched(void)
{
if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
system_state == SYSTEM_RUNNING) {
}
return 0;
}
-EXPORT_SYMBOL(cond_resched);
+EXPORT_SYMBOL(_cond_resched);
+#endif
/*
* cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
- * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
int cond_resched_lock(spinlock_t *lock)
{
+ int resched = need_resched() && system_state == SYSTEM_RUNNING;
int ret = 0;
- if (need_lockbreak(lock)) {
+ if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
- cpu_relax();
- ret = 1;
- spin_lock(lock);
- }
- if (need_resched() && system_state == SYSTEM_RUNNING) {
- spin_release(&lock->dep_map, 1, _THIS_IP_);
- _raw_spin_unlock(lock);
- preempt_enable_no_resched();
- __cond_resched();
+ if (resched && need_resched())
+ __cond_resched();
+ else
+ cpu_relax();
ret = 1;
spin_lock(lock);
}
EXPORT_SYMBOL(yield);
/*
- * This task is about to go to sleep on IO. Increment rq->nr_iowait so
+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*
* But don't do that if it is a deliberate, throttling IO wait (this task
if (retval)
goto out_unlock;
- if (p->policy == SCHED_FIFO)
- time_slice = 0;
- else if (p->policy == SCHED_RR)
+ /*
+ * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER
+ * tasks that are on an otherwise idle runqueue:
+ */
+ time_slice = 0;
+ if (p->policy == SCHED_RR) {
time_slice = DEF_TIMESLICE;
- else {
+ } else {
struct sched_entity *se = &p->se;
unsigned long flags;
struct rq *rq;
rq = task_rq_lock(p, &flags);
- time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
+ if (rq->cfs.load.weight)
+ time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
task_rq_unlock(rq, &flags);
}
read_unlock(&tasklist_lock);
static const char stat_nam[] = "RSDTtZX";
-static void show_task(struct task_struct *p)
+void sched_show_task(struct task_struct *p)
{
unsigned long free = 0;
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->real_parent));
- if (state != TASK_RUNNING)
- show_stack(p, NULL);
+ show_stack(p, NULL);
}
void show_state_filter(unsigned long state_filter)
*/
touch_nmi_watchdog();
if (!state_filter || (p->state & state_filter))
- show_task(p);
+ sched_show_task(p);
} while_each_thread(g, p);
touch_all_softlockup_watchdogs();
spin_unlock_irqrestore(&rq->lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
-#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
- task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
-#else
task_thread_info(idle)->preempt_count = 0;
-#endif
+
/*
* The idle tasks have their own, simple scheduling class:
*/
*/
cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+/*
+ * Increase the granularity value when there are more CPUs,
+ * because with more CPUs the 'effective latency' as visible
+ * to users decreases. But the relationship is not linear,
+ * so pick a second-best guess by going with the log2 of the
+ * number of CPUs.
+ *
+ * This idea comes from the SD scheduler of Con Kolivas:
+ */
+static inline void sched_init_granularity(void)
+{
+ unsigned int factor = 1 + ilog2(num_online_cpus());
+ const unsigned long limit = 200000000;
+
+ sysctl_sched_min_granularity *= factor;
+ if (sysctl_sched_min_granularity > limit)
+ sysctl_sched_min_granularity = limit;
+
+ sysctl_sched_latency *= factor;
+ if (sysctl_sched_latency > limit)
+ sysctl_sched_latency = limit;
+
+ sysctl_sched_wakeup_granularity *= factor;
+ sysctl_sched_batch_wakeup_granularity *= factor;
+}
+
#ifdef CONFIG_SMP
/*
* This is how migration works:
* is removed from the allowed bitmask.
*
* NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely. The
+ * task must not exit() & deallocate itself prematurely. The
* call is not atomic; no spinlocks may be held.
*/
int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
goto out;
}
- p->cpus_allowed = new_mask;
+ 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);
+ }
+
/* Can the task run on the task's current CPU? If so, we're done */
if (cpu_isset(task_cpu(p), new_mask))
goto out;
EXPORT_SYMBOL_GPL(set_cpus_allowed);
/*
- * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * Move (not current) task off this cpu, onto dest cpu. We're doing
* this because either it can't run here any more (set_cpus_allowed()
* away from this CPU, or CPU going down), or because we're
* attempting to rebalance this task on exec (sched_exec).
}
/*
- * 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);
* kernel threads (both mm NULL), since they never
* leave kernel.
*/
- if (p->mm && printk_ratelimit())
+ 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_irq(p, dead_cpu, dest_cpu));
}
}
/*
- * activate_idle_task - move idle task to the _front_ of runqueue.
- */
-static void activate_idle_task(struct task_struct *p, struct rq *rq)
-{
- update_rq_clock(rq);
-
- if (p->state == TASK_UNINTERRUPTIBLE)
- rq->nr_uninterruptible--;
-
- enqueue_task(rq, p, 0);
- inc_nr_running(p, rq);
-}
-
-/*
* Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible and adding it to
- * the _front_ of the runqueue. Used by CPU offline code.
+ * It does so by boosting its priority to highest possible.
+ * Used by CPU offline code.
*/
void sched_idle_next(void)
{
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
- /* Add idle task to the _front_ of its priority queue: */
- activate_idle_task(p, rq);
+ update_rq_clock(rq);
+ activate_task(rq, p, 0);
spin_unlock_irqrestore(&rq->lock, flags);
}
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
+ * that's OK. No task can be added to this CPU, so iteration is
* fine.
*/
spin_unlock_irq(&rq->lock);
.procname = "sched_domain",
.mode = 0555,
},
- {0,},
+ {0, },
};
static struct ctl_table sd_ctl_root[] = {
.mode = 0555,
.child = sd_ctl_dir,
},
- {0,},
+ {0, },
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
/*
* 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
+ * will always be set. In the lowest directory the names are
* static strings and all have proc handlers.
*/
for (entry = *tablep; entry->mode; entry++) {
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;
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
+ WARN_ON(sd_ctl_dir[0].child);
+ sd_ctl_dir[0].child = entry;
+
if (entry == NULL)
return;
- sd_ctl_dir[0].child = entry;
-
for_each_online_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->child = sd_alloc_ctl_cpu_table(i);
entry++;
}
+
+ WARN_ON(sd_sysctl_header);
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
}
+/* may be called multiple times per register */
static void unregister_sched_domain_sysctl(void)
{
- unregister_sysctl_table(sd_sysctl_header);
+ if (sd_sysctl_header)
+ unregister_sysctl_table(sd_sysctl_header);
sd_sysctl_header = NULL;
- sd_free_ctl_entry(&sd_ctl_dir[0].child);
+ if (sd_ctl_dir[0].child)
+ sd_free_ctl_entry(&sd_ctl_dir[0].child);
}
#else
static void register_sched_domain_sysctl(void)
struct rq *rq;
switch (action) {
- case CPU_LOCK_ACQUIRE:
- mutex_lock(&sched_hotcpu_mutex);
- break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
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);
+
+ /* Update our root-domain */
+ rq = cpu_rq(cpu);
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpu_isset(cpu, rq->rd->span));
+ cpu_set(cpu, rq->rd->online);
+ }
+ spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED_FROZEN:
if (!cpu_rq(cpu)->migration_thread)
break;
- /* Unbind it from offline cpu so it can run. Fall thru. */
+ /* Unbind it from offline cpu so it can run. Fall thru. */
kthread_bind(cpu_rq(cpu)->migration_thread,
any_online_cpu(cpu_online_map));
kthread_stop(cpu_rq(cpu)->migration_thread);
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->idle->sched_class = &idle_sched_class;
migrate_dead_tasks(cpu);
spin_unlock_irq(&rq->lock);
+ cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
- /* No need to migrate the tasks: it was best-effort if
- * they didn't take sched_hotcpu_mutex. Just wake up
- * the requestors. */
+ /*
+ * No need to migrate the tasks: it was best-effort if
+ * they didn't take sched_hotcpu_mutex. Just wake up
+ * the requestors.
+ */
spin_lock_irq(&rq->lock);
while (!list_empty(&rq->migration_queue)) {
struct migration_req *req;
}
spin_unlock_irq(&rq->lock);
break;
-#endif
- case CPU_LOCK_RELEASE:
- mutex_unlock(&sched_hotcpu_mutex);
+
+ case CPU_DOWN_PREPARE:
+ /* Update our root-domain */
+ rq = cpu_rq(cpu);
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpu_isset(cpu, rq->rd->span));
+ cpu_clear(cpu, rq->rd->online);
+ }
+ spin_unlock_irqrestore(&rq->lock, flags);
break;
+#endif
}
return NOTIFY_OK;
}
.priority = 10
};
-int __init migration_init(void)
+void __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
-
- return 0;
}
#endif
EXPORT_SYMBOL(nr_cpu_ids);
#ifdef CONFIG_SCHED_DEBUG
-static void sched_domain_debug(struct sched_domain *sd, int cpu)
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level)
{
- int level = 0;
+ struct sched_group *group = sd->groups;
+ cpumask_t groupmask;
+ char str[NR_CPUS];
- if (!sd) {
- printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
- return;
- }
+ cpumask_scnprintf(str, NR_CPUS, sd->span);
+ cpus_clear(groupmask);
- printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+ printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+ if (!(sd->flags & SD_LOAD_BALANCE)) {
+ printk("does not load-balance\n");
+ if (sd->parent)
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+ " has parent");
+ return -1;
+ }
+
+ printk(KERN_CONT "span %s\n", str);
+
+ if (!cpu_isset(cpu, sd->span)) {
+ printk(KERN_ERR "ERROR: domain->span does not contain "
+ "CPU%d\n", cpu);
+ }
+ if (!cpu_isset(cpu, group->cpumask)) {
+ printk(KERN_ERR "ERROR: domain->groups does not contain"
+ " CPU%d\n", cpu);
+ }
+
+ printk(KERN_DEBUG "%*s groups:", level + 1, "");
do {
- int i;
- char str[NR_CPUS];
- struct sched_group *group = sd->groups;
- cpumask_t groupmask;
-
- cpumask_scnprintf(str, NR_CPUS, sd->span);
- cpus_clear(groupmask);
-
- printk(KERN_DEBUG);
- for (i = 0; i < level + 1; i++)
- printk(" ");
- printk("domain %d: ", level);
-
- if (!(sd->flags & SD_LOAD_BALANCE)) {
- printk("does not load-balance\n");
- if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
- " has parent");
+ if (!group) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: group is NULL\n");
break;
}
- printk("span %s\n", str);
+ if (!group->__cpu_power) {
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: domain->cpu_power not "
+ "set\n");
+ break;
+ }
- if (!cpu_isset(cpu, sd->span))
- printk(KERN_ERR "ERROR: domain->span does not contain "
- "CPU%d\n", cpu);
- if (!cpu_isset(cpu, group->cpumask))
- printk(KERN_ERR "ERROR: domain->groups does not contain"
- " CPU%d\n", cpu);
+ if (!cpus_weight(group->cpumask)) {
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: empty group\n");
+ break;
+ }
- printk(KERN_DEBUG);
- for (i = 0; i < level + 2; i++)
- printk(" ");
- printk("groups:");
- do {
- if (!group) {
- printk("\n");
- printk(KERN_ERR "ERROR: group is NULL\n");
- break;
- }
+ if (cpus_intersects(groupmask, group->cpumask)) {
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: repeated CPUs\n");
+ break;
+ }
- if (!group->__cpu_power) {
- printk("\n");
- printk(KERN_ERR "ERROR: domain->cpu_power not "
- "set\n");
- break;
- }
+ cpus_or(groupmask, groupmask, group->cpumask);
- if (!cpus_weight(group->cpumask)) {
- printk("\n");
- printk(KERN_ERR "ERROR: empty group\n");
- break;
- }
+ cpumask_scnprintf(str, NR_CPUS, group->cpumask);
+ printk(KERN_CONT " %s", str);
- if (cpus_intersects(groupmask, group->cpumask)) {
- printk("\n");
- printk(KERN_ERR "ERROR: repeated CPUs\n");
- break;
- }
+ group = group->next;
+ } while (group != sd->groups);
+ printk(KERN_CONT "\n");
+
+ if (!cpus_equal(sd->span, groupmask))
+ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
- cpus_or(groupmask, groupmask, group->cpumask);
+ if (sd->parent && !cpus_subset(groupmask, sd->parent->span))
+ printk(KERN_ERR "ERROR: parent span is not a superset "
+ "of domain->span\n");
+ return 0;
+}
- cpumask_scnprintf(str, NR_CPUS, group->cpumask);
- printk(" %s", str);
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+ int level = 0;
- group = group->next;
- } while (group != sd->groups);
- printk("\n");
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
+ }
- if (!cpus_equal(sd->span, groupmask))
- printk(KERN_ERR "ERROR: groups don't span "
- "domain->span\n");
+ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+ for (;;) {
+ if (sched_domain_debug_one(sd, cpu, level))
+ break;
level++;
sd = sd->parent;
if (!sd)
- continue;
-
- if (!cpus_subset(groupmask, sd->span))
- printk(KERN_ERR "ERROR: parent span is not a superset "
- "of domain->span\n");
-
- } while (sd);
+ break;
+ }
}
#else
# define sched_domain_debug(sd, cpu) do { } while (0)
return 1;
}
+static void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+ unsigned long flags;
+ const struct sched_class *class;
+
+ spin_lock_irqsave(&rq->lock, flags);
+
+ if (rq->rd) {
+ struct root_domain *old_rd = rq->rd;
+
+ for (class = sched_class_highest; class; class = class->next) {
+ if (class->leave_domain)
+ class->leave_domain(rq);
+ }
+
+ cpu_clear(rq->cpu, old_rd->span);
+ cpu_clear(rq->cpu, old_rd->online);
+
+ if (atomic_dec_and_test(&old_rd->refcount))
+ kfree(old_rd);
+ }
+
+ atomic_inc(&rd->refcount);
+ rq->rd = rd;
+
+ cpu_set(rq->cpu, rd->span);
+ if (cpu_isset(rq->cpu, cpu_online_map))
+ cpu_set(rq->cpu, rd->online);
+
+ for (class = sched_class_highest; class; class = class->next) {
+ if (class->join_domain)
+ class->join_domain(rq);
+ }
+
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static void init_rootdomain(struct root_domain *rd)
+{
+ memset(rd, 0, sizeof(*rd));
+
+ cpus_clear(rd->span);
+ cpus_clear(rd->online);
+}
+
+static void init_defrootdomain(void)
+{
+ init_rootdomain(&def_root_domain);
+ atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+ struct root_domain *rd;
+
+ rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+ if (!rd)
+ return NULL;
+
+ init_rootdomain(rd);
+
+ return rd;
+}
+
/*
- * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
*/
-static void cpu_attach_domain(struct sched_domain *sd, int cpu)
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct sched_domain *tmp;
sched_domain_debug(sd, cpu);
+ rq_attach_root(rq, rd);
rcu_assign_pointer(rq->sd, sd);
}
* @node: node whose sched_domain we're building
* @used_nodes: nodes already in the sched_domain
*
- * Find the next node to include in a given scheduling domain. Simply
+ * Find the next node to include in a given scheduling domain. Simply
* finds the closest node not already in the @used_nodes map.
*
* Should use nodemask_t.
* @node: node whose cpumask we're constructing
* @size: number of nodes to include in this span
*
- * Given a node, construct a good cpumask for its sched_domain to span. It
+ * Given a node, construct a good cpumask for its sched_domain to span. It
* should be one that prevents unnecessary balancing, but also spreads tasks
* out optimally.
*/
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_cpus);
-static int cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map,
- struct sched_group **sg)
+static int
+cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
{
if (sg)
*sg = &per_cpu(sched_group_cpus, cpu);
#endif
#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)
+static int
+cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
{
int group;
cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
return group;
}
#elif defined(CONFIG_SCHED_MC)
-static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map,
- struct sched_group **sg)
+static int
+cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
{
if (sg)
*sg = &per_cpu(sched_group_core, cpu);
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_phys);
-static int cpu_to_phys_group(int cpu, const cpumask_t *cpu_map,
- struct sched_group **sg)
+static int
+cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
{
int group;
#ifdef CONFIG_SCHED_MC
static int build_sched_domains(const cpumask_t *cpu_map)
{
int i;
+ struct root_domain *rd;
#ifdef CONFIG_NUMA
struct sched_group **sched_group_nodes = NULL;
int sd_allnodes = 0;
* Allocate the per-node list of sched groups
*/
sched_group_nodes = kcalloc(MAX_NUMNODES, sizeof(struct sched_group *),
- GFP_KERNEL);
+ GFP_KERNEL);
if (!sched_group_nodes) {
printk(KERN_WARNING "Can not alloc sched group node list\n");
return -ENOMEM;
sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
+ rd = alloc_rootdomain();
+ if (!rd) {
+ printk(KERN_WARNING "Cannot alloc root domain\n");
+ return -ENOMEM;
+ }
+
/*
* Set up domains for cpus specified by the cpu_map.
*/
#else
sd = &per_cpu(phys_domains, i);
#endif
- cpu_attach_domain(sd, i);
+ cpu_attach_domain(sd, rd, i);
}
return 0;
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.
+ * 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);
-
+ 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);
+ err = build_sched_domains(doms_cur);
register_sched_domain_sysctl();
return err;
unregister_sched_domain_sysctl();
for_each_cpu_mask(i, *cpu_map)
- cpu_attach_domain(NULL, i);
+ cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
arch_destroy_sched_domains(cpu_map);
}
+/*
+ * 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
+ */
+void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
+{
+ int i, j;
+
+ lock_doms_cur();
+
+ /* always unregister in case we don't destroy any domains */
+ unregister_sched_domain_sysctl();
+
+ if (doms_new == NULL) {
+ ndoms_new = 1;
+ doms_new = &fallback_doms;
+ cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+ }
+
+ /* 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:
+ ;
+ }
+
+ /* 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;
+
+ register_sched_domain_sysctl();
+
+ unlock_doms_cur();
+}
+
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
static int arch_reinit_sched_domains(void)
{
int err;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
detach_destroy_domains(&cpu_online_map);
err = arch_init_sched_domains(&cpu_online_map);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return err;
}
#endif
/*
- * Force a reinitialization of the sched domains hierarchy. The domains
+ * 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 the NULL domain
* which will prevent rebalancing while the sched domains are recalculated.
{
cpumask_t non_isolated_cpus;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
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);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed(current, non_isolated_cpus) < 0)
BUG();
+ sched_init_granularity();
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ if (nr_cpu_ids == 1)
+ return;
+
+ lb_monitor_task = kthread_create(load_balance_monitor, NULL,
+ "group_balance");
+ if (!IS_ERR(lb_monitor_task)) {
+ lb_monitor_task->flags |= PF_NOFREEZE;
+ wake_up_process(lb_monitor_task);
+ } else {
+ printk(KERN_ERR "Could not create load balance monitor thread"
+ "(error = %ld) \n", PTR_ERR(lb_monitor_task));
+ }
+#endif
}
#else
void __init sched_init_smp(void)
{
+ sched_init_granularity();
}
#endif /* CONFIG_SMP */
int in_sched_functions(unsigned long addr)
{
- /* Linker adds these: start and end of __sched functions */
- extern char __sched_text_start[], __sched_text_end[];
-
return in_lock_functions(addr) ||
(addr >= (unsigned long)__sched_text_start
&& addr < (unsigned long)__sched_text_end);
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
+static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
+{
+ struct rt_prio_array *array;
+ int i;
+
+ array = &rt_rq->active;
+ for (i = 0; i < MAX_RT_PRIO; i++) {
+ INIT_LIST_HEAD(array->queue + i);
+ __clear_bit(i, array->bitmap);
+ }
+ /* delimiter for bitsearch: */
+ __set_bit(MAX_RT_PRIO, array->bitmap);
+
+#if defined CONFIG_SMP || defined CONFIG_FAIR_GROUP_SCHED
+ rt_rq->highest_prio = MAX_RT_PRIO;
+#endif
+#ifdef CONFIG_SMP
+ rt_rq->rt_nr_migratory = 0;
+ rt_rq->overloaded = 0;
+#endif
+
+ rt_rq->rt_time = 0;
+ rt_rq->rt_throttled = 0;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ rt_rq->rq = rq;
+#endif
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void init_tg_cfs_entry(struct rq *rq, struct task_group *tg,
+ struct cfs_rq *cfs_rq, struct sched_entity *se,
+ int cpu, int add)
+{
+ tg->cfs_rq[cpu] = cfs_rq;
+ init_cfs_rq(cfs_rq, rq);
+ cfs_rq->tg = tg;
+ if (add)
+ list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+
+ tg->se[cpu] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = tg->shares;
+ se->load.inv_weight = div64_64(1ULL<<32, se->load.weight);
+ se->parent = NULL;
+}
+
+static void init_tg_rt_entry(struct rq *rq, struct task_group *tg,
+ struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
+ int cpu, int add)
+{
+ tg->rt_rq[cpu] = rt_rq;
+ init_rt_rq(rt_rq, rq);
+ rt_rq->tg = tg;
+ rt_rq->rt_se = rt_se;
+ if (add)
+ list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
+
+ tg->rt_se[cpu] = rt_se;
+ rt_se->rt_rq = &rq->rt;
+ rt_se->my_q = rt_rq;
+ rt_se->parent = NULL;
+ INIT_LIST_HEAD(&rt_se->run_list);
+}
+#endif
+
void __init sched_init(void)
{
int highest_cpu = 0;
int i, j;
+#ifdef CONFIG_SMP
+ init_defrootdomain();
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ list_add(&init_task_group.list, &task_groups);
+#endif
+
for_each_possible_cpu(i) {
- struct rt_prio_array *array;
struct rq *rq;
rq = cpu_rq(i);
rq->nr_running = 0;
rq->clock = 1;
init_cfs_rq(&rq->cfs, rq);
+ init_rt_rq(&rq->rt, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
- INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
- {
- struct cfs_rq *cfs_rq = &per_cpu(init_cfs_rq, i);
- struct sched_entity *se =
- &per_cpu(init_sched_entity, i);
-
- init_cfs_rq_p[i] = cfs_rq;
- init_cfs_rq(cfs_rq, rq);
- cfs_rq->tg = &init_task_group;
- list_add(&cfs_rq->leaf_cfs_rq_list,
- &rq->leaf_cfs_rq_list);
-
- init_sched_entity_p[i] = se;
- se->cfs_rq = &rq->cfs;
- se->my_q = cfs_rq;
- se->load.weight = init_task_group_load;
- se->load.inv_weight =
- div64_64(1ULL<<32, init_task_group_load);
- se->parent = NULL;
- }
init_task_group.shares = init_task_group_load;
- spin_lock_init(&init_task_group.lock);
+ INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+ init_tg_cfs_entry(rq, &init_task_group,
+ &per_cpu(init_cfs_rq, i),
+ &per_cpu(init_sched_entity, i), i, 1);
+
+ init_task_group.rt_ratio = sysctl_sched_rt_ratio; /* XXX */
+ INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
+ init_tg_rt_entry(rq, &init_task_group,
+ &per_cpu(init_rt_rq, i),
+ &per_cpu(init_sched_rt_entity, i), i, 1);
#endif
+ rq->rt_period_expire = 0;
+ rq->rt_throttled = 0;
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
rq->cpu_load[j] = 0;
#ifdef CONFIG_SMP
rq->sd = NULL;
+ rq->rd = NULL;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
+ rq_attach_root(rq, &def_root_domain);
#endif
+ init_rq_hrtick(rq);
atomic_set(&rq->nr_iowait, 0);
-
- array = &rq->rt.active;
- for (j = 0; j < MAX_RT_PRIO; j++) {
- INIT_LIST_HEAD(array->queue + j);
- __clear_bit(j, array->bitmap);
- }
highest_cpu = i;
- /* delimiter for bitsearch: */
- __set_bit(MAX_RT_PRIO, array->bitmap);
}
set_load_weight(&init_task);
* @p: the task pointer to set.
*
* Description: This function must only be used when non-maskable interrupts
- * are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a cpu in a non-blocking manner. This function
+ * are serviced on a separate stack. It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner. This function
* must be called with all CPU's synchronized, and interrupts disabled, the
* and caller must save the original value of the current task (see
* curr_task() above) and restore that value before reenabling interrupts and
#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_SMP
+/*
+ * distribute shares of all task groups among their schedulable entities,
+ * to reflect load distribution across cpus.
+ */
+static int rebalance_shares(struct sched_domain *sd, int this_cpu)
+{
+ struct cfs_rq *cfs_rq;
+ struct rq *rq = cpu_rq(this_cpu);
+ cpumask_t sdspan = sd->span;
+ int balanced = 1;
+
+ /* Walk thr' all the task groups that we have */
+ for_each_leaf_cfs_rq(rq, cfs_rq) {
+ int i;
+ unsigned long total_load = 0, total_shares;
+ struct task_group *tg = cfs_rq->tg;
+
+ /* Gather total task load of this group across cpus */
+ for_each_cpu_mask(i, sdspan)
+ total_load += tg->cfs_rq[i]->load.weight;
+
+ /* Nothing to do if this group has no load */
+ if (!total_load)
+ continue;
+
+ /*
+ * tg->shares represents the number of cpu shares the task group
+ * is eligible to hold on a single cpu. On N cpus, it is
+ * eligible to hold (N * tg->shares) number of cpu shares.
+ */
+ total_shares = tg->shares * cpus_weight(sdspan);
+
+ /*
+ * redistribute total_shares across cpus as per the task load
+ * distribution.
+ */
+ for_each_cpu_mask(i, sdspan) {
+ unsigned long local_load, local_shares;
+
+ local_load = tg->cfs_rq[i]->load.weight;
+ local_shares = (local_load * total_shares) / total_load;
+ if (!local_shares)
+ local_shares = MIN_GROUP_SHARES;
+ if (local_shares == tg->se[i]->load.weight)
+ continue;
+
+ spin_lock_irq(&cpu_rq(i)->lock);
+ set_se_shares(tg->se[i], local_shares);
+ spin_unlock_irq(&cpu_rq(i)->lock);
+ balanced = 0;
+ }
+ }
+
+ return balanced;
+}
+
+/*
+ * How frequently should we rebalance_shares() across cpus?
+ *
+ * The more frequently we rebalance shares, the more accurate is the fairness
+ * of cpu bandwidth distribution between task groups. However higher frequency
+ * also implies increased scheduling overhead.
+ *
+ * sysctl_sched_min_bal_int_shares represents the minimum interval between
+ * consecutive calls to rebalance_shares() in the same sched domain.
+ *
+ * sysctl_sched_max_bal_int_shares represents the maximum interval between
+ * consecutive calls to rebalance_shares() in the same sched domain.
+ *
+ * These settings allows for the appropriate trade-off between accuracy of
+ * fairness and the associated overhead.
+ *
+ */
+
+/* default: 8ms, units: milliseconds */
+const_debug unsigned int sysctl_sched_min_bal_int_shares = 8;
+
+/* default: 128ms, units: milliseconds */
+const_debug unsigned int sysctl_sched_max_bal_int_shares = 128;
+
+/* kernel thread that runs rebalance_shares() periodically */
+static int load_balance_monitor(void *unused)
+{
+ unsigned int timeout = sysctl_sched_min_bal_int_shares;
+ struct sched_param schedparm;
+ int ret;
+
+ /*
+ * We don't want this thread's execution to be limited by the shares
+ * assigned to default group (init_task_group). Hence make it run
+ * as a SCHED_RR RT task at the lowest priority.
+ */
+ schedparm.sched_priority = 1;
+ ret = sched_setscheduler(current, SCHED_RR, &schedparm);
+ if (ret)
+ printk(KERN_ERR "Couldn't set SCHED_RR policy for load balance"
+ " monitor thread (error = %d) \n", ret);
+
+ while (!kthread_should_stop()) {
+ int i, cpu, balanced = 1;
+
+ /* Prevent cpus going down or coming up */
+ get_online_cpus();
+ /* lockout changes to doms_cur[] array */
+ lock_doms_cur();
+ /*
+ * Enter a rcu read-side critical section to safely walk rq->sd
+ * chain on various cpus and to walk task group list
+ * (rq->leaf_cfs_rq_list) in rebalance_shares().
+ */
+ rcu_read_lock();
+
+ for (i = 0; i < ndoms_cur; i++) {
+ cpumask_t cpumap = doms_cur[i];
+ struct sched_domain *sd = NULL, *sd_prev = NULL;
+
+ cpu = first_cpu(cpumap);
+
+ /* Find the highest domain at which to balance shares */
+ for_each_domain(cpu, sd) {
+ if (!(sd->flags & SD_LOAD_BALANCE))
+ continue;
+ sd_prev = sd;
+ }
+
+ sd = sd_prev;
+ /* sd == NULL? No load balance reqd in this domain */
+ if (!sd)
+ continue;
+
+ balanced &= rebalance_shares(sd, cpu);
+ }
+
+ rcu_read_unlock();
+
+ unlock_doms_cur();
+ put_online_cpus();
+
+ if (!balanced)
+ timeout = sysctl_sched_min_bal_int_shares;
+ else if (timeout < sysctl_sched_max_bal_int_shares)
+ timeout *= 2;
+
+ msleep_interruptible(timeout);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_SMP */
+
+static void free_sched_group(struct task_group *tg)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ if (tg->cfs_rq)
+ kfree(tg->cfs_rq[i]);
+ if (tg->se)
+ kfree(tg->se[i]);
+ if (tg->rt_rq)
+ kfree(tg->rt_rq[i]);
+ if (tg->rt_se)
+ kfree(tg->rt_se[i]);
+ }
+
+ kfree(tg->cfs_rq);
+ kfree(tg->se);
+ kfree(tg->rt_rq);
+ kfree(tg->rt_se);
+ kfree(tg);
+}
+
/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(void)
{
struct task_group *tg;
struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct rt_rq *rt_rq;
+ struct sched_rt_entity *rt_se;
struct rq *rq;
int i;
tg->se = kzalloc(sizeof(se) * NR_CPUS, GFP_KERNEL);
if (!tg->se)
goto err;
+ tg->rt_rq = kzalloc(sizeof(rt_rq) * NR_CPUS, GFP_KERNEL);
+ if (!tg->rt_rq)
+ goto err;
+ tg->rt_se = kzalloc(sizeof(rt_se) * NR_CPUS, GFP_KERNEL);
+ if (!tg->rt_se)
+ goto err;
+
+ tg->shares = NICE_0_LOAD;
+ tg->rt_ratio = 0; /* XXX */
for_each_possible_cpu(i) {
rq = cpu_rq(i);
- cfs_rq = kmalloc_node(sizeof(struct cfs_rq), GFP_KERNEL,
- cpu_to_node(i));
+ cfs_rq = kmalloc_node(sizeof(struct cfs_rq),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
if (!cfs_rq)
goto err;
- se = kmalloc_node(sizeof(struct sched_entity), GFP_KERNEL,
- cpu_to_node(i));
+ se = kmalloc_node(sizeof(struct sched_entity),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
if (!se)
goto err;
- memset(cfs_rq, 0, sizeof(struct cfs_rq));
- memset(se, 0, sizeof(struct sched_entity));
+ rt_rq = kmalloc_node(sizeof(struct rt_rq),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ if (!rt_rq)
+ goto err;
- tg->cfs_rq[i] = cfs_rq;
- init_cfs_rq(cfs_rq, rq);
- cfs_rq->tg = tg;
+ rt_se = kmalloc_node(sizeof(struct sched_rt_entity),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ if (!rt_se)
+ goto err;
- tg->se[i] = se;
- se->cfs_rq = &rq->cfs;
- se->my_q = cfs_rq;
- se->load.weight = NICE_0_LOAD;
- se->load.inv_weight = div64_64(1ULL<<32, NICE_0_LOAD);
- se->parent = NULL;
+ init_tg_cfs_entry(rq, tg, cfs_rq, se, i, 0);
+ init_tg_rt_entry(rq, tg, rt_rq, rt_se, i, 0);
}
+ lock_task_group_list();
for_each_possible_cpu(i) {
rq = cpu_rq(i);
cfs_rq = tg->cfs_rq[i];
list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+ rt_rq = tg->rt_rq[i];
+ list_add_rcu(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
}
-
- tg->shares = NICE_0_LOAD;
- spin_lock_init(&tg->lock);
+ list_add_rcu(&tg->list, &task_groups);
+ unlock_task_group_list();
return tg;
err:
- for_each_possible_cpu(i) {
- if (tg->cfs_rq)
- kfree(tg->cfs_rq[i]);
- if (tg->se)
- kfree(tg->se[i]);
- }
- kfree(tg->cfs_rq);
- kfree(tg->se);
- kfree(tg);
-
+ free_sched_group(tg);
return ERR_PTR(-ENOMEM);
}
/* rcu callback to free various structures associated with a task group */
-static void free_sched_group(struct rcu_head *rhp)
+static void free_sched_group_rcu(struct rcu_head *rhp)
{
- struct cfs_rq *cfs_rq = container_of(rhp, struct cfs_rq, rcu);
- struct task_group *tg = cfs_rq->tg;
- struct sched_entity *se;
- int i;
-
/* now it should be safe to free those cfs_rqs */
- for_each_possible_cpu(i) {
- cfs_rq = tg->cfs_rq[i];
- kfree(cfs_rq);
-
- se = tg->se[i];
- kfree(se);
- }
-
- kfree(tg->cfs_rq);
- kfree(tg->se);
- kfree(tg);
+ free_sched_group(container_of(rhp, struct task_group, rcu));
}
/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq = NULL;
+ struct rt_rq *rt_rq = NULL;
int i;
+ lock_task_group_list();
for_each_possible_cpu(i) {
cfs_rq = tg->cfs_rq[i];
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ rt_rq = tg->rt_rq[i];
+ list_del_rcu(&rt_rq->leaf_rt_rq_list);
}
+ list_del_rcu(&tg->list);
+ unlock_task_group_list();
- cfs_rq = tg->cfs_rq[0];
+ BUG_ON(!cfs_rq);
/* wait for possible concurrent references to cfs_rqs complete */
- call_rcu(&cfs_rq->rcu, free_sched_group);
+ call_rcu(&tg->rcu, free_sched_group_rcu);
}
/* change task's runqueue when it moves between groups.
rq = task_rq_lock(tsk, &flags);
- if (tsk->sched_class != &fair_sched_class)
- goto done;
-
update_rq_clock(rq);
- running = task_running(rq, tsk);
+ running = task_current(rq, tsk);
on_rq = tsk->se.on_rq;
if (on_rq) {
tsk->sched_class->put_prev_task(rq, tsk);
}
- set_task_cfs_rq(tsk);
+ set_task_rq(tsk, task_cpu(tsk));
if (on_rq) {
if (unlikely(running))
enqueue_task(rq, tsk, 0);
}
-done:
task_rq_unlock(rq, &flags);
}
+/* rq->lock to be locked by caller */
static void set_se_shares(struct sched_entity *se, unsigned long shares)
{
struct cfs_rq *cfs_rq = se->cfs_rq;
struct rq *rq = cfs_rq->rq;
int on_rq;
- spin_lock_irq(&rq->lock);
+ if (!shares)
+ shares = MIN_GROUP_SHARES;
on_rq = se->on_rq;
- if (on_rq)
+ if (on_rq) {
dequeue_entity(cfs_rq, se, 0);
+ dec_cpu_load(rq, se->load.weight);
+ }
se->load.weight = shares;
se->load.inv_weight = div64_64((1ULL<<32), shares);
- if (on_rq)
+ if (on_rq) {
enqueue_entity(cfs_rq, se, 0);
-
- spin_unlock_irq(&rq->lock);
+ inc_cpu_load(rq, se->load.weight);
+ }
}
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
- spin_lock(&tg->lock);
+ lock_task_group_list();
if (tg->shares == shares)
goto done;
+ if (shares < MIN_GROUP_SHARES)
+ shares = MIN_GROUP_SHARES;
+
+ /*
+ * Prevent any load balance activity (rebalance_shares,
+ * load_balance_fair) from referring to this group first,
+ * by taking it off the rq->leaf_cfs_rq_list on each cpu.
+ */
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ }
+
+ /* wait for any ongoing reference to this group to finish */
+ synchronize_sched();
+
+ /*
+ * Now we are free to modify the group's share on each cpu
+ * w/o tripping rebalance_share or load_balance_fair.
+ */
tg->shares = shares;
- for_each_possible_cpu(i)
+ for_each_possible_cpu(i) {
+ spin_lock_irq(&cpu_rq(i)->lock);
set_se_shares(tg->se[i], shares);
+ spin_unlock_irq(&cpu_rq(i)->lock);
+ }
+ /*
+ * Enable load balance activity on this group, by inserting it back on
+ * each cpu's rq->leaf_cfs_rq_list.
+ */
+ for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+ cfs_rq = tg->cfs_rq[i];
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+ }
done:
- spin_unlock(&tg->lock);
+ unlock_task_group_list();
return 0;
}
return tg->shares;
}
+/*
+ * Ensure the total rt_ratio <= sysctl_sched_rt_ratio
+ */
+int sched_group_set_rt_ratio(struct task_group *tg, unsigned long rt_ratio)
+{
+ struct task_group *tgi;
+ unsigned long total = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(tgi, &task_groups, list)
+ total += tgi->rt_ratio;
+ rcu_read_unlock();
+
+ if (total + rt_ratio - tg->rt_ratio > sysctl_sched_rt_ratio)
+ return -EINVAL;
+
+ tg->rt_ratio = rt_ratio;
+ return 0;
+}
+
+unsigned long sched_group_rt_ratio(struct task_group *tg)
+{
+ return tg->rt_ratio;
+}
+
#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 *cgrp)
+{
+ return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id),
+ struct task_group, css);
+}
+
+static struct cgroup_subsys_state *
+cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ struct task_group *tg;
+
+ if (!cgrp->parent) {
+ /* This is early initialization for the top cgroup */
+ init_task_group.css.cgroup = cgrp;
+ return &init_task_group.css;
+ }
+
+ /* we support only 1-level deep hierarchical scheduler atm */
+ if (cgrp->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 = cgrp;
+
+ return &tg->css;
+}
+
+static void
+cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ struct task_group *tg = cgroup_tg(cgrp);
+
+ sched_destroy_group(tg);
+}
+
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ 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 *cgrp,
+ struct cgroup *old_cont, struct task_struct *tsk)
+{
+ sched_move_task(tsk);
+}
+
+static int cpu_shares_write_uint(struct cgroup *cgrp, struct cftype *cftype,
+ u64 shareval)
+{
+ return sched_group_set_shares(cgroup_tg(cgrp), shareval);
+}
+
+static u64 cpu_shares_read_uint(struct cgroup *cgrp, struct cftype *cft)
+{
+ struct task_group *tg = cgroup_tg(cgrp);
+
+ return (u64) tg->shares;
+}
+
+static int cpu_rt_ratio_write_uint(struct cgroup *cgrp, struct cftype *cftype,
+ u64 rt_ratio_val)
+{
+ return sched_group_set_rt_ratio(cgroup_tg(cgrp), rt_ratio_val);
+}
+
+static u64 cpu_rt_ratio_read_uint(struct cgroup *cgrp, struct cftype *cft)
+{
+ struct task_group *tg = cgroup_tg(cgrp);
+
+ return (u64) tg->rt_ratio;
+}
+
+static struct cftype cpu_files[] = {
+ {
+ .name = "shares",
+ .read_uint = cpu_shares_read_uint,
+ .write_uint = cpu_shares_write_uint,
+ },
+ {
+ .name = "rt_ratio",
+ .read_uint = cpu_rt_ratio_read_uint,
+ .write_uint = cpu_rt_ratio_write_uint,
+ },
+};
+
+static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
+}
+
+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 */
+
+#ifdef CONFIG_CGROUP_CPUACCT
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* track cpu usage of a group of tasks */
+struct cpuacct {
+ struct cgroup_subsys_state css;
+ /* cpuusage holds pointer to a u64-type object on every cpu */
+ u64 *cpuusage;
+};
+
+struct cgroup_subsys cpuacct_subsys;
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cont)
+{
+ return container_of(cgroup_subsys_state(cont, cpuacct_subsys_id),
+ struct cpuacct, css);
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+ return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
+ struct cpuacct, css);
+}
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_create(
+ struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
+ if (!ca)
+ return ERR_PTR(-ENOMEM);
+
+ ca->cpuusage = alloc_percpu(u64);
+ if (!ca->cpuusage) {
+ kfree(ca);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return &ca->css;
+}
+
+/* destroy an existing cpu accounting group */
+static void
+cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct cpuacct *ca = cgroup_ca(cont);
+
+ free_percpu(ca->cpuusage);
+ kfree(ca);
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cont, struct cftype *cft)
+{
+ struct cpuacct *ca = cgroup_ca(cont);
+ 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);
+ }
+
+ return totalcpuusage;
+}
+
+static struct cftype files[] = {
+ {
+ .name = "usage",
+ .read_uint = cpuusage_read,
+ },
+};
+
+static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
+}
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+ struct cpuacct *ca;
+
+ if (!cpuacct_subsys.active)
+ return;
+
+ ca = task_ca(tsk);
+ if (ca) {
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk));
+
+ *cpuusage += cputime;
+ }
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+ .name = "cpuacct",
+ .create = cpuacct_create,
+ .destroy = cpuacct_destroy,
+ .populate = cpuacct_populate,
+ .subsys_id = cpuacct_subsys_id,
+};
+#endif /* CONFIG_CGROUP_CPUACCT */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff