The Brain Fuck Scheduler v0.101 by Con Kolivas. A single shared runqueue O(n) strict fairness earliest deadline first design. Ultra low latency and excellent desktop performance. Not recommended for 4096 cpus. --- Documentation/sysctl/kernel.txt | 14 fs/pipe.c | 4 fs/proc/base.c | 2 include/linux/init_task.h | 15 include/linux/sched.h | 187 init/Kconfig | 173 kernel/Makefile | 4 kernel/delayacct.c | 2 kernel/exit.c | 6 kernel/fork.c | 2 kernel/kthread.c | 4 kernel/posix-cpu-timers.c | 12 kernel/sched.c |10241 ---------------------------------------- kernel/sched_bfs.c | 5618 +++++++++++++++++++++ kernel/sched_debug.c | 509 - kernel/sched_fair.c | 1835 ------- kernel/sched_idletask.c | 128 kernel/sched_rt.c | 1771 ------ kernel/sysctl.c | 133 kernel/trace/trace.c | 4 kernel/workqueue.c | 2 mm/oom_kill.c | 2 22 files changed, 5693 insertions(+), 14975 deletions(-) Index: linux-2.6.30-bfs/Documentation/sysctl/kernel.txt =================================================================== --- linux-2.6.30-bfs.orig/Documentation/sysctl/kernel.txt 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/Documentation/sysctl/kernel.txt 2009-08-26 19:38:31.188300592 +1000 @@ -48,6 +48,7 @@ - randomize_va_space - real-root-dev ==> Documentation/initrd.txt - reboot-cmd [ SPARC only ] +- rr_interval - rtsig-max - rtsig-nr - sem @@ -322,6 +323,19 @@ ============================================================== +rr_interval: + +This is the smallest duration that any cpu process scheduling unit +will run for. Increasing this value can increase throughput of cpu +bound tasks substantially but at the expense of increased latencies +overall. This value is in milliseconds and the default value chosen +depends on the number of cpus available at scheduler initialisation +with a minimum of 6. + +Valid values are from 1-5000. + +============================================================== + rtsig-max & rtsig-nr: The file rtsig-max can be used to tune the maximum number Index: linux-2.6.30-bfs/fs/pipe.c =================================================================== --- linux-2.6.30-bfs.orig/fs/pipe.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/fs/pipe.c 2009-08-26 19:38:31.189300187 +1000 @@ -78,10 +78,6 @@ { DEFINE_WAIT(wait); - /* - * Pipes are system-local resources, so sleeping on them - * is considered a noninteractive wait: - */ prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); Index: linux-2.6.30-bfs/include/linux/init_task.h =================================================================== --- linux-2.6.30-bfs.orig/include/linux/init_task.h 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/include/linux/init_task.h 2009-08-26 19:38:31.215837532 +1000 @@ -119,21 +119,16 @@ .usage = ATOMIC_INIT(2), \ .flags = PF_KTHREAD, \ .lock_depth = -1, \ - .prio = MAX_PRIO-20, \ + .prio = NORMAL_PRIO, \ .static_prio = MAX_PRIO-20, \ - .normal_prio = MAX_PRIO-20, \ + .normal_prio = NORMAL_PRIO, \ + .deadline = 0, \ .policy = SCHED_NORMAL, \ .cpus_allowed = CPU_MASK_ALL, \ .mm = NULL, \ .active_mm = &init_mm, \ - .se = { \ - .group_node = LIST_HEAD_INIT(tsk.se.group_node), \ - }, \ - .rt = { \ - .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, \ - .nr_cpus_allowed = NR_CPUS, \ - }, \ + .run_list = LIST_HEAD_INIT(tsk.run_list), \ + .time_slice = HZ, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ Index: linux-2.6.30-bfs/include/linux/sched.h =================================================================== --- linux-2.6.30-bfs.orig/include/linux/sched.h 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/include/linux/sched.h 2009-08-26 19:38:31.219175361 +1000 @@ -141,13 +141,10 @@ extern unsigned long get_parent_ip(unsigned long addr); struct seq_file; -struct cfs_rq; struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -extern void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #else static inline void proc_sched_show_task(struct task_struct *p, struct seq_file *m) @@ -156,10 +153,6 @@ static inline void proc_sched_set_task(struct task_struct *p) { } -static inline void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) -{ -} #endif extern unsigned long long time_sync_thresh; @@ -251,8 +244,8 @@ extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); -extern int runqueue_is_locked(void); -extern void task_rq_unlock_wait(struct task_struct *p); +extern int grunqueue_is_locked(void); +extern void grq_unlock_wait(void); extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) @@ -969,151 +962,9 @@ struct mempolicy; struct pipe_inode_info; struct uts_namespace; - struct rq; struct sched_domain; -struct sched_class { - const struct sched_class *next; - - void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); - void (*yield_task) (struct rq *rq); - - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); - - struct task_struct * (*pick_next_task) (struct rq *rq); - void (*put_prev_task) (struct rq *rq, struct task_struct *p); - -#ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sync); - - unsigned long (*load_balance) (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); - - int (*move_one_task) (struct rq *this_rq, int this_cpu, - struct rq *busiest, struct sched_domain *sd, - enum cpu_idle_type idle); - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - int (*needs_post_schedule) (struct rq *this_rq); - void (*post_schedule) (struct rq *this_rq); - void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); - - void (*set_cpus_allowed)(struct task_struct *p, - const struct cpumask *newmask); - - void (*rq_online)(struct rq *rq); - void (*rq_offline)(struct rq *rq); -#endif - - void (*set_curr_task) (struct rq *rq); - void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); - void (*task_new) (struct rq *rq, struct task_struct *p); - - void (*switched_from) (struct rq *this_rq, struct task_struct *task, - int running); - void (*switched_to) (struct rq *this_rq, struct task_struct *task, - int running); - void (*prio_changed) (struct rq *this_rq, struct task_struct *task, - int oldprio, int running); - -#ifdef CONFIG_FAIR_GROUP_SCHED - void (*moved_group) (struct task_struct *p); -#endif -}; - -struct load_weight { - unsigned long weight, inv_weight; -}; - -/* - * CFS stats for a schedulable entity (task, task-group etc) - * - * Current field usage histogram: - * - * 4 se->block_start - * 4 se->run_node - * 4 se->sleep_start - * 6 se->load.weight - */ -struct sched_entity { - struct load_weight load; /* for load-balancing */ - struct rb_node run_node; - struct list_head group_node; - unsigned int on_rq; - - u64 exec_start; - u64 sum_exec_runtime; - u64 vruntime; - u64 prev_sum_exec_runtime; - - u64 last_wakeup; - u64 avg_overlap; - - u64 start_runtime; - u64 avg_wakeup; - u64 nr_migrations; - -#ifdef CONFIG_SCHEDSTATS - u64 wait_start; - u64 wait_max; - u64 wait_count; - u64 wait_sum; - - u64 sleep_start; - u64 sleep_max; - s64 sum_sleep_runtime; - - u64 block_start; - u64 block_max; - u64 exec_max; - u64 slice_max; - - u64 nr_migrations_cold; - u64 nr_failed_migrations_affine; - u64 nr_failed_migrations_running; - u64 nr_failed_migrations_hot; - u64 nr_forced_migrations; - u64 nr_forced2_migrations; - - u64 nr_wakeups; - u64 nr_wakeups_sync; - u64 nr_wakeups_migrate; - u64 nr_wakeups_local; - u64 nr_wakeups_remote; - u64 nr_wakeups_affine; - u64 nr_wakeups_affine_attempts; - u64 nr_wakeups_passive; - u64 nr_wakeups_idle; -#endif - -#ifdef CONFIG_FAIR_GROUP_SCHED - struct sched_entity *parent; - /* rq on which this entity is (to be) queued: */ - struct cfs_rq *cfs_rq; - /* rq "owned" by this entity/group: */ - struct cfs_rq *my_q; -#endif -}; - -struct sched_rt_entity { - struct list_head run_list; - unsigned long timeout; - unsigned int time_slice; - int nr_cpus_allowed; - - struct sched_rt_entity *back; -#ifdef CONFIG_RT_GROUP_SCHED - struct sched_rt_entity *parent; - /* rq on which this entity is (to be) queued: */ - struct rt_rq *rt_rq; - /* rq "owned" by this entity/group: */ - struct rt_rq *my_q; -#endif -}; - struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; @@ -1123,17 +974,20 @@ int lock_depth; /* BKL lock depth */ -#ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW int oncpu; -#endif -#endif - + int load_weight; /* for niceness load balancing purposes */ int prio, static_prio, normal_prio; + int time_slice, first_time_slice; + unsigned long deadline; + struct list_head run_list; unsigned int rt_priority; - const struct sched_class *sched_class; - struct sched_entity se; - struct sched_rt_entity rt; + unsigned long long timestamp, last_ran; + unsigned long long sched_time; /* sched_clock time spent running */ + + /* Compatibility crap */ + u64 se_sum_exec_runtime; + int rt_nr_cpus_allowed; + unsigned long rt_timeout; #ifdef CONFIG_PREEMPT_NOTIFIERS /* list of struct preempt_notifier: */ @@ -1449,8 +1303,12 @@ #define MAX_USER_RT_PRIO 100 #define MAX_RT_PRIO MAX_USER_RT_PRIO +#define PRIO_RANGE (40) + +#define MAX_PRIO (MAX_RT_PRIO + PRIO_RANGE) +#define NORMAL_PRIO MAX_RT_PRIO +#define PRIO_LIMIT ((NORMAL_PRIO) + 1) -#define MAX_PRIO (MAX_RT_PRIO + 40) #define DEFAULT_PRIO (MAX_RT_PRIO + 20) static inline int rt_prio(int prio) @@ -1733,11 +1591,7 @@ extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ -#ifdef CONFIG_SMP -extern void sched_exec(void); -#else #define sched_exec() {} -#endif extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); @@ -2283,7 +2137,10 @@ return task_thread_info(p)->cpu; } -extern void set_task_cpu(struct task_struct *p, unsigned int cpu); +static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + task_thread_info(p)->cpu = cpu; +} #else Index: linux-2.6.30-bfs/kernel/sched.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sched.c 2009-06-10 13:05:27.000000000 +1000 +++ /dev/null 1970-01-01 00:00:00.000000000 +0000 @@ -1,10241 +0,0 @@ -/* - * kernel/sched.c - * - * Kernel scheduler and related syscalls - * - * Copyright (C) 1991-2002 Linus Torvalds - * - * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and - * make semaphores SMP safe - * 1998-11-19 Implemented schedule_timeout() and related stuff - * by Andrea Arcangeli - * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: - * hybrid priority-list and round-robin design with - * an array-switch method of distributing timeslices - * and per-CPU runqueues. Cleanups and useful suggestions - * by Davide Libenzi, preemptible kernel bits by Robert Love. - * 2003-09-03 Interactivity tuning by Con Kolivas. - * 2004-04-02 Scheduler domains code by Nick Piggin - * 2007-04-15 Work begun on replacing all interactivity tuning with a - * fair scheduling design by Con Kolivas. - * 2007-05-05 Load balancing (smp-nice) and other improvements - * 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 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include "sched_cpupri.h" - -/* - * Convert user-nice values [ -20 ... 0 ... 19 ] - * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], - * and back. - */ -#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) -#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) -#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) - -/* - * 'User priority' is the nice value converted to something we - * can work with better when scaling various scheduler parameters, - * it's a [ 0 ... 39 ] range. - */ -#define USER_PRIO(p) ((p)-MAX_RT_PRIO) -#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) -#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) - -/* - * Helpers for converting nanosecond timing to jiffy resolution - */ -#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 - -/* - * These are the 'tuning knobs' of the scheduler: - * - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. - */ -#define DEF_TIMESLICE (100 * HZ / 1000) - -/* - * single value that denotes runtime == period, ie unlimited time. - */ -#define RUNTIME_INF ((u64)~0ULL) - -DEFINE_TRACE(sched_wait_task); -DEFINE_TRACE(sched_wakeup); -DEFINE_TRACE(sched_wakeup_new); -DEFINE_TRACE(sched_switch); -DEFINE_TRACE(sched_migrate_task); - -#ifdef CONFIG_SMP - -static void double_rq_lock(struct rq *rq1, struct rq *rq2); - -/* - * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) - * Since cpu_power is a 'constant', we can use a reciprocal divide. - */ -static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load) -{ - return reciprocal_divide(load, sg->reciprocal_cpu_power); -} - -/* - * Each time a sched group cpu_power is changed, - * we must compute its reciprocal value - */ -static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) -{ - sg->__cpu_power += val; - sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power); -} -#endif - -static inline int rt_policy(int policy) -{ - if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) - return 1; - return 0; -} - -static inline int task_has_rt_policy(struct task_struct *p) -{ - return rt_policy(p->policy); -} - -/* - * This is the priority-queue data structure of the RT scheduling class: - */ -struct rt_prio_array { - DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ - struct list_head queue[MAX_RT_PRIO]; -}; - -struct rt_bandwidth { - /* nests inside the rq lock: */ - spinlock_t rt_runtime_lock; - ktime_t rt_period; - u64 rt_runtime; - struct hrtimer rt_period_timer; -}; - -static struct rt_bandwidth def_rt_bandwidth; - -static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); - -static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) -{ - struct rt_bandwidth *rt_b = - container_of(timer, struct rt_bandwidth, rt_period_timer); - ktime_t now; - int overrun; - int idle = 0; - - for (;;) { - now = hrtimer_cb_get_time(timer); - overrun = hrtimer_forward(timer, now, rt_b->rt_period); - - if (!overrun) - break; - - idle = do_sched_rt_period_timer(rt_b, overrun); - } - - return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; -} - -static -void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) -{ - rt_b->rt_period = ns_to_ktime(period); - rt_b->rt_runtime = runtime; - - spin_lock_init(&rt_b->rt_runtime_lock); - - hrtimer_init(&rt_b->rt_period_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rt_b->rt_period_timer.function = sched_rt_period_timer; -} - -static inline int rt_bandwidth_enabled(void) -{ - return sysctl_sched_rt_runtime >= 0; -} - -static void start_rt_bandwidth(struct rt_bandwidth *rt_b) -{ - ktime_t now; - - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return; - - if (hrtimer_active(&rt_b->rt_period_timer)) - return; - - spin_lock(&rt_b->rt_runtime_lock); - for (;;) { - unsigned long delta; - ktime_t soft, hard; - - if (hrtimer_active(&rt_b->rt_period_timer)) - break; - - now = hrtimer_cb_get_time(&rt_b->rt_period_timer); - hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - - soft = hrtimer_get_softexpires(&rt_b->rt_period_timer); - hard = hrtimer_get_expires(&rt_b->rt_period_timer); - delta = ktime_to_ns(ktime_sub(hard, soft)); - __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, - HRTIMER_MODE_ABS, 0); - } - spin_unlock(&rt_b->rt_runtime_lock); -} - -#ifdef CONFIG_RT_GROUP_SCHED -static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) -{ - hrtimer_cancel(&rt_b->rt_period_timer); -} -#endif - -/* - * sched_domains_mutex serializes calls to arch_init_sched_domains, - * detach_destroy_domains and partition_sched_domains. - */ -static DEFINE_MUTEX(sched_domains_mutex); - -#ifdef CONFIG_GROUP_SCHED - -#include - -struct cfs_rq; - -static LIST_HEAD(task_groups); - -/* task group related information */ -struct task_group { -#ifdef CONFIG_CGROUP_SCHED - struct cgroup_subsys_state css; -#endif - -#ifdef CONFIG_USER_SCHED - uid_t uid; -#endif - -#ifdef CONFIG_FAIR_GROUP_SCHED - /* schedulable entities of this group on each cpu */ - struct sched_entity **se; - /* runqueue "owned" by this group on each cpu */ - struct cfs_rq **cfs_rq; - unsigned long shares; -#endif - -#ifdef CONFIG_RT_GROUP_SCHED - struct sched_rt_entity **rt_se; - struct rt_rq **rt_rq; - - struct rt_bandwidth rt_bandwidth; -#endif - - struct rcu_head rcu; - struct list_head list; - - struct task_group *parent; - struct list_head siblings; - struct list_head children; -}; - -#ifdef CONFIG_USER_SCHED - -/* Helper function to pass uid information to create_sched_user() */ -void set_tg_uid(struct user_struct *user) -{ - user->tg->uid = user->uid; -} - -/* - * Root task group. - * Every UID task group (including init_task_group aka UID-0) will - * be a child to this group. - */ -struct task_group root_task_group; - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* Default task group's sched entity on each cpu */ -static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); -/* Default task group's cfs_rq on each cpu */ -static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -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; -#endif /* CONFIG_RT_GROUP_SCHED */ -#else /* !CONFIG_USER_SCHED */ -#define root_task_group init_task_group -#endif /* CONFIG_USER_SCHED */ - -/* task_group_lock serializes add/remove of task groups and also changes to - * a task group's cpu shares. - */ -static DEFINE_SPINLOCK(task_group_lock); - -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return list_empty(&root_task_group.children); -} -#endif - -#ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_USER_SCHED -# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else /* !CONFIG_USER_SCHED */ -# define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif /* CONFIG_USER_SCHED */ - -/* - * A weight of 0 or 1 can cause arithmetics problems. - * A weight of a cfs_rq is the sum of weights of which entities - * are queued on this cfs_rq, so a weight of a entity should not be - * too large, so as the shares value of a task group. - * (The default weight is 1024 - so there's no practical - * limitation from this.) - */ -#define MIN_SHARES 2 -#define MAX_SHARES (1UL << 18) - -static int init_task_group_load = INIT_TASK_GROUP_LOAD; -#endif - -/* Default task group. - * Every task in system belong to this group at bootup. - */ -struct task_group init_task_group; - -/* return group to which a task belongs */ -static inline struct task_group *task_group(struct task_struct *p) -{ - struct task_group *tg; - -#ifdef CONFIG_USER_SCHED - rcu_read_lock(); - tg = __task_cred(p)->user->tg; - rcu_read_unlock(); -#elif defined(CONFIG_CGROUP_SCHED) - tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), - struct task_group, css); -#else - 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_rq(struct task_struct *p, unsigned int cpu) -{ -#ifdef CONFIG_FAIR_GROUP_SCHED - p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; - p->se.parent = task_group(p)->se[cpu]; -#endif - -#ifdef CONFIG_RT_GROUP_SCHED - p->rt.rt_rq = task_group(p)->rt_rq[cpu]; - p->rt.parent = task_group(p)->rt_se[cpu]; -#endif -} - -#else - -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return 1; -} -#endif - -static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } -static inline struct task_group *task_group(struct task_struct *p) -{ - return NULL; -} - -#endif /* CONFIG_GROUP_SCHED */ - -/* CFS-related fields in a runqueue */ -struct cfs_rq { - struct load_weight load; - unsigned long nr_running; - - u64 exec_clock; - u64 min_vruntime; - - struct rb_root tasks_timeline; - struct rb_node *rb_leftmost; - - struct list_head tasks; - struct list_head *balance_iterator; - - /* - * 'curr' points to currently running entity on this cfs_rq. - * It is set to NULL otherwise (i.e when none are currently running). - */ - struct sched_entity *curr, *next, *last; - - unsigned int nr_spread_over; - -#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 - * 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; - struct task_group *tg; /* group that "owns" this runqueue */ - -#ifdef CONFIG_SMP - /* - * the part of load.weight contributed by tasks - */ - unsigned long task_weight; - - /* - * h_load = weight * f(tg) - * - * Where f(tg) is the recursive weight fraction assigned to - * this group. - */ - unsigned long h_load; - - /* - * this cpu's part of tg->shares - */ - unsigned long shares; - - /* - * load.weight at the time we set shares - */ - unsigned long rq_weight; -#endif -#endif -}; - -/* Real-Time classes' related field in a runqueue: */ -struct rt_rq { - struct rt_prio_array active; - unsigned long rt_nr_running; -#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED - struct { - int curr; /* highest queued rt task prio */ -#ifdef CONFIG_SMP - int next; /* next highest */ -#endif - } highest_prio; -#endif -#ifdef CONFIG_SMP - unsigned long rt_nr_migratory; - int overloaded; - struct plist_head pushable_tasks; -#endif - int rt_throttled; - u64 rt_time; - u64 rt_runtime; - /* Nests inside the rq lock: */ - spinlock_t rt_runtime_lock; - -#ifdef CONFIG_RT_GROUP_SCHED - unsigned long rt_nr_boosted; - - 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_var_t span; - cpumask_var_t online; - - /* - * The "RT overload" flag: it gets set if a CPU has more than - * one runnable RT task. - */ - cpumask_var_t rto_mask; - atomic_t rto_count; -#ifdef CONFIG_SMP - struct cpupri cpupri; -#endif -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - /* - * Preferred wake up cpu nominated by sched_mc balance that will be - * used when most cpus are idle in the system indicating overall very - * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2) - */ - unsigned int sched_mc_preferred_wakeup_cpu; -#endif -}; - -/* - * 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 - * (such as the load balancing or the thread migration code), lock - * acquire operations must be ordered by ascending &runqueue. - */ -struct rq { - /* runqueue lock: */ - spinlock_t lock; - - /* - * nr_running and cpu_load should be in the same cacheline because - * remote CPUs use both these fields when doing load calculation. - */ - unsigned long nr_running; - #define CPU_LOAD_IDX_MAX 5 - unsigned long cpu_load[CPU_LOAD_IDX_MAX]; -#ifdef CONFIG_NO_HZ - unsigned long last_tick_seen; - unsigned char in_nohz_recently; -#endif - /* 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; - -#ifdef CONFIG_FAIR_GROUP_SCHED - /* list of leaf cfs_rq on this cpu: */ - struct list_head leaf_cfs_rq_list; -#endif -#ifdef CONFIG_RT_GROUP_SCHED - struct list_head leaf_rt_rq_list; -#endif - - /* - * This is part of a global counter where only the total sum - * over all CPUs matters. A task can increase this counter on - * one CPU and if it got migrated afterwards it may decrease - * it on another CPU. Always updated under the runqueue lock: - */ - unsigned long nr_uninterruptible; - - struct task_struct *curr, *idle; - unsigned long next_balance; - struct mm_struct *prev_mm; - - u64 clock; - - atomic_t nr_iowait; - -#ifdef CONFIG_SMP - struct root_domain *rd; - struct sched_domain *sd; - - unsigned char idle_at_tick; - /* For active balancing */ - int active_balance; - int push_cpu; - /* cpu of this runqueue: */ - int cpu; - int online; - - unsigned long avg_load_per_task; - - struct task_struct *migration_thread; - struct list_head migration_queue; -#endif - -#ifdef CONFIG_SCHED_HRTICK -#ifdef CONFIG_SMP - int hrtick_csd_pending; - struct call_single_data hrtick_csd; -#endif - struct hrtimer hrtick_timer; -#endif - -#ifdef CONFIG_SCHEDSTATS - /* latency stats */ - struct sched_info rq_sched_info; - unsigned long long rq_cpu_time; - /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ - - /* sys_sched_yield() stats */ - unsigned int yld_count; - - /* schedule() stats */ - unsigned int sched_switch; - unsigned int sched_count; - unsigned int sched_goidle; - - /* try_to_wake_up() stats */ - unsigned int ttwu_count; - unsigned int ttwu_local; - - /* BKL stats */ - unsigned int bkl_count; -#endif -}; - -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); - -static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) -{ - rq->curr->sched_class->check_preempt_curr(rq, p, sync); -} - -static inline int cpu_of(struct rq *rq) -{ -#ifdef CONFIG_SMP - return rq->cpu; -#else - return 0; -#endif -} - -/* - * The domain tree (rq->sd) is protected by RCU's quiescent state transition. - * See detach_destroy_domains: synchronize_sched for details. - * - * The domain tree of any CPU may only be accessed from within - * preempt-disabled sections. - */ -#define for_each_domain(cpu, __sd) \ - for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) - -#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) -#define this_rq() (&__get_cpu_var(runqueues)) -#define task_rq(p) cpu_rq(task_cpu(p)) -#define cpu_curr(cpu) (cpu_rq(cpu)->curr) - -static inline void update_rq_clock(struct rq *rq) -{ - rq->clock = sched_clock_cpu(cpu_of(rq)); -} - -/* - * Tunables that become constants when CONFIG_SCHED_DEBUG is off: - */ -#ifdef CONFIG_SCHED_DEBUG -# define const_debug __read_mostly -#else -# define const_debug static const -#endif - -/** - * runqueue_is_locked - * - * Returns true if the current cpu runqueue is locked. - * This interface allows printk to be called with the runqueue lock - * held and know whether or not it is OK to wake up the klogd. - */ -int runqueue_is_locked(void) -{ - int cpu = get_cpu(); - struct rq *rq = cpu_rq(cpu); - int ret; - - ret = spin_is_locked(&rq->lock); - put_cpu(); - return ret; -} - -/* - * Debugging: various feature bits - */ - -#define SCHED_FEAT(name, enabled) \ - __SCHED_FEAT_##name , - -enum { -#include "sched_features.h" -}; - -#undef SCHED_FEAT - -#define SCHED_FEAT(name, enabled) \ - (1UL << __SCHED_FEAT_##name) * enabled | - -const_debug unsigned int sysctl_sched_features = -#include "sched_features.h" - 0; - -#undef SCHED_FEAT - -#ifdef CONFIG_SCHED_DEBUG -#define SCHED_FEAT(name, enabled) \ - #name , - -static __read_mostly char *sched_feat_names[] = { -#include "sched_features.h" - NULL -}; - -#undef SCHED_FEAT - -static int sched_feat_show(struct seq_file *m, void *v) -{ - int i; - - for (i = 0; sched_feat_names[i]; i++) { - if (!(sysctl_sched_features & (1UL << i))) - seq_puts(m, "NO_"); - seq_printf(m, "%s ", sched_feat_names[i]); - } - seq_puts(m, "\n"); - - return 0; -} - -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - char *cmp = buf; - int neg = 0; - int i; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - if (strncmp(buf, "NO_", 3) == 0) { - neg = 1; - cmp += 3; - } - - for (i = 0; sched_feat_names[i]; i++) { - int len = strlen(sched_feat_names[i]); - - if (strncmp(cmp, sched_feat_names[i], len) == 0) { - if (neg) - sysctl_sched_features &= ~(1UL << i); - else - sysctl_sched_features |= (1UL << i); - break; - } - } - - if (!sched_feat_names[i]) - return -EINVAL; - - filp->f_pos += cnt; - - return cnt; -} - -static int sched_feat_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, sched_feat_show, NULL); -} - -static struct file_operations sched_feat_fops = { - .open = sched_feat_open, - .write = sched_feat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static __init int sched_init_debug(void) -{ - debugfs_create_file("sched_features", 0644, NULL, NULL, - &sched_feat_fops); - - return 0; -} -late_initcall(sched_init_debug); - -#endif - -#define sched_feat(x) (sysctl_sched_features & (1UL << __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; - -/* - * ratelimit for updating the group shares. - * default: 0.25ms - */ -unsigned int sysctl_sched_shares_ratelimit = 250000; - -/* - * Inject some fuzzyness into changing the per-cpu group shares - * this avoids remote rq-locks at the expense of fairness. - * default: 4 - */ -unsigned int sysctl_sched_shares_thresh = 4; - -/* - * period over which we measure -rt task cpu usage in us. - * default: 1s - */ -unsigned int sysctl_sched_rt_period = 1000000; - -static __read_mostly int scheduler_running; - -/* - * part of the period that we allow rt tasks to run in us. - * default: 0.95s - */ -int sysctl_sched_rt_runtime = 950000; - -static inline u64 global_rt_period(void) -{ - return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; -} - -static inline u64 global_rt_runtime(void) -{ - if (sysctl_sched_rt_runtime < 0) - return RUNTIME_INF; - - return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; -} - -#ifndef prepare_arch_switch -# define prepare_arch_switch(next) do { } while (0) -#endif -#ifndef finish_arch_switch -# 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 task_current(rq, p); -} - -static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) -{ -} - -static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = current; -#endif - /* - * If we are tracking spinlock dependencies then we have to - * fix up the runqueue lock - which gets 'carried over' from - * prev into current: - */ - spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - - spin_unlock_irq(&rq->lock); -} - -#else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - -static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) -{ -#ifdef CONFIG_SMP - /* - * We can optimise this out completely for !SMP, because the - * SMP rebalancing from interrupt is the only thing that cares - * here. - */ - next->oncpu = 1; -#endif -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - spin_unlock_irq(&rq->lock); -#else - spin_unlock(&rq->lock); -#endif -} - -static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) -{ -#ifdef CONFIG_SMP - /* - * After ->oncpu is cleared, the task can be moved to a different CPU. - * We must ensure this doesn't happen until the switch is completely - * finished. - */ - smp_wmb(); - prev->oncpu = 0; -#endif -#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_enable(); -#endif -} -#endif /* __ARCH_WANT_UNLOCKED_CTXSW */ - -/* - * __task_rq_lock - lock the runqueue a given task resides on. - * Must be called interrupts disabled. - */ -static inline struct rq *__task_rq_lock(struct task_struct *p) - __acquires(rq->lock) -{ - for (;;) { - struct rq *rq = task_rq(p); - spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) - return rq; - spin_unlock(&rq->lock); - } -} - -/* - * 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 - * explicitly disabling preemption. - */ -static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) - __acquires(rq->lock) -{ - struct rq *rq; - - for (;;) { - local_irq_save(*flags); - rq = task_rq(p); - spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) - return rq; - spin_unlock_irqrestore(&rq->lock, *flags); - } -} - -void task_rq_unlock_wait(struct task_struct *p) -{ - struct rq *rq = task_rq(p); - - smp_mb(); /* spin-unlock-wait is not a full memory barrier */ - spin_unlock_wait(&rq->lock); -} - -static void __task_rq_unlock(struct rq *rq) - __releases(rq->lock) -{ - spin_unlock(&rq->lock); -} - -static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) - __releases(rq->lock) -{ - spin_unlock_irqrestore(&rq->lock, *flags); -} - -/* - * this_rq_lock - lock this runqueue and disable interrupts. - */ -static struct rq *this_rq_lock(void) - __acquires(rq->lock) -{ - struct rq *rq; - - local_irq_disable(); - rq = this_rq(); - spin_lock(&rq->lock); - - return rq; -} - -#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. - */ - -/* - * 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; - if (!cpu_active(cpu_of(rq))) - return 0; - return hrtimer_is_hres_active(&rq->hrtick_timer); -} - -static void hrtick_clear(struct rq *rq) -{ - if (hrtimer_active(&rq->hrtick_timer)) - hrtimer_cancel(&rq->hrtick_timer); -} - -/* - * 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; -} - -#ifdef CONFIG_SMP -/* - * called from hardirq (IPI) context - */ -static void __hrtick_start(void *arg) -{ - struct rq *rq = arg; - - spin_lock(&rq->lock); - hrtimer_restart(&rq->hrtick_timer); - rq->hrtick_csd_pending = 0; - spin_unlock(&rq->lock); -} - -/* - * Called to set the hrtick timer state. - * - * called with rq->lock held and irqs disabled - */ -static void hrtick_start(struct rq *rq, u64 delay) -{ - struct hrtimer *timer = &rq->hrtick_timer; - ktime_t time = ktime_add_ns(timer->base->get_time(), delay); - - hrtimer_set_expires(timer, time); - - if (rq == this_rq()) { - hrtimer_restart(timer); - } else if (!rq->hrtick_csd_pending) { - __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); - rq->hrtick_csd_pending = 1; - } -} - -static int -hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int cpu = (int)(long)hcpu; - - switch (action) { - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - hrtick_clear(cpu_rq(cpu)); - return NOTIFY_OK; - } - - return NOTIFY_DONE; -} - -static __init void init_hrtick(void) -{ - hotcpu_notifier(hotplug_hrtick, 0); -} -#else -/* - * Called to set the hrtick timer state. - * - * called with rq->lock held and irqs disabled - */ -static void hrtick_start(struct rq *rq, u64 delay) -{ - __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, - HRTIMER_MODE_REL, 0); -} - -static inline void init_hrtick(void) -{ -} -#endif /* CONFIG_SMP */ - -static void init_rq_hrtick(struct rq *rq) -{ -#ifdef CONFIG_SMP - rq->hrtick_csd_pending = 0; - - rq->hrtick_csd.flags = 0; - rq->hrtick_csd.func = __hrtick_start; - rq->hrtick_csd.info = rq; -#endif - - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rq->hrtick_timer.function = hrtick; -} -#else /* CONFIG_SCHED_HRTICK */ -static inline void hrtick_clear(struct rq *rq) -{ -} - -static inline void init_rq_hrtick(struct rq *rq) -{ -} - -static inline void init_hrtick(void) -{ -} -#endif /* CONFIG_SCHED_HRTICK */ - -/* - * resched_task - mark a task 'to be rescheduled now'. - * - * On UP this means the setting of the need_resched flag, on SMP it - * might also involve a cross-CPU call to trigger the scheduler on - * the target CPU. - */ -#ifdef CONFIG_SMP - -#ifndef tsk_is_polling -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) -#endif - -static void resched_task(struct task_struct *p) -{ - int cpu; - - assert_spin_locked(&task_rq(p)->lock); - - if (test_tsk_need_resched(p)) - return; - - set_tsk_need_resched(p); - - cpu = task_cpu(p); - if (cpu == smp_processor_id()) - return; - - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) - smp_send_reschedule(cpu); -} - -static void resched_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - if (!spin_trylock_irqsave(&rq->lock, flags)) - return; - resched_task(cpu_curr(cpu)); - spin_unlock_irqrestore(&rq->lock, flags); -} - -#ifdef CONFIG_NO_HZ -/* - * When add_timer_on() enqueues a timer into the timer wheel of an - * idle CPU then this timer might expire before the next timer event - * which is scheduled to wake up that CPU. In case of a completely - * idle system the next event might even be infinite time into the - * future. wake_up_idle_cpu() ensures that the CPU is woken up and - * leaves the inner idle loop so the newly added timer is taken into - * account when the CPU goes back to idle and evaluates the timer - * wheel for the next timer event. - */ -void wake_up_idle_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - if (cpu == smp_processor_id()) - return; - - /* - * This is safe, as this function is called with the timer - * wheel base lock of (cpu) held. When the CPU is on the way - * to idle and has not yet set rq->curr to idle then it will - * be serialized on the timer wheel base lock and take the new - * timer into account automatically. - */ - if (rq->curr != rq->idle) - return; - - /* - * We can set TIF_RESCHED on the idle task of the other CPU - * lockless. The worst case is that the other CPU runs the - * idle task through an additional NOOP schedule() - */ - set_tsk_need_resched(rq->idle); - - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(rq->idle)) - smp_send_reschedule(cpu); -} -#endif /* CONFIG_NO_HZ */ - -#else /* !CONFIG_SMP */ -static void resched_task(struct task_struct *p) -{ - assert_spin_locked(&task_rq(p)->lock); - set_tsk_need_resched(p); -} -#endif /* CONFIG_SMP */ - -#if BITS_PER_LONG == 32 -# define WMULT_CONST (~0UL) -#else -# define WMULT_CONST (1UL << 32) -#endif - -#define WMULT_SHIFT 32 - -/* - * Shift right and round: - */ -#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) - -/* - * delta *= weight / lw - */ -static unsigned long -calc_delta_mine(unsigned long delta_exec, unsigned long weight, - struct load_weight *lw) -{ - u64 tmp; - - if (!lw->inv_weight) { - if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) - lw->inv_weight = 1; - else - lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) - / (lw->weight+1); - } - - tmp = (u64)delta_exec * weight; - /* - * Check whether we'd overflow the 64-bit multiplication: - */ - if (unlikely(tmp > WMULT_CONST)) - tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, - WMULT_SHIFT/2); - else - tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); - - return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); -} - -static inline void update_load_add(struct load_weight *lw, unsigned long inc) -{ - lw->weight += inc; - lw->inv_weight = 0; -} - -static inline void update_load_sub(struct load_weight *lw, unsigned long dec) -{ - lw->weight -= dec; - lw->inv_weight = 0; -} - -/* - * 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 - * scaled version of the new time slice allocation that they receive on time - * slice expiry etc. - */ - -#define WEIGHT_IDLEPRIO 3 -#define WMULT_IDLEPRIO 1431655765 - -/* - * Nice levels are multiplicative, with a gentle 10% change for every - * nice level changed. I.e. when a CPU-bound task goes from nice 0 to - * nice 1, it will get ~10% less CPU time than another CPU-bound task - * that remained on nice 0. - * - * The "10% effect" is relative and cumulative: from _any_ nice level, - * if you go up 1 level, it's -10% CPU usage, if you go down 1 level - * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. - * If a task goes up by ~10% and another task goes down by ~10% then - * the relative distance between them is ~25%.) - */ -static const int prio_to_weight[40] = { - /* -20 */ 88761, 71755, 56483, 46273, 36291, - /* -15 */ 29154, 23254, 18705, 14949, 11916, - /* -10 */ 9548, 7620, 6100, 4904, 3906, - /* -5 */ 3121, 2501, 1991, 1586, 1277, - /* 0 */ 1024, 820, 655, 526, 423, - /* 5 */ 335, 272, 215, 172, 137, - /* 10 */ 110, 87, 70, 56, 45, - /* 15 */ 36, 29, 23, 18, 15, -}; - -/* - * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. - * - * In cases where the weight does not change often, we can use the - * precalculated inverse to speed up arithmetics by turning divisions - * into multiplications: - */ -static const u32 prio_to_wmult[40] = { - /* -20 */ 48388, 59856, 76040, 92818, 118348, - /* -15 */ 147320, 184698, 229616, 287308, 360437, - /* -10 */ 449829, 563644, 704093, 875809, 1099582, - /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, - /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, - /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, - /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, - /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, -}; - -static void activate_task(struct rq *rq, struct task_struct *p, int wakeup); - -/* - * runqueue iterator, to support SMP load-balancing between different - * scheduling classes, without having to expose their internal data - * structures to the load-balancing proper: - */ -struct rq_iterator { - void *arg; - struct task_struct *(*start)(void *); - struct task_struct *(*next)(void *); -}; - -#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 - -/* Time spent by the tasks of the cpu accounting group executing in ... */ -enum cpuacct_stat_index { - CPUACCT_STAT_USER, /* ... user mode */ - CPUACCT_STAT_SYSTEM, /* ... kernel mode */ - - CPUACCT_STAT_NSTATS, -}; - -#ifdef CONFIG_CGROUP_CPUACCT -static void cpuacct_charge(struct task_struct *tsk, u64 cputime); -static void cpuacct_update_stats(struct task_struct *tsk, - enum cpuacct_stat_index idx, cputime_t val); -#else -static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} -static inline void cpuacct_update_stats(struct task_struct *tsk, - enum cpuacct_stat_index idx, cputime_t val) {} -#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); -} - -#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED) -typedef int (*tg_visitor)(struct task_group *, void *); - -/* - * Iterate the full tree, calling @down when first entering a node and @up when - * leaving it for the final time. - */ -static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) -{ - struct task_group *parent, *child; - int ret; - - rcu_read_lock(); - parent = &root_task_group; -down: - ret = (*down)(parent, data); - if (ret) - goto out_unlock; - list_for_each_entry_rcu(child, &parent->children, siblings) { - parent = child; - goto down; - -up: - continue; - } - ret = (*up)(parent, data); - if (ret) - goto out_unlock; - - child = parent; - parent = parent->parent; - if (parent) - goto up; -out_unlock: - rcu_read_unlock(); - - return ret; -} - -static int tg_nop(struct task_group *tg, void *data) -{ - return 0; -} -#endif - -#ifdef CONFIG_SMP -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); -static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - -static unsigned long cpu_avg_load_per_task(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long nr_running = ACCESS_ONCE(rq->nr_running); - - if (nr_running) - rq->avg_load_per_task = rq->load.weight / nr_running; - else - rq->avg_load_per_task = 0; - - return rq->avg_load_per_task; -} - -#ifdef CONFIG_FAIR_GROUP_SCHED - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - -/* - * Calculate and set the cpu's group shares. - */ -static void -update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, unsigned long sd_rq_weight) -{ - unsigned long shares; - unsigned long rq_weight; - - if (!tg->se[cpu]) - return; - - rq_weight = tg->cfs_rq[cpu]->rq_weight; - - /* - * \Sum shares * rq_weight - * shares = ----------------------- - * \Sum rq_weight - * - */ - shares = (sd_shares * rq_weight) / sd_rq_weight; - shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - - if (abs(shares - tg->se[cpu]->load.weight) > - sysctl_sched_shares_thresh) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - tg->cfs_rq[cpu]->shares = shares; - - __set_se_shares(tg->se[cpu], shares); - spin_unlock_irqrestore(&rq->lock, flags); - } -} - -/* - * Re-compute the task group their per cpu shares over the given domain. - * This needs to be done in a bottom-up fashion because the rq weight of a - * parent group depends on the shares of its child groups. - */ -static int tg_shares_up(struct task_group *tg, void *data) -{ - unsigned long weight, rq_weight = 0; - unsigned long shares = 0; - struct sched_domain *sd = data; - int i; - - for_each_cpu(i, sched_domain_span(sd)) { - /* - * If there are currently no tasks on the cpu pretend there - * is one of average load so that when a new task gets to - * run here it will not get delayed by group starvation. - */ - weight = tg->cfs_rq[i]->load.weight; - if (!weight) - weight = NICE_0_LOAD; - - tg->cfs_rq[i]->rq_weight = weight; - rq_weight += weight; - shares += tg->cfs_rq[i]->shares; - } - - if ((!shares && rq_weight) || shares > tg->shares) - shares = tg->shares; - - if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) - shares = tg->shares; - - for_each_cpu(i, sched_domain_span(sd)) - update_group_shares_cpu(tg, i, shares, rq_weight); - - return 0; -} - -/* - * Compute the cpu's hierarchical load factor for each task group. - * This needs to be done in a top-down fashion because the load of a child - * group is a fraction of its parents load. - */ -static int tg_load_down(struct task_group *tg, void *data) -{ - unsigned long load; - long cpu = (long)data; - - if (!tg->parent) { - load = cpu_rq(cpu)->load.weight; - } else { - load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->cfs_rq[cpu]->shares; - load /= tg->parent->cfs_rq[cpu]->load.weight + 1; - } - - tg->cfs_rq[cpu]->h_load = load; - - return 0; -} - -static void update_shares(struct sched_domain *sd) -{ - u64 now = cpu_clock(raw_smp_processor_id()); - s64 elapsed = now - sd->last_update; - - if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { - sd->last_update = now; - walk_tg_tree(tg_nop, tg_shares_up, sd); - } -} - -static void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ - spin_unlock(&rq->lock); - update_shares(sd); - spin_lock(&rq->lock); -} - -static void update_h_load(long cpu) -{ - walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); -} - -#else - -static inline void update_shares(struct sched_domain *sd) -{ -} - -static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ -} - -#endif - -#ifdef CONFIG_PREEMPT - -/* - * fair double_lock_balance: Safely acquires both rq->locks in a fair - * way at the expense of forcing extra atomic operations in all - * invocations. This assures that the double_lock is acquired using the - * same underlying policy as the spinlock_t on this architecture, which - * reduces latency compared to the unfair variant below. However, it - * also adds more overhead and therefore may reduce throughput. - */ -static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) - __releases(this_rq->lock) - __acquires(busiest->lock) - __acquires(this_rq->lock) -{ - spin_unlock(&this_rq->lock); - double_rq_lock(this_rq, busiest); - - return 1; -} - -#else -/* - * Unfair double_lock_balance: Optimizes throughput at the expense of - * latency by eliminating extra atomic operations when the locks are - * already in proper order on entry. This favors lower cpu-ids and will - * grant the double lock to lower cpus over higher ids under contention, - * regardless of entry order into the function. - */ -static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) - __releases(this_rq->lock) - __acquires(busiest->lock) - __acquires(this_rq->lock) -{ - int ret = 0; - - if (unlikely(!spin_trylock(&busiest->lock))) { - if (busiest < this_rq) { - spin_unlock(&this_rq->lock); - spin_lock(&busiest->lock); - spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); - ret = 1; - } else - spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); - } - return ret; -} - -#endif /* CONFIG_PREEMPT */ - -/* - * double_lock_balance - lock the busiest runqueue, this_rq is locked already. - */ -static int double_lock_balance(struct rq *this_rq, struct rq *busiest) -{ - if (unlikely(!irqs_disabled())) { - /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); - BUG_ON(1); - } - - return _double_lock_balance(this_rq, busiest); -} - -static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) - __releases(busiest->lock) -{ - spin_unlock(&busiest->lock); - lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); -} -#endif - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) -{ -#ifdef CONFIG_SMP - cfs_rq->shares = shares; -#endif -} -#endif - -#include "sched_stats.h" -#include "sched_idletask.c" -#include "sched_fair.c" -#include "sched_rt.c" -#ifdef CONFIG_SCHED_DEBUG -# include "sched_debug.c" -#endif - -#define sched_class_highest (&rt_sched_class) -#define for_each_class(class) \ - for (class = sched_class_highest; class; class = class->next) - -static void inc_nr_running(struct rq *rq) -{ - rq->nr_running++; -} - -static void dec_nr_running(struct rq *rq) -{ - rq->nr_running--; -} - -static void set_load_weight(struct task_struct *p) -{ - if (task_has_rt_policy(p)) { - p->se.load.weight = prio_to_weight[0] * 2; - p->se.load.inv_weight = prio_to_wmult[0] >> 1; - return; - } - - /* - * SCHED_IDLE tasks get minimal weight: - */ - if (p->policy == SCHED_IDLE) { - p->se.load.weight = WEIGHT_IDLEPRIO; - p->se.load.inv_weight = WMULT_IDLEPRIO; - return; - } - - p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO]; - p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; -} - -static void update_avg(u64 *avg, u64 sample) -{ - s64 diff = sample - *avg; - *avg += diff >> 3; -} - -static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) -{ - if (wakeup) - p->se.start_runtime = p->se.sum_exec_runtime; - - sched_info_queued(p); - p->sched_class->enqueue_task(rq, p, wakeup); - p->se.on_rq = 1; -} - -static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) -{ - if (sleep) { - if (p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } else { - update_avg(&p->se.avg_wakeup, - sysctl_sched_wakeup_granularity); - } - } - - sched_info_dequeued(p); - p->sched_class->dequeue_task(rq, p, sleep); - p->se.on_rq = 0; -} - -/* - * __normal_prio - return the priority that is based on the static prio - */ -static inline int __normal_prio(struct task_struct *p) -{ - return p->static_prio; -} - -/* - * Calculate the expected normal priority: i.e. priority - * without taking RT-inheritance into account. Might be - * boosted by interactivity modifiers. Changes upon fork, - * setprio syscalls, and whenever the interactivity - * estimator recalculates. - */ -static inline int normal_prio(struct task_struct *p) -{ - int prio; - - if (task_has_rt_policy(p)) - prio = MAX_RT_PRIO-1 - p->rt_priority; - else - prio = __normal_prio(p); - return prio; -} - -/* - * Calculate the current priority, i.e. the priority - * taken into account by the scheduler. This value might - * be boosted by RT tasks, or might be boosted by - * interactivity modifiers. Will be RT if the task got - * RT-boosted. If not then it returns p->normal_prio. - */ -static int effective_prio(struct task_struct *p) -{ - p->normal_prio = normal_prio(p); - /* - * If we are RT tasks or we were boosted to RT priority, - * keep the priority unchanged. Otherwise, update priority - * to the normal priority: - */ - if (!rt_prio(p->prio)) - return p->normal_prio; - return p->prio; -} - -/* - * activate_task - move a task to the runqueue. - */ -static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) -{ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible--; - - enqueue_task(rq, p, wakeup); - inc_nr_running(rq); -} - -/* - * deactivate_task - remove a task from the runqueue. - */ -static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) -{ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible++; - - dequeue_task(rq, p, sleep); - dec_nr_running(rq); -} - -/** - * task_curr - is this task currently executing on a CPU? - * @p: the task in question. - */ -inline int task_curr(const struct task_struct *p) -{ - return cpu_curr(task_cpu(p)) == 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 -} - -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 - -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(const int cpu) -{ - return cpu_rq(cpu)->load.weight; -} - -/* - * Is this task likely cache-hot: - */ -static int -task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) -{ - s64 delta; - - /* - * Buddy candidates are cache hot: - */ - if (sched_feat(CACHE_HOT_BUDDY) && - (&p->se == cfs_rq_of(&p->se)->next || - &p->se == cfs_rq_of(&p->se)->last)) - return 1; - - if (p->sched_class != &fair_sched_class) - return 0; - - if (sysctl_sched_migration_cost == -1) - return 1; - if (sysctl_sched_migration_cost == 0) - return 0; - - delta = now - p->se.exec_start; - - return delta < (s64)sysctl_sched_migration_cost; -} - - -void set_task_cpu(struct task_struct *p, unsigned int new_cpu) -{ - int old_cpu = task_cpu(p); - struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu); - struct cfs_rq *old_cfsrq = task_cfs_rq(p), - *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu); - u64 clock_offset; - - clock_offset = old_rq->clock - new_rq->clock; - - trace_sched_migrate_task(p, task_cpu(p), new_cpu); - -#ifdef CONFIG_SCHEDSTATS - if (p->se.wait_start) - p->se.wait_start -= clock_offset; - if (p->se.sleep_start) - p->se.sleep_start -= clock_offset; - if (p->se.block_start) - p->se.block_start -= clock_offset; - if (old_cpu != new_cpu) { - schedstat_inc(p, se.nr_migrations); - if (task_hot(p, old_rq->clock, NULL)) - schedstat_inc(p, se.nr_forced2_migrations); - } -#endif - p->se.vruntime -= old_cfsrq->min_vruntime - - new_cfsrq->min_vruntime; - - __set_task_cpu(p, new_cpu); -} - -struct migration_req { - struct list_head list; - - struct task_struct *task; - int dest_cpu; - - struct completion done; -}; - -/* - * The task's runqueue lock must be held. - * Returns true if you have to wait for migration thread. - */ -static int -migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) -{ - struct rq *rq = task_rq(p); - - /* - * If the task is not on a runqueue (and not running), then - * it is sufficient to simply update the task's cpu field. - */ - if (!p->se.on_rq && !task_running(rq, p)) { - set_task_cpu(p, dest_cpu); - return 0; - } - - init_completion(&req->done); - req->task = p; - req->dest_cpu = dest_cpu; - list_add(&req->list, &rq->migration_queue); - - return 1; -} - -/* - * wait_task_inactive - wait for a thread to unschedule. - * - * If @match_state is nonzero, it's the @p->state value just checked and - * not expected to change. If it changes, i.e. @p might have woken up, - * then return zero. When we succeed in waiting for @p to be off its CPU, - * we return a positive number (its total switch count). If a second call - * a short while later returns the same number, the caller can be sure that - * @p has remained unscheduled the whole time. - * - * The caller must ensure that the task *will* unschedule sometime soon, - * else this function might spin for a *long* time. This function can't - * be called with interrupts off, or it may introduce deadlock with - * smp_call_function() if an IPI is sent by the same process we are - * waiting to become inactive. - */ -unsigned long wait_task_inactive(struct task_struct *p, long match_state) -{ - unsigned long flags; - int running, on_rq; - unsigned long ncsw; - struct rq *rq; - - for (;;) { - /* - * We do the initial early heuristics without holding - * any task-queue locks at all. We'll only try to get - * the runqueue lock when things look like they will - * work out! - */ - rq = task_rq(p); - - /* - * If the task is actively running on another CPU - * still, just relax and busy-wait without holding - * any locks. - * - * NOTE! Since we don't hold any locks, it's not - * even sure that "rq" stays as the right runqueue! - * But we don't care, since "task_running()" will - * return false if the runqueue has changed and p - * is actually now running somewhere else! - */ - while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) - return 0; - cpu_relax(); - } - - /* - * Ok, time to look more closely! We need the rq - * lock now, to be *sure*. If we're wrong, we'll - * just go back and repeat. - */ - rq = task_rq_lock(p, &flags); - trace_sched_wait_task(rq, p); - running = task_running(rq, p); - on_rq = p->se.on_rq; - ncsw = 0; - if (!match_state || p->state == match_state) - ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, &flags); - - /* - * If it changed from the expected state, bail out now. - */ - if (unlikely(!ncsw)) - break; - - /* - * Was it really running after all now that we - * checked with the proper locks actually held? - * - * Oops. Go back and try again.. - */ - if (unlikely(running)) { - cpu_relax(); - continue; - } - - /* - * It's not enough that it's not actively running, - * it must be off the runqueue _entirely_, and not - * preempted! - * - * So if it was still runnable (but just not actively - * running right now), it's preempted, and we should - * yield - it could be a while. - */ - if (unlikely(on_rq)) { - schedule_timeout_uninterruptible(1); - continue; - } - - /* - * Ahh, all good. It wasn't running, and it wasn't - * runnable, which means that it will never become - * running in the future either. We're all done! - */ - break; - } - - return ncsw; -} - -/*** - * kick_process - kick a running thread to enter/exit the kernel - * @p: the to-be-kicked thread - * - * Cause a process which is running on another CPU to enter - * kernel-mode, without any delay. (to get signals handled.) - * - * NOTE: this function doesnt have to take the runqueue lock, - * because all it wants to ensure is that the remote task enters - * the kernel. If the IPI races and the task has been migrated - * to another CPU then no harm is done and the purpose has been - * achieved as well. - */ -void kick_process(struct task_struct *p) -{ - int cpu; - - preempt_disable(); - cpu = task_cpu(p); - if ((cpu != smp_processor_id()) && task_curr(p)) - smp_send_reschedule(cpu); - preempt_enable(); -} - -/* - * Return a low guess at the load of a migration-source cpu weighted - * according to the scheduling class and "nice" value. - * - * We want to under-estimate the load of migration sources, to - * balance conservatively. - */ -static unsigned long source_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return min(rq->cpu_load[type-1], total); -} - -/* - * Return a high guess at the load of a migration-target cpu weighted - * according to the scheduling class and "nice" value. - */ -static unsigned long target_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return max(rq->cpu_load[type-1], total); -} - -/* - * find_idlest_group finds and returns the least busy CPU group within the - * domain. - */ -static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) -{ - struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; - unsigned long min_load = ULONG_MAX, this_load = 0; - int load_idx = sd->forkexec_idx; - int imbalance = 100 + (sd->imbalance_pct-100)/2; - - do { - unsigned long load, avg_load; - int local_group; - int i; - - /* Skip over this group if it has no CPUs allowed */ - if (!cpumask_intersects(sched_group_cpus(group), - &p->cpus_allowed)) - continue; - - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - - /* Tally up the load of all CPUs in the group */ - avg_load = 0; - - for_each_cpu(i, sched_group_cpus(group)) { - /* Bias balancing toward cpus of our domain */ - if (local_group) - load = source_load(i, load_idx); - else - load = target_load(i, load_idx); - - avg_load += load; - } - - /* Adjust by relative CPU power of the group */ - avg_load = sg_div_cpu_power(group, - avg_load * SCHED_LOAD_SCALE); - - if (local_group) { - this_load = avg_load; - this = group; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; - } - } while (group = group->next, group != sd->groups); - - if (!idlest || 100*this_load < imbalance*min_load) - return NULL; - return idlest; -} - -/* - * find_idlest_cpu - find the idlest cpu among the cpus in group. - */ -static int -find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) -{ - unsigned long load, min_load = ULONG_MAX; - int idlest = -1; - int i; - - /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { - load = weighted_cpuload(i); - - if (load < min_load || (load == min_load && i == this_cpu)) { - min_load = load; - idlest = i; - } - } - - return idlest; -} - -/* - * sched_balance_self: balance the current task (running on cpu) in domains - * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and - * SD_BALANCE_EXEC. - * - * Balance, ie. select the least loaded group. - * - * Returns the target CPU number, or the same CPU if no balancing is needed. - * - * preempt must be disabled. - */ -static int sched_balance_self(int cpu, int flag) -{ - struct task_struct *t = current; - struct sched_domain *tmp, *sd = NULL; - - for_each_domain(cpu, tmp) { - /* - * If power savings logic is enabled for a domain, stop there. - */ - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - break; - if (tmp->flags & flag) - sd = tmp; - } - - if (sd) - update_shares(sd); - - while (sd) { - struct sched_group *group; - int new_cpu, weight; - - if (!(sd->flags & flag)) { - sd = sd->child; - continue; - } - - group = find_idlest_group(sd, t, cpu); - if (!group) { - sd = sd->child; - continue; - } - - new_cpu = find_idlest_cpu(group, t, cpu); - if (new_cpu == -1 || new_cpu == cpu) { - /* Now try balancing at a lower domain level of cpu */ - sd = sd->child; - continue; - } - - /* Now try balancing at a lower domain level of new_cpu */ - cpu = new_cpu; - weight = cpumask_weight(sched_domain_span(sd)); - sd = NULL; - for_each_domain(cpu, tmp) { - if (weight <= cpumask_weight(sched_domain_span(tmp))) - break; - if (tmp->flags & flag) - sd = tmp; - } - /* while loop will break here if sd == NULL */ - } - - return cpu; -} - -#endif /* CONFIG_SMP */ - -/*** - * 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) -{ - int cpu, orig_cpu, this_cpu, success = 0; - unsigned long flags; - long old_state; - struct rq *rq; - - if (!sched_feat(SYNC_WAKEUPS)) - sync = 0; - -#ifdef CONFIG_SMP - if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) { - struct sched_domain *sd; - - this_cpu = raw_smp_processor_id(); - cpu = task_cpu(p); - - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - update_shares(sd); - break; - } - } - } -#endif - - smp_wmb(); - rq = task_rq_lock(p, &flags); - update_rq_clock(rq); - old_state = p->state; - if (!(old_state & state)) - goto out; - - if (p->se.on_rq) - goto out_running; - - cpu = task_cpu(p); - orig_cpu = cpu; - this_cpu = smp_processor_id(); - -#ifdef CONFIG_SMP - if (unlikely(task_running(rq, p))) - goto out_activate; - - 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); - old_state = p->state; - if (!(old_state & state)) - goto out; - if (p->se.on_rq) - goto out_running; - - this_cpu = smp_processor_id(); - 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 (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd, ttwu_wake_remote); - break; - } - } - } -#endif /* CONFIG_SCHEDSTATS */ - -out_activate: -#endif /* CONFIG_SMP */ - schedstat_inc(p, se.nr_wakeups); - if (sync) - schedstat_inc(p, se.nr_wakeups_sync); - if (orig_cpu != cpu) - schedstat_inc(p, se.nr_wakeups_migrate); - if (cpu == this_cpu) - schedstat_inc(p, se.nr_wakeups_local); - else - schedstat_inc(p, se.nr_wakeups_remote); - activate_task(rq, p, 1); - success = 1; - - /* - * Only attribute actual wakeups done by this task. - */ - if (!in_interrupt()) { - struct sched_entity *se = ¤t->se; - u64 sample = se->sum_exec_runtime; - - if (se->last_wakeup) - sample -= se->last_wakeup; - else - sample -= se->start_runtime; - update_avg(&se->avg_wakeup, sample); - - se->last_wakeup = se->sum_exec_runtime; - } - -out_running: - trace_sched_wakeup(rq, p, success); - check_preempt_curr(rq, p, sync); - - p->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); - - return success; -} - -int wake_up_process(struct task_struct *p) -{ - return try_to_wake_up(p, TASK_ALL, 0); -} -EXPORT_SYMBOL(wake_up_process); - -int wake_up_state(struct task_struct *p, unsigned int state) -{ - return try_to_wake_up(p, state, 0); -} - -/* - * Perform scheduler related setup for a newly forked process p. - * p is forked by current. - * - * __sched_fork() is basic setup used by init_idle() too: - */ -static void __sched_fork(struct task_struct *p) -{ - p->se.exec_start = 0; - p->se.sum_exec_runtime = 0; - p->se.prev_sum_exec_runtime = 0; - p->se.last_wakeup = 0; - p->se.avg_overlap = 0; - p->se.start_runtime = 0; - p->se.avg_wakeup = sysctl_sched_wakeup_granularity; - -#ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sum_sleep_runtime = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; - p->se.sleep_max = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - p->se.wait_max = 0; -#endif - - INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); - -#ifdef CONFIG_PREEMPT_NOTIFIERS - INIT_HLIST_HEAD(&p->preempt_notifiers); -#endif - - /* - * We mark the process as running here, but have not actually - * inserted it onto the runqueue yet. This guarantees that - * nobody will actually run it, and a signal or other external - * event cannot wake it up and insert it on the runqueue either. - */ - p->state = TASK_RUNNING; -} - -/* - * fork()/clone()-time setup: - */ -void sched_fork(struct task_struct *p, int clone_flags) -{ - int cpu = get_cpu(); - - __sched_fork(p); - -#ifdef CONFIG_SMP - cpu = sched_balance_self(cpu, SD_BALANCE_FORK); -#endif - set_task_cpu(p, cpu); - - /* - * Make sure we do not leak PI boosting priority to the child: - */ - p->prio = current->normal_prio; - if (!rt_prio(p->prio)) - p->sched_class = &fair_sched_class; - -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) - if (likely(sched_info_on())) - memset(&p->sched_info, 0, sizeof(p->sched_info)); -#endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; -#endif -#ifdef CONFIG_PREEMPT - /* Want to start with kernel preemption disabled. */ - task_thread_info(p)->preempt_count = 1; -#endif - plist_node_init(&p->pushable_tasks, MAX_PRIO); - - put_cpu(); -} - -/* - * wake_up_new_task - wake up a newly created task for the first time. - * - * This function will do some initial scheduler statistics housekeeping - * that must be done for every newly created context, then puts the task - * on the runqueue and wakes it. - */ -void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) -{ - unsigned long flags; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - BUG_ON(p->state != TASK_RUNNING); - update_rq_clock(rq); - - p->prio = effective_prio(p); - - if (!p->sched_class->task_new || !current->se.on_rq) { - activate_task(rq, p, 0); - } else { - /* - * Let the scheduling class do new task startup - * management (if any): - */ - p->sched_class->task_new(rq, p); - inc_nr_running(rq); - } - trace_sched_wakeup_new(rq, p, 1); - check_preempt_curr(rq, p, 0); -#ifdef CONFIG_SMP - if (p->sched_class->task_wake_up) - p->sched_class->task_wake_up(rq, p); -#endif - task_rq_unlock(rq, &flags); -} - -#ifdef CONFIG_PREEMPT_NOTIFIERS - -/** - * preempt_notifier_register - tell me when current is being preempted & rescheduled - * @notifier: notifier struct to register - */ -void preempt_notifier_register(struct preempt_notifier *notifier) -{ - hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); -} -EXPORT_SYMBOL_GPL(preempt_notifier_register); - -/** - * preempt_notifier_unregister - no longer interested in preemption notifications - * @notifier: notifier struct to unregister - * - * This is safe to call from within a preemption notifier. - */ -void preempt_notifier_unregister(struct preempt_notifier *notifier) -{ - hlist_del(¬ifier->link); -} -EXPORT_SYMBOL_GPL(preempt_notifier_unregister); - -static void fire_sched_in_preempt_notifiers(struct task_struct *curr) -{ - struct preempt_notifier *notifier; - struct hlist_node *node; - - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) - notifier->ops->sched_in(notifier, raw_smp_processor_id()); -} - -static void -fire_sched_out_preempt_notifiers(struct task_struct *curr, - struct task_struct *next) -{ - struct preempt_notifier *notifier; - struct hlist_node *node; - - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) - notifier->ops->sched_out(notifier, next); -} - -#else /* !CONFIG_PREEMPT_NOTIFIERS */ - -static void fire_sched_in_preempt_notifiers(struct task_struct *curr) -{ -} - -static void -fire_sched_out_preempt_notifiers(struct task_struct *curr, - struct task_struct *next) -{ -} - -#endif /* CONFIG_PREEMPT_NOTIFIERS */ - -/** - * prepare_task_switch - prepare to switch tasks - * @rq: the runqueue preparing to switch - * @prev: the current task that is being switched out - * @next: the task we are going to switch to. - * - * This is called with the rq lock held and interrupts off. It must - * be paired with a subsequent finish_task_switch after the context - * switch. - * - * prepare_task_switch sets up locking and calls architecture specific - * hooks. - */ -static inline void -prepare_task_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next) -{ - fire_sched_out_preempt_notifiers(prev, next); - prepare_lock_switch(rq, next); - prepare_arch_switch(next); -} - -/** - * finish_task_switch - clean up after a task-switch - * @rq: runqueue associated with task-switch - * @prev: the thread we just switched away from. - * - * finish_task_switch must be called after the context switch, paired - * with a prepare_task_switch call before the context switch. - * finish_task_switch will reconcile locking set up by prepare_task_switch, - * and do any other architecture-specific cleanup actions. - * - * Note that we may have delayed dropping an mm in context_switch(). If - * so, we finish that here outside of the runqueue lock. (Doing it - * with the lock held can cause deadlocks; see schedule() for - * details.) - */ -static void finish_task_switch(struct rq *rq, struct task_struct *prev) - __releases(rq->lock) -{ - struct mm_struct *mm = rq->prev_mm; - long prev_state; -#ifdef CONFIG_SMP - int post_schedule = 0; - - if (current->sched_class->needs_post_schedule) - post_schedule = current->sched_class->needs_post_schedule(rq); -#endif - - rq->prev_mm = NULL; - - /* - * A task struct has one reference for the use as "current". - * If a task dies, then it sets TASK_DEAD in tsk->state and calls - * schedule one last time. The schedule call will never return, and - * the scheduled task must drop that reference. - * The test for TASK_DEAD must occur while the runqueue locks are - * still held, otherwise prev could be scheduled on another cpu, die - * there before we look at prev->state, and then the reference would - * be dropped twice. - * Manfred Spraul - */ - prev_state = prev->state; - finish_arch_switch(prev); - finish_lock_switch(rq, prev); -#ifdef CONFIG_SMP - if (post_schedule) - current->sched_class->post_schedule(rq); -#endif - - fire_sched_in_preempt_notifiers(current); - if (mm) - mmdrop(mm); - if (unlikely(prev_state == TASK_DEAD)) { - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - put_task_struct(prev); - } -} - -/** - * schedule_tail - first thing a freshly forked thread must call. - * @prev: the thread we just switched away from. - */ -asmlinkage void schedule_tail(struct task_struct *prev) - __releases(rq->lock) -{ - struct rq *rq = this_rq(); - - finish_task_switch(rq, prev); -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - /* In this case, finish_task_switch does not reenable preemption */ - preempt_enable(); -#endif - if (current->set_child_tid) - put_user(task_pid_vnr(current), current->set_child_tid); -} - -/* - * context_switch - switch to the new MM and the new - * thread's register state. - */ -static inline void -context_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next) -{ - struct mm_struct *mm, *oldmm; - - prepare_task_switch(rq, prev, next); - trace_sched_switch(rq, prev, next); - mm = next->mm; - oldmm = prev->active_mm; - /* - * For paravirt, this is coupled with an exit in switch_to to - * combine the page table reload and the switch backend into - * one hypercall. - */ - arch_enter_lazy_cpu_mode(); - - if (unlikely(!mm)) { - next->active_mm = oldmm; - atomic_inc(&oldmm->mm_count); - enter_lazy_tlb(oldmm, next); - } else - switch_mm(oldmm, mm, next); - - if (unlikely(!prev->mm)) { - prev->active_mm = NULL; - rq->prev_mm = oldmm; - } - /* - * Since the runqueue lock will be released by the next - * task (which is an invalid locking op but in the case - * of the scheduler it's an obvious special-case), so we - * do an early lockdep release here: - */ -#ifndef __ARCH_WANT_UNLOCKED_CTXSW - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); -#endif - - /* Here we just switch the register state and the stack. */ - switch_to(prev, next, prev); - - barrier(); - /* - * this_rq must be evaluated again because prev may have moved - * CPUs since it called schedule(), thus the 'rq' on its stack - * frame will be invalid. - */ - finish_task_switch(this_rq(), prev); -} - -/* - * nr_running, nr_uninterruptible and nr_context_switches: - * - * externally visible scheduler statistics: current number of runnable - * threads, current number of uninterruptible-sleeping threads, total - * number of context switches performed since bootup. - */ -unsigned long nr_running(void) -{ - unsigned long i, sum = 0; - - for_each_online_cpu(i) - sum += cpu_rq(i)->nr_running; - - return sum; -} - -unsigned long nr_uninterruptible(void) -{ - unsigned long i, sum = 0; - - for_each_possible_cpu(i) - sum += cpu_rq(i)->nr_uninterruptible; - - /* - * Since we read the counters lockless, it might be slightly - * inaccurate. Do not allow it to go below zero though: - */ - if (unlikely((long)sum < 0)) - sum = 0; - - return sum; -} - -unsigned long long nr_context_switches(void) -{ - int i; - unsigned long long sum = 0; - - for_each_possible_cpu(i) - sum += cpu_rq(i)->nr_switches; - - return sum; -} - -unsigned long nr_iowait(void) -{ - unsigned long i, sum = 0; - - for_each_possible_cpu(i) - sum += atomic_read(&cpu_rq(i)->nr_iowait); - - return sum; -} - -unsigned long nr_active(void) -{ - unsigned long i, running = 0, uninterruptible = 0; - - for_each_online_cpu(i) { - running += cpu_rq(i)->nr_running; - uninterruptible += cpu_rq(i)->nr_uninterruptible; - } - - if (unlikely((long)uninterruptible < 0)) - uninterruptible = 0; - - return running + uninterruptible; -} - -/* - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). - */ -static void update_cpu_load(struct rq *this_rq) -{ - unsigned long this_load = this_rq->load.weight; - int i, scale; - - this_rq->nr_load_updates++; - - /* Update our load: */ - for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale-1; - this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; - } -} - -#ifdef CONFIG_SMP - -/* - * double_rq_lock - safely lock two runqueues - * - * Note this does not disable interrupts like task_rq_lock, - * you need to do so manually before calling. - */ -static void double_rq_lock(struct rq *rq1, struct rq *rq2) - __acquires(rq1->lock) - __acquires(rq2->lock) -{ - BUG_ON(!irqs_disabled()); - if (rq1 == rq2) { - spin_lock(&rq1->lock); - __acquire(rq2->lock); /* Fake it out ;) */ - } else { - if (rq1 < rq2) { - spin_lock(&rq1->lock); - spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&rq2->lock); - spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); - } - } - update_rq_clock(rq1); - update_rq_clock(rq2); -} - -/* - * double_rq_unlock - safely unlock two runqueues - * - * Note this does not restore interrupts like task_rq_unlock, - * you need to do so manually after calling. - */ -static void double_rq_unlock(struct rq *rq1, struct rq *rq2) - __releases(rq1->lock) - __releases(rq2->lock) -{ - spin_unlock(&rq1->lock); - if (rq1 != rq2) - spin_unlock(&rq2->lock); - else - __release(rq2->lock); -} - -/* - * 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 - * the cpu_allowed mask is restored. - */ -static void sched_migrate_task(struct task_struct *p, int dest_cpu) -{ - struct migration_req req; - unsigned long flags; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) - || unlikely(!cpu_active(dest_cpu))) - goto out; - - /* force the process onto the specified CPU */ - if (migrate_task(p, dest_cpu, &req)) { - /* Need to wait for migration thread (might exit: take ref). */ - struct task_struct *mt = rq->migration_thread; - - get_task_struct(mt); - task_rq_unlock(rq, &flags); - wake_up_process(mt); - put_task_struct(mt); - wait_for_completion(&req.done); - - return; - } -out: - task_rq_unlock(rq, &flags); -} - -/* - * sched_exec - execve() is a valuable balancing opportunity, because at - * this point the task has the smallest effective memory and cache footprint. - */ -void sched_exec(void) -{ - int new_cpu, this_cpu = get_cpu(); - new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC); - put_cpu(); - if (new_cpu != this_cpu) - sched_migrate_task(current, new_cpu); -} - -/* - * pull_task - move a task from a remote runqueue to the local runqueue. - * Both runqueues must be locked. - */ -static void pull_task(struct rq *src_rq, struct task_struct *p, - struct rq *this_rq, int this_cpu) -{ - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); - /* - * Note that idle threads have a prio of MAX_PRIO, for this test - * to be always true for them. - */ - check_preempt_curr(this_rq, p, 0); -} - -/* - * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? - */ -static -int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned) -{ - int tsk_cache_hot = 0; - /* - * We do not migrate tasks that are: - * 1) running (obviously), or - * 2) cannot be migrated to this CPU due to cpus_allowed, or - * 3) are cache-hot on their current CPU. - */ - if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { - schedstat_inc(p, se.nr_failed_migrations_affine); - return 0; - } - *all_pinned = 0; - - if (task_running(rq, p)) { - schedstat_inc(p, se.nr_failed_migrations_running); - return 0; - } - - /* - * Aggressive migration if: - * 1) task is cache cold, or - * 2) too many balance attempts have failed. - */ - - tsk_cache_hot = task_hot(p, rq->clock, sd); - if (!tsk_cache_hot || - sd->nr_balance_failed > sd->cache_nice_tries) { -#ifdef CONFIG_SCHEDSTATS - if (tsk_cache_hot) { - schedstat_inc(sd, lb_hot_gained[idle]); - schedstat_inc(p, se.nr_forced_migrations); - } -#endif - return 1; - } - - if (tsk_cache_hot) { - schedstat_inc(p, se.nr_failed_migrations_hot); - return 0; - } - return 1; -} - -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 loops = 0, pulled = 0, pinned = 0; - struct task_struct *p; - long rem_load_move = max_load_move; - - if (max_load_move == 0) - goto out; - - pinned = 1; - - /* - * Start the load-balancing iterator: - */ - p = iterator->start(iterator->arg); -next: - if (!p || loops++ > sysctl_sched_nr_migrate) - goto out; - - if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { - p = iterator->next(iterator->arg); - goto next; - } - - pull_task(busiest, p, this_rq, this_cpu); - pulled++; - rem_load_move -= p->se.load.weight; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible kernels - * will stop after the first task is pulled to minimize the critical - * section. - */ - if (idle == CPU_NEWLY_IDLE) - goto out; -#endif - - /* - * We only want to steal up to the prescribed amount of weighted load. - */ - if (rem_load_move > 0) { - if (p->prio < *this_best_prio) - *this_best_prio = p->prio; - p = iterator->next(iterator->arg); - goto next; - } -out: - /* - * 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(). - */ - schedstat_add(sd, lb_gained[idle], pulled); - - if (all_pinned) - *all_pinned = pinned; - - return max_load_move - rem_load_move; -} - -/* - * move_tasks tries to move up to max_load_move weighted load from busiest to - * this_rq, as part of a balancing operation within domain "sd". - * Returns 1 if successful and 0 otherwise. - * - * Called with both runqueues locked. - */ -static int move_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) -{ - const struct sched_class *class = sched_class_highest; - unsigned long total_load_moved = 0; - int this_best_prio = this_rq->curr->prio; - - do { - total_load_moved += - class->load_balance(this_rq, this_cpu, busiest, - max_load_move - total_load_moved, - sd, idle, all_pinned, &this_best_prio); - class = class->next; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize - * the critical section. - */ - if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) - break; -#endif - } while (class && max_load_move > total_load_moved); - - return total_load_moved > 0; -} - -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". - * Returns 1 if successful and 0 otherwise. - * - * Called with both runqueues locked. - */ -static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) -{ - const struct sched_class *class; - - for (class = sched_class_highest; class; class = class->next) - if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) - return 1; - - return 0; -} -/********** Helpers for find_busiest_group ************************/ -/* - * sd_lb_stats - Structure to store the statistics of a sched_domain - * during load balancing. - */ -struct sd_lb_stats { - struct sched_group *busiest; /* Busiest group in this sd */ - struct sched_group *this; /* Local group in this sd */ - unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ - unsigned long avg_load; /* Average load across all groups in sd */ - - /** Statistics of this group */ - unsigned long this_load; - unsigned long this_load_per_task; - unsigned long this_nr_running; - - /* Statistics of the busiest group */ - unsigned long max_load; - unsigned long busiest_load_per_task; - unsigned long busiest_nr_running; - - int group_imb; /* Is there imbalance in this sd */ -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance; /* Is powersave balance needed for this sd */ - struct sched_group *group_min; /* Least loaded group in sd */ - struct sched_group *group_leader; /* Group which relieves group_min */ - unsigned long min_load_per_task; /* load_per_task in group_min */ - unsigned long leader_nr_running; /* Nr running of group_leader */ - unsigned long min_nr_running; /* Nr running of group_min */ -#endif -}; - -/* - * sg_lb_stats - stats of a sched_group required for load_balancing - */ -struct sg_lb_stats { - unsigned long avg_load; /*Avg load across the CPUs of the group */ - unsigned long group_load; /* Total load over the CPUs of the group */ - unsigned long sum_nr_running; /* Nr tasks running in the group */ - unsigned long sum_weighted_load; /* Weighted load of group's tasks */ - unsigned long group_capacity; - int group_imb; /* Is there an imbalance in the group ? */ -}; - -/** - * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. - * @group: The group whose first cpu is to be returned. - */ -static inline unsigned int group_first_cpu(struct sched_group *group) -{ - return cpumask_first(sched_group_cpus(group)); -} - -/** - * get_sd_load_idx - Obtain the load index for a given sched domain. - * @sd: The sched_domain whose load_idx is to be obtained. - * @idle: The Idle status of the CPU for whose sd load_icx is obtained. - */ -static inline int get_sd_load_idx(struct sched_domain *sd, - enum cpu_idle_type idle) -{ - int load_idx; - - switch (idle) { - case CPU_NOT_IDLE: - load_idx = sd->busy_idx; - break; - - case CPU_NEWLY_IDLE: - load_idx = sd->newidle_idx; - break; - default: - load_idx = sd->idle_idx; - break; - } - - return load_idx; -} - - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * init_sd_power_savings_stats - Initialize power savings statistics for - * the given sched_domain, during load balancing. - * - * @sd: Sched domain whose power-savings statistics are to be initialized. - * @sds: Variable containing the statistics for sd. - * @idle: Idle status of the CPU at which we're performing load-balancing. - */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - sds->power_savings_balance = 0; - else { - sds->power_savings_balance = 1; - sds->min_nr_running = ULONG_MAX; - sds->leader_nr_running = 0; - } -} - -/** - * update_sd_power_savings_stats - Update the power saving stats for a - * sched_domain while performing load balancing. - * - * @group: sched_group belonging to the sched_domain under consideration. - * @sds: Variable containing the statistics of the sched_domain - * @local_group: Does group contain the CPU for which we're performing - * load balancing ? - * @sgs: Variable containing the statistics of the group. - */ -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - - if (!sds->power_savings_balance) - return; - - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (sds->this_nr_running >= sgs->group_capacity || - !sds->this_nr_running)) - sds->power_savings_balance = 0; - - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!sds->power_savings_balance || - sgs->sum_nr_running >= sgs->group_capacity || - !sgs->sum_nr_running) - return; - - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sgs->sum_nr_running < sds->min_nr_running) || - (sgs->sum_nr_running == sds->min_nr_running && - group_first_cpu(group) > group_first_cpu(sds->group_min))) { - sds->group_min = group; - sds->min_nr_running = sgs->sum_nr_running; - sds->min_load_per_task = sgs->sum_weighted_load / - sgs->sum_nr_running; - } - - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sgs->sum_nr_running > sgs->group_capacity - 1) - return; - - if (sgs->sum_nr_running > sds->leader_nr_running || - (sgs->sum_nr_running == sds->leader_nr_running && - group_first_cpu(group) < group_first_cpu(sds->group_leader))) { - sds->group_leader = group; - sds->leader_nr_running = sgs->sum_nr_running; - } -} - -/** - * check_power_save_busiest_group - see if there is potential for some power-savings balance - * @sds: Variable containing the statistics of the sched_domain - * under consideration. - * @this_cpu: Cpu at which we're currently performing load-balancing. - * @imbalance: Variable to store the imbalance. - * - * Description: - * Check if we have potential to perform some power-savings balance. - * If yes, set the busiest group to be the least loaded group in the - * sched_domain, so that it's CPUs can be put to idle. - * - * Returns 1 if there is potential to perform power-savings balance. - * Else returns 0. - */ -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - if (!sds->power_savings_balance) - return 0; - - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - *imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = - group_first_cpu(sds->group_leader); - } - - return 1; - -} -#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - return; -} - -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - return; -} - -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - return 0; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - - -/** - * update_sg_lb_stats - Update sched_group's statistics for load balancing. - * @group: sched_group whose statistics are to be updated. - * @this_cpu: Cpu for which load balance is currently performed. - * @idle: Idle status of this_cpu - * @load_idx: Load index of sched_domain of this_cpu for load calc. - * @sd_idle: Idle status of the sched_domain containing group. - * @local_group: Does group contain this_cpu. - * @cpus: Set of cpus considered for load balancing. - * @balance: Should we balance. - * @sgs: variable to hold the statistics for this group. - */ -static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu, - enum cpu_idle_type idle, int load_idx, int *sd_idle, - int local_group, const struct cpumask *cpus, - int *balance, struct sg_lb_stats *sgs) -{ - unsigned long load, max_cpu_load, min_cpu_load; - int i; - unsigned int balance_cpu = -1, first_idle_cpu = 0; - unsigned long sum_avg_load_per_task; - unsigned long avg_load_per_task; - - if (local_group) - balance_cpu = group_first_cpu(group); - - /* Tally up the load of all CPUs in the group */ - sum_avg_load_per_task = avg_load_per_task = 0; - max_cpu_load = 0; - min_cpu_load = ~0UL; - - for_each_cpu_and(i, sched_group_cpus(group), cpus) { - struct rq *rq = cpu_rq(i); - - if (*sd_idle && rq->nr_running) - *sd_idle = 0; - - /* Bias balancing toward cpus of our domain */ - if (local_group) { - if (idle_cpu(i) && !first_idle_cpu) { - first_idle_cpu = 1; - balance_cpu = i; - } - - load = target_load(i, load_idx); - } else { - load = source_load(i, load_idx); - if (load > max_cpu_load) - max_cpu_load = load; - if (min_cpu_load > load) - min_cpu_load = load; - } - - sgs->group_load += load; - sgs->sum_nr_running += rq->nr_running; - sgs->sum_weighted_load += weighted_cpuload(i); - - sum_avg_load_per_task += cpu_avg_load_per_task(i); - } - - /* - * First idle cpu or the first cpu(busiest) in this sched group - * is eligible for doing load balancing at this and above - * domains. In the newly idle case, we will allow all the cpu's - * to do the newly idle load balance. - */ - if (idle != CPU_NEWLY_IDLE && local_group && - balance_cpu != this_cpu && balance) { - *balance = 0; - return; - } - - /* Adjust by relative CPU power of the group */ - sgs->avg_load = sg_div_cpu_power(group, - sgs->group_load * SCHED_LOAD_SCALE); - - - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of two tasks. - * - * APZ: with cgroup the avg task weight can vary wildly and - * might not be a suitable number - should we keep a - * normalized nr_running number somewhere that negates - * the hierarchy? - */ - avg_load_per_task = sg_div_cpu_power(group, - sum_avg_load_per_task * SCHED_LOAD_SCALE); - - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) - sgs->group_imb = 1; - - sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; - -} - -/** - * update_sd_lb_stats - Update sched_group's statistics for load balancing. - * @sd: sched_domain whose statistics are to be updated. - * @this_cpu: Cpu for which load balance is currently performed. - * @idle: Idle status of this_cpu - * @sd_idle: Idle status of the sched_domain containing group. - * @cpus: Set of cpus considered for load balancing. - * @balance: Should we balance. - * @sds: variable to hold the statistics for this sched_domain. - */ -static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, - enum cpu_idle_type idle, int *sd_idle, - const struct cpumask *cpus, int *balance, - struct sd_lb_stats *sds) -{ - struct sched_group *group = sd->groups; - struct sg_lb_stats sgs; - int load_idx; - - init_sd_power_savings_stats(sd, sds, idle); - load_idx = get_sd_load_idx(sd, idle); - - do { - int local_group; - - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle, - local_group, cpus, balance, &sgs); - - if (local_group && balance && !(*balance)) - return; - - sds->total_load += sgs.group_load; - sds->total_pwr += group->__cpu_power; - - if (local_group) { - sds->this_load = sgs.avg_load; - sds->this = group; - sds->this_nr_running = sgs.sum_nr_running; - sds->this_load_per_task = sgs.sum_weighted_load; - } else if (sgs.avg_load > sds->max_load && - (sgs.sum_nr_running > sgs.group_capacity || - sgs.group_imb)) { - sds->max_load = sgs.avg_load; - sds->busiest = group; - sds->busiest_nr_running = sgs.sum_nr_running; - sds->busiest_load_per_task = sgs.sum_weighted_load; - sds->group_imb = sgs.group_imb; - } - - update_sd_power_savings_stats(group, sds, local_group, &sgs); - group = group->next; - } while (group != sd->groups); - -} - -/** - * fix_small_imbalance - Calculate the minor imbalance that exists - * amongst the groups of a sched_domain, during - * load balancing. - * @sds: Statistics of the sched_domain whose imbalance is to be calculated. - * @this_cpu: The cpu at whose sched_domain we're performing load-balance. - * @imbalance: Variable to store the imbalance. - */ -static inline void fix_small_imbalance(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - unsigned long tmp, pwr_now = 0, pwr_move = 0; - unsigned int imbn = 2; - - if (sds->this_nr_running) { - sds->this_load_per_task /= sds->this_nr_running; - if (sds->busiest_load_per_task > - sds->this_load_per_task) - imbn = 1; - } else - sds->this_load_per_task = - cpu_avg_load_per_task(this_cpu); - - if (sds->max_load - sds->this_load + sds->busiest_load_per_task >= - sds->busiest_load_per_task * imbn) { - *imbalance = sds->busiest_load_per_task; - return; - } - - /* - * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by - * moving them. - */ - - pwr_now += sds->busiest->__cpu_power * - min(sds->busiest_load_per_task, sds->max_load); - pwr_now += sds->this->__cpu_power * - min(sds->this_load_per_task, sds->this_load); - pwr_now /= SCHED_LOAD_SCALE; - - /* Amount of load we'd subtract */ - tmp = sg_div_cpu_power(sds->busiest, - sds->busiest_load_per_task * SCHED_LOAD_SCALE); - if (sds->max_load > tmp) - pwr_move += sds->busiest->__cpu_power * - min(sds->busiest_load_per_task, sds->max_load - tmp); - - /* Amount of load we'd add */ - if (sds->max_load * sds->busiest->__cpu_power < - sds->busiest_load_per_task * SCHED_LOAD_SCALE) - tmp = sg_div_cpu_power(sds->this, - sds->max_load * sds->busiest->__cpu_power); - else - tmp = sg_div_cpu_power(sds->this, - sds->busiest_load_per_task * SCHED_LOAD_SCALE); - pwr_move += sds->this->__cpu_power * - min(sds->this_load_per_task, sds->this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; - - /* Move if we gain throughput */ - if (pwr_move > pwr_now) - *imbalance = sds->busiest_load_per_task; -} - -/** - * calculate_imbalance - Calculate the amount of imbalance present within the - * groups of a given sched_domain during load balance. - * @sds: statistics of the sched_domain whose imbalance is to be calculated. - * @this_cpu: Cpu for which currently load balance is being performed. - * @imbalance: The variable to store the imbalance. - */ -static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, - unsigned long *imbalance) -{ - unsigned long max_pull; - /* - * In the presence of smp nice balancing, certain scenarios can have - * max load less than avg load(as we skip the groups at or below - * its cpu_power, while calculating max_load..) - */ - if (sds->max_load < sds->avg_load) { - *imbalance = 0; - return fix_small_imbalance(sds, this_cpu, imbalance); - } - - /* Don't want to pull so many tasks that a group would go idle */ - max_pull = min(sds->max_load - sds->avg_load, - sds->max_load - sds->busiest_load_per_task); - - /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * sds->busiest->__cpu_power, - (sds->avg_load - sds->this_load) * sds->this->__cpu_power) - / SCHED_LOAD_SCALE; - - /* - * if *imbalance is less than the average load per runnable task - * there is no gaurantee that any tasks will be moved so we'll have - * a think about bumping its value to force at least one task to be - * moved - */ - if (*imbalance < sds->busiest_load_per_task) - return fix_small_imbalance(sds, this_cpu, imbalance); - -} -/******* find_busiest_group() helpers end here *********************/ - -/** - * find_busiest_group - Returns the busiest group within the sched_domain - * if there is an imbalance. If there isn't an imbalance, and - * the user has opted for power-savings, it returns a group whose - * CPUs can be put to idle by rebalancing those tasks elsewhere, if - * such a group exists. - * - * Also calculates the amount of weighted load which should be moved - * to restore balance. - * - * @sd: The sched_domain whose busiest group is to be returned. - * @this_cpu: The cpu for which load balancing is currently being performed. - * @imbalance: Variable which stores amount of weighted load which should - * be moved to restore balance/put a group to idle. - * @idle: The idle status of this_cpu. - * @sd_idle: The idleness of sd - * @cpus: The set of CPUs under consideration for load-balancing. - * @balance: Pointer to a variable indicating if this_cpu - * is the appropriate cpu to perform load balancing at this_level. - * - * Returns: - the busiest group if imbalance exists. - * - If no imbalance and user has opted for power-savings balance, - * return the least loaded group whose CPUs can be - * put to idle by rebalancing its tasks onto our group. - */ -static struct sched_group * -find_busiest_group(struct sched_domain *sd, int this_cpu, - unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const struct cpumask *cpus, int *balance) -{ - struct sd_lb_stats sds; - - memset(&sds, 0, sizeof(sds)); - - /* - * Compute the various statistics relavent for load balancing at - * this level. - */ - update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, - balance, &sds); - - /* Cases where imbalance does not exist from POV of this_cpu */ - /* 1) this_cpu is not the appropriate cpu to perform load balancing - * at this level. - * 2) There is no busy sibling group to pull from. - * 3) This group is the busiest group. - * 4) This group is more busy than the avg busieness at this - * sched_domain. - * 5) The imbalance is within the specified limit. - * 6) Any rebalance would lead to ping-pong - */ - if (balance && !(*balance)) - goto ret; - - if (!sds.busiest || sds.busiest_nr_running == 0) - goto out_balanced; - - if (sds.this_load >= sds.max_load) - goto out_balanced; - - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; - - if (sds.this_load >= sds.avg_load) - goto out_balanced; - - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) - goto out_balanced; - - sds.busiest_load_per_task /= sds.busiest_nr_running; - if (sds.group_imb) - sds.busiest_load_per_task = - min(sds.busiest_load_per_task, sds.avg_load); - - /* - * We're trying to get all the cpus to the average_load, so we don't - * want to push ourselves above the average load, nor do we wish to - * reduce the max loaded cpu below the average load, as either of these - * actions would just result in more rebalancing later, and ping-pong - * 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 - * appear as very large values with unsigned longs. - */ - if (sds.max_load <= sds.busiest_load_per_task) - goto out_balanced; - - /* Looks like there is an imbalance. Compute it */ - calculate_imbalance(&sds, this_cpu, imbalance); - return sds.busiest; - -out_balanced: - /* - * There is no obvious imbalance. But check if we can do some balancing - * to save power. - */ - if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) - return sds.busiest; -ret: - *imbalance = 0; - return NULL; -} - -/* - * find_busiest_queue - find the busiest runqueue among the cpus in group. - */ -static struct rq * -find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, - unsigned long imbalance, const struct cpumask *cpus) -{ - struct rq *busiest = NULL, *rq; - unsigned long max_load = 0; - int i; - - for_each_cpu(i, sched_group_cpus(group)) { - unsigned long wl; - - if (!cpumask_test_cpu(i, cpus)) - continue; - - rq = cpu_rq(i); - wl = weighted_cpuload(i); - - if (rq->nr_running == 1 && wl > imbalance) - continue; - - if (wl > max_load) { - max_load = wl; - busiest = rq; - } - } - - return busiest; -} - -/* - * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but - * so long as it is large enough. - */ -#define MAX_PINNED_INTERVAL 512 - -/* Working cpumask for load_balance and load_balance_newidle. */ -static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); - -/* - * Check this_cpu to ensure it is balanced within domain. Attempt to move - * tasks if there is an imbalance. - */ -static int load_balance(int this_cpu, struct rq *this_rq, - struct sched_domain *sd, enum cpu_idle_type idle, - int *balance) -{ - int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; - struct sched_group *group; - unsigned long imbalance; - struct rq *busiest; - unsigned long flags; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - - cpumask_setall(cpus); - - /* - * When power savings policy is enabled for the parent domain, idle - * sibling can pick up load irrespective of busy siblings. In this case, - * let the state of idle sibling percolate up as CPU_IDLE, instead of - * portraying it as CPU_NOT_IDLE. - */ - if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - sd_idle = 1; - - schedstat_inc(sd, lb_count[idle]); - -redo: - update_shares(sd); - group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, - cpus, balance); - - if (*balance == 0) - goto out_balanced; - - if (!group) { - schedstat_inc(sd, lb_nobusyg[idle]); - goto out_balanced; - } - - busiest = find_busiest_queue(group, idle, imbalance, cpus); - if (!busiest) { - schedstat_inc(sd, lb_nobusyq[idle]); - goto out_balanced; - } - - BUG_ON(busiest == this_rq); - - schedstat_add(sd, lb_imbalance[idle], imbalance); - - ld_moved = 0; - if (busiest->nr_running > 1) { - /* - * Attempt to move tasks. If find_busiest_group has found - * an imbalance but busiest->nr_running <= 1, the group is - * still unbalanced. ld_moved simply stays zero, so it is - * correctly treated as an imbalance. - */ - local_irq_save(flags); - double_rq_lock(this_rq, busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, idle, &all_pinned); - double_rq_unlock(this_rq, busiest); - local_irq_restore(flags); - - /* - * some other cpu did the load balance for us. - */ - if (ld_moved && this_cpu != smp_processor_id()) - resched_cpu(this_cpu); - - /* All tasks on this runqueue were pinned by CPU affinity */ - if (unlikely(all_pinned)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) - goto redo; - goto out_balanced; - } - } - - if (!ld_moved) { - schedstat_inc(sd, lb_failed[idle]); - sd->nr_balance_failed++; - - if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) { - - spin_lock_irqsave(&busiest->lock, flags); - - /* don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu - */ - if (!cpumask_test_cpu(this_cpu, - &busiest->curr->cpus_allowed)) { - spin_unlock_irqrestore(&busiest->lock, flags); - all_pinned = 1; - goto out_one_pinned; - } - - if (!busiest->active_balance) { - busiest->active_balance = 1; - busiest->push_cpu = this_cpu; - active_balance = 1; - } - spin_unlock_irqrestore(&busiest->lock, flags); - if (active_balance) - wake_up_process(busiest->migration_thread); - - /* - * We've kicked active balancing, reset the failure - * counter. - */ - sd->nr_balance_failed = sd->cache_nice_tries+1; - } - } else - sd->nr_balance_failed = 0; - - if (likely(!active_balance)) { - /* We were unbalanced, so reset the balancing interval */ - sd->balance_interval = sd->min_interval; - } else { - /* - * If we've begun active balancing, start to back off. This - * case may not be covered by the all_pinned logic if there - * is only 1 task on the busy runqueue (because we don't call - * move_tasks). - */ - if (sd->balance_interval < sd->max_interval) - sd->balance_interval *= 2; - } - - if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - - goto out; - -out_balanced: - schedstat_inc(sd, lb_balanced[idle]); - - sd->nr_balance_failed = 0; - -out_one_pinned: - /* tune up the balancing interval */ - if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) || - (sd->balance_interval < sd->max_interval)) - sd->balance_interval *= 2; - - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - else - ld_moved = 0; -out: - if (ld_moved) - update_shares(sd); - return ld_moved; -} - -/* - * Check this_cpu to ensure it is balanced within domain. Attempt to move - * tasks if there is an imbalance. - * - * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE). - * this_rq is locked. - */ -static int -load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) -{ - struct sched_group *group; - struct rq *busiest = NULL; - unsigned long imbalance; - int ld_moved = 0; - int sd_idle = 0; - int all_pinned = 0; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - - cpumask_setall(cpus); - - /* - * When power savings policy is enabled for the parent domain, idle - * sibling can pick up load irrespective of busy siblings. In this case, - * let the state of idle sibling percolate up as IDLE, instead of - * portraying it as CPU_NOT_IDLE. - */ - if (sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - sd_idle = 1; - - schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); -redo: - update_shares_locked(this_rq, sd); - group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, - &sd_idle, cpus, NULL); - if (!group) { - schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]); - goto out_balanced; - } - - busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus); - if (!busiest) { - schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]); - goto out_balanced; - } - - BUG_ON(busiest == this_rq); - - schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance); - - ld_moved = 0; - if (busiest->nr_running > 1) { - /* Attempt to move tasks */ - double_lock_balance(this_rq, busiest); - /* this_rq->clock is already updated */ - update_rq_clock(busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, CPU_NEWLY_IDLE, - &all_pinned); - double_unlock_balance(this_rq, busiest); - - if (unlikely(all_pinned)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) - goto redo; - } - } - - if (!ld_moved) { - int active_balance = 0; - - schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]); - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return -1; - - if (sd->nr_balance_failed++ < 2) - return -1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. The same method used to move task in load_balance() - * have been extended for load_balance_newidle() to speedup - * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2) - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - - /* Lock busiest in correct order while this_rq is held */ - double_lock_balance(this_rq, busiest); - - /* - * don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu - */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { - double_unlock_balance(this_rq, busiest); - all_pinned = 1; - return ld_moved; - } - - if (!busiest->active_balance) { - busiest->active_balance = 1; - busiest->push_cpu = this_cpu; - active_balance = 1; - } - - double_unlock_balance(this_rq, busiest); - /* - * Should not call ttwu while holding a rq->lock - */ - spin_unlock(&this_rq->lock); - if (active_balance) - wake_up_process(busiest->migration_thread); - spin_lock(&this_rq->lock); - - } else - sd->nr_balance_failed = 0; - - update_shares_locked(this_rq, sd); - return ld_moved; - -out_balanced: - schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]); - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - sd->nr_balance_failed = 0; - - return 0; -} - -/* - * idle_balance is called by schedule() if this_cpu is about to become - * idle. Attempts to pull tasks from other CPUs. - */ -static void idle_balance(int this_cpu, struct rq *this_rq) -{ - struct sched_domain *sd; - int pulled_task = 0; - unsigned long next_balance = jiffies + HZ; - - for_each_domain(this_cpu, sd) { - unsigned long interval; - - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; - - if (sd->flags & SD_BALANCE_NEWIDLE) - /* If we've pulled tasks over stop searching: */ - pulled_task = load_balance_newidle(this_cpu, this_rq, - sd); - - interval = msecs_to_jiffies(sd->balance_interval); - if (time_after(next_balance, sd->last_balance + interval)) - next_balance = sd->last_balance + interval; - if (pulled_task) - break; - } - if (pulled_task || time_after(jiffies, this_rq->next_balance)) { - /* - * We are going idle. next_balance may be set based on - * a busy processor. So reset next_balance. - */ - this_rq->next_balance = next_balance; - } -} - -/* - * active_load_balance is run by migration threads. It pushes running tasks - * off the busiest CPU onto idle CPUs. It requires at least 1 task to be - * running on each physical CPU where possible, and avoids physical / - * logical imbalances. - * - * Called with busiest_rq locked. - */ -static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) -{ - int target_cpu = busiest_rq->push_cpu; - struct sched_domain *sd; - struct rq *target_rq; - - /* Is there any task to move? */ - if (busiest_rq->nr_running <= 1) - return; - - target_rq = cpu_rq(target_cpu); - - /* - * This condition is "impossible", if it occurs - * we need to fix it. Originally reported by - * Bjorn Helgaas on a 128-cpu setup. - */ - BUG_ON(busiest_rq == target_rq); - - /* move a task from busiest_rq to target_rq */ - double_lock_balance(busiest_rq, target_rq); - update_rq_clock(busiest_rq); - update_rq_clock(target_rq); - - /* Search for an sd spanning us and the target CPU. */ - for_each_domain(target_cpu, sd) { - if ((sd->flags & SD_LOAD_BALANCE) && - cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) - break; - } - - if (likely(sd)) { - schedstat_inc(sd, alb_count); - - if (move_one_task(target_rq, target_cpu, busiest_rq, - sd, CPU_IDLE)) - schedstat_inc(sd, alb_pushed); - else - schedstat_inc(sd, alb_failed); - } - double_unlock_balance(busiest_rq, target_rq); -} - -#ifdef CONFIG_NO_HZ -static struct { - atomic_t load_balancer; - cpumask_var_t cpu_mask; -} nohz ____cacheline_aligned = { - .load_balancer = ATOMIC_INIT(-1), -}; - -/* - * This routine will try to nominate the ilb (idle load balancing) - * owner among the cpus whose ticks are stopped. ilb owner will do the idle - * load balancing on behalf of all those cpus. If all the cpus in the system - * go into this tickless mode, then there will be no ilb owner (as there is - * no need for one) and all the cpus will sleep till the next wakeup event - * arrives... - * - * For the ilb owner, tick is not stopped. And this tick will be used - * for idle load balancing. ilb owner will still be part of - * nohz.cpu_mask.. - * - * While stopping the tick, this cpu will become the ilb owner if there - * is no other owner. And will be the owner till that cpu becomes busy - * or if all cpus in the system stop their ticks at which point - * there is no need for ilb owner. - * - * When the ilb owner becomes busy, it nominates another owner, during the - * next busy scheduler_tick() - */ -int select_nohz_load_balancer(int stop_tick) -{ - int cpu = smp_processor_id(); - - if (stop_tick) { - cpu_rq(cpu)->in_nohz_recently = 1; - - if (!cpu_active(cpu)) { - if (atomic_read(&nohz.load_balancer) != cpu) - return 0; - - /* - * If we are going offline and still the leader, - * give up! - */ - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); - - return 0; - } - - cpumask_set_cpu(cpu, nohz.cpu_mask); - - /* time for ilb owner also to sleep */ - if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - if (atomic_read(&nohz.load_balancer) == cpu) - atomic_set(&nohz.load_balancer, -1); - return 0; - } - - if (atomic_read(&nohz.load_balancer) == -1) { - /* make me the ilb owner */ - if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) - return 1; - } else if (atomic_read(&nohz.load_balancer) == cpu) - return 1; - } else { - if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) - return 0; - - cpumask_clear_cpu(cpu, nohz.cpu_mask); - - if (atomic_read(&nohz.load_balancer) == cpu) - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); - } - return 0; -} -#endif - -static DEFINE_SPINLOCK(balancing); - -/* - * It checks each scheduling domain to see if it is due to be balanced, - * and initiates a balancing operation if so. - * - * Balancing parameters are set up in arch_init_sched_domains. - */ -static void rebalance_domains(int cpu, enum cpu_idle_type idle) -{ - int balance = 1; - struct rq *rq = cpu_rq(cpu); - unsigned long interval; - struct sched_domain *sd; - /* Earliest time when we have to do rebalance again */ - unsigned long next_balance = jiffies + 60*HZ; - int update_next_balance = 0; - int need_serialize; - - for_each_domain(cpu, sd) { - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; - - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; - - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - if (unlikely(!interval)) - interval = 1; - if (interval > HZ*NR_CPUS/10) - interval = HZ*NR_CPUS/10; - - need_serialize = sd->flags & SD_SERIALIZE; - - if (need_serialize) { - if (!spin_trylock(&balancing)) - goto out; - } - - if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance)) { - /* - * We've pulled tasks over so either we're no - * longer idle, or one of our SMT siblings is - * not idle. - */ - idle = CPU_NOT_IDLE; - } - sd->last_balance = jiffies; - } - if (need_serialize) - spin_unlock(&balancing); -out: - if (time_after(next_balance, sd->last_balance + interval)) { - next_balance = sd->last_balance + interval; - update_next_balance = 1; - } - - /* - * Stop the load balance at this level. There is another - * CPU in our sched group which is doing load balancing more - * actively. - */ - if (!balance) - break; - } - - /* - * next_balance will be updated only when there is a need. - * When the cpu is attached to null domain for ex, it will not be - * updated. - */ - if (likely(update_next_balance)) - rq->next_balance = next_balance; -} - -/* - * run_rebalance_domains is triggered when needed from the scheduler tick. - * In CONFIG_NO_HZ case, the idle load balance owner will do the - * rebalancing for all the cpus for whom scheduler ticks are stopped. - */ -static void run_rebalance_domains(struct softirq_action *h) -{ - int this_cpu = smp_processor_id(); - struct rq *this_rq = cpu_rq(this_cpu); - enum cpu_idle_type idle = this_rq->idle_at_tick ? - CPU_IDLE : CPU_NOT_IDLE; - - rebalance_domains(this_cpu, idle); - -#ifdef CONFIG_NO_HZ - /* - * If this cpu is the owner for idle load balancing, then do the - * balancing on behalf of the other idle cpus whose ticks are - * stopped. - */ - if (this_rq->idle_at_tick && - atomic_read(&nohz.load_balancer) == this_cpu) { - struct rq *rq; - int balance_cpu; - - for_each_cpu(balance_cpu, nohz.cpu_mask) { - if (balance_cpu == this_cpu) - continue; - - /* - * If this cpu gets work to do, stop the load balancing - * work being done for other cpus. Next load - * balancing owner will pick it up. - */ - if (need_resched()) - break; - - rebalance_domains(balance_cpu, CPU_IDLE); - - rq = cpu_rq(balance_cpu); - if (time_after(this_rq->next_balance, rq->next_balance)) - this_rq->next_balance = rq->next_balance; - } - } -#endif -} - -static inline int on_null_domain(int cpu) -{ - return !rcu_dereference(cpu_rq(cpu)->sd); -} - -/* - * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. - * - * In case of CONFIG_NO_HZ, this is the place where we nominate a new - * idle load balancing owner or decide to stop the periodic load balancing, - * if the whole system is idle. - */ -static inline void trigger_load_balance(struct rq *rq, int cpu) -{ -#ifdef CONFIG_NO_HZ - /* - * If we were in the nohz mode recently and busy at the current - * scheduler tick, then check if we need to nominate new idle - * load balancer. - */ - if (rq->in_nohz_recently && !rq->idle_at_tick) { - rq->in_nohz_recently = 0; - - if (atomic_read(&nohz.load_balancer) == cpu) { - cpumask_clear_cpu(cpu, nohz.cpu_mask); - atomic_set(&nohz.load_balancer, -1); - } - - if (atomic_read(&nohz.load_balancer) == -1) { - /* - * simple selection for now: Nominate the - * first cpu in the nohz list to be the next - * ilb owner. - * - * TBD: Traverse the sched domains and nominate - * the nearest cpu in the nohz.cpu_mask. - */ - int ilb = cpumask_first(nohz.cpu_mask); - - if (ilb < nr_cpu_ids) - resched_cpu(ilb); - } - } - - /* - * If this cpu is idle and doing idle load balancing for all the - * cpus with ticks stopped, is it time for that to stop? - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - resched_cpu(cpu); - return; - } - - /* - * If this cpu is idle and the idle load balancing is done by - * someone else, then no need raise the SCHED_SOFTIRQ - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpumask_test_cpu(cpu, nohz.cpu_mask)) - return; -#endif - /* Don't need to rebalance while attached to NULL domain */ - if (time_after_eq(jiffies, rq->next_balance) && - likely(!on_null_domain(cpu))) - raise_softirq(SCHED_SOFTIRQ); -} - -#else /* CONFIG_SMP */ - -/* - * on UP we do not need to balance between CPUs: - */ -static inline void idle_balance(int cpu, struct rq *rq) -{ -} - -#endif - -DEFINE_PER_CPU(struct kernel_stat, kstat); - -EXPORT_PER_CPU_SYMBOL(kstat); - -/* - * Return any ns on the sched_clock that have not yet been accounted in - * @p in case that task is currently running. - * - * Called with task_rq_lock() held on @rq. - */ -static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) -{ - u64 ns = 0; - - if (task_current(rq, p)) { - update_rq_clock(rq); - ns = rq->clock - p->se.exec_start; - if ((s64)ns < 0) - ns = 0; - } - - return ns; -} - -unsigned long long task_delta_exec(struct task_struct *p) -{ - unsigned long flags; - struct rq *rq; - u64 ns = 0; - - rq = task_rq_lock(p, &flags); - ns = do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Return accounted runtime for the task. - * In case the task is currently running, return the runtime plus current's - * pending runtime that have not been accounted yet. - */ -unsigned long long task_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - struct rq *rq; - u64 ns = 0; - - rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Return sum_exec_runtime for the thread group. - * In case the task is currently running, return the sum plus current's - * pending runtime that have not been accounted yet. - * - * Note that the thread group might have other running tasks as well, - * so the return value not includes other pending runtime that other - * running tasks might have. - */ -unsigned long long thread_group_sched_runtime(struct task_struct *p) -{ - struct task_cputime totals; - unsigned long flags; - struct rq *rq; - u64 ns; - - rq = task_rq_lock(p, &flags); - thread_group_cputime(p, &totals); - ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Account user cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in user space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_user_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t tmp; - - /* Add user time to process. */ - p->utime = cputime_add(p->utime, cputime); - p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); - account_group_user_time(p, cputime); - - /* Add user time to cpustat. */ - tmp = cputime_to_cputime64(cputime); - if (TASK_NICE(p) > 0) - cpustat->nice = cputime64_add(cpustat->nice, tmp); - else - cpustat->user = cputime64_add(cpustat->user, tmp); - - cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); - /* Account for user time used */ - acct_update_integrals(p); -} - -/* - * Account guest cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in virtual machine since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -static void account_guest_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - cputime64_t tmp; - struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - - tmp = cputime_to_cputime64(cputime); - - /* Add guest time to process. */ - p->utime = cputime_add(p->utime, cputime); - p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); - account_group_user_time(p, cputime); - p->gtime = cputime_add(p->gtime, cputime); - - /* Add guest time to cpustat. */ - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); -} - -/* - * Account system cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime, cputime_t cputime_scaled) -{ - struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t tmp; - - if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime, cputime_scaled); - return; - } - - /* Add system time to process. */ - p->stime = cputime_add(p->stime, cputime); - p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); - account_group_system_time(p, cputime); - - /* Add system time to cpustat. */ - tmp = cputime_to_cputime64(cputime); - if (hardirq_count() - hardirq_offset) - cpustat->irq = cputime64_add(cpustat->irq, tmp); - else if (softirq_count()) - cpustat->softirq = cputime64_add(cpustat->softirq, tmp); - else - cpustat->system = cputime64_add(cpustat->system, tmp); - - cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); - - /* Account for system time used */ - acct_update_integrals(p); -} - -/* - * Account for involuntary wait time. - * @steal: the cpu time spent in involuntary wait - */ -void account_steal_time(cputime_t cputime) -{ - struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t cputime64 = cputime_to_cputime64(cputime); - - cpustat->steal = cputime64_add(cpustat->steal, cputime64); -} - -/* - * Account for idle time. - * @cputime: the cpu time spent in idle wait - */ -void account_idle_time(cputime_t cputime) -{ - struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t cputime64 = cputime_to_cputime64(cputime); - struct rq *rq = this_rq(); - - if (atomic_read(&rq->nr_iowait) > 0) - cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); - else - cpustat->idle = cputime64_add(cpustat->idle, cputime64); -} - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - -/* - * Account a single tick of cpu time. - * @p: the process that the cpu time gets accounted to - * @user_tick: indicates if the tick is a user or a system tick - */ -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy = jiffies_to_cputime(1); - cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy); - struct rq *rq = this_rq(); - - if (user_tick) - account_user_time(p, one_jiffy, one_jiffy_scaled); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, one_jiffy, - one_jiffy_scaled); - else - account_idle_time(one_jiffy); -} - -/* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - account_idle_time(jiffies_to_cputime(ticks)); -} - -#endif - -/* - * Use precise platform statistics if available: - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -cputime_t task_utime(struct task_struct *p) -{ - return p->utime; -} - -cputime_t task_stime(struct task_struct *p) -{ - return p->stime; -} -#else -cputime_t task_utime(struct task_struct *p) -{ - clock_t utime = cputime_to_clock_t(p->utime), - total = utime + cputime_to_clock_t(p->stime); - u64 temp; - - /* - * Use CFS's precise accounting: - */ - temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); - - if (total) { - temp *= utime; - do_div(temp, total); - } - utime = (clock_t)temp; - - p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); - return p->prev_utime; -} - -cputime_t task_stime(struct task_struct *p) -{ - clock_t stime; - - /* - * Use CFS's precise accounting. (we subtract utime from - * the total, to make sure the total observed by userspace - * grows monotonically - apps rely on that): - */ - stime = nsec_to_clock_t(p->se.sum_exec_runtime) - - cputime_to_clock_t(task_utime(p)); - - if (stime >= 0) - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); - - return p->prev_stime; -} -#endif - -inline cputime_t task_gtime(struct task_struct *p) -{ - return p->gtime; -} - -/* - * This function gets called by the timer code, with HZ frequency. - * We call it with interrupts disabled. - * - * It also gets called by the fork code, when changing the parent's - * timeslices. - */ -void scheduler_tick(void) -{ - int cpu = smp_processor_id(); - struct rq *rq = cpu_rq(cpu); - struct task_struct *curr = rq->curr; - - sched_clock_tick(); - - spin_lock(&rq->lock); - update_rq_clock(rq); - update_cpu_load(rq); - curr->sched_class->task_tick(rq, curr, 0); - spin_unlock(&rq->lock); - -#ifdef CONFIG_SMP - rq->idle_at_tick = idle_cpu(cpu); - trigger_load_balance(rq, cpu); -#endif -} - -notrace unsigned long get_parent_ip(unsigned long addr) -{ - if (in_lock_functions(addr)) { - addr = CALLER_ADDR2; - if (in_lock_functions(addr)) - addr = CALLER_ADDR3; - } - return addr; -} - -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_PREEMPT_TRACER)) - -void __kprobes add_preempt_count(int val) -{ -#ifdef CONFIG_DEBUG_PREEMPT - /* - * Underflow? - */ - if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) - return; -#endif - preempt_count() += val; -#ifdef CONFIG_DEBUG_PREEMPT - /* - * Spinlock count overflowing soon? - */ - DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= - PREEMPT_MASK - 10); -#endif - if (preempt_count() == val) - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); -} -EXPORT_SYMBOL(add_preempt_count); - -void __kprobes sub_preempt_count(int val) -{ -#ifdef CONFIG_DEBUG_PREEMPT - /* - * Underflow? - */ - if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) - return; - /* - * Is the spinlock portion underflowing? - */ - if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && - !(preempt_count() & PREEMPT_MASK))) - return; -#endif - - if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); - preempt_count() -= val; -} -EXPORT_SYMBOL(sub_preempt_count); - -#endif - -/* - * Print scheduling while atomic bug: - */ -static noinline void __schedule_bug(struct task_struct *prev) -{ - 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); - print_modules(); - if (irqs_disabled()) - print_irqtrace_events(prev); - - if (regs) - show_regs(regs); - else - dump_stack(); -} - -/* - * Various schedule()-time debugging checks and statistics: - */ -static inline void schedule_debug(struct task_struct *prev) -{ - /* - * 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. - */ - if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) - __schedule_bug(prev); - - profile_hit(SCHED_PROFILING, __builtin_return_address(0)); - - schedstat_inc(this_rq(), sched_count); -#ifdef CONFIG_SCHEDSTATS - if (unlikely(prev->lock_depth >= 0)) { - schedstat_inc(this_rq(), bkl_count); - schedstat_inc(prev, sched_info.bkl_count); - } -#endif -} - -static void put_prev_task(struct rq *rq, struct task_struct *prev) -{ - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; - - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - - /* - * In order to avoid avg_overlap growing stale when we are - * indeed overlapping and hence not getting put to sleep, grow - * the avg_overlap on preemption. - * - * We use the average preemption runtime because that - * correlates to the amount of cache footprint a task can - * build up. - */ - update_avg(&prev->se.avg_overlap, runtime); - } - prev->sched_class->put_prev_task(rq, prev); -} - -/* - * Pick up the highest-prio task: - */ -static inline struct task_struct * -pick_next_task(struct rq *rq) -{ - const struct sched_class *class; - struct task_struct *p; - - /* - * Optimization: we know that if all tasks are in - * the fair class we can call that function directly: - */ - if (likely(rq->nr_running == rq->cfs.nr_running)) { - p = fair_sched_class.pick_next_task(rq); - if (likely(p)) - return p; - } - - class = sched_class_highest; - for ( ; ; ) { - p = class->pick_next_task(rq); - if (p) - return p; - /* - * Will never be NULL as the idle class always - * returns a non-NULL p: - */ - class = class->next; - } -} - -/* - * schedule() is the main scheduler function. - */ -asmlinkage void __sched __schedule(void) -{ - struct task_struct *prev, *next; - unsigned long *switch_count; - struct rq *rq; - int cpu; - - cpu = smp_processor_id(); - rq = cpu_rq(cpu); - rcu_qsctr_inc(cpu); - prev = rq->curr; - switch_count = &prev->nivcsw; - - release_kernel_lock(prev); -need_resched_nonpreemptible: - - schedule_debug(prev); - - if (sched_feat(HRTICK)) - hrtick_clear(rq); - - spin_lock_irq(&rq->lock); - update_rq_clock(rq); - clear_tsk_need_resched(prev); - - if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely(signal_pending_state(prev->state, prev))) - prev->state = TASK_RUNNING; - else - deactivate_task(rq, prev, 1); - 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); - - put_prev_task(rq, prev); - next = pick_next_task(rq); - - if (likely(prev != next)) { - sched_info_switch(prev, next); - - rq->nr_switches++; - rq->curr = next; - ++*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)) - goto need_resched_nonpreemptible; -} - -asmlinkage void __sched schedule(void) -{ -need_resched: - preempt_disable(); - __schedule(); - preempt_enable_no_resched(); - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) - goto need_resched; -} -EXPORT_SYMBOL(schedule); - -#ifdef CONFIG_SMP -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -{ - unsigned int cpu; - struct rq *rq; - - if (!sched_feat(OWNER_SPIN)) - return 0; - -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. - */ - if (probe_kernel_address(&owner->cpu, cpu)) - goto out; -#else - cpu = owner->cpu; -#endif - - /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. - */ - if (cpu >= nr_cpumask_bits) - goto out; - - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) - goto out; - - rq = cpu_rq(cpu); - - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) - break; - - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) - return 0; - - cpu_relax(); - } -out: - return 1; -} -#endif - -#ifdef CONFIG_PREEMPT -/* - * this is the entry point to schedule() from in-kernel preemption - * 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(); - - /* - * If there is a non-zero preempt_count or interrupts are disabled, - * we do not want to preempt the current task. Just return.. - */ - if (likely(ti->preempt_count || irqs_disabled())) - return; - - do { - add_preempt_count(PREEMPT_ACTIVE); - schedule(); - sub_preempt_count(PREEMPT_ACTIVE); - - /* - * Check again in case we missed a preemption opportunity - * between schedule and now. - */ - barrier(); - } while (need_resched()); -} -EXPORT_SYMBOL(preempt_schedule); - -/* - * this is the entry point to schedule() from kernel preemption - * off of irq context. - * Note, that this is called and return with irqs disabled. This will - * protect us against recursive calling from irq. - */ -asmlinkage void __sched preempt_schedule_irq(void) -{ - struct thread_info *ti = current_thread_info(); - - /* Catch callers which need to be fixed */ - BUG_ON(ti->preempt_count || !irqs_disabled()); - - do { - add_preempt_count(PREEMPT_ACTIVE); - local_irq_enable(); - schedule(); - local_irq_disable(); - sub_preempt_count(PREEMPT_ACTIVE); - - /* - * Check again in case we missed a preemption opportunity - * between schedule and now. - */ - barrier(); - } while (need_resched()); -} - -#endif /* CONFIG_PREEMPT */ - -int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, - void *key) -{ - return try_to_wake_up(curr->private, mode, sync); -} -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 - * 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 - * zero in this (rare) case, and we handle it by continuing to scan the queue. - */ -void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int sync, void *key) -{ - wait_queue_t *curr, *next; - - list_for_each_entry_safe(curr, next, &q->task_list, task_list) { - unsigned flags = curr->flags; - - if (curr->func(curr, mode, sync, key) && - (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) - break; - } -} - -/** - * __wake_up - wake up threads blocked on a waitqueue. - * @q: the waitqueue - * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up - * @key: is directly passed to the wakeup function - */ -void __wake_up(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, void *key) -{ - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, 0, key); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL(__wake_up); - -/* - * Same as __wake_up but called with the spinlock in wait_queue_head_t held. - */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) -{ - __wake_up_common(q, mode, 1, 0, NULL); -} - -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) -{ - __wake_up_common(q, mode, 1, 0, key); -} - -/** - * __wake_up_sync_key - wake up threads blocked on a waitqueue. - * @q: the waitqueue - * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up - * @key: opaque value to be passed to wakeup targets - * - * The sync wakeup differs that the waker knows that it will schedule - * away soon, so while the target thread will be woken up, it will not - * be migrated to another CPU - ie. the two threads are 'synchronized' - * with each other. This can prevent needless bouncing between CPUs. - * - * On UP it can prevent extra preemption. - */ -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, void *key) -{ - unsigned long flags; - int sync = 1; - - if (unlikely(!q)) - return; - - if (unlikely(!nr_exclusive)) - sync = 0; - - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, sync, key); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL_GPL(__wake_up_sync_key); - -/* - * __wake_up_sync - see __wake_up_sync_key() - */ -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) -{ - __wake_up_sync_key(q, mode, nr_exclusive, NULL); -} -EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ - -/** - * complete: - signals a single thread waiting on this completion - * @x: holds the state of this particular completion - * - * This will wake up a single thread waiting on this completion. Threads will be - * awakened in the same order in which they were queued. - * - * See also complete_all(), wait_for_completion() and related routines. - */ -void complete(struct completion *x) -{ - unsigned long flags; - - spin_lock_irqsave(&x->wait.lock, flags); - x->done++; - __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); -} -EXPORT_SYMBOL(complete); - -/** - * complete_all: - signals all threads waiting on this completion - * @x: holds the state of this particular completion - * - * This will wake up all threads waiting on this particular completion event. - */ -void complete_all(struct completion *x) -{ - unsigned long flags; - - spin_lock_irqsave(&x->wait.lock, flags); - x->done += UINT_MAX/2; - __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); -} -EXPORT_SYMBOL(complete_all); - -static inline long __sched -do_wait_for_common(struct completion *x, long timeout, int state) -{ - if (!x->done) { - DECLARE_WAITQUEUE(wait, current); - - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); - do { - if (signal_pending_state(state, current)) { - timeout = -ERESTARTSYS; - break; - } - __set_current_state(state); - spin_unlock_irq(&x->wait.lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&x->wait.lock); - } while (!x->done && timeout); - __remove_wait_queue(&x->wait, &wait); - if (!x->done) - return timeout; - } - x->done--; - return timeout ?: 1; -} - -static long __sched -wait_for_common(struct completion *x, long timeout, int state) -{ - might_sleep(); - - spin_lock_irq(&x->wait.lock); - timeout = do_wait_for_common(x, timeout, state); - spin_unlock_irq(&x->wait.lock); - return timeout; -} - -/** - * wait_for_completion: - waits for completion of a task - * @x: holds the state of this particular completion - * - * This waits to be signaled for completion of a specific task. It is NOT - * interruptible and there is no timeout. - * - * See also similar routines (i.e. wait_for_completion_timeout()) with timeout - * and interrupt capability. Also see complete(). - */ -void __sched wait_for_completion(struct completion *x) -{ - wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion); - -/** - * wait_for_completion_timeout: - waits for completion of a task (w/timeout) - * @x: holds the state of this particular completion - * @timeout: timeout value in jiffies - * - * This waits for either a completion of a specific task to be signaled or for a - * specified timeout to expire. The timeout is in jiffies. It is not - * interruptible. - */ -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_timeout); - -/** - * wait_for_completion_interruptible: - waits for completion of a task (w/intr) - * @x: holds the state of this particular completion - * - * This waits for completion of a specific task to be signaled. It is - * interruptible. - */ -int __sched wait_for_completion_interruptible(struct completion *x) -{ - long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); - if (t == -ERESTARTSYS) - return t; - return 0; -} -EXPORT_SYMBOL(wait_for_completion_interruptible); - -/** - * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) - * @x: holds the state of this particular completion - * @timeout: timeout value in jiffies - * - * This waits for either a completion of a specific task to be signaled or for a - * specified timeout to expire. It is interruptible. The timeout is in jiffies. - */ -unsigned long __sched -wait_for_completion_interruptible_timeout(struct completion *x, - unsigned long timeout) -{ - return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); - -/** - * wait_for_completion_killable: - waits for completion of a task (killable) - * @x: holds the state of this particular completion - * - * This waits to be signaled for completion of a specific task. It can be - * interrupted by a kill signal. - */ -int __sched wait_for_completion_killable(struct completion *x) -{ - long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); - if (t == -ERESTARTSYS) - return t; - return 0; -} -EXPORT_SYMBOL(wait_for_completion_killable); - -/** - * try_wait_for_completion - try to decrement a completion without blocking - * @x: completion structure - * - * Returns: 0 if a decrement cannot be done without blocking - * 1 if a decrement succeeded. - * - * If a completion is being used as a counting completion, - * attempt to decrement the counter without blocking. This - * enables us to avoid waiting if the resource the completion - * is protecting is not available. - */ -bool try_wait_for_completion(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - else - x->done--; - spin_unlock_irq(&x->wait.lock); - return ret; -} -EXPORT_SYMBOL(try_wait_for_completion); - -/** - * completion_done - Test to see if a completion has any waiters - * @x: completion structure - * - * Returns: 0 if there are waiters (wait_for_completion() in progress) - * 1 if there are no waiters. - * - */ -bool completion_done(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - spin_unlock_irq(&x->wait.lock); - return ret; -} -EXPORT_SYMBOL(completion_done); - -static long __sched -sleep_on_common(wait_queue_head_t *q, int state, long timeout) -{ - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - __set_current_state(state); - - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, &wait); - spin_unlock(&q->lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&q->lock); - __remove_wait_queue(q, &wait); - spin_unlock_irqrestore(&q->lock, flags); - - return timeout; -} - -void __sched interruptible_sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(interruptible_sleep_on); - -long __sched -interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(interruptible_sleep_on_timeout); - -void __sched sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(sleep_on); - -long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(sleep_on_timeout); - -#ifdef CONFIG_RT_MUTEXES - -/* - * rt_mutex_setprio - set the current priority of a task - * @p: task - * @prio: prio value (kernel-internal form) - * - * This function changes the 'effective' priority of a task. It does - * not touch ->normal_prio like __setscheduler(). - * - * Used by the rt_mutex code to implement priority inheritance logic. - */ -void rt_mutex_setprio(struct task_struct *p, int prio) -{ - 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); - - rq = task_rq_lock(p, &flags); - update_rq_clock(rq); - - oldprio = p->prio; - on_rq = p->se.on_rq; - running = task_current(rq, p); - if (on_rq) - dequeue_task(rq, p, 0); - if (running) - p->sched_class->put_prev_task(rq, p); - - if (rt_prio(prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; - - p->prio = prio; - - if (running) - p->sched_class->set_curr_task(rq); - if (on_rq) { - enqueue_task(rq, p, 0); - - check_class_changed(rq, p, prev_class, oldprio, running); - } - task_rq_unlock(rq, &flags); -} - -#endif - -void set_user_nice(struct task_struct *p, long nice) -{ - int old_prio, delta, on_rq; - unsigned long flags; - struct rq *rq; - - if (TASK_NICE(p) == nice || nice < -20 || nice > 19) - return; - /* - * We have to be careful, if called from sys_setpriority(), - * the task might be in the middle of scheduling on another CPU. - */ - rq = task_rq_lock(p, &flags); - update_rq_clock(rq); - /* - * The RT priorities are set via sched_setscheduler(), but we still - * allow the 'normal' nice value to be set - but as expected - * it wont have any effect on scheduling until the task is - * SCHED_FIFO/SCHED_RR: - */ - if (task_has_rt_policy(p)) { - p->static_prio = NICE_TO_PRIO(nice); - goto out_unlock; - } - on_rq = p->se.on_rq; - if (on_rq) - dequeue_task(rq, p, 0); - - p->static_prio = NICE_TO_PRIO(nice); - set_load_weight(p); - old_prio = p->prio; - p->prio = effective_prio(p); - delta = p->prio - old_prio; - - if (on_rq) { - enqueue_task(rq, p, 0); - /* - * If the task increased its priority or is running and - * lowered its priority, then reschedule its CPU: - */ - if (delta < 0 || (delta > 0 && task_running(rq, p))) - resched_task(rq->curr); - } -out_unlock: - task_rq_unlock(rq, &flags); -} -EXPORT_SYMBOL(set_user_nice); - -/* - * can_nice - check if a task can reduce its nice value - * @p: task - * @nice: nice value - */ -int can_nice(const struct task_struct *p, const int nice) -{ - /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; - - return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || - capable(CAP_SYS_NICE)); -} - -#ifdef __ARCH_WANT_SYS_NICE - -/* - * sys_nice - change the priority of the current process. - * @increment: priority increment - * - * sys_setpriority is a more generic, but much slower function that - * does similar things. - */ -SYSCALL_DEFINE1(nice, int, increment) -{ - long nice, retval; - - /* - * Setpriority might change our priority at the same moment. - * We don't have to worry. Conceptually one call occurs first - * and we have a single winner. - */ - if (increment < -40) - increment = -40; - if (increment > 40) - increment = 40; - - nice = TASK_NICE(current) + increment; - if (nice < -20) - nice = -20; - if (nice > 19) - nice = 19; - - if (increment < 0 && !can_nice(current, nice)) - return -EPERM; - - retval = security_task_setnice(current, nice); - if (retval) - return retval; - - set_user_nice(current, nice); - return 0; -} - -#endif - -/** - * task_prio - return the priority value of a given task. - * @p: the task in question. - * - * This is the priority value as seen by users in /proc. - * RT tasks are offset by -200. Normal tasks are centered - * around 0, value goes from -16 to +15. - */ -int task_prio(const struct task_struct *p) -{ - return p->prio - MAX_RT_PRIO; -} - -/** - * task_nice - return the nice value of a given task. - * @p: the task in question. - */ -int task_nice(const struct task_struct *p) -{ - return TASK_NICE(p); -} -EXPORT_SYMBOL(task_nice); - -/** - * idle_cpu - is a given cpu idle currently? - * @cpu: the processor in question. - */ -int idle_cpu(int cpu) -{ - return cpu_curr(cpu) == cpu_rq(cpu)->idle; -} - -/** - * idle_task - return the idle task for a given cpu. - * @cpu: the processor in question. - */ -struct task_struct *idle_task(int cpu) -{ - return cpu_rq(cpu)->idle; -} - -/** - * find_process_by_pid - find a process with a matching PID value. - * @pid: the pid in question. - */ -static struct task_struct *find_process_by_pid(pid_t pid) -{ - return pid ? find_task_by_vpid(pid) : current; -} - -/* Actually do priority change: must hold rq lock. */ -static void -__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) -{ - BUG_ON(p->se.on_rq); - - p->policy = policy; - switch (p->policy) { - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - p->sched_class = &fair_sched_class; - break; - case SCHED_FIFO: - case SCHED_RR: - p->sched_class = &rt_sched_class; - break; - } - - p->rt_priority = prio; - p->normal_prio = normal_prio(p); - /* we are holding p->pi_lock already */ - p->prio = rt_mutex_getprio(p); - set_load_weight(p); -} - -/* - * check the target process has a UID that matches the current process's - */ -static bool check_same_owner(struct task_struct *p) -{ - const struct cred *cred = current_cred(), *pcred; - bool match; - - rcu_read_lock(); - pcred = __task_cred(p); - match = (cred->euid == pcred->euid || - cred->euid == pcred->uid); - rcu_read_unlock(); - return match; -} - -static int __sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param, bool user) -{ - 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 */ - BUG_ON(in_interrupt()); -recheck: - /* double check policy once rq lock held */ - if (policy < 0) - policy = oldpolicy = p->policy; - else if (policy != SCHED_FIFO && policy != SCHED_RR && - policy != SCHED_NORMAL && policy != SCHED_BATCH && - policy != SCHED_IDLE) - return -EINVAL; - /* - * Valid priorities for SCHED_FIFO and SCHED_RR are - * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, - * SCHED_BATCH and SCHED_IDLE is 0. - */ - if (param->sched_priority < 0 || - (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || - (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) - return -EINVAL; - if (rt_policy(policy) != (param->sched_priority != 0)) - return -EINVAL; - - /* - * Allow unprivileged RT tasks to decrease priority: - */ - if (user && !capable(CAP_SYS_NICE)) { - if (rt_policy(policy)) { - unsigned long rlim_rtprio; - - if (!lock_task_sighand(p, &flags)) - return -ESRCH; - rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; - unlock_task_sighand(p, &flags); - - /* can't set/change the rt policy */ - if (policy != p->policy && !rlim_rtprio) - return -EPERM; - - /* can't increase priority */ - if (param->sched_priority > p->rt_priority && - param->sched_priority > rlim_rtprio) - return -EPERM; - } - /* - * Like positive nice levels, dont allow tasks to - * move out of SCHED_IDLE either: - */ - if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) - return -EPERM; - - /* can't change other user's priorities */ - if (!check_same_owner(p)) - return -EPERM; - } - - if (user) { -#ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (rt_bandwidth_enabled() && rt_policy(policy) && - task_group(p)->rt_bandwidth.rt_runtime == 0) - return -EPERM; -#endif - - retval = security_task_setscheduler(p, policy, param); - if (retval) - return retval; - } - - /* - * make sure no PI-waiters arrive (or leave) while we are - * changing the priority of the task: - */ - spin_lock_irqsave(&p->pi_lock, flags); - /* - * To be able to change p->policy safely, the apropriate - * runqueue lock must be held. - */ - rq = __task_rq_lock(p); - /* recheck policy now with rq lock held */ - if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { - policy = oldpolicy = -1; - __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); - goto recheck; - } - update_rq_clock(rq); - on_rq = p->se.on_rq; - running = task_current(rq, p); - if (on_rq) - deactivate_task(rq, p, 0); - if (running) - p->sched_class->put_prev_task(rq, p); - - oldprio = p->prio; - __setscheduler(rq, p, policy, param->sched_priority); - - if (running) - p->sched_class->set_curr_task(rq); - if (on_rq) { - activate_task(rq, p, 0); - - check_class_changed(rq, p, prev_class, oldprio, running); - } - __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); - - rt_mutex_adjust_pi(p); - - return 0; -} - -/** - * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * NOTE that the task may be already dead. - */ -int sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param) -{ - return __sched_setscheduler(p, policy, param, true); -} -EXPORT_SYMBOL_GPL(sched_setscheduler); - -/** - * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Just like sched_setscheduler, only don't bother checking if the - * current context has permission. For example, this is needed in - * stop_machine(): we create temporary high priority worker threads, - * but our caller might not have that capability. - */ -int sched_setscheduler_nocheck(struct task_struct *p, int policy, - struct sched_param *param) -{ - return __sched_setscheduler(p, policy, param, false); -} - -static int -do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) -{ - struct sched_param lparam; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - if (copy_from_user(&lparam, param, sizeof(struct sched_param))) - return -EFAULT; - - rcu_read_lock(); - retval = -ESRCH; - p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setscheduler(p, policy, &lparam); - rcu_read_unlock(); - - return retval; -} - -/** - * sys_sched_setscheduler - set/change the scheduler policy and RT priority - * @pid: the pid in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - */ -SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, - struct sched_param __user *, param) -{ - /* negative values for policy are not valid */ - if (policy < 0) - return -EINVAL; - - return do_sched_setscheduler(pid, policy, param); -} - -/** - * sys_sched_setparam - set/change the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the new RT priority. - */ -SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) -{ - return do_sched_setscheduler(pid, -1, param); -} - -/** - * sys_sched_getscheduler - get the policy (scheduling class) of a thread - * @pid: the pid in question. - */ -SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) -{ - struct task_struct *p; - int retval; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - read_lock(&tasklist_lock); - p = find_process_by_pid(pid); - if (p) { - retval = security_task_getscheduler(p); - if (!retval) - retval = p->policy; - } - read_unlock(&tasklist_lock); - return retval; -} - -/** - * sys_sched_getscheduler - get the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the RT priority. - */ -SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) -{ - struct sched_param lp; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - - read_lock(&tasklist_lock); - p = find_process_by_pid(pid); - retval = -ESRCH; - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - lp.sched_priority = p->rt_priority; - read_unlock(&tasklist_lock); - - /* - * This one might sleep, we cannot do it with a spinlock held ... - */ - retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; - - return retval; - -out_unlock: - read_unlock(&tasklist_lock); - return retval; -} - -long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) -{ - cpumask_var_t cpus_allowed, new_mask; - struct task_struct *p; - int retval; - - get_online_cpus(); - read_lock(&tasklist_lock); - - p = find_process_by_pid(pid); - if (!p) { - read_unlock(&tasklist_lock); - 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 - * usage count and then drop tasklist_lock. - */ - get_task_struct(p); - read_unlock(&tasklist_lock); - - if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_put_task; - } - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_free_cpus_allowed; - } - retval = -EPERM; - if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) - goto out_unlock; - - retval = security_task_setscheduler(p, 0, NULL); - if (retval) - goto out_unlock; - - cpuset_cpus_allowed(p, cpus_allowed); - cpumask_and(new_mask, in_mask, cpus_allowed); - again: - retval = set_cpus_allowed_ptr(p, new_mask); - - if (!retval) { - cpuset_cpus_allowed(p, cpus_allowed); - if (!cpumask_subset(new_mask, cpus_allowed)) { - /* - * We must have raced with a concurrent cpuset - * update. Just reset the cpus_allowed to the - * cpuset's cpus_allowed - */ - cpumask_copy(new_mask, cpus_allowed); - goto again; - } - } -out_unlock: - free_cpumask_var(new_mask); -out_free_cpus_allowed: - free_cpumask_var(cpus_allowed); -out_put_task: - put_task_struct(p); - put_online_cpus(); - return retval; -} - -static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, - struct cpumask *new_mask) -{ - if (len < cpumask_size()) - cpumask_clear(new_mask); - else if (len > cpumask_size()) - len = cpumask_size(); - - return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; -} - -/** - * sys_sched_setaffinity - set the cpu affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to the new cpu mask - */ -SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - cpumask_var_t new_mask; - int retval; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) - return -ENOMEM; - - retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); - if (retval == 0) - retval = sched_setaffinity(pid, new_mask); - free_cpumask_var(new_mask); - return retval; -} - -long sched_getaffinity(pid_t pid, struct cpumask *mask) -{ - struct task_struct *p; - int retval; - - get_online_cpus(); - read_lock(&tasklist_lock); - - retval = -ESRCH; - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); - -out_unlock: - read_unlock(&tasklist_lock); - put_online_cpus(); - - return retval; -} - -/** - * sys_sched_getaffinity - get the cpu affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to hold the current cpu mask - */ -SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - int ret; - cpumask_var_t mask; - - if (len < cpumask_size()) - return -EINVAL; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - ret = sched_getaffinity(pid, mask); - if (ret == 0) { - if (copy_to_user(user_mask_ptr, mask, cpumask_size())) - ret = -EFAULT; - else - ret = cpumask_size(); - } - free_cpumask_var(mask); - - return ret; -} - -/** - * sys_sched_yield - yield the current processor to other threads. - * - * This function yields the current CPU to other tasks. If there are no - * other threads running on this CPU then this function will return. - */ -SYSCALL_DEFINE0(sched_yield) -{ - struct rq *rq = this_rq_lock(); - - schedstat_inc(rq, yld_count); - current->sched_class->yield_task(rq); - - /* - * Since we are going to call schedule() anyway, there's - * no need to preempt or enable interrupts: - */ - __release(rq->lock); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); - _raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); - - schedule(); - - return 0; -} - -static void __cond_resched(void) -{ -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - __might_sleep(__FILE__, __LINE__); -#endif - /* - * The BKS might be reacquired before we have dropped - * PREEMPT_ACTIVE, which could trigger a second - * cond_resched() call. - */ - do { - add_preempt_count(PREEMPT_ACTIVE); - schedule(); - sub_preempt_count(PREEMPT_ACTIVE); - } while (need_resched()); -} - -int __sched _cond_resched(void) -{ - if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) && - system_state == SYSTEM_RUNNING) { - __cond_resched(); - return 1; - } - return 0; -} -EXPORT_SYMBOL(_cond_resched); - -/* - * 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 - * 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 (spin_needbreak(lock) || resched) { - spin_unlock(lock); - if (resched && need_resched()) - __cond_resched(); - else - cpu_relax(); - ret = 1; - spin_lock(lock); - } - return ret; -} -EXPORT_SYMBOL(cond_resched_lock); - -int __sched cond_resched_softirq(void) -{ - BUG_ON(!in_softirq()); - - if (need_resched() && system_state == SYSTEM_RUNNING) { - local_bh_enable(); - __cond_resched(); - local_bh_disable(); - return 1; - } - return 0; -} -EXPORT_SYMBOL(cond_resched_softirq); - -/** - * yield - yield the current processor to other threads. - * - * This is a shortcut for kernel-space yielding - it marks the - * thread runnable and calls sys_sched_yield(). - */ -void __sched yield(void) -{ - set_current_state(TASK_RUNNING); - sys_sched_yield(); -} -EXPORT_SYMBOL(yield); - -/* - * 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 - * has set its backing_dev_info: the queue against which it should throttle) - */ -void __sched io_schedule(void) -{ - struct rq *rq = &__raw_get_cpu_var(runqueues); - - delayacct_blkio_start(); - atomic_inc(&rq->nr_iowait); - schedule(); - atomic_dec(&rq->nr_iowait); - delayacct_blkio_end(); -} -EXPORT_SYMBOL(io_schedule); - -long __sched io_schedule_timeout(long timeout) -{ - struct rq *rq = &__raw_get_cpu_var(runqueues); - long ret; - - delayacct_blkio_start(); - atomic_inc(&rq->nr_iowait); - ret = schedule_timeout(timeout); - atomic_dec(&rq->nr_iowait); - delayacct_blkio_end(); - return ret; -} - -/** - * sys_sched_get_priority_max - return maximum RT priority. - * @policy: scheduling class. - * - * this syscall returns the maximum rt_priority that can be used - * by a given scheduling class. - */ -SYSCALL_DEFINE1(sched_get_priority_max, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = MAX_USER_RT_PRIO-1; - break; - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - break; - } - return ret; -} - -/** - * sys_sched_get_priority_min - return minimum RT priority. - * @policy: scheduling class. - * - * this syscall returns the minimum rt_priority that can be used - * by a given scheduling class. - */ -SYSCALL_DEFINE1(sched_get_priority_min, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = 1; - break; - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - } - return ret; -} - -/** - * sys_sched_rr_get_interval - return the default timeslice of a process. - * @pid: pid of the process. - * @interval: userspace pointer to the timeslice value. - * - * this syscall writes the default timeslice value of a given process - * into the user-space timespec buffer. A value of '0' means infinity. - */ -SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct timespec __user *, interval) -{ - struct task_struct *p; - unsigned int time_slice; - int retval; - struct timespec t; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - read_lock(&tasklist_lock); - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - /* - * 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 if (p->policy != SCHED_FIFO) { - struct sched_entity *se = &p->se; - unsigned long flags; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - if (rq->cfs.load.weight) - time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); - task_rq_unlock(rq, &flags); - } - read_unlock(&tasklist_lock); - jiffies_to_timespec(time_slice, &t); - retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; - return retval; - -out_unlock: - read_unlock(&tasklist_lock); - return retval; -} - -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - -void sched_show_task(struct task_struct *p) -{ - unsigned long free = 0; - unsigned state; - - state = p->state ? __ffs(p->state) + 1 : 0; - 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(KERN_CONT " running "); - else - printk(KERN_CONT " %08lx ", thread_saved_pc(p)); -#else - if (state == TASK_RUNNING) - printk(KERN_CONT " running task "); - else - printk(KERN_CONT " %016lx ", thread_saved_pc(p)); -#endif -#ifdef CONFIG_DEBUG_STACK_USAGE - free = stack_not_used(p); -#endif - printk(KERN_CONT "%5lu %5d %6d\n", free, - task_pid_nr(p), task_pid_nr(p->real_parent)); - - show_stack(p, NULL); -} - -void show_state_filter(unsigned long state_filter) -{ - struct task_struct *g, *p; - -#if BITS_PER_LONG == 32 - printk(KERN_INFO - " task PC stack pid father\n"); -#else - printk(KERN_INFO - " task PC stack pid father\n"); -#endif - read_lock(&tasklist_lock); - do_each_thread(g, p) { - /* - * reset the NMI-timeout, listing all files on a slow - * console might take alot of time: - */ - touch_nmi_watchdog(); - if (!state_filter || (p->state & state_filter)) - sched_show_task(p); - } while_each_thread(g, p); - - touch_all_softlockup_watchdogs(); - -#ifdef CONFIG_SCHED_DEBUG - sysrq_sched_debug_show(); -#endif - read_unlock(&tasklist_lock); - /* - * Only show locks if all tasks are dumped: - */ - if (state_filter == -1) - debug_show_all_locks(); -} - -void __cpuinit init_idle_bootup_task(struct task_struct *idle) -{ - idle->sched_class = &idle_sched_class; -} - -/** - * init_idle - set up an idle thread for a given CPU - * @idle: task in question - * @cpu: cpu the idle task belongs to - * - * NOTE: this function does not set the idle thread's NEED_RESCHED - * flag, to make booting more robust. - */ -void __cpuinit init_idle(struct task_struct *idle, int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - - __sched_fork(idle); - idle->se.exec_start = sched_clock(); - - idle->prio = idle->normal_prio = MAX_PRIO; - cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); - __set_task_cpu(idle, cpu); - - rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; -#endif - spin_unlock_irqrestore(&rq->lock, flags); - - /* Set the preempt count _outside_ the spinlocks! */ -#if defined(CONFIG_PREEMPT) - 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: - */ - idle->sched_class = &idle_sched_class; - ftrace_graph_init_task(idle); -} - -/* - * In a system that switches off the HZ timer nohz_cpu_mask - * indicates which cpus entered this state. This is used - * in the rcu update to wait only for active cpus. For system - * which do not switch off the HZ timer nohz_cpu_mask should - * always be CPU_BITS_NONE. - */ -cpumask_var_t nohz_cpu_mask; - -/* - * 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_shares_ratelimit *= factor; -} - -#ifdef CONFIG_SMP -/* - * This is how migration works: - * - * 1) we queue a struct migration_req structure in the source CPU's - * runqueue and wake up that CPU's migration thread. - * 2) we down() the locked semaphore => thread blocks. - * 3) migration thread wakes up (implicitly it forces the migrated - * thread off the CPU) - * 4) it gets the migration request and checks whether the migrated - * task is still in the wrong runqueue. - * 5) if it's in the wrong runqueue then the migration thread removes - * it and puts it into the right queue. - * 6) migration thread up()s the semaphore. - * 7) we wake up and the migration is done. - */ - -/* - * Change a given task's CPU affinity. Migrate the thread to a - * proper CPU and schedule it away if the CPU it's executing on - * 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 - * call is not atomic; no spinlocks may be held. - */ -int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) -{ - struct migration_req req; - unsigned long flags; - struct rq *rq; - int ret = 0; - - rq = task_rq_lock(p, &flags); - if (!cpumask_intersects(new_mask, cpu_online_mask)) { - ret = -EINVAL; - goto out; - } - - if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && - !cpumask_equal(&p->cpus_allowed, new_mask))) { - ret = -EINVAL; - goto out; - } - - if (p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - else { - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); - } - - /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) - goto out; - - if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) { - /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, &flags); - wake_up_process(rq->migration_thread); - wait_for_completion(&req.done); - tlb_migrate_finish(p->mm); - return 0; - } -out: - task_rq_unlock(rq, &flags); - - return ret; -} -EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); - -/* - * 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). - * - * So we race with normal scheduler movements, but that's OK, as long - * as the task is no longer on this CPU. - * - * Returns non-zero if task was successfully migrated. - */ -static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) -{ - struct rq *rq_dest, *rq_src; - int ret = 0, on_rq; - - if (unlikely(!cpu_active(dest_cpu))) - return ret; - - rq_src = cpu_rq(src_cpu); - rq_dest = cpu_rq(dest_cpu); - - double_rq_lock(rq_src, rq_dest); - /* Already moved. */ - if (task_cpu(p) != src_cpu) - goto done; - /* Affinity changed (again). */ - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) - goto fail; - - on_rq = p->se.on_rq; - if (on_rq) - deactivate_task(rq_src, p, 0); - - set_task_cpu(p, dest_cpu); - if (on_rq) { - activate_task(rq_dest, p, 0); - check_preempt_curr(rq_dest, p, 0); - } -done: - ret = 1; -fail: - double_rq_unlock(rq_src, rq_dest); - return ret; -} - -/* - * migration_thread - this is a highprio system thread that performs - * thread migration by bumping thread off CPU then 'pushing' onto - * another runqueue. - */ -static int migration_thread(void *data) -{ - int cpu = (long)data; - struct rq *rq; - - rq = cpu_rq(cpu); - BUG_ON(rq->migration_thread != current); - - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - struct migration_req *req; - struct list_head *head; - - spin_lock_irq(&rq->lock); - - if (cpu_is_offline(cpu)) { - spin_unlock_irq(&rq->lock); - goto wait_to_die; - } - - if (rq->active_balance) { - active_load_balance(rq, cpu); - rq->active_balance = 0; - } - - head = &rq->migration_queue; - - if (list_empty(head)) { - spin_unlock_irq(&rq->lock); - schedule(); - set_current_state(TASK_INTERRUPTIBLE); - continue; - } - req = list_entry(head->next, struct migration_req, list); - list_del_init(head->next); - - spin_unlock(&rq->lock); - __migrate_task(req->task, cpu, req->dest_cpu); - local_irq_enable(); - - complete(&req->done); - } - __set_current_state(TASK_RUNNING); - return 0; - -wait_to_die: - /* Wait for kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_INTERRUPTIBLE); - } - __set_current_state(TASK_RUNNING); - return 0; -} - -#ifdef CONFIG_HOTPLUG_CPU - -static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) -{ - int ret; - - local_irq_disable(); - ret = __migrate_task(p, src_cpu, dest_cpu); - local_irq_enable(); - return ret; -} - -/* - * Figure out where task on dead CPU should go, use force if necessary. - */ -static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) -{ - int dest_cpu; - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu)); - -again: - /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask) - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) - goto move; - - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask); - if (dest_cpu < nr_cpu_ids) - goto move; - - /* No more Mr. Nice Guy. */ - if (dest_cpu >= nr_cpu_ids) { - cpuset_cpus_allowed_locked(p, &p->cpus_allowed); - dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed); - - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, dead_cpu); - } - } - -move: - /* It can have affinity changed while we were choosing. */ - if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu))) - goto again; -} - -/* - * While a dead CPU has no uninterruptible tasks queued at this point, - * it might still have a nonzero ->nr_uninterruptible counter, because - * for performance reasons the counter is not stricly tracking tasks to - * their home CPUs. So we just add the counter to another CPU's counter, - * to keep the global sum constant after CPU-down: - */ -static void migrate_nr_uninterruptible(struct rq *rq_src) -{ - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask)); - unsigned long flags; - - local_irq_save(flags); - double_rq_lock(rq_src, rq_dest); - rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; - rq_src->nr_uninterruptible = 0; - double_rq_unlock(rq_src, rq_dest); - local_irq_restore(flags); -} - -/* Run through task list and migrate tasks from the dead cpu. */ -static void migrate_live_tasks(int src_cpu) -{ - struct task_struct *p, *t; - - read_lock(&tasklist_lock); - - do_each_thread(t, p) { - if (p == current) - continue; - - if (task_cpu(p) == src_cpu) - move_task_off_dead_cpu(src_cpu, p); - } while_each_thread(t, p); - - read_unlock(&tasklist_lock); -} - -/* - * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible. - * Used by CPU offline code. - */ -void sched_idle_next(void) -{ - int this_cpu = smp_processor_id(); - struct rq *rq = cpu_rq(this_cpu); - struct task_struct *p = rq->idle; - unsigned long flags; - - /* cpu has to be offline */ - BUG_ON(cpu_online(this_cpu)); - - /* - * Strictly not necessary since rest of the CPUs are stopped by now - * and interrupts disabled on the current cpu. - */ - spin_lock_irqsave(&rq->lock, flags); - - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - - update_rq_clock(rq); - activate_task(rq, p, 0); - - spin_unlock_irqrestore(&rq->lock, flags); -} - -/* - * Ensures that the idle task is using init_mm right before its cpu goes - * offline. - */ -void idle_task_exit(void) -{ - struct mm_struct *mm = current->active_mm; - - BUG_ON(cpu_online(smp_processor_id())); - - if (mm != &init_mm) - switch_mm(mm, &init_mm, current); - mmdrop(mm); -} - -/* called under rq->lock with disabled interrupts */ -static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) -{ - struct rq *rq = cpu_rq(dead_cpu); - - /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(!p->exit_state); - - /* Cannot have done final schedule yet: would have vanished. */ - BUG_ON(p->state == TASK_DEAD); - - get_task_struct(p); - - /* - * Drop lock around migration; if someone else moves it, - * that's OK. No task can be added to this CPU, so iteration is - * fine. - */ - spin_unlock_irq(&rq->lock); - move_task_off_dead_cpu(dead_cpu, p); - spin_lock_irq(&rq->lock); - - put_task_struct(p); -} - -/* release_task() removes task from tasklist, so we won't find dead tasks. */ -static void migrate_dead_tasks(unsigned int dead_cpu) -{ - struct rq *rq = cpu_rq(dead_cpu); - struct task_struct *next; - - for ( ; ; ) { - if (!rq->nr_running) - break; - update_rq_clock(rq); - next = pick_next_task(rq); - if (!next) - break; - next->sched_class->put_prev_task(rq, next); - migrate_dead(dead_cpu, next); - - } -} -#endif /* CONFIG_HOTPLUG_CPU */ - -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) - -static struct ctl_table sd_ctl_dir[] = { - { - .procname = "sched_domain", - .mode = 0555, - }, - {0, }, -}; - -static struct ctl_table sd_ctl_root[] = { - { - .ctl_name = CTL_KERN, - .procname = "kernel", - .mode = 0555, - .child = sd_ctl_dir, - }, - {0, }, -}; - -static struct ctl_table *sd_alloc_ctl_entry(int n) -{ - struct ctl_table *entry = - kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); - - return entry; -} - -static void sd_free_ctl_entry(struct ctl_table **tablep) -{ - struct ctl_table *entry; - - /* - * In the intermediate directories, both the child directory and - * procname are dynamically allocated and could fail but the mode - * will always be set. In the lowest directory the names are - * static strings and all have proc handlers. - */ - for (entry = *tablep; entry->mode; entry++) { - if (entry->child) - sd_free_ctl_entry(&entry->child); - if (entry->proc_handler == NULL) - kfree(entry->procname); - } - - kfree(*tablep); - *tablep = NULL; -} - -static void -set_table_entry(struct ctl_table *entry, - const char *procname, void *data, int maxlen, - mode_t mode, proc_handler *proc_handler) -{ - entry->procname = procname; - entry->data = data; - entry->maxlen = maxlen; - entry->mode = mode; - entry->proc_handler = proc_handler; -} - -static struct ctl_table * -sd_alloc_ctl_domain_table(struct sched_domain *sd) -{ - struct ctl_table *table = sd_alloc_ctl_entry(13); - - if (table == NULL) - return NULL; - - set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax); - set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax); - set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[9], "cache_nice_tries", - &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring); - /* &table[12] is terminator */ - - return table; -} - -static ctl_table *sd_alloc_ctl_cpu_table(int cpu) -{ - struct ctl_table *entry, *table; - struct sched_domain *sd; - int domain_num = 0, i; - char buf[32]; - - for_each_domain(cpu, sd) - domain_num++; - entry = table = sd_alloc_ctl_entry(domain_num + 1); - if (table == NULL) - return NULL; - - i = 0; - for_each_domain(cpu, sd) { - snprintf(buf, 32, "domain%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_domain_table(sd); - entry++; - i++; - } - return table; -} - -static struct ctl_table_header *sd_sysctl_header; -static void register_sched_domain_sysctl(void) -{ - int i, cpu_num = num_online_cpus(); - struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); - char buf[32]; - - WARN_ON(sd_ctl_dir[0].child); - sd_ctl_dir[0].child = entry; - - if (entry == NULL) - return; - - for_each_online_cpu(i) { - snprintf(buf, 32, "cpu%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_cpu_table(i); - entry++; - } - - 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) -{ - if (sd_sysctl_header) - unregister_sysctl_table(sd_sysctl_header); - sd_sysctl_header = NULL; - if (sd_ctl_dir[0].child) - sd_free_ctl_entry(&sd_ctl_dir[0].child); -} -#else -static void register_sched_domain_sysctl(void) -{ -} -static void unregister_sched_domain_sysctl(void) -{ -} -#endif - -static void set_rq_online(struct rq *rq) -{ - if (!rq->online) { - const struct sched_class *class; - - cpumask_set_cpu(rq->cpu, rq->rd->online); - rq->online = 1; - - for_each_class(class) { - if (class->rq_online) - class->rq_online(rq); - } - } -} - -static void set_rq_offline(struct rq *rq) -{ - if (rq->online) { - const struct sched_class *class; - - for_each_class(class) { - if (class->rq_offline) - class->rq_offline(rq); - } - - cpumask_clear_cpu(rq->cpu, rq->rd->online); - rq->online = 0; - } -} - -/* - * migration_call - callback that gets triggered when a CPU is added. - * Here we can start up the necessary migration thread for the new CPU. - */ -static int __cpuinit -migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - struct task_struct *p; - int cpu = (long)hcpu; - unsigned long flags; - struct rq *rq; - - switch (action) { - - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - p = kthread_create(migration_thread, hcpu, "migration/%d", cpu); - if (IS_ERR(p)) - return NOTIFY_BAD; - kthread_bind(p, cpu); - /* Must be high prio: stop_machine expects to yield to it. */ - rq = task_rq_lock(p, &flags); - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - task_rq_unlock(rq, &flags); - cpu_rq(cpu)->migration_thread = p; - break; - - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - /* 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(!cpumask_test_cpu(cpu, rq->rd->span)); - - set_rq_online(rq); - } - spin_unlock_irqrestore(&rq->lock, flags); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!cpu_rq(cpu)->migration_thread) - break; - /* Unbind it from offline cpu so it can run. Fall thru. */ - kthread_bind(cpu_rq(cpu)->migration_thread, - cpumask_any(cpu_online_mask)); - kthread_stop(cpu_rq(cpu)->migration_thread); - cpu_rq(cpu)->migration_thread = NULL; - break; - - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ - migrate_live_tasks(cpu); - rq = cpu_rq(cpu); - kthread_stop(rq->migration_thread); - rq->migration_thread = NULL; - /* Idle task back to normal (off runqueue, low prio) */ - spin_lock_irq(&rq->lock); - update_rq_clock(rq); - deactivate_task(rq, rq->idle, 0); - rq->idle->static_prio = MAX_PRIO; - __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); - rq->idle->sched_class = &idle_sched_class; - migrate_dead_tasks(cpu); - 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. - */ - spin_lock_irq(&rq->lock); - while (!list_empty(&rq->migration_queue)) { - struct migration_req *req; - - req = list_entry(rq->migration_queue.next, - struct migration_req, list); - list_del_init(&req->list); - spin_unlock_irq(&rq->lock); - complete(&req->done); - spin_lock_irq(&rq->lock); - } - spin_unlock_irq(&rq->lock); - break; - - case CPU_DYING: - case CPU_DYING_FROZEN: - /* Update our root-domain */ - rq = cpu_rq(cpu); - spin_lock_irqsave(&rq->lock, flags); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); - } - spin_unlock_irqrestore(&rq->lock, flags); - break; -#endif - } - return NOTIFY_OK; -} - -/* Register at highest priority so that task migration (migrate_all_tasks) - * happens before everything else. - */ -static struct notifier_block __cpuinitdata migration_notifier = { - .notifier_call = migration_call, - .priority = 10 -}; - -static int __init migration_init(void) -{ - void *cpu = (void *)(long)smp_processor_id(); - int err; - - /* Start one for the boot CPU: */ - err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); - BUG_ON(err == NOTIFY_BAD); - migration_call(&migration_notifier, CPU_ONLINE, cpu); - register_cpu_notifier(&migration_notifier); - - return err; -} -early_initcall(migration_init); -#endif - -#ifdef CONFIG_SMP - -#ifdef CONFIG_SCHED_DEBUG - -static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, - struct cpumask *groupmask) -{ - struct sched_group *group = sd->groups; - char str[256]; - - cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); - cpumask_clear(groupmask); - - 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 level %s\n", str, sd->name); - - if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { - printk(KERN_ERR "ERROR: domain->span does not contain " - "CPU%d\n", cpu); - } - if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { - printk(KERN_ERR "ERROR: domain->groups does not contain" - " CPU%d\n", cpu); - } - - printk(KERN_DEBUG "%*s groups:", level + 1, ""); - do { - if (!group) { - printk("\n"); - printk(KERN_ERR "ERROR: group is NULL\n"); - break; - } - - if (!group->__cpu_power) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); - break; - } - - if (!cpumask_weight(sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: empty group\n"); - break; - } - - if (cpumask_intersects(groupmask, sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: repeated CPUs\n"); - break; - } - - cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - - cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); - - printk(KERN_CONT " %s", str); - if (group->__cpu_power != SCHED_LOAD_SCALE) { - printk(KERN_CONT " (__cpu_power = %d)", - group->__cpu_power); - } - - group = group->next; - } while (group != sd->groups); - printk(KERN_CONT "\n"); - - if (!cpumask_equal(sched_domain_span(sd), groupmask)) - printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - - if (sd->parent && - !cpumask_subset(groupmask, sched_domain_span(sd->parent))) - printk(KERN_ERR "ERROR: parent span is not a superset " - "of domain->span\n"); - return 0; -} - -static void sched_domain_debug(struct sched_domain *sd, int cpu) -{ - cpumask_var_t groupmask; - int level = 0; - - if (!sd) { - printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); - return; - } - - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); - - if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { - printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); - return; - } - - for (;;) { - if (sched_domain_debug_one(sd, cpu, level, groupmask)) - break; - level++; - sd = sd->parent; - if (!sd) - break; - } - free_cpumask_var(groupmask); -} -#else /* !CONFIG_SCHED_DEBUG */ -# define sched_domain_debug(sd, cpu) do { } while (0) -#endif /* CONFIG_SCHED_DEBUG */ - -static int sd_degenerate(struct sched_domain *sd) -{ - if (cpumask_weight(sched_domain_span(sd)) == 1) - return 1; - - /* Following flags need at least 2 groups */ - if (sd->flags & (SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { - if (sd->groups != sd->groups->next) - return 0; - } - - /* Following flags don't use groups */ - if (sd->flags & (SD_WAKE_IDLE | - SD_WAKE_AFFINE | - SD_WAKE_BALANCE)) - return 0; - - return 1; -} - -static int -sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) -{ - unsigned long cflags = sd->flags, pflags = parent->flags; - - if (sd_degenerate(parent)) - return 1; - - if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) - return 0; - - /* Does parent contain flags not in child? */ - /* WAKE_BALANCE is a subset of WAKE_AFFINE */ - if (cflags & SD_WAKE_AFFINE) - pflags &= ~SD_WAKE_BALANCE; - /* Flags needing groups don't count if only 1 group in parent */ - if (parent->groups == parent->groups->next) { - pflags &= ~(SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES); - if (nr_node_ids == 1) - pflags &= ~SD_SERIALIZE; - } - if (~cflags & pflags) - return 0; - - return 1; -} - -static void free_rootdomain(struct root_domain *rd) -{ - cpupri_cleanup(&rd->cpupri); - - free_cpumask_var(rd->rto_mask); - free_cpumask_var(rd->online); - free_cpumask_var(rd->span); - kfree(rd); -} - -static void rq_attach_root(struct rq *rq, struct root_domain *rd) -{ - struct root_domain *old_rd = NULL; - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - - if (rq->rd) { - old_rd = rq->rd; - - if (cpumask_test_cpu(rq->cpu, old_rd->online)) - set_rq_offline(rq); - - cpumask_clear_cpu(rq->cpu, old_rd->span); - - /* - * If we dont want to free the old_rt yet then - * set old_rd to NULL to skip the freeing later - * in this function: - */ - if (!atomic_dec_and_test(&old_rd->refcount)) - old_rd = NULL; - } - - atomic_inc(&rd->refcount); - rq->rd = rd; - - cpumask_set_cpu(rq->cpu, rd->span); - if (cpumask_test_cpu(rq->cpu, cpu_online_mask)) - set_rq_online(rq); - - spin_unlock_irqrestore(&rq->lock, flags); - - if (old_rd) - free_rootdomain(old_rd); -} - -static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) -{ - memset(rd, 0, sizeof(*rd)); - - if (bootmem) { - alloc_bootmem_cpumask_var(&def_root_domain.span); - alloc_bootmem_cpumask_var(&def_root_domain.online); - alloc_bootmem_cpumask_var(&def_root_domain.rto_mask); - cpupri_init(&rd->cpupri, true); - return 0; - } - - if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) - goto out; - if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) - goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) - goto free_online; - - if (cpupri_init(&rd->cpupri, false) != 0) - goto free_rto_mask; - return 0; - -free_rto_mask: - free_cpumask_var(rd->rto_mask); -free_online: - free_cpumask_var(rd->online); -free_span: - free_cpumask_var(rd->span); -out: - return -ENOMEM; -} - -static void init_defrootdomain(void) -{ - init_rootdomain(&def_root_domain, true); - - 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; - - if (init_rootdomain(rd, false) != 0) { - kfree(rd); - return NULL; - } - - return rd; -} - -/* - * 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, struct root_domain *rd, int cpu) -{ - struct rq *rq = cpu_rq(cpu); - struct sched_domain *tmp; - - /* Remove the sched domains which do not contribute to scheduling. */ - for (tmp = sd; tmp; ) { - struct sched_domain *parent = tmp->parent; - if (!parent) - break; - - if (sd_parent_degenerate(tmp, parent)) { - tmp->parent = parent->parent; - if (parent->parent) - parent->parent->child = tmp; - } else - tmp = tmp->parent; - } - - if (sd && sd_degenerate(sd)) { - sd = sd->parent; - if (sd) - sd->child = NULL; - } - - sched_domain_debug(sd, cpu); - - rq_attach_root(rq, rd); - rcu_assign_pointer(rq->sd, sd); -} - -/* cpus with isolated domains */ -static cpumask_var_t cpu_isolated_map; - -/* Setup the mask of cpus configured for isolated domains */ -static int __init isolated_cpu_setup(char *str) -{ - cpulist_parse(str, cpu_isolated_map); - return 1; -} - -__setup("isolcpus=", isolated_cpu_setup); - -/* - * init_sched_build_groups takes the cpumask we wish to span, and a pointer - * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids - * (due to the fact that we keep track of groups covered with a struct cpumask). - * - * init_sched_build_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. - */ -static void -init_sched_build_groups(const struct cpumask *span, - const struct cpumask *cpu_map, - int (*group_fn)(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *tmpmask), - struct cpumask *covered, struct cpumask *tmpmask) -{ - struct sched_group *first = NULL, *last = NULL; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group = group_fn(i, cpu_map, &sg, tmpmask); - int j; - - if (cpumask_test_cpu(i, covered)) - continue; - - cpumask_clear(sched_group_cpus(sg)); - sg->__cpu_power = 0; - - for_each_cpu(j, span) { - if (group_fn(j, cpu_map, NULL, tmpmask) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; -} - -#define SD_NODES_PER_DOMAIN 16 - -#ifdef CONFIG_NUMA - -/** - * find_next_best_node - find the next node to include in a sched_domain - * @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 - * finds the closest node not already in the @used_nodes map. - * - * Should use nodemask_t. - */ -static int find_next_best_node(int node, nodemask_t *used_nodes) -{ - int i, n, val, min_val, best_node = 0; - - min_val = INT_MAX; - - for (i = 0; i < nr_node_ids; i++) { - /* Start at @node */ - n = (node + i) % nr_node_ids; - - if (!nr_cpus_node(n)) - continue; - - /* Skip already used nodes */ - if (node_isset(n, *used_nodes)) - continue; - - /* Simple min distance search */ - val = node_distance(node, n); - - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - node_set(best_node, *used_nodes); - return best_node; -} - -/** - * sched_domain_node_span - get a cpumask for a node's sched_domain - * @node: node whose cpumask we're constructing - * @span: resulting cpumask - * - * 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 void sched_domain_node_span(int node, struct cpumask *span) -{ - nodemask_t used_nodes; - int i; - - cpumask_clear(span); - nodes_clear(used_nodes); - - cpumask_or(span, span, cpumask_of_node(node)); - node_set(node, used_nodes); - - for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, &used_nodes); - - cpumask_or(span, span, cpumask_of_node(next_node)); - } -} -#endif /* CONFIG_NUMA */ - -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; - -/* - * The cpus mask in sched_group and sched_domain hangs off the end. - * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space - * for nr_cpu_ids < CONFIG_NR_CPUS. - */ -struct static_sched_group { - struct sched_group sg; - DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); -}; - -struct static_sched_domain { - struct sched_domain sd; - DECLARE_BITMAP(span, CONFIG_NR_CPUS); -}; - -/* - * SMT sched-domains: - */ -#ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); - -static int -cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) -{ - if (sg) - *sg = &per_cpu(sched_group_cpus, cpu).sg; - return cpu; -} -#endif /* CONFIG_SCHED_SMT */ - -/* - * multi-core sched-domains: - */ -#ifdef CONFIG_SCHED_MC -static DEFINE_PER_CPU(struct static_sched_domain, core_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); -#endif /* CONFIG_SCHED_MC */ - -#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) -static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group; - - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); - if (sg) - *sg = &per_cpu(sched_group_core, group).sg; - return group; -} -#elif defined(CONFIG_SCHED_MC) -static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) -{ - if (sg) - *sg = &per_cpu(sched_group_core, cpu).sg; - return cpu; -} -#endif - -static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); - -static int -cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group; -#ifdef CONFIG_SCHED_MC - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif - if (sg) - *sg = &per_cpu(sched_group_phys, group).sg; - return group; -} - -#ifdef CONFIG_NUMA -/* - * The init_sched_build_groups can't handle what we want to do with node - * groups, so roll our own. Now each node has its own list of groups which - * gets dynamically allocated. - */ -static DEFINE_PER_CPU(struct static_sched_domain, node_domains); -static struct sched_group ***sched_group_nodes_bycpu; - -static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); - -static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; - - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); - - if (sg) - *sg = &per_cpu(sched_group_allnodes, group).sg; - return group; -} - -static void init_numa_sched_groups_power(struct sched_group *group_head) -{ - struct sched_group *sg = group_head; - int j; - - if (!sg) - return; - do { - for_each_cpu(j, sched_group_cpus(sg)) { - struct sched_domain *sd; - - sd = &per_cpu(phys_domains, j).sd; - if (j != cpumask_first(sched_group_cpus(sd->groups))) { - /* - * Only add "power" once for each - * physical package. - */ - continue; - } - - sg_inc_cpu_power(sg, sd->groups->__cpu_power); - } - sg = sg->next; - } while (sg != group_head); -} -#endif /* CONFIG_NUMA */ - -#ifdef CONFIG_NUMA -/* Free memory allocated for various sched_group structures */ -static void free_sched_groups(const struct cpumask *cpu_map, - struct cpumask *nodemask) -{ - int cpu, i; - - for_each_cpu(cpu, cpu_map) { - struct sched_group **sched_group_nodes - = sched_group_nodes_bycpu[cpu]; - - if (!sched_group_nodes) - continue; - - for (i = 0; i < nr_node_ids; i++) { - struct sched_group *oldsg, *sg = sched_group_nodes[i]; - - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) - continue; - - if (sg == NULL) - continue; - sg = sg->next; -next_sg: - oldsg = sg; - sg = sg->next; - kfree(oldsg); - if (oldsg != sched_group_nodes[i]) - goto next_sg; - } - kfree(sched_group_nodes); - sched_group_nodes_bycpu[cpu] = NULL; - } -} -#else /* !CONFIG_NUMA */ -static void free_sched_groups(const struct cpumask *cpu_map, - struct cpumask *nodemask) -{ -} -#endif /* CONFIG_NUMA */ - -/* - * Initialize sched groups cpu_power. - * - * cpu_power indicates the capacity of sched group, which is used while - * distributing the load between different sched groups in a sched domain. - * Typically cpu_power for all the groups in a sched domain will be same unless - * there are asymmetries in the topology. If there are asymmetries, group - * having more cpu_power will pickup more load compared to the group having - * less cpu_power. - * - * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents - * the maximum number of tasks a group can handle in the presence of other idle - * or lightly loaded groups in the same sched domain. - */ -static void init_sched_groups_power(int cpu, struct sched_domain *sd) -{ - struct sched_domain *child; - struct sched_group *group; - - WARN_ON(!sd || !sd->groups); - - if (cpu != cpumask_first(sched_group_cpus(sd->groups))) - return; - - child = sd->child; - - sd->groups->__cpu_power = 0; - - /* - * For perf policy, if the groups in child domain share resources - * (for example cores sharing some portions of the cache hierarchy - * or SMT), then set this domain groups cpu_power such that each group - * can handle only one task, when there are other idle groups in the - * same sched domain. - */ - if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) && - (child->flags & - (SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) { - sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE); - return; - } - - /* - * add cpu_power of each child group to this groups cpu_power - */ - group = child->groups; - do { - sg_inc_cpu_power(sd->groups, group->__cpu_power); - group = group->next; - } while (group != child->groups); -} - -/* - * Initializers for schedule domains - * Non-inlined to reduce accumulated stack pressure in build_sched_domains() - */ - -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(sd, type) sd->name = #type -#else -# define SD_INIT_NAME(sd, type) do { } while (0) -#endif - -#define SD_INIT(sd, type) sd_init_##type(sd) - -#define SD_INIT_FUNC(type) \ -static noinline void sd_init_##type(struct sched_domain *sd) \ -{ \ - memset(sd, 0, sizeof(*sd)); \ - *sd = SD_##type##_INIT; \ - sd->level = SD_LV_##type; \ - SD_INIT_NAME(sd, type); \ -} - -SD_INIT_FUNC(CPU) -#ifdef CONFIG_NUMA - SD_INIT_FUNC(ALLNODES) - SD_INIT_FUNC(NODE) -#endif -#ifdef CONFIG_SCHED_SMT - SD_INIT_FUNC(SIBLING) -#endif -#ifdef CONFIG_SCHED_MC - SD_INIT_FUNC(MC) -#endif - -static int default_relax_domain_level = -1; - -static int __init setup_relax_domain_level(char *str) -{ - unsigned long val; - - val = simple_strtoul(str, NULL, 0); - if (val < SD_LV_MAX) - default_relax_domain_level = val; - - return 1; -} -__setup("relax_domain_level=", setup_relax_domain_level); - -static void set_domain_attribute(struct sched_domain *sd, - struct sched_domain_attr *attr) -{ - int request; - - if (!attr || attr->relax_domain_level < 0) { - if (default_relax_domain_level < 0) - return; - else - request = default_relax_domain_level; - } else - request = attr->relax_domain_level; - if (request < sd->level) { - /* turn off idle balance on this domain */ - sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE); - } else { - /* turn on idle balance on this domain */ - sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE); - } -} - -/* - * Build sched domains for a given set of cpus and attach the sched domains - * to the individual cpus - */ -static int __build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) -{ - int i, err = -ENOMEM; - struct root_domain *rd; - cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered, - tmpmask; -#ifdef CONFIG_NUMA - cpumask_var_t domainspan, covered, notcovered; - struct sched_group **sched_group_nodes = NULL; - int sd_allnodes = 0; - - if (!alloc_cpumask_var(&domainspan, GFP_KERNEL)) - goto out; - if (!alloc_cpumask_var(&covered, GFP_KERNEL)) - goto free_domainspan; - if (!alloc_cpumask_var(¬covered, GFP_KERNEL)) - goto free_covered; -#endif - - if (!alloc_cpumask_var(&nodemask, GFP_KERNEL)) - goto free_notcovered; - if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL)) - goto free_nodemask; - if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL)) - goto free_this_sibling_map; - if (!alloc_cpumask_var(&send_covered, GFP_KERNEL)) - goto free_this_core_map; - if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - goto free_send_covered; - -#ifdef CONFIG_NUMA - /* - * Allocate the per-node list of sched groups - */ - sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *), - GFP_KERNEL); - if (!sched_group_nodes) { - printk(KERN_WARNING "Can not alloc sched group node list\n"); - goto free_tmpmask; - } -#endif - - rd = alloc_rootdomain(); - if (!rd) { - printk(KERN_WARNING "Cannot alloc root domain\n"); - goto free_sched_groups; - } - -#ifdef CONFIG_NUMA - sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes; -#endif - - /* - * Set up domains for cpus specified by the cpu_map. - */ - for_each_cpu(i, cpu_map) { - struct sched_domain *sd = NULL, *p; - - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); - -#ifdef CONFIG_NUMA - if (cpumask_weight(cpu_map) > - SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) { - sd = &per_cpu(allnodes_domains, i).sd; - SD_INIT(sd, ALLNODES); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), cpu_map); - cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); - p = sd; - sd_allnodes = 1; - } else - p = NULL; - - sd = &per_cpu(node_domains, i).sd; - SD_INIT(sd, NODE); - set_domain_attribute(sd, attr); - sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); - sd->parent = p; - if (p) - p->child = sd; - cpumask_and(sched_domain_span(sd), - sched_domain_span(sd), cpu_map); -#endif - - p = sd; - sd = &per_cpu(phys_domains, i).sd; - SD_INIT(sd, CPU); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), nodemask); - sd->parent = p; - if (p) - p->child = sd; - cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask); - -#ifdef CONFIG_SCHED_MC - p = sd; - sd = &per_cpu(core_domains, i).sd; - SD_INIT(sd, MC); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), cpu_map, - cpu_coregroup_mask(i)); - sd->parent = p; - p->child = sd; - cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask); -#endif - -#ifdef CONFIG_SCHED_SMT - p = sd; - sd = &per_cpu(cpu_domains, i).sd; - SD_INIT(sd, SIBLING); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), - topology_thread_cpumask(i), cpu_map); - sd->parent = p; - p->child = sd; - cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); -#endif - } - -#ifdef CONFIG_SCHED_SMT - /* Set up CPU (sibling) groups */ - for_each_cpu(i, cpu_map) { - cpumask_and(this_sibling_map, - topology_thread_cpumask(i), cpu_map); - if (i != cpumask_first(this_sibling_map)) - continue; - - init_sched_build_groups(this_sibling_map, cpu_map, - &cpu_to_cpu_group, - send_covered, tmpmask); - } -#endif - -#ifdef CONFIG_SCHED_MC - /* Set up multi-core groups */ - for_each_cpu(i, cpu_map) { - cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map); - if (i != cpumask_first(this_core_map)) - continue; - - init_sched_build_groups(this_core_map, cpu_map, - &cpu_to_core_group, - send_covered, tmpmask); - } -#endif - - /* Set up physical groups */ - for (i = 0; i < nr_node_ids; i++) { - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) - continue; - - init_sched_build_groups(nodemask, cpu_map, - &cpu_to_phys_group, - send_covered, tmpmask); - } - -#ifdef CONFIG_NUMA - /* Set up node groups */ - if (sd_allnodes) { - init_sched_build_groups(cpu_map, cpu_map, - &cpu_to_allnodes_group, - send_covered, tmpmask); - } - - for (i = 0; i < nr_node_ids; i++) { - /* Set up node groups */ - struct sched_group *sg, *prev; - int j; - - cpumask_clear(covered); - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) { - sched_group_nodes[i] = NULL; - continue; - } - - sched_domain_node_span(i, domainspan); - cpumask_and(domainspan, domainspan, cpu_map); - - sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, i); - if (!sg) { - printk(KERN_WARNING "Can not alloc domain group for " - "node %d\n", i); - goto error; - } - sched_group_nodes[i] = sg; - for_each_cpu(j, nodemask) { - struct sched_domain *sd; - - sd = &per_cpu(node_domains, j).sd; - sd->groups = sg; - } - sg->__cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), nodemask); - sg->next = sg; - cpumask_or(covered, covered, nodemask); - prev = sg; - - for (j = 0; j < nr_node_ids; j++) { - int n = (i + j) % nr_node_ids; - - cpumask_complement(notcovered, covered); - cpumask_and(tmpmask, notcovered, cpu_map); - cpumask_and(tmpmask, tmpmask, domainspan); - if (cpumask_empty(tmpmask)) - break; - - cpumask_and(tmpmask, tmpmask, cpumask_of_node(n)); - if (cpumask_empty(tmpmask)) - continue; - - sg = kmalloc_node(sizeof(struct sched_group) + - cpumask_size(), - GFP_KERNEL, i); - if (!sg) { - printk(KERN_WARNING - "Can not alloc domain group for node %d\n", j); - goto error; - } - sg->__cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), tmpmask); - sg->next = prev->next; - cpumask_or(covered, covered, tmpmask); - prev->next = sg; - prev = sg; - } - } -#endif - - /* Calculate CPU power for physical packages and nodes */ -#ifdef CONFIG_SCHED_SMT - for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(cpu_domains, i).sd; - - init_sched_groups_power(i, sd); - } -#endif -#ifdef CONFIG_SCHED_MC - for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(core_domains, i).sd; - - init_sched_groups_power(i, sd); - } -#endif - - for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(phys_domains, i).sd; - - init_sched_groups_power(i, sd); - } - -#ifdef CONFIG_NUMA - for (i = 0; i < nr_node_ids; i++) - init_numa_sched_groups_power(sched_group_nodes[i]); - - if (sd_allnodes) { - struct sched_group *sg; - - cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, - tmpmask); - init_numa_sched_groups_power(sg); - } -#endif - - /* Attach the domains */ - for_each_cpu(i, cpu_map) { - struct sched_domain *sd; -#ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i).sd; -#elif defined(CONFIG_SCHED_MC) - sd = &per_cpu(core_domains, i).sd; -#else - sd = &per_cpu(phys_domains, i).sd; -#endif - cpu_attach_domain(sd, rd, i); - } - - err = 0; - -free_tmpmask: - free_cpumask_var(tmpmask); -free_send_covered: - free_cpumask_var(send_covered); -free_this_core_map: - free_cpumask_var(this_core_map); -free_this_sibling_map: - free_cpumask_var(this_sibling_map); -free_nodemask: - free_cpumask_var(nodemask); -free_notcovered: -#ifdef CONFIG_NUMA - free_cpumask_var(notcovered); -free_covered: - free_cpumask_var(covered); -free_domainspan: - free_cpumask_var(domainspan); -out: -#endif - return err; - -free_sched_groups: -#ifdef CONFIG_NUMA - kfree(sched_group_nodes); -#endif - goto free_tmpmask; - -#ifdef CONFIG_NUMA -error: - free_sched_groups(cpu_map, tmpmask); - free_rootdomain(rd); - goto free_tmpmask; -#endif -} - -static int build_sched_domains(const struct cpumask *cpu_map) -{ - return __build_sched_domains(cpu_map, NULL); -} - -static struct cpumask *doms_cur; /* current sched domains */ -static int ndoms_cur; /* number of sched domains in 'doms_cur' */ -static struct sched_domain_attr *dattr_cur; - /* attribues of custom domains in 'doms_cur' */ - -/* - * Special case: If a kmalloc of a doms_cur partition (array of - * cpumask) fails, then fallback to a single sched domain, - * as determined by the single cpumask fallback_doms. - */ -static cpumask_var_t fallback_doms; - -/* - * arch_update_cpu_topology lets virtualized architectures update the - * cpu core maps. It is supposed to return 1 if the topology changed - * or 0 if it stayed the same. - */ -int __attribute__((weak)) arch_update_cpu_topology(void) -{ - return 0; -} - -/* - * 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 struct cpumask *cpu_map) -{ - int err; - - arch_update_cpu_topology(); - ndoms_cur = 1; - doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); - if (!doms_cur) - doms_cur = fallback_doms; - cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); - dattr_cur = NULL; - err = build_sched_domains(doms_cur); - register_sched_domain_sysctl(); - - return err; -} - -static void arch_destroy_sched_domains(const struct cpumask *cpu_map, - struct cpumask *tmpmask) -{ - free_sched_groups(cpu_map, tmpmask); -} - -/* - * Detach sched domains from a group of cpus specified in cpu_map - * These cpus will now be attached to the NULL domain - */ -static void detach_destroy_domains(const struct cpumask *cpu_map) -{ - /* Save because hotplug lock held. */ - static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); - int i; - - for_each_cpu(i, cpu_map) - cpu_attach_domain(NULL, &def_root_domain, i); - synchronize_sched(); - arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); -} - -/* handle null as "default" */ -static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, - struct sched_domain_attr *new, int idx_new) -{ - struct sched_domain_attr tmp; - - /* fast path */ - if (!new && !cur) - return 1; - - tmp = SD_ATTR_INIT; - return !memcmp(cur ? (cur + idx_cur) : &tmp, - new ? (new + idx_new) : &tmp, - sizeof(struct sched_domain_attr)); -} - -/* - * 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'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 && - * ndoms_new == 1, and partition_sched_domains() will fallback to - * the single partition 'fallback_doms', it also forces the domains - * to be rebuilt. - * - * If doms_new == NULL it will be replaced with cpu_online_mask. - * ndoms_new == 0 is a special case for destroying existing domains, - * and it will not create the default domain. - * - * Call with hotplug lock held - */ -/* FIXME: Change to struct cpumask *doms_new[] */ -void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, - struct sched_domain_attr *dattr_new) -{ - int i, j, n; - int new_topology; - - mutex_lock(&sched_domains_mutex); - - /* always unregister in case we don't destroy any domains */ - unregister_sched_domain_sysctl(); - - /* Let architecture update cpu core mappings. */ - new_topology = arch_update_cpu_topology(); - - n = doms_new ? ndoms_new : 0; - - /* Destroy deleted domains */ - for (i = 0; i < ndoms_cur; i++) { - for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(&doms_cur[i], &doms_new[j]) - && dattrs_equal(dattr_cur, i, dattr_new, j)) - goto match1; - } - /* no match - a current sched domain not in new doms_new[] */ - detach_destroy_domains(doms_cur + i); -match1: - ; - } - - if (doms_new == NULL) { - ndoms_cur = 0; - doms_new = fallback_doms; - cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); - WARN_ON_ONCE(dattr_new); - } - - /* Build new domains */ - for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < ndoms_cur && !new_topology; j++) { - if (cpumask_equal(&doms_new[i], &doms_cur[j]) - && dattrs_equal(dattr_new, i, dattr_cur, j)) - goto match2; - } - /* no match - add a new doms_new */ - __build_sched_domains(doms_new + i, - dattr_new ? dattr_new + i : NULL); -match2: - ; - } - - /* Remember the new sched domains */ - if (doms_cur != fallback_doms) - kfree(doms_cur); - kfree(dattr_cur); /* kfree(NULL) is safe */ - doms_cur = doms_new; - dattr_cur = dattr_new; - ndoms_cur = ndoms_new; - - register_sched_domain_sysctl(); - - mutex_unlock(&sched_domains_mutex); -} - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void arch_reinit_sched_domains(void) -{ - get_online_cpus(); - - /* Destroy domains first to force the rebuild */ - partition_sched_domains(0, NULL, NULL); - - rebuild_sched_domains(); - put_online_cpus(); -} - -static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -{ - unsigned int level = 0; - - if (sscanf(buf, "%u", &level) != 1) - return -EINVAL; - - /* - * level is always be positive so don't check for - * level < POWERSAVINGS_BALANCE_NONE which is 0 - * What happens on 0 or 1 byte write, - * need to check for count as well? - */ - - if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) - return -EINVAL; - - if (smt) - sched_smt_power_savings = level; - else - sched_mc_power_savings = level; - - arch_reinit_sched_domains(); - - return count; -} - -#ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, - char *page) -{ - return sprintf(page, "%u\n", sched_mc_power_savings); -} -static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 0); -} -static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); -#endif - -#ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, - char *page) -{ - return sprintf(page, "%u\n", sched_smt_power_savings); -} -static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 1); -} -static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, - sched_smt_power_savings_show, - sched_smt_power_savings_store); -#endif - -int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) -{ - int err = 0; - -#ifdef CONFIG_SCHED_SMT - if (smt_capable()) - err = sysfs_create_file(&cls->kset.kobj, - &attr_sched_smt_power_savings.attr); -#endif -#ifdef CONFIG_SCHED_MC - if (!err && mc_capable()) - err = sysfs_create_file(&cls->kset.kobj, - &attr_sched_mc_power_savings.attr); -#endif - return err; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - -#ifndef CONFIG_CPUSETS -/* - * Add online and remove offline CPUs from the scheduler domains. - * When cpusets are enabled they take over this function. - */ -static int update_sched_domains(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - partition_sched_domains(1, NULL, NULL); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} -#endif - -static int update_runtime(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (int)(long)hcpu; - - switch (action) { - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - disable_runtime(cpu_rq(cpu)); - return NOTIFY_OK; - - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - enable_runtime(cpu_rq(cpu)); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} - -void __init sched_init_smp(void) -{ - cpumask_var_t non_isolated_cpus; - - alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); - -#if defined(CONFIG_NUMA) - sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), - GFP_KERNEL); - BUG_ON(sched_group_nodes_bycpu == NULL); -#endif - get_online_cpus(); - mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(cpu_online_mask); - cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); - if (cpumask_empty(non_isolated_cpus)) - cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); - mutex_unlock(&sched_domains_mutex); - put_online_cpus(); - -#ifndef CONFIG_CPUSETS - /* XXX: Theoretical race here - CPU may be hotplugged now */ - hotcpu_notifier(update_sched_domains, 0); -#endif - - /* RT runtime code needs to handle some hotplug events */ - hotcpu_notifier(update_runtime, 0); - - init_hrtick(); - - /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) - BUG(); - sched_init_granularity(); - free_cpumask_var(non_isolated_cpus); - - alloc_cpumask_var(&fallback_doms, GFP_KERNEL); - init_sched_rt_class(); -} -#else -void __init sched_init_smp(void) -{ - sched_init_granularity(); -} -#endif /* CONFIG_SMP */ - -int in_sched_functions(unsigned long addr) -{ - return in_lock_functions(addr) || - (addr >= (unsigned long)__sched_text_start - && addr < (unsigned long)__sched_text_end); -} - -static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) -{ - cfs_rq->tasks_timeline = RB_ROOT; - INIT_LIST_HEAD(&cfs_rq->tasks); -#ifdef CONFIG_FAIR_GROUP_SCHED - cfs_rq->rq = rq; -#endif - 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_RT_GROUP_SCHED - rt_rq->highest_prio.curr = MAX_RT_PRIO; -#ifdef CONFIG_SMP - rt_rq->highest_prio.next = MAX_RT_PRIO; -#endif -#endif -#ifdef CONFIG_SMP - rt_rq->rt_nr_migratory = 0; - rt_rq->overloaded = 0; - plist_head_init(&rq->rt.pushable_tasks, &rq->lock); -#endif - - rt_rq->rt_time = 0; - rt_rq->rt_throttled = 0; - rt_rq->rt_runtime = 0; - spin_lock_init(&rt_rq->rt_runtime_lock); - -#ifdef CONFIG_RT_GROUP_SCHED - rt_rq->rt_nr_boosted = 0; - rt_rq->rq = rq; -#endif -} - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, - struct sched_entity *se, int cpu, int add, - struct sched_entity *parent) -{ - struct rq *rq = cpu_rq(cpu); - 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 could be NULL for init_task_group */ - if (!se) - return; - - if (!parent) - se->cfs_rq = &rq->cfs; - else - se->cfs_rq = parent->my_q; - - se->my_q = cfs_rq; - se->load.weight = tg->shares; - se->load.inv_weight = 0; - se->parent = parent; -} -#endif - -#ifdef CONFIG_RT_GROUP_SCHED -static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, - struct sched_rt_entity *rt_se, int cpu, int add, - struct sched_rt_entity *parent) -{ - struct rq *rq = cpu_rq(cpu); - - tg->rt_rq[cpu] = rt_rq; - init_rt_rq(rt_rq, rq); - rt_rq->tg = tg; - rt_rq->rt_se = rt_se; - rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; - if (add) - list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list); - - tg->rt_se[cpu] = rt_se; - if (!rt_se) - return; - - if (!parent) - rt_se->rt_rq = &rq->rt; - else - rt_se->rt_rq = parent->my_q; - - rt_se->my_q = rt_rq; - rt_se->parent = parent; - INIT_LIST_HEAD(&rt_se->run_list); -} -#endif - -void __init sched_init(void) -{ - int i, j; - unsigned long alloc_size = 0, ptr; - -#ifdef CONFIG_FAIR_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); -#endif -#ifdef CONFIG_RT_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); -#endif -#ifdef CONFIG_USER_SCHED - alloc_size *= 2; -#endif -#ifdef CONFIG_CPUMASK_OFFSTACK - alloc_size += num_possible_cpus() * cpumask_size(); -#endif - /* - * As sched_init() is called before page_alloc is setup, - * we use alloc_bootmem(). - */ - if (alloc_size) { - ptr = (unsigned long)alloc_bootmem(alloc_size); - -#ifdef CONFIG_FAIR_GROUP_SCHED - init_task_group.se = (struct sched_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - init_task_group.cfs_rq = (struct cfs_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - -#ifdef CONFIG_USER_SCHED - root_task_group.se = (struct sched_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - root_task_group.cfs_rq = (struct cfs_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_FAIR_GROUP_SCHED */ -#ifdef CONFIG_RT_GROUP_SCHED - init_task_group.rt_se = (struct sched_rt_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - init_task_group.rt_rq = (struct rt_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - -#ifdef CONFIG_USER_SCHED - root_task_group.rt_se = (struct sched_rt_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - root_task_group.rt_rq = (struct rt_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_CPUMASK_OFFSTACK - for_each_possible_cpu(i) { - per_cpu(load_balance_tmpmask, i) = (void *)ptr; - ptr += cpumask_size(); - } -#endif /* CONFIG_CPUMASK_OFFSTACK */ - } - -#ifdef CONFIG_SMP - init_defrootdomain(); -#endif - - init_rt_bandwidth(&def_rt_bandwidth, - global_rt_period(), global_rt_runtime()); - -#ifdef CONFIG_RT_GROUP_SCHED - init_rt_bandwidth(&init_task_group.rt_bandwidth, - global_rt_period(), global_rt_runtime()); -#ifdef CONFIG_USER_SCHED - init_rt_bandwidth(&root_task_group.rt_bandwidth, - global_rt_period(), RUNTIME_INF); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_GROUP_SCHED - list_add(&init_task_group.list, &task_groups); - INIT_LIST_HEAD(&init_task_group.children); - -#ifdef CONFIG_USER_SCHED - INIT_LIST_HEAD(&root_task_group.children); - init_task_group.parent = &root_task_group; - list_add(&init_task_group.siblings, &root_task_group.children); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_GROUP_SCHED */ - - for_each_possible_cpu(i) { - struct rq *rq; - - rq = cpu_rq(i); - spin_lock_init(&rq->lock); - rq->nr_running = 0; - init_cfs_rq(&rq->cfs, rq); - init_rt_rq(&rq->rt, rq); -#ifdef CONFIG_FAIR_GROUP_SCHED - init_task_group.shares = init_task_group_load; - INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); -#ifdef CONFIG_CGROUP_SCHED - /* - * How much cpu bandwidth does init_task_group get? - * - * In case of task-groups formed thr' the cgroup filesystem, it - * gets 100% of the cpu resources in the system. This overall - * system cpu resource is divided among the tasks of - * init_task_group and its child task-groups in a fair manner, - * based on each entity's (task or task-group's) weight - * (se->load.weight). - * - * In other words, if init_task_group has 10 tasks of weight - * 1024) and two child groups A0 and A1 (of weight 1024 each), - * then A0's share of the cpu resource is: - * - * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% - * - * We achieve this by letting init_task_group's tasks sit - * directly in rq->cfs (i.e init_task_group->se[] = NULL). - */ - init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - root_task_group.shares = NICE_0_LOAD; - init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL); - /* - * In case of task-groups formed thr' the user id of tasks, - * init_task_group represents tasks belonging to root user. - * Hence it forms a sibling of all subsequent groups formed. - * In this case, init_task_group gets only a fraction of overall - * system cpu resource, based on the weight assigned to root - * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished - * by letting tasks of init_task_group sit in a separate cfs_rq - * (init_cfs_rq) and having one entity represent this group of - * tasks in rq->cfs (i.e init_task_group->se[] != NULL). - */ - init_tg_cfs_entry(&init_task_group, - &per_cpu(init_cfs_rq, i), - &per_cpu(init_sched_entity, i), i, 1, - root_task_group.se[i]); - -#endif -#endif /* CONFIG_FAIR_GROUP_SCHED */ - - rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; -#ifdef CONFIG_RT_GROUP_SCHED - INIT_LIST_HEAD(&rq->leaf_rt_rq_list); -#ifdef CONFIG_CGROUP_SCHED - init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL); - init_tg_rt_entry(&init_task_group, - &per_cpu(init_rt_rq, i), - &per_cpu(init_sched_rt_entity, i), i, 1, - root_task_group.rt_se[i]); -#endif -#endif - - 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->online = 0; - 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); - } - - set_load_weight(&init_task); - -#ifdef CONFIG_PREEMPT_NOTIFIERS - INIT_HLIST_HEAD(&init_task.preempt_notifiers); -#endif - -#ifdef CONFIG_SMP - open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); -#endif - -#ifdef CONFIG_RT_MUTEXES - plist_head_init(&init_task.pi_waiters, &init_task.pi_lock); -#endif - - /* - * The boot idle thread does lazy MMU switching as well: - */ - atomic_inc(&init_mm.mm_count); - enter_lazy_tlb(&init_mm, current); - - /* - * Make us the idle thread. Technically, schedule() should not be - * called from this thread, however somewhere below it might be, - * but because we are the idle thread, we just pick up running again - * when this runqueue becomes "idle". - */ - init_idle(current, smp_processor_id()); - /* - * During early bootup we pretend to be a normal task: - */ - current->sched_class = &fair_sched_class; - - /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - alloc_bootmem_cpumask_var(&nohz_cpu_mask); -#ifdef CONFIG_SMP -#ifdef CONFIG_NO_HZ - alloc_bootmem_cpumask_var(&nohz.cpu_mask); -#endif - alloc_bootmem_cpumask_var(&cpu_isolated_map); -#endif /* SMP */ - - scheduler_running = 1; -} - -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP -void __might_sleep(char *file, int line) -{ -#ifdef in_atomic - static unsigned long prev_jiffy; /* ratelimiting */ - - if ((!in_atomic() && !irqs_disabled()) || - system_state != SYSTEM_RUNNING || oops_in_progress) - return; - if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) - return; - prev_jiffy = jiffies; - - printk(KERN_ERR - "BUG: sleeping function called from invalid context at %s:%d\n", - file, line); - printk(KERN_ERR - "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", - in_atomic(), irqs_disabled(), - current->pid, current->comm); - - debug_show_held_locks(current); - if (irqs_disabled()) - print_irqtrace_events(current); - dump_stack(); -#endif -} -EXPORT_SYMBOL(__might_sleep); -#endif - -#ifdef CONFIG_MAGIC_SYSRQ -static void normalize_task(struct rq *rq, struct task_struct *p) -{ - int on_rq; - - update_rq_clock(rq); - on_rq = p->se.on_rq; - if (on_rq) - deactivate_task(rq, p, 0); - __setscheduler(rq, p, SCHED_NORMAL, 0); - if (on_rq) { - activate_task(rq, p, 0); - resched_task(rq->curr); - } -} - -void normalize_rt_tasks(void) -{ - struct task_struct *g, *p; - unsigned long flags; - struct rq *rq; - - read_lock_irqsave(&tasklist_lock, flags); - do_each_thread(g, p) { - /* - * Only normalize user tasks: - */ - if (!p->mm) - continue; - - p->se.exec_start = 0; -#ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; -#endif - - if (!rt_task(p)) { - /* - * Renice negative nice level userspace - * tasks back to 0: - */ - if (TASK_NICE(p) < 0 && p->mm) - set_user_nice(p, 0); - continue; - } - - spin_lock(&p->pi_lock); - rq = __task_rq_lock(p); - - normalize_task(rq, p); - - __task_rq_unlock(rq); - spin_unlock(&p->pi_lock); - } while_each_thread(g, p); - - read_unlock_irqrestore(&tasklist_lock, flags); -} - -#endif /* CONFIG_MAGIC_SYSRQ */ - -#ifdef CONFIG_IA64 -/* - * These functions are only useful for the IA64 MCA handling. - * - * They can only be called when the whole system has been - * stopped - every CPU needs to be quiescent, and no scheduling - * activity can take place. Using them for anything else would - * be a serious bug, and as a result, they aren't even visible - * under any other configuration. - */ - -/** - * curr_task - return the current task for a given cpu. - * @cpu: the processor in question. - * - * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! - */ -struct task_struct *curr_task(int cpu) -{ - return cpu_curr(cpu); -} - -/** - * set_curr_task - set the current task for a given cpu. - * @cpu: the processor in question. - * @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 - * 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 - * re-starting the system. - * - * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! - */ -void set_curr_task(int cpu, struct task_struct *p) -{ - cpu_curr(cpu) = p; -} - -#endif - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void free_fair_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]); - } - - kfree(tg->cfs_rq); - kfree(tg->se); -} - -static -int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) -{ - struct cfs_rq *cfs_rq; - struct sched_entity *se; - struct rq *rq; - int i; - - tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); - if (!tg->cfs_rq) - goto err; - tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); - if (!tg->se) - goto err; - - tg->shares = NICE_0_LOAD; - - for_each_possible_cpu(i) { - rq = cpu_rq(i); - - cfs_rq = kzalloc_node(sizeof(struct cfs_rq), - GFP_KERNEL, cpu_to_node(i)); - if (!cfs_rq) - goto err; - - se = kzalloc_node(sizeof(struct sched_entity), - GFP_KERNEL, cpu_to_node(i)); - if (!se) - goto err; - - init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]); - } - - return 1; - - err: - return 0; -} - -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list, - &cpu_rq(cpu)->leaf_cfs_rq_list); -} - -static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) -{ - list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list); -} -#else /* !CONFG_FAIR_GROUP_SCHED */ -static inline void free_fair_sched_group(struct task_group *tg) -{ -} - -static inline -int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) -{ - return 1; -} - -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ -} - -static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) -{ -} -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static void free_rt_sched_group(struct task_group *tg) -{ - int i; - - destroy_rt_bandwidth(&tg->rt_bandwidth); - - for_each_possible_cpu(i) { - if (tg->rt_rq) - kfree(tg->rt_rq[i]); - if (tg->rt_se) - kfree(tg->rt_se[i]); - } - - kfree(tg->rt_rq); - kfree(tg->rt_se); -} - -static -int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) -{ - struct rt_rq *rt_rq; - struct sched_rt_entity *rt_se; - struct rq *rq; - int i; - - tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); - if (!tg->rt_rq) - goto err; - tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); - if (!tg->rt_se) - goto err; - - init_rt_bandwidth(&tg->rt_bandwidth, - ktime_to_ns(def_rt_bandwidth.rt_period), 0); - - for_each_possible_cpu(i) { - rq = cpu_rq(i); - - rt_rq = kzalloc_node(sizeof(struct rt_rq), - GFP_KERNEL, cpu_to_node(i)); - if (!rt_rq) - goto err; - - rt_se = kzalloc_node(sizeof(struct sched_rt_entity), - GFP_KERNEL, cpu_to_node(i)); - if (!rt_se) - goto err; - - init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]); - } - - return 1; - - err: - return 0; -} - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list, - &cpu_rq(cpu)->leaf_rt_rq_list); -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ - list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list); -} -#else /* !CONFIG_RT_GROUP_SCHED */ -static inline void free_rt_sched_group(struct task_group *tg) -{ -} - -static inline -int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) -{ - return 1; -} - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_GROUP_SCHED -static void free_sched_group(struct task_group *tg) -{ - free_fair_sched_group(tg); - free_rt_sched_group(tg); - kfree(tg); -} - -/* allocate runqueue etc for a new task group */ -struct task_group *sched_create_group(struct task_group *parent) -{ - struct task_group *tg; - unsigned long flags; - int i; - - tg = kzalloc(sizeof(*tg), GFP_KERNEL); - if (!tg) - return ERR_PTR(-ENOMEM); - - if (!alloc_fair_sched_group(tg, parent)) - goto err; - - if (!alloc_rt_sched_group(tg, parent)) - goto err; - - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { - register_fair_sched_group(tg, i); - register_rt_sched_group(tg, i); - } - list_add_rcu(&tg->list, &task_groups); - - WARN_ON(!parent); /* root should already exist */ - - tg->parent = parent; - INIT_LIST_HEAD(&tg->children); - list_add_rcu(&tg->siblings, &parent->children); - spin_unlock_irqrestore(&task_group_lock, flags); - - return tg; - -err: - free_sched_group(tg); - return ERR_PTR(-ENOMEM); -} - -/* rcu callback to free various structures associated with a task group */ -static void free_sched_group_rcu(struct rcu_head *rhp) -{ - /* now it should be safe to free those cfs_rqs */ - 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) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { - unregister_fair_sched_group(tg, i); - unregister_rt_sched_group(tg, i); - } - list_del_rcu(&tg->list); - list_del_rcu(&tg->siblings); - spin_unlock_irqrestore(&task_group_lock, flags); - - /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); -} - -/* change task's runqueue when it moves between groups. - * The caller of this function should have put the task in its new group - * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to - * reflect its new group. - */ -void sched_move_task(struct task_struct *tsk) -{ - int on_rq, running; - unsigned long flags; - struct rq *rq; - - rq = task_rq_lock(tsk, &flags); - - update_rq_clock(rq); - - running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; - - if (on_rq) - dequeue_task(rq, tsk, 0); - if (unlikely(running)) - tsk->sched_class->put_prev_task(rq, tsk); - - set_task_rq(tsk, task_cpu(tsk)); - -#ifdef CONFIG_FAIR_GROUP_SCHED - if (tsk->sched_class->moved_group) - tsk->sched_class->moved_group(tsk); -#endif - - if (unlikely(running)) - tsk->sched_class->set_curr_task(rq); - if (on_rq) - enqueue_task(rq, tsk, 0); - - task_rq_unlock(rq, &flags); -} -#endif /* CONFIG_GROUP_SCHED */ - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void __set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - int on_rq; - - on_rq = se->on_rq; - if (on_rq) - dequeue_entity(cfs_rq, se, 0); - - se->load.weight = shares; - se->load.inv_weight = 0; - - if (on_rq) - enqueue_entity(cfs_rq, se, 0); -} - -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; - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __set_se_shares(se, shares); - spin_unlock_irqrestore(&rq->lock, flags); -} - -static DEFINE_MUTEX(shares_mutex); - -int sched_group_set_shares(struct task_group *tg, unsigned long shares) -{ - int i; - unsigned long flags; - - /* - * We can't change the weight of the root cgroup. - */ - if (!tg->se[0]) - return -EINVAL; - - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; - - mutex_lock(&shares_mutex); - if (tg->shares == shares) - goto done; - - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - unregister_fair_sched_group(tg, i); - list_del_rcu(&tg->siblings); - spin_unlock_irqrestore(&task_group_lock, flags); - - /* 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) { - /* - * force a rebalance - */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); - set_se_shares(tg->se[i], shares); - } - - /* - * Enable load balance activity on this group, by inserting it back on - * each cpu's rq->leaf_cfs_rq_list. - */ - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - register_fair_sched_group(tg, i); - list_add_rcu(&tg->siblings, &tg->parent->children); - spin_unlock_irqrestore(&task_group_lock, flags); -done: - mutex_unlock(&shares_mutex); - return 0; -} - -unsigned long sched_group_shares(struct task_group *tg) -{ - return tg->shares; -} -#endif - -#ifdef CONFIG_RT_GROUP_SCHED -/* - * Ensure that the real time constraints are schedulable. - */ -static DEFINE_MUTEX(rt_constraints_mutex); - -static unsigned long to_ratio(u64 period, u64 runtime) -{ - if (runtime == RUNTIME_INF) - return 1ULL << 20; - - return div64_u64(runtime << 20, period); -} - -/* Must be called with tasklist_lock held */ -static inline int tg_has_rt_tasks(struct task_group *tg) -{ - struct task_struct *g, *p; - - do_each_thread(g, p) { - if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) - return 1; - } while_each_thread(g, p); - - return 0; -} - -struct rt_schedulable_data { - struct task_group *tg; - u64 rt_period; - u64 rt_runtime; -}; - -static int tg_schedulable(struct task_group *tg, void *data) -{ - struct rt_schedulable_data *d = data; - struct task_group *child; - unsigned long total, sum = 0; - u64 period, runtime; - - period = ktime_to_ns(tg->rt_bandwidth.rt_period); - runtime = tg->rt_bandwidth.rt_runtime; - - if (tg == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - -#ifdef CONFIG_USER_SCHED - if (tg == &root_task_group) { - period = global_rt_period(); - runtime = global_rt_runtime(); - } -#endif - - /* - * Cannot have more runtime than the period. - */ - if (runtime > period && runtime != RUNTIME_INF) - return -EINVAL; - - /* - * Ensure we don't starve existing RT tasks. - */ - if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) - return -EBUSY; - - total = to_ratio(period, runtime); - - /* - * Nobody can have more than the global setting allows. - */ - if (total > to_ratio(global_rt_period(), global_rt_runtime())) - return -EINVAL; - - /* - * The sum of our children's runtime should not exceed our own. - */ - list_for_each_entry_rcu(child, &tg->children, siblings) { - period = ktime_to_ns(child->rt_bandwidth.rt_period); - runtime = child->rt_bandwidth.rt_runtime; - - if (child == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - - sum += to_ratio(period, runtime); - } - - if (sum > total) - return -EINVAL; - - return 0; -} - -static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) -{ - struct rt_schedulable_data data = { - .tg = tg, - .rt_period = period, - .rt_runtime = runtime, - }; - - return walk_tg_tree(tg_schedulable, tg_nop, &data); -} - -static int tg_set_bandwidth(struct task_group *tg, - u64 rt_period, u64 rt_runtime) -{ - int i, err = 0; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - err = __rt_schedulable(tg, rt_period, rt_runtime); - if (err) - goto unlock; - - spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); - tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); - tg->rt_bandwidth.rt_runtime = rt_runtime; - - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = tg->rt_rq[i]; - - spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = rt_runtime; - spin_unlock(&rt_rq->rt_runtime_lock); - } - spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); - unlock: - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return err; -} - -int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) -{ - u64 rt_runtime, rt_period; - - rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); - rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; - if (rt_runtime_us < 0) - rt_runtime = RUNTIME_INF; - - return tg_set_bandwidth(tg, rt_period, rt_runtime); -} - -long sched_group_rt_runtime(struct task_group *tg) -{ - u64 rt_runtime_us; - - if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) - return -1; - - rt_runtime_us = tg->rt_bandwidth.rt_runtime; - do_div(rt_runtime_us, NSEC_PER_USEC); - return rt_runtime_us; -} - -int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) -{ - u64 rt_runtime, rt_period; - - rt_period = (u64)rt_period_us * NSEC_PER_USEC; - rt_runtime = tg->rt_bandwidth.rt_runtime; - - if (rt_period == 0) - return -EINVAL; - - return tg_set_bandwidth(tg, rt_period, rt_runtime); -} - -long sched_group_rt_period(struct task_group *tg) -{ - u64 rt_period_us; - - rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); - do_div(rt_period_us, NSEC_PER_USEC); - return rt_period_us; -} - -static int sched_rt_global_constraints(void) -{ - u64 runtime, period; - int ret = 0; - - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - runtime = global_rt_runtime(); - period = global_rt_period(); - - /* - * Sanity check on the sysctl variables. - */ - if (runtime > period && runtime != RUNTIME_INF) - return -EINVAL; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - ret = __rt_schedulable(NULL, 0, 0); - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return ret; -} - -int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) -{ - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) - return 0; - - return 1; -} - -#else /* !CONFIG_RT_GROUP_SCHED */ -static int sched_rt_global_constraints(void) -{ - unsigned long flags; - int i; - - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = &cpu_rq(i)->rt; - - spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = global_rt_runtime(); - spin_unlock(&rt_rq->rt_runtime_lock); - } - spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - - return 0; -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int ret; - int old_period, old_runtime; - static DEFINE_MUTEX(mutex); - - mutex_lock(&mutex); - old_period = sysctl_sched_rt_period; - old_runtime = sysctl_sched_rt_runtime; - - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); - - if (!ret && write) { - ret = sched_rt_global_constraints(); - if (ret) { - sysctl_sched_rt_period = old_period; - sysctl_sched_rt_runtime = old_runtime; - } else { - def_rt_bandwidth.rt_runtime = global_rt_runtime(); - def_rt_bandwidth.rt_period = - ns_to_ktime(global_rt_period()); - } - } - mutex_unlock(&mutex); - - return ret; -} - -#ifdef CONFIG_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, *parent; - - if (!cgrp->parent) { - /* This is early initialization for the top cgroup */ - return &init_task_group.css; - } - - parent = cgroup_tg(cgrp->parent); - tg = sched_create_group(parent); - if (IS_ERR(tg)) - return ERR_PTR(-ENOMEM); - - 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) -{ -#ifdef CONFIG_RT_GROUP_SCHED - if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) - return -EINVAL; -#else - /* We don't support RT-tasks being in separate groups */ - if (tsk->sched_class != &fair_sched_class) - return -EINVAL; -#endif - - 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); -} - -#ifdef CONFIG_FAIR_GROUP_SCHED -static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 shareval) -{ - return sched_group_set_shares(cgroup_tg(cgrp), shareval); -} - -static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) -{ - struct task_group *tg = cgroup_tg(cgrp); - - return (u64) tg->shares; -} -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, - s64 val) -{ - return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); -} - -static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) -{ - return sched_group_rt_runtime(cgroup_tg(cgrp)); -} - -static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, - u64 rt_period_us) -{ - return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); -} - -static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) -{ - return sched_group_rt_period(cgroup_tg(cgrp)); -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -static struct cftype cpu_files[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED - { - .name = "shares", - .read_u64 = cpu_shares_read_u64, - .write_u64 = cpu_shares_write_u64, - }, -#endif -#ifdef CONFIG_RT_GROUP_SCHED - { - .name = "rt_runtime_us", - .read_s64 = cpu_rt_runtime_read, - .write_s64 = cpu_rt_runtime_write, - }, - { - .name = "rt_period_us", - .read_u64 = cpu_rt_period_read_uint, - .write_u64 = cpu_rt_period_write_uint, - }, -#endif -}; - -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_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 and its child groups */ -struct cpuacct { - struct cgroup_subsys_state css; - /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 *cpuusage; - struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; - struct cpuacct *parent; -}; - -struct cgroup_subsys cpuacct_subsys; - -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) -{ - return container_of(cgroup_subsys_state(cgrp, 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 *cgrp) -{ - struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); - int i; - - if (!ca) - goto out; - - ca->cpuusage = alloc_percpu(u64); - if (!ca->cpuusage) - goto out_free_ca; - - for (i = 0; i < CPUACCT_STAT_NSTATS; i++) - if (percpu_counter_init(&ca->cpustat[i], 0)) - goto out_free_counters; - - if (cgrp->parent) - ca->parent = cgroup_ca(cgrp->parent); - - return &ca->css; - -out_free_counters: - while (--i >= 0) - percpu_counter_destroy(&ca->cpustat[i]); - free_percpu(ca->cpuusage); -out_free_ca: - kfree(ca); -out: - return ERR_PTR(-ENOMEM); -} - -/* destroy an existing cpu accounting group */ -static void -cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int i; - - for (i = 0; i < CPUACCT_STAT_NSTATS; i++) - percpu_counter_destroy(&ca->cpustat[i]); - free_percpu(ca->cpuusage); - kfree(ca); -} - -static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - u64 data; - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit read safe on 32-bit platforms. - */ - spin_lock_irq(&cpu_rq(cpu)->lock); - data = *cpuusage; - spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - data = *cpuusage; -#endif - - return data; -} - -static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit write safe on 32-bit platforms. - */ - spin_lock_irq(&cpu_rq(cpu)->lock); - *cpuusage = val; - spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - *cpuusage = val; -#endif -} - -/* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - u64 totalcpuusage = 0; - int i; - - for_each_present_cpu(i) - totalcpuusage += cpuacct_cpuusage_read(ca, i); - - return totalcpuusage; -} - -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int err = 0; - int i; - - if (reset) { - err = -EINVAL; - goto out; - } - - for_each_present_cpu(i) - cpuacct_cpuusage_write(ca, i, 0); - -out: - return err; -} - -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) -{ - struct cpuacct *ca = cgroup_ca(cgroup); - u64 percpu; - int i; - - for_each_present_cpu(i) { - percpu = cpuacct_cpuusage_read(ca, i); - seq_printf(m, "%llu ", (unsigned long long) percpu); - } - seq_printf(m, "\n"); - return 0; -} - -static const char *cpuacct_stat_desc[] = { - [CPUACCT_STAT_USER] = "user", - [CPUACCT_STAT_SYSTEM] = "system", -}; - -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int i; - - for (i = 0; i < CPUACCT_STAT_NSTATS; i++) { - s64 val = percpu_counter_read(&ca->cpustat[i]); - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[i], val); - } - return 0; -} - -static struct cftype files[] = { - { - .name = "usage", - .read_u64 = cpuusage_read, - .write_u64 = cpuusage_write, - }, - { - .name = "usage_percpu", - .read_seq_string = cpuacct_percpu_seq_read, - }, - { - .name = "stat", - .read_map = cpuacct_stats_show, - }, -}; - -static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) -{ - return cgroup_add_files(cgrp, 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; - int cpu; - - if (unlikely(!cpuacct_subsys.active)) - return; - - cpu = task_cpu(tsk); - - rcu_read_lock(); - - ca = task_ca(tsk); - - for (; ca; ca = ca->parent) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - } - - rcu_read_unlock(); -} - -/* - * Charge the system/user time to the task's accounting group. - */ -static void cpuacct_update_stats(struct task_struct *tsk, - enum cpuacct_stat_index idx, cputime_t val) -{ - struct cpuacct *ca; - - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(tsk); - - do { - percpu_counter_add(&ca->cpustat[idx], val); - ca = ca->parent; - } while (ca); - rcu_read_unlock(); -} - -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 */ Index: linux-2.6.30-bfs/kernel/sysctl.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sysctl.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/sysctl.c 2009-08-26 19:38:31.228300798 +1000 @@ -83,6 +83,7 @@ extern int compat_log; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +extern int rr_interval; #ifndef CONFIG_MMU extern int sysctl_nr_trim_pages; #endif @@ -97,10 +98,11 @@ #endif static int zero; -static int __maybe_unused one = 1; static int __maybe_unused two = 2; static unsigned long one_ul = 1; -static int one_hundred = 100; +static int __read_mostly one = 1; +static int __read_mostly one_hundred = 100; +static int __read_mostly five_thousand = 5000; /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; @@ -234,123 +236,7 @@ { .ctl_name = 0 } }; -#ifdef CONFIG_SCHED_DEBUG -static int min_sched_granularity_ns = 100000; /* 100 usecs */ -static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ -static int min_wakeup_granularity_ns; /* 0 usecs */ -static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ -#endif - static struct ctl_table kern_table[] = { -#ifdef CONFIG_SCHED_DEBUG - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_min_granularity_ns", - .data = &sysctl_sched_min_granularity, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &sched_nr_latency_handler, - .strategy = &sysctl_intvec, - .extra1 = &min_sched_granularity_ns, - .extra2 = &max_sched_granularity_ns, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_latency_ns", - .data = &sysctl_sched_latency, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &sched_nr_latency_handler, - .strategy = &sysctl_intvec, - .extra1 = &min_sched_granularity_ns, - .extra2 = &max_sched_granularity_ns, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_wakeup_granularity_ns", - .data = &sysctl_sched_wakeup_granularity, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &min_wakeup_granularity_ns, - .extra2 = &max_wakeup_granularity_ns, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_shares_ratelimit", - .data = &sysctl_sched_shares_ratelimit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_shares_thresh", - .data = &sysctl_sched_shares_thresh, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &zero, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_features", - .data = &sysctl_sched_features, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_migration_cost", - .data = &sysctl_sched_migration_cost, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_nr_migrate", - .data = &sysctl_sched_nr_migrate, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, -#endif - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_rt_period_us", - .data = &sysctl_sched_rt_period, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &sched_rt_handler, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_rt_runtime_us", - .data = &sysctl_sched_rt_runtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &sched_rt_handler, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "sched_compat_yield", - .data = &sysctl_sched_compat_yield, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, #ifdef CONFIG_PROVE_LOCKING { .ctl_name = CTL_UNNUMBERED, @@ -756,6 +642,17 @@ .proc_handler = &proc_dointvec, }, #endif + { + .ctl_name = CTL_UNNUMBERED, + .procname = "rr_interval", + .data = &rr_interval, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &five_thousand, + }, #if defined(CONFIG_S390) && defined(CONFIG_SMP) { .ctl_name = KERN_SPIN_RETRY, Index: linux-2.6.30-bfs/kernel/workqueue.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/workqueue.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/workqueue.c 2009-08-26 19:38:31.241175471 +1000 @@ -320,8 +320,6 @@ if (cwq->wq->freezeable) set_freezable(); - set_user_nice(current, -5); - for (;;) { prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE); if (!freezing(current) && Index: linux-2.6.30-bfs/kernel/sched_fair.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sched_fair.c 2009-06-10 13:05:27.000000000 +1000 +++ /dev/null 1970-01-01 00:00:00.000000000 +0000 @@ -1,1835 +0,0 @@ -/* - * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH) - * - * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar - * - * Interactivity improvements by Mike Galbraith - * (C) 2007 Mike Galbraith - * - * Various enhancements by Dmitry Adamushko. - * (C) 2007 Dmitry Adamushko - * - * Group scheduling enhancements by Srivatsa Vaddagiri - * Copyright IBM Corporation, 2007 - * Author: Srivatsa Vaddagiri - * - * Scaled math optimizations by Thomas Gleixner - * Copyright (C) 2007, Thomas Gleixner - * - * Adaptive scheduling granularity, math enhancements by Peter Zijlstra - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra - */ - -#include - -/* - * Targeted preemption latency for CPU-bound tasks: - * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds) - * - * NOTE: this latency value is not the same as the concept of - * 'timeslice length' - timeslices in CFS are of variable length - * and have no persistent notion like in traditional, time-slice - * based scheduling concepts. - * - * (to see the precise effective timeslice length of your workload, - * run vmstat and monitor the context-switches (cs) field) - */ -unsigned int sysctl_sched_latency = 20000000ULL; - -/* - * Minimal preemption granularity for CPU-bound tasks: - * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds) - */ -unsigned int sysctl_sched_min_granularity = 4000000ULL; - -/* - * is kept at sysctl_sched_latency / sysctl_sched_min_granularity - */ -static unsigned int sched_nr_latency = 5; - -/* - * After fork, child runs first. (default) If set to 0 then - * parent will (try to) run first. - */ -const_debug unsigned int sysctl_sched_child_runs_first = 1; - -/* - * sys_sched_yield() compat mode - * - * This option switches the agressive yield implementation of the - * old scheduler back on. - */ -unsigned int __read_mostly sysctl_sched_compat_yield; - -/* - * SCHED_OTHER wake-up granularity. - * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds) - * - * This option delays the preemption effects of decoupled workloads - * and reduces their over-scheduling. Synchronous workloads will still - * have immediate wakeup/sleep latencies. - */ -unsigned int sysctl_sched_wakeup_granularity = 5000000UL; - -const_debug unsigned int sysctl_sched_migration_cost = 500000UL; - -static const struct sched_class fair_sched_class; - -/************************************************************** - * CFS operations on generic schedulable entities: - */ - -static inline struct task_struct *task_of(struct sched_entity *se) -{ - return container_of(se, struct task_struct, se); -} - -#ifdef CONFIG_FAIR_GROUP_SCHED - -/* cpu runqueue to which this cfs_rq is attached */ -static inline struct rq *rq_of(struct cfs_rq *cfs_rq) -{ - return cfs_rq->rq; -} - -/* An entity is a task if it doesn't "own" a runqueue */ -#define entity_is_task(se) (!se->my_q) - -/* Walk up scheduling entities hierarchy */ -#define for_each_sched_entity(se) \ - for (; se; se = se->parent) - -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) -{ - return p->se.cfs_rq; -} - -/* runqueue on which this entity is (to be) queued */ -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) -{ - return se->cfs_rq; -} - -/* runqueue "owned" by this group */ -static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) -{ - return grp->my_q; -} - -/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on - * another cpu ('this_cpu') - */ -static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) -{ - return cfs_rq->tg->cfs_rq[this_cpu]; -} - -/* Iterate thr' all leaf cfs_rq's on a runqueue */ -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) - -/* Do the two (enqueued) entities belong to the same group ? */ -static inline int -is_same_group(struct sched_entity *se, struct sched_entity *pse) -{ - if (se->cfs_rq == pse->cfs_rq) - return 1; - - return 0; -} - -static inline struct sched_entity *parent_entity(struct sched_entity *se) -{ - return se->parent; -} - -/* return depth at which a sched entity is present in the hierarchy */ -static inline int depth_se(struct sched_entity *se) -{ - int depth = 0; - - for_each_sched_entity(se) - depth++; - - return depth; -} - -static void -find_matching_se(struct sched_entity **se, struct sched_entity **pse) -{ - int se_depth, pse_depth; - - /* - * preemption test can be made between sibling entities who are in the - * same cfs_rq i.e who have a common parent. Walk up the hierarchy of - * both tasks until we find their ancestors who are siblings of common - * parent. - */ - - /* First walk up until both entities are at same depth */ - se_depth = depth_se(*se); - pse_depth = depth_se(*pse); - - while (se_depth > pse_depth) { - se_depth--; - *se = parent_entity(*se); - } - - while (pse_depth > se_depth) { - pse_depth--; - *pse = parent_entity(*pse); - } - - while (!is_same_group(*se, *pse)) { - *se = parent_entity(*se); - *pse = parent_entity(*pse); - } -} - -#else /* CONFIG_FAIR_GROUP_SCHED */ - -static inline struct rq *rq_of(struct cfs_rq *cfs_rq) -{ - return container_of(cfs_rq, struct rq, cfs); -} - -#define entity_is_task(se) 1 - -#define for_each_sched_entity(se) \ - for (; se; se = NULL) - -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) -{ - return &task_rq(p)->cfs; -} - -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) -{ - struct task_struct *p = task_of(se); - struct rq *rq = task_rq(p); - - return &rq->cfs; -} - -/* runqueue "owned" by this group */ -static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) -{ - return NULL; -} - -static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) -{ - return &cpu_rq(this_cpu)->cfs; -} - -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) - -static inline int -is_same_group(struct sched_entity *se, struct sched_entity *pse) -{ - return 1; -} - -static inline struct sched_entity *parent_entity(struct sched_entity *se) -{ - return NULL; -} - -static inline void -find_matching_se(struct sched_entity **se, struct sched_entity **pse) -{ -} - -#endif /* CONFIG_FAIR_GROUP_SCHED */ - - -/************************************************************** - * Scheduling class tree data structure manipulation methods: - */ - -static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime) -{ - s64 delta = (s64)(vruntime - min_vruntime); - if (delta > 0) - min_vruntime = vruntime; - - return min_vruntime; -} - -static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) -{ - s64 delta = (s64)(vruntime - min_vruntime); - if (delta < 0) - min_vruntime = vruntime; - - return min_vruntime; -} - -static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - return se->vruntime - cfs_rq->min_vruntime; -} - -static void update_min_vruntime(struct cfs_rq *cfs_rq) -{ - u64 vruntime = cfs_rq->min_vruntime; - - if (cfs_rq->curr) - vruntime = cfs_rq->curr->vruntime; - - if (cfs_rq->rb_leftmost) { - struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost, - struct sched_entity, - run_node); - - if (!cfs_rq->curr) - vruntime = se->vruntime; - else - vruntime = min_vruntime(vruntime, se->vruntime); - } - - cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); -} - -/* - * Enqueue an entity into the rb-tree: - */ -static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - struct rb_node **link = &cfs_rq->tasks_timeline.rb_node; - struct rb_node *parent = NULL; - struct sched_entity *entry; - s64 key = entity_key(cfs_rq, se); - int leftmost = 1; - - /* - * Find the right place in the rbtree: - */ - while (*link) { - parent = *link; - entry = rb_entry(parent, struct sched_entity, run_node); - /* - * We dont care about collisions. Nodes with - * the same key stay together. - */ - if (key < entity_key(cfs_rq, entry)) { - link = &parent->rb_left; - } else { - link = &parent->rb_right; - leftmost = 0; - } - } - - /* - * Maintain a cache of leftmost tree entries (it is frequently - * used): - */ - if (leftmost) - cfs_rq->rb_leftmost = &se->run_node; - - rb_link_node(&se->run_node, parent, link); - rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline); -} - -static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (cfs_rq->rb_leftmost == &se->run_node) { - struct rb_node *next_node; - - next_node = rb_next(&se->run_node); - cfs_rq->rb_leftmost = next_node; - } - - rb_erase(&se->run_node, &cfs_rq->tasks_timeline); -} - -static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq) -{ - struct rb_node *left = cfs_rq->rb_leftmost; - - if (!left) - return NULL; - - return rb_entry(left, struct sched_entity, run_node); -} - -static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) -{ - struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); - - if (!last) - return NULL; - - return rb_entry(last, struct sched_entity, run_node); -} - -/************************************************************** - * Scheduling class statistics methods: - */ - -#ifdef CONFIG_SCHED_DEBUG -int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); - - if (ret || !write) - return ret; - - sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, - sysctl_sched_min_granularity); - - return 0; -} -#endif - -/* - * delta /= w - */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) -{ - if (unlikely(se->load.weight != NICE_0_LOAD)) - delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); - - return delta; -} - -/* - * The idea is to set a period in which each task runs once. - * - * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch - * this period because otherwise the slices get too small. - * - * p = (nr <= nl) ? l : l*nr/nl - */ -static u64 __sched_period(unsigned long nr_running) -{ - u64 period = sysctl_sched_latency; - unsigned long nr_latency = sched_nr_latency; - - if (unlikely(nr_running > nr_latency)) { - period = sysctl_sched_min_granularity; - period *= nr_running; - } - - return period; -} - -/* - * We calculate the wall-time slice from the period by taking a part - * proportional to the weight. - * - * s = p*P[w/rw] - */ -static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); - - for_each_sched_entity(se) { - struct load_weight *load; - - cfs_rq = cfs_rq_of(se); - load = &cfs_rq->load; - - if (unlikely(!se->on_rq)) { - struct load_weight lw = cfs_rq->load; - - update_load_add(&lw, se->load.weight); - load = &lw; - } - slice = calc_delta_mine(slice, se->load.weight, load); - } - return slice; -} - -/* - * We calculate the vruntime slice of a to be inserted task - * - * vs = s/w - */ -static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - return calc_delta_fair(sched_slice(cfs_rq, se), se); -} - -/* - * Update the current task's runtime statistics. Skip current tasks that - * are not in our scheduling class. - */ -static inline void -__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, - unsigned long delta_exec) -{ - unsigned long delta_exec_weighted; - - schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max)); - - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); - curr->vruntime += delta_exec_weighted; - update_min_vruntime(cfs_rq); -} - -static void update_curr(struct cfs_rq *cfs_rq) -{ - struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_of(cfs_rq)->clock; - unsigned long delta_exec; - - if (unlikely(!curr)) - return; - - /* - * Get the amount of time the current task was running - * since the last time we changed load (this cannot - * overflow on 32 bits): - */ - delta_exec = (unsigned long)(now - curr->exec_start); - if (!delta_exec) - return; - - __update_curr(cfs_rq, curr, delta_exec); - curr->exec_start = now; - - if (entity_is_task(curr)) { - struct task_struct *curtask = task_of(curr); - - cpuacct_charge(curtask, delta_exec); - account_group_exec_runtime(curtask, delta_exec); - } -} - -static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - schedstat_set(se->wait_start, rq_of(cfs_rq)->clock); -} - -/* - * Task is being enqueued - update stats: - */ -static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - /* - * Are we enqueueing a waiting task? (for current tasks - * a dequeue/enqueue event is a NOP) - */ - if (se != cfs_rq->curr) - update_stats_wait_start(cfs_rq, se); -} - -static void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - schedstat_set(se->wait_max, max(se->wait_max, - rq_of(cfs_rq)->clock - se->wait_start)); - schedstat_set(se->wait_count, se->wait_count + 1); - schedstat_set(se->wait_sum, se->wait_sum + - rq_of(cfs_rq)->clock - se->wait_start); - schedstat_set(se->wait_start, 0); -} - -static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - /* - * Mark the end of the wait period if dequeueing a - * waiting task: - */ - if (se != cfs_rq->curr) - update_stats_wait_end(cfs_rq, se); -} - -/* - * We are picking a new current task - update its stats: - */ -static inline void -update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - /* - * We are starting a new run period: - */ - se->exec_start = rq_of(cfs_rq)->clock; -} - -/************************************************** - * Scheduling class queueing methods: - */ - -#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ - cfs_rq->task_weight += weight; -} -#else -static inline void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ -} -#endif - -static void -account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - update_load_add(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - inc_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, se->load.weight); - list_add(&se->group_node, &cfs_rq->tasks); - } - cfs_rq->nr_running++; - se->on_rq = 1; -} - -static void -account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - update_load_sub(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - dec_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, -se->load.weight); - list_del_init(&se->group_node); - } - cfs_rq->nr_running--; - se->on_rq = 0; -} - -static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -#ifdef CONFIG_SCHEDSTATS - if (se->sleep_start) { - u64 delta = rq_of(cfs_rq)->clock - se->sleep_start; - struct task_struct *tsk = task_of(se); - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > se->sleep_max)) - se->sleep_max = delta; - - se->sleep_start = 0; - se->sum_sleep_runtime += delta; - - account_scheduler_latency(tsk, delta >> 10, 1); - } - if (se->block_start) { - u64 delta = rq_of(cfs_rq)->clock - se->block_start; - struct task_struct *tsk = task_of(se); - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > se->block_max)) - se->block_max = delta; - - se->block_start = 0; - se->sum_sleep_runtime += delta; - - /* - * Blocking time is in units of nanosecs, so shift by 20 to - * get a milliseconds-range estimation of the amount of - * time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - - profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk), - delta >> 20); - } - account_scheduler_latency(tsk, delta >> 10, 0); - } -#endif -} - -static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -#ifdef CONFIG_SCHED_DEBUG - s64 d = se->vruntime - cfs_rq->min_vruntime; - - if (d < 0) - d = -d; - - if (d > 3*sysctl_sched_latency) - schedstat_inc(cfs_rq, nr_spread_over); -#endif -} - -static void -place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) -{ - u64 vruntime = cfs_rq->min_vruntime; - - /* - * The 'current' period is already promised to the current tasks, - * however the extra weight of the new task will slow them down a - * little, place the new task so that it fits in the slot that - * stays open at the end. - */ - if (initial && sched_feat(START_DEBIT)) - vruntime += sched_vslice(cfs_rq, se); - - if (!initial) { - /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS)) { - unsigned long thresh = sysctl_sched_latency; - - /* - * Convert the sleeper threshold into virtual time. - * SCHED_IDLE is a special sub-class. We care about - * fairness only relative to other SCHED_IDLE tasks, - * all of which have the same weight. - */ - if (sched_feat(NORMALIZED_SLEEPER) && - task_of(se)->policy != SCHED_IDLE) - thresh = calc_delta_fair(thresh, se); - - vruntime -= thresh; - } - - /* ensure we never gain time by being placed backwards. */ - vruntime = max_vruntime(se->vruntime, vruntime); - } - - se->vruntime = vruntime; -} - -static void -enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) -{ - /* - * Update run-time statistics of the 'current'. - */ - update_curr(cfs_rq); - account_entity_enqueue(cfs_rq, se); - - if (wakeup) { - place_entity(cfs_rq, se, 0); - enqueue_sleeper(cfs_rq, se); - } - - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); - if (se != cfs_rq->curr) - __enqueue_entity(cfs_rq, se); -} - -static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (cfs_rq->last == se) - cfs_rq->last = NULL; - - if (cfs_rq->next == se) - cfs_rq->next = NULL; -} - -static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - for_each_sched_entity(se) - __clear_buddies(cfs_rq_of(se), se); -} - -static void -dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) -{ - /* - * Update run-time statistics of the 'current'. - */ - update_curr(cfs_rq); - - update_stats_dequeue(cfs_rq, se); - if (sleep) { -#ifdef CONFIG_SCHEDSTATS - if (entity_is_task(se)) { - struct task_struct *tsk = task_of(se); - - if (tsk->state & TASK_INTERRUPTIBLE) - se->sleep_start = rq_of(cfs_rq)->clock; - if (tsk->state & TASK_UNINTERRUPTIBLE) - se->block_start = rq_of(cfs_rq)->clock; - } -#endif - } - - clear_buddies(cfs_rq, se); - - if (se != cfs_rq->curr) - __dequeue_entity(cfs_rq, se); - account_entity_dequeue(cfs_rq, se); - update_min_vruntime(cfs_rq); -} - -/* - * Preempt the current task with a newly woken task if needed: - */ -static void -check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) -{ - unsigned long ideal_runtime, delta_exec; - - ideal_runtime = sched_slice(cfs_rq, curr); - delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - if (delta_exec > ideal_runtime) { - resched_task(rq_of(cfs_rq)->curr); - /* - * The current task ran long enough, ensure it doesn't get - * re-elected due to buddy favours. - */ - clear_buddies(cfs_rq, curr); - } -} - -static void -set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - /* 'current' is not kept within the tree. */ - if (se->on_rq) { - /* - * Any task has to be enqueued before it get to execute on - * a CPU. So account for the time it spent waiting on the - * runqueue. - */ - update_stats_wait_end(cfs_rq, se); - __dequeue_entity(cfs_rq, se); - } - - update_stats_curr_start(cfs_rq, se); - cfs_rq->curr = se; -#ifdef CONFIG_SCHEDSTATS - /* - * Track our maximum slice length, if the CPU's load is at - * least twice that of our own weight (i.e. dont track it - * when there are only lesser-weight tasks around): - */ - if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { - se->slice_max = max(se->slice_max, - se->sum_exec_runtime - se->prev_sum_exec_runtime); - } -#endif - se->prev_sum_exec_runtime = se->sum_exec_runtime; -} - -static int -wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); - -static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) -{ - struct sched_entity *se = __pick_next_entity(cfs_rq); - - if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1) - return cfs_rq->next; - - if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1) - return cfs_rq->last; - - return se; -} - -static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) -{ - /* - * If still on the runqueue then deactivate_task() - * was not called and update_curr() has to be done: - */ - if (prev->on_rq) - update_curr(cfs_rq); - - check_spread(cfs_rq, prev); - if (prev->on_rq) { - update_stats_wait_start(cfs_rq, prev); - /* Put 'current' back into the tree. */ - __enqueue_entity(cfs_rq, prev); - } - cfs_rq->curr = NULL; -} - -static void -entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) -{ - /* - * Update run-time statistics of the 'current'. - */ - update_curr(cfs_rq); - -#ifdef CONFIG_SCHED_HRTICK - /* - * queued ticks are scheduled to match the slice, so don't bother - * validating it and just reschedule. - */ - if (queued) { - resched_task(rq_of(cfs_rq)->curr); - return; - } - /* - * don't let the period tick interfere with the hrtick preemption - */ - if (!sched_feat(DOUBLE_TICK) && - hrtimer_active(&rq_of(cfs_rq)->hrtick_timer)) - return; -#endif - - if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT)) - check_preempt_tick(cfs_rq, curr); -} - -/************************************************** - * CFS operations on tasks: - */ - -#ifdef CONFIG_SCHED_HRTICK -static void hrtick_start_fair(struct rq *rq, struct task_struct *p) -{ - struct sched_entity *se = &p->se; - struct cfs_rq *cfs_rq = cfs_rq_of(se); - - WARN_ON(task_rq(p) != rq); - - if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) { - u64 slice = sched_slice(cfs_rq, se); - u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; - s64 delta = slice - ran; - - if (delta < 0) { - if (rq->curr == p) - resched_task(p); - return; - } - - /* - * Don't schedule slices shorter than 10000ns, that just - * doesn't make sense. Rely on vruntime for fairness. - */ - if (rq->curr != p) - delta = max_t(s64, 10000LL, delta); - - hrtick_start(rq, delta); - } -} - -/* - * called from enqueue/dequeue and updates the hrtick when the - * current task is from our class and nr_running is low enough - * to matter. - */ -static void hrtick_update(struct rq *rq) -{ - struct task_struct *curr = rq->curr; - - if (curr->sched_class != &fair_sched_class) - return; - - if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) - hrtick_start_fair(rq, curr); -} -#else /* !CONFIG_SCHED_HRTICK */ -static inline void -hrtick_start_fair(struct rq *rq, struct task_struct *p) -{ -} - -static inline void hrtick_update(struct rq *rq) -{ -} -#endif - -/* - * The enqueue_task method is called before nr_running is - * increased. Here we update the fair scheduling stats and - * then put the task into the rbtree: - */ -static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) -{ - struct cfs_rq *cfs_rq; - struct sched_entity *se = &p->se; - - for_each_sched_entity(se) { - if (se->on_rq) - break; - cfs_rq = cfs_rq_of(se); - enqueue_entity(cfs_rq, se, wakeup); - wakeup = 1; - } - - hrtick_update(rq); -} - -/* - * The dequeue_task method is called before nr_running is - * decreased. We remove the task from the rbtree and - * update the fair scheduling stats: - */ -static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) -{ - struct cfs_rq *cfs_rq; - struct sched_entity *se = &p->se; - - for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); - dequeue_entity(cfs_rq, se, sleep); - /* Don't dequeue parent if it has other entities besides us */ - if (cfs_rq->load.weight) - break; - sleep = 1; - } - - hrtick_update(rq); -} - -/* - * sched_yield() support is very simple - we dequeue and enqueue. - * - * If compat_yield is turned on then we requeue to the end of the tree. - */ -static void yield_task_fair(struct rq *rq) -{ - struct task_struct *curr = rq->curr; - struct cfs_rq *cfs_rq = task_cfs_rq(curr); - struct sched_entity *rightmost, *se = &curr->se; - - /* - * Are we the only task in the tree? - */ - if (unlikely(cfs_rq->nr_running == 1)) - return; - - clear_buddies(cfs_rq, se); - - if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) { - update_rq_clock(rq); - /* - * Update run-time statistics of the 'current'. - */ - update_curr(cfs_rq); - - return; - } - /* - * Find the rightmost entry in the rbtree: - */ - rightmost = __pick_last_entity(cfs_rq); - /* - * Already in the rightmost position? - */ - if (unlikely(!rightmost || rightmost->vruntime < se->vruntime)) - return; - - /* - * Minimally necessary key value to be last in the tree: - * Upon rescheduling, sched_class::put_prev_task() will place - * 'current' within the tree based on its new key value. - */ - se->vruntime = rightmost->vruntime + 1; -} - -/* - * 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. - * Domains may include CPUs that are not usable for migration, - * hence we need to mask them out (cpu_active_mask) - * - * Returns the CPU we should wake onto. - */ -#if defined(ARCH_HAS_SCHED_WAKE_IDLE) -static int wake_idle(int cpu, struct task_struct *p) -{ - struct sched_domain *sd; - int i; - unsigned int chosen_wakeup_cpu; - int this_cpu; - - /* - * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu - * are idle and this is not a kernel thread and this task's affinity - * allows it to be moved to preferred cpu, then just move! - */ - - this_cpu = smp_processor_id(); - chosen_wakeup_cpu = - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu; - - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP && - idle_cpu(cpu) && idle_cpu(this_cpu) && - p->mm && !(p->flags & PF_KTHREAD) && - cpu_isset(chosen_wakeup_cpu, p->cpus_allowed)) - return chosen_wakeup_cpu; - - /* - * 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)->cfs.nr_running > 1) - return cpu; - - for_each_domain(cpu, sd) { - if ((sd->flags & SD_WAKE_IDLE) - || ((sd->flags & SD_WAKE_IDLE_FAR) - && !task_hot(p, task_rq(p)->clock, sd))) { - for_each_cpu_and(i, sched_domain_span(sd), - &p->cpus_allowed) { - if (cpu_active(i) && idle_cpu(i)) { - if (i != task_cpu(p)) { - schedstat_inc(p, - se.nr_wakeups_idle); - } - return i; - } - } - } else { - break; - } - } - return cpu; -} -#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/ -static inline int wake_idle(int cpu, struct task_struct *p) -{ - return cpu; -} -#endif - -#ifdef CONFIG_SMP - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* - * effective_load() calculates the load change as seen from the root_task_group - * - * Adding load to a group doesn't make a group heavier, but can cause movement - * of group shares between cpus. Assuming the shares were perfectly aligned one - * can calculate the shift in shares. - * - * The problem is that perfectly aligning the shares is rather expensive, hence - * we try to avoid doing that too often - see update_shares(), which ratelimits - * this change. - * - * We compensate this by not only taking the current delta into account, but - * also considering the delta between when the shares were last adjusted and - * now. - * - * We still saw a performance dip, some tracing learned us that between - * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased - * significantly. Therefore try to bias the error in direction of failing - * the affine wakeup. - * - */ -static long effective_load(struct task_group *tg, int cpu, - long wl, long wg) -{ - struct sched_entity *se = tg->se[cpu]; - - if (!tg->parent) - return wl; - - /* - * By not taking the decrease of shares on the other cpu into - * account our error leans towards reducing the affine wakeups. - */ - if (!wl && sched_feat(ASYM_EFF_LOAD)) - return wl; - - for_each_sched_entity(se) { - long S, rw, s, a, b; - long more_w; - - /* - * Instead of using this increment, also add the difference - * between when the shares were last updated and now. - */ - more_w = se->my_q->load.weight - se->my_q->rq_weight; - wl += more_w; - wg += more_w; - - S = se->my_q->tg->shares; - s = se->my_q->shares; - rw = se->my_q->rq_weight; - - a = S*(rw + wl); - b = S*rw + s*wg; - - wl = s*(a-b); - - if (likely(b)) - wl /= b; - - /* - * Assume the group is already running and will - * thus already be accounted for in the weight. - * - * That is, moving shares between CPUs, does not - * alter the group weight. - */ - wg = 0; - } - - return wl; -} - -#else - -static inline unsigned long effective_load(struct task_group *tg, int cpu, - unsigned long wl, unsigned long wg) -{ - return wl; -} - -#endif - -static int -wake_affine(struct sched_domain *this_sd, struct rq *this_rq, - struct task_struct *p, int prev_cpu, int this_cpu, int sync, - int idx, unsigned long load, unsigned long this_load, - unsigned int imbalance) -{ - struct task_struct *curr = this_rq->curr; - struct task_group *tg; - unsigned long tl = this_load; - unsigned long tl_per_task; - unsigned long weight; - int balanced; - - if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) - return 0; - - if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || - p->se.avg_overlap > sysctl_sched_migration_cost)) - sync = 0; - - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current CPU: - */ - if (sync) { - tg = task_group(current); - weight = current->se.load.weight; - - tl += effective_load(tg, this_cpu, -weight, -weight); - load += effective_load(tg, prev_cpu, 0, -weight); - } - - tg = task_group(p); - weight = p->se.load.weight; - - balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <= - imbalance*(load + effective_load(tg, prev_cpu, 0, weight)); - - /* - * If the currently running task will sleep within - * a reasonable amount of time then attract this newly - * woken task: - */ - if (sync && balanced) - return 1; - - schedstat_inc(p, se.nr_wakeups_affine_attempts); - tl_per_task = cpu_avg_load_per_task(this_cpu); - - if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <= - tl_per_task)) { - /* - * 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); - - return 1; - } - return 0; -} - -static int select_task_rq_fair(struct task_struct *p, int sync) -{ - struct sched_domain *sd, *this_sd = NULL; - int prev_cpu, this_cpu, new_cpu; - unsigned long load, this_load; - struct rq *this_rq; - unsigned int imbalance; - int idx; - - prev_cpu = task_cpu(p); - this_cpu = smp_processor_id(); - this_rq = cpu_rq(this_cpu); - new_cpu = prev_cpu; - - if (prev_cpu == this_cpu) - goto out; - /* - * 'this_sd' is the first domain that both - * this_cpu and prev_cpu are present in: - */ - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) { - this_sd = sd; - break; - } - } - - if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed))) - goto out; - - /* - * Check for affine wakeup and passive balancing possibilities. - */ - if (!this_sd) - goto out; - - idx = this_sd->wake_idx; - - imbalance = 100 + (this_sd->imbalance_pct - 100) / 2; - - load = source_load(prev_cpu, idx); - this_load = target_load(this_cpu, idx); - - if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx, - load, this_load, imbalance)) - return this_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); - return this_cpu; - } - } - -out: - return wake_idle(new_cpu, p); -} -#endif /* CONFIG_SMP */ - -/* - * Adaptive granularity - * - * se->avg_wakeup gives the average time a task runs until it does a wakeup, - * with the limit of wakeup_gran -- when it never does a wakeup. - * - * So the smaller avg_wakeup is the faster we want this task to preempt, - * but we don't want to treat the preemptee unfairly and therefore allow it - * to run for at least the amount of time we'd like to run. - * - * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one - * - * NOTE: we use *nr_running to scale with load, this nicely matches the - * degrading latency on load. - */ -static unsigned long -adaptive_gran(struct sched_entity *curr, struct sched_entity *se) -{ - u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running; - u64 gran = 0; - - if (this_run < expected_wakeup) - gran = expected_wakeup - this_run; - - return min_t(s64, gran, sysctl_sched_wakeup_granularity); -} - -static unsigned long -wakeup_gran(struct sched_entity *curr, struct sched_entity *se) -{ - unsigned long gran = sysctl_sched_wakeup_granularity; - - if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN)) - gran = adaptive_gran(curr, se); - - /* - * Since its curr running now, convert the gran from real-time - * to virtual-time in his units. - */ - if (sched_feat(ASYM_GRAN)) { - /* - * By using 'se' instead of 'curr' we penalize light tasks, so - * they get preempted easier. That is, if 'se' < 'curr' then - * the resulting gran will be larger, therefore penalizing the - * lighter, if otoh 'se' > 'curr' then the resulting gran will - * be smaller, again penalizing the lighter task. - * - * This is especially important for buddies when the leftmost - * task is higher priority than the buddy. - */ - if (unlikely(se->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, se); - } else { - if (unlikely(curr->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, curr); - } - - return gran; -} - -/* - * Should 'se' preempt 'curr'. - * - * |s1 - * |s2 - * |s3 - * g - * |<--->|c - * - * w(c, s1) = -1 - * w(c, s2) = 0 - * w(c, s3) = 1 - * - */ -static int -wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) -{ - s64 gran, vdiff = curr->vruntime - se->vruntime; - - if (vdiff <= 0) - return -1; - - gran = wakeup_gran(curr, se); - if (vdiff > gran) - return 1; - - return 0; -} - -static void set_last_buddy(struct sched_entity *se) -{ - if (likely(task_of(se)->policy != SCHED_IDLE)) { - for_each_sched_entity(se) - cfs_rq_of(se)->last = se; - } -} - -static void set_next_buddy(struct sched_entity *se) -{ - if (likely(task_of(se)->policy != SCHED_IDLE)) { - for_each_sched_entity(se) - cfs_rq_of(se)->next = se; - } -} - -/* - * Preempt the current task with a newly woken task if needed: - */ -static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) -{ - struct task_struct *curr = rq->curr; - struct sched_entity *se = &curr->se, *pse = &p->se; - struct cfs_rq *cfs_rq = task_cfs_rq(curr); - - update_curr(cfs_rq); - - if (unlikely(rt_prio(p->prio))) { - resched_task(curr); - return; - } - - if (unlikely(p->sched_class != &fair_sched_class)) - return; - - if (unlikely(se == pse)) - return; - - /* - * Only set the backward buddy when the current task is still on the - * rq. This can happen when a wakeup gets interleaved with schedule on - * the ->pre_schedule() or idle_balance() point, either of which can - * drop the rq lock. - * - * Also, during early boot the idle thread is in the fair class, for - * obvious reasons its a bad idea to schedule back to the idle thread. - */ - if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle)) - set_last_buddy(se); - set_next_buddy(pse); - - /* - * We can come here with TIF_NEED_RESCHED already set from new task - * wake up path. - */ - if (test_tsk_need_resched(curr)) - return; - - /* - * Batch and idle tasks do not preempt (their preemption is driven by - * the tick): - */ - if (unlikely(p->policy != SCHED_NORMAL)) - return; - - /* Idle tasks are by definition preempted by everybody. */ - if (unlikely(curr->policy == SCHED_IDLE)) { - resched_task(curr); - return; - } - - if (!sched_feat(WAKEUP_PREEMPT)) - return; - - if (sched_feat(WAKEUP_OVERLAP) && (sync || - (se->avg_overlap < sysctl_sched_migration_cost && - pse->avg_overlap < sysctl_sched_migration_cost))) { - resched_task(curr); - return; - } - - find_matching_se(&se, &pse); - - while (se) { - BUG_ON(!pse); - - if (wakeup_preempt_entity(se, pse) == 1) { - resched_task(curr); - break; - } - - se = parent_entity(se); - pse = parent_entity(pse); - } -} - -static struct task_struct *pick_next_task_fair(struct rq *rq) -{ - struct task_struct *p; - struct cfs_rq *cfs_rq = &rq->cfs; - struct sched_entity *se; - - if (unlikely(!cfs_rq->nr_running)) - return NULL; - - do { - se = pick_next_entity(cfs_rq); - /* - * If se was a buddy, clear it so that it will have to earn - * the favour again. - */ - __clear_buddies(cfs_rq, se); - set_next_entity(cfs_rq, se); - cfs_rq = group_cfs_rq(se); - } while (cfs_rq); - - p = task_of(se); - hrtick_start_fair(rq, p); - - return p; -} - -/* - * Account for a descheduled task: - */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) -{ - struct sched_entity *se = &prev->se; - struct cfs_rq *cfs_rq; - - for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); - put_prev_entity(cfs_rq, se); - } -} - -#ifdef CONFIG_SMP -/************************************************** - * Fair scheduling class load-balancing methods: - */ - -/* - * Load-balancing iterator. Note: while the runqueue stays locked - * during the whole iteration, the current task might be - * dequeued so the iterator has to be dequeue-safe. Here we - * achieve that by always pre-iterating before returning - * the current task: - */ -static struct task_struct * -__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next) -{ - struct task_struct *p = NULL; - struct sched_entity *se; - - if (next == &cfs_rq->tasks) - return NULL; - - se = list_entry(next, struct sched_entity, group_node); - p = task_of(se); - cfs_rq->balance_iterator = next->next; - - return p; -} - -static struct task_struct *load_balance_start_fair(void *arg) -{ - struct cfs_rq *cfs_rq = arg; - - return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next); -} - -static struct task_struct *load_balance_next_fair(void *arg) -{ - struct cfs_rq *cfs_rq = arg; - - return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator); -} - -static unsigned long -__load_balance_fair(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 cfs_rq *cfs_rq) -{ - struct rq_iterator cfs_rq_iterator; - - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; - cfs_rq_iterator.arg = cfs_rq; - - return balance_tasks(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &cfs_rq_iterator); -} - -#ifdef CONFIG_FAIR_GROUP_SCHED -static unsigned long -load_balance_fair(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) -{ - long rem_load_move = max_load_move; - int busiest_cpu = cpu_of(busiest); - struct task_group *tg; - - rcu_read_lock(); - update_h_load(busiest_cpu); - - list_for_each_entry_rcu(tg, &task_groups, list) { - struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu]; - unsigned long busiest_h_load = busiest_cfs_rq->h_load; - unsigned long busiest_weight = busiest_cfs_rq->load.weight; - u64 rem_load, moved_load; - - /* - * empty group - */ - if (!busiest_cfs_rq->task_weight) - continue; - - rem_load = (u64)rem_load_move * busiest_weight; - rem_load = div_u64(rem_load, busiest_h_load + 1); - - moved_load = __load_balance_fair(this_rq, this_cpu, busiest, - rem_load, sd, idle, all_pinned, this_best_prio, - tg->cfs_rq[busiest_cpu]); - - if (!moved_load) - continue; - - moved_load *= busiest_h_load; - moved_load = div_u64(moved_load, busiest_weight + 1); - - rem_load_move -= moved_load; - if (rem_load_move < 0) - break; - } - rcu_read_unlock(); - - return max_load_move - rem_load_move; -} -#else -static unsigned long -load_balance_fair(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) -{ - return __load_balance_fair(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &busiest->cfs); -} -#endif - -static int -move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) -{ - struct cfs_rq *busy_cfs_rq; - struct rq_iterator cfs_rq_iterator; - - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; - - for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { - /* - * pass busy_cfs_rq argument into - * load_balance_[start|next]_fair iterators - */ - cfs_rq_iterator.arg = busy_cfs_rq; - if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle, - &cfs_rq_iterator)) - return 1; - } - - return 0; -} -#endif /* CONFIG_SMP */ - -/* - * scheduler tick hitting a task of our scheduling class: - */ -static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) -{ - struct cfs_rq *cfs_rq; - struct sched_entity *se = &curr->se; - - for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); - entity_tick(cfs_rq, se, queued); - } -} - -/* - * Share the fairness runtime between parent and child, thus the - * total amount of pressure for CPU stays equal - new tasks - * get a chance to run but frequent forkers are not allowed to - * monopolize the CPU. Note: the parent runqueue is locked, - * the child is not running yet. - */ -static void task_new_fair(struct rq *rq, struct task_struct *p) -{ - struct cfs_rq *cfs_rq = task_cfs_rq(p); - struct sched_entity *se = &p->se, *curr = cfs_rq->curr; - int this_cpu = smp_processor_id(); - - sched_info_queued(p); - - update_curr(cfs_rq); - place_entity(cfs_rq, se, 1); - - /* 'curr' will be NULL if the child belongs to a different group */ - if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) && - curr && curr->vruntime < se->vruntime) { - /* - * Upon rescheduling, sched_class::put_prev_task() will place - * 'current' within the tree based on its new key value. - */ - swap(curr->vruntime, se->vruntime); - resched_task(rq->curr); - } - - enqueue_task_fair(rq, p, 0); -} - -/* - * Priority of the task has changed. Check to see if we preempt - * the current task. - */ -static void prio_changed_fair(struct rq *rq, struct task_struct *p, - int oldprio, int running) -{ - /* - * 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, 0); -} - -/* - * We switched to the sched_fair class. - */ -static void switched_to_fair(struct rq *rq, struct task_struct *p, - int running) -{ - /* - * We were most likely switched from sched_rt, so - * kick off the schedule if running, otherwise just see - * if we can still preempt the current task. - */ - if (running) - resched_task(rq->curr); - else - check_preempt_curr(rq, p, 0); -} - -/* Account for a task changing its policy or group. - * - * This routine is mostly called to set cfs_rq->curr field when a task - * migrates between groups/classes. - */ -static void set_curr_task_fair(struct rq *rq) -{ - struct sched_entity *se = &rq->curr->se; - - for_each_sched_entity(se) - set_next_entity(cfs_rq_of(se), se); -} - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void moved_group_fair(struct task_struct *p) -{ - struct cfs_rq *cfs_rq = task_cfs_rq(p); - - update_curr(cfs_rq); - place_entity(cfs_rq, &p->se, 1); -} -#endif - -/* - * All the scheduling class methods: - */ -static const struct sched_class fair_sched_class = { - .next = &idle_sched_class, - .enqueue_task = enqueue_task_fair, - .dequeue_task = dequeue_task_fair, - .yield_task = yield_task_fair, - - .check_preempt_curr = check_preempt_wakeup, - - .pick_next_task = pick_next_task_fair, - .put_prev_task = put_prev_task_fair, - -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_fair, - - .load_balance = load_balance_fair, - .move_one_task = move_one_task_fair, -#endif - - .set_curr_task = set_curr_task_fair, - .task_tick = task_tick_fair, - .task_new = task_new_fair, - - .prio_changed = prio_changed_fair, - .switched_to = switched_to_fair, - -#ifdef CONFIG_FAIR_GROUP_SCHED - .moved_group = moved_group_fair, -#endif -}; - -#ifdef CONFIG_SCHED_DEBUG -static void print_cfs_stats(struct seq_file *m, int cpu) -{ - struct cfs_rq *cfs_rq; - - rcu_read_lock(); - for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) - print_cfs_rq(m, cpu, cfs_rq); - rcu_read_unlock(); -} -#endif Index: linux-2.6.30-bfs/kernel/sched_idletask.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sched_idletask.c 2009-06-10 13:05:27.000000000 +1000 +++ /dev/null 1970-01-01 00:00:00.000000000 +0000 @@ -1,128 +0,0 @@ -/* - * idle-task scheduling class. - * - * (NOTE: these are not related to SCHED_IDLE tasks which are - * handled in sched_fair.c) - */ - -#ifdef CONFIG_SMP -static int select_task_rq_idle(struct task_struct *p, int sync) -{ - return task_cpu(p); /* IDLE tasks as never migrated */ -} -#endif /* CONFIG_SMP */ -/* - * Idle tasks are unconditionally rescheduled: - */ -static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync) -{ - resched_task(rq->idle); -} - -static struct task_struct *pick_next_task_idle(struct rq *rq) -{ - schedstat_inc(rq, sched_goidle); - - return rq->idle; -} - -/* - * It is not legal to sleep in the idle task - print a warning - * message if some code attempts to do it: - */ -static void -dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep) -{ - spin_unlock_irq(&rq->lock); - printk(KERN_ERR "bad: scheduling from the idle thread!\n"); - dump_stack(); - spin_lock_irq(&rq->lock); -} - -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) -{ -} - -#ifdef CONFIG_SMP -static unsigned long -load_balance_idle(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) -{ - return 0; -} - -static int -move_one_task_idle(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) -{ - return 0; -} -#endif - -static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) -{ -} - -static void set_curr_task_idle(struct rq *rq) -{ -} - -static void switched_to_idle(struct rq *rq, struct task_struct *p, - int running) -{ - /* Can this actually happen?? */ - if (running) - resched_task(rq->curr); - else - check_preempt_curr(rq, p, 0); -} - -static void prio_changed_idle(struct rq *rq, struct task_struct *p, - int oldprio, int running) -{ - /* This can happen for hot plug CPUS */ - - /* - * 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, 0); -} - -/* - * Simple, special scheduling class for the per-CPU idle tasks: - */ -static const struct sched_class idle_sched_class = { - /* .next is NULL */ - /* no enqueue/yield_task for idle tasks */ - - /* dequeue is not valid, we print a debug message there: */ - .dequeue_task = dequeue_task_idle, - - .check_preempt_curr = check_preempt_curr_idle, - - .pick_next_task = pick_next_task_idle, - .put_prev_task = put_prev_task_idle, - -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_idle, - - .load_balance = load_balance_idle, - .move_one_task = move_one_task_idle, -#endif - - .set_curr_task = set_curr_task_idle, - .task_tick = task_tick_idle, - - .prio_changed = prio_changed_idle, - .switched_to = switched_to_idle, - - /* no .task_new for idle tasks */ -}; Index: linux-2.6.30-bfs/kernel/sched_rt.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sched_rt.c 2009-06-10 13:05:27.000000000 +1000 +++ /dev/null 1970-01-01 00:00:00.000000000 +0000 @@ -1,1771 +0,0 @@ -/* - * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR - * policies) - */ - -static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) -{ - return container_of(rt_se, struct task_struct, rt); -} - -#ifdef CONFIG_RT_GROUP_SCHED - -static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) -{ - return rt_rq->rq; -} - -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) -{ - return rt_se->rt_rq; -} - -#else /* CONFIG_RT_GROUP_SCHED */ - -static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) -{ - return container_of(rt_rq, struct rq, rt); -} - -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) -{ - struct task_struct *p = rt_task_of(rt_se); - struct rq *rq = task_rq(p); - - return &rq->rt; -} - -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_SMP - -static inline int rt_overloaded(struct rq *rq) -{ - return atomic_read(&rq->rd->rto_count); -} - -static inline void rt_set_overload(struct rq *rq) -{ - if (!rq->online) - return; - - cpumask_set_cpu(rq->cpu, rq->rd->rto_mask); - /* - * Make sure the mask is visible before we set - * the overload count. That is checked to determine - * if we should look at the mask. It would be a shame - * if we looked at the mask, but the mask was not - * updated yet. - */ - wmb(); - atomic_inc(&rq->rd->rto_count); -} - -static inline void rt_clear_overload(struct rq *rq) -{ - if (!rq->online) - return; - - /* the order here really doesn't matter */ - atomic_dec(&rq->rd->rto_count); - cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask); -} - -static void update_rt_migration(struct rt_rq *rt_rq) -{ - if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) { - if (!rt_rq->overloaded) { - rt_set_overload(rq_of_rt_rq(rt_rq)); - rt_rq->overloaded = 1; - } - } else if (rt_rq->overloaded) { - rt_clear_overload(rq_of_rt_rq(rt_rq)); - rt_rq->overloaded = 0; - } -} - -static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - if (rt_se->nr_cpus_allowed > 1) - rt_rq->rt_nr_migratory++; - - update_rt_migration(rt_rq); -} - -static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - if (rt_se->nr_cpus_allowed > 1) - rt_rq->rt_nr_migratory--; - - update_rt_migration(rt_rq); -} - -static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) -{ - plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); - plist_node_init(&p->pushable_tasks, p->prio); - plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks); -} - -static void dequeue_pushable_task(struct rq *rq, struct task_struct *p) -{ - plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); -} - -#else - -static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p) -{ -} - -static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p) -{ -} - -static inline -void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ -} - -static inline -void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ -} - -#endif /* CONFIG_SMP */ - -static inline int on_rt_rq(struct sched_rt_entity *rt_se) -{ - return !list_empty(&rt_se->run_list); -} - -#ifdef CONFIG_RT_GROUP_SCHED - -static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) -{ - if (!rt_rq->tg) - return RUNTIME_INF; - - return rt_rq->rt_runtime; -} - -static inline u64 sched_rt_period(struct rt_rq *rt_rq) -{ - return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); -} - -#define for_each_leaf_rt_rq(rt_rq, rq) \ - list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) - -#define for_each_sched_rt_entity(rt_se) \ - for (; rt_se; rt_se = rt_se->parent) - -static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) -{ - return rt_se->my_q; -} - -static void enqueue_rt_entity(struct sched_rt_entity *rt_se); -static void dequeue_rt_entity(struct sched_rt_entity *rt_se); - -static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) -{ - struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; - struct sched_rt_entity *rt_se = rt_rq->rt_se; - - if (rt_rq->rt_nr_running) { - if (rt_se && !on_rt_rq(rt_se)) - enqueue_rt_entity(rt_se); - if (rt_rq->highest_prio.curr < curr->prio) - resched_task(curr); - } -} - -static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) -{ - struct sched_rt_entity *rt_se = rt_rq->rt_se; - - if (rt_se && on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); -} - -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; -} - -static int rt_se_boosted(struct sched_rt_entity *rt_se) -{ - struct rt_rq *rt_rq = group_rt_rq(rt_se); - struct task_struct *p; - - if (rt_rq) - return !!rt_rq->rt_nr_boosted; - - p = rt_task_of(rt_se); - return p->prio != p->normal_prio; -} - -#ifdef CONFIG_SMP -static inline const struct cpumask *sched_rt_period_mask(void) -{ - return cpu_rq(smp_processor_id())->rd->span; -} -#else -static inline const struct cpumask *sched_rt_period_mask(void) -{ - return cpu_online_mask; -} -#endif - -static inline -struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) -{ - return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu]; -} - -static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) -{ - return &rt_rq->tg->rt_bandwidth; -} - -#else /* !CONFIG_RT_GROUP_SCHED */ - -static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) -{ - return rt_rq->rt_runtime; -} - -static inline u64 sched_rt_period(struct rt_rq *rt_rq) -{ - return ktime_to_ns(def_rt_bandwidth.rt_period); -} - -#define for_each_leaf_rt_rq(rt_rq, rq) \ - for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL) - -#define for_each_sched_rt_entity(rt_se) \ - for (; rt_se; rt_se = NULL) - -static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) -{ - return NULL; -} - -static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) -{ - if (rt_rq->rt_nr_running) - resched_task(rq_of_rt_rq(rt_rq)->curr); -} - -static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) -{ -} - -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled; -} - -static inline const struct cpumask *sched_rt_period_mask(void) -{ - return cpu_online_mask; -} - -static inline -struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) -{ - return &cpu_rq(cpu)->rt; -} - -static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) -{ - return &def_rt_bandwidth; -} - -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_SMP -/* - * We ran out of runtime, see if we can borrow some from our neighbours. - */ -static int do_balance_runtime(struct rt_rq *rt_rq) -{ - struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); - struct root_domain *rd = cpu_rq(smp_processor_id())->rd; - int i, weight, more = 0; - u64 rt_period; - - weight = cpumask_weight(rd->span); - - spin_lock(&rt_b->rt_runtime_lock); - rt_period = ktime_to_ns(rt_b->rt_period); - for_each_cpu(i, rd->span) { - struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); - s64 diff; - - if (iter == rt_rq) - continue; - - spin_lock(&iter->rt_runtime_lock); - /* - * Either all rqs have inf runtime and there's nothing to steal - * or __disable_runtime() below sets a specific rq to inf to - * indicate its been disabled and disalow stealing. - */ - if (iter->rt_runtime == RUNTIME_INF) - goto next; - - /* - * From runqueues with spare time, take 1/n part of their - * spare time, but no more than our period. - */ - diff = iter->rt_runtime - iter->rt_time; - if (diff > 0) { - diff = div_u64((u64)diff, weight); - if (rt_rq->rt_runtime + diff > rt_period) - diff = rt_period - rt_rq->rt_runtime; - iter->rt_runtime -= diff; - rt_rq->rt_runtime += diff; - more = 1; - if (rt_rq->rt_runtime == rt_period) { - spin_unlock(&iter->rt_runtime_lock); - break; - } - } -next: - spin_unlock(&iter->rt_runtime_lock); - } - spin_unlock(&rt_b->rt_runtime_lock); - - return more; -} - -/* - * Ensure this RQ takes back all the runtime it lend to its neighbours. - */ -static void __disable_runtime(struct rq *rq) -{ - struct root_domain *rd = rq->rd; - struct rt_rq *rt_rq; - - if (unlikely(!scheduler_running)) - return; - - for_each_leaf_rt_rq(rt_rq, rq) { - struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); - s64 want; - int i; - - spin_lock(&rt_b->rt_runtime_lock); - spin_lock(&rt_rq->rt_runtime_lock); - /* - * Either we're all inf and nobody needs to borrow, or we're - * already disabled and thus have nothing to do, or we have - * exactly the right amount of runtime to take out. - */ - if (rt_rq->rt_runtime == RUNTIME_INF || - rt_rq->rt_runtime == rt_b->rt_runtime) - goto balanced; - spin_unlock(&rt_rq->rt_runtime_lock); - - /* - * Calculate the difference between what we started out with - * and what we current have, that's the amount of runtime - * we lend and now have to reclaim. - */ - want = rt_b->rt_runtime - rt_rq->rt_runtime; - - /* - * Greedy reclaim, take back as much as we can. - */ - for_each_cpu(i, rd->span) { - struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); - s64 diff; - - /* - * Can't reclaim from ourselves or disabled runqueues. - */ - if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF) - continue; - - spin_lock(&iter->rt_runtime_lock); - if (want > 0) { - diff = min_t(s64, iter->rt_runtime, want); - iter->rt_runtime -= diff; - want -= diff; - } else { - iter->rt_runtime -= want; - want -= want; - } - spin_unlock(&iter->rt_runtime_lock); - - if (!want) - break; - } - - spin_lock(&rt_rq->rt_runtime_lock); - /* - * We cannot be left wanting - that would mean some runtime - * leaked out of the system. - */ - BUG_ON(want); -balanced: - /* - * Disable all the borrow logic by pretending we have inf - * runtime - in which case borrowing doesn't make sense. - */ - rt_rq->rt_runtime = RUNTIME_INF; - spin_unlock(&rt_rq->rt_runtime_lock); - spin_unlock(&rt_b->rt_runtime_lock); - } -} - -static void disable_runtime(struct rq *rq) -{ - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __disable_runtime(rq); - spin_unlock_irqrestore(&rq->lock, flags); -} - -static void __enable_runtime(struct rq *rq) -{ - struct rt_rq *rt_rq; - - if (unlikely(!scheduler_running)) - return; - - /* - * Reset each runqueue's bandwidth settings - */ - for_each_leaf_rt_rq(rt_rq, rq) { - struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); - - spin_lock(&rt_b->rt_runtime_lock); - spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = rt_b->rt_runtime; - rt_rq->rt_time = 0; - rt_rq->rt_throttled = 0; - spin_unlock(&rt_rq->rt_runtime_lock); - spin_unlock(&rt_b->rt_runtime_lock); - } -} - -static void enable_runtime(struct rq *rq) -{ - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __enable_runtime(rq); - spin_unlock_irqrestore(&rq->lock, flags); -} - -static int balance_runtime(struct rt_rq *rt_rq) -{ - int more = 0; - - if (rt_rq->rt_time > rt_rq->rt_runtime) { - spin_unlock(&rt_rq->rt_runtime_lock); - more = do_balance_runtime(rt_rq); - spin_lock(&rt_rq->rt_runtime_lock); - } - - return more; -} -#else /* !CONFIG_SMP */ -static inline int balance_runtime(struct rt_rq *rt_rq) -{ - return 0; -} -#endif /* CONFIG_SMP */ - -static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) -{ - int i, idle = 1; - const struct cpumask *span; - - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return 1; - - span = sched_rt_period_mask(); - for_each_cpu(i, span) { - int enqueue = 0; - struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); - struct rq *rq = rq_of_rt_rq(rt_rq); - - spin_lock(&rq->lock); - if (rt_rq->rt_time) { - u64 runtime; - - spin_lock(&rt_rq->rt_runtime_lock); - if (rt_rq->rt_throttled) - balance_runtime(rt_rq); - runtime = rt_rq->rt_runtime; - rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime); - if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { - rt_rq->rt_throttled = 0; - enqueue = 1; - } - if (rt_rq->rt_time || rt_rq->rt_nr_running) - idle = 0; - spin_unlock(&rt_rq->rt_runtime_lock); - } else if (rt_rq->rt_nr_running) - idle = 0; - - if (enqueue) - sched_rt_rq_enqueue(rt_rq); - spin_unlock(&rq->lock); - } - - return idle; -} - -static inline int rt_se_prio(struct sched_rt_entity *rt_se) -{ -#ifdef CONFIG_RT_GROUP_SCHED - struct rt_rq *rt_rq = group_rt_rq(rt_se); - - if (rt_rq) - return rt_rq->highest_prio.curr; -#endif - - return rt_task_of(rt_se)->prio; -} - -static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) -{ - u64 runtime = sched_rt_runtime(rt_rq); - - if (rt_rq->rt_throttled) - return rt_rq_throttled(rt_rq); - - if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq)) - return 0; - - balance_runtime(rt_rq); - runtime = sched_rt_runtime(rt_rq); - if (runtime == RUNTIME_INF) - return 0; - - if (rt_rq->rt_time > runtime) { - rt_rq->rt_throttled = 1; - if (rt_rq_throttled(rt_rq)) { - sched_rt_rq_dequeue(rt_rq); - return 1; - } - } - - return 0; -} - -/* - * Update the current task's runtime statistics. Skip current tasks that - * are not in our scheduling class. - */ -static void update_curr_rt(struct rq *rq) -{ - struct task_struct *curr = rq->curr; - struct sched_rt_entity *rt_se = &curr->rt; - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); - u64 delta_exec; - - if (!task_has_rt_policy(curr)) - return; - - delta_exec = rq->clock - curr->se.exec_start; - if (unlikely((s64)delta_exec < 0)) - delta_exec = 0; - - schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); - - curr->se.sum_exec_runtime += delta_exec; - account_group_exec_runtime(curr, delta_exec); - - curr->se.exec_start = rq->clock; - cpuacct_charge(curr, delta_exec); - - if (!rt_bandwidth_enabled()) - return; - - for_each_sched_rt_entity(rt_se) { - rt_rq = rt_rq_of_se(rt_se); - - if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { - spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; - if (sched_rt_runtime_exceeded(rt_rq)) - resched_task(curr); - spin_unlock(&rt_rq->rt_runtime_lock); - } - } -} - -#if defined CONFIG_SMP - -static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu); - -static inline int next_prio(struct rq *rq) -{ - struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu); - - if (next && rt_prio(next->prio)) - return next->prio; - else - return MAX_RT_PRIO; -} - -static void -inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) -{ - struct rq *rq = rq_of_rt_rq(rt_rq); - - if (prio < prev_prio) { - - /* - * If the new task is higher in priority than anything on the - * run-queue, we know that the previous high becomes our - * next-highest. - */ - rt_rq->highest_prio.next = prev_prio; - - if (rq->online) - cpupri_set(&rq->rd->cpupri, rq->cpu, prio); - - } else if (prio == rt_rq->highest_prio.curr) - /* - * If the next task is equal in priority to the highest on - * the run-queue, then we implicitly know that the next highest - * task cannot be any lower than current - */ - rt_rq->highest_prio.next = prio; - else if (prio < rt_rq->highest_prio.next) - /* - * Otherwise, we need to recompute next-highest - */ - rt_rq->highest_prio.next = next_prio(rq); -} - -static void -dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) -{ - struct rq *rq = rq_of_rt_rq(rt_rq); - - if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next)) - rt_rq->highest_prio.next = next_prio(rq); - - if (rq->online && rt_rq->highest_prio.curr != prev_prio) - cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); -} - -#else /* CONFIG_SMP */ - -static inline -void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} -static inline -void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} - -#endif /* CONFIG_SMP */ - -#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED -static void -inc_rt_prio(struct rt_rq *rt_rq, int prio) -{ - int prev_prio = rt_rq->highest_prio.curr; - - if (prio < prev_prio) - rt_rq->highest_prio.curr = prio; - - inc_rt_prio_smp(rt_rq, prio, prev_prio); -} - -static void -dec_rt_prio(struct rt_rq *rt_rq, int prio) -{ - int prev_prio = rt_rq->highest_prio.curr; - - if (rt_rq->rt_nr_running) { - - WARN_ON(prio < prev_prio); - - /* - * This may have been our highest task, and therefore - * we may have some recomputation to do - */ - if (prio == prev_prio) { - struct rt_prio_array *array = &rt_rq->active; - - rt_rq->highest_prio.curr = - sched_find_first_bit(array->bitmap); - } - - } else - rt_rq->highest_prio.curr = MAX_RT_PRIO; - - dec_rt_prio_smp(rt_rq, prio, prev_prio); -} - -#else - -static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {} -static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {} - -#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED - -static void -inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - if (rt_se_boosted(rt_se)) - rt_rq->rt_nr_boosted++; - - if (rt_rq->tg) - start_rt_bandwidth(&rt_rq->tg->rt_bandwidth); -} - -static void -dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - if (rt_se_boosted(rt_se)) - rt_rq->rt_nr_boosted--; - - WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted); -} - -#else /* CONFIG_RT_GROUP_SCHED */ - -static void -inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - start_rt_bandwidth(&def_rt_bandwidth); -} - -static inline -void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} - -#endif /* CONFIG_RT_GROUP_SCHED */ - -static inline -void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - int prio = rt_se_prio(rt_se); - - WARN_ON(!rt_prio(prio)); - rt_rq->rt_nr_running++; - - inc_rt_prio(rt_rq, prio); - inc_rt_migration(rt_se, rt_rq); - inc_rt_group(rt_se, rt_rq); -} - -static inline -void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ - WARN_ON(!rt_prio(rt_se_prio(rt_se))); - WARN_ON(!rt_rq->rt_nr_running); - rt_rq->rt_nr_running--; - - dec_rt_prio(rt_rq, rt_se_prio(rt_se)); - dec_rt_migration(rt_se, rt_rq); - dec_rt_group(rt_se, rt_rq); -} - -static void __enqueue_rt_entity(struct sched_rt_entity *rt_se) -{ - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); - struct rt_prio_array *array = &rt_rq->active; - struct rt_rq *group_rq = group_rt_rq(rt_se); - struct list_head *queue = array->queue + rt_se_prio(rt_se); - - /* - * Don't enqueue the group if its throttled, or when empty. - * The latter is a consequence of the former when a child group - * get throttled and the current group doesn't have any other - * active members. - */ - if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) - return; - - list_add_tail(&rt_se->run_list, queue); - __set_bit(rt_se_prio(rt_se), array->bitmap); - - inc_rt_tasks(rt_se, rt_rq); -} - -static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) -{ - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); - struct rt_prio_array *array = &rt_rq->active; - - list_del_init(&rt_se->run_list); - if (list_empty(array->queue + rt_se_prio(rt_se))) - __clear_bit(rt_se_prio(rt_se), array->bitmap); - - dec_rt_tasks(rt_se, rt_rq); -} - -/* - * Because the prio of an upper entry depends on the lower - * entries, we must remove entries top - down. - */ -static void dequeue_rt_stack(struct sched_rt_entity *rt_se) -{ - struct sched_rt_entity *back = NULL; - - for_each_sched_rt_entity(rt_se) { - rt_se->back = back; - back = rt_se; - } - - for (rt_se = back; rt_se; rt_se = rt_se->back) { - if (on_rt_rq(rt_se)) - __dequeue_rt_entity(rt_se); - } -} - -static void enqueue_rt_entity(struct sched_rt_entity *rt_se) -{ - dequeue_rt_stack(rt_se); - for_each_sched_rt_entity(rt_se) - __enqueue_rt_entity(rt_se); -} - -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) -{ - dequeue_rt_stack(rt_se); - - for_each_sched_rt_entity(rt_se) { - struct rt_rq *rt_rq = group_rt_rq(rt_se); - - if (rt_rq && rt_rq->rt_nr_running) - __enqueue_rt_entity(rt_se); - } -} - -/* - * Adding/removing a task to/from a priority array: - */ -static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) -{ - struct sched_rt_entity *rt_se = &p->rt; - - if (wakeup) - rt_se->timeout = 0; - - enqueue_rt_entity(rt_se); - - if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1) - enqueue_pushable_task(rq, p); - - inc_cpu_load(rq, p->se.load.weight); -} - -static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) -{ - struct sched_rt_entity *rt_se = &p->rt; - - update_curr_rt(rq); - dequeue_rt_entity(rt_se); - - dequeue_pushable_task(rq, p); - - dec_cpu_load(rq, p->se.load.weight); -} - -/* - * Put task to the end of the run list without the overhead of dequeue - * followed by enqueue. - */ -static void -requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head) -{ - if (on_rt_rq(rt_se)) { - struct rt_prio_array *array = &rt_rq->active; - struct list_head *queue = array->queue + rt_se_prio(rt_se); - - if (head) - list_move(&rt_se->run_list, queue); - else - list_move_tail(&rt_se->run_list, queue); - } -} - -static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head) -{ - struct sched_rt_entity *rt_se = &p->rt; - struct rt_rq *rt_rq; - - for_each_sched_rt_entity(rt_se) { - rt_rq = rt_rq_of_se(rt_se); - requeue_rt_entity(rt_rq, rt_se, head); - } -} - -static void yield_task_rt(struct rq *rq) -{ - requeue_task_rt(rq, rq->curr, 0); -} - -#ifdef CONFIG_SMP -static int find_lowest_rq(struct task_struct *task); - -static int select_task_rq_rt(struct task_struct *p, int sync) -{ - struct rq *rq = task_rq(p); - - /* - * If the current task is an RT task, then - * try to see if we can wake this RT task up on another - * runqueue. Otherwise simply start this RT task - * on its current runqueue. - * - * We want to avoid overloading runqueues. Even if - * the RT task is of higher priority than the current RT task. - * RT tasks behave differently than other tasks. If - * one gets preempted, we try to push it off to another queue. - * So trying to keep a preempting RT task on the same - * cache hot CPU will force the running RT task to - * a cold CPU. So we waste all the cache for the lower - * RT task in hopes of saving some of a RT task - * that is just being woken and probably will have - * cold cache anyway. - */ - if (unlikely(rt_task(rq->curr)) && - (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); - - return (cpu == -1) ? task_cpu(p) : cpu; - } - - /* - * Otherwise, just let it ride on the affined RQ and the - * post-schedule router will push the preempted task away - */ - return task_cpu(p); -} - -static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) -{ - if (rq->curr->rt.nr_cpus_allowed == 1) - return; - - if (p->rt.nr_cpus_allowed != 1 - && cpupri_find(&rq->rd->cpupri, p, NULL)) - return; - - if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) - return; - - /* - * There appears to be other cpus that can accept - * current and none to run 'p', so lets reschedule - * to try and push current away: - */ - requeue_task_rt(rq, p, 1); - resched_task(rq->curr); -} - -#endif /* CONFIG_SMP */ - -/* - * Preempt the current task with a newly woken task if needed: - */ -static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync) -{ - if (p->prio < rq->curr->prio) { - resched_task(rq->curr); - return; - } - -#ifdef CONFIG_SMP - /* - * If: - * - * - the newly woken task is of equal priority to the current task - * - the newly woken task is non-migratable while current is migratable - * - current will be preempted on the next reschedule - * - * we should check to see if current can readily move to a different - * cpu. If so, we will reschedule to allow the push logic to try - * to move current somewhere else, making room for our non-migratable - * task. - */ - if (p->prio == rq->curr->prio && !need_resched()) - check_preempt_equal_prio(rq, p); -#endif -} - -static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, - struct rt_rq *rt_rq) -{ - struct rt_prio_array *array = &rt_rq->active; - struct sched_rt_entity *next = NULL; - struct list_head *queue; - int idx; - - idx = sched_find_first_bit(array->bitmap); - BUG_ON(idx >= MAX_RT_PRIO); - - queue = array->queue + idx; - next = list_entry(queue->next, struct sched_rt_entity, run_list); - - return next; -} - -static struct task_struct *_pick_next_task_rt(struct rq *rq) -{ - struct sched_rt_entity *rt_se; - struct task_struct *p; - struct rt_rq *rt_rq; - - rt_rq = &rq->rt; - - if (unlikely(!rt_rq->rt_nr_running)) - return NULL; - - if (rt_rq_throttled(rt_rq)) - return NULL; - - do { - rt_se = pick_next_rt_entity(rq, rt_rq); - BUG_ON(!rt_se); - rt_rq = group_rt_rq(rt_se); - } while (rt_rq); - - p = rt_task_of(rt_se); - p->se.exec_start = rq->clock; - - return p; -} - -static struct task_struct *pick_next_task_rt(struct rq *rq) -{ - struct task_struct *p = _pick_next_task_rt(rq); - - /* The running task is never eligible for pushing */ - if (p) - dequeue_pushable_task(rq, p); - - return p; -} - -static void put_prev_task_rt(struct rq *rq, struct task_struct *p) -{ - update_curr_rt(rq); - p->se.exec_start = 0; - - /* - * The previous task needs to be made eligible for pushing - * if it is still active - */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) - enqueue_pushable_task(rq, p); -} - -#ifdef CONFIG_SMP - -/* Only try algorithms three times */ -#define RT_MAX_TRIES 3 - -static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); - -static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) -{ - if (!task_running(rq, p) && - (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) && - (p->rt.nr_cpus_allowed > 1)) - return 1; - return 0; -} - -/* Return the second highest RT task, NULL otherwise */ -static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) -{ - struct task_struct *next = NULL; - struct sched_rt_entity *rt_se; - struct rt_prio_array *array; - struct rt_rq *rt_rq; - int idx; - - for_each_leaf_rt_rq(rt_rq, rq) { - array = &rt_rq->active; - idx = sched_find_first_bit(array->bitmap); - next_idx: - if (idx >= MAX_RT_PRIO) - continue; - if (next && next->prio < idx) - continue; - list_for_each_entry(rt_se, array->queue + idx, run_list) { - struct task_struct *p = rt_task_of(rt_se); - if (pick_rt_task(rq, p, cpu)) { - next = p; - break; - } - } - if (!next) { - idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1); - goto next_idx; - } - } - - return next; -} - -static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); - -static inline int pick_optimal_cpu(int this_cpu, - const struct cpumask *mask) -{ - int first; - - /* "this_cpu" is cheaper to preempt than a remote processor */ - if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask)) - return this_cpu; - - first = cpumask_first(mask); - if (first < nr_cpu_ids) - return first; - - return -1; -} - -static int find_lowest_rq(struct task_struct *task) -{ - struct sched_domain *sd; - struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask); - int this_cpu = smp_processor_id(); - int cpu = task_cpu(task); - cpumask_var_t domain_mask; - - if (task->rt.nr_cpus_allowed == 1) - return -1; /* No other targets possible */ - - if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) - return -1; /* No targets found */ - - /* - * Only consider CPUs that are usable for migration. - * I guess we might want to change cpupri_find() to ignore those - * in the first place. - */ - cpumask_and(lowest_mask, lowest_mask, cpu_active_mask); - - /* - * At this point we have built a mask of cpus representing the - * lowest priority tasks in the system. Now we want to elect - * the best one based on our affinity and topology. - * - * We prioritize the last cpu that the task executed on since - * it is most likely cache-hot in that location. - */ - if (cpumask_test_cpu(cpu, lowest_mask)) - return cpu; - - /* - * Otherwise, we consult the sched_domains span maps to figure - * out which cpu is logically closest to our hot cache data. - */ - if (this_cpu == cpu) - this_cpu = -1; /* Skip this_cpu opt if the same */ - - if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) { - for_each_domain(cpu, sd) { - if (sd->flags & SD_WAKE_AFFINE) { - int best_cpu; - - cpumask_and(domain_mask, - sched_domain_span(sd), - lowest_mask); - - best_cpu = pick_optimal_cpu(this_cpu, - domain_mask); - - if (best_cpu != -1) { - free_cpumask_var(domain_mask); - return best_cpu; - } - } - } - free_cpumask_var(domain_mask); - } - - /* - * And finally, if there were no matches within the domains - * just give the caller *something* to work with from the compatible - * locations. - */ - return pick_optimal_cpu(this_cpu, lowest_mask); -} - -/* Will lock the rq it finds */ -static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) -{ - struct rq *lowest_rq = NULL; - int tries; - int cpu; - - for (tries = 0; tries < RT_MAX_TRIES; tries++) { - cpu = find_lowest_rq(task); - - if ((cpu == -1) || (cpu == rq->cpu)) - break; - - lowest_rq = cpu_rq(cpu); - - /* if the prio of this runqueue changed, try again */ - if (double_lock_balance(rq, lowest_rq)) { - /* - * We had to unlock the run queue. In - * the mean time, task could have - * migrated already or had its affinity changed. - * Also make sure that it wasn't scheduled on its rq. - */ - if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, - &task->cpus_allowed) || - task_running(rq, task) || - !task->se.on_rq)) { - - spin_unlock(&lowest_rq->lock); - lowest_rq = NULL; - break; - } - } - - /* If this rq is still suitable use it. */ - if (lowest_rq->rt.highest_prio.curr > task->prio) - break; - - /* try again */ - double_unlock_balance(rq, lowest_rq); - lowest_rq = NULL; - } - - return lowest_rq; -} - -static inline int has_pushable_tasks(struct rq *rq) -{ - return !plist_head_empty(&rq->rt.pushable_tasks); -} - -static struct task_struct *pick_next_pushable_task(struct rq *rq) -{ - struct task_struct *p; - - if (!has_pushable_tasks(rq)) - return NULL; - - p = plist_first_entry(&rq->rt.pushable_tasks, - struct task_struct, pushable_tasks); - - BUG_ON(rq->cpu != task_cpu(p)); - BUG_ON(task_current(rq, p)); - BUG_ON(p->rt.nr_cpus_allowed <= 1); - - BUG_ON(!p->se.on_rq); - BUG_ON(!rt_task(p)); - - return p; -} - -/* - * If the current CPU has more than one RT task, see if the non - * running task can migrate over to a CPU that is running a task - * of lesser priority. - */ -static int push_rt_task(struct rq *rq) -{ - struct task_struct *next_task; - struct rq *lowest_rq; - - if (!rq->rt.overloaded) - return 0; - - next_task = pick_next_pushable_task(rq); - if (!next_task) - return 0; - - retry: - if (unlikely(next_task == rq->curr)) { - WARN_ON(1); - return 0; - } - - /* - * It's possible that the next_task slipped in of - * higher priority than current. If that's the case - * just reschedule current. - */ - if (unlikely(next_task->prio < rq->curr->prio)) { - resched_task(rq->curr); - return 0; - } - - /* We might release rq lock */ - get_task_struct(next_task); - - /* find_lock_lowest_rq locks the rq if found */ - lowest_rq = find_lock_lowest_rq(next_task, rq); - if (!lowest_rq) { - struct task_struct *task; - /* - * find lock_lowest_rq releases rq->lock - * so it is possible that next_task has migrated. - * - * We need to make sure that the task is still on the same - * run-queue and is also still the next task eligible for - * pushing. - */ - task = pick_next_pushable_task(rq); - if (task_cpu(next_task) == rq->cpu && task == next_task) { - /* - * If we get here, the task hasnt moved at all, but - * it has failed to push. We will not try again, - * since the other cpus will pull from us when they - * are ready. - */ - dequeue_pushable_task(rq, next_task); - goto out; - } - - if (!task) - /* No more tasks, just exit */ - goto out; - - /* - * Something has shifted, try again. - */ - put_task_struct(next_task); - next_task = task; - goto retry; - } - - deactivate_task(rq, next_task, 0); - set_task_cpu(next_task, lowest_rq->cpu); - activate_task(lowest_rq, next_task, 0); - - resched_task(lowest_rq->curr); - - double_unlock_balance(rq, lowest_rq); - -out: - put_task_struct(next_task); - - return 1; -} - -static void push_rt_tasks(struct rq *rq) -{ - /* push_rt_task will return true if it moved an RT */ - while (push_rt_task(rq)) - ; -} - -static int pull_rt_task(struct rq *this_rq) -{ - int this_cpu = this_rq->cpu, ret = 0, cpu; - struct task_struct *p; - struct rq *src_rq; - - if (likely(!rt_overloaded(this_rq))) - return 0; - - for_each_cpu(cpu, this_rq->rd->rto_mask) { - if (this_cpu == cpu) - continue; - - src_rq = cpu_rq(cpu); - - /* - * Don't bother taking the src_rq->lock if the next highest - * task is known to be lower-priority than our current task. - * This may look racy, but if this value is about to go - * logically higher, the src_rq will push this task away. - * And if its going logically lower, we do not care - */ - if (src_rq->rt.highest_prio.next >= - this_rq->rt.highest_prio.curr) - continue; - - /* - * We can potentially drop this_rq's lock in - * double_lock_balance, and another CPU could - * alter this_rq - */ - double_lock_balance(this_rq, src_rq); - - /* - * Are there still pullable RT tasks? - */ - if (src_rq->rt.rt_nr_running <= 1) - goto skip; - - p = pick_next_highest_task_rt(src_rq, this_cpu); - - /* - * Do we have an RT task that preempts - * the to-be-scheduled task? - */ - if (p && (p->prio < this_rq->rt.highest_prio.curr)) { - WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); - - /* - * There's a chance that p is higher in priority - * than what's currently running on its cpu. - * This is just that p is wakeing up and hasn't - * had a chance to schedule. We only pull - * p if it is lower in priority than the - * current task on the run queue - */ - if (p->prio < src_rq->curr->prio) - goto skip; - - ret = 1; - - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); - /* - * We continue with the search, just in - * case there's an even higher prio task - * in another runqueue. (low likelyhood - * but possible) - */ - } - skip: - double_unlock_balance(this_rq, src_rq); - } - - return ret; -} - -static void pre_schedule_rt(struct rq *rq, struct task_struct *prev) -{ - /* Try to pull RT tasks here if we lower this rq's prio */ - if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio) - pull_rt_task(rq); -} - -/* - * assumes rq->lock is held - */ -static int needs_post_schedule_rt(struct rq *rq) -{ - return has_pushable_tasks(rq); -} - -static void post_schedule_rt(struct rq *rq) -{ - /* - * This is only called if needs_post_schedule_rt() indicates that - * we need to push tasks away - */ - spin_lock_irq(&rq->lock); - push_rt_tasks(rq); - spin_unlock_irq(&rq->lock); -} - -/* - * If we are not running and we are not going to reschedule soon, we should - * try to push tasks away now - */ -static void task_wake_up_rt(struct rq *rq, struct task_struct *p) -{ - if (!task_running(rq, p) && - !test_tsk_need_resched(rq->curr) && - has_pushable_tasks(rq) && - p->rt.nr_cpus_allowed > 1) - push_rt_tasks(rq); -} - -static unsigned long -load_balance_rt(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) -{ - /* don't touch RT tasks */ - return 0; -} - -static int -move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) -{ - /* don't touch RT tasks */ - return 0; -} - -static void set_cpus_allowed_rt(struct task_struct *p, - const struct cpumask *new_mask) -{ - int weight = cpumask_weight(new_mask); - - BUG_ON(!rt_task(p)); - - /* - * Update the migration status of the RQ if we have an RT task - * which is running AND changing its weight value. - */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { - struct rq *rq = task_rq(p); - - if (!task_current(rq, p)) { - /* - * Make sure we dequeue this task from the pushable list - * before going further. It will either remain off of - * the list because we are no longer pushable, or it - * will be requeued. - */ - if (p->rt.nr_cpus_allowed > 1) - dequeue_pushable_task(rq, p); - - /* - * Requeue if our weight is changing and still > 1 - */ - if (weight > 1) - enqueue_pushable_task(rq, p); - - } - - if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) { - rq->rt.rt_nr_migratory++; - } else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) { - BUG_ON(!rq->rt.rt_nr_migratory); - rq->rt.rt_nr_migratory--; - } - - update_rt_migration(&rq->rt); - } - - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = weight; -} - -/* Assumes rq->lock is held */ -static void rq_online_rt(struct rq *rq) -{ - if (rq->rt.overloaded) - rt_set_overload(rq); - - __enable_runtime(rq); - - cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); -} - -/* Assumes rq->lock is held */ -static void rq_offline_rt(struct rq *rq) -{ - if (rq->rt.overloaded) - rt_clear_overload(rq); - - __disable_runtime(rq); - - cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID); -} - -/* - * When switch from the rt queue, we bring ourselves to a position - * that we might want to pull RT tasks from other runqueues. - */ -static void switched_from_rt(struct rq *rq, struct task_struct *p, - int running) -{ - /* - * If there are other RT tasks then we will reschedule - * and the scheduling of the other RT tasks will handle - * the balancing. But if we are the last RT task - * we may need to handle the pulling of RT tasks - * now. - */ - if (!rq->rt.rt_nr_running) - pull_rt_task(rq); -} - -static inline void init_sched_rt_class(void) -{ - unsigned int i; - - for_each_possible_cpu(i) - zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i), - GFP_KERNEL, cpu_to_node(i)); -} -#endif /* CONFIG_SMP */ - -/* - * When switching a task to RT, we may overload the runqueue - * with RT tasks. In this case we try to push them off to - * other runqueues. - */ -static void switched_to_rt(struct rq *rq, struct task_struct *p, - int running) -{ - int check_resched = 1; - - /* - * If we are already running, then there's nothing - * that needs to be done. But if we are not running - * we may need to preempt the current running task. - * If that current running task is also an RT task - * then see if we can move to another run queue. - */ - if (!running) { -#ifdef CONFIG_SMP - if (rq->rt.overloaded && push_rt_task(rq) && - /* Don't resched if we changed runqueues */ - rq != task_rq(p)) - check_resched = 0; -#endif /* CONFIG_SMP */ - if (check_resched && p->prio < rq->curr->prio) - resched_task(rq->curr); - } -} - -/* - * Priority of the task has changed. This may cause - * us to initiate a push or pull. - */ -static void prio_changed_rt(struct rq *rq, struct task_struct *p, - int oldprio, int running) -{ - if (running) { -#ifdef CONFIG_SMP - /* - * If our priority decreases while running, we - * may need to pull tasks to this runqueue. - */ - if (oldprio < p->prio) - pull_rt_task(rq); - /* - * If there's a higher priority task waiting to run - * then reschedule. Note, the above pull_rt_task - * can release the rq lock and p could migrate. - * Only reschedule if p is still on the same runqueue. - */ - if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) - resched_task(p); -#else - /* For UP simply resched on drop of prio */ - if (oldprio < p->prio) - resched_task(p); -#endif /* CONFIG_SMP */ - } else { - /* - * This task is not running, but if it is - * greater than the current running task - * then reschedule. - */ - if (p->prio < rq->curr->prio) - resched_task(rq->curr); - } -} - -static void watchdog(struct rq *rq, struct task_struct *p) -{ - unsigned long soft, hard; - - if (!p->signal) - return; - - soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur; - hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max; - - if (soft != RLIM_INFINITY) { - unsigned long next; - - p->rt.timeout++; - next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); - if (p->rt.timeout > next) - p->cputime_expires.sched_exp = p->se.sum_exec_runtime; - } -} - -static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) -{ - update_curr_rt(rq); - - watchdog(rq, p); - - /* - * RR tasks need a special form of timeslice management. - * FIFO tasks have no timeslices. - */ - if (p->policy != SCHED_RR) - return; - - if (--p->rt.time_slice) - return; - - p->rt.time_slice = DEF_TIMESLICE; - - /* - * Requeue to the end of queue if we are not the only element - * on the queue: - */ - if (p->rt.run_list.prev != p->rt.run_list.next) { - requeue_task_rt(rq, p, 0); - set_tsk_need_resched(p); - } -} - -static void set_curr_task_rt(struct rq *rq) -{ - struct task_struct *p = rq->curr; - - p->se.exec_start = rq->clock; - - /* The running task is never eligible for pushing */ - dequeue_pushable_task(rq, p); -} - -static const struct sched_class rt_sched_class = { - .next = &fair_sched_class, - .enqueue_task = enqueue_task_rt, - .dequeue_task = dequeue_task_rt, - .yield_task = yield_task_rt, - - .check_preempt_curr = check_preempt_curr_rt, - - .pick_next_task = pick_next_task_rt, - .put_prev_task = put_prev_task_rt, - -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_rt, - - .load_balance = load_balance_rt, - .move_one_task = move_one_task_rt, - .set_cpus_allowed = set_cpus_allowed_rt, - .rq_online = rq_online_rt, - .rq_offline = rq_offline_rt, - .pre_schedule = pre_schedule_rt, - .needs_post_schedule = needs_post_schedule_rt, - .post_schedule = post_schedule_rt, - .task_wake_up = task_wake_up_rt, - .switched_from = switched_from_rt, -#endif - - .set_curr_task = set_curr_task_rt, - .task_tick = task_tick_rt, - - .prio_changed = prio_changed_rt, - .switched_to = switched_to_rt, -}; - -#ifdef CONFIG_SCHED_DEBUG -extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); - -static void print_rt_stats(struct seq_file *m, int cpu) -{ - struct rt_rq *rt_rq; - - rcu_read_lock(); - for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu)) - print_rt_rq(m, cpu, rt_rq); - rcu_read_unlock(); -} -#endif /* CONFIG_SCHED_DEBUG */ - Index: linux-2.6.30-bfs/kernel/sched_bfs.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6.30-bfs/kernel/sched_bfs.c 2009-08-27 17:01:24.866767992 +1000 @@ -0,0 +1,5618 @@ +/* + * kernel/sched_bfs.c, was sched.c + * + * Kernel scheduler and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and + * make semaphores SMP safe + * 1998-11-19 Implemented schedule_timeout() and related stuff + * by Andrea Arcangeli + * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: + * hybrid priority-list and round-robin design with + * an array-switch method of distributing timeslices + * and per-CPU runqueues. Cleanups and useful suggestions + * by Davide Libenzi, preemptible kernel bits by Robert Love. + * 2003-09-03 Interactivity tuning by Con Kolivas. + * 2004-04-02 Scheduler domains code by Nick Piggin + * 2007-04-15 Work begun on replacing all interactivity tuning with a + * fair scheduling design by Con Kolivas. + * 2007-05-05 Load balancing (smp-nice) and other improvements + * 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 + * now Brainfuck deadline scheduling policy by Con Kolivas deletes + * a whole lot of those previous things. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * Priority of a process goes from 0..MAX_PRIO-1, valid RT + * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH + * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority + * values are inverted: lower p->prio value means higher priority. + */ + +#define MAX_USER_RT_PRIO 100 +#define MAX_RT_PRIO MAX_USER_RT_PRIO +#define PRIO_RANGE (40) +#define NORMAL_PRIO MAX_RT_PRIO +#define PRIO_LIMIT ((NORMAL_PRIO) + 1) +#define MAX_PRIO (MAX_RT_PRIO + PRIO_RANGE) + +#define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO) +#define rt_task(p) rt_prio((p)->prio) +#define batch_task(p) (unlikely((p)->policy == SCHED_BATCH)) +#define is_rt_policy(p) ((p) != SCHED_NORMAL && (p) != SCHED_BATCH) +#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy)) + +/* + * Convert user-nice values [ -20 ... 0 ... 19 ] + * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], + * and back. + */ +#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) +#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) +#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) + +/* + * 'User priority' is the nice value converted to something we + * can work with better when scaling various scheduler parameters, + * it's a [ 0 ... 39 ] range. + */ +#define USER_PRIO(p) ((p)-MAX_RT_PRIO) +#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) +#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) +#define SCHED_PRIO(p) ((p)+MAX_RT_PRIO) + +/* Some helpers for converting to/from various scales.*/ +#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) +#define MS_TO_NS(TIME) ((TIME) * 1000000) +#define MS_TO_US(TIME) ((TIME) * 1000) + + +DEFINE_TRACE(sched_wait_task); +DEFINE_TRACE(sched_wakeup); +DEFINE_TRACE(sched_wakeup_new); +DEFINE_TRACE(sched_switch); +DEFINE_TRACE(sched_migrate_task); + +#ifdef CONFIG_SMP +/* + * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) + * Since cpu_power is a 'constant', we can use a reciprocal divide. + */ +static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load) +{ + return reciprocal_divide(load, sg->reciprocal_cpu_power); +} + +/* + * Each time a sched group cpu_power is changed, + * we must compute its reciprocal value + */ +static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) +{ + sg->__cpu_power += val; + sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power); +} +#endif + +/* + * This is the time all tasks within the same priority round robin. + * Value is in ms and set to a minimum of 6ms. Scales with number of cpus. + * Tunable via /proc interface. + */ +int rr_interval __read_mostly = 6; +int prio_ratios[PRIO_RANGE] __read_mostly; + +static inline unsigned long timeslice(void) +{ + return MS_TO_US(rr_interval); +} + +struct global_rq { + spinlock_t lock; + unsigned long nr_running; + unsigned long nr_uninterruptible; + unsigned long long nr_switches; + struct list_head queue[PRIO_LIMIT]; + DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1); +#ifdef CONFIG_SMP + unsigned long nr_queued; +#endif +}; + +static struct global_rq grq; + +/* + * This is the main, per-CPU runqueue data structure. + * All this is protected by the global_rq lock. + */ +struct rq { +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ + unsigned char in_nohz_recently; +#endif +#endif + + /* Cached timestamp set by update_cpu_clock() */ + unsigned long long most_recent_timestamp; + struct task_struct *preempt_next; + struct task_struct *curr, *idle; + struct mm_struct *prev_mm; + + unsigned long queued_deadline; + int queued_prio; + + atomic_t nr_iowait; + + int cpu; /* cpu of this runqueue */ + int online; + +#ifdef CONFIG_SMP + struct root_domain *rd; + struct sched_domain *sd; + + struct list_head migration_queue; +#endif + + u64 clock; +#ifdef CONFIG_SCHEDSTATS + + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_switch; + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; + + /* BKL stats */ + unsigned int bkl_count; +#endif +}; + +static DEFINE_PER_CPU(struct rq, runqueues) ____cacheline_aligned_in_smp; +static DEFINE_MUTEX(sched_hotcpu_mutex); + +#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_var_t span; + cpumask_var_t online; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_var_t rto_mask; + atomic_t rto_count; +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + /* + * Preferred wake up cpu nominated by sched_mc balance that will be + * used when most cpus are idle in the system indicating overall very + * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2) + */ + unsigned int sched_mc_preferred_wakeup_cpu; +#endif +}; + +/* + * 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 + +static inline int cpu_of(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq->cpu; +#else + return 0; +#endif +} + +/* + * The domain tree (rq->sd) is protected by RCU's quiescent state transition. + * See detach_destroy_domains: synchronize_sched for details. + * + * The domain tree of any CPU may only be accessed from within + * preempt-disabled sections. + */ +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + +#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) +#define this_rq() (&__get_cpu_var(runqueues)) +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) + +#include "sched_stats.h" + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_switch +# define finish_arch_switch(prev) do { } while (0) +#endif + +/* + * This will cost if schedstats is enabled since it's done under lock. + */ +static inline void update_rq_clock(struct rq *rq) +{ +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + rq->clock = sched_clock_cpu(cpu_of(rq)); +#endif +} + +static inline int task_running(struct task_struct *p) +{ + return (!!p->oncpu); +} + +static inline void grq_lock(void) + __acquires(grq.lock) +{ + spin_lock(&grq.lock); +} + +static inline void grq_unlock(void) + __releases(grq.lock) +{ + spin_unlock(&grq.lock); +} + +static inline void grq_lock_irq(void) + __acquires(grq.lock) +{ + spin_lock_irq(&grq.lock); +} + +static inline void time_lock_rq(struct rq *rq) + __acquires(grq.lock) +{ + grq_lock(); + update_rq_clock(rq); +} + +static inline void grq_unlock_irq(void) + __releases(grq.lock) +{ + spin_unlock_irq(&grq.lock); +} + +static inline void grq_lock_irqsave(unsigned long *flags) + __acquires(grq.lock) +{ + local_irq_save(*flags); + spin_lock(&grq.lock); +} + +static inline void grq_unlock_irqrestore(unsigned long *flags) + __releases(grq.lock) +{ + spin_unlock(&grq.lock); + local_irq_restore(*flags); +} + +static inline struct rq +*task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + grq_lock_irqsave(flags); + return task_rq(p); +} + +static inline struct rq +*time_task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + struct rq *rq; + + grq_lock_irqsave(flags); + rq = task_rq(p); + update_rq_clock(rq); + return rq; +} + +static inline void task_grq_unlock(unsigned long *flags) + __releases(grq.lock) +{ + grq_unlock_irqrestore(flags); +} + +/** + * grunqueue_is_locked + * + * Returns true if the global runqueue is locked. + * This interface allows printk to be called with the runqueue lock + * held and know whether or not it is OK to wake up the klogd. + */ +int grunqueue_is_locked(void) +{ + return spin_is_locked(&grq.lock); +} + +void grq_unlock_wait(void) + __releases(grq.lock) +{ + smp_mb(); /* spin-unlock-wait is not a full memory barrier */ + spin_unlock_wait(&grq.lock); +} + +static inline void time_grq_lock(struct rq *rq, unsigned long *flags) + __acquires(grq.lock) +{ + local_irq_save(*flags); + time_lock_rq(rq); +} + +static inline struct rq *__task_grq_lock(struct task_struct *p) + __acquires(grq.lock) +{ + grq_lock(); + return task_rq(p); +} + +static inline void __task_grq_unlock(void) + __releases(grq.lock) +{ + grq_unlock(); +} + +#ifndef __ARCH_WANT_UNLOCKED_CTXSW +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + grq.lock.owner = current; +#endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_); + + grq_unlock_irq(); +} + +#else /* __ARCH_WANT_UNLOCKED_CTXSW */ + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + grq_unlock_irq(); +#else + grq_unlock(); +#endif +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ + smp_wmb(); +#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_enable(); +#endif +} +#endif /* __ARCH_WANT_UNLOCKED_CTXSW */ + +/* + * A task that is queued will be on the grq run list. + * A task that is not running or queued will not be on the grq run list. + * A task that is currently running will have ->oncpu set. + * The only time a task will be both queued and running by these definitions + * is during schedule, and all under grq_lock so it should never be seen. + */ + +static inline int task_queued(struct task_struct *p) +{ + return (!list_empty(&p->run_list)); +} + +static inline int queued_or_running(struct task_struct *p) +{ + return (task_queued(p) || task_running(p)); +} + +/* + * Removing from the global runqueue. Enter with grq locked. + */ +static void dequeue_task(struct task_struct *p) +{ + list_del_init(&p->run_list); + if (list_empty(grq.queue + p->prio)) + __clear_bit(p->prio, grq.prio_bitmap); +} + +static inline void reset_first_time_slice(struct task_struct *p) +{ + if (unlikely(p->first_time_slice)) + p->first_time_slice = 0; +} + +/* + * Adding to the global runqueue. Enter with grq locked. + */ +static inline void enqueue_task(struct task_struct *p) +{ + __set_bit(p->prio, grq.prio_bitmap); + list_add_tail(&p->run_list, grq.queue + p->prio); + sched_info_queued(p); +} + +/* Only idle task does this as a real time task*/ +static inline void enqueue_task_head(struct task_struct *p) +{ + __set_bit(p->prio, grq.prio_bitmap); + list_add(&p->run_list, grq.queue + p->prio); + sched_info_queued(p); +} + +/* No need to do anything, it happens on return_task */ +static inline void requeue_task(struct task_struct *p) +{ + sched_info_queued(p); +} + +/* + * Adjust timestamp when we move rqs. + */ +static void adjust_moved_rq(struct task_struct *p, struct rq *old_rq, + struct rq *new_rq) +{ +#ifdef CONFIG_SMP + /* Compensate for drifting sched_clock */ + p->timestamp = (p->timestamp - old_rq->most_recent_timestamp) + + new_rq->most_recent_timestamp; +#endif +} + +static inline int prio_ratio(struct task_struct *p) +{ + return prio_ratios[USER_PRIO(p->static_prio)]; +} + +/* + * task_timeslice - all tasks of all priorities get the exact same timeslice + * length. CPU distribution is handled by giving different deadlines to + * tasks of different priorities. + */ +static int task_timeslice(struct task_struct *p) +{ + return (rr_interval * prio_ratio(p) / 100); +} + +static inline void inc_nr_running(void) +{ + grq.nr_running++; +#ifdef CONFIG_SMP + grq.nr_queued++; +#endif +} + +static inline void dec_nr_running(void) +{ + grq.nr_running--; +#ifdef CONFIG_SMP + grq.nr_queued--; +#endif +} + +/* + * activate_idle_task - move idle task to the _front_ of runqueue. + */ +static inline void activate_idle_task(struct task_struct *p) +{ + enqueue_task_head(p); + inc_nr_running(); +} + +static inline int normal_prio(struct task_struct *p) +{ + if (has_rt_policy(p)) + return MAX_RT_PRIO - 1 - p->rt_priority; + return NORMAL_PRIO; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks as it will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/* + * activate_task - move a task to the runqueue. Enter with grq locked. + */ +static void activate_task(struct task_struct *p) +{ + unsigned long long now = sched_clock(); + + /* + * Sleep time is in units of nanosecs, so shift by 20 to get a + * milliseconds-range estimation of the amount of time that the task + * spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + if (p->state == TASK_UNINTERRUPTIBLE) + profile_hits(SLEEP_PROFILING, (void *)get_wchan(p), + (now - p->timestamp) >> 20); + } + + p->prio = effective_prio(p); + p->timestamp = now; + if (task_contributes_to_load(p)) + grq.nr_uninterruptible--; + enqueue_task(p); + inc_nr_running(); +} + +/* + * deactivate_task - If it's running, it's not on the grq and we can just + * decrement the nr_running. Otherwise we have to dequeue it. Enter with grq + * locked. The __ version is for returning tasks as the nr_queued and + * nr_running differ once taken by a runqueue. + */ +static inline void __deactivate_task(struct task_struct *p) +{ + if (task_contributes_to_load(p)) + grq.nr_uninterruptible++; +} + +static inline void deactivate_task(struct task_struct *p) +{ + __deactivate_task(p); + dec_nr_running(); +} + +/* + * Move a task off the global queue and take it to a cpu for it will + * become the running task. + */ +static inline void take_task(struct rq *rq, struct task_struct *p) +{ + set_task_cpu(p, rq->cpu); + dequeue_task(p); +#ifdef CONFIG_SMP + grq.nr_queued--; +#endif +} + +/* + * Returns a descheduling task to the grq runqueue unless it is being + * deactivated. + */ +static inline void return_task(struct task_struct *p, int deactivate) +{ + if (deactivate) { + __deactivate_task(p); + grq.nr_running--; + } else { +#ifdef CONFIG_SMP + grq.nr_queued++; +#endif + enqueue_task(p); + } +} + +/* + * resched_task - mark a task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +#ifdef CONFIG_SMP + +#ifndef tsk_is_polling +#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) +#endif + +static void resched_task(struct task_struct *p) +{ + int cpu; + + assert_spin_locked(&grq.lock); + + if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) + return; + + set_tsk_thread_flag(p, TIF_NEED_RESCHED); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(p)) + smp_send_reschedule(cpu); +} + +#else +static inline void resched_task(struct task_struct *p) +{ + assert_spin_locked(&grq.lock); + set_tsk_need_resched(p); +} +#endif + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +#ifdef CONFIG_SMP +struct migration_req { + struct list_head list; + + struct task_struct *task; + int dest_cpu; + + struct completion done; +}; + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + int running, on_rq; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_running()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_running(p)) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_grq_lock(p, &flags); + //trace_sched_wait_task(rq, p); /* Wtf is this for? */ + running = task_running(p); + on_rq = task_queued(p); + ncsw = 0; + if (!match_state || p->state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_grq_unlock(&flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(on_rq)) { + schedule_timeout_uninterruptible(1); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesnt have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} + +#endif + +/* + * We need to have a special definition for an idle runqueue when testing + * for preemption on CONFIG_HOTPLUG_CPU as the idle task may be scheduled as + * a realtime task in sched_idle_next. + */ +#ifdef CONFIG_HOTPLUG_CPU +#define rq_idle(rq) ((rq)->curr == (rq)->idle && !rt_task((rq)->curr)) +#else +#define rq_idle(rq) ((rq)->curr == (rq)->idle) +#endif + +static inline int task_preempts_curr(struct task_struct *p, struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int preempts = 0; + + if (rt_task(p)) { + if (p->prio < curr->prio) + preempts = 1; + } else if (p->prio == curr->prio && p->deadline < rq->queued_deadline) + preempts = 1; + return preempts; +} + +/* + * Wake up *any* suitable cpu to schedule this task. + */ +static void try_preempt(struct task_struct *p, struct rq *this_rq) +{ + unsigned long latest_deadline, cpu; + struct rq *lowest_prio_rq; + int lowest_prio; + cpumask_t tmp; + + if (cpu_isset(this_rq->cpu, p->cpus_allowed) && rq_idle(this_rq)) { + /* this_rq is idle, use that. */ + lowest_prio_rq = this_rq; + goto found_rq; + } + + /* Use this_rq as baseline and fall back on */ + latest_deadline = this_rq->queued_deadline; + lowest_prio = this_rq->queued_prio; + lowest_prio_rq = this_rq; + + cpus_and(tmp, cpu_online_map, p->cpus_allowed); + for_each_cpu_mask(cpu, tmp) { + unsigned long queued_deadline; + int queued_prio; + struct rq *rq; + + rq = cpu_rq(cpu); + + if (rq_idle(rq)) { + /* found an idle rq, use that one */ + lowest_prio_rq = rq; + goto found_rq; + } + + queued_prio = rq->queued_prio; + queued_deadline = rq->queued_deadline; + if (queued_prio < lowest_prio || + (queued_prio == lowest_prio && + queued_deadline > latest_deadline)) { + lowest_prio = queued_prio; + latest_deadline = queued_deadline; + lowest_prio_rq = rq; + } + } + + if (!task_preempts_curr(p, lowest_prio_rq)) + return; +found_rq: + resched_task(lowest_prio_rq->curr); + lowest_prio_rq->preempt_next = p; + return; +} + +/*** + * 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) +{ + int cpu, this_cpu, success = 0; + unsigned long flags; + long old_state; + struct rq *rq; + + rq = time_task_grq_lock(p, &flags); + old_state = p->state; + if (!(old_state & state)) + goto out_unlock; + + if (queued_or_running(p)) + goto out_running; + + cpu = task_cpu(p); + this_cpu = smp_processor_id(); + + /* + * Sync wakeups (i.e. those types of wakeups where the waker + * has indicated that it will leave the CPU in short order) + * don't trigger a preemption, if the woken up task will run on + * this cpu. (in this case the 'I will reschedule' promise of + * the waker guarantees that the freshly woken up task is going + * to be considered on this CPU.) + */ + activate_task(p); + if (!sync || cpu != this_cpu) + try_preempt(p, rq); + success = 1; + +out_running: + p->state = TASK_RUNNING; +out_unlock: + task_grq_unlock(&flags); + return success; +} + +int wake_up_process(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + */ +void sched_fork(struct task_struct *p, int clone_flags) +{ + int cpu = get_cpu(); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + /* + * We mark the process as running here, but have not actually + * inserted it onto the runqueue yet. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; + set_task_cpu(p, cpu); + + /* + * Make sure we do not leak PI boosting priority to the child: + */ + p->prio = current->normal_prio; + + INIT_LIST_HEAD(&p->run_list); +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + if (unlikely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif + + p->oncpu = 0; + +#ifdef CONFIG_PREEMPT + /* Want to start with kernel preemption disabled. */ + task_thread_info(p)->preempt_count = 1; +#endif + if (unlikely(p->policy == SCHED_FIFO)) + goto out; + /* + * Share the timeslice between parent and child, thus the + * total amount of pending timeslices in the system doesn't change, + * resulting in more scheduling fairness. + */ + local_irq_disable(); + if (current->time_slice > 0) { + current->time_slice /= 2; + if (current->time_slice) + p->time_slice = current->time_slice; + else + p->time_slice = 1; + /* + * The remainder of the first timeslice might be recovered by + * the parent if the child exits early enough. + */ + p->first_time_slice = 1; + } else + p->time_slice = 0; + + p->timestamp = sched_clock(); + local_irq_enable(); +out: + put_cpu(); +} + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) +{ + struct rq *rq; + unsigned long flags; + int this_cpu, cpu; + + rq = time_task_grq_lock(p, &flags); + this_cpu = smp_processor_id(); + BUG_ON(p->state != TASK_RUNNING); + cpu = task_cpu(p); + + if (likely(cpu == this_cpu)) { + activate_task(p); + if (!(clone_flags & CLONE_VM)) { + /* + * The VM isn't cloned, so we're in a good position to + * do child-runs-first in anticipation of an exec. This + * usually avoids a lot of COW overhead. Make the + * parent's deadline slightly later so the child gets + * selected. + */ + p->parent->deadline += 1; + set_need_resched(); + } + } else { + /* Does this even happen?? */ + struct rq *this_rq = cpu_rq(this_cpu); + + adjust_moved_rq(p, this_rq, rq); + activate_task(p); + try_preempt(p, rq); + } + task_grq_unlock(&flags); +} + +/* + * Potentially available exiting-child timeslices are + * retrieved here - this way the parent does not get + * penalized for creating too many threads. + * + * (this cannot be used to 'generate' timeslices + * artificially, because any timeslice recovered here + * was given away by the parent in the first place.) + */ +void sched_exit(struct task_struct *p) +{ + struct task_struct *parent; + unsigned long flags; + struct rq *rq; + + parent = p->parent; + rq = task_grq_lock(parent, &flags); + if (p->first_time_slice > 0 && task_cpu(p) == task_cpu(parent)) { + parent->time_slice += p->time_slice; + if (unlikely(parent->time_slice > timeslice())) + parent->time_slice = timeslice(); + } + task_grq_unlock(&flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + struct hlist_node *node; + + hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + struct hlist_node *node; + + hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + fire_sched_out_preempt_notifiers(prev, next); + prepare_lock_switch(rq, next); + prepare_arch_switch(next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @rq: runqueue associated with task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + */ +static inline void finish_task_switch(struct rq *rq, struct task_struct *prev) + __releases(grq.lock) +{ + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * The test for TASK_DEAD must occur while the runqueue locks are + * still held, otherwise prev could be scheduled on another cpu, die + * there before we look at prev->state, and then the reference would + * be dropped twice. + * Manfred Spraul + */ + prev_state = prev->state; + finish_arch_switch(prev); + finish_lock_switch(rq, prev); + + fire_sched_in_preempt_notifiers(current); + if (mm) + mmdrop(mm); + if (unlikely(prev_state == TASK_DEAD)) { + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + put_task_struct(prev); + } +} + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage void schedule_tail(struct task_struct *prev) + __releases(grq.lock) +{ + struct rq *rq = this_rq(); + + finish_task_switch(rq, prev); +#ifdef __ARCH_WANT_UNLOCKED_CTXSW + /* In this case, finish_task_switch does not reenable preemption */ + preempt_enable(); +#endif + if (current->set_child_tid) + put_user(current->pid, current->set_child_tid); +} + +/* + * context_switch - switch to the new MM and the new + * thread's register state. + */ +static inline void +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(rq, prev, next); + mm = next->mm; + oldmm = prev->active_mm; + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_enter_lazy_cpu_mode(); + + if (unlikely(!mm)) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm(oldmm, mm, next); + + if (unlikely(!prev->mm)) { + prev->active_mm = NULL; + rq->prev_mm = oldmm; + } + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ +#ifndef __ARCH_WANT_UNLOCKED_CTXSW + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); +#endif + + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + + barrier(); + /* + * this_rq must be evaluated again because prev may have moved + * CPUs since it called schedule(), thus the 'rq' on its stack + * frame will be invalid. + */ + finish_task_switch(this_rq(), prev); +} + +/* + * nr_running, nr_uninterruptible and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, current number of uninterruptible-sleeping threads, total + * number of context switches performed since bootup. + */ +unsigned long nr_running(void) +{ + return grq.nr_running; +} + +unsigned long nr_uninterruptible(void) +{ + unsigned long nu = grq.nr_uninterruptible; + + if (unlikely (nu < 0)) + nu = 0; + return nu; +} + +unsigned long long nr_context_switches(void) +{ + return grq.nr_switches; +} + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += atomic_read(&cpu_rq(i)->nr_iowait); + + return sum; +} + +unsigned long nr_active(void) +{ + return nr_running() + nr_uninterruptible(); +} + +DEFINE_PER_CPU(struct kernel_stat, kstat); + +EXPORT_PER_CPU_SYMBOL(kstat); + +/* + * This is called on clock ticks and on context switches. + * Bank in p->sched_time the ns elapsed since the last tick or switch. + * CPU scheduler quota accounting is also performed here in microseconds. + * The value returned from sched_clock() occasionally gives bogus values so + * some sanity checking is required. + */ +static void +update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now, + int tick) +{ + long time_diff = now - p->last_ran; + + if (tick) { + /* + * Called from scheduler_tick() there should be less than two + * jiffies worth, and not negative/overflow. + */ + if (time_diff > JIFFIES_TO_NS(2)) + time_diff = JIFFIES_TO_NS(2); + else if (time_diff < 0) + time_diff = 0; + } else { + /* + * Called from context_switch there should be less than one + * jiffy worth, and not negative/overflow. + */ + if (time_diff > JIFFIES_TO_NS(1)) + time_diff = JIFFIES_TO_NS(1); + else if(time_diff < 0) + time_diff = 0; + } + /* time_slice accounting is done in usecs to avoid overflow on 32bit */ + if (p != rq->idle && p->policy != SCHED_FIFO) + p->time_slice -= time_diff / 1000; + p->sched_time += time_diff; + p->last_ran = rq->most_recent_timestamp = now; +} + +/* + * Return any ns on the sched_clock that have not yet been accounted in + * @p in case that task is currently running. + * + * Called with task_grq_lock() held on @rq. + */ +static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) +{ + u64 ns = 0; + + if (p == rq->curr) { + update_rq_clock(rq); + ns = sched_clock() - p->last_ran; + if ((s64)ns < 0) + ns = 0; + } + + return ns; +} + +unsigned long long task_delta_exec(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns = 0; + + rq = task_grq_lock(p, &flags); + ns = do_task_delta_exec(p, rq); + task_grq_unlock(&flags); + + return ns; +} + +/* + * Return accounted runtime for the task. + * In case the task is currently running, return the runtime plus current's + * pending runtime that have not been accounted yet. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns = 0; + + rq = task_grq_lock(p, &flags); + ns = p->se_sum_exec_runtime + do_task_delta_exec(p, rq); + task_grq_unlock(&flags); + + return ns; +} + +/* + * Return current->sched_time plus any more ns on the sched_clock + * that have not yet been banked. + */ +unsigned long long current_sched_time(const struct task_struct *p) +{ + unsigned long long ns; + unsigned long flags; + + local_irq_save(flags); + ns = p->sched_time + sched_clock() - p->last_ran; + local_irq_restore(flags); + + return ns; +} + +/* + * Return sum_exec_runtime for the thread group. + * In case the task is currently running, return the sum plus current's + * pending runtime that have not been accounted yet. + * + * Note that the thread group might have other running tasks as well, + * so the return value not includes other pending runtime that other + * running tasks might have. + */ +unsigned long long thread_group_sched_runtime(struct task_struct *p) +{ + struct task_cputime totals; + unsigned long flags; + struct rq *rq; + u64 ns; + + rq = task_grq_lock(p, &flags); + thread_group_cputime(p, &totals); + ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); + task_grq_unlock(&flags); + + return ns; +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t tmp; + + /* Add user time to process. */ + p->utime = cputime_add(p->utime, cputime); + p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); + account_group_user_time(p, cputime); + + /* Add user time to cpustat. */ + tmp = cputime_to_cputime64(cputime); + if (TASK_NICE(p) > 0) + cpustat->nice = cputime64_add(cpustat->nice, tmp); + else + cpustat->user = cputime64_add(cpustat->user, tmp); + + //cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); + /* Account for user time used */ + acct_update_integrals(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + cputime64_t tmp; + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + + tmp = cputime_to_cputime64(cputime); + + /* Add guest time to process. */ + p->utime = cputime_add(p->utime, cputime); + p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); + account_group_user_time(p, cputime); + p->gtime = cputime_add(p->gtime, cputime); + + /* Add guest time to cpustat. */ + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t tmp; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime, cputime_scaled); + return; + } + + /* Add system time to process. */ + p->stime = cputime_add(p->stime, cputime); + p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + tmp = cputime_to_cputime64(cputime); + if (hardirq_count() - hardirq_offset) + cpustat->irq = cputime64_add(cpustat->irq, tmp); + else if (softirq_count()) + cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + else + cpustat->system = cputime64_add(cpustat->system, tmp); + + //cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * Account for involuntary wait time. + * @steal: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t cputime64 = cputime_to_cputime64(cputime); + + cpustat->steal = cputime64_add(cpustat->steal, cputime64); +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +void account_idle_time(cputime_t cputime) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t cputime64 = cputime_to_cputime64(cputime); + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); + else + cpustat->idle = cputime64_add(cpustat->idle, cputime64); +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy = jiffies_to_cputime(1); + cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy); + struct rq *rq = this_rq(); + + if (user_tick) + account_user_time(p, one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, one_jiffy, + one_jiffy_scaled); + else + account_idle_time(one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + account_idle_time(jiffies_to_cputime(ticks)); +} + +#endif +/* This manages tasks that have run out of timeslice during a scheduler_tick */ +static void task_running_tick(struct rq *rq, struct task_struct *p) +{ + /* SCHED_FIFO tasks never run out of timeslice. */ + if (p->time_slice > 0 || p->policy == SCHED_FIFO) + return; + + /* p->time_slice <= 0 */ + if (likely(task_running(p))) { + requeue_task(p); + set_tsk_need_resched(p); + } +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. + */ +void scheduler_tick(void) +{ + unsigned long long now = sched_clock(); + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + struct task_struct *p; + + time_lock_rq(rq); + p = rq->curr; + update_cpu_clock(p, rq, now, 1); + if (!rq_idle(rq)) + task_running_tick(rq, p); + grq_unlock(); +} + +#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT) + +void add_preempt_count(int val) +{ + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; + preempt_count() += val; + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +} +EXPORT_SYMBOL(add_preempt_count); + +void sub_preempt_count(int val) +{ + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; + + preempt_count() -= val; +} +EXPORT_SYMBOL(sub_preempt_count); + +#endif + +/* + * Deadline is "now" in jiffies + (offset by priority). Setting the deadline + * is the key to everything. It distributes cpu fairly amongst tasks of the + * same nice value, it proportions cpu according to nice level, it means the + * task that last woke up the longest ago has the earliest deadline, thus + * ensuring that interactive tasks get low latency on wake up. + */ +static inline void time_slice_expired(struct task_struct *p) +{ + reset_first_time_slice(p); + p->time_slice = timeslice(); + p->deadline = jiffies + (prio_ratio(p) * rr_interval * HZ / 1000 / 100); +} + +static inline void check_deadline(struct task_struct *p) +{ + if (p->time_slice <= 0) + time_slice_expired(p); +} + +static inline int longest_deadline(void) +{ + return (prio_ratios[39] * rr_interval * HZ / 1000 / 100) + 1; +} + +/* + * O(n) lookup of all tasks in the global runqueue. The real brainfuck + * of lock contention and O(n). + */ +static inline struct +task_struct *earliest_deadline_task(struct rq *rq, struct task_struct *idle) +{ + unsigned long long_deadline, shortest_deadline; + struct task_struct *edt, *p; + struct list_head *queue; + int idx = 0; + + if (rq->preempt_next) { + if (likely(task_queued(rq->preempt_next))) { + edt = rq->preempt_next; + goto out_take; + } + } +retry: + idx = find_next_bit(grq.prio_bitmap, PRIO_LIMIT, idx); + queue = &grq.queue[idx]; + if (idx < MAX_RT_PRIO) { + /* We found rt tasks */ + list_for_each_entry(p, queue, run_list) { + if (cpu_isset(rq->cpu, p->cpus_allowed)) { + edt = p; + goto out_take; + } + } + } + if (unlikely(idx < NORMAL_PRIO)) { + /* More rt tasks, we couldn't take the lower prio ones */ + ++idx; + goto retry; + } + + /* No rt tasks found, find earliest deadline normal task */ + edt = idle; + if (unlikely(idx >= PRIO_LIMIT)) { + /* All rt tasks but none suitable for this cpu */ + goto out; + } + + long_deadline = shortest_deadline = longest_deadline(); + list_for_each_entry(p, queue, run_list) { + unsigned long deadline_diff; + /* Make sure cpu affinity is ok */ + if (!cpu_isset(rq->cpu, p->cpus_allowed)) + continue; + + deadline_diff = p->deadline - jiffies; + + /* Check for jiffy wrap! */ + if (unlikely(deadline_diff > long_deadline)) + deadline_diff = 0; + + /* Select the earliest deadline task now */ + if (edt == idle || deadline_diff < shortest_deadline) { + shortest_deadline = deadline_diff; + edt = p; + } + } + if (edt == idle) + goto out; +out_take: + take_task(rq, edt); +out: + return edt; +} + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + 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); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); + + if (regs) + show_regs(regs); + else + dump_stack(); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ + /* + * 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. + */ + if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) + __schedule_bug(prev); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +#ifdef CONFIG_SCHEDSTATS + if (unlikely(prev->lock_depth >= 0)) { + schedstat_inc(this_rq(), bkl_count); + schedstat_inc(prev, sched_info.bkl_count); + } +#endif +} + +/* + * schedule() is the main scheduler function. + */ +asmlinkage void __sched __schedule(void) +{ + struct task_struct *prev, *next, *idle; + int deactivate = 0, cpu; + unsigned long long now; + long *switch_count; + struct rq *rq; + + cpu = smp_processor_id(); + rq = this_rq(); + rcu_qsctr_inc(cpu); + prev = rq->curr; + switch_count = &prev->nivcsw; + + release_kernel_lock(prev); +need_resched_nonpreemptible: + + schedule_debug(prev); + idle = rq->idle; + /* + * The idle thread is not allowed to schedule! + * Remove this check after it has been exercised a bit. + */ + if (unlikely(prev == idle) && prev->state != TASK_RUNNING) { + printk(KERN_ERR "bad: scheduling from the idle thread!\n"); + dump_stack(); + } + + now = sched_clock(); + + grq_lock_irq(); + update_rq_clock(rq); + clear_tsk_need_resched(prev); + + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) + prev->state = TASK_RUNNING; + else + deactivate = 1; + switch_count = &prev->nvcsw; + } + + if (prev != idle) { + check_deadline(prev); + return_task(prev, deactivate); + } + + if (likely(grq.nr_running)) { + next = earliest_deadline_task(rq, idle); + rq->queued_deadline = next->deadline; + } else { + next = idle; + schedstat_inc(rq, sched_goidle); + } + + rq->preempt_next = NULL; + + prefetch(next); + prefetch_stack(next); + + update_cpu_clock(prev, rq, now, 0); + prev->timestamp = prev->last_ran = now; + rq->queued_prio = next->prio; + + if (likely(prev != next)) { + sched_info_switch(prev, next); + grq.nr_switches++; + next->oncpu = 1; + prev->oncpu = 0; + rq->curr = next; + ++*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 + grq_unlock_irq(); + + if (unlikely(reacquire_kernel_lock(current) < 0)) + goto need_resched_nonpreemptible; +} + +asmlinkage void __sched schedule(void) +{ +need_resched: + preempt_disable(); + __schedule(); + preempt_enable_no_resched(); + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) + goto need_resched; +} +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_SMP +int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) +{ + return 0; +} +#endif + +#ifdef CONFIG_PREEMPT +/* + * this is the entry point to schedule() from in-kernel preemption + * 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(); + + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(ti->preempt_count || irqs_disabled())) + return; + + do { + add_preempt_count(PREEMPT_ACTIVE); + schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} +EXPORT_SYMBOL(preempt_schedule); + +/* + * this is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage void __sched preempt_schedule_irq(void) +{ + struct thread_info *ti = current_thread_info(); + + /* Catch callers which need to be fixed */ + BUG_ON(ti->preempt_count || !irqs_disabled()); + + do { + add_preempt_count(PREEMPT_ACTIVE); + local_irq_enable(); + schedule(); + local_irq_disable(); + sub_preempt_count(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} + +#endif /* CONFIG_PREEMPT */ + +int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, + void *key) +{ + return try_to_wake_up(curr->private, mode, sync); +} +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 + * 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 + * zero in this (rare) case, and we handle it by continuing to scan the queue. + */ +void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int sync, void *key) +{ + struct list_head *tmp, *next; + + list_for_each_safe(tmp, next, &q->task_list) { + wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list); + unsigned flags = curr->flags; + + if (curr->func(curr, mode, sync, key) && + (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + break; + } +} + +/** + * __wake_up - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: is directly passed to the wakeup function + */ +void __wake_up(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(__wake_up); + +/* + * Same as __wake_up but called with the spinlock in wait_queue_head_t held. + */ +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +{ + __wake_up_common(q, mode, 1, 0, NULL); +} + +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +{ + __wake_up_common(q, mode, 1, 0, key); +} + +/** + * __wake_up_sync_key - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: opaque value to be passed to wakeup targets + * + * The sync wakeup differs that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + */ +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + int sync = 1; + + if (unlikely(!q)) + return; + + if (unlikely(!nr_exclusive)) + sync = 0; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, sync, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(__wake_up_sync_key); + +/** + * __wake_up_sync - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * + * The sync wakeup differs that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + */ +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + unsigned long flags; + int sync = 1; + + if (unlikely(!q)) + return; + + if (unlikely(!nr_exclusive)) + sync = 0; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, sync, NULL); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ + +/** + * complete: - signals a single thread waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up a single thread waiting on this completion. Threads will be + * awakened in the same order in which they were queued. + * + * See also complete_all(), wait_for_completion() and related routines. + */ +void complete(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done++; + __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete); + +/** + * complete_all: - signals all threads waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up all threads waiting on this particular completion event. + */ +void complete_all(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; + __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete_all); + +static inline long __sched +do_wait_for_common(struct completion *x, long timeout, int state) +{ + if (!x->done) { + DECLARE_WAITQUEUE(wait, current); + + wait.flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_tail(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); + spin_unlock_irq(&x->wait.lock); + timeout = schedule_timeout(timeout); + spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); + __remove_wait_queue(&x->wait, &wait); + if (!x->done) + return timeout; + } + x->done--; + return timeout ?: 1; +} + +static long __sched +wait_for_common(struct completion *x, long timeout, int state) +{ + might_sleep(); + + spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, timeout, state); + spin_unlock_irq(&x->wait.lock); + return timeout; +} + +/** + * wait_for_completion: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. + * + * See also similar routines (i.e. wait_for_completion_timeout()) with timeout + * and interrupt capability. Also see complete(). + */ +void __sched wait_for_completion(struct completion *x) +{ + wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion); + +/** + * wait_for_completion_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. + */ +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_timeout); + +/** + * wait_for_completion_interruptible: - waits for completion of a task (w/intr) + * @x: holds the state of this particular completion + * + * This waits for completion of a specific task to be signaled. It is + * interruptible. + */ +int __sched wait_for_completion_interruptible(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_interruptible); + +/** + * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. It is interruptible. The timeout is in jiffies. + */ +unsigned long __sched +wait_for_completion_interruptible_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); + +/** + * wait_for_completion_killable: - waits for completion of a task (killable) + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It can be + * interrupted by a kill signal. + */ +int __sched wait_for_completion_killable(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_killable); + +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Returns: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +bool try_wait_for_completion(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + else + x->done--; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(try_wait_for_completion); + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Returns: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +bool completion_done(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(completion_done); + +static long __sched +sleep_on_common(wait_queue_head_t *q, int state, long timeout) +{ + unsigned long flags; + wait_queue_t wait; + + init_waitqueue_entry(&wait, current); + + __set_current_state(state); + + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, &wait); + spin_unlock(&q->lock); + timeout = schedule_timeout(timeout); + spin_lock_irq(&q->lock); + __remove_wait_queue(q, &wait); + spin_unlock_irqrestore(&q->lock, flags); + + return timeout; +} + +void __sched interruptible_sleep_on(wait_queue_head_t *q) +{ + sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} +EXPORT_SYMBOL(interruptible_sleep_on); + +long __sched +interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) +{ + return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); +} +EXPORT_SYMBOL(interruptible_sleep_on_timeout); + +void __sched sleep_on(wait_queue_head_t *q) +{ + sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} +EXPORT_SYMBOL(sleep_on); + +long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) +{ + return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); +} +EXPORT_SYMBOL(sleep_on_timeout); + +#ifdef CONFIG_RT_MUTEXES + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task + * @prio: prio value (kernel-internal form) + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance logic. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + unsigned long flags; + int queued, oldprio; + struct rq *rq; + + BUG_ON(prio < 0 || prio > MAX_PRIO); + + rq = time_task_grq_lock(p, &flags); + + oldprio = p->prio; + queued = task_queued(p); + if (queued) + dequeue_task(p); + p->prio = prio; + if (queued) { + enqueue_task(p); + try_preempt(p, rq); + } + + /* + * 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 (task_running(p) && p->prio > oldprio) + resched_task(p); + task_grq_unlock(&flags); +} + +#endif + +/* + * Adjust the deadline for when the priority is to change, before it's + * changed. + */ +static void adjust_deadline(struct task_struct *p, int new_prio) +{ + p->deadline += prio_ratios[USER_PRIO(new_prio)] - prio_ratio(p); +} + +void set_user_nice(struct task_struct *p, long nice) +{ + int queued, delta, new_static; + unsigned long flags; + struct rq *rq; + + if (TASK_NICE(p) == nice || nice < -20 || nice > 19) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = time_task_grq_lock(p, &flags); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * not SCHED_NORMAL/SCHED_BATCH: + */ + if (has_rt_policy(p)) { + p->static_prio = NICE_TO_PRIO(nice); + goto out_unlock; + } + queued = task_queued(p); + /* + * If p is actually running, we don't need to do anything when + * changing the priority because the grq is unaffected. + */ + if (queued) + dequeue_task(p); + + new_static = NICE_TO_PRIO(nice); + delta = new_static - p->static_prio; + adjust_deadline(p, new_static); + p->static_prio = new_static; + p->prio = effective_prio(p); + + if (queued) + enqueue_task(p); + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + if (task_running(p) && delta > 0) + resched_task(p); + else if (queued && !task_running(p) && delta < 0) + try_preempt(p, rq); +out_unlock: + task_grq_unlock(&flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = 20 - nice; + + return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + if (increment < -40) + increment = -40; + if (increment > 40) + increment = 40; + + nice = PRIO_TO_NICE(current->static_prio) + increment; + if (nice < -20) + nice = -20; + if (nice > 19) + nice = 19; + + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * This is the priority value as seen by users in /proc. + * RT tasks are offset by -100. Normal tasks are centered + * around 0, value goes from 0 to +100. + */ +int task_prio(const struct task_struct *p) +{ + int delta, prio = p->prio - MAX_RT_PRIO; + + if (prio < 0) + goto out; + + delta = (p->deadline - jiffies) * 100 / prio_ratios[39]; + if (delta > 100) + delta = 100; + else if (delta < 0) + delta = 0; + prio += delta; +out: + return prio; +} + +/** + * task_nice - return the nice value of a given task. + * @p: the task in question. + */ +int task_nice(const struct task_struct *p) +{ + return TASK_NICE(p); +} +EXPORT_SYMBOL_GPL(task_nice); + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + */ +int idle_cpu(int cpu) +{ + return cpu_curr(cpu) == cpu_rq(cpu)->idle; +} + +/** + * idle_task - return the idle task for a given cpu. + * @cpu: the processor in question. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + */ +static inline struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* Actually do priority change: must hold grq lock. */ +static void __setscheduler(struct task_struct *p, int policy, int prio) +{ + BUG_ON(task_queued(p)); + + p->policy = policy; + p->rt_priority = prio; + p->normal_prio = normal_prio(p); + /* we are holding p->pi_lock already */ + p->prio = rt_mutex_getprio(p); +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (cred->euid == pcred->euid || + cred->euid == pcred->uid); + rcu_read_unlock(); + return match; +} + +static int __sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param, bool user) +{ + int queued, retval, oldprio, oldpolicy = -1; + unsigned long flags; + struct rq *rq; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); +recheck: + /* double check policy once rq lock held */ + if (policy < 0) + policy = oldpolicy = p->policy; + else if (policy != SCHED_FIFO && policy != SCHED_RR && + policy != SCHED_NORMAL && policy != SCHED_BATCH) + return -EINVAL; + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and + * SCHED_BATCH is 0. + */ + if (param->sched_priority < 0 || + (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) + return -EINVAL; + if (is_rt_policy(policy) != (param->sched_priority != 0)) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (is_rt_policy(policy)) { + unsigned long rlim_rtprio; + unsigned long flags; + + if (!lock_task_sighand(p, &flags)) + return -ESRCH; + rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; + unlock_task_sighand(p, &flags); + + /* can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* can't increase priority */ + if (param->sched_priority > p->rt_priority && + param->sched_priority > rlim_rtprio) + return -EPERM; + } + + /* can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + } + + retval = security_task_setscheduler(p, policy, param); + if (retval) + return retval; + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + */ + spin_lock_irqsave(&p->pi_lock, flags); + /* + * To be able to change p->policy safely, the apropriate + * runqueue lock must be held. + */ + rq = __task_grq_lock(p); + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + __task_grq_unlock(); + spin_unlock_irqrestore(&p->pi_lock, flags); + policy = oldpolicy = -1; + goto recheck; + } + update_rq_clock(rq); + queued = task_queued(p); + if (queued) + dequeue_task(p); + oldprio = p->prio; + __setscheduler(p, policy, param->sched_priority); + /* + * 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 (task_running(p) && p->prio > oldprio) + resched_task(p); + if (queued) { + enqueue_task(p); + try_preempt(p, rq); + } + __task_grq_unlock(); + spin_unlock_irqrestore(&p->pi_lock, flags); + + rt_mutex_adjust_pi(p); + + return 0; +} + +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, true); +} + +EXPORT_SYMBOL_GPL(sched_setscheduler); + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, false); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setscheduler(p, policy, &lparam); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @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) +{ + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, -1, param); +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval = -EINVAL; + + if (pid < 0) + goto out_nounlock; + + retval = -ESRCH; + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy; + } + read_unlock(&tasklist_lock); + +out_nounlock: + return retval; +} + +/** + * sys_sched_getscheduler - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp; + struct task_struct *p; + int retval = -EINVAL; + + if (!param || pid < 0) + goto out_nounlock; + + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + lp.sched_priority = p->rt_priority; + read_unlock(&tasklist_lock); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + +out_nounlock: + return retval; + +out_unlock: + read_unlock(&tasklist_lock); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + get_online_cpus(); + read_lock(&tasklist_lock); + + p = find_process_by_pid(pid); + if (!p) { + read_unlock(&tasklist_lock); + 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 + * usage count and then drop tasklist_lock. + */ + get_task_struct(p); + read_unlock(&tasklist_lock); + + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) + goto out_unlock; + + retval = security_task_setscheduler(p, 0, NULL); + if (retval) + goto out_unlock; + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); + again: + retval = set_cpus_allowed_ptr(p, new_mask); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_unlock: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + put_task_struct(p); + put_online_cpus(); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + cpumask_t *new_mask) +{ + if (len < sizeof(cpumask_t)) { + memset(new_mask, 0, sizeof(cpumask_t)); + } else if (len > sizeof(cpumask_t)) { + len = sizeof(cpumask_t); + } + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + + +/** + * sys_sched_setaffinity - set the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new cpu mask + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, cpumask_t *mask) +{ + struct task_struct *p; + int retval; + + mutex_lock(&sched_hotcpu_mutex); + read_lock(&tasklist_lock); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + cpus_and(*mask, p->cpus_allowed, cpu_online_map); + +out_unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&sched_hotcpu_mutex); + if (retval) + return retval; + + return 0; +} + +/** + * sys_sched_getaffinity - get the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current cpu mask + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if (len < cpumask_size()) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + if (copy_to_user(user_mask_ptr, mask, cpumask_size())) + ret = -EFAULT; + else + ret = cpumask_size(); + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. If there are no + * other threads running on this CPU then this function will return. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct task_struct *p; + + grq_lock_irq(); + p = current; + schedstat_inc(this_rq(), yld_count); + time_slice_expired(p); + requeue_task(p); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(grq.lock); + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); + _raw_spin_unlock(&grq.lock); + preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +static void __cond_resched(void) +{ +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP + __might_sleep(__FILE__, __LINE__); +#endif + /* + * The BKS might be reacquired before we have dropped + * PREEMPT_ACTIVE, which could trigger a second + * cond_resched() call. + */ + do { + add_preempt_count(PREEMPT_ACTIVE); + schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + } while (need_resched()); +} + +int __sched _cond_resched(void) +{ + if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) && + system_state == SYSTEM_RUNNING) { + __cond_resched(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(_cond_resched); + +/* + * 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 + * 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 (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched && need_resched()) + __cond_resched(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(cond_resched_lock); + +int __sched cond_resched_softirq(void) +{ + BUG_ON(!in_softirq()); + + if (need_resched() && system_state == SYSTEM_RUNNING) { + local_bh_enable(); + __cond_resched(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(cond_resched_softirq); + +/** + * yield - yield the current processor to other threads. + * + * This is a shortcut for kernel-space yielding - it marks the + * thread runnable and calls sys_sched_yield(). + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/* + * 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 + * has set its backing_dev_info: the queue against which it should throttle) + */ +void __sched io_schedule(void) +{ + struct rq *rq = &__raw_get_cpu_var(runqueues); + + delayacct_blkio_start(); + atomic_inc(&rq->nr_iowait); + schedule(); + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); +} +EXPORT_SYMBOL(io_schedule); + +long __sched io_schedule_timeout(long timeout) +{ + struct rq *rq = &__raw_get_cpu_var(runqueues); + long ret; + + delayacct_blkio_start(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + return ret; +} + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * this syscall returns the maximum rt_priority that can be used + * by a given scheduling class. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * this syscall returns the minimum rt_priority that can be used + * by a given scheduling class. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + ret = 0; + } + return ret; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + int retval = -EINVAL; + struct timespec t; + + if (pid < 0) + goto out_nounlock; + + retval = -ESRCH; + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + t = ns_to_timespec(p->policy == SCHED_FIFO ? 0 : + MS_TO_NS(task_timeslice(p))); + read_unlock(&tasklist_lock); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; +out_nounlock: + return retval; +out_unlock: + read_unlock(&tasklist_lock); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + unsigned state; + + state = p->state ? __ffs(p->state) + 1 : 0; + 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(KERN_CONT " running "); + else + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); +#else + if (state == TASK_RUNNING) + printk(KERN_CONT " running task "); + else + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); +#endif +#ifdef CONFIG_DEBUG_STACK_USAGE + free = stack_not_used(p); +#endif + printk(KERN_CONT "%5lu %5d %6d\n", free, + task_pid_nr(p), task_pid_nr(p->real_parent)); + + show_stack(p, NULL); +} + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + read_lock(&tasklist_lock); + do_each_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take alot of time: + */ + touch_nmi_watchdog(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } while_each_thread(g, p); + + touch_all_softlockup_watchdogs(); + + read_unlock(&tasklist_lock); + /* + * Only show locks if all tasks are dumped: + */ + if (state_filter == -1) + debug_show_all_locks(); +} + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void __cpuinit init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + idle->timestamp = idle->last_ran = sched_clock(); + idle->state = TASK_RUNNING; + idle->cpus_allowed = cpumask_of_cpu(cpu); + grq_lock_irqsave(&flags); + set_task_cpu(idle, cpu); + rq->curr = rq->idle = idle; + idle->oncpu = 1; + grq_unlock_irqrestore(&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 +} + +/* + * In a system that switches off the HZ timer nohz_cpu_mask + * indicates which cpus entered this state. This is used + * in the rcu update to wait only for active cpus. For system + * which do not switch off the HZ timer nohz_cpu_mask should + * always be CPU_BITS_NONE. + */ +cpumask_var_t nohz_cpu_mask; + +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ +static struct { + atomic_t load_balancer; + cpumask_var_t cpu_mask; +} nohz ____cacheline_aligned = { + .load_balancer = ATOMIC_INIT(-1), +}; + +/* + * This routine will try to nominate the ilb (idle load balancing) + * owner among the cpus whose ticks are stopped. ilb owner will do the idle + * load balancing on behalf of all those cpus. If all the cpus in the system + * go into this tickless mode, then there will be no ilb owner (as there is + * no need for one) and all the cpus will sleep till the next wakeup event + * arrives... + * + * For the ilb owner, tick is not stopped. And this tick will be used + * for idle load balancing. ilb owner will still be part of + * nohz.cpu_mask.. + * + * While stopping the tick, this cpu will become the ilb owner if there + * is no other owner. And will be the owner till that cpu becomes busy + * or if all cpus in the system stop their ticks at which point + * there is no need for ilb owner. + * + * When the ilb owner becomes busy, it nominates another owner, during the + * next busy scheduler_tick() + */ +int select_nohz_load_balancer(int stop_tick) +{ + int cpu = smp_processor_id(); + + if (stop_tick) { + cpu_rq(cpu)->in_nohz_recently = 1; + + if (!cpu_active(cpu)) { + if (atomic_read(&nohz.load_balancer) != cpu) + return 0; + + /* + * If we are going offline and still the leader, + * give up! + */ + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + + return 0; + } + + cpumask_set_cpu(cpu, nohz.cpu_mask); + + /* time for ilb owner also to sleep */ + if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { + if (atomic_read(&nohz.load_balancer) == cpu) + atomic_set(&nohz.load_balancer, -1); + return 0; + } + + if (atomic_read(&nohz.load_balancer) == -1) { + /* make me the ilb owner */ + if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) + return 1; + } else if (atomic_read(&nohz.load_balancer) == cpu) + return 1; + } else { + if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) + return 0; + + cpumask_clear_cpu(cpu, nohz.cpu_mask); + + if (atomic_read(&nohz.load_balancer) == cpu) + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + } + return 0; +} + +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +void wake_up_idle_cpu(int cpu) +{ + struct task_struct *idle; + struct rq *rq; + + if (cpu == smp_processor_id()) + return; + + rq = cpu_rq(cpu); + idle = rq->idle; + + /* + * This is safe, as this function is called with the timer + * wheel base lock of (cpu) held. When the CPU is on the way + * to idle and has not yet set rq->curr to idle then it will + * be serialized on the timer wheel base lock and take the new + * timer into account automatically. + */ + if (unlikely(rq->curr != idle)) + return; + + /* + * We can set TIF_RESCHED on the idle task of the other CPU + * lockless. The worst case is that the other CPU runs the + * idle task through an additional NOOP schedule() + */ + set_tsk_need_resched(idle); + + /* NEED_RESCHED must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(idle)) + smp_send_reschedule(cpu); +} + +#endif /* CONFIG_NO_HZ */ + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * 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 + * call is not atomic; no spinlocks may be held. + */ +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + unsigned long flags; + struct rq *rq; + int ret = 0; + + rq = task_grq_lock(p, &flags); + if (!cpumask_intersects(new_mask, cpu_online_mask)) { + ret = -EINVAL; + goto out; + } + + if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && + !cpumask_equal(&p->cpus_allowed, new_mask))) { + ret = -EINVAL; + goto out; + } + + cpumask_copy(&p->cpus_allowed, new_mask); + p->rt_nr_cpus_allowed = cpumask_weight(new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + /* Can't run on this cpu, just resched it if it's running */ + if (task_running(p)) + set_tsk_need_resched(p); + +out: + task_grq_unlock(&flags); + + return ret; +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +#ifdef CONFIG_HOTPLUG_CPU +/* Schedules idle task to be the next runnable task on current CPU. + * It does so by boosting its priority to highest possible. + * Used by CPU offline code. + */ +void sched_idle_next(void) +{ + int this_cpu = smp_processor_id(); + struct rq *rq = cpu_rq(this_cpu); + struct task_struct *idle = rq->idle; + unsigned long flags; + + /* cpu has to be offline */ + BUG_ON(cpu_online(this_cpu)); + + /* + * Strictly not necessary since rest of the CPUs are stopped by now + * and interrupts disabled on the current cpu. + */ + grq_lock_irqsave(&flags); + + __setscheduler(idle, SCHED_FIFO, MAX_RT_PRIO - 1); + + update_rq_clock(rq); + activate_task(idle); + rq->preempt_next = idle; + resched_task(rq->curr); + + grq_unlock_irqrestore(&flags); +} + +/* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); + mmdrop(mm); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {0, }, +}; + +static struct ctl_table sd_ctl_root[] = { + { + .ctl_name = CTL_KERN, + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {0, }, +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + mode_t mode, proc_handler *proc_handler) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(13); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[11], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[12] is terminator */ + + return table; +} + +static ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +static void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_online_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_online_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + 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) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#else +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + cpumask_set_cpu(rq->cpu, rq->rd->online); + rq->online = 1; + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + cpumask_clear_cpu(rq->cpu, rq->rd->online); + rq->online = 0; + } +} + +/* + * This cpu is going down, so remove it from the cpus_allowed. No need to do + * anything special since they'll just move on next reschedule if they're + * running, and they're not on a cpu if they're in the global queue. + */ +static void remove_cpu(unsigned long cpu) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + + do_each_thread(t, p) { + cpu_clear(cpu, p->cpus_allowed); + if (cpus_equal(p->cpus_allowed, CPU_MASK_NONE)) + cpus_andnot(p->cpus_allowed, cpu_online_map, + cpumask_of_cpu(cpu)); + } while_each_thread(t, p); + + read_unlock(&tasklist_lock); +} + +/* + * This cpu is coming up so add it to the cpus_allowed. It means cpu affinity + * is not kept across freeze/thaw but who cares. + */ +static void add_cpu(unsigned long cpu) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + + do_each_thread(t, p) { + cpu_set(cpu, p->cpus_allowed); + } while_each_thread(t, p); + + read_unlock(&tasklist_lock); +} + +/* + * migration_call - callback that gets triggered when a CPU is added. + */ +static int __cpuinit +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + unsigned long flags; + struct rq *rq; + + switch (action) { + + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + break; + + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + /* Update our root-domain */ + rq = cpu_rq(cpu); + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + + set_rq_online(rq); + } + add_cpu(cpu); + grq_unlock_irqrestore(&flags); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + break; + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ + rq = cpu_rq(cpu); + /* Idle task back to normal (off runqueue, low prio) */ + grq_lock_irq(); + remove_cpu(cpu); + deactivate_task(rq->idle); + rq->idle->static_prio = MAX_PRIO; + __setscheduler(rq->idle, SCHED_NORMAL, 0); + grq_unlock_irq(); + cpuset_unlock(); + break; + + case CPU_DYING: + case CPU_DYING_FROZEN: + rq = cpu_rq(cpu); + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + grq_unlock_irqrestore(&flags); + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block __cpuinitdata migration_notifier = { + .notifier_call = migration_call, + .priority = 10 +}; + +int __init migration_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + /* Start one for the boot CPU: */ + err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); + BUG_ON(err == NOTIFY_BAD); + migration_call(&migration_notifier, CPU_ONLINE, cpu); + register_cpu_notifier(&migration_notifier); + + return 0; +} +early_initcall(migration_init); +#endif + +/* + * sched_domains_mutex serializes calls to arch_init_sched_domains, + * detach_destroy_domains and partition_sched_domains. + */ +static DEFINE_MUTEX(sched_domains_mutex); + +#ifdef CONFIG_SMP + +#ifdef CONFIG_SCHED_DEBUG + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + struct sched_group *group = sd->groups; + char str[256]; + + cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); + cpumask_clear(groupmask); + + 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 level %s\n", str, sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!group->__cpu_power) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: domain->cpu_power not " + "set\n"); + break; + } + + if (!cpumask_weight(sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (cpumask_intersects(groupmask, sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + + cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); + + printk(KERN_CONT " %s", str); + if (group->__cpu_power != SCHED_LOAD_SCALE) { + printk(KERN_CONT " (__cpu_power = %d)", + group->__cpu_power); + } + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + cpumask_var_t groupmask; + int level = 0; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { + printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); + return; + } + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, groupmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } + free_cpumask_var(groupmask); +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUPOWER | + SD_SHARE_PKG_RESOURCES)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_IDLE | + SD_WAKE_AFFINE | + SD_WAKE_BALANCE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + /* Does parent contain flags not in child? */ + /* WAKE_BALANCE is a subset of WAKE_AFFINE */ + if (cflags & SD_WAKE_AFFINE) + pflags &= ~SD_WAKE_BALANCE; + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUPOWER | + SD_SHARE_PKG_RESOURCES); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct root_domain *rd) +{ + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + grq_lock_irqsave(&flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rt yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_online_mask)) + set_rq_online(rq); + + grq_unlock_irqrestore(&flags); + + if (old_rd) + free_rootdomain(old_rd); +} + +static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) +{ + memset(rd, 0, sizeof(*rd)); + + if (bootmem) { + alloc_bootmem_cpumask_var(&def_root_domain.span); + alloc_bootmem_cpumask_var(&def_root_domain.online); + alloc_bootmem_cpumask_var(&def_root_domain.rto_mask); + return 0; + } + + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_online; + + return 0; + +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +static void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain, true); + + 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; + + if (init_rootdomain(rd, false) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +/* + * 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, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + sd = sd->parent; + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + rcu_assign_pointer(rq->sd, sd); +} + +/* cpus with isolated domains */ +static cpumask_var_t cpu_isolated_map; + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + cpulist_parse(str, cpu_isolated_map); + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +/* + * init_sched_build_groups takes the cpumask we wish to span, and a pointer + * to a function which identifies what group(along with sched group) a CPU + * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids + * (due to the fact that we keep track of groups covered with a struct cpumask). + * + * init_sched_build_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_power to 0. + */ +static void +init_sched_build_groups(const struct cpumask *span, + const struct cpumask *cpu_map, + int (*group_fn)(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, + struct cpumask *tmpmask), + struct cpumask *covered, struct cpumask *tmpmask) +{ + struct sched_group *first = NULL, *last = NULL; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct sched_group *sg; + int group = group_fn(i, cpu_map, &sg, tmpmask); + int j; + + if (cpumask_test_cpu(i, covered)) + continue; + + cpumask_clear(sched_group_cpus(sg)); + sg->__cpu_power = 0; + + for_each_cpu(j, span) { + if (group_fn(j, cpu_map, NULL, tmpmask) != group) + continue; + + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; +} + +#define SD_NODES_PER_DOMAIN 16 + +#ifdef CONFIG_NUMA + +/** + * find_next_best_node - find the next node to include in a sched_domain + * @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 + * finds the closest node not already in the @used_nodes map. + * + * Should use nodemask_t. + */ +static int find_next_best_node(int node, nodemask_t *used_nodes) +{ + int i, n, val, min_val, best_node = 0; + + min_val = INT_MAX; + + for (i = 0; i < nr_node_ids; i++) { + /* Start at @node */ + n = (node + i) % nr_node_ids; + + if (!nr_cpus_node(n)) + continue; + + /* Skip already used nodes */ + if (node_isset(n, *used_nodes)) + continue; + + /* Simple min distance search */ + val = node_distance(node, n); + + if (val < min_val) { + min_val = val; + best_node = n; + } + } + + node_set(best_node, *used_nodes); + return best_node; +} + +/** + * sched_domain_node_span - get a cpumask for a node's sched_domain + * @node: node whose cpumask we're constructing + * @span: resulting cpumask + * + * 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 void sched_domain_node_span(int node, struct cpumask *span) +{ + nodemask_t used_nodes; + int i; + + cpumask_clear(span); + nodes_clear(used_nodes); + + cpumask_or(span, span, cpumask_of_node(node)); + node_set(node, used_nodes); + + for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { + int next_node = find_next_best_node(node, &used_nodes); + + cpumask_or(span, span, cpumask_of_node(next_node)); + } +} +#endif /* CONFIG_NUMA */ + +int sched_smt_power_savings = 0, sched_mc_power_savings = 0; + +/* + * The cpus mask in sched_group and sched_domain hangs off the end. + * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space + * for nr_cpu_ids < CONFIG_NR_CPUS. + */ +struct static_sched_group { + struct sched_group sg; + DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); +}; + +struct static_sched_domain { + struct sched_domain sd; + DECLARE_BITMAP(span, CONFIG_NR_CPUS); +}; + +/* + * SMT sched-domains: + */ +#ifdef CONFIG_SCHED_SMT +static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); + +static int +cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *unused) +{ + if (sg) + *sg = &per_cpu(sched_group_cpus, cpu).sg; + return cpu; +} +#endif /* CONFIG_SCHED_SMT */ + +/* + * multi-core sched-domains: + */ +#ifdef CONFIG_SCHED_MC +static DEFINE_PER_CPU(struct static_sched_domain, core_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); +#endif /* CONFIG_SCHED_MC */ + +#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) +static int +cpu_to_core_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *mask) +{ + int group; + + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); + group = cpumask_first(mask); + if (sg) + *sg = &per_cpu(sched_group_core, group).sg; + return group; +} +#elif defined(CONFIG_SCHED_MC) +static int +cpu_to_core_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *unused) +{ + if (sg) + *sg = &per_cpu(sched_group_core, cpu).sg; + return cpu; +} +#endif + +static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); + +static int +cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *mask) +{ + int group; +#ifdef CONFIG_SCHED_MC + cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); + group = cpumask_first(mask); +#elif defined(CONFIG_SCHED_SMT) + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); + group = cpumask_first(mask); +#else + group = cpu; +#endif + if (sg) + *sg = &per_cpu(sched_group_phys, group).sg; + return group; +} + +#ifdef CONFIG_NUMA +/* + * The init_sched_build_groups can't handle what we want to do with node + * groups, so roll our own. Now each node has its own list of groups which + * gets dynamically allocated. + */ +static DEFINE_PER_CPU(struct static_sched_domain, node_domains); +static struct sched_group ***sched_group_nodes_bycpu; + +static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); + +static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, + struct cpumask *nodemask) +{ + int group; + + cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); + group = cpumask_first(nodemask); + + if (sg) + *sg = &per_cpu(sched_group_allnodes, group).sg; + return group; +} + +static void init_numa_sched_groups_power(struct sched_group *group_head) +{ + struct sched_group *sg = group_head; + int j; + + if (!sg) + return; + do { + for_each_cpu(j, sched_group_cpus(sg)) { + struct sched_domain *sd; + + sd = &per_cpu(phys_domains, j).sd; + if (j != cpumask_first(sched_group_cpus(sd->groups))) { + /* + * Only add "power" once for each + * physical package. + */ + continue; + } + + sg_inc_cpu_power(sg, sd->groups->__cpu_power); + } + sg = sg->next; + } while (sg != group_head); +} +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_NUMA +/* Free memory allocated for various sched_group structures */ +static void free_sched_groups(const struct cpumask *cpu_map, + struct cpumask *nodemask) +{ + int cpu, i; + + for_each_cpu(cpu, cpu_map) { + struct sched_group **sched_group_nodes + = sched_group_nodes_bycpu[cpu]; + + if (!sched_group_nodes) + continue; + + for (i = 0; i < nr_node_ids; i++) { + struct sched_group *oldsg, *sg = sched_group_nodes[i]; + + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) + continue; + + if (sg == NULL) + continue; + sg = sg->next; +next_sg: + oldsg = sg; + sg = sg->next; + kfree(oldsg); + if (oldsg != sched_group_nodes[i]) + goto next_sg; + } + kfree(sched_group_nodes); + sched_group_nodes_bycpu[cpu] = NULL; + } +} +#else /* !CONFIG_NUMA */ +static void free_sched_groups(const struct cpumask *cpu_map, + struct cpumask *nodemask) +{ +} +#endif /* CONFIG_NUMA */ + +/* + * Initialize sched groups cpu_power. + * + * cpu_power indicates the capacity of sched group, which is used while + * distributing the load between different sched groups in a sched domain. + * Typically cpu_power for all the groups in a sched domain will be same unless + * there are asymmetries in the topology. If there are asymmetries, group + * having more cpu_power will pickup more load compared to the group having + * less cpu_power. + * + * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents + * the maximum number of tasks a group can handle in the presence of other idle + * or lightly loaded groups in the same sched domain. + */ +static void init_sched_groups_power(int cpu, struct sched_domain *sd) +{ + struct sched_domain *child; + struct sched_group *group; + + WARN_ON(!sd || !sd->groups); + + if (cpu != cpumask_first(sched_group_cpus(sd->groups))) + return; + + child = sd->child; + + sd->groups->__cpu_power = 0; + + /* + * For perf policy, if the groups in child domain share resources + * (for example cores sharing some portions of the cache hierarchy + * or SMT), then set this domain groups cpu_power such that each group + * can handle only one task, when there are other idle groups in the + * same sched domain. + */ + if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) && + (child->flags & + (SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) { + sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE); + return; + } + + /* + * add cpu_power of each child group to this groups cpu_power + */ + group = child->groups; + do { + sg_inc_cpu_power(sd->groups, group->__cpu_power); + group = group->next; + } while (group != child->groups); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(sd, type) sd->name = #type +#else +# define SD_INIT_NAME(sd, type) do { } while (0) +#endif + +#define SD_INIT(sd, type) sd_init_##type(sd) + +#define SD_INIT_FUNC(type) \ +static noinline void sd_init_##type(struct sched_domain *sd) \ +{ \ + memset(sd, 0, sizeof(*sd)); \ + *sd = SD_##type##_INIT; \ + sd->level = SD_LV_##type; \ + SD_INIT_NAME(sd, type); \ +} + +SD_INIT_FUNC(CPU) +#ifdef CONFIG_NUMA + SD_INIT_FUNC(ALLNODES) + SD_INIT_FUNC(NODE) +#endif +#ifdef CONFIG_SCHED_SMT + SD_INIT_FUNC(SIBLING) +#endif +#ifdef CONFIG_SCHED_MC + SD_INIT_FUNC(MC) +#endif + +static int default_relax_domain_level = -1; + +static int __init setup_relax_domain_level(char *str) +{ + unsigned long val; + + val = simple_strtoul(str, NULL, 0); + if (val < SD_LV_MAX) + default_relax_domain_level = val; + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* turn off idle balance on this domain */ + sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE); + } +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int __build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + int i, err = -ENOMEM; + struct root_domain *rd; + cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered, + tmpmask; +#ifdef CONFIG_NUMA + cpumask_var_t domainspan, covered, notcovered; + struct sched_group **sched_group_nodes = NULL; + int sd_allnodes = 0; + + if (!alloc_cpumask_var(&domainspan, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&covered, GFP_KERNEL)) + goto free_domainspan; + if (!alloc_cpumask_var(¬covered, GFP_KERNEL)) + goto free_covered; +#endif + + if (!alloc_cpumask_var(&nodemask, GFP_KERNEL)) + goto free_notcovered; + if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL)) + goto free_nodemask; + if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL)) + goto free_this_sibling_map; + if (!alloc_cpumask_var(&send_covered, GFP_KERNEL)) + goto free_this_core_map; + if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + goto free_send_covered; + +#ifdef CONFIG_NUMA + /* + * Allocate the per-node list of sched groups + */ + sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *), + GFP_KERNEL); + if (!sched_group_nodes) { + printk(KERN_WARNING "Can not alloc sched group node list\n"); + goto free_tmpmask; + } +#endif + + rd = alloc_rootdomain(); + if (!rd) { + printk(KERN_WARNING "Cannot alloc root domain\n"); + goto free_sched_groups; + } + +#ifdef CONFIG_NUMA + sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes; +#endif + + /* + * Set up domains for cpus specified by the cpu_map. + */ + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = NULL, *p; + + cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); + +#ifdef CONFIG_NUMA + if (cpumask_weight(cpu_map) > + SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) { + sd = &per_cpu(allnodes_domains, i).sd; + SD_INIT(sd, ALLNODES); + set_domain_attribute(sd, attr); + cpumask_copy(sched_domain_span(sd), cpu_map); + cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); + p = sd; + sd_allnodes = 1; + } else + p = NULL; + + sd = &per_cpu(node_domains, i).sd; + SD_INIT(sd, NODE); + set_domain_attribute(sd, attr); + sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); + sd->parent = p; + if (p) + p->child = sd; + cpumask_and(sched_domain_span(sd), + sched_domain_span(sd), cpu_map); +#endif + + p = sd; + sd = &per_cpu(phys_domains, i).sd; + SD_INIT(sd, CPU); + set_domain_attribute(sd, attr); + cpumask_copy(sched_domain_span(sd), nodemask); + sd->parent = p; + if (p) + p->child = sd; + cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask); + +#ifdef CONFIG_SCHED_MC + p = sd; + sd = &per_cpu(core_domains, i).sd; + SD_INIT(sd, MC); + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), cpu_map, + cpu_coregroup_mask(i)); + sd->parent = p; + p->child = sd; + cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask); +#endif + +#ifdef CONFIG_SCHED_SMT + p = sd; + sd = &per_cpu(cpu_domains, i).sd; + SD_INIT(sd, SIBLING); + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), + topology_thread_cpumask(i), cpu_map); + sd->parent = p; + p->child = sd; + cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); +#endif + } + +#ifdef CONFIG_SCHED_SMT + /* Set up CPU (sibling) groups */ + for_each_cpu(i, cpu_map) { + cpumask_and(this_sibling_map, + topology_thread_cpumask(i), cpu_map); + if (i != cpumask_first(this_sibling_map)) + continue; + + init_sched_build_groups(this_sibling_map, cpu_map, + &cpu_to_cpu_group, + send_covered, tmpmask); + } +#endif + +#ifdef CONFIG_SCHED_MC + /* Set up multi-core groups */ + for_each_cpu(i, cpu_map) { + cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map); + if (i != cpumask_first(this_core_map)) + continue; + + init_sched_build_groups(this_core_map, cpu_map, + &cpu_to_core_group, + send_covered, tmpmask); + } +#endif + + /* Set up physical groups */ + for (i = 0; i < nr_node_ids; i++) { + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) + continue; + + init_sched_build_groups(nodemask, cpu_map, + &cpu_to_phys_group, + send_covered, tmpmask); + } + +#ifdef CONFIG_NUMA + /* Set up node groups */ + if (sd_allnodes) { + init_sched_build_groups(cpu_map, cpu_map, + &cpu_to_allnodes_group, + send_covered, tmpmask); + } + + for (i = 0; i < nr_node_ids; i++) { + /* Set up node groups */ + struct sched_group *sg, *prev; + int j; + + cpumask_clear(covered); + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) { + sched_group_nodes[i] = NULL; + continue; + } + + sched_domain_node_span(i, domainspan); + cpumask_and(domainspan, domainspan, cpu_map); + + sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, i); + if (!sg) { + printk(KERN_WARNING "Can not alloc domain group for " + "node %d\n", i); + goto error; + } + sched_group_nodes[i] = sg; + for_each_cpu(j, nodemask) { + struct sched_domain *sd; + + sd = &per_cpu(node_domains, j).sd; + sd->groups = sg; + } + sg->__cpu_power = 0; + cpumask_copy(sched_group_cpus(sg), nodemask); + sg->next = sg; + cpumask_or(covered, covered, nodemask); + prev = sg; + + for (j = 0; j < nr_node_ids; j++) { + int n = (i + j) % nr_node_ids; + + cpumask_complement(notcovered, covered); + cpumask_and(tmpmask, notcovered, cpu_map); + cpumask_and(tmpmask, tmpmask, domainspan); + if (cpumask_empty(tmpmask)) + break; + + cpumask_and(tmpmask, tmpmask, cpumask_of_node(n)); + if (cpumask_empty(tmpmask)) + continue; + + sg = kmalloc_node(sizeof(struct sched_group) + + cpumask_size(), + GFP_KERNEL, i); + if (!sg) { + printk(KERN_WARNING + "Can not alloc domain group for node %d\n", j); + goto error; + } + sg->__cpu_power = 0; + cpumask_copy(sched_group_cpus(sg), tmpmask); + sg->next = prev->next; + cpumask_or(covered, covered, tmpmask); + prev->next = sg; + prev = sg; + } + } +#endif + + /* Calculate CPU power for physical packages and nodes */ +#ifdef CONFIG_SCHED_SMT + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(cpu_domains, i).sd; + + init_sched_groups_power(i, sd); + } +#endif +#ifdef CONFIG_SCHED_MC + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(core_domains, i).sd; + + init_sched_groups_power(i, sd); + } +#endif + + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(phys_domains, i).sd; + + init_sched_groups_power(i, sd); + } + +#ifdef CONFIG_NUMA + for (i = 0; i < nr_node_ids; i++) + init_numa_sched_groups_power(sched_group_nodes[i]); + + if (sd_allnodes) { + struct sched_group *sg; + + cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, + tmpmask); + init_numa_sched_groups_power(sg); + } +#endif + + /* Attach the domains */ + for_each_cpu(i, cpu_map) { + struct sched_domain *sd; +#ifdef CONFIG_SCHED_SMT + sd = &per_cpu(cpu_domains, i).sd; +#elif defined(CONFIG_SCHED_MC) + sd = &per_cpu(core_domains, i).sd; +#else + sd = &per_cpu(phys_domains, i).sd; +#endif + cpu_attach_domain(sd, rd, i); + } + + err = 0; + +free_tmpmask: + free_cpumask_var(tmpmask); +free_send_covered: + free_cpumask_var(send_covered); +free_this_core_map: + free_cpumask_var(this_core_map); +free_this_sibling_map: + free_cpumask_var(this_sibling_map); +free_nodemask: + free_cpumask_var(nodemask); +free_notcovered: +#ifdef CONFIG_NUMA + free_cpumask_var(notcovered); +free_covered: + free_cpumask_var(covered); +free_domainspan: + free_cpumask_var(domainspan); +out: +#endif + return err; + +free_sched_groups: +#ifdef CONFIG_NUMA + kfree(sched_group_nodes); +#endif + goto free_tmpmask; + +#ifdef CONFIG_NUMA +error: + free_sched_groups(cpu_map, tmpmask); + free_rootdomain(rd); + goto free_tmpmask; +#endif +} + +static int build_sched_domains(const struct cpumask *cpu_map) +{ + return __build_sched_domains(cpu_map, NULL); +} + +static struct cpumask *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +static cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __attribute__((weak)) arch_update_cpu_topology(void) +{ + return 0; +} + +/* + * 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 struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); + if (!doms_cur) + doms_cur = fallback_doms; + cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); + dattr_cur = NULL; + err = build_sched_domains(doms_cur); + register_sched_domain_sysctl(); + + return err; +} + +static void arch_destroy_sched_domains(const struct cpumask *cpu_map, + struct cpumask *tmpmask) +{ + free_sched_groups(cpu_map, tmpmask); +} + +/* + * Detach sched domains from a group of cpus specified in cpu_map + * These cpus will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + /* Save because hotplug lock held. */ + static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); + int i; + + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + synchronize_sched(); + arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* fast path */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * 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'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 && + * ndoms_new == 1, and partition_sched_domains() will fallback to + * the single partition 'fallback_doms', it also forces the domains + * to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +/* FIXME: Change to struct cpumask *doms_new[] */ +void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(&doms_cur[i], &doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur + i); +match1: + ; + } + + if (doms_new == NULL) { + ndoms_cur = 0; + doms_new = fallback_doms; + cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < ndoms_cur && !new_topology; j++) { + if (cpumask_equal(&doms_new[i], &doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* no match - add a new doms_new */ + __build_sched_domains(doms_new + i, + dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != fallback_doms) + kfree(doms_cur); + kfree(dattr_cur); /* kfree(NULL) is safe */ + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +static void arch_reinit_sched_domains(void) +{ + get_online_cpus(); + + /* Destroy domains first to force the rebuild */ + partition_sched_domains(0, NULL, NULL); + + rebuild_sched_domains(); + put_online_cpus(); +} + +static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) +{ + unsigned int level = 0; + + if (sscanf(buf, "%u", &level) != 1) + return -EINVAL; + + /* + * level is always be positive so don't check for + * level < POWERSAVINGS_BALANCE_NONE which is 0 + * What happens on 0 or 1 byte write, + * need to check for count as well? + */ + + if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) + return -EINVAL; + + if (smt) + sched_smt_power_savings = level; + else + sched_mc_power_savings = level; + + arch_reinit_sched_domains(); + + return count; +} + +#ifdef CONFIG_SCHED_MC +static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + char *page) +{ + return sprintf(page, "%u\n", sched_mc_power_savings); +} +static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, + const char *buf, size_t count) +{ + return sched_power_savings_store(buf, count, 0); +} +static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, + sched_mc_power_savings_show, + sched_mc_power_savings_store); +#endif + +#ifdef CONFIG_SCHED_SMT +static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, + char *page) +{ + return sprintf(page, "%u\n", sched_smt_power_savings); +} +static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, + const char *buf, size_t count) +{ + return sched_power_savings_store(buf, count, 1); +} +static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, + sched_smt_power_savings_show, + sched_smt_power_savings_store); +#endif + +int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) +{ + int err = 0; + +#ifdef CONFIG_SCHED_SMT + if (smt_capable()) + err = sysfs_create_file(&cls->kset.kobj, + &attr_sched_smt_power_savings.attr); +#endif +#ifdef CONFIG_SCHED_MC + if (!err && mc_capable()) + err = sysfs_create_file(&cls->kset.kobj, + &attr_sched_mc_power_savings.attr); +#endif + return err; +} +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ + +#ifndef CONFIG_CPUSETS +/* + * Add online and remove offline CPUs from the scheduler domains. + * When cpusets are enabled they take over this function. + */ +static int update_sched_domains(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + partition_sched_domains(1, NULL, NULL); + return NOTIFY_OK; + + default: + return NOTIFY_DONE; + } +} +#endif + +static int update_runtime(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + return NOTIFY_OK; + + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + return NOTIFY_OK; + + default: + return NOTIFY_DONE; + } +} + +void __init sched_init_smp(void) +{ + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + +#if defined(CONFIG_NUMA) + sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), + GFP_KERNEL); + BUG_ON(sched_group_nodes_bycpu == NULL); +#endif + get_online_cpus(); + mutex_lock(&sched_domains_mutex); + arch_init_sched_domains(cpu_online_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + put_online_cpus(); + +#ifndef CONFIG_CPUSETS + /* XXX: Theoretical race here - CPU may be hotplugged now */ + hotcpu_notifier(update_sched_domains, 0); +#endif + + /* RT runtime code needs to handle some hotplug events */ + hotcpu_notifier(update_runtime, 0); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + BUG(); + free_cpumask_var(non_isolated_cpus); + + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + + /* + * Assume that every added cpu gives us slightly less overall latency + * allowing us to increase the base rr_interval, but in a non linear + * fashion. + */ + rr_interval *= 1 + ilog2(num_online_cpus()); +} +#else +void __init sched_init_smp(void) +{ +} +#endif /* CONFIG_SMP */ + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +void __init sched_init(void) +{ + int i; + int highest_cpu = 0; + + prio_ratios[0] = 100; + for (i = 1 ; i < PRIO_RANGE ; i++) + prio_ratios[i] = prio_ratios[i - 1] * 11 / 10; + +#ifdef CONFIG_SMP + init_defrootdomain(); + grq.nr_queued = 0; +#endif + spin_lock_init(&grq.lock); + for_each_possible_cpu(i) { + struct rq *rq; + + rq = cpu_rq(i); + rq->queued_deadline = 0; + rq->queued_prio = 0; + rq->preempt_next = NULL; + rq->cpu = i; +#ifdef CONFIG_SMP + rq->sd = NULL; + rq->rd = NULL; + rq->online = 0; + INIT_LIST_HEAD(&rq->migration_queue); + rq_attach_root(rq, &def_root_domain); +#endif + atomic_set(&rq->nr_iowait, 0); + highest_cpu = i; + } + grq.nr_running = grq.nr_uninterruptible = 0; + for (i = 0; i < PRIO_LIMIT; i++) + INIT_LIST_HEAD(grq.queue + i); + bitmap_zero(grq.prio_bitmap, PRIO_LIMIT); + /* delimiter for bitsearch */ + __set_bit(PRIO_LIMIT, grq.prio_bitmap); + +#ifdef CONFIG_SMP + nr_cpu_ids = highest_cpu + 1; +#endif + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#endif + +#ifdef CONFIG_RT_MUTEXES + plist_head_init(&init_task.pi_waiters, &init_task.pi_lock); +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + atomic_inc(&init_mm.mm_count); + enter_lazy_tlb(&init_mm, current); + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + + /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ + alloc_bootmem_cpumask_var(&nohz_cpu_mask); +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ + alloc_bootmem_cpumask_var(&nohz.cpu_mask); +#endif + alloc_bootmem_cpumask_var(&cpu_isolated_map); +#endif /* SMP */ +} + +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP +void __might_sleep(char *file, int line) +{ +#ifdef in_atomic + static unsigned long prev_jiffy; /* ratelimiting */ + + if ((in_atomic() || irqs_disabled()) && + system_state == SYSTEM_RUNNING && !oops_in_progress) { + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + printk(KERN_ERR "BUG: sleeping function called from invalid" + " context at %s:%d\n", file, line); + printk("in_atomic():%d, irqs_disabled():%d\n", + in_atomic(), irqs_disabled()); + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); + dump_stack(); + } +#endif +} +EXPORT_SYMBOL(__might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + int queued; + + read_lock_irq(&tasklist_lock); + + do_each_thread(g, p) { + if (!rt_task(p)) + continue; + + spin_lock_irqsave(&p->pi_lock, flags); + rq = __task_grq_lock(p); + + queued = task_queued(p); + if (queued) + dequeue_task(p); + __setscheduler(p, SCHED_NORMAL, 0); + if (queued) { + enqueue_task(p); + resched_task(rq->curr); + } + + __task_grq_unlock(); + spin_unlock_irqrestore(&p->pi_lock, flags); + } while_each_thread(g, p); + + read_unlock_irq(&tasklist_lock); +} + +#endif /* CONFIG_MAGIC_SYSRQ */ + +#ifdef CONFIG_IA64 +/* + * These functions are only useful for the IA64 MCA handling. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given cpu. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +/** + * set_curr_task - set the current task for a given cpu. + * @cpu: the processor in question. + * @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 + * 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 + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +cputime_t task_utime(struct task_struct *p) +{ + return p->utime; +} + +cputime_t task_stime(struct task_struct *p) +{ + return p->stime; +} +#else +cputime_t task_utime(struct task_struct *p) +{ + clock_t utime = cputime_to_clock_t(p->utime), + total = utime + cputime_to_clock_t(p->stime); + u64 temp; + + temp = (u64)nsec_to_clock_t(p->se_sum_exec_runtime); + + if (total) { + temp *= utime; + do_div(temp, total); + } + utime = (clock_t)temp; + + p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); + return p->prev_utime; +} + +cputime_t task_stime(struct task_struct *p) +{ + clock_t stime; + + stime = nsec_to_clock_t(p->se_sum_exec_runtime) - + cputime_to_clock_t(task_utime(p)); + + if (stime >= 0) + p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + + return p->prev_stime; +} +#endif + +inline cputime_t task_gtime(struct task_struct *p) +{ + return p->gtime; +} + +void __cpuinit init_idle_bootup_task(struct task_struct *idle) +{} + +#ifdef CONFIG_SCHED_DEBUG +void proc_sched_show_task(struct task_struct *p, struct seq_file *m) +{} + +void proc_sched_set_task(struct task_struct *p) +{} +#endif Index: linux-2.6.30-bfs/kernel/Makefile =================================================================== --- linux-2.6.30-bfs.orig/kernel/Makefile 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/Makefile 2009-08-26 19:38:31.266254662 +1000 @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ +obj-y = sched_bfs.o fork.o exec_domain.o panic.o printk.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ @@ -102,7 +102,7 @@ # me. I suspect most platforms don't need this, but until we know that for sure # I turn this off for IA-64 only. Andreas Schwab says it's also needed on m68k # to get a correct value for the wait-channel (WCHAN in ps). --davidm -CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer +CFLAGS_sched_bfs.o := $(PROFILING) -fno-omit-frame-pointer endif $(obj)/configs.o: $(obj)/config_data.h Index: linux-2.6.30-bfs/kernel/kthread.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/kthread.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/kthread.c 2009-08-26 19:38:31.291358031 +1000 @@ -15,7 +15,7 @@ #include #include -#define KTHREAD_NICE_LEVEL (-5) +#define KTHREAD_NICE_LEVEL (0) static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); @@ -180,7 +180,7 @@ } set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); - k->rt.nr_cpus_allowed = 1; + k->rt_nr_cpus_allowed = 1; k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); Index: linux-2.6.30-bfs/kernel/posix-cpu-timers.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/posix-cpu-timers.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/posix-cpu-timers.c 2009-08-26 19:38:31.316460632 +1000 @@ -249,7 +249,7 @@ do { times->utime = cputime_add(times->utime, t->utime); times->stime = cputime_add(times->stime, t->stime); - times->sum_exec_runtime += t->se.sum_exec_runtime; + times->sum_exec_runtime += t->se_sum_exec_runtime; t = next_thread(t); } while (t != tsk); @@ -516,7 +516,7 @@ void posix_cpu_timers_exit(struct task_struct *tsk) { cleanup_timers(tsk->cpu_timers, - tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); + tsk->utime, tsk->stime, tsk->se_sum_exec_runtime); } void posix_cpu_timers_exit_group(struct task_struct *tsk) @@ -1016,7 +1016,7 @@ struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); - if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { + if (!--maxfire || tsk->se_sum_exec_runtime < t->expires.sched) { tsk->cputime_expires.sched_exp = t->expires.sched; break; } @@ -1032,7 +1032,7 @@ unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur; if (hard != RLIM_INFINITY && - tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { + tsk->rt_timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { /* * At the hard limit, we just die. * No need to calculate anything else now. @@ -1040,7 +1040,7 @@ __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } - if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) { + if (tsk->rt_timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) { /* * At the soft limit, send a SIGXCPU every second. */ @@ -1356,7 +1356,7 @@ struct task_cputime task_sample = { .utime = tsk->utime, .stime = tsk->stime, - .sum_exec_runtime = tsk->se.sum_exec_runtime + .sum_exec_runtime = tsk->se_sum_exec_runtime }; if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) Index: linux-2.6.30-bfs/kernel/exit.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/exit.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/exit.c 2009-08-26 19:38:31.341453123 +1000 @@ -124,7 +124,7 @@ sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; + sig->sum_sched_runtime += tsk->se_sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -146,10 +146,10 @@ flush_sigqueue(&sig->shared_pending); taskstats_tgid_free(sig); /* - * Make sure ->signal can't go away under rq->lock, + * Make sure ->signal can't go away under grq.lock, * see account_group_exec_runtime(). */ - task_rq_unlock_wait(tsk); + grq_unlock_wait(); __cleanup_signal(sig); } } Index: linux-2.6.30-bfs/kernel/fork.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/fork.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/fork.c 2009-08-26 19:38:31.366700188 +1000 @@ -1204,7 +1204,7 @@ * parent's CPU). This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; - p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed; + p->rt_nr_cpus_allowed = current->rt_nr_cpus_allowed; if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) || !cpu_online(task_cpu(p)))) set_task_cpu(p, smp_processor_id()); Index: linux-2.6.30-bfs/mm/oom_kill.c =================================================================== --- linux-2.6.30-bfs.orig/mm/oom_kill.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/mm/oom_kill.c 2009-08-26 19:38:31.391837586 +1000 @@ -338,7 +338,7 @@ * all the memory it needs. That way it should be able to * exit() and clear out its resources quickly... */ - p->rt.time_slice = HZ; + p->time_slice = HZ; set_tsk_thread_flag(p, TIF_MEMDIE); force_sig(SIGKILL, p); Index: linux-2.6.30-bfs/init/Kconfig =================================================================== --- linux-2.6.30-bfs.orig/init/Kconfig 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/init/Kconfig 2009-08-26 19:38:31.417175153 +1000 @@ -435,179 +435,6 @@ config HAVE_UNSTABLE_SCHED_CLOCK bool -config GROUP_SCHED - bool "Group CPU scheduler" - depends on EXPERIMENTAL - default n - help - This feature lets CPU scheduler recognize task groups and control CPU - bandwidth allocation to such task groups. - In order to create a group from arbitrary set of processes, use - CONFIG_CGROUPS. (See Control Group support.) - -config FAIR_GROUP_SCHED - bool "Group scheduling for SCHED_OTHER" - depends on GROUP_SCHED - default GROUP_SCHED - -config RT_GROUP_SCHED - bool "Group scheduling for SCHED_RR/FIFO" - depends on EXPERIMENTAL - depends on GROUP_SCHED - default n - help - This feature lets you explicitly allocate real CPU bandwidth - to users or control groups (depending on the "Basis for grouping tasks" - setting below. If enabled, it will also make it impossible to - schedule realtime tasks for non-root users until you allocate - realtime bandwidth for them. - See Documentation/scheduler/sched-rt-group.txt for more information. - -choice - depends on GROUP_SCHED - prompt "Basis for grouping tasks" - default USER_SCHED - -config USER_SCHED - bool "user id" - help - This option will choose userid as the basis for grouping - tasks, thus providing equal CPU bandwidth to each user. - -config CGROUP_SCHED - bool "Control groups" - depends on CGROUPS - help - This option allows you to create arbitrary task groups - using the "cgroup" pseudo filesystem and control - the cpu bandwidth allocated to each such task group. - Refer to Documentation/cgroups/cgroups.txt for more - information on "cgroup" pseudo filesystem. - -endchoice - -menuconfig CGROUPS - boolean "Control Group support" - help - This option adds support for grouping sets of processes together, for - use with process control subsystems such as Cpusets, CFS, memory - controls or device isolation. - See - - Documentation/scheduler/sched-design-CFS.txt (CFS) - - Documentation/cgroups/ (features for grouping, isolation - and resource control) - - Say N if unsure. - -if CGROUPS - -config CGROUP_DEBUG - bool "Example debug cgroup subsystem" - depends on CGROUPS - default n - help - This option enables a simple cgroup subsystem that - exports useful debugging information about the cgroups - framework. - - Say N if unsure. - -config CGROUP_NS - bool "Namespace cgroup subsystem" - depends on CGROUPS - help - Provides a simple namespace cgroup subsystem to - provide hierarchical naming of sets of namespaces, - for instance virtual servers and checkpoint/restart - jobs. - -config CGROUP_FREEZER - bool "Freezer cgroup subsystem" - depends on CGROUPS - help - Provides a way to freeze and unfreeze all tasks in a - cgroup. - -config CGROUP_DEVICE - bool "Device controller for cgroups" - depends on CGROUPS && EXPERIMENTAL - help - Provides a cgroup implementing whitelists for devices which - a process in the cgroup can mknod or open. - -config CPUSETS - bool "Cpuset support" - depends on CGROUPS - help - This option will let you create and manage CPUSETs which - allow dynamically partitioning a system into sets of CPUs and - Memory Nodes and assigning tasks to run only within those sets. - This is primarily useful on large SMP or NUMA systems. - - Say N if unsure. - -config PROC_PID_CPUSET - bool "Include legacy /proc//cpuset file" - depends on CPUSETS - default y - -config CGROUP_CPUACCT - bool "Simple CPU accounting cgroup subsystem" - depends on CGROUPS - help - Provides a simple Resource Controller for monitoring the - total CPU consumed by the tasks in a cgroup. - -config RESOURCE_COUNTERS - bool "Resource counters" - help - This option enables controller independent resource accounting - infrastructure that works with cgroups. - depends on CGROUPS - -config CGROUP_MEM_RES_CTLR - bool "Memory Resource Controller for Control Groups" - depends on CGROUPS && RESOURCE_COUNTERS - select MM_OWNER - help - Provides a memory resource controller that manages both anonymous - memory and page cache. (See Documentation/cgroups/memory.txt) - - Note that setting this option increases fixed memory overhead - associated with each page of memory in the system. By this, - 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory - usage tracking struct at boot. Total amount of this is printed out - at boot. - - Only enable when you're ok with these trade offs and really - sure you need the memory resource controller. Even when you enable - this, you can set "cgroup_disable=memory" at your boot option to - disable memory resource controller and you can avoid overheads. - (and lose benefits of memory resource controller) - - This config option also selects MM_OWNER config option, which - could in turn add some fork/exit overhead. - -config CGROUP_MEM_RES_CTLR_SWAP - bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)" - depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL - help - Add swap management feature to memory resource controller. When you - enable this, you can limit mem+swap usage per cgroup. In other words, - when you disable this, memory resource controller has no cares to - usage of swap...a process can exhaust all of the swap. This extension - is useful when you want to avoid exhaustion swap but this itself - adds more overheads and consumes memory for remembering information. - Especially if you use 32bit system or small memory system, please - be careful about enabling this. When memory resource controller - is disabled by boot option, this will be automatically disabled and - there will be no overhead from this. Even when you set this config=y, - if boot option "noswapaccount" is set, swap will not be accounted. - Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page - size is 4096bytes, 512k per 1Gbytes of swap. - -endif # CGROUPS - config MM_OWNER bool Index: linux-2.6.30-bfs/kernel/delayacct.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/delayacct.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/delayacct.c 2009-08-26 19:38:31.442175967 +1000 @@ -127,7 +127,7 @@ */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; - t3 = tsk->se.sum_exec_runtime; + t3 = tsk->se_sum_exec_runtime; d->cpu_count += t1; Index: linux-2.6.30-bfs/kernel/trace/trace.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/trace/trace.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/kernel/trace/trace.c 2009-08-26 19:38:31.445175320 +1000 @@ -266,10 +266,10 @@ void trace_wake_up(void) { /* - * The runqueue_is_locked() can fail, but this is the best we + * The grunqueue_is_locked() can fail, but this is the best we * have for now: */ - if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked()) + if (!(trace_flags & TRACE_ITER_BLOCK) && !grunqueue_is_locked()) wake_up(&trace_wait); } Index: linux-2.6.30-bfs/fs/proc/base.c =================================================================== --- linux-2.6.30-bfs.orig/fs/proc/base.c 2009-06-10 13:05:27.000000000 +1000 +++ linux-2.6.30-bfs/fs/proc/base.c 2009-08-26 19:38:31.467384263 +1000 @@ -369,7 +369,7 @@ static int proc_pid_schedstat(struct task_struct *task, char *buffer) { return sprintf(buffer, "%llu %llu %lu\n", - (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)task->se_sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); } Index: linux-2.6.30-bfs/kernel/sched_debug.c =================================================================== --- linux-2.6.30-bfs.orig/kernel/sched_debug.c 2009-06-10 13:05:27.000000000 +1000 +++ /dev/null 1970-01-01 00:00:00.000000000 +0000 @@ -1,509 +0,0 @@ -/* - * kernel/time/sched_debug.c - * - * Print the CFS rbtree - * - * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include - -/* - * This allows printing both to /proc/sched_debug and - * to the console - */ -#define SEQ_printf(m, x...) \ - do { \ - if (m) \ - seq_printf(m, x); \ - else \ - printk(x); \ - } while (0) - -/* - * Ease the printing of nsec fields: - */ -static long long nsec_high(unsigned long long nsec) -{ - if ((long long)nsec < 0) { - nsec = -nsec; - do_div(nsec, 1000000); - return -nsec; - } - do_div(nsec, 1000000); - - return nsec; -} - -static unsigned long nsec_low(unsigned long long nsec) -{ - if ((long long)nsec < 0) - nsec = -nsec; - - return do_div(nsec, 1000000); -} - -#define SPLIT_NS(x) nsec_high(x), nsec_low(x) - -#ifdef CONFIG_FAIR_GROUP_SCHED -static void print_cfs_group_stats(struct seq_file *m, int cpu, - struct task_group *tg) -{ - struct sched_entity *se = tg->se[cpu]; - if (!se) - return; - -#define P(F) \ - SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) -#define PN(F) \ - SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) - - PN(se->exec_start); - PN(se->vruntime); - PN(se->sum_exec_runtime); -#ifdef CONFIG_SCHEDSTATS - PN(se->wait_start); - PN(se->sleep_start); - PN(se->block_start); - PN(se->sleep_max); - PN(se->block_max); - PN(se->exec_max); - PN(se->slice_max); - PN(se->wait_max); - PN(se->wait_sum); - P(se->wait_count); -#endif - P(se->load.weight); -#undef PN -#undef P -} -#endif - -static void -print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) -{ - if (rq->curr == p) - SEQ_printf(m, "R"); - else - SEQ_printf(m, " "); - - SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ", - p->comm, p->pid, - SPLIT_NS(p->se.vruntime), - (long long)(p->nvcsw + p->nivcsw), - p->prio); -#ifdef CONFIG_SCHEDSTATS - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.vruntime), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.sum_sleep_runtime)); -#else - SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", - 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); -#endif - -#ifdef CONFIG_CGROUP_SCHED - { - char path[64]; - - cgroup_path(task_group(p)->css.cgroup, path, sizeof(path)); - SEQ_printf(m, " %s", path); - } -#endif - SEQ_printf(m, "\n"); -} - -static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) -{ - struct task_struct *g, *p; - unsigned long flags; - - SEQ_printf(m, - "\nrunnable tasks:\n" - " task PID tree-key switches prio" - " exec-runtime sum-exec sum-sleep\n" - "------------------------------------------------------" - "----------------------------------------------------\n"); - - read_lock_irqsave(&tasklist_lock, flags); - - do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) - continue; - - print_task(m, rq, p); - } while_each_thread(g, p); - - read_unlock_irqrestore(&tasklist_lock, flags); -} - -#if defined(CONFIG_CGROUP_SCHED) && \ - (defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)) -static void task_group_path(struct task_group *tg, char *buf, int buflen) -{ - /* may be NULL if the underlying cgroup isn't fully-created yet */ - if (!tg->css.cgroup) { - buf[0] = '\0'; - return; - } - cgroup_path(tg->css.cgroup, buf, buflen); -} -#endif - -void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) -{ - s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1, - spread, rq0_min_vruntime, spread0; - struct rq *rq = &per_cpu(runqueues, cpu); - struct sched_entity *last; - unsigned long flags; - -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) - char path[128]; - struct task_group *tg = cfs_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); -#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) - { - uid_t uid = cfs_rq->tg->uid; - SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid); - } -#else - SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); -#endif - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", - SPLIT_NS(cfs_rq->exec_clock)); - - spin_lock_irqsave(&rq->lock, flags); - if (cfs_rq->rb_leftmost) - MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime; - last = __pick_last_entity(cfs_rq); - if (last) - max_vruntime = last->vruntime; - min_vruntime = cfs_rq->min_vruntime; - rq0_min_vruntime = per_cpu(runqueues, 0).cfs.min_vruntime; - spin_unlock_irqrestore(&rq->lock, flags); - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime", - SPLIT_NS(MIN_vruntime)); - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", - SPLIT_NS(min_vruntime)); - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime", - SPLIT_NS(max_vruntime)); - spread = max_vruntime - MIN_vruntime; - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", - SPLIT_NS(spread)); - spread0 = min_vruntime - rq0_min_vruntime; - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0", - SPLIT_NS(spread0)); - SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); - SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); - - SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", - cfs_rq->nr_spread_over); -#ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); -#endif - print_cfs_group_stats(m, cpu, cfs_rq->tg); -#endif -} - -void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) -{ -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED) - char path[128]; - struct task_group *tg = rt_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path); -#else - SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); -#endif - - -#define P(x) \ - SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) -#define PN(x) \ - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) - - P(rt_nr_running); - P(rt_throttled); - PN(rt_time); - PN(rt_runtime); - -#undef PN -#undef P -} - -static void print_cpu(struct seq_file *m, int cpu) -{ - struct rq *rq = &per_cpu(runqueues, cpu); - -#ifdef CONFIG_X86 - { - unsigned int freq = cpu_khz ? : 1; - - SEQ_printf(m, "\ncpu#%d, %u.%03u MHz\n", - cpu, freq / 1000, (freq % 1000)); - } -#else - SEQ_printf(m, "\ncpu#%d\n", cpu); -#endif - -#define P(x) \ - SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x)) -#define PN(x) \ - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) - - P(nr_running); - SEQ_printf(m, " .%-30s: %lu\n", "load", - rq->load.weight); - P(nr_switches); - P(nr_load_updates); - P(nr_uninterruptible); - PN(next_balance); - P(curr->pid); - PN(clock); - P(cpu_load[0]); - P(cpu_load[1]); - P(cpu_load[2]); - P(cpu_load[3]); - P(cpu_load[4]); -#undef P -#undef PN - -#ifdef CONFIG_SCHEDSTATS -#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); - - P(yld_count); - - P(sched_switch); - P(sched_count); - P(sched_goidle); - - P(ttwu_count); - P(ttwu_local); - - P(bkl_count); - -#undef P -#endif - print_cfs_stats(m, cpu); - print_rt_stats(m, cpu); - - print_rq(m, rq, cpu); -} - -static int sched_debug_show(struct seq_file *m, void *v) -{ - u64 now = ktime_to_ns(ktime_get()); - int cpu; - - SEQ_printf(m, "Sched Debug Version: v0.09, %s %.*s\n", - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - - SEQ_printf(m, "now at %Lu.%06ld msecs\n", SPLIT_NS(now)); - -#define P(x) \ - SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x)) -#define PN(x) \ - SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) - P(jiffies); - PN(sysctl_sched_latency); - PN(sysctl_sched_min_granularity); - PN(sysctl_sched_wakeup_granularity); - PN(sysctl_sched_child_runs_first); - P(sysctl_sched_features); -#undef PN -#undef P - - for_each_online_cpu(cpu) - print_cpu(m, cpu); - - SEQ_printf(m, "\n"); - - return 0; -} - -static void sysrq_sched_debug_show(void) -{ - sched_debug_show(NULL, NULL); -} - -static int sched_debug_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, sched_debug_show, NULL); -} - -static const struct file_operations sched_debug_fops = { - .open = sched_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init init_sched_debug_procfs(void) -{ - struct proc_dir_entry *pe; - - pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); - if (!pe) - return -ENOMEM; - return 0; -} - -__initcall(init_sched_debug_procfs); - -void proc_sched_show_task(struct task_struct *p, struct seq_file *m) -{ - unsigned long nr_switches; - unsigned long flags; - int num_threads = 1; - - if (lock_task_sighand(p, &flags)) { - num_threads = atomic_read(&p->signal->count); - unlock_task_sighand(p, &flags); - } - - SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, num_threads); - SEQ_printf(m, - "---------------------------------------------------------\n"); -#define __P(F) \ - SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)F) -#define P(F) \ - SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)p->F) -#define __PN(F) \ - SEQ_printf(m, "%-35s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) -#define PN(F) \ - SEQ_printf(m, "%-35s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) - - PN(se.exec_start); - PN(se.vruntime); - PN(se.sum_exec_runtime); - PN(se.avg_overlap); - PN(se.avg_wakeup); - - nr_switches = p->nvcsw + p->nivcsw; - -#ifdef CONFIG_SCHEDSTATS - PN(se.wait_start); - PN(se.sleep_start); - PN(se.block_start); - PN(se.sleep_max); - PN(se.block_max); - PN(se.exec_max); - PN(se.slice_max); - PN(se.wait_max); - PN(se.wait_sum); - P(se.wait_count); - P(sched_info.bkl_count); - P(se.nr_migrations); - P(se.nr_migrations_cold); - P(se.nr_failed_migrations_affine); - P(se.nr_failed_migrations_running); - P(se.nr_failed_migrations_hot); - P(se.nr_forced_migrations); - P(se.nr_forced2_migrations); - P(se.nr_wakeups); - P(se.nr_wakeups_sync); - P(se.nr_wakeups_migrate); - P(se.nr_wakeups_local); - P(se.nr_wakeups_remote); - P(se.nr_wakeups_affine); - P(se.nr_wakeups_affine_attempts); - P(se.nr_wakeups_passive); - P(se.nr_wakeups_idle); - - { - u64 avg_atom, avg_per_cpu; - - avg_atom = p->se.sum_exec_runtime; - if (nr_switches) - do_div(avg_atom, nr_switches); - else - avg_atom = -1LL; - - avg_per_cpu = p->se.sum_exec_runtime; - if (p->se.nr_migrations) { - avg_per_cpu = div64_u64(avg_per_cpu, - p->se.nr_migrations); - } else { - avg_per_cpu = -1LL; - } - - __PN(avg_atom); - __PN(avg_per_cpu); - } -#endif - __P(nr_switches); - SEQ_printf(m, "%-35s:%21Ld\n", - "nr_voluntary_switches", (long long)p->nvcsw); - SEQ_printf(m, "%-35s:%21Ld\n", - "nr_involuntary_switches", (long long)p->nivcsw); - - P(se.load.weight); - P(policy); - P(prio); -#undef PN -#undef __PN -#undef P -#undef __P - - { - unsigned int this_cpu = raw_smp_processor_id(); - u64 t0, t1; - - t0 = cpu_clock(this_cpu); - t1 = cpu_clock(this_cpu); - SEQ_printf(m, "%-35s:%21Ld\n", - "clock-delta", (long long)(t1-t0)); - } -} - -void proc_sched_set_task(struct task_struct *p) -{ -#ifdef CONFIG_SCHEDSTATS - p->se.wait_max = 0; - p->se.wait_sum = 0; - p->se.wait_count = 0; - p->se.sleep_max = 0; - p->se.sum_sleep_runtime = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - p->se.nr_migrations = 0; - p->se.nr_migrations_cold = 0; - p->se.nr_failed_migrations_affine = 0; - p->se.nr_failed_migrations_running = 0; - p->se.nr_failed_migrations_hot = 0; - p->se.nr_forced_migrations = 0; - p->se.nr_forced2_migrations = 0; - p->se.nr_wakeups = 0; - p->se.nr_wakeups_sync = 0; - p->se.nr_wakeups_migrate = 0; - p->se.nr_wakeups_local = 0; - p->se.nr_wakeups_remote = 0; - p->se.nr_wakeups_affine = 0; - p->se.nr_wakeups_affine_attempts = 0; - p->se.nr_wakeups_passive = 0; - p->se.nr_wakeups_idle = 0; - p->sched_info.bkl_count = 0; -#endif - p->se.sum_exec_runtime = 0; - p->se.prev_sum_exec_runtime = 0; - p->nvcsw = 0; - p->nivcsw = 0; -}