struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
-struct bio;
+struct bio_list;
struct fs_struct;
-struct bts_context;
struct perf_event_context;
/*
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
+#define TASK_STATE_MAX 512
+
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+
+extern char ___assert_task_state[1 - 2*!!(
+ sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
struct task_struct;
+#ifdef CONFIG_PROVE_RCU
+extern int lockdep_tasklist_lock_is_held(void);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
extern void sched_init(void);
extern void sched_init_smp(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
extern int get_nohz_load_balancer(void);
+extern int nohz_ratelimit(int cpu);
#else
static inline int select_nohz_load_balancer(int cpu)
{
return 0;
}
+
+static inline int nohz_ratelimit(int cpu)
+{
+ return 0;
+}
#endif
/*
#ifdef CONFIG_DETECT_SOFTLOCKUP
extern void softlockup_tick(void);
extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
void __user *buffer,
static inline void touch_softlockup_watchdog(void)
{
}
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
static inline void touch_all_softlockup_watchdogs(void)
{
}
* 1-3 now and depends on arch. We use "5" as safe margin, here.
*/
#define MAPCOUNT_ELF_CORE_MARGIN (5)
-#define DEFAULT_MAX_MAP_COUNT (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
+#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
extern int sysctl_max_map_count;
#include <linux/aio.h>
+#ifdef CONFIG_MMU
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
unsigned long flags);
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
+#else
+static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
+#endif
-#if USE_SPLIT_PTLOCKS
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
-#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
-
-#else /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
-#define get_mm_counter(mm, member) ((mm)->_##member)
-#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
-#define inc_mm_counter(mm, member) (mm)->_##member++
-#define dec_mm_counter(mm, member) (mm)->_##member--
-
-#endif /* !USE_SPLIT_PTLOCKS */
-
-#define get_mm_rss(mm) \
- (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
-#define update_hiwater_rss(mm) do { \
- unsigned long _rss = get_mm_rss(mm); \
- if ((mm)->hiwater_rss < _rss) \
- (mm)->hiwater_rss = _rss; \
-} while (0)
-#define update_hiwater_vm(mm) do { \
- if ((mm)->hiwater_vm < (mm)->total_vm) \
- (mm)->hiwater_vm = (mm)->total_vm; \
-} while (0)
-
-static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
-{
- return max(mm->hiwater_rss, get_mm_rss(mm));
-}
-
-static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
- struct mm_struct *mm)
-{
- unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
-
- if (*maxrss < hiwater_rss)
- *maxrss = hiwater_rss;
-}
-
-static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
-{
- return max(mm->hiwater_vm, mm->total_vm);
-}
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+ cputime_t prev_utime, prev_stime;
+#endif
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
uid_t uid;
struct user_namespace *user_ns;
-#ifdef CONFIG_USER_SCHED
- struct task_group *tg;
-#ifdef CONFIG_SYSFS
- struct kobject kobj;
- struct delayed_work work;
-#endif
-#endif
-
#ifdef CONFIG_PERF_EVENTS
atomic_long_t locked_vm;
#endif
if (sched_smt_power_savings)
return SD_POWERSAVINGS_BALANCE;
- return SD_PREFER_SIBLING;
+ if (!sched_mc_power_savings)
+ return SD_PREFER_SIBLING;
+
+ return 0;
}
static inline int sd_balance_for_package_power(void)
char *name;
#endif
+ unsigned int span_weight;
/*
* Span of all CPUs in this domain.
*
#define WF_SYNC 0x01 /* waker goes to sleep after wakup */
#define WF_FORK 0x02 /* child wakeup after fork */
+#define ENQUEUE_WAKEUP 1
+#define ENQUEUE_WAKING 2
+#define ENQUEUE_HEAD 4
+
+#define DEQUEUE_SLEEP 1
+
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 (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+ void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
- int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
-
- 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 (*select_task_rq)(struct rq *rq, struct task_struct *p,
+ int sd_flag, int flags);
- 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);
void (*post_schedule) (struct rq *this_rq);
- void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
+ void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+ void (*task_woken) (struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
const struct cpumask *newmask);
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 (*task_fork) (struct task_struct *p);
void (*switched_from) (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);
- unsigned int (*get_rr_interval) (struct task_struct *task);
+ unsigned int (*get_rr_interval) (struct rq *rq,
+ struct task_struct *task);
#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*moved_group) (struct task_struct *p);
+ void (*moved_group) (struct task_struct *p, int on_rq);
#endif
};
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 nr_migrations;
-
- u64 start_runtime;
- u64 avg_wakeup;
-
- u64 avg_running;
-
#ifdef CONFIG_SCHEDSTATS
+struct sched_statistics {
u64 wait_start;
u64 wait_max;
u64 wait_count;
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_affine_attempts;
u64 nr_wakeups_passive;
u64 nr_wakeups_idle;
+};
+#endif
+
+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 nr_migrations;
+
+#ifdef CONFIG_SCHEDSTATS
+ struct sched_statistics statistics;
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
struct plist_node pushable_tasks;
struct mm_struct *mm, *active_mm;
-
+#if defined(SPLIT_RSS_COUNTING)
+ struct task_rss_stat rss_stat;
+#endif
/* task state */
int exit_state;
int exit_code, exit_signal;
struct list_head ptraced;
struct list_head ptrace_entry;
- /*
- * This is the tracer handle for the ptrace BTS extension.
- * This field actually belongs to the ptracer task.
- */
- struct bts_context *bts;
-
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
cputime_t prev_utime, prev_stime;
+#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
it with task_lock())
- - initialized normally by flush_old_exec */
+ - initialized normally by setup_new_exec */
/* file system info */
int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
#endif
/* Protection of the PI data structures: */
- spinlock_t pi_lock;
+ raw_spinlock_t pi_lock;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
- int hardirqs_enabled;
unsigned long hardirq_enable_ip;
- unsigned int hardirq_enable_event;
unsigned long hardirq_disable_ip;
+ unsigned int hardirq_enable_event;
unsigned int hardirq_disable_event;
- int softirqs_enabled;
+ int hardirqs_enabled;
+ int hardirq_context;
unsigned long softirq_disable_ip;
- unsigned int softirq_disable_event;
unsigned long softirq_enable_ip;
+ unsigned int softirq_disable_event;
unsigned int softirq_enable_event;
- int hardirq_context;
+ int softirqs_enabled;
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
void *journal_info;
/* stacked block device info */
- struct bio *bio_list, **bio_tail;
+ struct bio_list *bio_list;
/* VM state */
struct reclaim_state *reclaim_state;
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
+ int mems_allowed_change_disable;
int cpuset_mem_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
struct list_head *scm_work_list;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- /* Index of current stored adress in ret_stack */
+ /* Index of current stored address in ret_stack */
int curr_ret_stack;
/* Stack of return addresses for return function tracing */
struct ftrace_ret_stack *ret_stack;
/* bitmask of trace recursion */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
- unsigned long stack_start;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
+ struct memcg_batch_info {
+ int do_batch; /* incremented when batch uncharge started */
+ struct mem_cgroup *memcg; /* target memcg of uncharge */
+ unsigned long bytes; /* uncharged usage */
+ unsigned long memsw_bytes; /* uncharged mem+swap usage */
+ } memcg_batch;
+#endif
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed)
+#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
}
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
/*
* Per process flags
extern int sched_clock_stable;
#endif
-extern unsigned long long sched_clock(void);
+/* ftrace calls sched_clock() directly */
+extern unsigned long long notrace sched_clock(void);
extern void sched_clock_init(void);
extern u64 sched_clock_cpu(int cpu);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#ifdef CONFIG_HOTPLUG_CPU
+extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
extern unsigned int sysctl_sched_shares_ratelimit;
extern unsigned int sysctl_sched_shares_thresh;
extern unsigned int sysctl_sched_child_runs_first;
+
+enum sched_tunable_scaling {
+ SCHED_TUNABLESCALING_NONE,
+ SCHED_TUNABLESCALING_LOG,
+ SCHED_TUNABLESCALING_LINEAR,
+ SCHED_TUNABLESCALING_END,
+};
+extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+
#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_features;
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
extern unsigned int sysctl_sched_time_avg;
extern unsigned int sysctl_timer_migration;
-int sched_nr_latency_handler(struct ctl_table *table, int write,
+int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos);
#endif
extern int do_notify_parent(struct task_struct *, int);
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int, struct task_struct *);
-extern void force_sig_specific(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern void zap_other_threads(struct task_struct *p);
extern struct sigqueue *sigqueue_alloc(void);
#define SEND_SIG_PRIV ((struct siginfo *) 1)
#define SEND_SIG_FORCED ((struct siginfo *) 2)
-static inline int is_si_special(const struct siginfo *info)
-{
- return info <= SEND_SIG_FORCED;
-}
-
-/* True if we are on the alternate signal stack. */
-
+/*
+ * True if we are on the alternate signal stack.
+ */
static inline int on_sig_stack(unsigned long sp)
{
- return (sp - current->sas_ss_sp < current->sas_ss_size);
+#ifdef CONFIG_STACK_GROWSUP
+ return sp >= current->sas_ss_sp &&
+ sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+ return sp > current->sas_ss_sp &&
+ sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
}
static inline int sas_ss_flags(unsigned long sp)
extern char *get_task_comm(char *to, struct task_struct *tsk);
#ifdef CONFIG_SMP
-extern void wait_task_context_switch(struct task_struct *p);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
#else
-static inline void wait_task_context_switch(struct task_struct *p) {}
static inline unsigned long wait_task_inactive(struct task_struct *p,
long match_state)
{
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
- sig->cputimer.cputime = INIT_CPUTIME;
spin_lock_init(&sig->cputimer.lock);
- sig->cputimer.running = 0;
}
static inline void thread_group_cputime_free(struct signal_struct *sig)
#endif /* CONFIG_SMP */
-extern void arch_pick_mmap_layout(struct mm_struct *mm);
-
#ifdef CONFIG_TRACING
extern void
__trace_special(void *__tr, void *__data,
extern void normalize_rt_tasks(void);
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
extern struct task_group init_task_group;
-#ifdef CONFIG_USER_SCHED
-extern struct task_group root_task_group;
-extern void set_tg_uid(struct user_struct *user);
-#endif
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
}
#endif /* CONFIG_MM_OWNER */
-#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
+static inline unsigned long task_rlimit(const struct task_struct *tsk,
+ unsigned int limit)
+{
+ return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+}
+
+static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+ unsigned int limit)
+{
+ return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+}
+
+static inline unsigned long rlimit(unsigned int limit)
+{
+ return task_rlimit(current, limit);
+}
+
+static inline unsigned long rlimit_max(unsigned int limit)
+{
+ return task_rlimit_max(current, limit);
+}
#endif /* __KERNEL__ */