diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 300 |
1 files changed, 78 insertions, 222 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..caa8f4d0186b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -127,18 +127,6 @@ 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) -{ -} -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 /* @@ -163,9 +151,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #define TASK_DEAD 64 #define TASK_WAKEKILL 128 #define TASK_WAKING 256 -#define TASK_STATE_MAX 512 +#define TASK_PARKED 512 +#define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; @@ -242,7 +231,7 @@ extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); extern int get_nohz_timer_target(void); @@ -320,13 +309,10 @@ extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; -#include <linux/aio.h> - #ifdef CONFIG_MMU extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long @@ -526,7 +512,8 @@ struct signal_struct { unsigned int has_child_subreaper:1; /* POSIX.1b Interval Timers */ - struct list_head posix_timers; + int posix_timer_id; + struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; @@ -570,7 +557,7 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -637,6 +624,7 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ +#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -768,31 +756,6 @@ enum cpu_idle_type { }; /* - * Increase resolution of nice-level calculations for 64-bit architectures. - * The extra resolution improves shares distribution and load balancing of - * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup - * hierarchies, especially on larger systems. This is not a user-visible change - * and does not change the user-interface for setting shares/weights. - * - * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution - * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the - * increased costs. - */ -#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ -# define SCHED_LOAD_RESOLUTION 10 -# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) -# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) -#else -# define SCHED_LOAD_RESOLUTION 0 -# define scale_load(w) (w) -# define scale_load_down(w) (w) -#endif - -#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) -#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) - -/* * Increase resolution of cpu_power calculations */ #define SCHED_POWER_SHIFT 10 @@ -817,62 +780,6 @@ enum cpu_idle_type { extern int __weak arch_sd_sibiling_asym_packing(void); -struct sched_group_power { - atomic_t ref; - /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. - */ - unsigned int power, power_orig; - unsigned long next_update; - /* - * Number of busy cpus in this group. - */ - atomic_t nr_busy_cpus; - - unsigned long cpumask[0]; /* iteration mask */ -}; - -struct sched_group { - struct sched_group *next; /* Must be a circular list */ - atomic_t ref; - - unsigned int group_weight; - struct sched_group_power *sgp; - - /* - * The CPUs this group covers. - * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ - unsigned long cpumask[0]; -}; - -static inline struct cpumask *sched_group_cpus(struct sched_group *sg) -{ - return to_cpumask(sg->cpumask); -} - -/* - * cpumask masking which cpus in the group are allowed to iterate up the domain - * tree. - */ -static inline struct cpumask *sched_group_mask(struct sched_group *sg) -{ - return to_cpumask(sg->sgp->cpumask); -} - -/** - * 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)); -} - struct sched_domain_attr { int relax_domain_level; }; @@ -883,6 +790,8 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct sched_group; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ @@ -899,6 +808,8 @@ struct sched_domain { unsigned int wake_idx; unsigned int forkexec_idx; unsigned int smt_gain; + + int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ int level; @@ -971,18 +882,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); -/* Test a flag in parent sched domain */ -static inline int test_sd_parent(struct sched_domain *sd, int flag) -{ - if (sd->parent && (sd->parent->flags & flag)) - return 1; - - return 0; -} - -unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); -unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); - bool cpus_share_cache(int this_cpu, int that_cpu); #else /* CONFIG_SMP */ @@ -1017,72 +916,6 @@ struct mempolicy; struct pipe_inode_info; struct uts_namespace; -struct rq; -struct sched_domain; - -/* - * wake flags - */ -#define WF_SYNC 0x01 /* waker goes to sleep after wakup */ -#define WF_FORK 0x02 /* child wakeup after fork */ -#define WF_MIGRATED 0x04 /* internal use, task got migrated */ - -#define ENQUEUE_WAKEUP 1 -#define ENQUEUE_HEAD 2 -#ifdef CONFIG_SMP -#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ -#else -#define ENQUEUE_WAKING 0 -#endif - -#define DEQUEUE_SLEEP 1 - -struct sched_class { - const struct sched_class *next; - - 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); - bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); - - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); - - 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 sd_flag, int flags); - void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (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 (*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_fork) (struct task_struct *p); - - void (*switched_from) (struct rq *this_rq, struct task_struct *task); - void (*switched_to) (struct rq *this_rq, struct task_struct *task); - void (*prio_changed) (struct rq *this_rq, struct task_struct *task, - int oldprio); - - unsigned int (*get_rr_interval) (struct rq *rq, - struct task_struct *task); - -#ifdef CONFIG_FAIR_GROUP_SCHED - void (*task_move_group) (struct task_struct *p, int on_rq); -#endif -}; - struct load_weight { unsigned long weight, inv_weight; }; @@ -1274,8 +1107,10 @@ struct task_struct { int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ unsigned int jobctl; /* JOBCTL_*, siglock protected */ - /* ??? */ + + /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; + unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ @@ -1327,7 +1162,7 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -1576,6 +1411,10 @@ struct task_struct { #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif +#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) + unsigned int sequential_io; + unsigned int sequential_io_avg; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ @@ -1793,7 +1632,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ -#define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1927,13 +1766,13 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON void calc_load_enter_idle(void); void calc_load_exit_idle(void); #else static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) @@ -2019,10 +1858,17 @@ extern void idle_task_exit(void); static inline void idle_task_exit(void) {} #endif -#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) -extern void wake_up_idle_cpu(int cpu); +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) +extern void wake_up_nohz_cpu(int cpu); #else -static inline void wake_up_idle_cpu(int cpu) { } +static inline void wake_up_nohz_cpu(int cpu) { } +#endif + +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(void); +extern u64 scheduler_tick_max_deferment(void); +#else +static inline bool sched_can_stop_tick(void) { return false; } #endif #ifdef CONFIG_SCHED_AUTOGROUP @@ -2412,27 +2258,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk) * * Lock the threadgroup @tsk belongs to. No new task is allowed to enter * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * perform exec. This is useful for cases where the threadgroup needs to - * stay stable across blockable operations. + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. * * fork and exit paths explicitly call threadgroup_change_{begin|end}() for * synchronization. While held, no new task will be added to threadgroup * and no existing live task will have its PF_EXITING set. * - * During exec, a task goes and puts its thread group through unusual - * changes. After de-threading, exclusive access is assumed to resources - * which are usually shared by tasks in the same group - e.g. sighand may - * be replaced with a new one. Also, the exec'ing task takes over group - * leader role including its pid. Exclude these changes while locked by - * grabbing cred_guard_mutex which is used to synchronize exec path. + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. */ static inline void threadgroup_lock(struct task_struct *tsk) { - /* - * exec uses exit for de-threading nesting group_rwsem inside - * cred_guard_mutex. Grab cred_guard_mutex first. - */ - mutex_lock(&tsk->signal->cred_guard_mutex); down_write(&tsk->signal->group_rwsem); } @@ -2445,7 +2282,6 @@ static inline void threadgroup_lock(struct task_struct *tsk) static inline void threadgroup_unlock(struct task_struct *tsk) { up_write(&tsk->signal->group_rwsem); - mutex_unlock(&tsk->signal->cred_guard_mutex); } #else static inline void threadgroup_change_begin(struct task_struct *tsk) {} @@ -2622,6 +2458,47 @@ static inline int spin_needbreak(spinlock_t *lock) } /* + * Idle thread specific functions to determine the need_resched + * polling state. We have two versions, one based on TS_POLLING in + * thread_info.status and one based on TIF_POLLING_NRFLAG in + * thread_info.flags + */ +#ifdef TS_POLLING +static inline int tsk_is_polling(struct task_struct *p) +{ + return task_thread_info(p)->status & TS_POLLING; +} +static inline void current_set_polling(void) +{ + current_thread_info()->status |= TS_POLLING; +} + +static inline void current_clr_polling(void) +{ + current_thread_info()->status &= ~TS_POLLING; + smp_mb__after_clear_bit(); +} +#elif defined(TIF_POLLING_NRFLAG) +static inline int tsk_is_polling(struct task_struct *p) +{ + return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); +} +static inline void current_set_polling(void) +{ + set_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline void current_clr_polling(void) +{ + clear_thread_flag(TIF_POLLING_NRFLAG); +} +#else +static inline int tsk_is_polling(struct task_struct *p) { return 0; } +static inline void current_set_polling(void) { } +static inline void current_clr_polling(void) { } +#endif + +/* * Thread group CPU time accounting. */ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); @@ -2681,28 +2558,7 @@ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifdef CONFIG_CGROUP_SCHED - extern struct task_group root_task_group; - -extern struct task_group *sched_create_group(struct task_group *parent); -extern void sched_online_group(struct task_group *tg, - struct task_group *parent); -extern void sched_destroy_group(struct task_group *tg); -extern void sched_offline_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); -#ifdef CONFIG_FAIR_GROUP_SCHED -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); -extern unsigned long sched_group_shares(struct task_group *tg); -#endif -#ifdef CONFIG_RT_GROUP_SCHED -extern int sched_group_set_rt_runtime(struct task_group *tg, - long rt_runtime_us); -extern long sched_group_rt_runtime(struct task_group *tg); -extern int sched_group_set_rt_period(struct task_group *tg, - long rt_period_us); -extern long sched_group_rt_period(struct task_group *tg); -extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); -#endif #endif /* CONFIG_CGROUP_SCHED */ extern int task_can_switch_user(struct user_struct *up, |