X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fsched.h;h=269b234609b866853564afc4b4f4c12cfc500ae7;hb=72c2d5823fc7be799a12184974c3bdc57acea3c4;hp=3e7f1890e55daa617fbf9f2ebed1315d92f3198a;hpb=41b86e9c510ae66639bf29d3201e1d2384a7fde6;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/sched.h b/include/linux/sched.h index 3e7f189..269b234 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1,8 +1,6 @@ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H -#include /* For AT_VECTOR_SIZE */ - /* * cloning flags: */ @@ -26,6 +24,8 @@ #define CLONE_STOPPED 0x02000000 /* Start in stopped state */ #define CLONE_NEWUTS 0x04000000 /* New utsname group? */ #define CLONE_NEWIPC 0x08000000 /* New ipcs */ +#define CLONE_NEWUSER 0x10000000 /* New user namespace */ +#define CLONE_NEWNET 0x40000000 /* New network namespace */ /* * Scheduling policies @@ -56,12 +56,12 @@ struct sched_param { #include #include #include +#include #include #include #include #include -#include #include #include @@ -74,6 +74,7 @@ struct sched_param { #include #include #include +#include #include #include #include @@ -85,6 +86,7 @@ struct sched_param { #include #include #include +#include #include @@ -112,7 +114,7 @@ extern unsigned long avenrun[]; /* Load averages */ #define FSHIFT 11 /* nr of bits of precision */ #define FIXED_1 (1<state again */ -#define TASK_NONINTERACTIVE 64 -#define TASK_DEAD 128 +#define TASK_DEAD 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -239,6 +261,7 @@ extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); +extern int softlockup_thresh; #else static inline void softlockup_tick(void) { @@ -267,6 +290,7 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); struct nsproxy; +struct user_namespace; /* Maximum number of active map areas.. This is a random (large) number */ #define DEFAULT_MAX_MAP_COUNT 65536 @@ -295,7 +319,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #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) -typedef atomic_long_t mm_counter_t; #else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ /* @@ -307,7 +330,6 @@ typedef atomic_long_t mm_counter_t; #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-- -typedef unsigned long mm_counter_t; #endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ @@ -323,79 +345,33 @@ typedef unsigned long mm_counter_t; (mm)->hiwater_vm = (mm)->total_vm; \ } while (0) -struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ - struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ - unsigned long (*get_unmapped_area) (struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct mm_struct *mm, unsigned long addr); - unsigned long mmap_base; /* base of mmap area */ - unsigned long task_size; /* size of task vm space */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ - unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ - pgd_t * pgd; - atomic_t mm_users; /* How many users with user space? */ - atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - int map_count; /* number of VMAs */ - struct rw_semaphore mmap_sem; - spinlock_t page_table_lock; /* Protects page tables and some counters */ - - struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung - * together off init_mm.mmlist, and are protected - * by mmlist_lock - */ - - /* Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - mm_counter_t _file_rss; - mm_counter_t _anon_rss; - - unsigned long hiwater_rss; /* High-watermark of RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ - - unsigned long total_vm, locked_vm, shared_vm, exec_vm; - unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; - unsigned long start_code, end_code, start_data, end_data; - unsigned long start_brk, brk, start_stack; - unsigned long arg_start, arg_end, env_start, env_end; - - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - - cpumask_t cpu_vm_mask; - - /* Architecture-specific MM context */ - mm_context_t context; - - /* Swap token stuff */ - /* - * Last value of global fault stamp as seen by this process. - * In other words, this value gives an indication of how long - * it has been since this task got the token. - * Look at mm/thrash.c - */ - unsigned int faultstamp; - unsigned int token_priority; - unsigned int last_interval; - - unsigned char dumpable:2; - - /* coredumping support */ - int core_waiters; - struct completion *core_startup_done, core_done; - - /* aio bits */ - rwlock_t ioctx_list_lock; - struct kioctx *ioctx_list; -}; +extern void set_dumpable(struct mm_struct *mm, int value); +extern int get_dumpable(struct mm_struct *mm); + +/* mm flags */ +/* dumpable bits */ +#define MMF_DUMPABLE 0 /* core dump is permitted */ +#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */ +#define MMF_DUMPABLE_BITS 2 + +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 5 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED)) struct sighand_struct { atomic_t count; struct k_sigaction action[_NSIG]; spinlock_t siglock; - struct list_head signalfd_list; + wait_queue_head_t signalfd_wqh; }; struct pacct_struct { @@ -472,6 +448,8 @@ struct signal_struct { * in __exit_signal, except for the group leader. */ cputime_t utime, stime, cutime, cstime; + cputime_t gtime; + cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -482,7 +460,6 @@ struct signal_struct { * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ - unsigned long sched_time; unsigned long long sum_sched_runtime; /* @@ -510,6 +487,10 @@ struct signal_struct { #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif +#ifdef CONFIG_AUDIT + unsigned audit_tty; + struct tty_audit_buf *tty_audit_buf; +#endif }; /* Context switch must be unlocked if interrupts are to be enabled */ @@ -525,31 +506,6 @@ struct signal_struct { #define SIGNAL_STOP_CONTINUED 0x00000004 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000008 /* group exit in progress */ - -/* - * 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. - * - * The MAX_USER_RT_PRIO value allows the actual maximum - * RT priority to be separate from the value exported to - * user-space. This allows kernel threads to set their - * priority to a value higher than any user task. Note: - * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. - */ - -#define MAX_USER_RT_PRIO 100 -#define MAX_RT_PRIO MAX_USER_RT_PRIO - -#define MAX_PRIO (MAX_RT_PRIO + 40) - -#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)) - /* * Some day this will be a full-fledged user tracking system.. */ @@ -562,8 +518,10 @@ struct user_struct { atomic_t inotify_watches; /* How many inotify watches does this user have? */ atomic_t inotify_devs; /* How many inotify devs does this user have opened? */ #endif +#ifdef CONFIG_POSIX_MQUEUE /* protected by mq_lock */ unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ +#endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ #ifdef CONFIG_KEYS @@ -572,10 +530,25 @@ struct user_struct { #endif /* Hash table maintenance information */ - struct list_head uidhash_list; + struct hlist_node uidhash_node; uid_t uid; + +#ifdef CONFIG_FAIR_USER_SCHED + struct task_group *tg; +#ifdef CONFIG_SYSFS + struct kset kset; + struct subsys_attribute user_attr; + struct work_struct work; +#endif +#endif }; +#ifdef CONFIG_FAIR_USER_SCHED +extern int uids_kobject_init(void); +#else +static inline int uids_kobject_init(void) { return 0; } +#endif + extern struct user_struct *find_user(uid_t); extern struct user_struct root_user; @@ -587,13 +560,17 @@ struct reclaim_state; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info { /* cumulative counters */ - unsigned long cpu_time, /* time spent on the cpu */ - run_delay, /* time spent waiting on a runqueue */ - pcnt; /* # of timeslices run on this cpu */ + unsigned long pcount; /* # of times run on this cpu */ + unsigned long long cpu_time, /* time spent on the cpu */ + run_delay; /* time spent waiting on a runqueue */ /* timestamps */ - unsigned long last_arrival, /* when we last ran on a cpu */ - last_queued; /* when we were last queued to run */ + unsigned long long last_arrival,/* when we last ran on a cpu */ + last_queued; /* when we were last queued to run */ +#ifdef CONFIG_SCHEDSTATS + /* BKL stats */ + unsigned long bkl_count; +#endif }; #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ @@ -660,7 +637,7 @@ enum cpu_idle_type { #define SCHED_LOAD_SHIFT 10 #define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) -#define SCHED_LOAD_SCALE_FUZZ (SCHED_LOAD_SCALE >> 5) +#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE #ifdef CONFIG_SMP #define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */ @@ -713,7 +690,6 @@ struct sched_domain { unsigned long max_interval; /* Maximum balance interval ms */ unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ - unsigned long long cache_hot_time; /* Task considered cache hot (ns) */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ unsigned int busy_idx; unsigned int idle_idx; @@ -729,7 +705,7 @@ struct sched_domain { #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ - unsigned long lb_cnt[CPU_MAX_IDLE_TYPES]; + unsigned long lb_count[CPU_MAX_IDLE_TYPES]; unsigned long lb_failed[CPU_MAX_IDLE_TYPES]; unsigned long lb_balanced[CPU_MAX_IDLE_TYPES]; unsigned long lb_imbalance[CPU_MAX_IDLE_TYPES]; @@ -739,17 +715,17 @@ struct sched_domain { unsigned long lb_nobusyq[CPU_MAX_IDLE_TYPES]; /* Active load balancing */ - unsigned long alb_cnt; + unsigned long alb_count; unsigned long alb_failed; unsigned long alb_pushed; /* SD_BALANCE_EXEC stats */ - unsigned long sbe_cnt; + unsigned long sbe_count; unsigned long sbe_balanced; unsigned long sbe_pushed; /* SD_BALANCE_FORK stats */ - unsigned long sbf_cnt; + unsigned long sbf_count; unsigned long sbf_balanced; unsigned long sbf_pushed; @@ -760,11 +736,24 @@ struct sched_domain { #endif }; -extern int partition_sched_domains(cpumask_t *partition1, - cpumask_t *partition2); - #endif /* CONFIG_SMP */ +/* + * A runqueue laden with a single nice 0 task scores a weighted_cpuload of + * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a + * task of nice 0 or enough lower priority tasks to bring up the + * weighted_cpuload + */ +static inline int above_background_load(void) +{ + unsigned long cpu; + + for_each_online_cpu(cpu) { + if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE) + return 1; + } + return 0; +} struct io_context; /* See blkdev.h */ struct cpuset; @@ -813,36 +802,26 @@ struct mempolicy; struct pipe_inode_info; struct uts_namespace; -enum sleep_type { - SLEEP_NORMAL, - SLEEP_NONINTERACTIVE, - SLEEP_INTERACTIVE, - SLEEP_INTERRUPTED, -}; - -struct prio_array; struct rq; struct sched_domain; struct sched_class { - struct sched_class *next; + const struct sched_class *next; - void (*enqueue_task) (struct rq *rq, struct task_struct *p, - int wakeup, u64 now); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, - int sleep, u64 now); - void (*yield_task) (struct rq *rq, struct task_struct *p); + 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); - struct task_struct * (*pick_next_task) (struct rq *rq, u64 now); - void (*put_prev_task) (struct rq *rq, struct task_struct *p, u64 now); + struct task_struct * (*pick_next_task) (struct rq *rq); + void (*put_prev_task) (struct rq *rq, struct task_struct *p); - int (*load_balance) (struct rq *this_rq, int this_cpu, + unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_nr_move, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *total_load_moved); + int *all_pinned, int *this_best_prio); void (*set_curr_task) (struct rq *rq); void (*task_tick) (struct rq *rq, struct task_struct *p); @@ -861,38 +840,51 @@ struct load_weight { * 4 se->block_start * 4 se->run_node * 4 se->sleep_start - * 4 se->sleep_start_fair * 6 se->load.weight - * 7 se->delta_fair - * 15 se->wait_runtime */ struct sched_entity { - long wait_runtime; - unsigned long delta_fair_run; - unsigned long delta_fair_sleep; - unsigned long delta_exec; - s64 fair_key; struct load_weight load; /* for load-balancing */ struct rb_node run_node; unsigned int on_rq; + int peer_preempt; - u64 wait_start_fair; - u64 wait_start; u64 exec_start; + u64 sum_exec_runtime; + u64 vruntime; + u64 prev_sum_exec_runtime; + +#ifdef CONFIG_SCHEDSTATS + u64 wait_start; + u64 wait_max; + u64 sleep_start; - u64 sleep_start_fair; - u64 block_start; u64 sleep_max; + s64 sum_sleep_runtime; + + u64 block_start; u64 block_max; u64 exec_max; - u64 wait_max; - u64 last_ran; + u64 slice_max; + + u64 nr_migrations; + 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 - u64 sum_exec_runtime; - s64 sum_wait_runtime; - s64 sum_sleep_runtime; - unsigned long wait_runtime_overruns; - unsigned long wait_runtime_underruns; #ifdef CONFIG_FAIR_GROUP_SCHED struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ @@ -916,25 +908,35 @@ struct task_struct { int oncpu; #endif #endif - int load_weight; /* for niceness load balancing purposes */ + int prio, static_prio, normal_prio; struct list_head run_list; - struct prio_array *array; - struct sched_class *sched_class; + const struct sched_class *sched_class; struct sched_entity se; +#ifdef CONFIG_PREEMPT_NOTIFIERS + /* list of struct preempt_notifier: */ + struct hlist_head preempt_notifiers; +#endif + unsigned short ioprio; + /* + * fpu_counter contains the number of consecutive context switches + * that the FPU is used. If this is over a threshold, the lazy fpu + * saving becomes unlazy to save the trap. This is an unsigned char + * so that after 256 times the counter wraps and the behavior turns + * lazy again; this to deal with bursty apps that only use FPU for + * a short time + */ + unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif - unsigned long sleep_avg; - unsigned long long timestamp, last_ran; - unsigned long long sched_time; /* sched_clock time spent running */ - enum sleep_type sleep_type; unsigned int policy; cpumask_t cpus_allowed; - unsigned int time_slice, first_time_slice; + unsigned int time_slice; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -990,8 +992,10 @@ struct task_struct { unsigned int rt_priority; cputime_t utime, stime; + cputime_t gtime; unsigned long nvcsw, nivcsw; /* context switch counts */ - struct timespec start_time; + struct timespec start_time; /* monotonic time */ + struct timespec real_start_time; /* boot based time */ /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; @@ -1011,16 +1015,6 @@ struct task_struct { struct key *thread_keyring; /* keyring private to this thread */ unsigned char jit_keyring; /* default keyring to attach requested keys to */ #endif - /* - * fpu_counter contains the number of consecutive context switches - * that the FPU is used. If this is over a threshold, the lazy fpu - * saving becomes unlazy to save the trap. This is an unsigned char - * so that after 256 times the counter wraps and the behavior turns - * lazy again; this to deal with bursty apps that only use FPU for - * a short time - */ - unsigned char fpu_counter; - int oomkilladj; /* OOM kill score adjustment (bit shift). */ char comm[TASK_COMM_LEN]; /* executable name excluding path - access with [gs]et_task_comm (which lock it with task_lock()) @@ -1052,8 +1046,9 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; - +#ifdef CONFIG_SECURITY void *security; +#endif struct audit_context *audit_context; seccomp_t seccomp; @@ -1115,13 +1110,6 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ -/* - * current io wait handle: wait queue entry to use for io waits - * If this thread is processing aio, this points at the waitqueue - * inside the currently handled kiocb. It may be NULL (i.e. default - * to a stack based synchronous wait) if its doing sync IO. - */ - wait_queue_t *io_wait; #ifdef CONFIG_TASK_XACCT /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; @@ -1142,13 +1130,14 @@ struct task_struct { int cpuset_mems_generation; int cpuset_mem_spread_rotor; #endif +#ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; - +#endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; @@ -1162,8 +1151,40 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; #endif + struct prop_local_single dirties; }; +/* + * 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. + * + * The MAX_USER_RT_PRIO value allows the actual maximum + * RT priority to be separate from the value exported to + * user-space. This allows kernel threads to set their + * priority to a value higher than any user task. Note: + * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. + */ + +#define MAX_USER_RT_PRIO 100 +#define MAX_RT_PRIO MAX_USER_RT_PRIO + +#define MAX_PRIO (MAX_RT_PRIO + 40) +#define DEFAULT_PRIO (MAX_RT_PRIO + 20) + +static inline int rt_prio(int prio) +{ + if (unlikely(prio < MAX_RT_PRIO)) + return 1; + return 0; +} + +static inline int rt_task(struct task_struct *p) +{ + return rt_prio(p->prio); +} + static inline pid_t process_group(struct task_struct *tsk) { return tsk->signal->pgrp; @@ -1249,6 +1270,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ +#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ @@ -1308,6 +1330,13 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) #endif extern unsigned long long sched_clock(void); + +/* + * For kernel-internal use: high-speed (but slightly incorrect) per-cpu + * clock constructed from sched_clock(): + */ +extern unsigned long long cpu_clock(int cpu); + extern unsigned long long task_sched_runtime(struct task_struct *task); @@ -1318,6 +1347,9 @@ extern void sched_exec(void); #define sched_exec() {} #endif +extern void sched_clock_idle_sleep_event(void); +extern void sched_clock_idle_wakeup_event(u64 delta_ns); + #ifdef CONFIG_HOTPLUG_CPU extern void idle_task_exit(void); #else @@ -1326,13 +1358,17 @@ static inline void idle_task_exit(void) {} extern void sched_idle_next(void); -extern unsigned int sysctl_sched_granularity; +#ifdef CONFIG_SCHED_DEBUG +extern unsigned int sysctl_sched_latency; +extern unsigned int sysctl_sched_nr_latency; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_batch_wakeup_granularity; -extern unsigned int sysctl_sched_stat_granularity; -extern unsigned int sysctl_sched_runtime_limit; extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; +extern unsigned int sysctl_sched_migration_cost; +#endif + +extern unsigned int sysctl_sched_compat_yield; #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); @@ -1389,7 +1425,7 @@ extern struct task_struct *find_task_by_pid_type(int type, int pid); extern void __set_special_pids(pid_t session, pid_t pgrp); /* per-UID process charging. */ -extern struct user_struct * alloc_uid(uid_t); +extern struct user_struct * alloc_uid(struct user_namespace *, uid_t); static inline struct user_struct *get_uid(struct user_struct *u) { atomic_inc(&u->__count); @@ -1397,6 +1433,7 @@ static inline struct user_struct *get_uid(struct user_struct *u) } extern void free_uid(struct user_struct *); extern void switch_uid(struct user_struct *); +extern void release_uids(struct user_namespace *ns); #include @@ -1411,8 +1448,8 @@ extern void FASTCALL(wake_up_new_task(struct task_struct * tsk, #else static inline void kick_process(struct task_struct *tsk) { } #endif -extern void FASTCALL(sched_fork(struct task_struct * p, int clone_flags)); -extern void FASTCALL(sched_exit(struct task_struct * p)); +extern void sched_fork(struct task_struct *p, int clone_flags); +extern void sched_dead(struct task_struct *p); extern int in_group_p(gid_t); extern int in_egroup_p(gid_t); @@ -1500,7 +1537,7 @@ extern struct mm_struct * mm_alloc(void); extern void FASTCALL(__mmdrop(struct mm_struct *)); static inline void mmdrop(struct mm_struct * mm) { - if (atomic_dec_and_test(&mm->mm_count)) + if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } @@ -1765,6 +1802,18 @@ extern int sched_mc_power_savings, sched_smt_power_savings; extern void normalize_rt_tasks(void); +#ifdef CONFIG_FAIR_GROUP_SCHED + +extern struct task_group init_task_group; + +extern struct task_group *sched_create_group(void); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_move_task(struct task_struct *tsk); +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_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) {