#ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H #include /* for HZ */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include struct exec_domain; /* * cloning flags: */ #define CSIGNAL 0x000000ff /* signal mask to be sent at exit */ #define CLONE_VM 0x00000100 /* set if VM shared between processes */ #define CLONE_FS 0x00000200 /* set if fs info shared between processes */ #define CLONE_FILES 0x00000400 /* set if open files shared between processes */ #define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */ #define CLONE_IDLETASK 0x00001000 /* set if new pid should be 0 (kernel only)*/ #define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */ #define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */ #define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */ #define CLONE_THREAD 0x00010000 /* Same thread group? */ #define CLONE_NEWNS 0x00020000 /* New namespace group? */ #define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */ #define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */ #define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */ #define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */ #define CLONE_DETACHED 0x00400000 /* parent wants no child-exit signal */ #define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ /* * List of flags we want to share for kernel threads, * if only because they are not used by them anyway. */ #define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND) /* * These are the constant used to fake the fixed-point load-average * counting. Some notes: * - 11 bit fractions expand to 22 bits by the multiplies: this gives * a load-average precision of 10 bits integer + 11 bits fractional * - if you want to count load-averages more often, you need more * precision, or rounding will get you. With 2-second counting freq, * the EXP_n values would be 1981, 2034 and 2043 if still using only * 11 bit fractions. */ extern unsigned long avenrun[]; /* Load averages */ #define FSHIFT 11 /* nr of bits of precision */ #define FIXED_1 (1<>= FSHIFT; #define CT_TO_SECS(x) ((x) / HZ) #define CT_TO_USECS(x) (((x) % HZ) * 1000000/HZ) extern int nr_threads; extern int last_pid; extern unsigned long nr_running(void); extern unsigned long nr_uninterruptible(void); extern unsigned long nr_iowait(void); #include #include #include #include #include #define TASK_RUNNING 0 #define TASK_INTERRUPTIBLE 1 #define TASK_UNINTERRUPTIBLE 2 #define TASK_STOPPED 4 #define TASK_ZOMBIE 8 #define TASK_DEAD 16 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ set_mb((tsk)->state, (state_value)) #define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) #define set_current_state(state_value) \ set_mb(current->state, (state_value)) /* * Scheduling policies */ #define SCHED_NORMAL 0 #define SCHED_FIFO 1 #define SCHED_RR 2 struct sched_param { int sched_priority; }; #ifdef __KERNEL__ #include /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; typedef struct task_struct task_t; extern void sched_init(void); extern void init_idle(task_t *idle, int cpu); extern void show_state(void); extern void show_trace(unsigned long *stack); extern void show_stack(unsigned long *stack); extern void show_regs(struct pt_regs *); void io_schedule(void); long io_schedule_timeout(long timeout); extern void cpu_init (void); extern void trap_init(void); extern void update_process_times(int user); extern void update_one_process(struct task_struct *p, unsigned long user, unsigned long system, int cpu); extern void scheduler_tick(int user_tick, int system); extern unsigned long cache_decay_ticks; #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern signed long FASTCALL(schedule_timeout(signed long timeout)); asmlinkage void schedule(void); struct namespace; /* Maximum number of active map areas.. This is a random (large) number */ #define MAX_MAP_COUNT (65536) #include 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 free_area_cache; /* first hole */ 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 task page tables and mm->rss */ struct list_head mmlist; /* List of all active mm's. These are globally strung * together off init_mm.mmlist, and are protected * by mmlist_lock */ 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 rss, total_vm, locked_vm; unsigned long def_flags; unsigned long cpu_vm_mask; unsigned long swap_address; unsigned dumpable:1; /* Architecture-specific MM context */ mm_context_t context; /* coredumping support */ int core_waiters; struct completion *core_startup_done, core_done; /* aio bits */ rwlock_t ioctx_list_lock; struct kioctx *ioctx_list; struct kioctx default_kioctx; }; extern int mmlist_nr; struct signal_struct { atomic_t count; struct k_sigaction action[_NSIG]; spinlock_t siglock; /* current thread group signal load-balancing target: */ task_t *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* thread group exit support */ int group_exit; int group_exit_code; struct task_struct *group_exit_task; }; /* * Priority of a process goes from 0..MAX_PRIO-1, valid RT * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL tasks are * in the range MAX_RT_PRIO..MAX_PRIO-1. Priority values * are inverted: lower p->prio value means higher priority. * * The MAX_RT_USER_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) /* * Some day this will be a full-fledged user tracking system.. */ struct user_struct { atomic_t __count; /* reference count */ atomic_t processes; /* How many processes does this user have? */ atomic_t files; /* How many open files does this user have? */ /* Hash table maintenance information */ struct list_head uidhash_list; uid_t uid; }; #define get_current_user() ({ \ struct user_struct *__user = current->user; \ atomic_inc(&__user->__count); \ __user; }) extern struct user_struct *find_user(uid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) typedef struct prio_array prio_array_t; struct backing_dev_info; struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ struct thread_info *thread_info; atomic_t usage; unsigned long flags; /* per process flags, defined below */ unsigned long ptrace; int lock_depth; /* Lock depth */ int prio, static_prio; struct list_head run_list; prio_array_t *array; unsigned long sleep_avg; unsigned long sleep_timestamp; unsigned long policy; unsigned long cpus_allowed; unsigned int time_slice, first_time_slice; struct list_head tasks; struct list_head ptrace_children; struct list_head ptrace_list; struct mm_struct *mm, *active_mm; /* task state */ struct linux_binfmt *binfmt; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ /* ??? */ unsigned long personality; int did_exec:1; pid_t pid; pid_t pgrp; pid_t tty_old_pgrp; pid_t session; pid_t tgid; /* boolean value for session group leader */ int leader; /* * pointers to (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->parent->pid) */ struct task_struct *real_parent; /* real parent process (when being debugged) */ struct task_struct *parent; /* parent process */ struct list_head children; /* list of my children */ struct list_head sibling; /* linkage in my parent's children list */ struct task_struct *group_leader; /* PID/PID hash table linkage. */ struct pid_link pids[PIDTYPE_MAX]; wait_queue_head_t wait_chldexit; /* for wait4() */ struct completion *vfork_done; /* for vfork() */ int *set_child_tid; /* CLONE_CHILD_SETTID */ int *clear_child_tid; /* CLONE_CHILD_CLEARTID */ unsigned long rt_priority; unsigned long it_real_value, it_prof_value, it_virt_value; unsigned long it_real_incr, it_prof_incr, it_virt_incr; struct timer_list real_timer; unsigned long utime, stime, cutime, cstime; unsigned long start_time; /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap; int swappable:1; /* process credentials */ uid_t uid,euid,suid,fsuid; gid_t gid,egid,sgid,fsgid; int ngroups; gid_t groups[NGROUPS]; kernel_cap_t cap_effective, cap_inheritable, cap_permitted; int keep_capabilities:1; struct user_struct *user; /* limits */ struct rlimit rlim[RLIM_NLIMITS]; unsigned short used_math; char comm[16]; /* file system info */ int link_count, total_link_count; struct tty_struct *tty; /* NULL if no tty */ unsigned int locks; /* How many file locks are being held */ /* ipc stuff */ struct sysv_sem sysvsem; /* CPU-specific state of this task */ struct thread_struct thread; /* filesystem information */ struct fs_struct *fs; /* open file information */ struct files_struct *files; /* namespace */ struct namespace *namespace; /* signal handlers */ struct signal_struct *sig; sigset_t blocked, real_blocked; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; void *security; /* Thread group tracking */ u32 parent_exec_id; u32 self_exec_id; /* Protection of (de-)allocation: mm, files, fs, tty */ spinlock_t alloc_lock; /* context-switch lock */ spinlock_t switch_lock; /* journalling filesystem info */ void *journal_info; struct dentry *proc_dentry; struct backing_dev_info *backing_dev_info; unsigned long ptrace_message; }; extern void __put_task_struct(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) #define put_task_struct(tsk) \ do { if (atomic_dec_and_test(&(tsk)->usage)) __put_task_struct(tsk); } while(0) /* * Per process flags */ #define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */ /* Not implemented yet, only for 486*/ #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ #define PF_SIGNALED 0x00000400 /* killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_MEMDIE 0x00001000 /* Killed for out-of-memory */ #define PF_FLUSHER 0x00002000 /* responsible for disk writeback */ #define PF_FREEZE 0x00004000 /* this task should be frozen for suspend */ #define PF_IOTHREAD 0x00008000 /* this thread is needed for doing I/O to swap */ #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ /* * Ptrace flags */ #define PT_PTRACED 0x00000001 #define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_TRACESYSGOOD 0x00000004 #define PT_PTRACE_CAP 0x00000008 /* ptracer can follow suid-exec */ #define PT_TRACE_FORK 0x00000010 #define PT_TRACE_VFORK 0x00000020 #define PT_TRACE_CLONE 0x00000040 #define PT_TRACE_EXEC 0x00000080 #if CONFIG_SMP extern void set_cpus_allowed(task_t *p, unsigned long new_mask); #else # define set_cpus_allowed(p, new_mask) do { } while (0) #endif extern void set_user_nice(task_t *p, long nice); extern int task_prio(task_t *p); extern int task_nice(task_t *p); extern int task_curr(task_t *p); extern int idle_cpu(int cpu); void yield(void); /* * The default (Linux) execution domain. */ extern struct exec_domain default_exec_domain; #ifndef INIT_THREAD_SIZE # define INIT_THREAD_SIZE 2048*sizeof(long) #endif union thread_union { struct thread_info thread_info; unsigned long stack[INIT_THREAD_SIZE/sizeof(long)]; }; extern union thread_union init_thread_union; extern struct task_struct init_task; extern struct mm_struct init_mm; extern struct task_struct *find_task_by_pid(int pid); /* per-UID process charging. */ extern struct user_struct * alloc_uid(uid_t); extern void free_uid(struct user_struct *); #include extern unsigned long itimer_ticks; extern unsigned long itimer_next; extern void do_timer(struct pt_regs *); extern int FASTCALL(wake_up_process(struct task_struct * tsk)); extern void FASTCALL(wake_up_forked_process(struct task_struct * tsk)); extern void FASTCALL(sched_exit(task_t * p)); asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru); extern int in_group_p(gid_t); extern int in_egroup_p(gid_t); extern void proc_caches_init(void); extern void flush_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *); extern void sig_exit(int, int, struct siginfo *); extern int dequeue_signal(sigset_t *mask, siginfo_t *info); extern void block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask); extern void unblock_all_signals(void); extern void release_task(struct task_struct * p); extern int send_sig_info(int, struct siginfo *, struct task_struct *); extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); extern int kill_sl_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); extern void notify_parent(struct task_struct *, int); extern void do_notify_parent(struct task_struct *, int); 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 int __broadcast_thread_group(struct task_struct *p, int sig); extern int kill_pg(pid_t, int, int); extern int kill_sl(pid_t, int, int); extern int kill_proc(pid_t, int, int); extern int do_sigaction(int, const struct k_sigaction *, struct k_sigaction *); extern int do_sigaltstack(const stack_t *, stack_t *, unsigned long); /* 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); } static inline int sas_ss_flags(unsigned long sp) { return (current->sas_ss_size == 0 ? SS_DISABLE : on_sig_stack(sp) ? SS_ONSTACK : 0); } #ifdef CONFIG_SECURITY /* code is in security.c */ extern int capable(int cap); #else static inline int capable(int cap) { if (cap_raised(current->cap_effective, cap)) { current->flags |= PF_SUPERPRIV; return 1; } return 0; } #endif /* * Routines for handling mm_structs */ extern struct mm_struct * mm_alloc(void); extern struct mm_struct * start_lazy_tlb(void); extern void end_lazy_tlb(struct mm_struct *mm); /* mmdrop drops the mm and the page tables */ extern inline void FASTCALL(__mmdrop(struct mm_struct *)); static inline void mmdrop(struct mm_struct * mm) { if (atomic_dec_and_test(&mm->mm_count)) __mmdrop(mm); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct */ extern void mm_release(void); extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *); extern void flush_thread(void); extern void exit_thread(void); extern void exit_mm(struct task_struct *); extern void exit_files(struct task_struct *); extern void exit_sighand(struct task_struct *); extern void __exit_sighand(struct task_struct *); extern void reparent_to_init(void); extern void daemonize(void); extern task_t *child_reaper; extern int do_execve(char *, char **, char **, struct pt_regs *); extern struct task_struct *do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int *, int *); #ifdef CONFIG_SMP extern void wait_task_inactive(task_t * p); #else #define wait_task_inactive(p) do { } while (0) #endif extern void kick_if_running(task_t * p); #define remove_parent(p) list_del_init(&(p)->sibling) #define add_parent(p, parent) list_add_tail(&(p)->sibling,&(parent)->children) #define REMOVE_LINKS(p) do { \ if (thread_group_leader(p)) \ list_del_init(&(p)->tasks); \ remove_parent(p); \ } while (0) #define SET_LINKS(p) do { \ if (thread_group_leader(p)) \ list_add_tail(&(p)->tasks,&init_task.tasks); \ add_parent(p, (p)->parent); \ } while (0) #define next_task(p) list_entry((p)->tasks.next, struct task_struct, tasks) #define prev_task(p) list_entry((p)->tasks.prev, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) /* * Careful: do_each_thread/while_each_thread is a double loop so * 'break' will not work as expected - use goto instead. */ #define do_each_thread(g, t) \ for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) extern task_t * FASTCALL(next_thread(task_t *p)); #define thread_group_leader(p) (p->pid == p->tgid) static inline int thread_group_empty(task_t *p) { struct pid *pid = p->pids[PIDTYPE_TGID].pidptr; return pid->task_list.next->next == &pid->task_list; } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern void unhash_process(struct task_struct *p); /* Protects ->fs, ->files, ->mm, and synchronises with wait4(). Nests inside tasklist_lock */ static inline void task_lock(struct task_struct *p) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) { spin_unlock(&p->alloc_lock); } /** * get_task_mm - acquire a reference to the task's mm * * Returns %NULL if the task has no mm. User must release * the mm via mmput() after use. */ static inline struct mm_struct * get_task_mm(struct task_struct * task) { struct mm_struct * mm; task_lock(task); mm = task->mm; if (mm) atomic_inc(&mm->mm_users); task_unlock(task); return mm; } /* set thread flags in other task's structures * - see asm/thread_info.h for TIF_xxxx flags available */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(tsk->thread_info,flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(tsk->thread_info,flag); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(tsk->thread_info,flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(tsk->thread_info,flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(tsk->thread_info,flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline int signal_pending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int need_resched(void) { return unlikely(test_thread_flag(TIF_NEED_RESCHED)); } extern void __cond_resched(void); static inline void cond_resched(void) { if (need_resched()) __cond_resched(); } #ifdef CONFIG_PREEMPT /* * cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * * Note: this does not assume the given lock is the _only_ lock held. * The kernel preemption counter gives us "free" checking that we are * atomic -- let's use it. */ static inline void cond_resched_lock(spinlock_t * lock) { if (need_resched() && preempt_count() == 1) { _raw_spin_unlock(lock); preempt_enable_no_resched(); __cond_resched(); spin_lock(lock); } } #else static inline void cond_resched_lock(spinlock_t * lock) { } #endif /* Reevaluate whether the task has signals pending delivery. This is required every time the blocked sigset_t changes. callers must hold sig->siglock. */ extern FASTCALL(void recalc_sigpending_tsk(struct task_struct *t)); extern void recalc_sigpending(void); /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(struct task_struct *p) { return p->thread_info->cpu; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { p->thread_info->cpu = cpu; } #else static inline unsigned int task_cpu(struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ #endif /* __KERNEL__ */ #endif