sched.h 50.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
#include <linux/auxvec.h>	/* For AT_VECTOR_SIZE */

/*
 * 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_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	/* Unused, ignored */
#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 */
#define CLONE_STOPPED		0x02000000	/* Start in stopped state */

/*
 * Scheduling policies
 */
#define SCHED_NORMAL		0
#define SCHED_FIFO		1
#define SCHED_RR		2
#define SCHED_BATCH		3

36
#ifdef __KERNEL__
37 38 39 40 41

struct sched_param {
	int sched_priority;
};

L
Linus Torvalds 已提交
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73
#include <asm/param.h>	/* for HZ */

#include <linux/capability.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/nodemask.h>

#include <asm/system.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>
#include <asm/cputime.h>

#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/securebits.h>
#include <linux/fs_struct.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/seccomp.h>
I
Ingo Molnar 已提交
74
#include <linux/rcupdate.h>
75
#include <linux/futex.h>
I
Ingo Molnar 已提交
76
#include <linux/rtmutex.h>
L
Linus Torvalds 已提交
77

78 79 80 81 82 83 84
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>

#include <asm/processor.h>
H
H. J. Lu 已提交
85

L
Linus Torvalds 已提交
86
struct exec_domain;
87
struct futex_pi_state;
L
Linus Torvalds 已提交
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125

/*
 * 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)	/* 1.0 as fixed-point */
#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
#define EXP_5		2014		/* 1/exp(5sec/5min) */
#define EXP_15		2037		/* 1/exp(5sec/15min) */

#define CALC_LOAD(load,exp,n) \
	load *= exp; \
	load += n*(FIXED_1-exp); \
	load >>= FSHIFT;

extern unsigned long total_forks;
extern int nr_threads;
extern int last_pid;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
126
extern unsigned long nr_active(void);
L
Linus Torvalds 已提交
127
extern unsigned long nr_iowait(void);
128
extern unsigned long weighted_cpuload(const int cpu);
L
Linus Torvalds 已提交
129 130


131 132 133 134 135 136 137 138 139 140
/*
 * Task state bitmask. NOTE! These bits are also
 * encoded in fs/proc/array.c: get_task_state().
 *
 * We have two separate sets of flags: task->state
 * is about runnability, while task->exit_state are
 * about the task exiting. Confusing, but this way
 * modifying one set can't modify the other one by
 * mistake.
 */
L
Linus Torvalds 已提交
141 142 143
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
144 145 146 147 148 149 150
#define TASK_STOPPED		4
#define TASK_TRACED		8
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
#define TASK_NONINTERACTIVE	64
L
Linus Torvalds 已提交
151 152 153 154 155 156

#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))

157 158 159 160 161 162 163 164 165 166 167
/*
 * set_current_state() includes a barrier so that the write of current->state
 * is correctly serialised wrt the caller's subsequent test of whether to
 * actually sleep:
 *
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (do_i_need_to_sleep())
 *		schedule();
 *
 * If the caller does not need such serialisation then use __set_current_state()
 */
L
Linus Torvalds 已提交
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186
#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))

/* Task command name length */
#define TASK_COMM_LEN 16

#include <linux/spinlock.h>

/*
 * 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;

187
struct task_struct;
L
Linus Torvalds 已提交
188 189 190

extern void sched_init(void);
extern void sched_init_smp(void);
191
extern void init_idle(struct task_struct *idle, int cpu);
L
Linus Torvalds 已提交
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212

extern cpumask_t nohz_cpu_mask;

extern void show_state(void);
extern void show_regs(struct pt_regs *);

/*
 * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
 * task), SP is the stack pointer of the first frame that should be shown in the back
 * trace (or NULL if the entire call-chain of the task should be shown).
 */
extern void show_stack(struct task_struct *task, unsigned long *sp);

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 scheduler_tick(void);

I
Ingo Molnar 已提交
213
#ifdef CONFIG_DETECT_SOFTLOCKUP
214
extern void softlockup_tick(void);
I
Ingo Molnar 已提交
215 216 217
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
#else
218
static inline void softlockup_tick(void)
I
Ingo Molnar 已提交
219 220 221 222 223 224 225 226 227 228 229
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
#endif


L
Linus Torvalds 已提交
230 231 232 233 234 235 236
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
extern signed long FASTCALL(schedule_timeout(signed long timeout));
237 238
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
asmlinkage void schedule(void);

struct namespace;

/* Maximum number of active map areas.. This is a random (large) number */
#define DEFAULT_MAX_MAP_COUNT	65536

extern int sysctl_max_map_count;

#include <linux/aio.h>

extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
		       unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags);
257 258
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
L
Linus Torvalds 已提交
259

260 261 262 263 264
#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
265 266 267 268 269 270
#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)
typedef atomic_long_t mm_counter_t;
271 272 273 274 275 276

#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
/*
 * The mm counters are protected by its page_table_lock,
 * so can be incremented directly.
 */
L
Linus Torvalds 已提交
277 278 279 280 281
#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--
282 283 284
typedef unsigned long mm_counter_t;

#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
285

286 287
#define get_mm_rss(mm)					\
	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
288 289 290 291 292 293 294 295 296 297
#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)

L
Linus Torvalds 已提交
298 299 300 301 302 303 304
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);
305
	void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
306 307 308
	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 */
309
	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
L
Linus Torvalds 已提交
310 311 312 313 314 315 316 317 318 319 320 321
	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
						 */

322 323 324
	/* Special counters, in some configurations protected by the
	 * page_table_lock, in other configurations by being atomic.
	 */
325
	mm_counter_t _file_rss;
L
Linus Torvalds 已提交
326 327
	mm_counter_t _anon_rss;

328 329 330 331 332 333 334 335 336
	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;

H
H. J. Lu 已提交
337
	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
L
Linus Torvalds 已提交
338

A
Alan Cox 已提交
339
	unsigned dumpable:2;
L
Linus Torvalds 已提交
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363
	cpumask_t cpu_vm_mask;

	/* Architecture-specific MM context */
	mm_context_t context;

	/* Token based thrashing protection. */
	unsigned long swap_token_time;
	char recent_pagein;

	/* coredumping support */
	int core_waiters;
	struct completion *core_startup_done, core_done;

	/* aio bits */
	rwlock_t		ioctx_list_lock;
	struct kioctx		*ioctx_list;
};

struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
};

364
struct pacct_struct {
365 366
	int			ac_flag;
	long			ac_exitcode;
367
	unsigned long		ac_mem;
368 369
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
370 371
};

L
Linus Torvalds 已提交
372 373 374 375 376 377 378 379 380 381 382 383 384 385
/*
 * NOTE! "signal_struct" does not have it's own
 * locking, because a shared signal_struct always
 * implies a shared sighand_struct, so locking
 * sighand_struct is always a proper superset of
 * the locking of signal_struct.
 */
struct signal_struct {
	atomic_t		count;
	atomic_t		live;

	wait_queue_head_t	wait_chldexit;	/* for wait4() */

	/* current thread group signal load-balancing target: */
386
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408

	/* shared signal handling: */
	struct sigpending	shared_pending;

	/* thread group exit support */
	int			group_exit_code;
	/* overloaded:
	 * - notify group_exit_task when ->count is equal to notify_count
	 * - everyone except group_exit_task is stopped during signal delivery
	 *   of fatal signals, group_exit_task processes the signal.
	 */
	struct task_struct	*group_exit_task;
	int			notify_count;

	/* thread group stop support, overloads group_exit_code too */
	int			group_stop_count;
	unsigned int		flags; /* see SIGNAL_* flags below */

	/* POSIX.1b Interval Timers */
	struct list_head posix_timers;

	/* ITIMER_REAL timer for the process */
409
	struct hrtimer real_timer;
410
	struct task_struct *tsk;
411
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462

	/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
	cputime_t it_prof_expires, it_virt_expires;
	cputime_t it_prof_incr, it_virt_incr;

	/* job control IDs */
	pid_t pgrp;
	pid_t tty_old_pgrp;
	pid_t session;
	/* boolean value for session group leader */
	int leader;

	struct tty_struct *tty; /* NULL if no tty */

	/*
	 * Cumulative resource counters for dead threads in the group,
	 * and for reaped dead child processes forked by this group.
	 * Live threads maintain their own counters and add to these
	 * in __exit_signal, except for the group leader.
	 */
	cputime_t utime, stime, cutime, cstime;
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;

	/*
	 * Cumulative ns of scheduled CPU time for dead threads in the
	 * group, not including a zombie group leader.  (This only differs
	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
	 * other than jiffies.)
	 */
	unsigned long long sched_time;

	/*
	 * We don't bother to synchronize most readers of this at all,
	 * because there is no reader checking a limit that actually needs
	 * to get both rlim_cur and rlim_max atomically, and either one
	 * alone is a single word that can safely be read normally.
	 * getrlimit/setrlimit use task_lock(current->group_leader) to
	 * protect this instead of the siglock, because they really
	 * have no need to disable irqs.
	 */
	struct rlimit rlim[RLIM_NLIMITS];

	struct list_head cpu_timers[3];

	/* keep the process-shared keyrings here so that they do the right
	 * thing in threads created with CLONE_THREAD */
#ifdef CONFIG_KEYS
	struct key *session_keyring;	/* keyring inherited over fork */
	struct key *process_keyring;	/* keyring private to this process */
#endif
463 464 465
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
466 467 468 469
#ifdef CONFIG_TASKSTATS
	spinlock_t stats_lock;
	struct taskstats *stats;
#endif
L
Linus Torvalds 已提交
470 471
};

472 473 474 475 476
/* Context switch must be unlocked if interrupts are to be enabled */
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
# define __ARCH_WANT_UNLOCKED_CTXSW
#endif

L
Linus Torvalds 已提交
477 478 479 480 481 482 483 484 485 486 487
/*
 * Bits in flags field of signal_struct.
 */
#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_DEQUEUED	0x00000002 /* stop signal dequeued */
#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
488 489 490
 * 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.
L
Linus Torvalds 已提交
491 492 493 494 495 496 497 498 499 500 501 502 503
 *
 * 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)

504 505
#define rt_prio(prio)		unlikely((prio) < MAX_RT_PRIO)
#define rt_task(p)		rt_prio((p)->prio)
506
#define batch_task(p)		(unlikely((p)->policy == SCHED_BATCH))
507 508
#define has_rt_policy(p) \
	unlikely((p)->policy != SCHED_NORMAL && (p)->policy != SCHED_BATCH)
L
Linus Torvalds 已提交
509 510 511 512 513 514 515 516 517

/*
 * 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? */
	atomic_t sigpending;	/* How many pending signals does this user have? */
518
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
519 520 521
	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
L
Linus Torvalds 已提交
522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
	unsigned long locked_shm; /* How many pages of mlocked shm ? */

#ifdef CONFIG_KEYS
	struct key *uid_keyring;	/* UID specific keyring */
	struct key *session_keyring;	/* UID's default session keyring */
#endif

	/* Hash table maintenance information */
	struct list_head uidhash_list;
	uid_t uid;
};

extern struct user_struct *find_user(uid_t);

extern struct user_struct root_user;
#define INIT_USER (&root_user)

struct backing_dev_info;
struct reclaim_state;

544
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
545 546 547 548 549 550 551 552 553 554
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 */

	/* timestamps */
	unsigned long	last_arrival,	/* when we last ran on a cpu */
			last_queued;	/* when we were last queued to run */
};
555
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
556

557
#ifdef CONFIG_SCHEDSTATS
L
Linus Torvalds 已提交
558
extern struct file_operations proc_schedstat_operations;
559
#endif /* CONFIG_SCHEDSTATS */
L
Linus Torvalds 已提交
560

561 562 563 564 565 566 567 568 569 570 571 572 573 574
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
	spinlock_t	lock;
	unsigned int	flags;	/* Private per-task flags */

	/* For each stat XXX, add following, aligned appropriately
	 *
	 * struct timespec XXX_start, XXX_end;
	 * u64 XXX_delay;
	 * u32 XXX_count;
	 *
	 * Atomicity of updates to XXX_delay, XXX_count protected by
	 * single lock above (split into XXX_lock if contention is an issue).
	 */
575 576 577 578 579 580 581 582 583 584 585 586 587

	/*
	 * XXX_count is incremented on every XXX operation, the delay
	 * associated with the operation is added to XXX_delay.
	 * XXX_delay contains the accumulated delay time in nanoseconds.
	 */
	struct timespec blkio_start, blkio_end;	/* Shared by blkio, swapin */
	u64 blkio_delay;	/* wait for sync block io completion */
	u64 swapin_delay;	/* wait for swapin block io completion */
	u32 blkio_count;	/* total count of the number of sync block */
				/* io operations performed */
	u32 swapin_count;	/* total count of the number of swapin block */
				/* io operations performed */
588
};
589 590 591 592 593 594 595 596 597 598 599
#endif	/* CONFIG_TASK_DELAY_ACCT */

static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
	return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
	extern int delayacct_on;
	return delayacct_on;
#else
	return 0;
600
#endif
601
}
602

L
Linus Torvalds 已提交
603 604 605 606 607 608 609 610 611 612 613 614 615
enum idle_type
{
	SCHED_IDLE,
	NOT_IDLE,
	NEWLY_IDLE,
	MAX_IDLE_TYPES
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
#define SCHED_LOAD_SCALE	128UL	/* increase resolution of load */

616
#ifdef CONFIG_SMP
L
Linus Torvalds 已提交
617 618 619
#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
#define SD_BALANCE_EXEC		4	/* Balance on exec */
N
Nick Piggin 已提交
620 621 622 623 624
#define SD_BALANCE_FORK		8	/* Balance on fork, clone */
#define SD_WAKE_IDLE		16	/* Wake to idle CPU on task wakeup */
#define SD_WAKE_AFFINE		32	/* Wake task to waking CPU */
#define SD_WAKE_BALANCE		64	/* Perform balancing at task wakeup */
#define SD_SHARE_CPUPOWER	128	/* Domain members share cpu power */
625 626 627 628 629
#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */

#define BALANCE_FOR_POWER	((sched_mc_power_savings || sched_smt_power_savings) \
				 ? SD_POWERSAVINGS_BALANCE : 0)

L
Linus Torvalds 已提交
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653

struct sched_group {
	struct sched_group *next;	/* Must be a circular list */
	cpumask_t cpumask;

	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
	 * single CPU. This is read only (except for setup, hotplug CPU).
	 */
	unsigned long cpu_power;
};

struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
	struct sched_group *groups;	/* the balancing groups of the domain */
	cpumask_t span;			/* span of all CPUs in this domain */
	unsigned long min_interval;	/* Minimum balance interval ms */
	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 per_cpu_gain;	/* CPU % gained by adding domain cpus */
N
Nick Piggin 已提交
654 655 656 657
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
658
	unsigned int forkexec_idx;
L
Linus Torvalds 已提交
659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681
	int flags;			/* See SD_* */

	/* Runtime fields. */
	unsigned long last_balance;	/* init to jiffies. units in jiffies */
	unsigned int balance_interval;	/* initialise to 1. units in ms. */
	unsigned int nr_balance_failed; /* initialise to 0 */

#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
	unsigned long lb_cnt[MAX_IDLE_TYPES];
	unsigned long lb_failed[MAX_IDLE_TYPES];
	unsigned long lb_balanced[MAX_IDLE_TYPES];
	unsigned long lb_imbalance[MAX_IDLE_TYPES];
	unsigned long lb_gained[MAX_IDLE_TYPES];
	unsigned long lb_hot_gained[MAX_IDLE_TYPES];
	unsigned long lb_nobusyg[MAX_IDLE_TYPES];
	unsigned long lb_nobusyq[MAX_IDLE_TYPES];

	/* Active load balancing */
	unsigned long alb_cnt;
	unsigned long alb_failed;
	unsigned long alb_pushed;

682 683 684
	/* SD_BALANCE_EXEC stats */
	unsigned long sbe_cnt;
	unsigned long sbe_balanced;
L
Linus Torvalds 已提交
685 686
	unsigned long sbe_pushed;

687 688 689 690 691
	/* SD_BALANCE_FORK stats */
	unsigned long sbf_cnt;
	unsigned long sbf_balanced;
	unsigned long sbf_pushed;

L
Linus Torvalds 已提交
692 693 694 695 696 697 698
	/* try_to_wake_up() stats */
	unsigned long ttwu_wake_remote;
	unsigned long ttwu_move_affine;
	unsigned long ttwu_move_balance;
#endif
};

699
extern int partition_sched_domains(cpumask_t *partition1,
700
				    cpumask_t *partition2);
701 702 703 704 705 706 707 708

/*
 * Maximum cache size the migration-costs auto-tuning code will
 * search from:
 */
extern unsigned int max_cache_size;

#endif	/* CONFIG_SMP */
L
Linus Torvalds 已提交
709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739


struct io_context;			/* See blkdev.h */
void exit_io_context(void);
struct cpuset;

#define NGROUPS_SMALL		32
#define NGROUPS_PER_BLOCK	((int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
	int ngroups;
	atomic_t usage;
	gid_t small_block[NGROUPS_SMALL];
	int nblocks;
	gid_t *blocks[0];
};

/*
 * get_group_info() must be called with the owning task locked (via task_lock())
 * when task != current.  The reason being that the vast majority of callers are
 * looking at current->group_info, which can not be changed except by the
 * current task.  Changing current->group_info requires the task lock, too.
 */
#define get_group_info(group_info) do { \
	atomic_inc(&(group_info)->usage); \
} while (0)

#define put_group_info(group_info) do { \
	if (atomic_dec_and_test(&(group_info)->usage)) \
		groups_free(group_info); \
} while (0)

740 741 742 743
extern struct group_info *groups_alloc(int gidsetsize);
extern void groups_free(struct group_info *group_info);
extern int set_current_groups(struct group_info *group_info);
extern int groups_search(struct group_info *group_info, gid_t grp);
L
Linus Torvalds 已提交
744 745 746 747
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])

748
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
749
extern void prefetch_stack(struct task_struct *t);
750 751 752
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
753 754 755

struct audit_context;		/* See audit.c */
struct mempolicy;
756
struct pipe_inode_info;
L
Linus Torvalds 已提交
757

758 759 760 761 762 763 764
enum sleep_type {
	SLEEP_NORMAL,
	SLEEP_NONINTERACTIVE,
	SLEEP_INTERACTIVE,
	SLEEP_INTERRUPTED,
};

765 766
struct prio_array;

L
Linus Torvalds 已提交
767 768 769 770 771 772 773
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;

774
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
775

776 777
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
778 779
	int oncpu;
#endif
780 781
#endif
	int load_weight;	/* for niceness load balancing purposes */
782
	int prio, static_prio, normal_prio;
L
Linus Torvalds 已提交
783
	struct list_head run_list;
784
	struct prio_array *array;
L
Linus Torvalds 已提交
785

786
	unsigned short ioprio;
787
	unsigned int btrace_seq;
788

L
Linus Torvalds 已提交
789 790 791
	unsigned long sleep_avg;
	unsigned long long timestamp, last_ran;
	unsigned long long sched_time; /* sched_clock time spent running */
792
	enum sleep_type sleep_type;
L
Linus Torvalds 已提交
793 794 795 796 797

	unsigned long policy;
	cpumask_t cpus_allowed;
	unsigned int time_slice, first_time_slice;

798
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821
	struct sched_info sched_info;
#endif

	struct list_head tasks;
	/*
	 * ptrace_list/ptrace_children forms the list of my children
	 * that were stolen by a ptracer.
	 */
	struct list_head ptrace_children;
	struct list_head ptrace_list;

	struct mm_struct *mm, *active_mm;

/* task state */
	struct linux_binfmt *binfmt;
	long exit_state;
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
	unsigned long personality;
	unsigned did_exec:1;
	pid_t pid;
	pid_t tgid;
822 823 824 825 826

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif
L
Linus Torvalds 已提交
827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
	/* 
	 * 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 */
	/*
	 * children/sibling forms the list of my children plus the
	 * tasks I'm ptracing.
	 */
	struct list_head children;	/* list of my children */
	struct list_head sibling;	/* linkage in my parent's children list */
	struct task_struct *group_leader;	/* threadgroup leader */

	/* PID/PID hash table linkage. */
843
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
844
	struct list_head thread_group;
L
Linus Torvalds 已提交
845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868

	struct completion *vfork_done;		/* for vfork() */
	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */

	unsigned long rt_priority;
	cputime_t utime, stime;
	unsigned long nvcsw, nivcsw; /* context switch counts */
	struct timespec 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;

  	cputime_t it_prof_expires, it_virt_expires;
	unsigned long long it_sched_expires;
	struct list_head cpu_timers[3];

/* process credentials */
	uid_t uid,euid,suid,fsuid;
	gid_t gid,egid,sgid,fsgid;
	struct group_info *group_info;
	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
	unsigned keep_capabilities:1;
	struct user_struct *user;
#ifdef CONFIG_KEYS
869
	struct key *request_key_auth;	/* assumed request_key authority */
L
Linus Torvalds 已提交
870
	struct key *thread_keyring;	/* keyring private to this thread */
871
	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
L
Linus Torvalds 已提交
872
#endif
873 874 875 876 877 878 879 880 881
	/*
	 * 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;
L
Linus Torvalds 已提交
882
	int oomkilladj; /* OOM kill score adjustment (bit shift). */
883 884 885 886
	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 */
L
Linus Torvalds 已提交
887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903
/* file system info */
	int link_count, total_link_count;
/* 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 *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
904
	sigset_t saved_sigmask;		/* To be restored with TIF_RESTORE_SIGMASK */
L
Linus Torvalds 已提交
905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922
	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;
	struct audit_context *audit_context;
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
	spinlock_t alloc_lock;

923 924 925
	/* Protection of the PI data structures: */
	spinlock_t pi_lock;

I
Ingo Molnar 已提交
926 927 928 929 930 931 932
#ifdef CONFIG_RT_MUTEXES
	/* PI waiters blocked on a rt_mutex held by this task */
	struct plist_head pi_waiters;
	/* Deadlock detection and priority inheritance handling */
	struct rt_mutex_waiter *pi_blocked_on;
#endif

933 934 935 936
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
#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_disable_event;
	int softirqs_enabled;
	unsigned long softirq_disable_ip;
	unsigned int softirq_disable_event;
	unsigned long softirq_enable_ip;
	unsigned int softirq_enable_event;
	int hardirq_context;
	int softirq_context;
#endif
I
Ingo Molnar 已提交
952 953 954 955 956 957 958
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 30UL
	u64 curr_chain_key;
	int lockdep_depth;
	struct held_lock held_locks[MAX_LOCK_DEPTH];
	unsigned int lockdep_recursion;
#endif
959

L
Linus Torvalds 已提交
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
/* journalling filesystem info */
	void *journal_info;

/* VM state */
	struct reclaim_state *reclaim_state;

	struct backing_dev_info *backing_dev_info;

	struct io_context *io_context;

	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;
/* i/o counters(bytes read/written, #syscalls */
	u64 rchar, wchar, syscr, syscw;
#if defined(CONFIG_BSD_PROCESS_ACCT)
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
	clock_t acct_stimexpd;	/* clock_t-converted stime since last update */
#endif
#ifdef CONFIG_NUMA
  	struct mempolicy *mempolicy;
	short il_next;
#endif
#ifdef CONFIG_CPUSETS
	struct cpuset *cpuset;
	nodemask_t mems_allowed;
	int cpuset_mems_generation;
994
	int cpuset_mem_spread_rotor;
L
Linus Torvalds 已提交
995
#endif
996
	struct robust_list_head __user *robust_list;
997 998 999
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1000 1001
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1002

1003
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1004
	struct rcu_head rcu;
1005 1006 1007 1008 1009

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1010 1011 1012
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
#endif
L
Linus Torvalds 已提交
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
};

static inline pid_t process_group(struct task_struct *tsk)
{
	return tsk->signal->pgrp;
}

/**
 * pid_alive - check that a task structure is not stale
 * @p: Task structure to be checked.
 *
 * Test if a process is not yet dead (at most zombie state)
 * If pid_alive fails, then pointers within the task structure
 * can be stale and must not be dereferenced.
 */
static inline int pid_alive(struct task_struct *p)
{
1030
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1031 1032 1033 1034
}

extern void free_task(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
I
Ingo Molnar 已提交
1035

1036
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1037 1038 1039 1040

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1041
		__put_task_struct(t);
I
Ingo Molnar 已提交
1042
}
L
Linus Torvalds 已提交
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065

/*
 * 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_DEAD		0x00000008	/* Dead */
#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_FLUSHER	0x00001000	/* responsible for disk writeback */
#define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
#define PF_FREEZE	0x00004000	/* this task is being frozen for suspend now */
#define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
#define PF_FROZEN	0x00010000	/* frozen for system suspend */
#define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
#define PF_KSWAPD	0x00040000	/* I am kswapd */
#define PF_SWAPOFF	0x00080000	/* I am in swapoff */
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
J
Jens Axboe 已提交
1066 1067 1068 1069 1070
#define PF_BORROWED_MM	0x00200000	/* I am a kthread doing use_mm */
#define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
#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 */
1071
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1072
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
L
Linus Torvalds 已提交
1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099

/*
 * Only the _current_ task can read/write to tsk->flags, but other
 * tasks can access tsk->flags in readonly mode for example
 * with tsk_used_math (like during threaded core dumping).
 * There is however an exception to this rule during ptrace
 * or during fork: the ptracer task is allowed to write to the
 * child->flags of its traced child (same goes for fork, the parent
 * can write to the child->flags), because we're guaranteed the
 * child is not running and in turn not changing child->flags
 * at the same time the parent does it.
 */
#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math() clear_stopped_child_used_math(current)
#define set_used_math() set_stopped_child_used_math(current)
#define conditional_stopped_child_used_math(condition, child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
#define conditional_used_math(condition) \
	conditional_stopped_child_used_math(condition, current)
#define copy_to_stopped_child_used_math(child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)

#ifdef CONFIG_SMP
1100
extern int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask);
L
Linus Torvalds 已提交
1101
#else
1102
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
L
Linus Torvalds 已提交
1103
{
1104
	if (!cpu_isset(0, new_mask))
L
Linus Torvalds 已提交
1105 1106 1107 1108 1109 1110
		return -EINVAL;
	return 0;
}
#endif

extern unsigned long long sched_clock(void);
1111 1112
extern unsigned long long
current_sched_time(const struct task_struct *current_task);
L
Linus Torvalds 已提交
1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127

/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec()   {}
#endif

#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif

extern void sched_idle_next(void);
1128 1129

#ifdef CONFIG_RT_MUTEXES
1130 1131 1132
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern void rt_mutex_adjust_pi(struct task_struct *p);
1133
#else
1134
static inline int rt_mutex_getprio(struct task_struct *p)
1135 1136 1137
{
	return p->normal_prio;
}
1138
# define rt_mutex_adjust_pi(p)		do { } while (0)
1139 1140
#endif

1141 1142 1143 1144 1145
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern int task_nice(const struct task_struct *p);
extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
L
Linus Torvalds 已提交
1146 1147
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
1148 1149 1150
extern struct task_struct *idle_task(int cpu);
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206

void yield(void);

/*
 * The default (Linux) execution domain.
 */
extern struct exec_domain	default_exec_domain;

union thread_union {
	struct thread_info thread_info;
	unsigned long stack[THREAD_SIZE/sizeof(long)];
};

#ifndef __HAVE_ARCH_KSTACK_END
static inline int kstack_end(void *addr)
{
	/* Reliable end of stack detection:
	 * Some APM bios versions misalign the stack
	 */
	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
}
#endif

extern union thread_union init_thread_union;
extern struct task_struct init_task;

extern struct   mm_struct init_mm;

#define find_task_by_pid(nr)	find_task_by_pid_type(PIDTYPE_PID, nr)
extern struct task_struct *find_task_by_pid_type(int type, int pid);
extern void set_special_pids(pid_t session, pid_t pgrp);
extern void __set_special_pids(pid_t session, pid_t pgrp);

/* per-UID process charging. */
extern struct user_struct * alloc_uid(uid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
{
	atomic_inc(&u->__count);
	return u;
}
extern void free_uid(struct user_struct *);
extern void switch_uid(struct user_struct *);

#include <asm/current.h>

extern void do_timer(struct pt_regs *);

extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
extern int FASTCALL(wake_up_process(struct task_struct * tsk));
extern void FASTCALL(wake_up_new_task(struct task_struct * tsk,
						unsigned long clone_flags));
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
1207 1208
extern void FASTCALL(sched_fork(struct task_struct * p, int clone_flags));
extern void FASTCALL(sched_exit(struct task_struct * p));
L
Linus Torvalds 已提交
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240

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 *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);

static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&tsk->sighand->siglock, flags);
	ret = dequeue_signal(tsk, mask, info);
	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);

	return ret;
}	

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 send_group_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, 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_proc_info(int, struct siginfo *, pid_t);
1241
extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t, u32);
L
Linus Torvalds 已提交
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
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 void zap_other_threads(struct task_struct *p);
extern int kill_pg(pid_t, int, int);
extern int kill_proc(pid_t, int, int);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(int, struct sigqueue *,  struct task_struct *);
extern int send_group_sigqueue(int, struct sigqueue *,  struct task_struct *);
1253
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
1254 1255 1256 1257 1258 1259 1260
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

/* These can be the second arg to send_sig_info/send_group_sig_info.  */
#define SEND_SIG_NOINFO ((struct siginfo *) 0)
#define SEND_SIG_PRIV	((struct siginfo *) 1)
#define SEND_SIG_FORCED	((struct siginfo *) 2)

1261 1262 1263 1264 1265
static inline int is_si_special(const struct siginfo *info)
{
	return info <= SEND_SIG_FORCED;
}

L
Linus Torvalds 已提交
1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303
/* 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);
}

/*
 * Routines for handling mm_structs
 */
extern struct mm_struct * mm_alloc(void);

/* mmdrop drops the mm and the page tables */
extern 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 *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);

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_files(struct task_struct *);
1304
extern void __cleanup_signal(struct signal_struct *);
1305
extern void __cleanup_sighand(struct sighand_struct *);
L
Linus Torvalds 已提交
1306 1307 1308 1309 1310 1311 1312
extern void exit_itimers(struct signal_struct *);

extern NORET_TYPE void do_group_exit(int);

extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);
1313
extern struct task_struct *child_reaper;
L
Linus Torvalds 已提交
1314 1315 1316

extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
1317
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
1318 1319 1320 1321 1322

extern void set_task_comm(struct task_struct *tsk, char *from);
extern void get_task_comm(char *to, struct task_struct *tsk);

#ifdef CONFIG_SMP
1323
extern void wait_task_inactive(struct task_struct * p);
L
Linus Torvalds 已提交
1324 1325 1326 1327 1328
#else
#define wait_task_inactive(p)	do { } while (0)
#endif

#define remove_parent(p)	list_del_init(&(p)->sibling)
1329
#define add_parent(p)		list_add_tail(&(p)->sibling,&(p)->parent->children)
L
Linus Torvalds 已提交
1330

1331
#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
L
Linus Torvalds 已提交
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345

#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)

1346 1347
/* de_thread depends on thread_group_leader not being a pid based check */
#define thread_group_leader(p)	(p == p->group_leader)
L
Linus Torvalds 已提交
1348

1349
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
1350 1351
{
	return list_entry(rcu_dereference(p->thread_group.next),
1352
			  struct task_struct, thread_group);
O
Oleg Nesterov 已提交
1353 1354
}

1355
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
1356
{
O
Oleg Nesterov 已提交
1357
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
1358 1359 1360 1361 1362 1363
}

#define delay_group_leader(p) \
		(thread_group_leader(p) && !thread_group_empty(p))

/*
1364
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
1365
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
1366
 * pins the final release of task.io_context.  Also protects ->cpuset.
L
Linus Torvalds 已提交
1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
 *
 * Nests both inside and outside of read_lock(&tasklist_lock).
 * It must not be nested with write_lock_irq(&tasklist_lock),
 * neither inside nor outside.
 */
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);
}

1382 1383 1384 1385 1386 1387 1388 1389 1390
extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
							unsigned long *flags);

static inline void unlock_task_sighand(struct task_struct *tsk,
						unsigned long *flags)
{
	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}

A
Al Viro 已提交
1391 1392
#ifndef __HAVE_THREAD_FUNCTIONS

A
Al Viro 已提交
1393
#define task_thread_info(task) (task)->thread_info
1394
#define task_stack_page(task) ((void*)((task)->thread_info))
A
Al Viro 已提交
1395

1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406
static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
{
	*task_thread_info(p) = *task_thread_info(org);
	task_thread_info(p)->task = p;
}

static inline unsigned long *end_of_stack(struct task_struct *p)
{
	return (unsigned long *)(p->thread_info + 1);
}

A
Al Viro 已提交
1407 1408
#endif

L
Linus Torvalds 已提交
1409 1410 1411 1412 1413
/* 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)
{
A
Al Viro 已提交
1414
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1415 1416 1417 1418
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1419
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1420 1421 1422 1423
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1424
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1425 1426 1427 1428
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1429
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1430 1431 1432 1433
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1434
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504
}

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));
}

/*
 * cond_resched() and cond_resched_lock(): latency reduction via
 * explicit rescheduling in places that are safe. The return
 * value indicates whether a reschedule was done in fact.
 * cond_resched_lock() will drop the spinlock before scheduling,
 * cond_resched_softirq() will enable bhs before scheduling.
 */
extern int cond_resched(void);
extern int cond_resched_lock(spinlock_t * lock);
extern int cond_resched_softirq(void);

/*
 * Does a critical section need to be broken due to another
 * task waiting?:
 */
#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)
# define need_lockbreak(lock) ((lock)->break_lock)
#else
# define need_lockbreak(lock) 0
#endif

/*
 * Does a critical section need to be broken due to another
 * task waiting or preemption being signalled:
 */
static inline int lock_need_resched(spinlock_t *lock)
{
	if (need_lockbreak(lock) || need_resched())
		return 1;
	return 0;
}

/* Reevaluate whether the task has signals pending delivery.
   This is required every time the blocked sigset_t changes.
   callers must hold sighand->siglock.  */

extern FASTCALL(void recalc_sigpending_tsk(struct task_struct *t));
extern void recalc_sigpending(void);

extern void signal_wake_up(struct task_struct *t, int resume_stopped);

/*
 * Wrappers for p->thread_info->cpu access. No-op on UP.
 */
#ifdef CONFIG_SMP

static inline unsigned int task_cpu(const struct task_struct *p)
{
A
Al Viro 已提交
1505
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
1506 1507 1508 1509
}

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
A
Al Viro 已提交
1510
	task_thread_info(p)->cpu = cpu;
L
Linus Torvalds 已提交
1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539
}

#else

static inline unsigned int task_cpu(const struct task_struct *p)
{
	return 0;
}

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
}

#endif /* CONFIG_SMP */

#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm)
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	mm->get_unmapped_area = arch_get_unmapped_area;
	mm->unmap_area = arch_unmap_area;
}
#endif

extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);

1540 1541 1542 1543 1544
#include <linux/sysdev.h>
extern int sched_mc_power_savings, sched_smt_power_savings;
extern struct sysdev_attribute attr_sched_mc_power_savings, attr_sched_smt_power_savings;
extern int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls);

L
Linus Torvalds 已提交
1545 1546 1547
extern void normalize_rt_tasks(void);

#ifdef CONFIG_PM
1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572
/*
 * Check if a process has been frozen
 */
static inline int frozen(struct task_struct *p)
{
	return p->flags & PF_FROZEN;
}

/*
 * Check if there is a request to freeze a process
 */
static inline int freezing(struct task_struct *p)
{
	return p->flags & PF_FREEZE;
}

/*
 * Request that a process be frozen
 * FIXME: SMP problem. We may not modify other process' flags!
 */
static inline void freeze(struct task_struct *p)
{
	p->flags |= PF_FREEZE;
}

1573 1574 1575 1576 1577 1578 1579 1580
/*
 * Sometimes we may need to cancel the previous 'freeze' request
 */
static inline void do_not_freeze(struct task_struct *p)
{
	p->flags &= ~PF_FREEZE;
}

1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
/*
 * Wake up a frozen process
 */
static inline int thaw_process(struct task_struct *p)
{
	if (frozen(p)) {
		p->flags &= ~PF_FROZEN;
		wake_up_process(p);
		return 1;
	}
	return 0;
}

/*
 * freezing is complete, mark process as frozen
 */
static inline void frozen_process(struct task_struct *p)
{
	p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN;
}

extern void refrigerator(void);
L
Linus Torvalds 已提交
1603 1604 1605
extern int freeze_processes(void);
extern void thaw_processes(void);

1606
static inline int try_to_freeze(void)
L
Linus Torvalds 已提交
1607
{
1608 1609
	if (freezing(current)) {
		refrigerator();
L
Linus Torvalds 已提交
1610 1611 1612 1613 1614
		return 1;
	} else
		return 0;
}
#else
1615 1616 1617 1618 1619 1620 1621
static inline int frozen(struct task_struct *p) { return 0; }
static inline int freezing(struct task_struct *p) { return 0; }
static inline void freeze(struct task_struct *p) { BUG(); }
static inline int thaw_process(struct task_struct *p) { return 1; }
static inline void frozen_process(struct task_struct *p) { BUG(); }

static inline void refrigerator(void) {}
L
Linus Torvalds 已提交
1622 1623 1624
static inline int freeze_processes(void) { BUG(); return 0; }
static inline void thaw_processes(void) {}

1625 1626
static inline int try_to_freeze(void) { return 0; }

L
Linus Torvalds 已提交
1627 1628 1629 1630
#endif /* CONFIG_PM */
#endif /* __KERNEL__ */

#endif