sched.h 63.4 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
/*
 * 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 */
25
#define CLONE_NEWUTS		0x04000000	/* New utsname group? */
K
Kirill Korotaev 已提交
26
#define CLONE_NEWIPC		0x08000000	/* New ipcs */
S
Serge E. Hallyn 已提交
27
#define CLONE_NEWUSER		0x10000000	/* New user namespace */
28
#define CLONE_NEWPID		0x20000000	/* New pid namespace */
29
#define CLONE_NEWNET		0x40000000	/* New network namespace */
30
#define CLONE_IO		0x80000000	/* Clone io context */
31 32 33 34 35 36 37 38

/*
 * Scheduling policies
 */
#define SCHED_NORMAL		0
#define SCHED_FIFO		1
#define SCHED_RR		2
#define SCHED_BATCH		3
I
Ingo Molnar 已提交
39 40
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE		5
41

42
#ifdef __KERNEL__
43 44 45 46 47

struct sched_param {
	int sched_priority;
};

L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56 57 58 59 60
#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>
61
#include <linux/mm_types.h>
L
Linus Torvalds 已提交
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76

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

#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.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>
P
Peter Zijlstra 已提交
77
#include <linux/proportions.h>
L
Linus Torvalds 已提交
78
#include <linux/seccomp.h>
I
Ingo Molnar 已提交
79
#include <linux/rcupdate.h>
I
Ingo Molnar 已提交
80
#include <linux/rtmutex.h>
L
Linus Torvalds 已提交
81

82 83 84 85 86
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
87
#include <linux/task_io_accounting.h>
88
#include <linux/kobject.h>
A
Arjan van de Ven 已提交
89
#include <linux/latencytop.h>
90 91

#include <asm/processor.h>
H
H. J. Lu 已提交
92

93
struct mem_cgroup;
L
Linus Torvalds 已提交
94
struct exec_domain;
95
struct futex_pi_state;
96
struct robust_list_head;
97
struct bio;
L
Linus Torvalds 已提交
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118

/*
 * 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 */
119
#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
L
Linus Torvalds 已提交
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134
#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;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
135
extern unsigned long nr_active(void);
L
Linus Torvalds 已提交
136
extern unsigned long nr_iowait(void);
137
extern unsigned long weighted_cpuload(const int cpu);
L
Linus Torvalds 已提交
138

I
Ingo Molnar 已提交
139 140
struct seq_file;
struct cfs_rq;
141
struct task_group;
I
Ingo Molnar 已提交
142 143 144 145
#ifdef CONFIG_SCHED_DEBUG
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
extern void
146
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
I
Ingo Molnar 已提交
147 148 149 150 151 152 153 154 155
#else
static inline void
proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
}
static inline void proc_sched_set_task(struct task_struct *p)
{
}
static inline void
156
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
I
Ingo Molnar 已提交
157 158 159
{
}
#endif
L
Linus Torvalds 已提交
160

161 162 163 164 165 166 167 168 169 170
/*
 * 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
171 172 173
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
M
Matthew Wilcox 已提交
174 175
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
176 177 178 179
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
180
#define TASK_DEAD		64
M
Matthew Wilcox 已提交
181 182 183 184 185 186
#define TASK_WAKEKILL		128

/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
L
Linus Torvalds 已提交
187

188 189
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
M
Matthew Wilcox 已提交
190
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
191 192 193

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
M
Matthew Wilcox 已提交
194 195
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED)
196

M
Matthew Wilcox 已提交
197 198
#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
199
#define task_is_stopped_or_traced(task)	\
M
Matthew Wilcox 已提交
200
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
201 202
#define task_contributes_to_load(task)	\
				((task->state & TASK_UNINTERRUPTIBLE) != 0)
L
Linus Torvalds 已提交
203 204 205 206 207 208

#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))

209 210 211 212 213 214 215 216 217 218 219
/*
 * 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
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
#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;

239
struct task_struct;
L
Linus Torvalds 已提交
240 241 242

extern void sched_init(void);
extern void sched_init_smp(void);
243
extern asmlinkage void schedule_tail(struct task_struct *prev);
244
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
245
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
246 247

extern cpumask_t nohz_cpu_mask;
248 249 250 251 252 253 254 255
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
#else
static inline int select_nohz_load_balancer(int cpu)
{
	return 0;
}
#endif
L
Linus Torvalds 已提交
256

P
Peter Zijlstra 已提交
257 258
extern unsigned long rt_needs_cpu(int cpu);

I
Ingo Molnar 已提交
259
/*
I
Ingo Molnar 已提交
260
 * Only dump TASK_* tasks. (0 for all tasks)
I
Ingo Molnar 已提交
261 262 263 264 265
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
I
Ingo Molnar 已提交
266
	show_state_filter(0);
I
Ingo Molnar 已提交
267 268
}

L
Linus Torvalds 已提交
269 270 271 272 273 274 275 276 277 278 279 280 281 282
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);
283
extern void account_process_tick(struct task_struct *task, int user);
L
Linus Torvalds 已提交
284 285
extern void update_process_times(int user);
extern void scheduler_tick(void);
P
Peter Zijlstra 已提交
286
extern void hrtick_resched(void);
L
Linus Torvalds 已提交
287

288 289
extern void sched_show_task(struct task_struct *p);

I
Ingo Molnar 已提交
290
#ifdef CONFIG_DETECT_SOFTLOCKUP
291
extern void softlockup_tick(void);
I
Ingo Molnar 已提交
292 293
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
294
extern void touch_all_softlockup_watchdogs(void);
I
Ingo Molnar 已提交
295
extern unsigned long  softlockup_thresh;
296 297
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
I
Ingo Molnar 已提交
298
extern unsigned long sysctl_hung_task_warnings;
I
Ingo Molnar 已提交
299
#else
300
static inline void softlockup_tick(void)
I
Ingo Molnar 已提交
301 302 303 304 305 306 307 308
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
309 310 311
static inline void touch_all_softlockup_watchdogs(void)
{
}
I
Ingo Molnar 已提交
312 313 314
#endif


L
Linus Torvalds 已提交
315 316
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
317 318 319 320

/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];

L
Linus Torvalds 已提交
321 322 323 324
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
325
extern signed long schedule_timeout(signed long timeout);
326
extern signed long schedule_timeout_interruptible(signed long timeout);
M
Matthew Wilcox 已提交
327
extern signed long schedule_timeout_killable(signed long timeout);
328
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
329 330
asmlinkage void schedule(void);

S
Serge E. Hallyn 已提交
331
struct nsproxy;
332
struct user_namespace;
L
Linus Torvalds 已提交
333 334 335 336 337 338 339 340 341 342 343 344 345 346 347

/* 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);
348 349
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
350

351 352 353 354 355
#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
356 357 358 359 360
#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)
361 362 363 364 365 366

#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
367 368 369 370 371
#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--
372 373

#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
374

375 376
#define get_mm_rss(mm)					\
	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
377 378 379 380 381 382 383 384 385 386
#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)

387 388 389 390
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
391
/* dumpable bits */
392 393
#define MMF_DUMPABLE      0  /* core dump is permitted */
#define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
394 395 396 397 398 399 400
#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
R
Roland McGrath 已提交
401
#define MMF_DUMP_ELF_HEADERS	6
402
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
R
Roland McGrath 已提交
403
#define MMF_DUMP_FILTER_BITS	5
404 405 406 407
#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))
408

L
Linus Torvalds 已提交
409 410 411 412
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
413
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
414 415
};

416
struct pacct_struct {
417 418
	int			ac_flag;
	long			ac_exitcode;
419
	unsigned long		ac_mem;
420 421
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
422 423
};

L
Linus Torvalds 已提交
424 425 426 427 428 429 430 431 432 433 434 435 436 437
/*
 * 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: */
438
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460

	/* 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 */
461
	struct hrtimer real_timer;
462
	struct pid *leader_pid;
463
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
464 465 466 467 468 469

	/* 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 */
470 471 472 473 474 475 476 477 478 479 480

	/*
	 * pgrp and session fields are deprecated.
	 * use the task_session_Xnr and task_pgrp_Xnr routines below
	 */

	union {
		pid_t pgrp __deprecated;
		pid_t __pgrp;
	};

481
	struct pid *tty_old_pgrp;
482 483 484 485 486 487

	union {
		pid_t session __deprecated;
		pid_t __session;
	};

L
Linus Torvalds 已提交
488 489 490 491 492 493 494 495 496 497 498 499
	/* 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;
500 501
	cputime_t gtime;
	cputime_t cgtime;
L
Linus Torvalds 已提交
502 503
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
504
	unsigned long inblock, oublock, cinblock, coublock;
L
Linus Torvalds 已提交
505 506 507 508 509 510 511

	/*
	 * 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.)
	 */
512
	unsigned long long sum_sched_runtime;
L
Linus Torvalds 已提交
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532

	/*
	 * 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
533 534 535
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
536 537 538
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
539 540 541 542
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
L
Linus Torvalds 已提交
543 544
};

545 546 547 548 549
/* 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
550 551 552 553 554 555 556
/*
 * 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 */
557 558 559 560 561 562
/*
 * Pending notifications to parent.
 */
#define SIGNAL_CLD_STOPPED	0x00000010
#define SIGNAL_CLD_CONTINUED	0x00000020
#define SIGNAL_CLD_MASK		(SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
L
Linus Torvalds 已提交
563

564 565 566 567 568 569 570
/* If true, all threads except ->group_exit_task have pending SIGKILL */
static inline int signal_group_exit(const struct signal_struct *sig)
{
	return	(sig->flags & SIGNAL_GROUP_EXIT) ||
		(sig->group_exit_task != NULL);
}

L
Linus Torvalds 已提交
571 572 573 574 575 576 577 578
/*
 * 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? */
579
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
580 581 582
	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
A
Alexey Dobriyan 已提交
583
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
584 585
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
586
#endif
L
Linus Torvalds 已提交
587 588 589 590 591 592 593 594
	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 */
P
Pavel Emelyanov 已提交
595
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
596
	uid_t uid;
597

598
#ifdef CONFIG_USER_SCHED
599
	struct task_group *tg;
D
Dhaval Giani 已提交
600
#ifdef CONFIG_SYSFS
601
	struct kobject kobj;
602
	struct work_struct work;
603
#endif
D
Dhaval Giani 已提交
604
#endif
L
Linus Torvalds 已提交
605 606
};

607
extern int uids_sysfs_init(void);
608

L
Linus Torvalds 已提交
609 610 611 612 613 614 615 616
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;

617
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
618 619
struct sched_info {
	/* cumulative counters */
620
	unsigned long pcount;	      /* # of times run on this cpu */
621 622
	unsigned long long cpu_time,  /* time spent on the cpu */
			   run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
623 624

	/* timestamps */
625 626
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
I
Ingo Molnar 已提交
627 628
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
629
	unsigned int bkl_count;
I
Ingo Molnar 已提交
630
#endif
L
Linus Torvalds 已提交
631
};
632
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
633

634
#ifdef CONFIG_SCHEDSTATS
635
extern const struct file_operations proc_schedstat_operations;
636
#endif /* CONFIG_SCHEDSTATS */
L
Linus Torvalds 已提交
637

638 639 640 641 642 643 644 645 646 647 648 649 650 651
#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).
	 */
652 653 654 655 656 657 658 659 660 661 662 663 664

	/*
	 * 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 */
665
};
666 667 668 669 670 671 672 673 674 675 676
#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;
677
#endif
678
}
679

I
Ingo Molnar 已提交
680 681 682 683 684
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
685 686 687 688 689
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
690 691 692 693 694 695 696

/*
 * Increase resolution of nice-level calculations:
 */
#define SCHED_LOAD_SHIFT	10
#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

697
#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
L
Linus Torvalds 已提交
698

699
#ifdef CONFIG_SMP
L
Linus Torvalds 已提交
700 701 702
#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
703 704 705 706 707
#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 */
708
#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
709
#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
710
#define SD_SERIALIZE		1024	/* Only a single load balancing instance */
711
#define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
712

713 714 715 716 717 718 719 720 721
#define BALANCE_FOR_MC_POWER	\
	(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)

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

#define test_sd_parent(sd, flag)	((sd->parent &&		\
					 (sd->parent->flags & flag)) ? 1 : 0)
722

L
Linus Torvalds 已提交
723 724 725 726 727 728 729 730

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).
731
	 * Note : Never change cpu_power without recompute its reciprocal
L
Linus Torvalds 已提交
732
	 */
733 734 735 736 737 738
	unsigned int __cpu_power;
	/*
	 * reciprocal value of cpu_power to avoid expensive divides
	 * (see include/linux/reciprocal_div.h)
	 */
	u32 reciprocal_cpu_power;
L
Linus Torvalds 已提交
739 740
};

741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758
enum sched_domain_level {
	SD_LV_NONE = 0,
	SD_LV_SIBLING,
	SD_LV_MC,
	SD_LV_CPU,
	SD_LV_NODE,
	SD_LV_ALLNODES,
	SD_LV_MAX
};

struct sched_domain_attr {
	int relax_domain_level;
};

#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
	.relax_domain_level = -1,			\
}

L
Linus Torvalds 已提交
759 760 761
struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
762
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
763 764
	struct sched_group *groups;	/* the balancing groups of the domain */
	cpumask_t span;			/* span of all CPUs in this domain */
765
	int first_cpu;			/* cache of the first cpu in this domain */
L
Linus Torvalds 已提交
766 767 768 769 770
	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 int cache_nice_tries;	/* Leave cache hot tasks for # tries */
N
Nick Piggin 已提交
771 772 773 774
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
775
	unsigned int forkexec_idx;
L
Linus Torvalds 已提交
776
	int flags;			/* See SD_* */
777
	enum sched_domain_level level;
L
Linus Torvalds 已提交
778 779 780 781 782 783 784 785

	/* 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 */
786 787 788 789 790 791 792 793
	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
L
Linus Torvalds 已提交
794 795

	/* Active load balancing */
796 797 798
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
799

800
	/* SD_BALANCE_EXEC stats */
801 802 803
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
804

805
	/* SD_BALANCE_FORK stats */
806 807 808
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
809

L
Linus Torvalds 已提交
810
	/* try_to_wake_up() stats */
811 812 813
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
814 815 816
#endif
};

817 818
extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
				    struct sched_domain_attr *dattr_new);
819
extern int arch_reinit_sched_domains(void);
P
Paul Jackson 已提交
820

821
#endif	/* CONFIG_SMP */
L
Linus Torvalds 已提交
822

823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
/*
 * 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;
}
L
Linus Torvalds 已提交
839 840 841

struct io_context;			/* See blkdev.h */
#define NGROUPS_SMALL		32
842
#define NGROUPS_PER_BLOCK	((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
L
Linus Torvalds 已提交
843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865
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)

866 867 868 869
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
870 871 872 873
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])

874
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
875
extern void prefetch_stack(struct task_struct *t);
876 877 878
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
879 880 881

struct audit_context;		/* See audit.c */
struct mempolicy;
882
struct pipe_inode_info;
883
struct uts_namespace;
L
Linus Torvalds 已提交
884

I
Ingo Molnar 已提交
885 886 887 888
struct rq;
struct sched_domain;

struct sched_class {
889
	const struct sched_class *next;
I
Ingo Molnar 已提交
890

891
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
892
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
893
	void (*yield_task) (struct rq *rq);
894
	int  (*select_task_rq)(struct task_struct *p, int sync);
I
Ingo Molnar 已提交
895 896 897

	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);

898
	struct task_struct * (*pick_next_task) (struct rq *rq);
899
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
900

901
#ifdef CONFIG_SMP
P
Peter Williams 已提交
902
	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
903
			struct rq *busiest, unsigned long max_load_move,
I
Ingo Molnar 已提交
904
			struct sched_domain *sd, enum cpu_idle_type idle,
905
			int *all_pinned, int *this_best_prio);
I
Ingo Molnar 已提交
906

907 908 909
	int (*move_one_task) (struct rq *this_rq, int this_cpu,
			      struct rq *busiest, struct sched_domain *sd,
			      enum cpu_idle_type idle);
910 911 912
	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	void (*post_schedule) (struct rq *this_rq);
	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
913
#endif
914

915
	void (*set_curr_task) (struct rq *rq);
P
Peter Zijlstra 已提交
916
	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
917
	void (*task_new) (struct rq *rq, struct task_struct *p);
918 919
	void (*set_cpus_allowed)(struct task_struct *p,
				 const cpumask_t *newmask);
G
Gregory Haskins 已提交
920 921 922

	void (*join_domain)(struct rq *rq);
	void (*leave_domain)(struct rq *rq);
923 924 925 926 927 928 929

	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
			       int running);
	void (*switched_to) (struct rq *this_rq, struct task_struct *task,
			     int running);
	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
			     int oldprio, int running);
P
Peter Zijlstra 已提交
930 931 932 933

#ifdef CONFIG_FAIR_GROUP_SCHED
	void (*moved_group) (struct task_struct *p);
#endif
I
Ingo Molnar 已提交
934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952
};

struct load_weight {
	unsigned long weight, inv_weight;
};

/*
 * CFS stats for a schedulable entity (task, task-group etc)
 *
 * Current field usage histogram:
 *
 *     4 se->block_start
 *     4 se->run_node
 *     4 se->sleep_start
 *     6 se->load.weight
 */
struct sched_entity {
	struct load_weight	load;		/* for load-balancing */
	struct rb_node		run_node;
953
	struct list_head	group_node;
I
Ingo Molnar 已提交
954 955
	unsigned int		on_rq;

956 957
	u64			exec_start;
	u64			sum_exec_runtime;
I
Ingo Molnar 已提交
958
	u64			vruntime;
959
	u64			prev_sum_exec_runtime;
960

I
Ingo Molnar 已提交
961 962 963
	u64			last_wakeup;
	u64			avg_overlap;

964
#ifdef CONFIG_SCHEDSTATS
I
Ingo Molnar 已提交
965
	u64			wait_start;
966
	u64			wait_max;
967 968
	u64			wait_count;
	u64			wait_sum;
969

I
Ingo Molnar 已提交
970 971
	u64			sleep_start;
	u64			sleep_max;
972 973 974
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
975 976
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
977
	u64			slice_max;
978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995

	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;
996 997
#endif

I
Ingo Molnar 已提交
998 999 1000 1001 1002 1003 1004 1005
#ifdef CONFIG_FAIR_GROUP_SCHED
	struct sched_entity	*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq		*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq		*my_q;
#endif
};
1006

P
Peter Zijlstra 已提交
1007 1008 1009
struct sched_rt_entity {
	struct list_head run_list;
	unsigned int time_slice;
1010
	unsigned long timeout;
P
Peter Zijlstra 已提交
1011 1012
	int nr_cpus_allowed;

1013
	struct sched_rt_entity *back;
1014
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
1015 1016 1017 1018 1019 1020
	struct sched_rt_entity	*parent;
	/* rq on which this entity is (to be) queued: */
	struct rt_rq		*rt_rq;
	/* rq "owned" by this entity/group: */
	struct rt_rq		*my_q;
#endif
P
Peter Zijlstra 已提交
1021 1022
};

L
Linus Torvalds 已提交
1023 1024
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
1025
	void *stack;
L
Linus Torvalds 已提交
1026
	atomic_t usage;
1027 1028
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
1029

1030
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
1031

1032 1033
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
1034 1035
	int oncpu;
#endif
1036
#endif
1037

1038
	int prio, static_prio, normal_prio;
1039
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
1040
	struct sched_entity se;
P
Peter Zijlstra 已提交
1041
	struct sched_rt_entity rt;
L
Linus Torvalds 已提交
1042

1043 1044 1045 1046 1047
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

1048 1049 1050 1051 1052 1053 1054 1055 1056 1057
	/*
	 * 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). */
1058
#ifdef CONFIG_BLK_DEV_IO_TRACE
1059
	unsigned int btrace_seq;
1060
#endif
L
Linus Torvalds 已提交
1061

1062
	unsigned int policy;
L
Linus Torvalds 已提交
1063 1064
	cpumask_t cpus_allowed;

P
Paul E. McKenney 已提交
1065 1066 1067 1068 1069
#ifdef CONFIG_PREEMPT_RCU
	int rcu_read_lock_nesting;
	int rcu_flipctr_idx;
#endif /* #ifdef CONFIG_PREEMPT_RCU */

1070
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
	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;
1086
	int exit_state;
L
Linus Torvalds 已提交
1087 1088 1089
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
1090
	unsigned int personality;
L
Linus Torvalds 已提交
1091 1092 1093
	unsigned did_exec:1;
	pid_t pid;
	pid_t tgid;
1094 1095 1096 1097 1098

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif
L
Linus Torvalds 已提交
1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114
	/* 
	 * 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. */
1115
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
1116
	struct list_head thread_group;
L
Linus Torvalds 已提交
1117 1118 1119 1120 1121

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

1122
	unsigned int rt_priority;
1123
	cputime_t utime, stime, utimescaled, stimescaled;
1124
	cputime_t gtime;
1125
	cputime_t prev_utime, prev_stime;
L
Linus Torvalds 已提交
1126
	unsigned long nvcsw, nivcsw; /* context switch counts */
1127 1128
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
/* 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;
1140
	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted, cap_bset;
1141
	unsigned securebits;
L
Linus Torvalds 已提交
1142 1143
	struct user_struct *user;
#ifdef CONFIG_KEYS
1144
	struct key *request_key_auth;	/* assumed request_key authority */
L
Linus Torvalds 已提交
1145
	struct key *thread_keyring;	/* keyring private to this thread */
1146
	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
L
Linus Torvalds 已提交
1147
#endif
1148 1149 1150 1151
	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
1152 1153
/* file system info */
	int link_count, total_link_count;
1154
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1155 1156
/* ipc stuff */
	struct sysv_sem sysvsem;
1157
#endif
1158 1159 1160 1161 1162
#ifdef CONFIG_DETECT_SOFTLOCKUP
/* hung task detection */
	unsigned long last_switch_timestamp;
	unsigned long last_switch_count;
#endif
L
Linus Torvalds 已提交
1163 1164 1165 1166 1167 1168
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1169
/* namespaces */
S
Serge E. Hallyn 已提交
1170
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1171 1172 1173 1174 1175
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1176
	sigset_t saved_sigmask;		/* To be restored with TIF_RESTORE_SIGMASK */
L
Linus Torvalds 已提交
1177 1178 1179 1180 1181 1182 1183
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	int (*notifier)(void *priv);
	void *notifier_data;
	sigset_t *notifier_mask;
1184
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1185
	void *security;
1186
#endif
L
Linus Torvalds 已提交
1187
	struct audit_context *audit_context;
A
Al Viro 已提交
1188 1189
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
1190
	unsigned int sessionid;
A
Al Viro 已提交
1191
#endif
L
Linus Torvalds 已提交
1192 1193 1194 1195 1196 1197 1198 1199
	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;

1200 1201 1202
	/* Protection of the PI data structures: */
	spinlock_t pi_lock;

I
Ingo Molnar 已提交
1203 1204 1205 1206 1207 1208 1209
#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

1210 1211 1212 1213
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228
#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
1229
#ifdef CONFIG_LOCKDEP
1230
# define MAX_LOCK_DEPTH 48UL
I
Ingo Molnar 已提交
1231 1232 1233 1234 1235
	u64 curr_chain_key;
	int lockdep_depth;
	struct held_lock held_locks[MAX_LOCK_DEPTH];
	unsigned int lockdep_recursion;
#endif
1236

L
Linus Torvalds 已提交
1237 1238 1239
/* journalling filesystem info */
	void *journal_info;

1240 1241 1242
/* stacked block device info */
	struct bio *bio_list, **bio_tail;

L
Linus Torvalds 已提交
1243 1244 1245 1246 1247 1248 1249 1250 1251
/* 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.  */
1252
#ifdef CONFIG_TASK_XACCT
L
Linus Torvalds 已提交
1253 1254
/* i/o counters(bytes read/written, #syscalls */
	u64 rchar, wchar, syscr, syscw;
1255
#endif
1256
	struct task_io_accounting ioac;
1257
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1258 1259
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
J
Jay Lan 已提交
1260
	cputime_t acct_stimexpd;/* stime since last update */
L
Linus Torvalds 已提交
1261 1262 1263 1264 1265 1266 1267 1268
#endif
#ifdef CONFIG_NUMA
  	struct mempolicy *mempolicy;
	short il_next;
#endif
#ifdef CONFIG_CPUSETS
	nodemask_t mems_allowed;
	int cpuset_mems_generation;
1269
	int cpuset_mem_spread_rotor;
L
Linus Torvalds 已提交
1270
#endif
1271
#ifdef CONFIG_CGROUPS
1272 1273 1274 1275
	/* Control Group info protected by css_set_lock */
	struct css_set *cgroups;
	/* cg_list protected by css_set_lock and tsk->alloc_lock */
	struct list_head cg_list;
1276
#endif
1277
#ifdef CONFIG_FUTEX
1278
	struct robust_list_head __user *robust_list;
1279 1280 1281
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1282 1283
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1284
#endif
1285
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1286
	struct rcu_head rcu;
1287 1288 1289 1290 1291

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1292 1293
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1294 1295 1296
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1297
#endif
P
Peter Zijlstra 已提交
1298
	struct prop_local_single dirties;
A
Arjan van de Ven 已提交
1299 1300 1301 1302
#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
L
Linus Torvalds 已提交
1303 1304
};

1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
/*
 * 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;
}

A
Alexey Dobriyan 已提交
1331
static inline int rt_task(struct task_struct *p)
1332 1333 1334 1335
{
	return rt_prio(p->prio);
}

P
Pavel Emelianov 已提交
1336
static inline void set_task_session(struct task_struct *tsk, pid_t session)
1337
{
P
Pavel Emelianov 已提交
1338
	tsk->signal->__session = session;
1339 1340
}

1341 1342 1343 1344 1345
static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
{
	tsk->signal->__pgrp = pgrp;
}

A
Alexey Dobriyan 已提交
1346
static inline struct pid *task_pid(struct task_struct *task)
1347 1348 1349 1350
{
	return task->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1351
static inline struct pid *task_tgid(struct task_struct *task)
1352 1353 1354 1355
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1356
static inline struct pid *task_pgrp(struct task_struct *task)
1357 1358 1359 1360
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

A
Alexey Dobriyan 已提交
1361
static inline struct pid *task_session(struct task_struct *task)
1362 1363 1364 1365
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

1366 1367 1368 1369 1370 1371 1372
struct pid_namespace;

/*
 * the helpers to get the task's different pids as they are seen
 * from various namespaces
 *
 * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
E
Eric W. Biederman 已提交
1373 1374
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1375 1376 1377 1378 1379 1380 1381
 * task_xid_nr_ns()  : id seen from the ns specified;
 *
 * set_task_vxid()   : assigns a virtual id to a task;
 *
 * see also pid_nr() etc in include/linux/pid.h
 */

A
Alexey Dobriyan 已提交
1382
static inline pid_t task_pid_nr(struct task_struct *tsk)
1383 1384 1385 1386
{
	return tsk->pid;
}

1387
pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1388 1389 1390 1391 1392 1393 1394

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
	return pid_vnr(task_pid(tsk));
}


A
Alexey Dobriyan 已提交
1395
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1396 1397 1398 1399
{
	return tsk->tgid;
}

1400
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1401 1402 1403 1404 1405 1406 1407

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
	return pid_vnr(task_tgid(tsk));
}


A
Alexey Dobriyan 已提交
1408
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
1409
{
1410
	return tsk->signal->__pgrp;
1411 1412
}

1413
pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1414 1415 1416 1417 1418 1419 1420

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
	return pid_vnr(task_pgrp(tsk));
}


A
Alexey Dobriyan 已提交
1421
static inline pid_t task_session_nr(struct task_struct *tsk)
1422 1423 1424 1425
{
	return tsk->signal->__session;
}

1426
pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1427 1428 1429 1430 1431 1432 1433

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
	return pid_vnr(task_session(tsk));
}


L
Linus Torvalds 已提交
1434 1435 1436 1437 1438 1439 1440 1441
/**
 * 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.
 */
A
Alexey Dobriyan 已提交
1442
static inline int pid_alive(struct task_struct *p)
L
Linus Torvalds 已提交
1443
{
1444
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1445 1446
}

1447
/**
1448
 * is_global_init - check if a task structure is init
1449 1450 1451
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1452
 */
A
Alexey Dobriyan 已提交
1453
static inline int is_global_init(struct task_struct *tsk)
1454 1455 1456
{
	return tsk->pid == 1;
}
1457 1458 1459 1460

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1461
 */
1462
extern int is_container_init(struct task_struct *tsk);
1463

1464 1465
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1466 1467
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
1468

1469
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1470 1471 1472 1473

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1474
		__put_task_struct(t);
I
Ingo Molnar 已提交
1475
}
L
Linus Torvalds 已提交
1476 1477 1478 1479 1480 1481 1482 1483

/*
 * 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 */
1484
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1485
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
L
Linus Torvalds 已提交
1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498
#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_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
1499 1500 1501 1502 1503
#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 */
1504
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1505
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
R
Rafael J. Wysocki 已提交
1506
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
L
Linus Torvalds 已提交
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533

/*
 * 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
1534 1535
extern int set_cpus_allowed_ptr(struct task_struct *p,
				const cpumask_t *new_mask);
L
Linus Torvalds 已提交
1536
#else
1537 1538
static inline int set_cpus_allowed_ptr(struct task_struct *p,
				       const cpumask_t *new_mask)
L
Linus Torvalds 已提交
1539
{
1540
	if (!cpu_isset(0, *new_mask))
L
Linus Torvalds 已提交
1541 1542 1543 1544
		return -EINVAL;
	return 0;
}
#endif
1545 1546 1547 1548
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
	return set_cpus_allowed_ptr(p, &new_mask);
}
L
Linus Torvalds 已提交
1549 1550

extern unsigned long long sched_clock(void);
1551 1552 1553 1554 1555 1556 1557

/*
 * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
 * clock constructed from sched_clock():
 */
extern unsigned long long cpu_clock(int cpu);

1558
extern unsigned long long
1559
task_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1560 1561 1562 1563 1564 1565 1566 1567

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

1568 1569
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
1570

L
Linus Torvalds 已提交
1571 1572 1573 1574 1575 1576 1577
#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);
1578

1579 1580 1581 1582 1583 1584
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
extern void wake_up_idle_cpu(int cpu);
#else
static inline void wake_up_idle_cpu(int cpu) { }
#endif

1585
#ifdef CONFIG_SCHED_DEBUG
1586
extern unsigned int sysctl_sched_latency;
1587
extern unsigned int sysctl_sched_min_granularity;
1588 1589 1590
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
extern unsigned int sysctl_sched_features;
1591
extern unsigned int sysctl_sched_migration_cost;
1592
extern unsigned int sysctl_sched_nr_migrate;
1593 1594 1595 1596

int sched_nr_latency_handler(struct ctl_table *table, int write,
		struct file *file, void __user *buffer, size_t *length,
		loff_t *ppos);
1597
#endif
P
Peter Zijlstra 已提交
1598 1599
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
1600

1601 1602 1603 1604
int sched_rt_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos);

1605
extern unsigned int sysctl_sched_compat_yield;
1606

1607
#ifdef CONFIG_RT_MUTEXES
1608 1609 1610
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);
1611
#else
A
Alexey Dobriyan 已提交
1612
static inline int rt_mutex_getprio(struct task_struct *p)
1613 1614 1615
{
	return p->normal_prio;
}
1616
# define rt_mutex_adjust_pi(p)		do { } while (0)
1617 1618
#endif

1619 1620 1621 1622 1623
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
1624 1625
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
1626 1627 1628
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
1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656

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;

1657 1658 1659 1660 1661 1662 1663 1664 1665 1666
extern struct pid_namespace init_pid_ns;

/*
 * find a task by one of its numerical ids
 *
 * find_task_by_pid_type_ns():
 *      it is the most generic call - it finds a task by all id,
 *      type and namespace specified
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
1667 1668
 * find_task_by_vpid():
 *      finds a task by its virtual pid
1669 1670 1671 1672 1673 1674 1675 1676 1677
 * find_task_by_pid():
 *      finds a task by its global pid
 *
 * see also find_pid() etc in include/linux/pid.h
 */

extern struct task_struct *find_task_by_pid_type_ns(int type, int pid,
		struct pid_namespace *ns);

1678 1679 1680 1681
extern struct task_struct *find_task_by_pid(pid_t nr);
extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr,
		struct pid_namespace *ns);
1682

1683
extern void __set_special_pids(struct pid *pid);
L
Linus Torvalds 已提交
1684 1685

/* per-UID process charging. */
1686
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
1687 1688 1689 1690 1691 1692 1693
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 *);
1694
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
1695 1696 1697

#include <asm/current.h>

1698
extern void do_timer(unsigned long ticks);
L
Linus Torvalds 已提交
1699

1700 1701 1702 1703
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk,
				unsigned long clone_flags);
L
Linus Torvalds 已提交
1704 1705 1706 1707 1708
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
1709 1710
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
L
Linus Torvalds 已提交
1711 1712 1713 1714 1715 1716

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 *);
1717
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739
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 force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
1740 1741
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
1742
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
1743 1744
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
1745
extern int kill_proc_info(int, struct siginfo *, pid_t);
L
Linus Torvalds 已提交
1746 1747 1748 1749 1750 1751 1752 1753
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_proc(pid_t, int, int);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
1754
extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
1755
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
1756 1757
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

1758 1759 1760 1761 1762
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
1763 1764 1765 1766 1767
/* 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)

1768 1769 1770 1771 1772
static inline int is_si_special(const struct siginfo *info)
{
	return info <= SEND_SIG_FORCED;
}

L
Linus Torvalds 已提交
1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791
/* 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 */
1792
extern void __mmdrop(struct mm_struct *);
L
Linus Torvalds 已提交
1793 1794
static inline void mmdrop(struct mm_struct * mm)
{
I
Ingo Molnar 已提交
1795
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
1796 1797 1798 1799 1800 1801 1802 1803 1804
		__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 *);
1805 1806
/* Allocate a new mm structure and copy contents from tsk->mm */
extern struct mm_struct *dup_mm(struct task_struct *tsk);
L
Linus Torvalds 已提交
1807 1808 1809 1810 1811 1812

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 *);
1813
extern void __cleanup_signal(struct signal_struct *);
1814
extern void __cleanup_sighand(struct sighand_struct *);
L
Linus Torvalds 已提交
1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
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);

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 *);
1825
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
1826 1827

extern void set_task_comm(struct task_struct *tsk, char *from);
1828
extern char *get_task_comm(char *to, struct task_struct *tsk);
L
Linus Torvalds 已提交
1829 1830

#ifdef CONFIG_SMP
1831
extern void wait_task_inactive(struct task_struct * p);
L
Linus Torvalds 已提交
1832 1833 1834 1835 1836
#else
#define wait_task_inactive(p)	do { } while (0)
#endif

#define remove_parent(p)	list_del_init(&(p)->sibling)
1837
#define add_parent(p)		list_add_tail(&(p)->sibling,&(p)->parent->children)
L
Linus Torvalds 已提交
1838

1839
#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
L
Linus Torvalds 已提交
1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853

#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)

1854 1855
/* 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
1856

1857 1858 1859 1860 1861 1862
/* Do to the insanities of de_thread it is possible for a process
 * to have the pid of the thread group leader without actually being
 * the thread group leader.  For iteration through the pids in proc
 * all we care about is that we have a task with the appropriate
 * pid, we don't actually care if we have the right task.
 */
A
Alexey Dobriyan 已提交
1863
static inline int has_group_leader_pid(struct task_struct *p)
1864 1865 1866 1867
{
	return p->pid == p->tgid;
}

1868 1869 1870 1871 1872 1873
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
	return p1->tgid == p2->tgid;
}

1874
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
1875 1876
{
	return list_entry(rcu_dereference(p->thread_group.next),
1877
			  struct task_struct, thread_group);
O
Oleg Nesterov 已提交
1878 1879
}

A
Alexey Dobriyan 已提交
1880
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
1881
{
O
Oleg Nesterov 已提交
1882
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
1883 1884 1885 1886 1887 1888
}

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

/*
1889
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
1890
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
1891 1892
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907
 *
 * 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);
}

1908 1909 1910 1911 1912 1913 1914 1915 1916
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
1917 1918
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
1919 1920
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
1921

1922 1923 1924 1925 1926 1927 1928 1929
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)
{
R
Roman Zippel 已提交
1930
	return (unsigned long *)(task_thread_info(p) + 1);
1931 1932
}

A
Al Viro 已提交
1933 1934
#endif

1935 1936
extern void thread_info_cache_init(void);

L
Linus Torvalds 已提交
1937 1938 1939 1940 1941
/* 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
1942
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1943 1944 1945 1946
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1947
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1948 1949 1950 1951
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1952
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1953 1954 1955 1956
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1957
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1958 1959 1960 1961
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1962
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978
}

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));
}
M
Matthew Wilcox 已提交
1979

1980
extern int __fatal_signal_pending(struct task_struct *p);
M
Matthew Wilcox 已提交
1981 1982 1983 1984 1985 1986

static inline int fatal_signal_pending(struct task_struct *p)
{
	return signal_pending(p) && __fatal_signal_pending(p);
}

L
Linus Torvalds 已提交
1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998
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.
 */
1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010
#ifdef CONFIG_PREEMPT
static inline int cond_resched(void)
{
	return 0;
}
#else
extern int _cond_resched(void);
static inline int cond_resched(void)
{
	return _cond_resched();
}
#endif
L
Linus Torvalds 已提交
2011 2012 2013 2014 2015
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
N
Nick Piggin 已提交
2016 2017
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
2018
 */
N
Nick Piggin 已提交
2019
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
2020
{
N
Nick Piggin 已提交
2021 2022 2023
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
2024
	return 0;
N
Nick Piggin 已提交
2025
#endif
L
Linus Torvalds 已提交
2026 2027
}

R
Roland McGrath 已提交
2028 2029 2030 2031 2032 2033 2034
/*
 * Reevaluate whether the task has signals pending delivery.
 * Wake the task if so.
 * This is required every time the blocked sigset_t changes.
 * callers must hold sighand->siglock.
 */
extern void recalc_sigpending_and_wake(struct task_struct *t);
L
Linus Torvalds 已提交
2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045
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
2046
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
2047 2048
}

I
Ingo Molnar 已提交
2049
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074

#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

2075
extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask);
L
Linus Torvalds 已提交
2076 2077
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);

2078 2079
extern int sched_mc_power_savings, sched_smt_power_savings;

L
Linus Torvalds 已提交
2080 2081
extern void normalize_rt_tasks(void);

2082
#ifdef CONFIG_GROUP_SCHED
2083

2084
extern struct task_group init_task_group;
2085 2086 2087
#ifdef CONFIG_USER_SCHED
extern struct task_group root_task_group;
#endif
2088

2089
extern struct task_group *sched_create_group(struct task_group *parent);
2090
extern void sched_destroy_group(struct task_group *tg);
2091
extern void sched_move_task(struct task_struct *tsk);
2092
#ifdef CONFIG_FAIR_GROUP_SCHED
2093
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
2094
extern unsigned long sched_group_shares(struct task_group *tg);
2095 2096
#endif
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
2097 2098 2099
extern int sched_group_set_rt_runtime(struct task_group *tg,
				      long rt_runtime_us);
extern long sched_group_rt_runtime(struct task_group *tg);
2100 2101 2102
extern int sched_group_set_rt_period(struct task_group *tg,
				      long rt_period_us);
extern long sched_group_rt_period(struct task_group *tg);
2103
#endif
2104 2105
#endif

2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
	tsk->rchar += amt;
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
	tsk->wchar += amt;
}

static inline void inc_syscr(struct task_struct *tsk)
{
	tsk->syscr++;
}

static inline void inc_syscw(struct task_struct *tsk)
{
	tsk->syscw++;
}
#else
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
}

static inline void inc_syscr(struct task_struct *tsk)
{
}

static inline void inc_syscw(struct task_struct *tsk)
{
}
#endif

2144 2145 2146 2147 2148 2149 2150 2151
#ifdef CONFIG_SMP
void migration_init(void);
#else
static inline void migration_init(void)
{
}
#endif

D
Dave Hansen 已提交
2152 2153 2154 2155
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168
#ifdef CONFIG_MM_OWNER
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}

static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
}
#endif /* CONFIG_MM_OWNER */

L
Linus Torvalds 已提交
2169 2170 2171
#endif /* __KERNEL__ */

#endif