sched.h 58.3 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_NEWNET		0x40000000	/* New network namespace */
29 30 31 32 33 34 35 36

/*
 * Scheduling policies
 */
#define SCHED_NORMAL		0
#define SCHED_FIFO		1
#define SCHED_RR		2
#define SCHED_BATCH		3
I
Ingo Molnar 已提交
37 38
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE		5
39

40
#ifdef __KERNEL__
41 42 43 44 45

struct sched_param {
	int sched_priority;
};

L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58
#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>
59
#include <linux/mm_types.h>
L
Linus Torvalds 已提交
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76

#include <asm/system.h>
#include <asm/semaphore.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/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>
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>
80
#include <linux/futex.h>
I
Ingo Molnar 已提交
81
#include <linux/rtmutex.h>
L
Linus Torvalds 已提交
82

83 84 85 86 87
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
88
#include <linux/task_io_accounting.h>
89
#include <linux/kobject.h>
90 91

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

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

/*
 * 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 */
117
#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
L
Linus Torvalds 已提交
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
#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);
133
extern unsigned long nr_active(void);
L
Linus Torvalds 已提交
134
extern unsigned long nr_iowait(void);
135
extern unsigned long weighted_cpuload(const int cpu);
L
Linus Torvalds 已提交
136

I
Ingo Molnar 已提交
137 138
struct seq_file;
struct cfs_rq;
139
struct task_group;
I
Ingo Molnar 已提交
140 141 142 143
#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
144
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
I
Ingo Molnar 已提交
145 146 147 148 149 150 151 152 153
#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
154
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
I
Ingo Molnar 已提交
155 156 157
{
}
#endif
L
Linus Torvalds 已提交
158

159 160 161 162 163 164 165 166 167 168
/*
 * 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
169 170 171
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
172 173 174 175 176 177
#define TASK_STOPPED		4
#define TASK_TRACED		8
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
178
#define TASK_DEAD		64
L
Linus Torvalds 已提交
179 180 181 182 183 184

#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))

185 186 187 188 189 190 191 192 193 194 195
/*
 * 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
196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
#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;

215
struct task_struct;
L
Linus Torvalds 已提交
216 217 218

extern void sched_init(void);
extern void sched_init_smp(void);
219
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
220
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
221 222

extern cpumask_t nohz_cpu_mask;
223 224 225 226 227 228 229 230
#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
231

I
Ingo Molnar 已提交
232
/*
I
Ingo Molnar 已提交
233
 * Only dump TASK_* tasks. (0 for all tasks)
I
Ingo Molnar 已提交
234 235 236 237 238
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
I
Ingo Molnar 已提交
239
	show_state_filter(0);
I
Ingo Molnar 已提交
240 241
}

L
Linus Torvalds 已提交
242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
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
259
#ifdef CONFIG_DETECT_SOFTLOCKUP
260
extern void softlockup_tick(void);
I
Ingo Molnar 已提交
261 262
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
263
extern void touch_all_softlockup_watchdogs(void);
264
extern int softlockup_thresh;
I
Ingo Molnar 已提交
265
#else
266
static inline void softlockup_tick(void)
I
Ingo Molnar 已提交
267 268 269 270 271 272 273 274
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
275 276 277
static inline void touch_all_softlockup_watchdogs(void)
{
}
I
Ingo Molnar 已提交
278 279 280
#endif


L
Linus Torvalds 已提交
281 282 283 284 285 286 287
/* 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));
288 289
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
290 291
asmlinkage void schedule(void);

S
Serge E. Hallyn 已提交
292
struct nsproxy;
293
struct user_namespace;
L
Linus Torvalds 已提交
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308

/* 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);
309 310
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
311

312 313 314 315 316
#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
317 318 319 320 321
#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)
322 323 324 325 326 327

#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
328 329 330 331 332
#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--
333 334

#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
335

336 337
#define get_mm_rss(mm)					\
	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
338 339 340 341 342 343 344 345 346 347
#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)

348 349 350 351
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
352
/* dumpable bits */
353 354
#define MMF_DUMPABLE      0  /* core dump is permitted */
#define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
355 356 357 358 359 360 361
#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
362
#define MMF_DUMP_ELF_HEADERS	6
363
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
R
Roland McGrath 已提交
364
#define MMF_DUMP_FILTER_BITS	5
365 366 367 368
#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))
369

L
Linus Torvalds 已提交
370 371 372 373
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
374
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
375 376
};

377
struct pacct_struct {
378 379
	int			ac_flag;
	long			ac_exitcode;
380
	unsigned long		ac_mem;
381 382
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
383 384
};

L
Linus Torvalds 已提交
385 386 387 388 389 390 391 392 393 394 395 396 397 398
/*
 * 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: */
399
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421

	/* 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 */
422
	struct hrtimer real_timer;
423
	struct task_struct *tsk;
424
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
425 426 427 428 429 430 431

	/* 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;
432
	struct pid *tty_old_pgrp;
433 434 435 436 437 438

	union {
		pid_t session __deprecated;
		pid_t __session;
	};

L
Linus Torvalds 已提交
439 440 441 442 443 444 445 446 447 448 449 450
	/* 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;
451 452
	cputime_t gtime;
	cputime_t cgtime;
L
Linus Torvalds 已提交
453 454
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
455
	unsigned long inblock, oublock, cinblock, coublock;
L
Linus Torvalds 已提交
456 457 458 459 460 461 462

	/*
	 * 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.)
	 */
463
	unsigned long long sum_sched_runtime;
L
Linus Torvalds 已提交
464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483

	/*
	 * 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
484 485 486
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
487 488 489
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
490 491 492 493
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
L
Linus Torvalds 已提交
494 495
};

496 497 498 499 500
/* 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
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516
/*
 * 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 */

/*
 * 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? */
517
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
518 519 520
	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
521
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
522 523
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
524
#endif
L
Linus Torvalds 已提交
525 526 527 528 529 530 531 532
	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
533
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
534
	uid_t uid;
535 536

#ifdef CONFIG_FAIR_USER_SCHED
537
	struct task_group *tg;
D
Dhaval Giani 已提交
538
#ifdef CONFIG_SYSFS
539 540 541
	struct kset kset;
	struct subsys_attribute user_attr;
	struct work_struct work;
542
#endif
D
Dhaval Giani 已提交
543
#endif
L
Linus Torvalds 已提交
544 545
};

546 547 548 549 550 551
#ifdef CONFIG_FAIR_USER_SCHED
extern int uids_kobject_init(void);
#else
static inline int uids_kobject_init(void) { return 0; }
#endif

L
Linus Torvalds 已提交
552 553 554 555 556 557 558 559
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;

560
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
561 562
struct sched_info {
	/* cumulative counters */
563
	unsigned long pcount;	      /* # of times run on this cpu */
564 565
	unsigned long long cpu_time,  /* time spent on the cpu */
			   run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
566 567

	/* timestamps */
568 569
	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
570 571
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
572
	unsigned int bkl_count;
I
Ingo Molnar 已提交
573
#endif
L
Linus Torvalds 已提交
574
};
575
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
576

577
#ifdef CONFIG_SCHEDSTATS
578
extern const struct file_operations proc_schedstat_operations;
579
#endif /* CONFIG_SCHEDSTATS */
L
Linus Torvalds 已提交
580

581 582 583 584 585 586 587 588 589 590 591 592 593 594
#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).
	 */
595 596 597 598 599 600 601 602 603 604 605 606 607

	/*
	 * 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 */
608
};
609 610 611 612 613 614 615 616 617 618 619
#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;
620
#endif
621
}
622

I
Ingo Molnar 已提交
623 624 625 626 627
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
628 629 630 631 632
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
633 634 635 636 637 638 639

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

640
#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
L
Linus Torvalds 已提交
641

642
#ifdef CONFIG_SMP
L
Linus Torvalds 已提交
643 644 645
#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
646 647 648 649 650
#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 */
651
#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
652
#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
653
#define SD_SERIALIZE		1024	/* Only a single load balancing instance */
654

655 656 657 658 659 660 661 662 663
#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)
664

L
Linus Torvalds 已提交
665 666 667 668 669 670 671 672

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).
673
	 * Note : Never change cpu_power without recompute its reciprocal
L
Linus Torvalds 已提交
674
	 */
675 676 677 678 679 680
	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
681 682 683 684 685
};

struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
686
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
687 688 689 690 691 692 693
	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 int cache_nice_tries;	/* Leave cache hot tasks for # tries */
N
Nick Piggin 已提交
694 695 696 697
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
698
	unsigned int forkexec_idx;
L
Linus Torvalds 已提交
699 700 701 702 703 704 705 706 707
	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 */
708 709 710 711 712 713 714 715
	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
716 717

	/* Active load balancing */
718 719 720
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
721

722
	/* SD_BALANCE_EXEC stats */
723 724 725
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
726

727
	/* SD_BALANCE_FORK stats */
728 729 730
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
731

L
Linus Torvalds 已提交
732
	/* try_to_wake_up() stats */
733 734 735
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
736 737 738
#endif
};

739
#endif	/* CONFIG_SMP */
L
Linus Torvalds 已提交
740

741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
/*
 * 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
757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783

struct io_context;			/* See blkdev.h */
#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)

784 785 786 787
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
788 789 790 791
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])

792
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
793
extern void prefetch_stack(struct task_struct *t);
794 795 796
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
797 798 799

struct audit_context;		/* See audit.c */
struct mempolicy;
800
struct pipe_inode_info;
801
struct uts_namespace;
L
Linus Torvalds 已提交
802

I
Ingo Molnar 已提交
803 804 805 806
struct rq;
struct sched_domain;

struct sched_class {
807
	const struct sched_class *next;
I
Ingo Molnar 已提交
808

809
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
810
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
811
	void (*yield_task) (struct rq *rq);
I
Ingo Molnar 已提交
812 813 814

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

815
	struct task_struct * (*pick_next_task) (struct rq *rq);
816
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
817

P
Peter Williams 已提交
818
	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
I
Ingo Molnar 已提交
819 820 821
			struct rq *busiest,
			unsigned long max_nr_move, unsigned long max_load_move,
			struct sched_domain *sd, enum cpu_idle_type idle,
822
			int *all_pinned, int *this_best_prio);
I
Ingo Molnar 已提交
823

824
	void (*set_curr_task) (struct rq *rq);
I
Ingo Molnar 已提交
825
	void (*task_tick) (struct rq *rq, struct task_struct *p);
826
	void (*task_new) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
};

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;
	unsigned int		on_rq;
847
	int			peer_preempt;
I
Ingo Molnar 已提交
848

849 850
	u64			exec_start;
	u64			sum_exec_runtime;
I
Ingo Molnar 已提交
851
	u64			vruntime;
852
	u64			prev_sum_exec_runtime;
853 854

#ifdef CONFIG_SCHEDSTATS
I
Ingo Molnar 已提交
855
	u64			wait_start;
856 857
	u64			wait_max;

I
Ingo Molnar 已提交
858 859
	u64			sleep_start;
	u64			sleep_max;
860 861 862
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
863 864
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
865
	u64			slice_max;
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883

	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;
884 885
#endif

I
Ingo Molnar 已提交
886 887 888 889 890 891 892 893
#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
};
894

L
Linus Torvalds 已提交
895 896
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
897
	void *stack;
L
Linus Torvalds 已提交
898
	atomic_t usage;
899 900
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
901

902
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
903

904 905
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
906 907
	int oncpu;
#endif
908
#endif
909

910
	int prio, static_prio, normal_prio;
L
Linus Torvalds 已提交
911
	struct list_head run_list;
912
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
913
	struct sched_entity se;
L
Linus Torvalds 已提交
914

915 916 917 918 919
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

920
	unsigned short ioprio;
921 922 923 924 925 926 927 928 929 930
	/*
	 * 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). */
931
#ifdef CONFIG_BLK_DEV_IO_TRACE
932
	unsigned int btrace_seq;
933
#endif
L
Linus Torvalds 已提交
934

935
	unsigned int policy;
L
Linus Torvalds 已提交
936
	cpumask_t cpus_allowed;
937
	unsigned int time_slice;
L
Linus Torvalds 已提交
938

939
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954
	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;
955
	int exit_state;
L
Linus Torvalds 已提交
956 957 958
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
959
	unsigned int personality;
L
Linus Torvalds 已提交
960 961 962
	unsigned did_exec:1;
	pid_t pid;
	pid_t tgid;
963 964 965 966 967

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif
L
Linus Torvalds 已提交
968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983
	/* 
	 * 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. */
984
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
985
	struct list_head thread_group;
L
Linus Torvalds 已提交
986 987 988 989 990

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

991
	unsigned int rt_priority;
992
	cputime_t utime, stime, utimescaled, stimescaled;
993
	cputime_t gtime;
L
Linus Torvalds 已提交
994
	unsigned long nvcsw, nivcsw; /* context switch counts */
995 996
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
/* 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
1012
	struct key *request_key_auth;	/* assumed request_key authority */
L
Linus Torvalds 已提交
1013
	struct key *thread_keyring;	/* keyring private to this thread */
1014
	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
L
Linus Torvalds 已提交
1015
#endif
1016 1017 1018 1019
	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
1020 1021
/* file system info */
	int link_count, total_link_count;
1022
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1023 1024
/* ipc stuff */
	struct sysv_sem sysvsem;
1025
#endif
L
Linus Torvalds 已提交
1026 1027 1028 1029 1030 1031
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1032
/* namespaces */
S
Serge E. Hallyn 已提交
1033
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1034 1035 1036 1037 1038
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1039
	sigset_t saved_sigmask;		/* To be restored with TIF_RESTORE_SIGMASK */
L
Linus Torvalds 已提交
1040 1041 1042 1043 1044 1045 1046
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	int (*notifier)(void *priv);
	void *notifier_data;
	sigset_t *notifier_mask;
1047
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1048
	void *security;
1049
#endif
L
Linus Torvalds 已提交
1050 1051 1052 1053 1054 1055 1056 1057 1058
	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;

1059 1060 1061
	/* Protection of the PI data structures: */
	spinlock_t pi_lock;

I
Ingo Molnar 已提交
1062 1063 1064 1065 1066 1067 1068
#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

1069 1070 1071 1072
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
#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
1088 1089 1090 1091 1092 1093 1094
#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
1095

L
Linus Torvalds 已提交
1096 1097 1098
/* journalling filesystem info */
	void *journal_info;

1099 1100 1101
/* stacked block device info */
	struct bio *bio_list, **bio_tail;

L
Linus Torvalds 已提交
1102 1103 1104 1105 1106 1107 1108 1109 1110
/* 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.  */
1111
#ifdef CONFIG_TASK_XACCT
L
Linus Torvalds 已提交
1112 1113
/* i/o counters(bytes read/written, #syscalls */
	u64 rchar, wchar, syscr, syscw;
1114
#endif
1115
	struct task_io_accounting ioac;
1116
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1117 1118
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
J
Jay Lan 已提交
1119
	cputime_t acct_stimexpd;/* stime since last update */
L
Linus Torvalds 已提交
1120 1121 1122 1123 1124 1125 1126 1127
#endif
#ifdef CONFIG_NUMA
  	struct mempolicy *mempolicy;
	short il_next;
#endif
#ifdef CONFIG_CPUSETS
	nodemask_t mems_allowed;
	int cpuset_mems_generation;
1128
	int cpuset_mem_spread_rotor;
L
Linus Torvalds 已提交
1129
#endif
1130
#ifdef CONFIG_CGROUPS
1131 1132 1133 1134
	/* 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;
1135
#endif
1136
#ifdef CONFIG_FUTEX
1137
	struct robust_list_head __user *robust_list;
1138 1139 1140
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1141 1142
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1143
#endif
1144
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1145
	struct rcu_head rcu;
1146 1147 1148 1149 1150

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1151 1152
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1153 1154 1155
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1156
#endif
P
Peter Zijlstra 已提交
1157
	struct prop_local_single dirties;
L
Linus Torvalds 已提交
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
/*
 * Priority of a process goes from 0..MAX_PRIO-1, valid RT
 * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
 * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
 * values are inverted: lower p->prio value means higher priority.
 *
 * The MAX_USER_RT_PRIO value allows the actual maximum
 * RT priority to be separate from the value exported to
 * user-space.  This allows kernel threads to set their
 * priority to a value higher than any user task. Note:
 * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
 */

#define MAX_USER_RT_PRIO	100
#define MAX_RT_PRIO		MAX_USER_RT_PRIO

#define MAX_PRIO		(MAX_RT_PRIO + 40)
#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)

static inline int rt_prio(int prio)
{
	if (unlikely(prio < MAX_RT_PRIO))
		return 1;
	return 0;
}

static inline int rt_task(struct task_struct *p)
{
	return rt_prio(p->prio);
}

P
Pavel Emelianov 已提交
1191
static inline void set_task_session(struct task_struct *tsk, pid_t session)
1192
{
P
Pavel Emelianov 已提交
1193
	tsk->signal->__session = session;
1194 1195
}

1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
static inline struct pid *task_pid(struct task_struct *task)
{
	return task->pids[PIDTYPE_PID].pid;
}

static inline struct pid *task_tgid(struct task_struct *task)
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

static inline struct pid *task_pgrp(struct task_struct *task)
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

static inline struct pid *task_session(struct task_struct *task)
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

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 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 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 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313
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;
 * task_xid_vnr()    : virtual id, i.e. the id seen from the namespace the task
 *                     belongs to. this only makes sence when called in the
 *                     context of the task that belongs to the same namespace;
 * task_xid_nr_ns()  : id seen from the ns specified;
 *
 * set_task_vxid()   : assigns a virtual id to a task;
 *
 * task_ppid_nr_ns() : the parent's id as seen from the namespace specified.
 *                     the result depends on the namespace and whether the
 *                     task in question is the namespace's init. e.g. for the
 *                     namespace's init this will return 0 when called from
 *                     the namespace of this init, or appropriate id otherwise.
 *
 *
 * see also pid_nr() etc in include/linux/pid.h
 */

static inline pid_t task_pid_nr(struct task_struct *tsk)
{
	return tsk->pid;
}

static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
		struct pid_namespace *ns)
{
	return pid_nr_ns(task_pid(tsk), ns);
}

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


static inline pid_t task_tgid_nr(struct task_struct *tsk)
{
	return tsk->tgid;
}

static inline pid_t task_tgid_nr_ns(struct task_struct *tsk,
		struct pid_namespace *ns)
{
	return pid_nr_ns(task_tgid(tsk), ns);
}

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


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

static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
		struct pid_namespace *ns)
{
	return pid_nr_ns(task_pgrp(tsk), ns);
}

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


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

static inline pid_t task_session_nr_ns(struct task_struct *tsk,
		struct pid_namespace *ns)
{
	return pid_nr_ns(task_session(tsk), ns);
}

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


static inline pid_t task_ppid_nr_ns(struct task_struct *tsk,
		struct pid_namespace *ns)
{
	return pid_nr_ns(task_pid(rcu_dereference(tsk->real_parent)), ns);
}

L
Linus Torvalds 已提交
1314 1315 1316 1317 1318 1319 1320 1321 1322 1323
/**
 * 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)
{
1324
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1325 1326
}

1327
/**
1328
 * is_global_init - check if a task structure is init
1329 1330 1331
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1332 1333 1334 1335 1336 1337 1338 1339
 *
 * TODO: We should inline this function after some cleanups in pid_namespace.h
 */
extern int is_global_init(struct task_struct *tsk);

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1340
 */
1341
static inline int is_container_init(struct task_struct *tsk)
1342 1343 1344 1345
{
	return tsk->pid == 1;
}

1346 1347
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1348 1349
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
1350

1351
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1352 1353 1354 1355

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1356
		__put_task_struct(t);
I
Ingo Molnar 已提交
1357
}
L
Linus Torvalds 已提交
1358 1359 1360 1361 1362 1363 1364 1365

/*
 * 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 */
1366
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1367
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
L
Linus Torvalds 已提交
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
#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
1381 1382 1383 1384 1385
#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 */
1386
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1387
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
R
Rafael J. Wysocki 已提交
1388
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
L
Linus Torvalds 已提交
1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415

/*
 * 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
1416
extern int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask);
L
Linus Torvalds 已提交
1417
#else
1418
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
L
Linus Torvalds 已提交
1419
{
1420
	if (!cpu_isset(0, new_mask))
L
Linus Torvalds 已提交
1421 1422 1423 1424 1425 1426
		return -EINVAL;
	return 0;
}
#endif

extern unsigned long long sched_clock(void);
1427 1428 1429 1430 1431 1432 1433

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

1434
extern unsigned long long
1435
task_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1436 1437 1438 1439 1440 1441 1442 1443

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

1444 1445
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
1446

L
Linus Torvalds 已提交
1447 1448 1449 1450 1451 1452 1453
#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);
1454

1455
#ifdef CONFIG_SCHED_DEBUG
1456
extern unsigned int sysctl_sched_latency;
1457
extern unsigned int sysctl_sched_nr_latency;
1458 1459 1460 1461
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_batch_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
extern unsigned int sysctl_sched_features;
1462
extern unsigned int sysctl_sched_migration_cost;
1463 1464 1465
#endif

extern unsigned int sysctl_sched_compat_yield;
1466

1467
#ifdef CONFIG_RT_MUTEXES
1468 1469 1470
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);
1471
#else
1472
static inline int rt_mutex_getprio(struct task_struct *p)
1473 1474 1475
{
	return p->normal_prio;
}
1476
# define rt_mutex_adjust_pi(p)		do { } while (0)
1477 1478
#endif

1479 1480 1481 1482 1483
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
1484 1485
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
1486 1487 1488
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
1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516

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;

1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545
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
 * find_task_by_pid_type():
 *      finds a task by its global id with the specified type, e.g.
 *      by global session id
 * 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);

#define find_task_by_pid_ns(nr, ns)	\
		find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns)
#define find_task_by_pid_type(type, nr)	\
		find_task_by_pid_type_ns(type, nr, &init_pid_ns)
#define find_task_by_pid(nr)		\
		find_task_by_pid_type(PIDTYPE_PID, nr)

L
Linus Torvalds 已提交
1546 1547 1548
extern void __set_special_pids(pid_t session, pid_t pgrp);

/* per-UID process charging. */
1549
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
1550 1551 1552 1553 1554 1555 1556
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 *);
1557
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
1558 1559 1560

#include <asm/current.h>

1561
extern void do_timer(unsigned long ticks);
L
Linus Torvalds 已提交
1562 1563 1564 1565 1566 1567 1568 1569 1570 1571

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
1572 1573
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
1574 1575 1576 1577 1578 1579

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 *);
1580
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
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 *);
1604 1605 1606
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
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);
1607
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
1608 1609
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
1610
extern int kill_proc_info(int, struct siginfo *, pid_t);
L
Linus Torvalds 已提交
1611 1612 1613 1614 1615 1616 1617 1618 1619 1620
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 *);
extern int send_sigqueue(int, struct sigqueue *,  struct task_struct *);
extern int send_group_sigqueue(int, struct sigqueue *,  struct task_struct *);
1621
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
1622 1623
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

1624 1625 1626 1627 1628
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
1629 1630 1631 1632 1633
/* 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)

1634 1635 1636 1637 1638
static inline int is_si_special(const struct siginfo *info)
{
	return info <= SEND_SIG_FORCED;
}

L
Linus Torvalds 已提交
1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660
/* 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)
{
I
Ingo Molnar 已提交
1661
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676
		__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 *);
1677
extern void __cleanup_signal(struct signal_struct *);
1678
extern void __cleanup_sighand(struct sighand_struct *);
L
Linus Torvalds 已提交
1679 1680 1681 1682 1683 1684 1685 1686 1687 1688
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 *);
1689
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
1690 1691 1692 1693 1694

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
1695
extern void wait_task_inactive(struct task_struct * p);
L
Linus Torvalds 已提交
1696 1697 1698 1699 1700
#else
#define wait_task_inactive(p)	do { } while (0)
#endif

#define remove_parent(p)	list_del_init(&(p)->sibling)
1701
#define add_parent(p)		list_add_tail(&(p)->sibling,&(p)->parent->children)
L
Linus Torvalds 已提交
1702

1703
#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
L
Linus Torvalds 已提交
1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717

#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)

1718 1719
/* 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
1720

1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731
/* 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.
 */
static inline int has_group_leader_pid(struct task_struct *p)
{
	return p->pid == p->tgid;
}

1732
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
1733 1734
{
	return list_entry(rcu_dereference(p->thread_group.next),
1735
			  struct task_struct, thread_group);
O
Oleg Nesterov 已提交
1736 1737
}

1738
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
1739
{
O
Oleg Nesterov 已提交
1740
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
1741 1742 1743 1744 1745 1746
}

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

/*
1747
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
1748
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
1749 1750
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765
 *
 * 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);
}

1766 1767 1768 1769 1770 1771 1772 1773 1774
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
1775 1776
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
1777 1778
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
1779

1780 1781 1782 1783 1784 1785 1786 1787
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
1788
	return (unsigned long *)(task_thread_info(p) + 1);
1789 1790
}

A
Al Viro 已提交
1791 1792
#endif

L
Linus Torvalds 已提交
1793 1794 1795 1796 1797
/* 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
1798
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1799 1800 1801 1802
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1803
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1804 1805 1806 1807
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1808
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1809 1810 1811 1812
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1813
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1814 1815 1816 1817
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1818
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
}

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;
}

R
Roland McGrath 已提交
1873 1874 1875 1876 1877 1878 1879
/*
 * 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
1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890
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
1891
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
1892 1893
}

I
Ingo Molnar 已提交
1894
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922

#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);

1923 1924
extern int sched_mc_power_savings, sched_smt_power_savings;

L
Linus Torvalds 已提交
1925 1926
extern void normalize_rt_tasks(void);

1927 1928
#ifdef CONFIG_FAIR_GROUP_SCHED

1929
extern struct task_group init_task_group;
1930

1931 1932
extern struct task_group *sched_create_group(void);
extern void sched_destroy_group(struct task_group *tg);
1933
extern void sched_move_task(struct task_struct *tsk);
1934
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
1935
extern unsigned long sched_group_shares(struct task_group *tg);
1936 1937 1938

#endif

1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976
#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

L
Linus Torvalds 已提交
1977 1978 1979
#endif /* __KERNEL__ */

#endif