sched.h 74.4 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
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK     0x40000000
43

44
#ifdef __KERNEL__
45 46 47 48 49

struct sched_param {
	int sched_priority;
};

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

#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>
73
#include <linux/path.h>
L
Linus Torvalds 已提交
74 75 76 77 78
#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
79
#include <linux/proportions.h>
L
Linus Torvalds 已提交
80
#include <linux/seccomp.h>
I
Ingo Molnar 已提交
81
#include <linux/rcupdate.h>
82
#include <linux/rculist.h>
I
Ingo Molnar 已提交
83
#include <linux/rtmutex.h>
L
Linus Torvalds 已提交
84

85 86 87 88 89
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
90
#include <linux/task_io_accounting.h>
91
#include <linux/kobject.h>
A
Arjan van de Ven 已提交
92
#include <linux/latencytop.h>
93
#include <linux/cred.h>
94 95

#include <asm/processor.h>
H
H. J. Lu 已提交
96

L
Linus Torvalds 已提交
97
struct exec_domain;
98
struct futex_pi_state;
99
struct robust_list_head;
100
struct bio;
101
struct fs_struct;
102
struct bts_context;
103
struct perf_event_context;
L
Linus Torvalds 已提交
104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121

/*
 * 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 */
122
extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
L
Linus Torvalds 已提交
123 124 125

#define FSHIFT		11		/* nr of bits of precision */
#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
126
#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
L
Linus Torvalds 已提交
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
#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);
extern unsigned long nr_iowait(void);
143 144 145 146
extern unsigned long nr_iowait_cpu(void);
extern unsigned long this_cpu_load(void);


147
extern void calc_global_load(void);
148
extern u64 cpu_nr_migrations(int cpu);
L
Linus Torvalds 已提交
149

150 151
extern unsigned long get_parent_ip(unsigned long addr);

I
Ingo Molnar 已提交
152 153
struct seq_file;
struct cfs_rq;
154
struct task_group;
I
Ingo Molnar 已提交
155 156 157 158
#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
159
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
I
Ingo Molnar 已提交
160 161 162 163 164 165 166 167 168
#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
169
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
I
Ingo Molnar 已提交
170 171 172
{
}
#endif
L
Linus Torvalds 已提交
173

174 175
extern unsigned long long time_sync_thresh;

176 177 178 179 180 181 182 183 184 185
/*
 * 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
186 187 188
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
M
Matthew Wilcox 已提交
189 190
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
191 192 193 194
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
195
#define TASK_DEAD		64
M
Matthew Wilcox 已提交
196
#define TASK_WAKEKILL		128
P
Peter Zijlstra 已提交
197
#define TASK_WAKING		256
M
Matthew Wilcox 已提交
198 199 200 201 202

/* 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
203

204 205
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
M
Matthew Wilcox 已提交
206
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
207 208 209

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
M
Matthew Wilcox 已提交
210 211
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED)
212

M
Matthew Wilcox 已提交
213 214
#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
215
#define task_is_stopped_or_traced(task)	\
M
Matthew Wilcox 已提交
216
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
217
#define task_contributes_to_load(task)	\
218
				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
219
				 (task->flags & PF_FREEZING) == 0)
L
Linus Torvalds 已提交
220 221 222 223 224 225

#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))

226 227 228 229 230 231 232 233 234 235 236
/*
 * 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
237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
#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;

256
struct task_struct;
L
Linus Torvalds 已提交
257 258 259

extern void sched_init(void);
extern void sched_init_smp(void);
260
extern asmlinkage void schedule_tail(struct task_struct *prev);
261
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
262
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
263

264
extern int runqueue_is_locked(int cpu);
265
extern void task_rq_unlock_wait(struct task_struct *p);
I
Ingo Molnar 已提交
266

267
extern cpumask_var_t nohz_cpu_mask;
268 269
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
270
extern int get_nohz_load_balancer(void);
271 272 273 274 275 276
#else
static inline int select_nohz_load_balancer(int cpu)
{
	return 0;
}
#endif
L
Linus Torvalds 已提交
277

I
Ingo Molnar 已提交
278
/*
I
Ingo Molnar 已提交
279
 * Only dump TASK_* tasks. (0 for all tasks)
I
Ingo Molnar 已提交
280 281 282 283 284
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
I
Ingo Molnar 已提交
285
	show_state_filter(0);
I
Ingo Molnar 已提交
286 287
}

L
Linus Torvalds 已提交
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
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);

305 306
extern void sched_show_task(struct task_struct *p);

I
Ingo Molnar 已提交
307
#ifdef CONFIG_DETECT_SOFTLOCKUP
308
extern void softlockup_tick(void);
I
Ingo Molnar 已提交
309
extern void touch_softlockup_watchdog(void);
310
extern void touch_all_softlockup_watchdogs(void);
311 312 313
extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
				    struct file *filp, void __user *buffer,
				    size_t *lenp, loff_t *ppos);
I
Ingo Molnar 已提交
314
extern unsigned int  softlockup_panic;
315
extern int softlockup_thresh;
I
Ingo Molnar 已提交
316
#else
317
static inline void softlockup_tick(void)
I
Ingo Molnar 已提交
318 319 320 321 322
{
}
static inline void touch_softlockup_watchdog(void)
{
}
323 324 325
static inline void touch_all_softlockup_watchdogs(void)
{
}
I
Ingo Molnar 已提交
326 327
#endif

328 329 330 331 332 333 334 335 336
#ifdef CONFIG_DETECT_HUNG_TASK
extern unsigned int  sysctl_hung_task_panic;
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
					 struct file *filp, void __user *buffer,
					 size_t *lenp, loff_t *ppos);
#endif
I
Ingo Molnar 已提交
337

L
Linus Torvalds 已提交
338 339
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
340 341 342 343

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

L
Linus Torvalds 已提交
344 345 346 347
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
348
extern signed long schedule_timeout(signed long timeout);
349
extern signed long schedule_timeout_interruptible(signed long timeout);
M
Matthew Wilcox 已提交
350
extern signed long schedule_timeout_killable(signed long timeout);
351
extern signed long schedule_timeout_uninterruptible(signed long timeout);
P
Peter Zijlstra 已提交
352
asmlinkage void __schedule(void);
L
Linus Torvalds 已提交
353
asmlinkage void schedule(void);
354
extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
L
Linus Torvalds 已提交
355

S
Serge E. Hallyn 已提交
356
struct nsproxy;
357
struct user_namespace;
L
Linus Torvalds 已提交
358

359 360 361 362 363 364 365 366 367 368 369 370 371 372
/*
 * Default maximum number of active map areas, this limits the number of vmas
 * per mm struct. Users can overwrite this number by sysctl but there is a
 * problem.
 *
 * When a program's coredump is generated as ELF format, a section is created
 * per a vma. In ELF, the number of sections is represented in unsigned short.
 * This means the number of sections should be smaller than 65535 at coredump.
 * Because the kernel adds some informative sections to a image of program at
 * generating coredump, we need some margin. The number of extra sections is
 * 1-3 now and depends on arch. We use "5" as safe margin, here.
 */
#define MAPCOUNT_ELF_CORE_MARGIN	(5)
#define DEFAULT_MAX_MAP_COUNT	(USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
L
Linus Torvalds 已提交
373 374 375 376 377 378 379 380 381 382 383 384

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);
385 386
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
387

388
#if USE_SPLIT_PTLOCKS
389 390 391 392
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
393 394 395 396 397
#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)
398

399
#else  /* !USE_SPLIT_PTLOCKS */
400 401 402 403
/*
 * The mm counters are protected by its page_table_lock,
 * so can be incremented directly.
 */
L
Linus Torvalds 已提交
404 405 406 407 408
#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--
409

410
#endif /* !USE_SPLIT_PTLOCKS */
411

412 413
#define get_mm_rss(mm)					\
	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
414 415 416 417 418 419 420 421 422 423
#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)

424 425 426 427 428
static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
{
	return max(mm->hiwater_rss, get_mm_rss(mm));
}

J
Jiri Pirko 已提交
429 430 431 432 433 434 435 436 437
static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
					 struct mm_struct *mm)
{
	unsigned long hiwater_rss = get_mm_hiwater_rss(mm);

	if (*maxrss < hiwater_rss)
		*maxrss = hiwater_rss;
}

438 439 440 441
static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
{
	return max(mm->hiwater_vm, mm->total_vm);
}
442

443 444 445 446
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
447
/* dumpable bits */
448 449
#define MMF_DUMPABLE      0  /* core dump is permitted */
#define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
H
Hugh Dickins 已提交
450

451
#define MMF_DUMPABLE_BITS 2
H
Hugh Dickins 已提交
452
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
453 454 455 456 457 458

/* 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
459
#define MMF_DUMP_ELF_HEADERS	6
460 461
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED  8
H
Hugh Dickins 已提交
462

463
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
464
#define MMF_DUMP_FILTER_BITS	7
465 466 467
#define MMF_DUMP_FILTER_MASK \
	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
468
	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
469 470 471 472 473 474 475
	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)

#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
#else
# define MMF_DUMP_MASK_DEFAULT_ELF	0
#endif
H
Hugh Dickins 已提交
476 477 478 479
					/* leave room for more dump flags */
#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */

#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
480

L
Linus Torvalds 已提交
481 482 483 484
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
485
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
486 487
};

488
struct pacct_struct {
489 490
	int			ac_flag;
	long			ac_exitcode;
491
	unsigned long		ac_mem;
492 493
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
494 495
};

496 497 498
struct cpu_itimer {
	cputime_t expires;
	cputime_t incr;
499 500
	u32 error;
	u32 incr_error;
501 502
};

503 504 505 506 507
/**
 * struct task_cputime - collected CPU time counts
 * @utime:		time spent in user mode, in &cputime_t units
 * @stime:		time spent in kernel mode, in &cputime_t units
 * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
508
 *
509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
 * This structure groups together three kinds of CPU time that are
 * tracked for threads and thread groups.  Most things considering
 * CPU time want to group these counts together and treat all three
 * of them in parallel.
 */
struct task_cputime {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};
/* Alternate field names when used to cache expirations. */
#define prof_exp	stime
#define virt_exp	utime
#define sched_exp	sum_exec_runtime

524 525 526 527 528 529 530
#define INIT_CPUTIME	\
	(struct task_cputime) {					\
		.utime = cputime_zero,				\
		.stime = cputime_zero,				\
		.sum_exec_runtime = 0,				\
	}

P
Peter Zijlstra 已提交
531 532 533
/*
 * Disable preemption until the scheduler is running.
 * Reset by start_kernel()->sched_init()->init_idle().
P
Peter Zijlstra 已提交
534 535 536
 *
 * We include PREEMPT_ACTIVE to avoid cond_resched() from working
 * before the scheduler is active -- see should_resched().
P
Peter Zijlstra 已提交
537
 */
P
Peter Zijlstra 已提交
538
#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
P
Peter Zijlstra 已提交
539

540
/**
541 542 543 544 545
 * struct thread_group_cputimer - thread group interval timer counts
 * @cputime:		thread group interval timers.
 * @running:		non-zero when there are timers running and
 * 			@cputime receives updates.
 * @lock:		lock for fields in this struct.
546 547
 *
 * This structure contains the version of task_cputime, above, that is
548
 * used for thread group CPU timer calculations.
549
 */
550 551 552 553
struct thread_group_cputimer {
	struct task_cputime cputime;
	int running;
	spinlock_t lock;
554 555
};

L
Linus Torvalds 已提交
556 557 558 559 560 561 562 563 564 565 566 567 568 569
/*
 * 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: */
570
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
571 572 573 574 575 576 577 578 579 580 581 582

	/* 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.
	 */
	int			notify_count;
583
	struct task_struct	*group_exit_task;
L
Linus Torvalds 已提交
584 585 586 587 588 589 590 591 592

	/* 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 */
593
	struct hrtimer real_timer;
594
	struct pid *leader_pid;
595
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
596

597 598 599 600 601 602
	/*
	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
	 * values are defined to 0 and 1 respectively
	 */
	struct cpu_itimer it[2];
L
Linus Torvalds 已提交
603

604
	/*
605 606
	 * Thread group totals for process CPU timers.
	 * See thread_group_cputimer(), et al, for details.
607
	 */
608
	struct thread_group_cputimer cputimer;
609 610 611 612 613 614

	/* Earliest-expiration cache. */
	struct task_cputime cputime_expires;

	struct list_head cpu_timers[3];

615
	struct pid *tty_old_pgrp;
616

L
Linus Torvalds 已提交
617 618 619 620 621 622 623 624 625 626 627
	/* 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.
	 */
628
	cputime_t utime, stime, cutime, cstime;
629 630
	cputime_t gtime;
	cputime_t cgtime;
L
Linus Torvalds 已提交
631 632
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
633
	unsigned long inblock, oublock, cinblock, coublock;
J
Jiri Pirko 已提交
634
	unsigned long maxrss, cmaxrss;
635
	struct task_io_accounting ioac;
L
Linus Torvalds 已提交
636

637 638 639 640 641 642 643 644
	/*
	 * Cumulative ns of schedule CPU time fo dead threads in the
	 * group, not including a zombie group leader, (This only differs
	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
	 * other than jiffies.)
	 */
	unsigned long long sum_sched_runtime;

L
Linus Torvalds 已提交
645 646 647 648 649 650 651 652 653 654 655
	/*
	 * 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];

656 657 658
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
659 660 661
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
662 663 664 665
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
666 667

	int oom_adj;	/* OOM kill score adjustment (bit shift) */
L
Linus Torvalds 已提交
668 669
};

670 671 672 673 674
/* 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
675 676 677 678 679 680 681
/*
 * 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 */
682 683 684 685 686 687
/*
 * 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
688

689 690
#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */

691 692 693 694 695 696 697
/* 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
698 699 700 701 702 703 704 705
/*
 * 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? */
706
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
707 708 709
	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
710 711 712
#ifdef CONFIG_EPOLL
	atomic_t epoll_watches;	/* The number of file descriptors currently watched */
#endif
A
Alexey Dobriyan 已提交
713
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
714 715
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
716
#endif
L
Linus Torvalds 已提交
717 718 719 720 721 722 723 724
	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
725
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
726
	uid_t uid;
727
	struct user_namespace *user_ns;
728

729
#ifdef CONFIG_USER_SCHED
730
	struct task_group *tg;
D
Dhaval Giani 已提交
731
#ifdef CONFIG_SYSFS
732
	struct kobject kobj;
733
	struct delayed_work work;
734
#endif
D
Dhaval Giani 已提交
735
#endif
736

737
#ifdef CONFIG_PERF_EVENTS
738 739
	atomic_long_t locked_vm;
#endif
L
Linus Torvalds 已提交
740 741
};

742
extern int uids_sysfs_init(void);
743

L
Linus Torvalds 已提交
744 745 746 747 748
extern struct user_struct *find_user(uid_t);

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

749

L
Linus Torvalds 已提交
750 751 752
struct backing_dev_info;
struct reclaim_state;

753
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
754 755
struct sched_info {
	/* cumulative counters */
756
	unsigned long pcount;	      /* # of times run on this cpu */
757
	unsigned long long run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
758 759

	/* timestamps */
760 761
	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
762 763
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
764
	unsigned int bkl_count;
I
Ingo Molnar 已提交
765
#endif
L
Linus Torvalds 已提交
766
};
767
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
768

769 770 771 772 773 774 775 776 777 778 779 780 781 782
#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).
	 */
783 784 785 786 787 788 789 790 791 792 793 794 795

	/*
	 * 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 */
796 797 798 799

	struct timespec freepages_start, freepages_end;
	u64 freepages_delay;	/* wait for memory reclaim */
	u32 freepages_count;	/* total count of memory reclaim */
800
};
801 802 803 804 805 806 807 808 809 810 811
#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;
812
#endif
813
}
814

I
Ingo Molnar 已提交
815 816 817 818 819
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
820 821 822 823 824
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
825 826 827 828 829 830 831

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

832
#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
L
Linus Torvalds 已提交
833

834
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
835 836 837 838
#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
839
#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
P
Peter Zijlstra 已提交
840
#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
P
Peter Zijlstra 已提交
841
#define SD_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
P
Peter Zijlstra 已提交
842 843 844 845
#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
#define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
846

P
Peter Zijlstra 已提交
847
#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
848

849 850 851 852 853 854 855 856 857 858
enum powersavings_balance_level {
	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
	POWERSAVINGS_BALANCE_BASIC,	/* Fill one thread/core/package
					 * first for long running threads
					 */
	POWERSAVINGS_BALANCE_WAKEUP,	/* Also bias task wakeups to semi-idle
					 * cpu package for power savings
					 */
	MAX_POWERSAVINGS_BALANCE_LEVELS
};
859

860
extern int sched_mc_power_savings, sched_smt_power_savings;
861

862 863 864 865
static inline int sd_balance_for_mc_power(void)
{
	if (sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;
866

P
Peter Zijlstra 已提交
867
	return SD_PREFER_SIBLING;
868
}
869

870 871 872 873 874
static inline int sd_balance_for_package_power(void)
{
	if (sched_mc_power_savings | sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;

P
Peter Zijlstra 已提交
875
	return SD_PREFER_SIBLING;
876
}
877

878 879 880 881 882 883 884 885 886 887 888 889 890
/*
 * Optimise SD flags for power savings:
 * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
 * Keep default SD flags if sched_{smt,mc}_power_saving=0
 */

static inline int sd_power_saving_flags(void)
{
	if (sched_mc_power_savings | sched_smt_power_savings)
		return SD_BALANCE_NEWIDLE;

	return 0;
}
L
Linus Torvalds 已提交
891 892 893 894 895 896

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

	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
897
	 * single CPU.
898
	 */
899
	unsigned int cpu_power;
900

901 902 903 904 905 906 907 908 909 910 911
	/*
	 * The CPUs this group covers.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 *
	 * It is also be embedded into static data structures at build
	 * time. (See 'struct static_sched_group' in kernel/sched.c)
	 */
	unsigned long cpumask[0];
L
Linus Torvalds 已提交
912 913
};

914 915
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
916
	return to_cpumask(sg->cpumask);
917 918
}

919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
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
937 938 939
struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
940
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
941 942 943 944 945 946
	struct sched_group *groups;	/* the balancing groups of the 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
947 948 949 950
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
951
	unsigned int forkexec_idx;
P
Peter Zijlstra 已提交
952
	unsigned int smt_gain;
L
Linus Torvalds 已提交
953
	int flags;			/* See SD_* */
954
	enum sched_domain_level level;
L
Linus Torvalds 已提交
955 956 957 958 959 960

	/* 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 */

P
Peter Zijlstra 已提交
961 962
	u64 last_update;

L
Linus Torvalds 已提交
963 964
#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
965 966 967 968 969 970 971 972
	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
973 974

	/* Active load balancing */
975 976 977
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
978

979
	/* SD_BALANCE_EXEC stats */
980 981 982
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
983

984
	/* SD_BALANCE_FORK stats */
985 986 987
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
988

L
Linus Torvalds 已提交
989
	/* try_to_wake_up() stats */
990 991 992
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
993
#endif
994 995 996
#ifdef CONFIG_SCHED_DEBUG
	char *name;
#endif
997

998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008
	/*
	 * Span of all CPUs in this domain.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 *
	 * It is also be embedded into static data structures at build
	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
	 */
	unsigned long span[0];
L
Linus Torvalds 已提交
1009 1010
};

1011 1012
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
1013
	return to_cpumask(sd->span);
1014 1015
}

1016
extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
1017
				    struct sched_domain_attr *dattr_new);
P
Paul Jackson 已提交
1018

1019 1020 1021 1022 1023 1024 1025 1026
/* Test a flag in parent sched domain */
static inline int test_sd_parent(struct sched_domain *sd, int flag)
{
	if (sd->parent && (sd->parent->flags & flag))
		return 1;

	return 0;
}
P
Paul Jackson 已提交
1027

1028 1029 1030
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);

1031
#else /* CONFIG_SMP */
L
Linus Torvalds 已提交
1032

1033
struct sched_domain_attr;
1034

1035
static inline void
1036
partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
1037 1038
			struct sched_domain_attr *dattr_new)
{
1039
}
1040
#endif	/* !CONFIG_SMP */
L
Linus Torvalds 已提交
1041

1042

L
Linus Torvalds 已提交
1043 1044 1045
struct io_context;			/* See blkdev.h */


1046
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
1047
extern void prefetch_stack(struct task_struct *t);
1048 1049 1050
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
1051 1052 1053

struct audit_context;		/* See audit.c */
struct mempolicy;
1054
struct pipe_inode_info;
1055
struct uts_namespace;
L
Linus Torvalds 已提交
1056

I
Ingo Molnar 已提交
1057 1058 1059
struct rq;
struct sched_domain;

P
Peter Zijlstra 已提交
1060 1061 1062 1063
/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
P
Peter Zijlstra 已提交
1064
#define WF_FORK		0x02		/* child wakeup after fork */
P
Peter Zijlstra 已提交
1065

I
Ingo Molnar 已提交
1066
struct sched_class {
1067
	const struct sched_class *next;
I
Ingo Molnar 已提交
1068

1069
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
1070
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
1071
	void (*yield_task) (struct rq *rq);
I
Ingo Molnar 已提交
1072

P
Peter Zijlstra 已提交
1073
	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
I
Ingo Molnar 已提交
1074

1075
	struct task_struct * (*pick_next_task) (struct rq *rq);
1076
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
1077

1078
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
1079
	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
L
Li Zefan 已提交
1080

P
Peter Williams 已提交
1081
	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
1082
			struct rq *busiest, unsigned long max_load_move,
I
Ingo Molnar 已提交
1083
			struct sched_domain *sd, enum cpu_idle_type idle,
1084
			int *all_pinned, int *this_best_prio);
I
Ingo Molnar 已提交
1085

1086 1087 1088
	int (*move_one_task) (struct rq *this_rq, int this_cpu,
			      struct rq *busiest, struct sched_domain *sd,
			      enum cpu_idle_type idle);
1089 1090 1091
	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);
1092

1093
	void (*set_cpus_allowed)(struct task_struct *p,
1094
				 const struct cpumask *newmask);
G
Gregory Haskins 已提交
1095

1096 1097
	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
L
Li Zefan 已提交
1098 1099 1100 1101 1102
#endif

	void (*set_curr_task) (struct rq *rq);
	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
	void (*task_new) (struct rq *rq, struct task_struct *p);
1103 1104 1105 1106 1107 1108 1109

	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
1110

1111 1112
	unsigned int (*get_rr_interval) (struct task_struct *task);

P
Peter Zijlstra 已提交
1113 1114 1115
#ifdef CONFIG_FAIR_GROUP_SCHED
	void (*moved_group) (struct task_struct *p);
#endif
I
Ingo Molnar 已提交
1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
};

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;
1135
	struct list_head	group_node;
I
Ingo Molnar 已提交
1136 1137
	unsigned int		on_rq;

1138 1139
	u64			exec_start;
	u64			sum_exec_runtime;
I
Ingo Molnar 已提交
1140
	u64			vruntime;
1141
	u64			prev_sum_exec_runtime;
1142

I
Ingo Molnar 已提交
1143 1144 1145
	u64			last_wakeup;
	u64			avg_overlap;

1146 1147
	u64			nr_migrations;

1148 1149 1150
	u64			start_runtime;
	u64			avg_wakeup;

1151 1152
	u64			avg_running;

1153
#ifdef CONFIG_SCHEDSTATS
I
Ingo Molnar 已提交
1154
	u64			wait_start;
1155
	u64			wait_max;
1156 1157
	u64			wait_count;
	u64			wait_sum;
1158 1159
	u64			iowait_count;
	u64			iowait_sum;
1160

I
Ingo Molnar 已提交
1161 1162
	u64			sleep_start;
	u64			sleep_max;
1163 1164 1165
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
1166 1167
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
1168
	u64			slice_max;
1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185

	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;
1186 1187
#endif

I
Ingo Molnar 已提交
1188 1189 1190 1191 1192 1193 1194 1195
#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
};
1196

P
Peter Zijlstra 已提交
1197 1198
struct sched_rt_entity {
	struct list_head run_list;
1199
	unsigned long timeout;
1200
	unsigned int time_slice;
P
Peter Zijlstra 已提交
1201 1202
	int nr_cpus_allowed;

1203
	struct sched_rt_entity *back;
1204
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
1205 1206 1207 1208 1209 1210
	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
1211 1212
};

1213 1214
struct rcu_node;

L
Linus Torvalds 已提交
1215 1216
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
1217
	void *stack;
L
Linus Torvalds 已提交
1218
	atomic_t usage;
1219 1220
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
1221

1222
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
1223

1224 1225
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
1226 1227
	int oncpu;
#endif
1228
#endif
1229

1230
	int prio, static_prio, normal_prio;
1231
	unsigned int rt_priority;
1232
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
1233
	struct sched_entity se;
P
Peter Zijlstra 已提交
1234
	struct sched_rt_entity rt;
L
Linus Torvalds 已提交
1235

1236 1237 1238 1239 1240
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

1241 1242 1243 1244 1245 1246 1247 1248 1249
	/*
	 * 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;
1250
#ifdef CONFIG_BLK_DEV_IO_TRACE
1251
	unsigned int btrace_seq;
1252
#endif
L
Linus Torvalds 已提交
1253

1254
	unsigned int policy;
L
Linus Torvalds 已提交
1255 1256
	cpumask_t cpus_allowed;

1257
#ifdef CONFIG_TREE_PREEMPT_RCU
P
Paul E. McKenney 已提交
1258
	int rcu_read_lock_nesting;
1259
	char rcu_read_unlock_special;
1260
	struct rcu_node *rcu_blocked_node;
1261 1262
	struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
P
Paul E. McKenney 已提交
1263

1264
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
1265 1266 1267 1268
	struct sched_info sched_info;
#endif

	struct list_head tasks;
1269
	struct plist_node pushable_tasks;
L
Linus Torvalds 已提交
1270 1271 1272 1273 1274

	struct mm_struct *mm, *active_mm;

/* task state */
	struct linux_binfmt *binfmt;
1275
	int exit_state;
L
Linus Torvalds 已提交
1276 1277 1278
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
1279
	unsigned int personality;
L
Linus Torvalds 已提交
1280
	unsigned did_exec:1;
1281 1282
	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
				 * execve */
1283 1284
	unsigned in_iowait:1;

1285 1286 1287 1288

	/* Revert to default priority/policy when forking */
	unsigned sched_reset_on_fork:1;

L
Linus Torvalds 已提交
1289 1290
	pid_t pid;
	pid_t tgid;
1291

1292
#ifdef CONFIG_CC_STACKPROTECTOR
1293 1294
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
1295
#endif
1296

L
Linus Torvalds 已提交
1297 1298 1299
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
R
Roland McGrath 已提交
1300
	 * p->real_parent->pid)
L
Linus Torvalds 已提交
1301
	 */
R
Roland McGrath 已提交
1302 1303
	struct task_struct *real_parent; /* real parent process */
	struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
L
Linus Torvalds 已提交
1304
	/*
R
Roland McGrath 已提交
1305
	 * children/sibling forms the list of my natural children
L
Linus Torvalds 已提交
1306 1307 1308 1309 1310
	 */
	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 */

R
Roland McGrath 已提交
1311 1312 1313 1314 1315 1316 1317 1318
	/*
	 * ptraced is the list of tasks this task is using ptrace on.
	 * This includes both natural children and PTRACE_ATTACH targets.
	 * p->ptrace_entry is p's link on the p->parent->ptraced list.
	 */
	struct list_head ptraced;
	struct list_head ptrace_entry;

1319 1320 1321 1322
	/*
	 * This is the tracer handle for the ptrace BTS extension.
	 * This field actually belongs to the ptracer task.
	 */
1323
	struct bts_context *bts;
1324

L
Linus Torvalds 已提交
1325
	/* PID/PID hash table linkage. */
1326
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
1327
	struct list_head thread_group;
L
Linus Torvalds 已提交
1328 1329 1330 1331 1332

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

1333
	cputime_t utime, stime, utimescaled, stimescaled;
1334
	cputime_t gtime;
1335
	cputime_t prev_utime, prev_stime;
L
Linus Torvalds 已提交
1336
	unsigned long nvcsw, nivcsw; /* context switch counts */
1337 1338
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
1339 1340 1341
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

1342
	struct task_cputime cputime_expires;
L
Linus Torvalds 已提交
1343 1344 1345
	struct list_head cpu_timers[3];

/* process credentials */
1346 1347 1348 1349
	const struct cred *real_cred;	/* objective and real subjective task
					 * credentials (COW) */
	const struct cred *cred;	/* effective (overridable) subjective task
					 * credentials (COW) */
1350 1351 1352
	struct mutex cred_guard_mutex;	/* guard against foreign influences on
					 * credential calculations
					 * (notably. ptrace) */
1353
	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
1354

1355 1356 1357 1358
	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
1359 1360
/* file system info */
	int link_count, total_link_count;
1361
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1362 1363
/* ipc stuff */
	struct sysv_sem sysvsem;
1364
#endif
1365
#ifdef CONFIG_DETECT_HUNG_TASK
1366 1367 1368
/* hung task detection */
	unsigned long last_switch_count;
#endif
L
Linus Torvalds 已提交
1369 1370 1371 1372 1373 1374
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1375
/* namespaces */
S
Serge E. Hallyn 已提交
1376
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1382
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
L
Linus Torvalds 已提交
1383 1384 1385 1386 1387 1388 1389 1390
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	int (*notifier)(void *priv);
	void *notifier_data;
	sigset_t *notifier_mask;
	struct audit_context *audit_context;
A
Al Viro 已提交
1391 1392
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
1393
	unsigned int sessionid;
A
Al Viro 已提交
1394
#endif
L
Linus Torvalds 已提交
1395 1396 1397 1398 1399
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
1400 1401
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
L
Linus Torvalds 已提交
1402 1403
	spinlock_t alloc_lock;

1404 1405 1406 1407 1408
#ifdef CONFIG_GENERIC_HARDIRQS
	/* IRQ handler threads */
	struct irqaction *irqaction;
#endif

1409 1410 1411
	/* Protection of the PI data structures: */
	spinlock_t pi_lock;

I
Ingo Molnar 已提交
1412 1413 1414 1415 1416 1417 1418
#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

1419 1420 1421 1422
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437
#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
1438
#ifdef CONFIG_LOCKDEP
1439
# define MAX_LOCK_DEPTH 48UL
I
Ingo Molnar 已提交
1440 1441 1442
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
1443
	struct held_lock held_locks[MAX_LOCK_DEPTH];
1444
	gfp_t lockdep_reclaim_gfp;
I
Ingo Molnar 已提交
1445
#endif
1446

L
Linus Torvalds 已提交
1447 1448 1449
/* journalling filesystem info */
	void *journal_info;

1450 1451 1452
/* stacked block device info */
	struct bio *bio_list, **bio_tail;

L
Linus Torvalds 已提交
1453 1454 1455 1456 1457 1458 1459 1460 1461
/* 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.  */
1462
	struct task_io_accounting ioac;
1463
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1464 1465
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
1466
	cputime_t acct_timexpd;	/* stime + utime since last update */
L
Linus Torvalds 已提交
1467 1468
#endif
#ifdef CONFIG_CPUSETS
1469
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
1470
	int cpuset_mem_spread_rotor;
L
Linus Torvalds 已提交
1471
#endif
1472
#ifdef CONFIG_CGROUPS
1473 1474 1475 1476
	/* 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;
1477
#endif
1478
#ifdef CONFIG_FUTEX
1479
	struct robust_list_head __user *robust_list;
1480 1481 1482
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1483 1484
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1485
#endif
1486 1487 1488 1489
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context *perf_event_ctxp;
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
1490
#endif
1491
#ifdef CONFIG_NUMA
1492
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
1493
	short il_next;
1494
#endif
1495
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1496
	struct rcu_head rcu;
1497 1498 1499 1500 1501

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1502 1503
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1504 1505 1506
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1507
#endif
P
Peter Zijlstra 已提交
1508
	struct prop_local_single dirties;
A
Arjan van de Ven 已提交
1509 1510 1511 1512
#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
1513 1514 1515 1516 1517 1518
	/*
	 * time slack values; these are used to round up poll() and
	 * select() etc timeout values. These are in nanoseconds.
	 */
	unsigned long timer_slack_ns;
	unsigned long default_timer_slack_ns;
1519 1520

	struct list_head	*scm_work_list;
1521
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
1522 1523 1524 1525
	/* Index of current stored adress in ret_stack */
	int curr_ret_stack;
	/* Stack of return addresses for return function tracing */
	struct ftrace_ret_stack	*ret_stack;
1526 1527
	/* time stamp for last schedule */
	unsigned long long ftrace_timestamp;
1528 1529 1530 1531 1532
	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun.
	 */
	atomic_t trace_overrun;
1533 1534
	/* Pause for the tracing */
	atomic_t tracing_graph_pause;
1535
#endif
1536 1537 1538
#ifdef CONFIG_TRACING
	/* state flags for use by tracers */
	unsigned long trace;
1539 1540 1541
	/* bitmask of trace recursion */
	unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
1542
	unsigned long stack_start;
L
Linus Torvalds 已提交
1543 1544
};

1545 1546 1547
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed)

1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
/*
 * 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
1574
static inline int rt_task(struct task_struct *p)
1575 1576 1577 1578
{
	return rt_prio(p->prio);
}

A
Alexey Dobriyan 已提交
1579
static inline struct pid *task_pid(struct task_struct *task)
1580 1581 1582 1583
{
	return task->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1584
static inline struct pid *task_tgid(struct task_struct *task)
1585 1586 1587 1588
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

1589 1590 1591 1592 1593
/*
 * Without tasklist or rcu lock it is not safe to dereference
 * the result of task_pgrp/task_session even if task == current,
 * we can race with another thread doing sys_setsid/sys_setpgid.
 */
A
Alexey Dobriyan 已提交
1594
static inline struct pid *task_pgrp(struct task_struct *task)
1595 1596 1597 1598
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

A
Alexey Dobriyan 已提交
1599
static inline struct pid *task_session(struct task_struct *task)
1600 1601 1602 1603
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

1604 1605 1606 1607 1608 1609 1610
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
1611 1612
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1613 1614 1615 1616 1617 1618
 * 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
 */
1619 1620
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
			struct pid_namespace *ns);
1621

A
Alexey Dobriyan 已提交
1622
static inline pid_t task_pid_nr(struct task_struct *tsk)
1623 1624 1625 1626
{
	return tsk->pid;
}

1627 1628 1629 1630 1631
static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
}
1632 1633 1634

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
1635
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
1636 1637 1638
}


A
Alexey Dobriyan 已提交
1639
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1640 1641 1642 1643
{
	return tsk->tgid;
}

1644
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1645 1646 1647 1648 1649 1650 1651

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


1652 1653
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1654
{
1655
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
1656 1657 1658 1659
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
1660
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
1661 1662 1663
}


1664 1665
static inline pid_t task_session_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1666
{
1667
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
1668 1669 1670 1671
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
1672
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
1673 1674
}

1675 1676 1677 1678 1679
/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
1680

L
Linus Torvalds 已提交
1681 1682 1683 1684 1685 1686 1687 1688
/**
 * 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
1689
static inline int pid_alive(struct task_struct *p)
L
Linus Torvalds 已提交
1690
{
1691
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1692 1693
}

1694
/**
1695
 * is_global_init - check if a task structure is init
1696 1697 1698
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1699
 */
A
Alexey Dobriyan 已提交
1700
static inline int is_global_init(struct task_struct *tsk)
1701 1702 1703
{
	return tsk->pid == 1;
}
1704 1705 1706 1707

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1708
 */
1709
extern int is_container_init(struct task_struct *tsk);
1710

1711 1712
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1713 1714
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
1715

1716
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1717 1718 1719 1720

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1721
		__put_task_struct(t);
I
Ingo Molnar 已提交
1722
}
L
Linus Torvalds 已提交
1723

1724 1725 1726 1727
extern cputime_t task_utime(struct task_struct *p);
extern cputime_t task_stime(struct task_struct *p);
extern cputime_t task_gtime(struct task_struct *p);

L
Linus Torvalds 已提交
1728 1729 1730 1731 1732 1733 1734
/*
 * 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 */
1735
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1736
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
L
Linus Torvalds 已提交
1737 1738 1739 1740 1741 1742 1743
#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 */
1744
#define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
L
Linus Torvalds 已提交
1745 1746 1747 1748
#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 */
H
Hugh Dickins 已提交
1749
#define PF_OOM_ORIGIN	0x00080000	/* Allocating much memory to others */
L
Linus Torvalds 已提交
1750
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
1751
#define PF_KTHREAD	0x00200000	/* I am a kernel thread */
J
Jens Axboe 已提交
1752 1753 1754 1755
#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 */
1756
#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
1757
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1758
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
R
Rafael J. Wysocki 已提交
1759
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
1760
#define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
L
Linus Torvalds 已提交
1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786

/*
 * 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)

1787 1788 1789 1790 1791 1792 1793 1794 1795
#ifdef CONFIG_TREE_PREEMPT_RCU

#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */

static inline void rcu_copy_process(struct task_struct *p)
{
	p->rcu_read_lock_nesting = 0;
	p->rcu_read_unlock_special = 0;
1796
	p->rcu_blocked_node = NULL;
1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807
	INIT_LIST_HEAD(&p->rcu_node_entry);
}

#else

static inline void rcu_copy_process(struct task_struct *p)
{
}

#endif

L
Linus Torvalds 已提交
1808
#ifdef CONFIG_SMP
1809
extern int set_cpus_allowed_ptr(struct task_struct *p,
1810
				const struct cpumask *new_mask);
L
Linus Torvalds 已提交
1811
#else
1812
static inline int set_cpus_allowed_ptr(struct task_struct *p,
1813
				       const struct cpumask *new_mask)
L
Linus Torvalds 已提交
1814
{
1815
	if (!cpumask_test_cpu(0, new_mask))
L
Linus Torvalds 已提交
1816 1817 1818 1819
		return -EINVAL;
	return 0;
}
#endif
1820 1821

#ifndef CONFIG_CPUMASK_OFFSTACK
1822 1823 1824 1825
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
	return set_cpus_allowed_ptr(p, &new_mask);
}
1826
#endif
L
Linus Torvalds 已提交
1827

1828 1829 1830 1831 1832 1833 1834 1835 1836 1837
/*
 * Architectures can set this to 1 if they have specified
 * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
 * but then during bootup it turns out that sched_clock()
 * is reliable after all:
 */
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
extern int sched_clock_stable;
#endif

L
Linus Torvalds 已提交
1838
extern unsigned long long sched_clock(void);
1839

1840 1841
extern void sched_clock_init(void);
extern u64 sched_clock_cpu(int cpu);
1842

1843
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
static inline void sched_clock_tick(void)
{
}

static inline void sched_clock_idle_sleep_event(void)
{
}

static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
{
}
#else
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#endif

1861 1862 1863 1864 1865 1866
/*
 * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
 * clock constructed from sched_clock():
 */
extern unsigned long long cpu_clock(int cpu);

1867
extern unsigned long long
1868
task_sched_runtime(struct task_struct *task);
1869
extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1870 1871 1872 1873 1874 1875 1876 1877

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

1878 1879
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
1880

L
Linus Torvalds 已提交
1881 1882 1883 1884 1885 1886 1887
#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);
1888

1889 1890 1891 1892 1893 1894
#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

1895
extern unsigned int sysctl_sched_latency;
1896
extern unsigned int sysctl_sched_min_granularity;
1897
extern unsigned int sysctl_sched_wakeup_granularity;
1898 1899
extern unsigned int sysctl_sched_shares_ratelimit;
extern unsigned int sysctl_sched_shares_thresh;
1900
extern unsigned int sysctl_sched_child_runs_first;
1901
#ifdef CONFIG_SCHED_DEBUG
1902
extern unsigned int sysctl_sched_features;
1903
extern unsigned int sysctl_sched_migration_cost;
1904
extern unsigned int sysctl_sched_nr_migrate;
1905
extern unsigned int sysctl_sched_time_avg;
1906
extern unsigned int sysctl_timer_migration;
1907 1908 1909 1910

int sched_nr_latency_handler(struct ctl_table *table, int write,
		struct file *file, void __user *buffer, size_t *length,
		loff_t *ppos);
1911
#endif
1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922
#ifdef CONFIG_SCHED_DEBUG
static inline unsigned int get_sysctl_timer_migration(void)
{
	return sysctl_timer_migration;
}
#else
static inline unsigned int get_sysctl_timer_migration(void)
{
	return 1;
}
#endif
P
Peter Zijlstra 已提交
1923 1924
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
1925

1926 1927 1928 1929
int sched_rt_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos);

1930
extern unsigned int sysctl_sched_compat_yield;
1931

1932
#ifdef CONFIG_RT_MUTEXES
1933 1934 1935
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);
1936
#else
A
Alexey Dobriyan 已提交
1937
static inline int rt_mutex_getprio(struct task_struct *p)
1938 1939 1940
{
	return p->normal_prio;
}
1941
# define rt_mutex_adjust_pi(p)		do { } while (0)
1942 1943
#endif

1944 1945 1946 1947 1948
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
1949 1950
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
1951 1952
extern int sched_setscheduler_nocheck(struct task_struct *, int,
				      struct sched_param *);
1953 1954 1955
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
1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983

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;

1984 1985 1986 1987 1988 1989 1990
extern struct pid_namespace init_pid_ns;

/*
 * find a task by one of its numerical ids
 *
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
1991 1992
 * find_task_by_vpid():
 *      finds a task by its virtual pid
1993
 *
1994
 * see also find_vpid() etc in include/linux/pid.h
1995 1996
 */

1997 1998 1999
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);
2000

2001
extern void __set_special_pids(struct pid *pid);
L
Linus Torvalds 已提交
2002 2003

/* per-UID process charging. */
2004
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
2005 2006 2007 2008 2009 2010
static inline struct user_struct *get_uid(struct user_struct *u)
{
	atomic_inc(&u->__count);
	return u;
}
extern void free_uid(struct user_struct *);
2011
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
2012 2013 2014

#include <asm/current.h>

2015
extern void do_timer(unsigned long ticks);
L
Linus Torvalds 已提交
2016

2017 2018 2019 2020
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
2021 2022 2023 2024 2025
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
2026 2027
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
2028 2029 2030

extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
2031
extern void __flush_signals(struct task_struct *);
2032
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054
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 *);
2055 2056
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);
2057
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
2058 2059
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
2060
extern int kill_proc_info(int, struct siginfo *, pid_t);
R
Roland McGrath 已提交
2061
extern int do_notify_parent(struct task_struct *, int);
2062
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
L
Linus Torvalds 已提交
2063 2064 2065 2066 2067 2068
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 struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
2069
extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
2070
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
2071 2072
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

2073 2074 2075 2076 2077
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
2078 2079 2080 2081 2082
/* 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)

2083 2084 2085 2086 2087
static inline int is_si_special(const struct siginfo *info)
{
	return info <= SEND_SIG_FORCED;
}

L
Linus Torvalds 已提交
2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106
/* 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 */
2107
extern void __mmdrop(struct mm_struct *);
L
Linus Torvalds 已提交
2108 2109
static inline void mmdrop(struct mm_struct * mm)
{
I
Ingo Molnar 已提交
2110
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
2111 2112 2113 2114 2115 2116 2117 2118 2119
		__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 *);
2120 2121
/* 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
2122

A
Alexey Dobriyan 已提交
2123 2124
extern int copy_thread(unsigned long, unsigned long, unsigned long,
			struct task_struct *, struct pt_regs *);
L
Linus Torvalds 已提交
2125 2126 2127 2128
extern void flush_thread(void);
extern void exit_thread(void);

extern void exit_files(struct task_struct *);
2129
extern void __cleanup_signal(struct signal_struct *);
2130
extern void __cleanup_sighand(struct sighand_struct *);
2131

L
Linus Torvalds 已提交
2132
extern void exit_itimers(struct signal_struct *);
2133
extern void flush_itimer_signals(void);
L
Linus Torvalds 已提交
2134 2135 2136 2137 2138 2139 2140 2141 2142

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 *);
2143
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
2144 2145

extern void set_task_comm(struct task_struct *tsk, char *from);
2146
extern char *get_task_comm(char *to, struct task_struct *tsk);
L
Linus Torvalds 已提交
2147 2148

#ifdef CONFIG_SMP
2149
extern void wait_task_context_switch(struct task_struct *p);
R
Roland McGrath 已提交
2150
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
L
Linus Torvalds 已提交
2151
#else
2152
static inline void wait_task_context_switch(struct task_struct *p) {}
R
Roland McGrath 已提交
2153 2154 2155 2156 2157
static inline unsigned long wait_task_inactive(struct task_struct *p,
					       long match_state)
{
	return 1;
}
L
Linus Torvalds 已提交
2158 2159
#endif

2160 2161
#define next_task(p) \
	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
L
Linus Torvalds 已提交
2162 2163 2164 2165

#define for_each_process(p) \
	for (p = &init_task ; (p = next_task(p)) != &init_task ; )

2166
extern bool current_is_single_threaded(void);
D
David Howells 已提交
2167

L
Linus Torvalds 已提交
2168 2169 2170 2171 2172 2173 2174 2175 2176 2177
/*
 * 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)

2178 2179
/* 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
2180

2181 2182 2183 2184 2185 2186
/* 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
2187
static inline int has_group_leader_pid(struct task_struct *p)
2188 2189 2190 2191
{
	return p->pid == p->tgid;
}

2192 2193 2194 2195 2196 2197
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
	return p1->tgid == p2->tgid;
}

2198
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
2199
{
2200 2201
	return list_entry_rcu(p->thread_group.next,
			      struct task_struct, thread_group);
O
Oleg Nesterov 已提交
2202 2203
}

A
Alexey Dobriyan 已提交
2204
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
2205
{
O
Oleg Nesterov 已提交
2206
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
2207 2208 2209 2210 2211
}

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

2212 2213 2214 2215 2216
static inline int task_detached(struct task_struct *p)
{
	return p->exit_signal == -1;
}

L
Linus Torvalds 已提交
2217
/*
2218
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
2219
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
2220 2221
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236
 *
 * 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);
}

2237 2238 2239 2240 2241 2242 2243 2244 2245
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
2246 2247
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
2248 2249
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
2250

2251 2252 2253 2254 2255 2256 2257 2258
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
2259
	return (unsigned long *)(task_thread_info(p) + 1);
2260 2261
}

A
Al Viro 已提交
2262 2263
#endif

2264 2265 2266 2267 2268 2269 2270
static inline int object_is_on_stack(void *obj)
{
	void *stack = task_stack_page(current);

	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
}

2271 2272
extern void thread_info_cache_init(void);

2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285
#ifdef CONFIG_DEBUG_STACK_USAGE
static inline unsigned long stack_not_used(struct task_struct *p)
{
	unsigned long *n = end_of_stack(p);

	do { 	/* Skip over canary */
		n++;
	} while (!*n);

	return (unsigned long)n - (unsigned long)end_of_stack(p);
}
#endif

L
Linus Torvalds 已提交
2286 2287 2288 2289 2290
/* 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
2291
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2292 2293 2294 2295
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2296
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2297 2298 2299 2300
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2301
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2302 2303 2304 2305
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2306
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2307 2308 2309 2310
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2311
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323
}

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);
}

2324 2325 2326 2327 2328
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

2329 2330 2331 2332 2333 2334
static inline int restart_syscall(void)
{
	set_tsk_thread_flag(current, TIF_SIGPENDING);
	return -ERESTARTNOINTR;
}

L
Linus Torvalds 已提交
2335 2336 2337 2338
static inline int signal_pending(struct task_struct *p)
{
	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
M
Matthew Wilcox 已提交
2339

2340 2341 2342 2343
static inline int __fatal_signal_pending(struct task_struct *p)
{
	return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
M
Matthew Wilcox 已提交
2344 2345 2346 2347 2348 2349

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

2350 2351 2352 2353 2354 2355 2356 2357 2358 2359
static inline int signal_pending_state(long state, struct task_struct *p)
{
	if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
		return 0;
	if (!signal_pending(p))
		return 0;

	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
}

L
Linus Torvalds 已提交
2360 2361
static inline int need_resched(void)
{
2362
	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
L
Linus Torvalds 已提交
2363 2364 2365 2366 2367 2368 2369 2370 2371
}

/*
 * 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.
 */
2372
extern int _cond_resched(void);
2373

2374 2375 2376 2377
#define cond_resched() ({			\
	__might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})
2378

2379 2380
extern int __cond_resched_lock(spinlock_t *lock);

2381 2382
#ifdef CONFIG_PREEMPT
#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
2383
#else
2384
#define PREEMPT_LOCK_OFFSET	0
2385
#endif
2386

2387
#define cond_resched_lock(lock) ({				\
2388
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
2389 2390 2391 2392 2393 2394 2395 2396 2397
	__cond_resched_lock(lock);				\
})

extern int __cond_resched_softirq(void);

#define cond_resched_softirq() ({				\
	__might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);	\
	__cond_resched_softirq();				\
})
L
Linus Torvalds 已提交
2398 2399 2400

/*
 * Does a critical section need to be broken due to another
N
Nick Piggin 已提交
2401 2402
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
2403
 */
N
Nick Piggin 已提交
2404
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
2405
{
N
Nick Piggin 已提交
2406 2407 2408
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
2409
	return 0;
N
Nick Piggin 已提交
2410
#endif
L
Linus Torvalds 已提交
2411 2412
}

2413 2414 2415
/*
 * Thread group CPU time accounting.
 */
2416
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
2417
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
2418

2419
static inline void thread_group_cputime_init(struct signal_struct *sig)
2420
{
2421 2422 2423
	sig->cputimer.cputime = INIT_CPUTIME;
	spin_lock_init(&sig->cputimer.lock);
	sig->cputimer.running = 0;
2424 2425 2426 2427 2428 2429
}

static inline void thread_group_cputime_free(struct signal_struct *sig)
{
}

R
Roland McGrath 已提交
2430 2431 2432 2433 2434 2435 2436
/*
 * 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
2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447
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
2448
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
2449 2450
}

I
Ingo Molnar 已提交
2451
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467

#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 */

extern void arch_pick_mmap_layout(struct mm_struct *mm);

I
Ingo Molnar 已提交
2468 2469 2470 2471
#ifdef CONFIG_TRACING
extern void
__trace_special(void *__tr, void *__data,
		unsigned long arg1, unsigned long arg2, unsigned long arg3);
L
Linus Torvalds 已提交
2472
#else
I
Ingo Molnar 已提交
2473 2474 2475
static inline void
__trace_special(void *__tr, void *__data,
		unsigned long arg1, unsigned long arg2, unsigned long arg3)
L
Linus Torvalds 已提交
2476 2477 2478 2479
{
}
#endif

2480 2481
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
2482

L
Linus Torvalds 已提交
2483 2484
extern void normalize_rt_tasks(void);

2485
#ifdef CONFIG_GROUP_SCHED
2486

2487
extern struct task_group init_task_group;
2488 2489
#ifdef CONFIG_USER_SCHED
extern struct task_group root_task_group;
2490
extern void set_tg_uid(struct user_struct *user);
2491
#endif
2492

2493
extern struct task_group *sched_create_group(struct task_group *parent);
2494
extern void sched_destroy_group(struct task_group *tg);
2495
extern void sched_move_task(struct task_struct *tsk);
2496
#ifdef CONFIG_FAIR_GROUP_SCHED
2497
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
2498
extern unsigned long sched_group_shares(struct task_group *tg);
2499 2500
#endif
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
2501 2502 2503
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);
2504 2505 2506
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);
2507
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
2508
#endif
2509 2510
#endif

2511 2512 2513
extern int task_can_switch_user(struct user_struct *up,
					struct task_struct *tsk);

2514 2515 2516
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
2517
	tsk->ioac.rchar += amt;
2518 2519 2520 2521
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
2522
	tsk->ioac.wchar += amt;
2523 2524 2525 2526
}

static inline void inc_syscr(struct task_struct *tsk)
{
2527
	tsk->ioac.syscr++;
2528 2529 2530 2531
}

static inline void inc_syscw(struct task_struct *tsk)
{
2532
	tsk->ioac.syscw++;
2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551
}
#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

D
Dave Hansen 已提交
2552 2553 2554 2555
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

T
Thomas Gleixner 已提交
2556 2557 2558 2559 2560 2561 2562
/*
 * Call the function if the target task is executing on a CPU right now:
 */
extern void task_oncpu_function_call(struct task_struct *p,
				     void (*func) (void *info), void *info);


2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575
#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 */

2576 2577
#define TASK_STATE_TO_CHAR_STR "RSDTtZX"

L
Linus Torvalds 已提交
2578 2579 2580
#endif /* __KERNEL__ */

#endif