sched.h 75.9 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);
L
Linus Torvalds 已提交
148

149 150
extern unsigned long get_parent_ip(unsigned long addr);

I
Ingo Molnar 已提交
151 152
struct seq_file;
struct cfs_rq;
153
struct task_group;
I
Ingo Molnar 已提交
154 155 156 157
#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
158
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
I
Ingo Molnar 已提交
159 160 161 162 163 164 165 166 167
#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
168
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
I
Ingo Molnar 已提交
169 170 171
{
}
#endif
L
Linus Torvalds 已提交
172

173 174 175 176 177 178 179 180 181 182
/*
 * 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
183 184 185
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
M
Matthew Wilcox 已提交
186 187
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
188 189 190 191
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
192
#define TASK_DEAD		64
M
Matthew Wilcox 已提交
193
#define TASK_WAKEKILL		128
P
Peter Zijlstra 已提交
194
#define TASK_WAKING		256
195
#define TASK_STATE_MAX		512
M
Matthew Wilcox 已提交
196

197
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
198

199 200
extern char ___assert_task_state[1 - 2*!!(
		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
M
Matthew Wilcox 已提交
201 202 203 204 205

/* 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
206

207 208
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
M
Matthew Wilcox 已提交
209
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
210 211 212

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
M
Matthew Wilcox 已提交
213 214
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED)
215

M
Matthew Wilcox 已提交
216 217
#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
218
#define task_is_stopped_or_traced(task)	\
M
Matthew Wilcox 已提交
219
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
220
#define task_contributes_to_load(task)	\
221
				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
222
				 (task->flags & PF_FREEZING) == 0)
L
Linus Torvalds 已提交
223 224 225 226 227 228

#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))

229 230 231 232 233 234 235 236 237 238 239
/*
 * 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
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
#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;

259
struct task_struct;
L
Linus Torvalds 已提交
260 261 262

extern void sched_init(void);
extern void sched_init_smp(void);
263
extern asmlinkage void schedule_tail(struct task_struct *prev);
264
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
265
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
266

267
extern int runqueue_is_locked(int cpu);
268
extern void task_rq_unlock_wait(struct task_struct *p);
I
Ingo Molnar 已提交
269

270
extern cpumask_var_t nohz_cpu_mask;
271 272
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
273
extern int get_nohz_load_balancer(void);
274 275 276 277 278 279
#else
static inline int select_nohz_load_balancer(int cpu)
{
	return 0;
}
#endif
L
Linus Torvalds 已提交
280

I
Ingo Molnar 已提交
281
/*
I
Ingo Molnar 已提交
282
 * Only dump TASK_* tasks. (0 for all tasks)
I
Ingo Molnar 已提交
283 284 285 286 287
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
I
Ingo Molnar 已提交
288
	show_state_filter(0);
I
Ingo Molnar 已提交
289 290
}

L
Linus Torvalds 已提交
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
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);

308 309
extern void sched_show_task(struct task_struct *p);

I
Ingo Molnar 已提交
310
#ifdef CONFIG_DETECT_SOFTLOCKUP
311
extern void softlockup_tick(void);
I
Ingo Molnar 已提交
312
extern void touch_softlockup_watchdog(void);
313
extern void touch_all_softlockup_watchdogs(void);
314
extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
315
				    void __user *buffer,
316
				    size_t *lenp, loff_t *ppos);
I
Ingo Molnar 已提交
317
extern unsigned int  softlockup_panic;
318
extern int softlockup_thresh;
I
Ingo Molnar 已提交
319
#else
320
static inline void softlockup_tick(void)
I
Ingo Molnar 已提交
321 322 323 324 325
{
}
static inline void touch_softlockup_watchdog(void)
{
}
326 327 328
static inline void touch_all_softlockup_watchdogs(void)
{
}
I
Ingo Molnar 已提交
329 330
#endif

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,
337
					 void __user *buffer,
338 339
					 size_t *lenp, loff_t *ppos);
#endif
I
Ingo Molnar 已提交
340

L
Linus Torvalds 已提交
341 342
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
343 344 345 346

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

L
Linus Torvalds 已提交
347 348 349 350
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
351
extern signed long schedule_timeout(signed long timeout);
352
extern signed long schedule_timeout_interruptible(signed long timeout);
M
Matthew Wilcox 已提交
353
extern signed long schedule_timeout_killable(signed long timeout);
354
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
355
asmlinkage void schedule(void);
356
extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
L
Linus Torvalds 已提交
357

S
Serge E. Hallyn 已提交
358
struct nsproxy;
359
struct user_namespace;
L
Linus Torvalds 已提交
360

361 362 363 364 365 366 367 368 369 370 371 372 373 374
/*
 * 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
375 376 377 378 379

extern int sysctl_max_map_count;

#include <linux/aio.h>

380 381
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
L
Linus Torvalds 已提交
382 383 384 385 386 387 388
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);
389 390
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
391 392 393
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
L
Linus Torvalds 已提交
394

395
#if USE_SPLIT_PTLOCKS
396 397 398 399
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
400 401 402 403 404
#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)
405

406
#else  /* !USE_SPLIT_PTLOCKS */
407 408 409 410
/*
 * The mm counters are protected by its page_table_lock,
 * so can be incremented directly.
 */
L
Linus Torvalds 已提交
411 412 413 414 415
#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--
416

417
#endif /* !USE_SPLIT_PTLOCKS */
418

419 420
#define get_mm_rss(mm)					\
	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
421 422 423 424 425 426 427 428 429 430
#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)

431 432 433 434 435
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
436 437 438 439 440 441 442 443 444
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;
}

445 446 447 448
static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
{
	return max(mm->hiwater_vm, mm->total_vm);
}
449

450 451 452 453
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
454
/* dumpable bits */
455 456
#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
457

458
#define MMF_DUMPABLE_BITS 2
H
Hugh Dickins 已提交
459
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
460 461 462 463 464 465

/* 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
466
#define MMF_DUMP_ELF_HEADERS	6
467 468
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED  8
H
Hugh Dickins 已提交
469

470
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
471
#define MMF_DUMP_FILTER_BITS	7
472 473 474
#define MMF_DUMP_FILTER_MASK \
	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
475
	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
476 477 478 479 480 481 482
	 (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
483 484 485 486
					/* 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)
487

L
Linus Torvalds 已提交
488 489 490 491
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
492
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
493 494
};

495
struct pacct_struct {
496 497
	int			ac_flag;
	long			ac_exitcode;
498
	unsigned long		ac_mem;
499 500
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
501 502
};

503 504 505
struct cpu_itimer {
	cputime_t expires;
	cputime_t incr;
506 507
	u32 error;
	u32 incr_error;
508 509
};

510 511 512 513 514
/**
 * 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
515
 *
516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
 * 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

531 532 533 534 535 536 537
#define INIT_CPUTIME	\
	(struct task_cputime) {					\
		.utime = cputime_zero,				\
		.stime = cputime_zero,				\
		.sum_exec_runtime = 0,				\
	}

P
Peter Zijlstra 已提交
538 539 540
/*
 * Disable preemption until the scheduler is running.
 * Reset by start_kernel()->sched_init()->init_idle().
P
Peter Zijlstra 已提交
541 542 543
 *
 * We include PREEMPT_ACTIVE to avoid cond_resched() from working
 * before the scheduler is active -- see should_resched().
P
Peter Zijlstra 已提交
544
 */
P
Peter Zijlstra 已提交
545
#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
P
Peter Zijlstra 已提交
546

547
/**
548 549 550 551 552
 * 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.
553 554
 *
 * This structure contains the version of task_cputime, above, that is
555
 * used for thread group CPU timer calculations.
556
 */
557 558 559 560
struct thread_group_cputimer {
	struct task_cputime cputime;
	int running;
	spinlock_t lock;
561 562
};

L
Linus Torvalds 已提交
563 564 565 566 567 568 569 570 571 572 573 574 575 576
/*
 * 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: */
577
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
578 579 580 581 582 583 584 585 586 587 588 589

	/* 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;
590
	struct task_struct	*group_exit_task;
L
Linus Torvalds 已提交
591 592 593 594 595 596 597 598 599

	/* 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 */
600
	struct hrtimer real_timer;
601
	struct pid *leader_pid;
602
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
603

604 605 606 607 608 609
	/*
	 * 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
610

611
	/*
612 613
	 * Thread group totals for process CPU timers.
	 * See thread_group_cputimer(), et al, for details.
614
	 */
615
	struct thread_group_cputimer cputimer;
616 617 618 619 620 621

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

	struct list_head cpu_timers[3];

622
	struct pid *tty_old_pgrp;
623

L
Linus Torvalds 已提交
624 625 626 627 628 629 630 631 632 633 634
	/* 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.
	 */
635
	cputime_t utime, stime, cutime, cstime;
636 637
	cputime_t gtime;
	cputime_t cgtime;
638 639 640
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
	cputime_t prev_utime, prev_stime;
#endif
L
Linus Torvalds 已提交
641 642
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
643
	unsigned long inblock, oublock, cinblock, coublock;
J
Jiri Pirko 已提交
644
	unsigned long maxrss, cmaxrss;
645
	struct task_io_accounting ioac;
L
Linus Torvalds 已提交
646

647 648 649 650 651 652 653 654
	/*
	 * 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
655 656 657 658 659 660 661 662 663 664 665
	/*
	 * 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];

666 667 668
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
669 670 671
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
672 673 674 675
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
676 677

	int oom_adj;	/* OOM kill score adjustment (bit shift) */
L
Linus Torvalds 已提交
678 679
};

680 681 682 683 684
/* 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
685 686 687 688 689 690 691
/*
 * 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 */
692 693 694 695 696 697
/*
 * 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
698

699 700
#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */

701 702 703 704 705 706 707
/* 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
708 709 710 711 712 713 714 715
/*
 * 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? */
716
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
717 718 719
	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
720 721 722
#ifdef CONFIG_EPOLL
	atomic_t epoll_watches;	/* The number of file descriptors currently watched */
#endif
A
Alexey Dobriyan 已提交
723
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
724 725
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
726
#endif
L
Linus Torvalds 已提交
727 728 729 730 731 732 733 734
	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
735
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
736
	uid_t uid;
737
	struct user_namespace *user_ns;
738

739
#ifdef CONFIG_USER_SCHED
740
	struct task_group *tg;
D
Dhaval Giani 已提交
741
#ifdef CONFIG_SYSFS
742
	struct kobject kobj;
743
	struct delayed_work work;
744
#endif
D
Dhaval Giani 已提交
745
#endif
746

747
#ifdef CONFIG_PERF_EVENTS
748 749
	atomic_long_t locked_vm;
#endif
L
Linus Torvalds 已提交
750 751
};

752
extern int uids_sysfs_init(void);
753

L
Linus Torvalds 已提交
754 755 756 757 758
extern struct user_struct *find_user(uid_t);

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

759

L
Linus Torvalds 已提交
760 761 762
struct backing_dev_info;
struct reclaim_state;

763
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
764 765
struct sched_info {
	/* cumulative counters */
766
	unsigned long pcount;	      /* # of times run on this cpu */
767
	unsigned long long run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
768 769

	/* timestamps */
770 771
	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
772 773
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
774
	unsigned int bkl_count;
I
Ingo Molnar 已提交
775
#endif
L
Linus Torvalds 已提交
776
};
777
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
778

779 780 781 782 783 784 785 786 787 788 789 790 791 792
#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).
	 */
793 794 795 796 797 798 799 800 801 802 803 804 805

	/*
	 * 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 */
806 807 808 809

	struct timespec freepages_start, freepages_end;
	u64 freepages_delay;	/* wait for memory reclaim */
	u32 freepages_count;	/* total count of memory reclaim */
810
};
811 812 813 814 815 816 817 818 819 820 821
#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;
822
#endif
823
}
824

I
Ingo Molnar 已提交
825 826 827 828 829
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
830 831 832 833 834
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
835 836 837 838 839 840 841

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

842
#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
L
Linus Torvalds 已提交
843

844
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
845 846 847 848
#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 */
849
#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
P
Peter Zijlstra 已提交
850
#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
P
Peter Zijlstra 已提交
851
#define SD_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
P
Peter Zijlstra 已提交
852 853 854 855
#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 */
856

P
Peter Zijlstra 已提交
857
#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
858

859 860 861 862 863 864 865 866 867 868
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
};
869

870
extern int sched_mc_power_savings, sched_smt_power_savings;
871

872 873 874 875
static inline int sd_balance_for_mc_power(void)
{
	if (sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;
876

P
Peter Zijlstra 已提交
877
	return SD_PREFER_SIBLING;
878
}
879

880 881 882 883 884
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
885
	return SD_PREFER_SIBLING;
886
}
887

888 889 890 891 892 893 894 895 896 897 898 899 900
/*
 * 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
901 902 903 904 905 906

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
907
	 * single CPU.
908
	 */
909
	unsigned int cpu_power;
910

911 912 913 914 915 916 917 918 919 920 921
	/*
	 * 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
922 923
};

924 925
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
926
	return to_cpumask(sg->cpumask);
927 928
}

929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
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
947 948 949
struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
950
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
951 952 953 954 955 956
	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
957 958 959 960
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
961
	unsigned int forkexec_idx;
P
Peter Zijlstra 已提交
962
	unsigned int smt_gain;
L
Linus Torvalds 已提交
963
	int flags;			/* See SD_* */
964
	enum sched_domain_level level;
L
Linus Torvalds 已提交
965 966 967 968 969 970

	/* 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
971 972
	u64 last_update;

L
Linus Torvalds 已提交
973 974
#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
975 976 977 978 979 980 981 982
	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
983 984

	/* Active load balancing */
985 986 987
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
988

989
	/* SD_BALANCE_EXEC stats */
990 991 992
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
993

994
	/* SD_BALANCE_FORK stats */
995 996 997
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
998

L
Linus Torvalds 已提交
999
	/* try_to_wake_up() stats */
1000 1001 1002
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
1003
#endif
1004 1005 1006
#ifdef CONFIG_SCHED_DEBUG
	char *name;
#endif
1007

1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018
	/*
	 * 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
1019 1020
};

1021 1022
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
1023
	return to_cpumask(sd->span);
1024 1025
}

1026
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
1027
				    struct sched_domain_attr *dattr_new);
P
Paul Jackson 已提交
1028

1029 1030 1031 1032
/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);

1033 1034 1035 1036 1037 1038 1039 1040
/* 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
1041

1042 1043 1044
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);

1045
#else /* CONFIG_SMP */
L
Linus Torvalds 已提交
1046

1047
struct sched_domain_attr;
1048

1049
static inline void
1050
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
1051 1052
			struct sched_domain_attr *dattr_new)
{
1053
}
1054
#endif	/* !CONFIG_SMP */
L
Linus Torvalds 已提交
1055

1056

L
Linus Torvalds 已提交
1057 1058 1059
struct io_context;			/* See blkdev.h */


1060
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
1061
extern void prefetch_stack(struct task_struct *t);
1062 1063 1064
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
1065 1066 1067

struct audit_context;		/* See audit.c */
struct mempolicy;
1068
struct pipe_inode_info;
1069
struct uts_namespace;
L
Linus Torvalds 已提交
1070

I
Ingo Molnar 已提交
1071 1072 1073
struct rq;
struct sched_domain;

P
Peter Zijlstra 已提交
1074 1075 1076 1077
/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
P
Peter Zijlstra 已提交
1078
#define WF_FORK		0x02		/* child wakeup after fork */
P
Peter Zijlstra 已提交
1079

I
Ingo Molnar 已提交
1080
struct sched_class {
1081
	const struct sched_class *next;
I
Ingo Molnar 已提交
1082

1083
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
1084
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
1085
	void (*yield_task) (struct rq *rq);
I
Ingo Molnar 已提交
1086

P
Peter Zijlstra 已提交
1087
	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
I
Ingo Molnar 已提交
1088

1089
	struct task_struct * (*pick_next_task) (struct rq *rq);
1090
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
1091

1092
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
1093
	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
L
Li Zefan 已提交
1094

P
Peter Williams 已提交
1095
	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
1096
			struct rq *busiest, unsigned long max_load_move,
I
Ingo Molnar 已提交
1097
			struct sched_domain *sd, enum cpu_idle_type idle,
1098
			int *all_pinned, int *this_best_prio);
I
Ingo Molnar 已提交
1099

1100 1101 1102
	int (*move_one_task) (struct rq *this_rq, int this_cpu,
			      struct rq *busiest, struct sched_domain *sd,
			      enum cpu_idle_type idle);
1103 1104
	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	void (*post_schedule) (struct rq *this_rq);
1105 1106
	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
1107

1108
	void (*set_cpus_allowed)(struct task_struct *p,
1109
				 const struct cpumask *newmask);
G
Gregory Haskins 已提交
1110

1111 1112
	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
L
Li Zefan 已提交
1113 1114 1115 1116
#endif

	void (*set_curr_task) (struct rq *rq);
	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
P
Peter Zijlstra 已提交
1117
	void (*task_fork) (struct task_struct *p);
1118 1119 1120 1121 1122 1123 1124

	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
1125

1126 1127
	unsigned int (*get_rr_interval) (struct rq *rq,
					 struct task_struct *task);
1128

P
Peter Zijlstra 已提交
1129
#ifdef CONFIG_FAIR_GROUP_SCHED
1130
	void (*moved_group) (struct task_struct *p, int on_rq);
P
Peter Zijlstra 已提交
1131
#endif
I
Ingo Molnar 已提交
1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
};

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;
1151
	struct list_head	group_node;
I
Ingo Molnar 已提交
1152 1153
	unsigned int		on_rq;

1154 1155
	u64			exec_start;
	u64			sum_exec_runtime;
I
Ingo Molnar 已提交
1156
	u64			vruntime;
1157
	u64			prev_sum_exec_runtime;
1158

I
Ingo Molnar 已提交
1159 1160 1161
	u64			last_wakeup;
	u64			avg_overlap;

1162 1163
	u64			nr_migrations;

1164 1165 1166
	u64			start_runtime;
	u64			avg_wakeup;

1167
#ifdef CONFIG_SCHEDSTATS
I
Ingo Molnar 已提交
1168
	u64			wait_start;
1169
	u64			wait_max;
1170 1171
	u64			wait_count;
	u64			wait_sum;
1172 1173
	u64			iowait_count;
	u64			iowait_sum;
1174

I
Ingo Molnar 已提交
1175 1176
	u64			sleep_start;
	u64			sleep_max;
1177 1178 1179
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
1180 1181
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
1182
	u64			slice_max;
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198

	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_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;
1199 1200
#endif

I
Ingo Molnar 已提交
1201 1202 1203 1204 1205 1206 1207 1208
#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
};
1209

P
Peter Zijlstra 已提交
1210 1211
struct sched_rt_entity {
	struct list_head run_list;
1212
	unsigned long timeout;
1213
	unsigned int time_slice;
P
Peter Zijlstra 已提交
1214 1215
	int nr_cpus_allowed;

1216
	struct sched_rt_entity *back;
1217
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
1218 1219 1220 1221 1222 1223
	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
1224 1225
};

1226 1227
struct rcu_node;

L
Linus Torvalds 已提交
1228 1229
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
1230
	void *stack;
L
Linus Torvalds 已提交
1231
	atomic_t usage;
1232 1233
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
1234

1235
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
1236

1237 1238
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
1239 1240
	int oncpu;
#endif
1241
#endif
1242

1243
	int prio, static_prio, normal_prio;
1244
	unsigned int rt_priority;
1245
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
1246
	struct sched_entity se;
P
Peter Zijlstra 已提交
1247
	struct sched_rt_entity rt;
L
Linus Torvalds 已提交
1248

1249 1250 1251 1252 1253
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

1254 1255 1256 1257 1258 1259 1260 1261 1262
	/*
	 * 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;
1263
#ifdef CONFIG_BLK_DEV_IO_TRACE
1264
	unsigned int btrace_seq;
1265
#endif
L
Linus Torvalds 已提交
1266

1267
	unsigned int policy;
L
Linus Torvalds 已提交
1268 1269
	cpumask_t cpus_allowed;

1270
#ifdef CONFIG_TREE_PREEMPT_RCU
P
Paul E. McKenney 已提交
1271
	int rcu_read_lock_nesting;
1272
	char rcu_read_unlock_special;
1273
	struct rcu_node *rcu_blocked_node;
1274 1275
	struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
P
Paul E. McKenney 已提交
1276

1277
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
1278 1279 1280 1281
	struct sched_info sched_info;
#endif

	struct list_head tasks;
1282
	struct plist_node pushable_tasks;
L
Linus Torvalds 已提交
1283 1284 1285 1286

	struct mm_struct *mm, *active_mm;

/* task state */
1287
	int exit_state;
L
Linus Torvalds 已提交
1288 1289 1290
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
1291
	unsigned int personality;
L
Linus Torvalds 已提交
1292
	unsigned did_exec:1;
1293 1294
	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
				 * execve */
1295 1296
	unsigned in_iowait:1;

1297 1298 1299 1300

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

L
Linus Torvalds 已提交
1301 1302
	pid_t pid;
	pid_t tgid;
1303

1304
#ifdef CONFIG_CC_STACKPROTECTOR
1305 1306
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
1307
#endif
1308

L
Linus Torvalds 已提交
1309 1310 1311
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
R
Roland McGrath 已提交
1312
	 * p->real_parent->pid)
L
Linus Torvalds 已提交
1313
	 */
R
Roland McGrath 已提交
1314 1315
	struct task_struct *real_parent; /* real parent process */
	struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
L
Linus Torvalds 已提交
1316
	/*
R
Roland McGrath 已提交
1317
	 * children/sibling forms the list of my natural children
L
Linus Torvalds 已提交
1318 1319 1320 1321 1322
	 */
	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
1323 1324 1325 1326 1327 1328 1329 1330
	/*
	 * 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;

1331 1332 1333 1334
	/*
	 * This is the tracer handle for the ptrace BTS extension.
	 * This field actually belongs to the ptracer task.
	 */
1335
	struct bts_context *bts;
1336

L
Linus Torvalds 已提交
1337
	/* PID/PID hash table linkage. */
1338
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
1339
	struct list_head thread_group;
L
Linus Torvalds 已提交
1340 1341 1342 1343 1344

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

1345
	cputime_t utime, stime, utimescaled, stimescaled;
1346
	cputime_t gtime;
1347
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
1348
	cputime_t prev_utime, prev_stime;
1349
#endif
L
Linus Torvalds 已提交
1350
	unsigned long nvcsw, nivcsw; /* context switch counts */
1351 1352
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
1353 1354 1355
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

1356
	struct task_cputime cputime_expires;
L
Linus Torvalds 已提交
1357 1358 1359
	struct list_head cpu_timers[3];

/* process credentials */
1360 1361 1362 1363
	const struct cred *real_cred;	/* objective and real subjective task
					 * credentials (COW) */
	const struct cred *cred;	/* effective (overridable) subjective task
					 * credentials (COW) */
1364 1365 1366
	struct mutex cred_guard_mutex;	/* guard against foreign influences on
					 * credential calculations
					 * (notably. ptrace) */
1367
	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
1368

1369 1370 1371
	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
1372
				     - initialized normally by setup_new_exec */
L
Linus Torvalds 已提交
1373 1374
/* file system info */
	int link_count, total_link_count;
1375
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1376 1377
/* ipc stuff */
	struct sysv_sem sysvsem;
1378
#endif
1379
#ifdef CONFIG_DETECT_HUNG_TASK
1380 1381 1382
/* hung task detection */
	unsigned long last_switch_count;
#endif
L
Linus Torvalds 已提交
1383 1384 1385 1386 1387 1388
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1389
/* namespaces */
S
Serge E. Hallyn 已提交
1390
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1391 1392 1393 1394 1395
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1396
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
L
Linus Torvalds 已提交
1397 1398 1399 1400 1401 1402 1403 1404
	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
1405 1406
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
1407
	unsigned int sessionid;
A
Al Viro 已提交
1408
#endif
L
Linus Torvalds 已提交
1409 1410 1411 1412 1413
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
1414 1415
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
L
Linus Torvalds 已提交
1416 1417
	spinlock_t alloc_lock;

1418 1419 1420 1421 1422
#ifdef CONFIG_GENERIC_HARDIRQS
	/* IRQ handler threads */
	struct irqaction *irqaction;
#endif

1423
	/* Protection of the PI data structures: */
1424
	raw_spinlock_t pi_lock;
1425

I
Ingo Molnar 已提交
1426 1427 1428 1429 1430 1431 1432
#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

1433 1434 1435 1436
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1437 1438 1439 1440
#ifdef CONFIG_TRACE_IRQFLAGS
	unsigned int irq_events;
	unsigned long hardirq_enable_ip;
	unsigned long hardirq_disable_ip;
1441
	unsigned int hardirq_enable_event;
1442
	unsigned int hardirq_disable_event;
1443 1444
	int hardirqs_enabled;
	int hardirq_context;
1445 1446
	unsigned long softirq_disable_ip;
	unsigned long softirq_enable_ip;
1447
	unsigned int softirq_disable_event;
1448
	unsigned int softirq_enable_event;
1449
	int softirqs_enabled;
1450 1451
	int softirq_context;
#endif
I
Ingo Molnar 已提交
1452
#ifdef CONFIG_LOCKDEP
1453
# define MAX_LOCK_DEPTH 48UL
I
Ingo Molnar 已提交
1454 1455 1456
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
1457
	struct held_lock held_locks[MAX_LOCK_DEPTH];
1458
	gfp_t lockdep_reclaim_gfp;
I
Ingo Molnar 已提交
1459
#endif
1460

L
Linus Torvalds 已提交
1461 1462 1463
/* journalling filesystem info */
	void *journal_info;

1464 1465 1466
/* stacked block device info */
	struct bio *bio_list, **bio_tail;

L
Linus Torvalds 已提交
1467 1468 1469 1470 1471 1472 1473 1474 1475
/* 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.  */
1476
	struct task_io_accounting ioac;
1477
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1478 1479
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
1480
	cputime_t acct_timexpd;	/* stime + utime since last update */
L
Linus Torvalds 已提交
1481 1482
#endif
#ifdef CONFIG_CPUSETS
1483
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
1484
	int cpuset_mem_spread_rotor;
L
Linus Torvalds 已提交
1485
#endif
1486
#ifdef CONFIG_CGROUPS
1487 1488 1489 1490
	/* 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;
1491
#endif
1492
#ifdef CONFIG_FUTEX
1493
	struct robust_list_head __user *robust_list;
1494 1495 1496
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1497 1498
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1499
#endif
1500 1501 1502 1503
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context *perf_event_ctxp;
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
1504
#endif
1505
#ifdef CONFIG_NUMA
1506
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
1507
	short il_next;
1508
#endif
1509
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1510
	struct rcu_head rcu;
1511 1512 1513 1514 1515

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1516 1517
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1518 1519 1520
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1521
#endif
P
Peter Zijlstra 已提交
1522
	struct prop_local_single dirties;
A
Arjan van de Ven 已提交
1523 1524 1525 1526
#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
1527 1528 1529 1530 1531 1532
	/*
	 * 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;
1533 1534

	struct list_head	*scm_work_list;
1535
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
1536 1537 1538 1539
	/* 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;
1540 1541
	/* time stamp for last schedule */
	unsigned long long ftrace_timestamp;
1542 1543 1544 1545 1546
	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun.
	 */
	atomic_t trace_overrun;
1547 1548
	/* Pause for the tracing */
	atomic_t tracing_graph_pause;
1549
#endif
1550 1551 1552
#ifdef CONFIG_TRACING
	/* state flags for use by tracers */
	unsigned long trace;
1553 1554 1555
	/* bitmask of trace recursion */
	unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
1556
	unsigned long stack_start;
1557 1558 1559 1560 1561 1562 1563 1564
#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
	struct memcg_batch_info {
		int do_batch;	/* incremented when batch uncharge started */
		struct mem_cgroup *memcg; /* target memcg of uncharge */
		unsigned long bytes; 		/* uncharged usage */
		unsigned long memsw_bytes; /* uncharged mem+swap usage */
	} memcg_batch;
#endif
L
Linus Torvalds 已提交
1565 1566
};

1567
/* Future-safe accessor for struct task_struct's cpus_allowed. */
1568
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
1569

1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
/*
 * 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
1596
static inline int rt_task(struct task_struct *p)
1597 1598 1599 1600
{
	return rt_prio(p->prio);
}

A
Alexey Dobriyan 已提交
1601
static inline struct pid *task_pid(struct task_struct *task)
1602 1603 1604 1605
{
	return task->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1606
static inline struct pid *task_tgid(struct task_struct *task)
1607 1608 1609 1610
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

1611 1612 1613 1614 1615
/*
 * 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
1616
static inline struct pid *task_pgrp(struct task_struct *task)
1617 1618 1619 1620
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

A
Alexey Dobriyan 已提交
1621
static inline struct pid *task_session(struct task_struct *task)
1622 1623 1624 1625
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

1626 1627 1628 1629 1630 1631 1632
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
1633 1634
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1635 1636 1637 1638 1639 1640
 * 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
 */
1641 1642
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
			struct pid_namespace *ns);
1643

A
Alexey Dobriyan 已提交
1644
static inline pid_t task_pid_nr(struct task_struct *tsk)
1645 1646 1647 1648
{
	return tsk->pid;
}

1649 1650 1651 1652 1653
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);
}
1654 1655 1656

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
1657
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
1658 1659 1660
}


A
Alexey Dobriyan 已提交
1661
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1662 1663 1664 1665
{
	return tsk->tgid;
}

1666
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1667 1668 1669 1670 1671 1672 1673

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


1674 1675
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1676
{
1677
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
1678 1679 1680 1681
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
1682
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
1683 1684 1685
}


1686 1687
static inline pid_t task_session_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1688
{
1689
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
1690 1691 1692 1693
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
1694
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
1695 1696
}

1697 1698 1699 1700 1701
/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
1702

L
Linus Torvalds 已提交
1703 1704 1705 1706 1707 1708 1709 1710
/**
 * 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
1711
static inline int pid_alive(struct task_struct *p)
L
Linus Torvalds 已提交
1712
{
1713
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1714 1715
}

1716
/**
1717
 * is_global_init - check if a task structure is init
1718 1719 1720
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1721
 */
A
Alexey Dobriyan 已提交
1722
static inline int is_global_init(struct task_struct *tsk)
1723 1724 1725
{
	return tsk->pid == 1;
}
1726 1727 1728 1729

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1730
 */
1731
extern int is_container_init(struct task_struct *tsk);
1732

1733 1734
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1735 1736
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
1737

1738
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1739 1740 1741 1742

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1743
		__put_task_struct(t);
I
Ingo Molnar 已提交
1744
}
L
Linus Torvalds 已提交
1745

1746
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1747
extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1748

L
Linus Torvalds 已提交
1749 1750 1751 1752 1753 1754 1755
/*
 * 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 */
1756
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1757
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
L
Linus Torvalds 已提交
1758
#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
1759
#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
L
Linus Torvalds 已提交
1760 1761 1762 1763 1764 1765
#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 */
1766
#define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
L
Linus Torvalds 已提交
1767 1768 1769 1770
#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
1771
#define PF_OOM_ORIGIN	0x00080000	/* Allocating much memory to others */
L
Linus Torvalds 已提交
1772
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
1773
#define PF_KTHREAD	0x00200000	/* I am a kernel thread */
J
Jens Axboe 已提交
1774 1775 1776 1777
#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 */
1778
#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
1779
#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
1780
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1781
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
R
Rafael J. Wysocki 已提交
1782
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
1783
#define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
L
Linus Torvalds 已提交
1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809

/*
 * 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)

1810 1811 1812 1813 1814 1815 1816 1817 1818
#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;
1819
	p->rcu_blocked_node = NULL;
1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830
	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
1831
#ifdef CONFIG_SMP
1832
extern int set_cpus_allowed_ptr(struct task_struct *p,
1833
				const struct cpumask *new_mask);
L
Linus Torvalds 已提交
1834
#else
1835
static inline int set_cpus_allowed_ptr(struct task_struct *p,
1836
				       const struct cpumask *new_mask)
L
Linus Torvalds 已提交
1837
{
1838
	if (!cpumask_test_cpu(0, new_mask))
L
Linus Torvalds 已提交
1839 1840 1841 1842
		return -EINVAL;
	return 0;
}
#endif
1843 1844

#ifndef CONFIG_CPUMASK_OFFSTACK
1845 1846 1847 1848
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
	return set_cpus_allowed_ptr(p, &new_mask);
}
1849
#endif
L
Linus Torvalds 已提交
1850

1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
/*
 * 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

1861 1862
/* ftrace calls sched_clock() directly */
extern unsigned long long notrace sched_clock(void);
1863

1864 1865
extern void sched_clock_init(void);
extern u64 sched_clock_cpu(int cpu);
1866

1867
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884
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

1885 1886 1887 1888 1889 1890
/*
 * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
 * clock constructed from sched_clock():
 */
extern unsigned long long cpu_clock(int cpu);

1891
extern unsigned long long
1892
task_sched_runtime(struct task_struct *task);
1893
extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1894 1895 1896 1897 1898 1899 1900 1901

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

1902 1903
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
1904

L
Linus Torvalds 已提交
1905 1906 1907 1908 1909 1910 1911
#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);
1912

1913 1914 1915 1916 1917 1918
#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

1919
extern unsigned int sysctl_sched_latency;
1920
extern unsigned int sysctl_sched_min_granularity;
1921
extern unsigned int sysctl_sched_wakeup_granularity;
1922 1923
extern unsigned int sysctl_sched_shares_ratelimit;
extern unsigned int sysctl_sched_shares_thresh;
1924
extern unsigned int sysctl_sched_child_runs_first;
1925 1926 1927 1928 1929 1930 1931 1932 1933

enum sched_tunable_scaling {
	SCHED_TUNABLESCALING_NONE,
	SCHED_TUNABLESCALING_LOG,
	SCHED_TUNABLESCALING_LINEAR,
	SCHED_TUNABLESCALING_END,
};
extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;

1934
#ifdef CONFIG_SCHED_DEBUG
1935
extern unsigned int sysctl_sched_migration_cost;
1936
extern unsigned int sysctl_sched_nr_migrate;
1937
extern unsigned int sysctl_sched_time_avg;
1938
extern unsigned int sysctl_timer_migration;
1939

1940
int sched_proc_update_handler(struct ctl_table *table, int write,
1941
		void __user *buffer, size_t *length,
1942
		loff_t *ppos);
1943
#endif
1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954
#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
1955 1956
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
1957

1958
int sched_rt_handler(struct ctl_table *table, int write,
1959
		void __user *buffer, size_t *lenp,
1960 1961
		loff_t *ppos);

1962
extern unsigned int sysctl_sched_compat_yield;
1963

1964
#ifdef CONFIG_RT_MUTEXES
1965 1966 1967
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);
1968
#else
A
Alexey Dobriyan 已提交
1969
static inline int rt_mutex_getprio(struct task_struct *p)
1970 1971 1972
{
	return p->normal_prio;
}
1973
# define rt_mutex_adjust_pi(p)		do { } while (0)
1974 1975
#endif

1976 1977 1978 1979 1980
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
1981 1982
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
1983 1984
extern int sched_setscheduler_nocheck(struct task_struct *, int,
				      struct sched_param *);
1985 1986 1987
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
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015

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;

2016 2017 2018 2019 2020 2021 2022
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
2023 2024
 * find_task_by_vpid():
 *      finds a task by its virtual pid
2025
 *
2026
 * see also find_vpid() etc in include/linux/pid.h
2027 2028
 */

2029 2030 2031
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);
2032

2033
extern void __set_special_pids(struct pid *pid);
L
Linus Torvalds 已提交
2034 2035

/* per-UID process charging. */
2036
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
2037 2038 2039 2040 2041 2042
static inline struct user_struct *get_uid(struct user_struct *u)
{
	atomic_inc(&u->__count);
	return u;
}
extern void free_uid(struct user_struct *);
2043
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
2044 2045 2046

#include <asm/current.h>

2047
extern void do_timer(unsigned long ticks);
L
Linus Torvalds 已提交
2048

2049 2050 2051 2052
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
2053 2054 2055 2056 2057
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
2058 2059
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
2060 2061 2062

extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
2063
extern void __flush_signals(struct task_struct *);
2064
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086
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 *);
2087 2088
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);
2089
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
2090 2091
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
2092
extern int kill_proc_info(int, struct siginfo *, pid_t);
R
Roland McGrath 已提交
2093
extern int do_notify_parent(struct task_struct *, int);
2094
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
L
Linus Torvalds 已提交
2095 2096 2097 2098 2099
extern void force_sig(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 *);
2100
extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
2101
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
2102 2103
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

2104 2105 2106 2107 2108
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
2109 2110 2111 2112 2113
/* 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)

2114 2115 2116
/*
 * True if we are on the alternate signal stack.
 */
L
Linus Torvalds 已提交
2117 2118
static inline int on_sig_stack(unsigned long sp)
{
2119 2120 2121 2122 2123 2124 2125
#ifdef CONFIG_STACK_GROWSUP
	return sp >= current->sas_ss_sp &&
		sp - current->sas_ss_sp < current->sas_ss_size;
#else
	return sp > current->sas_ss_sp &&
		sp - current->sas_ss_sp <= current->sas_ss_size;
#endif
L
Linus Torvalds 已提交
2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139
}

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 */
2140
extern void __mmdrop(struct mm_struct *);
L
Linus Torvalds 已提交
2141 2142
static inline void mmdrop(struct mm_struct * mm)
{
I
Ingo Molnar 已提交
2143
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
2144 2145 2146 2147 2148 2149 2150 2151 2152
		__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 *);
2153 2154
/* 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
2155

A
Alexey Dobriyan 已提交
2156 2157
extern int copy_thread(unsigned long, unsigned long, unsigned long,
			struct task_struct *, struct pt_regs *);
L
Linus Torvalds 已提交
2158 2159 2160 2161
extern void flush_thread(void);
extern void exit_thread(void);

extern void exit_files(struct task_struct *);
2162
extern void __cleanup_signal(struct signal_struct *);
2163
extern void __cleanup_sighand(struct sighand_struct *);
2164

L
Linus Torvalds 已提交
2165
extern void exit_itimers(struct signal_struct *);
2166
extern void flush_itimer_signals(void);
L
Linus Torvalds 已提交
2167 2168 2169 2170 2171 2172 2173 2174 2175

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 *);
2176
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
2177 2178

extern void set_task_comm(struct task_struct *tsk, char *from);
2179
extern char *get_task_comm(char *to, struct task_struct *tsk);
L
Linus Torvalds 已提交
2180 2181

#ifdef CONFIG_SMP
2182
extern void wait_task_context_switch(struct task_struct *p);
R
Roland McGrath 已提交
2183
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
L
Linus Torvalds 已提交
2184
#else
2185
static inline void wait_task_context_switch(struct task_struct *p) {}
R
Roland McGrath 已提交
2186 2187 2188 2189 2190
static inline unsigned long wait_task_inactive(struct task_struct *p,
					       long match_state)
{
	return 1;
}
L
Linus Torvalds 已提交
2191 2192
#endif

2193 2194
#define next_task(p) \
	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
L
Linus Torvalds 已提交
2195 2196 2197 2198

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

2199
extern bool current_is_single_threaded(void);
D
David Howells 已提交
2200

L
Linus Torvalds 已提交
2201 2202 2203 2204 2205 2206 2207 2208 2209 2210
/*
 * 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)

2211 2212
/* 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
2213

2214 2215 2216 2217 2218 2219
/* 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
2220
static inline int has_group_leader_pid(struct task_struct *p)
2221 2222 2223 2224
{
	return p->pid == p->tgid;
}

2225 2226 2227 2228 2229 2230
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
	return p1->tgid == p2->tgid;
}

2231
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
2232
{
2233 2234
	return list_entry_rcu(p->thread_group.next,
			      struct task_struct, thread_group);
O
Oleg Nesterov 已提交
2235 2236
}

A
Alexey Dobriyan 已提交
2237
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
2238
{
O
Oleg Nesterov 已提交
2239
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
2240 2241 2242 2243 2244
}

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

2245 2246 2247 2248 2249
static inline int task_detached(struct task_struct *p)
{
	return p->exit_signal == -1;
}

L
Linus Torvalds 已提交
2250
/*
2251
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
2252
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
2253 2254
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269
 *
 * 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);
}

2270 2271 2272 2273 2274 2275 2276 2277 2278
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
2279 2280
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
2281 2282
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
2283

2284 2285 2286 2287 2288 2289 2290 2291
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
2292
	return (unsigned long *)(task_thread_info(p) + 1);
2293 2294
}

A
Al Viro 已提交
2295 2296
#endif

2297 2298 2299 2300 2301 2302 2303
static inline int object_is_on_stack(void *obj)
{
	void *stack = task_stack_page(current);

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

2304 2305
extern void thread_info_cache_init(void);

2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318
#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
2319 2320 2321 2322 2323
/* 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
2324
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2325 2326 2327 2328
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2329
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2330 2331 2332 2333
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2334
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2335 2336 2337 2338
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2339
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2340 2341 2342 2343
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2344
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356
}

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);
}

2357 2358 2359 2360 2361
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

2362 2363 2364 2365 2366 2367
static inline int restart_syscall(void)
{
	set_tsk_thread_flag(current, TIF_SIGPENDING);
	return -ERESTARTNOINTR;
}

L
Linus Torvalds 已提交
2368 2369 2370 2371
static inline int signal_pending(struct task_struct *p)
{
	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
M
Matthew Wilcox 已提交
2372

2373 2374 2375 2376
static inline int __fatal_signal_pending(struct task_struct *p)
{
	return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
M
Matthew Wilcox 已提交
2377 2378 2379 2380 2381 2382

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

2383 2384 2385 2386 2387 2388 2389 2390 2391 2392
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
2393 2394
static inline int need_resched(void)
{
2395
	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
L
Linus Torvalds 已提交
2396 2397 2398 2399 2400 2401 2402 2403 2404
}

/*
 * 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.
 */
2405
extern int _cond_resched(void);
2406

2407 2408 2409 2410
#define cond_resched() ({			\
	__might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})
2411

2412 2413
extern int __cond_resched_lock(spinlock_t *lock);

2414 2415
#ifdef CONFIG_PREEMPT
#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
2416
#else
2417
#define PREEMPT_LOCK_OFFSET	0
2418
#endif
2419

2420
#define cond_resched_lock(lock) ({				\
2421
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
2422 2423 2424 2425 2426 2427 2428 2429 2430
	__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
2431 2432 2433

/*
 * Does a critical section need to be broken due to another
N
Nick Piggin 已提交
2434 2435
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
2436
 */
N
Nick Piggin 已提交
2437
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
2438
{
N
Nick Piggin 已提交
2439 2440 2441
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
2442
	return 0;
N
Nick Piggin 已提交
2443
#endif
L
Linus Torvalds 已提交
2444 2445
}

2446 2447 2448
/*
 * Thread group CPU time accounting.
 */
2449
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
2450
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
2451

2452
static inline void thread_group_cputime_init(struct signal_struct *sig)
2453
{
2454 2455 2456
	sig->cputimer.cputime = INIT_CPUTIME;
	spin_lock_init(&sig->cputimer.lock);
	sig->cputimer.running = 0;
2457 2458 2459 2460 2461 2462
}

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

R
Roland McGrath 已提交
2463 2464 2465 2466 2467 2468 2469
/*
 * 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
2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480
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
2481
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
2482 2483
}

I
Ingo Molnar 已提交
2484
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498

#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 */

I
Ingo Molnar 已提交
2499 2500 2501 2502
#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
2503
#else
I
Ingo Molnar 已提交
2504 2505 2506
static inline void
__trace_special(void *__tr, void *__data,
		unsigned long arg1, unsigned long arg2, unsigned long arg3)
L
Linus Torvalds 已提交
2507 2508 2509 2510
{
}
#endif

2511 2512
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
2513

L
Linus Torvalds 已提交
2514 2515
extern void normalize_rt_tasks(void);

2516
#ifdef CONFIG_GROUP_SCHED
2517

2518
extern struct task_group init_task_group;
2519 2520
#ifdef CONFIG_USER_SCHED
extern struct task_group root_task_group;
2521
extern void set_tg_uid(struct user_struct *user);
2522
#endif
2523

2524
extern struct task_group *sched_create_group(struct task_group *parent);
2525
extern void sched_destroy_group(struct task_group *tg);
2526
extern void sched_move_task(struct task_struct *tsk);
2527
#ifdef CONFIG_FAIR_GROUP_SCHED
2528
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
2529
extern unsigned long sched_group_shares(struct task_group *tg);
2530 2531
#endif
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
2532 2533 2534
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);
2535 2536 2537
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);
2538
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
2539
#endif
2540 2541
#endif

2542 2543 2544
extern int task_can_switch_user(struct user_struct *up,
					struct task_struct *tsk);

2545 2546 2547
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
2548
	tsk->ioac.rchar += amt;
2549 2550 2551 2552
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
2553
	tsk->ioac.wchar += amt;
2554 2555 2556 2557
}

static inline void inc_syscr(struct task_struct *tsk)
{
2558
	tsk->ioac.syscr++;
2559 2560 2561 2562
}

static inline void inc_syscw(struct task_struct *tsk)
{
2563
	tsk->ioac.syscw++;
2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582
}
#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
2583 2584 2585 2586
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

T
Thomas Gleixner 已提交
2587 2588 2589 2590 2591 2592 2593
/*
 * 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);


2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606
#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 */

2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628
static inline unsigned long task_rlimit(const struct task_struct *tsk,
		unsigned int limit)
{
	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
}

static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
		unsigned int limit)
{
	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
}

static inline unsigned long rlimit(unsigned int limit)
{
	return task_rlimit(current, limit);
}

static inline unsigned long rlimit_max(unsigned int limit)
{
	return task_rlimit_max(current, limit);
}

L
Linus Torvalds 已提交
2629 2630 2631
#endif /* __KERNEL__ */

#endif