sched.h 82.1 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
/*
 * 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 */
24 25
/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
   and is now available for re-use. */
26
#define CLONE_NEWUTS		0x04000000	/* New utsname group? */
K
Kirill Korotaev 已提交
27
#define CLONE_NEWIPC		0x08000000	/* New ipcs */
S
Serge E. Hallyn 已提交
28
#define CLONE_NEWUSER		0x10000000	/* New user namespace */
29
#define CLONE_NEWPID		0x20000000	/* New pid namespace */
30
#define CLONE_NEWNET		0x40000000	/* New network namespace */
31
#define CLONE_IO		0x80000000	/* Clone io context */
32 33 34 35 36 37 38 39

/*
 * Scheduling policies
 */
#define SCHED_NORMAL		0
#define SCHED_FIFO		1
#define SCHED_RR		2
#define SCHED_BATCH		3
I
Ingo Molnar 已提交
40 41
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE		5
42 43
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK     0x40000000
44

45
#ifdef __KERNEL__
46 47 48 49 50

struct sched_param {
	int sched_priority;
};

L
Linus Torvalds 已提交
51 52 53 54 55 56 57 58 59 60 61 62 63
#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>
64
#include <linux/mm_types.h>
L
Linus Torvalds 已提交
65 66 67 68 69 70 71 72 73 74 75 76 77 78

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

#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/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>
A
Arjan van de Ven 已提交
91
#include <linux/latencytop.h>
92
#include <linux/cred.h>
P
Peter Zijlstra 已提交
93
#include <linux/llist.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_list;
101
struct fs_struct;
102
struct perf_event_context;
103
struct blk_plug;
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
extern unsigned long nr_iowait_cpu(int cpu);
144 145 146
extern unsigned long this_cpu_load(void);


147
extern void calc_global_load(unsigned long ticks);
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_dead(task)	((task)->exit_state != 0)
219
#define task_is_stopped_or_traced(task)	\
M
Matthew Wilcox 已提交
220
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
221
#define task_contributes_to_load(task)	\
222
				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
T
Tejun Heo 已提交
223
				 (task->flags & PF_FROZEN) == 0)
L
Linus Torvalds 已提交
224 225 226 227 228 229

#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))

230 231 232 233 234 235 236 237 238 239 240
/*
 * 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
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
#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;

260
struct task_struct;
L
Linus Torvalds 已提交
261

262 263 264 265
#ifdef CONFIG_PROVE_RCU
extern int lockdep_tasklist_lock_is_held(void);
#endif /* #ifdef CONFIG_PROVE_RCU */

L
Linus Torvalds 已提交
266 267
extern void sched_init(void);
extern void sched_init_smp(void);
268
extern asmlinkage void schedule_tail(struct task_struct *prev);
269
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
270
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
271

272
extern int runqueue_is_locked(int cpu);
I
Ingo Molnar 已提交
273

274
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
275
extern void select_nohz_load_balancer(int stop_tick);
276
extern void set_cpu_sd_state_idle(void);
277
extern int get_nohz_timer_target(void);
278
#else
279
static inline void select_nohz_load_balancer(int stop_tick) { }
280
static inline void set_cpu_sd_state_idle(void) { }
281
#endif
L
Linus Torvalds 已提交
282

I
Ingo Molnar 已提交
283
/*
I
Ingo Molnar 已提交
284
 * Only dump TASK_* tasks. (0 for all tasks)
I
Ingo Molnar 已提交
285 286 287 288 289
 */
extern void show_state_filter(unsigned long state_filter);

static inline void show_state(void)
{
I
Ingo Molnar 已提交
290
	show_state_filter(0);
I
Ingo Molnar 已提交
291 292
}

L
Linus Torvalds 已提交
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
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);

310 311
extern void sched_show_task(struct task_struct *p);

312
#ifdef CONFIG_LOCKUP_DETECTOR
I
Ingo Molnar 已提交
313
extern void touch_softlockup_watchdog(void);
314
extern void touch_softlockup_watchdog_sync(void);
315
extern void touch_all_softlockup_watchdogs(void);
316 317 318
extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
				  void __user *buffer,
				  size_t *lenp, loff_t *ppos);
I
Ingo Molnar 已提交
319
extern unsigned int  softlockup_panic;
320
void lockup_detector_init(void);
I
Ingo Molnar 已提交
321 322 323 324
#else
static inline void touch_softlockup_watchdog(void)
{
}
325 326 327
static inline void touch_softlockup_watchdog_sync(void)
{
}
328 329 330
static inline void touch_all_softlockup_watchdogs(void)
{
}
331 332 333
static inline void lockup_detector_init(void)
{
}
I
Ingo Molnar 已提交
334 335
#endif

336 337 338 339 340 341
#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,
342
					 void __user *buffer,
343
					 size_t *lenp, loff_t *ppos);
344 345 346
#else
/* Avoid need for ifdefs elsewhere in the code */
enum { sysctl_hung_task_timeout_secs = 0 };
347
#endif
I
Ingo Molnar 已提交
348

L
Linus Torvalds 已提交
349 350
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
351 352 353 354

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

L
Linus Torvalds 已提交
355 356 357 358
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
359
extern signed long schedule_timeout(signed long timeout);
360
extern signed long schedule_timeout_interruptible(signed long timeout);
M
Matthew Wilcox 已提交
361
extern signed long schedule_timeout_killable(signed long timeout);
362
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
363
asmlinkage void schedule(void);
364
extern void schedule_preempt_disabled(void);
365
extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
L
Linus Torvalds 已提交
366

S
Serge E. Hallyn 已提交
367
struct nsproxy;
368
struct user_namespace;
L
Linus Torvalds 已提交
369

370 371 372 373 374 375 376 377 378 379 380 381 382
/*
 * 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)
383
#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
L
Linus Torvalds 已提交
384 385 386 387 388

extern int sysctl_max_map_count;

#include <linux/aio.h>

389 390
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
L
Linus Torvalds 已提交
391 392 393 394 395 396 397
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);
398 399
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
400 401 402
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
L
Linus Torvalds 已提交
403

404

405 406 407 408
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
409
/* dumpable bits */
410 411
#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
412

413
#define MMF_DUMPABLE_BITS 2
H
Hugh Dickins 已提交
414
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
415 416 417 418 419 420

/* 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
421
#define MMF_DUMP_ELF_HEADERS	6
422 423
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED  8
H
Hugh Dickins 已提交
424

425
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
426
#define MMF_DUMP_FILTER_BITS	7
427 428 429
#define MMF_DUMP_FILTER_MASK \
	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
430
	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
431 432 433 434 435 436 437
	 (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
438 439
					/* leave room for more dump flags */
#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
A
Andrea Arcangeli 已提交
440
#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
H
Hugh Dickins 已提交
441 442

#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
443

L
Linus Torvalds 已提交
444 445 446 447
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
448
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
449 450
};

451
struct pacct_struct {
452 453
	int			ac_flag;
	long			ac_exitcode;
454
	unsigned long		ac_mem;
455 456
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
457 458
};

459 460 461
struct cpu_itimer {
	cputime_t expires;
	cputime_t incr;
462 463
	u32 error;
	u32 incr_error;
464 465
};

466 467 468 469 470
/**
 * 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
471
 *
472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
 * 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

487 488
#define INIT_CPUTIME	\
	(struct task_cputime) {					\
489 490
		.utime = 0,					\
		.stime = 0,					\
491 492 493
		.sum_exec_runtime = 0,				\
	}

P
Peter Zijlstra 已提交
494 495 496
/*
 * Disable preemption until the scheduler is running.
 * Reset by start_kernel()->sched_init()->init_idle().
P
Peter Zijlstra 已提交
497 498 499
 *
 * We include PREEMPT_ACTIVE to avoid cond_resched() from working
 * before the scheduler is active -- see should_resched().
P
Peter Zijlstra 已提交
500
 */
P
Peter Zijlstra 已提交
501
#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
P
Peter Zijlstra 已提交
502

503
/**
504 505 506 507 508
 * 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.
509 510
 *
 * This structure contains the version of task_cputime, above, that is
511
 * used for thread group CPU timer calculations.
512
 */
513 514 515
struct thread_group_cputimer {
	struct task_cputime cputime;
	int running;
516
	raw_spinlock_t lock;
517 518
};

519
#include <linux/rwsem.h>
520 521
struct autogroup;

L
Linus Torvalds 已提交
522
/*
523
 * NOTE! "signal_struct" does not have its own
L
Linus Torvalds 已提交
524 525 526 527 528 529
 * 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 {
530
	atomic_t		sigcnt;
L
Linus Torvalds 已提交
531
	atomic_t		live;
532
	int			nr_threads;
L
Linus Torvalds 已提交
533 534 535 536

	wait_queue_head_t	wait_chldexit;	/* for wait4() */

	/* current thread group signal load-balancing target: */
537
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
538 539 540 541 542 543 544 545 546 547 548 549

	/* 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;
550
	struct task_struct	*group_exit_task;
L
Linus Torvalds 已提交
551 552 553 554 555 556 557 558 559

	/* 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 */
560
	struct hrtimer real_timer;
561
	struct pid *leader_pid;
562
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
563

564 565 566 567 568 569
	/*
	 * 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
570

571
	/*
572 573
	 * Thread group totals for process CPU timers.
	 * See thread_group_cputimer(), et al, for details.
574
	 */
575
	struct thread_group_cputimer cputimer;
576 577 578 579 580 581

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

	struct list_head cpu_timers[3];

582
	struct pid *tty_old_pgrp;
583

L
Linus Torvalds 已提交
584 585 586 587 588
	/* boolean value for session group leader */
	int leader;

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

589 590 591
#ifdef CONFIG_SCHED_AUTOGROUP
	struct autogroup *autogroup;
#endif
L
Linus Torvalds 已提交
592 593 594 595 596 597
	/*
	 * 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.
	 */
598
	cputime_t utime, stime, cutime, cstime;
599 600
	cputime_t gtime;
	cputime_t cgtime;
601 602 603
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
	cputime_t prev_utime, prev_stime;
#endif
L
Linus Torvalds 已提交
604 605
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
606
	unsigned long inblock, oublock, cinblock, coublock;
J
Jiri Pirko 已提交
607
	unsigned long maxrss, cmaxrss;
608
	struct task_io_accounting ioac;
L
Linus Torvalds 已提交
609

610 611 612 613 614 615 616 617
	/*
	 * 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
618 619 620 621 622 623 624 625 626 627 628
	/*
	 * 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];

629 630 631
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
632 633 634
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
635 636 637 638
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
639 640
#ifdef CONFIG_CGROUPS
	/*
641 642 643 644 645 646 647
	 * group_rwsem prevents new tasks from entering the threadgroup and
	 * member tasks from exiting,a more specifically, setting of
	 * PF_EXITING.  fork and exit paths are protected with this rwsem
	 * using threadgroup_change_begin/end().  Users which require
	 * threadgroup to remain stable should use threadgroup_[un]lock()
	 * which also takes care of exec path.  Currently, cgroup is the
	 * only user.
648
	 */
649
	struct rw_semaphore group_rwsem;
650
#endif
651

D
David Rientjes 已提交
652 653
	int oom_adj;		/* OOM kill score adjustment (bit shift) */
	int oom_score_adj;	/* OOM kill score adjustment */
654 655
	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
				 * Only settable by CAP_SYS_RESOURCE. */
656 657 658 659

	struct mutex cred_guard_mutex;	/* guard against foreign influences on
					 * credential calculations
					 * (notably. ptrace) */
L
Linus Torvalds 已提交
660 661
};

662 663 664 665 666
/* 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
667 668 669 670
/*
 * Bits in flags field of signal_struct.
 */
#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
671 672
#define SIGNAL_STOP_CONTINUED	0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT	0x00000004 /* group exit in progress */
673 674 675 676 677 678
/*
 * 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
679

680 681
#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */

682 683 684 685 686 687 688
/* 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
689 690 691 692 693 694 695 696
/*
 * 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? */
697
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
698 699 700
	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
701 702 703
#ifdef CONFIG_FANOTIFY
	atomic_t fanotify_listeners;
#endif
704
#ifdef CONFIG_EPOLL
705
	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
706
#endif
A
Alexey Dobriyan 已提交
707
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
708 709
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
710
#endif
L
Linus Torvalds 已提交
711 712 713 714 715 716 717 718
	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
719
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
720
	uid_t uid;
721
	struct user_namespace *user_ns;
722

723
#ifdef CONFIG_PERF_EVENTS
724 725
	atomic_long_t locked_vm;
#endif
L
Linus Torvalds 已提交
726 727
};

728
extern int uids_sysfs_init(void);
729

L
Linus Torvalds 已提交
730 731 732 733 734
extern struct user_struct *find_user(uid_t);

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

735

L
Linus Torvalds 已提交
736 737 738
struct backing_dev_info;
struct reclaim_state;

739
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
740 741
struct sched_info {
	/* cumulative counters */
742
	unsigned long pcount;	      /* # of times run on this cpu */
743
	unsigned long long run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
744 745

	/* timestamps */
746 747
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
L
Linus Torvalds 已提交
748
};
749
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
750

751 752 753 754 755 756 757 758 759 760 761 762 763 764
#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).
	 */
765 766 767 768 769 770 771 772 773 774 775 776 777

	/*
	 * 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 */
778 779 780 781

	struct timespec freepages_start, freepages_end;
	u64 freepages_delay;	/* wait for memory reclaim */
	u32 freepages_count;	/* total count of memory reclaim */
782
};
783 784 785 786 787 788 789 790 791 792 793
#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;
794
#endif
795
}
796

I
Ingo Molnar 已提交
797 798 799 800 801
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
802 803 804
};

/*
805 806 807 808 809 810 811 812 813 814
 * Increase resolution of nice-level calculations for 64-bit architectures.
 * The extra resolution improves shares distribution and load balancing of
 * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
 * hierarchies, especially on larger systems. This is not a user-visible change
 * and does not change the user-interface for setting shares/weights.
 *
 * We increase resolution only if we have enough bits to allow this increased
 * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
 * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
 * increased costs.
L
Linus Torvalds 已提交
815
 */
816
#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
817 818 819 820 821 822 823 824
# define SCHED_LOAD_RESOLUTION	10
# define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)
#else
# define SCHED_LOAD_RESOLUTION	0
# define scale_load(w)		(w)
# define scale_load_down(w)	(w)
#endif
825

826
#define SCHED_LOAD_SHIFT	(10 + SCHED_LOAD_RESOLUTION)
827 828
#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

829 830 831 832 833
/*
 * Increase resolution of cpu_power calculations
 */
#define SCHED_POWER_SHIFT	10
#define SCHED_POWER_SCALE	(1L << SCHED_POWER_SHIFT)
L
Linus Torvalds 已提交
834

835 836 837
/*
 * sched-domains (multiprocessor balancing) declarations:
 */
838
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
839 840 841 842
#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 */
843
#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
P
Peter Zijlstra 已提交
844
#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
P
Peter Zijlstra 已提交
845
#define SD_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
P
Peter Zijlstra 已提交
846 847 848 849
#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 */
850
#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
P
Peter Zijlstra 已提交
851
#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
852
#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
853

854 855 856 857 858 859 860 861 862 863
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
};
864

865
extern int sched_mc_power_savings, sched_smt_power_savings;
866

867 868 869 870
static inline int sd_balance_for_mc_power(void)
{
	if (sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;
871

872 873 874 875
	if (!sched_mc_power_savings)
		return SD_PREFER_SIBLING;

	return 0;
876
}
877

878 879 880 881 882
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
883
	return SD_PREFER_SIBLING;
884
}
885

886 887
extern int __weak arch_sd_sibiling_asym_packing(void);

888 889
/*
 * Optimise SD flags for power savings:
L
Lucas De Marchi 已提交
890
 * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings.
891 892 893 894 895 896 897 898 899 900
 * 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
struct sched_group_power {
903
	atomic_t ref;
L
Linus Torvalds 已提交
904 905
	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
906
	 * single CPU.
907
	 */
908
	unsigned int power, power_orig;
909
	unsigned long next_update;
910 911 912 913
	/*
	 * Number of busy cpus in this group.
	 */
	atomic_t nr_busy_cpus;
914 915 916 917 918 919
};

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

920
	unsigned int group_weight;
921
	struct sched_group_power *sgp;
922

923 924 925 926 927 928 929 930
	/*
	 * 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)
	 */
	unsigned long cpumask[0];
L
Linus Torvalds 已提交
931 932
};

933 934
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
935
	return to_cpumask(sg->cpumask);
936 937
}

938 939 940 941 942 943 944 945 946
/**
 * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
 * @group: The group whose first cpu is to be returned.
 */
static inline unsigned int group_first_cpu(struct sched_group *group)
{
	return cpumask_first(sched_group_cpus(group));
}

947 948 949 950 951 952 953 954
struct sched_domain_attr {
	int relax_domain_level;
};

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

955 956
extern int sched_domain_level_max;

L
Linus Torvalds 已提交
957 958 959
struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
960
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
961 962 963 964 965 966
	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
967 968 969 970
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
971
	unsigned int forkexec_idx;
P
Peter Zijlstra 已提交
972
	unsigned int smt_gain;
L
Linus Torvalds 已提交
973
	int flags;			/* See SD_* */
974
	int level;
L
Linus Torvalds 已提交
975 976 977 978 979 980

	/* 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
981 982
	u64 last_update;

L
Linus Torvalds 已提交
983 984
#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
985 986 987 988 989 990 991 992
	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
993 994

	/* Active load balancing */
995 996 997
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
998

999
	/* SD_BALANCE_EXEC stats */
1000 1001 1002
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
1003

1004
	/* SD_BALANCE_FORK stats */
1005 1006 1007
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
1008

L
Linus Torvalds 已提交
1009
	/* try_to_wake_up() stats */
1010 1011 1012
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
1013
#endif
1014 1015 1016
#ifdef CONFIG_SCHED_DEBUG
	char *name;
#endif
1017 1018 1019 1020
	union {
		void *private;		/* used during construction */
		struct rcu_head rcu;	/* used during destruction */
	};
1021

1022
	unsigned int span_weight;
1023 1024 1025 1026 1027 1028 1029 1030
	/*
	 * 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)
	 */
	unsigned long span[0];
L
Linus Torvalds 已提交
1031 1032
};

1033 1034
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
1035
	return to_cpumask(sd->span);
1036 1037
}

1038
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
1039
				    struct sched_domain_attr *dattr_new);
P
Paul Jackson 已提交
1040

1041 1042 1043 1044
/* 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);

1045 1046 1047 1048 1049 1050 1051 1052
/* 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
1053

1054 1055 1056
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);

1057 1058
bool cpus_share_cache(int this_cpu, int that_cpu);

1059
#else /* CONFIG_SMP */
L
Linus Torvalds 已提交
1060

1061
struct sched_domain_attr;
1062

1063
static inline void
1064
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
1065 1066
			struct sched_domain_attr *dattr_new)
{
1067
}
1068 1069 1070 1071 1072 1073

static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
	return true;
}

1074
#endif	/* !CONFIG_SMP */
L
Linus Torvalds 已提交
1075

1076

L
Linus Torvalds 已提交
1077 1078 1079
struct io_context;			/* See blkdev.h */


1080
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
1081
extern void prefetch_stack(struct task_struct *t);
1082 1083 1084
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
1085 1086 1087

struct audit_context;		/* See audit.c */
struct mempolicy;
1088
struct pipe_inode_info;
1089
struct uts_namespace;
L
Linus Torvalds 已提交
1090

I
Ingo Molnar 已提交
1091 1092 1093
struct rq;
struct sched_domain;

P
Peter Zijlstra 已提交
1094 1095 1096 1097
/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
P
Peter Zijlstra 已提交
1098
#define WF_FORK		0x02		/* child wakeup after fork */
1099
#define WF_MIGRATED	0x04		/* internal use, task got migrated */
P
Peter Zijlstra 已提交
1100

1101
#define ENQUEUE_WAKEUP		1
1102 1103 1104 1105 1106 1107
#define ENQUEUE_HEAD		2
#ifdef CONFIG_SMP
#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
#else
#define ENQUEUE_WAKING		0
#endif
1108 1109 1110

#define DEQUEUE_SLEEP		1

I
Ingo Molnar 已提交
1111
struct sched_class {
1112
	const struct sched_class *next;
I
Ingo Molnar 已提交
1113

1114 1115
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
1116
	void (*yield_task) (struct rq *rq);
1117
	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
I
Ingo Molnar 已提交
1118

P
Peter Zijlstra 已提交
1119
	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
I
Ingo Molnar 已提交
1120

1121
	struct task_struct * (*pick_next_task) (struct rq *rq);
1122
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
1123

1124
#ifdef CONFIG_SMP
1125
	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
L
Li Zefan 已提交
1126

1127 1128
	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	void (*post_schedule) (struct rq *this_rq);
1129
	void (*task_waking) (struct task_struct *task);
1130
	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
1131

1132
	void (*set_cpus_allowed)(struct task_struct *p,
1133
				 const struct cpumask *newmask);
G
Gregory Haskins 已提交
1134

1135 1136
	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
L
Li Zefan 已提交
1137 1138 1139 1140
#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
1141
	void (*task_fork) (struct task_struct *p);
1142

P
Peter Zijlstra 已提交
1143 1144
	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
1145
	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
P
Peter Zijlstra 已提交
1146
			     int oldprio);
P
Peter Zijlstra 已提交
1147

1148 1149
	unsigned int (*get_rr_interval) (struct rq *rq,
					 struct task_struct *task);
1150

P
Peter Zijlstra 已提交
1151
#ifdef CONFIG_FAIR_GROUP_SCHED
1152
	void (*task_move_group) (struct task_struct *p, int on_rq);
P
Peter Zijlstra 已提交
1153
#endif
I
Ingo Molnar 已提交
1154 1155 1156 1157 1158 1159
};

struct load_weight {
	unsigned long weight, inv_weight;
};

1160
#ifdef CONFIG_SCHEDSTATS
1161
struct sched_statistics {
I
Ingo Molnar 已提交
1162
	u64			wait_start;
1163
	u64			wait_max;
1164 1165
	u64			wait_count;
	u64			wait_sum;
1166 1167
	u64			iowait_count;
	u64			iowait_sum;
1168

I
Ingo Molnar 已提交
1169 1170
	u64			sleep_start;
	u64			sleep_max;
1171 1172 1173
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
1174 1175
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
1176
	u64			slice_max;
1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192

	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;
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210
};
#endif

struct sched_entity {
	struct load_weight	load;		/* for load-balancing */
	struct rb_node		run_node;
	struct list_head	group_node;
	unsigned int		on_rq;

	u64			exec_start;
	u64			sum_exec_runtime;
	u64			vruntime;
	u64			prev_sum_exec_runtime;

	u64			nr_migrations;

#ifdef CONFIG_SCHEDSTATS
	struct sched_statistics statistics;
1211 1212
#endif

I
Ingo Molnar 已提交
1213 1214 1215 1216 1217 1218 1219 1220
#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
};
1221

P
Peter Zijlstra 已提交
1222 1223
struct sched_rt_entity {
	struct list_head run_list;
1224
	unsigned long timeout;
1225
	unsigned int time_slice;
P
Peter Zijlstra 已提交
1226 1227
	int nr_cpus_allowed;

1228
	struct sched_rt_entity *back;
1229
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
1230 1231 1232 1233 1234 1235
	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
1236 1237
};

1238 1239 1240 1241 1242 1243
/*
 * default timeslice is 100 msecs (used only for SCHED_RR tasks).
 * Timeslices get refilled after they expire.
 */
#define RR_TIMESLICE		(100 * HZ / 1000)

1244 1245
struct rcu_node;

P
Peter Zijlstra 已提交
1246 1247 1248
enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
1249
	perf_sw_context,
P
Peter Zijlstra 已提交
1250 1251 1252
	perf_nr_task_contexts,
};

L
Linus Torvalds 已提交
1253 1254
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
1255
	void *stack;
L
Linus Torvalds 已提交
1256
	atomic_t usage;
1257 1258
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
1259

1260
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
1261
	struct llist_node wake_entry;
P
Peter Zijlstra 已提交
1262
	int on_cpu;
1263
#endif
P
Peter Zijlstra 已提交
1264
	int on_rq;
1265

1266
	int prio, static_prio, normal_prio;
1267
	unsigned int rt_priority;
1268
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
1269
	struct sched_entity se;
P
Peter Zijlstra 已提交
1270
	struct sched_rt_entity rt;
L
Linus Torvalds 已提交
1271

1272 1273 1274 1275 1276
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

1277 1278 1279 1280 1281 1282 1283 1284 1285
	/*
	 * 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;
1286
#ifdef CONFIG_BLK_DEV_IO_TRACE
1287
	unsigned int btrace_seq;
1288
#endif
L
Linus Torvalds 已提交
1289

1290
	unsigned int policy;
L
Linus Torvalds 已提交
1291 1292
	cpumask_t cpus_allowed;

P
Paul E. McKenney 已提交
1293
#ifdef CONFIG_PREEMPT_RCU
P
Paul E. McKenney 已提交
1294
	int rcu_read_lock_nesting;
1295 1296
	char rcu_read_unlock_special;
	struct list_head rcu_node_entry;
P
Paul E. McKenney 已提交
1297 1298 1299
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
	struct rcu_node *rcu_blocked_node;
1300
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
1301 1302 1303
#ifdef CONFIG_RCU_BOOST
	struct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */
P
Paul E. McKenney 已提交
1304

1305
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
1306 1307 1308 1309
	struct sched_info sched_info;
#endif

	struct list_head tasks;
1310
#ifdef CONFIG_SMP
1311
	struct plist_node pushable_tasks;
1312
#endif
L
Linus Torvalds 已提交
1313 1314

	struct mm_struct *mm, *active_mm;
1315 1316 1317
#ifdef CONFIG_COMPAT_BRK
	unsigned brk_randomized:1;
#endif
1318 1319 1320
#if defined(SPLIT_RSS_COUNTING)
	struct task_rss_stat	rss_stat;
#endif
L
Linus Torvalds 已提交
1321
/* task state */
1322
	int exit_state;
L
Linus Torvalds 已提交
1323 1324
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
1325
	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
L
Linus Torvalds 已提交
1326
	/* ??? */
1327
	unsigned int personality;
L
Linus Torvalds 已提交
1328
	unsigned did_exec:1;
1329 1330
	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
				 * execve */
1331 1332
	unsigned in_iowait:1;

1333 1334 1335

	/* Revert to default priority/policy when forking */
	unsigned sched_reset_on_fork:1;
1336
	unsigned sched_contributes_to_load:1;
1337

L
Linus Torvalds 已提交
1338 1339
	pid_t pid;
	pid_t tgid;
1340

1341
#ifdef CONFIG_CC_STACKPROTECTOR
1342 1343
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
1344
#endif
1345

L
Linus Torvalds 已提交
1346 1347 1348
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
R
Roland McGrath 已提交
1349
	 * p->real_parent->pid)
L
Linus Torvalds 已提交
1350
	 */
1351 1352
	struct task_struct __rcu *real_parent; /* real parent process */
	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
L
Linus Torvalds 已提交
1353
	/*
R
Roland McGrath 已提交
1354
	 * children/sibling forms the list of my natural children
L
Linus Torvalds 已提交
1355 1356 1357 1358 1359
	 */
	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
1360 1361 1362 1363 1364 1365 1366 1367
	/*
	 * 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;

L
Linus Torvalds 已提交
1368
	/* PID/PID hash table linkage. */
1369
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
1370
	struct list_head thread_group;
L
Linus Torvalds 已提交
1371 1372 1373 1374 1375

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

1376
	cputime_t utime, stime, utimescaled, stimescaled;
1377
	cputime_t gtime;
1378
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
1379
	cputime_t prev_utime, prev_stime;
1380
#endif
L
Linus Torvalds 已提交
1381
	unsigned long nvcsw, nivcsw; /* context switch counts */
1382 1383
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
1384 1385 1386
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

1387
	struct task_cputime cputime_expires;
L
Linus Torvalds 已提交
1388 1389 1390
	struct list_head cpu_timers[3];

/* process credentials */
A
Arnd Bergmann 已提交
1391
	const struct cred __rcu *real_cred; /* objective and real subjective task
1392
					 * credentials (COW) */
A
Arnd Bergmann 已提交
1393
	const struct cred __rcu *cred;	/* effective (overridable) subjective task
1394
					 * credentials (COW) */
1395
	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
1396

1397 1398 1399
	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
1400
				     - initialized normally by setup_new_exec */
L
Linus Torvalds 已提交
1401 1402
/* file system info */
	int link_count, total_link_count;
1403
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1404 1405
/* ipc stuff */
	struct sysv_sem sysvsem;
1406
#endif
1407
#ifdef CONFIG_DETECT_HUNG_TASK
1408 1409 1410
/* hung task detection */
	unsigned long last_switch_count;
#endif
L
Linus Torvalds 已提交
1411 1412 1413 1414 1415 1416
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1417
/* namespaces */
S
Serge E. Hallyn 已提交
1418
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1419 1420 1421 1422 1423
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1424
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
L
Linus Torvalds 已提交
1425 1426 1427 1428 1429 1430 1431 1432
	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
1433 1434
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
1435
	unsigned int sessionid;
A
Al Viro 已提交
1436
#endif
L
Linus Torvalds 已提交
1437 1438 1439 1440 1441
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
1442 1443
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
L
Linus Torvalds 已提交
1444 1445
	spinlock_t alloc_lock;

1446 1447 1448 1449 1450
#ifdef CONFIG_GENERIC_HARDIRQS
	/* IRQ handler threads */
	struct irqaction *irqaction;
#endif

1451
	/* Protection of the PI data structures: */
1452
	raw_spinlock_t pi_lock;
1453

I
Ingo Molnar 已提交
1454 1455 1456 1457 1458 1459 1460
#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

1461 1462 1463 1464
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1465 1466 1467 1468
#ifdef CONFIG_TRACE_IRQFLAGS
	unsigned int irq_events;
	unsigned long hardirq_enable_ip;
	unsigned long hardirq_disable_ip;
1469
	unsigned int hardirq_enable_event;
1470
	unsigned int hardirq_disable_event;
1471 1472
	int hardirqs_enabled;
	int hardirq_context;
1473 1474
	unsigned long softirq_disable_ip;
	unsigned long softirq_enable_ip;
1475
	unsigned int softirq_disable_event;
1476
	unsigned int softirq_enable_event;
1477
	int softirqs_enabled;
1478 1479
	int softirq_context;
#endif
I
Ingo Molnar 已提交
1480
#ifdef CONFIG_LOCKDEP
1481
# define MAX_LOCK_DEPTH 48UL
I
Ingo Molnar 已提交
1482 1483 1484
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
1485
	struct held_lock held_locks[MAX_LOCK_DEPTH];
1486
	gfp_t lockdep_reclaim_gfp;
I
Ingo Molnar 已提交
1487
#endif
1488

L
Linus Torvalds 已提交
1489 1490 1491
/* journalling filesystem info */
	void *journal_info;

1492
/* stacked block device info */
1493
	struct bio_list *bio_list;
1494

1495 1496 1497 1498 1499
#ifdef CONFIG_BLOCK
/* stack plugging */
	struct blk_plug *plug;
#endif

L
Linus Torvalds 已提交
1500 1501 1502 1503 1504 1505 1506 1507 1508
/* 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.  */
1509
	struct task_io_accounting ioac;
1510
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1511 1512
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
1513
	cputime_t acct_timexpd;	/* stime + utime since last update */
L
Linus Torvalds 已提交
1514 1515
#endif
#ifdef CONFIG_CPUSETS
1516
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
1517
	int mems_allowed_change_disable;
1518
	int cpuset_mem_spread_rotor;
1519
	int cpuset_slab_spread_rotor;
L
Linus Torvalds 已提交
1520
#endif
1521
#ifdef CONFIG_CGROUPS
1522
	/* Control Group info protected by css_set_lock */
A
Arnd Bergmann 已提交
1523
	struct css_set __rcu *cgroups;
1524 1525
	/* cg_list protected by css_set_lock and tsk->alloc_lock */
	struct list_head cg_list;
1526
#endif
1527
#ifdef CONFIG_FUTEX
1528
	struct robust_list_head __user *robust_list;
1529 1530 1531
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1532 1533
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1534
#endif
1535
#ifdef CONFIG_PERF_EVENTS
P
Peter Zijlstra 已提交
1536
	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
1537 1538
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
1539
#endif
1540
#ifdef CONFIG_NUMA
1541
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
1542
	short il_next;
1543
	short pref_node_fork;
1544
#endif
I
Ingo Molnar 已提交
1545
	struct rcu_head rcu;
1546 1547 1548 1549 1550

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1551 1552
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1553 1554 1555
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1556
#endif
1557 1558 1559 1560 1561 1562
	/*
	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for some dirty throttling pause
	 */
	int nr_dirtied;
	int nr_dirtied_pause;
1563
	unsigned long dirty_paused_when; /* start of a write-and-pause period */
1564

A
Arjan van de Ven 已提交
1565 1566 1567 1568
#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
1569 1570 1571 1572 1573 1574
	/*
	 * 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;
1575 1576

	struct list_head	*scm_work_list;
1577
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
D
Daniel Mack 已提交
1578
	/* Index of current stored address in ret_stack */
1579 1580 1581
	int curr_ret_stack;
	/* Stack of return addresses for return function tracing */
	struct ftrace_ret_stack	*ret_stack;
1582 1583
	/* time stamp for last schedule */
	unsigned long long ftrace_timestamp;
1584 1585 1586 1587 1588
	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun.
	 */
	atomic_t trace_overrun;
1589 1590
	/* Pause for the tracing */
	atomic_t tracing_graph_pause;
1591
#endif
1592 1593 1594
#ifdef CONFIG_TRACING
	/* state flags for use by tracers */
	unsigned long trace;
1595
	/* bitmask and counter of trace recursion */
1596 1597
	unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
1598 1599 1600 1601
#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 */
1602 1603
		unsigned long nr_pages;	/* uncharged usage */
		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
1604 1605
	} memcg_batch;
#endif
1606 1607 1608
#ifdef CONFIG_HAVE_HW_BREAKPOINT
	atomic_t ptrace_bp_refcnt;
#endif
L
Linus Torvalds 已提交
1609 1610
};

1611
/* Future-safe accessor for struct task_struct's cpus_allowed. */
1612
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
1613

1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
/*
 * 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
1640
static inline int rt_task(struct task_struct *p)
1641 1642 1643 1644
{
	return rt_prio(p->prio);
}

A
Alexey Dobriyan 已提交
1645
static inline struct pid *task_pid(struct task_struct *task)
1646 1647 1648 1649
{
	return task->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1650
static inline struct pid *task_tgid(struct task_struct *task)
1651 1652 1653 1654
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

1655 1656 1657 1658 1659
/*
 * 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
1660
static inline struct pid *task_pgrp(struct task_struct *task)
1661 1662 1663 1664
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

A
Alexey Dobriyan 已提交
1665
static inline struct pid *task_session(struct task_struct *task)
1666 1667 1668 1669
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

1670 1671 1672 1673 1674 1675 1676
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
1677 1678
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1679 1680 1681 1682 1683 1684
 * 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
 */
1685 1686
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
			struct pid_namespace *ns);
1687

A
Alexey Dobriyan 已提交
1688
static inline pid_t task_pid_nr(struct task_struct *tsk)
1689 1690 1691 1692
{
	return tsk->pid;
}

1693 1694 1695 1696 1697
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);
}
1698 1699 1700

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
1701
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
1702 1703 1704
}


A
Alexey Dobriyan 已提交
1705
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1706 1707 1708 1709
{
	return tsk->tgid;
}

1710
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1711 1712 1713 1714 1715 1716 1717

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


1718 1719
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1720
{
1721
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
1722 1723 1724 1725
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
1726
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
1727 1728 1729
}


1730 1731
static inline pid_t task_session_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1732
{
1733
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
1734 1735 1736 1737
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
1738
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
1739 1740
}

1741 1742 1743 1744 1745
/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
1746

L
Linus Torvalds 已提交
1747 1748 1749 1750 1751 1752 1753 1754
/**
 * 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
1755
static inline int pid_alive(struct task_struct *p)
L
Linus Torvalds 已提交
1756
{
1757
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1758 1759
}

1760
/**
1761
 * is_global_init - check if a task structure is init
1762 1763 1764
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1765
 */
A
Alexey Dobriyan 已提交
1766
static inline int is_global_init(struct task_struct *tsk)
1767 1768 1769
{
	return tsk->pid == 1;
}
1770 1771 1772 1773

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1774
 */
1775
extern int is_container_init(struct task_struct *tsk);
1776

1777 1778
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1779 1780
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
1781

1782
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1783 1784 1785 1786

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1787
		__put_task_struct(t);
I
Ingo Molnar 已提交
1788
}
L
Linus Torvalds 已提交
1789

1790
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1791
extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1792

L
Linus Torvalds 已提交
1793 1794 1795 1796 1797
/*
 * Per process flags
 */
#define PF_STARTING	0x00000002	/* being created */
#define PF_EXITING	0x00000004	/* getting shut down */
1798
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1799
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
T
Tejun Heo 已提交
1800
#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
L
Linus Torvalds 已提交
1801
#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
1802
#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
L
Linus Torvalds 已提交
1803 1804 1805 1806
#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 */
1807
#define PF_NPROC_EXCEEDED 0x00001000	/* set_user noticed that RLIMIT_NPROC was exceeded */
L
Linus Torvalds 已提交
1808 1809 1810 1811 1812 1813
#define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
#define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
#define PF_FROZEN	0x00010000	/* frozen for system suspend */
#define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
#define PF_KSWAPD	0x00040000	/* I am kswapd */
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
1814
#define PF_KTHREAD	0x00200000	/* I am a kernel thread */
J
Jens Axboe 已提交
1815 1816 1817 1818
#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 */
1819
#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
1820
#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
1821
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1822
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
1823
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
L
Linus Torvalds 已提交
1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849

/*
 * 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)

1850
/*
1851
 * task->jobctl flags
1852
 */
1853
#define JOBCTL_STOP_SIGMASK	0xffff	/* signr of the last group stop */
1854

1855 1856 1857
#define JOBCTL_STOP_DEQUEUED_BIT 16	/* stop signal dequeued */
#define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
#define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
1858
#define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
1859
#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
1860
#define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
T
Tejun Heo 已提交
1861
#define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
1862 1863 1864 1865

#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
1866
#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
1867
#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
1868
#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
T
Tejun Heo 已提交
1869
#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
1870

1871
#define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
1872
#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
1873

1874 1875
extern bool task_set_jobctl_pending(struct task_struct *task,
				    unsigned int mask);
1876
extern void task_clear_jobctl_trapping(struct task_struct *task);
1877 1878
extern void task_clear_jobctl_pending(struct task_struct *task,
				      unsigned int mask);
1879

P
Paul E. McKenney 已提交
1880
#ifdef CONFIG_PREEMPT_RCU
1881 1882

#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
1883 1884
#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */
1885 1886 1887 1888 1889

static inline void rcu_copy_process(struct task_struct *p)
{
	p->rcu_read_lock_nesting = 0;
	p->rcu_read_unlock_special = 0;
P
Paul E. McKenney 已提交
1890
#ifdef CONFIG_TREE_PREEMPT_RCU
1891
	p->rcu_blocked_node = NULL;
1892 1893 1894 1895
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
	p->rcu_boost_mutex = NULL;
#endif /* #ifdef CONFIG_RCU_BOOST */
1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906
	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
1907
#ifdef CONFIG_SMP
1908 1909 1910
extern void do_set_cpus_allowed(struct task_struct *p,
			       const struct cpumask *new_mask);

1911
extern int set_cpus_allowed_ptr(struct task_struct *p,
1912
				const struct cpumask *new_mask);
L
Linus Torvalds 已提交
1913
#else
1914 1915 1916 1917
static inline void do_set_cpus_allowed(struct task_struct *p,
				      const struct cpumask *new_mask)
{
}
1918
static inline int set_cpus_allowed_ptr(struct task_struct *p,
1919
				       const struct cpumask *new_mask)
L
Linus Torvalds 已提交
1920
{
1921
	if (!cpumask_test_cpu(0, new_mask))
L
Linus Torvalds 已提交
1922 1923 1924 1925
		return -EINVAL;
	return 0;
}
#endif
1926 1927

#ifndef CONFIG_CPUMASK_OFFSTACK
1928 1929 1930 1931
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
	return set_cpus_allowed_ptr(p, &new_mask);
}
1932
#endif
L
Linus Torvalds 已提交
1933

1934
/*
1935 1936 1937 1938 1939 1940
 * Do not use outside of architecture code which knows its limitations.
 *
 * sched_clock() has no promise of monotonicity or bounded drift between
 * CPUs, use (which you should not) requires disabling IRQs.
 *
 * Please use one of the three interfaces below.
1941
 */
1942
extern unsigned long long notrace sched_clock(void);
1943 1944 1945 1946 1947 1948 1949
/*
 * See the comment in kernel/sched_clock.c
 */
extern u64 cpu_clock(int cpu);
extern u64 local_clock(void);
extern u64 sched_clock_cpu(int cpu);

1950

1951
extern void sched_clock_init(void);
1952

1953
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
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
1966 1967 1968 1969 1970 1971 1972 1973
/*
 * 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:
 */
extern int sched_clock_stable;

1974 1975 1976 1977 1978
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

1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
 * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
 * The reason for this explicit opt-in is not to have perf penalty with
 * slow sched_clocks.
 */
extern void enable_sched_clock_irqtime(void);
extern void disable_sched_clock_irqtime(void);
#else
static inline void enable_sched_clock_irqtime(void) {}
static inline void disable_sched_clock_irqtime(void) {}
#endif

1992
extern unsigned long long
1993
task_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1994 1995 1996 1997 1998 1999 2000 2001

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

2002 2003
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
2004

L
Linus Torvalds 已提交
2005 2006 2007 2008 2009 2010
#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif

2011 2012 2013 2014 2015 2016
#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

2017
extern unsigned int sysctl_sched_latency;
2018
extern unsigned int sysctl_sched_min_granularity;
2019 2020
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
2021 2022 2023 2024 2025 2026 2027 2028 2029

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;

2030
#ifdef CONFIG_SCHED_DEBUG
2031
extern unsigned int sysctl_sched_migration_cost;
2032
extern unsigned int sysctl_sched_nr_migrate;
2033
extern unsigned int sysctl_sched_time_avg;
2034
extern unsigned int sysctl_timer_migration;
2035
extern unsigned int sysctl_sched_shares_window;
2036

2037
int sched_proc_update_handler(struct ctl_table *table, int write,
2038
		void __user *buffer, size_t *length,
2039
		loff_t *ppos);
2040
#endif
2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051
#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
2052 2053
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
2054

2055
int sched_rt_handler(struct ctl_table *table, int write,
2056
		void __user *buffer, size_t *lenp,
2057 2058
		loff_t *ppos);

2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076
#ifdef CONFIG_SCHED_AUTOGROUP
extern unsigned int sysctl_sched_autogroup_enabled;

extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern void sched_autogroup_fork(struct signal_struct *sig);
extern void sched_autogroup_exit(struct signal_struct *sig);
#ifdef CONFIG_PROC_FS
extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
#endif
#else
static inline void sched_autogroup_create_attach(struct task_struct *p) { }
static inline void sched_autogroup_detach(struct task_struct *p) { }
static inline void sched_autogroup_fork(struct signal_struct *sig) { }
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif

2077 2078 2079 2080
#ifdef CONFIG_CFS_BANDWIDTH
extern unsigned int sysctl_sched_cfs_bandwidth_slice;
#endif

2081
#ifdef CONFIG_RT_MUTEXES
2082 2083 2084
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);
2085
#else
A
Alexey Dobriyan 已提交
2086
static inline int rt_mutex_getprio(struct task_struct *p)
2087 2088 2089
{
	return p->normal_prio;
}
2090
# define rt_mutex_adjust_pi(p)		do { } while (0)
2091 2092
#endif

2093
extern bool yield_to(struct task_struct *p, bool preempt);
2094 2095 2096 2097 2098
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
2099
extern int idle_cpu(int cpu);
2100 2101
extern int sched_setscheduler(struct task_struct *, int,
			      const struct sched_param *);
2102
extern int sched_setscheduler_nocheck(struct task_struct *, int,
2103
				      const struct sched_param *);
2104
extern struct task_struct *idle_task(int cpu);
2105 2106
/**
 * is_idle_task - is the specified task an idle task?
2107
 * @p: the task in question.
2108
 */
2109
static inline bool is_idle_task(const struct task_struct *p)
2110 2111 2112
{
	return p->pid == 0;
}
2113 2114
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
2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142

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;

2143 2144 2145 2146 2147 2148 2149
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
2150 2151
 * find_task_by_vpid():
 *      finds a task by its virtual pid
2152
 *
2153
 * see also find_vpid() etc in include/linux/pid.h
2154 2155
 */

2156 2157 2158
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);
2159

2160
extern void __set_special_pids(struct pid *pid);
L
Linus Torvalds 已提交
2161 2162

/* per-UID process charging. */
2163
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
2164 2165 2166 2167 2168 2169
static inline struct user_struct *get_uid(struct user_struct *u)
{
	atomic_inc(&u->__count);
	return u;
}
extern void free_uid(struct user_struct *);
2170
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
2171 2172 2173

#include <asm/current.h>

T
Torben Hohn 已提交
2174
extern void xtime_update(unsigned long ticks);
L
Linus Torvalds 已提交
2175

2176 2177
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
2178
extern void wake_up_new_task(struct task_struct *tsk);
L
Linus Torvalds 已提交
2179 2180 2181 2182 2183
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
2184
extern void sched_fork(struct task_struct *p);
2185
extern void sched_dead(struct task_struct *p);
L
Linus Torvalds 已提交
2186 2187 2188

extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
2189
extern void __flush_signals(struct task_struct *);
2190
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203
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;
2204
}
L
Linus Torvalds 已提交
2205 2206 2207 2208 2209 2210 2211 2212

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 *);
2213 2214
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);
2215 2216
extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
				const struct cred *, u32);
2217 2218
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
2219
extern int kill_proc_info(int, struct siginfo *, pid_t);
2220
extern __must_check bool do_notify_parent(struct task_struct *, int);
2221
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
L
Linus Torvalds 已提交
2222 2223
extern void force_sig(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
2224
extern int zap_other_threads(struct task_struct *p);
L
Linus Torvalds 已提交
2225 2226
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
2227
extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
2228
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
2229 2230
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

2231 2232 2233 2234 2235
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
2236 2237 2238 2239 2240
/* 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)

2241 2242 2243
/*
 * True if we are on the alternate signal stack.
 */
L
Linus Torvalds 已提交
2244 2245
static inline int on_sig_stack(unsigned long sp)
{
2246 2247 2248 2249 2250 2251 2252
#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
2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266
}

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 */
2267
extern void __mmdrop(struct mm_struct *);
L
Linus Torvalds 已提交
2268 2269
static inline void mmdrop(struct mm_struct * mm)
{
I
Ingo Molnar 已提交
2270
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
2271 2272 2273 2274 2275 2276 2277
		__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);
2278 2279 2280 2281 2282 2283
/*
 * Grab a reference to a task's mm, if it is not already going away
 * and ptrace_may_access with the mode parameter passed to it
 * succeeds.
 */
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
L
Linus Torvalds 已提交
2284 2285
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
2286 2287
/* 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
2288

A
Alexey Dobriyan 已提交
2289 2290
extern int copy_thread(unsigned long, unsigned long, unsigned long,
			struct task_struct *, struct pt_regs *);
L
Linus Torvalds 已提交
2291 2292 2293 2294
extern void flush_thread(void);
extern void exit_thread(void);

extern void exit_files(struct task_struct *);
2295
extern void __cleanup_sighand(struct sighand_struct *);
2296

L
Linus Torvalds 已提交
2297
extern void exit_itimers(struct signal_struct *);
2298
extern void flush_itimer_signals(void);
L
Linus Torvalds 已提交
2299

2300
extern void do_group_exit(int);
L
Linus Torvalds 已提交
2301 2302 2303 2304 2305

extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);

2306 2307 2308
extern int do_execve(const char *,
		     const char __user * const __user *,
		     const char __user * const __user *, struct pt_regs *);
L
Linus Torvalds 已提交
2309
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
2310
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
2311 2312

extern void set_task_comm(struct task_struct *tsk, char *from);
2313
extern char *get_task_comm(char *to, struct task_struct *tsk);
L
Linus Torvalds 已提交
2314 2315

#ifdef CONFIG_SMP
2316
void scheduler_ipi(void);
R
Roland McGrath 已提交
2317
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
L
Linus Torvalds 已提交
2318
#else
2319
static inline void scheduler_ipi(void) { }
R
Roland McGrath 已提交
2320 2321 2322 2323 2324
static inline unsigned long wait_task_inactive(struct task_struct *p,
					       long match_state)
{
	return 1;
}
L
Linus Torvalds 已提交
2325 2326
#endif

2327 2328
#define next_task(p) \
	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
L
Linus Torvalds 已提交
2329 2330 2331 2332

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

2333
extern bool current_is_single_threaded(void);
D
David Howells 已提交
2334

L
Linus Torvalds 已提交
2335 2336 2337 2338 2339 2340 2341 2342 2343 2344
/*
 * 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)

2345 2346
static inline int get_nr_threads(struct task_struct *tsk)
{
2347
	return tsk->signal->nr_threads;
2348 2349
}

2350 2351 2352 2353
static inline bool thread_group_leader(struct task_struct *p)
{
	return p->exit_signal >= 0;
}
L
Linus Torvalds 已提交
2354

2355 2356 2357 2358 2359 2360
/* 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
2361
static inline int has_group_leader_pid(struct task_struct *p)
2362 2363 2364 2365
{
	return p->pid == p->tgid;
}

2366 2367 2368 2369 2370 2371
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
	return p1->tgid == p2->tgid;
}

2372
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
2373
{
2374 2375
	return list_entry_rcu(p->thread_group.next,
			      struct task_struct, thread_group);
O
Oleg Nesterov 已提交
2376 2377
}

A
Alexey Dobriyan 已提交
2378
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
2379
{
O
Oleg Nesterov 已提交
2380
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
2381 2382 2383 2384 2385 2386
}

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

/*
2387
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
2388
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
2389 2390
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405
 *
 * 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);
}

2406
extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
2407 2408
							unsigned long *flags);

2409 2410 2411 2412 2413 2414 2415 2416 2417
static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
						       unsigned long *flags)
{
	struct sighand_struct *ret;

	ret = __lock_task_sighand(tsk, flags);
	(void)__cond_lock(&tsk->sighand->siglock, ret);
	return ret;
}
2418

2419 2420 2421 2422 2423 2424
static inline void unlock_task_sighand(struct task_struct *tsk,
						unsigned long *flags)
{
	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}

2425
#ifdef CONFIG_CGROUPS
2426
static inline void threadgroup_change_begin(struct task_struct *tsk)
2427
{
2428
	down_read(&tsk->signal->group_rwsem);
2429
}
2430
static inline void threadgroup_change_end(struct task_struct *tsk)
2431
{
2432
	up_read(&tsk->signal->group_rwsem);
2433
}
2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454

/**
 * threadgroup_lock - lock threadgroup
 * @tsk: member task of the threadgroup to lock
 *
 * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
 * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
 * perform exec.  This is useful for cases where the threadgroup needs to
 * stay stable across blockable operations.
 *
 * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
 * synchronization.  While held, no new task will be added to threadgroup
 * and no existing live task will have its PF_EXITING set.
 *
 * During exec, a task goes and puts its thread group through unusual
 * changes.  After de-threading, exclusive access is assumed to resources
 * which are usually shared by tasks in the same group - e.g. sighand may
 * be replaced with a new one.  Also, the exec'ing task takes over group
 * leader role including its pid.  Exclude these changes while locked by
 * grabbing cred_guard_mutex which is used to synchronize exec path.
 */
2455
static inline void threadgroup_lock(struct task_struct *tsk)
2456
{
2457 2458 2459 2460 2461
	/*
	 * exec uses exit for de-threading nesting group_rwsem inside
	 * cred_guard_mutex. Grab cred_guard_mutex first.
	 */
	mutex_lock(&tsk->signal->cred_guard_mutex);
2462
	down_write(&tsk->signal->group_rwsem);
2463
}
2464 2465 2466 2467 2468 2469 2470

/**
 * threadgroup_unlock - unlock threadgroup
 * @tsk: member task of the threadgroup to unlock
 *
 * Reverse threadgroup_lock().
 */
2471
static inline void threadgroup_unlock(struct task_struct *tsk)
2472
{
2473
	up_write(&tsk->signal->group_rwsem);
2474
	mutex_unlock(&tsk->signal->cred_guard_mutex);
2475 2476
}
#else
2477 2478 2479 2480
static inline void threadgroup_change_begin(struct task_struct *tsk) {}
static inline void threadgroup_change_end(struct task_struct *tsk) {}
static inline void threadgroup_lock(struct task_struct *tsk) {}
static inline void threadgroup_unlock(struct task_struct *tsk) {}
2481 2482
#endif

A
Al Viro 已提交
2483 2484
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
2485 2486
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
2487

2488 2489 2490 2491 2492 2493 2494 2495
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
2496
	return (unsigned long *)(task_thread_info(p) + 1);
2497 2498
}

A
Al Viro 已提交
2499 2500
#endif

2501 2502 2503 2504 2505 2506 2507
static inline int object_is_on_stack(void *obj)
{
	void *stack = task_stack_page(current);

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

2508 2509
extern void thread_info_cache_init(void);

2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522
#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
2523 2524 2525 2526 2527
/* 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
2528
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2529 2530 2531 2532
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2533
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2534 2535 2536 2537
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2538
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2539 2540 2541 2542
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2543
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2544 2545 2546 2547
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2548
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560
}

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);
}

2561 2562 2563 2564 2565
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

2566 2567 2568 2569 2570 2571
static inline int restart_syscall(void)
{
	set_tsk_thread_flag(current, TIF_SIGPENDING);
	return -ERESTARTNOINTR;
}

L
Linus Torvalds 已提交
2572 2573 2574 2575
static inline int signal_pending(struct task_struct *p)
{
	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
M
Matthew Wilcox 已提交
2576

2577 2578 2579 2580
static inline int __fatal_signal_pending(struct task_struct *p)
{
	return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
M
Matthew Wilcox 已提交
2581 2582 2583 2584 2585 2586

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

2587 2588 2589 2590 2591 2592 2593 2594 2595 2596
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
2597 2598
static inline int need_resched(void)
{
2599
	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
L
Linus Torvalds 已提交
2600 2601 2602 2603 2604 2605 2606 2607 2608
}

/*
 * 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.
 */
2609
extern int _cond_resched(void);
2610

2611 2612 2613 2614
#define cond_resched() ({			\
	__might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})
2615

2616 2617
extern int __cond_resched_lock(spinlock_t *lock);

2618
#ifdef CONFIG_PREEMPT_COUNT
2619
#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
2620
#else
2621
#define PREEMPT_LOCK_OFFSET	0
2622
#endif
2623

2624
#define cond_resched_lock(lock) ({				\
2625
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
2626 2627 2628 2629 2630
	__cond_resched_lock(lock);				\
})

extern int __cond_resched_softirq(void);

2631 2632 2633
#define cond_resched_softirq() ({					\
	__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
	__cond_resched_softirq();					\
2634
})
L
Linus Torvalds 已提交
2635 2636 2637

/*
 * Does a critical section need to be broken due to another
N
Nick Piggin 已提交
2638 2639
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
2640
 */
N
Nick Piggin 已提交
2641
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
2642
{
N
Nick Piggin 已提交
2643 2644 2645
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
2646
	return 0;
N
Nick Piggin 已提交
2647
#endif
L
Linus Torvalds 已提交
2648 2649
}

2650 2651 2652
/*
 * Thread group CPU time accounting.
 */
2653
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
2654
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
2655

2656
static inline void thread_group_cputime_init(struct signal_struct *sig)
2657
{
2658
	raw_spin_lock_init(&sig->cputimer.lock);
2659 2660
}

R
Roland McGrath 已提交
2661 2662 2663 2664 2665 2666 2667
/*
 * 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
2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678
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
2679
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
2680 2681
}

I
Ingo Molnar 已提交
2682
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696

#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 */

2697 2698
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
2699

L
Linus Torvalds 已提交
2700 2701
extern void normalize_rt_tasks(void);

D
Dhaval Giani 已提交
2702
#ifdef CONFIG_CGROUP_SCHED
2703

2704
extern struct task_group root_task_group;
2705

2706
extern struct task_group *sched_create_group(struct task_group *parent);
2707
extern void sched_destroy_group(struct task_group *tg);
2708
extern void sched_move_task(struct task_struct *tsk);
2709
#ifdef CONFIG_FAIR_GROUP_SCHED
2710
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
2711
extern unsigned long sched_group_shares(struct task_group *tg);
2712 2713
#endif
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
2714 2715 2716
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);
2717 2718 2719
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);
2720
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
2721
#endif
2722 2723
#endif

2724 2725 2726
extern int task_can_switch_user(struct user_struct *up,
					struct task_struct *tsk);

2727 2728 2729
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
2730
	tsk->ioac.rchar += amt;
2731 2732 2733 2734
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
2735
	tsk->ioac.wchar += amt;
2736 2737 2738 2739
}

static inline void inc_syscr(struct task_struct *tsk)
{
2740
	tsk->ioac.syscr++;
2741 2742 2743 2744
}

static inline void inc_syscw(struct task_struct *tsk)
{
2745
	tsk->ioac.syscw++;
2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764
}
#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
2765 2766 2767 2768
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781
#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 */

2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803
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
2804 2805 2806
#endif /* __KERNEL__ */

#endif