sched.h 75.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 * 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>
93 94

#include <asm/processor.h>
H
H. J. Lu 已提交
95

L
Linus Torvalds 已提交
96
struct exec_domain;
97
struct futex_pi_state;
98
struct robust_list_head;
99
struct bio_list;
100
struct fs_struct;
101
struct perf_event_context;
102
struct blk_plug;
L
Linus Torvalds 已提交
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120

/*
 * 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 */
121
extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
L
Linus Torvalds 已提交
122 123 124

#define FSHIFT		11		/* nr of bits of precision */
#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
125
#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
L
Linus Torvalds 已提交
126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141
#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);
142
extern unsigned long nr_iowait_cpu(int cpu);
143 144 145
extern unsigned long this_cpu_load(void);


146
extern void calc_global_load(unsigned long ticks);
L
Linus Torvalds 已提交
147

148 149
extern unsigned long get_parent_ip(unsigned long addr);

I
Ingo Molnar 已提交
150 151
struct seq_file;
struct cfs_rq;
152
struct task_group;
I
Ingo Molnar 已提交
153 154 155 156
#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
157
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
I
Ingo Molnar 已提交
158 159 160 161 162 163 164 165 166
#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
167
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
I
Ingo Molnar 已提交
168 169 170
{
}
#endif
L
Linus Torvalds 已提交
171

172 173 174 175 176 177 178 179 180 181
/*
 * 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
182 183 184
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
M
Matthew Wilcox 已提交
185 186
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
187 188 189 190
/* in tsk->exit_state */
#define EXIT_ZOMBIE		16
#define EXIT_DEAD		32
/* in tsk->state again */
191
#define TASK_DEAD		64
M
Matthew Wilcox 已提交
192
#define TASK_WAKEKILL		128
P
Peter Zijlstra 已提交
193
#define TASK_WAKING		256
194
#define TASK_STATE_MAX		512
M
Matthew Wilcox 已提交
195

196
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
197

198 199
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
200 201 202 203 204

/* 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
205

206 207
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
M
Matthew Wilcox 已提交
208
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
209 210 211

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
M
Matthew Wilcox 已提交
212 213
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED)
214

M
Matthew Wilcox 已提交
215 216
#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
217
#define task_is_dead(task)	((task)->exit_state != 0)
218
#define task_is_stopped_or_traced(task)	\
M
Matthew Wilcox 已提交
219
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
220
#define task_contributes_to_load(task)	\
221
				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
222
				 (task->flags & PF_FREEZING) == 0)
L
Linus Torvalds 已提交
223 224 225 226 227 228

#define __set_task_state(tsk, state_value)		\
	do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value)		\
	set_mb((tsk)->state, (state_value))

229 230 231 232 233 234 235 236 237 238 239
/*
 * set_current_state() includes a barrier so that the write of current->state
 * is correctly serialised wrt the caller's subsequent test of whether to
 * actually sleep:
 *
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (do_i_need_to_sleep())
 *		schedule();
 *
 * If the caller does not need such serialisation then use __set_current_state()
 */
L
Linus Torvalds 已提交
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
#define __set_current_state(state_value)			\
	do { current->state = (state_value); } while (0)
#define set_current_state(state_value)		\
	set_mb(current->state, (state_value))

/* Task command name length */
#define TASK_COMM_LEN 16

#include <linux/spinlock.h>

/*
 * This serializes "schedule()" and also protects
 * the run-queue from deletions/modifications (but
 * _adding_ to the beginning of the run-queue has
 * a separate lock).
 */
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;

259
struct task_struct;
L
Linus Torvalds 已提交
260

261 262 263 264
#ifdef CONFIG_PROVE_RCU
extern int lockdep_tasklist_lock_is_held(void);
#endif /* #ifdef CONFIG_PROVE_RCU */

L
Linus Torvalds 已提交
265 266
extern void sched_init(void);
extern void sched_init_smp(void);
267
extern asmlinkage void schedule_tail(struct task_struct *prev);
268
extern void init_idle(struct task_struct *idle, int cpu);
I
Ingo Molnar 已提交
269
extern void init_idle_bootup_task(struct task_struct *idle);
L
Linus Torvalds 已提交
270

271
extern int runqueue_is_locked(int cpu);
I
Ingo Molnar 已提交
272

273
extern cpumask_var_t nohz_cpu_mask;
274
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
275 276
extern void select_nohz_load_balancer(int stop_tick);
extern int get_nohz_timer_target(void);
277
#else
278
static inline void select_nohz_load_balancer(int stop_tick) { }
279
#endif
L
Linus Torvalds 已提交
280

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

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

L
Linus Torvalds 已提交
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
extern void show_regs(struct pt_regs *);

/*
 * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
 * task), SP is the stack pointer of the first frame that should be shown in the back
 * trace (or NULL if the entire call-chain of the task should be shown).
 */
extern void show_stack(struct task_struct *task, unsigned long *sp);

void io_schedule(void);
long io_schedule_timeout(long timeout);

extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);

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

310
#ifdef CONFIG_LOCKUP_DETECTOR
I
Ingo Molnar 已提交
311
extern void touch_softlockup_watchdog(void);
312
extern void touch_softlockup_watchdog_sync(void);
313
extern void touch_all_softlockup_watchdogs(void);
314 315 316
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
317
extern unsigned int  softlockup_panic;
318
extern int softlockup_thresh;
319
void lockup_detector_init(void);
I
Ingo Molnar 已提交
320 321 322 323
#else
static inline void touch_softlockup_watchdog(void)
{
}
324 325 326
static inline void touch_softlockup_watchdog_sync(void)
{
}
327 328 329
static inline void touch_all_softlockup_watchdogs(void)
{
}
330 331 332
static inline void lockup_detector_init(void)
{
}
I
Ingo Molnar 已提交
333 334
#endif

335 336 337 338 339 340
#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,
341
					 void __user *buffer,
342
					 size_t *lenp, loff_t *ppos);
343 344 345
#else
/* Avoid need for ifdefs elsewhere in the code */
enum { sysctl_hung_task_timeout_secs = 0 };
346
#endif
I
Ingo Molnar 已提交
347

L
Linus Torvalds 已提交
348 349
/* Attach to any functions which should be ignored in wchan output. */
#define __sched		__attribute__((__section__(".sched.text")))
350 351 352 353

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

L
Linus Torvalds 已提交
354 355 356 357
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
358
extern signed long schedule_timeout(signed long timeout);
359
extern signed long schedule_timeout_interruptible(signed long timeout);
M
Matthew Wilcox 已提交
360
extern signed long schedule_timeout_killable(signed long timeout);
361
extern signed long schedule_timeout_uninterruptible(signed long timeout);
L
Linus Torvalds 已提交
362
asmlinkage void schedule(void);
363
extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
L
Linus Torvalds 已提交
364

S
Serge E. Hallyn 已提交
365
struct nsproxy;
366
struct user_namespace;
L
Linus Torvalds 已提交
367

368 369 370 371 372 373 374 375 376 377 378 379 380
/*
 * 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)
381
#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
L
Linus Torvalds 已提交
382 383 384 385 386

extern int sysctl_max_map_count;

#include <linux/aio.h>

387 388
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
L
Linus Torvalds 已提交
389 390 391 392 393 394 395
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);
396 397
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
398 399 400
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
L
Linus Torvalds 已提交
401

402

403 404 405 406
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);

/* mm flags */
407
/* dumpable bits */
408 409
#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
410

411
#define MMF_DUMPABLE_BITS 2
H
Hugh Dickins 已提交
412
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
413 414 415 416 417 418

/* 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
419
#define MMF_DUMP_ELF_HEADERS	6
420 421
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED  8
H
Hugh Dickins 已提交
422

423
#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
424
#define MMF_DUMP_FILTER_BITS	7
425 426 427
#define MMF_DUMP_FILTER_MASK \
	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
428
	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
429 430 431 432 433 434 435
	 (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
436 437
					/* leave room for more dump flags */
#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
A
Andrea Arcangeli 已提交
438
#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
H
Hugh Dickins 已提交
439 440

#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
441

L
Linus Torvalds 已提交
442 443 444 445
struct sighand_struct {
	atomic_t		count;
	struct k_sigaction	action[_NSIG];
	spinlock_t		siglock;
D
Davide Libenzi 已提交
446
	wait_queue_head_t	signalfd_wqh;
L
Linus Torvalds 已提交
447 448
};

449
struct pacct_struct {
450 451
	int			ac_flag;
	long			ac_exitcode;
452
	unsigned long		ac_mem;
453 454
	cputime_t		ac_utime, ac_stime;
	unsigned long		ac_minflt, ac_majflt;
455 456
};

457 458 459
struct cpu_itimer {
	cputime_t expires;
	cputime_t incr;
460 461
	u32 error;
	u32 incr_error;
462 463
};

464 465 466 467 468
/**
 * 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
469
 *
470 471 472 473 474 475 476 477 478 479 480 481 482 483 484
 * 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

485 486 487 488 489 490 491
#define INIT_CPUTIME	\
	(struct task_cputime) {					\
		.utime = cputime_zero,				\
		.stime = cputime_zero,				\
		.sum_exec_runtime = 0,				\
	}

P
Peter Zijlstra 已提交
492 493 494
/*
 * Disable preemption until the scheduler is running.
 * Reset by start_kernel()->sched_init()->init_idle().
P
Peter Zijlstra 已提交
495 496 497
 *
 * We include PREEMPT_ACTIVE to avoid cond_resched() from working
 * before the scheduler is active -- see should_resched().
P
Peter Zijlstra 已提交
498
 */
P
Peter Zijlstra 已提交
499
#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
P
Peter Zijlstra 已提交
500

501
/**
502 503 504 505 506
 * 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.
507 508
 *
 * This structure contains the version of task_cputime, above, that is
509
 * used for thread group CPU timer calculations.
510
 */
511 512 513 514
struct thread_group_cputimer {
	struct task_cputime cputime;
	int running;
	spinlock_t lock;
515 516
};

517 518
struct autogroup;

L
Linus Torvalds 已提交
519
/*
520
 * NOTE! "signal_struct" does not have its own
L
Linus Torvalds 已提交
521 522 523 524 525 526
 * 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 {
527
	atomic_t		sigcnt;
L
Linus Torvalds 已提交
528
	atomic_t		live;
529
	int			nr_threads;
L
Linus Torvalds 已提交
530 531 532 533

	wait_queue_head_t	wait_chldexit;	/* for wait4() */

	/* current thread group signal load-balancing target: */
534
	struct task_struct	*curr_target;
L
Linus Torvalds 已提交
535 536 537 538 539 540 541 542 543 544 545 546

	/* 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;
547
	struct task_struct	*group_exit_task;
L
Linus Torvalds 已提交
548 549 550 551 552 553 554 555 556

	/* 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 */
557
	struct hrtimer real_timer;
558
	struct pid *leader_pid;
559
	ktime_t it_real_incr;
L
Linus Torvalds 已提交
560

561 562 563 564 565 566
	/*
	 * 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
567

568
	/*
569 570
	 * Thread group totals for process CPU timers.
	 * See thread_group_cputimer(), et al, for details.
571
	 */
572
	struct thread_group_cputimer cputimer;
573 574 575 576 577 578

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

	struct list_head cpu_timers[3];

579
	struct pid *tty_old_pgrp;
580

L
Linus Torvalds 已提交
581 582 583 584 585
	/* boolean value for session group leader */
	int leader;

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

586 587 588
#ifdef CONFIG_SCHED_AUTOGROUP
	struct autogroup *autogroup;
#endif
L
Linus Torvalds 已提交
589 590 591 592 593 594
	/*
	 * 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.
	 */
595
	cputime_t utime, stime, cutime, cstime;
596 597
	cputime_t gtime;
	cputime_t cgtime;
598 599 600
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
	cputime_t prev_utime, prev_stime;
#endif
L
Linus Torvalds 已提交
601 602
	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
603
	unsigned long inblock, oublock, cinblock, coublock;
J
Jiri Pirko 已提交
604
	unsigned long maxrss, cmaxrss;
605
	struct task_io_accounting ioac;
L
Linus Torvalds 已提交
606

607 608 609 610 611 612 613 614
	/*
	 * 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
615 616 617 618 619 620 621 622 623 624 625
	/*
	 * 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];

626 627 628
#ifdef CONFIG_BSD_PROCESS_ACCT
	struct pacct_struct pacct;	/* per-process accounting information */
#endif
629 630 631
#ifdef CONFIG_TASKSTATS
	struct taskstats *stats;
#endif
M
Miloslav Trmac 已提交
632 633 634 635
#ifdef CONFIG_AUDIT
	unsigned audit_tty;
	struct tty_audit_buf *tty_audit_buf;
#endif
636

D
David Rientjes 已提交
637 638
	int oom_adj;		/* OOM kill score adjustment (bit shift) */
	int oom_score_adj;	/* OOM kill score adjustment */
639 640
	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
				 * Only settable by CAP_SYS_RESOURCE. */
641 642 643 644

	struct mutex cred_guard_mutex;	/* guard against foreign influences on
					 * credential calculations
					 * (notably. ptrace) */
L
Linus Torvalds 已提交
645 646
};

647 648 649 650 651
/* 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
652 653 654 655 656 657 658
/*
 * Bits in flags field of signal_struct.
 */
#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_DEQUEUED	0x00000002 /* stop signal dequeued */
#define SIGNAL_STOP_CONTINUED	0x00000004 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT	0x00000008 /* group exit in progress */
659 660 661 662 663 664
/*
 * 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
665

666 667
#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */

668 669 670 671 672 673 674
/* 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
675 676 677 678 679 680 681 682
/*
 * 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? */
683
#ifdef CONFIG_INOTIFY_USER
R
Robert Love 已提交
684 685 686
	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
687 688 689
#ifdef CONFIG_FANOTIFY
	atomic_t fanotify_listeners;
#endif
690
#ifdef CONFIG_EPOLL
691
	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
692
#endif
A
Alexey Dobriyan 已提交
693
#ifdef CONFIG_POSIX_MQUEUE
L
Linus Torvalds 已提交
694 695
	/* protected by mq_lock	*/
	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
A
Alexey Dobriyan 已提交
696
#endif
L
Linus Torvalds 已提交
697 698 699 700 701 702 703 704
	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
705
	struct hlist_node uidhash_node;
L
Linus Torvalds 已提交
706
	uid_t uid;
707
	struct user_namespace *user_ns;
708

709
#ifdef CONFIG_PERF_EVENTS
710 711
	atomic_long_t locked_vm;
#endif
L
Linus Torvalds 已提交
712 713
};

714
extern int uids_sysfs_init(void);
715

L
Linus Torvalds 已提交
716 717 718 719 720
extern struct user_struct *find_user(uid_t);

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

721

L
Linus Torvalds 已提交
722 723 724
struct backing_dev_info;
struct reclaim_state;

725
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
726 727
struct sched_info {
	/* cumulative counters */
728
	unsigned long pcount;	      /* # of times run on this cpu */
729
	unsigned long long run_delay; /* time spent waiting on a runqueue */
L
Linus Torvalds 已提交
730 731

	/* timestamps */
732 733
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
I
Ingo Molnar 已提交
734 735
#ifdef CONFIG_SCHEDSTATS
	/* BKL stats */
736
	unsigned int bkl_count;
I
Ingo Molnar 已提交
737
#endif
L
Linus Torvalds 已提交
738
};
739
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
L
Linus Torvalds 已提交
740

741 742 743 744 745 746 747 748 749 750 751 752 753 754
#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).
	 */
755 756 757 758 759 760 761 762 763 764 765 766 767

	/*
	 * 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 */
768 769 770 771

	struct timespec freepages_start, freepages_end;
	u64 freepages_delay;	/* wait for memory reclaim */
	u32 freepages_count;	/* total count of memory reclaim */
772
};
773 774 775 776 777 778 779 780 781 782 783
#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;
784
#endif
785
}
786

I
Ingo Molnar 已提交
787 788 789 790 791
enum cpu_idle_type {
	CPU_IDLE,
	CPU_NOT_IDLE,
	CPU_NEWLY_IDLE,
	CPU_MAX_IDLE_TYPES
L
Linus Torvalds 已提交
792 793 794 795 796
};

/*
 * sched-domains (multiprocessor balancing) declarations:
 */
797 798 799 800 801 802 803

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

804
#define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
L
Linus Torvalds 已提交
805

806
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
807 808 809 810
#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 */
811
#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
P
Peter Zijlstra 已提交
812
#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
P
Peter Zijlstra 已提交
813
#define SD_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
P
Peter Zijlstra 已提交
814 815 816 817
#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 */
818
#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
P
Peter Zijlstra 已提交
819
#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
820

821 822 823 824 825 826 827 828 829 830
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
};
831

832
extern int sched_mc_power_savings, sched_smt_power_savings;
833

834 835 836 837
static inline int sd_balance_for_mc_power(void)
{
	if (sched_smt_power_savings)
		return SD_POWERSAVINGS_BALANCE;
838

839 840 841 842
	if (!sched_mc_power_savings)
		return SD_PREFER_SIBLING;

	return 0;
843
}
844

845 846 847 848 849
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
850
	return SD_PREFER_SIBLING;
851
}
852

853 854
extern int __weak arch_sd_sibiling_asym_packing(void);

855 856
/*
 * Optimise SD flags for power savings:
L
Lucas De Marchi 已提交
857
 * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings.
858 859 860 861 862 863 864 865 866 867
 * 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
868 869 870 871 872 873

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

	/*
	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
874
	 * single CPU.
875
	 */
876
	unsigned int cpu_power, cpu_power_orig;
877
	unsigned int group_weight;
878

879 880 881 882 883 884 885 886 887 888 889
	/*
	 * The CPUs this group covers.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 *
	 * It is also be embedded into static data structures at build
	 * time. (See 'struct static_sched_group' in kernel/sched.c)
	 */
	unsigned long cpumask[0];
L
Linus Torvalds 已提交
890 891
};

892 893
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
894
	return to_cpumask(sg->cpumask);
895 896
}

897 898 899 900
enum sched_domain_level {
	SD_LV_NONE = 0,
	SD_LV_SIBLING,
	SD_LV_MC,
901
	SD_LV_BOOK,
902 903 904 905 906 907 908 909 910 911 912 913 914 915
	SD_LV_CPU,
	SD_LV_NODE,
	SD_LV_ALLNODES,
	SD_LV_MAX
};

struct sched_domain_attr {
	int relax_domain_level;
};

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

L
Linus Torvalds 已提交
916 917 918
struct sched_domain {
	/* These fields must be setup */
	struct sched_domain *parent;	/* top domain must be null terminated */
919
	struct sched_domain *child;	/* bottom domain must be null terminated */
L
Linus Torvalds 已提交
920 921 922 923 924 925
	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
926 927 928 929
	unsigned int busy_idx;
	unsigned int idle_idx;
	unsigned int newidle_idx;
	unsigned int wake_idx;
N
Nick Piggin 已提交
930
	unsigned int forkexec_idx;
P
Peter Zijlstra 已提交
931
	unsigned int smt_gain;
L
Linus Torvalds 已提交
932
	int flags;			/* See SD_* */
933
	enum sched_domain_level level;
L
Linus Torvalds 已提交
934 935 936 937 938 939

	/* 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
940 941
	u64 last_update;

L
Linus Torvalds 已提交
942 943
#ifdef CONFIG_SCHEDSTATS
	/* load_balance() stats */
944 945 946 947 948 949 950 951
	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
952 953

	/* Active load balancing */
954 955 956
	unsigned int alb_count;
	unsigned int alb_failed;
	unsigned int alb_pushed;
L
Linus Torvalds 已提交
957

958
	/* SD_BALANCE_EXEC stats */
959 960 961
	unsigned int sbe_count;
	unsigned int sbe_balanced;
	unsigned int sbe_pushed;
L
Linus Torvalds 已提交
962

963
	/* SD_BALANCE_FORK stats */
964 965 966
	unsigned int sbf_count;
	unsigned int sbf_balanced;
	unsigned int sbf_pushed;
967

L
Linus Torvalds 已提交
968
	/* try_to_wake_up() stats */
969 970 971
	unsigned int ttwu_wake_remote;
	unsigned int ttwu_move_affine;
	unsigned int ttwu_move_balance;
L
Linus Torvalds 已提交
972
#endif
973 974 975
#ifdef CONFIG_SCHED_DEBUG
	char *name;
#endif
976

977
	unsigned int span_weight;
978 979 980 981 982 983 984 985 986 987 988
	/*
	 * Span of all CPUs in this domain.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 *
	 * It is also be embedded into static data structures at build
	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
	 */
	unsigned long span[0];
L
Linus Torvalds 已提交
989 990
};

991 992
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
993
	return to_cpumask(sd->span);
994 995
}

996
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
997
				    struct sched_domain_attr *dattr_new);
P
Paul Jackson 已提交
998

999 1000 1001 1002
/* 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);

1003 1004 1005 1006 1007 1008 1009 1010
/* 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
1011

1012 1013 1014
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);

1015
#else /* CONFIG_SMP */
L
Linus Torvalds 已提交
1016

1017
struct sched_domain_attr;
1018

1019
static inline void
1020
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
1021 1022
			struct sched_domain_attr *dattr_new)
{
1023
}
1024
#endif	/* !CONFIG_SMP */
L
Linus Torvalds 已提交
1025

1026

L
Linus Torvalds 已提交
1027 1028 1029
struct io_context;			/* See blkdev.h */


1030
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
1031
extern void prefetch_stack(struct task_struct *t);
1032 1033 1034
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
L
Linus Torvalds 已提交
1035 1036 1037

struct audit_context;		/* See audit.c */
struct mempolicy;
1038
struct pipe_inode_info;
1039
struct uts_namespace;
L
Linus Torvalds 已提交
1040

I
Ingo Molnar 已提交
1041 1042 1043
struct rq;
struct sched_domain;

P
Peter Zijlstra 已提交
1044 1045 1046 1047
/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
P
Peter Zijlstra 已提交
1048
#define WF_FORK		0x02		/* child wakeup after fork */
P
Peter Zijlstra 已提交
1049

1050 1051 1052 1053 1054 1055
#define ENQUEUE_WAKEUP		1
#define ENQUEUE_WAKING		2
#define ENQUEUE_HEAD		4

#define DEQUEUE_SLEEP		1

I
Ingo Molnar 已提交
1056
struct sched_class {
1057
	const struct sched_class *next;
I
Ingo Molnar 已提交
1058

1059 1060
	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
1061
	void (*yield_task) (struct rq *rq);
1062
	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
I
Ingo Molnar 已提交
1063

P
Peter Zijlstra 已提交
1064
	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
I
Ingo Molnar 已提交
1065

1066
	struct task_struct * (*pick_next_task) (struct rq *rq);
1067
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
I
Ingo Molnar 已提交
1068

1069
#ifdef CONFIG_SMP
1070 1071
	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
			       int sd_flag, int flags);
L
Li Zefan 已提交
1072

1073 1074
	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	void (*post_schedule) (struct rq *this_rq);
1075 1076
	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
1077

1078
	void (*set_cpus_allowed)(struct task_struct *p,
1079
				 const struct cpumask *newmask);
G
Gregory Haskins 已提交
1080

1081 1082
	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
L
Li Zefan 已提交
1083 1084 1085 1086
#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
1087
	void (*task_fork) (struct task_struct *p);
1088

P
Peter Zijlstra 已提交
1089 1090
	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
1091
	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
P
Peter Zijlstra 已提交
1092
			     int oldprio);
P
Peter Zijlstra 已提交
1093

1094 1095
	unsigned int (*get_rr_interval) (struct rq *rq,
					 struct task_struct *task);
1096

P
Peter Zijlstra 已提交
1097
#ifdef CONFIG_FAIR_GROUP_SCHED
1098
	void (*task_move_group) (struct task_struct *p, int on_rq);
P
Peter Zijlstra 已提交
1099
#endif
I
Ingo Molnar 已提交
1100 1101 1102 1103 1104 1105
};

struct load_weight {
	unsigned long weight, inv_weight;
};

1106
#ifdef CONFIG_SCHEDSTATS
1107
struct sched_statistics {
I
Ingo Molnar 已提交
1108
	u64			wait_start;
1109
	u64			wait_max;
1110 1111
	u64			wait_count;
	u64			wait_sum;
1112 1113
	u64			iowait_count;
	u64			iowait_sum;
1114

I
Ingo Molnar 已提交
1115 1116
	u64			sleep_start;
	u64			sleep_max;
1117 1118 1119
	s64			sum_sleep_runtime;

	u64			block_start;
I
Ingo Molnar 已提交
1120 1121
	u64			block_max;
	u64			exec_max;
I
Ingo Molnar 已提交
1122
	u64			slice_max;
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138

	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;
1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
};
#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;
1157 1158
#endif

I
Ingo Molnar 已提交
1159 1160 1161 1162 1163 1164 1165 1166
#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
};
1167

P
Peter Zijlstra 已提交
1168 1169
struct sched_rt_entity {
	struct list_head run_list;
1170
	unsigned long timeout;
1171
	unsigned int time_slice;
P
Peter Zijlstra 已提交
1172 1173
	int nr_cpus_allowed;

1174
	struct sched_rt_entity *back;
1175
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
1176 1177 1178 1179 1180 1181
	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
1182 1183
};

1184 1185
struct rcu_node;

P
Peter Zijlstra 已提交
1186 1187 1188
enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
1189
	perf_sw_context,
P
Peter Zijlstra 已提交
1190 1191 1192
	perf_nr_task_contexts,
};

L
Linus Torvalds 已提交
1193 1194
struct task_struct {
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
R
Roman Zippel 已提交
1195
	void *stack;
L
Linus Torvalds 已提交
1196
	atomic_t usage;
1197 1198
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;
L
Linus Torvalds 已提交
1199

1200
	int lock_depth;		/* BKL lock depth */
L
Linus Torvalds 已提交
1201

1202
#ifdef CONFIG_SMP
P
Peter Zijlstra 已提交
1203
	int on_cpu;
1204
#endif
1205

1206
	int prio, static_prio, normal_prio;
1207
	unsigned int rt_priority;
1208
	const struct sched_class *sched_class;
I
Ingo Molnar 已提交
1209
	struct sched_entity se;
P
Peter Zijlstra 已提交
1210
	struct sched_rt_entity rt;
L
Linus Torvalds 已提交
1211

1212 1213 1214 1215 1216
#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

1217 1218 1219 1220 1221 1222 1223 1224 1225
	/*
	 * 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;
1226
#ifdef CONFIG_BLK_DEV_IO_TRACE
1227
	unsigned int btrace_seq;
1228
#endif
L
Linus Torvalds 已提交
1229

1230
	unsigned int policy;
L
Linus Torvalds 已提交
1231 1232
	cpumask_t cpus_allowed;

P
Paul E. McKenney 已提交
1233
#ifdef CONFIG_PREEMPT_RCU
P
Paul E. McKenney 已提交
1234
	int rcu_read_lock_nesting;
1235 1236
	char rcu_read_unlock_special;
	struct list_head rcu_node_entry;
P
Paul E. McKenney 已提交
1237 1238 1239
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
	struct rcu_node *rcu_blocked_node;
1240
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
1241 1242 1243
#ifdef CONFIG_RCU_BOOST
	struct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */
P
Paul E. McKenney 已提交
1244

1245
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
L
Linus Torvalds 已提交
1246 1247 1248 1249
	struct sched_info sched_info;
#endif

	struct list_head tasks;
1250
#ifdef CONFIG_SMP
1251
	struct plist_node pushable_tasks;
1252
#endif
L
Linus Torvalds 已提交
1253 1254

	struct mm_struct *mm, *active_mm;
1255 1256 1257
#if defined(SPLIT_RSS_COUNTING)
	struct task_rss_stat	rss_stat;
#endif
L
Linus Torvalds 已提交
1258
/* task state */
1259
	int exit_state;
L
Linus Torvalds 已提交
1260 1261 1262
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	/* ??? */
1263
	unsigned int personality;
L
Linus Torvalds 已提交
1264
	unsigned did_exec:1;
1265 1266
	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
				 * execve */
1267 1268
	unsigned in_iowait:1;

1269 1270 1271 1272

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

L
Linus Torvalds 已提交
1273 1274
	pid_t pid;
	pid_t tgid;
1275

1276
#ifdef CONFIG_CC_STACKPROTECTOR
1277 1278
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
1279
#endif
1280

L
Linus Torvalds 已提交
1281 1282 1283
	/* 
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with 
R
Roland McGrath 已提交
1284
	 * p->real_parent->pid)
L
Linus Torvalds 已提交
1285
	 */
R
Roland McGrath 已提交
1286 1287
	struct task_struct *real_parent; /* real parent process */
	struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
L
Linus Torvalds 已提交
1288
	/*
R
Roland McGrath 已提交
1289
	 * children/sibling forms the list of my natural children
L
Linus Torvalds 已提交
1290 1291 1292 1293 1294
	 */
	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
1295 1296 1297 1298 1299 1300 1301 1302
	/*
	 * 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
1303
	/* PID/PID hash table linkage. */
1304
	struct pid_link pids[PIDTYPE_MAX];
O
Oleg Nesterov 已提交
1305
	struct list_head thread_group;
L
Linus Torvalds 已提交
1306 1307 1308 1309 1310

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

1311
	cputime_t utime, stime, utimescaled, stimescaled;
1312
	cputime_t gtime;
1313
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
1314
	cputime_t prev_utime, prev_stime;
1315
#endif
L
Linus Torvalds 已提交
1316
	unsigned long nvcsw, nivcsw; /* context switch counts */
1317 1318
	struct timespec start_time; 		/* monotonic time */
	struct timespec real_start_time;	/* boot based time */
L
Linus Torvalds 已提交
1319 1320 1321
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

1322
	struct task_cputime cputime_expires;
L
Linus Torvalds 已提交
1323 1324 1325
	struct list_head cpu_timers[3];

/* process credentials */
A
Arnd Bergmann 已提交
1326
	const struct cred __rcu *real_cred; /* objective and real subjective task
1327
					 * credentials (COW) */
A
Arnd Bergmann 已提交
1328
	const struct cred __rcu *cred;	/* effective (overridable) subjective task
1329
					 * credentials (COW) */
1330
	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
1331

1332 1333 1334
	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
1335
				     - initialized normally by setup_new_exec */
L
Linus Torvalds 已提交
1336 1337
/* file system info */
	int link_count, total_link_count;
1338
#ifdef CONFIG_SYSVIPC
L
Linus Torvalds 已提交
1339 1340
/* ipc stuff */
	struct sysv_sem sysvsem;
1341
#endif
1342
#ifdef CONFIG_DETECT_HUNG_TASK
1343 1344 1345
/* hung task detection */
	unsigned long last_switch_count;
#endif
L
Linus Torvalds 已提交
1346 1347 1348 1349 1350 1351
/* CPU-specific state of this task */
	struct thread_struct thread;
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
1352
/* namespaces */
S
Serge E. Hallyn 已提交
1353
	struct nsproxy *nsproxy;
L
Linus Torvalds 已提交
1354 1355 1356 1357 1358
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
1359
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
L
Linus Torvalds 已提交
1360 1361 1362 1363 1364 1365 1366 1367
	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
1368 1369
#ifdef CONFIG_AUDITSYSCALL
	uid_t loginuid;
1370
	unsigned int sessionid;
A
Al Viro 已提交
1371
#endif
L
Linus Torvalds 已提交
1372 1373 1374 1375 1376
	seccomp_t seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
1377 1378
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
L
Linus Torvalds 已提交
1379 1380
	spinlock_t alloc_lock;

1381 1382 1383 1384 1385
#ifdef CONFIG_GENERIC_HARDIRQS
	/* IRQ handler threads */
	struct irqaction *irqaction;
#endif

1386
	/* Protection of the PI data structures: */
1387
	raw_spinlock_t pi_lock;
1388

I
Ingo Molnar 已提交
1389 1390 1391 1392 1393 1394 1395
#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

1396 1397 1398 1399
#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
1400 1401 1402 1403
#ifdef CONFIG_TRACE_IRQFLAGS
	unsigned int irq_events;
	unsigned long hardirq_enable_ip;
	unsigned long hardirq_disable_ip;
1404
	unsigned int hardirq_enable_event;
1405
	unsigned int hardirq_disable_event;
1406 1407
	int hardirqs_enabled;
	int hardirq_context;
1408 1409
	unsigned long softirq_disable_ip;
	unsigned long softirq_enable_ip;
1410
	unsigned int softirq_disable_event;
1411
	unsigned int softirq_enable_event;
1412
	int softirqs_enabled;
1413 1414
	int softirq_context;
#endif
I
Ingo Molnar 已提交
1415
#ifdef CONFIG_LOCKDEP
1416
# define MAX_LOCK_DEPTH 48UL
I
Ingo Molnar 已提交
1417 1418 1419
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
1420
	struct held_lock held_locks[MAX_LOCK_DEPTH];
1421
	gfp_t lockdep_reclaim_gfp;
I
Ingo Molnar 已提交
1422
#endif
1423

L
Linus Torvalds 已提交
1424 1425 1426
/* journalling filesystem info */
	void *journal_info;

1427
/* stacked block device info */
1428
	struct bio_list *bio_list;
1429

1430 1431 1432 1433 1434
#ifdef CONFIG_BLOCK
/* stack plugging */
	struct blk_plug *plug;
#endif

L
Linus Torvalds 已提交
1435 1436 1437 1438 1439 1440 1441 1442 1443
/* 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.  */
1444
	struct task_io_accounting ioac;
1445
#if defined(CONFIG_TASK_XACCT)
L
Linus Torvalds 已提交
1446 1447
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
1448
	cputime_t acct_timexpd;	/* stime + utime since last update */
L
Linus Torvalds 已提交
1449 1450
#endif
#ifdef CONFIG_CPUSETS
1451
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
1452
	int mems_allowed_change_disable;
1453
	int cpuset_mem_spread_rotor;
1454
	int cpuset_slab_spread_rotor;
L
Linus Torvalds 已提交
1455
#endif
1456
#ifdef CONFIG_CGROUPS
1457
	/* Control Group info protected by css_set_lock */
A
Arnd Bergmann 已提交
1458
	struct css_set __rcu *cgroups;
1459 1460
	/* cg_list protected by css_set_lock and tsk->alloc_lock */
	struct list_head cg_list;
1461
#endif
1462
#ifdef CONFIG_FUTEX
1463
	struct robust_list_head __user *robust_list;
1464 1465 1466
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
1467 1468
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
1469
#endif
1470
#ifdef CONFIG_PERF_EVENTS
P
Peter Zijlstra 已提交
1471
	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
1472 1473
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
1474
#endif
1475
#ifdef CONFIG_NUMA
1476
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
1477
	short il_next;
1478
	short pref_node_fork;
1479
#endif
1480
	atomic_t fs_excl;	/* holding fs exclusive resources */
I
Ingo Molnar 已提交
1481
	struct rcu_head rcu;
1482 1483 1484 1485 1486

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;
1487 1488
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
1489 1490 1491
#endif
#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
1492
#endif
P
Peter Zijlstra 已提交
1493
	struct prop_local_single dirties;
A
Arjan van de Ven 已提交
1494 1495 1496 1497
#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
1498 1499 1500 1501 1502 1503
	/*
	 * 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;
1504 1505

	struct list_head	*scm_work_list;
1506
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
D
Daniel Mack 已提交
1507
	/* Index of current stored address in ret_stack */
1508 1509 1510
	int curr_ret_stack;
	/* Stack of return addresses for return function tracing */
	struct ftrace_ret_stack	*ret_stack;
1511 1512
	/* time stamp for last schedule */
	unsigned long long ftrace_timestamp;
1513 1514 1515 1516 1517
	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun.
	 */
	atomic_t trace_overrun;
1518 1519
	/* Pause for the tracing */
	atomic_t tracing_graph_pause;
1520
#endif
1521 1522 1523
#ifdef CONFIG_TRACING
	/* state flags for use by tracers */
	unsigned long trace;
1524 1525 1526
	/* bitmask of trace recursion */
	unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
1527 1528 1529 1530
#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 */
1531 1532
		unsigned long nr_pages;	/* uncharged usage */
		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
1533 1534
	} memcg_batch;
#endif
L
Linus Torvalds 已提交
1535 1536
};

1537
/* Future-safe accessor for struct task_struct's cpus_allowed. */
1538
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
1539

1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565
/*
 * 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
1566
static inline int rt_task(struct task_struct *p)
1567 1568 1569 1570
{
	return rt_prio(p->prio);
}

A
Alexey Dobriyan 已提交
1571
static inline struct pid *task_pid(struct task_struct *task)
1572 1573 1574 1575
{
	return task->pids[PIDTYPE_PID].pid;
}

A
Alexey Dobriyan 已提交
1576
static inline struct pid *task_tgid(struct task_struct *task)
1577 1578 1579 1580
{
	return task->group_leader->pids[PIDTYPE_PID].pid;
}

1581 1582 1583 1584 1585
/*
 * 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
1586
static inline struct pid *task_pgrp(struct task_struct *task)
1587 1588 1589 1590
{
	return task->group_leader->pids[PIDTYPE_PGID].pid;
}

A
Alexey Dobriyan 已提交
1591
static inline struct pid *task_session(struct task_struct *task)
1592 1593 1594 1595
{
	return task->group_leader->pids[PIDTYPE_SID].pid;
}

1596 1597 1598 1599 1600 1601 1602
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
1603 1604
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1605 1606 1607 1608 1609 1610
 * 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
 */
1611 1612
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
			struct pid_namespace *ns);
1613

A
Alexey Dobriyan 已提交
1614
static inline pid_t task_pid_nr(struct task_struct *tsk)
1615 1616 1617 1618
{
	return tsk->pid;
}

1619 1620 1621 1622 1623
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);
}
1624 1625 1626

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
1627
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
1628 1629 1630
}


A
Alexey Dobriyan 已提交
1631
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1632 1633 1634 1635
{
	return tsk->tgid;
}

1636
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
1637 1638 1639 1640 1641 1642 1643

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


1644 1645
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1646
{
1647
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
1648 1649 1650 1651
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
1652
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
1653 1654 1655
}


1656 1657
static inline pid_t task_session_nr_ns(struct task_struct *tsk,
					struct pid_namespace *ns)
1658
{
1659
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
1660 1661 1662 1663
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
1664
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
1665 1666
}

1667 1668 1669 1670 1671
/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
1672

L
Linus Torvalds 已提交
1673 1674 1675 1676 1677 1678 1679 1680
/**
 * 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
1681
static inline int pid_alive(struct task_struct *p)
L
Linus Torvalds 已提交
1682
{
1683
	return p->pids[PIDTYPE_PID].pid != NULL;
L
Linus Torvalds 已提交
1684 1685
}

1686
/**
1687
 * is_global_init - check if a task structure is init
1688 1689 1690
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1691
 */
A
Alexey Dobriyan 已提交
1692
static inline int is_global_init(struct task_struct *tsk)
1693 1694 1695
{
	return tsk->pid == 1;
}
1696 1697 1698 1699

/*
 * is_container_init:
 * check whether in the task is init in its own pid namespace.
1700
 */
1701
extern int is_container_init(struct task_struct *tsk);
1702

1703 1704
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1705 1706
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
1707

1708
extern void __put_task_struct(struct task_struct *t);
I
Ingo Molnar 已提交
1709 1710 1711 1712

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
1713
		__put_task_struct(t);
I
Ingo Molnar 已提交
1714
}
L
Linus Torvalds 已提交
1715

1716
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1717
extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
1718

L
Linus Torvalds 已提交
1719 1720 1721 1722 1723
/*
 * Per process flags
 */
#define PF_STARTING	0x00000002	/* being created */
#define PF_EXITING	0x00000004	/* getting shut down */
1724
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
1725
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
T
Tejun Heo 已提交
1726
#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
L
Linus Torvalds 已提交
1727
#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
1728
#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
L
Linus Torvalds 已提交
1729 1730 1731 1732 1733
#define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
#define PF_DUMPCORE	0x00000200	/* dumped core */
#define PF_SIGNALED	0x00000400	/* killed by a signal */
#define PF_MEMALLOC	0x00000800	/* Allocating memory */
#define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
1734
#define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
L
Linus Torvalds 已提交
1735 1736 1737 1738
#define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
#define PF_FROZEN	0x00010000	/* frozen for system suspend */
#define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
#define PF_KSWAPD	0x00040000	/* I am kswapd */
H
Hugh Dickins 已提交
1739
#define PF_OOM_ORIGIN	0x00080000	/* Allocating much memory to others */
L
Linus Torvalds 已提交
1740
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
1741
#define PF_KTHREAD	0x00200000	/* I am a kernel thread */
J
Jens Axboe 已提交
1742 1743 1744 1745
#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 */
1746
#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
1747
#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
1748
#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
1749
#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
1750
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
1751
#define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
L
Linus Torvalds 已提交
1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777

/*
 * 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)

P
Paul E. McKenney 已提交
1778
#ifdef CONFIG_PREEMPT_RCU
1779 1780

#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
1781 1782
#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. */
1783 1784 1785 1786 1787

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
1788
#ifdef CONFIG_TREE_PREEMPT_RCU
1789
	p->rcu_blocked_node = NULL;
1790 1791 1792 1793
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
	p->rcu_boost_mutex = NULL;
#endif /* #ifdef CONFIG_RCU_BOOST */
1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804
	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
1805
#ifdef CONFIG_SMP
1806
extern int set_cpus_allowed_ptr(struct task_struct *p,
1807
				const struct cpumask *new_mask);
L
Linus Torvalds 已提交
1808
#else
1809
static inline int set_cpus_allowed_ptr(struct task_struct *p,
1810
				       const struct cpumask *new_mask)
L
Linus Torvalds 已提交
1811
{
1812
	if (!cpumask_test_cpu(0, new_mask))
L
Linus Torvalds 已提交
1813 1814 1815 1816
		return -EINVAL;
	return 0;
}
#endif
1817 1818

#ifndef CONFIG_CPUMASK_OFFSTACK
1819 1820 1821 1822
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
	return set_cpus_allowed_ptr(p, &new_mask);
}
1823
#endif
L
Linus Torvalds 已提交
1824

1825
/*
1826 1827 1828 1829 1830 1831
 * 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.
1832
 */
1833
extern unsigned long long notrace sched_clock(void);
1834 1835 1836 1837 1838 1839 1840
/*
 * 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);

1841

1842
extern void sched_clock_init(void);
1843

1844
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856
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
1857 1858 1859 1860 1861 1862 1863 1864
/*
 * 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;

1865 1866 1867 1868 1869
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

1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882
#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

1883
extern unsigned long long
1884
task_sched_runtime(struct task_struct *task);
1885
extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
L
Linus Torvalds 已提交
1886 1887 1888 1889 1890 1891 1892 1893

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

1894 1895
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
1896

L
Linus Torvalds 已提交
1897 1898 1899 1900 1901 1902
#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif

1903 1904 1905 1906 1907 1908
#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

1909
extern unsigned int sysctl_sched_latency;
1910
extern unsigned int sysctl_sched_min_granularity;
1911 1912
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
1913 1914 1915 1916 1917 1918 1919 1920 1921

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;

1922
#ifdef CONFIG_SCHED_DEBUG
1923
extern unsigned int sysctl_sched_migration_cost;
1924
extern unsigned int sysctl_sched_nr_migrate;
1925
extern unsigned int sysctl_sched_time_avg;
1926
extern unsigned int sysctl_timer_migration;
1927
extern unsigned int sysctl_sched_shares_window;
1928

1929
int sched_proc_update_handler(struct ctl_table *table, int write,
1930
		void __user *buffer, size_t *length,
1931
		loff_t *ppos);
1932
#endif
1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943
#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
1944 1945
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
1946

1947
int sched_rt_handler(struct ctl_table *table, int write,
1948
		void __user *buffer, size_t *lenp,
1949 1950
		loff_t *ppos);

1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
#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

1969
#ifdef CONFIG_RT_MUTEXES
1970 1971 1972
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);
1973
#else
A
Alexey Dobriyan 已提交
1974
static inline int rt_mutex_getprio(struct task_struct *p)
1975 1976 1977
{
	return p->normal_prio;
}
1978
# define rt_mutex_adjust_pi(p)		do { } while (0)
1979 1980
#endif

1981
extern bool yield_to(struct task_struct *p, bool preempt);
1982 1983 1984 1985 1986
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
1987
extern int idle_cpu(int cpu);
1988 1989
extern int sched_setscheduler(struct task_struct *, int,
			      const struct sched_param *);
1990
extern int sched_setscheduler_nocheck(struct task_struct *, int,
1991
				      const struct sched_param *);
1992 1993 1994
extern struct task_struct *idle_task(int cpu);
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
L
Linus Torvalds 已提交
1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022

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;

2023 2024 2025 2026 2027 2028 2029
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
2030 2031
 * find_task_by_vpid():
 *      finds a task by its virtual pid
2032
 *
2033
 * see also find_vpid() etc in include/linux/pid.h
2034 2035
 */

2036 2037 2038
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);
2039

2040
extern void __set_special_pids(struct pid *pid);
L
Linus Torvalds 已提交
2041 2042

/* per-UID process charging. */
2043
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
L
Linus Torvalds 已提交
2044 2045 2046 2047 2048 2049
static inline struct user_struct *get_uid(struct user_struct *u)
{
	atomic_inc(&u->__count);
	return u;
}
extern void free_uid(struct user_struct *);
2050
extern void release_uids(struct user_namespace *ns);
L
Linus Torvalds 已提交
2051 2052 2053

#include <asm/current.h>

T
Torben Hohn 已提交
2054
extern void xtime_update(unsigned long ticks);
L
Linus Torvalds 已提交
2055

2056 2057 2058 2059
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk,
				unsigned long clone_flags);
L
Linus Torvalds 已提交
2060 2061 2062 2063 2064
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif
2065 2066
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
L
Linus Torvalds 已提交
2067 2068 2069

extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
2070
extern void __flush_signals(struct task_struct *);
2071
extern void ignore_signals(struct task_struct *);
L
Linus Torvalds 已提交
2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);

static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&tsk->sighand->siglock, flags);
	ret = dequeue_signal(tsk, mask, info);
	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);

	return ret;
}	

extern void block_all_signals(int (*notifier)(void *priv), void *priv,
			      sigset_t *mask);
extern void unblock_all_signals(void);
extern void release_task(struct task_struct * p);
extern int send_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
2094 2095
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);
2096
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
2097 2098
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
2099
extern int kill_proc_info(int, struct siginfo *, pid_t);
R
Roland McGrath 已提交
2100
extern int do_notify_parent(struct task_struct *, int);
2101
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
L
Linus Torvalds 已提交
2102 2103
extern void force_sig(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
2104
extern int zap_other_threads(struct task_struct *p);
L
Linus Torvalds 已提交
2105 2106
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
2107
extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
2108
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
L
Linus Torvalds 已提交
2109 2110
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);

2111 2112 2113 2114 2115
static inline int kill_cad_pid(int sig, int priv)
{
	return kill_pid(cad_pid, sig, priv);
}

L
Linus Torvalds 已提交
2116 2117 2118 2119 2120
/* 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)

2121 2122 2123
/*
 * True if we are on the alternate signal stack.
 */
L
Linus Torvalds 已提交
2124 2125
static inline int on_sig_stack(unsigned long sp)
{
2126 2127 2128 2129 2130 2131 2132
#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
2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146
}

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 */
2147
extern void __mmdrop(struct mm_struct *);
L
Linus Torvalds 已提交
2148 2149
static inline void mmdrop(struct mm_struct * mm)
{
I
Ingo Molnar 已提交
2150
	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
L
Linus Torvalds 已提交
2151 2152 2153 2154 2155 2156 2157 2158 2159
		__mmdrop(mm);
}

/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
2160 2161
/* 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
2162

A
Alexey Dobriyan 已提交
2163 2164
extern int copy_thread(unsigned long, unsigned long, unsigned long,
			struct task_struct *, struct pt_regs *);
L
Linus Torvalds 已提交
2165 2166 2167 2168
extern void flush_thread(void);
extern void exit_thread(void);

extern void exit_files(struct task_struct *);
2169
extern void __cleanup_sighand(struct sighand_struct *);
2170

L
Linus Torvalds 已提交
2171
extern void exit_itimers(struct signal_struct *);
2172
extern void flush_itimer_signals(void);
L
Linus Torvalds 已提交
2173 2174 2175 2176 2177 2178 2179

extern NORET_TYPE void do_group_exit(int);

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

2180 2181 2182
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
2183
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
2184
struct task_struct *fork_idle(int);
L
Linus Torvalds 已提交
2185 2186

extern void set_task_comm(struct task_struct *tsk, char *from);
2187
extern char *get_task_comm(char *to, struct task_struct *tsk);
L
Linus Torvalds 已提交
2188 2189

#ifdef CONFIG_SMP
2190
static inline void scheduler_ipi(void) { }
R
Roland McGrath 已提交
2191
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
L
Linus Torvalds 已提交
2192
#else
2193
static inline void scheduler_ipi(void) { }
R
Roland McGrath 已提交
2194 2195 2196 2197 2198
static inline unsigned long wait_task_inactive(struct task_struct *p,
					       long match_state)
{
	return 1;
}
L
Linus Torvalds 已提交
2199 2200
#endif

2201 2202
#define next_task(p) \
	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
L
Linus Torvalds 已提交
2203 2204 2205 2206

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

2207
extern bool current_is_single_threaded(void);
D
David Howells 已提交
2208

L
Linus Torvalds 已提交
2209 2210 2211 2212 2213 2214 2215 2216 2217 2218
/*
 * 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)

2219 2220
static inline int get_nr_threads(struct task_struct *tsk)
{
2221
	return tsk->signal->nr_threads;
2222 2223
}

2224 2225
/* de_thread depends on thread_group_leader not being a pid based check */
#define thread_group_leader(p)	(p == p->group_leader)
L
Linus Torvalds 已提交
2226

2227 2228 2229 2230 2231 2232
/* 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
2233
static inline int has_group_leader_pid(struct task_struct *p)
2234 2235 2236 2237
{
	return p->pid == p->tgid;
}

2238 2239 2240 2241 2242 2243
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
	return p1->tgid == p2->tgid;
}

2244
static inline struct task_struct *next_thread(const struct task_struct *p)
O
Oleg Nesterov 已提交
2245
{
2246 2247
	return list_entry_rcu(p->thread_group.next,
			      struct task_struct, thread_group);
O
Oleg Nesterov 已提交
2248 2249
}

A
Alexey Dobriyan 已提交
2250
static inline int thread_group_empty(struct task_struct *p)
L
Linus Torvalds 已提交
2251
{
O
Oleg Nesterov 已提交
2252
	return list_empty(&p->thread_group);
L
Linus Torvalds 已提交
2253 2254 2255 2256 2257
}

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

2258 2259 2260 2261 2262
static inline int task_detached(struct task_struct *p)
{
	return p->exit_signal == -1;
}

L
Linus Torvalds 已提交
2263
/*
2264
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
2265
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
2266 2267
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[].
L
Linus Torvalds 已提交
2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282
 *
 * 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);
}

2283
extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
2284 2285
							unsigned long *flags);

2286 2287 2288 2289 2290 2291 2292
#define lock_task_sighand(tsk, flags)					\
({	struct sighand_struct *__ss;					\
	__cond_lock(&(tsk)->sighand->siglock,				\
		    (__ss = __lock_task_sighand(tsk, flags)));		\
	__ss;								\
})									\

2293 2294 2295 2296 2297 2298
static inline void unlock_task_sighand(struct task_struct *tsk,
						unsigned long *flags)
{
	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}

A
Al Viro 已提交
2299 2300
#ifndef __HAVE_THREAD_FUNCTIONS

R
Roman Zippel 已提交
2301 2302
#define task_thread_info(task)	((struct thread_info *)(task)->stack)
#define task_stack_page(task)	((task)->stack)
A
Al Viro 已提交
2303

2304 2305 2306 2307 2308 2309 2310 2311
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
2312
	return (unsigned long *)(task_thread_info(p) + 1);
2313 2314
}

A
Al Viro 已提交
2315 2316
#endif

2317 2318 2319 2320 2321 2322 2323
static inline int object_is_on_stack(void *obj)
{
	void *stack = task_stack_page(current);

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

2324 2325
extern void thread_info_cache_init(void);

2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338
#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
2339 2340 2341 2342 2343
/* 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
2344
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2345 2346 2347 2348
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2349
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2350 2351 2352 2353
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2354
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2355 2356 2357 2358
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2359
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2360 2361 2362 2363
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
2364
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376
}

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);
}

2377 2378 2379 2380 2381
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

2382 2383 2384 2385 2386 2387
static inline int restart_syscall(void)
{
	set_tsk_thread_flag(current, TIF_SIGPENDING);
	return -ERESTARTNOINTR;
}

L
Linus Torvalds 已提交
2388 2389 2390 2391
static inline int signal_pending(struct task_struct *p)
{
	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
M
Matthew Wilcox 已提交
2392

2393 2394 2395 2396
static inline int __fatal_signal_pending(struct task_struct *p)
{
	return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
M
Matthew Wilcox 已提交
2397 2398 2399 2400 2401 2402

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

2403 2404 2405 2406 2407 2408 2409 2410 2411 2412
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
2413 2414
static inline int need_resched(void)
{
2415
	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
L
Linus Torvalds 已提交
2416 2417 2418 2419 2420 2421 2422 2423 2424
}

/*
 * 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.
 */
2425
extern int _cond_resched(void);
2426

2427 2428 2429 2430
#define cond_resched() ({			\
	__might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})
2431

2432 2433
extern int __cond_resched_lock(spinlock_t *lock);

2434 2435
#ifdef CONFIG_PREEMPT
#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
2436
#else
2437
#define PREEMPT_LOCK_OFFSET	0
2438
#endif
2439

2440
#define cond_resched_lock(lock) ({				\
2441
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
2442 2443 2444 2445 2446
	__cond_resched_lock(lock);				\
})

extern int __cond_resched_softirq(void);

2447 2448 2449
#define cond_resched_softirq() ({					\
	__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
	__cond_resched_softirq();					\
2450
})
L
Linus Torvalds 已提交
2451 2452 2453

/*
 * Does a critical section need to be broken due to another
N
Nick Piggin 已提交
2454 2455
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
2456
 */
N
Nick Piggin 已提交
2457
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
2458
{
N
Nick Piggin 已提交
2459 2460 2461
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
2462
	return 0;
N
Nick Piggin 已提交
2463
#endif
L
Linus Torvalds 已提交
2464 2465
}

2466 2467 2468
/*
 * Thread group CPU time accounting.
 */
2469
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
2470
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
2471

2472
static inline void thread_group_cputime_init(struct signal_struct *sig)
2473
{
2474
	spin_lock_init(&sig->cputimer.lock);
2475 2476
}

R
Roland McGrath 已提交
2477 2478 2479 2480 2481 2482 2483
/*
 * 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
2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494
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
2495
	return task_thread_info(p)->cpu;
L
Linus Torvalds 已提交
2496 2497
}

I
Ingo Molnar 已提交
2498
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512

#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 */

2513 2514
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
2515

L
Linus Torvalds 已提交
2516 2517
extern void normalize_rt_tasks(void);

D
Dhaval Giani 已提交
2518
#ifdef CONFIG_CGROUP_SCHED
2519

2520
extern struct task_group root_task_group;
2521

2522
extern struct task_group *sched_create_group(struct task_group *parent);
2523
extern void sched_destroy_group(struct task_group *tg);
2524
extern void sched_move_task(struct task_struct *tsk);
2525
#ifdef CONFIG_FAIR_GROUP_SCHED
2526
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
2527
extern unsigned long sched_group_shares(struct task_group *tg);
2528 2529
#endif
#ifdef CONFIG_RT_GROUP_SCHED
P
Peter Zijlstra 已提交
2530 2531 2532
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);
2533 2534 2535
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);
2536
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
2537
#endif
2538 2539
#endif

2540 2541 2542
extern int task_can_switch_user(struct user_struct *up,
					struct task_struct *tsk);

2543 2544 2545
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
2546
	tsk->ioac.rchar += amt;
2547 2548 2549 2550
}

static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
2551
	tsk->ioac.wchar += amt;
2552 2553 2554 2555
}

static inline void inc_syscr(struct task_struct *tsk)
{
2556
	tsk->ioac.syscr++;
2557 2558 2559 2560
}

static inline void inc_syscw(struct task_struct *tsk)
{
2561
	tsk->ioac.syscw++;
2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
}
#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
2581 2582 2583 2584
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597
#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 */

2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619
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
2620 2621 2622
#endif /* __KERNEL__ */

#endif