sched.h 52.3 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
L
Linus Torvalds 已提交
2 3 4
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

5 6 7 8
/*
 * Define 'struct task_struct' and provide the main scheduler
 * APIs (schedule(), wakeup variants, etc.)
 */
9

10
#include <uapi/linux/sched.h>
11

12
#include <asm/current.h>
L
Linus Torvalds 已提交
13

14
#include <linux/pid.h>
L
Linus Torvalds 已提交
15
#include <linux/sem.h>
16
#include <linux/shm.h>
17 18 19 20
#include <linux/kcov.h>
#include <linux/mutex.h>
#include <linux/plist.h>
#include <linux/hrtimer.h>
L
Linus Torvalds 已提交
21
#include <linux/seccomp.h>
22
#include <linux/nodemask.h>
23
#include <linux/rcupdate.h>
24
#include <linux/resource.h>
A
Arjan van de Ven 已提交
25
#include <linux/latencytop.h>
26 27 28 29
#include <linux/sched/prio.h>
#include <linux/signal_types.h>
#include <linux/mm_types_task.h>
#include <linux/task_io_accounting.h>
30
#include <linux/rseq.h>
31

32
/* task_struct member predeclarations (sorted alphabetically): */
33 34
struct audit_context;
struct backing_dev_info;
35
struct bio_list;
36
struct blk_plug;
37 38 39 40 41
struct cfs_rq;
struct fs_struct;
struct futex_pi_state;
struct io_context;
struct mempolicy;
42
struct nameidata;
43 44 45 46 47 48 49 50 51
struct nsproxy;
struct perf_event_context;
struct pid_namespace;
struct pipe_inode_info;
struct rcu_node;
struct reclaim_state;
struct robust_list_head;
struct sched_attr;
struct sched_param;
I
Ingo Molnar 已提交
52
struct seq_file;
53 54 55
struct sighand_struct;
struct signal_struct;
struct task_delay_info;
56
struct task_group;
L
Linus Torvalds 已提交
57

58 59 60 61 62 63 64 65 66 67
/*
 * 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.
 */
68 69

/* Used in tsk->state: */
70 71 72 73 74
#define TASK_RUNNING			0x0000
#define TASK_INTERRUPTIBLE		0x0001
#define TASK_UNINTERRUPTIBLE		0x0002
#define __TASK_STOPPED			0x0004
#define __TASK_TRACED			0x0008
75
/* Used in tsk->exit_state: */
76 77
#define EXIT_DEAD			0x0010
#define EXIT_ZOMBIE			0x0020
78 79
#define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
/* Used in tsk->state again: */
80 81 82 83
#define TASK_PARKED			0x0040
#define TASK_DEAD			0x0080
#define TASK_WAKEKILL			0x0100
#define TASK_WAKING			0x0200
84 85 86
#define TASK_NOLOAD			0x0400
#define TASK_NEW			0x0800
#define TASK_STATE_MAX			0x1000
87 88 89 90 91 92 93 94 95 96 97 98 99 100

/* Convenience macros for the sake of set_current_state: */
#define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED			(TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED			(TASK_WAKEKILL | __TASK_TRACED)

#define TASK_IDLE			(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)

/* Convenience macros for the sake of wake_up(): */
#define TASK_NORMAL			(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)

/* get_task_state(): */
#define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
					 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
101 102
					 __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
					 TASK_PARKED)
103 104 105 106 107 108 109 110 111 112

#define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)

#define task_is_stopped(task)		((task->state & __TASK_STOPPED) != 0)

#define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)

#define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
					 (task->flags & PF_FROZEN) == 0 && \
					 (task->state & TASK_NOLOAD) == 0)
L
Linus Torvalds 已提交
113

P
Peter Zijlstra 已提交
114 115
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP

116 117 118 119 120
/*
 * Special states are those that do not use the normal wait-loop pattern. See
 * the comment with set_special_state().
 */
#define is_special_task_state(state)				\
121
	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
122

P
Peter Zijlstra 已提交
123 124
#define __set_current_state(state_value)			\
	do {							\
125
		WARN_ON_ONCE(is_special_task_state(state_value));\
P
Peter Zijlstra 已提交
126 127 128
		current->task_state_change = _THIS_IP_;		\
		current->state = (state_value);			\
	} while (0)
129

P
Peter Zijlstra 已提交
130 131
#define set_current_state(state_value)				\
	do {							\
132
		WARN_ON_ONCE(is_special_task_state(state_value));\
P
Peter Zijlstra 已提交
133
		current->task_state_change = _THIS_IP_;		\
134
		smp_store_mb(current->state, (state_value));	\
P
Peter Zijlstra 已提交
135 136
	} while (0)

137 138 139 140 141 142 143 144 145
#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		WARN_ON_ONCE(!is_special_task_state(state_value));	\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->task_state_change = _THIS_IP_;			\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)
P
Peter Zijlstra 已提交
146
#else
147 148 149 150 151
/*
 * 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:
 *
152
 *   for (;;) {
153
 *	set_current_state(TASK_UNINTERRUPTIBLE);
154 155 156 157 158 159 160 161 162 163 164 165 166
 *	if (!need_sleep)
 *		break;
 *
 *	schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 *
 * If the caller does not need such serialisation (because, for instance, the
 * condition test and condition change and wakeup are under the same lock) then
 * use __set_current_state().
 *
 * The above is typically ordered against the wakeup, which does:
 *
167 168
 *   need_sleep = false;
 *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
169
 *
170 171
 * where wake_up_state() executes a full memory barrier before accessing the
 * task state.
172 173 174 175
 *
 * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
 * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
 * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
176
 *
177 178 179 180
 * However, with slightly different timing the wakeup TASK_RUNNING store can
 * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
 * a problem either because that will result in one extra go around the loop
 * and our @cond test will save the day.
181
 *
182
 * Also see the comments of try_to_wake_up().
183
 */
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
#define __set_current_state(state_value)				\
	current->state = (state_value)

#define set_current_state(state_value)					\
	smp_store_mb(current->state, (state_value))

/*
 * set_special_state() should be used for those states when the blocking task
 * can not use the regular condition based wait-loop. In that case we must
 * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
 * will not collide with our state change.
 */
#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)

P
Peter Zijlstra 已提交
204 205
#endif

206 207
/* Task command name length: */
#define TASK_COMM_LEN			16
L
Linus Torvalds 已提交
208 209 210

extern void scheduler_tick(void);

211 212 213 214 215 216 217
#define	MAX_SCHEDULE_TIMEOUT		LONG_MAX

extern long schedule_timeout(long timeout);
extern long schedule_timeout_interruptible(long timeout);
extern long schedule_timeout_killable(long timeout);
extern long schedule_timeout_uninterruptible(long timeout);
extern long schedule_timeout_idle(long timeout);
L
Linus Torvalds 已提交
218
asmlinkage void schedule(void);
219
extern void schedule_preempt_disabled(void);
L
Linus Torvalds 已提交
220

221 222
extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
223
extern long io_schedule_timeout(long timeout);
224
extern void io_schedule(void);
225

226
/**
227
 * struct prev_cputime - snapshot of system and user cputime
228 229
 * @utime: time spent in user mode
 * @stime: time spent in system mode
230
 * @lock: protects the above two fields
231
 *
232 233
 * Stores previous user/system time values such that we can guarantee
 * monotonicity.
234
 */
235 236
struct prev_cputime {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
237 238 239
	u64				utime;
	u64				stime;
	raw_spinlock_t			lock;
240
#endif
241 242
};

243 244
/**
 * struct task_cputime - collected CPU time counts
245 246
 * @utime:		time spent in user mode, in nanoseconds
 * @stime:		time spent in kernel mode, in nanoseconds
247
 * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
248
 *
249 250 251
 * 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.
252 253
 */
struct task_cputime {
254 255 256
	u64				utime;
	u64				stime;
	unsigned long long		sum_exec_runtime;
257
};
258

259 260 261 262
/* Alternate field names when used on cache expirations: */
#define virt_exp			utime
#define prof_exp			stime
#define sched_exp			sum_exec_runtime
263

264 265 266 267 268 269 270 271 272 273 274 275 276
enum vtime_state {
	/* Task is sleeping or running in a CPU with VTIME inactive: */
	VTIME_INACTIVE = 0,
	/* Task runs in userspace in a CPU with VTIME active: */
	VTIME_USER,
	/* Task runs in kernelspace in a CPU with VTIME active: */
	VTIME_SYS,
};

struct vtime {
	seqcount_t		seqcount;
	unsigned long long	starttime;
	enum vtime_state	state;
277 278 279
	u64			utime;
	u64			stime;
	u64			gtime;
280 281
};

L
Linus Torvalds 已提交
282
struct sched_info {
283
#ifdef CONFIG_SCHED_INFO
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298
	/* Cumulative counters: */

	/* # of times we have run on this CPU: */
	unsigned long			pcount;

	/* Time spent waiting on a runqueue: */
	unsigned long long		run_delay;

	/* Timestamps: */

	/* When did we last run on a CPU? */
	unsigned long long		last_arrival;

	/* When were we last queued to run? */
	unsigned long long		last_queued;
L
Linus Torvalds 已提交
299

300
#endif /* CONFIG_SCHED_INFO */
301
};
L
Linus Torvalds 已提交
302

303 304 305 306 307 308 309
/*
 * Integer metrics need fixed point arithmetic, e.g., sched/fair
 * has a few: load, load_avg, util_avg, freq, and capacity.
 *
 * We define a basic fixed point arithmetic range, and then formalize
 * all these metrics based on that basic range.
 */
310 311
# define SCHED_FIXEDPOINT_SHIFT		10
# define SCHED_FIXEDPOINT_SCALE		(1L << SCHED_FIXEDPOINT_SHIFT)
312

I
Ingo Molnar 已提交
313
struct load_weight {
314 315
	unsigned long			weight;
	u32				inv_weight;
I
Ingo Molnar 已提交
316 317
};

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343
/**
 * struct util_est - Estimation utilization of FAIR tasks
 * @enqueued: instantaneous estimated utilization of a task/cpu
 * @ewma:     the Exponential Weighted Moving Average (EWMA)
 *            utilization of a task
 *
 * Support data structure to track an Exponential Weighted Moving Average
 * (EWMA) of a FAIR task's utilization. New samples are added to the moving
 * average each time a task completes an activation. Sample's weight is chosen
 * so that the EWMA will be relatively insensitive to transient changes to the
 * task's workload.
 *
 * The enqueued attribute has a slightly different meaning for tasks and cpus:
 * - task:   the task's util_avg at last task dequeue time
 * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
 * Thus, the util_est.enqueued of a task represents the contribution on the
 * estimated utilization of the CPU where that task is currently enqueued.
 *
 * Only for tasks we track a moving average of the past instantaneous
 * estimated utilization. This allows to absorb sporadic drops in utilization
 * of an otherwise almost periodic task.
 */
struct util_est {
	unsigned int			enqueued;
	unsigned int			ewma;
#define UTIL_EST_WEIGHT_SHIFT		2
344
} __attribute__((__aligned__(sizeof(u64))));
345

346
/*
347 348 349 350 351 352 353 354 355
 * The load_avg/util_avg accumulates an infinite geometric series
 * (see __update_load_avg() in kernel/sched/fair.c).
 *
 * [load_avg definition]
 *
 *   load_avg = runnable% * scale_load_down(load)
 *
 * where runnable% is the time ratio that a sched_entity is runnable.
 * For cfs_rq, it is the aggregated load_avg of all runnable and
356
 * blocked sched_entities.
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
 *
 * load_avg may also take frequency scaling into account:
 *
 *   load_avg = runnable% * scale_load_down(load) * freq%
 *
 * where freq% is the CPU frequency normalized to the highest frequency.
 *
 * [util_avg definition]
 *
 *   util_avg = running% * SCHED_CAPACITY_SCALE
 *
 * where running% is the time ratio that a sched_entity is running on
 * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
 * and blocked sched_entities.
 *
 * util_avg may also factor frequency scaling and CPU capacity scaling:
 *
 *   util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity%
 *
 * where freq% is the same as above, and capacity% is the CPU capacity
 * normalized to the greatest capacity (due to uarch differences, etc).
 *
 * N.B., the above ratios (runnable%, running%, freq%, and capacity%)
 * themselves are in the range of [0, 1]. To do fixed point arithmetics,
 * we therefore scale them to as large a range as necessary. This is for
 * example reflected by util_avg's SCHED_CAPACITY_SCALE.
 *
 * [Overflow issue]
 *
 * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
 * with the highest load (=88761), always runnable on a single cfs_rq,
 * and should not overflow as the number already hits PID_MAX_LIMIT.
 *
 * For all other cases (including 32-bit kernels), struct load_weight's
 * weight will overflow first before we do, because:
 *
 *    Max(load_avg) <= Max(load.weight)
 *
 * Then it is the load_weight's responsibility to consider overflow
 * issues.
397
 */
398
struct sched_avg {
399 400
	u64				last_update_time;
	u64				load_sum;
401
	u64				runnable_load_sum;
402 403 404
	u32				util_sum;
	u32				period_contrib;
	unsigned long			load_avg;
405
	unsigned long			runnable_load_avg;
406
	unsigned long			util_avg;
407
	struct util_est			util_est;
408
} ____cacheline_aligned;
409

410
struct sched_statistics {
411
#ifdef CONFIG_SCHEDSTATS
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
	u64				wait_start;
	u64				wait_max;
	u64				wait_count;
	u64				wait_sum;
	u64				iowait_count;
	u64				iowait_sum;

	u64				sleep_start;
	u64				sleep_max;
	s64				sum_sleep_runtime;

	u64				block_start;
	u64				block_max;
	u64				exec_max;
	u64				slice_max;

	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;
443
#endif
444
};
445 446

struct sched_entity {
447 448
	/* For load-balancing: */
	struct load_weight		load;
449
	unsigned long			runnable_weight;
450 451 452
	struct rb_node			run_node;
	struct list_head		group_node;
	unsigned int			on_rq;
453

454 455 456 457
	u64				exec_start;
	u64				sum_exec_runtime;
	u64				vruntime;
	u64				prev_sum_exec_runtime;
458

459
	u64				nr_migrations;
460

461
	struct sched_statistics		statistics;
462

I
Ingo Molnar 已提交
463
#ifdef CONFIG_FAIR_GROUP_SCHED
464 465
	int				depth;
	struct sched_entity		*parent;
I
Ingo Molnar 已提交
466
	/* rq on which this entity is (to be) queued: */
467
	struct cfs_rq			*cfs_rq;
I
Ingo Molnar 已提交
468
	/* rq "owned" by this entity/group: */
469
	struct cfs_rq			*my_q;
I
Ingo Molnar 已提交
470
#endif
471

472
#ifdef CONFIG_SMP
473 474 475 476 477 478
	/*
	 * Per entity load average tracking.
	 *
	 * Put into separate cache line so it does not
	 * collide with read-mostly values above.
	 */
479
	struct sched_avg		avg;
480
#endif
I
Ingo Molnar 已提交
481
};
482

P
Peter Zijlstra 已提交
483
struct sched_rt_entity {
484 485 486 487 488 489 490 491
	struct list_head		run_list;
	unsigned long			timeout;
	unsigned long			watchdog_stamp;
	unsigned int			time_slice;
	unsigned short			on_rq;
	unsigned short			on_list;

	struct sched_rt_entity		*back;
492
#ifdef CONFIG_RT_GROUP_SCHED
493
	struct sched_rt_entity		*parent;
P
Peter Zijlstra 已提交
494
	/* rq on which this entity is (to be) queued: */
495
	struct rt_rq			*rt_rq;
P
Peter Zijlstra 已提交
496
	/* rq "owned" by this entity/group: */
497
	struct rt_rq			*my_q;
P
Peter Zijlstra 已提交
498
#endif
499
} __randomize_layout;
P
Peter Zijlstra 已提交
500

501
struct sched_dl_entity {
502
	struct rb_node			rb_node;
503 504 505

	/*
	 * Original scheduling parameters. Copied here from sched_attr
506 507
	 * during sched_setattr(), they will remain the same until
	 * the next sched_setattr().
508
	 */
509 510 511
	u64				dl_runtime;	/* Maximum runtime for each instance	*/
	u64				dl_deadline;	/* Relative deadline of each instance	*/
	u64				dl_period;	/* Separation of two instances (period) */
512
	u64				dl_bw;		/* dl_runtime / dl_period		*/
513
	u64				dl_density;	/* dl_runtime / dl_deadline		*/
514 515 516 517 518 519

	/*
	 * Actual scheduling parameters. Initialized with the values above,
	 * they are continously updated during task execution. Note that
	 * the remaining runtime could be < 0 in case we are in overrun.
	 */
520 521 522
	s64				runtime;	/* Remaining runtime for this instance	*/
	u64				deadline;	/* Absolute deadline for this instance	*/
	unsigned int			flags;		/* Specifying the scheduler behaviour	*/
523 524 525 526 527 528 529 530

	/*
	 * Some bool flags:
	 *
	 * @dl_throttled tells if we exhausted the runtime. If so, the
	 * task has to wait for a replenishment to be performed at the
	 * next firing of dl_timer.
	 *
531 532
	 * @dl_boosted tells if we are boosted due to DI. If so we are
	 * outside bandwidth enforcement mechanism (but only until we
533 534
	 * exit the critical section);
	 *
535
	 * @dl_yielded tells if task gave up the CPU before consuming
536
	 * all its available runtime during the last job.
537 538 539 540 541 542 543
	 *
	 * @dl_non_contending tells if the task is inactive while still
	 * contributing to the active utilization. In other words, it
	 * indicates if the inactive timer has been armed and its handler
	 * has not been executed yet. This flag is useful to avoid race
	 * conditions between the inactive timer handler and the wakeup
	 * code.
544 545 546
	 *
	 * @dl_overrun tells if the task asked to be informed about runtime
	 * overruns.
547
	 */
548 549 550 551
	unsigned int			dl_throttled      : 1;
	unsigned int			dl_boosted        : 1;
	unsigned int			dl_yielded        : 1;
	unsigned int			dl_non_contending : 1;
552
	unsigned int			dl_overrun	  : 1;
553 554 555 556 557

	/*
	 * Bandwidth enforcement timer. Each -deadline task has its
	 * own bandwidth to be enforced, thus we need one timer per task.
	 */
558
	struct hrtimer			dl_timer;
559 560 561 562 563 564 565 566 567

	/*
	 * Inactive timer, responsible for decreasing the active utilization
	 * at the "0-lag time". When a -deadline task blocks, it contributes
	 * to GRUB's active utilization until the "0-lag time", hence a
	 * timer is needed to decrease the active utilization at the correct
	 * time.
	 */
	struct hrtimer inactive_timer;
568
};
569

570 571
union rcu_special {
	struct {
572 573 574 575 576 577
		u8			blocked;
		u8			need_qs;
		u8			exp_need_qs;

		/* Otherwise the compiler can store garbage here: */
		u8			pad;
578 579
	} b; /* Bits. */
	u32 s; /* Set of bits. */
580
};
581

P
Peter Zijlstra 已提交
582 583 584
enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
585
	perf_sw_context,
P
Peter Zijlstra 已提交
586 587 588
	perf_nr_task_contexts,
};

589 590 591 592
struct wake_q_node {
	struct wake_q_node *next;
};

L
Linus Torvalds 已提交
593
struct task_struct {
594 595 596 597 598
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/*
	 * For reasons of header soup (see current_thread_info()), this
	 * must be the first element of task_struct.
	 */
599
	struct thread_info		thread_info;
600
#endif
601 602
	/* -1 unrunnable, 0 runnable, >0 stopped: */
	volatile long			state;
K
Kees Cook 已提交
603 604 605 606 607 608 609

	/*
	 * This begins the randomizable portion of task_struct. Only
	 * scheduling-critical items should be added above here.
	 */
	randomized_struct_fields_start

610 611 612 613 614
	void				*stack;
	atomic_t			usage;
	/* Per task flags (PF_*), defined further below: */
	unsigned int			flags;
	unsigned int			ptrace;
L
Linus Torvalds 已提交
615

616
#ifdef CONFIG_SMP
617 618
	struct llist_node		wake_entry;
	int				on_cpu;
619
#ifdef CONFIG_THREAD_INFO_IN_TASK
620 621
	/* Current CPU: */
	unsigned int			cpu;
622
#endif
623 624 625
	unsigned int			wakee_flips;
	unsigned long			wakee_flip_decay_ts;
	struct task_struct		*last_wakee;
626

627 628 629 630 631 632 633 634
	/*
	 * recent_used_cpu is initially set as the last CPU used by a task
	 * that wakes affine another task. Waker/wakee relationships can
	 * push tasks around a CPU where each wakeup moves to the next one.
	 * Tracking a recently used CPU allows a quick search for a recently
	 * used CPU that may be idle.
	 */
	int				recent_used_cpu;
635
	int				wake_cpu;
636
#endif
637 638 639 640 641 642
	int				on_rq;

	int				prio;
	int				static_prio;
	int				normal_prio;
	unsigned int			rt_priority;
643

644 645 646
	const struct sched_class	*sched_class;
	struct sched_entity		se;
	struct sched_rt_entity		rt;
P
Peter Zijlstra 已提交
647
#ifdef CONFIG_CGROUP_SCHED
648
	struct task_group		*sched_task_group;
P
Peter Zijlstra 已提交
649
#endif
650
	struct sched_dl_entity		dl;
L
Linus Torvalds 已提交
651

652
#ifdef CONFIG_PREEMPT_NOTIFIERS
653 654
	/* List of struct preempt_notifier: */
	struct hlist_head		preempt_notifiers;
655 656
#endif

657
#ifdef CONFIG_BLK_DEV_IO_TRACE
658
	unsigned int			btrace_seq;
659
#endif
L
Linus Torvalds 已提交
660

661 662 663
	unsigned int			policy;
	int				nr_cpus_allowed;
	cpumask_t			cpus_allowed;
L
Linus Torvalds 已提交
664

P
Paul E. McKenney 已提交
665
#ifdef CONFIG_PREEMPT_RCU
666 667 668 669
	int				rcu_read_lock_nesting;
	union rcu_special		rcu_read_unlock_special;
	struct list_head		rcu_node_entry;
	struct rcu_node			*rcu_blocked_node;
670
#endif /* #ifdef CONFIG_PREEMPT_RCU */
671

P
Paul E. McKenney 已提交
672
#ifdef CONFIG_TASKS_RCU
673
	unsigned long			rcu_tasks_nvcsw;
674 675
	u8				rcu_tasks_holdout;
	u8				rcu_tasks_idx;
676
	int				rcu_tasks_idle_cpu;
677
	struct list_head		rcu_tasks_holdout_list;
P
Paul E. McKenney 已提交
678
#endif /* #ifdef CONFIG_TASKS_RCU */
P
Paul E. McKenney 已提交
679

680
	struct sched_info		sched_info;
L
Linus Torvalds 已提交
681

682
	struct list_head		tasks;
683
#ifdef CONFIG_SMP
684 685
	struct plist_node		pushable_tasks;
	struct rb_node			pushable_dl_tasks;
686
#endif
L
Linus Torvalds 已提交
687

688 689
	struct mm_struct		*mm;
	struct mm_struct		*active_mm;
690 691

	/* Per-thread vma caching: */
692
	struct vmacache			vmacache;
693

694 695
#ifdef SPLIT_RSS_COUNTING
	struct task_rss_stat		rss_stat;
696
#endif
697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
	int				exit_state;
	int				exit_code;
	int				exit_signal;
	/* The signal sent when the parent dies: */
	int				pdeath_signal;
	/* JOBCTL_*, siglock protected: */
	unsigned long			jobctl;

	/* Used for emulating ABI behavior of previous Linux versions: */
	unsigned int			personality;

	/* Scheduler bits, serialized by scheduler locks: */
	unsigned			sched_reset_on_fork:1;
	unsigned			sched_contributes_to_load:1;
	unsigned			sched_migrated:1;
	unsigned			sched_remote_wakeup:1;
	/* Force alignment to the next boundary: */
	unsigned			:0;

	/* Unserialized, strictly 'current' */

	/* Bit to tell LSMs we're in execve(): */
	unsigned			in_execve:1;
	unsigned			in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
	unsigned			restore_sigmask:1;
723
#endif
T
Tejun Heo 已提交
724
#ifdef CONFIG_MEMCG
725
	unsigned			in_user_fault:1;
726
#ifdef CONFIG_MEMCG_KMEM
727
	unsigned			memcg_kmem_skip_account:1;
728
#endif
729
#endif
730
#ifdef CONFIG_COMPAT_BRK
731
	unsigned			brk_randomized:1;
732
#endif
733 734 735 736
#ifdef CONFIG_CGROUPS
	/* disallow userland-initiated cgroup migration */
	unsigned			no_cgroup_migration:1;
#endif
737 738 739 740
#ifdef CONFIG_BLK_CGROUP
	/* to be used once the psi infrastructure lands upstream. */
	unsigned			use_memdelay:1;
#endif
741

742
	unsigned long			atomic_flags; /* Flags requiring atomic access. */
743

744
	struct restart_block		restart_block;
745

746 747
	pid_t				pid;
	pid_t				tgid;
748

749
#ifdef CONFIG_STACKPROTECTOR
750 751
	/* Canary value for the -fstack-protector GCC feature: */
	unsigned long			stack_canary;
752
#endif
753
	/*
754
	 * Pointers to the (original) parent process, youngest child, younger sibling,
755
	 * older sibling, respectively.  (p->father can be replaced with
R
Roland McGrath 已提交
756
	 * p->real_parent->pid)
L
Linus Torvalds 已提交
757
	 */
758 759 760 761 762 763 764

	/* Real parent process: */
	struct task_struct __rcu	*real_parent;

	/* Recipient of SIGCHLD, wait4() reports: */
	struct task_struct __rcu	*parent;

L
Linus Torvalds 已提交
765
	/*
766
	 * Children/sibling form the list of natural children:
L
Linus Torvalds 已提交
767
	 */
768 769 770
	struct list_head		children;
	struct list_head		sibling;
	struct task_struct		*group_leader;
L
Linus Torvalds 已提交
771

R
Roland McGrath 已提交
772
	/*
773 774
	 * 'ptraced' is the list of tasks this task is using ptrace() on.
	 *
R
Roland McGrath 已提交
775
	 * This includes both natural children and PTRACE_ATTACH targets.
776
	 * 'ptrace_entry' is this task's link on the p->parent->ptraced list.
R
Roland McGrath 已提交
777
	 */
778 779
	struct list_head		ptraced;
	struct list_head		ptrace_entry;
R
Roland McGrath 已提交
780

L
Linus Torvalds 已提交
781
	/* PID/PID hash table linkage. */
782 783
	struct pid			*thread_pid;
	struct hlist_node		pid_links[PIDTYPE_MAX];
784 785 786 787
	struct list_head		thread_group;
	struct list_head		thread_node;

	struct completion		*vfork_done;
L
Linus Torvalds 已提交
788

789 790
	/* CLONE_CHILD_SETTID: */
	int __user			*set_child_tid;
L
Linus Torvalds 已提交
791

792 793 794 795 796
	/* CLONE_CHILD_CLEARTID: */
	int __user			*clear_child_tid;

	u64				utime;
	u64				stime;
797
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
798 799
	u64				utimescaled;
	u64				stimescaled;
800
#endif
801 802
	u64				gtime;
	struct prev_cputime		prev_cputime;
803
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
804
	struct vtime			vtime;
805
#endif
806 807

#ifdef CONFIG_NO_HZ_FULL
808
	atomic_t			tick_dep_mask;
809
#endif
810 811 812 813 814 815 816 817 818 819 820 821 822
	/* Context switch counts: */
	unsigned long			nvcsw;
	unsigned long			nivcsw;

	/* Monotonic time in nsecs: */
	u64				start_time;

	/* Boot based time in nsecs: */
	u64				real_start_time;

	/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
	unsigned long			min_flt;
	unsigned long			maj_flt;
L
Linus Torvalds 已提交
823

824
#ifdef CONFIG_POSIX_TIMERS
825 826
	struct task_cputime		cputime_expires;
	struct list_head		cpu_timers[3];
827
#endif
L
Linus Torvalds 已提交
828

829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850
	/* Process credentials: */

	/* Tracer's credentials at attach: */
	const struct cred __rcu		*ptracer_cred;

	/* Objective and real subjective task credentials (COW): */
	const struct cred __rcu		*real_cred;

	/* Effective (overridable) subjective task credentials (COW): */
	const struct cred __rcu		*cred;

	/*
	 * executable name, excluding path.
	 *
	 * - normally initialized setup_new_exec()
	 * - access it with [gs]et_task_comm()
	 * - lock it with task_lock()
	 */
	char				comm[TASK_COMM_LEN];

	struct nameidata		*nameidata;

851
#ifdef CONFIG_SYSVIPC
852 853
	struct sysv_sem			sysvsem;
	struct sysv_shm			sysvshm;
854
#endif
855
#ifdef CONFIG_DETECT_HUNG_TASK
856
	unsigned long			last_switch_count;
857
	unsigned long			last_switch_time;
858
#endif
859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882
	/* Filesystem information: */
	struct fs_struct		*fs;

	/* Open file information: */
	struct files_struct		*files;

	/* Namespaces: */
	struct nsproxy			*nsproxy;

	/* Signal handlers: */
	struct signal_struct		*signal;
	struct sighand_struct		*sighand;
	sigset_t			blocked;
	sigset_t			real_blocked;
	/* Restored if set_restore_sigmask() was used: */
	sigset_t			saved_sigmask;
	struct sigpending		pending;
	unsigned long			sas_ss_sp;
	size_t				sas_ss_size;
	unsigned int			sas_ss_flags;

	struct callback_head		*task_works;

	struct audit_context		*audit_context;
A
Al Viro 已提交
883
#ifdef CONFIG_AUDITSYSCALL
884 885
	kuid_t				loginuid;
	unsigned int			sessionid;
A
Al Viro 已提交
886
#endif
887 888 889 890 891
	struct seccomp			seccomp;

	/* Thread group tracking: */
	u32				parent_exec_id;
	u32				self_exec_id;
L
Linus Torvalds 已提交
892

893 894
	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
	spinlock_t			alloc_lock;
L
Linus Torvalds 已提交
895

896
	/* Protection of the PI data structures: */
897
	raw_spinlock_t			pi_lock;
898

899
	struct wake_q_node		wake_q;
900

I
Ingo Molnar 已提交
901
#ifdef CONFIG_RT_MUTEXES
902
	/* PI waiters blocked on a rt_mutex held by this task: */
903
	struct rb_root_cached		pi_waiters;
904 905
	/* Updated under owner's pi_lock and rq lock */
	struct task_struct		*pi_top_task;
906 907
	/* Deadlock detection and priority inheritance handling: */
	struct rt_mutex_waiter		*pi_blocked_on;
I
Ingo Molnar 已提交
908 909
#endif

910
#ifdef CONFIG_DEBUG_MUTEXES
911 912
	/* Mutex deadlock detection: */
	struct mutex_waiter		*blocked_on;
913
#endif
914

915
#ifdef CONFIG_TRACE_IRQFLAGS
916 917 918 919 920 921 922 923 924 925 926 927 928
	unsigned int			irq_events;
	unsigned long			hardirq_enable_ip;
	unsigned long			hardirq_disable_ip;
	unsigned int			hardirq_enable_event;
	unsigned int			hardirq_disable_event;
	int				hardirqs_enabled;
	int				hardirq_context;
	unsigned long			softirq_disable_ip;
	unsigned long			softirq_enable_ip;
	unsigned int			softirq_disable_event;
	unsigned int			softirq_enable_event;
	int				softirqs_enabled;
	int				softirq_context;
929
#endif
930

I
Ingo Molnar 已提交
931
#ifdef CONFIG_LOCKDEP
932 933 934 935 936
# define MAX_LOCK_DEPTH			48UL
	u64				curr_chain_key;
	int				lockdep_depth;
	unsigned int			lockdep_recursion;
	struct held_lock		held_locks[MAX_LOCK_DEPTH];
I
Ingo Molnar 已提交
937
#endif
938

939
#ifdef CONFIG_UBSAN
940
	unsigned int			in_ubsan;
941
#endif
942

943 944
	/* Journalling filesystem info: */
	void				*journal_info;
L
Linus Torvalds 已提交
945

946 947
	/* Stacked block device info: */
	struct bio_list			*bio_list;
948

949
#ifdef CONFIG_BLOCK
950 951
	/* Stack plugging: */
	struct blk_plug			*plug;
952 953
#endif

954 955 956 957
	/* VM state: */
	struct reclaim_state		*reclaim_state;

	struct backing_dev_info		*backing_dev_info;
L
Linus Torvalds 已提交
958

959
	struct io_context		*io_context;
L
Linus Torvalds 已提交
960

961 962 963
	/* Ptrace state: */
	unsigned long			ptrace_message;
	siginfo_t			*last_siginfo;
L
Linus Torvalds 已提交
964

965 966 967 968 969 970 971 972
	struct task_io_accounting	ioac;
#ifdef CONFIG_TASK_XACCT
	/* Accumulated RSS usage: */
	u64				acct_rss_mem1;
	/* Accumulated virtual memory usage: */
	u64				acct_vm_mem1;
	/* stime + utime since last update: */
	u64				acct_timexpd;
L
Linus Torvalds 已提交
973 974
#endif
#ifdef CONFIG_CPUSETS
975 976 977 978 979 980
	/* Protected by ->alloc_lock: */
	nodemask_t			mems_allowed;
	/* Seqence number to catch updates: */
	seqcount_t			mems_allowed_seq;
	int				cpuset_mem_spread_rotor;
	int				cpuset_slab_spread_rotor;
L
Linus Torvalds 已提交
981
#endif
982
#ifdef CONFIG_CGROUPS
983 984 985 986
	/* Control Group info protected by css_set_lock: */
	struct css_set __rcu		*cgroups;
	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
	struct list_head		cg_list;
987
#endif
988
#ifdef CONFIG_INTEL_RDT
989
	u32				closid;
990
	u32				rmid;
F
Fenghua Yu 已提交
991
#endif
992
#ifdef CONFIG_FUTEX
993
	struct robust_list_head __user	*robust_list;
994 995 996
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
997 998
	struct list_head		pi_state_list;
	struct futex_pi_state		*pi_state_cache;
999
#endif
1000
#ifdef CONFIG_PERF_EVENTS
1001 1002 1003
	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
	struct mutex			perf_event_mutex;
	struct list_head		perf_event_list;
1004
#endif
1005
#ifdef CONFIG_DEBUG_PREEMPT
1006
	unsigned long			preempt_disable_ip;
1007
#endif
1008
#ifdef CONFIG_NUMA
1009 1010
	/* Protected by alloc_lock: */
	struct mempolicy		*mempolicy;
1011
	short				il_prev;
1012
	short				pref_node_fork;
1013
#endif
1014
#ifdef CONFIG_NUMA_BALANCING
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026
	int				numa_scan_seq;
	unsigned int			numa_scan_period;
	unsigned int			numa_scan_period_max;
	int				numa_preferred_nid;
	unsigned long			numa_migrate_retry;
	/* Migration stamp: */
	u64				node_stamp;
	u64				last_task_numa_placement;
	u64				last_sum_exec_runtime;
	struct callback_head		numa_work;

	struct numa_group		*numa_group;
1027

1028
	/*
1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
	 * numa_faults is an array split into four regions:
	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
	 * in this precise order.
	 *
	 * faults_memory: Exponential decaying average of faults on a per-node
	 * basis. Scheduling placement decisions are made based on these
	 * counts. The values remain static for the duration of a PTE scan.
	 * faults_cpu: Track the nodes the process was running on when a NUMA
	 * hinting fault was incurred.
	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
	 * during the current scan window. When the scan completes, the counts
	 * in faults_memory and faults_cpu decay and these values are copied.
1041
	 */
1042 1043
	unsigned long			*numa_faults;
	unsigned long			total_numa_faults;
1044

1045 1046
	/*
	 * numa_faults_locality tracks if faults recorded during the last
1047 1048 1049
	 * scan window were remote/local or failed to migrate. The task scan
	 * period is adapted based on the locality of the faults with different
	 * weights depending on whether they were shared or private faults
1050
	 */
1051
	unsigned long			numa_faults_locality[3];
1052

1053
	unsigned long			numa_pages_migrated;
1054 1055
#endif /* CONFIG_NUMA_BALANCING */

1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066
#ifdef CONFIG_RSEQ
	struct rseq __user *rseq;
	u32 rseq_len;
	u32 rseq_sig;
	/*
	 * RmW on rseq_event_mask must be performed atomically
	 * with respect to preemption.
	 */
	unsigned long rseq_event_mask;
#endif

1067
	struct tlbflush_unmap_batch	tlb_ubc;
1068

1069
	struct rcu_head			rcu;
1070

1071 1072
	/* Cache last used pipe for splice(): */
	struct pipe_inode_info		*splice_pipe;
1073

1074
	struct page_frag		task_frag;
1075

1076 1077
#ifdef CONFIG_TASK_DELAY_ACCT
	struct task_delay_info		*delays;
1078
#endif
1079

1080
#ifdef CONFIG_FAULT_INJECTION
1081
	int				make_it_fail;
1082
	unsigned int			fail_nth;
1083
#endif
1084
	/*
1085 1086
	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for a dirty throttling pause:
1087
	 */
1088 1089 1090 1091
	int				nr_dirtied;
	int				nr_dirtied_pause;
	/* Start of a write-and-pause period: */
	unsigned long			dirty_paused_when;
1092

A
Arjan van de Ven 已提交
1093
#ifdef CONFIG_LATENCYTOP
1094 1095
	int				latency_record_count;
	struct latency_record		latency_record[LT_SAVECOUNT];
A
Arjan van de Ven 已提交
1096
#endif
1097
	/*
1098
	 * Time slack values; these are used to round up poll() and
1099 1100
	 * select() etc timeout values. These are in nanoseconds.
	 */
1101 1102
	u64				timer_slack_ns;
	u64				default_timer_slack_ns;
1103

1104
#ifdef CONFIG_KASAN
1105
	unsigned int			kasan_depth;
1106
#endif
1107

1108
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
1109 1110
	/* Index of current stored address in ret_stack: */
	int				curr_ret_stack;
1111
	int				curr_ret_depth;
1112 1113 1114 1115 1116 1117 1118

	/* Stack of return addresses for return function tracing: */
	struct ftrace_ret_stack		*ret_stack;

	/* Timestamp for last schedule: */
	unsigned long long		ftrace_timestamp;

1119 1120
	/*
	 * Number of functions that haven't been traced
1121
	 * because of depth overrun:
1122
	 */
1123 1124 1125 1126
	atomic_t			trace_overrun;

	/* Pause tracing: */
	atomic_t			tracing_graph_pause;
1127
#endif
1128

1129
#ifdef CONFIG_TRACING
1130 1131 1132 1133 1134
	/* State flags for use by tracers: */
	unsigned long			trace;

	/* Bitmask and counter of trace recursion: */
	unsigned long			trace_recursion;
1135
#endif /* CONFIG_TRACING */
1136

D
Dmitry Vyukov 已提交
1137
#ifdef CONFIG_KCOV
1138
	/* Coverage collection mode enabled for this task (0 if disabled): */
1139
	unsigned int			kcov_mode;
1140 1141 1142 1143 1144 1145 1146 1147 1148

	/* Size of the kcov_area: */
	unsigned int			kcov_size;

	/* Buffer for coverage collection: */
	void				*kcov_area;

	/* KCOV descriptor wired with this task or NULL: */
	struct kcov			*kcov;
D
Dmitry Vyukov 已提交
1149
#endif
1150

1151
#ifdef CONFIG_MEMCG
1152 1153 1154
	struct mem_cgroup		*memcg_in_oom;
	gfp_t				memcg_oom_gfp_mask;
	int				memcg_oom_order;
1155

1156 1157
	/* Number of pages to reclaim on returning to userland: */
	unsigned int			memcg_nr_pages_over_high;
1158 1159 1160

	/* Used by memcontrol for targeted memcg charge: */
	struct mem_cgroup		*active_memcg;
1161
#endif
1162

1163 1164 1165 1166
#ifdef CONFIG_BLK_CGROUP
	struct request_queue		*throttle_queue;
#endif

1167
#ifdef CONFIG_UPROBES
1168
	struct uprobe_task		*utask;
1169
#endif
K
Kent Overstreet 已提交
1170
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
1171 1172
	unsigned int			sequential_io;
	unsigned int			sequential_io_avg;
K
Kent Overstreet 已提交
1173
#endif
P
Peter Zijlstra 已提交
1174
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
1175
	unsigned long			task_state_change;
P
Peter Zijlstra 已提交
1176
#endif
1177
	int				pagefault_disabled;
1178
#ifdef CONFIG_MMU
1179
	struct task_struct		*oom_reaper_list;
1180
#endif
1181
#ifdef CONFIG_VMAP_STACK
1182
	struct vm_struct		*stack_vm_area;
1183
#endif
1184
#ifdef CONFIG_THREAD_INFO_IN_TASK
1185 1186
	/* A live task holds one reference: */
	atomic_t			stack_refcount;
1187 1188 1189
#endif
#ifdef CONFIG_LIVEPATCH
	int patch_state;
1190
#endif
1191 1192 1193
#ifdef CONFIG_SECURITY
	/* Used by LSM modules for access restriction: */
	void				*security;
1194
#endif
K
Kees Cook 已提交
1195 1196 1197 1198 1199 1200 1201

	/*
	 * New fields for task_struct should be added above here, so that
	 * they are included in the randomized portion of task_struct.
	 */
	randomized_struct_fields_end

1202 1203 1204 1205 1206 1207 1208 1209 1210
	/* CPU-specific state of this task: */
	struct thread_struct		thread;

	/*
	 * WARNING: on x86, 'thread_struct' contains a variable-sized
	 * structure.  It *MUST* be at the end of 'task_struct'.
	 *
	 * Do not put anything below here!
	 */
L
Linus Torvalds 已提交
1211 1212
};

A
Alexey Dobriyan 已提交
1213
static inline struct pid *task_pid(struct task_struct *task)
1214
{
1215
	return task->thread_pid;
1216 1217
}

1218 1219 1220 1221 1222
/*
 * 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
1223 1224
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
1225 1226 1227 1228
 * task_xid_nr_ns()  : id seen from the ns specified;
 *
 * see also pid_nr() etc in include/linux/pid.h
 */
1229
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
1230

A
Alexey Dobriyan 已提交
1231
static inline pid_t task_pid_nr(struct task_struct *tsk)
1232 1233 1234 1235
{
	return tsk->pid;
}

1236
static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
1237 1238 1239
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
}
1240 1241 1242

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
1243
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
1244 1245 1246
}


A
Alexey Dobriyan 已提交
1247
static inline pid_t task_tgid_nr(struct task_struct *tsk)
1248 1249 1250 1251
{
	return tsk->tgid;
}

1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263
/**
 * 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.
 *
 * Return: 1 if the process is alive. 0 otherwise.
 */
static inline int pid_alive(const struct task_struct *p)
{
1264
	return p->thread_pid != NULL;
1265
}
1266

1267
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
1268
{
1269
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
1270 1271 1272 1273
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
1274
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
1275 1276 1277
}


1278
static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
1279
{
1280
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
1281 1282 1283 1284
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
1285
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
1286 1287
}

1288 1289
static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
E
Eric W. Biederman 已提交
1290
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
1291 1292 1293 1294
}

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
E
Eric W. Biederman 已提交
1295
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314
}

static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
{
	pid_t pid = 0;

	rcu_read_lock();
	if (pid_alive(tsk))
		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
	rcu_read_unlock();

	return pid;
}

static inline pid_t task_ppid_nr(const struct task_struct *tsk)
{
	return task_ppid_nr_ns(tsk, &init_pid_ns);
}

1315
/* Obsolete, do not use: */
1316 1317 1318 1319
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
1320

1321 1322 1323
#define TASK_REPORT_IDLE	(TASK_REPORT + 1)
#define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)

1324
static inline unsigned int task_state_index(struct task_struct *tsk)
1325
{
1326 1327
	unsigned int tsk_state = READ_ONCE(tsk->state);
	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
1328

1329 1330 1331 1332 1333
	BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);

	if (tsk_state == TASK_IDLE)
		state = TASK_REPORT_IDLE;

1334 1335 1336
	return fls(state);
}

1337
static inline char task_index_to_char(unsigned int state)
1338
{
1339
	static const char state_char[] = "RSDTtXZPI";
1340

1341
	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
1342

1343 1344 1345 1346 1347
	return state_char[state];
}

static inline char task_state_to_char(struct task_struct *tsk)
{
1348
	return task_index_to_char(task_state_index(tsk));
1349 1350
}

1351
/**
1352 1353
 * is_global_init - check if a task structure is init. Since init
 * is free to have sub-threads we need to check tgid.
1354 1355 1356
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
1357 1358
 *
 * Return: 1 if the task structure is init. 0 otherwise.
1359
 */
A
Alexey Dobriyan 已提交
1360
static inline int is_global_init(struct task_struct *tsk)
1361
{
1362
	return task_tgid_nr(tsk) == 1;
1363
}
1364

1365 1366
extern struct pid *cad_pid;

L
Linus Torvalds 已提交
1367 1368 1369
/*
 * Per process flags
 */
1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385
#define PF_IDLE			0x00000002	/* I am an IDLE thread */
#define PF_EXITING		0x00000004	/* Getting shut down */
#define PF_EXITPIDONE		0x00000008	/* PI exit done on shut down */
#define PF_VCPU			0x00000010	/* I'm a virtual CPU */
#define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
#define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
#define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
#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_NPROC_EXCEEDED	0x00001000	/* set_user() noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
#define PF_USED_ASYNC		0x00004000	/* Used async_schedule*(), used by module init */
#define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
#define PF_FROZEN		0x00010000	/* Frozen for system suspend */
1386 1387 1388
#define PF_KSWAPD		0x00020000	/* I am kswapd */
#define PF_MEMALLOC_NOFS	0x00040000	/* All allocation requests will inherit GFP_NOFS */
#define PF_MEMALLOC_NOIO	0x00080000	/* All allocation requests will inherit GFP_NOIO */
1389 1390 1391 1392 1393 1394 1395 1396 1397
#define PF_LESS_THROTTLE	0x00100000	/* Throttle me less: I clean memory */
#define PF_KTHREAD		0x00200000	/* I am a kernel thread */
#define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
#define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
#define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
L
Linus Torvalds 已提交
1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409

/*
 * 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.
 */
1410 1411 1412 1413 1414
#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)

L
Linus Torvalds 已提交
1415 1416
#define conditional_stopped_child_used_math(condition, child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
1417 1418 1419

#define conditional_used_math(condition)	conditional_stopped_child_used_math(condition, current)

L
Linus Torvalds 已提交
1420 1421
#define copy_to_stopped_child_used_math(child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
1422

L
Linus Torvalds 已提交
1423
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
1424 1425
#define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
#define used_math()				tsk_used_math(current)
L
Linus Torvalds 已提交
1426

1427 1428 1429 1430 1431 1432 1433 1434 1435 1436
static inline bool is_percpu_thread(void)
{
#ifdef CONFIG_SMP
	return (current->flags & PF_NO_SETAFFINITY) &&
		(current->nr_cpus_allowed  == 1);
#else
	return true;
#endif
}

1437
/* Per-process atomic flags. */
1438 1439 1440
#define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
#define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
1441 1442
#define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
#define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/
1443 1444
#define PFA_SPEC_IB_DISABLE		5	/* Indirect branch speculation restricted */
#define PFA_SPEC_IB_FORCE_DISABLE	6	/* Indirect branch speculation permanently restricted */
1445

1446 1447 1448
#define TASK_PFA_TEST(name, func)					\
	static inline bool task_##func(struct task_struct *p)		\
	{ return test_bit(PFA_##name, &p->atomic_flags); }
1449

1450 1451 1452
#define TASK_PFA_SET(name, func)					\
	static inline void task_set_##func(struct task_struct *p)	\
	{ set_bit(PFA_##name, &p->atomic_flags); }
1453

1454 1455 1456 1457 1458 1459
#define TASK_PFA_CLEAR(name, func)					\
	static inline void task_clear_##func(struct task_struct *p)	\
	{ clear_bit(PFA_##name, &p->atomic_flags); }

TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)
1460

1461 1462 1463 1464 1465 1466 1467
TASK_PFA_TEST(SPREAD_PAGE, spread_page)
TASK_PFA_SET(SPREAD_PAGE, spread_page)
TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)

TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
1468

1469 1470 1471 1472 1473 1474 1475
TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)

TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)

1476 1477 1478 1479 1480 1481 1482
TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)

TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)

1483
static inline void
1484
current_restore_flags(unsigned long orig_flags, unsigned long flags)
1485
{
1486 1487
	current->flags &= ~flags;
	current->flags |= orig_flags & flags;
1488 1489
}

1490 1491
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
L
Linus Torvalds 已提交
1492
#ifdef CONFIG_SMP
1493 1494
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
L
Linus Torvalds 已提交
1495
#else
1496
static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
1497 1498
{
}
1499
static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
L
Linus Torvalds 已提交
1500
{
1501
	if (!cpumask_test_cpu(0, new_mask))
L
Linus Torvalds 已提交
1502 1503 1504 1505
		return -EINVAL;
	return 0;
}
#endif
1506

1507 1508 1509 1510
#ifndef cpu_relax_yield
#define cpu_relax_yield() cpu_relax()
#endif

1511
extern int yield_to(struct task_struct *p, bool preempt);
1512 1513
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
1514

1515 1516 1517 1518 1519 1520 1521 1522 1523 1524
/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 *
 * Return: The nice value [ -20 ... 0 ... 19 ].
 */
static inline int task_nice(const struct task_struct *p)
{
	return PRIO_TO_NICE((p)->static_prio);
}
1525

1526 1527
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
1528
extern int idle_cpu(int cpu);
1529
extern int available_idle_cpu(int cpu);
1530 1531 1532
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
1533
extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
1534
extern struct task_struct *idle_task(int cpu);
1535

1536 1537
/**
 * is_idle_task - is the specified task an idle task?
1538
 * @p: the task in question.
1539 1540
 *
 * Return: 1 if @p is an idle task. 0 otherwise.
1541
 */
1542
static inline bool is_idle_task(const struct task_struct *p)
1543
{
1544
	return !!(p->flags & PF_IDLE);
1545
}
1546

1547
extern struct task_struct *curr_task(int cpu);
1548
extern void ia64_set_curr_task(int cpu, struct task_struct *p);
L
Linus Torvalds 已提交
1549 1550 1551 1552

void yield(void);

union thread_union {
1553 1554 1555
#ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK
	struct task_struct task;
#endif
1556
#ifndef CONFIG_THREAD_INFO_IN_TASK
L
Linus Torvalds 已提交
1557
	struct thread_info thread_info;
1558
#endif
L
Linus Torvalds 已提交
1559 1560 1561
	unsigned long stack[THREAD_SIZE/sizeof(long)];
};

1562 1563 1564 1565 1566 1567
#ifndef CONFIG_THREAD_INFO_IN_TASK
extern struct thread_info init_thread_info;
#endif

extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];

1568 1569 1570 1571 1572 1573 1574 1575 1576
#ifdef CONFIG_THREAD_INFO_IN_TASK
static inline struct thread_info *task_thread_info(struct task_struct *task)
{
	return &task->thread_info;
}
#elif !defined(__HAVE_THREAD_FUNCTIONS)
# define task_thread_info(task)	((struct thread_info *)(task)->stack)
#endif

1577 1578 1579 1580 1581
/*
 * find a task by one of its numerical ids
 *
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
1582 1583
 * find_task_by_vpid():
 *      finds a task by its virtual pid
1584
 *
1585
 * see also find_vpid() etc in include/linux/pid.h
1586 1587
 */

1588
extern struct task_struct *find_task_by_vpid(pid_t nr);
1589
extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns);
1590

1591 1592 1593 1594 1595
/*
 * find a task by its virtual pid and get the task struct
 */
extern struct task_struct *find_get_task_by_vpid(pid_t nr);

1596 1597
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
1598
extern void wake_up_new_task(struct task_struct *tsk);
1599

L
Linus Torvalds 已提交
1600
#ifdef CONFIG_SMP
1601
extern void kick_process(struct task_struct *tsk);
L
Linus Torvalds 已提交
1602
#else
1603
static inline void kick_process(struct task_struct *tsk) { }
L
Linus Torvalds 已提交
1604 1605
#endif

1606
extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
1607

1608 1609 1610 1611
static inline void set_task_comm(struct task_struct *tsk, const char *from)
{
	__set_task_comm(tsk, from, false);
}
1612

1613 1614 1615 1616 1617
extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
#define get_task_comm(buf, tsk) ({			\
	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
	__get_task_comm(buf, sizeof(buf), tsk);		\
})
L
Linus Torvalds 已提交
1618 1619

#ifdef CONFIG_SMP
1620
void scheduler_ipi(void);
R
Roland McGrath 已提交
1621
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
L
Linus Torvalds 已提交
1622
#else
1623
static inline void scheduler_ipi(void) { }
1624
static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state)
R
Roland McGrath 已提交
1625 1626 1627
{
	return 1;
}
L
Linus Torvalds 已提交
1628 1629
#endif

1630 1631 1632
/*
 * Set thread flags in other task's structures.
 * See asm/thread_info.h for TIF_xxxx flags available:
L
Linus Torvalds 已提交
1633 1634 1635
 */
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1636
	set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1637 1638 1639 1640
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1641
	clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1642 1643
}

1644 1645 1646 1647 1648 1649
static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag,
					  bool value)
{
	update_ti_thread_flag(task_thread_info(tsk), flag, value);
}

L
Linus Torvalds 已提交
1650 1651
static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1652
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1653 1654 1655 1656
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1657
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1658 1659 1660 1661
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
A
Al Viro 已提交
1662
	return test_ti_thread_flag(task_thread_info(tsk), flag);
L
Linus Torvalds 已提交
1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674
}

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);
}

1675 1676 1677 1678 1679
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

L
Linus Torvalds 已提交
1680 1681 1682 1683 1684 1685
/*
 * 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,
 */
1686
#ifndef CONFIG_PREEMPT
1687
extern int _cond_resched(void);
1688 1689 1690
#else
static inline int _cond_resched(void) { return 0; }
#endif
1691

1692
#define cond_resched() ({			\
1693
	___might_sleep(__FILE__, __LINE__, 0);	\
1694 1695
	_cond_resched();			\
})
1696

1697 1698 1699
extern int __cond_resched_lock(spinlock_t *lock);

#define cond_resched_lock(lock) ({				\
1700
	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
1701 1702 1703
	__cond_resched_lock(lock);				\
})

1704 1705 1706 1707 1708 1709 1710 1711 1712
static inline void cond_resched_rcu(void)
{
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
	rcu_read_unlock();
	cond_resched();
	rcu_read_lock();
#endif
}

L
Linus Torvalds 已提交
1713 1714
/*
 * Does a critical section need to be broken due to another
N
Nick Piggin 已提交
1715 1716
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
L
Linus Torvalds 已提交
1717
 */
N
Nick Piggin 已提交
1718
static inline int spin_needbreak(spinlock_t *lock)
L
Linus Torvalds 已提交
1719
{
N
Nick Piggin 已提交
1720 1721 1722
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
L
Linus Torvalds 已提交
1723
	return 0;
N
Nick Piggin 已提交
1724
#endif
L
Linus Torvalds 已提交
1725 1726
}

1727 1728 1729 1730 1731
static __always_inline bool need_resched(void)
{
	return unlikely(tif_need_resched());
}

L
Linus Torvalds 已提交
1732 1733 1734 1735 1736 1737 1738
/*
 * 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)
{
1739
#ifdef CONFIG_THREAD_INFO_IN_TASK
1740
	return READ_ONCE(p->cpu);
1741
#else
1742
	return READ_ONCE(task_thread_info(p)->cpu);
1743
#endif
L
Linus Torvalds 已提交
1744 1745
}

I
Ingo Molnar 已提交
1746
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
L
Linus Torvalds 已提交
1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760

#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 */

1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
/*
 * In order to reduce various lock holder preemption latencies provide an
 * interface to see if a vCPU is currently running or not.
 *
 * This allows us to terminate optimistic spin loops and block, analogous to
 * the native optimistic spin heuristic of testing if the lock owner task is
 * running or not.
 */
#ifndef vcpu_is_preempted
# define vcpu_is_preempted(cpu)	false
#endif

1773 1774
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
1775

D
Dave Hansen 已提交
1776 1777 1778 1779
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
#ifdef CONFIG_RSEQ

/*
 * Map the event mask on the user-space ABI enum rseq_cs_flags
 * for direct mask checks.
 */
enum rseq_event_mask_bits {
	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
};

enum rseq_event_mask {
	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
};

static inline void rseq_set_notify_resume(struct task_struct *t)
{
	if (t->rseq)
		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}

1804
void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
1805

1806 1807
static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
1808 1809
{
	if (current->rseq)
1810
		__rseq_handle_notify_resume(ksig, regs);
1811 1812
}

1813 1814
static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
1815 1816 1817 1818
{
	preempt_disable();
	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
	preempt_enable();
1819
	rseq_handle_notify_resume(ksig, regs);
1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837
}

/* rseq_preempt() requires preemption to be disabled. */
static inline void rseq_preempt(struct task_struct *t)
{
	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
	rseq_set_notify_resume(t);
}

/* rseq_migrate() requires preemption to be disabled. */
static inline void rseq_migrate(struct task_struct *t)
{
	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
	rseq_set_notify_resume(t);
}

/*
 * If parent process has a registered restartable sequences area, the
1838
 * child inherits. Only applies when forking a process, not a thread.
1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
 */
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
	if (clone_flags & CLONE_THREAD) {
		t->rseq = NULL;
		t->rseq_len = 0;
		t->rseq_sig = 0;
		t->rseq_event_mask = 0;
	} else {
		t->rseq = current->rseq;
		t->rseq_len = current->rseq_len;
		t->rseq_sig = current->rseq_sig;
		t->rseq_event_mask = current->rseq_event_mask;
	}
}

static inline void rseq_execve(struct task_struct *t)
{
	t->rseq = NULL;
	t->rseq_len = 0;
	t->rseq_sig = 0;
	t->rseq_event_mask = 0;
}

#else

static inline void rseq_set_notify_resume(struct task_struct *t)
{
}
1868 1869
static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
1870 1871
{
}
1872 1873
static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902
{
}
static inline void rseq_preempt(struct task_struct *t)
{
}
static inline void rseq_migrate(struct task_struct *t)
{
}
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
}
static inline void rseq_execve(struct task_struct *t)
{
}

#endif

#ifdef CONFIG_DEBUG_RSEQ

void rseq_syscall(struct pt_regs *regs);

#else

static inline void rseq_syscall(struct pt_regs *regs)
{
}

#endif

L
Linus Torvalds 已提交
1903
#endif