summaryrefslogtreecommitdiffstats
path: root/include/linux/sched/task.h
blob: d362aacf9f897343f8cfababed5f21fdf430bfb7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_TASK_H
#define _LINUX_SCHED_TASK_H

/*
 * Interface between the scheduler and various task lifetime (fork()/exit())
 * functionality:
 */

#include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/sched.h>
#include <linux/uaccess.h>

struct task_struct;
struct rusage;
union thread_union;
struct css_set;

/* All the bits taken by the old clone syscall. */
#define CLONE_LEGACY_FLAGS 0xffffffffULL

struct kernel_clone_args {
	u64 flags;
	int __user *pidfd;
	int __user *child_tid;
	int __user *parent_tid;
	const char *name;
	int exit_signal;
	u32 kthread:1;
	u32 io_thread:1;
	u32 user_worker:1;
	u32 no_files:1;
	unsigned long stack;
	unsigned long stack_size;
	unsigned long tls;
	pid_t *set_tid;
	/* Number of elements in *set_tid */
	size_t set_tid_size;
	int cgroup;
	int idle;
	int (*fn)(void *);
	void *fn_arg;
	struct cgroup *cgrp;
	struct css_set *cset;
};

/*
 * 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;

extern union thread_union init_thread_union;
extern struct task_struct init_task;

extern int lockdep_tasklist_lock_is_held(void);

extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);

extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
extern void sched_post_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);

void __noreturn do_task_dead(void);
void __noreturn make_task_dead(int signr);

extern void mm_cache_init(void);
extern void proc_caches_init(void);

extern void fork_init(void);

extern void release_task(struct task_struct * p);

extern int copy_thread(struct task_struct *, const struct kernel_clone_args *);

extern void flush_thread(void);

#ifdef CONFIG_HAVE_EXIT_THREAD
extern void exit_thread(struct task_struct *tsk);
#else
static inline void exit_thread(struct task_struct *tsk)
{
}
#endif
extern __noreturn void do_group_exit(int);

extern void exit_files(struct task_struct *);
extern void exit_itimers(struct task_struct *);

extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *copy_process(struct pid *pid, int trace, int node,
				 struct kernel_clone_args *args);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
struct task_struct *fork_idle(int);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name,
			    unsigned long flags);
extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
int kernel_wait(pid_t pid, int *stat);

extern void free_task(struct task_struct *tsk);

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

static inline struct task_struct *get_task_struct(struct task_struct *t)
{
	refcount_inc(&t->usage);
	return t;
}

extern void __put_task_struct(struct task_struct *t);
extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);

static inline void put_task_struct(struct task_struct *t)
{
	if (!refcount_dec_and_test(&t->usage))
		return;

	/*
	 * In !RT, it is always safe to call __put_task_struct().
	 * Under RT, we can only call it in preemptible context.
	 */
	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
		static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);

		lock_map_acquire_try(&put_task_map);
		__put_task_struct(t);
		lock_map_release(&put_task_map);
		return;
	}

	/*
	 * under PREEMPT_RT, we can't call put_task_struct
	 * in atomic context because it will indirectly
	 * acquire sleeping locks.
	 *
	 * call_rcu() will schedule delayed_put_task_struct_rcu()
	 * to be called in process context.
	 *
	 * __put_task_struct() is called when
	 * refcount_dec_and_test(&t->usage) succeeds.
	 *
	 * This means that it can't "conflict" with
	 * put_task_struct_rcu_user() which abuses ->rcu the same
	 * way; rcu_users has a reference so task->usage can't be
	 * zero after rcu_users 1 -> 0 transition.
	 *
	 * delayed_free_task() also uses ->rcu, but it is only called
	 * when it fails to fork a process. Therefore, there is no
	 * way it can conflict with put_task_struct().
	 */
	call_rcu(&t->rcu, __put_task_struct_rcu_cb);
}

DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T))

static inline void put_task_struct_many(struct task_struct *t, int nr)
{
	if (refcount_sub_and_test(nr, &t->usage))
		__put_task_struct(t);
}

void put_task_struct_rcu_user(struct task_struct *task);

/* Free all architecture-specific resources held by a thread. */
void release_thread(struct task_struct *dead_task);

#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
extern int arch_task_struct_size __read_mostly;
#else
# define arch_task_struct_size (sizeof(struct task_struct))
#endif

#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
/*
 * If an architecture has not declared a thread_struct whitelist we
 * must assume something there may need to be copied to userspace.
 */
static inline void arch_thread_struct_whitelist(unsigned long *offset,
						unsigned long *size)
{
	*offset = 0;
	/* Handle dynamically sized thread_struct. */
	*size = arch_task_struct_size - offsetof(struct task_struct, thread);
}
#endif

#ifdef CONFIG_VMAP_STACK
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
{
	return t->stack_vm_area;
}
#else
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
{
	return NULL;
}
#endif

/*
 * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
 * subscriptions and synchronises with wait4().  Also used in procfs.  Also
 * pins the final release of task.io_context.  Also protects ->cpuset and
 * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
 *
 * 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);
}

DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))

#endif /* _LINUX_SCHED_TASK_H */