summaryrefslogtreecommitdiffstats
path: root/kernel/task_work.c
blob: 15b087286bea45ae2383108ec5713ac0032ddb29 (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
// SPDX-License-Identifier: GPL-2.0
#include <linux/spinlock.h>
#include <linux/task_work.h>
#include <linux/tracehook.h>

static struct callback_head work_exited; /* all we need is ->next == NULL */

/*
 * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster
 * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is
 * shared for threads, and can cause contention on sighand->lock. Even for
 * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking
 * or IRQ disabling is involved for notification (or running) purposes.
 */
static void task_work_notify_signal(struct task_struct *task)
{
#if defined(TIF_NOTIFY_SIGNAL)
	set_notify_signal(task);
#else
	unsigned long flags;

	/*
	 * Only grab the sighand lock if we don't already have some
	 * task_work pending. This pairs with the smp_store_mb()
	 * in get_signal(), see comment there.
	 */
	if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
	    lock_task_sighand(task, &flags)) {
		task->jobctl |= JOBCTL_TASK_WORK;
		signal_wake_up(task, 0);
		unlock_task_sighand(task, &flags);
	}
#endif
}

/**
 * task_work_add - ask the @task to execute @work->func()
 * @task: the task which should run the callback
 * @work: the callback to run
 * @notify: how to notify the targeted task
 *
 * Queue @work for task_work_run() below and notify the @task if @notify
 * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
 * it will interrupt the targeted task and run the task_work. @TWA_RESUME
 * work is run only when the task exits the kernel and returns to user mode,
 * or before entering guest mode. Fails if the @task is exiting/exited and thus
 * it can't process this @work. Otherwise @work->func() will be called when the
 * @task goes through one of the aforementioned transitions, or exits.
 *
 * If the targeted task is exiting, then an error is returned and the work item
 * is not queued. It's up to the caller to arrange for an alternative mechanism
 * in that case.
 *
 * Note: there is no ordering guarantee on works queued here. The task_work
 * list is LIFO.
 *
 * RETURNS:
 * 0 if succeeds or -ESRCH.
 */
int task_work_add(struct task_struct *task, struct callback_head *work,
		  enum task_work_notify_mode notify)
{
	struct callback_head *head;

	do {
		head = READ_ONCE(task->task_works);
		if (unlikely(head == &work_exited))
			return -ESRCH;
		work->next = head;
	} while (cmpxchg(&task->task_works, head, work) != head);

	switch (notify) {
	case TWA_NONE:
		break;
	case TWA_RESUME:
		set_notify_resume(task);
		break;
	case TWA_SIGNAL:
		task_work_notify_signal(task);
		break;
	default:
		WARN_ON_ONCE(1);
		break;
	}

	return 0;
}

/**
 * task_work_cancel - cancel a pending work added by task_work_add()
 * @task: the task which should execute the work
 * @func: identifies the work to remove
 *
 * Find the last queued pending work with ->func == @func and remove
 * it from queue.
 *
 * RETURNS:
 * The found work or NULL if not found.
 */
struct callback_head *
task_work_cancel(struct task_struct *task, task_work_func_t func)
{
	struct callback_head **pprev = &task->task_works;
	struct callback_head *work;
	unsigned long flags;

	if (likely(!task->task_works))
		return NULL;
	/*
	 * If cmpxchg() fails we continue without updating pprev.
	 * Either we raced with task_work_add() which added the
	 * new entry before this work, we will find it again. Or
	 * we raced with task_work_run(), *pprev == NULL/exited.
	 */
	raw_spin_lock_irqsave(&task->pi_lock, flags);
	while ((work = READ_ONCE(*pprev))) {
		if (work->func != func)
			pprev = &work->next;
		else if (cmpxchg(pprev, work, work->next) == work)
			break;
	}
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	return work;
}

/**
 * task_work_run - execute the works added by task_work_add()
 *
 * Flush the pending works. Should be used by the core kernel code.
 * Called before the task returns to the user-mode or stops, or when
 * it exits. In the latter case task_work_add() can no longer add the
 * new work after task_work_run() returns.
 */
void task_work_run(void)
{
	struct task_struct *task = current;
	struct callback_head *work, *head, *next;

	for (;;) {
		/*
		 * work->func() can do task_work_add(), do not set
		 * work_exited unless the list is empty.
		 */
		do {
			head = NULL;
			work = READ_ONCE(task->task_works);
			if (!work) {
				if (task->flags & PF_EXITING)
					head = &work_exited;
				else
					break;
			}
		} while (cmpxchg(&task->task_works, work, head) != work);

		if (!work)
			break;
		/*
		 * Synchronize with task_work_cancel(). It can not remove
		 * the first entry == work, cmpxchg(task_works) must fail.
		 * But it can remove another entry from the ->next list.
		 */
		raw_spin_lock_irq(&task->pi_lock);
		raw_spin_unlock_irq(&task->pi_lock);

		do {
			next = work->next;
			work->func(work);
			work = next;
			cond_resched();
		} while (work);
	}
}