aboutsummaryrefslogtreecommitdiff
path: root/fs/timerfd.c
blob: 61983f3b107c5ee5d12521d3f38255a77bc6f781 (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
/*
 *  fs/timerfd.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *
 *
 *  Thanks to Thomas Gleixner for code reviews and useful comments.
 *
 */

#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/time.h>
#include <linux/hrtimer.h>
#include <linux/anon_inodes.h>
#include <linux/timerfd.h>

struct timerfd_ctx {
	struct hrtimer tmr;
	ktime_t tintv;
	wait_queue_head_t wqh;
	int expired;
};

/*
 * This gets called when the timer event triggers. We set the "expired"
 * flag, but we do not re-arm the timer (in case it's necessary,
 * tintv.tv64 != 0) until the timer is read.
 */
static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
{
	struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
	unsigned long flags;

	spin_lock_irqsave(&ctx->wqh.lock, flags);
	ctx->expired = 1;
	wake_up_locked(&ctx->wqh);
	spin_unlock_irqrestore(&ctx->wqh.lock, flags);

	return HRTIMER_NORESTART;
}

static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags,
			  const struct itimerspec *ktmr)
{
	enum hrtimer_mode htmode;
	ktime_t texp;

	htmode = (flags & TFD_TIMER_ABSTIME) ?
		HRTIMER_MODE_ABS: HRTIMER_MODE_REL;

	texp = timespec_to_ktime(ktmr->it_value);
	ctx->expired = 0;
	ctx->tintv = timespec_to_ktime(ktmr->it_interval);
	hrtimer_init(&ctx->tmr, clockid, htmode);
	ctx->tmr.expires = texp;
	ctx->tmr.function = timerfd_tmrproc;
	if (texp.tv64 != 0)
		hrtimer_start(&ctx->tmr, texp, htmode);
}

static int timerfd_release(struct inode *inode, struct file *file)
{
	struct timerfd_ctx *ctx = file->private_data;

	hrtimer_cancel(&ctx->tmr);
	kfree(ctx);
	return 0;
}

static unsigned int timerfd_poll(struct file *file, poll_table *wait)
{
	struct timerfd_ctx *ctx = file->private_data;
	unsigned int events = 0;
	unsigned long flags;

	poll_wait(file, &ctx->wqh, wait);

	spin_lock_irqsave(&ctx->wqh.lock, flags);
	if (ctx->expired)
		events |= POLLIN;
	spin_unlock_irqrestore(&ctx->wqh.lock, flags);

	return events;
}

static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
			    loff_t *ppos)
{
	struct timerfd_ctx *ctx = file->private_data;
	ssize_t res;
	u64 ticks = 0;
	DECLARE_WAITQUEUE(wait, current);

	if (count < sizeof(ticks))
		return -EINVAL;
	spin_lock_irq(&ctx->wqh.lock);
	res = -EAGAIN;
	if (!ctx->expired && !(file->f_flags & O_NONBLOCK)) {
		__add_wait_queue(&ctx->wqh, &wait);
		for (res = 0;;) {
			set_current_state(TASK_INTERRUPTIBLE);
			if (ctx->expired) {
				res = 0;
				break;
			}
			if (signal_pending(current)) {
				res = -ERESTARTSYS;
				break;
			}
			spin_unlock_irq(&ctx->wqh.lock);
			schedule();
			spin_lock_irq(&ctx->wqh.lock);
		}
		__remove_wait_queue(&ctx->wqh, &wait);
		__set_current_state(TASK_RUNNING);
	}
	if (ctx->expired) {
		ctx->expired = 0;
		if (ctx->tintv.tv64 != 0) {
			/*
			 * If tintv.tv64 != 0, this is a periodic timer that
			 * needs to be re-armed. We avoid doing it in the timer
			 * callback to avoid DoS attacks specifying a very
			 * short timer period.
			 */
			ticks = (u64)
				hrtimer_forward(&ctx->tmr,
						hrtimer_cb_get_time(&ctx->tmr),
						ctx->tintv);
			hrtimer_restart(&ctx->tmr);
		} else
			ticks = 1;
	}
	spin_unlock_irq(&ctx->wqh.lock);
	if (ticks)
		res = put_user(ticks, (u64 __user *) buf) ? -EFAULT: sizeof(ticks);
	return res;
}

static const struct file_operations timerfd_fops = {
	.release	= timerfd_release,
	.poll		= timerfd_poll,
	.read		= timerfd_read,
};

asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
			    const struct itimerspec __user *utmr)
{
	int error;
	struct timerfd_ctx *ctx;
	struct file *file;
	struct inode *inode;
	struct itimerspec ktmr;

	if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
		return -EFAULT;

	if (clockid != CLOCK_MONOTONIC &&
	    clockid != CLOCK_REALTIME)
		return -EINVAL;
	if (!timespec_valid(&ktmr.it_value) ||
	    !timespec_valid(&ktmr.it_interval))
		return -EINVAL;

	if (ufd == -1) {
		ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
		if (!ctx)
			return -ENOMEM;

		init_waitqueue_head(&ctx->wqh);

		timerfd_setup(ctx, clockid, flags, &ktmr);

		/*
		 * When we call this, the initialization must be complete, since
		 * anon_inode_getfd() will install the fd.
		 */
		error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]",
					 &timerfd_fops, ctx);
		if (error)
			goto err_tmrcancel;
	} else {
		file = fget(ufd);
		if (!file)
			return -EBADF;
		ctx = file->private_data;
		if (file->f_op != &timerfd_fops) {
			fput(file);
			return -EINVAL;
		}
		/*
		 * We need to stop the existing timer before reprogramming
		 * it to the new values.
		 */
		for (;;) {
			spin_lock_irq(&ctx->wqh.lock);
			if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
				break;
			spin_unlock_irq(&ctx->wqh.lock);
			cpu_relax();
		}
		/*
		 * Re-program the timer to the new value ...
		 */
		timerfd_setup(ctx, clockid, flags, &ktmr);

		spin_unlock_irq(&ctx->wqh.lock);
		fput(file);
	}

	return ufd;

err_tmrcancel:
	hrtimer_cancel(&ctx->tmr);
	kfree(ctx);
	return error;
}