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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
|
/*
* 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>
#include <linux/syscalls.h>
struct timerfd_ctx {
struct hrtimer tmr;
ktime_t tintv;
wait_queue_head_t wqh;
u64 ticks;
int expired;
int clockid;
};
/*
* 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 accessed.
*/
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;
ctx->ticks++;
wake_up_locked(&ctx->wqh);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return HRTIMER_NORESTART;
}
static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
{
ktime_t remaining;
remaining = hrtimer_expires_remaining(&ctx->tmr);
return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
}
static void timerfd_setup(struct timerfd_ctx *ctx, 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->ticks = 0;
ctx->tintv = timespec_to_ktime(ktmr->it_interval);
hrtimer_init(&ctx->tmr, ctx->clockid, htmode);
hrtimer_set_expires(&ctx->tmr, 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->ticks)
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->ticks && !(file->f_flags & O_NONBLOCK)) {
__add_wait_queue(&ctx->wqh, &wait);
for (res = 0;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (ctx->ticks) {
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->ticks) {
ticks = ctx->ticks;
if (ctx->expired && ctx->tintv.tv64) {
/*
* 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 += hrtimer_forward_now(&ctx->tmr,
ctx->tintv) - 1;
hrtimer_restart(&ctx->tmr);
}
ctx->expired = 0;
ctx->ticks = 0;
}
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,
};
static struct file *timerfd_fget(int fd)
{
struct file *file;
file = fget(fd);
if (!file)
return ERR_PTR(-EBADF);
if (file->f_op != &timerfd_fops) {
fput(file);
return ERR_PTR(-EINVAL);
}
return file;
}
SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
{
int ufd;
struct timerfd_ctx *ctx;
/* Check the TFD_* constants for consistency. */
BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK);
if (flags & ~(TFD_CLOEXEC | TFD_NONBLOCK))
return -EINVAL;
if (clockid != CLOCK_MONOTONIC &&
clockid != CLOCK_REALTIME)
return -EINVAL;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
init_waitqueue_head(&ctx->wqh);
ctx->clockid = clockid;
hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
flags & (O_CLOEXEC | O_NONBLOCK));
if (ufd < 0)
kfree(ctx);
return ufd;
}
SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
const struct itimerspec __user *, utmr,
struct itimerspec __user *, otmr)
{
struct file *file;
struct timerfd_ctx *ctx;
struct itimerspec ktmr, kotmr;
if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
return -EFAULT;
if (!timespec_valid(&ktmr.it_value) ||
!timespec_valid(&ktmr.it_interval))
return -EINVAL;
file = timerfd_fget(ufd);
if (IS_ERR(file))
return PTR_ERR(file);
ctx = file->private_data;
/*
* 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();
}
/*
* If the timer is expired and it's periodic, we need to advance it
* because the caller may want to know the previous expiration time.
* We do not update "ticks" and "expired" since the timer will be
* re-programmed again in the following timerfd_setup() call.
*/
if (ctx->expired && ctx->tintv.tv64)
hrtimer_forward_now(&ctx->tmr, ctx->tintv);
kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
kotmr.it_interval = ktime_to_timespec(ctx->tintv);
/*
* Re-program the timer to the new value ...
*/
timerfd_setup(ctx, flags, &ktmr);
spin_unlock_irq(&ctx->wqh.lock);
fput(file);
if (otmr && copy_to_user(otmr, &kotmr, sizeof(kotmr)))
return -EFAULT;
return 0;
}
SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
{
struct file *file;
struct timerfd_ctx *ctx;
struct itimerspec kotmr;
file = timerfd_fget(ufd);
if (IS_ERR(file))
return PTR_ERR(file);
ctx = file->private_data;
spin_lock_irq(&ctx->wqh.lock);
if (ctx->expired && ctx->tintv.
|