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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
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
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
|
// SPDX-License-Identifier: GPL-2.0
/*
* fs/signalfd.c
*
* Copyright (C) 2003 Linus Torvalds
*
* Mon Mar 5, 2007: Davide Libenzi <davidel@xmailserver.org>
* Changed ->read() to return a siginfo strcture instead of signal number.
* Fixed locking in ->poll().
* Added sighand-detach notification.
* Added fd re-use in sys_signalfd() syscall.
* Now using anonymous inode source.
* Thanks to Oleg Nesterov for useful code review and suggestions.
* More comments and suggestions from Arnd Bergmann.
* Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br>
* Retrieve multiple signals with one read() call
* Sun Jul 15, 2007: Davide Libenzi <davidel@xmailserver.org>
* Attach to the sighand only during read() and poll().
*/
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
#include <linux/signalfd.h>
#include <linux/syscalls.h>
#include <linux/proc_fs.h>
#include <linux/compat.h>
void signalfd_cleanup(struct sighand_struct *sighand)
{
wait_queue_head_t *wqh = &sighand->signalfd_wqh;
/*
* The lockless check can race with remove_wait_queue() in progress,
* but in this case its caller should run under rcu_read_lock() and
* sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
*/
if (likely(!waitqueue_active(wqh)))
return;
/* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
wake_up_poll(wqh, EPOLLHUP | POLLFREE);
}
struct signalfd_ctx {
sigset_t sigmask;
};
static int signalfd_release(struct inode *inode, struct file *file)
{
kfree(file->private_data);
return 0;
}
static __poll_t signalfd_poll(struct file *file, poll_table *wait)
{
struct signalfd_ctx *ctx = file->private_data;
__poll_t events = 0;
poll_wait(file, ¤t->sighand->signalfd_wqh, wait);
spin_lock_irq(¤t->sighand->siglock);
if (next_signal(¤t->pending, &ctx->sigmask) ||
next_signal(¤t->signal->shared_pending,
&ctx->sigmask))
events |= EPOLLIN;
spin_unlock_irq(¤t->sighand->siglock);
return events;
}
/*
* Copied from copy_siginfo_to_user() in kernel/signal.c
*/
static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
kernel_siginfo_t const *kinfo)
{
struct signalfd_siginfo new;
BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
/*
* Unused members should be zero ...
*/
memset(&new, 0, sizeof(new));
/*
* If you change siginfo_t structure, please be sure
* this code is fixed accordingly.
*/
new.ssi_signo = kinfo->si_signo;
new.ssi_errno = kinfo->si_errno;
new.ssi_code = kinfo->si_code;
switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) {
case SIL_KILL:
new.ssi_pid = kinfo->si_pid;
new.ssi_uid = kinfo->si_uid;
break;
case SIL_TIMER:
new.ssi_tid = kinfo->si_tid;
new.ssi_overrun = kinfo->si_overrun;
new.ssi_ptr = (long) kinfo->si_ptr;
new.ssi_int = kinfo->si_int;
break;
case SIL_POLL:
new.ssi_band = kinfo->si_band;
new.ssi_fd = kinfo->si_fd;
break;
case SIL_FAULT_BNDERR:
case SIL_FAULT_PKUERR:
/*
* Fall through to the SIL_FAULT case. Both SIL_FAULT_BNDERR
* and SIL_FAULT_PKUERR are only generated by faults that
* deliver them synchronously to userspace. In case someone
* injects one of these signals and signalfd catches it treat
* it as SIL_FAULT.
*/
case SIL_FAULT:
new.ssi_addr = (long) kinfo->si_addr;
#ifdef __ARCH_SI_TRAPNO
new.ssi_trapno = kinfo->si_trapno;
#endif
break;
case SIL_FAULT_MCEERR:
new.ssi_addr = (long) kinfo->si_addr;
#ifdef __ARCH_SI_TRAPNO
new.ssi_trapno = kinfo->si_trapno;
#endif
new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
break;
case SIL_CHLD:
new.ssi_pid = kinfo->si_pid;
new.ssi_uid = kinfo->si_uid;
new.ssi_status = kinfo->si_status;
new.ssi_utime = kinfo->si_utime;
new.ssi_stime = kinfo->si_stime;
break;
case SIL_RT:
/*
* This case catches also the signals queued by sigqueue().
*/
new.ssi_pid = kinfo->si_pid;
new.ssi_uid = kinfo->si_uid;
new.ssi_ptr = (long) kinfo->si_ptr;
new.ssi_int = kinfo->si_int;
break;
case SIL_SYS:
new.ssi_call_addr = (long) kinfo->si_call_addr;
new.ssi_syscall = kinfo->si_syscall;
new.ssi_arch = kinfo->si_arch;
break;
}
if (copy_to_user(uinfo, &new, sizeof(struct signalfd_siginfo)))
return -EFAULT;
return sizeof(*uinfo);
}
static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info,
int nonblock)
{
ssize_t ret;
DECLARE_WAITQUEUE(wait, current);
spin_lock_irq(¤t->sighand->siglock);
ret = dequeue_signal(current, &ctx->sigmask, info);
switch (ret) {
case 0:
if (!nonblock)
break;
ret = -EAGAIN;
default:
spin_unlock_irq(¤t->sighand->siglock);
return ret;
}
add_wait_queue(¤t->sighand->signalfd_wqh, &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
ret = dequeue_signal(current, &ctx->sigmask, info);
if (ret != 0)
break;
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
spin_unlock_irq(¤t->sighand->siglock);
schedule();
spin_lock_irq(¤t->sighand->siglock);
}
spin_unlock_irq(¤t->sighand->siglock);
remove_wait_queue(¤t->sighand->signalfd_wqh, &wait);
__set_current_state(TASK_RUNNING);
return ret;
}
/*
* Returns a multiple of the size of a "struct signalfd_siginfo", or a negative
* error code. The "count" parameter must be at least the size of a
* "struct signalfd_siginfo".
*/
static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct signalfd_ctx *ctx = file->private_data;
struct signalfd_siginfo __user *siginfo;
int nonblock = file->f_flags & O_NONBLOCK;
ssize_t ret, total = 0;
kernel_siginfo_t info;
count /= sizeof(struct signalfd_siginfo);
if (!count)
return -EINVAL;
siginfo = (struct signalfd_siginfo __user *) buf;
do {
ret = signalfd_dequeue(ctx, &info, nonblock);
if (unlikely(ret <= 0))
break;
ret = signalfd_copyinfo(siginfo, &info);
if (ret < 0)
break;
siginfo++;
total += ret;
nonblock = 1;
} while (--count);
return total ? total: ret;
}
#ifdef CONFIG_PROC_FS
static void signalfd_show_fdinfo(struct seq_file *m, struct file *f)
{
struct signalfd_ctx *ctx = f->private_data;
sigset_t sigmask;
sigmask = ctx->sigmask;
signotset(&sigmask);
render_sigset_t(m, "sigmask:\t", &sigmask);
}
#endif
static const struct file_operations signalfd_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = signalfd_show_fdinfo,
#endif
.release = signalfd_release,
.poll = signalfd_poll,
.read = signalfd_read,
.llseek = noop_llseek,
};
static int do_signalfd4(int ufd, sigset_t *mask, int flags)
{
struct signalfd_ctx *ctx;
/* Check the SFD_* constants for consistency. */
BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK);
if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
return -EINVAL;
sigdelsetmask(mask, sigmask(SIGKILL) | sigmask(SIGSTOP));
signotset(mask);
if (ufd == -1) {
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->sigmask = *mask;
/*
* When we call this, the initialization must be complete, since
* anon_inode_getfd() will install the fd.
*/
ufd = anon_inode_getfd("[signalfd]"
|