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
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
|
// SPDX-License-Identifier: GPL-2.0
/*
* devtmpfs - kernel-maintained tmpfs-based /dev
*
* Copyright (C) 2009, Kay Sievers <kay.sievers@vrfy.org>
*
* During bootup, before any driver core device is registered,
* devtmpfs, a tmpfs-based filesystem is created. Every driver-core
* device which requests a device node, will add a node in this
* filesystem.
* By default, all devices are named after the name of the device,
* owned by root and have a default mode of 0600. Subsystems can
* overwrite the default setting if needed.
*/
#define pr_fmt(fmt) "devtmpfs: " fmt
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/device.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
#include <linux/fs.h>
#include <linux/shmem_fs.h>
#include <linux/ramfs.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/init_syscalls.h>
#include <uapi/linux/mount.h>
#include "base.h"
#ifdef CONFIG_DEVTMPFS_SAFE
#define DEVTMPFS_MFLAGS (MS_SILENT | MS_NOEXEC | MS_NOSUID)
#else
#define DEVTMPFS_MFLAGS (MS_SILENT)
#endif
static struct task_struct *thread;
static int __initdata mount_dev = IS_ENABLED(CONFIG_DEVTMPFS_MOUNT);
static DEFINE_SPINLOCK(req_lock);
static struct req {
struct req *next;
struct completion done;
int err;
const char *name;
umode_t mode; /* 0 => delete */
kuid_t uid;
kgid_t gid;
struct device *dev;
} *requests;
static int __init mount_param(char *str)
{
mount_dev = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("devtmpfs.mount=", mount_param);
static struct vfsmount *mnt;
static struct dentry *public_dev_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data)
{
struct super_block *s = mnt->mnt_sb;
int err;
atomic_inc(&s->s_active);
down_write(&s->s_umount);
err = reconfigure_single(s, flags, data);
if (err < 0) {
deactivate_locked_super(s);
return ERR_PTR(err);
}
return dget(s->s_root);
}
static struct file_system_type internal_fs_type = {
.name = "devtmpfs",
#ifdef CONFIG_TMPFS
.init_fs_context = shmem_init_fs_context,
#else
.init_fs_context = ramfs_init_fs_context,
#endif
.kill_sb = kill_litter_super,
};
static struct file_system_type dev_fs_type = {
.name = "devtmpfs",
.mount = public_dev_mount,
};
#ifdef CONFIG_BLOCK
static inline int is_blockdev(struct device *dev)
{
return dev->class == &block_class;
}
#else
static inline int is_blockdev(struct device *dev) { return 0; }
#endif
static int devtmpfs_submit_req(struct req *req, const char *tmp)
{
init_completion(&req->done);
spin_lock(&req_lock);
req->next = requests;
requests = req;
spin_unlock(&req_lock);
wake_up_process(thread);
wait_for_completion(&req->done);
kfree(tmp);
return req->err;
}
int devtmpfs_create_node(struct device *dev)
{
const char *tmp = NULL;
struct req req;
if (!thread)
return 0;
req.mode = 0;
req.uid = GLOBAL_ROOT_UID;
req.gid = GLOBAL_ROOT_GID;
req.name = device_get_devnode(dev, &req.mode, &req.uid, &req.gid, &tmp);
if (!req.name)
return -ENOMEM;
if (req.mode == 0)
req.mode = 0600;
if (is_blockdev(dev))
req.mode |= S_IFBLK;
else
req.mode |= S_IFCHR;
req.dev = dev;
return devtmpfs_submit_req(&req, tmp);
}
void devtmpfs_delete_node(struct device *dev)
{
const char *tmp = NULL;
struct req req;
if (!thread)
return;
req.name = device_get_devnode(dev, NULL, NULL, NULL, &tmp);
if (!req.name)
return;
req.mode = 0;
req.dev = dev;
devtmpfs_submit_req(&req, tmp);
}
static int dev_mkdir(const char *name, umode_t mode)
{
struct dentry *dentry;
struct path path;
int err;
dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
err = vfs_mkdir(&init_user_ns, d_inode(path.dentry), dentry, mode);
if (!err)
/* mark as kernel-created inode */
d_inode(dentry)->i_private = &thread;
done_path_create(&path, dentry);
return err;
}
static int create_path(const char *nodepath)
{
char *path;
char *s;
int err = 0;
/* parent directories do not exist, create them */
path = kstrdup(nodepath, GFP_KERNEL);
if (!path)
return -ENOMEM;
s = path;
for (;;) {
s = strchr(s, '/');
if (!s)
break;
s[0] = '\0';
err = dev_mkdir(path, 0755);
if (err && err != -EEXIST)
break;
s[0] = '/';
s++;
}
kfree(path);
return err;
}
static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
kgid_t gid, struct device *dev)
{
struct dentry *dentry;
struct path path;
int err;
dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
if (dentry == ERR_PTR(-ENOENT)) {
create_path(nodename);
dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
}
if (IS_ERR(dentry))
return PTR_ERR(dentry);
err = vfs_mknod(&init_user_ns, d_inode(path.dentry), dentry, mode,
dev->devt);
if (!err) {
struct iattr newattrs;
newattrs.ia_mode = mode;
newattrs.ia_uid = uid;
newattrs.ia_gid = gid;
newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
inode_lock(d_inode(dentry));
notify_change(&init_user_ns, dentry, &newattrs, NULL);
inode_unlock(d_inode(dentry));
/* mark as kernel-created inode */
d_inode(dentry)->i_private = &thread;
}
done_path_create(&path, dentry);
return err;
}
static int dev_rmdir(const char *name)
{
struct path parent;
struct dentry *dentry;
int err;
dentry = kern_path_locked(name, &parent);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
if (d_really_is_positive(dentry)) {
if (d_inode(dentry)->i_private == &thread)
err = vfs_rmdir(&init_user_ns, d_inode(parent.dentry),
dentry);
else
err = -EPERM;
} else {
err = -ENOENT;
}
dput(dentry);
inode_unlock(d_inode(parent.dentry));
path_put(&parent);
return err;
}
static int delete_path(const char *nodepath)
{
char *path;
int err = 0;
path = kstrdup(nodepath, GFP_KERNEL);
if (!path)
return -ENOMEM;
for (;;) {
char *base;
base = strrchr(path, '/');
if (!base)
break;
base[0] = '\0';
err = dev_rmdir(path);
if (err)
break;
}
kfree(path);
return err;
}
static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
{
/* did we create it */
if (inode->i_private != &thread)
return 0;
/* does the dev_t match */
if (is_blockdev(dev)) {
if (!S_ISBLK(stat->mode))
return 0;
} else {
if (!S_ISCHR(stat->mode))
return 0;
}
if (stat->rdev != dev->devt)
return 0;
/* ours */
return 1;
}
static int handle_remove(const char *nodename, struct device *dev)
{
struct path parent;
struct dentry *dentry;
int deleted = 0;
int err;
dentry = kern_path_locked(nodename, &parent);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
if (d_really_is_positive(dentry)) {
struct kstat stat;
struct path p = {.mnt = parent.mnt, .dentry = dentry};
err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
AT_STATX_SYNC_AS_STAT);
if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
struct iattr newattrs;
/*
* before unlinking this node, reset permissions
* of possible references like hardlinks
*/
newattrs.ia_uid = GLOBAL_ROOT_UID;
newattrs.ia_gid = GLOBAL_ROOT_GID;
newattrs.ia_mode = stat.mode & ~0777;
newattrs.ia_valid =
ATTR_UID|ATTR_GID|ATTR_MODE;
inode_lock(d_inode(dentry));
notify_change(&init_user_ns, dentry, &newattrs, NULL);
inode_unlock(d_inode(dentry));
err = vfs_unlink(&init_user_ns, d_inode(parent.dentry),
dentry, NULL);
if (!err || err == -ENOENT)
deleted = 1;
}
} else {
err = -ENOENT;
}
dput(dentry);
inode_unlock(d_inode(parent.dentry));
path_put(&parent);
if (deleted && strchr(nodename, '/'))
delete_path(nodename);
return err;
}
/*
* If configured, or requested by the commandline, devtmpfs will be
* auto-mounted after the kernel mounted the root filesystem.
*/
int __init devtmpfs_mount(void)
{
int err;
if (!mount_dev)
return 0;
if (!thread)
return 0;
err = init_mount("devtmpfs", "dev", "devtmpfs", DEVTMPFS_MFLAGS, NULL);
if (err)
pr_info("error mounting %d\n", err);
else
pr_info("mounted\n");
return err;
}
static __initdata DECLARE_COMPLETION(setup_done);
static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid,
struct device *dev)
{
int ret;
if (mode)
ret = handle_create(name, mode, uid, gid, dev);
else
ret = handle_remove(name, dev);
if (ret)
dev_err(dev, "failed to %s %s, ret = %d\n",
mode ? "create" : "remove", name, ret);
return ret;
}
static void __noreturn devtmpfs_work_loop(void)
{
while (1) {
spin_lock(&req_lock);
while (requests) {
struct req *req = requests;
requests = NULL;
spin_unlock(&req_lock);
while (req) {
struct req *next = req->next;
req->err = handle(req->name, req->mode,
req->uid, req->gid, req->dev);
complete(&req->done);
req = next;
}
spin_lock(&req_lock);
}
__set_current_state(TASK_INTERRUPTIBLE);
spin_unlock(&req_lock);
schedule();
}
}
static noinline int __init devtmpfs_setup(void *p)
{
int err;
err = ksys_unshare(CLONE_NEWNS);
if (err)
goto out;
err = init_mount("devtmpfs", "/", "devtmpfs", DEVTMPFS_MFLAGS, NULL);
if (err)
goto out;
init_chdir("/.."); /* will traverse into overmounted root */
init_chroot(".");
out:
*(int *)p = err;
return err;
}
/*
* The __ref is because devtmpfs_setup needs to be __init for the routines it
* calls. That call is done while devtmpfs_init, which is marked __init,
* synchronously waits for it to complete.
*/
static int __ref devtmpfsd(void *p)
{
int err = devtmpfs_setup(p);
complete(&setup_done);
if (err)
return err;
devtmpfs_work_loop();
return 0;
}
/*
* Create devtmpfs instance, driver-core devices will add their device
* nodes here.
*/
int __init devtmpfs_init(void)
{
char opts[] = "mode=0755";
int err;
mnt = vfs_kern_mount(&internal_fs_type, 0, "devtmpfs", opts);
if (IS_ERR(mnt)) {
pr_err("unable to create devtmpfs %ld\n", PTR_ERR(mnt));
return PTR_ERR(mnt);
}
err = register_filesystem(&dev_fs_type);
if (err) {
pr_err("unable to register devtmpfs type %d\n", err);
return err;
}
thread = kthread_run(devtmpfsd, &err, "kdevtmpfs");
if (!IS_ERR(thread)) {
wait_for_completion(&setup_done);
} else {
err = PTR_ERR(thread);
thread = NULL;
}
if (err) {
pr_err("unable to create devtmpfs %d\n", err);
unregister_filesystem(&dev_fs_type);
thread = NULL;
return err;
}
pr_info("initialized\n");
return 0;
}
|