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
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
|
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/proc/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/cache.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/pid_namespace.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/completion.h>
#include <linux/poll.h>
#include <linux/printk.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/bug.h>
#include "internal.h"
static void proc_evict_inode(struct inode *inode)
{
struct proc_dir_entry *de;
struct ctl_table_header *head;
struct proc_inode *ei = PROC_I(inode);
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
/* Stop tracking associated processes */
if (ei->pid) {
proc_pid_evict_inode(ei);
ei->pid = NULL;
}
/* Let go of any associated proc directory entry */
de = ei->pde;
if (de) {
pde_put(de);
ei->pde = NULL;
}
head = ei->sysctl;
if (head) {
RCU_INIT_POINTER(ei->sysctl, NULL);
proc_sys_evict_inode(inode, head);
}
}
static struct kmem_cache *proc_inode_cachep __ro_after_init;
static struct kmem_cache *pde_opener_cache __ro_after_init;
static struct inode *proc_alloc_inode(struct super_block *sb)
{
struct proc_inode *ei;
ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
ei->pid = NULL;
ei->fd = 0;
ei->op.proc_get_link = NULL;
ei->pde = NULL;
ei->sysctl = NULL;
ei->sysctl_entry = NULL;
INIT_HLIST_NODE(&ei->sibling_inodes);
ei->ns_ops = NULL;
return &ei->vfs_inode;
}
static void proc_free_inode(struct inode *inode)
{
kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}
static void init_once(void *foo)
{
struct proc_inode *ei = (struct proc_inode *) foo;
inode_init_once(&ei->vfs_inode);
}
void __init proc_init_kmemcache(void)
{
proc_inode_cachep = kmem_cache_create("proc_inode_cache",
sizeof(struct proc_inode),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_ACCOUNT|
SLAB_PANIC),
init_once);
pde_opener_cache =
kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0,
SLAB_ACCOUNT|SLAB_PANIC, NULL);
proc_dir_entry_cache = kmem_cache_create_usercopy(
"proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC,
offsetof(struct proc_dir_entry, inline_name),
SIZEOF_PDE_INLINE_NAME, NULL);
BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE);
}
void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
{
struct hlist_node *node;
struct super_block *old_sb = NULL;
rcu_read_lock();
while ((node = hlist_first_rcu(inodes))) {
struct proc_inode *ei = hlist_entry(node, struct proc_inode, sibling_inodes);
struct super_block *sb;
struct inode *inode;
spin_lock(lock);
hlist_del_init_rcu(&ei->sibling_inodes);
spin_unlock(lock);
inode = &ei->vfs_inode;
sb = inode->i_sb;
if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active))
continue;
inode = igrab(inode);
rcu_read_unlock();
if (sb != old_sb) {
if (old_sb)
deactivate_super(old_sb);
old_sb = sb;
}
if (unlikely(!inode)) {
rcu_read_lock();
continue;
}
if (S_ISDIR(inode->i_mode)) {
struct dentry *dir = d_find_any_alias(inode);
if (dir) {
d_invalidate(dir);
dput(dir);
}
} else {
struct dentry *dentry;
while ((dentry = d_find_alias(inode))) {
d_invalidate(dentry);
dput(dentry);
}
}
iput(inode);
rcu_read_lock();
}
rcu_read_unlock();
if (old_sb)
deactivate_super(old_sb);
}
static inline const char *hidepid2str(enum proc_hidepid v)
{
switch (v) {
case HIDEPID_OFF: return "off";
case HIDEPID_NO_ACCESS: return "noaccess";
case HIDEPID_INVISIBLE: return "invisible";
case HIDEPID_NOT_PTRACEABLE: return "ptraceable";
}
WARN_ONCE(1, "bad hide_pid value: %d\n", v);
return "unknown";
}
static int proc_show_options(struct seq_file *seq, struct dentry *root)
{
struct proc_fs_info *fs_info = proc_sb_info(root->d_sb);
if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID))
seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid));
if (fs_info->hide_pid != HIDEPID_OFF)
seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid));
if (fs_info->pidonly != PROC_PIDONLY_OFF)
seq_printf(seq, ",subset=pid");
return 0;
}
const struct super_operations proc_sops = {
.alloc_inode = proc_alloc_inode,
.free_inode = proc_free_inode,
.drop_inode = generic_delete_inode,
.evict_inode = proc_evict_inode,
.statfs = simple_statfs,
.show_options = proc_show_options,
};
enum {BIAS = -1U<<31};
static inline int use_pde(struct proc_dir_entry *pde)
{
return likely(atomic_inc_unless_negative(&pde->in_use));
}
static void unuse_pde(struct proc_dir_entry *pde)
{
if (unlikely(atomic_dec_return(&pde->in_use) == BIAS))
complete(pde->pde_unload_completion);
}
/*
* At most 2 contexts can enter this function: the one doing the last
* close on the descriptor and whoever is deleting PDE itself.
*
* First to enter calls ->proc_release hook and signals its completion
* to the second one which waits and then does nothing.
*
* PDE is locked on entry, unlocked on exit.
*/
static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
__releases(&pde->pde_unload_lock)
{
/*
* close() (proc_reg_release()) can't delete an entry and proceed:
* ->release hook needs to be available at the right moment.
*
* rmmod (remove_proc_entry() et al) can't delete an entry and proceed:
* "struct file" needs to be available at the right moment.
*/
if (pdeo->closing) {
/* somebody else is doing that, just wait */
DECLARE_COMPLETION_ONSTACK(c);
pdeo->c = &c;
spin_unlock(&pde->pde_unload_lock);
wait_for_completion(&c);
} else {
struct file *file;
struct completion *c;
pdeo->closing = true;
spin_unlock(&pde->pde_unload_lock);
file = pdeo->file;
pde->proc_ops->proc_release(file_inode(file), file);
spin_lock(&pde->pde_unload_lock);
/* Strictly after ->proc_release, see above. */
list_del(&pdeo->lh);
c = pdeo->c;
spin_unlock(&pde->pde_unload_lock);
if (unlikely(c))
complete(c);
kmem_cache_free(pde_opener_cache, pdeo);
}
}
void proc_entry_rundown(struct proc_dir_entry *de)
{
DECLARE_COMPLETION_ONSTACK(c);
/* Wait until all existing callers into module are done. */
de->pde_unload_completion = &c;
if (atomic_add_return(BIAS, &de->in_use) != BIAS)
wait_for_completion(&c);
/* ->pde_openers list can't grow from now on. */
spin_lock(&de->pde_unload_lock);
while (!list_empty(&de->pde_openers)) {
struct pde_opener *pdeo;
pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
close_pdeo(de, pdeo);
spin_lock(&de->pde_unload_lock);
}
spin_unlock(&de->pde_unload_lock);
}
static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
loff_t rv = -EINVAL;
if (pde_is_permanent(pde)) {
return pde->proc_ops->proc_lseek(file, offset, whence);
} else if (use_pde(pde)) {
rv = pde->proc_ops->proc_lseek(file, offset, whence);
unuse_pde(pde);
}
return rv;
}
static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
ssize_t ret;
if (pde_is_permanent(pde))
return pde->proc_ops->proc_read_iter(iocb, iter);
if (!use_pde(pde))
return -EIO;
ret = pde->proc_ops->proc_read_iter(iocb, iter);
unuse_pde(pde);
return ret;
}
static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
typeof_member(struct proc_ops, proc_read) read;
read = pde->proc_ops->proc_read;
if (read)
return read(file, buf, count, ppos);
return -EIO;
}
static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
if (pde_is_permanent(pde)) {
return pde_read(pde, file, buf, count, ppos);
} else if (use_pde(pde)) {
rv = pde_read(pde, file, buf, count, ppos);
unuse_pde(pde);
}
return rv;
}
static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
typeof_member(struct proc_ops, proc_write) write;
write = pde->proc_ops->proc_write;
if (write)
return write(file, buf, count, ppos);
return -EIO;
}
static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
if (pde_is_permanent(pde)) {
return pde_write(pde, file, buf, count, ppos);
} else if (use_pde(pde)) {
rv = pde_write(pde, file, buf, count, ppos);
unuse_pde(pde);
}
return rv;
}
static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts)
{
typeof_member(struct proc_ops, proc_poll) poll;
poll = pde->proc_ops->proc_poll;
if (poll)
return poll(file, pts);
return DEFAULT_POLLMASK;
}
static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
__poll_t rv = DEFAULT_POLLMASK;
if (pde_is_permanent(pde)) {
return pde_poll(pde, file, pts);
} else if (use_pde(pde)) {
rv = pde_poll(pde, file, pts);
unuse_pde(pde);
}
return rv;
}
static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
{
typeof_member(struct proc_ops, proc_ioctl) ioctl;
ioctl = pde->proc_ops->proc_ioctl;
if (ioctl)
return ioctl(file, cmd, arg);
return -ENOTTY;
}
static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
if (pde_is_permanent(pde)) {
return pde_ioctl(pde, file, cmd, arg);
} else if (use_pde(pde)) {
rv = pde_ioctl(pde, file, cmd, arg);
unuse_pde(pde);
}
return rv;
}
#ifdef CONFIG_COMPAT
static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
{
typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
compat_ioctl = pde->proc_ops->proc_compat_ioctl;
if (compat_ioctl)
return compat_ioctl(file, cmd, arg);
return -ENOTTY;
}
static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
if (pde_is_permanent(pde)) {
return pde_compat_ioctl(pde, file, cmd, arg);
} else if (use_pde(pde)) {
rv = pde_compat_ioctl(pde, file, cmd, arg);
unuse_pde(pde);
}
return rv;
}
#endif
static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma)
{
typeof_member(struct proc_ops, proc_mmap) mmap;
mmap = pde->proc_ops->proc_mmap;
if (mmap)
return mmap(file, vma);
return -EIO;
}
static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
int rv = -EIO;
if (pde_is_permanent(pde)) {
return pde_mmap(pde, file, vma);
} else if (use_pde(pde)) {
rv = pde_mmap(pde, file, vma);
unuse_pde(pde);
}
return rv;
}
static unsigned long
pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr,
unsigned long len, unsigned long pgoff,
unsigned long flags)
{
typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
get_area = pde->proc_ops->proc_get_unmapped_area;
#ifdef CONFIG_MMU
if (!get_area)
get_area = current->mm->get_unmapped_area;
#endif
if (get_area)
return get_area(file, orig_addr, len, pgoff, flags);
return orig_addr;
}
static unsigned long
proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
unsigned long len, unsigned long pgoff,
unsigned long flags)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
unsigned long rv = -EIO;
if (pde_is_permanent(pde)) {
return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
} else if (use_pde(pde)) {
rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
unuse_pde(pde);
}
return rv;
}
static int proc_reg_open(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
typeof_member(struct proc_ops, proc_open) open;
typeof_member(struct proc_ops, proc_release) release;
struct pde_opener *pdeo;
if (!pde->proc_ops->proc_lseek)
file->f_mode &= ~FMODE_LSEEK;
if (pde_is_permanent(pde)) {
open = pde->proc_ops->proc_open;
if (open)
rv = open(inode, file);
return rv;
}
/*
* Ensure that
* 1) PDE's ->release hook will be called no matter what
* either normally by close()/->release, or forcefully by
* rmmod/remove_proc_entry.
*
* 2) rmmod isn't blocked by opening file in /proc and sitting on
* the descriptor (including "rmmod foo </proc/foo" scenario).
*
* Save every "struct file" with custom ->release hook.
*/
if (!use_pde(pde))
return -ENOENT;
release = pde->proc_ops->proc_release;
if (release) {
pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
if (!pdeo) {
rv = -ENOMEM;
goto out_unuse;
}
}
open = pde->proc_ops->proc_open;
if (open)
rv = open(inode, file);
if (release) {
if (rv == 0) {
/* To know what to release. */
pdeo->file = file;
pdeo->closing = false;
pdeo->c = NULL;
spin_lock(&pde->pde_unload_lock);
list_add(&pdeo->lh, &pde->pde_openers);
spin_unlock(&pde->pde_unload_lock);
} else
kmem_cache_free(pde_opener_cache, pdeo);
}
out_unuse:
unuse_pde(pde);
return rv;
}
static int proc_reg_release(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
struct pde_opener *pdeo;
if (pde_is_permanent(pde)) {
typeof_member(struct proc_ops, proc_release) release;
release = pde->proc_ops->proc_release;
if (release) {
return release(inode, file);
}
return 0;
}
spin_lock(&pde->pde_unload_lock);
list_for_each_entry(pdeo, &pde->pde_openers, lh) {
if (pdeo->file == file) {
close_pdeo(pde, pdeo);
return 0;
}
}
spin_unlock(&pde->pde_unload_lock);
return 0;
}
static const struct file_operations proc_reg_file_ops = {
.llseek = proc_reg_llseek,
.read = proc_reg_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
.get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
static const struct file_operations proc_iter_file_ops = {
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
.write = proc_reg_write,
.splice_read = copy_splice_read,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
.get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
#ifdef CONFIG_COMPAT
static const struct file_operations proc_reg_file_ops_compat = {
.llseek = proc_reg_llseek,
.read = proc_reg_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.compat_ioctl = proc_reg_compat_ioctl,
.mmap = proc_reg_mmap,
.get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
static const struct file_operations proc_iter_file_ops_compat = {
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
.splice_read = copy_splice_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.compat_ioctl = proc_reg_compat_ioctl,
.mmap = proc_reg_mmap,
.get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
#endif
static void proc_put_link(void *p)
{
unuse_pde(p);
}
static const char *proc_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
struct proc_dir_entry *pde = PDE(inode);
if (!use_pde(pde))
return ERR_PTR(-EINVAL);
set_delayed_call(done, proc_put_link, pde);
return pde->data;
}
const struct inode_operations proc_link_inode_operations = {
.get_link = proc_get_link,
};
struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
{
struct inode *inode = new_inode(sb);
if (!inode) {
pde_put(de);
return NULL;
}
inode->i_private = de->data;
inode->i_ino = de->low_ino;
simple_inode_init_ts(inode);
PROC_I(inode)->pde = de;
if (is_empty_pde(de)) {
make_empty_dir_inode(inode);
return inode;
}
if (de->mode) {
inode->i_mode = de->mode;
inode->i_uid = de->uid;
inode->i_gid = de->gid;
}
if (de->size)
inode->i_size = de->size;
if (de->nlink)
set_nlink(inode, de->nlink);
if (S_ISREG(inode->i_mode)) {
inode->i_op = de->proc_iops;
if (de->proc_ops->proc_read_iter)
inode->i_fop = &proc_iter_file_ops;
else
inode->i_fop = &proc_reg_file_ops;
#ifdef CONFIG_COMPAT
if (de->proc_ops->proc_compat_ioctl) {
if (de->proc_ops->proc_read_iter)
inode->i_fop = &proc_iter_file_ops_compat;
else
inode->i_fop = &proc_reg_file_ops_compat;
}
#endif
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = de->proc_iops;
inode->i_fop = de->proc_dir_ops;
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = de->proc_iops;
inode->i_fop = NULL;
} else {
BUG();
}
return inode;
}
|