summaryrefslogtreecommitdiff
path: root/kernel/watch_queue.c
blob: 230038d4f90818843b5ff69274fea1aa14f5d6ac (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
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
// SPDX-License-Identifier: GPL-2.0
/* Watch queue and general notification mechanism, built on pipes
 *
 * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * See Documentation/watch_queue.rst
 */

#define pr_fmt(fmt) "watchq: " fmt
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/printk.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/poll.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/file.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/sched/signal.h>
#include <linux/watch_queue.h>
#include <linux/pipe_fs_i.h>

MODULE_DESCRIPTION("Watch queue");
MODULE_AUTHOR("Red Hat, Inc.");
MODULE_LICENSE("GPL");

#define WATCH_QUEUE_NOTE_SIZE 128
#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)

static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
					 struct pipe_buffer *buf)
{
	struct watch_queue *wqueue = (struct watch_queue *)buf->private;
	struct page *page;
	unsigned int bit;

	/* We need to work out which note within the page this refers to, but
	 * the note might have been maximum size, so merely ANDing the offset
	 * off doesn't work.  OTOH, the note must've been more than zero size.
	 */
	bit = buf->offset + buf->len;
	if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0)
		bit -= WATCH_QUEUE_NOTE_SIZE;
	bit /= WATCH_QUEUE_NOTE_SIZE;

	page = buf->page;
	bit += page->index;

	set_bit(bit, wqueue->notes_bitmap);
	generic_pipe_buf_release(pipe, buf);
}

// No try_steal function => no stealing
#define watch_queue_pipe_buf_try_steal NULL

/* New data written to a pipe may be appended to a buffer with this type. */
static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
	.release	= watch_queue_pipe_buf_release,
	.try_steal	= watch_queue_pipe_buf_try_steal,
	.get		= generic_pipe_buf_get,
};

/*
 * Post a notification to a watch queue.
 */
static bool post_one_notification(struct watch_queue *wqueue,
				  struct watch_notification *n)
{
	void *p;
	struct pipe_inode_info *pipe = wqueue->pipe;
	struct pipe_buffer *buf;
	struct page *page;
	unsigned int head, tail, mask, note, offset, len;
	bool done = false;

	if (!pipe)
		return false;

	spin_lock_irq(&pipe->rd_wait.lock);

	if (wqueue->defunct)
		goto out;

	mask = pipe->ring_size - 1;
	head = pipe->head;
	tail = pipe->tail;
	if (pipe_full(head, tail, pipe->ring_size))
		goto lost;

	note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes);
	if (note >= wqueue->nr_notes)
		goto lost;

	page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE];
	offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE;
	get_page(page);
	len = n->info & WATCH_INFO_LENGTH;
	p = kmap_atomic(page);
	memcpy(p + offset, n, len);
	kunmap_atomic(p);

	buf = &pipe->bufs[head & mask];
	buf->page = page;
	buf->private = (unsigned long)wqueue;
	buf->ops = &watch_queue_pipe_buf_ops;
	buf->offset = offset;
	buf->len = len;
	buf->flags = PIPE_BUF_FLAG_WHOLE;
	smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */

	if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
		spin_unlock_irq(&pipe->rd_wait.lock);
		BUG();
	}
	wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
	done = true;

out:
	spin_unlock_irq(&pipe->rd_wait.lock);
	if (done)
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
	return done;

lost:
	buf = &pipe->bufs[(head - 1) & mask];
	buf->flags |= PIPE_BUF_FLAG_LOSS;
	goto out;
}

/*
 * Apply filter rules to a notification.
 */
static bool filter_watch_notification(const struct watch_filter *wf,
				      const struct watch_notification *n)
{
	const struct watch_type_filter *wt;
	unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8;
	unsigned int st_index = n->subtype / st_bits;
	unsigned int st_bit = 1U << (n->subtype % st_bits);
	int i;

	if (!test_bit(n->type, wf->type_filter))
		return false;

	for (i = 0; i < wf->nr_filters; i++) {
		wt = &wf->filters[i];
		if (n->type == wt->type &&
		    (wt->subtype_filter[st_index] & st_bit) &&
		    (n->info & wt->info_mask) == wt->info_filter)
			return true;
	}

	return false; /* If there is a filter, the default is to reject. */
}

/**
 * __post_watch_notification - Post an event notification
 * @wlist: The watch list to post the event to.
 * @n: The notification record to post.
 * @cred: The creds of the process that triggered the notification.
 * @id: The ID to match on the watch.
 *
 * Post a notification of an event into a set of watch queues and let the users
 * know.
 *
 * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and
 * should be in units of sizeof(*n).
 */
void __post_watch_notification(struct watch_list *wlist,
			       struct watch_notification *n,
			       const struct cred *cred,
			       u64 id)
{
	const struct watch_filter *wf;
	struct watch_queue *wqueue;
	struct watch *watch;

	if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) {
		WARN_ON(1);
		return;
	}

	rcu_read_lock();

	hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) {
		if (watch->id != id)
			continue;
		n->info &= ~WATCH_INFO_ID;
		n->info |= watch->info_id;

		wqueue = rcu_dereference(watch->queue);
		wf = rcu_dereference(wqueue->filter);
		if (wf && !filter_watch_notification(wf, n))
			continue;

		if (security_post_notification(watch->cred, cred, n) < 0)
			continue;

		post_one_notification(wqueue, n);
	}

	rcu_read_unlock();
}
EXPORT_SYMBOL(__post_watch_notification);

/*
 * Allocate sufficient pages to preallocation for the requested number of
 * notifications.
 */
long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
{
	struct watch_queue *wqueue = pipe->watch_queue;
	struct page **pages;
	unsigned long *bitmap;
	unsigned long user_bufs;
	int ret, i, nr_pages;

	if (!wqueue)
		return -ENODEV;
	if (wqueue->notes)
		return -EBUSY;

	if (nr_notes < 1 ||
	    nr_notes > 512) /* TODO: choose a better hard limit */
		return -EINVAL;

	nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1);
	nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE;
	user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages);

	if (nr_pages > pipe->max_usage &&
	    (too_many_pipe_buffers_hard(user_bufs) ||
	     too_many_pipe_buffers_soft(user_bufs)) &&
	    pipe_is_unprivileged_user()) {
		ret = -EPERM;
		goto error;
	}

	nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
	ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes));
	if (ret < 0)
		goto error;

	pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
	if (!pages)
		goto error;

	for (i = 0; i < nr_pages; i++) {
		pages[i] = alloc_page(GFP_KERNEL);
		if (!pages[i])
			goto error_p;
		pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE;
	}

	bitmap = bitmap_alloc(nr_notes, GFP_KERNEL);
	if (!bitmap)
		goto error_p;

	bitmap_fill(bitmap, nr_notes);
	wqueue->notes = pages;
	wqueue->notes_bitmap = bitmap;
	wqueue->nr_pages = nr_pages;
	wqueue->nr_notes = nr_notes;
	return 0;

error_p:
	while (--i >= 0)
		__free_page(pages[i]);
	kfree(pages);
error:
	(void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted);
	return ret;
}

/*
 * Set the filter on a watch queue.
 */
long watch_queue_set_filter(struct pipe_inode_info *pipe,
			    struct watch_notification_filter __user *_filter)
{
	struct watch_notification_type_filter *tf;
	struct watch_notification_filter filter;
	struct watch_type_filter *q;
	struct watch_filter *wfilter;
	struct watch_queue *wqueue = pipe->watch_queue;
	int ret, nr_filter = 0, i;

	if (!wqueue)
		return -ENODEV;

	if (!_filter) {
		/* Remove the old filter */
		wfilter = NULL;
		goto set;
	}

	/* Grab the user's filter specification */
	if (copy_from_user(&filter, _filter, sizeof(filter)) != 0)
		return -EFAULT;
	if (filter.nr_filters == 0 ||
	    filter.nr_filters > 16 ||
	    filter.__reserved != 0)
		return -EINVAL;

	tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf));
	if (IS_ERR(tf))
		return PTR_ERR(tf);

	ret = -EINVAL;
	for (i = 0; i < filter.nr_filters; i++) {
		if ((tf[i].info_filter & ~tf[i].info_mask) ||
		    tf[i].info_mask & WATCH_INFO_LENGTH)
			goto err_filter;
		/* Ignore any unknown types */
		if (tf[i].type >= WATCH_TYPE__NR)
			continue;
		nr_filter++;
	}

	/* Now we need to build the internal filter from only the relevant
	 * user-specified filters.
	 */
	ret = -ENOMEM;
	wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL);
	if (!wfilter)
		goto err_filter;
	wfilter->nr_filters = nr_filter;

	q = wfilter->filters;
	for (i = 0; i < filter.nr_filters; i++) {
		if (tf[i].type >= WATCH_TYPE__NR)
			continue;

		q->type			= tf[i].type;
		q->info_filter		= tf[i].info_filter;
		q->info_mask		= tf[i].info_mask;
		q->subtype_filter[0]	= tf[i].subtype_filter[0];
		__set_bit(q->type, wfilter->type_filter);
		q++;
	}

	kfree(tf);
set:
	pipe_lock(pipe);
	wfilter = rcu_replace_pointer(wqueue->filter, wfilter,
				      lockdep_is_held(&pipe->mutex));
	pipe_unlock(pipe);
	if (wfilter)
		kfree_rcu(wfilter, rcu);
	return 0;

err_filter:
	kfree(tf);
	return ret;
}

static void __put_watch_queue(struct kref *kref)
{
	struct watch_queue *wqueue =
		container_of(kref, struct watch_queue, usage);
	struct watch_filter *wfilter;
	int i;

	for (i = 0; i < wqueue->nr_pages; i++)
		__free_page(wqueue->notes[i]);
	kfree(wqueue->notes);
	bitmap_free(wqueue->notes_bitmap);

	wfilter = rcu_access_pointer(wqueue->filter);
	if (wfilter)
		kfree_rcu(wfilter, rcu);
	kfree_rcu(wqueue, rcu);
}

/**
 * put_watch_queue - Dispose of a ref on a watchqueue.
 * @wqueue: The watch queue to unref.
 */
void put_watch_queue(struct watch_queue *wqueue)
{
	kref_put(&wqueue->usage, __put_watch_queue);
}
EXPORT_SYMBOL(put_watch_queue);

static void free_watch(struct rcu_head *rcu)
{
	struct watch *watch = container_of(rcu, struct watch, rcu);

	put_watch_queue(rcu_access_pointer(watch->queue));
	atomic_dec(&watch->cred->user->nr_watches);
	put_cred(watch->cred);
	kfree(watch);
}

static void __put_watch(struct kref *kref)
{
	struct watch *watch = container_of(kref, struct watch, usage);

	call_rcu(&watch->rcu, free_watch);
}

/*
 * Discard a watch.
 */
static void put_watch(struct watch *watch)
{
	kref_put(&watch->usage, __put_watch);
}

/**
 * init_watch - Initialise a watch
 * @watch: The watch to initialise.
 * @wqueue: The queue to assign.
 *
 * Initialise a watch and set the watch queue.
 */
void init_watch(struct watch *watch, struct watch_queue *wqueue)
{
	kref_init(&watch->usage);
	INIT_HLIST_NODE(&watch->list_node);
	INIT_HLIST_NODE(&watch->queue_node);
	rcu_assign_pointer(watch->queue, wqueue);
}

/**
 * add_watch_to_object - Add a watch on an object to a watch list
 * @watch: The watch to add
 * @wlist: The watch list to add to
 *
 * @watch->queue must have been set to point to the queue to post notifications
 * to and the watch list of the object to be watched.  @watch->cred must also
 * have been set to the appropriate credentials and a ref taken on them.
 *
 * The caller must pin the queue and the list both and must hold the list
 * locked against racing watch additions/removals.
 */
int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
{
	struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
	struct watch *w;

	hlist_for_each_entry(w, &wlist->watchers, list_node) {
		struct watch_queue *wq = rcu_access_pointer(w->queue);
		if (wqueue == wq && watch->id == w->id)
			return -EBUSY;
	}

	watch->cred = get_current_cred();
	rcu_assign_pointer(watch->watch_list, wlist);

	if (atomic_inc_return(&watch->cred->user->nr_watches) >
	    task_rlimit(current, RLIMIT_NOFILE)) {
		atomic_dec(&watch->cred->user->nr_watches);
		put_cred(watch->cred);
		return -EAGAIN;
	}

	spin_lock_bh(&wqueue->lock);
	kref_get(&wqueue->usage);
	kref_get(&watch->usage);
	hlist_add_head(&watch->queue_node, &wqueue->watches);
	spin_unlock_bh(&wqueue->lock);

	hlist_add_head(&watch->list_node, &wlist->watchers);
	return 0;
}
EXPORT_SYMBOL(add_watch_to_object);

/**
 * remove_watch_from_object - Remove a watch or all watches from an object.
 * @wlist: The watch list to remove from
 * @wq: The watch queue of interest (ignored if @all is true)
 * @id: The ID of the watch to remove (ignored if @all is true)
 * @all: True to remove all objects
 *
 * Remove a specific watch or all watches from an object.  A notification is
 * sent to the watcher to tell them that this happened.
 */
int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq,
			     u64 id, bool all)
{
	struct watch_notification_removal n;
	struct watch_queue *wqueue;
	struct watch *watch;
	int ret = -EBADSLT;

	rcu_read_lock();

again:
	spin_lock(&wlist->lock);
	hlist_for_each_entry(watch, &wlist->watchers, list_node) {
		if (all ||
		    (watch->id == id && rcu_access_pointer(watch->queue) == wq))
			goto found;
	}
	spin_unlock(&wlist->lock);
	goto out;

found:
	ret = 0;
	hlist_del_init_rcu(&watch->list_node);
	rcu_assign_pointer(watch->watch_list, NULL);
	spin_unlock(&wlist->lock);

	/* We now own the reference on watch that used to belong to wlist. */

	n.watch.type = WATCH_TYPE_META;
	n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION;
	n.watch.info = watch->info_id | watch_sizeof(n.watch);
	n.id = id;
	if (id != 0)
		n.watch.info = watch->info_id | watch_sizeof(n);

	wqueue = rcu_dereference(watch->queue);

	/* We don't need the watch list lock for the next bit as RCU is
	 * protecting *wqueue from deallocation.
	 */
	if (wqueue) {
		post_one_notification(wqueue, &n.watch);

		spin_lock_bh(&wqueue->lock);

		if (!hlist_unhashed(&watch->queue_node)) {
			hlist_del_init_rcu(&watch->queue_node);
			put_watch(watch);
		}

		spin_unlock_bh(&wqueue->lock);
	}

	if (wlist->release_watch) {
		void (*release_watch)(struct watch *);

		release_watch = wlist->release_watch;
		rcu_read_unlock();
		(*release_watch)(watch);
		rcu_read_lock();
	}
	put_watch(watch);

	if (all && !hlist_empty(&wlist->watchers))
		goto again;
out:
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL(remove_watch_from_object);

/*
 * Remove all the watches that are contributory to a queue.  This has the
 * potential to race with removal of the watches by the destruction of the
 * objects being watched or with the distribution of notifications.
 */
void watch_queue_clear(struct watch_queue *wqueue)
{
	struct watch_list *wlist;
	struct watch *watch;
	bool release;

	rcu_read_lock();
	spin_lock_bh(&wqueue->lock);

	/* Prevent new notifications from being stored. */
	wqueue->defunct = true;

	while (!hlist_empty(&wqueue->watches)) {
		watch = hlist_entry(wqueue->watches.first, struct watch, queue_node);
		hlist_del_init_rcu(&watch->queue_node);
		/* We now own a ref on the watch. */
		spin_unlock_bh(&wqueue->lock);

		/* We can't do the next bit under the queue lock as we need to
		 * get the list lock - which would cause a deadlock if someone
		 * was removing from the opposite direction at the same time or
		 * posting a notification.
		 */
		wlist = rcu_dereference(watch->watch_list);
		if (wlist) {
			void (*release_watch)(struct watch *);

			spin_lock(&wlist->lock);

			release = !hlist_unhashed(&watch->list_node);
			if (release) {
				hlist_del_init_rcu(&watch->list_node);
				rcu_assign_pointer(watch->watch_list, NULL);

				/* We now own a second ref on the watch. */
			}

			release_watch = wlist->release_watch;
			spin_unlock(&wlist->lock);

			if (release) {
				if (release_watch) {
					rcu_read_unlock();
					/* This might need to call dput(), so
					 * we have to drop all the locks.
					 */
					(*release_watch)(watch);
					rcu_read_lock();
				}
				put_watch(watch);
			}
		}

		put_watch(watch);
		spin_lock_bh(&wqueue->lock);
	}

	spin_unlock_bh(&wqueue->lock);
	rcu_read_unlock();
}

/**
 * get_watch_queue - Get a watch queue from its file descriptor.
 * @fd: The fd to query.
 */
struct watch_queue *get_watch_queue(int fd)
{
	struct pipe_inode_info *pipe;
	struct watch_queue *wqueue = ERR_PTR(-EINVAL);
	struct fd f;

	f = fdget(fd);
	if (f.file) {
		pipe = get_pipe_info(f.file, false);
		if (pipe && pipe->watch_queue) {
			wqueue = pipe->watch_queue;
			kref_get(&wqueue->usage);
		}
		fdput(f);
	}

	return wqueue;
}
EXPORT_SYMBOL(get_watch_queue);

/*
 * Initialise a watch queue
 */
int watch_queue_init(struct pipe_inode_info *pipe)
{
	struct watch_queue *wqueue;

	wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL);
	if (!wqueue)
		return -ENOMEM;

	wqueue->pipe = pipe;
	kref_init(&wqueue->usage);
	spin_lock_init(&wqueue->lock);
	INIT_HLIST_HEAD(&wqueue->watches);

	pipe->watch_queue = wqueue;
	return 0;
}