summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/locking.c
blob: d7e6baf1b2054f1998608902385bc5016020c2cf (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
/*
 * Copyright (C) 2008 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */
#include <linux/sched.h>
#include <linux/pagemap.h>
#include <linux/spinlock.h>
#include <linux/page-flags.h>
#include <asm/bug.h>
#include "ctree.h"
#include "extent_io.h"
#include "locking.h"

static void btrfs_assert_tree_read_locked(struct extent_buffer *eb);

/*
 * if we currently have a spinning reader or writer lock
 * (indicated by the rw flag) this will bump the count
 * of blocking holders and drop the spinlock.
 */
void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
	/*
	 * no lock is required.  The lock owner may change if
	 * we have a read lock, but it won't change to or away
	 * from us.  If we have the write lock, we are the owner
	 * and it'll never change.
	 */
	if (eb->lock_nested && current->pid == eb->lock_owner)
		return;
	if (rw == BTRFS_WRITE_LOCK) {
		if (atomic_read(&eb->blocking_writers) == 0) {
			WARN_ON(atomic_read(&eb->spinning_writers) != 1);
			atomic_dec(&eb->spinning_writers);
			btrfs_assert_tree_locked(eb);
			atomic_inc(&eb->blocking_writers);
			write_unlock(&eb->lock);
		}
	} else if (rw == BTRFS_READ_LOCK) {
		btrfs_assert_tree_read_locked(eb);
		atomic_inc(&eb->blocking_readers);
		WARN_ON(atomic_read(&eb->spinning_readers) == 0);
		atomic_dec(&eb->spinning_readers);
		read_unlock(&eb->lock);
	}
	return;
}

/*
 * if we currently have a blocking lock, take the spinlock
 * and drop our blocking count
 */
void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
	/*
	 * no lock is required.  The lock owner may change if
	 * we have a read lock, but it won't change to or away
	 * from us.  If we have the write lock, we are the owner
	 * and it'll never change.
	 */
	if (eb->lock_nested && current->pid == eb->lock_owner)
		return;

	if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
		BUG_ON(atomic_read(&eb->blocking_writers) != 1);
		write_lock(&eb->lock);
		WARN_ON(atomic_read(&eb->spinning_writers));
		atomic_inc(&eb->spinning_writers);
		if (atomic_dec_and_test(&eb->blocking_writers) &&
		    waitqueue_active(&eb->write_lock_wq))
			wake_up(&eb->write_lock_wq);
	} else if (rw == BTRFS_READ_LOCK_BLOCKING) {
		BUG_ON(atomic_read(&eb->blocking_readers) == 0);
		read_lock(&eb->lock);
		atomic_inc(&eb->spinning_readers);
		if (atomic_dec_and_test(&eb->blocking_readers) &&
		    waitqueue_active(&eb->read_lock_wq))
			wake_up(&eb->read_lock_wq);
	}
	return;
}

/*
 * take a spinning read lock.  This will wait for any blocking
 * writers
 */
void btrfs_tree_read_lock(struct extent_buffer *eb)
{
again:
	BUG_ON(!atomic_read(&eb->blocking_writers) &&
	       current->pid == eb->lock_owner);

	read_lock(&eb->lock);
	if (atomic_read(&eb->blocking_writers) &&
	    current->pid == eb->lock_owner) {
		/*
		 * This extent is already write-locked by our thread. We allow
		 * an additional read lock to be added because it's for the same
		 * thread. btrfs_find_all_roots() depends on this as it may be
		 * called on a partly (write-)locked tree.
		 */
		BUG_ON(eb->lock_nested);
		eb->lock_nested = 1;
		read_unlock(&eb->lock);
		return;
	}
	if (atomic_read(&eb->blocking_writers)) {
		read_unlock(&eb->lock);
		wait_event(eb->write_lock_wq,
			   atomic_read(&eb->blocking_writers) == 0);
		goto again;
	}
	atomic_inc(&eb->read_locks);
	atomic_inc(&eb->spinning_readers);
}

/*
 * take a spinning read lock.
 * returns 1 if we get the read lock and 0 if we don't
 * this won't wait for blocking writers
 */
int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
{
	if (atomic_read(&eb->blocking_writers))
		return 0;

	read_lock(&eb->lock);
	if (atomic_read(&eb->blocking_writers)) {
		read_unlock(&eb->lock);
		return 0;
	}
	atomic_inc(&eb->read_locks);
	atomic_inc(&eb->spinning_readers);
	return 1;
}

/*
 * returns 1 if we get the read lock and 0 if we don't
 * this won't wait for blocking writers
 */
int btrfs_try_tree_read_lock(struct extent_buffer *eb)
{
	if (atomic_read(&eb->blocking_writers))
		return 0;

	if (!read_trylock(&eb->lock))
		return 0;

	if (atomic_read(&eb->blocking_writers)) {
		read_unlock(&eb->lock);
		return 0;
	}
	atomic_inc(&eb->read_locks);
	atomic_inc(&eb->spinning_readers);
	return 1;
}

/*
 * returns 1 if we get the read lock and 0 if we don't
 * this won't wait for blocking writers or readers
 */
int btrfs_try_tree_write_lock(struct extent_buffer *eb)
{
	if (atomic_read(&eb->blocking_writers) ||
	    atomic_read(&eb->blocking_readers))
		return 0;

	write_lock(&eb->lock);
	if (atomic_read(&eb->blocking_writers) ||
	    atomic_read(&eb->blocking_readers)) {
		write_unlock(&eb->lock);
		return 0;
	}
	atomic_inc(&eb->write_locks);
	atomic_inc(&eb->spinning_writers);
	eb->lock_owner = current->pid;
	return 1;
}

/*
 * drop a spinning read lock
 */
void btrfs_tree_read_unlock(struct extent_buffer *eb)
{
	/*
	 * if we're nested, we have the write lock.  No new locking
	 * is needed as long as we are the lock owner.
	 * The write unlock will do a barrier for us, and the lock_nested
	 * field only matters to the lock owner.
	 */
	if (eb->lock_nested && current->pid == eb->lock_owner) {
		eb->lock_nested = 0;
		return;
	}
	btrfs_assert_tree_read_locked(eb);
	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
	atomic_dec(&eb->spinning_readers);
	atomic_dec(&eb->read_locks);
	read_unlock(&eb->lock);
}

/*
 * drop a blocking read lock
 */
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
{
	/*
	 * if we're nested, we have the write lock.  No new locking
	 * is needed as long as we are the lock owner.
	 * The write unlock will do a barrier for us, and the lock_nested
	 * field only matters to the lock owner.
	 */
	if (eb->lock_nested && current->pid == eb->lock_owner) {
		eb->lock_nested = 0;
		return;
	}
	btrfs_assert_tree_read_locked(eb);
	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
	if (atomic_dec_and_test(&eb->blocking_readers) &&
	    waitqueue_active(&eb->read_lock_wq))
		wake_up(&eb->read_lock_wq);
	atomic_dec(&eb->read_locks);
}

/*
 * take a spinning write lock.  This will wait for both
 * blocking readers or writers
 */
void btrfs_tree_lock(struct extent_buffer *eb)
{
	WARN_ON(eb->lock_owner == current->pid);
again:
	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
	wait_event(eb->write_lock_wq, atomic_read(&eb->blocking_writers) == 0);
	write_lock(&eb->lock);
	if (atomic_read(&eb->blocking_readers)) {
		write_unlock(&eb->lock);
		wait_event(eb->read_lock_wq,
			   atomic_read(&eb->blocking_readers) == 0);
		goto again;
	}
	if (atomic_read(&eb->blocking_writers)) {
		write_unlock(&eb->lock);
		wait_event(eb->write_lock_wq,
			   atomic_read(&eb->blocking_writers) == 0);
		goto again;
	}
	WARN_ON(atomic_read(&eb->spinning_writers));
	atomic_inc(&eb->spinning_writers);
	atomic_inc(&eb->write_locks);
	eb->lock_owner = current->pid;
}

/*
 * drop a spinning or a blocking write lock.
 */
void btrfs_tree_unlock(struct extent_buffer *eb)
{
	int blockers = atomic_read(&eb->blocking_writers);

	BUG_ON(blockers > 1);

	btrfs_assert_tree_locked(eb);
	eb->lock_owner = 0;
	atomic_dec(&eb->write_locks);

	if (blockers) {
		WARN_ON(atomic_read(&eb->spinning_writers));
		atomic_dec(&eb->blocking_writers);
		smp_mb();
		if (waitqueue_active(&eb->write_lock_wq))
			wake_up(&eb->write_lock_wq);
	} else {
		WARN_ON(atomic_read(&eb->spinning_writers) != 1);
		atomic_dec(&eb->spinning_writers);
		write_unlock(&eb->lock);
	}
}

void btrfs_assert_tree_locked(struct extent_buffer *eb)
{
	BUG_ON(!atomic_read(&eb->write_locks));
}

static void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
{
	BUG_ON(!atomic_read(&eb->read_locks));
}