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
|
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2010 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
/*
* Copyright (c) 2012 by Delphix. All rights reserved.
*/
/*
* This file contains the code to implement file range locking in
* ZFS, although there isn't much specific to ZFS (all that comes to mind
* support for growing the blocksize).
*
* Interface
* ---------
* Defined in zfs_rlock.h but essentially:
* rl = zfs_range_lock(zp, off, len, lock_type);
* zfs_range_unlock(rl);
* zfs_range_reduce(rl, off, len);
*
* AVL tree
* --------
* An AVL tree is used to maintain the state of the existing ranges
* that are locked for exclusive (writer) or shared (reader) use.
* The starting range offset is used for searching and sorting the tree.
*
* Common case
* -----------
* The (hopefully) usual case is of no overlaps or contention for
* locks. On entry to zfs_lock_range() a rl_t is allocated; the tree
* searched that finds no overlap, and *this* rl_t is placed in the tree.
*
* Overlaps/Reference counting/Proxy locks
* ---------------------------------------
* The avl code only allows one node at a particular offset. Also it's very
* inefficient to search through all previous entries looking for overlaps
* (because the very 1st in the ordered list might be at offset 0 but
* cover the whole file).
* So this implementation uses reference counts and proxy range locks.
* Firstly, only reader locks use reference counts and proxy locks,
* because writer locks are exclusive.
* When a reader lock overlaps with another then a proxy lock is created
* for that range and replaces the original lock. If the overlap
* is exact then the reference count of the proxy is simply incremented.
* Otherwise, the proxy lock is split into smaller lock ranges and
* new proxy locks created for non overlapping ranges.
* The reference counts are adjusted accordingly.
* Meanwhile, the orginal lock is kept around (this is the callers handle)
* and its offset and length are used when releasing the lock.
*
* Thread coordination
* -------------------
* In order to make wakeups efficient and to ensure multiple continuous
* readers on a range don't starve a writer for the same range lock,
* two condition variables are allocated in each rl_t.
* If a writer (or reader) can't get a range it initialises the writer
* (or reader) cv; sets a flag saying there's a writer (or reader) waiting;
* and waits on that cv. When a thread unlocks that range it wakes up all
* writers then all readers before destroying the lock.
*
* Append mode writes
* ------------------
* Append mode writes need to lock a range at the end of a file.
* The offset of the end of the file is determined under the
* range locking mutex, and the lock type converted from RL_APPEND to
* RL_WRITER and the range locked.
*
* Grow block handling
* -------------------
* ZFS supports multiple block sizes currently upto 128K. The smallest
* block size is used for the file which is grown as needed. During this
* growth all other writers and readers must be excluded.
* So if the block size needs to be grown then the whole file is
* exclusively locked, then later the caller will reduce the lock
* range to just the range to be written using zfs_reduce_range.
*/
#include <sys/zfs_rlock.h>
/*
* Check if a write lock can be grabbed, or wait and recheck until available.
*/
static void
zfs_range_lock_writer(znode_t *zp, rl_t *new)
{
avl_tree_t *tree = &zp->z_range_avl;
rl_t *rl;
avl_index_t where;
uint64_t end_size;
uint64_t off = new->r_off;
uint64_t len = new->r_len;
for (;;) {
/*
* Range locking is also used by zvol and uses a
* dummied up znode. However, for zvol, we don't need to
* append or grow blocksize, and besides we don't have
* a "sa" data or z_zfsvfs - so skip that processing.
*
* Yes, this is ugly, and would be solved by not handling
* grow or append in range lock code. If that was done then
* we could make the range locking code generically available
* to other non-zfs consumers.
*/
if (zp->z_vnode) { /* caller is ZPL */
/*
* If in append mode pick up the current end of file.
* This is done under z_range_lock to avoid races.
*/
if (new->r_type == RL_APPEND)
new->r_off = zp->z_size;
/*
* If we need to grow the block size then grab the whole
* file range. This is also done under z_range_lock to
* avoid races.
*/
end_size = MAX(zp->z_size, new->r_off + len);
if (end_size > zp->z_blksz && (!ISP2(zp->z_blksz) ||
zp->z_blksz < zp->z_zfsvfs->z_max_blksz)) {
new->r_off = 0;
new->r_len = UINT64_MAX;
}
}
/*
* First check for the usual case of no locks
*/
if (avl_numnodes(tree) == 0) {
new->r_type = RL_WRITER; /* convert to writer */
avl_add(tree, new);
return;
}
/*
* Look for any locks in the range.
*/
rl = avl_find(tree, new, &where);
if (rl)
goto wait; /* already locked at same offset */
rl = (rl_t *)avl_nearest(tree, where, AVL_AFTER);
if (rl && (rl->r_off < new->r_off + new->r_len))
goto wait;
rl = (rl_t *)avl_nearest(tree, where, AVL_BEFORE);
if (rl && rl->r_off + rl->r_len > new->r_off)
goto wait;
new->r_type = RL_WRITER; /* convert possible RL_APPEND */
avl_insert(tree, new, where);
return;
wait:
if (!rl->r_write_wanted) {
cv_init(&rl->r_wr_cv, NULL, CV_DEFAULT, NULL);
rl->r_write_wanted = B_TRUE;
}
cv_wait(&rl->r_wr_cv, &zp->z_range_lock);
/* reset to original */
new->r_off = off;
new->r_len = len;
}
}
/*
* If this is an original (non-proxy) lock then replace it by
* a proxy and return the proxy.
*/
static rl_t *
zfs_range_proxify(avl_tree_t *tree, rl_t *rl)
{
rl_t *proxy;
if (rl->r_proxy)
return (rl); /* already a proxy */
ASSERT3U(rl->r_cnt, ==, 1);
ASSERT(rl->r_write_wanted == B_FALSE);
ASSERT(rl->r_read_wanted == B_FALSE);
avl_remove(tree, rl);
rl->r_cnt = 0;
/* create a proxy range lock */
proxy = kmem_alloc(sizeof (rl_t), KM_SLEEP);
proxy->r_off = rl->r_off;
proxy->r_len = rl->r_len;
proxy->r_cnt = 1;
proxy->r_type = RL_READER;
proxy->r_proxy = B_TRUE;
proxy->r_write_wanted = B_FALSE;
proxy->r_read_wanted = B_FALSE;
avl_add(tree, proxy);
return (proxy);
}
/*
* Split the range lock at the supplied offset
* returning the *front* proxy.
*/
static rl_t *
zfs_range_split(avl_tree_t *tree, rl_t *rl, uint64_t off)
{
rl_t *front, *rear;
ASSERT3U(rl->r_len, >, 1);
ASSERT3U(off, >, rl->r_off);
ASSERT3U(off, <, rl->r_off + rl->r_len);
ASSERT(rl->r_write_wanted == B_FALSE);
ASSERT(rl->r_read_wanted == B_FALSE);
/* create the rear proxy range lock */
rear = kmem_alloc(sizeof (rl_t), KM_SLEEP);
rear->r_off = off;
rear->r_len = rl->r_off + rl->r_len - off;
rear->r_cnt = rl->r_cnt;
rear->r_type = RL_READER;
rear->r_proxy = B_TRUE;
rear->r_write_wanted = B_FALSE;
rear->r_read_wanted = B_FALSE;
front = zfs_range_proxify(tree, rl);
front->r_len = off - rl->r_off;
avl_insert_here(tree, rear, front, AVL_AFTER);
return (front);
}
/*
* Create and add a new proxy range lock for the supplied range.
*/
static void
zfs_range_new_proxy(avl_tree_t *tree, uint64_t off, uint64_t len)
{
rl_t *rl;
ASSERT(len);
rl = kmem_alloc(sizeof (rl_t), KM_SLEEP);
rl->r_off = off;
rl->r_len = len;
rl->r_cnt = 1;
rl->r_type = RL_READER;
rl->r_proxy = B_TRUE;
rl->r_write_wanted = B_FALSE;
rl->r_read_wanted = B_FALSE;
avl_add(tree, rl);
}
static void
zfs_range_add_reader(avl_tree_t *tree, rl_t *new, rl_t *prev, avl_index_t where)
{
rl_t *next;
uint64_t off = new->r_off;
uint64_t len = new->r_len;
/*
* prev arrives either:
* - pointing to an entry at the same offset
* - pointing to the entry with the closest previous offset whose
* range may overlap with the new range
* - null, if there were no ranges starting before the new one
*/
if (prev) {
if (prev->r_off + prev->r_len <= off) {
prev = NULL;
} else if (prev->r_off != off) {
/*
* convert to proxy if needed then
* split this entry and bump ref count
*/
prev = zfs_range_split(tree, prev, off);
prev = AVL_NEXT(tree, prev); /* move to rear range */
}
}
ASSERT((prev == NULL) || (prev->r_off == off));
if (prev)
next = prev;
else
next = (rl_t *)avl_nearest(tree, where, AVL_AFTER);
if (next == NULL || off + len <= next->r_off) {
/* no overlaps, use the original new rl_t in the tree */
avl_insert(tree, new, where);
return;
}
if (off < next->r_off) {
/* Add a proxy for initial range before the overlap */
zfs_range_new_proxy(tree, off, next->r_off - off);
}
new->r_cnt = 0; /* will use proxies in tree */
/*
* We now search forward through the ranges, until we go past the end
* of the new range. For each entry we make it a proxy if it
* isn't already, then bump its reference count. If there's any
* gaps between the ranges then we create a new proxy range.
*/
for (prev = NULL; next; prev = next, next = AVL_NEXT(tree, next)) {
if (off + len <= next->r_off)
break;
if (prev && prev->r_off + prev->r_len < next->r_off) {
/* there's a gap */
ASSERT3U(next->r_off, >, prev->r_off + prev->r_len);
zfs_range_new_proxy(tree, prev->r_off + prev->r_len,
next->r_off - (prev->r_off + prev->r_len));
}
if (off + len == next->r_off + next->r_len) {
/* exact overlap with end */
next = zfs_range_proxify(tree, next);
next->r_cnt++;
return;
}
if (off + len < next->r_off + next->r_len) {
/* new range ends in the middle of this block */
next = zfs_range_split(tree, next, off + len);
next->r_cnt++;
return;
}
ASSERT3U(off + len, >, next->r_off + next->r_len);
next = zfs_range_proxify(tree, next);
next->r_cnt++;
}
/* Add the remaining end range. */
zfs_range_new_proxy(tree, prev->r_off + prev->r_len,
(off + len) - (prev->r_off + prev->r_len));
}
/*
* Check if a reader lock can be grabbed, or wait and recheck until available.
*/
static void
zfs_range_lock_reader(znode_t *zp, rl_t *new)
{
avl_tree_t *tree = &zp->z_range_avl;
rl_t *prev, *next;
avl_index_t where;
uint64_t off = new->r_off;
uint64_t len = new->r_len;
/*
* Look for any writer locks in the range.
*/
retry:
prev = avl_find(tree, new, &where);
if (prev == NULL)
prev = (rl_t *)avl_nearest(tree, where, AVL_BEFORE);
/*
* Check the previous range for a writer lock overlap.
*/
if (prev && (off < prev->r_off + prev->r_len)) {
if ((prev->r_type == RL_WRITER) || (prev->r_write_wanted)) {
if (!prev->r_read_wanted) {
cv_init(&prev->r_rd_cv, NULL, CV_DEFAULT, NULL);
prev->r_read_wanted = B_TRUE;
}
cv_wait(&prev->r_rd_cv, &zp->z_range_lock);
goto retry;
}
if (off + len < prev->r_off + prev->r_len)
goto got_lock;
}
/*
* Search through the following ranges to see if there's
* write lock any overlap.
*/
if (prev)
next = AVL_NEXT(tree, prev);
else
next = (rl_t *)avl_nearest(tree, where, AVL_AFTER);
for (; next; next = AVL_NEXT(tree, next)) {
if (off + len <= next->r_off)
goto got_lock;
if ((next->r_type == RL_WRITER) || (next->r_write_wanted)) {
if (!next->r_read_wanted) {
cv_init(&next->r_rd_cv, NULL, CV_DEFAULT, NULL);
next->r_read_wanted = B_TRUE;
}
cv_wait(&next->r_rd_cv, &zp->z_range_lock);
goto retry;
}
if (off + len <= next->r_off + next->r_len)
goto got_lock;
}
got_lock:
/*
* Add the read lock, which may involve splitting existing
* locks and bumping ref counts (r_cnt).
*/
zfs_range_add_reader(tree, new, prev, where);
}
/*
* Lock a range (offset, length) as either shared (RL_READER)
* or exclusive (RL_WRITER). Returns the range lock structure
* for later unlocking or reduce range (if entire file
* previously locked as RL_WRITER).
*/
rl_t *
zfs_range_lock(znode_t *zp, uint64_t off, uint64_t len, rl_type_t type)
{
rl_t *new;
ASSERT(type == RL_READER || type == RL_WRITER || type == RL_APPEND);
new = kmem_alloc(sizeof (rl_t), KM_SLEEP);
new->r_zp = zp;
new->r_off = off;
if (len + off < off) /* overflow */
len = UINT64_MAX - off;
new->r_len = len;
new->r_cnt = 1; /* assume it's going to be in the tree */
new->r_type = type;
new->r_proxy = B_FALSE;
new->r_write_wanted = B_FALSE;
new->r_read_wanted = B_FALSE;
mutex_enter(&zp->z_range_lock);
if (type == RL_READER) {
/*
* First check for the usual case of no locks
*/
if (avl_numnodes(&zp->z_range_avl) == 0)
avl_add(&zp->z_range_avl, new);
else
zfs_range_lock_reader(zp, new);
} else
zfs_range_lock_writer(zp, new); /* RL_WRITER or RL_APPEND */
mutex_exit(&zp->z_range_lock);
return (new);
}
/*
* Unlock a reader lock
*/
static void
zfs_range_unlock_reader(znode_t *zp, rl_t *remove)
{
avl_tree_t *tree = &zp->z_range_avl;
rl_t *rl, *next = NULL;
uint64_t len;
/*
* The common case is when the remove entry is in the tree
* (cnt == 1) meaning there's been no other reader locks overlapping
* with this one. Otherwise the remove entry will have been
* removed from the tree and replaced by proxies (one or
* more ranges mapping to the entire range).
*/
if (remove->r_cnt == 1) {
avl_remove(tree, remove);
if (remove->r_write_wanted) {
cv_broadcast(&remove->r_wr_cv);
cv_destroy(&remove->r_wr_cv);
}
if (remove->r_read_wanted) {
cv_broadcast(&remove->r_rd_cv);
cv_destroy(&remove->r_rd_cv);
}
} else {
ASSERT0(remove->r_cnt);
ASSERT0(remove->r_write_wanted);
ASSERT0(remove->r_read_wanted);
/*
* Find start proxy representing this reader lock,
* then decrement ref count on all proxies
* that make up this range, freeing them as needed.
*/
rl = avl_find(tree, remove, NULL);
ASSERT(rl);
ASSERT(rl->r_cnt);
ASSERT(rl->r_type == RL_READER);
for (len = remove->r_len; len != 0; rl = next) {
len -= rl->r_len;
if (len) {
next = AVL_NEXT(tree, rl);
ASSERT(next);
ASSERT(rl->r_off + rl->r_len == next->r_off);
ASSERT(next->r_cnt);
ASSERT(next->r_type == RL_READER);
}
rl->r_cnt--;
if (rl->r_cnt == 0) {
avl_remove(tree, rl);
if (rl->r_write_wanted) {
cv_broadcast(&rl->r_wr_cv);
cv_destroy(&rl->r_wr_cv);
}
if (rl->r_read_wanted) {
cv_broadcast(&rl->r_rd_cv);
cv_destroy(&rl->r_rd_cv);
}
kmem_free(rl, sizeof (rl_t));
}
}
}
kmem_free(remove, sizeof (rl_t));
}
/*
* Unlock range and destroy range lock structure.
*/
void
zfs_range_unlock(rl_t *rl)
{
znode_t *zp = rl->r_zp;
ASSERT(rl->r_type == RL_WRITER || rl->r_type == RL_READER);
ASSERT(rl->r_cnt == 1 || rl->r_cnt == 0);
ASSERT(!rl->r_proxy);
mutex_enter(&zp->z_range_lock);
if (rl->r_type == RL_WRITER) {
/* writer locks can't be shared or split */
avl_remove(&zp->z_range_avl, rl);
mutex_exit(&zp->z_range_lock);
if (rl->r_write_wanted) {
cv_broadcast(&rl->r_wr_cv);
cv_destroy(&rl->r_wr_cv);
}
if (rl->r_read_wanted) {
cv_broadcast(&rl->r_rd_cv);
cv_destroy(&rl->r_rd_cv);
}
kmem_free(rl, sizeof (rl_t));
} else {
/*
* lock may be shared, let zfs_range_unlock_reader()
* release the lock and free the rl_t
*/
zfs_range_unlock_reader(zp, rl);
mutex_exit(&zp->z_range_lock);
}
}
/*
* Reduce range locked as RL_WRITER from whole file to specified range.
* Asserts the whole file is exclusivly locked and so there's only one
* entry in the tree.
*/
void
zfs_range_reduce(rl_t *rl, uint64_t off, uint64_t len)
{
znode_t *zp = rl->r_zp;
/* Ensure there are no other locks */
ASSERT(avl_numnodes(&zp->z_range_avl) == 1);
ASSERT(rl->r_off == 0);
ASSERT(rl->r_type == RL_WRITER);
ASSERT(!rl->r_proxy);
ASSERT3U(rl->r_len, ==, UINT64_MAX);
ASSERT3U(rl->r_cnt, ==, 1);
mutex_enter(&zp->z_range_lock);
rl->r_off = off;
rl->r_len = len;
mutex_exit(&zp->z_range_lock);
if (rl->r_write_wanted)
cv_broadcast(&rl->r_wr_cv);
if (rl->r_read_wanted)
cv_broadcast(&rl->r_rd_cv);
}
/*
* AVL comparison function used to order range locks
* Locks are ordered on the start offset of the range.
*/
int
zfs_range_compare(const void *arg1, const void *arg2)
{
const rl_t *rl1 = arg1;
const rl_t *rl2 = arg2;
if (rl1->r_off > rl2->r_off)
return (1);
if (rl1->r_off < rl2->r_off)
return (-1);
return (0);
}
|