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
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2016-present, Facebook, Inc.
* All rights reserved.
*
*/
#include <linux/bio.h>
#include <linux/bitmap.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/pagemap.h>
#include <linux/refcount.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/zstd.h>
#include "compression.h"
#include "ctree.h"
#define ZSTD_BTRFS_MAX_WINDOWLOG 17
#define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
#define ZSTD_BTRFS_DEFAULT_LEVEL 3
#define ZSTD_BTRFS_MAX_LEVEL 15
/* 307s to avoid pathologically clashing with transaction commit */
#define ZSTD_BTRFS_RECLAIM_JIFFIES (307 * HZ)
static ZSTD_parameters zstd_get_btrfs_parameters(unsigned int level,
size_t src_len)
{
ZSTD_parameters params = ZSTD_getParams(level, src_len, 0);
if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT);
return params;
}
struct workspace {
void *mem;
size_t size;
char *buf;
unsigned int level;
unsigned int req_level;
unsigned long last_used; /* jiffies */
struct list_head list;
struct list_head lru_list;
ZSTD_inBuffer in_buf;
ZSTD_outBuffer out_buf;
};
/*
* Zstd Workspace Management
*
* Zstd workspaces have different memory requirements depending on the level.
* The zstd workspaces are managed by having individual lists for each level
* and a global lru. Forward progress is maintained by protecting a max level
* workspace.
*
* Getting a workspace is done by using the bitmap to identify the levels that
* have available workspaces and scans up. This lets us recycle higher level
* workspaces because of the monotonic memory guarantee. A workspace's
* last_used is only updated if it is being used by the corresponding memory
* level. Putting a workspace involves adding it back to the appropriate places
* and adding it back to the lru if necessary.
*
* A timer is used to reclaim workspaces if they have not been used for
* ZSTD_BTRFS_RECLAIM_JIFFIES. This helps keep only active workspaces around.
* The upper bound is provided by the workqueue limit which is 2 (percpu limit).
*/
struct zstd_workspace_manager {
const struct btrfs_compress_op *ops;
spinlock_t lock;
struct list_head lru_list;
struct list_head idle_ws[ZSTD_BTRFS_MAX_LEVEL];
unsigned long active_map;
wait_queue_head_t wait;
struct timer_list timer;
};
static struct zstd_workspace_manager wsm;
static size_t zstd_ws_mem_sizes[ZSTD_BTRFS_MAX_LEVEL];
static inline struct workspace *list_to_workspace(struct list_head *list)
{
return container_of(list, struct workspace, list);
}
static void zstd_free_workspace(struct list_head *ws);
static struct list_head *zstd_alloc_workspace(unsigned int level);
/*
* zstd_reclaim_timer_fn - reclaim timer
* @t: timer
*
* This scans the lru_list and attempts to reclaim any workspace that hasn't
* been used for ZSTD_BTRFS_RECLAIM_JIFFIES.
*/
static void zstd_reclaim_timer_fn(struct timer_list *timer)
{
unsigned long reclaim_threshold = jiffies - ZSTD_BTRFS_RECLAIM_JIFFIES;
struct list_head *pos, *next;
spin_lock(&wsm.lock);
if (list_empty(&wsm.lru_list)) {
spin_unlock(&wsm.lock);
return;
}
list_for_each_prev_safe(pos, next, &wsm.lru_list) {
struct workspace *victim = container_of(pos, struct workspace,
lru_list);
unsigned int level;
if (time_after(victim->last_used, reclaim_threshold))
break;
/* workspace is in use */
if (victim->req_level)
continue;
level = victim->level;
list_del(&victim->lru_list);
list_del(&victim->list);
zstd_free_workspace(&victim->list);
if (list_empty(&wsm.idle_ws[level - 1]))
clear_bit(level - 1, &wsm.active_map);
}
if (!list_empty(&wsm.lru_list))
mod_timer(&wsm.timer, jiffies + ZSTD_BTRFS_RECLAIM_JIFFIES);
spin_unlock(&wsm.lock);
}
/*
* zstd_calc_ws_mem_sizes - calculate monotonic memory bounds
*
* It is possible based on the level configurations that a higher level
* workspace uses less memory than a lower level workspace. In order to reuse
* workspaces, this must be made a monotonic relationship. This precomputes
* the required memory for each level and enforces the monotonicity between
* level and memory required.
*/
static void zstd_calc_ws_mem_sizes(void)
{
size_t max_size = 0;
unsigned int level;
for (level = 1; level <= ZSTD_BTRFS_MAX_LEVEL; level++) {
ZSTD_parameters params =
zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT);
size_t level_size =
max_t(size_t,
ZSTD_CStreamWorkspaceBound(params.cParams),
ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT));
max_size = max_t(size_t, max_size, level_size);
zstd_ws_mem_sizes[level - 1] = max_size;
}
}
static void zstd_init_workspace_manager(void)
{
struct list_head *ws;
int i;
zstd_calc_ws_mem_sizes();
wsm.ops = &btrfs_zstd_compress;
spin_lock_init(&wsm.lock);
init_waitqueue_head(&wsm.wait);
timer_setup(&wsm.timer, zstd_reclaim_timer_fn, 0);
INIT_LIST_HEAD(&wsm.lru_list);
for (i = 0; i < ZSTD_BTRFS_MAX_LEVEL; i++)
INIT_LIST_HEAD(&wsm.idle_ws[i]);
ws = zstd_alloc_workspace(ZSTD_BTRFS_MAX_LEVEL);
if (IS_ERR(ws)) {
pr_warn(
"BTRFS: cannot preallocate zstd compression workspace\n");
} else {
set_bit(ZSTD_BTRFS_MAX_LEVEL - 1, &wsm.active_map);
list_add(ws, &wsm.idle_ws[ZSTD_BTRFS_MAX_LEVEL - 1]);
}
}
static void zstd_cleanup_workspace_manager(void)
{
struct workspace *workspace;
int i;
spin_lock(&wsm.lock);
for (i = 0; i < ZSTD_BTRFS_MAX_LEVEL; i++) {
while (!list_empty(&wsm.idle_ws[i])) {
workspace = container_of(wsm.idle_ws[i].next,
struct workspace, list);
list_del(&workspace->list);
list_del(&workspace->lru_list);
zstd_free_workspace(&workspace->list);
}
}
spin_unlock(&wsm.lock);
del_timer_sync(&wsm.timer);
}
/*
* zstd_find_workspace - find workspace
* @level: compression level
*
* This iterates over the set bits in the active_map beginning at the requested
* compression level. This lets us utilize already allocated workspaces before
* allocating a new one. If the workspace is of a larger size, it is used, but
* the place in the lru_list and last_used times are not updated. This is to
* offer the opportunity to reclaim the workspace in favor of allocating an
* appropriately sized one in the future.
*/
static struct list_head *zstd_find_workspace(unsigned int level)
{
struct list_head *ws;
struct w
|