summaryrefslogtreecommitdiff
path: root/fs/bcachefs/buckets.c
blob: 941401a210f56993359548e51b5095d0db45e691 (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
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
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
// SPDX-License-Identifier: GPL-2.0
/*
 * Code for manipulating bucket marks for garbage collection.
 *
 * Copyright 2014 Datera, Inc.
 */

#include "bcachefs.h"
#include "alloc_background.h"
#include "backpointers.h"
#include "bset.h"
#include "btree_gc.h"
#include "btree_update.h"
#include "buckets.h"
#include "buckets_waiting_for_journal.h"
#include "ec.h"
#include "error.h"
#include "inode.h"
#include "movinggc.h"
#include "recovery.h"
#include "reflink.h"
#include "replicas.h"
#include "subvolume.h"
#include "trace.h"

#include <linux/preempt.h>

static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage,
					      enum bch_data_type data_type,
					      s64 sectors)
{
	switch (data_type) {
	case BCH_DATA_btree:
		fs_usage->btree		+= sectors;
		break;
	case BCH_DATA_user:
	case BCH_DATA_parity:
		fs_usage->data		+= sectors;
		break;
	case BCH_DATA_cached:
		fs_usage->cached	+= sectors;
		break;
	default:
		break;
	}
}

void bch2_fs_usage_initialize(struct bch_fs *c)
{
	percpu_down_write(&c->mark_lock);
	struct bch_fs_usage *usage = c->usage_base;

	for (unsigned i = 0; i < ARRAY_SIZE(c->usage); i++)
		bch2_fs_usage_acc_to_base(c, i);

	for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++)
		usage->b.reserved += usage->persistent_reserved[i];

	for (unsigned i = 0; i < c->replicas.nr; i++) {
		struct bch_replicas_entry_v1 *e =
			cpu_replicas_entry(&c->replicas, i);

		fs_usage_data_type_to_base(&usage->b, e->data_type, usage->replicas[i]);
	}

	for_each_member_device(c, ca) {
		struct bch_dev_usage dev = bch2_dev_usage_read(ca);

		usage->b.hidden += (dev.d[BCH_DATA_sb].buckets +
				    dev.d[BCH_DATA_journal].buckets) *
			ca->mi.bucket_size;
	}

	percpu_up_write(&c->mark_lock);
}

static inline struct bch_dev_usage *dev_usage_ptr(struct bch_dev *ca,
						  unsigned journal_seq,
						  bool gc)
{
	BUG_ON(!gc && !journal_seq);

	return this_cpu_ptr(gc
			    ? ca->usage_gc
			    : ca->usage[journal_seq & JOURNAL_BUF_MASK]);
}

void bch2_dev_usage_read_fast(struct bch_dev *ca, struct bch_dev_usage *usage)
{
	struct bch_fs *c = ca->fs;
	unsigned seq, i, u64s = dev_usage_u64s();

	do {
		seq = read_seqcount_begin(&c->usage_lock);
		memcpy(usage, ca->usage_base, u64s * sizeof(u64));
		for (i = 0; i < ARRAY_SIZE(ca->usage); i++)
			acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage[i], u64s);
	} while (read_seqcount_retry(&c->usage_lock, seq));
}

u64 bch2_fs_usage_read_one(struct bch_fs *c, u64 *v)
{
	ssize_t offset = v - (u64 *) c->usage_base;
	unsigned i, seq;
	u64 ret;

	BUG_ON(offset < 0 || offset >= fs_usage_u64s(c));
	percpu_rwsem_assert_held(&c->mark_lock);

	do {
		seq = read_seqcount_begin(&c->usage_lock);
		ret = *v;

		for (i = 0; i < ARRAY_SIZE(c->usage); i++)
			ret += percpu_u64_get((u64 __percpu *) c->usage[i] + offset);
	} while (read_seqcount_retry(&c->usage_lock, seq));

	return ret;
}

struct bch_fs_usage_online *bch2_fs_usage_read(struct bch_fs *c)
{
	struct bch_fs_usage_online *ret;
	unsigned nr_replicas = READ_ONCE(c->replicas.nr);
	unsigned seq, i;
retry:
	ret = kmalloc(__fs_usage_online_u64s(nr_replicas) * sizeof(u64), GFP_KERNEL);
	if (unlikely(!ret))
		return NULL;

	percpu_down_read(&c->mark_lock);

	if (nr_replicas != c->replicas.nr) {
		nr_replicas = c->replicas.nr;
		percpu_up_read(&c->mark_lock);
		kfree(ret);
		goto retry;
	}

	ret->online_reserved = percpu_u64_get(c->online_reserved);

	do {
		seq = read_seqcount_begin(&c->usage_lock);
		unsafe_memcpy(&ret->u, c->usage_base,
			      __fs_usage_u64s(nr_replicas) * sizeof(u64),
			      "embedded variable length struct");
		for (i = 0; i < ARRAY_SIZE(c->usage); i++)
			acc_u64s_percpu((u64 *) &ret->u, (u64 __percpu *) c->usage[i],
					__fs_usage_u64s(nr_replicas));
	} while (read_seqcount_retry(&c->usage_lock, seq));

	return ret;
}

void bch2_fs_usage_acc_to_base(struct bch_fs *c, unsigned idx)
{
	unsigned u64s = fs_usage_u64s(c);

	BUG_ON(idx >= ARRAY_SIZE(c->usage));

	preempt_disable();
	write_seqcount_begin(&c->usage_lock);

	acc_u64s_percpu((u64 *) c->usage_base,
			(u64 __percpu *) c->usage[idx], u64s);
	percpu_memset(c->usage[idx], 0, u64s * sizeof(u64));

	rcu_read_lock();
	for_each_member_device_rcu(c, ca, NULL) {
		u64s = dev_usage_u64s();

		acc_u64s_percpu((u64 *) ca->usage_base,
				(u64 __percpu *) ca->usage[idx], u64s);
		percpu_memset(ca->usage[idx], 0, u64s * sizeof(u64));
	}
	rcu_read_unlock();

	write_seqcount_end(&c->usage_lock);
	preempt_enable();
}

void bch2_fs_usage_to_text(struct printbuf *out,
			   struct bch_fs *c,
			   struct bch_fs_usage_online *fs_usage)
{
	unsigned i;

	prt_printf(out, "capacity:\t\t\t%llu\n", c->capacity);

	prt_printf(out, "hidden:\t\t\t\t%llu\n",
	       fs_usage->u.b.hidden);
	prt_printf(out, "data:\t\t\t\t%llu\n",
	       fs_usage->u.b.data);
	prt_printf(out, "cached:\t\t\t\t%llu\n",
	       fs_usage->u.b.cached);
	prt_printf(out, "reserved:\t\t\t%llu\n",
	       fs_usage->u.b.reserved);
	prt_printf(out, "nr_inodes:\t\t\t%llu\n",
	       fs_usage->u.b.nr_inodes);
	prt_printf(out, "online reserved:\t\t%llu\n",
	       fs_usage->online_reserved);

	for (i = 0;
	     i < ARRAY_SIZE(fs_usage->u.persistent_reserved);
	     i++) {
		prt_printf(out, "%u replicas:\n", i + 1);
		prt_printf(out, "\treserved:\t\t%llu\n",
		       fs_usage->u.persistent_reserved[i]);
	}

	for (i = 0; i < c->replicas.nr; i++) {
		struct bch_replicas_entry_v1 *e =
			cpu_replicas_entry(&c->replicas, i);

		prt_printf(out, "\t");
		bch2_replicas_entry_to_text(out, e);
		prt_printf(out, ":\t%llu\n", fs_usage->u.replicas[i]);
	}
}

static u64 reserve_factor(u64 r)
{
	return r + (round_up(r, (1 << RESERVE_FACTOR)) >> RESERVE_FACTOR);
}

u64 bch2_fs_sectors_used(struct bch_fs *c, struct bch_fs_usage_online *fs_usage)
{
	return min(fs_usage->u.b.hidden +
		   fs_usage->u.b.btree +
		   fs_usage->u.b.data +
		   reserve_factor(fs_usage->u.b.reserved +
				  fs_usage->online_reserved),
		   c->capacity);
}

static struct bch_fs_usage_short
__bch2_fs_usage_read_short(struct bch_fs *c)
{
	struct bch_fs_usage_short ret;
	u64 data, reserved;

	ret.capacity = c->capacity -
		bch2_fs_usage_read_one(c, &c->usage_base->b.hidden);

	data		= bch2_fs_usage_read_one(c, &c->usage_base->b.data) +
		bch2_fs_usage_read_one(c, &c->usage_base->b.btree);
	reserved	= bch2_fs_usage_read_one(c, &c->usage_base->b.reserved) +
		percpu_u64_get(c->online_reserved);

	ret.used	= min(ret.capacity, data + reserve_factor(reserved));
	ret.free	= ret.capacity - ret.used;

	ret.nr_inodes	= bch2_fs_usage_read_one(c, &c->usage_base->b.nr_inodes);

	return ret;
}

struct bch_fs_usage_short
bch2_fs_usage_read_short(struct bch_fs *c)
{
	struct bch_fs_usage_short ret;

	percpu_down_read(&c->mark_lock);
	ret = __bch2_fs_usage_read_short(c);
	percpu_up_read(&c->mark_lock);

	return ret;
}

void bch2_dev_usage_init(struct bch_dev *ca)
{
	ca->usage_base->d[BCH_DATA_free].buckets = ca->mi.nbuckets - ca->mi.first_bucket;
}

void bch2_dev_usage_to_text(struct printbuf *out, struct bch_dev_usage *usage)
{
	prt_tab(out);
	prt_str(out, "buckets");
	prt_tab_rjust(out);
	prt_str(out, "sectors");
	prt_tab_rjust(out);
	prt_str(out, "fragmented");
	prt_tab_rjust(out);
	prt_newline(out);

	for (unsigned i = 0; i < BCH_DATA_NR; i++) {
		bch2_prt_data_type(out, i);
		prt_tab(out);
		prt_u64(out, usage->d[i].buckets);
		prt_tab_rjust(out);
		prt_u64(out, usage->d[i].sectors);
		prt_tab_rjust(out);
		prt_u64(out, usage->d[i].fragmented);
		prt_tab_rjust(out);
		prt_newline(out);
	}
}

void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
			   const struct bch_alloc_v4 *old,
			   const struct bch_alloc_v4 *new,
			   u64 journal_seq, bool gc)
{
	struct bch_fs_usage *fs_usage;
	struct bch_dev_usage *u;

	preempt_disable();
	fs_usage = fs_usage_ptr(c, journal_seq, gc);

	if (data_type_is_hidden(old->data_type))
		fs_usage->b.hidden -= ca->mi.bucket_size;
	if (data_type_is_hidden(new->data_type))
		fs_usage->b.hidden += ca->mi.bucket_size;

	u = dev_usage_ptr(ca, journal_seq, gc);

	u->d[old->data_type].buckets--;
	u->d[new->data_type].buckets++;

	u->d[old->data_type].sectors -= bch2_bucket_sectors_dirty(*old);
	u->d[new->data_type].sectors += bch2_bucket_sectors_dirty(*new);

	u->d[BCH_DATA_cached].sectors += new->cached_sectors;
	u->d[BCH_DATA_cached].sectors -= old->cached_sectors;

	u->d[old->data_type].fragmented -= bch2_bucket_sectors_fragmented(ca, *old);
	u->d[new->data_type].fragmented += bch2_bucket_sectors_fragmented(ca, *new);

	preempt_enable();
}

static inline struct bch_alloc_v4 bucket_m_to_alloc(struct bucket b)
{
	return (struct bch_alloc_v4) {
		.gen		= b.gen,
		.data_type	= b.data_type,
		.dirty_sectors	= b.dirty_sectors,
		.cached_sectors	= b.cached_sectors,
		.stripe		= b.stripe,
	};
}

void bch2_dev_usage_update_m(struct bch_fs *c, struct bch_dev *ca,
			     struct bucket *old, struct bucket *new)
{
	struct bch_alloc_v4 old_a = bucket_m_to_alloc(*old);
	struct bch_alloc_v4 new_a = bucket_m_to_alloc(*new);

	bch2_dev_usage_update(c, ca, &old_a, &new_a, 0, true);
}

static inline int __update_replicas(struct bch_fs *c,
				    struct bch_fs_usage *fs_usage,
				    struct bch_replicas_entry_v1 *r,
				    s64 sectors)
{
	int idx = bch2_replicas_entry_idx(c, r);

	if (idx < 0)
		return -1;

	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
	fs_usage->replicas[idx]		+= sectors;
	return 0;
}

int bch2_update_replicas(struct bch_fs *c, struct bkey_s_c k,
			 struct bch_replicas_entry_v1 *r, s64 sectors,
			 unsigned journal_seq, bool gc)
{
	struct bch_fs_usage *fs_usage;
	int idx, ret = 0;
	struct printbuf buf = PRINTBUF;

	percpu_down_read(&c->mark_lock);

	idx = bch2_replicas_entry_idx(c, r);
	if (idx < 0 &&
	    fsck_err(c, ptr_to_missing_replicas_entry,
		     "no replicas entry\n  while marking %s",
		     (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
		percpu_up_read(&c->mark_lock);
		ret = bch2_mark_replicas(c, r);
		percpu_down_read(&c->mark_lock);

		if (ret)
			goto err;
		idx = bch2_replicas_entry_idx(c, r);
	}
	if (idx < 0) {
		ret = -1;
		goto err;
	}

	preempt_disable();
	fs_usage = fs_usage_ptr(c, journal_seq, gc);
	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
	fs_usage->replicas[idx]		+= sectors;
	preempt_enable();
err:
fsck_err:
	percpu_up_read(&c->mark_lock);
	printbuf_exit(&buf);
	return ret;
}

static inline int update_cached_sectors(struct bch_fs *c,
			struct bkey_s_c k,
			unsigned dev, s64 sectors,
			unsigned journal_seq, bool gc)
{
	struct bch_replicas_padded r;

	bch2_replicas_entry_cached(&r.e, dev);

	return bch2_update_replicas(c, k, &r.e, sectors, journal_seq, gc);
}

static int __replicas_deltas_realloc(struct btree_trans *trans, unsigned more,
				     gfp_t gfp)
{
	struct replicas_delta_list *d = trans->fs_usage_deltas;
	unsigned new_size = d ? (d->size + more) * 2 : 128;
	unsigned alloc_size = sizeof(*d) + new_size;

	WARN_ON_ONCE(alloc_size > REPLICAS_DELTA_LIST_MAX);

	if (!d || d->used + more > d->size) {
		d = krealloc(d, alloc_size, gfp|__GFP_ZERO);

		if (unlikely(!d)) {
			if (alloc_size > REPLICAS_DELTA_LIST_MAX)
				return -ENOMEM;

			d = mempool_alloc(&trans->c->replicas_delta_pool, gfp);
			if (!d)
				return -ENOMEM;

			memset(d, 0, REPLICAS_DELTA_LIST_MAX);

			if (trans->fs_usage_deltas)
				memcpy(d, trans->fs_usage_deltas,
				       trans->fs_usage_deltas->size + sizeof(*d));

			new_size = REPLICAS_DELTA_LIST_MAX - sizeof(*d);
			kfree(trans->fs_usage_deltas);
		}

		d->size = new_size;
		trans->fs_usage_deltas = d;
	}

	return 0;
}

int bch2_replicas_deltas_realloc(struct btree_trans *trans, unsigned more)
{
	return allocate_dropping_locks_errcode(trans,
				__replicas_deltas_realloc(trans, more, _gfp));
}

int bch2_update_replicas_list(struct btree_trans *trans,
			 struct bch_replicas_entry_v1 *r,
			 s64 sectors)
{
	struct replicas_delta_list *d;
	struct replicas_delta *n;
	unsigned b;
	int ret;

	if (!sectors)
		return 0;

	b = replicas_entry_bytes(r) + 8;
	ret = bch2_replicas_deltas_realloc(trans, b);
	if (ret)
		return ret;

	d = trans->fs_usage_deltas;
	n = (void *) d->d + d->used;
	n->delta = sectors;
	unsafe_memcpy((void *) n + offsetof(struct replicas_delta, r),
		      r, replicas_entry_bytes(r),
		      "flexible array member embedded in strcuct with padding");
	bch2_replicas_entry_sort(&n->r);
	d->used += b;
	return 0;
}

int bch2_update_cached_sectors_list(struct btree_trans *trans, unsigned dev, s64 sectors)
{
	struct bch_replicas_padded r;

	bch2_replicas_entry_cached(&r.e, dev);

	return bch2_update_replicas_list(trans, &r.e, sectors);
}

int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
			      size_t b, enum bch_data_type data_type,
			      unsigned sectors, struct gc_pos pos,
			      unsigned flags)
{
	struct bucket old, new, *g;
	int ret = 0;

	BUG_ON(!(flags & BTREE_TRIGGER_GC));
	BUG_ON(data_type != BCH_DATA_sb &&
	       data_type != BCH_DATA_journal);

	/*
	 * Backup superblock might be past the end of our normal usable space:
	 */
	if (b >= ca->mi.nbuckets)
		return 0;

	percpu_down_read(&c->mark_lock);
	g = gc_bucket(ca, b);

	bucket_lock(g);
	old = *g;

	if (bch2_fs_inconsistent_on(g->data_type &&
			g->data_type != data_type, c,
			"different types of data in same bucket: %s, %s",
			bch2_data_type_str(g->data_type),
			bch2_data_type_str(data_type))) {
		BUG();
		ret = -EIO;
		goto err;
	}

	if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c,
			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %u > bucket size",
			ca->dev_idx, b, g->gen,
			bch2_data_type_str(g->data_type ?: data_type),
			g->dirty_sectors, sectors)) {
		ret = -EIO;
		goto err;
	}

	g->data_type = data_type;
	g->dirty_sectors += sectors;
	new = *g;
err:
	bucket_unlock(g);
	if (!ret)
		bch2_dev_usage_update_m(c, ca, &old, &new);
	percpu_up_read(&c->mark_lock);
	return ret;
}

int bch2_check_bucket_ref(struct btree_trans *trans,
			  struct bkey_s_c k,
			  const struct bch_extent_ptr *ptr,
			  s64 sectors, enum bch_data_type ptr_data_type,
			  u8 b_gen, u8 bucket_data_type,
			  u32 bucket_sectors)
{
	struct bch_fs *c = trans->c;
	struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
	size_t bucket_nr = PTR_BUCKET_NR(ca, ptr);
	struct printbuf buf = PRINTBUF;
	int ret = 0;

	if (bucket_data_type == BCH_DATA_cached)
		bucket_data_type = BCH_DATA_user;

	if ((bucket_data_type == BCH_DATA_stripe && ptr_data_type == BCH_DATA_user) ||
	    (bucket_data_type == BCH_DATA_user   && ptr_data_type == BCH_DATA_stripe))
		bucket_data_type = ptr_data_type = BCH_DATA_stripe;

	if (gen_after(ptr->gen, b_gen)) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_ptr_gen_newer_than_bucket_gen,
			"bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n"
			"while marking %s",
			ptr->dev, bucket_nr, b_gen,
			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
			ptr->gen,
			(bch2_bkey_val_to_text(&buf, c, k), buf.buf));
		ret = -EIO;
		goto err;
	}

	if (gen_cmp(b_gen, ptr->gen) > BUCKET_GC_GEN_MAX) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_ptr_too_stale,
			"bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n"
			"while marking %s",
			ptr->dev, bucket_nr, b_gen,
			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
			ptr->gen,
			(printbuf_reset(&buf),
			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
		ret = -EIO;
		goto err;
	}

	if (b_gen != ptr->gen && !ptr->cached) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_stale_dirty_ptr,
			"bucket %u:%zu gen %u (mem gen %u) data type %s: stale dirty ptr (gen %u)\n"
			"while marking %s",
			ptr->dev, bucket_nr, b_gen,
			*bucket_gen(ca, bucket_nr),
			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
			ptr->gen,
			(printbuf_reset(&buf),
			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
		ret = -EIO;
		goto err;
	}

	if (b_gen != ptr->gen) {
		ret = 1;
		goto out;
	}

	if (!data_type_is_empty(bucket_data_type) &&
	    ptr_data_type &&
	    bucket_data_type != ptr_data_type) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_ptr_bucket_data_type_mismatch,
			"bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n"
			"while marking %s",
			ptr->dev, bucket_nr, b_gen,
			bch2_data_type_str(bucket_data_type),
			bch2_data_type_str(ptr_data_type),
			(printbuf_reset(&buf),
			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
		BUG();
		ret = -EIO;
		goto err;
	}

	if ((u64) bucket_sectors + sectors > U32_MAX) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_bucket_sector_count_overflow,
			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n"
			"while marking %s",
			ptr->dev, bucket_nr, b_gen,
			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
			bucket_sectors, sectors,
			(printbuf_reset(&buf),
			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
		ret = -EIO;
		goto err;
	}
out:
	printbuf_exit(&buf);
	return ret;
err:
	bch2_dump_trans_updates(trans);
	goto out;
}

void bch2_trans_fs_usage_revert(struct btree_trans *trans,
				struct replicas_delta_list *deltas)
{
	struct bch_fs *c = trans->c;
	struct bch_fs_usage *dst;
	struct replicas_delta *d, *top = (void *) deltas->d + deltas->used;
	s64 added = 0;
	unsigned i;

	percpu_down_read(&c->mark_lock);
	preempt_disable();
	dst = fs_usage_ptr(c, trans->journal_res.seq, false);

	/* revert changes: */
	for (d = deltas->d; d != top; d = replicas_delta_next(d)) {
		switch (d->r.data_type) {
		case BCH_DATA_btree:
		case BCH_DATA_user:
		case BCH_DATA_parity:
			added += d->delta;
		}
		BUG_ON(__update_replicas(c, dst, &d->r, -d->delta));
	}

	dst->b.nr_inodes -= deltas->nr_inodes;

	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
		added				-= deltas->persistent_reserved[i];
		dst->b.reserved			-= deltas->persistent_reserved[i];
		dst->persistent_reserved[i]	-= deltas->persistent_reserved[i];
	}

	if (added > 0) {
		trans->disk_res->sectors += added;
		this_cpu_add(*c->online_reserved, added);
	}

	preempt_enable();
	percpu_up_read(&c->mark_lock);
}

void bch2_trans_account_disk_usage_change(struct btree_trans *trans)
{
	struct bch_fs *c = trans->c;
	u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0;
	static int warned_disk_usage = 0;
	bool warn = false;

	percpu_down_read(&c->mark_lock);
	preempt_disable();
	struct bch_fs_usage_base *dst = &fs_usage_ptr(c, trans->journal_res.seq, false)->b;
	struct bch_fs_usage_base *src = &trans->fs_usage_delta;

	s64 added = src->btree + src->data + src->reserved;

	/*
	 * Not allowed to reduce sectors_available except by getting a
	 * reservation:
	 */
	s64 should_not_have_added = added - (s64) disk_res_sectors;
	if (unlikely(should_not_have_added > 0)) {
		u64 old, new, v = atomic64_read(&c->sectors_available);

		do {
			old = v;
			new = max_t(s64, 0, old - should_not_have_added);
		} while ((v = atomic64_cmpxchg(&c->sectors_available,
					       old, new)) != old);

		added -= should_not_have_added;
		warn = true;
	}

	if (added > 0) {
		trans->disk_res->sectors -= added;
		this_cpu_sub(*c->online_reserved, added);
	}

	dst->hidden	+= src->hidden;
	dst->btree	+= src->btree;
	dst->data	+= src->data;
	dst->cached	+= src->cached;
	dst->reserved	+= src->reserved;
	dst->nr_inodes	+= src->nr_inodes;

	preempt_enable();
	percpu_up_read(&c->mark_lock);

	if (unlikely(warn) && !xchg(&warned_disk_usage, 1))
		bch2_trans_inconsistent(trans,
					"disk usage increased %lli more than %llu sectors reserved)",
					should_not_have_added, disk_res_sectors);
}

int bch2_trans_fs_usage_apply(struct btree_trans *trans,
			      struct replicas_delta_list *deltas)
{
	struct bch_fs *c = trans->c;
	struct replicas_delta *d, *d2;
	struct replicas_delta *top = (void *) deltas->d + deltas->used;
	struct bch_fs_usage *dst;
	unsigned i;

	percpu_down_read(&c->mark_lock);
	preempt_disable();
	dst = fs_usage_ptr(c, trans->journal_res.seq, false);

	for (d = deltas->d; d != top; d = replicas_delta_next(d))
		if (__update_replicas(c, dst, &d->r, d->delta))
			goto need_mark;

	dst->b.nr_inodes += deltas->nr_inodes;

	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
		dst->b.reserved			+= deltas->persistent_reserved[i];
		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
	}

	preempt_enable();
	percpu_up_read(&c->mark_lock);
	return 0;
need_mark:
	/* revert changes: */
	for (d2 = deltas->d; d2 != d; d2 = replicas_delta_next(d2))
		BUG_ON(__update_replicas(c, dst, &d2->r, -d2->delta));

	preempt_enable();
	percpu_up_read(&c->mark_lock);
	return -1;
}

/* KEY_TYPE_extent: */

static int __mark_pointer(struct btree_trans *trans,
			  struct bkey_s_c k,
			  const struct bch_extent_ptr *ptr,
			  s64 sectors, enum bch_data_type ptr_data_type,
			  u8 bucket_gen, u8 *bucket_data_type,
			  u32 *dirty_sectors, u32 *cached_sectors)
{
	u32 *dst_sectors = !ptr->cached
		? dirty_sectors
		: cached_sectors;
	int ret = bch2_check_bucket_ref(trans, k, ptr, sectors, ptr_data_type,
				   bucket_gen, *bucket_data_type, *dst_sectors);

	if (ret)
		return ret;

	*dst_sectors += sectors;

	if (!*dirty_sectors && !*cached_sectors)
		*bucket_data_type = 0;
	else if (*bucket_data_type != BCH_DATA_stripe)
		*bucket_data_type = ptr_data_type;

	return 0;
}

static int bch2_trigger_pointer(struct btree_trans *trans,
			enum btree_id btree_id, unsigned level,
			struct bkey_s_c k, struct extent_ptr_decoded p,
			const union bch_extent_entry *entry,
			s64 *sectors, unsigned flags)
{
	bool insert = !(flags & BTREE_TRIGGER_OVERWRITE);
	struct bpos bucket;
	struct bch_backpointer bp;

	bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, entry, &bucket, &bp);
	*sectors = insert ? bp.bucket_len : -((s64) bp.bucket_len);

	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
		struct btree_iter iter;
		struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, &iter, bucket);
		int ret = PTR_ERR_OR_ZERO(a);
		if (ret)
			return ret;

		ret = __mark_pointer(trans, k, &p.ptr, *sectors, bp.data_type,
				     a->v.gen, &a->v.data_type,
				     &a->v.dirty_sectors, &a->v.cached_sectors) ?:
			bch2_trans_update(trans, &iter, &a->k_i, 0);
		bch2_trans_iter_exit(trans, &iter);

		if (ret)
			return ret;

		if (!p.ptr.cached) {
			ret = bch2_bucket_backpointer_mod(trans, bucket, bp, k, insert);
			if (ret)
				return ret;
		}
	}

	if (flags & BTREE_TRIGGER_GC) {
		struct bch_fs *c = trans->c;
		struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
		enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry);

		percpu_down_read(&c->mark_lock);
		struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr);
		bucket_lock(g);
		struct bucket old = *g;

		u8 bucket_data_type = g->data_type;
		int ret = __mark_pointer(trans, k, &p.ptr, *sectors,
				     data_type, g->gen,
				     &bucket_data_type,
				     &g->dirty_sectors,
				     &g->cached_sectors);
		if (ret) {
			bucket_unlock(g);
			percpu_up_read(&c->mark_lock);
			return ret;
		}

		g->data_type = bucket_data_type;
		struct bucket new = *g;
		bucket_unlock(g);
		bch2_dev_usage_update_m(c, ca, &old, &new);
		percpu_up_read(&c->mark_lock);
	}

	return 0;
}

static int bch2_trigger_stripe_ptr(struct btree_trans *trans,
				struct bkey_s_c k,
				struct extent_ptr_decoded p,
				enum bch_data_type data_type,
				s64 sectors, unsigned flags)
{
	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
		struct btree_iter iter;
		struct bkey_i_stripe *s = bch2_bkey_get_mut_typed(trans, &iter,
				BTREE_ID_stripes, POS(0, p.ec.idx),
				BTREE_ITER_WITH_UPDATES, stripe);
		int ret = PTR_ERR_OR_ZERO(s);
		if (unlikely(ret)) {
			bch2_trans_inconsistent_on(bch2_err_matches(ret, ENOENT), trans,
				"pointer to nonexistent stripe %llu",
				(u64) p.ec.idx);
			goto err;
		}

		if (!bch2_ptr_matches_stripe(&s->v, p)) {
			bch2_trans_inconsistent(trans,
				"stripe pointer doesn't match stripe %llu",
				(u64) p.ec.idx);
			ret = -EIO;
			goto err;
		}

		stripe_blockcount_set(&s->v, p.ec.block,
			stripe_blockcount_get(&s->v, p.ec.block) +
			sectors);

		struct bch_replicas_padded r;
		bch2_bkey_to_replicas(&r.e, bkey_i_to_s_c(&s->k_i));
		r.e.data_type = data_type;
		ret = bch2_update_replicas_list(trans, &r.e, sectors);
err:
		bch2_trans_iter_exit(trans, &iter);
		return ret;
	}

	if (flags & BTREE_TRIGGER_GC) {
		struct bch_fs *c = trans->c;

		BUG_ON(!(flags & BTREE_TRIGGER_GC));

		struct gc_stripe *m = genradix_ptr_alloc(&c->gc_stripes, p.ec.idx, GFP_KERNEL);
		if (!m) {
			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
				(u64) p.ec.idx);
			return -BCH_ERR_ENOMEM_mark_stripe_ptr;
		}

		mutex_lock(&c->ec_stripes_heap_lock);

		if (!m || !m->alive) {
			mutex_unlock(&c->ec_stripes_heap_lock);
			struct printbuf buf = PRINTBUF;
			bch2_bkey_val_to_text(&buf, c, k);
			bch_err_ratelimited(c, "pointer to nonexistent stripe %llu\n  while marking %s",
					    (u64) p.ec.idx, buf.buf);
			printbuf_exit(&buf);
			bch2_inconsistent_error(c);
			return -EIO;
		}

		m->block_sectors[p.ec.block] += sectors;

		struct bch_replicas_padded r = m->r;
		mutex_unlock(&c->ec_stripes_heap_lock);

		r.e.data_type = data_type;
		bch2_update_replicas(c, k, &r.e, sectors, trans->journal_res.seq, true);
	}

	return 0;
}

static int __trigger_extent(struct btree_trans *trans,
			    enum btree_id btree_id, unsigned level,
			    struct bkey_s_c k, unsigned flags)
{
	bool gc = flags & BTREE_TRIGGER_GC;
	struct bch_fs *c = trans->c;
	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
	const union bch_extent_entry *entry;
	struct extent_ptr_decoded p;
	struct bch_replicas_padded r;
	enum bch_data_type data_type = bkey_is_btree_ptr(k.k)
		? BCH_DATA_btree
		: BCH_DATA_user;
	s64 dirty_sectors = 0;
	int ret = 0;

	r.e.data_type	= data_type;
	r.e.nr_devs	= 0;
	r.e.nr_required	= 1;

	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
		s64 disk_sectors;
		ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags);
		if (ret < 0)
			return ret;

		bool stale = ret > 0;

		if (p.ptr.cached) {
			if (!stale) {
				ret = !gc
					? bch2_update_cached_sectors_list(trans, p.ptr.dev, disk_sectors)
					: update_cached_sectors(c, k, p.ptr.dev, disk_sectors, 0, true);
				bch2_fs_fatal_err_on(ret && gc, c, "%s: no replicas entry while updating cached sectors",
						     bch2_err_str(ret));
				if (ret)
					return ret;
			}
		} else if (!p.has_ec) {
			dirty_sectors	       += disk_sectors;
			r.e.devs[r.e.nr_devs++]	= p.ptr.dev;
		} else {
			ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags);
			if (ret)
				return ret;

			/*
			 * There may be other dirty pointers in this extent, but
			 * if so they're not required for mounting if we have an
			 * erasure coded pointer in this extent:
			 */
			r.e.nr_required = 0;
		}
	}

	if (r.e.nr_devs) {
		ret = !gc
			? bch2_update_replicas_list(trans, &r.e, dirty_sectors)
			: bch2_update_replicas(c, k, &r.e, dirty_sectors, 0, true);
		if (unlikely(ret && gc)) {
			struct printbuf buf = PRINTBUF;

			bch2_bkey_val_to_text(&buf, c, k);
			bch2_fs_fatal_error(c, ": no replicas entry for %s", buf.buf);
			printbuf_exit(&buf);
		}
		if (ret)
			return ret;
	}

	return 0;
}

int bch2_trigger_extent(struct btree_trans *trans,
			enum btree_id btree_id, unsigned level,
			struct bkey_s_c old, struct bkey_s new,
			unsigned flags)
{
	struct bkey_ptrs_c new_ptrs = bch2_bkey_ptrs_c(new.s_c);
	struct bkey_ptrs_c old_ptrs = bch2_bkey_ptrs_c(old);
	unsigned new_ptrs_bytes = (void *) new_ptrs.end - (void *) new_ptrs.start;
	unsigned old_ptrs_bytes = (void *) old_ptrs.end - (void *) old_ptrs.start;

	/* if pointers aren't changing - nothing to do: */
	if (new_ptrs_bytes == old_ptrs_bytes &&
	    !memcmp(new_ptrs.start,
		    old_ptrs.start,
		    new_ptrs_bytes))
		return 0;

	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
		struct bch_fs *c = trans->c;
		int mod = (int) bch2_bkey_needs_rebalance(c, new.s_c) -
			  (int) bch2_bkey_needs_rebalance(c, old);

		if (mod) {
			int ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_rebalance_work,
							      new.k->p, mod > 0);
			if (ret)
				return ret;
		}
	}

	if (flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))
		return trigger_run_overwrite_then_insert(__trigger_extent, trans, btree_id, level, old, new, flags);

	return 0;
}

/* KEY_TYPE_reservation */

static int __trigger_reservation(struct btree_trans *trans,
				 enum btree_id btree_id, unsigned level,
				 struct bkey_s_c k, unsigned flags)
{
	struct bch_fs *c = trans->c;
	unsigned replicas = bkey_s_c_to_reservation(k).v->nr_replicas;
	s64 sectors = (s64) k.k->size * replicas;

	if (flags & BTREE_TRIGGER_OVERWRITE)
		sectors = -sectors;

	if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
		int ret = bch2_replicas_deltas_realloc(trans, 0);
		if (ret)
			return ret;

		struct replicas_delta_list *d = trans->fs_usage_deltas;
		replicas = min(replicas, ARRAY_SIZE(d->persistent_reserved));

		d->persistent_reserved[replicas - 1] += sectors;
	}

	if (flags & BTREE_TRIGGER_GC) {
		percpu_down_read(&c->mark_lock);
		preempt_disable();

		struct bch_fs_usage *fs_usage = this_cpu_ptr(c->usage_gc);

		replicas = min(replicas, ARRAY_SIZE(fs_usage->persistent_reserved));
		fs_usage->b.reserved				+= sectors;
		fs_usage->persistent_reserved[replicas - 1]	+= sectors;

		preempt_enable();
		percpu_up_read(&c->mark_lock);
	}

	return 0;
}

int bch2_trigger_reservation(struct btree_trans *trans,
			  enum btree_id btree_id, unsigned level,
			  struct bkey_s_c old, struct bkey_s new,
			  unsigned flags)
{
	return trigger_run_overwrite_then_insert(__trigger_reservation, trans, btree_id, level, old, new, flags);
}

/* Mark superblocks: */

static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
				    struct bch_dev *ca, size_t b,
				    enum bch_data_type type,
				    unsigned sectors)
{
	struct bch_fs *c = trans->c;
	struct btree_iter iter;
	struct bkey_i_alloc_v4 *a;
	int ret = 0;

	/*
	 * Backup superblock might be past the end of our normal usable space:
	 */
	if (b >= ca->mi.nbuckets)
		return 0;

	a = bch2_trans_start_alloc_update(trans, &iter, POS(ca->dev_idx, b));
	if (IS_ERR(a))
		return PTR_ERR(a);

	if (a->v.data_type && type && a->v.data_type != type) {
		bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
			      BCH_FSCK_ERR_bucket_metadata_type_mismatch,
			"bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n"
			"while marking %s",
			iter.pos.inode, iter.pos.offset, a->v.gen,
			bch2_data_type_str(a->v.data_type),
			bch2_data_type_str(type),
			bch2_data_type_str(type));
		ret = -EIO;
		goto err;
	}

	if (a->v.data_type	!= type ||
	    a->v.dirty_sectors	!= sectors) {
		a->v.data_type		= type;
		a->v.dirty_sectors	= sectors;
		ret = bch2_trans_update(trans, &iter, &a->k_i, 0);
	}
err:
	bch2_trans_iter_exit(trans, &iter);
	return ret;
}

int bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
				    struct bch_dev *ca, size_t b,
				    enum bch_data_type type,
				    unsigned sectors)
{
	return commit_do(trans, NULL, NULL, 0,
			__bch2_trans_mark_metadata_bucket(trans, ca, b, type, sectors));
}

static int bch2_trans_mark_metadata_sectors(struct btree_trans *trans,
					    struct bch_dev *ca,
					    u64 start, u64 end,
					    enum bch_data_type type,
					    u64 *bucket, unsigned *bucket_sectors)
{
	do {
		u64 b = sector_to_bucket(ca, start);
		unsigned sectors =
			min_t(u64, bucket_to_sector(ca, b + 1), end) - start;

		if (b != *bucket && *bucket_sectors) {
			int ret = bch2_trans_mark_metadata_bucket(trans, ca, *bucket,
								  type, *bucket_sectors);
			if (ret)
				return ret;

			*bucket_sectors = 0;
		}

		*bucket		= b;
		*bucket_sectors	+= sectors;
		start += sectors;
	} while (start < end);

	return 0;
}

static int __bch2_trans_mark_dev_sb(struct btree_trans *trans,
				    struct bch_dev *ca)
{
	struct bch_sb_layout *layout = &ca->disk_sb.sb->layout;
	u64 bucket = 0;
	unsigned i, bucket_sectors = 0;
	int ret;

	for (i = 0; i < layout->nr_superblocks; i++) {
		u64 offset = le64_to_cpu(layout->sb_offset[i]);

		if (offset == BCH_SB_SECTOR) {
			ret = bch2_trans_mark_metadata_sectors(trans, ca,
						0, BCH_SB_SECTOR,
						BCH_DATA_sb, &bucket, &bucket_sectors);
			if (ret)
				return ret;
		}

		ret = bch2_trans_mark_metadata_sectors(trans, ca, offset,
				      offset + (1 << layout->sb_max_size_bits),
				      BCH_DATA_sb, &bucket, &bucket_sectors);
		if (ret)
			return ret;
	}

	if (bucket_sectors) {
		ret = bch2_trans_mark_metadata_bucket(trans, ca,
				bucket, BCH_DATA_sb, bucket_sectors);
		if (ret)
			return ret;
	}

	for (i = 0; i < ca->journal.nr; i++) {
		ret = bch2_trans_mark_metadata_bucket(trans, ca,
				ca->journal.buckets[i],
				BCH_DATA_journal, ca->mi.bucket_size);
		if (ret)
			return ret;
	}

	return 0;
}

int bch2_trans_mark_dev_sb(struct bch_fs *c, struct bch_dev *ca)
{
	int ret = bch2_trans_run(c, __bch2_trans_mark_dev_sb(trans, ca));

	bch_err_fn(c, ret);
	return ret;
}

int bch2_trans_mark_dev_sbs(struct bch_fs *c)
{
	for_each_online_member(c, ca) {
		int ret = bch2_trans_mark_dev_sb(c, ca);
		if (ret) {
			percpu_ref_put(&ca->ref);
			return ret;
		}
	}

	return 0;
}

/* Disk reservations: */

#define SECTORS_CACHE	1024

int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res,
			      u64 sectors, int flags)
{
	struct bch_fs_pcpu *pcpu;
	u64 old, v, get;
	s64 sectors_available;
	int ret;

	percpu_down_read(&c->mark_lock);
	preempt_disable();
	pcpu = this_cpu_ptr(c->pcpu);

	if (sectors <= pcpu->sectors_available)
		goto out;

	v = atomic64_read(&c->sectors_available);
	do {
		old = v;
		get = min((u64) sectors + SECTORS_CACHE, old);

		if (get < sectors) {
			preempt_enable();
			goto recalculate;
		}
	} while ((v = atomic64_cmpxchg(&c->sectors_available,
				       old, old - get)) != old);

	pcpu->sectors_available		+= get;

out:
	pcpu->sectors_available		-= sectors;
	this_cpu_add(*c->online_reserved, sectors);
	res->sectors			+= sectors;

	preempt_enable();
	percpu_up_read(&c->mark_lock);
	return 0;

recalculate:
	mutex_lock(&c->sectors_available_lock);

	percpu_u64_set(&c->pcpu->sectors_available, 0);
	sectors_available = avail_factor(__bch2_fs_usage_read_short(c).free);

	if (sectors <= sectors_available ||
	    (flags & BCH_DISK_RESERVATION_NOFAIL)) {
		atomic64_set(&c->sectors_available,
			     max_t(s64, 0, sectors_available - sectors));
		this_cpu_add(*c->online_reserved, sectors);
		res->sectors			+= sectors;
		ret = 0;
	} else {
		atomic64_set(&c->sectors_available, sectors_available);
		ret = -BCH_ERR_ENOSPC_disk_reservation;
	}

	mutex_unlock(&c->sectors_available_lock);
	percpu_up_read(&c->mark_lock);

	return ret;
}

/* Startup/shutdown: */

static void bucket_gens_free_rcu(struct rcu_head *rcu)
{
	struct bucket_gens *buckets =
		container_of(rcu, struct bucket_gens, rcu);

	kvfree(buckets);
}

int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
{
	struct bucket_gens *bucket_gens = NULL, *old_bucket_gens = NULL;
	unsigned long *buckets_nouse = NULL;
	bool resize = ca->bucket_gens != NULL;
	int ret;

	if (!(bucket_gens	= kvmalloc(sizeof(struct bucket_gens) + nbuckets,
					   GFP_KERNEL|__GFP_ZERO))) {
		ret = -BCH_ERR_ENOMEM_bucket_gens;
		goto err;
	}

	if ((c->opts.buckets_nouse &&
	     !(buckets_nouse	= kvmalloc(BITS_TO_LONGS(nbuckets) *
					   sizeof(unsigned long),
					   GFP_KERNEL|__GFP_ZERO)))) {
		ret = -BCH_ERR_ENOMEM_buckets_nouse;
		goto err;
	}

	bucket_gens->first_bucket = ca->mi.first_bucket;
	bucket_gens->nbuckets	= nbuckets;

	if (resize) {
		down_write(&c->gc_lock);
		down_write(&ca->bucket_lock);
		percpu_down_write(&c->mark_lock);
	}

	old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1);

	if (resize) {
		size_t n = min(bucket_gens->nbuckets, old_bucket_gens->nbuckets);

		memcpy(bucket_gens->b,
		       old_bucket_gens->b,
		       n);
		if (buckets_nouse)
			memcpy(buckets_nouse,
			       ca->buckets_nouse,
			       BITS_TO_LONGS(n) * sizeof(unsigned long));
	}

	rcu_assign_pointer(ca->bucket_gens, bucket_gens);
	bucket_gens	= old_bucket_gens;

	swap(ca->buckets_nouse, buckets_nouse);

	nbuckets = ca->mi.nbuckets;

	if (resize) {
		percpu_up_write(&c->mark_lock);
		up_write(&ca->bucket_lock);
		up_write(&c->gc_lock);
	}

	ret = 0;
err:
	kvfree(buckets_nouse);
	if (bucket_gens)
		call_rcu(&bucket_gens->rcu, bucket_gens_free_rcu);

	return ret;
}

void bch2_dev_buckets_free(struct bch_dev *ca)
{
	kvfree(ca->buckets_nouse);
	kvfree(rcu_dereference_protected(ca->bucket_gens, 1));

	for (unsigned i = 0; i < ARRAY_SIZE(ca->usage); i++)
		free_percpu(ca->usage[i]);
	kfree(ca->usage_base);
}

int bch2_dev_buckets_alloc(struct bch_fs *c, struct bch_dev *ca)
{
	ca->usage_base = kzalloc(sizeof(struct bch_dev_usage), GFP_KERNEL);
	if (!ca->usage_base)
		return -BCH_ERR_ENOMEM_usage_init;

	for (unsigned i = 0; i < ARRAY_SIZE(ca->usage); i++) {
		ca->usage[i] = alloc_percpu(struct bch_dev_usage);
		if (!ca->usage[i])
			return -BCH_ERR_ENOMEM_usage_init;
	}

	return bch2_dev_buckets_resize(c, ca, ca->mi.nbuckets);
}