forked from kdave/btrfs-progs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathzoned.c
1223 lines (1035 loc) · 30 KB
/
zoned.c
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
// SPDX-License-Identifier: GPL-2.0
/*
* 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 "kerncompat.h"
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <unistd.h>
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#include "kernel-lib/list.h"
#include "kernel-shared/volumes.h"
#include "kernel-shared/zoned.h"
#include "kernel-shared/accessors.h"
#include "kernel-shared/ctree.h"
#include "kernel-shared/extent_io.h"
#include "kernel-shared/uapi/btrfs.h"
#include "kernel-shared/uapi/btrfs_tree.h"
#include "common/utils.h"
#include "common/device-utils.h"
#include "common/extent-cache.h"
#include "common/internal.h"
#include "common/string-utils.h"
#include "common/messages.h"
#include "mkfs/common.h"
/* Maximum number of zones to report per ioctl(BLKREPORTZONE) call */
#define BTRFS_REPORT_NR_ZONES 4096
/* Invalid allocation pointer value for missing devices */
#define WP_MISSING_DEV ((u64)-1)
/* Pseudo write pointer value for conventional zone */
#define WP_CONVENTIONAL ((u64)-2)
#define DEFAULT_EMULATED_ZONE_SIZE SZ_256M
static u64 emulated_zone_size = DEFAULT_EMULATED_ZONE_SIZE;
/*
* Minimum / maximum supported zone size. Currently, SMR disks have a zone size
* of 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do
* not expect the zone size to become larger than 8GiB or smaller than 4MiB in
* the near future.
*/
#define BTRFS_MAX_ZONE_SIZE (8ULL * SZ_1G)
#define BTRFS_MIN_ZONE_SIZE (SZ_4M)
static int btrfs_get_dev_zone_info(struct btrfs_device *device);
enum btrfs_zoned_model zoned_model(const char *file)
{
const char host_aware[] = "host-aware";
const char host_managed[] = "host-managed";
struct stat st;
char model[32];
int ret;
ret = stat(file, &st);
if (ret < 0) {
error("zoned: unable to stat %s", file);
return -ENOENT;
}
/* Consider a regular file as non-zoned device */
if (!S_ISBLK(st.st_mode))
return ZONED_NONE;
ret = device_get_queue_param(file, "zoned", model, sizeof(model));
if (ret <= 0)
return ZONED_NONE;
if (strncmp(model, host_aware, strlen(host_aware)) == 0)
return ZONED_HOST_AWARE;
if (strncmp(model, host_managed, strlen(host_managed)) == 0)
return ZONED_HOST_MANAGED;
return ZONED_NONE;
}
u64 zone_size(const char *file)
{
char chunk[32];
int ret;
/* Zoned emulation on regular device */
if (zoned_model(file) == ZONED_NONE) {
const char *tmp;
u64 size = DEFAULT_EMULATED_ZONE_SIZE;
tmp = bconf_param_value("zone-size");
if (tmp) {
size = arg_strtou64_with_suffix(tmp);
if (!is_power_of_2(size) || size < BTRFS_MIN_ZONE_SIZE ||
size > BTRFS_MAX_ZONE_SIZE) {
error("invalid emulated zone size %llu", size);
exit(1);
}
}
emulated_zone_size = size;
return emulated_zone_size;
}
ret = device_get_queue_param(file, "chunk_sectors", chunk, sizeof(chunk));
if (ret <= 0)
return 0;
return strtoull((const char *)chunk, NULL, 10) << SECTOR_SHIFT;
}
static u64 max_zone_append_size(const char *file)
{
char chunk[32];
int ret;
ret = device_get_queue_param(file, "zone_append_max_bytes", chunk,
sizeof(chunk));
if (ret <= 0)
return 0;
return strtoull((const char *)chunk, NULL, 10);
}
#ifdef BTRFS_ZONED
/*
* Emulate blkdev_report_zones() for a non-zoned device. It slices up the block
* device into fixed-sized chunks and emulate a conventional zone on each of
* them.
*/
static int emulate_report_zones(const char *file, int fd, u64 pos,
struct blk_zone *zones, unsigned int nr_zones)
{
const sector_t zone_sectors = emulated_zone_size >> SECTOR_SHIFT;
struct stat st;
sector_t bdev_size;
unsigned int i;
int ret;
ret = fstat(fd, &st);
if (ret < 0) {
error("unable to stat %s: %m", file);
return -EIO;
}
bdev_size = device_get_partition_size_fd_stat(fd, &st) >> SECTOR_SHIFT;
pos >>= SECTOR_SHIFT;
for (i = 0; i < nr_zones; i++) {
zones[i].start = i * zone_sectors + pos;
zones[i].len = zone_sectors;
zones[i].capacity = zone_sectors;
zones[i].wp = zones[i].start + zone_sectors;
zones[i].type = BLK_ZONE_TYPE_CONVENTIONAL;
zones[i].cond = BLK_ZONE_COND_NOT_WP;
if (zones[i].wp >= bdev_size) {
i++;
break;
}
}
return i;
}
static int sb_write_pointer(int fd, struct blk_zone *zones, u64 *wp_ret)
{
bool empty[BTRFS_NR_SB_LOG_ZONES];
bool full[BTRFS_NR_SB_LOG_ZONES];
sector_t sector;
ASSERT(zones[0].type != BLK_ZONE_TYPE_CONVENTIONAL &&
zones[1].type != BLK_ZONE_TYPE_CONVENTIONAL);
empty[0] = (zones[0].cond == BLK_ZONE_COND_EMPTY);
empty[1] = (zones[1].cond == BLK_ZONE_COND_EMPTY);
full[0] = (zones[0].cond == BLK_ZONE_COND_FULL);
full[1] = (zones[1].cond == BLK_ZONE_COND_FULL);
/*
* Possible states of log buffer zones
*
* Empty[0] In use[0] Full[0]
* Empty[1] * x 0
* In use[1] 0 x 0
* Full[1] 1 1 C
*
* Log position:
* *: Special case, no superblock is written
* 0: Use write pointer of zones[0]
* 1: Use write pointer of zones[1]
* C: Compare super blocks from zones[0] and zones[1], use the latest
* one determined by generation
* x: Invalid state
*/
if (empty[0] && empty[1]) {
/* Special case to distinguish no superblock to read */
*wp_ret = (zones[0].start << SECTOR_SHIFT);
return -ENOENT;
} else if (full[0] && full[1]) {
/* Compare two super blocks */
u8 buf[BTRFS_NR_SB_LOG_ZONES][BTRFS_SUPER_INFO_SIZE];
struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES];
int i;
int ret;
for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
u64 bytenr;
bytenr = ((zones[i].start + zones[i].len)
<< SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE;
ret = pread(fd, buf[i], BTRFS_SUPER_INFO_SIZE, bytenr);
if (ret != BTRFS_SUPER_INFO_SIZE)
return -EIO;
super[i] = (struct btrfs_super_block *)&buf[i];
}
if (super[0]->generation > super[1]->generation)
sector = zones[1].start;
else
sector = zones[0].start;
} else if (!full[0] && (empty[1] || full[1])) {
sector = zones[0].wp;
} else if (full[0]) {
sector = zones[1].wp;
} else {
return -EUCLEAN;
}
*wp_ret = sector << SECTOR_SHIFT;
return 0;
}
int btrfs_reset_dev_zone(int fd, struct blk_zone *zone)
{
struct blk_zone_range range;
/* Nothing to do if it is already empty */
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL ||
zone->cond == BLK_ZONE_COND_EMPTY)
return 0;
range.sector = zone->start;
range.nr_sectors = zone->len;
if (ioctl(fd, BLKRESETZONE, &range) < 0)
return -errno;
zone->cond = BLK_ZONE_COND_EMPTY;
zone->wp = zone->start;
return 0;
}
static int report_zones(int fd, const char *file,
struct btrfs_zoned_device_info *zinfo)
{
u64 device_size;
u64 zone_bytes = zone_size(file);
size_t rep_size;
u64 sector = 0;
struct stat st;
struct blk_zone_report *rep;
struct blk_zone *zone;
unsigned int i, n = 0;
int ret;
/*
* Zones are guaranteed (by kernel) to be a power of 2 number of
* sectors. Check this here and make sure that zones are not too small.
*/
if (!zone_bytes || !is_power_of_2(zone_bytes)) {
error("zoned: illegal zone size %llu (not a power of 2)",
zone_bytes);
exit(1);
}
/*
* The zone size must be large enough to hold the initial system
* block group for mkfs time.
*/
if (zone_bytes < BTRFS_MKFS_SYSTEM_GROUP_SIZE) {
error("zoned: illegal zone size %llu (smaller than %d)",
zone_bytes, BTRFS_MKFS_SYSTEM_GROUP_SIZE);
exit(1);
}
ret = fstat(fd, &st);
if (ret < 0) {
error("error when reading zone info on %s: %m", file);
return -EIO;
}
device_size = device_get_partition_size_fd_stat(fd, &st);
if (device_size == 0) {
error("zoned: failed to read size of %s: %m", file);
exit(1);
}
/* Allocate the zone information array */
zinfo->zone_size = zone_bytes;
zinfo->nr_zones = device_size / zone_bytes;
if (zinfo->zone_size > BTRFS_MAX_ZONE_SIZE) {
error("zoned: zone size %llu larger than supported maximum %llu",
zinfo->zone_size, BTRFS_MAX_ZONE_SIZE);
exit(1);
} else if (zinfo->zone_size < BTRFS_MIN_ZONE_SIZE) {
error("zoned: zone size %llu smaller than supported minimum %u",
zinfo->zone_size, BTRFS_MIN_ZONE_SIZE);
exit(1);
}
if (device_size & (zone_bytes - 1))
zinfo->nr_zones++;
if (zoned_model(file) != ZONED_NONE && max_zone_append_size(file) == 0) {
error(
"zoned: device %s does not support ZONE_APPEND command", file);
exit(1);
}
zinfo->zones = calloc(zinfo->nr_zones, sizeof(struct blk_zone));
if (!zinfo->zones) {
error_msg(ERROR_MSG_MEMORY, "zone information");
exit(1);
}
/* Allocate a zone report */
rep_size = sizeof(struct blk_zone_report) +
sizeof(struct blk_zone) * BTRFS_REPORT_NR_ZONES;
rep = kmalloc(rep_size, GFP_KERNEL);
if (!rep) {
error_msg(ERROR_MSG_MEMORY, "zone report");
exit(1);
}
/* Get zone information */
zone = (struct blk_zone *)(rep + 1);
while (n < zinfo->nr_zones) {
memset(rep, 0, rep_size);
rep->sector = sector;
rep->nr_zones = BTRFS_REPORT_NR_ZONES;
if (zinfo->model != ZONED_NONE) {
ret = ioctl(fd, BLKREPORTZONE, rep);
if (ret != 0) {
error("zoned: ioctl BLKREPORTZONE failed (%m)");
exit(1);
}
zinfo->emulated = false;
} else {
ret = emulate_report_zones(file, fd,
sector << SECTOR_SHIFT,
zone, BTRFS_REPORT_NR_ZONES);
if (ret < 0) {
error("zoned: failed to emulate BLKREPORTZONE");
exit(1);
}
zinfo->emulated = true;
}
if (!rep->nr_zones)
break;
for (i = 0; i < rep->nr_zones; i++) {
if (n >= zinfo->nr_zones)
break;
memcpy(&zinfo->zones[n], &zone[i],
sizeof(struct blk_zone));
n++;
}
sector = zone[rep->nr_zones - 1].start +
zone[rep->nr_zones - 1].len;
}
kfree(rep);
return 0;
}
/*
* Discard blocks in the zones of a zoned block device. Process this with zone
* size granularity so that blocks in conventional zones are discarded using
* discard_range and blocks in sequential zones are reset though a zone reset.
*
* We need to ensure that zones outside of the FS is not active, so that
* the FS can use all the active zones. Return EBUSY if there is an active
* zone.
*/
int btrfs_reset_zones(int fd, struct btrfs_zoned_device_info *zinfo, u64 byte_count)
{
unsigned int i;
int ret = 0;
ASSERT(zinfo);
ASSERT(IS_ALIGNED(byte_count, zinfo->zone_size));
/* Zone size granularity */
for (i = 0; i < zinfo->nr_zones; i++) {
if (byte_count == 0)
break;
if (zinfo->zones[i].type == BLK_ZONE_TYPE_CONVENTIONAL) {
ret = device_discard_blocks(fd,
zinfo->zones[i].start << SECTOR_SHIFT,
zinfo->zone_size);
if (ret == EOPNOTSUPP)
ret = 0;
} else if (zinfo->zones[i].cond != BLK_ZONE_COND_EMPTY) {
ret = btrfs_reset_dev_zone(fd, &zinfo->zones[i]);
} else {
ret = 0;
}
if (ret)
return ret;
byte_count -= zinfo->zone_size;
}
for (; i < zinfo->nr_zones; i++) {
const enum blk_zone_cond cond = zinfo->zones[i].cond;
if (zinfo->zones[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
continue;
if (cond == BLK_ZONE_COND_IMP_OPEN ||
cond == BLK_ZONE_COND_EXP_OPEN ||
cond == BLK_ZONE_COND_CLOSED)
return EBUSY;
}
return fsync(fd);
}
int zero_zone_blocks(int fd, struct btrfs_zoned_device_info *zinfo, off_t start,
size_t len)
{
size_t zone_len = zinfo->zone_size;
off_t ofst = start;
size_t count;
int ret;
/* Make sure that device_zero_blocks does not write sequential zones */
while (len > 0) {
/* Limit device_zero_blocks to a single zone */
count = min_t(size_t, len, zone_len);
if (count > zone_len - (ofst & (zone_len - 1)))
count = zone_len - (ofst & (zone_len - 1));
if (!zone_is_sequential(zinfo, ofst)) {
ret = device_zero_blocks(fd, ofst, count, true);
if (ret != 0)
return ret;
}
len -= count;
ofst += count;
}
return 0;
}
static int sb_log_location(int fd, struct blk_zone *zones, int rw, u64 *bytenr_ret)
{
u64 wp;
int ret;
/* Use the head of the zones if either zone is conventional */
if (zones[0].type == BLK_ZONE_TYPE_CONVENTIONAL) {
*bytenr_ret = zones[0].start << SECTOR_SHIFT;
return 0;
} else if (zones[1].type == BLK_ZONE_TYPE_CONVENTIONAL) {
*bytenr_ret = zones[1].start << SECTOR_SHIFT;
return 0;
}
ret = sb_write_pointer(fd, zones, &wp);
if (ret != -ENOENT && ret < 0)
return ret;
if (rw == WRITE) {
struct blk_zone *reset = NULL;
if (wp == zones[0].start << SECTOR_SHIFT)
reset = &zones[0];
else if (wp == zones[1].start << SECTOR_SHIFT)
reset = &zones[1];
if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
ASSERT(reset->cond == BLK_ZONE_COND_FULL);
ret = btrfs_reset_dev_zone(fd, reset);
if (ret)
return ret;
}
} else if (ret != -ENOENT) {
/* For READ, we want the previous one */
if (wp == zones[0].start << SECTOR_SHIFT)
wp = (zones[1].start + zones[1].len) << SECTOR_SHIFT;
wp -= BTRFS_SUPER_INFO_SIZE;
}
*bytenr_ret = wp;
return 0;
}
static u32 sb_bytenr_to_sb_zone(u64 bytenr, int zone_size_shift)
{
int mirror = -1;
for (int i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
if (bytenr == btrfs_sb_offset(i)) {
mirror = i;
break;
}
}
ASSERT(mirror != -1);
return sb_zone_number(zone_size_shift, mirror);
}
size_t btrfs_sb_io(int fd, void *buf, off_t offset, int rw)
{
size_t count = BTRFS_SUPER_INFO_SIZE;
struct stat stat_buf;
struct blk_zone_report *rep;
struct blk_zone *zones;
const u64 sb_size_sector = (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
u64 mapped = U64_MAX;
u32 zone_num;
u32 zone_size_sector;
size_t rep_size;
int ret;
size_t ret_sz;
ASSERT(rw == READ || rw == WRITE);
if (fstat(fd, &stat_buf) == -1) {
error("fstat failed: %m");
exit(1);
}
/* Do not call ioctl(BLKGETZONESZ) on a regular file. */
if ((stat_buf.st_mode & S_IFMT) == S_IFBLK) {
ret = ioctl(fd, BLKGETZONESZ, &zone_size_sector);
if (ret < 0) {
if (errno == ENOTTY || errno == EINVAL) {
/*
* No kernel support, assuming non-zoned device.
*
* Note: older kernels before 5.11 could return
* EINVAL in case the ioctl is not available,
* which is wrong.
*/
zone_size_sector = 0;
} else {
error("zoned: ioctl BLKGETZONESZ failed: %m");
exit(1);
}
}
} else {
zone_size_sector = 0;
}
/* We can call pread/pwrite if 'fd' is non-zoned device/file */
if (zone_size_sector == 0) {
if (rw == READ)
return pread(fd, buf, count, offset);
return pwrite(fd, buf, count, offset);
}
ASSERT(IS_ALIGNED(zone_size_sector, sb_size_sector));
zone_num = sb_bytenr_to_sb_zone(offset, ilog2(zone_size_sector) + SECTOR_SHIFT);
rep_size = sizeof(struct blk_zone_report) + sizeof(struct blk_zone) * 2;
rep = calloc(1, rep_size);
if (!rep) {
error_msg(ERROR_MSG_MEMORY, "zone report");
exit(1);
}
rep->sector = zone_num * (sector_t)zone_size_sector;
rep->nr_zones = 2;
ret = ioctl(fd, BLKREPORTZONE, rep);
if (ret) {
if (errno == ENOTTY || errno == EINVAL) {
/*
* Note: older kernels before 5.11 could return EINVAL
* in case the ioctl is not available, which is wrong.
*/
error("zoned: BLKREPORTZONE failed but BLKGETZONESZ works: %m");
exit(1);
}
error("zoned: ioctl BLKREPORTZONE failed: %m");
exit(1);
}
if (rep->nr_zones != 2) {
if (errno == ENOENT || errno == 0)
return (rw == WRITE ? count : 0);
error("zoned: failed to read zone info of %u and %u: %m",
zone_num, zone_num + 1);
kfree(rep);
return 0;
}
zones = (struct blk_zone *)(rep + 1);
ret = sb_log_location(fd, zones, rw, &mapped);
kfree(rep);
/*
* Special case: no superblock found in the zones. This case happens
* when initializing a file-system.
*/
if (rw == READ && ret == -ENOENT) {
memset(buf, 0, count);
return count;
}
if (ret)
return ret;
if (rw == READ)
ret_sz = btrfs_pread(fd, buf, count, mapped, true);
else
ret_sz = btrfs_pwrite(fd, buf, count, mapped, true);
if (ret_sz != count)
return ret_sz;
/* Call fsync() to force the write order */
if (rw == WRITE && fsync(fd)) {
error("failed to synchronize superblock: %m");
exit(1);
}
return ret_sz;
}
/**
* btrfs_find_allocatable_zones - find allocatable zones within a given region
*
* @device: the device to allocate a region on
* @hole_start: the position of the hole to allocate the region
* @num_bytes: size of wanted region
* @hole_end: the end of the hole
* @return: position of allocatable zones
*
* Allocatable region should not contain any superblock locations.
*/
u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
u64 hole_end, u64 num_bytes)
{
struct btrfs_zoned_device_info *zinfo = device->zone_info;
int shift = ilog2(zinfo->zone_size);
u64 nzones = num_bytes >> shift;
u64 pos = hole_start;
u64 begin, end;
bool is_sequential;
bool have_sb;
int i;
ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size));
ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size));
while (pos < hole_end) {
begin = pos >> shift;
end = begin + nzones;
if (end > zinfo->nr_zones)
return hole_end;
/*
* The zones must be all sequential (and empty), or
* conventional
*/
is_sequential = btrfs_dev_is_sequential(device, pos);
for (i = 0; i < end - begin; i++) {
u64 zone_offset = pos + ((u64)i << shift);
if ((is_sequential &&
!btrfs_dev_is_empty_zone(device, zone_offset)) ||
(is_sequential !=
btrfs_dev_is_sequential(device, zone_offset))) {
pos += zinfo->zone_size;
continue;
}
}
have_sb = false;
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
u32 sb_zone;
u64 sb_pos;
sb_zone = sb_zone_number(shift, i);
if (!(end <= sb_zone ||
sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) {
have_sb = true;
pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift;
break;
}
/* We also need to exclude regular superblock positions */
sb_pos = btrfs_sb_offset(i);
if (!(pos + num_bytes <= sb_pos ||
sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) {
have_sb = true;
pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE,
zinfo->zone_size);
break;
}
}
if (!have_sb)
break;
}
return pos;
}
/*
* Calculate an allocation pointer from the extent allocation information
* for a block group consisting of conventional zones. It is pointed to the
* end of the highest addressed extent in the block group as an allocation
* offset.
*/
static int calculate_alloc_pointer(struct btrfs_fs_info *fs_info,
struct btrfs_block_group *cache,
u64 *offset_ret)
{
struct btrfs_root *root = btrfs_extent_root(fs_info, cache->start);
struct btrfs_path *path;
struct btrfs_key key;
struct btrfs_key found_key;
int ret;
u64 length;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
key.objectid = cache->start + cache->length;
key.type = 0;
key.offset = 0;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
/* There should be no exact match (ie. an extent) at this address */
if (!ret)
ret = -EUCLEAN;
if (ret < 0)
goto out;
ret = btrfs_previous_extent_item(root, path, cache->start);
if (ret) {
if (ret == 1) {
ret = 0;
*offset_ret = 0;
}
goto out;
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
if (found_key.type == BTRFS_EXTENT_ITEM_KEY)
length = found_key.offset;
else
length = fs_info->nodesize;
if (!(found_key.objectid >= cache->start &&
found_key.objectid + length <= cache->start + cache->length)) {
ret = -EUCLEAN;
goto out;
}
*offset_ret = found_key.objectid + length - cache->start;
ret = 0;
out:
btrfs_free_path(path);
return ret;
}
bool zoned_profile_supported(u64 map_type, bool rst)
{
bool data = (map_type & BTRFS_BLOCK_GROUP_DATA);
u64 flags = (map_type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
/* SINGLE */
if (flags == 0)
return true;
if (data) {
if ((flags & BTRFS_BLOCK_GROUP_DUP) && rst)
return true;
/* Data RAID1 needs a raid-stripe-tree. */
if ((flags & BTRFS_BLOCK_GROUP_RAID1_MASK) && rst)
return true;
/* Data RAID0 needs a raid-stripe-tree. */
if ((flags & BTRFS_BLOCK_GROUP_RAID0) && rst)
return true;
/* Data RAID10 needs a raid-stripe-tree. */
if ((flags & BTRFS_BLOCK_GROUP_RAID10) && rst)
return true;
} else {
/* We can support DUP on metadata/system. */
if (flags & BTRFS_BLOCK_GROUP_DUP)
return true;
/* We can support RAID1 on metadata/system. */
if (flags & BTRFS_BLOCK_GROUP_RAID1_MASK)
return true;
/* We can support RAID0 on metadata/system. */
if (flags & BTRFS_BLOCK_GROUP_RAID0)
return true;
/* We can support RAID10 on metadata/system. */
if (flags & BTRFS_BLOCK_GROUP_RAID10)
return true;
}
/* All other profiles are not supported yet */
return false;
}
int btrfs_load_block_group_zone_info(struct btrfs_fs_info *fs_info,
struct btrfs_block_group *cache)
{
struct btrfs_device *device;
struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct cache_extent *ce;
struct map_lookup *map;
u64 logical = cache->start;
u64 length = cache->length;
u64 physical = 0;
int ret = 0;
int i;
u64 *alloc_offsets = NULL;
u64 last_alloc = 0;
u32 num_conventional = 0;
if (!btrfs_is_zoned(fs_info))
return 0;
/* Sanity check */
if (logical == BTRFS_BLOCK_RESERVED_1M_FOR_SUPER) {
if (length + SZ_1M != fs_info->zone_size) {
error("zoned: unaligned initial system block group");
return -EIO;
}
} else if (!IS_ALIGNED(length, fs_info->zone_size)) {
error("zoned: unaligned block group at %llu + %llu", logical,
length);
return -EIO;
}
/* Get the chunk mapping */
ce = search_cache_extent(&map_tree->cache_tree, logical);
if (!ce) {
error("zoned: failed to find block group at %llu", logical);
return -ENOENT;
}
map = container_of(ce, struct map_lookup, ce);
alloc_offsets = calloc(map->num_stripes, sizeof(*alloc_offsets));
if (!alloc_offsets) {
error_msg(ERROR_MSG_MEMORY, "zone offsets");
return -ENOMEM;
}
for (i = 0; i < map->num_stripes; i++) {
bool is_sequential;
struct blk_zone zone;
device = map->stripes[i].dev;
physical = map->stripes[i].physical;
if (device->fd == -1) {
alloc_offsets[i] = WP_MISSING_DEV;
continue;
}
is_sequential = btrfs_dev_is_sequential(device, physical);
if (!is_sequential)
num_conventional++;
if (!is_sequential) {
alloc_offsets[i] = WP_CONVENTIONAL;
continue;
}
/*
* The group is mapped to a sequential zone. Get the zone write
* pointer to determine the allocation offset within the zone.
*/
WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size));
zone = device->zone_info->zones[physical / fs_info->zone_size];
switch (zone.cond) {
case BLK_ZONE_COND_OFFLINE:
case BLK_ZONE_COND_READONLY:
error(
"zoned: offline/readonly zone %llu on device %s (devid %llu)",
physical / fs_info->zone_size, device->name,
device->devid);
alloc_offsets[i] = WP_MISSING_DEV;
break;
case BLK_ZONE_COND_EMPTY:
alloc_offsets[i] = 0;
break;
case BLK_ZONE_COND_FULL:
alloc_offsets[i] = fs_info->zone_size;
break;
default:
/* Partially used zone */
alloc_offsets[i] =
((zone.wp - zone.start) << SECTOR_SHIFT);
break;
}
}
if (num_conventional > 0) {
ret = calculate_alloc_pointer(fs_info, cache, &last_alloc);
if (ret || map->num_stripes == num_conventional) {
if (!ret)
cache->alloc_offset = last_alloc;
else
error(
"zoned: failed to determine allocation offset of block group %llu",
cache->start);
goto out;
}
}
if (!zoned_profile_supported(map->type, !!fs_info->stripe_root)) {
error("zoned: profile %s not yet supported",
btrfs_group_profile_str(map->type));
ret = -EINVAL;
goto out;
}
cache->alloc_offset = alloc_offsets[0];
out:
/* An extent is allocated after the write pointer */
if (!ret && num_conventional && last_alloc > cache->alloc_offset) {
error(
"zoned: got wrong write pointer in block group %llu: %llu > %llu",
logical, last_alloc, cache->alloc_offset);
ret = -EIO;
}
if (!ret)
cache->write_offset = cache->alloc_offset;
kfree(alloc_offsets);
return ret;
}
bool btrfs_redirty_extent_buffer_for_zoned(struct btrfs_fs_info *fs_info,
u64 start, u64 end)
{
u64 next;
struct btrfs_block_group *cache;
struct extent_buffer *eb;
if (!btrfs_is_zoned(fs_info))
return false;
cache = btrfs_lookup_first_block_group(fs_info, start);
BUG_ON(!cache);
if (cache->start + cache->write_offset < start) {
next = cache->start + cache->write_offset;
BUG_ON(next + fs_info->nodesize > start);
eb = btrfs_find_create_tree_block(fs_info, next);
btrfs_mark_buffer_dirty(eb);
free_extent_buffer(eb);
return true;
}
cache->write_offset += (end + 1 - start);
return false;
}
int btrfs_reset_chunk_zones(struct btrfs_fs_info *fs_info, u64 devid,
u64 offset, u64 length)
{
struct btrfs_device *device;
list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
struct btrfs_zoned_device_info *zinfo;
struct blk_zone *reset;