summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/volumes.c
blob: b9294e3c05f0b53447d5ac14f7028cfb6180d7d0 (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
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */
#include <linux/sched.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <asm/div64.h>
#include "ctree.h"
#include "extent_map.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "volumes.h"

struct stripe {
	struct btrfs_device *dev;
	u64 physical;
};

struct multi_bio {
	atomic_t stripes;
	bio_end_io_t *end_io;
	void *private;
	int error;
};

struct map_lookup {
	u64 type;
	int io_align;
	int io_width;
	int stripe_len;
	int sector_size;
	int num_stripes;
	struct stripe stripes[];
};

#define map_lookup_size(n) (sizeof(struct map_lookup) + \
			    (sizeof(struct stripe) * (n)))

static DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);

int btrfs_cleanup_fs_uuids(void)
{
	struct btrfs_fs_devices *fs_devices;
	struct list_head *uuid_cur;
	struct list_head *devices_cur;
	struct btrfs_device *dev;

	list_for_each(uuid_cur, &fs_uuids) {
		fs_devices = list_entry(uuid_cur, struct btrfs_fs_devices,
					list);
		while(!list_empty(&fs_devices->devices)) {
			devices_cur = fs_devices->devices.next;
			dev = list_entry(devices_cur, struct btrfs_device,
					 dev_list);
			printk("uuid cleanup finds %s\n", dev->name);
			if (dev->bdev) {
				printk("closing\n");
				close_bdev_excl(dev->bdev);
			}
			list_del(&dev->dev_list);
			kfree(dev);
		}
	}
	return 0;
}

static struct btrfs_device *__find_device(struct list_head *head, u64 devid)
{
	struct btrfs_device *dev;
	struct list_head *cur;

	list_for_each(cur, head) {
		dev = list_entry(cur, struct btrfs_device, dev_list);
		if (dev->devid == devid)
			return dev;
	}
	return NULL;
}

static struct btrfs_fs_devices *find_fsid(u8 *fsid)
{
	struct list_head *cur;
	struct btrfs_fs_devices *fs_devices;

	list_for_each(cur, &fs_uuids) {
		fs_devices = list_entry(cur, struct btrfs_fs_devices, list);
		if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
			return fs_devices;
	}
	return NULL;
}

static int device_list_add(const char *path,
			   struct btrfs_super_block *disk_super,
			   u64 devid, struct btrfs_fs_devices **fs_devices_ret)
{
	struct btrfs_device *device;
	struct btrfs_fs_devices *fs_devices;
	u64 found_transid = btrfs_super_generation(disk_super);

	fs_devices = find_fsid(disk_super->fsid);
	if (!fs_devices) {
		fs_devices = kmalloc(sizeof(*fs_devices), GFP_NOFS);
		if (!fs_devices)
			return -ENOMEM;
		INIT_LIST_HEAD(&fs_devices->devices);
		list_add(&fs_devices->list, &fs_uuids);
		memcpy(fs_devices->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
		fs_devices->latest_devid = devid;
		fs_devices->latest_trans = found_transid;
		fs_devices->lowest_devid = (u64)-1;
		fs_devices->num_devices = 0;
		device = NULL;
	} else {
		device = __find_device(&fs_devices->devices, devid);
	}
	if (!device) {
		device = kzalloc(sizeof(*device), GFP_NOFS);
		if (!device) {
			/* we can safely leave the fs_devices entry around */
			return -ENOMEM;
		}
		device->devid = devid;
		device->name = kstrdup(path, GFP_NOFS);
		if (!device->name) {
			kfree(device);
			return -ENOMEM;
		}
		list_add(&device->dev_list, &fs_devices->devices);
		fs_devices->num_devices++;
	}

	if (found_transid > fs_devices->latest_trans) {
		fs_devices->latest_devid = devid;
		fs_devices->latest_trans = found_transid;
	}
	if (fs_devices->lowest_devid > devid) {
		fs_devices->lowest_devid = devid;
		printk("lowest devid now %Lu\n", devid);
	}
	*fs_devices_ret = fs_devices;
	return 0;
}

int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
	struct list_head *head = &fs_devices->devices;
	struct list_head *cur;
	struct btrfs_device *device;

	mutex_lock(&uuid_mutex);
	list_for_each(cur, head) {
		device = list_entry(cur, struct btrfs_device, dev_list);
		if (device->bdev) {
			close_bdev_excl(device->bdev);
			printk("close devices closes %s\n", device->name);
		}
		device->bdev = NULL;
	}
	mutex_unlock(&uuid_mutex);
	return 0;
}

int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
		       int flags, void *holder)
{
	struct block_device *bdev;
	struct list_head *head = &fs_devices->devices;
	struct list_head *cur;
	struct btrfs_device *device;
	int ret;

	mutex_lock(&uuid_mutex);
	list_for_each(cur, head) {
		device = list_entry(cur, struct btrfs_device, dev_list);
		bdev = open_bdev_excl(device->name, flags, holder);
printk("opening %s devid %Lu\n", device->name, device->devid);
		if (IS_ERR(bdev)) {
			printk("open %s failed\n", device->name);
			ret = PTR_ERR(bdev);
			goto fail;
		}
		if (device->devid == fs_devices->latest_devid)
			fs_devices->latest_bdev = bdev;
		if (device->devid == fs_devices->lowest_devid) {
			fs_devices->lowest_bdev = bdev;
printk("lowest bdev %s\n", device->name);
		}
		device->bdev = bdev;
	}
	mutex_unlock(&uuid_mutex);
	return 0;
fail:
	mutex_unlock(&uuid_mutex);
	btrfs_close_devices(fs_devices);
	return ret;
}

int btrfs_scan_one_device(const char *path, int flags, void *holder,
			  struct btrfs_fs_devices **fs_devices_ret)
{
	struct btrfs_super_block *disk_super;
	struct block_device *bdev;
	struct buffer_head *bh;
	int ret;
	u64 devid;

	mutex_lock(&uuid_mutex);

	printk("scan one opens %s\n", path);
	bdev = open_bdev_excl(path, flags, holder);

	if (IS_ERR(bdev)) {
		printk("open failed\n");
		ret = PTR_ERR(bdev);
		goto error;
	}

	ret = set_blocksize(bdev, 4096);
	if (ret)
		goto error_close;
	bh = __bread(bdev, BTRFS_SUPER_INFO_OFFSET / 4096, 4096);
	if (!bh) {
		ret = -EIO;
		goto error_close;
	}
	disk_super = (struct btrfs_super_block *)bh->b_data;
	if (strncmp((char *)(&disk_super->magic), BTRFS_MAGIC,
	    sizeof(disk_super->magic))) {
		printk("no btrfs found on %s\n", path);
		ret = -EINVAL;
		goto error_brelse;
	}
	devid = le64_to_cpu(disk_super->dev_item.devid);
	printk("found device %Lu on %s\n", devid, path);
	ret = device_list_add(path, disk_super, devid, fs_devices_ret);

error_brelse:
	brelse(bh);
error_close:
	close_bdev_excl(bdev);
	printk("scan one closes bdev %s\n", path);
error:
	mutex_unlock(&uuid_mutex);
	return ret;
}

/*
 * this uses a pretty simple search, the expectation is that it is
 * called very infrequently and that a given device has a small number
 * of extents
 */
static int find_free_dev_extent(struct btrfs_trans_handle *trans,
				struct btrfs_device *device,
				struct btrfs_path *path,
				u64 num_bytes, u64 *start)
{
	struct btrfs_key key;
	struct btrfs_root *root = device->dev_root;
	struct btrfs_dev_extent *dev_extent = NULL;
	u64 hole_size = 0;
	u64 last_byte = 0;
	u64 search_start = 0;
	u64 search_end = device->total_bytes;
	int ret;
	int slot = 0;
	int start_found;
	struct extent_buffer *l;

	start_found = 0;
	path->reada = 2;

	/* FIXME use last free of some kind */

	/* we don't want to overwrite the superblock on the drive,
	 * so we make sure to start at an offset of at least 1MB
	 */
	search_start = max((u64)1024 * 1024, search_start);
	key.objectid = device->devid;
	key.offset = search_start;
	key.type = BTRFS_DEV_EXTENT_KEY;
	ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
	if (ret < 0)
		goto error;
	ret = btrfs_previous_item(root, path, 0, key.type);
	if (ret < 0)
		goto error;
	l = path->nodes[0];
	btrfs_item_key_to_cpu(l, &key, path->slots[0]);
	while (1) {
		l = path->nodes[0];
		slot = path->slots[0];
		if (slot >= btrfs_header_nritems(l)) {
			ret = btrfs_next_leaf(root, path);
			if (ret == 0)
				continue;
			if (ret < 0)
				goto error;
no_more_items:
			if (!start_found) {
				if (search_start >= search_end) {
					ret = -ENOSPC;
					goto error;
				}
				*start = search_start;
				start_found = 1;
				goto check_pending;
			}
			*start = last_byte > search_start ?
				last_byte : search_start;
			if (search_end <= *start) {
				ret = -ENOSPC;
				goto error;
			}
			goto check_pending;
		}
		btrfs_item_key_to_cpu(l, &key, slot);

		if (key.objectid < device->devid)
			goto next;

		if (key.objectid > device->devid)
			goto no_more_items;

		if (key.offset >= search_start && key.offset > last_byte &&
		    start_found) {
			if (last_byte < search_start)
				last_byte = search_start;
			hole_size = key.offset - last_byte;
			if (key.offset > last_byte &&
			    hole_size >= num_bytes) {
				*start = last_byte;
				goto check_pending;
			}
		}
		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY) {
			goto next;
		}

		start_found = 1;
		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
		last_byte = key.offset + btrfs_dev_extent_length(l, dev_extent);
next:
		path->slots[0]++;
		cond_resched();
	}
check_pending:
	/* we have to make sure we didn't find an extent that has already
	 * been allocated by the map tree or the original allocation
	 */
	btrfs_release_path(root, path);
	BUG_ON(*start < search_start);

	if (*start + num_bytes > search_end) {
		ret = -ENOSPC;
		goto error;
	}
	/* check for pending inserts here */
	return 0;

error:
	btrfs_release_path(root, path);
	return ret;
}

int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
			   struct btrfs_device *device,
			   u64 owner, u64 num_bytes, u64 *start)
{
	int ret;
	struct btrfs_path *path;
	struct btrfs_root *root = device->dev_root;
	struct btrfs_dev_extent *extent;
	struct extent_buffer *leaf;
	struct btrfs_key key;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = find_free_dev_extent(trans, device, path, num_bytes, start);
	if (ret) {
		goto err;
	}

	key.objectid = device->devid;
	key.offset = *start;
	key.type = BTRFS_DEV_EXTENT_KEY;
	ret = btrfs_insert_empty_item(trans, root, path, &key,
				      sizeof(*extent));
	BUG_ON(ret);

	leaf = path->nodes[0];
	extent = btrfs_item_ptr(leaf, path->slots[0],
				struct btrfs_dev_extent);
	btrfs_set_dev_extent_owner(leaf, extent, owner);
	btrfs_set_dev_extent_length(leaf, extent, num_bytes);
	btrfs_mark_buffer_dirty(leaf);
err:
	btrfs_free_path(path);
	return ret;
}

static int find_next_chunk(struct btrfs_root *root, u64 *objectid)
{
	struct btrfs_path *path;
	int ret;
	struct btrfs_key key;
	struct btrfs_key found_key;

	path = btrfs_alloc_path();
	BUG_ON(!path);

	key.objectid = (u64)-1;
	key.offset = (u64)-1;
	key.type = BTRFS_CHUNK_ITEM_KEY;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto error;

	BUG_ON(ret == 0);

	ret = btrfs_previous_item(root, path, 0, BTRFS_CHUNK_ITEM_KEY);
	if (ret) {
		*objectid = 0;
	} else {
		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
				      path->slots[0]);
		*objectid = found_key.objectid + found_key.offset;
	}
	ret = 0;
error:
	btrfs_free_path(path);
	return ret;
}

static int find_next_devid(struct btrfs_root *root, struct btrfs_path *path,
			   u64 *objectid)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_key found_key;

	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
	key.type = BTRFS_DEV_ITEM_KEY;
	key.offset = (u64)-1;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto error;

	BUG_ON(ret == 0);

	ret = btrfs_previous_item(root, path, BTRFS_DEV_ITEMS_OBJECTID,
				  BTRFS_DEV_ITEM_KEY);
	if (ret) {
		*objectid = 1;
	} else {
		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
				      path->slots[0]);
		*objectid = found_key.offset + 1;
	}
	ret = 0;
error:
	btrfs_release_path(root, path);
	return ret;
}

/*
 * the device information is stored in the chunk root
 * the btrfs_device struct should be fully filled in
 */
int btrfs_add_device(struct btrfs_trans_handle *trans,
		     struct btrfs_root *root,
		     struct btrfs_device *device)
{
	int ret;
	struct btrfs_path *path;
	struct btrfs_dev_item *dev_item;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	unsigned long ptr;
	u64 free_devid;

	root = root->fs_info->chunk_root;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = find_next_devid(root, path, &free_devid);
	if (ret)
		goto out;

	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
	key.type = BTRFS_DEV_ITEM_KEY;
	key.offset = free_devid;

	ret = btrfs_insert_empty_item(trans, root, path, &key,
				      sizeof(*dev_item));
	if (ret)
		goto out;

	leaf = path->nodes[0];
	dev_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_item);

	device->devid = free_devid;
	btrfs_set_device_id(leaf, dev_item, device->devid);
	btrfs_set_device_type(leaf, dev_item, device->type);
	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
	btrfs_set_device_total_bytes(leaf, dev_item, device->total_bytes);
	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);

	ptr = (unsigned long)btrfs_device_uuid(dev_item);
	write_extent_buffer(leaf, device->uuid, ptr, BTRFS_DEV_UUID_SIZE);
	btrfs_mark_buffer_dirty(leaf);
	ret = 0;

out:
	btrfs_free_path(path);
	return ret;
}
int btrfs_update_device(struct btrfs_trans_handle *trans,
			struct btrfs_device *device)
{
	int ret;
	struct btrfs_path *path;
	struct btrfs_root *root;
	struct btrfs_dev_item *dev_item;
	struct extent_buffer *leaf;
	struct btrfs_key key;

	root = device->dev_root->fs_info->chunk_root;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
	key.type = BTRFS_DEV_ITEM_KEY;
	key.offset = device->devid;

	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
	if (ret < 0)
		goto out;

	if (ret > 0) {
		ret = -ENOENT;
		goto out;
	}

	leaf = path->nodes[0];
	dev_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_item);

	btrfs_set_device_id(leaf, dev_item, device->devid);
	btrfs_set_device_type(leaf, dev_item, device->type);
	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
	btrfs_set_device_total_bytes(leaf, dev_item, device->total_bytes);
	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
	btrfs_mark_buffer_dirty(leaf);

out:
	btrfs_free_path(path);
	return ret;
}

int btrfs_add_system_chunk(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root,
			   struct btrfs_key *key,
			   struct btrfs_chunk *chunk, int item_size)
{
	struct btrfs_super_block *super_copy = &root->fs_info->super_copy;
	struct btrfs_disk_key disk_key;
	u32 array_size;
	u8 *ptr;

	array_size = btrfs_super_sys_array_size(super_copy);
	if (array_size + item_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
		return -EFBIG;

	ptr = super_copy->sys_chunk_array + array_size;
	btrfs_cpu_key_to_disk(&disk_key, key);
	memcpy(ptr, &disk_key, sizeof(disk_key));
	ptr += sizeof(disk_key);
	memcpy(ptr, chunk, item_size);
	item_size += sizeof(disk_key);
	btrfs_set_super_sys_array_size(super_copy, array_size + item_size);
	return 0;
}

int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
		      struct btrfs_root *extent_root, u64 *start,
		      u64 *num_bytes, u64 type)
{
	u64 dev_offset;
	struct btrfs_fs_info *info = extent_root->fs_info;
	struct btrfs_root *chunk_root = extent_root->fs_info->chunk_root;
	struct btrfs_stripe *stripes;
	struct btrfs_device *device = NULL;
	struct btrfs_chunk *chunk;
	struct list_head private_devs;
	struct list_head *dev_list = &extent_root->fs_info->fs_devices->devices;
	struct list_head *cur;
	struct extent_map_tree *em_tree;
	struct map_lookup *map;
	struct extent_map *em;
	u64 physical;
	u64 calc_size = 1024 * 1024 * 1024;
	u64 min_free = calc_size;
	u64 avail;
	u64 max_avail = 0;
	int num_stripes = 1;
	int looped = 0;
	int ret;
	int index;
	int stripe_len = 64 * 1024;
	struct btrfs_key key;

	if (list_empty(dev_list))
		return -ENOSPC;

	if (type & (BTRFS_BLOCK_GROUP_RAID0))
		num_stripes = btrfs_super_num_devices(&info->super_copy);
	if (type & (BTRFS_BLOCK_GROUP_DUP))
		num_stripes = 2;
	if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
		num_stripes = min_t(u64, 2,
				  btrfs_super_num_devices(&info->super_copy));
	}
again:
	INIT_LIST_HEAD(&private_devs);
	cur = dev_list->next;
	index = 0;

	if (type & BTRFS_BLOCK_GROUP_DUP)
		min_free = calc_size * 2;

	/* build a private list of devices we will allocate from */
	while(index < num_stripes) {
		device = list_entry(cur, struct btrfs_device, dev_list);

		avail = device->total_bytes - device->bytes_used;
		cur = cur->next;
		if (avail > max_avail)
			max_avail = avail;
		if (avail >= min_free) {
			list_move_tail(&device->dev_list, &private_devs);
			index++;
			if (type & BTRFS_BLOCK_GROUP_DUP)
				index++;
		}
		if (cur == dev_list)
			break;
	}
	if (index < num_stripes) {
		list_splice(&private_devs, dev_list);
		if (!looped && max_avail > 0) {
			looped = 1;
			calc_size = max_avail;
			goto again;
		}
		return -ENOSPC;
	}

	ret = find_next_chunk(chunk_root, &key.objectid);
	if (ret)
		return ret;

	chunk = kmalloc(btrfs_chunk_item_size(num_stripes), GFP_NOFS);
	if (!chunk)
		return -ENOMEM;

	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
	if (!map) {
		kfree(chunk);
		return -ENOMEM;
	}

	stripes = &chunk->stripe;

	if (type & (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_DUP))
		*num_bytes = calc_size;
	else
		*num_bytes = calc_size * num_stripes;

	index = 0;
printk("new chunk type %Lu start %Lu size %Lu\n", type, key.objectid, *num_bytes);
	while(index < num_stripes) {
		BUG_ON(list_empty(&private_devs));
		cur = private_devs.next;
		device = list_entry(cur, struct btrfs_device, dev_list);

		/* loop over this device again if we're doing a dup group */
		if (!(type & BTRFS_BLOCK_GROUP_DUP) ||
		    (index == num_stripes - 1))
			list_move_tail(&device->dev_list, dev_list);

		ret = btrfs_alloc_dev_extent(trans, device,
					     key.objectid,
					     calc_size, &dev_offset);
		BUG_ON(ret);
printk("alloc chunk start %Lu size %Lu from dev %Lu type %Lu\n", key.objectid, calc_size, device->devid, type);
		device->bytes_used += calc_size;
		ret = btrfs_update_device(trans, device);
		BUG_ON(ret);

		map->stripes[index].dev = device;
		map->stripes[index].physical = dev_offset;
		btrfs_set_stack_stripe_devid(stripes + index, device->devid);
		btrfs_set_stack_stripe_offset(stripes + index, dev_offset);
		physical = dev_offset;
		index++;
	}
	BUG_ON(!list_empty(&private_devs));

	/* key.objectid was set above */
	key.offset = *num_bytes;
	key.type = BTRFS_CHUNK_ITEM_KEY;
	btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
	btrfs_set_stack_chunk_stripe_len(chunk, stripe_len);
	btrfs_set_stack_chunk_type(chunk, type);
	btrfs_set_stack_chunk_num_stripes(chunk, num_stripes);
	btrfs_set_stack_chunk_io_align(chunk, stripe_len);
	btrfs_set_stack_chunk_io_width(chunk, stripe_len);
	btrfs_set_stack_chunk_sector_size(chunk, extent_root->sectorsize);
	map->sector_size = extent_root->sectorsize;
	map->stripe_len = stripe_len;
	map->io_align = stripe_len;
	map->io_width = stripe_len;
	map->type = type;
	map->num_stripes = num_stripes;

	ret = btrfs_insert_item(trans, chunk_root, &key, chunk,
				btrfs_chunk_item_size(num_stripes));
	BUG_ON(ret);
	*start = key.objectid;

	em = alloc_extent_map(GFP_NOFS);
	if (!em)
		return -ENOMEM;
	em->bdev = (struct block_device *)map;
	em->start = key.objectid;
	em->len = key.offset;
	em->block_start = 0;

	kfree(chunk);

	em_tree = &extent_root->fs_info->mapping_tree.map_tree;
	spin_lock(&em_tree->lock);
	ret = add_extent_mapping(em_tree, em);
	BUG_ON(ret);
	spin_unlock(&em_tree->lock);
	free_extent_map(em);
	return ret;
}

void btrfs_mapping_init(struct btrfs_mapping_tree *tree)
{
	extent_map_tree_init(&tree->map_tree, GFP_NOFS);
}

void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
{
	struct extent_map *em;

	while(1) {
		spin_lock(&tree->map_tree.lock);
		em = lookup_extent_mapping(&tree->map_tree, 0, (u64)-1);
		if (em)
			remove_extent_mapping(&tree->map_tree, em);
		spin_unlock(&tree->map_tree.lock);
		if (!em)
			break;
		kfree(em->bdev);
		/* once for us */
		free_extent_map(em);
		/* once for the tree */
		free_extent_map(em);
	}
}

int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
		    int dev_nr, u64 logical, u64 *phys, u64 *length,
		    struct btrfs_device **dev, int *total_devs)
{
	struct extent_map *em;
	struct map_lookup *map;
	struct extent_map_tree *em_tree = &map_tree->map_tree;
	u64 offset;
	u64 stripe_offset;
	u64 stripe_nr;
	int stripe_index;


	spin_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, logical, *length);
	BUG_ON(!em);

	BUG_ON(em->start > logical || em->start + em->len < logical);
	map = (struct map_lookup *)em->bdev;
	offset = logical - em->start;

	stripe_nr = offset;
	/*
	 * stripe_nr counts the total number of stripes we have to stride
	 * to get to this block
	 */
	do_div(stripe_nr, map->stripe_len);

	stripe_offset = stripe_nr * map->stripe_len;
	BUG_ON(offset < stripe_offset);

	/* stripe_offset is the offset of this block in its stripe*/
	stripe_offset = offset - stripe_offset;

	if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
		stripe_index = dev_nr;
		if (rw & (1 << BIO_RW))
			*total_devs = map->num_stripes;
		else {
			int i;
			u64 least = (u64)-1;
			struct btrfs_device *cur;

			for (i = 0; i < map->num_stripes; i++) {
				cur = map->stripes[i].dev;
				spin_lock(&cur->io_lock);
				if (cur->total_ios < least) {
					least = cur->total_ios;
					stripe_index = i;
				}
				spin_unlock(&cur->io_lock);
			}
			*total_devs = 1;
		}
	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
		if (rw == WRITE) {
			*total_devs = map->num_stripes;
			stripe_index = dev_nr;
		} else {
			stripe_index = 0;
			*total_devs = 1;
		}
	} else {
		/*
		 * after this do_div call, stripe_nr is the number of stripes
		 * on this device we have to walk to find the data, and
		 * stripe_index is the number of our device in the stripe array
		 */
		stripe_index = do_div(stripe_nr, map->num_stripes);
	}
	BUG_ON(stripe_index >= map->num_stripes);
	*phys = map->stripes[stripe_index].physical + stripe_offset +
		stripe_nr * map->stripe_len;

	if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
			 BTRFS_BLOCK_GROUP_DUP)) {
		/* we limit the length of each bio to what fits in a stripe */
		*length = min_t(u64, em->len - offset,
			      map->stripe_len - stripe_offset);
	} else {
		*length = em->len - offset;
	}
	*dev = map->stripes[stripe_index].dev;
	free_extent_map(em);
	spin_unlock(&em_tree->lock);
	return 0;
}

#if LINUX_VERSION_CODE > KERNEL_VERSION(2,6,23)
static void end_bio_multi_stripe(struct bio *bio, int err)
#else
static int end_bio_multi_stripe(struct bio *bio,
				   unsigned int bytes_done, int err)
#endif
{
	struct multi_bio *multi = bio->bi_private;

#if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,23)
	if (bio->bi_size)
		return 1;
#endif
	if (err)
		multi->error = err;

	if (atomic_dec_and_test(&multi->stripes)) {
		bio->bi_private = multi->private;
		bio->bi_end_io = multi->end_io;

		if (!err && multi->error)
			err = multi->error;
		kfree(multi);

		bio_endio(bio, err);
	} else {
		bio_put(bio);
	}
#if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,23)
	return 0;
#endif
}

int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio)
{
	struct btrfs_mapping_tree *map_tree;
	struct btrfs_device *dev;
	struct bio *first_bio = bio;
	u64 logical = bio->bi_sector << 9;
	u64 physical;
	u64 length = 0;
	u64 map_length;
	struct bio_vec *bvec;
	struct multi_bio *multi = NULL;
	int i;
	int ret;
	int dev_nr = 0;
	int total_devs = 1;

	bio_for_each_segment(bvec, bio, i) {
		length += bvec->bv_len;
	}

	map_tree = &root->fs_info->mapping_tree;
	map_length = length;
	while(dev_nr < total_devs) {
		ret = btrfs_map_block(map_tree, rw, dev_nr, logical,
				      &physical, &map_length, &dev,
				      &total_devs);
		if (map_length < length) {
			printk("mapping failed logical %Lu bio len %Lu physical %Lu "
			       "len %Lu\n", logical, length, physical, map_length);
			BUG();
		}
		BUG_ON(map_length < length);
		if (total_devs > 1) {
			if (!multi) {
				multi = kmalloc(sizeof(*multi), GFP_NOFS);
				atomic_set(&multi->stripes, 1);
				multi->end_io = bio->bi_end_io;
				multi->private = first_bio->bi_private;
				multi->error = 0;
			} else {
				atomic_inc(&multi->stripes);
			}
			if (dev_nr < total_devs - 1) {
				bio = bio_clone(first_bio, GFP_NOFS);
				BUG_ON(!bio);
			} else {
				bio = first_bio;
			}
			bio->bi_private = multi;
			bio->bi_end_io = end_bio_multi_stripe;
		}
		bio->bi_sector = physical >> 9;
		bio->bi_bdev = dev->bdev;
		spin_lock(&dev->io_lock);
		dev->total_ios++;
		spin_unlock(&dev->io_lock);
		submit_bio(rw, bio);
		dev_nr++;
	}
	return 0;
}

struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid)
{
	struct list_head *head = &root->fs_info->fs_devices->devices;

	return __find_device(head, devid);
}

static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
			  struct extent_buffer *leaf,
			  struct btrfs_chunk *chunk)
{
	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
	struct map_lookup *map;
	struct extent_map *em;
	u64 logical;
	u64 length;
	u64 devid;
	int num_stripes;
	int ret;
	int i;

	logical = key->objectid;
	length = key->offset;
	spin_lock(&map_tree->map_tree.lock);
	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);

	/* already mapped? */
	if (em && em->start <= logical && em->start + em->len > logical) {
		free_extent_map(em);
		spin_unlock(&map_tree->map_tree.lock);
		return 0;
	} else if (em) {
		free_extent_map(em);
	}
	spin_unlock(&map_tree->map_tree.lock);

	map = kzalloc(sizeof(*map), GFP_NOFS);
	if (!map)
		return -ENOMEM;

	em = alloc_extent_map(GFP_NOFS);
	if (!em)
		return -ENOMEM;
	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
	if (!map) {
		free_extent_map(em);
		return -ENOMEM;
	}

	em->bdev = (struct block_device *)map;
	em->start = logical;
	em->len = length;
	em->block_start = 0;

	map->num_stripes = num_stripes;
	map->io_width = btrfs_chunk_io_width(leaf, chunk);
	map->io_align = btrfs_chunk_io_align(leaf, chunk);
	map->sector_size = btrfs_chunk_sector_size(leaf, chunk);
	map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
	map->type = btrfs_chunk_type(leaf, chunk);
	for (i = 0; i < num_stripes; i++) {
		map->stripes[i].physical =
			btrfs_stripe_offset_nr(leaf, chunk, i);
		devid = btrfs_stripe_devid_nr(leaf, chunk, i);
		map->stripes[i].dev = btrfs_find_device(root, devid);
		if (!map->stripes[i].dev) {
			kfree(map);
			free_extent_map(em);
			return -EIO;
		}
	}

	spin_lock(&map_tree->map_tree.lock);
	ret = add_extent_mapping(&map_tree->map_tree, em);
	BUG_ON(ret);
	spin_unlock(&map_tree->map_tree.lock);
	free_extent_map(em);

	return 0;
}

static int fill_device_from_item(struct extent_buffer *leaf,
				 struct btrfs_dev_item *dev_item,
				 struct btrfs_device *device)
{
	unsigned long ptr;

	device->devid = btrfs_device_id(leaf, dev_item);
	device->total_bytes = btrfs_device_total_bytes(leaf, dev_item);
	device->bytes_used = btrfs_device_bytes_used(leaf, dev_item);
	device->type = btrfs_device_type(leaf, dev_item);
	device->io_align = btrfs_device_io_align(leaf, dev_item);
	device->io_width = btrfs_device_io_width(leaf, dev_item);
	device->sector_size = btrfs_device_sector_size(leaf, dev_item);

	ptr = (unsigned long)btrfs_device_uuid(dev_item);
	read_extent_buffer(leaf, device->uuid, ptr, BTRFS_DEV_UUID_SIZE);

	return 0;
}

static int read_one_dev(struct btrfs_root *root,
			struct extent_buffer *leaf,
			struct btrfs_dev_item *dev_item)
{
	struct btrfs_device *device;
	u64 devid;
	int ret;

	devid = btrfs_device_id(leaf, dev_item);
	device = btrfs_find_device(root, devid);
	if (!device) {
		printk("warning devid %Lu not found already\n", devid);
		device = kmalloc(sizeof(*device), GFP_NOFS);
		if (!device)
			return -ENOMEM;
		list_add(&device->dev_list,
			 &root->fs_info->fs_devices->devices);
		device->total_ios = 0;
		spin_lock_init(&device->io_lock);
	}

	fill_device_from_item(leaf, dev_item, device);
	device->dev_root = root->fs_info->dev_root;
	ret = 0;
#if 0
	ret = btrfs_open_device(device);
	if (ret) {
		kfree(device);
	}
#endif
	return ret;
}

int btrfs_read_super_device(struct btrfs_root *root, struct extent_buffer *buf)
{
	struct btrfs_dev_item *dev_item;

	dev_item = (struct btrfs_dev_item *)offsetof(struct btrfs_super_block,
						     dev_item);
	return read_one_dev(root, buf, dev_item);
}

int btrfs_read_sys_array(struct btrfs_root *root)
{
	struct btrfs_super_block *super_copy = &root->fs_info->super_copy;
	struct extent_buffer *sb = root->fs_info->sb_buffer;
	struct btrfs_disk_key *disk_key;
	struct btrfs_chunk *chunk;
	struct btrfs_key key;
	u32 num_stripes;
	u32 array_size;
	u32 len = 0;
	u8 *ptr;
	unsigned long sb_ptr;
	u32 cur;
	int ret;

	array_size = btrfs_super_sys_array_size(super_copy);

	/*
	 * we do this loop twice, once for the device items and
	 * once for all of the chunks.  This way there are device
	 * structs filled in for every chunk
	 */
	ptr = super_copy->sys_chunk_array;
	sb_ptr = offsetof(struct btrfs_super_block, sys_chunk_array);
	cur = 0;

	while (cur < array_size) {
		disk_key = (struct btrfs_disk_key *)ptr;
		btrfs_disk_key_to_cpu(&key, disk_key);

		len = sizeof(*disk_key);
		ptr += len;
		sb_ptr += len;
		cur += len;

		if (key.type == BTRFS_CHUNK_ITEM_KEY) {
			chunk = (struct btrfs_chunk *)sb_ptr;
			ret = read_one_chunk(root, &key, sb, chunk);
			BUG_ON(ret);
			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
			len = btrfs_chunk_item_size(num_stripes);
		} else {
			BUG();
		}
		ptr += len;
		sb_ptr += len;
		cur += len;
	}
	return 0;
}

int btrfs_read_chunk_tree(struct btrfs_root *root)
{
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	struct btrfs_key found_key;
	int ret;
	int slot;

	root = root->fs_info->chunk_root;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/* first we search for all of the device items, and then we
	 * read in all of the chunk items.  This way we can create chunk
	 * mappings that reference all of the devices that are afound
	 */
	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
	key.offset = 0;
	key.type = 0;
again:
	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	while(1) {
		leaf = path->nodes[0];
		slot = path->slots[0];
		if (slot >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret == 0)
				continue;
			if (ret < 0)
				goto error;
			break;
		}
		btrfs_item_key_to_cpu(leaf, &found_key, slot);
		if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) {
			if (found_key.objectid != BTRFS_DEV_ITEMS_OBJECTID)
				break;
			if (found_key.type == BTRFS_DEV_ITEM_KEY) {
				struct btrfs_dev_item *dev_item;
				dev_item = btrfs_item_ptr(leaf, slot,
						  struct btrfs_dev_item);
				ret = read_one_dev(root, leaf, dev_item);
				BUG_ON(ret);
			}
		} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
			struct btrfs_chunk *chunk;
			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
			ret = read_one_chunk(root, &found_key, leaf, chunk);
		}
		path->slots[0]++;
	}
	if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) {
		key.objectid = 0;
		btrfs_release_path(root, path);
		goto again;
	}

	btrfs_free_path(path);
	ret = 0;
error:
	return ret;
}