blob: 552f1c4f4dc6cc84f1c6b1f5b519bfb028c0b6ef [file] [log] [blame]
Vishal Verma5212e112015-06-25 04:20:32 -04001/*
2 * Block Translation Table
3 * Copyright (c) 2014-2015, Intel Corporation.
4 *
5 * This program is free software; you can redistribute it and/or modify it
6 * under the terms and conditions of the GNU General Public License,
7 * version 2, as published by the Free Software Foundation.
8 *
9 * This program is distributed in the hope it will be useful, but WITHOUT
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
11 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
12 * more details.
13 */
14#include <linux/highmem.h>
15#include <linux/debugfs.h>
16#include <linux/blkdev.h>
17#include <linux/module.h>
18#include <linux/device.h>
19#include <linux/mutex.h>
20#include <linux/hdreg.h>
21#include <linux/genhd.h>
22#include <linux/sizes.h>
23#include <linux/ndctl.h>
24#include <linux/fs.h>
25#include <linux/nd.h>
26#include "btt.h"
27#include "nd.h"
28
29enum log_ent_request {
30 LOG_NEW_ENT = 0,
31 LOG_OLD_ENT
32};
33
34static int btt_major;
35
36static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
37 void *buf, size_t n)
38{
39 struct nd_btt *nd_btt = arena->nd_btt;
40 struct nd_namespace_common *ndns = nd_btt->ndns;
41
42 /* arena offsets are 4K from the base of the device */
43 offset += SZ_4K;
44 return nvdimm_read_bytes(ndns, offset, buf, n);
45}
46
47static int arena_write_bytes(struct arena_info *arena, resource_size_t offset,
48 void *buf, size_t n)
49{
50 struct nd_btt *nd_btt = arena->nd_btt;
51 struct nd_namespace_common *ndns = nd_btt->ndns;
52
53 /* arena offsets are 4K from the base of the device */
54 offset += SZ_4K;
55 return nvdimm_write_bytes(ndns, offset, buf, n);
56}
57
58static int btt_info_write(struct arena_info *arena, struct btt_sb *super)
59{
60 int ret;
61
62 ret = arena_write_bytes(arena, arena->info2off, super,
63 sizeof(struct btt_sb));
64 if (ret)
65 return ret;
66
67 return arena_write_bytes(arena, arena->infooff, super,
68 sizeof(struct btt_sb));
69}
70
71static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
72{
73 WARN_ON(!super);
74 return arena_read_bytes(arena, arena->infooff, super,
75 sizeof(struct btt_sb));
76}
77
78/*
79 * 'raw' version of btt_map write
80 * Assumptions:
81 * mapping is in little-endian
82 * mapping contains 'E' and 'Z' flags as desired
83 */
84static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping)
85{
86 u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
87
88 WARN_ON(lba >= arena->external_nlba);
89 return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE);
90}
91
92static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
93 u32 z_flag, u32 e_flag)
94{
95 u32 ze;
96 __le32 mapping_le;
97
98 /*
99 * This 'mapping' is supposed to be just the LBA mapping, without
100 * any flags set, so strip the flag bits.
101 */
102 mapping &= MAP_LBA_MASK;
103
104 ze = (z_flag << 1) + e_flag;
105 switch (ze) {
106 case 0:
107 /*
108 * We want to set neither of the Z or E flags, and
109 * in the actual layout, this means setting the bit
110 * positions of both to '1' to indicate a 'normal'
111 * map entry
112 */
113 mapping |= MAP_ENT_NORMAL;
114 break;
115 case 1:
116 mapping |= (1 << MAP_ERR_SHIFT);
117 break;
118 case 2:
119 mapping |= (1 << MAP_TRIM_SHIFT);
120 break;
121 default:
122 /*
123 * The case where Z and E are both sent in as '1' could be
124 * construed as a valid 'normal' case, but we decide not to,
125 * to avoid confusion
126 */
127 WARN_ONCE(1, "Invalid use of Z and E flags\n");
128 return -EIO;
129 }
130
131 mapping_le = cpu_to_le32(mapping);
132 return __btt_map_write(arena, lba, mapping_le);
133}
134
135static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
136 int *trim, int *error)
137{
138 int ret;
139 __le32 in;
140 u32 raw_mapping, postmap, ze, z_flag, e_flag;
141 u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
142
143 WARN_ON(lba >= arena->external_nlba);
144
145 ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE);
146 if (ret)
147 return ret;
148
149 raw_mapping = le32_to_cpu(in);
150
151 z_flag = (raw_mapping & MAP_TRIM_MASK) >> MAP_TRIM_SHIFT;
152 e_flag = (raw_mapping & MAP_ERR_MASK) >> MAP_ERR_SHIFT;
153 ze = (z_flag << 1) + e_flag;
154 postmap = raw_mapping & MAP_LBA_MASK;
155
156 /* Reuse the {z,e}_flag variables for *trim and *error */
157 z_flag = 0;
158 e_flag = 0;
159
160 switch (ze) {
161 case 0:
162 /* Initial state. Return postmap = premap */
163 *mapping = lba;
164 break;
165 case 1:
166 *mapping = postmap;
167 e_flag = 1;
168 break;
169 case 2:
170 *mapping = postmap;
171 z_flag = 1;
172 break;
173 case 3:
174 *mapping = postmap;
175 break;
176 default:
177 return -EIO;
178 }
179
180 if (trim)
181 *trim = z_flag;
182 if (error)
183 *error = e_flag;
184
185 return ret;
186}
187
188static int btt_log_read_pair(struct arena_info *arena, u32 lane,
189 struct log_entry *ent)
190{
191 WARN_ON(!ent);
192 return arena_read_bytes(arena,
193 arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
194 2 * LOG_ENT_SIZE);
195}
196
197static struct dentry *debugfs_root;
198
199static void arena_debugfs_init(struct arena_info *a, struct dentry *parent,
200 int idx)
201{
202 char dirname[32];
203 struct dentry *d;
204
205 /* If for some reason, parent bttN was not created, exit */
206 if (!parent)
207 return;
208
209 snprintf(dirname, 32, "arena%d", idx);
210 d = debugfs_create_dir(dirname, parent);
211 if (IS_ERR_OR_NULL(d))
212 return;
213 a->debugfs_dir = d;
214
215 debugfs_create_x64("size", S_IRUGO, d, &a->size);
216 debugfs_create_x64("external_lba_start", S_IRUGO, d,
217 &a->external_lba_start);
218 debugfs_create_x32("internal_nlba", S_IRUGO, d, &a->internal_nlba);
219 debugfs_create_u32("internal_lbasize", S_IRUGO, d,
220 &a->internal_lbasize);
221 debugfs_create_x32("external_nlba", S_IRUGO, d, &a->external_nlba);
222 debugfs_create_u32("external_lbasize", S_IRUGO, d,
223 &a->external_lbasize);
224 debugfs_create_u32("nfree", S_IRUGO, d, &a->nfree);
225 debugfs_create_u16("version_major", S_IRUGO, d, &a->version_major);
226 debugfs_create_u16("version_minor", S_IRUGO, d, &a->version_minor);
227 debugfs_create_x64("nextoff", S_IRUGO, d, &a->nextoff);
228 debugfs_create_x64("infooff", S_IRUGO, d, &a->infooff);
229 debugfs_create_x64("dataoff", S_IRUGO, d, &a->dataoff);
230 debugfs_create_x64("mapoff", S_IRUGO, d, &a->mapoff);
231 debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff);
232 debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off);
233 debugfs_create_x32("flags", S_IRUGO, d, &a->flags);
234}
235
236static void btt_debugfs_init(struct btt *btt)
237{
238 int i = 0;
239 struct arena_info *arena;
240
241 btt->debugfs_dir = debugfs_create_dir(dev_name(&btt->nd_btt->dev),
242 debugfs_root);
243 if (IS_ERR_OR_NULL(btt->debugfs_dir))
244 return;
245
246 list_for_each_entry(arena, &btt->arena_list, list) {
247 arena_debugfs_init(arena, btt->debugfs_dir, i);
248 i++;
249 }
250}
251
252/*
253 * This function accepts two log entries, and uses the
254 * sequence number to find the 'older' entry.
255 * It also updates the sequence number in this old entry to
256 * make it the 'new' one if the mark_flag is set.
257 * Finally, it returns which of the entries was the older one.
258 *
259 * TODO The logic feels a bit kludge-y. make it better..
260 */
261static int btt_log_get_old(struct log_entry *ent)
262{
263 int old;
264
265 /*
266 * the first ever time this is seen, the entry goes into [0]
267 * the next time, the following logic works out to put this
268 * (next) entry into [1]
269 */
270 if (ent[0].seq == 0) {
271 ent[0].seq = cpu_to_le32(1);
272 return 0;
273 }
274
275 if (ent[0].seq == ent[1].seq)
276 return -EINVAL;
277 if (le32_to_cpu(ent[0].seq) + le32_to_cpu(ent[1].seq) > 5)
278 return -EINVAL;
279
280 if (le32_to_cpu(ent[0].seq) < le32_to_cpu(ent[1].seq)) {
281 if (le32_to_cpu(ent[1].seq) - le32_to_cpu(ent[0].seq) == 1)
282 old = 0;
283 else
284 old = 1;
285 } else {
286 if (le32_to_cpu(ent[0].seq) - le32_to_cpu(ent[1].seq) == 1)
287 old = 1;
288 else
289 old = 0;
290 }
291
292 return old;
293}
294
295static struct device *to_dev(struct arena_info *arena)
296{
297 return &arena->nd_btt->dev;
298}
299
300/*
301 * This function copies the desired (old/new) log entry into ent if
302 * it is not NULL. It returns the sub-slot number (0 or 1)
303 * where the desired log entry was found. Negative return values
304 * indicate errors.
305 */
306static int btt_log_read(struct arena_info *arena, u32 lane,
307 struct log_entry *ent, int old_flag)
308{
309 int ret;
310 int old_ent, ret_ent;
311 struct log_entry log[2];
312
313 ret = btt_log_read_pair(arena, lane, log);
314 if (ret)
315 return -EIO;
316
317 old_ent = btt_log_get_old(log);
318 if (old_ent < 0 || old_ent > 1) {
319 dev_info(to_dev(arena),
320 "log corruption (%d): lane %d seq [%d, %d]\n",
321 old_ent, lane, log[0].seq, log[1].seq);
322 /* TODO set error state? */
323 return -EIO;
324 }
325
326 ret_ent = (old_flag ? old_ent : (1 - old_ent));
327
328 if (ent != NULL)
329 memcpy(ent, &log[ret_ent], LOG_ENT_SIZE);
330
331 return ret_ent;
332}
333
334/*
335 * This function commits a log entry to media
336 * It does _not_ prepare the freelist entry for the next write
337 * btt_flog_write is the wrapper for updating the freelist elements
338 */
339static int __btt_log_write(struct arena_info *arena, u32 lane,
340 u32 sub, struct log_entry *ent)
341{
342 int ret;
343 /*
344 * Ignore the padding in log_entry for calculating log_half.
345 * The entry is 'committed' when we write the sequence number,
346 * and we want to ensure that that is the last thing written.
347 * We don't bother writing the padding as that would be extra
348 * media wear and write amplification
349 */
350 unsigned int log_half = (LOG_ENT_SIZE - 2 * sizeof(u64)) / 2;
351 u64 ns_off = arena->logoff + (((2 * lane) + sub) * LOG_ENT_SIZE);
352 void *src = ent;
353
354 /* split the 16B write into atomic, durable halves */
355 ret = arena_write_bytes(arena, ns_off, src, log_half);
356 if (ret)
357 return ret;
358
359 ns_off += log_half;
360 src += log_half;
361 return arena_write_bytes(arena, ns_off, src, log_half);
362}
363
364static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
365 struct log_entry *ent)
366{
367 int ret;
368
369 ret = __btt_log_write(arena, lane, sub, ent);
370 if (ret)
371 return ret;
372
373 /* prepare the next free entry */
374 arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
375 if (++(arena->freelist[lane].seq) == 4)
376 arena->freelist[lane].seq = 1;
377 arena->freelist[lane].block = le32_to_cpu(ent->old_map);
378
379 return ret;
380}
381
382/*
383 * This function initializes the BTT map to the initial state, which is
384 * all-zeroes, and indicates an identity mapping
385 */
386static int btt_map_init(struct arena_info *arena)
387{
388 int ret = -EINVAL;
389 void *zerobuf;
390 size_t offset = 0;
391 size_t chunk_size = SZ_2M;
392 size_t mapsize = arena->logoff - arena->mapoff;
393
394 zerobuf = kzalloc(chunk_size, GFP_KERNEL);
395 if (!zerobuf)
396 return -ENOMEM;
397
398 while (mapsize) {
399 size_t size = min(mapsize, chunk_size);
400
401 ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf,
402 size);
403 if (ret)
404 goto free;
405
406 offset += size;
407 mapsize -= size;
408 cond_resched();
409 }
410
411 free:
412 kfree(zerobuf);
413 return ret;
414}
415
416/*
417 * This function initializes the BTT log with 'fake' entries pointing
418 * to the initial reserved set of blocks as being free
419 */
420static int btt_log_init(struct arena_info *arena)
421{
422 int ret;
423 u32 i;
424 struct log_entry log, zerolog;
425
426 memset(&zerolog, 0, sizeof(zerolog));
427
428 for (i = 0; i < arena->nfree; i++) {
429 log.lba = cpu_to_le32(i);
430 log.old_map = cpu_to_le32(arena->external_nlba + i);
431 log.new_map = cpu_to_le32(arena->external_nlba + i);
432 log.seq = cpu_to_le32(LOG_SEQ_INIT);
433 ret = __btt_log_write(arena, i, 0, &log);
434 if (ret)
435 return ret;
436 ret = __btt_log_write(arena, i, 1, &zerolog);
437 if (ret)
438 return ret;
439 }
440
441 return 0;
442}
443
444static int btt_freelist_init(struct arena_info *arena)
445{
446 int old, new, ret;
447 u32 i, map_entry;
448 struct log_entry log_new, log_old;
449
450 arena->freelist = kcalloc(arena->nfree, sizeof(struct free_entry),
451 GFP_KERNEL);
452 if (!arena->freelist)
453 return -ENOMEM;
454
455 for (i = 0; i < arena->nfree; i++) {
456 old = btt_log_read(arena, i, &log_old, LOG_OLD_ENT);
457 if (old < 0)
458 return old;
459
460 new = btt_log_read(arena, i, &log_new, LOG_NEW_ENT);
461 if (new < 0)
462 return new;
463
464 /* sub points to the next one to be overwritten */
465 arena->freelist[i].sub = 1 - new;
466 arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
467 arena->freelist[i].block = le32_to_cpu(log_new.old_map);
468
469 /* This implies a newly created or untouched flog entry */
470 if (log_new.old_map == log_new.new_map)
471 continue;
472
473 /* Check if map recovery is needed */
474 ret = btt_map_read(arena, le32_to_cpu(log_new.lba), &map_entry,
475 NULL, NULL);
476 if (ret)
477 return ret;
478 if ((le32_to_cpu(log_new.new_map) != map_entry) &&
479 (le32_to_cpu(log_new.old_map) == map_entry)) {
480 /*
481 * Last transaction wrote the flog, but wasn't able
482 * to complete the map write. So fix up the map.
483 */
484 ret = btt_map_write(arena, le32_to_cpu(log_new.lba),
485 le32_to_cpu(log_new.new_map), 0, 0);
486 if (ret)
487 return ret;
488 }
489
490 }
491
492 return 0;
493}
494
495static int btt_rtt_init(struct arena_info *arena)
496{
497 arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL);
498 if (arena->rtt == NULL)
499 return -ENOMEM;
500
501 return 0;
502}
503
504static int btt_maplocks_init(struct arena_info *arena)
505{
506 u32 i;
507
508 arena->map_locks = kcalloc(arena->nfree, sizeof(struct aligned_lock),
509 GFP_KERNEL);
510 if (!arena->map_locks)
511 return -ENOMEM;
512
513 for (i = 0; i < arena->nfree; i++)
514 spin_lock_init(&arena->map_locks[i].lock);
515
516 return 0;
517}
518
519static struct arena_info *alloc_arena(struct btt *btt, size_t size,
520 size_t start, size_t arena_off)
521{
522 struct arena_info *arena;
523 u64 logsize, mapsize, datasize;
524 u64 available = size;
525
526 arena = kzalloc(sizeof(struct arena_info), GFP_KERNEL);
527 if (!arena)
528 return NULL;
529 arena->nd_btt = btt->nd_btt;
530
531 if (!size)
532 return arena;
533
534 arena->size = size;
535 arena->external_lba_start = start;
536 arena->external_lbasize = btt->lbasize;
537 arena->internal_lbasize = roundup(arena->external_lbasize,
538 INT_LBASIZE_ALIGNMENT);
539 arena->nfree = BTT_DEFAULT_NFREE;
540 arena->version_major = 1;
541 arena->version_minor = 1;
542
543 if (available % BTT_PG_SIZE)
544 available -= (available % BTT_PG_SIZE);
545
546 /* Two pages are reserved for the super block and its copy */
547 available -= 2 * BTT_PG_SIZE;
548
549 /* The log takes a fixed amount of space based on nfree */
550 logsize = roundup(2 * arena->nfree * sizeof(struct log_entry),
551 BTT_PG_SIZE);
552 available -= logsize;
553
554 /* Calculate optimal split between map and data area */
555 arena->internal_nlba = div_u64(available - BTT_PG_SIZE,
556 arena->internal_lbasize + MAP_ENT_SIZE);
557 arena->external_nlba = arena->internal_nlba - arena->nfree;
558
559 mapsize = roundup((arena->external_nlba * MAP_ENT_SIZE), BTT_PG_SIZE);
560 datasize = available - mapsize;
561
562 /* 'Absolute' values, relative to start of storage space */
563 arena->infooff = arena_off;
564 arena->dataoff = arena->infooff + BTT_PG_SIZE;
565 arena->mapoff = arena->dataoff + datasize;
566 arena->logoff = arena->mapoff + mapsize;
567 arena->info2off = arena->logoff + logsize;
568 return arena;
569}
570
571static void free_arenas(struct btt *btt)
572{
573 struct arena_info *arena, *next;
574
575 list_for_each_entry_safe(arena, next, &btt->arena_list, list) {
576 list_del(&arena->list);
577 kfree(arena->rtt);
578 kfree(arena->map_locks);
579 kfree(arena->freelist);
580 debugfs_remove_recursive(arena->debugfs_dir);
581 kfree(arena);
582 }
583}
584
585/*
586 * This function checks if the metadata layout is valid and error free
587 */
588static int arena_is_valid(struct arena_info *arena, struct btt_sb *super,
589 u8 *uuid, u32 lbasize)
590{
591 u64 checksum;
592
593 if (memcmp(super->uuid, uuid, 16))
594 return 0;
595
596 checksum = le64_to_cpu(super->checksum);
597 super->checksum = 0;
598 if (checksum != nd_btt_sb_checksum(super))
599 return 0;
600 super->checksum = cpu_to_le64(checksum);
601
602 if (lbasize != le32_to_cpu(super->external_lbasize))
603 return 0;
604
605 /* TODO: figure out action for this */
606 if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
607 dev_info(to_dev(arena), "Found arena with an error flag\n");
608
609 return 1;
610}
611
612/*
613 * This function reads an existing valid btt superblock and
614 * populates the corresponding arena_info struct
615 */
616static void parse_arena_meta(struct arena_info *arena, struct btt_sb *super,
617 u64 arena_off)
618{
619 arena->internal_nlba = le32_to_cpu(super->internal_nlba);
620 arena->internal_lbasize = le32_to_cpu(super->internal_lbasize);
621 arena->external_nlba = le32_to_cpu(super->external_nlba);
622 arena->external_lbasize = le32_to_cpu(super->external_lbasize);
623 arena->nfree = le32_to_cpu(super->nfree);
624 arena->version_major = le16_to_cpu(super->version_major);
625 arena->version_minor = le16_to_cpu(super->version_minor);
626
627 arena->nextoff = (super->nextoff == 0) ? 0 : (arena_off +
628 le64_to_cpu(super->nextoff));
629 arena->infooff = arena_off;
630 arena->dataoff = arena_off + le64_to_cpu(super->dataoff);
631 arena->mapoff = arena_off + le64_to_cpu(super->mapoff);
632 arena->logoff = arena_off + le64_to_cpu(super->logoff);
633 arena->info2off = arena_off + le64_to_cpu(super->info2off);
634
Dan Williams5e329402015-07-11 10:02:46 -0400635 arena->size = (le64_to_cpu(super->nextoff) > 0)
636 ? (le64_to_cpu(super->nextoff))
637 : (arena->info2off - arena->infooff + BTT_PG_SIZE);
Vishal Verma5212e112015-06-25 04:20:32 -0400638
639 arena->flags = le32_to_cpu(super->flags);
640}
641
642static int discover_arenas(struct btt *btt)
643{
644 int ret = 0;
645 struct arena_info *arena;
646 struct btt_sb *super;
647 size_t remaining = btt->rawsize;
648 u64 cur_nlba = 0;
649 size_t cur_off = 0;
650 int num_arenas = 0;
651
652 super = kzalloc(sizeof(*super), GFP_KERNEL);
653 if (!super)
654 return -ENOMEM;
655
656 while (remaining) {
657 /* Alloc memory for arena */
658 arena = alloc_arena(btt, 0, 0, 0);
659 if (!arena) {
660 ret = -ENOMEM;
661 goto out_super;
662 }
663
664 arena->infooff = cur_off;
665 ret = btt_info_read(arena, super);
666 if (ret)
667 goto out;
668
669 if (!arena_is_valid(arena, super, btt->nd_btt->uuid,
670 btt->lbasize)) {
671 if (remaining == btt->rawsize) {
672 btt->init_state = INIT_NOTFOUND;
673 dev_info(to_dev(arena), "No existing arenas\n");
674 goto out;
675 } else {
676 dev_info(to_dev(arena),
677 "Found corrupted metadata!\n");
678 ret = -ENODEV;
679 goto out;
680 }
681 }
682
683 arena->external_lba_start = cur_nlba;
684 parse_arena_meta(arena, super, cur_off);
685
686 ret = btt_freelist_init(arena);
687 if (ret)
688 goto out;
689
690 ret = btt_rtt_init(arena);
691 if (ret)
692 goto out;
693
694 ret = btt_maplocks_init(arena);
695 if (ret)
696 goto out;
697
698 list_add_tail(&arena->list, &btt->arena_list);
699
700 remaining -= arena->size;
701 cur_off += arena->size;
702 cur_nlba += arena->external_nlba;
703 num_arenas++;
704
705 if (arena->nextoff == 0)
706 break;
707 }
708 btt->num_arenas = num_arenas;
709 btt->nlba = cur_nlba;
710 btt->init_state = INIT_READY;
711
712 kfree(super);
713 return ret;
714
715 out:
716 kfree(arena);
717 free_arenas(btt);
718 out_super:
719 kfree(super);
720 return ret;
721}
722
723static int create_arenas(struct btt *btt)
724{
725 size_t remaining = btt->rawsize;
726 size_t cur_off = 0;
727
728 while (remaining) {
729 struct arena_info *arena;
730 size_t arena_size = min_t(u64, ARENA_MAX_SIZE, remaining);
731
732 remaining -= arena_size;
733 if (arena_size < ARENA_MIN_SIZE)
734 break;
735
736 arena = alloc_arena(btt, arena_size, btt->nlba, cur_off);
737 if (!arena) {
738 free_arenas(btt);
739 return -ENOMEM;
740 }
741 btt->nlba += arena->external_nlba;
742 if (remaining >= ARENA_MIN_SIZE)
743 arena->nextoff = arena->size;
744 else
745 arena->nextoff = 0;
746 cur_off += arena_size;
747 list_add_tail(&arena->list, &btt->arena_list);
748 }
749
750 return 0;
751}
752
753/*
754 * This function completes arena initialization by writing
755 * all the metadata.
756 * It is only called for an uninitialized arena when a write
757 * to that arena occurs for the first time.
758 */
759static int btt_arena_write_layout(struct arena_info *arena, u8 *uuid)
760{
761 int ret;
762 struct btt_sb *super;
763
764 ret = btt_map_init(arena);
765 if (ret)
766 return ret;
767
768 ret = btt_log_init(arena);
769 if (ret)
770 return ret;
771
772 super = kzalloc(sizeof(struct btt_sb), GFP_NOIO);
773 if (!super)
774 return -ENOMEM;
775
776 strncpy(super->signature, BTT_SIG, BTT_SIG_LEN);
777 memcpy(super->uuid, uuid, 16);
778 super->flags = cpu_to_le32(arena->flags);
779 super->version_major = cpu_to_le16(arena->version_major);
780 super->version_minor = cpu_to_le16(arena->version_minor);
781 super->external_lbasize = cpu_to_le32(arena->external_lbasize);
782 super->external_nlba = cpu_to_le32(arena->external_nlba);
783 super->internal_lbasize = cpu_to_le32(arena->internal_lbasize);
784 super->internal_nlba = cpu_to_le32(arena->internal_nlba);
785 super->nfree = cpu_to_le32(arena->nfree);
786 super->infosize = cpu_to_le32(sizeof(struct btt_sb));
787 super->nextoff = cpu_to_le64(arena->nextoff);
788 /*
789 * Subtract arena->infooff (arena start) so numbers are relative
790 * to 'this' arena
791 */
792 super->dataoff = cpu_to_le64(arena->dataoff - arena->infooff);
793 super->mapoff = cpu_to_le64(arena->mapoff - arena->infooff);
794 super->logoff = cpu_to_le64(arena->logoff - arena->infooff);
795 super->info2off = cpu_to_le64(arena->info2off - arena->infooff);
796
797 super->flags = 0;
798 super->checksum = cpu_to_le64(nd_btt_sb_checksum(super));
799
800 ret = btt_info_write(arena, super);
801
802 kfree(super);
803 return ret;
804}
805
806/*
807 * This function completes the initialization for the BTT namespace
808 * such that it is ready to accept IOs
809 */
810static int btt_meta_init(struct btt *btt)
811{
812 int ret = 0;
813 struct arena_info *arena;
814
815 mutex_lock(&btt->init_lock);
816 list_for_each_entry(arena, &btt->arena_list, list) {
817 ret = btt_arena_write_layout(arena, btt->nd_btt->uuid);
818 if (ret)
819 goto unlock;
820
821 ret = btt_freelist_init(arena);
822 if (ret)
823 goto unlock;
824
825 ret = btt_rtt_init(arena);
826 if (ret)
827 goto unlock;
828
829 ret = btt_maplocks_init(arena);
830 if (ret)
831 goto unlock;
832 }
833
834 btt->init_state = INIT_READY;
835
836 unlock:
837 mutex_unlock(&btt->init_lock);
838 return ret;
839}
840
Vishal Verma41cd8b72015-06-25 04:21:52 -0400841static u32 btt_meta_size(struct btt *btt)
842{
843 return btt->lbasize - btt->sector_size;
844}
845
Vishal Verma5212e112015-06-25 04:20:32 -0400846/*
847 * This function calculates the arena in which the given LBA lies
848 * by doing a linear walk. This is acceptable since we expect only
849 * a few arenas. If we have backing devices that get much larger,
850 * we can construct a balanced binary tree of arenas at init time
851 * so that this range search becomes faster.
852 */
853static int lba_to_arena(struct btt *btt, sector_t sector, __u32 *premap,
854 struct arena_info **arena)
855{
856 struct arena_info *arena_list;
857 __u64 lba = div_u64(sector << SECTOR_SHIFT, btt->sector_size);
858
859 list_for_each_entry(arena_list, &btt->arena_list, list) {
860 if (lba < arena_list->external_nlba) {
861 *arena = arena_list;
862 *premap = lba;
863 return 0;
864 }
865 lba -= arena_list->external_nlba;
866 }
867
868 return -EIO;
869}
870
871/*
872 * The following (lock_map, unlock_map) are mostly just to improve
873 * readability, since they index into an array of locks
874 */
875static void lock_map(struct arena_info *arena, u32 premap)
876 __acquires(&arena->map_locks[idx].lock)
877{
878 u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree;
879
880 spin_lock(&arena->map_locks[idx].lock);
881}
882
883static void unlock_map(struct arena_info *arena, u32 premap)
884 __releases(&arena->map_locks[idx].lock)
885{
886 u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree;
887
888 spin_unlock(&arena->map_locks[idx].lock);
889}
890
891static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
892{
893 return arena->dataoff + ((u64)lba * arena->internal_lbasize);
894}
895
896static int btt_data_read(struct arena_info *arena, struct page *page,
897 unsigned int off, u32 lba, u32 len)
898{
899 int ret;
900 u64 nsoff = to_namespace_offset(arena, lba);
901 void *mem = kmap_atomic(page);
902
903 ret = arena_read_bytes(arena, nsoff, mem + off, len);
904 kunmap_atomic(mem);
905
906 return ret;
907}
908
909static int btt_data_write(struct arena_info *arena, u32 lba,
910 struct page *page, unsigned int off, u32 len)
911{
912 int ret;
913 u64 nsoff = to_namespace_offset(arena, lba);
914 void *mem = kmap_atomic(page);
915
916 ret = arena_write_bytes(arena, nsoff, mem + off, len);
917 kunmap_atomic(mem);
918
919 return ret;
920}
921
922static void zero_fill_data(struct page *page, unsigned int off, u32 len)
923{
924 void *mem = kmap_atomic(page);
925
926 memset(mem + off, 0, len);
927 kunmap_atomic(mem);
928}
929
Vishal Verma41cd8b72015-06-25 04:21:52 -0400930#ifdef CONFIG_BLK_DEV_INTEGRITY
931static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
932 struct arena_info *arena, u32 postmap, int rw)
933{
934 unsigned int len = btt_meta_size(btt);
935 u64 meta_nsoff;
936 int ret = 0;
937
938 if (bip == NULL)
939 return 0;
940
941 meta_nsoff = to_namespace_offset(arena, postmap) + btt->sector_size;
942
943 while (len) {
944 unsigned int cur_len;
945 struct bio_vec bv;
946 void *mem;
947
948 bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter);
949 /*
950 * The 'bv' obtained from bvec_iter_bvec has its .bv_len and
951 * .bv_offset already adjusted for iter->bi_bvec_done, and we
952 * can use those directly
953 */
954
955 cur_len = min(len, bv.bv_len);
956 mem = kmap_atomic(bv.bv_page);
957 if (rw)
958 ret = arena_write_bytes(arena, meta_nsoff,
959 mem + bv.bv_offset, cur_len);
960 else
961 ret = arena_read_bytes(arena, meta_nsoff,
962 mem + bv.bv_offset, cur_len);
963
964 kunmap_atomic(mem);
965 if (ret)
966 return ret;
967
968 len -= cur_len;
969 meta_nsoff += cur_len;
970 bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
971 }
972
973 return ret;
974}
975
976#else /* CONFIG_BLK_DEV_INTEGRITY */
977static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
978 struct arena_info *arena, u32 postmap, int rw)
979{
980 return 0;
981}
982#endif
983
984static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
985 struct page *page, unsigned int off, sector_t sector,
986 unsigned int len)
Vishal Verma5212e112015-06-25 04:20:32 -0400987{
988 int ret = 0;
989 int t_flag, e_flag;
990 struct arena_info *arena = NULL;
991 u32 lane = 0, premap, postmap;
992
993 while (len) {
994 u32 cur_len;
995
996 lane = nd_region_acquire_lane(btt->nd_region);
997
998 ret = lba_to_arena(btt, sector, &premap, &arena);
999 if (ret)
1000 goto out_lane;
1001
1002 cur_len = min(btt->sector_size, len);
1003
1004 ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag);
1005 if (ret)
1006 goto out_lane;
1007
1008 /*
1009 * We loop to make sure that the post map LBA didn't change
1010 * from under us between writing the RTT and doing the actual
1011 * read.
1012 */
1013 while (1) {
1014 u32 new_map;
1015
1016 if (t_flag) {
1017 zero_fill_data(page, off, cur_len);
1018 goto out_lane;
1019 }
1020
1021 if (e_flag) {
1022 ret = -EIO;
1023 goto out_lane;
1024 }
1025
1026 arena->rtt[lane] = RTT_VALID | postmap;
1027 /*
1028 * Barrier to make sure this write is not reordered
1029 * to do the verification map_read before the RTT store
1030 */
1031 barrier();
1032
1033 ret = btt_map_read(arena, premap, &new_map, &t_flag,
1034 &e_flag);
1035 if (ret)
1036 goto out_rtt;
1037
1038 if (postmap == new_map)
1039 break;
1040
1041 postmap = new_map;
1042 }
1043
1044 ret = btt_data_read(arena, page, off, postmap, cur_len);
1045 if (ret)
1046 goto out_rtt;
1047
Vishal Verma41cd8b72015-06-25 04:21:52 -04001048 if (bip) {
1049 ret = btt_rw_integrity(btt, bip, arena, postmap, READ);
1050 if (ret)
1051 goto out_rtt;
1052 }
1053
Vishal Verma5212e112015-06-25 04:20:32 -04001054 arena->rtt[lane] = RTT_INVALID;
1055 nd_region_release_lane(btt->nd_region, lane);
1056
1057 len -= cur_len;
1058 off += cur_len;
1059 sector += btt->sector_size >> SECTOR_SHIFT;
1060 }
1061
1062 return 0;
1063
1064 out_rtt:
1065 arena->rtt[lane] = RTT_INVALID;
1066 out_lane:
1067 nd_region_release_lane(btt->nd_region, lane);
1068 return ret;
1069}
1070
Vishal Verma41cd8b72015-06-25 04:21:52 -04001071static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
1072 sector_t sector, struct page *page, unsigned int off,
1073 unsigned int len)
Vishal Verma5212e112015-06-25 04:20:32 -04001074{
1075 int ret = 0;
1076 struct arena_info *arena = NULL;
1077 u32 premap = 0, old_postmap, new_postmap, lane = 0, i;
1078 struct log_entry log;
1079 int sub;
1080
1081 while (len) {
1082 u32 cur_len;
1083
1084 lane = nd_region_acquire_lane(btt->nd_region);
1085
1086 ret = lba_to_arena(btt, sector, &premap, &arena);
1087 if (ret)
1088 goto out_lane;
1089 cur_len = min(btt->sector_size, len);
1090
1091 if ((arena->flags & IB_FLAG_ERROR_MASK) != 0) {
1092 ret = -EIO;
1093 goto out_lane;
1094 }
1095
1096 new_postmap = arena->freelist[lane].block;
1097
1098 /* Wait if the new block is being read from */
1099 for (i = 0; i < arena->nfree; i++)
1100 while (arena->rtt[i] == (RTT_VALID | new_postmap))
1101 cpu_relax();
1102
1103
1104 if (new_postmap >= arena->internal_nlba) {
1105 ret = -EIO;
1106 goto out_lane;
Vishal Verma41cd8b72015-06-25 04:21:52 -04001107 }
1108
1109 ret = btt_data_write(arena, new_postmap, page, off, cur_len);
Vishal Verma5212e112015-06-25 04:20:32 -04001110 if (ret)
1111 goto out_lane;
1112
Vishal Verma41cd8b72015-06-25 04:21:52 -04001113 if (bip) {
1114 ret = btt_rw_integrity(btt, bip, arena, new_postmap,
1115 WRITE);
1116 if (ret)
1117 goto out_lane;
1118 }
1119
Vishal Verma5212e112015-06-25 04:20:32 -04001120 lock_map(arena, premap);
1121 ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL);
1122 if (ret)
1123 goto out_map;
1124 if (old_postmap >= arena->internal_nlba) {
1125 ret = -EIO;
1126 goto out_map;
1127 }
1128
1129 log.lba = cpu_to_le32(premap);
1130 log.old_map = cpu_to_le32(old_postmap);
1131 log.new_map = cpu_to_le32(new_postmap);
1132 log.seq = cpu_to_le32(arena->freelist[lane].seq);
1133 sub = arena->freelist[lane].sub;
1134 ret = btt_flog_write(arena, lane, sub, &log);
1135 if (ret)
1136 goto out_map;
1137
1138 ret = btt_map_write(arena, premap, new_postmap, 0, 0);
1139 if (ret)
1140 goto out_map;
1141
1142 unlock_map(arena, premap);
1143 nd_region_release_lane(btt->nd_region, lane);
1144
1145 len -= cur_len;
1146 off += cur_len;
1147 sector += btt->sector_size >> SECTOR_SHIFT;
1148 }
1149
1150 return 0;
1151
1152 out_map:
1153 unlock_map(arena, premap);
1154 out_lane:
1155 nd_region_release_lane(btt->nd_region, lane);
1156 return ret;
1157}
1158
Vishal Verma41cd8b72015-06-25 04:21:52 -04001159static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
1160 struct page *page, unsigned int len, unsigned int off,
1161 int rw, sector_t sector)
Vishal Verma5212e112015-06-25 04:20:32 -04001162{
1163 int ret;
1164
1165 if (rw == READ) {
Vishal Verma41cd8b72015-06-25 04:21:52 -04001166 ret = btt_read_pg(btt, bip, page, off, sector, len);
Vishal Verma5212e112015-06-25 04:20:32 -04001167 flush_dcache_page(page);
1168 } else {
1169 flush_dcache_page(page);
Vishal Verma41cd8b72015-06-25 04:21:52 -04001170 ret = btt_write_pg(btt, bip, sector, page, off, len);
Vishal Verma5212e112015-06-25 04:20:32 -04001171 }
1172
1173 return ret;
1174}
1175
1176static void btt_make_request(struct request_queue *q, struct bio *bio)
1177{
Vishal Verma41cd8b72015-06-25 04:21:52 -04001178 struct bio_integrity_payload *bip = bio_integrity(bio);
Vishal Verma5212e112015-06-25 04:20:32 -04001179 struct btt *btt = q->queuedata;
1180 struct bvec_iter iter;
Dan Williamsf0dc0892015-05-16 12:28:53 -04001181 unsigned long start;
Vishal Verma5212e112015-06-25 04:20:32 -04001182 struct bio_vec bvec;
1183 int err = 0, rw;
Dan Williamsf0dc0892015-05-16 12:28:53 -04001184 bool do_acct;
Vishal Verma5212e112015-06-25 04:20:32 -04001185
Vishal Verma41cd8b72015-06-25 04:21:52 -04001186 /*
1187 * bio_integrity_enabled also checks if the bio already has an
1188 * integrity payload attached. If it does, we *don't* do a
1189 * bio_integrity_prep here - the payload has been generated by
1190 * another kernel subsystem, and we just pass it through.
1191 */
1192 if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
1193 err = -EIO;
1194 goto out;
1195 }
1196
Dan Williamsf0dc0892015-05-16 12:28:53 -04001197 do_acct = nd_iostat_start(bio, &start);
Vishal Verma5212e112015-06-25 04:20:32 -04001198 rw = bio_data_dir(bio);
1199 bio_for_each_segment(bvec, bio, iter) {
1200 unsigned int len = bvec.bv_len;
1201
1202 BUG_ON(len > PAGE_SIZE);
1203 /* Make sure len is in multiples of sector size. */
1204 /* XXX is this right? */
1205 BUG_ON(len < btt->sector_size);
1206 BUG_ON(len % btt->sector_size);
1207
Vishal Verma41cd8b72015-06-25 04:21:52 -04001208 err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
Vishal Verma5212e112015-06-25 04:20:32 -04001209 rw, iter.bi_sector);
1210 if (err) {
1211 dev_info(&btt->nd_btt->dev,
1212 "io error in %s sector %lld, len %d,\n",
1213 (rw == READ) ? "READ" : "WRITE",
1214 (unsigned long long) iter.bi_sector, len);
Dan Williamsf0dc0892015-05-16 12:28:53 -04001215 break;
Vishal Verma5212e112015-06-25 04:20:32 -04001216 }
1217 }
Dan Williamsf0dc0892015-05-16 12:28:53 -04001218 if (do_acct)
1219 nd_iostat_end(bio, start);
Vishal Verma5212e112015-06-25 04:20:32 -04001220
1221out:
1222 bio_endio(bio, err);
1223}
1224
1225static int btt_rw_page(struct block_device *bdev, sector_t sector,
1226 struct page *page, int rw)
1227{
1228 struct btt *btt = bdev->bd_disk->private_data;
1229
Vishal Verma41cd8b72015-06-25 04:21:52 -04001230 btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector);
Vishal Verma5212e112015-06-25 04:20:32 -04001231 page_endio(page, rw & WRITE, 0);
1232 return 0;
1233}
1234
1235
1236static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo)
1237{
1238 /* some standard values */
1239 geo->heads = 1 << 6;
1240 geo->sectors = 1 << 5;
1241 geo->cylinders = get_capacity(bd->bd_disk) >> 11;
1242 return 0;
1243}
1244
1245static const struct block_device_operations btt_fops = {
1246 .owner = THIS_MODULE,
1247 .rw_page = btt_rw_page,
1248 .getgeo = btt_getgeo,
Dan Williams58138822015-06-23 20:08:34 -04001249 .revalidate_disk = nvdimm_revalidate_disk,
Vishal Verma5212e112015-06-25 04:20:32 -04001250};
1251
1252static int btt_blk_init(struct btt *btt)
1253{
1254 struct nd_btt *nd_btt = btt->nd_btt;
1255 struct nd_namespace_common *ndns = nd_btt->ndns;
1256
1257 /* create a new disk and request queue for btt */
1258 btt->btt_queue = blk_alloc_queue(GFP_KERNEL);
1259 if (!btt->btt_queue)
1260 return -ENOMEM;
1261
1262 btt->btt_disk = alloc_disk(0);
1263 if (!btt->btt_disk) {
1264 blk_cleanup_queue(btt->btt_queue);
1265 return -ENOMEM;
1266 }
1267
1268 nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
1269 btt->btt_disk->driverfs_dev = &btt->nd_btt->dev;
1270 btt->btt_disk->major = btt_major;
1271 btt->btt_disk->first_minor = 0;
1272 btt->btt_disk->fops = &btt_fops;
1273 btt->btt_disk->private_data = btt;
1274 btt->btt_disk->queue = btt->btt_queue;
1275 btt->btt_disk->flags = GENHD_FL_EXT_DEVT;
1276
1277 blk_queue_make_request(btt->btt_queue, btt_make_request);
1278 blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
1279 blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
1280 blk_queue_bounce_limit(btt->btt_queue, BLK_BOUNCE_ANY);
1281 queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue);
1282 btt->btt_queue->queuedata = btt;
1283
Vishal Verma41cd8b72015-06-25 04:21:52 -04001284 set_capacity(btt->btt_disk, 0);
Vishal Verma5212e112015-06-25 04:20:32 -04001285 add_disk(btt->btt_disk);
Vishal Verma41cd8b72015-06-25 04:21:52 -04001286 if (btt_meta_size(btt)) {
1287 int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt));
1288
1289 if (rc) {
1290 del_gendisk(btt->btt_disk);
1291 put_disk(btt->btt_disk);
1292 blk_cleanup_queue(btt->btt_queue);
1293 return rc;
1294 }
1295 }
1296 set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
Dan Williams58138822015-06-23 20:08:34 -04001297 revalidate_disk(btt->btt_disk);
Vishal Verma5212e112015-06-25 04:20:32 -04001298
1299 return 0;
1300}
1301
1302static void btt_blk_cleanup(struct btt *btt)
1303{
Vishal Verma41cd8b72015-06-25 04:21:52 -04001304 blk_integrity_unregister(btt->btt_disk);
Vishal Verma5212e112015-06-25 04:20:32 -04001305 del_gendisk(btt->btt_disk);
1306 put_disk(btt->btt_disk);
1307 blk_cleanup_queue(btt->btt_queue);
1308}
1309
1310/**
1311 * btt_init - initialize a block translation table for the given device
1312 * @nd_btt: device with BTT geometry and backing device info
1313 * @rawsize: raw size in bytes of the backing device
1314 * @lbasize: lba size of the backing device
1315 * @uuid: A uuid for the backing device - this is stored on media
1316 * @maxlane: maximum number of parallel requests the device can handle
1317 *
1318 * Initialize a Block Translation Table on a backing device to provide
1319 * single sector power fail atomicity.
1320 *
1321 * Context:
1322 * Might sleep.
1323 *
1324 * Returns:
1325 * Pointer to a new struct btt on success, NULL on failure.
1326 */
1327static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
1328 u32 lbasize, u8 *uuid, struct nd_region *nd_region)
1329{
1330 int ret;
1331 struct btt *btt;
1332 struct device *dev = &nd_btt->dev;
1333
1334 btt = kzalloc(sizeof(struct btt), GFP_KERNEL);
1335 if (!btt)
1336 return NULL;
1337
1338 btt->nd_btt = nd_btt;
1339 btt->rawsize = rawsize;
1340 btt->lbasize = lbasize;
1341 btt->sector_size = ((lbasize >= 4096) ? 4096 : 512);
1342 INIT_LIST_HEAD(&btt->arena_list);
1343 mutex_init(&btt->init_lock);
1344 btt->nd_region = nd_region;
1345
1346 ret = discover_arenas(btt);
1347 if (ret) {
1348 dev_err(dev, "init: error in arena_discover: %d\n", ret);
1349 goto out_free;
1350 }
1351
Dan Williams58138822015-06-23 20:08:34 -04001352 if (btt->init_state != INIT_READY && nd_region->ro) {
1353 dev_info(dev, "%s is read-only, unable to init btt metadata\n",
1354 dev_name(&nd_region->dev));
1355 goto out_free;
1356 } else if (btt->init_state != INIT_READY) {
Vishal Verma5212e112015-06-25 04:20:32 -04001357 btt->num_arenas = (rawsize / ARENA_MAX_SIZE) +
1358 ((rawsize % ARENA_MAX_SIZE) ? 1 : 0);
1359 dev_dbg(dev, "init: %d arenas for %llu rawsize\n",
1360 btt->num_arenas, rawsize);
1361
1362 ret = create_arenas(btt);
1363 if (ret) {
1364 dev_info(dev, "init: create_arenas: %d\n", ret);
1365 goto out_free;
1366 }
1367
1368 ret = btt_meta_init(btt);
1369 if (ret) {
1370 dev_err(dev, "init: error in meta_init: %d\n", ret);
Dan Williams58138822015-06-23 20:08:34 -04001371 goto out_free;
Vishal Verma5212e112015-06-25 04:20:32 -04001372 }
1373 }
1374
1375 ret = btt_blk_init(btt);
1376 if (ret) {
1377 dev_err(dev, "init: error in blk_init: %d\n", ret);
1378 goto out_free;
1379 }
1380
1381 btt_debugfs_init(btt);
1382
1383 return btt;
1384
1385 out_free:
1386 kfree(btt);
1387 return NULL;
1388}
1389
1390/**
1391 * btt_fini - de-initialize a BTT
1392 * @btt: the BTT handle that was generated by btt_init
1393 *
1394 * De-initialize a Block Translation Table on device removal
1395 *
1396 * Context:
1397 * Might sleep.
1398 */
1399static void btt_fini(struct btt *btt)
1400{
1401 if (btt) {
1402 btt_blk_cleanup(btt);
1403 free_arenas(btt);
1404 debugfs_remove_recursive(btt->debugfs_dir);
1405 kfree(btt);
1406 }
1407}
1408
1409int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
1410{
1411 struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
1412 struct nd_region *nd_region;
1413 struct btt *btt;
1414 size_t rawsize;
1415
1416 if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize)
1417 return -ENODEV;
1418
1419 rawsize = nvdimm_namespace_capacity(ndns) - SZ_4K;
1420 if (rawsize < ARENA_MIN_SIZE) {
1421 return -ENXIO;
1422 }
1423 nd_region = to_nd_region(nd_btt->dev.parent);
1424 btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid,
1425 nd_region);
1426 if (!btt)
1427 return -ENOMEM;
1428 nd_btt->btt = btt;
1429
1430 return 0;
1431}
1432EXPORT_SYMBOL(nvdimm_namespace_attach_btt);
1433
1434int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns)
1435{
1436 struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
1437 struct btt *btt = nd_btt->btt;
1438
1439 btt_fini(btt);
1440 nd_btt->btt = NULL;
1441
1442 return 0;
1443}
1444EXPORT_SYMBOL(nvdimm_namespace_detach_btt);
1445
1446static int __init nd_btt_init(void)
1447{
1448 int rc;
1449
1450 BUILD_BUG_ON(sizeof(struct btt_sb) != SZ_4K);
1451
1452 btt_major = register_blkdev(0, "btt");
1453 if (btt_major < 0)
1454 return btt_major;
1455
1456 debugfs_root = debugfs_create_dir("btt", NULL);
1457 if (IS_ERR_OR_NULL(debugfs_root)) {
1458 rc = -ENXIO;
1459 goto err_debugfs;
1460 }
1461
1462 return 0;
1463
1464 err_debugfs:
1465 unregister_blkdev(btt_major, "btt");
1466
1467 return rc;
1468}
1469
1470static void __exit nd_btt_exit(void)
1471{
1472 debugfs_remove_recursive(debugfs_root);
1473 unregister_blkdev(btt_major, "btt");
1474}
1475
1476MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT);
1477MODULE_AUTHOR("Vishal Verma <vishal.l.verma@linux.intel.com>");
1478MODULE_LICENSE("GPL v2");
1479module_init(nd_btt_init);
1480module_exit(nd_btt_exit);