1/* 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 reads an existing valid btt superblock and 587 * populates the corresponding arena_info struct 588 */ 589static void parse_arena_meta(struct arena_info *arena, struct btt_sb *super, 590 u64 arena_off) 591{ 592 arena->internal_nlba = le32_to_cpu(super->internal_nlba); 593 arena->internal_lbasize = le32_to_cpu(super->internal_lbasize); 594 arena->external_nlba = le32_to_cpu(super->external_nlba); 595 arena->external_lbasize = le32_to_cpu(super->external_lbasize); 596 arena->nfree = le32_to_cpu(super->nfree); 597 arena->version_major = le16_to_cpu(super->version_major); 598 arena->version_minor = le16_to_cpu(super->version_minor); 599 600 arena->nextoff = (super->nextoff == 0) ? 0 : (arena_off + 601 le64_to_cpu(super->nextoff)); 602 arena->infooff = arena_off; 603 arena->dataoff = arena_off + le64_to_cpu(super->dataoff); 604 arena->mapoff = arena_off + le64_to_cpu(super->mapoff); 605 arena->logoff = arena_off + le64_to_cpu(super->logoff); 606 arena->info2off = arena_off + le64_to_cpu(super->info2off); 607 608 arena->size = (le64_to_cpu(super->nextoff) > 0) 609 ? (le64_to_cpu(super->nextoff)) 610 : (arena->info2off - arena->infooff + BTT_PG_SIZE); 611 612 arena->flags = le32_to_cpu(super->flags); 613} 614 615static int discover_arenas(struct btt *btt) 616{ 617 int ret = 0; 618 struct arena_info *arena; 619 struct btt_sb *super; 620 size_t remaining = btt->rawsize; 621 u64 cur_nlba = 0; 622 size_t cur_off = 0; 623 int num_arenas = 0; 624 625 super = kzalloc(sizeof(*super), GFP_KERNEL); 626 if (!super) 627 return -ENOMEM; 628 629 while (remaining) { 630 /* Alloc memory for arena */ 631 arena = alloc_arena(btt, 0, 0, 0); 632 if (!arena) { 633 ret = -ENOMEM; 634 goto out_super; 635 } 636 637 arena->infooff = cur_off; 638 ret = btt_info_read(arena, super); 639 if (ret) 640 goto out; 641 642 if (!nd_btt_arena_is_valid(btt->nd_btt, super)) { 643 if (remaining == btt->rawsize) { 644 btt->init_state = INIT_NOTFOUND; 645 dev_info(to_dev(arena), "No existing arenas\n"); 646 goto out; 647 } else { 648 dev_info(to_dev(arena), 649 "Found corrupted metadata!\n"); 650 ret = -ENODEV; 651 goto out; 652 } 653 } 654 655 arena->external_lba_start = cur_nlba; 656 parse_arena_meta(arena, super, cur_off); 657 658 ret = btt_freelist_init(arena); 659 if (ret) 660 goto out; 661 662 ret = btt_rtt_init(arena); 663 if (ret) 664 goto out; 665 666 ret = btt_maplocks_init(arena); 667 if (ret) 668 goto out; 669 670 list_add_tail(&arena->list, &btt->arena_list); 671 672 remaining -= arena->size; 673 cur_off += arena->size; 674 cur_nlba += arena->external_nlba; 675 num_arenas++; 676 677 if (arena->nextoff == 0) 678 break; 679 } 680 btt->num_arenas = num_arenas; 681 btt->nlba = cur_nlba; 682 btt->init_state = INIT_READY; 683 684 kfree(super); 685 return ret; 686 687 out: 688 kfree(arena); 689 free_arenas(btt); 690 out_super: 691 kfree(super); 692 return ret; 693} 694 695static int create_arenas(struct btt *btt) 696{ 697 size_t remaining = btt->rawsize; 698 size_t cur_off = 0; 699 700 while (remaining) { 701 struct arena_info *arena; 702 size_t arena_size = min_t(u64, ARENA_MAX_SIZE, remaining); 703 704 remaining -= arena_size; 705 if (arena_size < ARENA_MIN_SIZE) 706 break; 707 708 arena = alloc_arena(btt, arena_size, btt->nlba, cur_off); 709 if (!arena) { 710 free_arenas(btt); 711 return -ENOMEM; 712 } 713 btt->nlba += arena->external_nlba; 714 if (remaining >= ARENA_MIN_SIZE) 715 arena->nextoff = arena->size; 716 else 717 arena->nextoff = 0; 718 cur_off += arena_size; 719 list_add_tail(&arena->list, &btt->arena_list); 720 } 721 722 return 0; 723} 724 725/* 726 * This function completes arena initialization by writing 727 * all the metadata. 728 * It is only called for an uninitialized arena when a write 729 * to that arena occurs for the first time. 730 */ 731static int btt_arena_write_layout(struct arena_info *arena) 732{ 733 int ret; 734 u64 sum; 735 struct btt_sb *super; 736 struct nd_btt *nd_btt = arena->nd_btt; 737 const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); 738 739 ret = btt_map_init(arena); 740 if (ret) 741 return ret; 742 743 ret = btt_log_init(arena); 744 if (ret) 745 return ret; 746 747 super = kzalloc(sizeof(struct btt_sb), GFP_NOIO); 748 if (!super) 749 return -ENOMEM; 750 751 strncpy(super->signature, BTT_SIG, BTT_SIG_LEN); 752 memcpy(super->uuid, nd_btt->uuid, 16); 753 memcpy(super->parent_uuid, parent_uuid, 16); 754 super->flags = cpu_to_le32(arena->flags); 755 super->version_major = cpu_to_le16(arena->version_major); 756 super->version_minor = cpu_to_le16(arena->version_minor); 757 super->external_lbasize = cpu_to_le32(arena->external_lbasize); 758 super->external_nlba = cpu_to_le32(arena->external_nlba); 759 super->internal_lbasize = cpu_to_le32(arena->internal_lbasize); 760 super->internal_nlba = cpu_to_le32(arena->internal_nlba); 761 super->nfree = cpu_to_le32(arena->nfree); 762 super->infosize = cpu_to_le32(sizeof(struct btt_sb)); 763 super->nextoff = cpu_to_le64(arena->nextoff); 764 /* 765 * Subtract arena->infooff (arena start) so numbers are relative 766 * to 'this' arena 767 */ 768 super->dataoff = cpu_to_le64(arena->dataoff - arena->infooff); 769 super->mapoff = cpu_to_le64(arena->mapoff - arena->infooff); 770 super->logoff = cpu_to_le64(arena->logoff - arena->infooff); 771 super->info2off = cpu_to_le64(arena->info2off - arena->infooff); 772 773 super->flags = 0; 774 sum = nd_sb_checksum((struct nd_gen_sb *) super); 775 super->checksum = cpu_to_le64(sum); 776 777 ret = btt_info_write(arena, super); 778 779 kfree(super); 780 return ret; 781} 782 783/* 784 * This function completes the initialization for the BTT namespace 785 * such that it is ready to accept IOs 786 */ 787static int btt_meta_init(struct btt *btt) 788{ 789 int ret = 0; 790 struct arena_info *arena; 791 792 mutex_lock(&btt->init_lock); 793 list_for_each_entry(arena, &btt->arena_list, list) { 794 ret = btt_arena_write_layout(arena); 795 if (ret) 796 goto unlock; 797 798 ret = btt_freelist_init(arena); 799 if (ret) 800 goto unlock; 801 802 ret = btt_rtt_init(arena); 803 if (ret) 804 goto unlock; 805 806 ret = btt_maplocks_init(arena); 807 if (ret) 808 goto unlock; 809 } 810 811 btt->init_state = INIT_READY; 812 813 unlock: 814 mutex_unlock(&btt->init_lock); 815 return ret; 816} 817 818static u32 btt_meta_size(struct btt *btt) 819{ 820 return btt->lbasize - btt->sector_size; 821} 822 823/* 824 * This function calculates the arena in which the given LBA lies 825 * by doing a linear walk. This is acceptable since we expect only 826 * a few arenas. If we have backing devices that get much larger, 827 * we can construct a balanced binary tree of arenas at init time 828 * so that this range search becomes faster. 829 */ 830static int lba_to_arena(struct btt *btt, sector_t sector, __u32 *premap, 831 struct arena_info **arena) 832{ 833 struct arena_info *arena_list; 834 __u64 lba = div_u64(sector << SECTOR_SHIFT, btt->sector_size); 835 836 list_for_each_entry(arena_list, &btt->arena_list, list) { 837 if (lba < arena_list->external_nlba) { 838 *arena = arena_list; 839 *premap = lba; 840 return 0; 841 } 842 lba -= arena_list->external_nlba; 843 } 844 845 return -EIO; 846} 847 848/* 849 * The following (lock_map, unlock_map) are mostly just to improve 850 * readability, since they index into an array of locks 851 */ 852static void lock_map(struct arena_info *arena, u32 premap) 853 __acquires(&arena->map_locks[idx].lock) 854{ 855 u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree; 856 857 spin_lock(&arena->map_locks[idx].lock); 858} 859 860static void unlock_map(struct arena_info *arena, u32 premap) 861 __releases(&arena->map_locks[idx].lock) 862{ 863 u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree; 864 865 spin_unlock(&arena->map_locks[idx].lock); 866} 867 868static u64 to_namespace_offset(struct arena_info *arena, u64 lba) 869{ 870 return arena->dataoff + ((u64)lba * arena->internal_lbasize); 871} 872 873static int btt_data_read(struct arena_info *arena, struct page *page, 874 unsigned int off, u32 lba, u32 len) 875{ 876 int ret; 877 u64 nsoff = to_namespace_offset(arena, lba); 878 void *mem = kmap_atomic(page); 879 880 ret = arena_read_bytes(arena, nsoff, mem + off, len); 881 kunmap_atomic(mem); 882 883 return ret; 884} 885 886static int btt_data_write(struct arena_info *arena, u32 lba, 887 struct page *page, unsigned int off, u32 len) 888{ 889 int ret; 890 u64 nsoff = to_namespace_offset(arena, lba); 891 void *mem = kmap_atomic(page); 892 893 ret = arena_write_bytes(arena, nsoff, mem + off, len); 894 kunmap_atomic(mem); 895 896 return ret; 897} 898 899static void zero_fill_data(struct page *page, unsigned int off, u32 len) 900{ 901 void *mem = kmap_atomic(page); 902 903 memset(mem + off, 0, len); 904 kunmap_atomic(mem); 905} 906 907#ifdef CONFIG_BLK_DEV_INTEGRITY 908static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip, 909 struct arena_info *arena, u32 postmap, int rw) 910{ 911 unsigned int len = btt_meta_size(btt); 912 u64 meta_nsoff; 913 int ret = 0; 914 915 if (bip == NULL) 916 return 0; 917 918 meta_nsoff = to_namespace_offset(arena, postmap) + btt->sector_size; 919 920 while (len) { 921 unsigned int cur_len; 922 struct bio_vec bv; 923 void *mem; 924 925 bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter); 926 /* 927 * The 'bv' obtained from bvec_iter_bvec has its .bv_len and 928 * .bv_offset already adjusted for iter->bi_bvec_done, and we 929 * can use those directly 930 */ 931 932 cur_len = min(len, bv.bv_len); 933 mem = kmap_atomic(bv.bv_page); 934 if (rw) 935 ret = arena_write_bytes(arena, meta_nsoff, 936 mem + bv.bv_offset, cur_len); 937 else 938 ret = arena_read_bytes(arena, meta_nsoff, 939 mem + bv.bv_offset, cur_len); 940 941 kunmap_atomic(mem); 942 if (ret) 943 return ret; 944 945 len -= cur_len; 946 meta_nsoff += cur_len; 947 bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len); 948 } 949 950 return ret; 951} 952 953#else /* CONFIG_BLK_DEV_INTEGRITY */ 954static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip, 955 struct arena_info *arena, u32 postmap, int rw) 956{ 957 return 0; 958} 959#endif 960 961static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip, 962 struct page *page, unsigned int off, sector_t sector, 963 unsigned int len) 964{ 965 int ret = 0; 966 int t_flag, e_flag; 967 struct arena_info *arena = NULL; 968 u32 lane = 0, premap, postmap; 969 970 while (len) { 971 u32 cur_len; 972 973 lane = nd_region_acquire_lane(btt->nd_region); 974 975 ret = lba_to_arena(btt, sector, &premap, &arena); 976 if (ret) 977 goto out_lane; 978 979 cur_len = min(btt->sector_size, len); 980 981 ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag); 982 if (ret) 983 goto out_lane; 984 985 /* 986 * We loop to make sure that the post map LBA didn't change 987 * from under us between writing the RTT and doing the actual 988 * read. 989 */ 990 while (1) { 991 u32 new_map; 992 993 if (t_flag) { 994 zero_fill_data(page, off, cur_len); 995 goto out_lane; 996 } 997 998 if (e_flag) { 999 ret = -EIO; 1000 goto out_lane; 1001 } 1002 1003 arena->rtt[lane] = RTT_VALID | postmap; 1004 /* 1005 * Barrier to make sure this write is not reordered 1006 * to do the verification map_read before the RTT store 1007 */ 1008 barrier(); 1009 1010 ret = btt_map_read(arena, premap, &new_map, &t_flag, 1011 &e_flag); 1012 if (ret) 1013 goto out_rtt; 1014 1015 if (postmap == new_map) 1016 break; 1017 1018 postmap = new_map; 1019 } 1020 1021 ret = btt_data_read(arena, page, off, postmap, cur_len); 1022 if (ret) 1023 goto out_rtt; 1024 1025 if (bip) { 1026 ret = btt_rw_integrity(btt, bip, arena, postmap, READ); 1027 if (ret) 1028 goto out_rtt; 1029 } 1030 1031 arena->rtt[lane] = RTT_INVALID; 1032 nd_region_release_lane(btt->nd_region, lane); 1033 1034 len -= cur_len; 1035 off += cur_len; 1036 sector += btt->sector_size >> SECTOR_SHIFT; 1037 } 1038 1039 return 0; 1040 1041 out_rtt: 1042 arena->rtt[lane] = RTT_INVALID; 1043 out_lane: 1044 nd_region_release_lane(btt->nd_region, lane); 1045 return ret; 1046} 1047 1048static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, 1049 sector_t sector, struct page *page, unsigned int off, 1050 unsigned int len) 1051{ 1052 int ret = 0; 1053 struct arena_info *arena = NULL; 1054 u32 premap = 0, old_postmap, new_postmap, lane = 0, i; 1055 struct log_entry log; 1056 int sub; 1057 1058 while (len) { 1059 u32 cur_len; 1060 1061 lane = nd_region_acquire_lane(btt->nd_region); 1062 1063 ret = lba_to_arena(btt, sector, &premap, &arena); 1064 if (ret) 1065 goto out_lane; 1066 cur_len = min(btt->sector_size, len); 1067 1068 if ((arena->flags & IB_FLAG_ERROR_MASK) != 0) { 1069 ret = -EIO; 1070 goto out_lane; 1071 } 1072 1073 new_postmap = arena->freelist[lane].block; 1074 1075 /* Wait if the new block is being read from */ 1076 for (i = 0; i < arena->nfree; i++) 1077 while (arena->rtt[i] == (RTT_VALID | new_postmap)) 1078 cpu_relax(); 1079 1080 1081 if (new_postmap >= arena->internal_nlba) { 1082 ret = -EIO; 1083 goto out_lane; 1084 } 1085 1086 ret = btt_data_write(arena, new_postmap, page, off, cur_len); 1087 if (ret) 1088 goto out_lane; 1089 1090 if (bip) { 1091 ret = btt_rw_integrity(btt, bip, arena, new_postmap, 1092 WRITE); 1093 if (ret) 1094 goto out_lane; 1095 } 1096 1097 lock_map(arena, premap); 1098 ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL); 1099 if (ret) 1100 goto out_map; 1101 if (old_postmap >= arena->internal_nlba) { 1102 ret = -EIO; 1103 goto out_map; 1104 } 1105 1106 log.lba = cpu_to_le32(premap); 1107 log.old_map = cpu_to_le32(old_postmap); 1108 log.new_map = cpu_to_le32(new_postmap); 1109 log.seq = cpu_to_le32(arena->freelist[lane].seq); 1110 sub = arena->freelist[lane].sub; 1111 ret = btt_flog_write(arena, lane, sub, &log); 1112 if (ret) 1113 goto out_map; 1114 1115 ret = btt_map_write(arena, premap, new_postmap, 0, 0); 1116 if (ret) 1117 goto out_map; 1118 1119 unlock_map(arena, premap); 1120 nd_region_release_lane(btt->nd_region, lane); 1121 1122 len -= cur_len; 1123 off += cur_len; 1124 sector += btt->sector_size >> SECTOR_SHIFT; 1125 } 1126 1127 return 0; 1128 1129 out_map: 1130 unlock_map(arena, premap); 1131 out_lane: 1132 nd_region_release_lane(btt->nd_region, lane); 1133 return ret; 1134} 1135 1136static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip, 1137 struct page *page, unsigned int len, unsigned int off, 1138 int rw, sector_t sector) 1139{ 1140 int ret; 1141 1142 if (rw == READ) { 1143 ret = btt_read_pg(btt, bip, page, off, sector, len); 1144 flush_dcache_page(page); 1145 } else { 1146 flush_dcache_page(page); 1147 ret = btt_write_pg(btt, bip, sector, page, off, len); 1148 } 1149 1150 return ret; 1151} 1152 1153static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) 1154{ 1155 struct bio_integrity_payload *bip = bio_integrity(bio); 1156 struct btt *btt = q->queuedata; 1157 struct bvec_iter iter; 1158 unsigned long start; 1159 struct bio_vec bvec; 1160 int err = 0, rw; 1161 bool do_acct; 1162 1163 /* 1164 * bio_integrity_enabled also checks if the bio already has an 1165 * integrity payload attached. If it does, we *don't* do a 1166 * bio_integrity_prep here - the payload has been generated by 1167 * another kernel subsystem, and we just pass it through. 1168 */ 1169 if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { 1170 bio->bi_error = -EIO; 1171 goto out; 1172 } 1173 1174 do_acct = nd_iostat_start(bio, &start); 1175 rw = bio_data_dir(bio); 1176 bio_for_each_segment(bvec, bio, iter) { 1177 unsigned int len = bvec.bv_len; 1178 1179 BUG_ON(len > PAGE_SIZE); 1180 /* Make sure len is in multiples of sector size. */ 1181 /* XXX is this right? */ 1182 BUG_ON(len < btt->sector_size); 1183 BUG_ON(len % btt->sector_size); 1184 1185 err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset, 1186 rw, iter.bi_sector); 1187 if (err) { 1188 dev_info(&btt->nd_btt->dev, 1189 "io error in %s sector %lld, len %d,\n", 1190 (rw == READ) ? "READ" : "WRITE", 1191 (unsigned long long) iter.bi_sector, len); 1192 bio->bi_error = err; 1193 break; 1194 } 1195 } 1196 if (do_acct) 1197 nd_iostat_end(bio, start); 1198 1199out: 1200 bio_endio(bio); 1201 return BLK_QC_T_NONE; 1202} 1203 1204static int btt_rw_page(struct block_device *bdev, sector_t sector, 1205 struct page *page, int rw) 1206{ 1207 struct btt *btt = bdev->bd_disk->private_data; 1208 1209 btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector); 1210 page_endio(page, rw & WRITE, 0); 1211 return 0; 1212} 1213 1214 1215static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo) 1216{ 1217 /* some standard values */ 1218 geo->heads = 1 << 6; 1219 geo->sectors = 1 << 5; 1220 geo->cylinders = get_capacity(bd->bd_disk) >> 11; 1221 return 0; 1222} 1223 1224static const struct block_device_operations btt_fops = { 1225 .owner = THIS_MODULE, 1226 .rw_page = btt_rw_page, 1227 .getgeo = btt_getgeo, 1228 .revalidate_disk = nvdimm_revalidate_disk, 1229}; 1230 1231static int btt_blk_init(struct btt *btt) 1232{ 1233 struct nd_btt *nd_btt = btt->nd_btt; 1234 struct nd_namespace_common *ndns = nd_btt->ndns; 1235 1236 /* create a new disk and request queue for btt */ 1237 btt->btt_queue = blk_alloc_queue(GFP_KERNEL); 1238 if (!btt->btt_queue) 1239 return -ENOMEM; 1240 1241 btt->btt_disk = alloc_disk(0); 1242 if (!btt->btt_disk) { 1243 blk_cleanup_queue(btt->btt_queue); 1244 return -ENOMEM; 1245 } 1246 1247 nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name); 1248 btt->btt_disk->driverfs_dev = &btt->nd_btt->dev; 1249 btt->btt_disk->major = btt_major; 1250 btt->btt_disk->first_minor = 0; 1251 btt->btt_disk->fops = &btt_fops; 1252 btt->btt_disk->private_data = btt; 1253 btt->btt_disk->queue = btt->btt_queue; 1254 btt->btt_disk->flags = GENHD_FL_EXT_DEVT; 1255 1256 blk_queue_make_request(btt->btt_queue, btt_make_request); 1257 blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); 1258 blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); 1259 blk_queue_bounce_limit(btt->btt_queue, BLK_BOUNCE_ANY); 1260 queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue); 1261 btt->btt_queue->queuedata = btt; 1262 1263 set_capacity(btt->btt_disk, 0); 1264 add_disk(btt->btt_disk); 1265 if (btt_meta_size(btt)) { 1266 int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt)); 1267 1268 if (rc) { 1269 del_gendisk(btt->btt_disk); 1270 put_disk(btt->btt_disk); 1271 blk_cleanup_queue(btt->btt_queue); 1272 return rc; 1273 } 1274 } 1275 set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); 1276 revalidate_disk(btt->btt_disk); 1277 1278 return 0; 1279} 1280 1281static void btt_blk_cleanup(struct btt *btt) 1282{ 1283 del_gendisk(btt->btt_disk); 1284 put_disk(btt->btt_disk); 1285 blk_cleanup_queue(btt->btt_queue); 1286} 1287 1288/** 1289 * btt_init - initialize a block translation table for the given device 1290 * @nd_btt: device with BTT geometry and backing device info 1291 * @rawsize: raw size in bytes of the backing device 1292 * @lbasize: lba size of the backing device 1293 * @uuid: A uuid for the backing device - this is stored on media 1294 * @maxlane: maximum number of parallel requests the device can handle 1295 * 1296 * Initialize a Block Translation Table on a backing device to provide 1297 * single sector power fail atomicity. 1298 * 1299 * Context: 1300 * Might sleep. 1301 * 1302 * Returns: 1303 * Pointer to a new struct btt on success, NULL on failure. 1304 */ 1305static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, 1306 u32 lbasize, u8 *uuid, struct nd_region *nd_region) 1307{ 1308 int ret; 1309 struct btt *btt; 1310 struct device *dev = &nd_btt->dev; 1311 1312 btt = kzalloc(sizeof(struct btt), GFP_KERNEL); 1313 if (!btt) 1314 return NULL; 1315 1316 btt->nd_btt = nd_btt; 1317 btt->rawsize = rawsize; 1318 btt->lbasize = lbasize; 1319 btt->sector_size = ((lbasize >= 4096) ? 4096 : 512); 1320 INIT_LIST_HEAD(&btt->arena_list); 1321 mutex_init(&btt->init_lock); 1322 btt->nd_region = nd_region; 1323 1324 ret = discover_arenas(btt); 1325 if (ret) { 1326 dev_err(dev, "init: error in arena_discover: %d\n", ret); 1327 goto out_free; 1328 } 1329 1330 if (btt->init_state != INIT_READY && nd_region->ro) { 1331 dev_info(dev, "%s is read-only, unable to init btt metadata\n", 1332 dev_name(&nd_region->dev)); 1333 goto out_free; 1334 } else if (btt->init_state != INIT_READY) { 1335 btt->num_arenas = (rawsize / ARENA_MAX_SIZE) + 1336 ((rawsize % ARENA_MAX_SIZE) ? 1 : 0); 1337 dev_dbg(dev, "init: %d arenas for %llu rawsize\n", 1338 btt->num_arenas, rawsize); 1339 1340 ret = create_arenas(btt); 1341 if (ret) { 1342 dev_info(dev, "init: create_arenas: %d\n", ret); 1343 goto out_free; 1344 } 1345 1346 ret = btt_meta_init(btt); 1347 if (ret) { 1348 dev_err(dev, "init: error in meta_init: %d\n", ret); 1349 goto out_free; 1350 } 1351 } 1352 1353 ret = btt_blk_init(btt); 1354 if (ret) { 1355 dev_err(dev, "init: error in blk_init: %d\n", ret); 1356 goto out_free; 1357 } 1358 1359 btt_debugfs_init(btt); 1360 1361 return btt; 1362 1363 out_free: 1364 kfree(btt); 1365 return NULL; 1366} 1367 1368/** 1369 * btt_fini - de-initialize a BTT 1370 * @btt: the BTT handle that was generated by btt_init 1371 * 1372 * De-initialize a Block Translation Table on device removal 1373 * 1374 * Context: 1375 * Might sleep. 1376 */ 1377static void btt_fini(struct btt *btt) 1378{ 1379 if (btt) { 1380 btt_blk_cleanup(btt); 1381 free_arenas(btt); 1382 debugfs_remove_recursive(btt->debugfs_dir); 1383 kfree(btt); 1384 } 1385} 1386 1387int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) 1388{ 1389 struct nd_btt *nd_btt = to_nd_btt(ndns->claim); 1390 struct nd_region *nd_region; 1391 struct btt *btt; 1392 size_t rawsize; 1393 1394 if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize) 1395 return -ENODEV; 1396 1397 rawsize = nvdimm_namespace_capacity(ndns) - SZ_4K; 1398 if (rawsize < ARENA_MIN_SIZE) { 1399 return -ENXIO; 1400 } 1401 nd_region = to_nd_region(nd_btt->dev.parent); 1402 btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid, 1403 nd_region); 1404 if (!btt) 1405 return -ENOMEM; 1406 nd_btt->btt = btt; 1407 1408 return 0; 1409} 1410EXPORT_SYMBOL(nvdimm_namespace_attach_btt); 1411 1412int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns) 1413{ 1414 struct nd_btt *nd_btt = to_nd_btt(ndns->claim); 1415 struct btt *btt = nd_btt->btt; 1416 1417 btt_fini(btt); 1418 nd_btt->btt = NULL; 1419 1420 return 0; 1421} 1422EXPORT_SYMBOL(nvdimm_namespace_detach_btt); 1423 1424static int __init nd_btt_init(void) 1425{ 1426 int rc; 1427 1428 btt_major = register_blkdev(0, "btt"); 1429 if (btt_major < 0) 1430 return btt_major; 1431 1432 debugfs_root = debugfs_create_dir("btt", NULL); 1433 if (IS_ERR_OR_NULL(debugfs_root)) { 1434 rc = -ENXIO; 1435 goto err_debugfs; 1436 } 1437 1438 return 0; 1439 1440 err_debugfs: 1441 unregister_blkdev(btt_major, "btt"); 1442 1443 return rc; 1444} 1445 1446static void __exit nd_btt_exit(void) 1447{ 1448 debugfs_remove_recursive(debugfs_root); 1449 unregister_blkdev(btt_major, "btt"); 1450} 1451 1452MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT); 1453MODULE_AUTHOR("Vishal Verma <vishal.l.verma@linux.intel.com>"); 1454MODULE_LICENSE("GPL v2"); 1455module_init(nd_btt_init); 1456module_exit(nd_btt_exit); 1457