1/* SPDX-License-Identifier: GPL-2.0 */ 2/* 3 * Copyright (C) 2015 IT University of Copenhagen (rrpc.h) 4 * Copyright (C) 2016 CNEX Labs 5 * Initial release: Matias Bjorling <matias@cnexlabs.com> 6 * Write buffering: Javier Gonzalez <javier@cnexlabs.com> 7 * 8 * This program is free software; you can redistribute it and/or 9 * modify it under the terms of the GNU General Public License version 10 * 2 as published by the Free Software Foundation. 11 * 12 * This program is distributed in the hope that it will be useful, but 13 * WITHOUT ANY WARRANTY; without even the implied warranty of 14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 15 * General Public License for more details. 16 * 17 * Implementation of a Physical Block-device target for Open-channel SSDs. 18 * 19 */ 20 21#ifndef PBLK_H_ 22#define PBLK_H_ 23 24#include <linux/blkdev.h> 25#include <linux/blk-mq.h> 26#include <linux/bio.h> 27#include <linux/module.h> 28#include <linux/kthread.h> 29#include <linux/vmalloc.h> 30#include <linux/crc32.h> 31#include <linux/uuid.h> 32 33#include <linux/lightnvm.h> 34 35/* Run only GC if less than 1/X blocks are free */ 36#define GC_LIMIT_INVERSE 5 37#define GC_TIME_MSECS 1000 38 39#define PBLK_SECTOR (512) 40#define PBLK_EXPOSED_PAGE_SIZE (4096) 41 42#define PBLK_NR_CLOSE_JOBS (4) 43 44#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16) 45 46/* Max 512 LUNs per device */ 47#define PBLK_MAX_LUNS_BITMAP (4) 48 49#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR) 50 51/* Static pool sizes */ 52#define PBLK_GEN_WS_POOL_SIZE (2) 53 54#define PBLK_DEFAULT_OP (11) 55 56enum { 57 PBLK_READ = READ, 58 PBLK_WRITE = WRITE,/* Write from write buffer */ 59 PBLK_WRITE_INT, /* Internal write - no write buffer */ 60 PBLK_READ_RECOV, /* Recovery read - errors allowed */ 61 PBLK_ERASE, 62}; 63 64enum { 65 /* IO Types */ 66 PBLK_IOTYPE_USER = 1 << 0, 67 PBLK_IOTYPE_GC = 1 << 1, 68 69 /* Write buffer flags */ 70 PBLK_FLUSH_ENTRY = 1 << 2, 71 PBLK_WRITTEN_DATA = 1 << 3, 72 PBLK_SUBMITTED_ENTRY = 1 << 4, 73 PBLK_WRITABLE_ENTRY = 1 << 5, 74}; 75 76enum { 77 PBLK_BLK_ST_OPEN = 0x1, 78 PBLK_BLK_ST_CLOSED = 0x2, 79}; 80 81enum { 82 PBLK_CHUNK_RESET_START, 83 PBLK_CHUNK_RESET_DONE, 84 PBLK_CHUNK_RESET_FAILED, 85}; 86 87struct pblk_sec_meta { 88 u64 reserved; 89 __le64 lba; 90}; 91 92/* The number of GC lists and the rate-limiter states go together. This way the 93 * rate-limiter can dictate how much GC is needed based on resource utilization. 94 */ 95#define PBLK_GC_NR_LISTS 4 96 97enum { 98 PBLK_RL_OFF = 0, 99 PBLK_RL_WERR = 1, 100 PBLK_RL_HIGH = 2, 101 PBLK_RL_MID = 3, 102 PBLK_RL_LOW = 4 103}; 104 105#define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA) 106 107/* write buffer completion context */ 108struct pblk_c_ctx { 109 struct list_head list; /* Head for out-of-order completion */ 110 111 unsigned long *lun_bitmap; /* Luns used on current request */ 112 unsigned int sentry; 113 unsigned int nr_valid; 114 unsigned int nr_padded; 115}; 116 117/* read context */ 118struct pblk_g_ctx { 119 void *private; 120 unsigned long start_time; 121 u64 lba; 122}; 123 124/* Pad context */ 125struct pblk_pad_rq { 126 struct pblk *pblk; 127 struct completion wait; 128 struct kref ref; 129}; 130 131/* Recovery context */ 132struct pblk_rec_ctx { 133 struct pblk *pblk; 134 struct nvm_rq *rqd; 135 struct work_struct ws_rec; 136}; 137 138/* Write context */ 139struct pblk_w_ctx { 140 struct bio_list bios; /* Original bios - used for completion 141 * in REQ_FUA, REQ_FLUSH case 142 */ 143 u64 lba; /* Logic addr. associated with entry */ 144 struct ppa_addr ppa; /* Physic addr. associated with entry */ 145 int flags; /* Write context flags */ 146}; 147 148struct pblk_rb_entry { 149 struct ppa_addr cacheline; /* Cacheline for this entry */ 150 void *data; /* Pointer to data on this entry */ 151 struct pblk_w_ctx w_ctx; /* Context for this entry */ 152 struct list_head index; /* List head to enable indexes */ 153}; 154 155#define EMPTY_ENTRY (~0U) 156 157struct pblk_rb_pages { 158 struct page *pages; 159 int order; 160 struct list_head list; 161}; 162 163struct pblk_rb { 164 struct pblk_rb_entry *entries; /* Ring buffer entries */ 165 unsigned int mem; /* Write offset - points to next 166 * writable entry in memory 167 */ 168 unsigned int subm; /* Read offset - points to last entry 169 * that has been submitted to the media 170 * to be persisted 171 */ 172 unsigned int sync; /* Synced - backpointer that signals 173 * the last submitted entry that has 174 * been successfully persisted to media 175 */ 176 unsigned int flush_point; /* Sync point - last entry that must be 177 * flushed to the media. Used with 178 * REQ_FLUSH and REQ_FUA 179 */ 180 unsigned int l2p_update; /* l2p update point - next entry for 181 * which l2p mapping will be updated to 182 * contain a device ppa address (instead 183 * of a cacheline 184 */ 185 unsigned int nr_entries; /* Number of entries in write buffer - 186 * must be a power of two 187 */ 188 unsigned int seg_size; /* Size of the data segments being 189 * stored on each entry. Typically this 190 * will be 4KB 191 */ 192 193 unsigned int back_thres; /* Threshold that shall be maintained by 194 * the backpointer in order to respect 195 * geo->mw_cunits on a per chunk basis 196 */ 197 198 struct list_head pages; /* List of data pages */ 199 200 spinlock_t w_lock; /* Write lock */ 201 spinlock_t s_lock; /* Sync lock */ 202 203#ifdef CONFIG_NVM_PBLK_DEBUG 204 atomic_t inflight_flush_point; /* Not served REQ_FLUSH | REQ_FUA */ 205#endif 206}; 207 208#define PBLK_RECOVERY_SECTORS 16 209 210struct pblk_lun { 211 struct ppa_addr bppa; 212 struct semaphore wr_sem; 213}; 214 215struct pblk_gc_rq { 216 struct pblk_line *line; 217 void *data; 218 u64 paddr_list[NVM_MAX_VLBA]; 219 u64 lba_list[NVM_MAX_VLBA]; 220 int nr_secs; 221 int secs_to_gc; 222 struct list_head list; 223}; 224 225struct pblk_gc { 226 /* These states are not protected by a lock since (i) they are in the 227 * fast path, and (ii) they are not critical. 228 */ 229 int gc_active; 230 int gc_enabled; 231 int gc_forced; 232 233 struct task_struct *gc_ts; 234 struct task_struct *gc_writer_ts; 235 struct task_struct *gc_reader_ts; 236 237 struct workqueue_struct *gc_line_reader_wq; 238 struct workqueue_struct *gc_reader_wq; 239 240 struct timer_list gc_timer; 241 242 struct semaphore gc_sem; 243 atomic_t read_inflight_gc; /* Number of lines with inflight GC reads */ 244 atomic_t pipeline_gc; /* Number of lines in the GC pipeline - 245 * started reads to finished writes 246 */ 247 int w_entries; 248 249 struct list_head w_list; 250 struct list_head r_list; 251 252 spinlock_t lock; 253 spinlock_t w_lock; 254 spinlock_t r_lock; 255}; 256 257struct pblk_rl { 258 unsigned int high; /* Upper threshold for rate limiter (free run - 259 * user I/O rate limiter 260 */ 261 unsigned int high_pw; /* High rounded up as a power of 2 */ 262 263#define PBLK_USER_HIGH_THRS 8 /* Begin write limit at 12% available blks */ 264#define PBLK_USER_LOW_THRS 10 /* Aggressive GC at 10% available blocks */ 265 266 int rb_windows_pw; /* Number of rate windows in the write buffer 267 * given as a power-of-2. This guarantees that 268 * when user I/O is being rate limited, there 269 * will be reserved enough space for the GC to 270 * place its payload. A window is of 271 * pblk->max_write_pgs size, which in NVMe is 272 * 64, i.e., 256kb. 273 */ 274 int rb_budget; /* Total number of entries available for I/O */ 275 int rb_user_max; /* Max buffer entries available for user I/O */ 276 int rb_gc_max; /* Max buffer entries available for GC I/O */ 277 int rb_gc_rsv; /* Reserved buffer entries for GC I/O */ 278 int rb_state; /* Rate-limiter current state */ 279 int rb_max_io; /* Maximum size for an I/O giving the config */ 280 281 atomic_t rb_user_cnt; /* User I/O buffer counter */ 282 atomic_t rb_gc_cnt; /* GC I/O buffer counter */ 283 atomic_t rb_space; /* Space limit in case of reaching capacity */ 284 285 int rsv_blocks; /* Reserved blocks for GC */ 286 287 int rb_user_active; 288 int rb_gc_active; 289 290 atomic_t werr_lines; /* Number of write error lines that needs gc */ 291 292 struct timer_list u_timer; 293 294 unsigned long total_blocks; 295 296 atomic_t free_blocks; /* Total number of free blocks (+ OP) */ 297 atomic_t free_user_blocks; /* Number of user free blocks (no OP) */ 298}; 299 300#define PBLK_LINE_EMPTY (~0U) 301 302enum { 303 /* Line Types */ 304 PBLK_LINETYPE_FREE = 0, 305 PBLK_LINETYPE_LOG = 1, 306 PBLK_LINETYPE_DATA = 2, 307 308 /* Line state */ 309 PBLK_LINESTATE_NEW = 9, 310 PBLK_LINESTATE_FREE = 10, 311 PBLK_LINESTATE_OPEN = 11, 312 PBLK_LINESTATE_CLOSED = 12, 313 PBLK_LINESTATE_GC = 13, 314 PBLK_LINESTATE_BAD = 14, 315 PBLK_LINESTATE_CORRUPT = 15, 316 317 /* GC group */ 318 PBLK_LINEGC_NONE = 20, 319 PBLK_LINEGC_EMPTY = 21, 320 PBLK_LINEGC_LOW = 22, 321 PBLK_LINEGC_MID = 23, 322 PBLK_LINEGC_HIGH = 24, 323 PBLK_LINEGC_FULL = 25, 324 PBLK_LINEGC_WERR = 26 325}; 326 327#define PBLK_MAGIC 0x70626c6b /*pblk*/ 328 329/* emeta/smeta persistent storage format versions: 330 * Changes in major version requires offline migration. 331 * Changes in minor version are handled automatically during 332 * recovery. 333 */ 334 335#define SMETA_VERSION_MAJOR (0) 336#define SMETA_VERSION_MINOR (1) 337 338#define EMETA_VERSION_MAJOR (0) 339#define EMETA_VERSION_MINOR (2) 340 341struct line_header { 342 __le32 crc; 343 __le32 identifier; /* pblk identifier */ 344 __u8 uuid[16]; /* instance uuid */ 345 __le16 type; /* line type */ 346 __u8 version_major; /* version major */ 347 __u8 version_minor; /* version minor */ 348 __le32 id; /* line id for current line */ 349}; 350 351struct line_smeta { 352 struct line_header header; 353 354 __le32 crc; /* Full structure including struct crc */ 355 /* Previous line metadata */ 356 __le32 prev_id; /* Line id for previous line */ 357 358 /* Current line metadata */ 359 __le64 seq_nr; /* Sequence number for current line */ 360 361 /* Active writers */ 362 __le32 window_wr_lun; /* Number of parallel LUNs to write */ 363 364 __le32 rsvd[2]; 365 366 __le64 lun_bitmap[]; 367}; 368 369 370/* 371 * Metadata layout in media: 372 * First sector: 373 * 1. struct line_emeta 374 * 2. bad block bitmap (u64 * window_wr_lun) 375 * 3. write amplification counters 376 * Mid sectors (start at lbas_sector): 377 * 3. nr_lbas (u64) forming lba list 378 * Last sectors (start at vsc_sector): 379 * 4. u32 valid sector count (vsc) for all lines (~0U: free line) 380 */ 381struct line_emeta { 382 struct line_header header; 383 384 __le32 crc; /* Full structure including struct crc */ 385 386 /* Previous line metadata */ 387 __le32 prev_id; /* Line id for prev line */ 388 389 /* Current line metadata */ 390 __le64 seq_nr; /* Sequence number for current line */ 391 392 /* Active writers */ 393 __le32 window_wr_lun; /* Number of parallel LUNs to write */ 394 395 /* Bookkeeping for recovery */ 396 __le32 next_id; /* Line id for next line */ 397 __le64 nr_lbas; /* Number of lbas mapped in line */ 398 __le64 nr_valid_lbas; /* Number of valid lbas mapped in line */ 399 __le64 bb_bitmap[]; /* Updated bad block bitmap for line */ 400}; 401 402 403/* Write amplification counters stored on media */ 404struct wa_counters { 405 __le64 user; /* Number of user written sectors */ 406 __le64 gc; /* Number of sectors written by GC*/ 407 __le64 pad; /* Number of padded sectors */ 408}; 409 410struct pblk_emeta { 411 struct line_emeta *buf; /* emeta buffer in media format */ 412 int mem; /* Write offset - points to next 413 * writable entry in memory 414 */ 415 atomic_t sync; /* Synced - backpointer that signals the 416 * last entry that has been successfully 417 * persisted to media 418 */ 419 unsigned int nr_entries; /* Number of emeta entries */ 420}; 421 422struct pblk_smeta { 423 struct line_smeta *buf; /* smeta buffer in persistent format */ 424}; 425 426struct pblk_w_err_gc { 427 int has_write_err; 428 int has_gc_err; 429 __le64 *lba_list; 430}; 431 432struct pblk_line { 433 struct pblk *pblk; 434 unsigned int id; /* Line number corresponds to the 435 * block line 436 */ 437 unsigned int seq_nr; /* Unique line sequence number */ 438 439 int state; /* PBLK_LINESTATE_X */ 440 int type; /* PBLK_LINETYPE_X */ 441 int gc_group; /* PBLK_LINEGC_X */ 442 struct list_head list; /* Free, GC lists */ 443 444 unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */ 445 446 struct nvm_chk_meta *chks; /* Chunks forming line */ 447 448 struct pblk_smeta *smeta; /* Start metadata */ 449 struct pblk_emeta *emeta; /* End medatada */ 450 451 int meta_line; /* Metadata line id */ 452 int meta_distance; /* Distance between data and metadata */ 453 454 u64 emeta_ssec; /* Sector where emeta starts */ 455 456 unsigned int sec_in_line; /* Number of usable secs in line */ 457 458 atomic_t blk_in_line; /* Number of good blocks in line */ 459 unsigned long *blk_bitmap; /* Bitmap for valid/invalid blocks */ 460 unsigned long *erase_bitmap; /* Bitmap for erased blocks */ 461 462 unsigned long *map_bitmap; /* Bitmap for mapped sectors in line */ 463 unsigned long *invalid_bitmap; /* Bitmap for invalid sectors in line */ 464 465 atomic_t left_eblks; /* Blocks left for erasing */ 466 atomic_t left_seblks; /* Blocks left for sync erasing */ 467 468 int left_msecs; /* Sectors left for mapping */ 469 unsigned int cur_sec; /* Sector map pointer */ 470 unsigned int nr_valid_lbas; /* Number of valid lbas in line */ 471 472 __le32 *vsc; /* Valid sector count in line */ 473 474 struct kref ref; /* Write buffer L2P references */ 475 atomic_t sec_to_update; /* Outstanding L2P updates to ppa */ 476 477 struct pblk_w_err_gc *w_err_gc; /* Write error gc recovery metadata */ 478 479 spinlock_t lock; /* Necessary for invalid_bitmap only */ 480}; 481 482#define PBLK_DATA_LINES 4 483 484enum { 485 PBLK_EMETA_TYPE_HEADER = 1, /* struct line_emeta first sector */ 486 PBLK_EMETA_TYPE_LLBA = 2, /* lba list - type: __le64 */ 487 PBLK_EMETA_TYPE_VSC = 3, /* vsc list - type: __le32 */ 488}; 489 490struct pblk_line_mgmt { 491 int nr_lines; /* Total number of full lines */ 492 int nr_free_lines; /* Number of full lines in free list */ 493 494 /* Free lists - use free_lock */ 495 struct list_head free_list; /* Full lines ready to use */ 496 struct list_head corrupt_list; /* Full lines corrupted */ 497 struct list_head bad_list; /* Full lines bad */ 498 499 /* GC lists - use gc_lock */ 500 struct list_head *gc_lists[PBLK_GC_NR_LISTS]; 501 struct list_head gc_high_list; /* Full lines ready to GC, high isc */ 502 struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */ 503 struct list_head gc_low_list; /* Full lines ready to GC, low isc */ 504 505 struct list_head gc_werr_list; /* Write err recovery list */ 506 507 struct list_head gc_full_list; /* Full lines ready to GC, no valid */ 508 struct list_head gc_empty_list; /* Full lines close, all valid */ 509 510 struct pblk_line *log_line; /* Current FTL log line */ 511 struct pblk_line *data_line; /* Current data line */ 512 struct pblk_line *log_next; /* Next FTL log line */ 513 struct pblk_line *data_next; /* Next data line */ 514 515 struct list_head emeta_list; /* Lines queued to schedule emeta */ 516 517 __le32 *vsc_list; /* Valid sector counts for all lines */ 518 519 /* Pre-allocated metadata for data lines */ 520 struct pblk_smeta *sline_meta[PBLK_DATA_LINES]; 521 struct pblk_emeta *eline_meta[PBLK_DATA_LINES]; 522 unsigned long meta_bitmap; 523 524 /* Cache and mempool for map/invalid bitmaps */ 525 struct kmem_cache *bitmap_cache; 526 mempool_t *bitmap_pool; 527 528 /* Helpers for fast bitmap calculations */ 529 unsigned long *bb_template; 530 unsigned long *bb_aux; 531 532 unsigned long d_seq_nr; /* Data line unique sequence number */ 533 unsigned long l_seq_nr; /* Log line unique sequence number */ 534 535 spinlock_t free_lock; 536 spinlock_t close_lock; 537 spinlock_t gc_lock; 538}; 539 540struct pblk_line_meta { 541 unsigned int smeta_len; /* Total length for smeta */ 542 unsigned int smeta_sec; /* Sectors needed for smeta */ 543 544 unsigned int emeta_len[4]; /* Lengths for emeta: 545 * [0]: Total 546 * [1]: struct line_emeta + 547 * bb_bitmap + struct wa_counters 548 * [2]: L2P portion 549 * [3]: vsc 550 */ 551 unsigned int emeta_sec[4]; /* Sectors needed for emeta. Same layout 552 * as emeta_len 553 */ 554 555 unsigned int emeta_bb; /* Boundary for bb that affects emeta */ 556 557 unsigned int vsc_list_len; /* Length for vsc list */ 558 unsigned int sec_bitmap_len; /* Length for sector bitmap in line */ 559 unsigned int blk_bitmap_len; /* Length for block bitmap in line */ 560 unsigned int lun_bitmap_len; /* Length for lun bitmap in line */ 561 562 unsigned int blk_per_line; /* Number of blocks in a full line */ 563 unsigned int sec_per_line; /* Number of sectors in a line */ 564 unsigned int dsec_per_line; /* Number of data sectors in a line */ 565 unsigned int min_blk_line; /* Min. number of good blocks in line */ 566 567 unsigned int mid_thrs; /* Threshold for GC mid list */ 568 unsigned int high_thrs; /* Threshold for GC high list */ 569 570 unsigned int meta_distance; /* Distance between data and metadata */ 571}; 572 573enum { 574 PBLK_STATE_RUNNING = 0, 575 PBLK_STATE_STOPPING = 1, 576 PBLK_STATE_RECOVERING = 2, 577 PBLK_STATE_STOPPED = 3, 578}; 579 580/* Internal format to support not power-of-2 device formats */ 581struct pblk_addrf { 582 /* gen to dev */ 583 int sec_stripe; 584 int ch_stripe; 585 int lun_stripe; 586 587 /* dev to gen */ 588 int sec_lun_stripe; 589 int sec_ws_stripe; 590}; 591 592struct pblk { 593 struct nvm_tgt_dev *dev; 594 struct gendisk *disk; 595 596 struct kobject kobj; 597 598 struct pblk_lun *luns; 599 600 struct pblk_line *lines; /* Line array */ 601 struct pblk_line_mgmt l_mg; /* Line management */ 602 struct pblk_line_meta lm; /* Line metadata */ 603 604 struct nvm_addrf addrf; /* Aligned address format */ 605 struct pblk_addrf uaddrf; /* Unaligned address format */ 606 int addrf_len; 607 608 struct pblk_rb rwb; 609 610 int state; /* pblk line state */ 611 612 int min_write_pgs; /* Minimum amount of pages required by controller */ 613 int min_write_pgs_data; /* Minimum amount of payload pages */ 614 int max_write_pgs; /* Maximum amount of pages supported by controller */ 615 int oob_meta_size; /* Size of OOB sector metadata */ 616 617 sector_t capacity; /* Device capacity when bad blocks are subtracted */ 618 619 int op; /* Percentage of device used for over-provisioning */ 620 int op_blks; /* Number of blocks used for over-provisioning */ 621 622 /* pblk provisioning values. Used by rate limiter */ 623 struct pblk_rl rl; 624 625 int sec_per_write; 626 627 guid_t instance_uuid; 628 629 /* Persistent write amplification counters, 4kb sector I/Os */ 630 atomic64_t user_wa; /* Sectors written by user */ 631 atomic64_t gc_wa; /* Sectors written by GC */ 632 atomic64_t pad_wa; /* Padded sectors written */ 633 634 /* Reset values for delta write amplification measurements */ 635 u64 user_rst_wa; 636 u64 gc_rst_wa; 637 u64 pad_rst_wa; 638 639 /* Counters used for calculating padding distribution */ 640 atomic64_t *pad_dist; /* Padding distribution buckets */ 641 u64 nr_flush_rst; /* Flushes reset value for pad dist.*/ 642 atomic64_t nr_flush; /* Number of flush/fua I/O */ 643 644#ifdef CONFIG_NVM_PBLK_DEBUG 645 /* Non-persistent debug counters, 4kb sector I/Os */ 646 atomic_long_t inflight_writes; /* Inflight writes (user and gc) */ 647 atomic_long_t padded_writes; /* Sectors padded due to flush/fua */ 648 atomic_long_t padded_wb; /* Sectors padded in write buffer */ 649 atomic_long_t req_writes; /* Sectors stored on write buffer */ 650 atomic_long_t sub_writes; /* Sectors submitted from buffer */ 651 atomic_long_t sync_writes; /* Sectors synced to media */ 652 atomic_long_t inflight_reads; /* Inflight sector read requests */ 653 atomic_long_t cache_reads; /* Read requests that hit the cache */ 654 atomic_long_t sync_reads; /* Completed sector read requests */ 655 atomic_long_t recov_writes; /* Sectors submitted from recovery */ 656 atomic_long_t recov_gc_writes; /* Sectors submitted from write GC */ 657 atomic_long_t recov_gc_reads; /* Sectors submitted from read GC */ 658#endif 659 660 spinlock_t lock; 661 662 atomic_long_t read_failed; 663 atomic_long_t read_empty; 664 atomic_long_t read_high_ecc; 665 atomic_long_t read_failed_gc; 666 atomic_long_t write_failed; 667 atomic_long_t erase_failed; 668 669 atomic_t inflight_io; /* General inflight I/O counter */ 670 671 struct task_struct *writer_ts; 672 673 /* Simple translation map of logical addresses to physical addresses. 674 * The logical addresses is known by the host system, while the physical 675 * addresses are used when writing to the disk block device. 676 */ 677 unsigned char *trans_map; 678 spinlock_t trans_lock; 679 680 struct list_head compl_list; 681 682 spinlock_t resubmit_lock; /* Resubmit list lock */ 683 struct list_head resubmit_list; /* Resubmit list for failed writes*/ 684 685 mempool_t page_bio_pool; 686 mempool_t gen_ws_pool; 687 mempool_t rec_pool; 688 mempool_t r_rq_pool; 689 mempool_t w_rq_pool; 690 mempool_t e_rq_pool; 691 692 struct workqueue_struct *close_wq; 693 struct workqueue_struct *bb_wq; 694 struct workqueue_struct *r_end_wq; 695 696 struct timer_list wtimer; 697 698 struct pblk_gc gc; 699}; 700 701struct pblk_line_ws { 702 struct pblk *pblk; 703 struct pblk_line *line; 704 void *priv; 705 struct work_struct ws; 706}; 707 708#define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx)) 709#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx)) 710 711#define pblk_err(pblk, fmt, ...) \ 712 pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) 713#define pblk_info(pblk, fmt, ...) \ 714 pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) 715#define pblk_warn(pblk, fmt, ...) \ 716 pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) 717#define pblk_debug(pblk, fmt, ...) \ 718 pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) 719 720/* 721 * pblk ring buffer operations 722 */ 723int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, 724 unsigned int seg_sz); 725int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio, 726 unsigned int nr_entries, unsigned int *pos); 727int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries, 728 unsigned int *pos); 729void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data, 730 struct pblk_w_ctx w_ctx, unsigned int pos); 731void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data, 732 struct pblk_w_ctx w_ctx, struct pblk_line *line, 733 u64 paddr, unsigned int pos); 734struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos); 735void pblk_rb_flush(struct pblk_rb *rb); 736 737void pblk_rb_sync_l2p(struct pblk_rb *rb); 738unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, 739 unsigned int pos, unsigned int nr_entries, 740 unsigned int count); 741int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, 742 struct ppa_addr ppa); 743unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries); 744 745unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags); 746unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries); 747unsigned int pblk_rb_ptr_wrap(struct pblk_rb *rb, unsigned int p, 748 unsigned int nr_entries); 749void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags); 750unsigned int pblk_rb_flush_point_count(struct pblk_rb *rb); 751 752unsigned int pblk_rb_read_count(struct pblk_rb *rb); 753unsigned int pblk_rb_sync_count(struct pblk_rb *rb); 754unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos); 755 756int pblk_rb_tear_down_check(struct pblk_rb *rb); 757int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos); 758void pblk_rb_free(struct pblk_rb *rb); 759ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf); 760 761/* 762 * pblk core 763 */ 764struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type); 765void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type); 766int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd); 767void pblk_free_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd); 768void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write); 769int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd, 770 struct pblk_c_ctx *c_ctx); 771void pblk_discard(struct pblk *pblk, struct bio *bio); 772struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk); 773struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk, 774 struct nvm_chk_meta *lp, 775 struct ppa_addr ppa); 776void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd); 777void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd); 778int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf); 779int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf); 780int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line); 781void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd); 782struct pblk_line *pblk_line_get(struct pblk *pblk); 783struct pblk_line *pblk_line_get_first_data(struct pblk *pblk); 784struct pblk_line *pblk_line_replace_data(struct pblk *pblk); 785void pblk_ppa_to_line_put(struct pblk *pblk, struct ppa_addr ppa); 786void pblk_rq_to_line_put(struct pblk *pblk, struct nvm_rq *rqd); 787int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line); 788void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line); 789struct pblk_line *pblk_line_get_data(struct pblk *pblk); 790struct pblk_line *pblk_line_get_erase(struct pblk *pblk); 791int pblk_line_erase(struct pblk *pblk, struct pblk_line *line); 792int pblk_line_is_full(struct pblk_line *line); 793void pblk_line_free(struct pblk_line *line); 794void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line); 795void pblk_line_close(struct pblk *pblk, struct pblk_line *line); 796void pblk_line_close_ws(struct work_struct *work); 797void pblk_pipeline_stop(struct pblk *pblk); 798void __pblk_pipeline_stop(struct pblk *pblk); 799void __pblk_pipeline_flush(struct pblk *pblk); 800void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, 801 void (*work)(struct work_struct *), gfp_t gfp_mask, 802 struct workqueue_struct *wq); 803u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line); 804int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line); 805int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line, 806 void *emeta_buf); 807int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa); 808void pblk_line_put(struct kref *ref); 809void pblk_line_put_wq(struct kref *ref); 810struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line); 811u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line); 812void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); 813u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); 814u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); 815int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, 816 unsigned long secs_to_flush, bool skip_meta); 817void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa, 818 unsigned long *lun_bitmap); 819void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa); 820void pblk_up_chunk(struct pblk *pblk, struct ppa_addr ppa); 821void pblk_up_rq(struct pblk *pblk, unsigned long *lun_bitmap); 822int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags, 823 int nr_pages); 824void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off, 825 int nr_pages); 826void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa); 827void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, 828 u64 paddr); 829void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa); 830void pblk_update_map_cache(struct pblk *pblk, sector_t lba, 831 struct ppa_addr ppa); 832void pblk_update_map_dev(struct pblk *pblk, sector_t lba, 833 struct ppa_addr ppa, struct ppa_addr entry_line); 834int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa, 835 struct pblk_line *gc_line, u64 paddr); 836void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas, 837 u64 *lba_list, int nr_secs); 838int pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas, 839 sector_t blba, int nr_secs, bool *from_cache); 840void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd); 841void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd); 842 843/* 844 * pblk user I/O write path 845 */ 846void pblk_write_to_cache(struct pblk *pblk, struct bio *bio, 847 unsigned long flags); 848int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq); 849 850/* 851 * pblk map 852 */ 853int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd, 854 unsigned int sentry, unsigned long *lun_bitmap, 855 unsigned int valid_secs, struct ppa_addr *erase_ppa); 856int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry, 857 unsigned long *lun_bitmap, unsigned int valid_secs, 858 unsigned int off); 859 860/* 861 * pblk write thread 862 */ 863int pblk_write_ts(void *data); 864void pblk_write_timer_fn(struct timer_list *t); 865void pblk_write_should_kick(struct pblk *pblk); 866void pblk_write_kick(struct pblk *pblk); 867 868/* 869 * pblk read path 870 */ 871extern struct bio_set pblk_bio_set; 872void pblk_submit_read(struct pblk *pblk, struct bio *bio); 873int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq); 874/* 875 * pblk recovery 876 */ 877struct pblk_line *pblk_recov_l2p(struct pblk *pblk); 878int pblk_recov_pad(struct pblk *pblk); 879int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta); 880 881/* 882 * pblk gc 883 */ 884#define PBLK_GC_MAX_READERS 8 /* Max number of outstanding GC reader jobs */ 885#define PBLK_GC_RQ_QD 128 /* Queue depth for inflight GC requests */ 886#define PBLK_GC_L_QD 4 /* Queue depth for inflight GC lines */ 887 888int pblk_gc_init(struct pblk *pblk); 889void pblk_gc_exit(struct pblk *pblk, bool graceful); 890void pblk_gc_should_start(struct pblk *pblk); 891void pblk_gc_should_stop(struct pblk *pblk); 892void pblk_gc_should_kick(struct pblk *pblk); 893void pblk_gc_free_full_lines(struct pblk *pblk); 894void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled, 895 int *gc_active); 896int pblk_gc_sysfs_force(struct pblk *pblk, int force); 897void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line); 898 899/* 900 * pblk rate limiter 901 */ 902void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold); 903void pblk_rl_free(struct pblk_rl *rl); 904void pblk_rl_update_rates(struct pblk_rl *rl); 905int pblk_rl_high_thrs(struct pblk_rl *rl); 906unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl); 907unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl); 908int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries); 909void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries); 910void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries); 911int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries); 912void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries); 913void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc); 914int pblk_rl_max_io(struct pblk_rl *rl); 915void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line); 916void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line, 917 bool used); 918int pblk_rl_is_limit(struct pblk_rl *rl); 919 920void pblk_rl_werr_line_in(struct pblk_rl *rl); 921void pblk_rl_werr_line_out(struct pblk_rl *rl); 922 923/* 924 * pblk sysfs 925 */ 926int pblk_sysfs_init(struct gendisk *tdisk); 927void pblk_sysfs_exit(struct gendisk *tdisk); 928 929static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx) 930{ 931 return c_ctx - sizeof(struct nvm_rq); 932} 933 934static inline void *emeta_to_bb(struct line_emeta *emeta) 935{ 936 return emeta->bb_bitmap; 937} 938 939static inline void *emeta_to_wa(struct pblk_line_meta *lm, 940 struct line_emeta *emeta) 941{ 942 return emeta->bb_bitmap + lm->blk_bitmap_len; 943} 944 945static inline void *emeta_to_lbas(struct pblk *pblk, struct line_emeta *emeta) 946{ 947 return ((void *)emeta + pblk->lm.emeta_len[1]); 948} 949 950static inline void *emeta_to_vsc(struct pblk *pblk, struct line_emeta *emeta) 951{ 952 return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]); 953} 954 955static inline int pblk_line_vsc(struct pblk_line *line) 956{ 957 return le32_to_cpu(*line->vsc); 958} 959 960static inline int pblk_ppa_to_line_id(struct ppa_addr p) 961{ 962 return p.a.blk; 963} 964 965static inline struct pblk_line *pblk_ppa_to_line(struct pblk *pblk, 966 struct ppa_addr p) 967{ 968 return &pblk->lines[pblk_ppa_to_line_id(p)]; 969} 970 971static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p) 972{ 973 return p.a.lun * geo->num_ch + p.a.ch; 974} 975 976static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr, 977 u64 line_id) 978{ 979 struct nvm_tgt_dev *dev = pblk->dev; 980 struct nvm_geo *geo = &dev->geo; 981 struct ppa_addr ppa; 982 983 if (geo->version == NVM_OCSSD_SPEC_12) { 984 struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf; 985 986 ppa.ppa = 0; 987 ppa.g.blk = line_id; 988 ppa.g.pg = (paddr & ppaf->pg_mask) >> ppaf->pg_offset; 989 ppa.g.lun = (paddr & ppaf->lun_mask) >> ppaf->lun_offset; 990 ppa.g.ch = (paddr & ppaf->ch_mask) >> ppaf->ch_offset; 991 ppa.g.pl = (paddr & ppaf->pln_mask) >> ppaf->pln_offset; 992 ppa.g.sec = (paddr & ppaf->sec_mask) >> ppaf->sec_offset; 993 } else { 994 struct pblk_addrf *uaddrf = &pblk->uaddrf; 995 int secs, chnls, luns; 996 997 ppa.ppa = 0; 998 999 ppa.m.chk = line_id; 1000 1001 paddr = div_u64_rem(paddr, uaddrf->sec_stripe, &secs); 1002 ppa.m.sec = secs; 1003 1004 paddr = div_u64_rem(paddr, uaddrf->ch_stripe, &chnls); 1005 ppa.m.grp = chnls; 1006 1007 paddr = div_u64_rem(paddr, uaddrf->lun_stripe, &luns); 1008 ppa.m.pu = luns; 1009 1010 ppa.m.sec += uaddrf->sec_stripe * paddr; 1011 } 1012 1013 return ppa; 1014} 1015 1016static inline struct nvm_chk_meta *pblk_dev_ppa_to_chunk(struct pblk *pblk, 1017 struct ppa_addr p) 1018{ 1019 struct nvm_tgt_dev *dev = pblk->dev; 1020 struct nvm_geo *geo = &dev->geo; 1021 struct pblk_line *line = pblk_ppa_to_line(pblk, p); 1022 int pos = pblk_ppa_to_pos(geo, p); 1023 1024 return &line->chks[pos]; 1025} 1026 1027static inline u64 pblk_dev_ppa_to_chunk_addr(struct pblk *pblk, 1028 struct ppa_addr p) 1029{ 1030 struct nvm_tgt_dev *dev = pblk->dev; 1031 1032 return dev_to_chunk_addr(dev->parent, &pblk->addrf, p); 1033} 1034 1035static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk, 1036 struct ppa_addr p) 1037{ 1038 struct nvm_tgt_dev *dev = pblk->dev; 1039 struct nvm_geo *geo = &dev->geo; 1040 u64 paddr; 1041 1042 if (geo->version == NVM_OCSSD_SPEC_12) { 1043 struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf; 1044 1045 paddr = (u64)p.g.ch << ppaf->ch_offset; 1046 paddr |= (u64)p.g.lun << ppaf->lun_offset; 1047 paddr |= (u64)p.g.pg << ppaf->pg_offset; 1048 paddr |= (u64)p.g.pl << ppaf->pln_offset; 1049 paddr |= (u64)p.g.sec << ppaf->sec_offset; 1050 } else { 1051 struct pblk_addrf *uaddrf = &pblk->uaddrf; 1052 u64 secs = p.m.sec; 1053 int sec_stripe; 1054 1055 paddr = (u64)p.m.grp * uaddrf->sec_stripe; 1056 paddr += (u64)p.m.pu * uaddrf->sec_lun_stripe; 1057 1058 secs = div_u64_rem(secs, uaddrf->sec_stripe, &sec_stripe); 1059 paddr += secs * uaddrf->sec_ws_stripe; 1060 paddr += sec_stripe; 1061 } 1062 1063 return paddr; 1064} 1065 1066static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32) 1067{ 1068 struct nvm_tgt_dev *dev = pblk->dev; 1069 1070 return nvm_ppa32_to_ppa64(dev->parent, &pblk->addrf, ppa32); 1071} 1072 1073static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64) 1074{ 1075 struct nvm_tgt_dev *dev = pblk->dev; 1076 1077 return nvm_ppa64_to_ppa32(dev->parent, &pblk->addrf, ppa64); 1078} 1079 1080static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk, 1081 sector_t lba) 1082{ 1083 struct ppa_addr ppa; 1084 1085 if (pblk->addrf_len < 32) { 1086 u32 *map = (u32 *)pblk->trans_map; 1087 1088 ppa = pblk_ppa32_to_ppa64(pblk, map[lba]); 1089 } else { 1090 struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map; 1091 1092 ppa = map[lba]; 1093 } 1094 1095 return ppa; 1096} 1097 1098static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba, 1099 struct ppa_addr ppa) 1100{ 1101 if (pblk->addrf_len < 32) { 1102 u32 *map = (u32 *)pblk->trans_map; 1103 1104 map[lba] = pblk_ppa64_to_ppa32(pblk, ppa); 1105 } else { 1106 u64 *map = (u64 *)pblk->trans_map; 1107 1108 map[lba] = ppa.ppa; 1109 } 1110} 1111 1112static inline int pblk_ppa_empty(struct ppa_addr ppa_addr) 1113{ 1114 return (ppa_addr.ppa == ADDR_EMPTY); 1115} 1116 1117static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr) 1118{ 1119 ppa_addr->ppa = ADDR_EMPTY; 1120} 1121 1122static inline bool pblk_ppa_comp(struct ppa_addr lppa, struct ppa_addr rppa) 1123{ 1124 return (lppa.ppa == rppa.ppa); 1125} 1126 1127static inline int pblk_addr_in_cache(struct ppa_addr ppa) 1128{ 1129 return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached); 1130} 1131 1132static inline int pblk_addr_to_cacheline(struct ppa_addr ppa) 1133{ 1134 return ppa.c.line; 1135} 1136 1137static inline struct ppa_addr pblk_cacheline_to_addr(int addr) 1138{ 1139 struct ppa_addr p; 1140 1141 p.c.line = addr; 1142 p.c.is_cached = 1; 1143 1144 return p; 1145} 1146 1147static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk, 1148 struct line_header *header) 1149{ 1150 u32 crc = ~(u32)0; 1151 1152 crc = crc32_le(crc, (unsigned char *)header + sizeof(crc), 1153 sizeof(struct line_header) - sizeof(crc)); 1154 1155 return crc; 1156} 1157 1158static inline u32 pblk_calc_smeta_crc(struct pblk *pblk, 1159 struct line_smeta *smeta) 1160{ 1161 struct pblk_line_meta *lm = &pblk->lm; 1162 u32 crc = ~(u32)0; 1163 1164 crc = crc32_le(crc, (unsigned char *)smeta + 1165 sizeof(struct line_header) + sizeof(crc), 1166 lm->smeta_len - 1167 sizeof(struct line_header) - sizeof(crc)); 1168 1169 return crc; 1170} 1171 1172static inline u32 pblk_calc_emeta_crc(struct pblk *pblk, 1173 struct line_emeta *emeta) 1174{ 1175 struct pblk_line_meta *lm = &pblk->lm; 1176 u32 crc = ~(u32)0; 1177 1178 crc = crc32_le(crc, (unsigned char *)emeta + 1179 sizeof(struct line_header) + sizeof(crc), 1180 lm->emeta_len[0] - 1181 sizeof(struct line_header) - sizeof(crc)); 1182 1183 return crc; 1184} 1185 1186static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs) 1187{ 1188 return !(nr_secs % pblk->min_write_pgs); 1189} 1190 1191#ifdef CONFIG_NVM_PBLK_DEBUG 1192static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p, 1193 char *msg, int error) 1194{ 1195 struct nvm_geo *geo = &pblk->dev->geo; 1196 1197 if (p->c.is_cached) { 1198 pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n", 1199 msg, error, (u64)p->c.line); 1200 } else if (geo->version == NVM_OCSSD_SPEC_12) { 1201 pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n", 1202 msg, error, 1203 p->g.ch, p->g.lun, p->g.blk, 1204 p->g.pg, p->g.pl, p->g.sec); 1205 } else { 1206 pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n", 1207 msg, error, 1208 p->m.grp, p->m.pu, p->m.chk, p->m.sec); 1209 } 1210} 1211 1212static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd, 1213 int error) 1214{ 1215 int bit = -1; 1216 1217 if (rqd->nr_ppas == 1) { 1218 print_ppa(pblk, &rqd->ppa_addr, "rqd", error); 1219 return; 1220 } 1221 1222 while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas, 1223 bit + 1)) < rqd->nr_ppas) { 1224 print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error); 1225 } 1226 1227 pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status); 1228} 1229 1230static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev, 1231 struct ppa_addr *ppas, int nr_ppas) 1232{ 1233 struct nvm_geo *geo = &tgt_dev->geo; 1234 struct ppa_addr *ppa; 1235 int i; 1236 1237 for (i = 0; i < nr_ppas; i++) { 1238 ppa = &ppas[i]; 1239 1240 if (geo->version == NVM_OCSSD_SPEC_12) { 1241 if (!ppa->c.is_cached && 1242 ppa->g.ch < geo->num_ch && 1243 ppa->g.lun < geo->num_lun && 1244 ppa->g.pl < geo->num_pln && 1245 ppa->g.blk < geo->num_chk && 1246 ppa->g.pg < geo->num_pg && 1247 ppa->g.sec < geo->ws_min) 1248 continue; 1249 } else { 1250 if (!ppa->c.is_cached && 1251 ppa->m.grp < geo->num_ch && 1252 ppa->m.pu < geo->num_lun && 1253 ppa->m.chk < geo->num_chk && 1254 ppa->m.sec < geo->clba) 1255 continue; 1256 } 1257 1258 print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i); 1259 1260 return 1; 1261 } 1262 return 0; 1263} 1264 1265static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd) 1266{ 1267 struct nvm_tgt_dev *dev = pblk->dev; 1268 struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); 1269 1270 if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) { 1271 WARN_ON(1); 1272 return -EINVAL; 1273 } 1274 1275 if (rqd->opcode == NVM_OP_PWRITE) { 1276 struct pblk_line *line; 1277 int i; 1278 1279 for (i = 0; i < rqd->nr_ppas; i++) { 1280 line = pblk_ppa_to_line(pblk, ppa_list[i]); 1281 1282 spin_lock(&line->lock); 1283 if (line->state != PBLK_LINESTATE_OPEN) { 1284 pblk_err(pblk, "bad ppa: line:%d,state:%d\n", 1285 line->id, line->state); 1286 WARN_ON(1); 1287 spin_unlock(&line->lock); 1288 return -EINVAL; 1289 } 1290 spin_unlock(&line->lock); 1291 } 1292 } 1293 1294 return 0; 1295} 1296#endif 1297 1298static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr) 1299{ 1300 struct pblk_line_meta *lm = &pblk->lm; 1301 1302 if (paddr > lm->sec_per_line) 1303 return 1; 1304 1305 return 0; 1306} 1307 1308static inline unsigned int pblk_get_bi_idx(struct bio *bio) 1309{ 1310 return bio->bi_iter.bi_idx; 1311} 1312 1313static inline sector_t pblk_get_lba(struct bio *bio) 1314{ 1315 return bio->bi_iter.bi_sector / NR_PHY_IN_LOG; 1316} 1317 1318static inline unsigned int pblk_get_secs(struct bio *bio) 1319{ 1320 return bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE; 1321} 1322 1323static inline char *pblk_disk_name(struct pblk *pblk) 1324{ 1325 struct gendisk *disk = pblk->disk; 1326 1327 return disk->disk_name; 1328} 1329 1330static inline unsigned int pblk_get_min_chks(struct pblk *pblk) 1331{ 1332 struct pblk_line_meta *lm = &pblk->lm; 1333 /* In a worst-case scenario every line will have OP invalid sectors. 1334 * We will then need a minimum of 1/OP lines to free up a single line 1335 */ 1336 1337 return DIV_ROUND_UP(100, pblk->op) * lm->blk_per_line; 1338} 1339 1340static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk, 1341 void *meta, int index) 1342{ 1343 return meta + 1344 max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size) 1345 * index; 1346} 1347 1348static inline int pblk_dma_meta_size(struct pblk *pblk) 1349{ 1350 return max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size) 1351 * NVM_MAX_VLBA; 1352} 1353 1354static inline int pblk_is_oob_meta_supported(struct pblk *pblk) 1355{ 1356 return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta); 1357} 1358#endif /* PBLK_H_ */ 1359