1// SPDX-License-Identifier: GPL-2.0 2/* 3 * Copyright (C) 2016 CNEX Labs 4 * Initial release: Javier Gonzalez <javier@cnexlabs.com> 5 * Matias Bjorling <matias@cnexlabs.com> 6 * 7 * This program is free software; you can redistribute it and/or 8 * modify it under the terms of the GNU General Public License version 9 * 2 as published by the Free Software Foundation. 10 * 11 * This program is distributed in the hope that it will be useful, but 12 * WITHOUT ANY WARRANTY; without even the implied warranty of 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 * General Public License for more details. 15 * 16 * pblk-read.c - pblk's read path 17 */ 18 19#include "pblk.h" 20 21/* 22 * There is no guarantee that the value read from cache has not been updated and 23 * resides at another location in the cache. We guarantee though that if the 24 * value is read from the cache, it belongs to the mapped lba. In order to 25 * guarantee and order between writes and reads are ordered, a flush must be 26 * issued. 27 */ 28static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio, 29 sector_t lba, struct ppa_addr ppa) 30{ 31#ifdef CONFIG_NVM_PBLK_DEBUG 32 /* Callers must ensure that the ppa points to a cache address */ 33 BUG_ON(pblk_ppa_empty(ppa)); 34 BUG_ON(!pblk_addr_in_cache(ppa)); 35#endif 36 37 return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa); 38} 39 40static int pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd, 41 struct bio *bio, sector_t blba, 42 bool *from_cache) 43{ 44 void *meta_list = rqd->meta_list; 45 int nr_secs, i; 46 47retry: 48 nr_secs = pblk_lookup_l2p_seq(pblk, rqd->ppa_list, blba, rqd->nr_ppas, 49 from_cache); 50 51 if (!*from_cache) 52 goto end; 53 54 for (i = 0; i < nr_secs; i++) { 55 struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); 56 sector_t lba = blba + i; 57 58 if (pblk_ppa_empty(rqd->ppa_list[i])) { 59 __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); 60 61 meta->lba = addr_empty; 62 } else if (pblk_addr_in_cache(rqd->ppa_list[i])) { 63 /* 64 * Try to read from write buffer. The address is later 65 * checked on the write buffer to prevent retrieving 66 * overwritten data. 67 */ 68 if (!pblk_read_from_cache(pblk, bio, lba, 69 rqd->ppa_list[i])) { 70 if (i == 0) { 71 /* 72 * We didn't call with bio_advance() 73 * yet, so we can just retry. 74 */ 75 goto retry; 76 } else { 77 /* 78 * We already call bio_advance() 79 * so we cannot retry and we need 80 * to quit that function in order 81 * to allow caller to handle the bio 82 * splitting in the current sector 83 * position. 84 */ 85 nr_secs = i; 86 goto end; 87 } 88 } 89 meta->lba = cpu_to_le64(lba); 90#ifdef CONFIG_NVM_PBLK_DEBUG 91 atomic_long_inc(&pblk->cache_reads); 92#endif 93 } 94 bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); 95 } 96 97end: 98 if (pblk_io_aligned(pblk, nr_secs)) 99 rqd->is_seq = 1; 100 101#ifdef CONFIG_NVM_PBLK_DEBUG 102 atomic_long_add(nr_secs, &pblk->inflight_reads); 103#endif 104 105 return nr_secs; 106} 107 108 109static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd, 110 sector_t blba) 111{ 112 void *meta_list = rqd->meta_list; 113 int nr_lbas = rqd->nr_ppas; 114 int i; 115 116 if (!pblk_is_oob_meta_supported(pblk)) 117 return; 118 119 for (i = 0; i < nr_lbas; i++) { 120 struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); 121 u64 lba = le64_to_cpu(meta->lba); 122 123 if (lba == ADDR_EMPTY) 124 continue; 125 126 if (lba != blba + i) { 127#ifdef CONFIG_NVM_PBLK_DEBUG 128 struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); 129 130 print_ppa(pblk, &ppa_list[i], "seq", i); 131#endif 132 pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n", 133 lba, (u64)blba + i); 134 WARN_ON(1); 135 } 136 } 137} 138 139/* 140 * There can be holes in the lba list. 141 */ 142static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd, 143 u64 *lba_list, int nr_lbas) 144{ 145 void *meta_lba_list = rqd->meta_list; 146 int i, j; 147 148 if (!pblk_is_oob_meta_supported(pblk)) 149 return; 150 151 for (i = 0, j = 0; i < nr_lbas; i++) { 152 struct pblk_sec_meta *meta = pblk_get_meta(pblk, 153 meta_lba_list, j); 154 u64 lba = lba_list[i]; 155 u64 meta_lba; 156 157 if (lba == ADDR_EMPTY) 158 continue; 159 160 meta_lba = le64_to_cpu(meta->lba); 161 162 if (lba != meta_lba) { 163#ifdef CONFIG_NVM_PBLK_DEBUG 164 struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); 165 166 print_ppa(pblk, &ppa_list[j], "rnd", j); 167#endif 168 pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n", 169 meta_lba, lba); 170 WARN_ON(1); 171 } 172 173 j++; 174 } 175 176 WARN_ONCE(j != rqd->nr_ppas, "pblk: corrupted random request\n"); 177} 178 179static void pblk_end_user_read(struct bio *bio, int error) 180{ 181 if (error && error != NVM_RSP_WARN_HIGHECC) 182 bio_io_error(bio); 183 else 184 bio_endio(bio); 185} 186 187static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd, 188 bool put_line) 189{ 190 struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); 191 struct bio *int_bio = rqd->bio; 192 unsigned long start_time = r_ctx->start_time; 193 194 bio_end_io_acct(int_bio, start_time); 195 196 if (rqd->error) 197 pblk_log_read_err(pblk, rqd); 198 199 pblk_read_check_seq(pblk, rqd, r_ctx->lba); 200 bio_put(int_bio); 201 202 if (put_line) 203 pblk_rq_to_line_put(pblk, rqd); 204 205#ifdef CONFIG_NVM_PBLK_DEBUG 206 atomic_long_add(rqd->nr_ppas, &pblk->sync_reads); 207 atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads); 208#endif 209 210 pblk_free_rqd(pblk, rqd, PBLK_READ); 211 atomic_dec(&pblk->inflight_io); 212} 213 214static void pblk_end_io_read(struct nvm_rq *rqd) 215{ 216 struct pblk *pblk = rqd->private; 217 struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); 218 struct bio *bio = (struct bio *)r_ctx->private; 219 220 pblk_end_user_read(bio, rqd->error); 221 __pblk_end_io_read(pblk, rqd, true); 222} 223 224static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio, 225 sector_t lba, bool *from_cache) 226{ 227 struct pblk_sec_meta *meta = pblk_get_meta(pblk, rqd->meta_list, 0); 228 struct ppa_addr ppa; 229 230 pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); 231 232#ifdef CONFIG_NVM_PBLK_DEBUG 233 atomic_long_inc(&pblk->inflight_reads); 234#endif 235 236retry: 237 if (pblk_ppa_empty(ppa)) { 238 __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); 239 240 meta->lba = addr_empty; 241 return; 242 } 243 244 /* Try to read from write buffer. The address is later checked on the 245 * write buffer to prevent retrieving overwritten data. 246 */ 247 if (pblk_addr_in_cache(ppa)) { 248 if (!pblk_read_from_cache(pblk, bio, lba, ppa)) { 249 pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); 250 goto retry; 251 } 252 253 meta->lba = cpu_to_le64(lba); 254 255#ifdef CONFIG_NVM_PBLK_DEBUG 256 atomic_long_inc(&pblk->cache_reads); 257#endif 258 } else { 259 rqd->ppa_addr = ppa; 260 } 261} 262 263void pblk_submit_read(struct pblk *pblk, struct bio *bio) 264{ 265 sector_t blba = pblk_get_lba(bio); 266 unsigned int nr_secs = pblk_get_secs(bio); 267 bool from_cache; 268 struct pblk_g_ctx *r_ctx; 269 struct nvm_rq *rqd; 270 struct bio *int_bio, *split_bio; 271 unsigned long start_time; 272 273 start_time = bio_start_io_acct(bio); 274 275 rqd = pblk_alloc_rqd(pblk, PBLK_READ); 276 277 rqd->opcode = NVM_OP_PREAD; 278 rqd->nr_ppas = nr_secs; 279 rqd->private = pblk; 280 rqd->end_io = pblk_end_io_read; 281 282 r_ctx = nvm_rq_to_pdu(rqd); 283 r_ctx->start_time = start_time; 284 r_ctx->lba = blba; 285 286 if (pblk_alloc_rqd_meta(pblk, rqd)) { 287 bio_io_error(bio); 288 pblk_free_rqd(pblk, rqd, PBLK_READ); 289 return; 290 } 291 292 /* Clone read bio to deal internally with: 293 * -read errors when reading from drive 294 * -bio_advance() calls during cache reads 295 */ 296 int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); 297 298 if (nr_secs > 1) 299 nr_secs = pblk_read_ppalist_rq(pblk, rqd, int_bio, blba, 300 &from_cache); 301 else 302 pblk_read_rq(pblk, rqd, int_bio, blba, &from_cache); 303 304split_retry: 305 r_ctx->private = bio; /* original bio */ 306 rqd->bio = int_bio; /* internal bio */ 307 308 if (from_cache && nr_secs == rqd->nr_ppas) { 309 /* All data was read from cache, we can complete the IO. */ 310 pblk_end_user_read(bio, 0); 311 atomic_inc(&pblk->inflight_io); 312 __pblk_end_io_read(pblk, rqd, false); 313 } else if (nr_secs != rqd->nr_ppas) { 314 /* The read bio request could be partially filled by the write 315 * buffer, but there are some holes that need to be read from 316 * the drive. In order to handle this, we will use block layer 317 * mechanism to split this request in to smaller ones and make 318 * a chain of it. 319 */ 320 split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL, 321 &pblk_bio_set); 322 bio_chain(split_bio, bio); 323 submit_bio_noacct(bio); 324 325 /* New bio contains first N sectors of the previous one, so 326 * we can continue to use existing rqd, but we need to shrink 327 * the number of PPAs in it. New bio is also guaranteed that 328 * it contains only either data from cache or from drive, newer 329 * mix of them. 330 */ 331 bio = split_bio; 332 rqd->nr_ppas = nr_secs; 333 if (rqd->nr_ppas == 1) 334 rqd->ppa_addr = rqd->ppa_list[0]; 335 336 /* Recreate int_bio - existing might have some needed internal 337 * fields modified already. 338 */ 339 bio_put(int_bio); 340 int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); 341 goto split_retry; 342 } else if (pblk_submit_io(pblk, rqd, NULL)) { 343 /* Submitting IO to drive failed, let's report an error */ 344 rqd->error = -ENODEV; 345 pblk_end_io_read(rqd); 346 } 347} 348 349static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd, 350 struct pblk_line *line, u64 *lba_list, 351 u64 *paddr_list_gc, unsigned int nr_secs) 352{ 353 struct ppa_addr ppa_list_l2p[NVM_MAX_VLBA]; 354 struct ppa_addr ppa_gc; 355 int valid_secs = 0; 356 int i; 357 358 pblk_lookup_l2p_rand(pblk, ppa_list_l2p, lba_list, nr_secs); 359 360 for (i = 0; i < nr_secs; i++) { 361 if (lba_list[i] == ADDR_EMPTY) 362 continue; 363 364 ppa_gc = addr_to_gen_ppa(pblk, paddr_list_gc[i], line->id); 365 if (!pblk_ppa_comp(ppa_list_l2p[i], ppa_gc)) { 366 paddr_list_gc[i] = lba_list[i] = ADDR_EMPTY; 367 continue; 368 } 369 370 rqd->ppa_list[valid_secs++] = ppa_list_l2p[i]; 371 } 372 373#ifdef CONFIG_NVM_PBLK_DEBUG 374 atomic_long_add(valid_secs, &pblk->inflight_reads); 375#endif 376 377 return valid_secs; 378} 379 380static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd, 381 struct pblk_line *line, sector_t lba, 382 u64 paddr_gc) 383{ 384 struct ppa_addr ppa_l2p, ppa_gc; 385 int valid_secs = 0; 386 387 if (lba == ADDR_EMPTY) 388 goto out; 389 390 /* logic error: lba out-of-bounds */ 391 if (lba >= pblk->capacity) { 392 WARN(1, "pblk: read lba out of bounds\n"); 393 goto out; 394 } 395 396 spin_lock(&pblk->trans_lock); 397 ppa_l2p = pblk_trans_map_get(pblk, lba); 398 spin_unlock(&pblk->trans_lock); 399 400 ppa_gc = addr_to_gen_ppa(pblk, paddr_gc, line->id); 401 if (!pblk_ppa_comp(ppa_l2p, ppa_gc)) 402 goto out; 403 404 rqd->ppa_addr = ppa_l2p; 405 valid_secs = 1; 406 407#ifdef CONFIG_NVM_PBLK_DEBUG 408 atomic_long_inc(&pblk->inflight_reads); 409#endif 410 411out: 412 return valid_secs; 413} 414 415int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq) 416{ 417 struct nvm_rq rqd; 418 int ret = NVM_IO_OK; 419 420 memset(&rqd, 0, sizeof(struct nvm_rq)); 421 422 ret = pblk_alloc_rqd_meta(pblk, &rqd); 423 if (ret) 424 return ret; 425 426 if (gc_rq->nr_secs > 1) { 427 gc_rq->secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, gc_rq->line, 428 gc_rq->lba_list, 429 gc_rq->paddr_list, 430 gc_rq->nr_secs); 431 if (gc_rq->secs_to_gc == 1) 432 rqd.ppa_addr = rqd.ppa_list[0]; 433 } else { 434 gc_rq->secs_to_gc = read_rq_gc(pblk, &rqd, gc_rq->line, 435 gc_rq->lba_list[0], 436 gc_rq->paddr_list[0]); 437 } 438 439 if (!(gc_rq->secs_to_gc)) 440 goto out; 441 442 rqd.opcode = NVM_OP_PREAD; 443 rqd.nr_ppas = gc_rq->secs_to_gc; 444 445 if (pblk_submit_io_sync(pblk, &rqd, gc_rq->data)) { 446 ret = -EIO; 447 goto err_free_dma; 448 } 449 450 pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs); 451 452 atomic_dec(&pblk->inflight_io); 453 454 if (rqd.error) { 455 atomic_long_inc(&pblk->read_failed_gc); 456#ifdef CONFIG_NVM_PBLK_DEBUG 457 pblk_print_failed_rqd(pblk, &rqd, rqd.error); 458#endif 459 } 460 461#ifdef CONFIG_NVM_PBLK_DEBUG 462 atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads); 463 atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads); 464 atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads); 465#endif 466 467out: 468 pblk_free_rqd_meta(pblk, &rqd); 469 return ret; 470 471err_free_dma: 472 pblk_free_rqd_meta(pblk, &rqd); 473 return ret; 474} 475