1// SPDX-License-Identifier: GPL-2.0 2/* 3 * Copyright (c) 2000-2005 Silicon Graphics, Inc. 4 * All Rights Reserved. 5 */ 6#ifndef __XFS_BUF_H__ 7#define __XFS_BUF_H__ 8 9#include <linux/list.h> 10#include <linux/types.h> 11#include <linux/spinlock.h> 12#include <linux/mm.h> 13#include <linux/fs.h> 14#include <linux/dax.h> 15#include <linux/uio.h> 16#include <linux/list_lru.h> 17 18extern struct kmem_cache *xfs_buf_cache; 19 20/* 21 * Base types 22 */ 23struct xfs_buf; 24 25#define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) 26 27#define XBF_READ (1u << 0) /* buffer intended for reading from device */ 28#define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ 29#define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ 30#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ 31#define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ 32#define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ 33#define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ 34#define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ 35 36/* buffer type flags for write callbacks */ 37#define _XBF_INODES (1u << 16)/* inode buffer */ 38#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ 39#define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ 40 41/* flags used only internally */ 42#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ 43#define _XBF_KMEM (1u << 21)/* backed by heap memory */ 44#define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ 45 46/* flags used only as arguments to access routines */ 47/* 48 * Online fsck is scanning the buffer cache for live buffers. Do not warn 49 * about length mismatches during lookups and do not return stale buffers. 50 */ 51#define XBF_LIVESCAN (1u << 28) 52#define XBF_INCORE (1u << 29)/* lookup only, return if found in cache */ 53#define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ 54#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ 55 56 57typedef unsigned int xfs_buf_flags_t; 58 59#define XFS_BUF_FLAGS \ 60 { XBF_READ, "READ" }, \ 61 { XBF_WRITE, "WRITE" }, \ 62 { XBF_READ_AHEAD, "READ_AHEAD" }, \ 63 { XBF_NO_IOACCT, "NO_IOACCT" }, \ 64 { XBF_ASYNC, "ASYNC" }, \ 65 { XBF_DONE, "DONE" }, \ 66 { XBF_STALE, "STALE" }, \ 67 { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ 68 { _XBF_INODES, "INODES" }, \ 69 { _XBF_DQUOTS, "DQUOTS" }, \ 70 { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ 71 { _XBF_PAGES, "PAGES" }, \ 72 { _XBF_KMEM, "KMEM" }, \ 73 { _XBF_DELWRI_Q, "DELWRI_Q" }, \ 74 /* The following interface flags should never be set */ \ 75 { XBF_LIVESCAN, "LIVESCAN" }, \ 76 { XBF_INCORE, "INCORE" }, \ 77 { XBF_TRYLOCK, "TRYLOCK" }, \ 78 { XBF_UNMAPPED, "UNMAPPED" } 79 80/* 81 * Internal state flags. 82 */ 83#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ 84#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */ 85 86/* 87 * The xfs_buftarg contains 2 notions of "sector size" - 88 * 89 * 1) The metadata sector size, which is the minimum unit and 90 * alignment of IO which will be performed by metadata operations. 91 * 2) The device logical sector size 92 * 93 * The first is specified at mkfs time, and is stored on-disk in the 94 * superblock's sb_sectsize. 95 * 96 * The latter is derived from the underlying device, and controls direct IO 97 * alignment constraints. 98 */ 99typedef struct xfs_buftarg { 100 dev_t bt_dev; 101 struct block_device *bt_bdev; 102 struct dax_device *bt_daxdev; 103 u64 bt_dax_part_off; 104 struct xfs_mount *bt_mount; 105 unsigned int bt_meta_sectorsize; 106 size_t bt_meta_sectormask; 107 size_t bt_logical_sectorsize; 108 size_t bt_logical_sectormask; 109 110 /* LRU control structures */ 111 struct shrinker bt_shrinker; 112 struct list_lru bt_lru; 113 114 struct percpu_counter bt_io_count; 115 struct ratelimit_state bt_ioerror_rl; 116} xfs_buftarg_t; 117 118#define XB_PAGES 2 119 120struct xfs_buf_map { 121 xfs_daddr_t bm_bn; /* block number for I/O */ 122 int bm_len; /* size of I/O */ 123 unsigned int bm_flags; 124}; 125 126/* 127 * Online fsck is scanning the buffer cache for live buffers. Do not warn 128 * about length mismatches during lookups and do not return stale buffers. 129 */ 130#define XBM_LIVESCAN (1U << 0) 131 132#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \ 133 struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) }; 134 135struct xfs_buf_ops { 136 char *name; 137 union { 138 __be32 magic[2]; /* v4 and v5 on disk magic values */ 139 __be16 magic16[2]; /* v4 and v5 on disk magic values */ 140 }; 141 void (*verify_read)(struct xfs_buf *); 142 void (*verify_write)(struct xfs_buf *); 143 xfs_failaddr_t (*verify_struct)(struct xfs_buf *bp); 144}; 145 146struct xfs_buf { 147 /* 148 * first cacheline holds all the fields needed for an uncontended cache 149 * hit to be fully processed. The semaphore straddles the cacheline 150 * boundary, but the counter and lock sits on the first cacheline, 151 * which is the only bit that is touched if we hit the semaphore 152 * fast-path on locking. 153 */ 154 struct rhash_head b_rhash_head; /* pag buffer hash node */ 155 156 xfs_daddr_t b_rhash_key; /* buffer cache index */ 157 int b_length; /* size of buffer in BBs */ 158 atomic_t b_hold; /* reference count */ 159 atomic_t b_lru_ref; /* lru reclaim ref count */ 160 xfs_buf_flags_t b_flags; /* status flags */ 161 struct semaphore b_sema; /* semaphore for lockables */ 162 163 /* 164 * concurrent access to b_lru and b_lru_flags are protected by 165 * bt_lru_lock and not by b_sema 166 */ 167 struct list_head b_lru; /* lru list */ 168 spinlock_t b_lock; /* internal state lock */ 169 unsigned int b_state; /* internal state flags */ 170 int b_io_error; /* internal IO error state */ 171 wait_queue_head_t b_waiters; /* unpin waiters */ 172 struct list_head b_list; 173 struct xfs_perag *b_pag; /* contains rbtree root */ 174 struct xfs_mount *b_mount; 175 struct xfs_buftarg *b_target; /* buffer target (device) */ 176 void *b_addr; /* virtual address of buffer */ 177 struct work_struct b_ioend_work; 178 struct completion b_iowait; /* queue for I/O waiters */ 179 struct xfs_buf_log_item *b_log_item; 180 struct list_head b_li_list; /* Log items list head */ 181 struct xfs_trans *b_transp; 182 struct page **b_pages; /* array of page pointers */ 183 struct page *b_page_array[XB_PAGES]; /* inline pages */ 184 struct xfs_buf_map *b_maps; /* compound buffer map */ 185 struct xfs_buf_map __b_map; /* inline compound buffer map */ 186 int b_map_count; 187 atomic_t b_pin_count; /* pin count */ 188 atomic_t b_io_remaining; /* #outstanding I/O requests */ 189 unsigned int b_page_count; /* size of page array */ 190 unsigned int b_offset; /* page offset of b_addr, 191 only for _XBF_KMEM buffers */ 192 int b_error; /* error code on I/O */ 193 194 /* 195 * async write failure retry count. Initialised to zero on the first 196 * failure, then when it exceeds the maximum configured without a 197 * success the write is considered to be failed permanently and the 198 * iodone handler will take appropriate action. 199 * 200 * For retry timeouts, we record the jiffie of the first failure. This 201 * means that we can change the retry timeout for buffers already under 202 * I/O and thus avoid getting stuck in a retry loop with a long timeout. 203 * 204 * last_error is used to ensure that we are getting repeated errors, not 205 * different errors. e.g. a block device might change ENOSPC to EIO when 206 * a failure timeout occurs, so we want to re-initialise the error 207 * retry behaviour appropriately when that happens. 208 */ 209 int b_retries; 210 unsigned long b_first_retry_time; /* in jiffies */ 211 int b_last_error; 212 213 const struct xfs_buf_ops *b_ops; 214 struct rcu_head b_rcu; 215}; 216 217/* Finding and Reading Buffers */ 218int xfs_buf_get_map(struct xfs_buftarg *target, struct xfs_buf_map *map, 219 int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp); 220int xfs_buf_read_map(struct xfs_buftarg *target, struct xfs_buf_map *map, 221 int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp, 222 const struct xfs_buf_ops *ops, xfs_failaddr_t fa); 223void xfs_buf_readahead_map(struct xfs_buftarg *target, 224 struct xfs_buf_map *map, int nmaps, 225 const struct xfs_buf_ops *ops); 226 227static inline int 228xfs_buf_incore( 229 struct xfs_buftarg *target, 230 xfs_daddr_t blkno, 231 size_t numblks, 232 xfs_buf_flags_t flags, 233 struct xfs_buf **bpp) 234{ 235 DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); 236 237 return xfs_buf_get_map(target, &map, 1, XBF_INCORE | flags, bpp); 238} 239 240static inline int 241xfs_buf_get( 242 struct xfs_buftarg *target, 243 xfs_daddr_t blkno, 244 size_t numblks, 245 struct xfs_buf **bpp) 246{ 247 DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); 248 249 return xfs_buf_get_map(target, &map, 1, 0, bpp); 250} 251 252static inline int 253xfs_buf_read( 254 struct xfs_buftarg *target, 255 xfs_daddr_t blkno, 256 size_t numblks, 257 xfs_buf_flags_t flags, 258 struct xfs_buf **bpp, 259 const struct xfs_buf_ops *ops) 260{ 261 DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); 262 263 return xfs_buf_read_map(target, &map, 1, flags, bpp, ops, 264 __builtin_return_address(0)); 265} 266 267static inline void 268xfs_buf_readahead( 269 struct xfs_buftarg *target, 270 xfs_daddr_t blkno, 271 size_t numblks, 272 const struct xfs_buf_ops *ops) 273{ 274 DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); 275 return xfs_buf_readahead_map(target, &map, 1, ops); 276} 277 278int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, 279 xfs_buf_flags_t flags, struct xfs_buf **bpp); 280int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, 281 size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, 282 const struct xfs_buf_ops *ops); 283int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); 284void xfs_buf_hold(struct xfs_buf *bp); 285 286/* Releasing Buffers */ 287extern void xfs_buf_rele(struct xfs_buf *); 288 289/* Locking and Unlocking Buffers */ 290extern int xfs_buf_trylock(struct xfs_buf *); 291extern void xfs_buf_lock(struct xfs_buf *); 292extern void xfs_buf_unlock(struct xfs_buf *); 293#define xfs_buf_islocked(bp) \ 294 ((bp)->b_sema.count <= 0) 295 296static inline void xfs_buf_relse(struct xfs_buf *bp) 297{ 298 xfs_buf_unlock(bp); 299 xfs_buf_rele(bp); 300} 301 302/* Buffer Read and Write Routines */ 303extern int xfs_bwrite(struct xfs_buf *bp); 304 305extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error, 306 xfs_failaddr_t failaddr); 307#define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address) 308extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa); 309void xfs_buf_ioend_fail(struct xfs_buf *); 310void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize); 311void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa); 312#define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address) 313 314/* Buffer Utility Routines */ 315extern void *xfs_buf_offset(struct xfs_buf *, size_t); 316extern void xfs_buf_stale(struct xfs_buf *bp); 317 318/* Delayed Write Buffer Routines */ 319extern void xfs_buf_delwri_cancel(struct list_head *); 320extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); 321extern int xfs_buf_delwri_submit(struct list_head *); 322extern int xfs_buf_delwri_submit_nowait(struct list_head *); 323extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); 324 325static inline xfs_daddr_t xfs_buf_daddr(struct xfs_buf *bp) 326{ 327 return bp->b_maps[0].bm_bn; 328} 329 330void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref); 331 332/* 333 * If the buffer is already on the LRU, do nothing. Otherwise set the buffer 334 * up with a reference count of 0 so it will be tossed from the cache when 335 * released. 336 */ 337static inline void xfs_buf_oneshot(struct xfs_buf *bp) 338{ 339 if (!list_empty(&bp->b_lru) || atomic_read(&bp->b_lru_ref) > 1) 340 return; 341 atomic_set(&bp->b_lru_ref, 0); 342} 343 344static inline int xfs_buf_ispinned(struct xfs_buf *bp) 345{ 346 return atomic_read(&bp->b_pin_count); 347} 348 349static inline int 350xfs_buf_verify_cksum(struct xfs_buf *bp, unsigned long cksum_offset) 351{ 352 return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), 353 cksum_offset); 354} 355 356static inline void 357xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) 358{ 359 xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), 360 cksum_offset); 361} 362 363/* 364 * Handling of buftargs. 365 */ 366struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp, 367 struct block_device *bdev); 368extern void xfs_free_buftarg(struct xfs_buftarg *); 369extern void xfs_buftarg_wait(struct xfs_buftarg *); 370extern void xfs_buftarg_drain(struct xfs_buftarg *); 371extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int); 372 373#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) 374#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) 375 376int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops); 377bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic); 378bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic); 379 380#endif /* __XFS_BUF_H__ */ 381