summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_buf.h
blob: d79a1fe5d738df70f8b08c453fdcc74c9549e779 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#ifndef __XFS_BUF_H__
#define __XFS_BUF_H__

#include <linux/list.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/dax.h>
#include <linux/uio.h>
#include <linux/list_lru.h>

/*
 *	Base types
 */

#define XFS_BUF_DADDR_NULL	((xfs_daddr_t) (-1LL))

#define XBF_READ	 (1 << 0) /* buffer intended for reading from device */
#define XBF_WRITE	 (1 << 1) /* buffer intended for writing to device */
#define XBF_READ_AHEAD	 (1 << 2) /* asynchronous read-ahead */
#define XBF_NO_IOACCT	 (1 << 3) /* bypass I/O accounting (non-LRU bufs) */
#define XBF_ASYNC	 (1 << 4) /* initiator will not wait for completion */
#define XBF_DONE	 (1 << 5) /* all pages in the buffer uptodate */
#define XBF_STALE	 (1 << 6) /* buffer has been staled, do not find it */
#define XBF_WRITE_FAIL	 (1 << 7) /* async writes have failed on this buffer */

/* flags used only as arguments to access routines */
#define XBF_TRYLOCK	 (1 << 16)/* lock requested, but do not wait */
#define XBF_UNMAPPED	 (1 << 17)/* do not map the buffer */

/* flags used only internally */
#define _XBF_PAGES	 (1 << 20)/* backed by refcounted pages */
#define _XBF_KMEM	 (1 << 21)/* backed by heap memory */
#define _XBF_DELWRI_Q	 (1 << 22)/* buffer on a delwri queue */

typedef unsigned int xfs_buf_flags_t;

#define XFS_BUF_FLAGS \
	{ XBF_READ,		"READ" }, \
	{ XBF_WRITE,		"WRITE" }, \
	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
	{ XBF_NO_IOACCT,	"NO_IOACCT" }, \
	{ XBF_ASYNC,		"ASYNC" }, \
	{ XBF_DONE,		"DONE" }, \
	{ XBF_STALE,		"STALE" }, \
	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
	{ XBF_TRYLOCK,		"TRYLOCK" },	/* should never be set */\
	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
	{ _XBF_PAGES,		"PAGES" }, \
	{ _XBF_KMEM,		"KMEM" }, \
	{ _XBF_DELWRI_Q,	"DELWRI_Q" }


/*
 * Internal state flags.
 */
#define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
#define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */

/*
 * The xfs_buftarg contains 2 notions of "sector size" -
 *
 * 1) The metadata sector size, which is the minimum unit and
 *    alignment of IO which will be performed by metadata operations.
 * 2) The device logical sector size
 *
 * The first is specified at mkfs time, and is stored on-disk in the
 * superblock's sb_sectsize.
 *
 * The latter is derived from the underlying device, and controls direct IO
 * alignment constraints.
 */
typedef struct xfs_buftarg {
	dev_t			bt_dev;
	struct block_device	*bt_bdev;
	struct dax_device	*bt_daxdev;
	struct xfs_mount	*bt_mount;
	unsigned int		bt_meta_sectorsize;
	size_t			bt_meta_sectormask;
	size_t			bt_logical_sectorsize;
	size_t			bt_logical_sectormask;

	/* LRU control structures */
	struct shrinker		bt_shrinker;
	struct list_lru		bt_lru;

	struct percpu_counter	bt_io_count;
} xfs_buftarg_t;

struct xfs_buf;
typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);


#define XB_PAGES	2

struct xfs_buf_map {
	xfs_daddr_t		bm_bn;	/* block number for I/O */
	int			bm_len;	/* size of I/O */
};

#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \
	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };

struct xfs_buf_ops {
	char *name;
	union {
		__be32 magic[2];	/* v4 and v5 on disk magic values */
		__be16 magic16[2];	/* v4 and v5 on disk magic values */
	};
	void (*verify_read)(struct xfs_buf *);
	void (*verify_write)(struct xfs_buf *);
	xfs_failaddr_t (*verify_struct)(struct xfs_buf *bp);
};

typedef struct xfs_buf {
	/*
	 * first cacheline holds all the fields needed for an uncontended cache
	 * hit to be fully processed. The semaphore straddles the cacheline
	 * boundary, but the counter and lock sits on the first cacheline,
	 * which is the only bit that is touched if we hit the semaphore
	 * fast-path on locking.
	 */
	struct rhash_head	b_rhash_head;	/* pag buffer hash node */
	xfs_daddr_t		b_bn;		/* block number of buffer */
	int			b_length;	/* size of buffer in BBs */
	atomic_t		b_hold;		/* reference count */
	atomic_t		b_lru_ref;	/* lru reclaim ref count */
	xfs_buf_flags_t		b_flags;	/* status flags */
	struct semaphore	b_sema;		/* semaphore for lockables */

	/*
	 * concurrent access to b_lru and b_lru_flags are protected by
	 * bt_lru_lock and not by b_sema
	 */
	struct list_head	b_lru;		/* lru list */
	spinlock_t		b_lock;		/* internal state lock */
	unsigned int		b_state;	/* internal state flags */
	int			b_io_error;	/* internal IO error state */
	wait_queue_head_t	b_waiters;	/* unpin waiters */
	struct list_head	b_list;
	struct xfs_perag	*b_pag;		/* contains rbtree root */
	struct xfs_mount	*b_mount;
	xfs_buftarg_t		*b_target;	/* buffer target (device) */
	void			*b_addr;	/* virtual address of buffer */
	struct work_struct	b_ioend_work;
	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
	struct completion	b_iowait;	/* queue for I/O waiters */
	struct xfs_buf_log_item	*b_log_item;
	struct list_head	b_li_list;	/* Log items list head */
	struct xfs_trans	*b_transp;
	struct page		**b_pages;	/* array of page pointers */
	struct page		*b_page_array[XB_PAGES]; /* inline pages */
	struct xfs_buf_map	*b_maps;	/* compound buffer map */
	struct xfs_buf_map	__b_map;	/* inline compound buffer map */
	int			b_map_count;
	atomic_t		b_pin_count;	/* pin count */
	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
	unsigned int		b_page_count;	/* size of page array */
	unsigned int		b_offset;	/* page offset in first page */
	int			b_error;	/* error code on I/O */

	/*
	 * async write failure retry count. Initialised to zero on the first
	 * failure, then when it exceeds the maximum configured without a
	 * success the write is considered to be failed permanently and the
	 * iodone handler will take appropriate action.
	 *
	 * For retry timeouts, we record the jiffie of the first failure. This
	 * means that we can change the retry timeout for buffers already under
	 * I/O and thus avoid getting stuck in a retry loop with a long timeout.
	 *
	 * last_error is used to ensure that we are getting repeated errors, not
	 * different errors. e.g. a block device might change ENOSPC to EIO when
	 * a failure timeout occurs, so we want to re-initialise the error
	 * retry behaviour appropriately when that happens.
	 */
	int			b_retries;
	unsigned long		b_first_retry_time; /* in jiffies */
	int			b_last_error;

	const struct xfs_buf_ops	*b_ops;
} xfs_buf_t;

/* Finding and Reading Buffers */
struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target,
			   xfs_daddr_t blkno, size_t numblks,
			   xfs_buf_flags_t flags);

int xfs_buf_get_map(struct xfs_buftarg *target, struct xfs_buf_map *map,
		int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp);
int xfs_buf_read_map(struct xfs_buftarg *target, struct xfs_buf_map *map,
		int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp,
		const struct xfs_buf_ops *ops, xfs_failaddr_t fa);
void xfs_buf_readahead_map(struct xfs_buftarg *target,
			       struct xfs_buf_map *map, int nmaps,
			       const struct xfs_buf_ops *ops);

static inline int
xfs_buf_get(
	struct xfs_buftarg	*target,
	xfs_daddr_t		blkno,
	size_t			numblks,
	struct xfs_buf		**bpp)
{
	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);

	return xfs_buf_get_map(target, &map, 1, 0, bpp);
}

static inline int
xfs_buf_read(
	struct xfs_buftarg	*target,
	xfs_daddr_t		blkno,
	size_t			numblks,
	xfs_buf_flags_t		flags,
	struct xfs_buf		**bpp,
	const struct xfs_buf_ops *ops)
{
	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);

	return xfs_buf_read_map(target, &map, 1, flags, bpp, ops,
			__builtin_return_address(0));
}

static inline void
xfs_buf_readahead(
	struct xfs_buftarg	*target,
	xfs_daddr_t		blkno,
	size_t			numblks,
	const struct xfs_buf_ops *ops)
{
	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
	return xfs_buf_readahead_map(target, &map, 1, ops);
}

int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags,
		struct xfs_buf **bpp);
int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
			  size_t numblks, int flags, struct xfs_buf **bpp,
			  const struct xfs_buf_ops *ops);
void xfs_buf_hold(struct xfs_buf *bp);

/* Releasing Buffers */
extern void xfs_buf_rele(xfs_buf_t *);

/* Locking and Unlocking Buffers */
extern int xfs_buf_trylock(xfs_buf_t *);
extern void xfs_buf_lock(xfs_buf_t *);
extern void xfs_buf_unlock(xfs_buf_t *);
#define xfs_buf_islocked(bp) \
	((bp)->b_sema.count <= 0)

/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
extern void xfs_buf_ioend(struct xfs_buf *bp);
extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
		xfs_failaddr_t failaddr);
#define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa);

extern int __xfs_buf_submit(struct xfs_buf *bp, bool);
static inline int xfs_buf_submit(struct xfs_buf *bp)
{
	bool wait = bp->b_flags & XBF_ASYNC ? false : true;
	return __xfs_buf_submit(bp, wait);
}

void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize);

/* Buffer Utility Routines */
extern void *xfs_buf_offset(struct xfs_buf *, size_t);
extern void xfs_buf_stale(struct xfs_buf *bp);

/* Delayed Write Buffer Routines */
extern void xfs_buf_delwri_cancel(struct list_head *);
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);

/* Buffer Daemon Setup Routines */
extern int xfs_buf_init(void);
extern void xfs_buf_terminate(void);

/*
 * These macros use the IO block map rather than b_bn. b_bn is now really
 * just for the buffer cache index for cached buffers. As IO does not use b_bn
 * anymore, uncached buffers do not use b_bn at all and hence must modify the IO
 * map directly. Uncached buffers are not allowed to be discontiguous, so this
 * is safe to do.
 *
 * In future, uncached buffers will pass the block number directly to the io
 * request function and hence these macros will go away at that point.
 */
#define XFS_BUF_ADDR(bp)		((bp)->b_maps[0].bm_bn)
#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_maps[0].bm_bn = (xfs_daddr_t)(bno))

void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref);

/*
 * If the buffer is already on the LRU, do nothing. Otherwise set the buffer
 * up with a reference count of 0 so it will be tossed from the cache when
 * released.
 */
static inline void xfs_buf_oneshot(struct xfs_buf *bp)
{
	if (!list_empty(&bp->b_lru) || atomic_read(&bp->b_lru_ref) > 1)
		return;
	atomic_set(&bp->b_lru_ref, 0);
}

static inline int xfs_buf_ispinned(struct xfs_buf *bp)
{
	return atomic_read(&bp->b_pin_count);
}

static inline void xfs_buf_relse(xfs_buf_t *bp)
{
	xfs_buf_unlock(bp);
	xfs_buf_rele(bp);
}

static inline int
xfs_buf_verify_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
{
	return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
				cksum_offset);
}

static inline void
xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
{
	xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
			 cksum_offset);
}

/*
 *	Handling of buftargs.
 */
extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
			struct block_device *, struct dax_device *);
extern void xfs_free_buftarg(struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);

#define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)

static inline int
xfs_buftarg_dma_alignment(struct xfs_buftarg *bt)
{
	return queue_dma_alignment(bt->bt_bdev->bd_disk->queue);
}

int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic);
bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic);

#endif	/* __XFS_BUF_H__ */