Boot Linux faster!

Check our new training course

Boot Linux faster!

Check our new training course
and Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

  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
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Block data types and constants.  Directly include this file only to
 * break include dependency loop.
 */
#ifndef __LINUX_BLK_TYPES_H
#define __LINUX_BLK_TYPES_H

#include <linux/types.h>
#include <linux/bvec.h>
#include <linux/ktime.h>

struct bio_set;
struct bio;
struct bio_integrity_payload;
struct page;
struct io_context;
struct cgroup_subsys_state;
typedef void (bio_end_io_t) (struct bio *);
struct bio_crypt_ctx;

struct block_device {
	dev_t			bd_dev;
	int			bd_openers;
	struct inode *		bd_inode;	/* will die */
	struct super_block *	bd_super;
	struct mutex		bd_mutex;	/* open/close mutex */
	void *			bd_claiming;
	void *			bd_holder;
	int			bd_holders;
	bool			bd_write_holder;
#ifdef CONFIG_SYSFS
	struct list_head	bd_holder_disks;
#endif
	struct block_device *	bd_contains;
	u8			bd_partno;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;

	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
	struct gendisk *	bd_disk;
	struct backing_dev_info *bd_bdi;

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
} __randomize_layout;

/*
 * Block error status values.  See block/blk-core:blk_errors for the details.
 * Alpha cannot write a byte atomically, so we need to use 32-bit value.
 */
#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__)
typedef u32 __bitwise blk_status_t;
#else
typedef u8 __bitwise blk_status_t;
#endif
#define	BLK_STS_OK 0
#define BLK_STS_NOTSUPP		((__force blk_status_t)1)
#define BLK_STS_TIMEOUT		((__force blk_status_t)2)
#define BLK_STS_NOSPC		((__force blk_status_t)3)
#define BLK_STS_TRANSPORT	((__force blk_status_t)4)
#define BLK_STS_TARGET		((__force blk_status_t)5)
#define BLK_STS_NEXUS		((__force blk_status_t)6)
#define BLK_STS_MEDIUM		((__force blk_status_t)7)
#define BLK_STS_PROTECTION	((__force blk_status_t)8)
#define BLK_STS_RESOURCE	((__force blk_status_t)9)
#define BLK_STS_IOERR		((__force blk_status_t)10)

/* hack for device mapper, don't use elsewhere: */
#define BLK_STS_DM_REQUEUE    ((__force blk_status_t)11)

#define BLK_STS_AGAIN		((__force blk_status_t)12)

/*
 * BLK_STS_DEV_RESOURCE is returned from the driver to the block layer if
 * device related resources are unavailable, but the driver can guarantee
 * that the queue will be rerun in the future once resources become
 * available again. This is typically the case for device specific
 * resources that are consumed for IO. If the driver fails allocating these
 * resources, we know that inflight (or pending) IO will free these
 * resource upon completion.
 *
 * This is different from BLK_STS_RESOURCE in that it explicitly references
 * a device specific resource. For resources of wider scope, allocation
 * failure can happen without having pending IO. This means that we can't
 * rely on request completions freeing these resources, as IO may not be in
 * flight. Examples of that are kernel memory allocations, DMA mappings, or
 * any other system wide resources.
 */
#define BLK_STS_DEV_RESOURCE	((__force blk_status_t)13)

/*
 * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
 * related resources are unavailable, but the driver can guarantee the queue
 * will be rerun in the future once the resources become available again.
 *
 * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
 * a zone specific resource and IO to a different zone on the same device could
 * still be served. Examples of that are zones that are write-locked, but a read
 * to the same zone could be served.
 */
#define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)

/*
 * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
 * path if the device returns a status indicating that too many zone resources
 * are currently open. The same command should be successful if resubmitted
 * after the number of open zones decreases below the device's limits, which is
 * reported in the request_queue's max_open_zones.
 */
#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)

/*
 * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
 * path if the device returns a status indicating that too many zone resources
 * are currently active. The same command should be successful if resubmitted
 * after the number of active zones decreases below the device's limits, which
 * is reported in the request_queue's max_active_zones.
 */
#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)

/**
 * blk_path_error - returns true if error may be path related
 * @error: status the request was completed with
 *
 * Description:
 *     This classifies block error status into non-retryable errors and ones
 *     that may be successful if retried on a failover path.
 *
 * Return:
 *     %false - retrying failover path will not help
 *     %true  - may succeed if retried
 */
static inline bool blk_path_error(blk_status_t error)
{
	switch (error) {
	case BLK_STS_NOTSUPP:
	case BLK_STS_NOSPC:
	case BLK_STS_TARGET:
	case BLK_STS_NEXUS:
	case BLK_STS_MEDIUM:
	case BLK_STS_PROTECTION:
		return false;
	}

	/* Anything else could be a path failure, so should be retried */
	return true;
}

/*
 * From most significant bit:
 * 1 bit: reserved for other usage, see below
 * 12 bits: original size of bio
 * 51 bits: issue time of bio
 */
#define BIO_ISSUE_RES_BITS      1
#define BIO_ISSUE_SIZE_BITS     12
#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
#define BIO_ISSUE_SIZE_MASK     \
	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))

/* Reserved bit for blk-throtl */
#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)

struct bio_issue {
	u64 value;
};

static inline u64 __bio_issue_time(u64 time)
{
	return time & BIO_ISSUE_TIME_MASK;
}

static inline u64 bio_issue_time(struct bio_issue *issue)
{
	return __bio_issue_time(issue->value);
}

static inline sector_t bio_issue_size(struct bio_issue *issue)
{
	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
}

static inline void bio_issue_init(struct bio_issue *issue,
				       sector_t size)
{
	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
			((u64)size << BIO_ISSUE_SIZE_SHIFT));
}

/*
 * main unit of I/O for the block layer and lower layers (ie drivers and
 * stacking drivers)
 */
struct bio {
	struct bio		*bi_next;	/* request queue link */
	struct gendisk		*bi_disk;
	unsigned int		bi_opf;		/* bottom bits req flags,
						 * top bits REQ_OP. Use
						 * accessors.
						 */
	unsigned short		bi_flags;	/* status, etc and bvec pool number */
	unsigned short		bi_ioprio;
	unsigned short		bi_write_hint;
	blk_status_t		bi_status;
	u8			bi_partno;
	atomic_t		__bi_remaining;

	struct bvec_iter	bi_iter;

	bio_end_io_t		*bi_end_io;

	void			*bi_private;
#ifdef CONFIG_BLK_CGROUP
	/*
	 * Represents the association of the css and request_queue for the bio.
	 * If a bio goes direct to device, it will not have a blkg as it will
	 * not have a request_queue associated with it.  The reference is put
	 * on release of the bio.
	 */
	struct blkcg_gq		*bi_blkg;
	struct bio_issue	bi_issue;
#ifdef CONFIG_BLK_CGROUP_IOCOST
	u64			bi_iocost_cost;
#endif
#endif

#ifdef CONFIG_BLK_INLINE_ENCRYPTION
	struct bio_crypt_ctx	*bi_crypt_context;
#endif

	union {
#if defined(CONFIG_BLK_DEV_INTEGRITY)
		struct bio_integrity_payload *bi_integrity; /* data integrity */
#endif
	};

	unsigned short		bi_vcnt;	/* how many bio_vec's */

	/*
	 * Everything starting with bi_max_vecs will be preserved by bio_reset()
	 */

	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */

	atomic_t		__bi_cnt;	/* pin count */

	struct bio_vec		*bi_io_vec;	/* the actual vec list */

	struct bio_set		*bi_pool;

	/*
	 * We can inline a number of vecs at the end of the bio, to avoid
	 * double allocations for a small number of bio_vecs. This member
	 * MUST obviously be kept at the very end of the bio.
	 */
	struct bio_vec		bi_inline_vecs[];
};

#define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)

/*
 * bio flags
 */
enum {
	BIO_NO_PAGE_REF,	/* don't put release vec pages */
	BIO_CLONED,		/* doesn't own data */
	BIO_BOUNCED,		/* bio is a bounce bio */
	BIO_WORKINGSET,		/* contains userspace workingset pages */
	BIO_QUIET,		/* Make BIO Quiet */
	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
	BIO_REFFED,		/* bio has elevated ->bi_cnt */
	BIO_THROTTLED,		/* This bio has already been subjected to
				 * throttling rules. Don't do it again. */
	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
				 * of this bio. */
	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
	BIO_TRACKED,		/* set if bio goes through the rq_qos path */
	BIO_FLAG_LAST
};

/* See BVEC_POOL_OFFSET below before adding new flags */

/*
 * We support 6 different bvec pools, the last one is magic in that it
 * is backed by a mempool.
 */
#define BVEC_POOL_NR		6
#define BVEC_POOL_MAX		(BVEC_POOL_NR - 1)

/*
 * Top 3 bits of bio flags indicate the pool the bvecs came from.  We add
 * 1 to the actual index so that 0 indicates that there are no bvecs to be
 * freed.
 */
#define BVEC_POOL_BITS		(3)
#define BVEC_POOL_OFFSET	(16 - BVEC_POOL_BITS)
#define BVEC_POOL_IDX(bio)	((bio)->bi_flags >> BVEC_POOL_OFFSET)
#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1)
# error "BVEC_POOL_BITS is too small"
#endif

/*
 * Flags starting here get preserved by bio_reset() - this includes
 * only BVEC_POOL_IDX()
 */
#define BIO_RESET_BITS	BVEC_POOL_OFFSET

typedef __u32 __bitwise blk_mq_req_flags_t;

/*
 * Operations and flags common to the bio and request structures.
 * We use 8 bits for encoding the operation, and the remaining 24 for flags.
 *
 * The least significant bit of the operation number indicates the data
 * transfer direction:
 *
 *   - if the least significant bit is set transfers are TO the device
 *   - if the least significant bit is not set transfers are FROM the device
 *
 * If a operation does not transfer data the least significant bit has no
 * meaning.
 */
#define REQ_OP_BITS	8
#define REQ_OP_MASK	((1 << REQ_OP_BITS) - 1)
#define REQ_FLAG_BITS	24

enum req_opf {
	/* read sectors from the device */
	REQ_OP_READ		= 0,
	/* write sectors to the device */
	REQ_OP_WRITE		= 1,
	/* flush the volatile write cache */
	REQ_OP_FLUSH		= 2,
	/* discard sectors */
	REQ_OP_DISCARD		= 3,
	/* securely erase sectors */
	REQ_OP_SECURE_ERASE	= 5,
	/* write the same sector many times */
	REQ_OP_WRITE_SAME	= 7,
	/* write the zero filled sector many times */
	REQ_OP_WRITE_ZEROES	= 9,
	/* Open a zone */
	REQ_OP_ZONE_OPEN	= 10,
	/* Close a zone */
	REQ_OP_ZONE_CLOSE	= 11,
	/* Transition a zone to full */
	REQ_OP_ZONE_FINISH	= 12,
	/* write data at the current zone write pointer */
	REQ_OP_ZONE_APPEND	= 13,
	/* reset a zone write pointer */
	REQ_OP_ZONE_RESET	= 15,
	/* reset all the zone present on the device */
	REQ_OP_ZONE_RESET_ALL	= 17,

	/* SCSI passthrough using struct scsi_request */
	REQ_OP_SCSI_IN		= 32,
	REQ_OP_SCSI_OUT		= 33,
	/* Driver private requests */
	REQ_OP_DRV_IN		= 34,
	REQ_OP_DRV_OUT		= 35,

	REQ_OP_LAST,
};

enum req_flag_bits {
	__REQ_FAILFAST_DEV =	/* no driver retries of device errors */
		REQ_OP_BITS,
	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
	__REQ_SYNC,		/* request is sync (sync write or read) */
	__REQ_META,		/* metadata io request */
	__REQ_PRIO,		/* boost priority in cfq */
	__REQ_NOMERGE,		/* don't touch this for merging */
	__REQ_IDLE,		/* anticipate more IO after this one */
	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
	__REQ_FUA,		/* forced unit access */
	__REQ_PREFLUSH,		/* request for cache flush */
	__REQ_RAHEAD,		/* read ahead, can fail anytime */
	__REQ_BACKGROUND,	/* background IO */
	__REQ_NOWAIT,           /* Don't wait if request will block */
	/*
	 * When a shared kthread needs to issue a bio for a cgroup, doing
	 * so synchronously can lead to priority inversions as the kthread
	 * can be trapped waiting for that cgroup.  CGROUP_PUNT flag makes
	 * submit_bio() punt the actual issuing to a dedicated per-blkcg
	 * work item to avoid such priority inversions.
	 */
	__REQ_CGROUP_PUNT,

	/* command specific flags for REQ_OP_WRITE_ZEROES: */
	__REQ_NOUNMAP,		/* do not free blocks when zeroing */

	__REQ_HIPRI,

	/* for driver use */
	__REQ_DRV,
	__REQ_SWAP,		/* swapping request. */
	__REQ_NR_BITS,		/* stops here */
};

#define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
#define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
#define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
#define REQ_SYNC		(1ULL << __REQ_SYNC)
#define REQ_META		(1ULL << __REQ_META)
#define REQ_PRIO		(1ULL << __REQ_PRIO)
#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
#define REQ_IDLE		(1ULL << __REQ_IDLE)
#define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
#define REQ_FUA			(1ULL << __REQ_FUA)
#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
#define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
#define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
#define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)

#define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
#define REQ_HIPRI		(1ULL << __REQ_HIPRI)

#define REQ_DRV			(1ULL << __REQ_DRV)
#define REQ_SWAP		(1ULL << __REQ_SWAP)

#define REQ_FAILFAST_MASK \
	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)

#define REQ_NOMERGE_FLAGS \
	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)

enum stat_group {
	STAT_READ,
	STAT_WRITE,
	STAT_DISCARD,
	STAT_FLUSH,

	NR_STAT_GROUPS
};

#define bio_op(bio) \
	((bio)->bi_opf & REQ_OP_MASK)
#define req_op(req) \
	((req)->cmd_flags & REQ_OP_MASK)

/* obsolete, don't use in new code */
static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
		unsigned op_flags)
{
	bio->bi_opf = op | op_flags;
}

static inline bool op_is_write(unsigned int op)
{
	return (op & 1);
}

/*
 * Check if the bio or request is one that needs special treatment in the
 * flush state machine.
 */
static inline bool op_is_flush(unsigned int op)
{
	return op & (REQ_FUA | REQ_PREFLUSH);
}

/*
 * Reads are always treated as synchronous, as are requests with the FUA or
 * PREFLUSH flag.  Other operations may be marked as synchronous using the
 * REQ_SYNC flag.
 */
static inline bool op_is_sync(unsigned int op)
{
	return (op & REQ_OP_MASK) == REQ_OP_READ ||
		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
}

static inline bool op_is_discard(unsigned int op)
{
	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
}

/*
 * Check if a bio or request operation is a zone management operation, with
 * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
 * due to its different handling in the block layer and device response in
 * case of command failure.
 */
static inline bool op_is_zone_mgmt(enum req_opf op)
{
	switch (op & REQ_OP_MASK) {
	case REQ_OP_ZONE_RESET:
	case REQ_OP_ZONE_OPEN:
	case REQ_OP_ZONE_CLOSE:
	case REQ_OP_ZONE_FINISH:
		return true;
	default:
		return false;
	}
}

static inline int op_stat_group(unsigned int op)
{
	if (op_is_discard(op))
		return STAT_DISCARD;
	return op_is_write(op);
}

typedef unsigned int blk_qc_t;
#define BLK_QC_T_NONE		-1U
#define BLK_QC_T_SHIFT		16
#define BLK_QC_T_INTERNAL	(1U << 31)

static inline bool blk_qc_t_valid(blk_qc_t cookie)
{
	return cookie != BLK_QC_T_NONE;
}

static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
{
	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
}

static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
{
	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
}

static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
{
	return (cookie & BLK_QC_T_INTERNAL) != 0;
}

struct blk_rq_stat {
	u64 mean;
	u64 min;
	u64 max;
	u32 nr_samples;
	u64 batch;
};

#endif /* __LINUX_BLK_TYPES_H */