summaryrefslogtreecommitdiff
path: root/block/blk.h
blob: 305e0ac22bf7c321d480e9fa363fbe169cf0cfc0 (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
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_INTERNAL_H
#define BLK_INTERNAL_H

#include <linux/idr.h>
#include <linux/blk-mq.h>
#include <linux/part_stat.h>
#include <xen/xen.h>
#include "blk-mq.h"
#include "blk-mq-sched.h"

/* Max future timer expiry for timeouts */
#define BLK_MAX_TIMEOUT		(5 * HZ)

#ifdef CONFIG_DEBUG_FS
extern struct dentry *blk_debugfs_root;
#endif

struct blk_flush_queue {
	unsigned int		flush_queue_delayed:1;
	unsigned int		flush_pending_idx:1;
	unsigned int		flush_running_idx:1;
	blk_status_t 		rq_status;
	unsigned long		flush_pending_since;
	struct list_head	flush_queue[2];
	struct list_head	flush_data_in_flight;
	struct request		*flush_rq;

	/*
	 * flush_rq shares tag with this rq, both can't be active
	 * at the same time
	 */
	struct request		*orig_rq;
	struct lock_class_key	key;
	spinlock_t		mq_flush_lock;
};

extern struct kmem_cache *blk_requestq_cachep;
extern struct kobj_type blk_queue_ktype;
extern struct ida blk_queue_ida;

static inline struct blk_flush_queue *
blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
{
	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
}

static inline void __blk_get_queue(struct request_queue *q)
{
	kobject_get(&q->kobj);
}

static inline bool
is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
{
	return hctx->fq->flush_rq == req;
}

struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
					      gfp_t flags);
void blk_free_flush_queue(struct blk_flush_queue *q);

void blk_freeze_queue(struct request_queue *q);

static inline void blk_queue_enter_live(struct request_queue *q)
{
	/*
	 * Given that running in generic_make_request() context
	 * guarantees that a live reference against q_usage_counter has
	 * been established, further references under that same context
	 * need not check that the queue has been frozen (marked dead).
	 */
	percpu_ref_get(&q->q_usage_counter);
}

static inline bool biovec_phys_mergeable(struct request_queue *q,
		struct bio_vec *vec1, struct bio_vec *vec2)
{
	unsigned long mask = queue_segment_boundary(q);
	phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset;
	phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset;

	if (addr1 + vec1->bv_len != addr2)
		return false;
	if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page))
		return false;
	if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask))
		return false;
	return true;
}

static inline bool __bvec_gap_to_prev(struct request_queue *q,
		struct bio_vec *bprv, unsigned int offset)
{
	return (offset & queue_virt_boundary(q)) ||
		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
}

/*
 * Check if adding a bio_vec after bprv with offset would create a gap in
 * the SG list. Most drivers don't care about this, but some do.
 */
static inline bool bvec_gap_to_prev(struct request_queue *q,
		struct bio_vec *bprv, unsigned int offset)
{
	if (!queue_virt_boundary(q))
		return false;
	return __bvec_gap_to_prev(q, bprv, offset);
}

static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
		unsigned int nr_segs)
{
	rq->nr_phys_segments = nr_segs;
	rq->__data_len = bio->bi_iter.bi_size;
	rq->bio = rq->biotail = bio;
	rq->ioprio = bio_prio(bio);

	if (bio->bi_disk)
		rq->rq_disk = bio->bi_disk;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
void blk_flush_integrity(void);
bool __bio_integrity_endio(struct bio *);
void bio_integrity_free(struct bio *bio);
static inline bool bio_integrity_endio(struct bio *bio)
{
	if (bio_integrity(bio))
		return __bio_integrity_endio(bio);
	return true;
}

static inline bool integrity_req_gap_back_merge(struct request *req,
		struct bio *next)
{
	struct bio_integrity_payload *bip = bio_integrity(req->bio);
	struct bio_integrity_payload *bip_next = bio_integrity(next);

	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
				bip_next->bip_vec[0].bv_offset);
}

static inline bool integrity_req_gap_front_merge(struct request *req,
		struct bio *bio)
{
	struct bio_integrity_payload *bip = bio_integrity(bio);
	struct bio_integrity_payload *bip_next = bio_integrity(req->bio);

	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
				bip_next->bip_vec[0].bv_offset);
}

void blk_integrity_add(struct gendisk *);
void blk_integrity_del(struct gendisk *);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline bool integrity_req_gap_back_merge(struct request *req,
		struct bio *next)
{
	return false;
}
static inline bool integrity_req_gap_front_merge(struct request *req,
		struct bio *bio)
{
	return false;
}

static inline void blk_flush_integrity(void)
{
}
static inline bool bio_integrity_endio(struct bio *bio)
{
	return true;
}
static inline void bio_integrity_free(struct bio *bio)
{
}
static inline void blk_integrity_add(struct gendisk *disk)
{
}
static inline void blk_integrity_del(struct gendisk *disk)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

unsigned long blk_rq_timeout(unsigned long timeout);
void blk_add_timer(struct request *req);

bool bio_attempt_front_merge(struct request *req, struct bio *bio,
		unsigned int nr_segs);
bool bio_attempt_back_merge(struct request *req, struct bio *bio,
		unsigned int nr_segs);
bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
		struct bio *bio);
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
		unsigned int nr_segs, struct request **same_queue_rq);

void blk_account_io_start(struct request *req, bool new_io);
void blk_account_io_completion(struct request *req, unsigned int bytes);
void blk_account_io_done(struct request *req, u64 now);

/*
 * Internal elevator interface
 */
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)

void blk_insert_flush(struct request *rq);

void elevator_init_mq(struct request_queue *q);
int elevator_switch_mq(struct request_queue *q,
			      struct elevator_type *new_e);
void __elevator_exit(struct request_queue *, struct elevator_queue *);
int elv_register_queue(struct request_queue *q, bool uevent);
void elv_unregister_queue(struct request_queue *q);

static inline void elevator_exit(struct request_queue *q,
		struct elevator_queue *e)
{
	lockdep_assert_held(&q->sysfs_lock);

	blk_mq_sched_free_requests(q);
	__elevator_exit(q, e);
}

struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);

ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
		char *buf);
ssize_t part_stat_show(struct device *dev, struct device_attribute *attr,
		char *buf);
ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
		char *buf);
ssize_t part_fail_show(struct device *dev, struct device_attribute *attr,
		char *buf);
ssize_t part_fail_store(struct device *dev, struct device_attribute *attr,
		const char *buf, size_t count);

#ifdef CONFIG_FAIL_IO_TIMEOUT
int blk_should_fake_timeout(struct request_queue *);
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
ssize_t part_timeout_store(struct device *, struct device_attribute *,
				const char *, size_t);
#else
static inline int blk_should_fake_timeout(struct request_queue *q)
{
	return 0;
}
#endif

void __blk_queue_split(struct request_queue *q, struct bio **bio,
		unsigned int *nr_segs);
int ll_back_merge_fn(struct request *req, struct bio *bio,
		unsigned int nr_segs);
int ll_front_merge_fn(struct request *req,  struct bio *bio,
		unsigned int nr_segs);
struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
				struct request *next);
unsigned int blk_recalc_rq_segments(struct request *rq);
void blk_rq_set_mixed_merge(struct request *rq);
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);

int blk_dev_init(void);

/*
 * Contribute to IO statistics IFF:
 *
 *	a) it's attached to a gendisk, and
 *	b) the queue had IO stats enabled when this request was started
 */
static inline bool blk_do_io_stat(struct request *rq)
{
	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
}

static inline void req_set_nomerge(struct request_queue *q, struct request *req)
{
	req->cmd_flags |= REQ_NOMERGE;
	if (req == q->last_merge)
		q->last_merge = NULL;
}

/*
 * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
 * is defined as 'unsigned int', meantime it has to aligned to with logical
 * block size which is the minimum accepted unit by hardware.
 */
static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
{
	return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
}

/*
 * Internal io_context interface
 */
void get_io_context(struct io_context *ioc);
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
			     gfp_t gfp_mask);
void ioc_clear_queue(struct request_queue *q);

int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);

/**
 * create_io_context - try to create task->io_context
 * @gfp_mask: allocation mask
 * @node: allocation node
 *
 * If %current->io_context is %NULL, allocate a new io_context and install
 * it.  Returns the current %current->io_context which may be %NULL if
 * allocation failed.
 *
 * Note that this function can't be called with IRQ disabled because
 * task_lock which protects %current->io_context is IRQ-unsafe.
 */
static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
{
	WARN_ON_ONCE(irqs_disabled());
	if (unlikely(!current->io_context))
		create_task_io_context(current, gfp_mask, node);
	return current->io_context;
}

/*
 * Internal throttling interface
 */
#ifdef CONFIG_BLK_DEV_THROTTLING
extern void blk_throtl_drain(struct request_queue *q);
extern int blk_throtl_init(struct request_queue *q);
extern void blk_throtl_exit(struct request_queue *q);
extern void blk_throtl_register_queue(struct request_queue *q);
#else /* CONFIG_BLK_DEV_THROTTLING */
static inline void blk_throtl_drain(struct request_queue *q) { }
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline void blk_throtl_exit(struct request_queue *q) { }
static inline void blk_throtl_register_queue(struct request_queue *q) { }
#endif /* CONFIG_BLK_DEV_THROTTLING */
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
	const char *page, size_t count);
extern void blk_throtl_bio_endio(struct bio *bio);
extern void blk_throtl_stat_add(struct request *rq, u64 time);
#else
static inline void blk_throtl_bio_endio(struct bio *bio) { }
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
#endif

#ifdef CONFIG_BOUNCE
extern int init_emergency_isa_pool(void);
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
#else
static inline int init_emergency_isa_pool(void)
{
	return 0;
}
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
{
}
#endif /* CONFIG_BOUNCE */

#ifdef CONFIG_BLK_CGROUP_IOLATENCY
extern int blk_iolatency_init(struct request_queue *q);
#else
static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
#endif

struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);

#ifdef CONFIG_BLK_DEV_ZONED
void blk_queue_free_zone_bitmaps(struct request_queue *q);
#else
static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
#endif

void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
			int rw);
void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
			int rw);
void update_io_ticks(struct hd_struct *part, unsigned long now, bool end);
struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);

int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
void blk_free_devt(dev_t devt);
void blk_invalidate_devt(dev_t devt);
char *disk_name(struct gendisk *hd, int partno, char *buf);
#define ADDPART_FLAG_NONE	0
#define ADDPART_FLAG_RAID	1
#define ADDPART_FLAG_WHOLEDISK	2
void __delete_partition(struct percpu_ref *ref);
void delete_partition(struct gendisk *disk, int partno);
int bdev_add_partition(struct block_device *bdev, int partno,
		sector_t start, sector_t length);
int bdev_del_partition(struct block_device *bdev, int partno);
int bdev_resize_partition(struct block_device *bdev, int partno,
		sector_t start, sector_t length);
int disk_expand_part_tbl(struct gendisk *disk, int target);

static inline int hd_ref_init(struct hd_struct *part)
{
	if (percpu_ref_init(&part->ref, __delete_partition, 0,
				GFP_KERNEL))
		return -ENOMEM;
	return 0;
}

static inline void hd_struct_get(struct hd_struct *part)
{
	percpu_ref_get(&part->ref);
}

static inline int hd_struct_try_get(struct hd_struct *part)
{
	return percpu_ref_tryget_live(&part->ref);
}

static inline void hd_struct_put(struct hd_struct *part)
{
	percpu_ref_put(&part->ref);
}

static inline void hd_struct_kill(struct hd_struct *part)
{
	percpu_ref_kill(&part->ref);
}

static inline void hd_free_part(struct hd_struct *part)
{
	free_part_stats(part);
	kfree(part->info);
	percpu_ref_exit(&part->ref);
}

/*
 * Any access of part->nr_sects which is not protected by partition
 * bd_mutex or gendisk bdev bd_mutex, should be done using this
 * accessor function.
 *
 * Code written along the lines of i_size_read() and i_size_write().
 * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
 * on.
 */
static inline sector_t part_nr_sects_read(struct hd_struct *part)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	sector_t nr_sects;
	unsigned seq;
	do {
		seq = read_seqcount_begin(&part->nr_sects_seq);
		nr_sects = part->nr_sects;
	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
	return nr_sects;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
	sector_t nr_sects;

	preempt_disable();
	nr_sects = part->nr_sects;
	preempt_enable();
	return nr_sects;
#else
	return part->nr_sects;
#endif
}

/*
 * Should be called with mutex lock held (typically bd_mutex) of partition
 * to provide mutual exlusion among writers otherwise seqcount might be
 * left in wrong state leaving the readers spinning infinitely.
 */
static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	write_seqcount_begin(&part->nr_sects_seq);
	part->nr_sects = size;
	write_seqcount_end(&part->nr_sects_seq);
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
	preempt_disable();
	part->nr_sects = size;
	preempt_enable();
#else
	part->nr_sects = size;
#endif
}

struct request_queue *__blk_alloc_queue(int node_id);

int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
		struct page *page, unsigned int len, unsigned int offset,
		bool *same_page);

#endif /* BLK_INTERNAL_H */