aboutsummaryrefslogtreecommitdiff
path: root/block/blk.h
blob: 0089fefdf771d7082ee05ca97504005090a26025 (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
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_INTERNAL_H
#define BLK_INTERNAL_H

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

/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME	(HZ/50UL)

/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ	32

/* 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;
	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;
	spinlock_t		mq_flush_lock;
};

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

/*
 * @q->queue_lock is set while a queue is being initialized. Since we know
 * that no other threads access the queue object before @q->queue_lock has
 * been set, it is safe to manipulate queue flags without holding the
 * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and
 * blk_init_allocated_queue().
 */
static inline void queue_lockdep_assert_held(struct request_queue *q)
{
	if (q->queue_lock)
		lockdep_assert_held(q->queue_lock);
}

static inline void queue_flag_set_unlocked(unsigned int flag,
					   struct request_queue *q)
{
	if (test_bit(QUEUE_FLAG_INIT_DONE, &q->queue_flags) &&
	    kref_read(&q->kobj.kref))
		lockdep_assert_held(q->queue_lock);
	__set_bit(flag, &q->queue_flags);
}

static inline void queue_flag_clear_unlocked(unsigned int flag,
					     struct request_queue *q)
{
	if (test_bit(QUEUE_FLAG_INIT_DONE, &q->queue_flags) &&
	    kref_read(&q->kobj.kref))
		lockdep_assert_held(q->queue_lock);
	__clear_bit(flag, &q->queue_flags);
}

static inline int queue_flag_test_and_clear(unsigned int flag,
					    struct request_queue *q)
{
	queue_lockdep_assert_held(q);

	if (test_bit(flag, &q->queue_flags)) {
		__clear_bit(flag, &q->queue_flags);
		return 1;
	}

	return 0;
}

static inline int queue_flag_test_and_set(unsigned int flag,
					  struct request_queue *q)
{
	queue_lockdep_assert_held(q);

	if (!test_bit(flag, &q->queue_flags)) {
		__set_bit(flag, &q->queue_flags);
		return 0;
	}

	return 1;
}

static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
{
	queue_lockdep_assert_held(q);
	__set_bit(flag, &q->queue_flags);
}

static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
{
	queue_lockdep_assert_held(q);
	__clear_bit(flag, &q->queue_flags);
}

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

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

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

int blk_init_rl(struct request_list *rl, struct request_queue *q,
		gfp_t gfp_mask);
void blk_exit_rl(struct request_queue *q, struct request_list *rl);
void blk_exit_queue(struct request_queue *q);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
			struct bio *bio);
void blk_queue_bypass_start(struct request_queue *q);
void blk_queue_bypass_end(struct request_queue *q);
void __blk_queue_free_tags(struct request_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))
		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);
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
void blk_flush_integrity(void);
bool __bio_integrity_endio(struct 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);
}
#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;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

void blk_timeout_work(struct work_struct *work);
unsigned long blk_rq_timeout(unsigned long timeout);
void blk_add_timer(struct request *req);
void blk_delete_timer(struct request *);


bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
			     struct bio *bio);
bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
			    struct bio *bio);
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 *request_count,
			    struct request **same_queue_rq);
unsigned int blk_plug_queued_count(struct request_queue *q);

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);

/*
 * EH timer and IO completion will both attempt to 'grab' the request, make
 * sure that only one of them succeeds. Steal the bottom bit of the
 * __deadline field for this.
 */
static inline int blk_mark_rq_complete(struct request *rq)
{
	return test_and_set_bit(0, &rq->__deadline);
}

static inline void blk_clear_rq_complete(struct request *rq)
{
	clear_bit(0, &rq->__deadline);
}

static inline bool blk_rq_is_complete(struct request *rq)
{
	return test_bit(0, &rq->__deadline);
}

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

void blk_insert_flush(struct request *rq);

static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.sq.elevator_activate_req_fn)
		e->type->ops.sq.elevator_activate_req_fn(q, rq);
}

static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.sq.elevator_deactivate_req_fn)
		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
}

int elevator_init(struct request_queue *);
int 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);
void elv_unregister_queue(struct request_queue *q);

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

#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

int ll_back_merge_fn(struct request_queue *q, struct request *req,
		     struct bio *bio);
int ll_front_merge_fn(struct request_queue *q, struct request *req, 
		      struct bio *bio);
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);
void 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);

void blk_queue_congestion_threshold(struct request_queue *q);

int blk_dev_init(void);


/*
 * Return the threshold (number of used requests) at which the queue is
 * considered to be congested.  It include a little hysteresis to keep the
 * context switch rate down.
 */
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
	return q->nr_congestion_on;
}

/*
 * The threshold at which a queue is considered to be uncongested
 */
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
	return q->nr_congestion_off;
}

extern int blk_update_nr_requests(struct request_queue *, unsigned int);

/*
 * 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, and
 *	c) it's a file system request
 */
static inline bool blk_do_io_stat(struct request *rq)
{
	return rq->rq_disk &&
	       (rq->rq_flags & RQF_IO_STAT) &&
		!blk_rq_is_passthrough(rq);
}

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;
}

/*
 * Steal a bit from this field for legacy IO path atomic IO marking. Note that
 * setting the deadline clears the bottom bit, potentially clearing the
 * completed bit. The user has to be OK with this (current ones are fine).
 */
static inline void blk_rq_set_deadline(struct request *rq, unsigned long time)
{
	rq->__deadline = time & ~0x1UL;
}

static inline unsigned long blk_rq_deadline(struct request *rq)
{
	return rq->__deadline & ~0x1UL;
}

/*
 * 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);

/**
 * rq_ioc - determine io_context for request allocation
 * @bio: request being allocated is for this bio (can be %NULL)
 *
 * Determine io_context to use for request allocation for @bio.  May return
 * %NULL if %current->io_context doesn't exist.
 */
static inline struct io_context *rq_ioc(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
	if (bio && bio->bi_ioc)
		return bio->bi_ioc;
#endif
	return current->io_context;
}

/**
 * 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 */

extern void blk_drain_queue(struct request_queue *q);

#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

#endif /* BLK_INTERNAL_H */