summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-rq.c
blob: a41209a43506c0bf491794fe4fd92892fe45fb96 (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
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
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
/*
 * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm-core.h"
#include "dm-rq.h"

#include <linux/blk-mq.h>

#define DM_MSG_PREFIX "core-rq"

/*
 * One of these is allocated per request.
 */
struct dm_rq_target_io {
	struct mapped_device *md;
	struct dm_target *ti;
	struct request *orig, *clone;
	struct kthread_work work;
	blk_status_t error;
	union map_info info;
	struct dm_stats_aux stats_aux;
	unsigned long duration_jiffies;
	unsigned n_sectors;
	unsigned completed;
};

#define DM_MQ_NR_HW_QUEUES 1
#define DM_MQ_QUEUE_DEPTH 2048
static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;

/*
 * Request-based DM's mempools' reserved IOs set by the user.
 */
#define RESERVED_REQUEST_BASED_IOS	256
static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;

unsigned dm_get_reserved_rq_based_ios(void)
{
	return __dm_get_module_param(&reserved_rq_based_ios,
				     RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS);
}

static unsigned dm_get_blk_mq_nr_hw_queues(void)
{
	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
}

static unsigned dm_get_blk_mq_queue_depth(void)
{
	return __dm_get_module_param(&dm_mq_queue_depth,
				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
}

int dm_request_based(struct mapped_device *md)
{
	return queue_is_mq(md->queue);
}

void dm_start_queue(struct request_queue *q)
{
	blk_mq_unquiesce_queue(q);
	blk_mq_kick_requeue_list(q);
}

void dm_stop_queue(struct request_queue *q)
{
	blk_mq_quiesce_queue(q);
}

/*
 * Partial completion handling for request-based dm
 */
static void end_clone_bio(struct bio *clone)
{
	struct dm_rq_clone_bio_info *info =
		container_of(clone, struct dm_rq_clone_bio_info, clone);
	struct dm_rq_target_io *tio = info->tio;
	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
	blk_status_t error = clone->bi_status;
	bool is_last = !clone->bi_next;

	bio_put(clone);

	if (tio->error)
		/*
		 * An error has already been detected on the request.
		 * Once error occurred, just let clone->end_io() handle
		 * the remainder.
		 */
		return;
	else if (error) {
		/*
		 * Don't notice the error to the upper layer yet.
		 * The error handling decision is made by the target driver,
		 * when the request is completed.
		 */
		tio->error = error;
		goto exit;
	}

	/*
	 * I/O for the bio successfully completed.
	 * Notice the data completion to the upper layer.
	 */
	tio->completed += nr_bytes;

	/*
	 * Update the original request.
	 * Do not use blk_mq_end_request() here, because it may complete
	 * the original request before the clone, and break the ordering.
	 */
	if (is_last)
 exit:
		blk_update_request(tio->orig, BLK_STS_OK, tio->completed);
}

static struct dm_rq_target_io *tio_from_request(struct request *rq)
{
	return blk_mq_rq_to_pdu(rq);
}

static void rq_end_stats(struct mapped_device *md, struct request *orig)
{
	if (unlikely(dm_stats_used(&md->stats))) {
		struct dm_rq_target_io *tio = tio_from_request(orig);
		tio->duration_jiffies = jiffies - tio->duration_jiffies;
		dm_stats_account_io(&md->stats, rq_data_dir(orig),
				    blk_rq_pos(orig), tio->n_sectors, true,
				    tio->duration_jiffies, &tio->stats_aux);
	}
}

/*
 * Don't touch any member of the md after calling this function because
 * the md may be freed in dm_put() at the end of this function.
 * Or do dm_get() before calling this function and dm_put() later.
 */
static void rq_completed(struct mapped_device *md)
{
	/*
	 * dm_put() must be at the end of this function. See the comment above
	 */
	dm_put(md);
}

/*
 * Complete the clone and the original request.
 * Must be called without clone's queue lock held,
 * see end_clone_request() for more details.
 */
static void dm_end_request(struct request *clone, blk_status_t error)
{
	struct dm_rq_target_io *tio = clone->end_io_data;
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;

	blk_rq_unprep_clone(clone);
	tio->ti->type->release_clone_rq(clone, NULL);

	rq_end_stats(md, rq);
	blk_mq_end_request(rq, error);
	rq_completed(md);
}

static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
{
	blk_mq_delay_kick_requeue_list(q, msecs);
}

void dm_mq_kick_requeue_list(struct mapped_device *md)
{
	__dm_mq_kick_requeue_list(md->queue, 0);
}
EXPORT_SYMBOL(dm_mq_kick_requeue_list);

static void dm_mq_delay_requeue_request(struct request *rq, unsigned long msecs)
{
	blk_mq_requeue_request(rq, false);
	__dm_mq_kick_requeue_list(rq->q, msecs);
}

static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_requeue)
{
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;
	unsigned long delay_ms = delay_requeue ? 100 : 0;

	rq_end_stats(md, rq);
	if (tio->clone) {
		blk_rq_unprep_clone(tio->clone);
		tio->ti->type->release_clone_rq(tio->clone, NULL);
	}

	dm_mq_delay_requeue_request(rq, delay_ms);
	rq_completed(md);
}

static void dm_done(struct request *clone, blk_status_t error, bool mapped)
{
	int r = DM_ENDIO_DONE;
	struct dm_rq_target_io *tio = clone->end_io_data;
	dm_request_endio_fn rq_end_io = NULL;

	if (tio->ti) {
		rq_end_io = tio->ti->type->rq_end_io;

		if (mapped && rq_end_io)
			r = rq_end_io(tio->ti, clone, error, &tio->info);
	}

	if (unlikely(error == BLK_STS_TARGET)) {
		if (req_op(clone) == REQ_OP_DISCARD &&
		    !clone->q->limits.max_discard_sectors)
			disable_discard(tio->md);
		else if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
			 !clone->q->limits.max_write_zeroes_sectors)
			disable_write_zeroes(tio->md);
	}

	switch (r) {
	case DM_ENDIO_DONE:
		/* The target wants to complete the I/O */
		dm_end_request(clone, error);
		break;
	case DM_ENDIO_INCOMPLETE:
		/* The target will handle the I/O */
		return;
	case DM_ENDIO_REQUEUE:
		/* The target wants to requeue the I/O */
		dm_requeue_original_request(tio, false);
		break;
	case DM_ENDIO_DELAY_REQUEUE:
		/* The target wants to requeue the I/O after a delay */
		dm_requeue_original_request(tio, true);
		break;
	default:
		DMCRIT("unimplemented target endio return value: %d", r);
		BUG();
	}
}

/*
 * Request completion handler for request-based dm
 */
static void dm_softirq_done(struct request *rq)
{
	bool mapped = true;
	struct dm_rq_target_io *tio = tio_from_request(rq);
	struct request *clone = tio->clone;

	if (!clone) {
		struct mapped_device *md = tio->md;

		rq_end_stats(md, rq);
		blk_mq_end_request(rq, tio->error);
		rq_completed(md);
		return;
	}

	if (rq->rq_flags & RQF_FAILED)
		mapped = false;

	dm_done(clone, tio->error, mapped);
}

/*
 * Complete the clone and the original request with the error status
 * through softirq context.
 */
static void dm_complete_request(struct request *rq, blk_status_t error)
{
	struct dm_rq_target_io *tio = tio_from_request(rq);

	tio->error = error;
	if (likely(!blk_should_fake_timeout(rq->q)))
		blk_mq_complete_request(rq);
}

/*
 * Complete the not-mapped clone and the original request with the error status
 * through softirq context.
 * Target's rq_end_io() function isn't called.
 * This may be used when the target's clone_and_map_rq() function fails.
 */
static void dm_kill_unmapped_request(struct request *rq, blk_status_t error)
{
	rq->rq_flags |= RQF_FAILED;
	dm_complete_request(rq, error);
}

static enum rq_end_io_ret end_clone_request(struct request *clone,
					    blk_status_t error)
{
	struct dm_rq_target_io *tio = clone->end_io_data;

	dm_complete_request(tio->orig, error);
	return RQ_END_IO_NONE;
}

static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
				 void *data)
{
	struct dm_rq_target_io *tio = data;
	struct dm_rq_clone_bio_info *info =
		container_of(bio, struct dm_rq_clone_bio_info, clone);

	info->orig = bio_orig;
	info->tio = tio;
	bio->bi_end_io = end_clone_bio;

	return 0;
}

static int setup_clone(struct request *clone, struct request *rq,
		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
{
	int r;

	r = blk_rq_prep_clone(clone, rq, &tio->md->mempools->bs, gfp_mask,
			      dm_rq_bio_constructor, tio);
	if (r)
		return r;

	clone->end_io = end_clone_request;
	clone->end_io_data = tio;

	tio->clone = clone;

	return 0;
}

static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
		     struct mapped_device *md)
{
	tio->md = md;
	tio->ti = NULL;
	tio->clone = NULL;
	tio->orig = rq;
	tio->error = 0;
	tio->completed = 0;
	/*
	 * Avoid initializing info for blk-mq; it passes
	 * target-specific data through info.ptr
	 * (see: dm_mq_init_request)
	 */
	if (!md->init_tio_pdu)
		memset(&tio->info, 0, sizeof(tio->info));
}

/*
 * Returns:
 * DM_MAPIO_*       : the request has been processed as indicated
 * DM_MAPIO_REQUEUE : the original request needs to be immediately requeued
 * < 0              : the request was completed due to failure
 */
static int map_request(struct dm_rq_target_io *tio)
{
	int r;
	struct dm_target *ti = tio->ti;
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;
	struct request *clone = NULL;
	blk_status_t ret;

	r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
	switch (r) {
	case DM_MAPIO_SUBMITTED:
		/* The target has taken the I/O to submit by itself later */
		break;
	case DM_MAPIO_REMAPPED:
		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
			/* -ENOMEM */
			ti->type->release_clone_rq(clone, &tio->info);
			return DM_MAPIO_REQUEUE;
		}

		/* The target has remapped the I/O so dispatch it */
		trace_block_rq_remap(clone, disk_devt(dm_disk(md)),
				     blk_rq_pos(rq));
		ret = blk_insert_cloned_request(clone);
		switch (ret) {
		case BLK_STS_OK:
			break;
		case BLK_STS_RESOURCE:
		case BLK_STS_DEV_RESOURCE:
			blk_rq_unprep_clone(clone);
			blk_mq_cleanup_rq(clone);
			tio->ti->type->release_clone_rq(clone, &tio->info);
			tio->clone = NULL;
			return DM_MAPIO_REQUEUE;
		default:
			/* must complete clone in terms of original request */
			dm_complete_request(rq, ret);
		}
		break;
	case DM_MAPIO_REQUEUE:
		/* The target wants to requeue the I/O */
		break;
	case DM_MAPIO_DELAY_REQUEUE:
		/* The target wants to requeue the I/O after a delay */
		dm_requeue_original_request(tio, true);
		break;
	case DM_MAPIO_KILL:
		/* The target wants to complete the I/O */
		dm_kill_unmapped_request(rq, BLK_STS_IOERR);
		break;
	default:
		DMCRIT("unimplemented target map return value: %d", r);
		BUG();
	}

	return r;
}

/* DEPRECATED: previously used for request-based merge heuristic in dm_request_fn() */
ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
{
	return sprintf(buf, "%u\n", 0);
}

ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
						     const char *buf, size_t count)
{
	return count;
}

static void dm_start_request(struct mapped_device *md, struct request *orig)
{
	blk_mq_start_request(orig);

	if (unlikely(dm_stats_used(&md->stats))) {
		struct dm_rq_target_io *tio = tio_from_request(orig);
		tio->duration_jiffies = jiffies;
		tio->n_sectors = blk_rq_sectors(orig);
		dm_stats_account_io(&md->stats, rq_data_dir(orig),
				    blk_rq_pos(orig), tio->n_sectors, false, 0,
				    &tio->stats_aux);
	}

	/*
	 * Hold the md reference here for the in-flight I/O.
	 * We can't rely on the reference count by device opener,
	 * because the device may be closed during the request completion
	 * when all bios are completed.
	 * See the comment in rq_completed() too.
	 */
	dm_get(md);
}

static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
			      unsigned int hctx_idx, unsigned int numa_node)
{
	struct mapped_device *md = set->driver_data;
	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);

	/*
	 * Must initialize md member of tio, otherwise it won't
	 * be available in dm_mq_queue_rq.
	 */
	tio->md = md;

	if (md->init_tio_pdu) {
		/* target-specific per-io data is immediately after the tio */
		tio->info.ptr = tio + 1;
	}

	return 0;
}

static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
			  const struct blk_mq_queue_data *bd)
{
	struct request *rq = bd->rq;
	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
	struct mapped_device *md = tio->md;
	struct dm_target *ti = md->immutable_target;

	/*
	 * blk-mq's unquiesce may come from outside events, such as
	 * elevator switch, updating nr_requests or others, and request may
	 * come during suspend, so simply ask for blk-mq to requeue it.
	 */
	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)))
		return BLK_STS_RESOURCE;

	if (unlikely(!ti)) {
		int srcu_idx;
		struct dm_table *map;

		map = dm_get_live_table(md, &srcu_idx);
		if (unlikely(!map)) {
			dm_put_live_table(md, srcu_idx);
			return BLK_STS_RESOURCE;
		}
		ti = dm_table_find_target(map, 0);
		dm_put_live_table(md, srcu_idx);
	}

	if (ti->type->busy && ti->type->busy(ti))
		return BLK_STS_RESOURCE;

	dm_start_request(md, rq);

	/* Init tio using md established in .init_request */
	init_tio(tio, rq, md);

	/*
	 * Establish tio->ti before calling map_request().
	 */
	tio->ti = ti;

	/* Direct call is fine since .queue_rq allows allocations */
	if (map_request(tio) == DM_MAPIO_REQUEUE) {
		/* Undo dm_start_request() before requeuing */
		rq_end_stats(md, rq);
		rq_completed(md);
		return BLK_STS_RESOURCE;
	}

	return BLK_STS_OK;
}

static const struct blk_mq_ops dm_mq_ops = {
	.queue_rq = dm_mq_queue_rq,
	.complete = dm_softirq_done,
	.init_request = dm_mq_init_request,
};

int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
{
	struct dm_target *immutable_tgt;
	int err;

	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
	if (!md->tag_set)
		return -ENOMEM;

	md->tag_set->ops = &dm_mq_ops;
	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
	md->tag_set->numa_node = md->numa_node_id;
	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING;
	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
	md->tag_set->driver_data = md;

	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
	immutable_tgt = dm_table_get_immutable_target(t);
	if (immutable_tgt && immutable_tgt->per_io_data_size) {
		/* any target-specific per-io data is immediately after the tio */
		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
		md->init_tio_pdu = true;
	}

	err = blk_mq_alloc_tag_set(md->tag_set);
	if (err)
		goto out_kfree_tag_set;

	err = blk_mq_init_allocated_queue(md->tag_set, md->queue);
	if (err)
		goto out_tag_set;
	return 0;

out_tag_set:
	blk_mq_free_tag_set(md->tag_set);
out_kfree_tag_set:
	kfree(md->tag_set);
	md->tag_set = NULL;

	return err;
}

void dm_mq_cleanup_mapped_device(struct mapped_device *md)
{
	if (md->tag_set) {
		blk_mq_free_tag_set(md->tag_set);
		kfree(md->tag_set);
		md->tag_set = NULL;
	}
}

module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");

/* Unused, but preserved for userspace compatibility */
static bool use_blk_mq = true;
module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");

module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");

module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");