aboutsummaryrefslogtreecommitdiffstats
path: root/block/blk-mq-tag.c
blob: cded7fdcad8ef38e2df09a67d87f5a0fbbef0385 (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
597
598
599
600
601
602
// SPDX-License-Identifier: GPL-2.0
/*
 * Tag allocation using scalable bitmaps. Uses active queue tracking to support
 * fairer distribution of tags between multiple submitters when a shared tag map
 * is used.
 *
 * Copyright (C) 2013-2014 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/module.h>

#include <linux/blk-mq.h>
#include <linux/delay.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"

/*
 * If a previously inactive queue goes active, bump the active user count.
 * We need to do this before try to allocate driver tag, then even if fail
 * to get tag when first time, the other shared-tag users could reserve
 * budget for it.
 */
bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
	    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
		atomic_inc(&hctx->tags->active_queues);

	return true;
}

/*
 * Wakeup all potentially sleeping on tags
 */
void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
{
	sbitmap_queue_wake_all(&tags->bitmap_tags);
	if (include_reserve)
		sbitmap_queue_wake_all(&tags->breserved_tags);
}

/*
 * If a previously busy queue goes inactive, potential waiters could now
 * be allowed to queue. Wake them up and check.
 */
void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
	struct blk_mq_tags *tags = hctx->tags;

	if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
		return;

	atomic_dec(&tags->active_queues);

	blk_mq_tag_wakeup_all(tags, false);
}

/*
 * For shared tag users, we track the number of currently active users
 * and attempt to provide a fair share of the tag depth for each of them.
 */
static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
				  struct sbitmap_queue *bt)
{
	unsigned int depth, users;

	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED))
		return true;
	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
		return true;

	/*
	 * Don't try dividing an ant
	 */
	if (bt->sb.depth == 1)
		return true;

	users = atomic_read(&hctx->tags->active_queues);
	if (!users)
		return true;

	/*
	 * Allow at least some tags
	 */
	depth = max((bt->sb.depth + users - 1) / users, 4U);
	return atomic_read(&hctx->nr_active) < depth;
}

static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
			    struct sbitmap_queue *bt)
{
	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
	    !hctx_may_queue(data->hctx, bt))
		return BLK_MQ_NO_TAG;
	if (data->shallow_depth)
		return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
	else
		return __sbitmap_queue_get(bt);
}

unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
{
	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
	struct sbitmap_queue *bt;
	struct sbq_wait_state *ws;
	DEFINE_SBQ_WAIT(wait);
	unsigned int tag_offset;
	int tag;

	if (data->flags & BLK_MQ_REQ_RESERVED) {
		if (unlikely(!tags->nr_reserved_tags)) {
			WARN_ON_ONCE(1);
			return BLK_MQ_NO_TAG;
		}
		bt = &tags->breserved_tags;
		tag_offset = 0;
	} else {
		bt = &tags->bitmap_tags;
		tag_offset = tags->nr_reserved_tags;
	}

	tag = __blk_mq_get_tag(data, bt);
	if (tag != BLK_MQ_NO_TAG)
		goto found_tag;

	if (data->flags & BLK_MQ_REQ_NOWAIT)
		return BLK_MQ_NO_TAG;

	ws = bt_wait_ptr(bt, data->hctx);
	do {
		struct sbitmap_queue *bt_prev;

		/*
		 * We're out of tags on this hardware queue, kick any
		 * pending IO submits before going to sleep waiting for
		 * some to complete.
		 */
		blk_mq_run_hw_queue(data->hctx, false);

		/*
		 * Retry tag allocation after running the hardware queue,
		 * as running the queue may also have found completions.
		 */
		tag = __blk_mq_get_tag(data, bt);
		if (tag != BLK_MQ_NO_TAG)
			break;

		sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE);

		tag = __blk_mq_get_tag(data, bt);
		if (tag != BLK_MQ_NO_TAG)
			break;

		bt_prev = bt;
		io_schedule();

		sbitmap_finish_wait(bt, ws, &wait);

		data->ctx = blk_mq_get_ctx(data->q);
		data->hctx = blk_mq_map_queue(data->q, data->cmd_flags,
						data->ctx);
		tags = blk_mq_tags_from_data(data);
		if (data->flags & BLK_MQ_REQ_RESERVED)
			bt = &tags->breserved_tags;
		else
			bt = &tags->bitmap_tags;

		/*
		 * If destination hw queue is changed, fake wake up on
		 * previous queue for compensating the wake up miss, so
		 * other allocations on previous queue won't be starved.
		 */
		if (bt != bt_prev)
			sbitmap_queue_wake_up(bt_prev);

		ws = bt_wait_ptr(bt, data->hctx);
	} while (1);

	sbitmap_finish_wait(bt, ws, &wait);

found_tag:
	/*
	 * Give up this allocation if the hctx is inactive.  The caller will
	 * retry on an active hctx.
	 */
	if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) {
		blk_mq_put_tag(tags, data->ctx, tag + tag_offset);
		return BLK_MQ_NO_TAG;
	}
	return tag + tag_offset;
}

bool __blk_mq_get_driver_tag(struct request *rq)
{
	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
	bool shared = blk_mq_tag_busy(rq->mq_hctx);
	int tag;

	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
		bt = &rq->mq_hctx->tags->breserved_tags;
		tag_offset = 0;
	}

	if (!hctx_may_queue(rq->mq_hctx, bt))
		return false;
	tag = __sbitmap_queue_get(bt);
	if (tag == BLK_MQ_NO_TAG)
		return false;

	rq->tag = tag + tag_offset;
	if (shared) {
		rq->rq_flags |= RQF_MQ_INFLIGHT;
		atomic_inc(&rq->mq_hctx->nr_active);
	}
	rq->mq_hctx->tags->rqs[rq->tag] = rq;
	return true;
}

void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
		    unsigned int tag)
{
	if (!blk_mq_tag_is_reserved(tags, tag)) {
		const int real_tag = tag - tags->nr_reserved_tags;

		BUG_ON(real_tag >= tags->nr_tags);
		sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu);
	} else {
		BUG_ON(tag >= tags->nr_reserved_tags);
		sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu);
	}
}

struct bt_iter_data {
	struct blk_mq_hw_ctx *hctx;
	busy_iter_fn *fn;
	void *data;
	bool reserved;
};

static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
{
	struct bt_iter_data *iter_data = data;
	struct blk_mq_hw_ctx *hctx = iter_data->hctx;
	struct blk_mq_tags *tags = hctx->tags;
	bool reserved = iter_data->reserved;
	struct request *rq;

	if (!reserved)
		bitnr += tags->nr_reserved_tags;
	rq = tags->rqs[bitnr];

	/*
	 * We can hit rq == NULL here, because the tagging functions
	 * test and set the bit before assigning ->rqs[].
	 */
	if (rq && rq->q == hctx->queue)
		return iter_data->fn(hctx, rq, iter_data->data, reserved);
	return true;
}

/**
 * bt_for_each - iterate over the requests associated with a hardware queue
 * @hctx:	Hardware queue to examine.
 * @bt:		sbitmap to examine. This is either the breserved_tags member
 *		or the bitmap_tags member of struct blk_mq_tags.
 * @fn:		Pointer to the function that will be called for each request
 *		associated with @hctx that has been assigned a driver tag.
 *		@fn will be called as follows: @fn(@hctx, rq, @data, @reserved)
 *		where rq is a pointer to a request. Return true to continue
 *		iterating tags, false to stop.
 * @data:	Will be passed as third argument to @fn.
 * @reserved:	Indicates whether @bt is the breserved_tags member or the
 *		bitmap_tags member of struct blk_mq_tags.
 */
static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt,
			busy_iter_fn *fn, void *data, bool reserved)
{
	struct bt_iter_data iter_data = {
		.hctx = hctx,
		.fn = fn,
		.data = data,
		.reserved = reserved,
	};

	sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data);
}

struct bt_tags_iter_data {
	struct blk_mq_tags *tags;
	busy_tag_iter_fn *fn;
	void *data;
	unsigned int flags;
};

#define BT_TAG_ITER_RESERVED		(1 << 0)
#define BT_TAG_ITER_STARTED		(1 << 1)

static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
{
	struct bt_tags_iter_data *iter_data = data;
	struct blk_mq_tags *tags = iter_data->tags;
	bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED;
	struct request *rq;

	if (!reserved)
		bitnr += tags->nr_reserved_tags;

	/*
	 * We can hit rq == NULL here, because the tagging functions
	 * test and set the bit before assining ->rqs[].
	 */
	rq = tags->rqs[bitnr];
	if (!rq)
		return true;
	if ((iter_data->flags & BT_TAG_ITER_STARTED) &&
	    !blk_mq_request_started(rq))
		return true;
	return iter_data->fn(rq, iter_data->data, reserved);
}

/**
 * bt_tags_for_each - iterate over the requests in a tag map
 * @tags:	Tag map to iterate over.
 * @bt:		sbitmap to examine. This is either the breserved_tags member
 *		or the bitmap_tags member of struct blk_mq_tags.
 * @fn:		Pointer to the function that will be called for each started
 *		request. @fn will be called as follows: @fn(rq, @data,
 *		@reserved) where rq is a pointer to a request. Return true
 *		to continue iterating tags, false to stop.
 * @data:	Will be passed as second argument to @fn.
 * @flags:	BT_TAG_ITER_*
 */
static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt,
			     busy_tag_iter_fn *fn, void *data, unsigned int flags)
{
	struct bt_tags_iter_data iter_data = {
		.tags = tags,
		.fn = fn,
		.data = data,
		.flags = flags,
	};

	if (tags->rqs)
		sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data);
}

static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags,
		busy_tag_iter_fn *fn, void *priv, unsigned int flags)
{
	WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED);

	if (tags->nr_reserved_tags)
		bt_tags_for_each(tags, &tags->breserved_tags, fn, priv,
				 flags | BT_TAG_ITER_RESERVED);
	bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags);
}

/**
 * blk_mq_all_tag_iter - iterate over all requests in a tag map
 * @tags:	Tag map to iterate over.
 * @fn:		Pointer to the function that will be called for each
 *		request. @fn will be called as follows: @fn(rq, @priv,
 *		reserved) where rq is a pointer to a request. 'reserved'
 *		indicates whether or not @rq is a reserved request. Return
 *		true to continue iterating tags, false to stop.
 * @priv:	Will be passed as second argument to @fn.
 */
void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
		void *priv)
{
	return __blk_mq_all_tag_iter(tags, fn, priv, 0);
}

/**
 * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set
 * @tagset:	Tag set to iterate over.
 * @fn:		Pointer to the function that will be called for each started
 *		request. @fn will be called as follows: @fn(rq, @priv,
 *		reserved) where rq is a pointer to a request. 'reserved'
 *		indicates whether or not @rq is a reserved request. Return
 *		true to continue iterating tags, false to stop.
 * @priv:	Will be passed as second argument to @fn.
 */
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
		busy_tag_iter_fn *fn, void *priv)
{
	int i;

	for (i = 0; i < tagset->nr_hw_queues; i++) {
		if (tagset->tags && tagset->tags[i])
			__blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
					      BT_TAG_ITER_STARTED);
	}
}
EXPORT_SYMBOL(blk_mq_tagset_busy_iter);

static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
		void *data, bool reserved)
{
	unsigned *count = data;

	if (blk_mq_request_completed(rq))
		(*count)++;
	return true;
}

/**
 * blk_mq_tagset_wait_completed_request - wait until all completed req's
 * complete funtion is run
 * @tagset:	Tag set to drain completed request
 *
 * Note: This function has to be run after all IO queues are shutdown
 */
void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset)
{
	while (true) {
		unsigned count = 0;

		blk_mq_tagset_busy_iter(tagset,
				blk_mq_tagset_count_completed_rqs, &count);
		if (!count)
			break;
		msleep(5);
	}
}
EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);

/**
 * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag
 * @q:		Request queue to examine.
 * @fn:		Pointer to the function that will be called for each request
 *		on @q. @fn will be called as follows: @fn(hctx, rq, @priv,
 *		reserved) where rq is a pointer to a request and hctx points
 *		to the hardware queue associated with the request. 'reserved'
 *		indicates whether or not @rq is a reserved request.
 * @priv:	Will be passed as third argument to @fn.
 *
 * Note: if @q->tag_set is shared with other request queues then @fn will be
 * called for all requests on all queues that share that tag set and not only
 * for requests associated with @q.
 */
void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
		void *priv)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	/*
	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx
	 * while the queue is frozen. So we can use q_usage_counter to avoid
	 * racing with it. __blk_mq_update_nr_hw_queues() uses
	 * synchronize_rcu() to ensure this function left the critical section
	 * below.
	 */
	if (!percpu_ref_tryget(&q->q_usage_counter))
		return;

	queue_for_each_hw_ctx(q, hctx, i) {
		struct blk_mq_tags *tags = hctx->tags;

		/*
		 * If no software queues are currently mapped to this
		 * hardware queue, there's nothing to check
		 */
		if (!blk_mq_hw_queue_mapped(hctx))
			continue;

		if (tags->nr_reserved_tags)
			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
	}
	blk_queue_exit(q);
}

static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
		    bool round_robin, int node)
{
	return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL,
				       node);
}

static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
						   int node, int alloc_policy)
{
	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;

	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
		goto free_tags;
	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, round_robin,
		     node))
		goto free_bitmap_tags;

	return tags;
free_bitmap_tags:
	sbitmap_queue_free(&tags->bitmap_tags);
free_tags:
	kfree(tags);
	return NULL;
}

struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
				     unsigned int reserved_tags,
				     int node, int alloc_policy)
{
	struct blk_mq_tags *tags;

	if (total_tags > BLK_MQ_TAG_MAX) {
		pr_err("blk-mq: tag depth too large\n");
		return NULL;
	}

	tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);
	if (!tags)
		return NULL;

	tags->nr_tags = total_tags;
	tags->nr_reserved_tags = reserved_tags;

	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
}

void blk_mq_free_tags(struct blk_mq_tags *tags)
{
	sbitmap_queue_free(&tags->bitmap_tags);
	sbitmap_queue_free(&tags->breserved_tags);
	kfree(tags);
}

int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
			    struct blk_mq_tags **tagsptr, unsigned int tdepth,
			    bool can_grow)
{
	struct blk_mq_tags *tags = *tagsptr;

	if (tdepth <= tags->nr_reserved_tags)
		return -EINVAL;

	/*
	 * If we are allowed to grow beyond the original size, allocate
	 * a new set of tags before freeing the old one.
	 */
	if (tdepth > tags->nr_tags) {
		struct blk_mq_tag_set *set = hctx->queue->tag_set;
		struct blk_mq_tags *new;
		bool ret;

		if (!can_grow)
			return -EINVAL;

		/*
		 * We need some sort of upper limit, set it high enough that
		 * no valid use cases should require more.
		 */
		if (tdepth > 16 * BLKDEV_MAX_RQ)
			return -EINVAL;

		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
				tags->nr_reserved_tags);
		if (!new)
			return -ENOMEM;
		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
		if (ret) {
			blk_mq_free_rq_map(new);
			return -ENOMEM;
		}

		blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
		blk_mq_free_rq_map(*tagsptr);
		*tagsptr = new;
	} else {
		/*
		 * Don't need (or can't) update reserved tags here, they
		 * remain static and should never need resizing.
		 */
		sbitmap_queue_resize(&tags->bitmap_tags,
				tdepth - tags->nr_reserved_tags);
	}

	return 0;
}

/**
 * blk_mq_unique_tag() - return a tag that is unique queue-wide
 * @rq: request for which to compute a unique tag
 *
 * The tag field in struct request is unique per hardware queue but not over
 * all hardware queues. Hence this function that returns a tag with the
 * hardware context index in the upper bits and the per hardware queue tag in
 * the lower bits.
 *
 * Note: When called for a request that is queued on a non-multiqueue request
 * queue, the hardware context index is set to zero.
 */
u32 blk_mq_unique_tag(struct request *rq)
{
	return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) |
		(rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
}
EXPORT_SYMBOL(blk_mq_unique_tag);