summaryrefslogtreecommitdiffstats
path: root/block/mq-deadline.c
blob: a1cad4331eddc68e7f53feec21327dbd71d63eab (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
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
/*
 *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
 *  for the blk-mq scheduling framework
 *
 *  Copyright (C) 2016 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/rbtree.h>
#include <linux/sbitmap.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"

/*
 * See Documentation/block/deadline-iosched.txt
 */
static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
static const int writes_starved = 2;    /* max times reads can starve a write */
static const int fifo_batch = 16;       /* # of sequential requests treated as one
				     by the above parameters. For throughput. */

struct deadline_data {
	/*
	 * run time data
	 */

	/*
	 * requests (deadline_rq s) are present on both sort_list and fifo_list
	 */
	struct rb_root sort_list[2];
	struct list_head fifo_list[2];

	/*
	 * next in sort order. read, write or both are NULL
	 */
	struct request *next_rq[2];
	unsigned int batching;		/* number of sequential requests made */
	unsigned int starved;		/* times reads have starved writes */

	/*
	 * settings that change how the i/o scheduler behaves
	 */
	int fifo_expire[2];
	int fifo_batch;
	int writes_starved;
	int front_merges;

	spinlock_t lock;
	struct list_head dispatch;
};

static inline struct rb_root *
deadline_rb_root(struct deadline_data *dd, struct request *rq)
{
	return &dd->sort_list[rq_data_dir(rq)];
}

/*
 * get the request after `rq' in sector-sorted order
 */
static inline struct request *
deadline_latter_request(struct request *rq)
{
	struct rb_node *node = rb_next(&rq->rb_node);

	if (node)
		return rb_entry_rq(node);

	return NULL;
}

static void
deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
{
	struct rb_root *root = deadline_rb_root(dd, rq);

	elv_rb_add(root, rq);
}

static inline void
deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
{
	const int data_dir = rq_data_dir(rq);

	if (dd->next_rq[data_dir] == rq)
		dd->next_rq[data_dir] = deadline_latter_request(rq);

	elv_rb_del(deadline_rb_root(dd, rq), rq);
}

/*
 * remove rq from rbtree and fifo.
 */
static void deadline_remove_request(struct request_queue *q, struct request *rq)
{
	struct deadline_data *dd = q->elevator->elevator_data;

	list_del_init(&rq->queuelist);

	/*
	 * We might not be on the rbtree, if we are doing an insert merge
	 */
	if (!RB_EMPTY_NODE(&rq->rb_node))
		deadline_del_rq_rb(dd, rq);

	elv_rqhash_del(q, rq);
	if (q->last_merge == rq)
		q->last_merge = NULL;
}

static void dd_request_merged(struct request_queue *q, struct request *req,
			      enum elv_merge type)
{
	struct deadline_data *dd = q->elevator->elevator_data;

	/*
	 * if the merge was a front merge, we need to reposition request
	 */
	if (type == ELEVATOR_FRONT_MERGE) {
		elv_rb_del(deadline_rb_root(dd, req), req);
		deadline_add_rq_rb(dd, req);
	}
}

static void dd_merged_requests(struct request_queue *q, struct request *req,
			       struct request *next)
{
	/*
	 * if next expires before rq, assign its expire time to rq
	 * and move into next position (next will be deleted) in fifo
	 */
	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
		if (time_before((unsigned long)next->fifo_time,
				(unsigned long)req->fifo_time)) {
			list_move(&req->queuelist, &next->queuelist);
			req->fifo_time = next->fifo_time;
		}
	}

	/*
	 * kill knowledge of next, this one is a goner
	 */
	deadline_remove_request(q, next);
}

/*
 * move an entry to dispatch queue
 */
static void
deadline_move_request(struct deadline_data *dd, struct request *rq)
{
	const int data_dir = rq_data_dir(rq);

	dd->next_rq[READ] = NULL;
	dd->next_rq[WRITE] = NULL;
	dd->next_rq[data_dir] = deadline_latter_request(rq);

	/*
	 * take it off the sort and fifo list
	 */
	deadline_remove_request(rq->q, rq);
}

/*
 * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
 * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
 */
static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
{
	struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);

	/*
	 * rq is expired!
	 */
	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
		return 1;

	return 0;
}

/*
 * deadline_dispatch_requests selects the best request according to
 * read/write expire, fifo_batch, etc
 */
static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
	struct request *rq;
	bool reads, writes;
	int data_dir;

	if (!list_empty(&dd->dispatch)) {
		rq = list_first_entry(&dd->dispatch, struct request, queuelist);
		list_del_init(&rq->queuelist);
		goto done;
	}

	reads = !list_empty(&dd->fifo_list[READ]);
	writes = !list_empty(&dd->fifo_list[WRITE]);

	/*
	 * batches are currently reads XOR writes
	 */
	if (dd->next_rq[WRITE])
		rq = dd->next_rq[WRITE];
	else
		rq = dd->next_rq[READ];

	if (rq && dd->batching < dd->fifo_batch)
		/* we have a next request are still entitled to batch */
		goto dispatch_request;

	/*
	 * at this point we are not running a batch. select the appropriate
	 * data direction (read / write)
	 */

	if (reads) {
		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));

		if (writes && (dd->starved++ >= dd->writes_starved))
			goto dispatch_writes;

		data_dir = READ;

		goto dispatch_find_request;
	}

	/*
	 * there are either no reads or writes have been starved
	 */

	if (writes) {
dispatch_writes:
		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));

		dd->starved = 0;

		data_dir = WRITE;

		goto dispatch_find_request;
	}

	return NULL;

dispatch_find_request:
	/*
	 * we are not running a batch, find best request for selected data_dir
	 */
	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
		/*
		 * A deadline has expired, the last request was in the other
		 * direction, or we have run out of higher-sectored requests.
		 * Start again from the request with the earliest expiry time.
		 */
		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
	} else {
		/*
		 * The last req was the same dir and we have a next request in
		 * sort order. No expired requests so continue on from here.
		 */
		rq = dd->next_rq[data_dir];
	}

	dd->batching = 0;

dispatch_request:
	/*
	 * rq is the selected appropriate request.
	 */
	dd->batching++;
	deadline_move_request(dd, rq);
done:
	rq->rq_flags |= RQF_STARTED;
	return rq;
}

static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
	struct request *rq;

	spin_lock(&dd->lock);
	rq = __dd_dispatch_request(hctx);
	spin_unlock(&dd->lock);

	return rq;
}

static void dd_exit_queue(struct elevator_queue *e)
{
	struct deadline_data *dd = e->elevator_data;

	BUG_ON(!list_empty(&dd->fifo_list[READ]));
	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));

	kfree(dd);
}

/*
 * initialize elevator private data (deadline_data).
 */
static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
{
	struct deadline_data *dd;
	struct elevator_queue *eq;

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
	if (!dd) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}
	eq->elevator_data = dd;

	INIT_LIST_HEAD(&dd->fifo_list[READ]);
	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
	dd->sort_list[READ] = RB_ROOT;
	dd->sort_list[WRITE] = RB_ROOT;
	dd->fifo_expire[READ] = read_expire;
	dd->fifo_expire[WRITE] = write_expire;
	dd->writes_starved = writes_starved;
	dd->front_merges = 1;
	dd->fifo_batch = fifo_batch;
	spin_lock_init(&dd->lock);
	INIT_LIST_HEAD(&dd->dispatch);

	q->elevator = eq;
	return 0;
}

static int dd_request_merge(struct request_queue *q, struct request **rq,
			    struct bio *bio)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	sector_t sector = bio_end_sector(bio);
	struct request *__rq;

	if (!dd->front_merges)
		return ELEVATOR_NO_MERGE;

	__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
	if (__rq) {
		BUG_ON(sector != blk_rq_pos(__rq));

		if (elv_bio_merge_ok(__rq, bio)) {
			*rq = __rq;
			return ELEVATOR_FRONT_MERGE;
		}
	}

	return ELEVATOR_NO_MERGE;
}

static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;
	struct request *free = NULL;
	bool ret;

	spin_lock(&dd->lock);
	ret = blk_mq_sched_try_merge(q, bio, &free);
	spin_unlock(&dd->lock);

	if (free)
		blk_mq_free_request(free);

	return ret;
}

/*
 * add rq to rbtree and fifo
 */
static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			      bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;
	const int data_dir = rq_data_dir(rq);

	if (blk_mq_sched_try_insert_merge(q, rq))
		return;

	blk_mq_sched_request_inserted(rq);

	if (at_head || blk_rq_is_passthrough(rq)) {
		if (at_head)
			list_add(&rq->queuelist, &dd->dispatch);
		else
			list_add_tail(&rq->queuelist, &dd->dispatch);
	} else {
		deadline_add_rq_rb(dd, rq);

		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}

		/*
		 * set expire time and add to fifo list
		 */
		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
		list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
	}
}

static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
			       struct list_head *list, bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;

	spin_lock(&dd->lock);
	while (!list_empty(list)) {
		struct request *rq;

		rq = list_first_entry(list, struct request, queuelist);
		list_del_init(&rq->queuelist);
		dd_insert_request(hctx, rq, at_head);
	}
	spin_unlock(&dd->lock);
}

static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
{
	struct deadline_data *dd = hctx->queue->elevator->elevator_data;

	return !list_empty_careful(&dd->dispatch) ||
		!list_empty_careful(&dd->fifo_list[0]) ||
		!list_empty_careful(&dd->fifo_list[1]);
}

/*
 * sysfs parts below
 */
static ssize_t
deadline_var_show(int var, char *page)
{
	return sprintf(page, "%d\n", var);
}

static void
deadline_var_store(int *var, const char *page)
{
	char *p = (char *) page;

	*var = simple_strtol(p, &p, 10);
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct deadline_data *dd = e->elevator_data;			\
	int __data = __VAR;						\
	if (__CONV)							\
		__data = jiffies_to_msecs(__data);			\
	return deadline_var_show(__data, (page));			\
}
SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
#undef SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
{									\
	struct deadline_data *dd = e->elevator_data;			\
	int __data;							\
	deadline_var_store(&__data, (page));				\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	if (__CONV)							\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else								\
		*(__PTR) = __data;					\
	return count;							\
}
STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
#undef STORE_FUNCTION

#define DD_ATTR(name) \
	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
				      deadline_##name##_store)

static struct elv_fs_entry deadline_attrs[] = {
	DD_ATTR(read_expire),
	DD_ATTR(write_expire),
	DD_ATTR(writes_starved),
	DD_ATTR(front_merges),
	DD_ATTR(fifo_batch),
	__ATTR_NULL
};

#ifdef CONFIG_BLK_DEBUG_FS
#define DEADLINE_DEBUGFS_DDIR_ATTRS(ddir, name)				\
static void *deadline_##name##_fifo_start(struct seq_file *m,		\
					  loff_t *pos)			\
	__acquires(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
									\
	spin_lock(&dd->lock);						\
	return seq_list_start(&dd->fifo_list[ddir], *pos);		\
}									\
									\
static void *deadline_##name##_fifo_next(struct seq_file *m, void *v,	\
					 loff_t *pos)			\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
									\
	return seq_list_next(v, &dd->fifo_list[ddir], pos);		\
}									\
									\
static void deadline_##name##_fifo_stop(struct seq_file *m, void *v)	\
	__releases(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
									\
	spin_unlock(&dd->lock);						\
}									\
									\
static const struct seq_operations deadline_##name##_fifo_seq_ops = {	\
	.start	= deadline_##name##_fifo_start,				\
	.next	= deadline_##name##_fifo_next,				\
	.stop	= deadline_##name##_fifo_stop,				\
	.show	= blk_mq_debugfs_rq_show,				\
};									\
									\
static int deadline_##name##_next_rq_show(void *data,			\
					  struct seq_file *m)		\
{									\
	struct request_queue *q = data;					\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct request *rq = dd->next_rq[ddir];				\
									\
	if (rq)								\
		__blk_mq_debugfs_rq_show(m, rq);			\
	return 0;							\
}
DEADLINE_DEBUGFS_DDIR_ATTRS(READ, read)
DEADLINE_DEBUGFS_DDIR_ATTRS(WRITE, write)
#undef DEADLINE_DEBUGFS_DDIR_ATTRS

static int deadline_batching_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u\n", dd->batching);
	return 0;
}

static int deadline_starved_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u\n", dd->starved);
	return 0;
}

static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos)
	__acquires(&dd->lock)
{
	struct request_queue *q = m->private;
	struct deadline_data *dd = q->elevator->elevator_data;

	spin_lock(&dd->lock);
	return seq_list_start(&dd->dispatch, *pos);
}

static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct request_queue *q = m->private;
	struct deadline_data *dd = q->elevator->elevator_data;

	return seq_list_next(v, &dd->dispatch, pos);
}

static void deadline_dispatch_stop(struct seq_file *m, void *v)
	__releases(&dd->lock)
{
	struct request_queue *q = m->private;
	struct deadline_data *dd = q->elevator->elevator_data;

	spin_unlock(&dd->lock);
}

static const struct seq_operations deadline_dispatch_seq_ops = {
	.start	= deadline_dispatch_start,
	.next	= deadline_dispatch_next,
	.stop	= deadline_dispatch_stop,
	.show	= blk_mq_debugfs_rq_show,
};

#define DEADLINE_QUEUE_DDIR_ATTRS(name)						\
	{#name "_fifo_list", 0400, .seq_ops = &deadline_##name##_fifo_seq_ops},	\
	{#name "_next_rq", 0400, deadline_##name##_next_rq_show}
static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = {
	DEADLINE_QUEUE_DDIR_ATTRS(read),
	DEADLINE_QUEUE_DDIR_ATTRS(write),
	{"batching", 0400, deadline_batching_show},
	{"starved", 0400, deadline_starved_show},
	{"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops},
	{},
};
#undef DEADLINE_QUEUE_DDIR_ATTRS
#endif

static struct elevator_type mq_deadline = {
	.ops.mq = {
		.insert_requests	= dd_insert_requests,
		.dispatch_request	= dd_dispatch_request,
		.next_request		= elv_rb_latter_request,
		.former_request		= elv_rb_former_request,
		.bio_merge		= dd_bio_merge,
		.request_merge		= dd_request_merge,
		.requests_merged	= dd_merged_requests,
		.request_merged		= dd_request_merged,
		.has_work		= dd_has_work,
		.init_sched		= dd_init_queue,
		.exit_sched		= dd_exit_queue,
	},

	.uses_mq	= true,
#ifdef CONFIG_BLK_DEBUG_FS
	.queue_debugfs_attrs = deadline_queue_debugfs_attrs,
#endif
	.elevator_attrs = deadline_attrs,
	.elevator_name = "mq-deadline",
	.elevator_owner = THIS_MODULE,
};
MODULE_ALIAS("mq-deadline-iosched");

static int __init deadline_init(void)
{
	return elv_register(&mq_deadline);
}

static void __exit deadline_exit(void)
{
	elv_unregister(&mq_deadline);
}

module_init(deadline_init);
module_exit(deadline_exit);

MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MQ deadline IO scheduler");
OpenPOWER on IntegriCloud