aboutsummaryrefslogtreecommitdiffstats
blob: 001ab18078f5ba1b8c6f34e021cc02ef401d98b6 (plain) (blame)
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
/*
 * Functions related to sysfs handling
 */
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blktrace_api.h>

#include "blk.h"

struct queue_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct request_queue *, char *);
	ssize_t (*store)(struct request_queue *, const char *, size_t);
};

static ssize_t
queue_var_show(unsigned long var, char *page)
{
	return sprintf(page, "%lu\n", var);
}

static ssize_t
queue_var_store(unsigned long *var, const char *page, size_t count)
{
	char *p = (char *) page;

	*var = simple_strtoul(p, &p, 10);
	return count;
}

static ssize_t queue_requests_show(struct request_queue *q, char *page)
{
	return queue_var_show(q->nr_requests, (page));
}

static ssize_t
queue_requests_store(struct request_queue *q, const char *page, size_t count)
{
	struct request_list *rl = &q->rq;
	unsigned long nr;
	int ret;

	if (!q->request_fn)
		return -EINVAL;

	ret = queue_var_store(&nr, page, count);
	if (nr < BLKDEV_MIN_RQ)
		nr = BLKDEV_MIN_RQ;

	spin_lock_irq(q->queue_lock);
	q->nr_requests = nr;
	blk_queue_congestion_threshold(q);

	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
		blk_set_queue_congested(q, BLK_RW_SYNC);
	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
		blk_clear_queue_congested(q, BLK_RW_SYNC);

	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
		blk_set_queue_congested(q, BLK_RW_ASYNC);
	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
		blk_clear_queue_congested(q, BLK_RW_ASYNC);

	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
		blk_set_queue_full(q, BLK_RW_SYNC);
	} else if (rl->count[BLK_RW_SYNC]+1 <= q->nr_requests) {
		blk_clear_queue_full(q, BLK_RW_SYNC);
		wake_up(&rl->wait[BLK_RW_SYNC]);
	}

	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
		blk_set_queue_full(q, BLK_RW_ASYNC);
	} else if (rl->count[BLK_RW_ASYNC]+1 <= q->nr_requests) {
		blk_clear_queue_full(q, BLK_RW_ASYNC);
		wake_up(&rl->wait[BLK_RW_ASYNC]);
	}
	spin_unlock_irq(q->queue_lock);
	return ret;
}

static ssize_t queue_ra_show(struct request_queue *q, char *page)
{
	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
					(PAGE_CACHE_SHIFT - 10);

	return queue_var_show(ra_kb, (page));
}

static ssize_t
queue_ra_store(struct request_queue *q, const char *page, size_t count)
{
	unsigned long ra_kb;
	ssize_t ret = queue_var_store(&ra_kb, page, count);

	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);

	return ret;
}

static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
{
	int max_sectors_kb = queue_max_sectors(q) >> 1;

	return queue_var_show(max_sectors_kb, (page));
}

static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_max_segments(q), (page));
}

static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
{
	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
		return queue_var_show(queue_max_segment_size(q), (page));

	return queue_var_show(PAGE_CACHE_SIZE, (page));
}

static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_logical_block_size(q), page);
}

static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_physical_block_size(q), page);
}

static ssize_t queue_io_min_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_io_min(q), page);
}

static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_io_opt(q), page);
}

static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
{
	return queue_var_show(q->limits.discard_granularity, page);
}

static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
{
	return queue_var_show(q->limits.max_discard_sectors << 9, page);
}

static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
{
	return queue_var_show(queue_discard_zeroes_data(q), page);
}

static ssize_t
queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
{
	unsigned long max_sectors_kb,
		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);

	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
		return -EINVAL;

	spin_lock_irq(q->queue_lock);
	q->limits.max_sectors = max_sectors_kb << 1;
	spin_unlock_irq(q->queue_lock);

	return ret;
}

static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
{
	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;

	return queue_var_show(max_hw_sectors_kb, (page));
}

#define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
static ssize_t								\
queue_show_##name(struct request_queue *q, char *page)			\
{									\
	int bit;							\
	bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags);		\
	return queue_var_show(neg ? !bit : bit, page);			\
}									\
static ssize_t								\
queue_store_##name(struct request_queue *q, const char *page, size_t count) \
{									\
	unsigned long val;						\
	ssize_t ret;							\
	ret = queue_var_store(&val, page, count);			\
	if (neg)							\
		val = !val;						\
									\
	spin_lock_irq(q->queue_lock);					\
	if (val)							\
		queue_flag_set(QUEUE_FLAG_##flag, q);			\
	else								\
		queue_flag_clear(QUEUE_FLAG_##flag, q);			\
	spin_unlock_irq(q->queue_lock);					\
	return ret;							\
}

QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
#undef QUEUE_SYSFS_BIT_FNS

static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
{
	return queue_var_show((blk_queue_nomerges(q) << 1) |
			       blk_queue_noxmerges(q), page);
}

static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
				    size_t count)
{
	unsigned long nm;
	ssize_t ret = queue_var_store(&nm, page, count);

	spin_lock_irq(q->queue_lock);
	queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
	queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
	if (nm == 2)
		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
	else if (nm)
		queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
	spin_unlock_irq(q->queue_lock);

	return ret;
}

static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
{
	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);

	return queue_var_show(set, page);
}

static ssize_t
queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
{
	ssize_t ret = -EINVAL;
#if defined(CONFIG_USE_GENERIC_SMP_HELPERS)
	unsigned long val;

	ret = queue_var_store(&val, page, count);
	spin_lock_irq(q->queue_lock);
	if (val)
		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
	else
		queue_flag_clear(QUEUE_FLAG_SAME_COMP,  q);
	spin_unlock_irq(q->queue_lock);
#endif
	return ret;
}

static struct queue_sysfs_entry queue_requests_entry = {
	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
	.show = queue_requests_show,
	.store = queue_requests_store,
};

static struct queue_sysfs_entry queue_ra_entry = {
	.attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
	.show = queue_ra_show,
	.store = queue_ra_store,
};

static struct queue_sysfs_entry queue_max_sectors_entry = {
	.attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
	.show = queue_max_sectors_show,
	.store = queue_max_sectors_store,
};

static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
	.attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO },
	.show = queue_max_hw_sectors_show,
};

static struct queue_sysfs_entry queue_max_segments_entry = {
	.attr = {.name = "max_segments", .mode = S_IRUGO },
	.show = queue_max_segments_show,
};

static struct queue_sysfs_entry queue_max_segment_size_entry = {
	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
	.show = queue_max_segment_size_show,
};

static struct queue_sysfs_entry queue_iosched_entry = {
	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
	.show = elv_iosched_show,
	.store = elv_iosched_store,
};

static struct queue_sysfs_entry queue_hw_sector_size_entry = {
	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
	.show = queue_logical_block_size_show,
};

static struct queue_sysfs_entry queue_logical_block_size_entry = {
	.attr = {.name = "logical_block_size", .mode = S_IRUGO },
	.show = queue_logical_block_size_show,
};

static struct queue_sysfs_entry queue_physical_block_size_entry = {
	.attr = {.name = "physical_block_size", .mode = S_IRUGO },
	.show = queue_physical_block_size_show,
};

static struct queue_sysfs_entry queue_io_min_entry = {
	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
	.show = queue_io_min_show,
};

static struct queue_sysfs_entry queue_io_opt_entry = {
	.attr = {.name = "optimal_io_size", .mode = S_IRUGO },
	.show = queue_io_opt_show,
};

static struct queue_sysfs_entry queue_discard_granularity_entry = {
	.attr = {.name = "discard_granularity", .mode = S_IRUGO },
	.show = queue_discard_granularity_show,
};

static struct queue_sysfs_entry queue_discard_max_entry = {
	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
	.show = queue_discard_max_show,
};

static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
	.attr = {.name = "discard_zeroes_data", .mode = S_IRUGO },
	.show = queue_discard_zeroes_data_show,
};

static struct queue_sysfs_entry queue_nonrot_entry = {
	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
	.show = queue_show_nonrot,
	.store = queue_store_nonrot,
};

static struct queue_sysfs_entry queue_nomerges_entry = {
	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
	.show = queue_nomerges_show,
	.store = queue_nomerges_store,
};

static struct queue_sysfs_entry queue_rq_affinity_entry = {
	.attr = {.name = "rq_affinity", .mode = S_IRUGO | S_IWUSR },
	.show = queue_rq_affinity_show,
	.store = queue_rq_affinity_store,
};

static struct queue_sysfs_entry queue_iostats_entry = {
	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
	.show = queue_show_iostats,
	.store = queue_store_iostats,
};

static struct queue_sysfs_entry queue_random_entry = {
	.attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR },
	.show = queue_show_random,
	.store = queue_store_random,
};

static struct attribute *default_attrs[] = {
	&queue_requests_entry.attr,
	&queue_ra_entry.attr,
	&queue_max_hw_sectors_entry.attr,
	&queue_max_sectors_entry.attr,
	&queue_max_segments_entry.attr,
	&queue_max_segment_size_entry.attr,
	&queue_iosched_entry.attr,
	&queue_hw_sector_size_entry.attr,
	&queue_logical_block_size_entry.attr,
	&queue_physical_block_size_entry.attr,
	&queue_io_min_entry.attr,
	&queue_io_opt_entry.attr,
	&queue_discard_granularity_entry.attr,
	&queue_discard_max_entry.attr,
	&queue_discard_zeroes_data_entry.attr,
	&queue_nonrot_entry.attr,
	&queue_nomerges_entry.attr,
	&queue_rq_affinity_entry.attr,
	&queue_iostats_entry.attr,
	&queue_random_entry.attr,
	NULL,
};

#define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)

static ssize_t
queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct queue_sysfs_entry *entry = to_queue(attr);
	struct request_queue *q =
		container_of(kobj, struct request_queue, kobj);
	ssize_t res;

	if (!entry->show)
		return -EIO;
	mutex_lock(&q->sysfs_lock);
	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
		mutex_unlock(&q->sysfs_lock);
		return -ENOENT;
	}
	res = entry->show(q, page);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t
queue_attr_store(struct kobject *kobj, struct attribute *attr,
		    const char *page, size_t length)
{
	struct queue_sysfs_entry *entry = to_queue(attr);
	struct request_queue *q;
	ssize_t res;

	if (!entry->store)
		return -EIO;

	q = container_of(kobj, struct request_queue, kobj);
	mutex_lock(&q->sysfs_lock);
	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
		mutex_unlock(&q->sysfs_lock);
		return -ENOENT;
	}
	res = entry->store(q, page, length);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

/**
 * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed
 * @kobj:    the kobj belonging of the request queue to be released
 *
 * Description:
 *     blk_cleanup_queue is the pair to blk_init_queue() or
 *     blk_queue_make_request().  It should be called when a request queue is
 *     being released; typically when a block device is being de-registered.
 *     Currently, its primary task it to free all the &struct request
 *     structures that were allocated to the queue and the queue itself.
 *
 * Caveat:
 *     Hopefully the low level driver will have finished any
 *     outstanding requests first...
 **/
static void blk_release_queue(struct kobject *kobj)
{
	struct request_queue *q =
		container_of(kobj, struct request_queue, kobj);
	struct request_list *rl = &q->rq;

	blk_sync_queue(q);

	if (rl->rq_pool)
		mempool_destroy(rl->rq_pool);

	if (q->queue_tags)
		__blk_queue_free_tags(q);

	blk_trace_shutdown(q);

	bdi_destroy(&q->backing_dev_info);
	kmem_cache_free(blk_requestq_cachep, q);
}

static const struct sysfs_ops queue_sysfs_ops = {
	.show	= queue_attr_show,
	.store	= queue_attr_store,
};

struct kobj_type blk_queue_ktype = {
	.sysfs_ops	= &queue_sysfs_ops,
	.default_attrs	= default_attrs,
	.release	= blk_release_queue,
};

int blk_register_queue(struct gendisk *disk)
{
	int ret;
	struct device *dev = disk_to_dev(disk);

	struct request_queue *q = disk->queue;

	if (WARN_ON(!q))
		return -ENXIO;

	ret = blk_trace_init_sysfs(dev);
	if (ret)
		return ret;

	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
	if (ret < 0)
		return ret;

	kobject_uevent(&q->kobj, KOBJ_ADD);

	if (!q->request_fn)
		return 0;

	ret = elv_register_queue(q);
	if (ret) {
		kobject_uevent(&q->kobj, KOBJ_REMOVE);
		kobject_del(&q->kobj);
		blk_trace_remove_sysfs(disk_to_dev(disk));
		return ret;
	}

	return 0;
}

void blk_unregister_queue(struct gendisk *disk)
{
	struct request_queue *q = disk->queue;

	if (WARN_ON(!q))
		return;

	if (q->request_fn)
		elv_unregister_queue(q);

	kobject_uevent(&q->kobj, KOBJ_REMOVE);
	kobject_del(&q->kobj);
	blk_trace_remove_sysfs(disk_to_dev(disk));
	kobject_put(&disk_to_dev(disk)->kobj);
}