summaryrefslogtreecommitdiffstats
path: root/kernel/block/blk-tag.c
blob: f0344e6939d537ecaac05c21a0542c46d37d2808 (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
/*
 * Functions related to tagged command queuing
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/slab.h>

#include "blk.h"

/**
 * blk_queue_find_tag - find a request by its tag and queue
 * @q:	 The request queue for the device
 * @tag: The tag of the request
 *
 * Notes:
 *    Should be used when a device returns a tag and you want to match
 *    it with a request.
 *
 *    no locks need be held.
 **/
struct request *blk_queue_find_tag(struct request_queue *q, int tag)
{
	return blk_map_queue_find_tag(q->queue_tags, tag);
}
EXPORT_SYMBOL(blk_queue_find_tag);

/**
 * blk_free_tags - release a given set of tag maintenance info
 * @bqt:	the tag map to free
 *
 * Drop the reference count on @bqt and frees it when the last reference
 * is dropped.
 */
void blk_free_tags(struct blk_queue_tag *bqt)
{
	if (atomic_dec_and_test(&bqt->refcnt)) {
		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
							bqt->max_depth);

		kfree(bqt->tag_index);
		bqt->tag_index = NULL;

		kfree(bqt->tag_map);
		bqt->tag_map = NULL;

		kfree(bqt);
	}
}
EXPORT_SYMBOL(blk_free_tags);

/**
 * __blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *    blk_cleanup_queue() will take care of calling this function, if tagging
 *    has been used. So there's no need to call this directly.
 **/
void __blk_queue_free_tags(struct request_queue *q)
{
	struct blk_queue_tag *bqt = q->queue_tags;

	if (!bqt)
		return;

	blk_free_tags(bqt);

	q->queue_tags = NULL;
	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
}

/**
 * blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *	This is used to disable tagged queuing to a device, yet leave
 *	queue in function.
 **/
void blk_queue_free_tags(struct request_queue *q)
{
	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
}
EXPORT_SYMBOL(blk_queue_free_tags);

static int
init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
{
	struct request **tag_index;
	unsigned long *tag_map;
	int nr_ulongs;

	if (q && depth > q->nr_requests * 2) {
		depth = q->nr_requests * 2;
		printk(KERN_ERR "%s: adjusted depth to %d\n",
		       __func__, depth);
	}

	tag_index = kzalloc(depth * sizeof(struct request *), GFP_ATOMIC);
	if (!tag_index)
		goto fail;

	nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
	tag_map = kzalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
	if (!tag_map)
		goto fail;

	tags->real_max_depth = depth;
	tags->max_depth = depth;
	tags->tag_index = tag_index;
	tags->tag_map = tag_map;

	return 0;
fail:
	kfree(tag_index);
	return -ENOMEM;
}

static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
						int depth, int alloc_policy)
{
	struct blk_queue_tag *tags;

	tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
	if (!tags)
		goto fail;

	if (init_tag_map(q, tags, depth))
		goto fail;

	atomic_set(&tags->refcnt, 1);
	tags->alloc_policy = alloc_policy;
	tags->next_tag = 0;
	return tags;
fail:
	kfree(tags);
	return NULL;
}

/**
 * blk_init_tags - initialize the tag info for an external tag map
 * @depth:	the maximum queue depth supported
 * @alloc_policy: tag allocation policy
 **/
struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy)
{
	return __blk_queue_init_tags(NULL, depth, alloc_policy);
}
EXPORT_SYMBOL(blk_init_tags);

/**
 * blk_queue_init_tags - initialize the queue tag info
 * @q:  the request queue for the device
 * @depth:  the maximum queue depth supported
 * @tags: the tag to use
 * @alloc_policy: tag allocation policy
 *
 * Queue lock must be held here if the function is called to resize an
 * existing map.
 **/
int blk_queue_init_tags(struct request_queue *q, int depth,
			struct blk_queue_tag *tags, int alloc_policy)
{
	int rc;

	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);

	if (!tags && !q->queue_tags) {
		tags = __blk_queue_init_tags(q, depth, alloc_policy);

		if (!tags)
			return -ENOMEM;

	} else if (q->queue_tags) {
		rc = blk_queue_resize_tags(q, depth);
		if (rc)
			return rc;
		queue_flag_set(QUEUE_FLAG_QUEUED, q);
		return 0;
	} else
		atomic_inc(&tags->refcnt);

	/*
	 * assign it, all done
	 */
	q->queue_tags = tags;
	queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
	INIT_LIST_HEAD(&q->tag_busy_list);
	return 0;
}
EXPORT_SYMBOL(blk_queue_init_tags);

/**
 * blk_queue_resize_tags - change the queueing depth
 * @q:  the request queue for the device
 * @new_depth: the new max command queueing depth
 *
 *  Notes:
 *    Must be called with the queue lock held.
 **/
int blk_queue_resize_tags(struct request_queue *q, int new_depth)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	struct request **tag_index;
	unsigned long *tag_map;
	int max_depth, nr_ulongs;

	if (!bqt)
		return -ENXIO;

	/*
	 * if we already have large enough real_max_depth.  just
	 * adjust max_depth.  *NOTE* as requests with tag value
	 * between new_depth and real_max_depth can be in-flight, tag
	 * map can not be shrunk blindly here.
	 */
	if (new_depth <= bqt->real_max_depth) {
		bqt->max_depth = new_depth;
		return 0;
	}

	/*
	 * Currently cannot replace a shared tag map with a new
	 * one, so error out if this is the case
	 */
	if (atomic_read(&bqt->refcnt) != 1)
		return -EBUSY;

	/*
	 * save the old state info, so we can copy it back
	 */
	tag_index = bqt->tag_index;
	tag_map = bqt->tag_map;
	max_depth = bqt->real_max_depth;

	if (init_tag_map(q, bqt, new_depth))
		return -ENOMEM;

	memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
	nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
	memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));

	kfree(tag_index);
	kfree(tag_map);
	return 0;
}
EXPORT_SYMBOL(blk_queue_resize_tags);

/**
 * blk_queue_end_tag - end tag operations for a request
 * @q:  the request queue for the device
 * @rq: the request that has completed
 *
 *  Description:
 *    Typically called when end_that_request_first() returns %0, meaning
 *    all transfers have been done for a request. It's important to call
 *    this function before end_that_request_last(), as that will put the
 *    request back on the free list thus corrupting the internal tag list.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	unsigned tag = rq->tag; /* negative tags invalid */

	BUG_ON(tag >= bqt->real_max_depth);

	list_del_init(&rq->queuelist);
	rq->cmd_flags &= ~REQ_QUEUED;
	rq->tag = -1;

	if (unlikely(bqt->tag_index[tag] == NULL))
		printk(KERN_ERR "%s: tag %d is missing\n",
		       __func__, tag);

	bqt->tag_index[tag] = NULL;

	if (unlikely(!test_bit(tag, bqt->tag_map))) {
		printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
		       __func__, tag);
		return;
	}
	/*
	 * The tag_map bit acts as a lock for tag_index[bit], so we need
	 * unlock memory barrier semantics.
	 */
	clear_bit_unlock(tag, bqt->tag_map);
}
EXPORT_SYMBOL(blk_queue_end_tag);

/**
 * blk_queue_start_tag - find a free tag and assign it
 * @q:  the request queue for the device
 * @rq:  the block request that needs tagging
 *
 *  Description:
 *    This can either be used as a stand-alone helper, or possibly be
 *    assigned as the queue &prep_rq_fn (in which case &struct request
 *    automagically gets a tag assigned). Note that this function
 *    assumes that any type of request can be queued! if this is not
 *    true for your device, you must check the request type before
 *    calling this function.  The request will also be removed from
 *    the request queue, so it's the drivers responsibility to readd
 *    it if it should need to be restarted for some reason.
 *
 *  Notes:
 *   queue lock must be held.
 **/
int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	unsigned max_depth;
	int tag;

	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
		printk(KERN_ERR
		       "%s: request %p for device [%s] already tagged %d",
		       __func__, rq,
		       rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
		BUG();
	}

	/*
	 * Protect against shared tag maps, as we may not have exclusive
	 * access to the tag map.
	 *
	 * We reserve a few tags just for sync IO, since we don't want
	 * to starve sync IO on behalf of flooding async IO.
	 */
	max_depth = bqt->max_depth;
	if (!rq_is_sync(rq) && max_depth > 1) {
		switch (max_depth) {
		case 2:
			max_depth = 1;
			break;
		case 3:
			max_depth = 2;
			break;
		default:
			max_depth -= 2;
		}
		if (q->in_flight[BLK_RW_ASYNC] > max_depth)
			return 1;
	}

	do {
		if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) {
			tag = find_first_zero_bit(bqt->tag_map, max_depth);
			if (tag >= max_depth)
				return 1;
		} else {
			int start = bqt->next_tag;
			int size = min_t(int, bqt->max_depth, max_depth + start);
			tag = find_next_zero_bit(bqt->tag_map, size, start);
			if (tag >= size && start + size > bqt->max_depth) {
				size = start + size - bqt->max_depth;
				tag = find_first_zero_bit(bqt->tag_map, size);
			}
			if (tag >= size)
				return 1;
		}

	} while (test_and_set_bit_lock(tag, bqt->tag_map));
	/*
	 * We need lock ordering semantics given by test_and_set_bit_lock.
	 * See blk_queue_end_tag for details.
	 */

	bqt->next_tag = (tag + 1) % bqt->max_depth;
	rq->cmd_flags |= REQ_QUEUED;
	rq->tag = tag;
	bqt->tag_index[tag] = rq;
	blk_start_request(rq);
	list_add(&rq->queuelist, &q->tag_busy_list);
	return 0;
}
EXPORT_SYMBOL(blk_queue_start_tag);

/**
 * blk_queue_invalidate_tags - invalidate all pending tags
 * @q:  the request queue for the device
 *
 *  Description:
 *   Hardware conditions may dictate a need to stop all pending requests.
 *   In this case, we will safely clear the block side of the tag queue and
 *   readd all requests to the request queue in the right order.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_invalidate_tags(struct request_queue *q)
{
	struct list_head *tmp, *n;

	list_for_each_safe(tmp, n, &q->tag_busy_list)
		blk_requeue_request(q, list_entry_rq(tmp));
}
EXPORT_SYMBOL(blk_queue_invalidate_tags);