aboutsummaryrefslogtreecommitdiffstats
path: root/block/blk-barrier.c
blob: 7c6f4a714687e177a14123887fce87f3a337bbec (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
/*
 * Functions related to barrier IO handling
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/gfp.h>

#include "blk.h"

/**
 * blk_queue_ordered - does this queue support ordered writes
 * @q:        the request queue
 * @ordered:  one of QUEUE_ORDERED_*
 * @prepare_flush_fn: rq setup helper for cache flush ordered writes
 *
 * Description:
 *   For journalled file systems, doing ordered writes on a commit
 *   block instead of explicitly doing wait_on_buffer (which is bad
 *   for performance) can be a big win. Block drivers supporting this
 *   feature should call this function and indicate so.
 *
 **/
int blk_queue_ordered(struct request_queue *q, unsigned ordered,
		      prepare_flush_fn *prepare_flush_fn)
{
	if (!prepare_flush_fn && (ordered & (QUEUE_ORDERED_DO_PREFLUSH |
					     QUEUE_ORDERED_DO_POSTFLUSH))) {
		printk(KERN_ERR "%s: prepare_flush_fn required\n", __func__);
		return -EINVAL;
	}

	if (ordered != QUEUE_ORDERED_NONE &&
	    ordered != QUEUE_ORDERED_DRAIN &&
	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
	    ordered != QUEUE_ORDERED_TAG &&
	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
	    ordered != QUEUE_ORDERED_TAG_FUA) {
		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
		return -EINVAL;
	}

	q->ordered = ordered;
	q->next_ordered = ordered;
	q->prepare_flush_fn = prepare_flush_fn;

	return 0;
}
EXPORT_SYMBOL(blk_queue_ordered);

/*
 * Cache flushing for ordered writes handling
 */
unsigned blk_ordered_cur_seq(struct request_queue *q)
{
	if (!q->ordseq)
		return 0;
	return 1 << ffz(q->ordseq);
}

unsigned blk_ordered_req_seq(struct request *rq)
{
	struct request_queue *q = rq->q;

	BUG_ON(q->ordseq == 0);

	if (rq == &q->pre_flush_rq)
		return QUEUE_ORDSEQ_PREFLUSH;
	if (rq == &q->bar_rq)
		return QUEUE_ORDSEQ_BAR;
	if (rq == &q->post_flush_rq)
		return QUEUE_ORDSEQ_POSTFLUSH;

	/*
	 * !fs requests don't need to follow barrier ordering.  Always
	 * put them at the front.  This fixes the following deadlock.
	 *
	 * http://thread.gmane.org/gmane.linux.kernel/537473
	 */
	if (rq->cmd_type != REQ_TYPE_FS)
		return QUEUE_ORDSEQ_DRAIN;

	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
		return QUEUE_ORDSEQ_DRAIN;
	else
		return QUEUE_ORDSEQ_DONE;
}

bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
{
	struct request *rq;

	if (error && !q->orderr)
		q->orderr = error;

	BUG_ON(q->ordseq & seq);
	q->ordseq |= seq;

	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
		return false;

	/*
	 * Okay, sequence complete.
	 */
	q->ordseq = 0;
	rq = q->orig_bar_rq;
	__blk_end_request_all(rq, q->orderr);
	return true;
}

static void pre_flush_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
}

static void bar_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
}

static void post_flush_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
}

static void queue_flush(struct request_queue *q, unsigned which)
{
	struct request *rq;
	rq_end_io_fn *end_io;

	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
		rq = &q->pre_flush_rq;
		end_io = pre_flush_end_io;
	} else {
		rq = &q->post_flush_rq;
		end_io = post_flush_end_io;
	}

	blk_rq_init(q, rq);
	rq->cmd_flags = REQ_HARDBARRIER;
	rq->rq_disk = q->bar_rq.rq_disk;
	rq->end_io = end_io;
	q->prepare_flush_fn(q, rq);

	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}

static inline bool start_ordered(struct request_queue *q, struct request **rqp)
{
	struct request *rq = *rqp;
	unsigned skip = 0;

	q->orderr = 0;
	q->ordered = q->next_ordered;
	q->ordseq |= QUEUE_ORDSEQ_STARTED;

	/*
	 * For an empty barrier, there's no actual BAR request, which
	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
	 */
	if (!blk_rq_sectors(rq)) {
		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
				QUEUE_ORDERED_DO_POSTFLUSH);
		/*
		 * Empty barrier on a write-through device w/ ordered
		 * tag has no command to issue and without any command
		 * to issue, ordering by tag can't be used.  Drain
		 * instead.
		 */
		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
		}
	}

	/* stash away the original request */
	blk_dequeue_request(rq);
	q->orig_bar_rq = rq;
	rq = NULL;

	/*
	 * Queue ordered sequence.  As we stack them at the head, we
	 * need to queue in reverse order.  Note that we rely on that
	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
	 * request gets inbetween ordered sequence.
	 */
	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
		rq = &q->post_flush_rq;
	} else
		skip |= QUEUE_ORDSEQ_POSTFLUSH;

	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
		rq = &q->bar_rq;

		/* initialize proxy request and queue it */
		blk_rq_init(q, rq);
		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
			rq->cmd_flags |= REQ_WRITE;
		if (q->ordered & QUEUE_ORDERED_DO_FUA)
			rq->cmd_flags |= REQ_FUA;
		init_request_from_bio(rq, q->orig_bar_rq->bio);
		rq->end_io = bar_end_io;

		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
	} else
		skip |= QUEUE_ORDSEQ_BAR;

	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
		rq = &q->pre_flush_rq;
	} else
		skip |= QUEUE_ORDSEQ_PREFLUSH;

	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
		rq = NULL;
	else
		skip |= QUEUE_ORDSEQ_DRAIN;

	*rqp = rq;

	/*
	 * Complete skipped sequences.  If whole sequence is complete,
	 * return false to tell elevator that this request is gone.
	 */
	return !blk_ordered_complete_seq(q, skip, 0);
}

bool blk_do_ordered(struct request_queue *q, struct request **rqp)
{
	struct request *rq = *rqp;
	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
				(rq->cmd_flags & REQ_HARDBARRIER);

	if (!q->ordseq) {
		if (!is_barrier)
			return true;

		if (q->next_ordered != QUEUE_ORDERED_NONE)
			return start_ordered(q, rqp);
		else {
			/*
			 * Queue ordering not supported.  Terminate
			 * with prejudice.
			 */
			blk_dequeue_request(rq);
			__blk_end_request_all(rq, -EOPNOTSUPP);
			*rqp = NULL;
			return false;
		}
	}

	/*
	 * Ordered sequence in progress
	 */

	/* Special requests are not subject to ordering rules. */
	if (rq->cmd_type != REQ_TYPE_FS &&
	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
		return true;

	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
		/* Ordered by tag.  Blocking the next barrier is enough. */
		if (is_barrier && rq != &q->bar_rq)
			*rqp = NULL;
	} else {
		/* Ordered by draining.  Wait for turn. */
		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
			*rqp = NULL;
	}

	return true;
}

static void bio_end_empty_barrier(struct bio *bio, int err)
{
	if (err) {
		if (err == -EOPNOTSUPP)
			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	}
	if (bio->bi_private)
		complete(bio->bi_private);
	bio_put(bio);
}

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:	blockdev to issue flush for
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 * @error_sector:	error sector
 * @flags:	BLKDEV_IFL_* flags to control behaviour
 *
 * Description:
 *    Issue a flush for the block device in question. Caller can supply
 *    room for storing the error offset in case of a flush error, if they
 *    wish to. If WAIT flag is not passed then caller may check only what
 *    request was pushed in some internal queue for later handling.
 */
int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
		sector_t *error_sector, unsigned long flags)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	struct request_queue *q;
	struct bio *bio;
	int ret = 0;

	if (bdev->bd_disk == NULL)
		return -ENXIO;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;

	bio = bio_alloc(gfp_mask, 0);
	bio->bi_end_io = bio_end_empty_barrier;
	bio->bi_bdev = bdev;
	if (test_bit(BLKDEV_WAIT, &flags))
		bio->bi_private = &wait;

	bio_get(bio);
	submit_bio(WRITE_BARRIER, bio);
	if (test_bit(BLKDEV_WAIT, &flags)) {
		wait_for_completion(&wait);
		/*
		 * The driver must store the error location in ->bi_sector, if
		 * it supports it. For non-stacked drivers, this should be
		 * copied from blk_rq_pos(rq).
		 */
		if (error_sector)
			*error_sector = bio->bi_sector;
	}

	if (bio_flagged(bio, BIO_EOPNOTSUPP))
		ret = -EOPNOTSUPP;
	else if (!bio_flagged(bio, BIO_UPTODATE))
		ret = -EIO;

	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL(blkdev_issue_flush);