summaryrefslogtreecommitdiffstats
path: root/block/blk-flush.c
blob: 452c552e9ead6466ac420fe55fec4e09ab85fe14 (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
/*
 * Functions to sequence FLUSH and FUA writes.
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/gfp.h>

#include "blk.h"

/* FLUSH/FUA sequences */
enum {
	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
	QUEUE_FSEQ_DONE		= (1 << 4),
};

static struct request *queue_next_fseq(struct request_queue *q);

unsigned blk_flush_cur_seq(struct request_queue *q)
{
	if (!q->flush_seq)
		return 0;
	return 1 << ffz(q->flush_seq);
}

static struct request *blk_flush_complete_seq(struct request_queue *q,
					      unsigned seq, int error)
{
	struct request *next_rq = NULL;

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

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

	if (blk_flush_cur_seq(q) != QUEUE_FSEQ_DONE) {
		/* not complete yet, queue the next flush sequence */
		next_rq = queue_next_fseq(q);
	} else {
		/* complete this flush request */
		__blk_end_request_all(q->orig_flush_rq, q->flush_err);
		q->orig_flush_rq = NULL;
		q->flush_seq = 0;

		/* dispatch the next flush if there's one */
		if (!list_empty(&q->pending_flushes)) {
			next_rq = list_entry_rq(q->pending_flushes.next);
			list_move(&next_rq->queuelist, &q->queue_head);
		}
	}
	return next_rq;
}

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

static void flush_data_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_flush_complete_seq(rq->q, QUEUE_FSEQ_DATA, error);
}

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

static void queue_flush(struct request_queue *q, struct request *rq,
			rq_end_io_fn *end_io)
{
	blk_rq_init(q, rq);
	rq->cmd_type = REQ_TYPE_FS;
	rq->cmd_flags = REQ_FLUSH;
	rq->rq_disk = q->orig_flush_rq->rq_disk;
	rq->end_io = end_io;

	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}

static struct request *queue_next_fseq(struct request_queue *q)
{
	struct request *orig_rq = q->orig_flush_rq;
	struct request *rq = &q->flush_rq;

	switch (blk_flush_cur_seq(q)) {
	case QUEUE_FSEQ_PREFLUSH:
		queue_flush(q, rq, pre_flush_end_io);
		break;

	case QUEUE_FSEQ_DATA:
		/* initialize proxy request, inherit FLUSH/FUA and queue it */
		blk_rq_init(q, rq);
		init_request_from_bio(rq, orig_rq->bio);
		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
		rq->end_io = flush_data_end_io;

		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
		break;

	case QUEUE_FSEQ_POSTFLUSH:
		queue_flush(q, rq, post_flush_end_io);
		break;

	default:
		BUG();
	}
	return rq;
}

struct request *blk_do_flush(struct request_queue *q, struct request *rq)
{
	unsigned int fflags = q->flush_flags; /* may change, cache it */
	bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA;
	bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH);
	bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA);
	unsigned skip = 0;

	/*
	 * Special case.  If there's data but flush is not necessary,
	 * the request can be issued directly.
	 *
	 * Flush w/o data should be able to be issued directly too but
	 * currently some drivers assume that rq->bio contains
	 * non-zero data if it isn't NULL and empty FLUSH requests
	 * getting here usually have bio's without data.
	 */
	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
		rq->cmd_flags &= ~REQ_FLUSH;
		if (!has_fua)
			rq->cmd_flags &= ~REQ_FUA;
		return rq;
	}

	/*
	 * Sequenced flushes can't be processed in parallel.  If
	 * another one is already in progress, queue for later
	 * processing.
	 */
	if (q->flush_seq) {
		list_move_tail(&rq->queuelist, &q->pending_flushes);
		return NULL;
	}

	/*
	 * Start a new flush sequence
	 */
	q->flush_err = 0;
	q->flush_seq |= QUEUE_FSEQ_STARTED;

	/* adjust FLUSH/FUA of the original request and stash it away */
	rq->cmd_flags &= ~REQ_FLUSH;
	if (!has_fua)
		rq->cmd_flags &= ~REQ_FUA;
	blk_dequeue_request(rq);
	q->orig_flush_rq = rq;

	/* skip unneded sequences and return the first one */
	if (!do_preflush)
		skip |= QUEUE_FSEQ_PREFLUSH;
	if (!blk_rq_sectors(rq))
		skip |= QUEUE_FSEQ_DATA;
	if (!do_postflush)
		skip |= QUEUE_FSEQ_POSTFLUSH;
	return blk_flush_complete_seq(q, skip, 0);
}

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;

	/*
	 * some block devices may not have their queue correctly set up here
	 * (e.g. loop device without a backing file) and so issuing a flush
	 * here will panic. Ensure there is a request function before issuing
	 * the barrier.
	 */
	if (!q->make_request_fn)
		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);
OpenPOWER on IntegriCloud