blk-flush.c 12.5 KB
Newer Older
1
/*
2
 * Functions to sequence FLUSH and FUA writes.
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
 *
 * Copyright (C) 2011		Max Planck Institute for Gravitational Physics
 * Copyright (C) 2011		Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 *
 * REQ_{FLUSH|FUA} requests are decomposed to sequences consisted of three
 * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
 * properties and hardware capability.
 *
 * If a request doesn't have data, only REQ_FLUSH makes sense, which
 * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
 * that the device cache should be flushed before the data is executed, and
 * REQ_FUA means that the data must be on non-volatile media on request
 * completion.
 *
 * If the device doesn't have writeback cache, FLUSH and FUA don't make any
 * difference.  The requests are either completed immediately if there's no
 * data or executed as normal requests otherwise.
 *
 * If the device has writeback cache and supports FUA, REQ_FLUSH is
 * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
 *
 * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
 * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
 *
 * The actual execution of flush is double buffered.  Whenever a request
 * needs to execute PRE or POSTFLUSH, it queues at
 * q->flush_queue[q->flush_pending_idx].  Once certain criteria are met, a
 * flush is issued and the pending_idx is toggled.  When the flush
 * completes, all the requests which were pending are proceeded to the next
 * step.  This allows arbitrary merging of different types of FLUSH/FUA
 * requests.
 *
 * Currently, the following conditions are used to determine when to issue
 * flush.
 *
 * C1. At any given time, only one flush shall be in progress.  This makes
 *     double buffering sufficient.
 *
 * C2. Flush is deferred if any request is executing DATA of its sequence.
 *     This avoids issuing separate POSTFLUSHes for requests which shared
 *     PREFLUSH.
 *
 * C3. The second condition is ignored if there is a request which has
 *     waited longer than FLUSH_PENDING_TIMEOUT.  This is to avoid
 *     starvation in the unlikely case where there are continuous stream of
 *     FUA (without FLUSH) requests.
 *
 * For devices which support FUA, it isn't clear whether C2 (and thus C3)
 * is beneficial.
 *
 * Note that a sequenced FLUSH/FUA request with DATA is completed twice.
 * Once while executing DATA and again after the whole sequence is
 * complete.  The first completion updates the contained bio but doesn't
 * finish it so that the bio submitter is notified only after the whole
 * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
 * req_bio_endio().
 *
 * The above peculiarity requires that each FLUSH/FUA request has only one
 * bio attached to it, which is guaranteed as they aren't allowed to be
 * merged in the usual way.
65
 */
66

67
68
69
70
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
71
#include <linux/gfp.h>
72
73
74

#include "blk.h"

75
76
/* FLUSH/FUA sequences */
enum {
77
78
79
80
81
82
83
84
85
86
87
88
89
	REQ_FSEQ_PREFLUSH	= (1 << 0), /* pre-flushing in progress */
	REQ_FSEQ_DATA		= (1 << 1), /* data write in progress */
	REQ_FSEQ_POSTFLUSH	= (1 << 2), /* post-flushing in progress */
	REQ_FSEQ_DONE		= (1 << 3),

	REQ_FSEQ_ACTIONS	= REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA |
				  REQ_FSEQ_POSTFLUSH,

	/*
	 * If flush has been pending longer than the following timeout,
	 * it's issued even if flush_data requests are still in flight.
	 */
	FLUSH_PENDING_TIMEOUT	= 5 * HZ,
90
91
};

92
static bool blk_kick_flush(struct request_queue *q);
93

94
static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
95
{
96
	unsigned int policy = 0;
97

98
99
100
101
102
103
104
	if (fflags & REQ_FLUSH) {
		if (rq->cmd_flags & REQ_FLUSH)
			policy |= REQ_FSEQ_PREFLUSH;
		if (blk_rq_sectors(rq))
			policy |= REQ_FSEQ_DATA;
		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
			policy |= REQ_FSEQ_POSTFLUSH;
105
	}
106
	return policy;
107
108
}

109
static unsigned int blk_flush_cur_seq(struct request *rq)
110
{
111
112
	return 1 << ffz(rq->flush.seq);
}
113

114
115
static void blk_flush_restore_request(struct request *rq)
{
116
	/*
117
118
119
	 * After flush data completion, @rq->bio is %NULL but we need to
	 * complete the bio again.  @rq->biotail is guaranteed to equal the
	 * original @rq->bio.  Restore it.
120
	 */
121
122
123
124
125
	rq->bio = rq->biotail;

	/* make @rq a normal request */
	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
	rq->end_io = NULL;
126
127
}

128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
/**
 * blk_flush_complete_seq - complete flush sequence
 * @rq: FLUSH/FUA request being sequenced
 * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
 * @error: whether an error occurred
 *
 * @rq just completed @seq part of its flush sequence, record the
 * completion and trigger the next step.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock)
 *
 * RETURNS:
 * %true if requests were added to the dispatch queue, %false otherwise.
 */
static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
				   int error)
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
	struct request_queue *q = rq->q;
	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
	bool queued = false;

	BUG_ON(rq->flush.seq & seq);
	rq->flush.seq |= seq;

	if (likely(!error))
		seq = blk_flush_cur_seq(rq);
	else
		seq = REQ_FSEQ_DONE;

	switch (seq) {
	case REQ_FSEQ_PREFLUSH:
	case REQ_FSEQ_POSTFLUSH:
		/* queue for flush */
		if (list_empty(pending))
			q->flush_pending_since = jiffies;
		list_move_tail(&rq->flush.list, pending);
		break;

	case REQ_FSEQ_DATA:
		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
		list_add(&rq->queuelist, &q->queue_head);
		queued = true;
		break;

	case REQ_FSEQ_DONE:
		/*
		 * @rq was previously adjusted by blk_flush_issue() for
		 * flush sequencing and may already have gone through the
		 * flush data request completion path.  Restore @rq for
		 * normal completion and end it.
		 */
		BUG_ON(!list_empty(&rq->queuelist));
		list_del_init(&rq->flush.list);
		blk_flush_restore_request(rq);
		__blk_end_request_all(rq, error);
		break;

	default:
		BUG();
	}

	return blk_kick_flush(q) | queued;
191
192
}

193
static void flush_end_io(struct request *flush_rq, int error)
194
{
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
	struct request_queue *q = flush_rq->q;
	struct list_head *running = &q->flush_queue[q->flush_running_idx];
	bool queued = false;
	struct request *rq, *n;

	BUG_ON(q->flush_pending_idx == q->flush_running_idx);

	/* account completion of the flush request */
	q->flush_running_idx ^= 1;
	elv_completed_request(q, flush_rq);

	/* and push the waiting requests to the next stage */
	list_for_each_entry_safe(rq, n, running, flush.list) {
		unsigned int seq = blk_flush_cur_seq(rq);

		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
		queued |= blk_flush_complete_seq(rq, seq, error);
	}

214
215
	/*
	 * Moving a request silently to empty queue_head may stall the
216
217
218
	 * queue.  Kick the queue in those cases.  This function is called
	 * from request completion path and calling directly into
	 * request_fn may confuse the driver.  Always use kblockd.
219
	 */
Jens Axboe's avatar
Jens Axboe committed
220
	if (queued)
221
		__blk_run_queue(q, true);
222
223
}

224
225
226
227
228
229
230
231
232
233
234
235
236
237
/**
 * blk_kick_flush - consider issuing flush request
 * @q: request_queue being kicked
 *
 * Flush related states of @q have changed, consider issuing flush request.
 * Please read the comment at the top of this file for more info.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock)
 *
 * RETURNS:
 * %true if flush was issued, %false otherwise.
 */
static bool blk_kick_flush(struct request_queue *q)
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
	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
	struct request *first_rq =
		list_first_entry(pending, struct request, flush.list);

	/* C1 described at the top of this file */
	if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
		return false;

	/* C2 and C3 */
	if (!list_empty(&q->flush_data_in_flight) &&
	    time_before(jiffies,
			q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
		return false;

	/*
	 * Issue flush and toggle pending_idx.  This makes pending_idx
	 * different from running_idx, which means flush is in flight.
	 */
	blk_rq_init(q, &q->flush_rq);
	q->flush_rq.cmd_type = REQ_TYPE_FS;
	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
	q->flush_rq.rq_disk = first_rq->rq_disk;
	q->flush_rq.end_io = flush_end_io;

	q->flush_pending_idx ^= 1;
264
	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
265
	return true;
266
267
}

268
static void flush_data_end_io(struct request *rq, int error)
269
{
270
271
	struct request_queue *q = rq->q;

272
273
274
275
	/*
	 * After populating an empty queue, kick it to avoid stall.  Read
	 * the comment in flush_end_io().
	 */
276
	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
277
		__blk_run_queue(q, true);
278
279
}

280
281
282
283
/**
 * blk_insert_flush - insert a new FLUSH/FUA request
 * @rq: request to insert
 *
284
 * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions.
285
286
287
288
289
290
291
 * @rq is being submitted.  Analyze what needs to be done and put it on the
 * right queue.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock)
 */
void blk_insert_flush(struct request *rq)
292
{
293
294
295
	struct request_queue *q = rq->q;
	unsigned int fflags = q->flush_flags;	/* may change, cache */
	unsigned int policy = blk_flush_policy(fflags, rq);
296

297
298
	BUG_ON(rq->end_io);
	BUG_ON(!rq->bio || rq->bio != rq->biotail);
299

300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
	/*
	 * @policy now records what operations need to be done.  Adjust
	 * REQ_FLUSH and FUA for the driver.
	 */
	rq->cmd_flags &= ~REQ_FLUSH;
	if (!(fflags & REQ_FUA))
		rq->cmd_flags &= ~REQ_FUA;

	/*
	 * If there's data but flush is not necessary, the request can be
	 * processed directly without going through flush machinery.  Queue
	 * for normal execution.
	 */
	if ((policy & REQ_FSEQ_DATA) &&
	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
315
		list_add_tail(&rq->queuelist, &q->queue_head);
316
		return;
317
	}
318

319
320
321
322
323
324
	/*
	 * @rq should go through flush machinery.  Mark it part of flush
	 * sequence and submit for further processing.
	 */
	memset(&rq->flush, 0, sizeof(rq->flush));
	INIT_LIST_HEAD(&rq->flush.list);
Tejun Heo's avatar
Tejun Heo committed
325
	rq->cmd_flags |= REQ_FLUSH_SEQ;
326
327
328
	rq->end_io = flush_data_end_io;

	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
329
330
}

331
332
333
334
335
336
337
338
339
340
341
/**
 * blk_abort_flushes - @q is being aborted, abort flush requests
 * @q: request_queue being aborted
 *
 * To be called from elv_abort_queue().  @q is being aborted.  Prepare all
 * FLUSH/FUA requests for abortion.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock)
 */
void blk_abort_flushes(struct request_queue *q)
342
{
343
344
	struct request *rq, *n;
	int i;
345

346
	/*
347
348
	 * Requests in flight for data are already owned by the dispatch
	 * queue or the device driver.  Just restore for normal completion.
349
	 */
350
351
352
	list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) {
		list_del_init(&rq->flush.list);
		blk_flush_restore_request(rq);
353
	}
354

355
	/*
356
357
	 * We need to give away requests on flush queues.  Restore for
	 * normal completion and put them on the dispatch queue.
358
	 */
359
360
361
362
363
364
365
	for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) {
		list_for_each_entry_safe(rq, n, &q->flush_queue[i],
					 flush.list) {
			list_del_init(&rq->flush.list);
			blk_flush_restore_request(rq);
			list_add_tail(&rq->queuelist, &q->queue_head);
		}
366
	}
367
368
}

369
static void bio_end_flush(struct bio *bio, int err)
370
{
371
	if (err)
372
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
373
374
375
	if (bio->bi_private)
		complete(bio->bi_private);
	bio_put(bio);
376
377
378
379
380
}

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:	blockdev to issue flush for
381
 * @gfp_mask:	memory allocation flags (for bio_alloc)
382
383
384
385
386
 * @error_sector:	error sector
 *
 * 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
387
388
 *    wish to. If WAIT flag is not passed then caller may check only what
 *    request was pushed in some internal queue for later handling.
389
 */
390
int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
391
		sector_t *error_sector)
392
393
394
395
{
	DECLARE_COMPLETION_ONSTACK(wait);
	struct request_queue *q;
	struct bio *bio;
396
	int ret = 0;
397
398
399
400
401
402
403
404

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

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

405
406
407
408
	/*
	 * 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
409
	 * the flush.
410
411
412
413
	 */
	if (!q->make_request_fn)
		return -ENXIO;

414
	bio = bio_alloc(gfp_mask, 0);
415
	bio->bi_end_io = bio_end_flush;
416
	bio->bi_bdev = bdev;
417
	bio->bi_private = &wait;
418

419
	bio_get(bio);
420
	submit_bio(WRITE_FLUSH, bio);
421
422
423
424
425
426
427
428
429
	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;
430

431
	if (!bio_flagged(bio, BIO_UPTODATE))
432
433
434
435
436
437
		ret = -EIO;

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