aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/bcache/journal.c
blob: f9afb164b887db71d6cd585c81ec82e769eb8d44 (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
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
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
// SPDX-License-Identifier: GPL-2.0
/*
 * bcache journalling code, for btree insertions
 *
 * Copyright 2012 Google, Inc.
 */

#include "bcache.h"
#include "btree.h"
#include "debug.h"
#include "extents.h"

#include <trace/events/bcache.h>

/*
 * Journal replay/recovery:
 *
 * This code is all driven from run_cache_set(); we first read the journal
 * entries, do some other stuff, then we mark all the keys in the journal
 * entries (same as garbage collection would), then we replay them - reinserting
 * them into the cache in precisely the same order as they appear in the
 * journal.
 *
 * We only journal keys that go in leaf nodes, which simplifies things quite a
 * bit.
 */

static void journal_read_endio(struct bio *bio)
{
	struct closure *cl = bio->bi_private;

	closure_put(cl);
}

static int journal_read_bucket(struct cache *ca, struct list_head *list,
			       unsigned int bucket_index)
{
	struct journal_device *ja = &ca->journal;
	struct bio *bio = &ja->bio;

	struct journal_replay *i;
	struct jset *j, *data = ca->set->journal.w[0].data;
	struct closure cl;
	unsigned int len, left, offset = 0;
	int ret = 0;
	sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bucket_index]);

	closure_init_stack(&cl);

	pr_debug("reading %u", bucket_index);

	while (offset < ca->sb.bucket_size) {
reread:		left = ca->sb.bucket_size - offset;
		len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS);

		bio_reset(bio);
		bio->bi_iter.bi_sector	= bucket + offset;
		bio_set_dev(bio, ca->bdev);
		bio->bi_iter.bi_size	= len << 9;

		bio->bi_end_io	= journal_read_endio;
		bio->bi_private = &cl;
		bio_set_op_attrs(bio, REQ_OP_READ, 0);
		bch_bio_map(bio, data);

		closure_bio_submit(ca->set, bio, &cl);
		closure_sync(&cl);

		/* This function could be simpler now since we no longer write
		 * journal entries that overlap bucket boundaries; this means
		 * the start of a bucket will always have a valid journal entry
		 * if it has any journal entries at all.
		 */

		j = data;
		while (len) {
			struct list_head *where;
			size_t blocks, bytes = set_bytes(j);

			if (j->magic != jset_magic(&ca->sb)) {
				pr_debug("%u: bad magic", bucket_index);
				return ret;
			}

			if (bytes > left << 9 ||
			    bytes > PAGE_SIZE << JSET_BITS) {
				pr_info("%u: too big, %zu bytes, offset %u",
					bucket_index, bytes, offset);
				return ret;
			}

			if (bytes > len << 9)
				goto reread;

			if (j->csum != csum_set(j)) {
				pr_info("%u: bad csum, %zu bytes, offset %u",
					bucket_index, bytes, offset);
				return ret;
			}

			blocks = set_blocks(j, block_bytes(ca->set));

			while (!list_empty(list)) {
				i = list_first_entry(list,
					struct journal_replay, list);
				if (i->j.seq >= j->last_seq)
					break;
				list_del(&i->list);
				kfree(i);
			}

			list_for_each_entry_reverse(i, list, list) {
				if (j->seq == i->j.seq)
					goto next_set;

				if (j->seq < i->j.last_seq)
					goto next_set;

				if (j->seq > i->j.seq) {
					where = &i->list;
					goto add;
				}
			}

			where = list;
add:
			i = kmalloc(offsetof(struct journal_replay, j) +
				    bytes, GFP_KERNEL);
			if (!i)
				return -ENOMEM;
			memcpy(&i->j, j, bytes);
			list_add(&i->list, where);
			ret = 1;

			ja->seq[bucket_index] = j->seq;
next_set:
			offset	+= blocks * ca->sb.block_size;
			len	-= blocks * ca->sb.block_size;
			j = ((void *) j) + blocks * block_bytes(ca);
		}
	}

	return ret;
}

int bch_journal_read(struct cache_set *c, struct list_head *list)
{
#define read_bucket(b)							\
	({								\
		ret = journal_read_bucket(ca, list, b);			\
		__set_bit(b, bitmap);					\
		if (ret < 0)						\
			return ret;					\
		ret;							\
	})

	struct cache *ca;
	unsigned int iter;
	int ret = 0;

	for_each_cache(ca, c, iter) {
		struct journal_device *ja = &ca->journal;
		DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
		unsigned int i, l, r, m;
		uint64_t seq;

		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
		pr_debug("%u journal buckets", ca->sb.njournal_buckets);

		/*
		 * Read journal buckets ordered by golden ratio hash to quickly
		 * find a sequence of buckets with valid journal entries
		 */
		for (i = 0; i < ca->sb.njournal_buckets; i++) {
			/*
			 * We must try the index l with ZERO first for
			 * correctness due to the scenario that the journal
			 * bucket is circular buffer which might have wrapped
			 */
			l = (i * 2654435769U) % ca->sb.njournal_buckets;

			if (test_bit(l, bitmap))
				break;

			if (read_bucket(l))
				goto bsearch;
		}

		/*
		 * If that fails, check all the buckets we haven't checked
		 * already
		 */
		pr_debug("falling back to linear search");

		for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
		     l < ca->sb.njournal_buckets;
		     l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets,
					    l + 1))
			if (read_bucket(l))
				goto bsearch;

		/* no journal entries on this device? */
		if (l == ca->sb.njournal_buckets)
			continue;
bsearch:
		BUG_ON(list_empty(list));

		/* Binary search */
		m = l;
		r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
		pr_debug("starting binary search, l %u r %u", l, r);

		while (l + 1 < r) {
			seq = list_entry(list->prev, struct journal_replay,
					 list)->j.seq;

			m = (l + r) >> 1;
			read_bucket(m);

			if (seq != list_entry(list->prev, struct journal_replay,
					      list)->j.seq)
				l = m;
			else
				r = m;
		}

		/*
		 * Read buckets in reverse order until we stop finding more
		 * journal entries
		 */
		pr_debug("finishing up: m %u njournal_buckets %u",
			 m, ca->sb.njournal_buckets);
		l = m;

		while (1) {
			if (!l--)
				l = ca->sb.njournal_buckets - 1;

			if (l == m)
				break;

			if (test_bit(l, bitmap))
				continue;

			if (!read_bucket(l))
				break;
		}

		seq = 0;

		for (i = 0; i < ca->sb.njournal_buckets; i++)
			if (ja->seq[i] > seq) {
				seq = ja->seq[i];
				/*
				 * When journal_reclaim() goes to allocate for
				 * the first time, it'll use the bucket after
				 * ja->cur_idx
				 */
				ja->cur_idx = i;
				ja->last_idx = ja->discard_idx = (i + 1) %
					ca->sb.njournal_buckets;

			}
	}

	if (!list_empty(list))
		c->journal.seq = list_entry(list->prev,
					    struct journal_replay,
					    list)->j.seq;

	return ret;
#undef read_bucket
}

void bch_journal_mark(struct cache_set *c, struct list_head *list)
{
	atomic_t p = { 0 };
	struct bkey *k;
	struct journal_replay *i;
	struct journal *j = &c->journal;
	uint64_t last = j->seq;

	/*
	 * journal.pin should never fill up - we never write a journal
	 * entry when it would fill up. But if for some reason it does, we
	 * iterate over the list in reverse order so that we can just skip that
	 * refcount instead of bugging.
	 */

	list_for_each_entry_reverse(i, list, list) {
		BUG_ON(last < i->j.seq);
		i->pin = NULL;

		while (last-- != i->j.seq)
			if (fifo_free(&j->pin) > 1) {
				fifo_push_front(&j->pin, p);
				atomic_set(&fifo_front(&j->pin), 0);
			}

		if (fifo_free(&j->pin) > 1) {
			fifo_push_front(&j->pin, p);
			i->pin = &fifo_front(&j->pin);
			atomic_set(i->pin, 1);
		}

		for (k = i->j.start;
		     k < bset_bkey_last(&i->j);
		     k = bkey_next(k))
			if (!__bch_extent_invalid(c, k)) {
				unsigned int j;

				for (j = 0; j < KEY_PTRS(k); j++)
					if (ptr_available(c, k, j))
						atomic_inc(&PTR_BUCKET(c, k, j)->pin);

				bch_initial_mark_key(c, 0, k);
			}
	}
}

bool is_discard_enabled(struct cache_set *s)
{
	struct cache *ca;
	unsigned int i;

	for_each_cache(ca, s, i)
		if (ca->discard)
			return true;

	return false;
}

int bch_journal_replay(struct cache_set *s, struct list_head *list)
{
	int ret = 0, keys = 0, entries = 0;
	struct bkey *k;
	struct journal_replay *i =
		list_entry(list->prev, struct journal_replay, list);

	uint64_t start = i->j.last_seq, end = i->j.seq, n = start;
	struct keylist keylist;

	list_for_each_entry(i, list, list) {
		BUG_ON(i->pin && atomic_read(i->pin) != 1);

		if (n != i->j.seq) {
			if (n == start && is_discard_enabled(s))
				pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)",
					n, i->j.seq - 1, start, end);
			else {
				pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
					n, i->j.seq - 1, start, end);
				ret = -EIO;
				goto err;
			}
		}

		for (k = i->j.start;
		     k < bset_bkey_last(&i->j);
		     k = bkey_next(k)) {
			trace_bcache_journal_replay_key(k);

			bch_keylist_init_single(&keylist, k);

			ret = bch_btree_insert(s, &keylist, i->pin, NULL);
			if (ret)
				goto err;

			BUG_ON(!bch_keylist_empty(&keylist));
			keys++;

			cond_resched();
		}

		if (i->pin)
			atomic_dec(i->pin);
		n = i->j.seq + 1;
		entries++;
	}

	pr_info("journal replay done, %i keys in %i entries, seq %llu",
		keys, entries, end);
err:
	while (!list_empty(list)) {
		i = list_first_entry(list, struct journal_replay, list);
		list_del(&i->list);
		kfree(i);
	}

	return ret;
}

/* Journalling */
#define journal_max_cmp(l, r) \
	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
#define journal_min_cmp(l, r) \
	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))

static void btree_flush_write(struct cache_set *c)
{
	/*
	 * Try to find the btree node with that references the oldest journal
	 * entry, best is our current candidate and is locked if non NULL:
	 */
	struct btree *b;
	int i;

	atomic_long_inc(&c->flush_write);

retry:
	spin_lock(&c->journal.lock);
	if (heap_empty(&c->flush_btree)) {
		for_each_cached_btree(b, c, i)
			if (btree_current_write(b)->journal) {
				if (!heap_full(&c->flush_btree))
					heap_add(&c->flush_btree, b,
						 journal_max_cmp);
				else if (journal_max_cmp(b,
					 heap_peek(&c->flush_btree))) {
					c->flush_btree.data[0] = b;
					heap_sift(&c->flush_btree, 0,
						  journal_max_cmp);
				}
			}

		for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
			heap_sift(&c->flush_btree, i, journal_min_cmp);
	}

	b = NULL;
	heap_pop(&c->flush_btree, b, journal_min_cmp);
	spin_unlock(&c->journal.lock);

	if (b) {
		mutex_lock(&b->write_lock);
		if (!btree_current_write(b)->journal) {
			mutex_unlock(&b->write_lock);
			/* We raced */
			atomic_long_inc(&c->retry_flush_write);
			goto retry;
		}

		__bch_btree_node_write(b, NULL);
		mutex_unlock(&b->write_lock);
	}
}

#define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)

static void journal_discard_endio(struct bio *bio)
{
	struct journal_device *ja =
		container_of(bio, struct journal_device, discard_bio);
	struct cache *ca = container_of(ja, struct cache, journal);

	atomic_set(&ja->discard_in_flight, DISCARD_DONE);

	closure_wake_up(&ca->set->journal.wait);
	closure_put(&ca->set->cl);
}

static void journal_discard_work(struct work_struct *work)
{
	struct journal_device *ja =
		container_of(work, struct journal_device, discard_work);

	submit_bio(&ja->discard_bio);
}

static void do_journal_discard(struct cache *ca)
{
	struct journal_device *ja = &ca->journal;
	struct bio *bio = &ja->discard_bio;

	if (!ca->discard) {
		ja->discard_idx = ja->last_idx;
		return;
	}

	switch (atomic_read(&ja->discard_in_flight)) {
	case DISCARD_IN_FLIGHT:
		return;

	case DISCARD_DONE:
		ja->discard_idx = (ja->discard_idx + 1) %
			ca->sb.njournal_buckets;

		atomic_set(&ja->discard_in_flight, DISCARD_READY);
		/* fallthrough */

	case DISCARD_READY:
		if (ja->discard_idx == ja->last_idx)
			return;

		atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);

		bio_init(bio, bio->bi_inline_vecs, 1);
		bio_set_op_attrs(bio, REQ_OP_DISCARD, 0);
		bio->bi_iter.bi_sector	= bucket_to_sector(ca->set,
						ca->sb.d[ja->discard_idx]);
		bio_set_dev(bio, ca->bdev);
		bio->bi_iter.bi_size	= bucket_bytes(ca);
		bio->bi_end_io		= journal_discard_endio;

		closure_get(&ca->set->cl);
		INIT_WORK(&ja->discard_work, journal_discard_work);
		queue_work(bch_journal_wq, &ja->discard_work);
	}
}

static void journal_reclaim(struct cache_set *c)
{
	struct bkey *k = &c->journal.key;
	struct cache *ca;
	uint64_t last_seq;
	unsigned int iter, n = 0;
	atomic_t p __maybe_unused;

	atomic_long_inc(&c->reclaim);

	while (!atomic_read(&fifo_front(&c->journal.pin)))
		fifo_pop(&c->journal.pin, p);

	last_seq = last_seq(&c->journal);

	/* Update last_idx */

	for_each_cache(ca, c, iter) {
		struct journal_device *ja = &ca->journal;

		while (ja->last_idx != ja->cur_idx &&
		       ja->seq[ja->last_idx] < last_seq)
			ja->last_idx = (ja->last_idx + 1) %
				ca->sb.njournal_buckets;
	}

	for_each_cache(ca, c, iter)
		do_journal_discard(ca);

	if (c->journal.blocks_free)
		goto out;

	/*
	 * Allocate:
	 * XXX: Sort by free journal space
	 */

	for_each_cache(ca, c, iter) {
		struct journal_device *ja = &ca->journal;
		unsigned int next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;

		/* No space available on this device */
		if (next == ja->discard_idx)
			continue;

		ja->cur_idx = next;
		k->ptr[n++] = MAKE_PTR(0,
				  bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
				  ca->sb.nr_this_dev);
	}

	if (n) {
		bkey_init(k);
		SET_KEY_PTRS(k, n);
		c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
	}
out:
	if (!journal_full(&c->journal))
		__closure_wake_up(&c->journal.wait);
}

void bch_journal_next(struct journal *j)
{
	atomic_t p = { 1 };

	j->cur = (j->cur == j->w)
		? &j->w[1]
		: &j->w[0];

	/*
	 * The fifo_push() needs to happen at the same time as j->seq is
	 * incremented for last_seq() to be calculated correctly
	 */
	BUG_ON(!fifo_push(&j->pin, p));
	atomic_set(&fifo_back(&j->pin), 1);

	j->cur->data->seq	= ++j->seq;
	j->cur->dirty		= false;
	j->cur->need_write	= false;
	j->cur->data->keys	= 0;

	if (fifo_full(&j->pin))
		pr_debug("journal_pin full (%zu)", fifo_used(&j->pin));
}

static void journal_write_endio(struct bio *bio)
{
	struct journal_write *w = bio->bi_private;

	cache_set_err_on(bio->bi_status, w->c, "journal io error");
	closure_put(&w->c->journal.io);
}

static void journal_write(struct closure *cl);

static void journal_write_done(struct closure *cl)
{
	struct journal *j = container_of(cl, struct journal, io);
	struct journal_write *w = (j->cur == j->w)
		? &j->w[1]
		: &j->w[0];

	__closure_wake_up(&w->wait);
	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
}

static void journal_write_unlock(struct closure *cl)
	__releases(&c->journal.lock)
{
	struct cache_set *c = container_of(cl, struct cache_set, journal.io);

	c->journal.io_in_flight = 0;
	spin_unlock(&c->journal.lock);
}

static void journal_write_unlocked(struct closure *cl)
	__releases(c->journal.lock)
{
	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
	struct cache *ca;
	struct journal_write *w = c->journal.cur;
	struct bkey *k = &c->journal.key;
	unsigned int i, sectors = set_blocks(w->data, block_bytes(c)) *
		c->sb.block_size;

	struct bio *bio;
	struct bio_list list;

	bio_list_init(&list);

	if (!w->need_write) {
		closure_return_with_destructor(cl, journal_write_unlock);
		return;
	} else if (journal_full(&c->journal)) {
		journal_reclaim(c);
		spin_unlock(&c->journal.lock);

		btree_flush_write(c);
		continue_at(cl, journal_write, bch_journal_wq);
		return;
	}

	c->journal.blocks_free -= set_blocks(w->data, block_bytes(c));

	w->data->btree_level = c->root->level;

	bkey_copy(&w->data->btree_root, &c->root->key);
	bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);

	for_each_cache(ca, c, i)
		w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];

	w->data->magic		= jset_magic(&c->sb);
	w->data->version	= BCACHE_JSET_VERSION;
	w->data->last_seq	= last_seq(&c->journal);
	w->data->csum		= csum_set(w->data);

	for (i = 0; i < KEY_PTRS(k); i++) {
		ca = PTR_CACHE(c, k, i);
		bio = &ca->journal.bio;

		atomic_long_add(sectors, &ca->meta_sectors_written);

		bio_reset(bio);
		bio->bi_iter.bi_sector	= PTR_OFFSET(k, i);
		bio_set_dev(bio, ca->bdev);
		bio->bi_iter.bi_size = sectors << 9;

		bio->bi_end_io	= journal_write_endio;
		bio->bi_private = w;
		bio_set_op_attrs(bio, REQ_OP_WRITE,
				 REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
		bch_bio_map(bio, w->data);

		trace_bcache_journal_write(bio, w->data->keys);
		bio_list_add(&list, bio);

		SET_PTR_OFFSET(k, i, PTR_OFFSET(k, i) + sectors);

		ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
	}

	/* If KEY_PTRS(k) == 0, this jset gets lost in air */
	BUG_ON(i == 0);

	atomic_dec_bug(&fifo_back(&c->journal.pin));
	bch_journal_next(&c->journal);
	journal_reclaim(c);

	spin_unlock(&c->journal.lock);

	while ((bio = bio_list_pop(&list)))
		closure_bio_submit(c, bio, cl);

	continue_at(cl, journal_write_done, NULL);
}

static void journal_write(struct closure *cl)
{
	struct cache_set *c = container_of(cl, struct cache_set, journal.io);

	spin_lock(&c->journal.lock);
	journal_write_unlocked(cl);
}

static void journal_try_write(struct cache_set *c)
	__releases(c->journal.lock)
{
	struct closure *cl = &c->journal.io;
	struct journal_write *w = c->journal.cur;

	w->need_write = true;

	if (!c->journal.io_in_flight) {
		c->journal.io_in_flight = 1;
		closure_call(cl, journal_write_unlocked, NULL, &c->cl);
	} else {
		spin_unlock(&c->journal.lock);
	}
}

static struct journal_write *journal_wait_for_write(struct cache_set *c,
						    unsigned int nkeys)
	__acquires(&c->journal.lock)
{
	size_t sectors;
	struct closure cl;
	bool wait = false;

	closure_init_stack(&cl);

	spin_lock(&c->journal.lock);

	while (1) {
		struct journal_write *w = c->journal.cur;

		sectors = __set_blocks(w->data, w->data->keys + nkeys,
				       block_bytes(c)) * c->sb.block_size;

		if (sectors <= min_t(size_t,
				     c->journal.blocks_free * c->sb.block_size,
				     PAGE_SECTORS << JSET_BITS))
			return w;

		if (wait)
			closure_wait(&c->journal.wait, &cl);

		if (!journal_full(&c->journal)) {
			if (wait)
				trace_bcache_journal_entry_full(c);

			/*
			 * XXX: If we were inserting so many keys that they
			 * won't fit in an _empty_ journal write, we'll
			 * deadlock. For now, handle this in
			 * bch_keylist_realloc() - but something to think about.
			 */
			BUG_ON(!w->data->keys);

			journal_try_write(c); /* unlocks */
		} else {
			if (wait)
				trace_bcache_journal_full(c);

			journal_reclaim(c);
			spin_unlock(&c->journal.lock);

			btree_flush_write(c);
		}

		closure_sync(&cl);
		spin_lock(&c->journal.lock);
		wait = true;
	}
}

static void journal_write_work(struct work_struct *work)
{
	struct cache_set *c = container_of(to_delayed_work(work),
					   struct cache_set,
					   journal.work);
	spin_lock(&c->journal.lock);
	if (c->journal.cur->dirty)
		journal_try_write(c);
	else
		spin_unlock(&c->journal.lock);
}

/*
 * Entry point to the journalling code - bio_insert() and btree_invalidate()
 * pass bch_journal() a list of keys to be journalled, and then
 * bch_journal() hands those same keys off to btree_insert_async()
 */

atomic_t *bch_journal(struct cache_set *c,
		      struct keylist *keys,
		      struct closure *parent)
{
	struct journal_write *w;
	atomic_t *ret;

	if (!CACHE_SYNC(&c->sb))
		return NULL;

	w = journal_wait_for_write(c, bch_keylist_nkeys(keys));

	memcpy(bset_bkey_last(w->data), keys->keys, bch_keylist_bytes(keys));
	w->data->keys += bch_keylist_nkeys(keys);

	ret = &fifo_back(&c->journal.pin);
	atomic_inc(ret);

	if (parent) {
		closure_wait(&w->wait, parent);
		journal_try_write(c);
	} else if (!w->dirty) {
		w->dirty = true;
		schedule_delayed_work(&c->journal.work,
				      msecs_to_jiffies(c->journal_delay_ms));
		spin_unlock(&c->journal.lock);
	} else {
		spin_unlock(&c->journal.lock);
	}


	return ret;
}

void bch_journal_meta(struct cache_set *c, struct closure *cl)
{
	struct keylist keys;
	atomic_t *ref;

	bch_keylist_init(&keys);

	ref = bch_journal(c, &keys, cl);
	if (ref)
		atomic_dec_bug(ref);
}

void bch_journal_free(struct cache_set *c)
{
	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
	free_fifo(&c->journal.pin);
	free_heap(&c->flush_btree);
}

int bch_journal_alloc(struct cache_set *c)
{
	struct journal *j = &c->journal;

	spin_lock_init(&j->lock);
	INIT_DELAYED_WORK(&j->work, journal_write_work);

	c->journal_delay_ms = 100;

	j->w[0].c = c;
	j->w[1].c = c;

	if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
	    !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
		return -ENOMEM;

	return 0;
}