summaryrefslogtreecommitdiffstats
path: root/drivers/block/drbd/drbd_actlog.c
blob: 2096628d6e65502936c26be63f3706ab1b0209b1 (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
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
/*
   drbd_actlog.c

   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.

   Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
   Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
   Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.

   drbd is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   drbd is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with drbd; see the file COPYING.  If not, write to
   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#include <linux/slab.h>
#include <linux/drbd.h>
#include "drbd_int.h"
#include "drbd_wrappers.h"

/* We maintain a trivial check sum in our on disk activity log.
 * With that we can ensure correct operation even when the storage
 * device might do a partial (last) sector write while loosing power.
 */
struct __packed al_transaction {
	u32       magic;
	u32       tr_number;
	struct __packed {
		u32 pos;
		u32 extent; } updates[1 + AL_EXTENTS_PT];
	u32       xor_sum;
};

struct update_odbm_work {
	struct drbd_work w;
	unsigned int enr;
};

struct update_al_work {
	struct drbd_work w;
	struct lc_element *al_ext;
	struct completion event;
	unsigned int enr;
	/* if old_enr != LC_FREE, write corresponding bitmap sector, too */
	unsigned int old_enr;
};

struct drbd_atodb_wait {
	atomic_t           count;
	struct completion  io_done;
	struct drbd_conf   *mdev;
	int                error;
};


int w_al_write_transaction(struct drbd_conf *, struct drbd_work *, int);

static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
				 struct drbd_backing_dev *bdev,
				 struct page *page, sector_t sector,
				 int rw, int size)
{
	struct bio *bio;
	struct drbd_md_io md_io;
	int ok;

	md_io.mdev = mdev;
	init_completion(&md_io.event);
	md_io.error = 0;

	if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
		rw |= REQ_FUA;
	rw |= REQ_UNPLUG | REQ_SYNC;

	bio = bio_alloc(GFP_NOIO, 1);
	bio->bi_bdev = bdev->md_bdev;
	bio->bi_sector = sector;
	ok = (bio_add_page(bio, page, size, 0) == size);
	if (!ok)
		goto out;
	bio->bi_private = &md_io;
	bio->bi_end_io = drbd_md_io_complete;
	bio->bi_rw = rw;

	if (FAULT_ACTIVE(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
		bio_endio(bio, -EIO);
	else
		submit_bio(rw, bio);
	wait_for_completion(&md_io.event);
	ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0;

 out:
	bio_put(bio);
	return ok;
}

int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
			 sector_t sector, int rw)
{
	int logical_block_size, mask, ok;
	int offset = 0;
	struct page *iop = mdev->md_io_page;

	D_ASSERT(mutex_is_locked(&mdev->md_io_mutex));

	BUG_ON(!bdev->md_bdev);

	logical_block_size = bdev_logical_block_size(bdev->md_bdev);
	if (logical_block_size == 0)
		logical_block_size = MD_SECTOR_SIZE;

	/* in case logical_block_size != 512 [ s390 only? ] */
	if (logical_block_size != MD_SECTOR_SIZE) {
		mask = (logical_block_size / MD_SECTOR_SIZE) - 1;
		D_ASSERT(mask == 1 || mask == 3 || mask == 7);
		D_ASSERT(logical_block_size == (mask+1) * MD_SECTOR_SIZE);
		offset = sector & mask;
		sector = sector & ~mask;
		iop = mdev->md_io_tmpp;

		if (rw & WRITE) {
			/* these are GFP_KERNEL pages, pre-allocated
			 * on device initialization */
			void *p = page_address(mdev->md_io_page);
			void *hp = page_address(mdev->md_io_tmpp);

			ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector,
					READ, logical_block_size);

			if (unlikely(!ok)) {
				dev_err(DEV, "drbd_md_sync_page_io(,%llus,"
				    "READ [logical_block_size!=512]) failed!\n",
				    (unsigned long long)sector);
				return 0;
			}

			memcpy(hp + offset*MD_SECTOR_SIZE, p, MD_SECTOR_SIZE);
		}
	}

	if (sector < drbd_md_first_sector(bdev) ||
	    sector > drbd_md_last_sector(bdev))
		dev_alert(DEV, "%s [%d]:%s(,%llus,%s) out of range md access!\n",
		     current->comm, current->pid, __func__,
		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");

	ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, logical_block_size);
	if (unlikely(!ok)) {
		dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed!\n",
		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
		return 0;
	}

	if (logical_block_size != MD_SECTOR_SIZE && !(rw & WRITE)) {
		void *p = page_address(mdev->md_io_page);
		void *hp = page_address(mdev->md_io_tmpp);

		memcpy(p, hp + offset*MD_SECTOR_SIZE, MD_SECTOR_SIZE);
	}

	return ok;
}

static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr)
{
	struct lc_element *al_ext;
	struct lc_element *tmp;
	unsigned long     al_flags = 0;

	spin_lock_irq(&mdev->al_lock);
	tmp = lc_find(mdev->resync, enr/AL_EXT_PER_BM_SECT);
	if (unlikely(tmp != NULL)) {
		struct bm_extent  *bm_ext = lc_entry(tmp, struct bm_extent, lce);
		if (test_bit(BME_NO_WRITES, &bm_ext->flags)) {
			spin_unlock_irq(&mdev->al_lock);
			return NULL;
		}
	}
	al_ext   = lc_get(mdev->act_log, enr);
	al_flags = mdev->act_log->flags;
	spin_unlock_irq(&mdev->al_lock);

	/*
	if (!al_ext) {
		if (al_flags & LC_STARVING)
			dev_warn(DEV, "Have to wait for LRU element (AL too small?)\n");
		if (al_flags & LC_DIRTY)
			dev_warn(DEV, "Ongoing AL update (AL device too slow?)\n");
	}
	*/

	return al_ext;
}

void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector)
{
	unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9));
	struct lc_element *al_ext;
	struct update_al_work al_work;

	D_ASSERT(atomic_read(&mdev->local_cnt) > 0);

	wait_event(mdev->al_wait, (al_ext = _al_get(mdev, enr)));

	if (al_ext->lc_number != enr) {
		/* drbd_al_write_transaction(mdev,al_ext,enr);
		 * recurses into generic_make_request(), which
		 * disallows recursion, bios being serialized on the
		 * current->bio_tail list now.
		 * we have to delegate updates to the activity log
		 * to the worker thread. */
		init_completion(&al_work.event);
		al_work.al_ext = al_ext;
		al_work.enr = enr;
		al_work.old_enr = al_ext->lc_number;
		al_work.w.cb = w_al_write_transaction;
		drbd_queue_work_front(&mdev->data.work, &al_work.w);
		wait_for_completion(&al_work.event);

		mdev->al_writ_cnt++;

		spin_lock_irq(&mdev->al_lock);
		lc_changed(mdev->act_log, al_ext);
		spin_unlock_irq(&mdev->al_lock);
		wake_up(&mdev->al_wait);
	}
}

void drbd_al_complete_io(struct drbd_conf *mdev, sector_t sector)
{
	unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9));
	struct lc_element *extent;
	unsigned long flags;

	spin_lock_irqsave(&mdev->al_lock, flags);

	extent = lc_find(mdev->act_log, enr);

	if (!extent) {
		spin_unlock_irqrestore(&mdev->al_lock, flags);
		dev_err(DEV, "al_complete_io() called on inactive extent %u\n", enr);
		return;
	}

	if (lc_put(mdev->act_log, extent) == 0)
		wake_up(&mdev->al_wait);

	spin_unlock_irqrestore(&mdev->al_lock, flags);
}

int
w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct update_al_work *aw = container_of(w, struct update_al_work, w);
	struct lc_element *updated = aw->al_ext;
	const unsigned int new_enr = aw->enr;
	const unsigned int evicted = aw->old_enr;
	struct al_transaction *buffer;
	sector_t sector;
	int i, n, mx;
	unsigned int extent_nr;
	u32 xor_sum = 0;

	if (!get_ldev(mdev)) {
		dev_err(DEV,
			"disk is %s, cannot start al transaction (-%d +%d)\n",
			drbd_disk_str(mdev->state.disk), evicted, new_enr);
		complete(&((struct update_al_work *)w)->event);
		return 1;
	}
	/* do we have to do a bitmap write, first?
	 * TODO reduce maximum latency:
	 * submit both bios, then wait for both,
	 * instead of doing two synchronous sector writes.
	 * For now, we must not write the transaction,
	 * if we cannot write out the bitmap of the evicted extent. */
	if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE)
		drbd_bm_write_sect(mdev, evicted/AL_EXT_PER_BM_SECT);

	/* The bitmap write may have failed, causing a state change. */
	if (mdev->state.disk < D_INCONSISTENT) {
		dev_err(DEV,
			"disk is %s, cannot write al transaction (-%d +%d)\n",
			drbd_disk_str(mdev->state.disk), evicted, new_enr);
		complete(&((struct update_al_work *)w)->event);
		put_ldev(mdev);
		return 1;
	}

	mutex_lock(&mdev->md_io_mutex); /* protects md_io_buffer, al_tr_cycle, ... */
	buffer = (struct al_transaction *)page_address(mdev->md_io_page);

	buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC);
	buffer->tr_number = cpu_to_be32(mdev->al_tr_number);

	n = lc_index_of(mdev->act_log, updated);

	buffer->updates[0].pos = cpu_to_be32(n);
	buffer->updates[0].extent = cpu_to_be32(new_enr);

	xor_sum ^= new_enr;

	mx = min_t(int, AL_EXTENTS_PT,
		   mdev->act_log->nr_elements - mdev->al_tr_cycle);
	for (i = 0; i < mx; i++) {
		unsigned idx = mdev->al_tr_cycle + i;
		extent_nr = lc_element_by_index(mdev->act_log, idx)->lc_number;
		buffer->updates[i+1].pos = cpu_to_be32(idx);
		buffer->updates[i+1].extent = cpu_to_be32(extent_nr);
		xor_sum ^= extent_nr;
	}
	for (; i < AL_EXTENTS_PT; i++) {
		buffer->updates[i+1].pos = __constant_cpu_to_be32(-1);
		buffer->updates[i+1].extent = __constant_cpu_to_be32(LC_FREE);
		xor_sum ^= LC_FREE;
	}
	mdev->al_tr_cycle += AL_EXTENTS_PT;
	if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
		mdev->al_tr_cycle = 0;

	buffer->xor_sum = cpu_to_be32(xor_sum);

	sector =  mdev->ldev->md.md_offset
		+ mdev->ldev->md.al_offset + mdev->al_tr_pos;

	if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE))
		drbd_chk_io_error(mdev, 1, TRUE);

	if (++mdev->al_tr_pos >
	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
		mdev->al_tr_pos = 0;

	D_ASSERT(mdev->al_tr_pos < MD_AL_MAX_SIZE);
	mdev->al_tr_number++;

	mutex_unlock(&mdev->md_io_mutex);

	complete(&((struct update_al_work *)w)->event);
	put_ldev(mdev);

	return 1;
}

/**
 * drbd_al_read_tr() - Read a single transaction from the on disk activity log
 * @mdev:	DRBD device.
 * @bdev:	Block device to read form.
 * @b:		pointer to an al_transaction.
 * @index:	On disk slot of the transaction to read.
 *
 * Returns -1 on IO error, 0 on checksum error and 1 upon success.
 */
static int drbd_al_read_tr(struct drbd_conf *mdev,
			   struct drbd_backing_dev *bdev,
			   struct al_transaction *b,
			   int index)
{
	sector_t sector;
	int rv, i;
	u32 xor_sum = 0;

	sector = bdev->md.md_offset + bdev->md.al_offset + index;

	/* Dont process error normally,
	 * as this is done before disk is attached! */
	if (!drbd_md_sync_page_io(mdev, bdev, sector, READ))
		return -1;

	rv = (be32_to_cpu(b->magic) == DRBD_MAGIC);

	for (i = 0; i < AL_EXTENTS_PT + 1; i++)
		xor_sum ^= be32_to_cpu(b->updates[i].extent);
	rv &= (xor_sum == be32_to_cpu(b->xor_sum));

	return rv;
}

/**
 * drbd_al_read_log() - Restores the activity log from its on disk representation.
 * @mdev:	DRBD device.
 * @bdev:	Block device to read form.
 *
 * Returns 1 on success, returns 0 when reading the log failed due to IO errors.
 */
int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
{
	struct al_transaction *buffer;
	int i;
	int rv;
	int mx;
	int active_extents = 0;
	int transactions = 0;
	int found_valid = 0;
	int from = 0;
	int to = 0;
	u32 from_tnr = 0;
	u32 to_tnr = 0;
	u32 cnr;

	mx = div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT);

	/* lock out all other meta data io for now,
	 * and make sure the page is mapped.
	 */
	mutex_lock(&mdev->md_io_mutex);
	buffer = page_address(mdev->md_io_page);

	/* Find the valid transaction in the log */
	for (i = 0; i <= mx; i++) {
		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
		if (rv == 0)
			continue;
		if (rv == -1) {
			mutex_unlock(&mdev->md_io_mutex);
			return 0;
		}
		cnr = be32_to_cpu(buffer->tr_number);

		if (++found_valid == 1) {
			from = i;
			to = i;
			from_tnr = cnr;
			to_tnr = cnr;
			continue;
		}
		if ((int)cnr - (int)from_tnr < 0) {
			D_ASSERT(from_tnr - cnr + i - from == mx+1);
			from = i;
			from_tnr = cnr;
		}
		if ((int)cnr - (int)to_tnr > 0) {
			D_ASSERT(cnr - to_tnr == i - to);
			to = i;
			to_tnr = cnr;
		}
	}

	if (!found_valid) {
		dev_warn(DEV, "No usable activity log found.\n");
		mutex_unlock(&mdev->md_io_mutex);
		return 1;
	}

	/* Read the valid transactions.
	 * dev_info(DEV, "Reading from %d to %d.\n",from,to); */
	i = from;
	while (1) {
		int j, pos;
		unsigned int extent_nr;
		unsigned int trn;

		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
		ERR_IF(rv == 0) goto cancel;
		if (rv == -1) {
			mutex_unlock(&mdev->md_io_mutex);
			return 0;
		}

		trn = be32_to_cpu(buffer->tr_number);

		spin_lock_irq(&mdev->al_lock);

		/* This loop runs backwards because in the cyclic
		   elements there might be an old version of the
		   updated element (in slot 0). So the element in slot 0
		   can overwrite old versions. */
		for (j = AL_EXTENTS_PT; j >= 0; j--) {
			pos = be32_to_cpu(buffer->updates[j].pos);
			extent_nr = be32_to_cpu(buffer->updates[j].extent);

			if (extent_nr == LC_FREE)
				continue;

			lc_set(mdev->act_log, extent_nr, pos);
			active_extents++;
		}
		spin_unlock_irq(&mdev->al_lock);

		transactions++;

cancel:
		if (i == to)
			break;
		i++;
		if (i > mx)
			i = 0;
	}

	mdev->al_tr_number = to_tnr+1;
	mdev->al_tr_pos = to;
	if (++mdev->al_tr_pos >
	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
		mdev->al_tr_pos = 0;

	/* ok, we are done with it */
	mutex_unlock(&mdev->md_io_mutex);

	dev_info(DEV, "Found %d transactions (%d active extents) in activity log.\n",
	     transactions, active_extents);

	return 1;
}

static void atodb_endio(struct bio *bio, int error)
{
	struct drbd_atodb_wait *wc = bio->bi_private;
	struct drbd_conf *mdev = wc->mdev;
	struct page *page;
	int uptodate = bio_flagged(bio, BIO_UPTODATE);

	/* strange behavior of some lower level drivers...
	 * fail the request by clearing the uptodate flag,
	 * but do not return any error?! */
	if (!error && !uptodate)
		error = -EIO;

	drbd_chk_io_error(mdev, error, TRUE);
	if (error && wc->error == 0)
		wc->error = error;

	if (atomic_dec_and_test(&wc->count))
		complete(&wc->io_done);

	page = bio->bi_io_vec[0].bv_page;
	put_page(page);
	bio_put(bio);
	mdev->bm_writ_cnt++;
	put_ldev(mdev);
}

/* sector to word */
#define S2W(s)	((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))

/* activity log to on disk bitmap -- prepare bio unless that sector
 * is already covered by previously prepared bios */
static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
					struct bio **bios,
					unsigned int enr,
					struct drbd_atodb_wait *wc) __must_hold(local)
{
	struct bio *bio;
	struct page *page;
	sector_t on_disk_sector;
	unsigned int page_offset = PAGE_SIZE;
	int offset;
	int i = 0;
	int err = -ENOMEM;

	/* We always write aligned, full 4k blocks,
	 * so we can ignore the logical_block_size (for now) */
	enr &= ~7U;
	on_disk_sector = enr + mdev->ldev->md.md_offset
			     + mdev->ldev->md.bm_offset;

	D_ASSERT(!(on_disk_sector & 7U));

	/* Check if that enr is already covered by an already created bio.
	 * Caution, bios[] is not NULL terminated,
	 * but only initialized to all NULL.
	 * For completely scattered activity log,
	 * the last invocation iterates over all bios,
	 * and finds the last NULL entry.
	 */
	while ((bio = bios[i])) {
		if (bio->bi_sector == on_disk_sector)
			return 0;
		i++;
	}
	/* bios[i] == NULL, the next not yet used slot */

	/* GFP_KERNEL, we are not in the write-out path */
	bio = bio_alloc(GFP_KERNEL, 1);
	if (bio == NULL)
		return -ENOMEM;

	if (i > 0) {
		const struct bio_vec *prev_bv = bios[i-1]->bi_io_vec;
		page_offset = prev_bv->bv_offset + prev_bv->bv_len;
		page = prev_bv->bv_page;
	}
	if (page_offset == PAGE_SIZE) {
		page = alloc_page(__GFP_HIGHMEM);
		if (page == NULL)
			goto out_bio_put;
		page_offset = 0;
	} else {
		get_page(page);
	}

	offset = S2W(enr);
	drbd_bm_get_lel(mdev, offset,
			min_t(size_t, S2W(8), drbd_bm_words(mdev) - offset),
			kmap(page) + page_offset);
	kunmap(page);

	bio->bi_private = wc;
	bio->bi_end_io = atodb_endio;
	bio->bi_bdev = mdev->ldev->md_bdev;
	bio->bi_sector = on_disk_sector;

	if (bio_add_page(bio, page, 4096, page_offset) != 4096)
		goto out_put_page;

	atomic_inc(&wc->count);
	/* we already know that we may do this...
	 * get_ldev_if_state(mdev,D_ATTACHING);
	 * just get the extra reference, so that the local_cnt reflects
	 * the number of pending IO requests DRBD at its backing device.
	 */
	atomic_inc(&mdev->local_cnt);

	bios[i] = bio;

	return 0;

out_put_page:
	err = -EINVAL;
	put_page(page);
out_bio_put:
	bio_put(bio);
	return err;
}

/**
 * drbd_al_to_on_disk_bm() -  * Writes bitmap parts covered by active AL extents
 * @mdev:	DRBD device.
 *
 * Called when we detach (unconfigure) local storage,
 * or when we go from R_PRIMARY to R_SECONDARY role.
 */
void drbd_al_to_on_disk_bm(struct drbd_conf *mdev)
{
	int i, nr_elements;
	unsigned int enr;
	struct bio **bios;
	struct drbd_atodb_wait wc;

	ERR_IF (!get_ldev_if_state(mdev, D_ATTACHING))
		return; /* sorry, I don't have any act_log etc... */

	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));

	nr_elements = mdev->act_log->nr_elements;

	/* GFP_KERNEL, we are not in anyone's write-out path */
	bios = kzalloc(sizeof(struct bio *) * nr_elements, GFP_KERNEL);
	if (!bios)
		goto submit_one_by_one;

	atomic_set(&wc.count, 0);
	init_completion(&wc.io_done);
	wc.mdev = mdev;
	wc.error = 0;

	for (i = 0; i < nr_elements; i++) {
		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
		if (enr == LC_FREE)
			continue;
		/* next statement also does atomic_inc wc.count and local_cnt */
		if (atodb_prepare_unless_covered(mdev, bios,
						enr/AL_EXT_PER_BM_SECT,
						&wc))
			goto free_bios_submit_one_by_one;
	}

	/* unnecessary optimization? */
	lc_unlock(mdev->act_log);
	wake_up(&mdev->al_wait);

	/* all prepared, submit them */
	for (i = 0; i < nr_elements; i++) {
		if (bios[i] == NULL)
			break;
		if (FAULT_ACTIVE(mdev, DRBD_FAULT_MD_WR)) {
			bios[i]->bi_rw = WRITE;
			bio_endio(bios[i], -EIO);
		} else {
			submit_bio(WRITE, bios[i]);
		}
	}

	/* always (try to) flush bitmap to stable storage */
	drbd_md_flush(mdev);

	/* In case we did not submit a single IO do not wait for
	 * them to complete. ( Because we would wait forever here. )
	 *
	 * In case we had IOs and they are already complete, there
	 * is not point in waiting anyways.
	 * Therefore this if () ... */
	if (atomic_read(&wc.count))
		wait_for_completion(&wc.io_done);

	put_ldev(mdev);

	kfree(bios);
	return;

 free_bios_submit_one_by_one:
	/* free everything by calling the endio callback directly. */
	for (i = 0; i < nr_elements && bios[i]; i++)
		bio_endio(bios[i], 0);

	kfree(bios);

 submit_one_by_one:
	dev_warn(DEV, "Using the slow drbd_al_to_on_disk_bm()\n");

	for (i = 0; i < mdev->act_log->nr_elements; i++) {
		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
		if (enr == LC_FREE)
			continue;
		/* Really slow: if we have al-extents 16..19 active,
		 * sector 4 will be written four times! Synchronous! */
		drbd_bm_write_sect(mdev, enr/AL_EXT_PER_BM_SECT);
	}

	lc_unlock(mdev->act_log);
	wake_up(&mdev->al_wait);
	put_ldev(mdev);
}

/**
 * drbd_al_apply_to_bm() - Sets the bitmap to diry(1) where covered ba active AL extents
 * @mdev:	DRBD device.
 */
void drbd_al_apply_to_bm(struct drbd_conf *mdev)
{
	unsigned int enr;
	unsigned long add = 0;
	char ppb[10];
	int i, tmp;

	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));

	for (i = 0; i < mdev->act_log->nr_elements; i++) {
		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
		if (enr == LC_FREE)
			continue;
		tmp = drbd_bm_ALe_set_all(mdev, enr);
		dynamic_dev_dbg(DEV, "AL: set %d bits in extent %u\n", tmp, enr);
		add += tmp;
	}

	lc_unlock(mdev->act_log);
	wake_up(&mdev->al_wait);

	dev_info(DEV, "Marked additional %s as out-of-sync based on AL.\n",
	     ppsize(ppb, Bit2KB(add)));
}

static int _try_lc_del(struct drbd_conf *mdev, struct lc_element *al_ext)
{
	int rv;

	spin_lock_irq(&mdev->al_lock);
	rv = (al_ext->refcnt == 0);
	if (likely(rv))
		lc_del(mdev->act_log, al_ext);
	spin_unlock_irq(&mdev->al_lock);

	return rv;
}

/**
 * drbd_al_shrink() - Removes all active extents form the activity log
 * @mdev:	DRBD device.
 *
 * Removes all active extents form the activity log, waiting until
 * the reference count of each entry dropped to 0 first, of course.
 *
 * You need to lock mdev->act_log with lc_try_lock() / lc_unlock()
 */
void drbd_al_shrink(struct drbd_conf *mdev)
{
	struct lc_element *al_ext;
	int i;

	D_ASSERT(test_bit(__LC_DIRTY, &mdev->act_log->flags));

	for (i = 0; i < mdev->act_log->nr_elements; i++) {
		al_ext = lc_element_by_index(mdev->act_log, i);
		if (al_ext->lc_number == LC_FREE)
			continue;
		wait_event(mdev->al_wait, _try_lc_del(mdev, al_ext));
	}

	wake_up(&mdev->al_wait);
}

static int w_update_odbm(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w);

	if (!get_ldev(mdev)) {
		if (__ratelimit(&drbd_ratelimit_state))
			dev_warn(DEV, "Can not update on disk bitmap, local IO disabled.\n");
		kfree(udw);
		return 1;
	}

	drbd_bm_write_sect(mdev, udw->enr);
	put_ldev(mdev);

	kfree(udw);

	if (drbd_bm_total_weight(mdev) <= mdev->rs_failed) {
		switch (mdev->state.conn) {
		case C_SYNC_SOURCE:  case C_SYNC_TARGET:
		case C_PAUSED_SYNC_S: case C_PAUSED_SYNC_T:
			drbd_resync_finished(mdev);
		default:
			/* nothing to do */
			break;
		}
	}
	drbd_bcast_sync_progress(mdev);

	return 1;
}


/* ATTENTION. The AL's extents are 4MB each, while the extents in the
 * resync LRU-cache are 16MB each.
 * The caller of this function has to hold an get_ldev() reference.
 *
 * TODO will be obsoleted once we have a caching lru of the on disk bitmap
 */
static void drbd_try_clear_on_disk_bm(struct drbd_conf *mdev, sector_t sector,
				      int count, int success)
{
	struct lc_element *e;
	struct update_odbm_work *udw;

	unsigned int enr;

	D_ASSERT(atomic_read(&mdev->local_cnt));

	/* I simply assume that a sector/size pair never crosses
	 * a 16 MB extent border. (Currently this is true...) */
	enr = BM_SECT_TO_EXT(sector);

	e = lc_get(mdev->resync, enr);
	if (e) {
		struct bm_extent *ext = lc_entry(e, struct bm_extent, lce);
		if (ext->lce.lc_number == enr) {
			if (success)
				ext->rs_left -= count;
			else
				ext->rs_failed += count;
			if (ext->rs_left < ext->rs_failed) {
				dev_err(DEV, "BAD! sector=%llus enr=%u rs_left=%d "
				    "rs_failed=%d count=%d\n",
				     (unsigned long long)sector,
				     ext->lce.lc_number, ext->rs_left,
				     ext->rs_failed, count);
				dump_stack();

				lc_put(mdev->resync, &ext->lce);
				drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
				return;
			}
		} else {
			/* Normally this element should be in the cache,
			 * since drbd_rs_begin_io() pulled it already in.
			 *
			 * But maybe an application write finished, and we set
			 * something outside the resync lru_cache in sync.
			 */
			int rs_left = drbd_bm_e_weight(mdev, enr);
			if (ext->flags != 0) {
				dev_warn(DEV, "changing resync lce: %d[%u;%02lx]"
				     " -> %d[%u;00]\n",
				     ext->lce.lc_number, ext->rs_left,
				     ext->flags, enr, rs_left);
				ext->flags = 0;
			}
			if (ext->rs_failed) {
				dev_warn(DEV, "Kicking resync_lru element enr=%u "
				     "out with rs_failed=%d\n",
				     ext->lce.lc_number, ext->rs_failed);
				set_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags);
			}
			ext->rs_left = rs_left;
			ext->rs_failed = success ? 0 : count;
			lc_changed(mdev->resync, &ext->lce);
		}
		lc_put(mdev->resync, &ext->lce);
		/* no race, we are within the al_lock! */

		if (ext->rs_left == ext->rs_failed) {
			ext->rs_failed = 0;

			udw = kmalloc(sizeof(*udw), GFP_ATOMIC);
			if (udw) {
				udw->enr = ext->lce.lc_number;
				udw->w.cb = w_update_odbm;
				drbd_queue_work_front(&mdev->data.work, &udw->w);
			} else {
				dev_warn(DEV, "Could not kmalloc an udw\n");
				set_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags);
			}
		}
	} else {
		dev_err(DEV, "lc_get() failed! locked=%d/%d flags=%lu\n",
		    mdev->resync_locked,
		    mdev->resync->nr_elements,
		    mdev->resync->flags);
	}
}

/* clear the bit corresponding to the piece of storage in question:
 * size byte of data starting from sector.  Only clear a bits of the affected
 * one ore more _aligned_ BM_BLOCK_SIZE blocks.
 *
 * called by worker on C_SYNC_TARGET and receiver on SyncSource.
 *
 */
void __drbd_set_in_sync(struct drbd_conf *mdev, sector_t sector, int size,
		       const char *file, const unsigned int line)
{
	/* Is called from worker and receiver context _only_ */
	unsigned long sbnr, ebnr, lbnr;
	unsigned long count = 0;
	sector_t esector, nr_sectors;
	int wake_up = 0;
	unsigned long flags;

	if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) {
		dev_err(DEV, "drbd_set_in_sync: sector=%llus size=%d nonsense!\n",
				(unsigned long long)sector, size);
		return;
	}
	nr_sectors = drbd_get_capacity(mdev->this_bdev);
	esector = sector + (size >> 9) - 1;

	ERR_IF(sector >= nr_sectors) return;
	ERR_IF(esector >= nr_sectors) esector = (nr_sectors-1);

	lbnr = BM_SECT_TO_BIT(nr_sectors-1);

	/* we clear it (in sync).
	 * round up start sector, round down end sector.  we make sure we only
	 * clear full, aligned, BM_BLOCK_SIZE (4K) blocks */
	if (unlikely(esector < BM_SECT_PER_BIT-1))
		return;
	if (unlikely(esector == (nr_sectors-1)))
		ebnr = lbnr;
	else
		ebnr = BM_SECT_TO_BIT(esector - (BM_SECT_PER_BIT-1));
	sbnr = BM_SECT_TO_BIT(sector + BM_SECT_PER_BIT-1);

	if (sbnr > ebnr)
		return;

	/*
	 * ok, (capacity & 7) != 0 sometimes, but who cares...
	 * we count rs_{total,left} in bits, not sectors.
	 */
	count = drbd_bm_clear_bits(mdev, sbnr, ebnr);
	if (count && get_ldev(mdev)) {
		unsigned long now = jiffies;
		unsigned long last = mdev->rs_mark_time[mdev->rs_last_mark];
		int next = (mdev->rs_last_mark + 1) % DRBD_SYNC_MARKS;
		if (time_after_eq(now, last + DRBD_SYNC_MARK_STEP)) {
			unsigned long tw = drbd_bm_total_weight(mdev);
			if (mdev->rs_mark_left[mdev->rs_last_mark] != tw &&
			    mdev->state.conn != C_PAUSED_SYNC_T &&
			    mdev->state.conn != C_PAUSED_SYNC_S) {
				mdev->rs_mark_time[next] = now;
				mdev->rs_mark_left[next] = tw;
				mdev->rs_last_mark = next;
			}
		}
		spin_lock_irqsave(&mdev->al_lock, flags);
		drbd_try_clear_on_disk_bm(mdev, sector, count, TRUE);
		spin_unlock_irqrestore(&mdev->al_lock, flags);

		/* just wake_up unconditional now, various lc_chaged(),
		 * lc_put() in drbd_try_clear_on_disk_bm(). */
		wake_up = 1;
		put_ldev(mdev);
	}
	if (wake_up)
		wake_up(&mdev->al_wait);
}

/*
 * this is intended to set one request worth of data out of sync.
 * affects at least 1 bit,
 * and at most 1+DRBD_MAX_SEGMENT_SIZE/BM_BLOCK_SIZE bits.
 *
 * called by tl_clear and drbd_send_dblock (==drbd_make_request).
 * so this can be _any_ process.
 */
void __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, int size,
			    const char *file, const unsigned int line)
{
	unsigned long sbnr, ebnr, lbnr, flags;
	sector_t esector, nr_sectors;
	unsigned int enr, count;
	struct lc_element *e;

	if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) {
		dev_err(DEV, "sector: %llus, size: %d\n",
			(unsigned long long)sector, size);
		return;
	}

	if (!get_ldev(mdev))
		return; /* no disk, no metadata, no bitmap to set bits in */

	nr_sectors = drbd_get_capacity(mdev->this_bdev);
	esector = sector + (size >> 9) - 1;

	ERR_IF(sector >= nr_sectors)
		goto out;
	ERR_IF(esector >= nr_sectors)
		esector = (nr_sectors-1);

	lbnr = BM_SECT_TO_BIT(nr_sectors-1);

	/* we set it out of sync,
	 * we do not need to round anything here */
	sbnr = BM_SECT_TO_BIT(sector);
	ebnr = BM_SECT_TO_BIT(esector);

	/* ok, (capacity & 7) != 0 sometimes, but who cares...
	 * we count rs_{total,left} in bits, not sectors.  */
	spin_lock_irqsave(&mdev->al_lock, flags);
	count = drbd_bm_set_bits(mdev, sbnr, ebnr);

	enr = BM_SECT_TO_EXT(sector);
	e = lc_find(mdev->resync, enr);
	if (e)
		lc_entry(e, struct bm_extent, lce)->rs_left += count;
	spin_unlock_irqrestore(&mdev->al_lock, flags);

out:
	put_ldev(mdev);
}

static
struct bm_extent *_bme_get(struct drbd_conf *mdev, unsigned int enr)
{
	struct lc_element *e;
	struct bm_extent *bm_ext;
	int wakeup = 0;
	unsigned long rs_flags;

	spin_lock_irq(&mdev->al_lock);
	if (mdev->resync_locked > mdev->resync->nr_elements/2) {
		spin_unlock_irq(&mdev->al_lock);
		return NULL;
	}
	e = lc_get(mdev->resync, enr);
	bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
	if (bm_ext) {
		if (bm_ext->lce.lc_number != enr) {
			bm_ext->rs_left = drbd_bm_e_weight(mdev, enr);
			bm_ext->rs_failed = 0;
			lc_changed(mdev->resync, &bm_ext->lce);
			wakeup = 1;
		}
		if (bm_ext->lce.refcnt == 1)
			mdev->resync_locked++;
		set_bit(BME_NO_WRITES, &bm_ext->flags);
	}
	rs_flags = mdev->resync->flags;
	spin_unlock_irq(&mdev->al_lock);
	if (wakeup)
		wake_up(&mdev->al_wait);

	if (!bm_ext) {
		if (rs_flags & LC_STARVING)
			dev_warn(DEV, "Have to wait for element"
			     " (resync LRU too small?)\n");
		BUG_ON(rs_flags & LC_DIRTY);
	}

	return bm_ext;
}

static int _is_in_al(struct drbd_conf *mdev, unsigned int enr)
{
	struct lc_element *al_ext;
	int rv = 0;

	spin_lock_irq(&mdev->al_lock);
	if (unlikely(enr == mdev->act_log->new_number))
		rv = 1;
	else {
		al_ext = lc_find(mdev->act_log, enr);
		if (al_ext) {
			if (al_ext->refcnt)
				rv = 1;
		}
	}
	spin_unlock_irq(&mdev->al_lock);

	/*
	if (unlikely(rv)) {
		dev_info(DEV, "Delaying sync read until app's write is done\n");
	}
	*/
	return rv;
}

/**
 * drbd_rs_begin_io() - Gets an extent in the resync LRU cache and sets it to BME_LOCKED
 * @mdev:	DRBD device.
 * @sector:	The sector number.
 *
 * This functions sleeps on al_wait. Returns 0 on success, -EINTR if interrupted.
 */
int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector)
{
	unsigned int enr = BM_SECT_TO_EXT(sector);
	struct bm_extent *bm_ext;
	int i, sig;

	sig = wait_event_interruptible(mdev->al_wait,
			(bm_ext = _bme_get(mdev, enr)));
	if (sig)
		return -EINTR;

	if (test_bit(BME_LOCKED, &bm_ext->flags))
		return 0;

	for (i = 0; i < AL_EXT_PER_BM_SECT; i++) {
		sig = wait_event_interruptible(mdev->al_wait,
				!_is_in_al(mdev, enr * AL_EXT_PER_BM_SECT + i));
		if (sig) {
			spin_lock_irq(&mdev->al_lock);
			if (lc_put(mdev->resync, &bm_ext->lce) == 0) {
				clear_bit(BME_NO_WRITES, &bm_ext->flags);
				mdev->resync_locked--;
				wake_up(&mdev->al_wait);
			}
			spin_unlock_irq(&mdev->al_lock);
			return -EINTR;
		}
	}
	set_bit(BME_LOCKED, &bm_ext->flags);
	return 0;
}

/**
 * drbd_try_rs_begin_io() - Gets an extent in the resync LRU cache, does not sleep
 * @mdev:	DRBD device.
 * @sector:	The sector number.
 *
 * Gets an extent in the resync LRU cache, sets it to BME_NO_WRITES, then
 * tries to set it to BME_LOCKED. Returns 0 upon success, and -EAGAIN
 * if there is still application IO going on in this area.
 */
int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector)
{
	unsigned int enr = BM_SECT_TO_EXT(sector);
	const unsigned int al_enr = enr*AL_EXT_PER_BM_SECT;
	struct lc_element *e;
	struct bm_extent *bm_ext;
	int i;

	spin_lock_irq(&mdev->al_lock);
	if (mdev->resync_wenr != LC_FREE && mdev->resync_wenr != enr) {
		/* in case you have very heavy scattered io, it may
		 * stall the syncer undefined if we give up the ref count
		 * when we try again and requeue.
		 *
		 * if we don't give up the refcount, but the next time
		 * we are scheduled this extent has been "synced" by new
		 * application writes, we'd miss the lc_put on the
		 * extent we keep the refcount on.
		 * so we remembered which extent we had to try again, and
		 * if the next requested one is something else, we do
		 * the lc_put here...
		 * we also have to wake_up
		 */
		e = lc_find(mdev->resync, mdev->resync_wenr);
		bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
		if (bm_ext) {
			D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags));
			D_ASSERT(test_bit(BME_NO_WRITES, &bm_ext->flags));
			clear_bit(BME_NO_WRITES, &bm_ext->flags);
			mdev->resync_wenr = LC_FREE;
			if (lc_put(mdev->resync, &bm_ext->lce) == 0)
				mdev->resync_locked--;
			wake_up(&mdev->al_wait);
		} else {
			dev_alert(DEV, "LOGIC BUG\n");
		}
	}
	/* TRY. */
	e = lc_try_get(mdev->resync, enr);
	bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
	if (bm_ext) {
		if (test_bit(BME_LOCKED, &bm_ext->flags))
			goto proceed;
		if (!test_and_set_bit(BME_NO_WRITES, &bm_ext->flags)) {
			mdev->resync_locked++;
		} else {
			/* we did set the BME_NO_WRITES,
			 * but then could not set BME_LOCKED,
			 * so we tried again.
			 * drop the extra reference. */
			bm_ext->lce.refcnt--;
			D_ASSERT(bm_ext->lce.refcnt > 0);
		}
		goto check_al;
	} else {
		/* do we rather want to try later? */
		if (mdev->resync_locked > mdev->resync->nr_elements-3)
			goto try_again;
		/* Do or do not. There is no try. -- Yoda */
		e = lc_get(mdev->resync, enr);
		bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
		if (!bm_ext) {
			const unsigned long rs_flags = mdev->resync->flags;
			if (rs_flags & LC_STARVING)
				dev_warn(DEV, "Have to wait for element"
				     " (resync LRU too small?)\n");
			BUG_ON(rs_flags & LC_DIRTY);
			goto try_again;
		}
		if (bm_ext->lce.lc_number != enr) {
			bm_ext->rs_left = drbd_bm_e_weight(mdev, enr);
			bm_ext->rs_failed = 0;
			lc_changed(mdev->resync, &bm_ext->lce);
			wake_up(&mdev->al_wait);
			D_ASSERT(test_bit(BME_LOCKED, &bm_ext->flags) == 0);
		}
		set_bit(BME_NO_WRITES, &bm_ext->flags);
		D_ASSERT(bm_ext->lce.refcnt == 1);
		mdev->resync_locked++;
		goto check_al;
	}
check_al:
	for (i = 0; i < AL_EXT_PER_BM_SECT; i++) {
		if (unlikely(al_enr+i == mdev->act_log->new_number))
			goto try_again;
		if (lc_is_used(mdev->act_log, al_enr+i))
			goto try_again;
	}
	set_bit(BME_LOCKED, &bm_ext->flags);
proceed:
	mdev->resync_wenr = LC_FREE;
	spin_unlock_irq(&mdev->al_lock);
	return 0;

try_again:
	if (bm_ext)
		mdev->resync_wenr = enr;
	spin_unlock_irq(&mdev->al_lock);
	return -EAGAIN;
}

void drbd_rs_complete_io(struct drbd_conf *mdev, sector_t sector)
{
	unsigned int enr = BM_SECT_TO_EXT(sector);
	struct lc_element *e;
	struct bm_extent *bm_ext;
	unsigned long flags;

	spin_lock_irqsave(&mdev->al_lock, flags);
	e = lc_find(mdev->resync, enr);
	bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
	if (!bm_ext) {
		spin_unlock_irqrestore(&mdev->al_lock, flags);
		if (__ratelimit(&drbd_ratelimit_state))
			dev_err(DEV, "drbd_rs_complete_io() called, but extent not found\n");
		return;
	}

	if (bm_ext->lce.refcnt == 0) {
		spin_unlock_irqrestore(&mdev->al_lock, flags);
		dev_err(DEV, "drbd_rs_complete_io(,%llu [=%u]) called, "
		    "but refcnt is 0!?\n",
		    (unsigned long long)sector, enr);
		return;
	}

	if (lc_put(mdev->resync, &bm_ext->lce) == 0) {
		clear_bit(BME_LOCKED, &bm_ext->flags);
		clear_bit(BME_NO_WRITES, &bm_ext->flags);
		mdev->resync_locked--;
		wake_up(&mdev->al_wait);
	}

	spin_unlock_irqrestore(&mdev->al_lock, flags);
}

/**
 * drbd_rs_cancel_all() - Removes all extents from the resync LRU (even BME_LOCKED)
 * @mdev:	DRBD device.
 */
void drbd_rs_cancel_all(struct drbd_conf *mdev)
{
	spin_lock_irq(&mdev->al_lock);

	if (get_ldev_if_state(mdev, D_FAILED)) { /* Makes sure ->resync is there. */
		lc_reset(mdev->resync);
		put_ldev(mdev);
	}
	mdev->resync_locked = 0;
	mdev->resync_wenr = LC_FREE;
	spin_unlock_irq(&mdev->al_lock);
	wake_up(&mdev->al_wait);
}

/**
 * drbd_rs_del_all() - Gracefully remove all extents from the resync LRU
 * @mdev:	DRBD device.
 *
 * Returns 0 upon success, -EAGAIN if at least one reference count was
 * not zero.
 */
int drbd_rs_del_all(struct drbd_conf *mdev)
{
	struct lc_element *e;
	struct bm_extent *bm_ext;
	int i;

	spin_lock_irq(&mdev->al_lock);

	if (get_ldev_if_state(mdev, D_FAILED)) {
		/* ok, ->resync is there. */
		for (i = 0; i < mdev->resync->nr_elements; i++) {
			e = lc_element_by_index(mdev->resync, i);
			bm_ext = lc_entry(e, struct bm_extent, lce);
			if (bm_ext->lce.lc_number == LC_FREE)
				continue;
			if (bm_ext->lce.lc_number == mdev->resync_wenr) {
				dev_info(DEV, "dropping %u in drbd_rs_del_all, apparently"
				     " got 'synced' by application io\n",
				     mdev->resync_wenr);
				D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags));
				D_ASSERT(test_bit(BME_NO_WRITES, &bm_ext->flags));
				clear_bit(BME_NO_WRITES, &bm_ext->flags);
				mdev->resync_wenr = LC_FREE;
				lc_put(mdev->resync, &bm_ext->lce);
			}
			if (bm_ext->lce.refcnt != 0) {
				dev_info(DEV, "Retrying drbd_rs_del_all() later. "
				     "refcnt=%d\n", bm_ext->lce.refcnt);
				put_ldev(mdev);
				spin_unlock_irq(&mdev->al_lock);
				return -EAGAIN;
			}
			D_ASSERT(!test_bit(BME_LOCKED, &bm_ext->flags));
			D_ASSERT(!test_bit(BME_NO_WRITES, &bm_ext->flags));
			lc_del(mdev->resync, &bm_ext->lce);
		}
		D_ASSERT(mdev->resync->used == 0);
		put_ldev(mdev);
	}
	spin_unlock_irq(&mdev->al_lock);

	return 0;
}

/**
 * drbd_rs_failed_io() - Record information on a failure to resync the specified blocks
 * @mdev:	DRBD device.
 * @sector:	The sector number.
 * @size:	Size of failed IO operation, in byte.
 */
void drbd_rs_failed_io(struct drbd_conf *mdev, sector_t sector, int size)
{
	/* Is called from worker and receiver context _only_ */
	unsigned long sbnr, ebnr, lbnr;
	unsigned long count;
	sector_t esector, nr_sectors;
	int wake_up = 0;

	if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) {
		dev_err(DEV, "drbd_rs_failed_io: sector=%llus size=%d nonsense!\n",
				(unsigned long long)sector, size);
		return;
	}
	nr_sectors = drbd_get_capacity(mdev->this_bdev);
	esector = sector + (size >> 9) - 1;

	ERR_IF(sector >= nr_sectors) return;
	ERR_IF(esector >= nr_sectors) esector = (nr_sectors-1);

	lbnr = BM_SECT_TO_BIT(nr_sectors-1);

	/*
	 * round up start sector, round down end sector.  we make sure we only
	 * handle full, aligned, BM_BLOCK_SIZE (4K) blocks */
	if (unlikely(esector < BM_SECT_PER_BIT-1))
		return;
	if (unlikely(esector == (nr_sectors-1)))
		ebnr = lbnr;
	else
		ebnr = BM_SECT_TO_BIT(esector - (BM_SECT_PER_BIT-1));
	sbnr = BM_SECT_TO_BIT(sector + BM_SECT_PER_BIT-1);

	if (sbnr > ebnr)
		return;

	/*
	 * ok, (capacity & 7) != 0 sometimes, but who cares...
	 * we count rs_{total,left} in bits, not sectors.
	 */
	spin_lock_irq(&mdev->al_lock);
	count = drbd_bm_count_bits(mdev, sbnr, ebnr);
	if (count) {
		mdev->rs_failed += count;

		if (get_ldev(mdev)) {
			drbd_try_clear_on_disk_bm(mdev, sector, count, FALSE);
			put_ldev(mdev);
		}

		/* just wake_up unconditional now, various lc_chaged(),
		 * lc_put() in drbd_try_clear_on_disk_bm(). */
		wake_up = 1;
	}
	spin_unlock_irq(&mdev->al_lock);
	if (wake_up)
		wake_up(&mdev->al_wait);
}