summaryrefslogtreecommitdiff
path: root/drivers/md/md-cluster.c
blob: 7fbd41e156c973f5d282949512f2a90361812906 (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
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2015, SUSE
 */


#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/dlm.h>
#include <linux/sched.h>
#include <linux/raid/md_p.h>
#include "md.h"
#include "md-bitmap.h"
#include "md-cluster.h"

#define LVB_SIZE	64
#define NEW_DEV_TIMEOUT 5000

struct dlm_lock_resource {
	dlm_lockspace_t *ls;
	struct dlm_lksb lksb;
	char *name; /* lock name. */
	uint32_t flags; /* flags to pass to dlm_lock() */
	wait_queue_head_t sync_locking; /* wait queue for synchronized locking */
	bool sync_locking_done;
	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
	struct mddev *mddev; /* pointing back to mddev. */
	int mode;
};

struct resync_info {
	__le64 lo;
	__le64 hi;
};

/* md_cluster_info flags */
#define		MD_CLUSTER_WAITING_FOR_NEWDISK		1
#define		MD_CLUSTER_SUSPEND_READ_BALANCING	2
#define		MD_CLUSTER_BEGIN_JOIN_CLUSTER		3

/* Lock the send communication. This is done through
 * bit manipulation as opposed to a mutex in order to
 * accomodate lock and hold. See next comment.
 */
#define		MD_CLUSTER_SEND_LOCK			4
/* If cluster operations (such as adding a disk) must lock the
 * communication channel, so as to perform extra operations
 * (update metadata) and no other operation is allowed on the
 * MD. Token needs to be locked and held until the operation
 * completes witha md_update_sb(), which would eventually release
 * the lock.
 */
#define		MD_CLUSTER_SEND_LOCKED_ALREADY		5
/* We should receive message after node joined cluster and
 * set up all the related infos such as bitmap and personality */
#define		MD_CLUSTER_ALREADY_IN_CLUSTER		6
#define		MD_CLUSTER_PENDING_RECV_EVENT		7
#define 	MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD		8

struct md_cluster_info {
	struct mddev *mddev; /* the md device which md_cluster_info belongs to */
	/* dlm lock space and resources for clustered raid. */
	dlm_lockspace_t *lockspace;
	int slot_number;
	struct completion completion;
	struct mutex recv_mutex;
	struct dlm_lock_resource *bitmap_lockres;
	struct dlm_lock_resource **other_bitmap_lockres;
	struct dlm_lock_resource *resync_lockres;
	struct list_head suspend_list;

	spinlock_t suspend_lock;
	/* record the region which write should be suspended */
	sector_t suspend_lo;
	sector_t suspend_hi;
	int suspend_from; /* the slot which broadcast suspend_lo/hi */

	struct md_thread *recovery_thread;
	unsigned long recovery_map;
	/* communication loc resources */
	struct dlm_lock_resource *ack_lockres;
	struct dlm_lock_resource *message_lockres;
	struct dlm_lock_resource *token_lockres;
	struct dlm_lock_resource *no_new_dev_lockres;
	struct md_thread *recv_thread;
	struct completion newdisk_completion;
	wait_queue_head_t wait;
	unsigned long state;
	/* record the region in RESYNCING message */
	sector_t sync_low;
	sector_t sync_hi;
};

enum msg_type {
	METADATA_UPDATED = 0,
	RESYNCING,
	NEWDISK,
	REMOVE,
	RE_ADD,
	BITMAP_NEEDS_SYNC,
	CHANGE_CAPACITY,
	BITMAP_RESIZE,
};

struct cluster_msg {
	__le32 type;
	__le32 slot;
	/* TODO: Unionize this for smaller footprint */
	__le64 low;
	__le64 high;
	char uuid[16];
	__le32 raid_slot;
};

static void sync_ast(void *arg)
{
	struct dlm_lock_resource *res;

	res = arg;
	res->sync_locking_done = true;
	wake_up(&res->sync_locking);
}

static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
{
	int ret = 0;

	ret = dlm_lock(res->ls, mode, &res->lksb,
			res->flags, res->name, strlen(res->name),
			0, sync_ast, res, res->bast);
	if (ret)
		return ret;
	wait_event(res->sync_locking, res->sync_locking_done);
	res->sync_locking_done = false;
	if (res->lksb.sb_status == 0)
		res->mode = mode;
	return res->lksb.sb_status;
}

static int dlm_unlock_sync(struct dlm_lock_resource *res)
{
	return dlm_lock_sync(res, DLM_LOCK_NL);
}

/*
 * An variation of dlm_lock_sync, which make lock request could
 * be interrupted
 */
static int dlm_lock_sync_interruptible(struct dlm_lock_resource *res, int mode,
				       struct mddev *mddev)
{
	int ret = 0;

	ret = dlm_lock(res->ls, mode, &res->lksb,
			res->flags, res->name, strlen(res->name),
			0, sync_ast, res, res->bast);
	if (ret)
		return ret;

	wait_event(res->sync_locking, res->sync_locking_done
				      || kthread_should_stop()
				      || test_bit(MD_CLOSING, &mddev->flags));
	if (!res->sync_locking_done) {
		/*
		 * the convert queue contains the lock request when request is
		 * interrupted, and sync_ast could still be run, so need to
		 * cancel the request and reset completion
		 */
		ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_CANCEL,
			&res->lksb, res);
		res->sync_locking_done = false;
		if (unlikely(ret != 0))
			pr_info("failed to cancel previous lock request "
				 "%s return %d\n", res->name, ret);
		return -EPERM;
	} else
		res->sync_locking_done = false;
	if (res->lksb.sb_status == 0)
		res->mode = mode;
	return res->lksb.sb_status;
}

static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
	struct dlm_lock_resource *res = NULL;
	int ret, namelen;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
	if (!res)
		return NULL;
	init_waitqueue_head(&res->sync_locking);
	res->sync_locking_done = false;
	res->ls = cinfo->lockspace;
	res->mddev = mddev;
	res->mode = DLM_LOCK_IV;
	namelen = strlen(name);
	res->name = kzalloc(namelen + 1, GFP_KERNEL);
	if (!res->name) {
		pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
		goto out_err;
	}
	strlcpy(res->name, name, namelen + 1);
	if (with_lvb) {
		res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
		if (!res->lksb.sb_lvbptr) {
			pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name);
			goto out_err;
		}
		res->flags = DLM_LKF_VALBLK;
	}

	if (bastfn)
		res->bast = bastfn;

	res->flags |= DLM_LKF_EXPEDITE;

	ret = dlm_lock_sync(res, DLM_LOCK_NL);
	if (ret) {
		pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name);
		goto out_err;
	}
	res->flags &= ~DLM_LKF_EXPEDITE;
	res->flags |= DLM_LKF_CONVERT;

	return res;
out_err:
	kfree(res->lksb.sb_lvbptr);
	kfree(res->name);
	kfree(res);
	return NULL;
}

static void lockres_free(struct dlm_lock_resource *res)
{
	int ret = 0;

	if (!res)
		return;

	/*
	 * use FORCEUNLOCK flag, so we can unlock even the lock is on the
	 * waiting or convert queue
	 */
	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_FORCEUNLOCK,
		&res->lksb, res);
	if (unlikely(ret != 0))
		pr_err("failed to unlock %s return %d\n", res->name, ret);
	else
		wait_event(res->sync_locking, res->sync_locking_done);

	kfree(res->name);
	kfree(res->lksb.sb_lvbptr);
	kfree(res);
}

static void add_resync_info(struct dlm_lock_resource *lockres,
			    sector_t lo, sector_t hi)
{
	struct resync_info *ri;

	ri = (struct resync_info *)lockres->lksb.sb_lvbptr;
	ri->lo = cpu_to_le64(lo);
	ri->hi = cpu_to_le64(hi);
}

static int read_resync_info(struct mddev *mddev,
			    struct dlm_lock_resource *lockres)
{
	struct resync_info ri;
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int ret = 0;

	dlm_lock_sync(lockres, DLM_LOCK_CR);
	memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
	if (le64_to_cpu(ri.hi) > 0) {
		cinfo->suspend_hi = le64_to_cpu(ri.hi);
		cinfo->suspend_lo = le64_to_cpu(ri.lo);
		ret = 1;
	}
	dlm_unlock_sync(lockres);
	return ret;
}

static void recover_bitmaps(struct md_thread *thread)
{
	struct mddev *mddev = thread->mddev;
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct dlm_lock_resource *bm_lockres;
	char str[64];
	int slot, ret;
	sector_t lo, hi;

	while (cinfo->recovery_map) {
		slot = fls64((u64)cinfo->recovery_map) - 1;

		snprintf(str, 64, "bitmap%04d", slot);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres) {
			pr_err("md-cluster: Cannot initialize bitmaps\n");
			goto clear_bit;
		}

		ret = dlm_lock_sync_interruptible(bm_lockres, DLM_LOCK_PW, mddev);
		if (ret) {
			pr_err("md-cluster: Could not DLM lock %s: %d\n",
					str, ret);
			goto clear_bit;
		}
		ret = md_bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
		if (ret) {
			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
			goto clear_bit;
		}

		/* Clear suspend_area associated with the bitmap */
		spin_lock_irq(&cinfo->suspend_lock);
		cinfo->suspend_hi = 0;
		cinfo->suspend_lo = 0;
		cinfo->suspend_from = -1;
		spin_unlock_irq(&cinfo->suspend_lock);

		/* Kick off a reshape if needed */
		if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) &&
		    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
		    mddev->reshape_position != MaxSector)
			md_wakeup_thread(mddev->sync_thread);

		if (hi > 0) {
			if (lo < mddev->recovery_cp)
				mddev->recovery_cp = lo;
			/* wake up thread to continue resync in case resync
			 * is not finished */
			if (mddev->recovery_cp != MaxSector) {
				/*
				 * clear the REMOTE flag since we will launch
				 * resync thread in current node.
				 */
				clear_bit(MD_RESYNCING_REMOTE,
					  &mddev->recovery);
				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
				md_wakeup_thread(mddev->thread);
			}
		}
clear_bit:
		lockres_free(bm_lockres);
		clear_bit(slot, &cinfo->recovery_map);
	}
}

static void recover_prep(void *arg)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;
	set_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
}

static void __recover_slot(struct mddev *mddev, int slot)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	set_bit(slot, &cinfo->recovery_map);
	if (!cinfo->recovery_thread) {
		cinfo->recovery_thread = md_register_thread(recover_bitmaps,
				mddev, "recover");
		if (!cinfo->recovery_thread) {
			pr_warn("md-cluster: Could not create recovery thread\n");
			return;
		}
	}
	md_wakeup_thread(cinfo->recovery_thread);
}

static void recover_slot(void *arg, struct dlm_slot *slot)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
			mddev->bitmap_info.cluster_name,
			slot->nodeid, slot->slot,
			cinfo->slot_number);
	/* deduct one since dlm slot starts from one while the num of
	 * cluster-md begins with 0 */
	__recover_slot(mddev, slot->slot - 1);
}

static void recover_done(void *arg, struct dlm_slot *slots,
		int num_slots, int our_slot,
		uint32_t generation)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	cinfo->slot_number = our_slot;
	/* completion is only need to be complete when node join cluster,
	 * it doesn't need to run during another node's failure */
	if (test_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state)) {
		complete(&cinfo->completion);
		clear_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
	}
	clear_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
}

/* the ops is called when node join the cluster, and do lock recovery
 * if node failure occurs */
static const struct dlm_lockspace_ops md_ls_ops = {
	.recover_prep = recover_prep,
	.recover_slot = recover_slot,
	.recover_done = recover_done,
};

/*
 * The BAST function for the ack lock resource
 * This function wakes up the receive thread in
 * order to receive and process the message.
 */
static void ack_bast(void *arg, int mode)
{
	struct dlm_lock_resource *res = arg;
	struct md_cluster_info *cinfo = res->mddev->cluster_info;

	if (mode == DLM_LOCK_EX) {
		if (test_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state))
			md_wakeup_thread(cinfo->recv_thread);
		else
			set_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state);
	}
}

static void remove_suspend_info(struct mddev *mddev, int slot)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	mddev->pers->quiesce(mddev, 1);
	spin_lock_irq(&cinfo->suspend_lock);
	cinfo->suspend_hi = 0;
	cinfo->suspend_lo = 0;
	spin_unlock_irq(&cinfo->suspend_lock);
	mddev->pers->quiesce(mddev, 0);
}

static void process_suspend_info(struct mddev *mddev,
		int slot, sector_t lo, sector_t hi)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct mdp_superblock_1 *sb = NULL;
	struct md_rdev *rdev;

	if (!hi) {
		/*
		 * clear the REMOTE flag since resync or recovery is finished
		 * in remote node.
		 */
		clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
		remove_suspend_info(mddev, slot);
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
		md_wakeup_thread(mddev->thread);
		return;
	}

	rdev_for_each(rdev, mddev)
		if (rdev->raid_disk > -1 && !test_bit(Faulty, &rdev->flags)) {
			sb = page_address(rdev->sb_page);
			break;
		}

	/*
	 * The bitmaps are not same for different nodes
	 * if RESYNCING is happening in one node, then
	 * the node which received the RESYNCING message
	 * probably will perform resync with the region
	 * [lo, hi] again, so we could reduce resync time
	 * a lot if we can ensure that the bitmaps among
	 * different nodes are match up well.
	 *
	 * sync_low/hi is used to record the region which
	 * arrived in the previous RESYNCING message,
	 *
	 * Call md_bitmap_sync_with_cluster to clear NEEDED_MASK
	 * and set RESYNC_MASK since  resync thread is running
	 * in another node, so we don't need to do the resync
	 * again with the same section.
	 *
	 * Skip md_bitmap_sync_with_cluster in case reshape
	 * happening, because reshaping region is small and
	 * we don't want to trigger lots of WARN.
	 */
	if (sb && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE))
		md_bitmap_sync_with_cluster(mddev, cinfo->sync_low,
					    cinfo->sync_hi, lo, hi);
	cinfo->sync_low = lo;
	cinfo->sync_hi = hi;

	mddev->pers->quiesce(mddev, 1);
	spin_lock_irq(&cinfo->suspend_lock);
	cinfo->suspend_from = slot;
	cinfo->suspend_lo = lo;
	cinfo->suspend_hi = hi;
	spin_unlock_irq(&cinfo->suspend_lock);
	mddev->pers->quiesce(mddev, 0);
}

static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
{
	char disk_uuid[64];
	struct md_cluster_info *cinfo = mddev->cluster_info;
	char event_name[] = "EVENT=ADD_DEVICE";
	char raid_slot[16];
	char *envp[] = {event_name, disk_uuid, raid_slot, NULL};
	int len;

	len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
	sprintf(disk_uuid + len, "%pU", cmsg->uuid);
	snprintf(raid_slot, 16, "RAID_DISK=%d", le32_to_cpu(cmsg->raid_slot));
	pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot);
	init_completion(&cinfo->newdisk_completion);
	set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
	kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
	wait_for_completion_timeout(&cinfo->newdisk_completion,
			NEW_DEV_TIMEOUT);
	clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
}


static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
{
	int got_lock = 0;
	struct md_cluster_info *cinfo = mddev->cluster_info;
	mddev->good_device_nr = le32_to_cpu(msg->raid_slot);

	dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
	wait_event(mddev->thread->wqueue,
		   (got_lock = mddev_trylock(mddev)) ||
		    test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state));
	md_reload_sb(mddev, mddev->good_device_nr);
	if (got_lock)
		mddev_unlock(mddev);
}

static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
{
	struct md_rdev *rdev;

	rcu_read_lock();
	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
	if (rdev) {
		set_bit(ClusterRemove, &rdev->flags);
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
		md_wakeup_thread(mddev->thread);
	}
	else
		pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
	rcu_read_unlock();
}

static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
{
	struct md_rdev *rdev;

	rcu_read_lock();
	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
	if (rdev && test_bit(Faulty, &rdev->flags))
		clear_bit(Faulty, &rdev->flags);
	else
		pr_warn("%s: %d Could not find disk(%d) which is faulty",
			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
	rcu_read_unlock();
}

static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{
	int ret = 0;

	if (WARN(mddev->cluster_info->slot_number - 1 == le32_to_cpu(msg->slot),
		"node %d received it's own msg\n", le32_to_cpu(msg->slot)))
		return -1;
	switch (le32_to_cpu(msg->type)) {
	case METADATA_UPDATED:
		process_metadata_update(mddev, msg);
		break;
	case CHANGE_CAPACITY:
		set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
		break;
	case RESYNCING:
		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
		process_suspend_info(mddev, le32_to_cpu(msg->slot),
				     le64_to_cpu(msg->low),
				     le64_to_cpu(msg->high));
		break;
	case NEWDISK:
		process_add_new_disk(mddev, msg);
		break;
	case REMOVE:
		process_remove_disk(mddev, msg);
		break;
	case RE_ADD:
		process_readd_disk(mddev, msg);
		break;
	case BITMAP_NEEDS_SYNC:
		__recover_slot(mddev, le32_to_cpu(msg->slot));
		break;
	case BITMAP_RESIZE:
		if (le64_to_cpu(msg->high) != mddev->pers->size(mddev, 0, 0))
			ret = md_bitmap_resize(mddev->bitmap,
					    le64_to_cpu(msg->high), 0, 0);
		break;
	default:
		ret = -1;
		pr_warn("%s:%d Received unknown message from %d\n",
			__func__, __LINE__, msg->slot);
	}
	return ret;
}

/*
 * thread for receiving message
 */
static void recv_daemon(struct md_thread *thread)
{
	struct md_cluster_info *cinfo = thread->mddev->cluster_info;
	struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres;
	struct dlm_lock_resource *message_lockres = cinfo->message_lockres;
	struct cluster_msg msg;
	int ret;

	mutex_lock(&cinfo->recv_mutex);
	/*get CR on Message*/
	if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) {
		pr_err("md/raid1:failed to get CR on MESSAGE\n");
		mutex_unlock(&cinfo->recv_mutex);
		return;
	}

	/* read lvb and wake up thread to process this message_lockres */
	memcpy(&msg, message_lockres->lksb.sb_lvbptr, sizeof(struct cluster_msg));
	ret = process_recvd_msg(thread->mddev, &msg);
	if (ret)
		goto out;

	/*release CR on ack_lockres*/
	ret = dlm_unlock_sync(ack_lockres);
	if (unlikely(ret != 0))
		pr_info("unlock ack failed return %d\n", ret);
	/*up-convert to PR on message_lockres*/
	ret = dlm_lock_sync(message_lockres, DLM_LOCK_PR);
	if (unlikely(ret != 0))
		pr_info("lock PR on msg failed return %d\n", ret);
	/*get CR on ack_lockres again*/
	ret = dlm_lock_sync(ack_lockres, DLM_LOCK_CR);
	if (unlikely(ret != 0))
		pr_info("lock CR on ack failed return %d\n", ret);
out:
	/*release CR on message_lockres*/
	ret = dlm_unlock_sync(message_lockres);
	if (unlikely(ret != 0))
		pr_info("unlock msg failed return %d\n", ret);
	mutex_unlock(&cinfo->recv_mutex);
}

/* lock_token()
 * Takes the lock on the TOKEN lock resource so no other
 * node can communicate while the operation is underway.
 */
static int lock_token(struct md_cluster_info *cinfo)
{
	int error;

	error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
	if (error) {
		pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
				__func__, __LINE__, error);
	} else {
		/* Lock the receive sequence */
		mutex_lock(&cinfo->recv_mutex);
	}
	return error;
}

/* lock_comm()
 * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel.
 */
static int lock_comm(struct md_cluster_info *cinfo, bool mddev_locked)
{
	int rv, set_bit = 0;
	struct mddev *mddev = cinfo->mddev;

	/*
	 * If resync thread run after raid1d thread, then process_metadata_update
	 * could not continue if raid1d held reconfig_mutex (and raid1d is blocked
	 * since another node already got EX on Token and waitting the EX of Ack),
	 * so let resync wake up thread in case flag is set.
	 */
	if (mddev_locked && !test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
				      &cinfo->state)) {
		rv = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
					      &cinfo->state);
		WARN_ON_ONCE(rv);
		md_wakeup_thread(mddev->thread);
		set_bit = 1;
	}

	wait_event(cinfo->wait,
		   !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state));
	rv = lock_token(cinfo);
	if (set_bit)
		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
	return rv;
}

static void unlock_comm(struct md_cluster_info *cinfo)
{
	WARN_ON(cinfo->token_lockres->mode != DLM_LOCK_EX);
	mutex_unlock(&cinfo->recv_mutex);
	dlm_unlock_sync(cinfo->token_lockres);
	clear_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state);
	wake_up(&cinfo->wait);
}

/* __sendmsg()
 * This function performs the actual sending of the message. This function is
 * usually called after performing the encompassing operation
 * The function:
 * 1. Grabs the message lockresource in EX mode
 * 2. Copies the message to the message LVB
 * 3. Downconverts message lockresource to CW
 * 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes
 *    and the other nodes read the message. The thread will wait here until all other
 *    nodes have released ack lock resource.
 * 5. Downconvert ack lockresource to CR
 */
static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
{
	int error;
	int slot = cinfo->slot_number - 1;

	cmsg->slot = cpu_to_le32(slot);
	/*get EX on Message*/
	error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX);
	if (error) {
		pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error);
		goto failed_message;
	}

	memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg,
			sizeof(struct cluster_msg));
	/*down-convert EX to CW on Message*/
	error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CW);
	if (error) {
		pr_err("md-cluster: failed to convert EX to CW on MESSAGE(%d)\n",
				error);
		goto failed_ack;
	}

	/*up-convert CR to EX on Ack*/
	error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_EX);
	if (error) {
		pr_err("md-cluster: failed to convert CR to EX on ACK(%d)\n",
				error);
		goto failed_ack;
	}

	/*down-convert EX to CR on Ack*/
	error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR);
	if (error) {
		pr_err("md-cluster: failed to convert EX to CR on ACK(%d)\n",
				error);
		goto failed_ack;
	}

failed_ack:
	error = dlm_unlock_sync(cinfo->message_lockres);
	if (unlikely(error != 0)) {
		pr_err("md-cluster: failed convert to NL on MESSAGE(%d)\n",
			error);
		/* in case the message can't be released due to some reason */
		goto failed_ack;
	}
failed_message:
	return error;
}

static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg,
		   bool mddev_locked)
{
	int ret;

	ret = lock_comm(cinfo, mddev_locked);
	if (!ret) {
		ret = __sendmsg(cinfo, cmsg);
		unlock_comm(cinfo);
	}
	return ret;
}

static int gather_all_resync_info(struct mddev *mddev, int total_slots)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int i, ret = 0;
	struct dlm_lock_resource *bm_lockres;
	char str[64];
	sector_t lo, hi;


	for (i = 0; i < total_slots; i++) {
		memset(str, '\0', 64);
		snprintf(str, 64, "bitmap%04d", i);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres)
			return -ENOMEM;
		if (i == (cinfo->slot_number - 1)) {
			lockres_free(bm_lockres);
			continue;
		}

		bm_lockres->flags |= DLM_LKF_NOQUEUE;
		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
		if (ret == -EAGAIN) {
			if (read_resync_info(mddev, bm_lockres)) {
				pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
						__func__, __LINE__,
					(unsigned long long) cinfo->suspend_lo,
					(unsigned long long) cinfo->suspend_hi,
					i);
				cinfo->suspend_from = i;
			}
			ret = 0;
			lockres_free(bm_lockres);
			continue;
		}
		if (ret) {
			lockres_free(bm_lockres);
			goto out;
		}

		/* Read the disk bitmap sb and check if it needs recovery */
		ret = md_bitmap_copy_from_slot(mddev, i, &lo, &hi, false);
		if (ret) {
			pr_warn("md-cluster: Could not gather bitmaps from slot %d", i);
			lockres_free(bm_lockres);
			continue;
		}
		if ((hi > 0) && (lo < mddev->recovery_cp)) {
			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
			mddev->recovery_cp = lo;
			md_check_recovery(mddev);
		}

		lockres_free(bm_lockres);
	}
out:
	return ret;
}

static int join(struct mddev *mddev, int nodes)
{
	struct md_cluster_info *cinfo;
	int ret, ops_rv;
	char str[64];

	cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
	if (!cinfo)
		return -ENOMEM;

	INIT_LIST_HEAD(&cinfo->suspend_list);
	spin_lock_init(&cinfo->suspend_lock);
	init_completion(&cinfo->completion);
	set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
	init_waitqueue_head(&cinfo->wait);
	mutex_init(&cinfo->recv_mutex);

	mddev->cluster_info = cinfo;
	cinfo->mddev = mddev;

	memset(str, 0, 64);
	sprintf(str, "%pU", mddev->uuid);
	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
				DLM_LSFL_FS, LVB_SIZE,
				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
	if (ret)
		goto err;
	wait_for_completion(&cinfo->completion);
	if (nodes < cinfo->slot_number) {
		pr_err("md-cluster: Slot allotted(%d) is greater than available slots(%d).",
			cinfo->slot_number, nodes);
		ret = -ERANGE;
		goto err;
	}
	/* Initiate the communication resources */
	ret = -ENOMEM;
	cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv");
	if (!cinfo->recv_thread) {
		pr_err("md-cluster: cannot allocate memory for recv_thread!\n");
		goto err;
	}
	cinfo->message_lockres = lockres_init(mddev, "message", NULL, 1);
	if (!cinfo->message_lockres)
		goto err;
	cinfo->token_lockres = lockres_init(mddev, "token", NULL, 0);
	if (!cinfo->token_lockres)
		goto err;
	cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0);
	if (!cinfo->no_new_dev_lockres)
		goto err;

	ret = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
	if (ret) {
		ret = -EAGAIN;
		pr_err("md-cluster: can't join cluster to avoid lock issue\n");
		goto err;
	}
	cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
	if (!cinfo->ack_lockres) {
		ret = -ENOMEM;
		goto err;
	}
	/* get sync CR lock on ACK. */
	if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
		pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
				ret);
	dlm_unlock_sync(cinfo->token_lockres);
	/* get sync CR lock on no-new-dev. */
	if (dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR))
		pr_err("md-cluster: failed to get a sync CR lock on no-new-dev!(%d)\n", ret);


	pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
	snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
	cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
	if (!cinfo->bitmap_lockres) {
		ret = -ENOMEM;
		goto err;
	}
	if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
		pr_err("Failed to get bitmap lock\n");
		ret = -EINVAL;
		goto err;
	}

	cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
	if (!cinfo->resync_lockres) {
		ret = -ENOMEM;
		goto err;
	}

	return 0;
err:
	set_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
	md_unregister_thread(&cinfo->recovery_thread);
	md_unregister_thread(&cinfo->recv_thread);
	lockres_free(cinfo->message_lockres);
	lockres_free(cinfo->token_lockres);
	lockres_free(cinfo->ack_lockres);
	lockres_free(cinfo->no_new_dev_lockres);
	lockres_free(cinfo->resync_lockres);
	lockres_free(cinfo->bitmap_lockres);
	if (cinfo->lockspace)
		dlm_release_lockspace(cinfo->lockspace, 2);
	mddev->cluster_info = NULL;
	kfree(cinfo);
	return ret;
}

static void load_bitmaps(struct mddev *mddev, int total_slots)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	/* load all the node's bitmap info for resync */
	if (gather_all_resync_info(mddev, total_slots))
		pr_err("md-cluster: failed to gather all resyn infos\n");
	set_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state);
	/* wake up recv thread in case something need to be handled */
	if (test_and_clear_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state))
		md_wakeup_thread(cinfo->recv_thread);
}

static void resync_bitmap(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct cluster_msg cmsg = {0};
	int err;

	cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);
	err = sendmsg(cinfo, &cmsg, 1);
	if (err)
		pr_err("%s:%d: failed to send BITMAP_NEEDS_SYNC message (%d)\n",
			__func__, __LINE__, err);
}

static void unlock_all_bitmaps(struct mddev *mddev);
static int leave(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	if (!cinfo)
		return 0;

	/*
	 * BITMAP_NEEDS_SYNC message should be sent when node
	 * is leaving the cluster with dirty bitmap, also we
	 * can only deliver it when dlm connection is available.
	 *
	 * Also, we should send BITMAP_NEEDS_SYNC message in
	 * case reshaping is interrupted.
	 */
	if ((cinfo->slot_number > 0 && mddev->recovery_cp != MaxSector) ||
	    (mddev->reshape_position != MaxSector &&
	     test_bit(MD_CLOSING, &mddev->flags)))
		resync_bitmap(mddev);

	set_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
	md_unregister_thread(&cinfo->recovery_thread);
	md_unregister_thread(&cinfo->recv_thread);
	lockres_free(cinfo->message_lockres);
	lockres_free(cinfo->token_lockres);
	lockres_free(cinfo->ack_lockres);
	lockres_free(cinfo->no_new_dev_lockres);
	lockres_free(cinfo->resync_lockres);
	lockres_free(cinfo->bitmap_lockres);
	unlock_all_bitmaps(mddev);
	dlm_release_lockspace(cinfo->lockspace, 2);
	kfree(cinfo);
	return 0;
}

/* slot_number(): Returns the MD slot number to use
 * DLM starts the slot numbers from 1, wheras cluster-md
 * wants the number to be from zero, so we deduct one
 */
static int slot_number(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	return cinfo->slot_number - 1;
}

/*
 * Check if the communication is already locked, else lock the communication
 * channel.
 * If it is already locked, token is in EX mode, and hence lock_token()
 * should not be called.
 */
static int metadata_update_start(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int ret;

	/*
	 * metadata_update_start is always called with the protection of
	 * reconfig_mutex, so set WAITING_FOR_TOKEN here.
	 */
	ret = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
				    &cinfo->state);
	WARN_ON_ONCE(ret);
	md_wakeup_thread(mddev->thread);

	wait_event(cinfo->wait,
		   !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state) ||
		   test_and_clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state));

	/* If token is already locked, return 0 */
	if (cinfo->token_lockres->mode == DLM_LOCK_EX) {
		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
		return 0;
	}

	ret = lock_token(cinfo);
	clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
	return ret;
}

static int metadata_update_finish(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct cluster_msg cmsg;
	struct md_rdev *rdev;
	int ret = 0;
	int raid_slot = -1;

	memset(&cmsg, 0, sizeof(cmsg));
	cmsg.type = cpu_to_le32(METADATA_UPDATED);
	/* Pick up a good active device number to send.
	 */
	rdev_for_each(rdev, mddev)
		if (rdev->raid_disk > -1 && !test_bit(Faulty, &rdev->flags)) {
			raid_slot = rdev->desc_nr;
			break;
		}
	if (raid_slot >= 0) {
		cmsg.raid_slot = cpu_to_le32(raid_slot);
		ret = __sendmsg(cinfo, &cmsg);
	} else
		pr_warn("md-cluster: No good device id found to send\n");
	clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
	unlock_comm(cinfo);
	return ret;
}

static void metadata_update_cancel(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
	unlock_comm(cinfo);
}

static int update_bitmap_size(struct mddev *mddev, sector_t size)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct cluster_msg cmsg = {0};
	int ret;

	cmsg.type = cpu_to_le32(BITMAP_RESIZE);
	cmsg.high = cpu_to_le64(size);
	ret = sendmsg(cinfo, &cmsg, 0);
	if (ret)
		pr_err("%s:%d: failed to send BITMAP_RESIZE message (%d)\n",
			__func__, __LINE__, ret);
	return ret;
}

static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsize)
{
	struct bitmap_counts *counts;
	char str[64];
	struct dlm_lock_resource *bm_lockres;
	struct bitmap *bitmap = mddev->bitmap;
	unsigned long my_pages = bitmap->counts.pages;
	int i, rv;

	/*
	 * We need to ensure all the nodes can grow to a larger
	 * bitmap size before make the reshaping.
	 */
	rv = update_bitmap_size(mddev, newsize);
	if (rv)
		return rv;

	for (i = 0; i < mddev->bitmap_info.nodes; i++) {
		if (i == md_cluster_ops->slot_number(mddev))
			continue;

		bitmap = get_bitmap_from_slot(mddev, i);
		if (IS_ERR(bitmap)) {
			pr_err("can't get bitmap from slot %d\n", i);
			bitmap = NULL;
			goto out;
		}
		counts = &bitmap->counts;

		/*
		 * If we can hold the bitmap lock of one node then
		 * the slot is not occupied, update the pages.
		 */
		snprintf(str, 64, "bitmap%04d", i);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres) {
			pr_err("Cannot initialize %s lock\n", str);
			goto out;
		}
		bm_lockres->flags |= DLM_LKF_NOQUEUE;
		rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
		if (!rv)
			counts->pages = my_pages;
		lockres_free(bm_lockres);

		if (my_pages != counts->pages)
			/*
			 * Let's revert the bitmap size if one node
			 * can't resize bitmap
			 */
			goto out;
		md_bitmap_free(bitmap);
	}

	return 0;
out:
	md_bitmap_free(bitmap);
	update_bitmap_size(mddev, oldsize);
	return -1;
}

/*
 * return 0 if all the bitmaps have the same sync_size
 */
static int cluster_check_sync_size(struct mddev *mddev)
{
	int i, rv;
	bitmap_super_t *sb;
	unsigned long my_sync_size, sync_size = 0;
	int node_num = mddev->bitmap_info.nodes;
	int current_slot = md_cluster_ops->slot_number(mddev);
	struct bitmap *bitmap = mddev->bitmap;
	char str[64];
	struct dlm_lock_resource *bm_lockres;

	sb = kmap_atomic(bitmap->storage.sb_page);
	my_sync_size = sb->sync_size;
	kunmap_atomic(sb);

	for (i = 0; i < node_num; i++) {
		if (i == current_slot)
			continue;

		bitmap = get_bitmap_from_slot(mddev, i);
		if (IS_ERR(bitmap)) {
			pr_err("can't get bitmap from slot %d\n", i);
			return -1;
		}

		/*
		 * If we can hold the bitmap lock of one node then
		 * the slot is not occupied, update the sb.
		 */
		snprintf(str, 64, "bitmap%04d", i);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres) {
			pr_err("md-cluster: Cannot initialize %s\n", str);
			md_bitmap_free(bitmap);
			return -1;
		}
		bm_lockres->flags |= DLM_LKF_NOQUEUE;
		rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
		if (!rv)
			md_bitmap_update_sb(bitmap);
		lockres_free(bm_lockres);

		sb = kmap_atomic(bitmap->storage.sb_page);
		if (sync_size == 0)
			sync_size = sb->sync_size;
		else if (sync_size != sb->sync_size) {
			kunmap_atomic(sb);
			md_bitmap_free(bitmap);
			return -1;
		}
		kunmap_atomic(sb);
		md_bitmap_free(bitmap);
	}

	return (my_sync_size == sync_size) ? 0 : -1;
}

/*
 * Update the size for cluster raid is a little more complex, we perform it
 * by the steps:
 * 1. hold token lock and update superblock in initiator node.
 * 2. send METADATA_UPDATED msg to other nodes.
 * 3. The initiator node continues to check each bitmap's sync_size, if all
 *    bitmaps have the same value of sync_size, then we can set capacity and
 *    let other nodes to perform it. If one node can't update sync_size
 *    accordingly, we need to revert to previous value.
 */
static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct cluster_msg cmsg;
	struct md_rdev *rdev;
	int ret = 0;
	int raid_slot = -1;

	md_update_sb(mddev, 1);
	if (lock_comm(cinfo, 1)) {
		pr_err("%s: lock_comm failed\n", __func__);
		return;
	}

	memset(&cmsg, 0, sizeof(cmsg));
	cmsg.type = cpu_to_le32(METADATA_UPDATED);
	rdev_for_each(rdev, mddev)
		if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) {
			raid_slot = rdev->desc_nr;
			break;
		}
	if (raid_slot >= 0) {
		cmsg.raid_slot = cpu_to_le32(raid_slot);
		/*
		 * We can only change capiticy after all the nodes can do it,
		 * so need to wait after other nodes already received the msg
		 * and handled the change
		 */
		ret = __sendmsg(cinfo, &cmsg);
		if (ret) {
			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
			       __func__, __LINE__);
			unlock_comm(cinfo);
			return;
		}
	} else {
		pr_err("md-cluster: No good device id found to send\n");
		unlock_comm(cinfo);
		return;
	}

	/*
	 * check the sync_size from other node's bitmap, if sync_size
	 * have already updated in other nodes as expected, send an
	 * empty metadata msg to permit the change of capacity
	 */
	if (cluster_check_sync_size(mddev) == 0) {
		memset(&cmsg, 0, sizeof(cmsg));
		cmsg.type = cpu_to_le32(CHANGE_CAPACITY);
		ret = __sendmsg(cinfo, &cmsg);
		if (ret)
			pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n",
			       __func__, __LINE__);
		set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
	} else {
		/* revert to previous sectors */
		ret = mddev->pers->resize(mddev, old_dev_sectors);
		ret = __sendmsg(cinfo, &cmsg);
		if (ret)
			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
			       __func__, __LINE__);
	}
	unlock_comm(cinfo);
}

static int resync_start(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	return dlm_lock_sync_interruptible(cinfo->resync_lockres, DLM_LOCK_EX, mddev);
}

static void resync_info_get(struct mddev *mddev, sector_t *lo, sector_t *hi)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	spin_lock_irq(&cinfo->suspend_lock);
	*lo = cinfo->suspend_lo;
	*hi = cinfo->suspend_hi;
	spin_unlock_irq(&cinfo->suspend_lock);
}

static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct resync_info ri;
	struct cluster_msg cmsg = {0};

	/* do not send zero again, if we have sent before */
	if (hi == 0) {
		memcpy(&ri, cinfo->bitmap_lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
		if (le64_to_cpu(ri.hi) == 0)
			return 0;
	}

	add_resync_info(cinfo->bitmap_lockres, lo, hi);
	/* Re-acquire the lock to refresh LVB */
	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
	cmsg.type = cpu_to_le32(RESYNCING);
	cmsg.low = cpu_to_le64(lo);
	cmsg.high = cpu_to_le64(hi);

	/*
	 * mddev_lock is held if resync_info_update is called from
	 * resync_finish (md_reap_sync_thread -> resync_finish)
	 */
	if (lo == 0 && hi == 0)
		return sendmsg(cinfo, &cmsg, 1);
	else
		return sendmsg(cinfo, &cmsg, 0);
}

static int resync_finish(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int ret = 0;

	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);

	/*
	 * If resync thread is interrupted so we can't say resync is finished,
	 * another node will launch resync thread to continue.
	 */
	if (!test_bit(MD_CLOSING, &mddev->flags))
		ret = resync_info_update(mddev, 0, 0);
	dlm_unlock_sync(cinfo->resync_lockres);
	return ret;
}

static int area_resyncing(struct mddev *mddev, int direction,
		sector_t lo, sector_t hi)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int ret = 0;

	if ((direction == READ) &&
		test_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state))
		return 1;

	spin_lock_irq(&cinfo->suspend_lock);
	if (hi > cinfo->suspend_lo && lo < cinfo->suspend_hi)
		ret = 1;
	spin_unlock_irq(&cinfo->suspend_lock);
	return ret;
}

/* add_new_disk() - initiates a disk add
 * However, if this fails before writing md_update_sb(),
 * add_new_disk_cancel() must be called to release token lock
 */
static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct cluster_msg cmsg;
	int ret = 0;
	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
	char *uuid = sb->device_uuid;

	memset(&cmsg, 0, sizeof(cmsg));
	cmsg.type = cpu_to_le32(NEWDISK);
	memcpy(cmsg.uuid, uuid, 16);
	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
	if (lock_comm(cinfo, 1))
		return -EAGAIN;
	ret = __sendmsg(cinfo, &cmsg);
	if (ret) {
		unlock_comm(cinfo);
		return ret;
	}
	cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
	ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
	cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
	/* Some node does not "see" the device */
	if (ret == -EAGAIN)
		ret = -ENOENT;
	if (ret)
		unlock_comm(cinfo);
	else {
		dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
		/* Since MD_CHANGE_DEVS will be set in add_bound_rdev which
		 * will run soon after add_new_disk, the below path will be
		 * invoked:
		 *   md_wakeup_thread(mddev->thread)
		 *	-> conf->thread (raid1d)
		 *	-> md_check_recovery -> md_update_sb
		 *	-> metadata_update_start/finish
		 * MD_CLUSTER_SEND_LOCKED_ALREADY will be cleared eventually.
		 *
		 * For other failure cases, metadata_update_cancel and
		 * add_new_disk_cancel also clear below bit as well.
		 * */
		set_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
		wake_up(&cinfo->wait);
	}
	return ret;
}

static void add_new_disk_cancel(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
	unlock_comm(cinfo);
}

static int new_disk_ack(struct mddev *mddev, bool ack)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) {
		pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev));
		return -EINVAL;
	}

	if (ack)
		dlm_unlock_sync(cinfo->no_new_dev_lockres);
	complete(&cinfo->newdisk_completion);
	return 0;
}

static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
	struct cluster_msg cmsg = {0};
	struct md_cluster_info *cinfo = mddev->cluster_info;
	cmsg.type = cpu_to_le32(REMOVE);
	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
	return sendmsg(cinfo, &cmsg, 1);
}

static int lock_all_bitmaps(struct mddev *mddev)
{
	int slot, my_slot, ret, held = 1, i = 0;
	char str[64];
	struct md_cluster_info *cinfo = mddev->cluster_info;

	cinfo->other_bitmap_lockres =
		kcalloc(mddev->bitmap_info.nodes - 1,
			sizeof(struct dlm_lock_resource *), GFP_KERNEL);
	if (!cinfo->other_bitmap_lockres) {
		pr_err("md: can't alloc mem for other bitmap locks\n");
		return 0;
	}

	my_slot = slot_number(mddev);
	for (slot = 0; slot < mddev->bitmap_info.nodes; slot++) {
		if (slot == my_slot)
			continue;

		memset(str, '\0', 64);
		snprintf(str, 64, "bitmap%04d", slot);
		cinfo->other_bitmap_lockres[i] = lockres_init(mddev, str, NULL, 1);
		if (!cinfo->other_bitmap_lockres[i])
			return -ENOMEM;

		cinfo->other_bitmap_lockres[i]->flags |= DLM_LKF_NOQUEUE;
		ret = dlm_lock_sync(cinfo->other_bitmap_lockres[i], DLM_LOCK_PW);
		if (ret)
			held = -1;
		i++;
	}

	return held;
}

static void unlock_all_bitmaps(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int i;

	/* release other node's bitmap lock if they are existed */
	if (cinfo->other_bitmap_lockres) {
		for (i = 0; i < mddev->bitmap_info.nodes - 1; i++) {
			if (cinfo->other_bitmap_lockres[i]) {
				lockres_free(cinfo->other_bitmap_lockres[i]);
			}
		}
		kfree(cinfo->other_bitmap_lockres);
		cinfo->other_bitmap_lockres = NULL;
	}
}

static int gather_bitmaps(struct md_rdev *rdev)
{
	int sn, err;
	sector_t lo, hi;
	struct cluster_msg cmsg = {0};
	struct mddev *mddev = rdev->mddev;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	cmsg.type = cpu_to_le32(RE_ADD);
	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
	err = sendmsg(cinfo, &cmsg, 1);
	if (err)
		goto out;

	for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) {
		if (sn == (cinfo->slot_number - 1))
			continue;
		err = md_bitmap_copy_from_slot(mddev, sn, &lo, &hi, false);
		if (err) {
			pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn);
			goto out;
		}
		if ((hi > 0) && (lo < mddev->recovery_cp))
			mddev->recovery_cp = lo;
	}
out:
	return err;
}

static struct md_cluster_operations cluster_ops = {
	.join   = join,
	.leave  = leave,
	.slot_number = slot_number,
	.resync_start = resync_start,
	.resync_finish = resync_finish,
	.resync_info_update = resync_info_update,
	.resync_info_get = resync_info_get,
	.metadata_update_start = metadata_update_start,
	.metadata_update_finish = metadata_update_finish,
	.metadata_update_cancel = metadata_update_cancel,
	.area_resyncing = area_resyncing,
	.add_new_disk = add_new_disk,
	.add_new_disk_cancel = add_new_disk_cancel,
	.new_disk_ack = new_disk_ack,
	.remove_disk = remove_disk,
	.load_bitmaps = load_bitmaps,
	.gather_bitmaps = gather_bitmaps,
	.resize_bitmaps = resize_bitmaps,
	.lock_all_bitmaps = lock_all_bitmaps,
	.unlock_all_bitmaps = unlock_all_bitmaps,
	.update_size = update_size,
};

static int __init cluster_init(void)
{
	pr_warn("md-cluster: support raid1 and raid10 (limited support)\n");
	pr_info("Registering Cluster MD functions\n");
	register_md_cluster_operations(&cluster_ops, THIS_MODULE);
	return 0;
}

static void cluster_exit(void)
{
	unregister_md_cluster_operations();
}

module_init(cluster_init);
module_exit(cluster_exit);
MODULE_AUTHOR("SUSE");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");