summaryrefslogtreecommitdiffstats
path: root/fs/dlm/midcomms.c
blob: 3635e42b066962c14219baae56828b7479f4e0a7 (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
// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2021 Red Hat, Inc.  All rights reserved.
**
**
*******************************************************************************
******************************************************************************/

/*
 * midcomms.c
 *
 * This is the appallingly named "mid-level" comms layer. It takes care about
 * deliver an on application layer "reliable" communication above the used
 * lowcomms transport layer.
 *
 * How it works:
 *
 * Each nodes keeps track of all send DLM messages in send_queue with a sequence
 * number. The receive will send an DLM_ACK message back for every DLM message
 * received at the other side. If a reconnect happens in lowcomms we will send
 * all unacknowledged dlm messages again. The receiving side might drop any already
 * received message by comparing sequence numbers.
 *
 * How version detection works:
 *
 * Due the fact that dlm has pre-configured node addresses on every side
 * it is in it's nature that every side connects at starts to transmit
 * dlm messages which ends in a race. However DLM_RCOM_NAMES, DLM_RCOM_STATUS
 * and their replies are the first messages which are exchanges. Due backwards
 * compatibility these messages are not covered by the midcomms re-transmission
 * layer. These messages have their own re-transmission handling in the dlm
 * application layer. The version field of every node will be set on these RCOM
 * messages as soon as they arrived and the node isn't yet part of the nodes
 * hash. There exists also logic to detect version mismatched if something weird
 * going on or the first messages isn't an expected one.
 *
 * Termination:
 *
 * The midcomms layer does a 4 way handshake for termination on DLM protocol
 * like TCP supports it with half-closed socket support. SCTP doesn't support
 * half-closed socket, so we do it on DLM layer. Also socket shutdown() can be
 * interrupted by .e.g. tcp reset itself. Additional there exists the othercon
 * paradigm in lowcomms which cannot be easily without breaking backwards
 * compatibility. A node cannot send anything to another node when a DLM_FIN
 * message was send. There exists additional logic to print a warning if
 * DLM wants to do it. There exists a state handling like RFC 793 but reduced
 * to termination only. The event "member removal event" describes the cluster
 * manager removed the node from internal lists, at this point DLM does not
 * send any message to the other node. There exists two cases:
 *
 * 1. The cluster member was removed and we received a FIN
 * OR
 * 2. We received a FIN but the member was not removed yet
 *
 * One of these cases will do the CLOSE_WAIT to LAST_ACK change.
 *
 *
 *                              +---------+
 *                              | CLOSED  |
 *                              +---------+
 *                                   | add member/receive RCOM version
 *                                   |            detection msg
 *                                   V
 *                              +---------+
 *                              |  ESTAB  |
 *                              +---------+
 *                       CLOSE    |     |    rcv FIN
 *                      -------   |     |    -------
 * +---------+          snd FIN  /       \   snd ACK          +---------+
 * |  FIN    |<-----------------           ------------------>|  CLOSE  |
 * | WAIT-1  |------------------                              |   WAIT  |
 * +---------+          rcv FIN  \                            +---------+
 * | rcv ACK of FIN   -------   |                            CLOSE  | member
 * | --------------   snd ACK   |                           ------- | removal
 * V        x                   V                           snd FIN V event
 * +---------+                  +---------+                   +---------+
 * |FINWAIT-2|                  | CLOSING |                   | LAST-ACK|
 * +---------+                  +---------+                   +---------+
 * |                rcv ACK of FIN |                 rcv ACK of FIN |
 * |  rcv FIN       -------------- |                 -------------- |
 * |  -------              x       V                        x       V
 *  \ snd ACK                 +---------+                   +---------+
 *   ------------------------>| CLOSED  |                   | CLOSED  |
 *                            +---------+                   +---------+
 *
 * NOTE: any state can interrupted by midcomms_close() and state will be
 * switched to CLOSED in case of fencing. There exists also some timeout
 * handling when we receive the version detection RCOM messages which is
 * made by observation.
 *
 * Future improvements:
 *
 * There exists some known issues/improvements of the dlm handling. Some
 * of them should be done in a next major dlm version bump which makes
 * it incompatible with previous versions.
 *
 * Unaligned memory access:
 *
 * There exists cases when the dlm message buffer length is not aligned
 * to 8 byte. However seems nobody detected any problem with it. This
 * can be fixed in the next major version bump of dlm.
 *
 * Version detection:
 *
 * The version detection and how it's done is related to backwards
 * compatibility. There exists better ways to make a better handling.
 * However this should be changed in the next major version bump of dlm.
 *
 * Tail Size checking:
 *
 * There exists a message tail payload in e.g. DLM_MSG however we don't
 * check it against the message length yet regarding to the receive buffer
 * length. That need to be validated.
 *
 * Fencing bad nodes:
 *
 * At timeout places or weird sequence number behaviours we should send
 * a fencing request to the cluster manager.
 */

/* Debug switch to enable a 5 seconds sleep waiting of a termination.
 * This can be useful to test fencing while termination is running.
 * This requires a setup with only gfs2 as dlm user, so that the
 * last umount will terminate the connection.
 *
 * However it became useful to test, while the 5 seconds block in umount
 * just press the reset button. In a lot of dropping the termination
 * process can could take several seconds.
 */
#define DLM_DEBUG_FENCE_TERMINATION	0

#include <net/tcp.h>

#include "dlm_internal.h"
#include "lowcomms.h"
#include "config.h"
#include "memory.h"
#include "lock.h"
#include "util.h"
#include "midcomms.h"

/* init value for sequence numbers for testing purpose only e.g. overflows */
#define DLM_SEQ_INIT		0
/* 3 minutes wait to sync ending of dlm */
#define DLM_SHUTDOWN_TIMEOUT	msecs_to_jiffies(3 * 60 * 1000)
#define DLM_VERSION_NOT_SET	0

struct midcomms_node {
	int nodeid;
	uint32_t version;
	uint32_t seq_send;
	uint32_t seq_next;
	/* These queues are unbound because we cannot drop any message in dlm.
	 * We could send a fence signal for a specific node to the cluster
	 * manager if queues hits some maximum value, however this handling
	 * not supported yet.
	 */
	struct list_head send_queue;
	spinlock_t send_queue_lock;
	atomic_t send_queue_cnt;
#define DLM_NODE_FLAG_CLOSE	1
#define DLM_NODE_FLAG_STOP_TX	2
#define DLM_NODE_FLAG_STOP_RX	3
#define DLM_NODE_ULP_DELIVERED	4
	unsigned long flags;
	wait_queue_head_t shutdown_wait;

	/* dlm tcp termination state */
#define DLM_CLOSED	1
#define DLM_ESTABLISHED	2
#define DLM_FIN_WAIT1	3
#define DLM_FIN_WAIT2	4
#define DLM_CLOSE_WAIT	5
#define DLM_LAST_ACK	6
#define DLM_CLOSING	7
	int state;
	spinlock_t state_lock;

	/* counts how many lockspaces are using this node
	 * this refcount is necessary to determine if the
	 * node wants to disconnect.
	 */
	int users;

	/* not protected by srcu, node_hash lifetime */
	void *debugfs;

	struct hlist_node hlist;
	struct rcu_head rcu;
};

struct dlm_mhandle {
	const struct dlm_header *inner_hd;
	struct midcomms_node *node;
	struct dlm_opts *opts;
	struct dlm_msg *msg;
	bool committed;
	uint32_t seq;

	void (*ack_rcv)(struct midcomms_node *node);

	/* get_mhandle/commit srcu idx exchange */
	int idx;

	struct list_head list;
	struct rcu_head rcu;
};

static struct hlist_head node_hash[CONN_HASH_SIZE];
static DEFINE_SPINLOCK(nodes_lock);
DEFINE_STATIC_SRCU(nodes_srcu);

/* This mutex prevents that midcomms_close() is running while
 * stop() or remove(). As I experienced invalid memory access
 * behaviours when DLM_DEBUG_FENCE_TERMINATION is enabled and
 * resetting machines. I will end in some double deletion in nodes
 * datastructure.
 */
static DEFINE_MUTEX(close_lock);

struct kmem_cache *dlm_midcomms_cache_create(void)
{
	return kmem_cache_create("dlm_mhandle", sizeof(struct dlm_mhandle),
				 0, 0, NULL);
}

static inline const char *dlm_state_str(int state)
{
	switch (state) {
	case DLM_CLOSED:
		return "CLOSED";
	case DLM_ESTABLISHED:
		return "ESTABLISHED";
	case DLM_FIN_WAIT1:
		return "FIN_WAIT1";
	case DLM_FIN_WAIT2:
		return "FIN_WAIT2";
	case DLM_CLOSE_WAIT:
		return "CLOSE_WAIT";
	case DLM_LAST_ACK:
		return "LAST_ACK";
	case DLM_CLOSING:
		return "CLOSING";
	default:
		return "UNKNOWN";
	}
}

const char *dlm_midcomms_state(struct midcomms_node *node)
{
	return dlm_state_str(node->state);
}

unsigned long dlm_midcomms_flags(struct midcomms_node *node)
{
	return node->flags;
}

int dlm_midcomms_send_queue_cnt(struct midcomms_node *node)
{
	return atomic_read(&node->send_queue_cnt);
}

uint32_t dlm_midcomms_version(struct midcomms_node *node)
{
	return node->version;
}

static struct midcomms_node *__find_node(int nodeid, int r)
{
	struct midcomms_node *node;

	hlist_for_each_entry_rcu(node, &node_hash[r], hlist) {
		if (node->nodeid == nodeid)
			return node;
	}

	return NULL;
}

static void dlm_mhandle_release(struct rcu_head *rcu)
{
	struct dlm_mhandle *mh = container_of(rcu, struct dlm_mhandle, rcu);

	dlm_lowcomms_put_msg(mh->msg);
	dlm_free_mhandle(mh);
}

static void dlm_mhandle_delete(struct midcomms_node *node,
			       struct dlm_mhandle *mh)
{
	list_del_rcu(&mh->list);
	atomic_dec(&node->send_queue_cnt);
	call_rcu(&mh->rcu, dlm_mhandle_release);
}

static void dlm_send_queue_flush(struct midcomms_node *node)
{
	struct dlm_mhandle *mh;

	pr_debug("flush midcomms send queue of node %d\n", node->nodeid);

	rcu_read_lock();
	spin_lock(&node->send_queue_lock);
	list_for_each_entry_rcu(mh, &node->send_queue, list) {
		dlm_mhandle_delete(node, mh);
	}
	spin_unlock(&node->send_queue_lock);
	rcu_read_unlock();
}

static void midcomms_node_reset(struct midcomms_node *node)
{
	pr_debug("reset node %d\n", node->nodeid);

	node->seq_next = DLM_SEQ_INIT;
	node->seq_send = DLM_SEQ_INIT;
	node->version = DLM_VERSION_NOT_SET;
	node->flags = 0;

	dlm_send_queue_flush(node);
	node->state = DLM_CLOSED;
	wake_up(&node->shutdown_wait);
}

static struct midcomms_node *nodeid2node(int nodeid, gfp_t alloc)
{
	struct midcomms_node *node, *tmp;
	int r = nodeid_hash(nodeid);

	node = __find_node(nodeid, r);
	if (node || !alloc)
		return node;

	node = kmalloc(sizeof(*node), alloc);
	if (!node)
		return NULL;

	node->nodeid = nodeid;
	spin_lock_init(&node->state_lock);
	spin_lock_init(&node->send_queue_lock);
	atomic_set(&node->send_queue_cnt, 0);
	INIT_LIST_HEAD(&node->send_queue);
	init_waitqueue_head(&node->shutdown_wait);
	node->users = 0;
	midcomms_node_reset(node);

	spin_lock(&nodes_lock);
	/* check again if there was somebody else
	 * earlier here to add the node
	 */
	tmp = __find_node(nodeid, r);
	if (tmp) {
		spin_unlock(&nodes_lock);
		kfree(node);
		return tmp;
	}

	hlist_add_head_rcu(&node->hlist, &node_hash[r]);
	spin_unlock(&nodes_lock);

	node->debugfs = dlm_create_debug_comms_file(nodeid, node);
	return node;
}

static int dlm_send_ack(int nodeid, uint32_t seq)
{
	int mb_len = sizeof(struct dlm_header);
	struct dlm_header *m_header;
	struct dlm_msg *msg;
	char *ppc;

	msg = dlm_lowcomms_new_msg(nodeid, mb_len, GFP_NOFS, &ppc,
				   NULL, NULL);
	if (!msg)
		return -ENOMEM;

	m_header = (struct dlm_header *)ppc;

	m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
	m_header->h_nodeid = dlm_our_nodeid();
	m_header->h_length = mb_len;
	m_header->h_cmd = DLM_ACK;
	m_header->u.h_seq = seq;

	header_out(m_header);
	dlm_lowcomms_commit_msg(msg);
	dlm_lowcomms_put_msg(msg);

	return 0;
}

static int dlm_send_fin(struct midcomms_node *node,
			void (*ack_rcv)(struct midcomms_node *node))
{
	int mb_len = sizeof(struct dlm_header);
	struct dlm_header *m_header;
	struct dlm_mhandle *mh;
	char *ppc;

	mh = dlm_midcomms_get_mhandle(node->nodeid, mb_len, GFP_NOFS, &ppc);
	if (!mh)
		return -ENOMEM;

	mh->ack_rcv = ack_rcv;

	m_header = (struct dlm_header *)ppc;

	m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
	m_header->h_nodeid = dlm_our_nodeid();
	m_header->h_length = mb_len;
	m_header->h_cmd = DLM_FIN;

	header_out(m_header);

	pr_debug("sending fin msg to node %d\n", node->nodeid);
	dlm_midcomms_commit_mhandle(mh);
	set_bit(DLM_NODE_FLAG_STOP_TX, &node->flags);

	return 0;
}

static void dlm_receive_ack(struct midcomms_node *node, uint32_t seq)
{
	struct dlm_mhandle *mh;

	rcu_read_lock();
	list_for_each_entry_rcu(mh, &node->send_queue, list) {
		if (before(mh->seq, seq)) {
			if (mh->ack_rcv)
				mh->ack_rcv(node);
		} else {
			/* send queue should be ordered */
			break;
		}
	}

	spin_lock(&node->send_queue_lock);
	list_for_each_entry_rcu(mh, &node->send_queue, list) {
		if (before(mh->seq, seq)) {
			dlm_mhandle_delete(node, mh);
		} else {
			/* send queue should be ordered */
			break;
		}
	}
	spin_unlock(&node->send_queue_lock);
	rcu_read_unlock();
}

static void dlm_pas_fin_ack_rcv(struct midcomms_node *node)
{
	spin_lock(&node->state_lock);
	pr_debug("receive passive fin ack from node %d with state %s\n",
		 node->nodeid, dlm_state_str(node->state));

	switch (node->state) {
	case DLM_LAST_ACK:
		/* DLM_CLOSED */
		midcomms_node_reset(node);
		break;
	case DLM_CLOSED:
		/* not valid but somehow we got what we want */
		wake_up(&node->shutdown_wait);
		break;
	default:
		spin_unlock(&node->state_lock);
		log_print("%s: unexpected state: %d\n",
			  __func__, node->state);
		WARN_ON(1);
		return;
	}
	spin_unlock(&node->state_lock);
}

static void dlm_midcomms_receive_buffer(union dlm_packet *p,
					struct midcomms_node *node,
					uint32_t seq)
{
	if (seq == node->seq_next) {
		node->seq_next++;

		switch (p->header.h_cmd) {
		case DLM_FIN:
			/* send ack before fin */
			dlm_send_ack(node->nodeid, node->seq_next);

			spin_lock(&node->state_lock);
			pr_debug("receive fin msg from node %d with state %s\n",
				 node->nodeid, dlm_state_str(node->state));

			switch (node->state) {
			case DLM_ESTABLISHED:
				node->state = DLM_CLOSE_WAIT;
				pr_debug("switch node %d to state %s\n",
					 node->nodeid, dlm_state_str(node->state));
				/* passive shutdown DLM_LAST_ACK case 1
				 * additional we check if the node is used by
				 * cluster manager events at all.
				 */
				if (node->users == 0) {
					node->state = DLM_LAST_ACK;
					pr_debug("switch node %d to state %s case 1\n",
						 node->nodeid, dlm_state_str(node->state));
					spin_unlock(&node->state_lock);
					goto send_fin;
				}
				break;
			case DLM_FIN_WAIT1:
				node->state = DLM_CLOSING;
				pr_debug("switch node %d to state %s\n",
					 node->nodeid, dlm_state_str(node->state));
				break;
			case DLM_FIN_WAIT2:
				midcomms_node_reset(node);
				pr_debug("switch node %d to state %s\n",
					 node->nodeid, dlm_state_str(node->state));
				wake_up(&node->shutdown_wait);
				break;
			case DLM_LAST_ACK:
				/* probably remove_member caught it, do nothing */
				break;
			default:
				spin_unlock(&node->state_lock);
				log_print("%s: unexpected state: %d\n",
					  __func__, node->state);
				WARN_ON(1);
				return;
			}
			spin_unlock(&node->state_lock);

			set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
			break;
		default:
			WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags));
			dlm_receive_buffer(p, node->nodeid);
			set_bit(DLM_NODE_ULP_DELIVERED, &node->flags);
			break;
		}
	} else {
		/* retry to ack message which we already have by sending back
		 * current node->seq_next number as ack.
		 */
		if (seq < node->seq_next)
			dlm_send_ack(node->nodeid, node->seq_next);

		log_print_ratelimited("ignore dlm msg because seq mismatch, seq: %u, expected: %u, nodeid: %d",
				      seq, node->seq_next, node->nodeid);
	}

	return;

send_fin:
	set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
	dlm_send_fin(node, dlm_pas_fin_ack_rcv);
}

static struct midcomms_node *
dlm_midcomms_recv_node_lookup(int nodeid, const union dlm_packet *p,
			      uint16_t msglen, int (*cb)(struct midcomms_node *node))
{
	struct midcomms_node *node = NULL;
	gfp_t allocation = 0;
	int ret;

	switch (p->header.h_cmd) {
	case DLM_RCOM:
		if (msglen < sizeof(struct dlm_rcom)) {
			log_print("rcom msg too small: %u, will skip this message from node %d",
				  msglen, nodeid);
			return NULL;
		}

		switch (le32_to_cpu(p->rcom.rc_type)) {
		case DLM_RCOM_NAMES:
			fallthrough;
		case DLM_RCOM_NAMES_REPLY:
			fallthrough;
		case DLM_RCOM_STATUS:
			fallthrough;
		case DLM_RCOM_STATUS_REPLY:
			node = nodeid2node(nodeid, 0);
			if (node) {
				spin_lock(&node->state_lock);
				if (node->state != DLM_ESTABLISHED)
					pr_debug("receive begin RCOM msg from node %d with state %s\n",
						 node->nodeid, dlm_state_str(node->state));

				switch (node->state) {
				case DLM_CLOSED:
					node->state = DLM_ESTABLISHED;
					pr_debug("switch node %d to state %s\n",
						 node->nodeid, dlm_state_str(node->state));
					break;
				case DLM_ESTABLISHED:
					break;
				default:
					/* some invalid state passive shutdown
					 * was failed, we try to reset and
					 * hope it will go on.
					 */
					log_print("reset node %d because shutdown stuck",
						  node->nodeid);

					midcomms_node_reset(node);
					node->state = DLM_ESTABLISHED;
					break;
				}
				spin_unlock(&node->state_lock);
			}

			allocation = GFP_NOFS;
			break;
		default:
			break;
		}

		break;
	default:
		break;
	}

	node = nodeid2node(nodeid, allocation);
	if (!node) {
		switch (p->header.h_cmd) {
		case DLM_OPTS:
			if (msglen < sizeof(struct dlm_opts)) {
				log_print("opts msg too small: %u, will skip this message from node %d",
					  msglen, nodeid);
				return NULL;
			}

			log_print_ratelimited("received dlm opts message nextcmd %d from node %d in an invalid sequence",
					      p->opts.o_nextcmd, nodeid);
			break;
		default:
			log_print_ratelimited("received dlm message cmd %d from node %d in an invalid sequence",
					      p->header.h_cmd, nodeid);
			break;
		}

		return NULL;
	}

	ret = cb(node);
	if (ret < 0)
		return NULL;

	return node;
}

static int dlm_midcomms_version_check_3_2(struct midcomms_node *node)
{
	switch (node->version) {
	case DLM_VERSION_NOT_SET:
		node->version = DLM_VERSION_3_2;
		log_print("version 0x%08x for node %d detected", DLM_VERSION_3_2,
			  node->nodeid);
		break;
	case DLM_VERSION_3_2:
		break;
	default:
		log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x",
				      DLM_VERSION_3_2, node->nodeid, node->version);
		return -1;
	}

	return 0;
}

static int dlm_opts_check_msglen(union dlm_packet *p, uint16_t msglen, int nodeid)
{
	int len = msglen;

	/* we only trust outer header msglen because
	 * it's checked against receive buffer length.
	 */
	if (len < sizeof(struct dlm_opts))
		return -1;
	len -= sizeof(struct dlm_opts);

	if (len < le16_to_cpu(p->opts.o_optlen))
		return -1;
	len -= le16_to_cpu(p->opts.o_optlen);

	switch (p->opts.o_nextcmd) {
	case DLM_FIN:
		if (len < sizeof(struct dlm_header)) {
			log_print("fin too small: %d, will skip this message from node %d",
				  len, nodeid);
			return -1;
		}

		break;
	case DLM_MSG:
		if (len < sizeof(struct dlm_message)) {
			log_print("msg too small: %d, will skip this message from node %d",
				  msglen, nodeid);
			return -1;
		}

		break;
	case DLM_RCOM:
		if (len < sizeof(struct dlm_rcom)) {
			log_print("rcom msg too small: %d, will skip this message from node %d",
				  len, nodeid);
			return -1;
		}

		break;
	default:
		log_print("unsupported o_nextcmd received: %u, will skip this message from node %d",
			  p->opts.o_nextcmd, nodeid);
		return -1;
	}

	return 0;
}

static void dlm_midcomms_receive_buffer_3_2(union dlm_packet *p, int nodeid)
{
	uint16_t msglen = le16_to_cpu(p->header.h_length);
	struct midcomms_node *node;
	uint32_t seq;
	int ret, idx;

	idx = srcu_read_lock(&nodes_srcu);
	node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen,
					     dlm_midcomms_version_check_3_2);
	if (!node)
		goto out;

	switch (p->header.h_cmd) {
	case DLM_RCOM:
		/* these rcom message we use to determine version.
		 * they have their own retransmission handling and
		 * are the first messages of dlm.
		 *
		 * length already checked.
		 */
		switch (le32_to_cpu(p->rcom.rc_type)) {
		case DLM_RCOM_NAMES:
			fallthrough;
		case DLM_RCOM_NAMES_REPLY:
			fallthrough;
		case DLM_RCOM_STATUS:
			fallthrough;
		case DLM_RCOM_STATUS_REPLY:
			break;
		default:
			log_print("unsupported rcom type received: %u, will skip this message from node %d",
				  le32_to_cpu(p->rcom.rc_type), nodeid);
			goto out;
		}

		WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags));
		dlm_receive_buffer(p, nodeid);
		break;
	case DLM_OPTS:
		seq = le32_to_cpu(p->header.u.h_seq);

		ret = dlm_opts_check_msglen(p, msglen, nodeid);
		if (ret < 0) {
			log_print("opts msg too small: %u, will skip this message from node %d",
				  msglen, nodeid);
			goto out;
		}

		p = (union dlm_packet *)((unsigned char *)p->opts.o_opts +
					 le16_to_cpu(p->opts.o_optlen));

		/* recheck inner msglen just if it's not garbage */
		msglen = le16_to_cpu(p->header.h_length);
		switch (p->header.h_cmd) {
		case DLM_RCOM:
			if (msglen < sizeof(struct dlm_rcom)) {
				log_print("inner rcom msg too small: %u, will skip this message from node %d",
					  msglen, nodeid);
				goto out;
			}

			break;
		case DLM_MSG:
			if (msglen < sizeof(struct dlm_message)) {
				log_print("inner msg too small: %u, will skip this message from node %d",
					  msglen, nodeid);
				goto out;
			}

			break;
		case DLM_FIN:
			if (msglen < sizeof(struct dlm_header)) {
				log_print("inner fin too small: %u, will skip this message from node %d",
					  msglen, nodeid);
				goto out;
			}

			break;
		default:
			log_print("unsupported inner h_cmd received: %u, will skip this message from node %d",
				  msglen, nodeid);
			goto out;
		}

		dlm_midcomms_receive_buffer(p, node, seq);
		break;
	case DLM_ACK:
		seq = le32_to_cpu(p->header.u.h_seq);
		dlm_receive_ack(node, seq);
		break;
	default:
		log_print("unsupported h_cmd received: %u, will skip this message from node %d",
			  p->header.h_cmd, nodeid);
		break;
	}

out:
	srcu_read_unlock(&nodes_srcu, idx);
}

static int dlm_midcomms_version_check_3_1(struct midcomms_node *node)
{
	switch (node->version) {
	case DLM_VERSION_NOT_SET:
		node->version = DLM_VERSION_3_1;
		log_print("version 0x%08x for node %d detected", DLM_VERSION_3_1,
			  node->nodeid);
		break;
	case DLM_VERSION_3_1:
		break;
	default:
		log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x",
				      DLM_VERSION_3_1, node->nodeid, node->version);
		return -1;
	}

	return 0;
}

static void dlm_midcomms_receive_buffer_3_1(union dlm_packet *p, int nodeid)
{
	uint16_t msglen = le16_to_cpu(p->header.h_length);
	struct midcomms_node *node;
	int idx;

	idx = srcu_read_lock(&nodes_srcu);
	node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen,
					     dlm_midcomms_version_check_3_1);
	if (!node) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}
	srcu_read_unlock(&nodes_srcu, idx);

	switch (p->header.h_cmd) {
	case DLM_RCOM:
		/* length already checked */
		break;
	case DLM_MSG:
		if (msglen < sizeof(struct dlm_message)) {
			log_print("msg too small: %u, will skip this message from node %d",
				  msglen, nodeid);
			return;
		}

		break;
	default:
		log_print("unsupported h_cmd received: %u, will skip this message from node %d",
			  p->header.h_cmd, nodeid);
		return;
	}

	dlm_receive_buffer(p, nodeid);
}

/*
 * Called from the low-level comms layer to process a buffer of
 * commands.
 */

int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len)
{
	const unsigned char *ptr = buf;
	const struct dlm_header *hd;
	uint16_t msglen;
	int ret = 0;

	while (len >= sizeof(struct dlm_header)) {
		hd = (struct dlm_header *)ptr;

		/* no message should be more than DLM_MAX_SOCKET_BUFSIZE or
		 * less than dlm_header size.
		 *
		 * Some messages does not have a 8 byte length boundary yet
		 * which can occur in a unaligned memory access of some dlm
		 * messages. However this problem need to be fixed at the
		 * sending side, for now it seems nobody run into architecture
		 * related issues yet but it slows down some processing.
		 * Fixing this issue should be scheduled in future by doing
		 * the next major version bump.
		 */
		msglen = le16_to_cpu(hd->h_length);
		if (msglen > DLM_MAX_SOCKET_BUFSIZE ||
		    msglen < sizeof(struct dlm_header)) {
			log_print("received invalid length header: %u from node %d, will abort message parsing",
				  msglen, nodeid);
			return -EBADMSG;
		}

		/* caller will take care that leftover
		 * will be parsed next call with more data
		 */
		if (msglen > len)
			break;

		switch (hd->h_version) {
		case cpu_to_le32(DLM_VERSION_3_1):
			dlm_midcomms_receive_buffer_3_1((union dlm_packet *)ptr, nodeid);
			break;
		case cpu_to_le32(DLM_VERSION_3_2):
			dlm_midcomms_receive_buffer_3_2((union dlm_packet *)ptr, nodeid);
			break;
		default:
			log_print("received invalid version header: %u from node %d, will skip this message",
				  le32_to_cpu(hd->h_version), nodeid);
			break;
		}

		ret += msglen;
		len -= msglen;
		ptr += msglen;
	}

	return ret;
}

void dlm_midcomms_receive_done(int nodeid)
{
	struct midcomms_node *node;
	int idx;

	idx = srcu_read_lock(&nodes_srcu);
	node = nodeid2node(nodeid, 0);
	if (!node) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	/* old protocol, we do nothing */
	switch (node->version) {
	case DLM_VERSION_3_2:
		break;
	default:
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	/* do nothing if we didn't delivered stateful to ulp */
	if (!test_and_clear_bit(DLM_NODE_ULP_DELIVERED,
				&node->flags)) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	spin_lock(&node->state_lock);
	/* we only ack if state is ESTABLISHED */
	switch (node->state) {
	case DLM_ESTABLISHED:
		spin_unlock(&node->state_lock);
		dlm_send_ack(node->nodeid, node->seq_next);
		break;
	default:
		spin_unlock(&node->state_lock);
		/* do nothing FIN has it's own ack send */
		break;
	}
	srcu_read_unlock(&nodes_srcu, idx);
}

void dlm_midcomms_unack_msg_resend(int nodeid)
{
	struct midcomms_node *node;
	struct dlm_mhandle *mh;
	int idx, ret;

	idx = srcu_read_lock(&nodes_srcu);
	node = nodeid2node(nodeid, 0);
	if (!node) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	/* old protocol, we don't support to retransmit on failure */
	switch (node->version) {
	case DLM_VERSION_3_2:
		break;
	default:
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	rcu_read_lock();
	list_for_each_entry_rcu(mh, &node->send_queue, list) {
		if (!mh->committed)
			continue;

		ret = dlm_lowcomms_resend_msg(mh->msg);
		if (!ret)
			log_print_ratelimited("retransmit dlm msg, seq %u, nodeid %d",
					      mh->seq, node->nodeid);
	}
	rcu_read_unlock();
	srcu_read_unlock(&nodes_srcu, idx);
}

static void dlm_fill_opts_header(struct dlm_opts *opts, uint16_t inner_len,
				 uint32_t seq)
{
	opts->o_header.h_cmd = DLM_OPTS;
	opts->o_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
	opts->o_header.h_nodeid = dlm_our_nodeid();
	opts->o_header.h_length = DLM_MIDCOMMS_OPT_LEN + inner_len;
	opts->o_header.u.h_seq = seq;
	header_out(&opts->o_header);
}

static void midcomms_new_msg_cb(void *data)
{
	struct dlm_mhandle *mh = data;

	atomic_inc(&mh->node->send_queue_cnt);

	spin_lock(&mh->node->send_queue_lock);
	list_add_tail_rcu(&mh->list, &mh->node->send_queue);
	spin_unlock(&mh->node->send_queue_lock);

	mh->seq = mh->node->seq_send++;
}

static struct dlm_msg *dlm_midcomms_get_msg_3_2(struct dlm_mhandle *mh, int nodeid,
						int len, gfp_t allocation, char **ppc)
{
	struct dlm_opts *opts;
	struct dlm_msg *msg;

	msg = dlm_lowcomms_new_msg(nodeid, len + DLM_MIDCOMMS_OPT_LEN,
				   allocation, ppc, midcomms_new_msg_cb, mh);
	if (!msg)
		return NULL;

	opts = (struct dlm_opts *)*ppc;
	mh->opts = opts;

	/* add possible options here */
	dlm_fill_opts_header(opts, len, mh->seq);

	*ppc += sizeof(*opts);
	mh->inner_hd = (const struct dlm_header *)*ppc;
	return msg;
}

struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len,
					     gfp_t allocation, char **ppc)
{
	struct midcomms_node *node;
	struct dlm_mhandle *mh;
	struct dlm_msg *msg;
	int idx;

	idx = srcu_read_lock(&nodes_srcu);
	node = nodeid2node(nodeid, 0);
	if (!node) {
		WARN_ON_ONCE(1);
		goto err;
	}

	/* this is a bug, however we going on and hope it will be resolved */
	WARN_ON(test_bit(DLM_NODE_FLAG_STOP_TX, &node->flags));

	mh = dlm_allocate_mhandle();
	if (!mh)
		goto err;

	mh->committed = false;
	mh->ack_rcv = NULL;
	mh->idx = idx;
	mh->node = node;

	switch (node->version) {
	case DLM_VERSION_3_1:
		msg = dlm_lowcomms_new_msg(nodeid, len, allocation, ppc,
					   NULL, NULL);
		if (!msg) {
			dlm_free_mhandle(mh);
			goto err;
		}

		break;
	case DLM_VERSION_3_2:
		msg = dlm_midcomms_get_msg_3_2(mh, nodeid, len, allocation,
					       ppc);
		if (!msg) {
			dlm_free_mhandle(mh);
			goto err;
		}

		break;
	default:
		dlm_free_mhandle(mh);
		WARN_ON(1);
		goto err;
	}

	mh->msg = msg;

	/* keep in mind that is a must to call
	 * dlm_midcomms_commit_msg() which releases
	 * nodes_srcu using mh->idx which is assumed
	 * here that the application will call it.
	 */
	return mh;

err:
	srcu_read_unlock(&nodes_srcu, idx);
	return NULL;
}

static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh)
{
	/* nexthdr chain for fast lookup */
	mh->opts->o_nextcmd = mh->inner_hd->h_cmd;
	mh->committed = true;
	dlm_lowcomms_commit_msg(mh->msg);
}

void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh)
{
	switch (mh->node->version) {
	case DLM_VERSION_3_1:
		srcu_read_unlock(&nodes_srcu, mh->idx);

		dlm_lowcomms_commit_msg(mh->msg);
		dlm_lowcomms_put_msg(mh->msg);
		/* mh is not part of rcu list in this case */
		dlm_free_mhandle(mh);
		break;
	case DLM_VERSION_3_2:
		dlm_midcomms_commit_msg_3_2(mh);
		srcu_read_unlock(&nodes_srcu, mh->idx);
		break;
	default:
		srcu_read_unlock(&nodes_srcu, mh->idx);
		WARN_ON(1);
		break;
	}
}

int dlm_midcomms_start(void)
{
	int i;

	for (i = 0; i < CONN_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&node_hash[i]);

	return dlm_lowcomms_start();
}

static void dlm_act_fin_ack_rcv(struct midcomms_node *node)
{
	spin_lock(&node->state_lock);
	pr_debug("receive active fin ack from node %d with state %s\n",
		 node->nodeid, dlm_state_str(node->state));

	switch (node->state) {
	case DLM_FIN_WAIT1:
		node->state = DLM_FIN_WAIT2;
		pr_debug("switch node %d to state %s\n",
			 node->nodeid, dlm_state_str(node->state));
		break;
	case DLM_CLOSING:
		midcomms_node_reset(node);
		pr_debug("switch node %d to state %s\n",
			 node->nodeid, dlm_state_str(node->state));
		wake_up(&node->shutdown_wait);
		break;
	case DLM_CLOSED:
		/* not valid but somehow we got what we want */
		wake_up(&node->shutdown_wait);
		break;
	default:
		spin_unlock(&node->state_lock);
		log_print("%s: unexpected state: %d\n",
			  __func__, node->state);
		WARN_ON(1);
		return;
	}
	spin_unlock(&node->state_lock);
}

void dlm_midcomms_add_member(int nodeid)
{
	struct midcomms_node *node;
	int idx;

	if (nodeid == dlm_our_nodeid())
		return;

	idx = srcu_read_lock(&nodes_srcu);
	node = nodeid2node(nodeid, GFP_NOFS);
	if (!node) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	spin_lock(&node->state_lock);
	if (!node->users) {
		pr_debug("receive add member from node %d with state %s\n",
			 node->nodeid, dlm_state_str(node->state));
		switch (node->state) {
		case DLM_ESTABLISHED:
			break;
		case DLM_CLOSED:
			node->state = DLM_ESTABLISHED;
			pr_debug("switch node %d to state %s\n",
				 node->nodeid, dlm_state_str(node->state));
			break;
		default:
			/* some invalid state passive shutdown
			 * was failed, we try to reset and
			 * hope it will go on.
			 */
			log_print("reset node %d because shutdown stuck",
				  node->nodeid);

			midcomms_node_reset(node);
			node->state = DLM_ESTABLISHED;
			break;
		}
	}

	node->users++;
	pr_debug("node %d users inc count %d\n", nodeid, node->users);
	spin_unlock(&node->state_lock);

	srcu_read_unlock(&nodes_srcu, idx);
}

void dlm_midcomms_remove_member(int nodeid)
{
	struct midcomms_node *node;
	int idx;

	if (nodeid == dlm_our_nodeid())
		return;

	idx = srcu_read_lock(&nodes_srcu);
	node = nodeid2node(nodeid, 0);
	if (!node) {
		srcu_read_unlock(&nodes_srcu, idx);
		return;
	}

	spin_lock(&node->state_lock);
	node->users--;
	pr_debug("node %d users dec count %d\n", nodeid, node->users);

	/* hitting users count to zero means the
	 * other side is running dlm_midcomms_stop()
	 * we meet us to have a clean disconnect.
	 */
	if (node->users == 0) {
		pr_debug("receive remove member from node %d with state %s\n",
			 node->nodeid, dlm_state_str(node->state));
		switch (node->state) {
		case DLM_ESTABLISHED:
			break;
		case DLM_CLOSE_WAIT:
			/* passive shutdown DLM_LAST_ACK case 2 */
			node->state = DLM_LAST_ACK;
			spin_unlock(&node->state_lock);

			pr_debug("switch node %d to state %s case 2\n",
				 node->nodeid, dlm_state_str(node->state));
			goto send_fin;
		case DLM_LAST_ACK:
			/* probably receive fin caught it, do nothing */
			break;
		case DLM_CLOSED:
			/* already gone, do nothing */
			break;
		default:
			log_print("%s: unexpected state: %d\n",
				  __func__, node->state);
			break;
		}
	}
	spin_unlock(&node->state_lock);

	srcu_read_unlock(&nodes_srcu, idx);
	return;

send_fin:
	set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
	dlm_send_fin(node, dlm_pas_fin_ack_rcv);
	srcu_read_unlock(&nodes_srcu, idx);
}

static void midcomms_node_release(struct rcu_head *rcu)
{
	struct midcomms_node *node = container_of(rcu, struct midcomms_node, rcu);

	WARN_ON(atomic_read(&node->send_queue_cnt));
	kfree(node);
}

static void midcomms_shutdown(struct midcomms_node *node)
{
	int ret;

	/* old protocol, we don't wait for pending operations */
	switch (node->version) {
	case DLM_VERSION_3_2:
		break;
	default:
		return;
	}

	spin_lock(&node->state_lock);
	pr_debug("receive active shutdown for node %d with state %s\n",
		 node->nodeid, dlm_state_str(node->state));
	switch (node->state) {
	case DLM_ESTABLISHED:
		node->state = DLM_FIN_WAIT1;
		pr_debug("switch node %d to state %s case 2\n",
			 node->nodeid, dlm_state_str(node->state));
		break;
	case DLM_CLOSED:
		/* we have what we want */
		spin_unlock(&node->state_lock);
		return;
	default:
		/* busy to enter DLM_FIN_WAIT1, wait until passive
		 * done in shutdown_wait to enter DLM_CLOSED.
		 */
		break;
	}
	spin_unlock(&node->state_lock);

	if (node->state == DLM_FIN_WAIT1) {
		dlm_send_fin(node, dlm_act_fin_ack_rcv);

		if (DLM_DEBUG_FENCE_TERMINATION)
			msleep(5000);
	}

	/* wait for other side dlm + fin */
	ret = wait_event_timeout(node->shutdown_wait,
				 node->state == DLM_CLOSED ||
				 test_bit(DLM_NODE_FLAG_CLOSE, &node->flags),
				 DLM_SHUTDOWN_TIMEOUT);
	if (!ret || test_bit(DLM_NODE_FLAG_CLOSE, &node->flags)) {
		pr_debug("active shutdown timed out for node %d with state %s\n",
			 node->nodeid, dlm_state_str(node->state));
		midcomms_node_reset(node);
		return;
	}

	pr_debug("active shutdown done for node %d with state %s\n",
		 node->nodeid, dlm_state_str(node->state));
}

void dlm_midcomms_shutdown(void)
{
	struct midcomms_node *node;
	int i, idx;

	mutex_lock(&close_lock);
	idx = srcu_read_lock(&nodes_srcu);
	for (i = 0; i < CONN_HASH_SIZE; i++) {
		hlist_for_each_entry_rcu(node, &node_hash[i], hlist) {
			midcomms_shutdown(node);

			dlm_delete_debug_comms_file(node->debugfs);

			spin_lock(&nodes_lock);
			hlist_del_rcu(&node->hlist);
			spin_unlock(&nodes_lock);

			call_srcu(&nodes_srcu, &node->rcu, midcomms_node_release);
		}
	}
	srcu_read_unlock(&nodes_srcu, idx);
	mutex_unlock(&close_lock);

	dlm_lowcomms_shutdown();
}

int dlm_midcomms_close(int nodeid)
{
	struct midcomms_node *node;
	int idx, ret;

	if (nodeid == dlm_our_nodeid())
		return 0;

	idx = srcu_read_lock(&nodes_srcu);
	/* Abort pending close/remove operation */
	node = nodeid2node(nodeid, 0);
	if (node) {
		/* let shutdown waiters leave */
		set_bit(DLM_NODE_FLAG_CLOSE, &node->flags);
		wake_up(&node->shutdown_wait);
	}
	srcu_read_unlock(&nodes_srcu, idx);

	synchronize_srcu(&nodes_srcu);

	idx = srcu_read_lock(&nodes_srcu);
	mutex_lock(&close_lock);
	node = nodeid2node(nodeid, 0);
	if (!node) {
		mutex_unlock(&close_lock);
		srcu_read_unlock(&nodes_srcu, idx);
		return dlm_lowcomms_close(nodeid);
	}

	ret = dlm_lowcomms_close(nodeid);
	spin_lock(&node->state_lock);
	midcomms_node_reset(node);
	spin_unlock(&node->state_lock);
	srcu_read_unlock(&nodes_srcu, idx);
	mutex_unlock(&close_lock);

	return ret;
}

/* debug functionality to send raw dlm msg from user space */
struct dlm_rawmsg_data {
	struct midcomms_node *node;
	void *buf;
};

static void midcomms_new_rawmsg_cb(void *data)
{
	struct dlm_rawmsg_data *rd = data;
	struct dlm_header *h = rd->buf;

	switch (h->h_version) {
	case cpu_to_le32(DLM_VERSION_3_1):
		break;
	default:
		switch (h->h_cmd) {
		case DLM_OPTS:
			if (!h->u.h_seq)
				h->u.h_seq = rd->node->seq_send++;
			break;
		default:
			break;
		}
		break;
	}
}

int dlm_midcomms_rawmsg_send(struct midcomms_node *node, void *buf,
			     int buflen)
{
	struct dlm_rawmsg_data rd;
	struct dlm_msg *msg;
	char *msgbuf;

	rd.node = node;
	rd.buf = buf;

	msg = dlm_lowcomms_new_msg(node->nodeid, buflen, GFP_NOFS,
				   &msgbuf, midcomms_new_rawmsg_cb, &rd);
	if (!msg)
		return -ENOMEM;

	memcpy(msgbuf, buf, buflen);
	dlm_lowcomms_commit_msg(msg);
	return 0;
}