forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlowcomms.c
1728 lines (1466 loc) · 41.9 KB
/
lowcomms.c
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
// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
** Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved.
**
**
*******************************************************************************
******************************************************************************/
/*
* lowcomms.c
*
* This is the "low-level" comms layer.
*
* It is responsible for sending/receiving messages
* from other nodes in the cluster.
*
* Cluster nodes are referred to by their nodeids. nodeids are
* simply 32 bit numbers to the locking module - if they need to
* be expanded for the cluster infrastructure then that is its
* responsibility. It is this layer's
* responsibility to resolve these into IP address or
* whatever it needs for inter-node communication.
*
* The comms level is two kernel threads that deal mainly with
* the receiving of messages from other nodes and passing them
* up to the mid-level comms layer (which understands the
* message format) for execution by the locking core, and
* a send thread which does all the setting up of connections
* to remote nodes and the sending of data. Threads are not allowed
* to send their own data because it may cause them to wait in times
* of high load. Also, this way, the sending thread can collect together
* messages bound for one node and send them in one block.
*
* lowcomms will choose to use either TCP or SCTP as its transport layer
* depending on the configuration variable 'protocol'. This should be set
* to 0 (default) for TCP or 1 for SCTP. It should be configured using a
* cluster-wide mechanism as it must be the same on all nodes of the cluster
* for the DLM to function.
*
*/
#include <asm/ioctls.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mutex.h>
#include <linux/sctp.h>
#include <linux/slab.h>
#include <net/sctp/sctp.h>
#include <net/ipv6.h>
#include "dlm_internal.h"
#include "lowcomms.h"
#include "midcomms.h"
#include "config.h"
#define NEEDED_RMEM (4*1024*1024)
#define CONN_HASH_SIZE 32
/* Number of messages to send before rescheduling */
#define MAX_SEND_MSG_COUNT 25
#define DLM_SHUTDOWN_WAIT_TIMEOUT msecs_to_jiffies(10000)
struct connection {
struct socket *sock; /* NULL if not connected */
uint32_t nodeid; /* So we know who we are in the list */
struct mutex sock_mutex;
unsigned long flags;
#define CF_READ_PENDING 1
#define CF_WRITE_PENDING 2
#define CF_INIT_PENDING 4
#define CF_IS_OTHERCON 5
#define CF_CLOSE 6
#define CF_APP_LIMITED 7
#define CF_CLOSING 8
#define CF_SHUTDOWN 9
struct list_head writequeue; /* List of outgoing writequeue_entries */
spinlock_t writequeue_lock;
int (*rx_action) (struct connection *); /* What to do when active */
void (*connect_action) (struct connection *); /* What to do to connect */
void (*shutdown_action)(struct connection *con); /* What to do to shutdown */
int retries;
#define MAX_CONNECT_RETRIES 3
struct hlist_node list;
struct connection *othercon;
struct work_struct rwork; /* Receive workqueue */
struct work_struct swork; /* Send workqueue */
wait_queue_head_t shutdown_wait; /* wait for graceful shutdown */
unsigned char *rx_buf;
int rx_buflen;
int rx_leftover;
struct rcu_head rcu;
};
#define sock2con(x) ((struct connection *)(x)->sk_user_data)
/* An entry waiting to be sent */
struct writequeue_entry {
struct list_head list;
struct page *page;
int offset;
int len;
int end;
int users;
struct connection *con;
};
struct dlm_node_addr {
struct list_head list;
int nodeid;
int addr_count;
int curr_addr_index;
struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
};
static struct listen_sock_callbacks {
void (*sk_error_report)(struct sock *);
void (*sk_data_ready)(struct sock *);
void (*sk_state_change)(struct sock *);
void (*sk_write_space)(struct sock *);
} listen_sock;
static LIST_HEAD(dlm_node_addrs);
static DEFINE_SPINLOCK(dlm_node_addrs_spin);
static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
static int dlm_local_count;
static int dlm_allow_conn;
/* Work queues */
static struct workqueue_struct *recv_workqueue;
static struct workqueue_struct *send_workqueue;
static struct hlist_head connection_hash[CONN_HASH_SIZE];
static DEFINE_SPINLOCK(connections_lock);
DEFINE_STATIC_SRCU(connections_srcu);
static void process_recv_sockets(struct work_struct *work);
static void process_send_sockets(struct work_struct *work);
/* This is deliberately very simple because most clusters have simple
sequential nodeids, so we should be able to go straight to a connection
struct in the array */
static inline int nodeid_hash(int nodeid)
{
return nodeid & (CONN_HASH_SIZE-1);
}
static struct connection *__find_con(int nodeid)
{
int r, idx;
struct connection *con;
r = nodeid_hash(nodeid);
idx = srcu_read_lock(&connections_srcu);
hlist_for_each_entry_rcu(con, &connection_hash[r], list) {
if (con->nodeid == nodeid) {
srcu_read_unlock(&connections_srcu, idx);
return con;
}
}
srcu_read_unlock(&connections_srcu, idx);
return NULL;
}
/*
* If 'allocation' is zero then we don't attempt to create a new
* connection structure for this node.
*/
static struct connection *nodeid2con(int nodeid, gfp_t alloc)
{
struct connection *con, *tmp;
int r;
con = __find_con(nodeid);
if (con || !alloc)
return con;
con = kzalloc(sizeof(*con), alloc);
if (!con)
return NULL;
con->rx_buflen = dlm_config.ci_buffer_size;
con->rx_buf = kmalloc(con->rx_buflen, GFP_NOFS);
if (!con->rx_buf) {
kfree(con);
return NULL;
}
con->nodeid = nodeid;
mutex_init(&con->sock_mutex);
INIT_LIST_HEAD(&con->writequeue);
spin_lock_init(&con->writequeue_lock);
INIT_WORK(&con->swork, process_send_sockets);
INIT_WORK(&con->rwork, process_recv_sockets);
init_waitqueue_head(&con->shutdown_wait);
/* Setup action pointers for child sockets */
if (con->nodeid) {
struct connection *zerocon = __find_con(0);
con->connect_action = zerocon->connect_action;
if (!con->rx_action)
con->rx_action = zerocon->rx_action;
}
r = nodeid_hash(nodeid);
spin_lock(&connections_lock);
/* Because multiple workqueues/threads calls this function it can
* race on multiple cpu's. Instead of locking hot path __find_con()
* we just check in rare cases of recently added nodes again
* under protection of connections_lock. If this is the case we
* abort our connection creation and return the existing connection.
*/
tmp = __find_con(nodeid);
if (tmp) {
spin_unlock(&connections_lock);
kfree(con->rx_buf);
kfree(con);
return tmp;
}
hlist_add_head_rcu(&con->list, &connection_hash[r]);
spin_unlock(&connections_lock);
return con;
}
/* Loop round all connections */
static void foreach_conn(void (*conn_func)(struct connection *c))
{
int i, idx;
struct connection *con;
idx = srcu_read_lock(&connections_srcu);
for (i = 0; i < CONN_HASH_SIZE; i++) {
hlist_for_each_entry_rcu(con, &connection_hash[i], list)
conn_func(con);
}
srcu_read_unlock(&connections_srcu, idx);
}
static struct dlm_node_addr *find_node_addr(int nodeid)
{
struct dlm_node_addr *na;
list_for_each_entry(na, &dlm_node_addrs, list) {
if (na->nodeid == nodeid)
return na;
}
return NULL;
}
static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
{
switch (x->ss_family) {
case AF_INET: {
struct sockaddr_in *sinx = (struct sockaddr_in *)x;
struct sockaddr_in *siny = (struct sockaddr_in *)y;
if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
return 0;
if (sinx->sin_port != siny->sin_port)
return 0;
break;
}
case AF_INET6: {
struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
return 0;
if (sinx->sin6_port != siny->sin6_port)
return 0;
break;
}
default:
return 0;
}
return 1;
}
static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
struct sockaddr *sa_out, bool try_new_addr)
{
struct sockaddr_storage sas;
struct dlm_node_addr *na;
if (!dlm_local_count)
return -1;
spin_lock(&dlm_node_addrs_spin);
na = find_node_addr(nodeid);
if (na && na->addr_count) {
memcpy(&sas, na->addr[na->curr_addr_index],
sizeof(struct sockaddr_storage));
if (try_new_addr) {
na->curr_addr_index++;
if (na->curr_addr_index == na->addr_count)
na->curr_addr_index = 0;
}
}
spin_unlock(&dlm_node_addrs_spin);
if (!na)
return -EEXIST;
if (!na->addr_count)
return -ENOENT;
if (sas_out)
memcpy(sas_out, &sas, sizeof(struct sockaddr_storage));
if (!sa_out)
return 0;
if (dlm_local_addr[0]->ss_family == AF_INET) {
struct sockaddr_in *in4 = (struct sockaddr_in *) &sas;
struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out;
ret4->sin_addr.s_addr = in4->sin_addr.s_addr;
} else {
struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) &sas;
struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) sa_out;
ret6->sin6_addr = in6->sin6_addr;
}
return 0;
}
static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
{
struct dlm_node_addr *na;
int rv = -EEXIST;
int addr_i;
spin_lock(&dlm_node_addrs_spin);
list_for_each_entry(na, &dlm_node_addrs, list) {
if (!na->addr_count)
continue;
for (addr_i = 0; addr_i < na->addr_count; addr_i++) {
if (addr_compare(na->addr[addr_i], addr)) {
*nodeid = na->nodeid;
rv = 0;
goto unlock;
}
}
}
unlock:
spin_unlock(&dlm_node_addrs_spin);
return rv;
}
int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
{
struct sockaddr_storage *new_addr;
struct dlm_node_addr *new_node, *na;
new_node = kzalloc(sizeof(struct dlm_node_addr), GFP_NOFS);
if (!new_node)
return -ENOMEM;
new_addr = kzalloc(sizeof(struct sockaddr_storage), GFP_NOFS);
if (!new_addr) {
kfree(new_node);
return -ENOMEM;
}
memcpy(new_addr, addr, len);
spin_lock(&dlm_node_addrs_spin);
na = find_node_addr(nodeid);
if (!na) {
new_node->nodeid = nodeid;
new_node->addr[0] = new_addr;
new_node->addr_count = 1;
list_add(&new_node->list, &dlm_node_addrs);
spin_unlock(&dlm_node_addrs_spin);
return 0;
}
if (na->addr_count >= DLM_MAX_ADDR_COUNT) {
spin_unlock(&dlm_node_addrs_spin);
kfree(new_addr);
kfree(new_node);
return -ENOSPC;
}
na->addr[na->addr_count++] = new_addr;
spin_unlock(&dlm_node_addrs_spin);
kfree(new_node);
return 0;
}
/* Data available on socket or listen socket received a connect */
static void lowcomms_data_ready(struct sock *sk)
{
struct connection *con;
read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags))
queue_work(recv_workqueue, &con->rwork);
read_unlock_bh(&sk->sk_callback_lock);
}
static void lowcomms_write_space(struct sock *sk)
{
struct connection *con;
read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (!con)
goto out;
clear_bit(SOCK_NOSPACE, &con->sock->flags);
if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
con->sock->sk->sk_write_pending--;
clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
}
queue_work(send_workqueue, &con->swork);
out:
read_unlock_bh(&sk->sk_callback_lock);
}
static inline void lowcomms_connect_sock(struct connection *con)
{
if (test_bit(CF_CLOSE, &con->flags))
return;
queue_work(send_workqueue, &con->swork);
cond_resched();
}
static void lowcomms_state_change(struct sock *sk)
{
/* SCTP layer is not calling sk_data_ready when the connection
* is done, so we catch the signal through here. Also, it
* doesn't switch socket state when entering shutdown, so we
* skip the write in that case.
*/
if (sk->sk_shutdown) {
if (sk->sk_shutdown == RCV_SHUTDOWN)
lowcomms_data_ready(sk);
} else if (sk->sk_state == TCP_ESTABLISHED) {
lowcomms_write_space(sk);
}
}
int dlm_lowcomms_connect_node(int nodeid)
{
struct connection *con;
if (nodeid == dlm_our_nodeid())
return 0;
con = nodeid2con(nodeid, GFP_NOFS);
if (!con)
return -ENOMEM;
lowcomms_connect_sock(con);
return 0;
}
static void lowcomms_error_report(struct sock *sk)
{
struct connection *con;
struct sockaddr_storage saddr;
void (*orig_report)(struct sock *) = NULL;
read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con == NULL)
goto out;
orig_report = listen_sock.sk_error_report;
if (con->sock == NULL ||
kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) {
printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
"sending to node %d, port %d, "
"sk_err=%d/%d\n", dlm_our_nodeid(),
con->nodeid, dlm_config.ci_tcp_port,
sk->sk_err, sk->sk_err_soft);
} else if (saddr.ss_family == AF_INET) {
struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr;
printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
"sending to node %d at %pI4, port %d, "
"sk_err=%d/%d\n", dlm_our_nodeid(),
con->nodeid, &sin4->sin_addr.s_addr,
dlm_config.ci_tcp_port, sk->sk_err,
sk->sk_err_soft);
} else {
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&saddr;
printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
"sending to node %d at %u.%u.%u.%u, "
"port %d, sk_err=%d/%d\n", dlm_our_nodeid(),
con->nodeid, sin6->sin6_addr.s6_addr32[0],
sin6->sin6_addr.s6_addr32[1],
sin6->sin6_addr.s6_addr32[2],
sin6->sin6_addr.s6_addr32[3],
dlm_config.ci_tcp_port, sk->sk_err,
sk->sk_err_soft);
}
out:
read_unlock_bh(&sk->sk_callback_lock);
if (orig_report)
orig_report(sk);
}
/* Note: sk_callback_lock must be locked before calling this function. */
static void save_listen_callbacks(struct socket *sock)
{
struct sock *sk = sock->sk;
listen_sock.sk_data_ready = sk->sk_data_ready;
listen_sock.sk_state_change = sk->sk_state_change;
listen_sock.sk_write_space = sk->sk_write_space;
listen_sock.sk_error_report = sk->sk_error_report;
}
static void restore_callbacks(struct socket *sock)
{
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
sk->sk_user_data = NULL;
sk->sk_data_ready = listen_sock.sk_data_ready;
sk->sk_state_change = listen_sock.sk_state_change;
sk->sk_write_space = listen_sock.sk_write_space;
sk->sk_error_report = listen_sock.sk_error_report;
write_unlock_bh(&sk->sk_callback_lock);
}
/* Make a socket active */
static void add_sock(struct socket *sock, struct connection *con)
{
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
con->sock = sock;
sk->sk_user_data = con;
/* Install a data_ready callback */
sk->sk_data_ready = lowcomms_data_ready;
sk->sk_write_space = lowcomms_write_space;
sk->sk_state_change = lowcomms_state_change;
sk->sk_allocation = GFP_NOFS;
sk->sk_error_report = lowcomms_error_report;
write_unlock_bh(&sk->sk_callback_lock);
}
/* Add the port number to an IPv6 or 4 sockaddr and return the address
length */
static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
int *addr_len)
{
saddr->ss_family = dlm_local_addr[0]->ss_family;
if (saddr->ss_family == AF_INET) {
struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
in4_addr->sin_port = cpu_to_be16(port);
*addr_len = sizeof(struct sockaddr_in);
memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero));
} else {
struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
in6_addr->sin6_port = cpu_to_be16(port);
*addr_len = sizeof(struct sockaddr_in6);
}
memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len);
}
/* Close a remote connection and tidy up */
static void close_connection(struct connection *con, bool and_other,
bool tx, bool rx)
{
bool closing = test_and_set_bit(CF_CLOSING, &con->flags);
if (tx && !closing && cancel_work_sync(&con->swork)) {
log_print("canceled swork for node %d", con->nodeid);
clear_bit(CF_WRITE_PENDING, &con->flags);
}
if (rx && !closing && cancel_work_sync(&con->rwork)) {
log_print("canceled rwork for node %d", con->nodeid);
clear_bit(CF_READ_PENDING, &con->flags);
}
mutex_lock(&con->sock_mutex);
if (con->sock) {
restore_callbacks(con->sock);
sock_release(con->sock);
con->sock = NULL;
}
if (con->othercon && and_other) {
/* Will only re-enter once. */
close_connection(con->othercon, false, true, true);
}
con->rx_leftover = 0;
con->retries = 0;
mutex_unlock(&con->sock_mutex);
clear_bit(CF_CLOSING, &con->flags);
}
static void shutdown_connection(struct connection *con)
{
int ret;
if (cancel_work_sync(&con->swork)) {
log_print("canceled swork for node %d", con->nodeid);
clear_bit(CF_WRITE_PENDING, &con->flags);
}
mutex_lock(&con->sock_mutex);
/* nothing to shutdown */
if (!con->sock) {
mutex_unlock(&con->sock_mutex);
return;
}
set_bit(CF_SHUTDOWN, &con->flags);
ret = kernel_sock_shutdown(con->sock, SHUT_WR);
mutex_unlock(&con->sock_mutex);
if (ret) {
log_print("Connection %p failed to shutdown: %d will force close",
con, ret);
goto force_close;
} else {
ret = wait_event_timeout(con->shutdown_wait,
!test_bit(CF_SHUTDOWN, &con->flags),
DLM_SHUTDOWN_WAIT_TIMEOUT);
if (ret == 0) {
log_print("Connection %p shutdown timed out, will force close",
con);
goto force_close;
}
}
return;
force_close:
clear_bit(CF_SHUTDOWN, &con->flags);
close_connection(con, false, true, true);
}
static void dlm_tcp_shutdown(struct connection *con)
{
if (con->othercon)
shutdown_connection(con->othercon);
shutdown_connection(con);
}
static int con_realloc_receive_buf(struct connection *con, int newlen)
{
unsigned char *newbuf;
newbuf = kmalloc(newlen, GFP_NOFS);
if (!newbuf)
return -ENOMEM;
/* copy any leftover from last receive */
if (con->rx_leftover)
memmove(newbuf, con->rx_buf, con->rx_leftover);
/* swap to new buffer space */
kfree(con->rx_buf);
con->rx_buflen = newlen;
con->rx_buf = newbuf;
return 0;
}
/* Data received from remote end */
static int receive_from_sock(struct connection *con)
{
int call_again_soon = 0;
struct msghdr msg;
struct kvec iov;
int ret, buflen;
mutex_lock(&con->sock_mutex);
if (con->sock == NULL) {
ret = -EAGAIN;
goto out_close;
}
if (con->nodeid == 0) {
ret = -EINVAL;
goto out_close;
}
/* realloc if we get new buffer size to read out */
buflen = dlm_config.ci_buffer_size;
if (con->rx_buflen != buflen && con->rx_leftover <= buflen) {
ret = con_realloc_receive_buf(con, buflen);
if (ret < 0)
goto out_resched;
}
/* calculate new buffer parameter regarding last receive and
* possible leftover bytes
*/
iov.iov_base = con->rx_buf + con->rx_leftover;
iov.iov_len = con->rx_buflen - con->rx_leftover;
memset(&msg, 0, sizeof(msg));
msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
ret = kernel_recvmsg(con->sock, &msg, &iov, 1, iov.iov_len,
msg.msg_flags);
if (ret <= 0)
goto out_close;
else if (ret == iov.iov_len)
call_again_soon = 1;
/* new buflen according readed bytes and leftover from last receive */
buflen = ret + con->rx_leftover;
ret = dlm_process_incoming_buffer(con->nodeid, con->rx_buf, buflen);
if (ret < 0)
goto out_close;
/* calculate leftover bytes from process and put it into begin of
* the receive buffer, so next receive we have the full message
* at the start address of the receive buffer.
*/
con->rx_leftover = buflen - ret;
if (con->rx_leftover) {
memmove(con->rx_buf, con->rx_buf + ret,
con->rx_leftover);
call_again_soon = true;
}
if (call_again_soon)
goto out_resched;
mutex_unlock(&con->sock_mutex);
return 0;
out_resched:
if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
queue_work(recv_workqueue, &con->rwork);
mutex_unlock(&con->sock_mutex);
return -EAGAIN;
out_close:
mutex_unlock(&con->sock_mutex);
if (ret != -EAGAIN) {
/* Reconnect when there is something to send */
close_connection(con, false, true, false);
if (ret == 0) {
log_print("connection %p got EOF from %d",
con, con->nodeid);
/* handling for tcp shutdown */
clear_bit(CF_SHUTDOWN, &con->flags);
wake_up(&con->shutdown_wait);
/* signal to breaking receive worker */
ret = -1;
}
}
return ret;
}
/* Listening socket is busy, accept a connection */
static int accept_from_sock(struct connection *con)
{
int result;
struct sockaddr_storage peeraddr;
struct socket *newsock;
int len;
int nodeid;
struct connection *newcon;
struct connection *addcon;
unsigned int mark;
if (!dlm_allow_conn) {
return -1;
}
mutex_lock_nested(&con->sock_mutex, 0);
if (!con->sock) {
mutex_unlock(&con->sock_mutex);
return -ENOTCONN;
}
result = kernel_accept(con->sock, &newsock, O_NONBLOCK);
if (result < 0)
goto accept_err;
/* Get the connected socket's peer */
memset(&peeraddr, 0, sizeof(peeraddr));
len = newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, 2);
if (len < 0) {
result = -ECONNABORTED;
goto accept_err;
}
/* Get the new node's NODEID */
make_sockaddr(&peeraddr, 0, &len);
if (addr_to_nodeid(&peeraddr, &nodeid)) {
unsigned char *b=(unsigned char *)&peeraddr;
log_print("connect from non cluster node");
print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
b, sizeof(struct sockaddr_storage));
sock_release(newsock);
mutex_unlock(&con->sock_mutex);
return -1;
}
dlm_comm_mark(nodeid, &mark);
sock_set_mark(newsock->sk, mark);
log_print("got connection from %d", nodeid);
/* Check to see if we already have a connection to this node. This
* could happen if the two nodes initiate a connection at roughly
* the same time and the connections cross on the wire.
* In this case we store the incoming one in "othercon"
*/
newcon = nodeid2con(nodeid, GFP_NOFS);
if (!newcon) {
result = -ENOMEM;
goto accept_err;
}
mutex_lock_nested(&newcon->sock_mutex, 1);
if (newcon->sock) {
struct connection *othercon = newcon->othercon;
if (!othercon) {
othercon = kzalloc(sizeof(*othercon), GFP_NOFS);
if (!othercon) {
log_print("failed to allocate incoming socket");
mutex_unlock(&newcon->sock_mutex);
result = -ENOMEM;
goto accept_err;
}
othercon->rx_buflen = dlm_config.ci_buffer_size;
othercon->rx_buf = kmalloc(othercon->rx_buflen, GFP_NOFS);
if (!othercon->rx_buf) {
mutex_unlock(&newcon->sock_mutex);
kfree(othercon);
log_print("failed to allocate incoming socket receive buffer");
result = -ENOMEM;
goto accept_err;
}
othercon->nodeid = nodeid;
othercon->rx_action = receive_from_sock;
mutex_init(&othercon->sock_mutex);
INIT_LIST_HEAD(&othercon->writequeue);
spin_lock_init(&othercon->writequeue_lock);
INIT_WORK(&othercon->swork, process_send_sockets);
INIT_WORK(&othercon->rwork, process_recv_sockets);
init_waitqueue_head(&othercon->shutdown_wait);
set_bit(CF_IS_OTHERCON, &othercon->flags);
} else {
/* close other sock con if we have something new */
close_connection(othercon, false, true, false);
}
mutex_lock_nested(&othercon->sock_mutex, 2);
newcon->othercon = othercon;
add_sock(newsock, othercon);
addcon = othercon;
mutex_unlock(&othercon->sock_mutex);
}
else {
newcon->rx_action = receive_from_sock;
/* accept copies the sk after we've saved the callbacks, so we
don't want to save them a second time or comm errors will
result in calling sk_error_report recursively. */
add_sock(newsock, newcon);
addcon = newcon;
}
mutex_unlock(&newcon->sock_mutex);
/*
* Add it to the active queue in case we got data
* between processing the accept adding the socket
* to the read_sockets list
*/
if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
queue_work(recv_workqueue, &addcon->rwork);
mutex_unlock(&con->sock_mutex);
return 0;
accept_err:
mutex_unlock(&con->sock_mutex);
if (newsock)
sock_release(newsock);
if (result != -EAGAIN)
log_print("error accepting connection from node: %d", result);
return result;
}
static void free_entry(struct writequeue_entry *e)
{
__free_page(e->page);
kfree(e);
}
/*
* writequeue_entry_complete - try to delete and free write queue entry
* @e: write queue entry to try to delete
* @completed: bytes completed
*
* writequeue_lock must be held.
*/
static void writequeue_entry_complete(struct writequeue_entry *e, int completed)
{
e->offset += completed;
e->len -= completed;
if (e->len == 0 && e->users == 0) {
list_del(&e->list);
free_entry(e);
}
}
/*
* sctp_bind_addrs - bind a SCTP socket to all our addresses
*/
static int sctp_bind_addrs(struct connection *con, uint16_t port)
{
struct sockaddr_storage localaddr;
struct sockaddr *addr = (struct sockaddr *)&localaddr;
int i, addr_len, result = 0;
for (i = 0; i < dlm_local_count; i++) {
memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr));
make_sockaddr(&localaddr, port, &addr_len);
if (!i)
result = kernel_bind(con->sock, addr, addr_len);
else
result = sock_bind_add(con->sock->sk, addr, addr_len);
if (result < 0) {
log_print("Can't bind to %d addr number %d, %d.\n",
port, i + 1, result);
break;
}
}
return result;
}
/* Initiate an SCTP association.
This is a special case of send_to_sock() in that we don't yet have a
peeled-off socket for this association, so we use the listening socket
and add the primary IP address of the remote node.
*/
static void sctp_connect_to_sock(struct connection *con)
{
struct sockaddr_storage daddr;
int result;
int addr_len;
struct socket *sock;
unsigned int mark;
if (con->nodeid == 0) {
log_print("attempt to connect sock 0 foiled");
return;
}
dlm_comm_mark(con->nodeid, &mark);
mutex_lock(&con->sock_mutex);
/* Some odd races can cause double-connects, ignore them */
if (con->retries++ > MAX_CONNECT_RETRIES)
goto out;
if (con->sock) {
log_print("node %d already connected.", con->nodeid);
goto out;
}
memset(&daddr, 0, sizeof(daddr));
result = nodeid_to_addr(con->nodeid, &daddr, NULL, true);
if (result < 0) {
log_print("no address for nodeid %d", con->nodeid);
goto out;
}
/* Create a socket to communicate with */
result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
SOCK_STREAM, IPPROTO_SCTP, &sock);
if (result < 0)
goto socket_err;