forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsvcsock.c
1654 lines (1459 loc) · 42.2 KB
/
svcsock.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
/*
* linux/net/sunrpc/svcsock.c
*
* These are the RPC server socket internals.
*
* The server scheduling algorithm does not always distribute the load
* evenly when servicing a single client. May need to modify the
* svc_xprt_enqueue procedure...
*
* TCP support is largely untested and may be a little slow. The problem
* is that we currently do two separate recvfrom's, one for the 4-byte
* record length, and the second for the actual record. This could possibly
* be improved by always reading a minimum size of around 100 bytes and
* tucking any superfluous bytes away in a temporary store. Still, that
* leaves write requests out in the rain. An alternative may be to peek at
* the first skb in the queue, and if it matches the next TCP sequence
* number, to extract the record marker. Yuck.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/file.h>
#include <linux/freezer.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/tcp_states.h>
#include <net/tls_prot.h>
#include <net/handshake.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <asm/ioctls.h>
#include <linux/key.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/xprt.h>
#include <trace/events/sock.h>
#include <trace/events/sunrpc.h>
#include "socklib.h"
#include "sunrpc.h"
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
/* To-do: to avoid tying up an nfsd thread while waiting for a
* handshake request, the request could instead be deferred.
*/
enum {
SVC_HANDSHAKE_TO = 5U * HZ
};
static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
int flags);
static int svc_udp_recvfrom(struct svc_rqst *);
static int svc_udp_sendto(struct svc_rqst *);
static void svc_sock_detach(struct svc_xprt *);
static void svc_tcp_sock_detach(struct svc_xprt *);
static void svc_sock_free(struct svc_xprt *);
static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
struct net *, struct sockaddr *,
int, int);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key svc_key[2];
static struct lock_class_key svc_slock_key[2];
static void svc_reclassify_socket(struct socket *sock)
{
struct sock *sk = sock->sk;
if (WARN_ON_ONCE(!sock_allow_reclassification(sk)))
return;
switch (sk->sk_family) {
case AF_INET:
sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
&svc_slock_key[0],
"sk_xprt.xpt_lock-AF_INET-NFSD",
&svc_key[0]);
break;
case AF_INET6:
sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
&svc_slock_key[1],
"sk_xprt.xpt_lock-AF_INET6-NFSD",
&svc_key[1]);
break;
default:
BUG();
}
}
#else
static void svc_reclassify_socket(struct socket *sock)
{
}
#endif
/**
* svc_tcp_release_ctxt - Release transport-related resources
* @xprt: the transport which owned the context
* @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
*
*/
static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
{
}
/**
* svc_udp_release_ctxt - Release transport-related resources
* @xprt: the transport which owned the context
* @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
*
*/
static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
{
struct sk_buff *skb = ctxt;
if (skb)
consume_skb(skb);
}
union svc_pktinfo_u {
struct in_pktinfo pkti;
struct in6_pktinfo pkti6;
};
#define SVC_PKTINFO_SPACE \
CMSG_SPACE(sizeof(union svc_pktinfo_u))
static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
switch (svsk->sk_sk->sk_family) {
case AF_INET: {
struct in_pktinfo *pki = CMSG_DATA(cmh);
cmh->cmsg_level = SOL_IP;
cmh->cmsg_type = IP_PKTINFO;
pki->ipi_ifindex = 0;
pki->ipi_spec_dst.s_addr =
svc_daddr_in(rqstp)->sin_addr.s_addr;
cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
}
break;
case AF_INET6: {
struct in6_pktinfo *pki = CMSG_DATA(cmh);
struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp);
cmh->cmsg_level = SOL_IPV6;
cmh->cmsg_type = IPV6_PKTINFO;
pki->ipi6_ifindex = daddr->sin6_scope_id;
pki->ipi6_addr = daddr->sin6_addr;
cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
}
break;
}
}
static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
{
return 0;
}
/*
* Report socket names for nfsdfs
*/
static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
{
const struct sock *sk = svsk->sk_sk;
const char *proto_name = sk->sk_protocol == IPPROTO_UDP ?
"udp" : "tcp";
int len;
switch (sk->sk_family) {
case PF_INET:
len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n",
proto_name,
&inet_sk(sk)->inet_rcv_saddr,
inet_sk(sk)->inet_num);
break;
#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
proto_name,
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
break;
#endif
default:
len = snprintf(buf, remaining, "*unknown-%d*\n",
sk->sk_family);
}
if (len >= remaining) {
*buf = '\0';
return -ENAMETOOLONG;
}
return len;
}
static int
svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
struct cmsghdr *cmsg, int ret)
{
u8 content_type = tls_get_record_type(sock->sk, cmsg);
u8 level, description;
switch (content_type) {
case 0:
break;
case TLS_RECORD_TYPE_DATA:
/* TLS sets EOR at the end of each application data
* record, even though there might be more frames
* waiting to be decrypted.
*/
msg->msg_flags &= ~MSG_EOR;
break;
case TLS_RECORD_TYPE_ALERT:
tls_alert_recv(sock->sk, msg, &level, &description);
ret = (level == TLS_ALERT_LEVEL_FATAL) ?
-ENOTCONN : -EAGAIN;
break;
default:
/* discard this record type */
ret = -EAGAIN;
}
return ret;
}
static int
svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
{
union {
struct cmsghdr cmsg;
u8 buf[CMSG_SPACE(sizeof(u8))];
} u;
struct socket *sock = svsk->sk_sock;
int ret;
msg->msg_control = &u;
msg->msg_controllen = sizeof(u);
ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
if (unlikely(msg->msg_controllen != sizeof(u)))
ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret);
return ret;
}
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek)
{
struct bvec_iter bi = {
.bi_size = size + seek,
};
struct bio_vec bv;
bvec_iter_advance(bvec, &bi, seek & PAGE_MASK);
for_each_bvec(bv, bvec, bi, bi)
flush_dcache_page(bv.bv_page);
}
#else
static inline void svc_flush_bvec(const struct bio_vec *bvec, size_t size,
size_t seek)
{
}
#endif
/*
* Read from @rqstp's transport socket. The incoming message fills whole
* pages in @rqstp's rq_pages array until the last page of the message
* has been received into a partial page.
*/
static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
size_t seek)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct bio_vec *bvec = rqstp->rq_bvec;
struct msghdr msg = { NULL };
unsigned int i;
ssize_t len;
size_t t;
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE)
bvec_set_page(&bvec[i], rqstp->rq_pages[i], PAGE_SIZE, 0);
rqstp->rq_respages = &rqstp->rq_pages[i];
rqstp->rq_next_page = rqstp->rq_respages + 1;
iov_iter_bvec(&msg.msg_iter, ITER_DEST, bvec, i, buflen);
if (seek) {
iov_iter_advance(&msg.msg_iter, seek);
buflen -= seek;
}
len = svc_tcp_sock_recv_cmsg(svsk, &msg);
if (len > 0)
svc_flush_bvec(bvec, len, seek);
/* If we read a full record, then assume there may be more
* data to read (stream based sockets only!)
*/
if (len == buflen)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
return len;
}
/*
* Set socket snd and rcv buffer lengths
*/
static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs)
{
unsigned int max_mesg = svsk->sk_xprt.xpt_server->sv_max_mesg;
struct socket *sock = svsk->sk_sock;
nreqs = min(nreqs, INT_MAX / 2 / max_mesg);
lock_sock(sock->sk);
sock->sk->sk_sndbuf = nreqs * max_mesg * 2;
sock->sk->sk_rcvbuf = nreqs * max_mesg * 2;
sock->sk->sk_write_space(sock->sk);
release_sock(sock->sk);
}
static void svc_sock_secure_port(struct svc_rqst *rqstp)
{
if (svc_port_is_privileged(svc_addr(rqstp)))
set_bit(RQ_SECURE, &rqstp->rq_flags);
else
clear_bit(RQ_SECURE, &rqstp->rq_flags);
}
/*
* INET callback when data has been received on the socket.
*/
static void svc_data_ready(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
trace_sk_data_ready(sk);
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_odata(sk);
trace_svcsock_data_ready(&svsk->sk_xprt, 0);
if (test_bit(XPT_HANDSHAKE, &svsk->sk_xprt.xpt_flags))
return;
if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags))
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
/*
* INET callback when space is newly available on the socket.
*/
static void svc_write_space(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data);
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
trace_svcsock_write_space(&svsk->sk_xprt, 0);
svsk->sk_owspace(sk);
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
static int svc_tcp_has_wspace(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
if (test_bit(XPT_LISTENER, &xprt->xpt_flags))
return 1;
return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
}
static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
sock_no_linger(svsk->sk_sock->sk);
}
/**
* svc_tcp_handshake_done - Handshake completion handler
* @data: address of xprt to wake
* @status: status of handshake
* @peerid: serial number of key containing the remote peer's identity
*
* If a security policy is specified as an export option, we don't
* have a specific export here to check. So we set a "TLS session
* is present" flag on the xprt and let an upper layer enforce local
* security policy.
*/
static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid)
{
struct svc_xprt *xprt = data;
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
if (!status) {
if (peerid != TLS_NO_PEERID)
set_bit(XPT_PEER_AUTH, &xprt->xpt_flags);
set_bit(XPT_TLS_SESSION, &xprt->xpt_flags);
}
clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags);
complete_all(&svsk->sk_handshake_done);
}
/**
* svc_tcp_handshake - Perform a transport-layer security handshake
* @xprt: connected transport endpoint
*
*/
static void svc_tcp_handshake(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct sock *sk = svsk->sk_sock->sk;
struct tls_handshake_args args = {
.ta_sock = svsk->sk_sock,
.ta_done = svc_tcp_handshake_done,
.ta_data = xprt,
};
int ret;
trace_svc_tls_upcall(xprt);
clear_bit(XPT_TLS_SESSION, &xprt->xpt_flags);
init_completion(&svsk->sk_handshake_done);
ret = tls_server_hello_x509(&args, GFP_KERNEL);
if (ret) {
trace_svc_tls_not_started(xprt);
goto out_failed;
}
ret = wait_for_completion_interruptible_timeout(&svsk->sk_handshake_done,
SVC_HANDSHAKE_TO);
if (ret <= 0) {
if (tls_handshake_cancel(sk)) {
trace_svc_tls_timed_out(xprt);
goto out_close;
}
}
if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) {
trace_svc_tls_unavailable(xprt);
goto out_close;
}
/* Mark the transport ready in case the remote sent RPC
* traffic before the kernel received the handshake
* completion downcall.
*/
set_bit(XPT_DATA, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
return;
out_close:
set_bit(XPT_CLOSE, &xprt->xpt_flags);
out_failed:
clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags);
set_bit(XPT_DATA, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
}
/*
* See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo
*/
static int svc_udp_get_dest_address4(struct svc_rqst *rqstp,
struct cmsghdr *cmh)
{
struct in_pktinfo *pki = CMSG_DATA(cmh);
struct sockaddr_in *daddr = svc_daddr_in(rqstp);
if (cmh->cmsg_type != IP_PKTINFO)
return 0;
daddr->sin_family = AF_INET;
daddr->sin_addr.s_addr = pki->ipi_spec_dst.s_addr;
return 1;
}
/*
* See net/ipv6/datagram.c : ip6_datagram_recv_ctl
*/
static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
struct cmsghdr *cmh)
{
struct in6_pktinfo *pki = CMSG_DATA(cmh);
struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp);
if (cmh->cmsg_type != IPV6_PKTINFO)
return 0;
daddr->sin6_family = AF_INET6;
daddr->sin6_addr = pki->ipi6_addr;
daddr->sin6_scope_id = pki->ipi6_ifindex;
return 1;
}
/*
* Copy the UDP datagram's destination address to the rqstp structure.
* The 'destination' address in this case is the address to which the
* peer sent the datagram, i.e. our local address. For multihomed
* hosts, this can change from msg to msg. Note that only the IP
* address changes, the port number should remain the same.
*/
static int svc_udp_get_dest_address(struct svc_rqst *rqstp,
struct cmsghdr *cmh)
{
switch (cmh->cmsg_level) {
case SOL_IP:
return svc_udp_get_dest_address4(rqstp, cmh);
case SOL_IPV6:
return svc_udp_get_dest_address6(rqstp, cmh);
}
return 0;
}
/**
* svc_udp_recvfrom - Receive a datagram from a UDP socket.
* @rqstp: request structure into which to receive an RPC Call
*
* Called in a loop when XPT_DATA has been set.
*
* Returns:
* On success, the number of bytes in a received RPC Call, or
* %0 if a complete RPC Call message was not ready to return
*/
static int svc_udp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct sk_buff *skb;
union {
struct cmsghdr hdr;
long all[SVC_PKTINFO_SPACE / sizeof(long)];
} buffer;
struct cmsghdr *cmh = &buffer.hdr;
struct msghdr msg = {
.msg_name = svc_addr(rqstp),
.msg_control = cmh,
.msg_controllen = sizeof(buffer),
.msg_flags = MSG_DONTWAIT,
};
size_t len;
int err;
if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
/* udp sockets need large rcvbuf as all pending
* requests are still in that buffer. sndbuf must
* also be large enough that there is enough space
* for one reply per thread. We count all threads
* rather than threads in a particular pool, which
* provides an upper bound on the number of threads
* which will access the socket.
*/
svc_sock_setbufsize(svsk, serv->sv_nrthreads + 3);
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
0, 0, MSG_PEEK | MSG_DONTWAIT);
if (err < 0)
goto out_recv_err;
skb = skb_recv_udp(svsk->sk_sk, MSG_DONTWAIT, &err);
if (!skb)
goto out_recv_err;
len = svc_addr_len(svc_addr(rqstp));
rqstp->rq_addrlen = len;
if (skb->tstamp == 0) {
skb->tstamp = ktime_get_real();
/* Don't enable netstamp, sunrpc doesn't
need that much accuracy */
}
sock_write_timestamp(svsk->sk_sk, skb->tstamp);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
len = skb->len;
rqstp->rq_arg.len = len;
trace_svcsock_udp_recv(&svsk->sk_xprt, len);
rqstp->rq_prot = IPPROTO_UDP;
if (!svc_udp_get_dest_address(rqstp, cmh))
goto out_cmsg_err;
rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp));
if (skb_is_nonlinear(skb)) {
/* we have to copy */
local_bh_disable();
if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb))
goto out_bh_enable;
local_bh_enable();
consume_skb(skb);
} else {
/* we can use it in-place */
rqstp->rq_arg.head[0].iov_base = skb->data;
rqstp->rq_arg.head[0].iov_len = len;
if (skb_checksum_complete(skb))
goto out_free;
rqstp->rq_xprt_ctxt = skb;
}
rqstp->rq_arg.page_base = 0;
if (len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = len;
rqstp->rq_arg.page_len = 0;
rqstp->rq_respages = rqstp->rq_pages+1;
} else {
rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
rqstp->rq_respages = rqstp->rq_pages + 1 +
DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
}
rqstp->rq_next_page = rqstp->rq_respages+1;
if (serv->sv_stats)
serv->sv_stats->netudpcnt++;
svc_sock_secure_port(rqstp);
svc_xprt_received(rqstp->rq_xprt);
return len;
out_recv_err:
if (err != -EAGAIN) {
/* possibly an icmp error */
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
}
trace_svcsock_udp_recv_err(&svsk->sk_xprt, err);
goto out_clear_busy;
out_cmsg_err:
net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
cmh->cmsg_level, cmh->cmsg_type);
goto out_free;
out_bh_enable:
local_bh_enable();
out_free:
kfree_skb(skb);
out_clear_busy:
svc_xprt_received(rqstp->rq_xprt);
return 0;
}
/**
* svc_udp_sendto - Send out a reply on a UDP socket
* @rqstp: completed svc_rqst
*
* xpt_mutex ensures @rqstp's whole message is written to the socket
* without interruption.
*
* Returns the number of bytes sent, or a negative errno.
*/
static int svc_udp_sendto(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct xdr_buf *xdr = &rqstp->rq_res;
union {
struct cmsghdr hdr;
long all[SVC_PKTINFO_SPACE / sizeof(long)];
} buffer;
struct cmsghdr *cmh = &buffer.hdr;
struct msghdr msg = {
.msg_name = &rqstp->rq_addr,
.msg_namelen = rqstp->rq_addrlen,
.msg_control = cmh,
.msg_controllen = sizeof(buffer),
};
unsigned int sent;
int err;
svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
rqstp->rq_xprt_ctxt = NULL;
svc_set_cmsg_data(rqstp, cmh);
mutex_lock(&xprt->xpt_mutex);
if (svc_xprt_is_dead(xprt))
goto out_notconn;
err = xdr_alloc_bvec(xdr, GFP_KERNEL);
if (err < 0)
goto out_unlock;
err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
if (err == -ECONNREFUSED) {
/* ICMP error on earlier request. */
err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
}
xdr_free_bvec(xdr);
trace_svcsock_udp_send(xprt, err);
out_unlock:
mutex_unlock(&xprt->xpt_mutex);
if (err < 0)
return err;
return sent;
out_notconn:
mutex_unlock(&xprt->xpt_mutex);
return -ENOTCONN;
}
static int svc_udp_has_wspace(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = xprt->xpt_server;
unsigned long required;
/*
* Set the SOCK_NOSPACE flag before checking the available
* sock space.
*/
set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg;
if (required*2 > sock_wspace(svsk->sk_sk))
return 0;
clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
return 1;
}
static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
{
BUG();
return NULL;
}
static void svc_udp_kill_temp_xprt(struct svc_xprt *xprt)
{
}
static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
struct net *net,
struct sockaddr *sa, int salen,
int flags)
{
return svc_create_socket(serv, IPPROTO_UDP, net, sa, salen, flags);
}
static const struct svc_xprt_ops svc_udp_ops = {
.xpo_create = svc_udp_create,
.xpo_recvfrom = svc_udp_recvfrom,
.xpo_sendto = svc_udp_sendto,
.xpo_result_payload = svc_sock_result_payload,
.xpo_release_ctxt = svc_udp_release_ctxt,
.xpo_detach = svc_sock_detach,
.xpo_free = svc_sock_free,
.xpo_has_wspace = svc_udp_has_wspace,
.xpo_accept = svc_udp_accept,
.xpo_kill_temp_xprt = svc_udp_kill_temp_xprt,
};
static struct svc_xprt_class svc_udp_class = {
.xcl_name = "udp",
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_udp_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
.xcl_ident = XPRT_TRANSPORT_UDP,
};
static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class,
&svsk->sk_xprt, serv);
clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
svsk->sk_sk->sk_data_ready = svc_data_ready;
svsk->sk_sk->sk_write_space = svc_write_space;
/* initialise setting must have enough space to
* receive and respond to one request.
* svc_udp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk, 3);
/* data might have come in before data_ready set up */
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
/* make sure we get destination address info */
switch (svsk->sk_sk->sk_family) {
case AF_INET:
ip_sock_set_pktinfo(svsk->sk_sock->sk);
break;
case AF_INET6:
ip6_sock_set_recvpktinfo(svsk->sk_sock->sk);
break;
default:
BUG();
}
}
/*
* A data_ready event on a listening socket means there's a connection
* pending. Do not use state_change as a substitute for it.
*/
static void svc_tcp_listen_data_ready(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
trace_sk_data_ready(sk);
/*
* This callback may called twice when a new connection
* is established as a child socket inherits everything
* from a parent LISTEN socket.
* 1) data_ready method of the parent socket will be called
* when one of child sockets become ESTABLISHED.
* 2) data_ready method of the child socket may be called
* when it receives data before the socket is accepted.
* In case of 2, we should ignore it silently and DO NOT
* dereference svsk.
*/
if (sk->sk_state != TCP_LISTEN)
return;
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_odata(sk);
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
/*
* A state change on a connected socket means it's dying or dead.
*/
static void svc_tcp_state_change(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_ostate(sk);
trace_svcsock_tcp_state(&svsk->sk_xprt, svsk->sk_sock);
if (sk->sk_state != TCP_ESTABLISHED)
svc_xprt_deferred_close(&svsk->sk_xprt);
}
}
/*
* Accept a TCP connection
*/
static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct sockaddr_storage addr;
struct sockaddr *sin = (struct sockaddr *) &addr;
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct socket *sock = svsk->sk_sock;
struct socket *newsock;
struct svc_sock *newsvsk;
int err, slen;
if (!sock)
return NULL;
clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
err = kernel_accept(sock, &newsock, O_NONBLOCK);
if (err < 0) {
if (err != -EAGAIN)
trace_svcsock_accept_err(xprt, serv->sv_name, err);
return NULL;
}
if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL)))
return NULL;
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
err = kernel_getpeername(newsock, sin);
if (err < 0) {
trace_svcsock_getpeername_err(xprt, serv->sv_name, err);
goto failed; /* aborted connection or whatever */
}
slen = err;
/* Reset the inherited callbacks before calling svc_setup_socket */
newsock->sk->sk_state_change = svsk->sk_ostate;
newsock->sk->sk_data_ready = svsk->sk_odata;
newsock->sk->sk_write_space = svsk->sk_owspace;
/* make sure that a write doesn't block forever when
* low on memory
*/
newsock->sk->sk_sndtimeo = HZ*30;
newsvsk = svc_setup_socket(serv, newsock,
(SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY));
if (IS_ERR(newsvsk))
goto failed;
svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
err = kernel_getsockname(newsock, sin);
slen = err;
if (unlikely(err < 0))
slen = offsetof(struct sockaddr, sa_data);
svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
if (sock_is_loopback(newsock->sk))
set_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
else
clear_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
if (serv->sv_stats)
serv->sv_stats->nettcpconn++;
return &newsvsk->sk_xprt;
failed:
sockfd_put(newsock);
return NULL;
}
static size_t svc_tcp_restore_pages(struct svc_sock *svsk,
struct svc_rqst *rqstp)
{
size_t len = svsk->sk_datalen;
unsigned int i, npages;
if (!len)
return 0;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (rqstp->rq_pages[i] != NULL)
put_page(rqstp->rq_pages[i]);
BUG_ON(svsk->sk_pages[i] == NULL);
rqstp->rq_pages[i] = svsk->sk_pages[i];
svsk->sk_pages[i] = NULL;
}
rqstp->rq_arg.head[0].iov_base = page_address(rqstp->rq_pages[0]);
return len;
}
static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
unsigned int i, len, npages;
if (svsk->sk_datalen == 0)
return;
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
svsk->sk_pages[i] = rqstp->rq_pages[i];
rqstp->rq_pages[i] = NULL;
}
}
static void svc_tcp_clear_pages(struct svc_sock *svsk)
{
unsigned int i, len, npages;
if (svsk->sk_datalen == 0)
goto out;
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (svsk->sk_pages[i] == NULL) {
WARN_ON_ONCE(1);
continue;
}
put_page(svsk->sk_pages[i]);
svsk->sk_pages[i] = NULL;
}
out:
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
}
/*
* Receive fragment record header into sk_marker.