forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxprtsock.c
1656 lines (1437 loc) · 42.9 KB
/
xprtsock.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
/*
* linux/net/sunrpc/xprtsock.c
*
* Client-side transport implementation for sockets.
*
* TCP callback races fixes (C) 1998 Red Hat Software <[email protected]>
* TCP send fixes (C) 1998 Red Hat Software <[email protected]>
* TCP NFS related read + write fixes
* (C) 1999 Dave Airlie, University of Limerick, Ireland <[email protected]>
*
* Rewrite of larges part of the code in order to stabilize TCP stuff.
* Fix behaviour when socket buffer is full.
* (C) 1999 Trond Myklebust <[email protected]>
*
* IP socket transport implementation, (C) 2005 Chuck Lever <[email protected]>
*/
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include <linux/sched.h>
#include <linux/pagemap.h>
#include <linux/errno.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/sched.h>
#include <linux/file.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/tcp.h>
/*
* xprtsock tunables
*/
unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE;
unsigned int xprt_tcp_slot_table_entries = RPC_DEF_SLOT_TABLE;
unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;
/*
* We can register our own files under /proc/sys/sunrpc by
* calling register_sysctl_table() again. The files in that
* directory become the union of all files registered there.
*
* We simply need to make sure that we don't collide with
* someone else's file names!
*/
#ifdef RPC_DEBUG
static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;
static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT;
static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT;
static struct ctl_table_header *sunrpc_table_header;
/*
* FIXME: changing the UDP slot table size should also resize the UDP
* socket buffers for existing UDP transports
*/
static ctl_table xs_tunables_table[] = {
{
.ctl_name = CTL_SLOTTABLE_UDP,
.procname = "udp_slot_table_entries",
.data = &xprt_udp_slot_table_entries,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &min_slot_table_size,
.extra2 = &max_slot_table_size
},
{
.ctl_name = CTL_SLOTTABLE_TCP,
.procname = "tcp_slot_table_entries",
.data = &xprt_tcp_slot_table_entries,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &min_slot_table_size,
.extra2 = &max_slot_table_size
},
{
.ctl_name = CTL_MIN_RESVPORT,
.procname = "min_resvport",
.data = &xprt_min_resvport,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &xprt_min_resvport_limit,
.extra2 = &xprt_max_resvport_limit
},
{
.ctl_name = CTL_MAX_RESVPORT,
.procname = "max_resvport",
.data = &xprt_max_resvport,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &xprt_min_resvport_limit,
.extra2 = &xprt_max_resvport_limit
},
{
.ctl_name = 0,
},
};
static ctl_table sunrpc_table[] = {
{
.ctl_name = CTL_SUNRPC,
.procname = "sunrpc",
.mode = 0555,
.child = xs_tunables_table
},
{
.ctl_name = 0,
},
};
#endif
/*
* How many times to try sending a request on a socket before waiting
* for the socket buffer to clear.
*/
#define XS_SENDMSG_RETRY (10U)
/*
* Time out for an RPC UDP socket connect. UDP socket connects are
* synchronous, but we set a timeout anyway in case of resource
* exhaustion on the local host.
*/
#define XS_UDP_CONN_TO (5U * HZ)
/*
* Wait duration for an RPC TCP connection to be established. Solaris
* NFS over TCP uses 60 seconds, for example, which is in line with how
* long a server takes to reboot.
*/
#define XS_TCP_CONN_TO (60U * HZ)
/*
* Wait duration for a reply from the RPC portmapper.
*/
#define XS_BIND_TO (60U * HZ)
/*
* Delay if a UDP socket connect error occurs. This is most likely some
* kind of resource problem on the local host.
*/
#define XS_UDP_REEST_TO (2U * HZ)
/*
* The reestablish timeout allows clients to delay for a bit before attempting
* to reconnect to a server that just dropped our connection.
*
* We implement an exponential backoff when trying to reestablish a TCP
* transport connection with the server. Some servers like to drop a TCP
* connection when they are overworked, so we start with a short timeout and
* increase over time if the server is down or not responding.
*/
#define XS_TCP_INIT_REEST_TO (3U * HZ)
#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ)
/*
* TCP idle timeout; client drops the transport socket if it is idle
* for this long. Note that we also timeout UDP sockets to prevent
* holding port numbers when there is no RPC traffic.
*/
#define XS_IDLE_DISC_TO (5U * 60 * HZ)
#ifdef RPC_DEBUG
# undef RPC_DEBUG_DATA
# define RPCDBG_FACILITY RPCDBG_TRANS
#endif
#ifdef RPC_DEBUG_DATA
static void xs_pktdump(char *msg, u32 *packet, unsigned int count)
{
u8 *buf = (u8 *) packet;
int j;
dprintk("RPC: %s\n", msg);
for (j = 0; j < count && j < 128; j += 4) {
if (!(j & 31)) {
if (j)
dprintk("\n");
dprintk("0x%04x ", j);
}
dprintk("%02x%02x%02x%02x ",
buf[j], buf[j+1], buf[j+2], buf[j+3]);
}
dprintk("\n");
}
#else
static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
{
/* NOP */
}
#endif
struct sock_xprt {
struct rpc_xprt xprt;
/*
* Network layer
*/
struct socket * sock;
struct sock * inet;
/*
* State of TCP reply receive
*/
__be32 tcp_fraghdr,
tcp_xid;
u32 tcp_offset,
tcp_reclen;
unsigned long tcp_copied,
tcp_flags;
/*
* Connection of transports
*/
struct delayed_work connect_worker;
unsigned short port;
/*
* UDP socket buffer size parameters
*/
size_t rcvsize,
sndsize;
/*
* Saved socket callback addresses
*/
void (*old_data_ready)(struct sock *, int);
void (*old_state_change)(struct sock *);
void (*old_write_space)(struct sock *);
};
/*
* TCP receive state flags
*/
#define TCP_RCV_LAST_FRAG (1UL << 0)
#define TCP_RCV_COPY_FRAGHDR (1UL << 1)
#define TCP_RCV_COPY_XID (1UL << 2)
#define TCP_RCV_COPY_DATA (1UL << 3)
static void xs_format_peer_addresses(struct rpc_xprt *xprt)
{
struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
char *buf;
buf = kzalloc(20, GFP_KERNEL);
if (buf) {
snprintf(buf, 20, "%u.%u.%u.%u",
NIPQUAD(addr->sin_addr.s_addr));
}
xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
buf = kzalloc(8, GFP_KERNEL);
if (buf) {
snprintf(buf, 8, "%u",
ntohs(addr->sin_port));
}
xprt->address_strings[RPC_DISPLAY_PORT] = buf;
if (xprt->prot == IPPROTO_UDP)
xprt->address_strings[RPC_DISPLAY_PROTO] = "udp";
else
xprt->address_strings[RPC_DISPLAY_PROTO] = "tcp";
buf = kzalloc(48, GFP_KERNEL);
if (buf) {
snprintf(buf, 48, "addr=%u.%u.%u.%u port=%u proto=%s",
NIPQUAD(addr->sin_addr.s_addr),
ntohs(addr->sin_port),
xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
}
xprt->address_strings[RPC_DISPLAY_ALL] = buf;
}
static void xs_free_peer_addresses(struct rpc_xprt *xprt)
{
kfree(xprt->address_strings[RPC_DISPLAY_ADDR]);
kfree(xprt->address_strings[RPC_DISPLAY_PORT]);
kfree(xprt->address_strings[RPC_DISPLAY_ALL]);
}
#define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more)
{
struct msghdr msg = {
.msg_name = addr,
.msg_namelen = addrlen,
.msg_flags = XS_SENDMSG_FLAGS | (more ? MSG_MORE : 0),
};
struct kvec iov = {
.iov_base = vec->iov_base + base,
.iov_len = vec->iov_len - base,
};
if (iov.iov_len != 0)
return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}
static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
{
struct page **ppage;
unsigned int remainder;
int err, sent = 0;
remainder = xdr->page_len - base;
base += xdr->page_base;
ppage = xdr->pages + (base >> PAGE_SHIFT);
base &= ~PAGE_MASK;
for(;;) {
unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
int flags = XS_SENDMSG_FLAGS;
remainder -= len;
if (remainder != 0 || more)
flags |= MSG_MORE;
err = sock->ops->sendpage(sock, *ppage, base, len, flags);
if (remainder == 0 || err != len)
break;
sent += err;
ppage++;
base = 0;
}
if (sent == 0)
return err;
if (err > 0)
sent += err;
return sent;
}
/**
* xs_sendpages - write pages directly to a socket
* @sock: socket to send on
* @addr: UDP only -- address of destination
* @addrlen: UDP only -- length of destination address
* @xdr: buffer containing this request
* @base: starting position in the buffer
*
*/
static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
{
unsigned int remainder = xdr->len - base;
int err, sent = 0;
if (unlikely(!sock))
return -ENOTCONN;
clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
if (base != 0) {
addr = NULL;
addrlen = 0;
}
if (base < xdr->head[0].iov_len || addr != NULL) {
unsigned int len = xdr->head[0].iov_len - base;
remainder -= len;
err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
if (remainder == 0 || err != len)
goto out;
sent += err;
base = 0;
} else
base -= xdr->head[0].iov_len;
if (base < xdr->page_len) {
unsigned int len = xdr->page_len - base;
remainder -= len;
err = xs_send_pagedata(sock, xdr, base, remainder != 0);
if (remainder == 0 || err != len)
goto out;
sent += err;
base = 0;
} else
base -= xdr->page_len;
if (base >= xdr->tail[0].iov_len)
return sent;
err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
out:
if (sent == 0)
return err;
if (err > 0)
sent += err;
return sent;
}
/**
* xs_nospace - place task on wait queue if transmit was incomplete
* @task: task to put to sleep
*
*/
static void xs_nospace(struct rpc_task *task)
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
dprintk("RPC: %4d xmit incomplete (%u left of %u)\n",
task->tk_pid, req->rq_slen - req->rq_bytes_sent,
req->rq_slen);
if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
/* Protect against races with write_space */
spin_lock_bh(&xprt->transport_lock);
/* Don't race with disconnect */
if (!xprt_connected(xprt))
task->tk_status = -ENOTCONN;
else if (test_bit(SOCK_NOSPACE, &transport->sock->flags))
xprt_wait_for_buffer_space(task);
spin_unlock_bh(&xprt->transport_lock);
} else
/* Keep holding the socket if it is blocked */
rpc_delay(task, HZ>>4);
}
/**
* xs_udp_send_request - write an RPC request to a UDP socket
* @task: address of RPC task that manages the state of an RPC request
*
* Return values:
* 0: The request has been sent
* EAGAIN: The socket was blocked, please call again later to
* complete the request
* ENOTCONN: Caller needs to invoke connect logic then call again
* other: Some other error occured, the request was not sent
*/
static int xs_udp_send_request(struct rpc_task *task)
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status;
xs_pktdump("packet data:",
req->rq_svec->iov_base,
req->rq_svec->iov_len);
req->rq_xtime = jiffies;
status = xs_sendpages(transport->sock,
(struct sockaddr *) &xprt->addr,
xprt->addrlen, xdr,
req->rq_bytes_sent);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
if (likely(status >= (int) req->rq_slen))
return 0;
/* Still some bytes left; set up for a retry later. */
if (status > 0)
status = -EAGAIN;
switch (status) {
case -ENETUNREACH:
case -EPIPE:
case -ECONNREFUSED:
/* When the server has died, an ICMP port unreachable message
* prompts ECONNREFUSED. */
break;
case -EAGAIN:
xs_nospace(task);
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
break;
}
return status;
}
static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf)
{
u32 reclen = buf->len - sizeof(rpc_fraghdr);
rpc_fraghdr *base = buf->head[0].iov_base;
*base = htonl(RPC_LAST_STREAM_FRAGMENT | reclen);
}
/**
* xs_tcp_send_request - write an RPC request to a TCP socket
* @task: address of RPC task that manages the state of an RPC request
*
* Return values:
* 0: The request has been sent
* EAGAIN: The socket was blocked, please call again later to
* complete the request
* ENOTCONN: Caller needs to invoke connect logic then call again
* other: Some other error occured, the request was not sent
*
* XXX: In the case of soft timeouts, should we eventually give up
* if sendmsg is not able to make progress?
*/
static int xs_tcp_send_request(struct rpc_task *task)
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status, retry = 0;
xs_encode_tcp_record_marker(&req->rq_snd_buf);
xs_pktdump("packet data:",
req->rq_svec->iov_base,
req->rq_svec->iov_len);
/* Continue transmitting the packet/record. We must be careful
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
while (1) {
req->rq_xtime = jiffies;
status = xs_sendpages(transport->sock,
NULL, 0, xdr, req->rq_bytes_sent);
dprintk("RPC: xs_tcp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
if (unlikely(status < 0))
break;
/* If we've sent the entire packet, immediately
* reset the count of bytes sent. */
req->rq_bytes_sent += status;
task->tk_bytes_sent += status;
if (likely(req->rq_bytes_sent >= req->rq_slen)) {
req->rq_bytes_sent = 0;
return 0;
}
status = -EAGAIN;
if (retry++ > XS_SENDMSG_RETRY)
break;
}
switch (status) {
case -EAGAIN:
xs_nospace(task);
break;
case -ECONNREFUSED:
case -ECONNRESET:
case -ENOTCONN:
case -EPIPE:
status = -ENOTCONN;
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
xprt_disconnect(xprt);
break;
}
return status;
}
/**
* xs_tcp_release_xprt - clean up after a tcp transmission
* @xprt: transport
* @task: rpc task
*
* This cleans up if an error causes us to abort the transmission of a request.
* In this case, the socket may need to be reset in order to avoid confusing
* the server.
*/
static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
{
struct rpc_rqst *req;
if (task != xprt->snd_task)
return;
if (task == NULL)
goto out_release;
req = task->tk_rqstp;
if (req->rq_bytes_sent == 0)
goto out_release;
if (req->rq_bytes_sent == req->rq_snd_buf.len)
goto out_release;
set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state);
out_release:
xprt_release_xprt(xprt, task);
}
/**
* xs_close - close a socket
* @xprt: transport
*
* This is used when all requests are complete; ie, no DRC state remains
* on the server we want to save.
*/
static void xs_close(struct rpc_xprt *xprt)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct socket *sock = transport->sock;
struct sock *sk = transport->inet;
if (!sk)
goto clear_close_wait;
dprintk("RPC: xs_close xprt %p\n", xprt);
write_lock_bh(&sk->sk_callback_lock);
transport->inet = NULL;
transport->sock = NULL;
sk->sk_user_data = NULL;
sk->sk_data_ready = transport->old_data_ready;
sk->sk_state_change = transport->old_state_change;
sk->sk_write_space = transport->old_write_space;
write_unlock_bh(&sk->sk_callback_lock);
sk->sk_no_check = 0;
sock_release(sock);
clear_close_wait:
smp_mb__before_clear_bit();
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
smp_mb__after_clear_bit();
}
/**
* xs_destroy - prepare to shutdown a transport
* @xprt: doomed transport
*
*/
static void xs_destroy(struct rpc_xprt *xprt)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
dprintk("RPC: xs_destroy xprt %p\n", xprt);
cancel_delayed_work(&transport->connect_worker);
flush_scheduled_work();
xprt_disconnect(xprt);
xs_close(xprt);
xs_free_peer_addresses(xprt);
kfree(xprt->slot);
kfree(xprt);
}
static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
{
return (struct rpc_xprt *) sk->sk_user_data;
}
/**
* xs_udp_data_ready - "data ready" callback for UDP sockets
* @sk: socket with data to read
* @len: how much data to read
*
*/
static void xs_udp_data_ready(struct sock *sk, int len)
{
struct rpc_task *task;
struct rpc_xprt *xprt;
struct rpc_rqst *rovr;
struct sk_buff *skb;
int err, repsize, copied;
u32 _xid;
__be32 *xp;
read_lock(&sk->sk_callback_lock);
dprintk("RPC: xs_udp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
if ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL)
goto out;
if (xprt->shutdown)
goto dropit;
repsize = skb->len - sizeof(struct udphdr);
if (repsize < 4) {
dprintk("RPC: impossible RPC reply size %d!\n", repsize);
goto dropit;
}
/* Copy the XID from the skb... */
xp = skb_header_pointer(skb, sizeof(struct udphdr),
sizeof(_xid), &_xid);
if (xp == NULL)
goto dropit;
/* Look up and lock the request corresponding to the given XID */
spin_lock(&xprt->transport_lock);
rovr = xprt_lookup_rqst(xprt, *xp);
if (!rovr)
goto out_unlock;
task = rovr->rq_task;
if ((copied = rovr->rq_private_buf.buflen) > repsize)
copied = repsize;
/* Suck it into the iovec, verify checksum if not done by hw. */
if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb))
goto out_unlock;
/* Something worked... */
dst_confirm(skb->dst);
xprt_adjust_cwnd(task, copied);
xprt_update_rtt(task);
xprt_complete_rqst(task, copied);
out_unlock:
spin_unlock(&xprt->transport_lock);
dropit:
skb_free_datagram(sk, skb);
out:
read_unlock(&sk->sk_callback_lock);
}
static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
size_t len, used;
char *p;
p = ((char *) &transport->tcp_fraghdr) + transport->tcp_offset;
len = sizeof(transport->tcp_fraghdr) - transport->tcp_offset;
used = xdr_skb_read_bits(desc, p, len);
transport->tcp_offset += used;
if (used != len)
return;
transport->tcp_reclen = ntohl(transport->tcp_fraghdr);
if (transport->tcp_reclen & RPC_LAST_STREAM_FRAGMENT)
transport->tcp_flags |= TCP_RCV_LAST_FRAG;
else
transport->tcp_flags &= ~TCP_RCV_LAST_FRAG;
transport->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK;
transport->tcp_flags &= ~TCP_RCV_COPY_FRAGHDR;
transport->tcp_offset = 0;
/* Sanity check of the record length */
if (unlikely(transport->tcp_reclen < 4)) {
dprintk("RPC: invalid TCP record fragment length\n");
xprt_disconnect(xprt);
return;
}
dprintk("RPC: reading TCP record fragment of length %d\n",
transport->tcp_reclen);
}
static void xs_tcp_check_fraghdr(struct sock_xprt *transport)
{
if (transport->tcp_offset == transport->tcp_reclen) {
transport->tcp_flags |= TCP_RCV_COPY_FRAGHDR;
transport->tcp_offset = 0;
if (transport->tcp_flags & TCP_RCV_LAST_FRAG) {
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
transport->tcp_flags |= TCP_RCV_COPY_XID;
transport->tcp_copied = 0;
}
}
}
static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
size_t len, used;
char *p;
len = sizeof(transport->tcp_xid) - transport->tcp_offset;
dprintk("RPC: reading XID (%Zu bytes)\n", len);
p = ((char *) &transport->tcp_xid) + transport->tcp_offset;
used = xdr_skb_read_bits(desc, p, len);
transport->tcp_offset += used;
if (used != len)
return;
transport->tcp_flags &= ~TCP_RCV_COPY_XID;
transport->tcp_flags |= TCP_RCV_COPY_DATA;
transport->tcp_copied = 4;
dprintk("RPC: reading reply for XID %08x\n",
ntohl(transport->tcp_xid));
xs_tcp_check_fraghdr(transport);
}
static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct rpc_rqst *req;
struct xdr_buf *rcvbuf;
size_t len;
ssize_t r;
/* Find and lock the request corresponding to this xid */
spin_lock(&xprt->transport_lock);
req = xprt_lookup_rqst(xprt, transport->tcp_xid);
if (!req) {
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
dprintk("RPC: XID %08x request not found!\n",
ntohl(transport->tcp_xid));
spin_unlock(&xprt->transport_lock);
return;
}
rcvbuf = &req->rq_private_buf;
len = desc->count;
if (len > transport->tcp_reclen - transport->tcp_offset) {
struct xdr_skb_reader my_desc;
len = transport->tcp_reclen - transport->tcp_offset;
memcpy(&my_desc, desc, sizeof(my_desc));
my_desc.count = len;
r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
&my_desc, xdr_skb_read_bits);
desc->count -= r;
desc->offset += r;
} else
r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
desc, xdr_skb_read_bits);
if (r > 0) {
transport->tcp_copied += r;
transport->tcp_offset += r;
}
if (r != len) {
/* Error when copying to the receive buffer,
* usually because we weren't able to allocate
* additional buffer pages. All we can do now
* is turn off TCP_RCV_COPY_DATA, so the request
* will not receive any additional updates,
* and time out.
* Any remaining data from this record will
* be discarded.
*/
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
dprintk("RPC: XID %08x truncated request\n",
ntohl(transport->tcp_xid));
dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u\n",
xprt, transport->tcp_copied, transport->tcp_offset,
transport->tcp_reclen);
goto out;
}
dprintk("RPC: XID %08x read %Zd bytes\n",
ntohl(transport->tcp_xid), r);
dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u\n",
xprt, transport->tcp_copied, transport->tcp_offset,
transport->tcp_reclen);
if (transport->tcp_copied == req->rq_private_buf.buflen)
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
else if (transport->tcp_offset == transport->tcp_reclen) {
if (transport->tcp_flags & TCP_RCV_LAST_FRAG)
transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
}
out:
if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
xprt_complete_rqst(req->rq_task, transport->tcp_copied);
spin_unlock(&xprt->transport_lock);
xs_tcp_check_fraghdr(transport);
}
static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
size_t len;
len = transport->tcp_reclen - transport->tcp_offset;
if (len > desc->count)
len = desc->count;
desc->count -= len;
desc->offset += len;
transport->tcp_offset += len;
dprintk("RPC: discarded %Zu bytes\n", len);
xs_tcp_check_fraghdr(transport);
}
static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)
{
struct rpc_xprt *xprt = rd_desc->arg.data;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_skb_reader desc = {
.skb = skb,
.offset = offset,
.count = len,
};
dprintk("RPC: xs_tcp_data_recv started\n");
do {
/* Read in a new fragment marker if necessary */
/* Can we ever really expect to get completely empty fragments? */
if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
xs_tcp_read_fraghdr(xprt, &desc);
continue;
}
/* Read in the xid if necessary */
if (transport->tcp_flags & TCP_RCV_COPY_XID) {
xs_tcp_read_xid(transport, &desc);
continue;
}
/* Read in the request data */
if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
xs_tcp_read_request(xprt, &desc);
continue;
}
/* Skip over any trailing bytes on short reads */
xs_tcp_read_discard(transport, &desc);
} while (desc.count);
dprintk("RPC: xs_tcp_data_recv done\n");
return len - desc.count;
}
/**
* xs_tcp_data_ready - "data ready" callback for TCP sockets
* @sk: socket with data to read
* @bytes: how much data to read
*
*/
static void xs_tcp_data_ready(struct sock *sk, int bytes)
{
struct rpc_xprt *xprt;
read_descriptor_t rd_desc;
read_lock(&sk->sk_callback_lock);
dprintk("RPC: xs_tcp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
if (xprt->shutdown)
goto out;
/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
rd_desc.arg.data = xprt;
rd_desc.count = 65536;
tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
out:
read_unlock(&sk->sk_callback_lock);
}
/**
* xs_tcp_state_change - callback to handle TCP socket state changes
* @sk: socket whose state has changed
*
*/
static void xs_tcp_state_change(struct sock *sk)
{
struct rpc_xprt *xprt;
read_lock(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
dprintk("RPC: state %x conn %d dead %d zapped %d\n",
sk->sk_state, xprt_connected(xprt),
sock_flag(sk, SOCK_DEAD),
sock_flag(sk, SOCK_ZAPPED));
switch (sk->sk_state) {
case TCP_ESTABLISHED:
spin_lock_bh(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
struct sock_xprt *transport = container_of(xprt,
struct sock_xprt, xprt);
/* Reset TCP record info */
transport->tcp_offset = 0;
transport->tcp_reclen = 0;
transport->tcp_copied = 0;
transport->tcp_flags =
TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
xprt_wake_pending_tasks(xprt, 0);
}
spin_unlock_bh(&xprt->transport_lock);
break;
case TCP_SYN_SENT:
case TCP_SYN_RECV:
break;
case TCP_CLOSE_WAIT:
/* Try to schedule an autoclose RPC calls */