forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
svc_xprt.c
1437 lines (1259 loc) · 38 KB
/
svc_xprt.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/svc_xprt.c
*
* Author: Tom Tucker <[email protected]>
*/
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svc_xprt.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/xprt.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <trace/events/sunrpc.h>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
static unsigned int svc_rpc_per_connection_limit __read_mostly;
module_param(svc_rpc_per_connection_limit, uint, 0644);
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
static void svc_age_temp_xprts(struct timer_list *t);
static void svc_delete_xprt(struct svc_xprt *xprt);
/* apparently the "standard" is that clients close
* idle connections after 5 minutes, servers after
* 6 minutes
* http://nfsv4bat.org/Documents/ConnectAThon/1996/nfstcp.pdf
*/
static int svc_conn_age_period = 6*60;
/* List of registered transport classes */
static DEFINE_SPINLOCK(svc_xprt_class_lock);
static LIST_HEAD(svc_xprt_class_list);
/* SMP locking strategy:
*
* svc_pool->sp_lock protects most of the fields of that pool.
* svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
* when both need to be taken (rare), svc_serv->sv_lock is first.
* The "service mutex" protects svc_serv->sv_nrthread.
* svc_sock->sk_lock protects the svc_sock->sk_deferred list
* and the ->sk_info_authunix cache.
*
* The XPT_BUSY bit in xprt->xpt_flags prevents a transport being
* enqueued multiply. During normal transport processing this bit
* is set by svc_xprt_enqueue and cleared by svc_xprt_received.
* Providers should not manipulate this bit directly.
*
* Some flags can be set to certain values at any time
* providing that certain rules are followed:
*
* XPT_CONN, XPT_DATA:
* - Can be set or cleared at any time.
* - After a set, svc_xprt_enqueue must be called to enqueue
* the transport for processing.
* - After a clear, the transport must be read/accepted.
* If this succeeds, it must be set again.
* XPT_CLOSE:
* - Can set at any time. It is never cleared.
* XPT_DEAD:
* - Can only be set while XPT_BUSY is held which ensures
* that no other thread will be using the transport or will
* try to set XPT_DEAD.
*/
int svc_reg_xprt_class(struct svc_xprt_class *xcl)
{
struct svc_xprt_class *cl;
int res = -EEXIST;
dprintk("svc: Adding svc transport class '%s'\n", xcl->xcl_name);
INIT_LIST_HEAD(&xcl->xcl_list);
spin_lock(&svc_xprt_class_lock);
/* Make sure there isn't already a class with the same name */
list_for_each_entry(cl, &svc_xprt_class_list, xcl_list) {
if (strcmp(xcl->xcl_name, cl->xcl_name) == 0)
goto out;
}
list_add_tail(&xcl->xcl_list, &svc_xprt_class_list);
res = 0;
out:
spin_unlock(&svc_xprt_class_lock);
return res;
}
EXPORT_SYMBOL_GPL(svc_reg_xprt_class);
void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
{
dprintk("svc: Removing svc transport class '%s'\n", xcl->xcl_name);
spin_lock(&svc_xprt_class_lock);
list_del_init(&xcl->xcl_list);
spin_unlock(&svc_xprt_class_lock);
}
EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
/*
* Format the transport list for printing
*/
int svc_print_xprts(char *buf, int maxlen)
{
struct svc_xprt_class *xcl;
char tmpstr[80];
int len = 0;
buf[0] = '\0';
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
int slen;
sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
slen = strlen(tmpstr);
if (len + slen > maxlen)
break;
len += slen;
strcat(buf, tmpstr);
}
spin_unlock(&svc_xprt_class_lock);
return len;
}
static void svc_xprt_free(struct kref *kref)
{
struct svc_xprt *xprt =
container_of(kref, struct svc_xprt, xpt_ref);
struct module *owner = xprt->xpt_class->xcl_owner;
if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
svcauth_unix_info_release(xprt);
put_cred(xprt->xpt_cred);
put_net(xprt->xpt_net);
/* See comment on corresponding get in xs_setup_bc_tcp(): */
if (xprt->xpt_bc_xprt)
xprt_put(xprt->xpt_bc_xprt);
if (xprt->xpt_bc_xps)
xprt_switch_put(xprt->xpt_bc_xps);
xprt->xpt_ops->xpo_free(xprt);
module_put(owner);
}
void svc_xprt_put(struct svc_xprt *xprt)
{
kref_put(&xprt->xpt_ref, svc_xprt_free);
}
EXPORT_SYMBOL_GPL(svc_xprt_put);
/*
* Called by transport drivers to initialize the transport independent
* portion of the transport instance.
*/
void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl,
struct svc_xprt *xprt, struct svc_serv *serv)
{
memset(xprt, 0, sizeof(*xprt));
xprt->xpt_class = xcl;
xprt->xpt_ops = xcl->xcl_ops;
kref_init(&xprt->xpt_ref);
xprt->xpt_server = serv;
INIT_LIST_HEAD(&xprt->xpt_list);
INIT_LIST_HEAD(&xprt->xpt_ready);
INIT_LIST_HEAD(&xprt->xpt_deferred);
INIT_LIST_HEAD(&xprt->xpt_users);
mutex_init(&xprt->xpt_mutex);
spin_lock_init(&xprt->xpt_lock);
set_bit(XPT_BUSY, &xprt->xpt_flags);
xprt->xpt_net = get_net(net);
strcpy(xprt->xpt_remotebuf, "uninitialized");
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
struct svc_serv *serv,
struct net *net,
const int family,
const unsigned short port,
int flags)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
#if IS_ENABLED(CONFIG_IPV6)
struct sockaddr_in6 sin6 = {
.sin6_family = AF_INET6,
.sin6_addr = IN6ADDR_ANY_INIT,
.sin6_port = htons(port),
};
#endif
struct sockaddr *sap;
size_t len;
switch (family) {
case PF_INET:
sap = (struct sockaddr *)&sin;
len = sizeof(sin);
break;
#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
sap = (struct sockaddr *)&sin6;
len = sizeof(sin6);
break;
#endif
default:
return ERR_PTR(-EAFNOSUPPORT);
}
return xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
}
/*
* svc_xprt_received conditionally queues the transport for processing
* by another thread. The caller must hold the XPT_BUSY bit and must
* not thereafter touch transport data.
*
* Note: XPT_DATA only gets cleared when a read-attempt finds no (or
* insufficient) data.
*/
static void svc_xprt_received(struct svc_xprt *xprt)
{
if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) {
WARN_ONCE(1, "xprt=0x%p already busy!", xprt);
return;
}
/* As soon as we clear busy, the xprt could be closed and
* 'put', so we need a reference to call svc_enqueue_xprt with:
*/
svc_xprt_get(xprt);
smp_mb__before_atomic();
clear_bit(XPT_BUSY, &xprt->xpt_flags);
xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt);
svc_xprt_put(xprt);
}
void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new)
{
clear_bit(XPT_TEMP, &new->xpt_flags);
spin_lock_bh(&serv->sv_lock);
list_add(&new->xpt_list, &serv->sv_permsocks);
spin_unlock_bh(&serv->sv_lock);
svc_xprt_received(new);
}
static int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags,
const struct cred *cred)
{
struct svc_xprt_class *xcl;
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
struct svc_xprt *newxprt;
unsigned short newport;
if (strcmp(xprt_name, xcl->xcl_name))
continue;
if (!try_module_get(xcl->xcl_owner))
goto err;
spin_unlock(&svc_xprt_class_lock);
newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags);
if (IS_ERR(newxprt)) {
module_put(xcl->xcl_owner);
return PTR_ERR(newxprt);
}
newxprt->xpt_cred = get_cred(cred);
svc_add_new_perm_xprt(serv, newxprt);
newport = svc_xprt_local_port(newxprt);
return newport;
}
err:
spin_unlock(&svc_xprt_class_lock);
/* This errno is exposed to user space. Provide a reasonable
* perror msg for a bad transport. */
return -EPROTONOSUPPORT;
}
int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags,
const struct cred *cred)
{
int err;
dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred);
if (err == -EPROTONOSUPPORT) {
request_module("svc%s", xprt_name);
err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred);
}
if (err < 0)
dprintk("svc: transport %s not found, err %d\n",
xprt_name, -err);
return err;
}
EXPORT_SYMBOL_GPL(svc_create_xprt);
/*
* Copy the local and remote xprt addresses to the rqstp structure
*/
void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
memcpy(&rqstp->rq_addr, &xprt->xpt_remote, xprt->xpt_remotelen);
rqstp->rq_addrlen = xprt->xpt_remotelen;
/*
* Destination address in request is needed for binding the
* source address in RPC replies/callbacks later.
*/
memcpy(&rqstp->rq_daddr, &xprt->xpt_local, xprt->xpt_locallen);
rqstp->rq_daddrlen = xprt->xpt_locallen;
}
EXPORT_SYMBOL_GPL(svc_xprt_copy_addrs);
/**
* svc_print_addr - Format rq_addr field for printing
* @rqstp: svc_rqst struct containing address to print
* @buf: target buffer for formatted address
* @len: length of target buffer
*
*/
char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
{
return __svc_print_addr(svc_addr(rqstp), buf, len);
}
EXPORT_SYMBOL_GPL(svc_print_addr);
static bool svc_xprt_slots_in_range(struct svc_xprt *xprt)
{
unsigned int limit = svc_rpc_per_connection_limit;
int nrqsts = atomic_read(&xprt->xpt_nr_rqsts);
return limit == 0 || (nrqsts >= 0 && nrqsts < limit);
}
static bool svc_xprt_reserve_slot(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
if (!test_bit(RQ_DATA, &rqstp->rq_flags)) {
if (!svc_xprt_slots_in_range(xprt))
return false;
atomic_inc(&xprt->xpt_nr_rqsts);
set_bit(RQ_DATA, &rqstp->rq_flags);
}
return true;
}
static void svc_xprt_release_slot(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
if (test_and_clear_bit(RQ_DATA, &rqstp->rq_flags)) {
atomic_dec(&xprt->xpt_nr_rqsts);
smp_wmb(); /* See smp_rmb() in svc_xprt_ready() */
svc_xprt_enqueue(xprt);
}
}
static bool svc_xprt_ready(struct svc_xprt *xprt)
{
unsigned long xpt_flags;
/*
* If another cpu has recently updated xpt_flags,
* sk_sock->flags, xpt_reserved, or xpt_nr_rqsts, we need to
* know about it; otherwise it's possible that both that cpu and
* this one could call svc_xprt_enqueue() without either
* svc_xprt_enqueue() recognizing that the conditions below
* are satisfied, and we could stall indefinitely:
*/
smp_rmb();
xpt_flags = READ_ONCE(xprt->xpt_flags);
if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE)))
return true;
if (xpt_flags & (BIT(XPT_DATA) | BIT(XPT_DEFERRED))) {
if (xprt->xpt_ops->xpo_has_wspace(xprt) &&
svc_xprt_slots_in_range(xprt))
return true;
trace_svc_xprt_no_write_space(xprt);
return false;
}
return false;
}
void svc_xprt_do_enqueue(struct svc_xprt *xprt)
{
struct svc_pool *pool;
struct svc_rqst *rqstp = NULL;
int cpu;
if (!svc_xprt_ready(xprt))
return;
/* Mark transport as busy. It will remain in this state until
* the provider calls svc_xprt_received. We update XPT_BUSY
* atomically because it also guards against trying to enqueue
* the transport twice.
*/
if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
return;
cpu = get_cpu();
pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
atomic_long_inc(&pool->sp_stats.packets);
spin_lock_bh(&pool->sp_lock);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
pool->sp_stats.sockets_queued++;
spin_unlock_bh(&pool->sp_lock);
/* find a thread for this xprt */
rcu_read_lock();
list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
continue;
atomic_long_inc(&pool->sp_stats.threads_woken);
rqstp->rq_qtime = ktime_get();
wake_up_process(rqstp->rq_task);
goto out_unlock;
}
set_bit(SP_CONGESTED, &pool->sp_flags);
rqstp = NULL;
out_unlock:
rcu_read_unlock();
put_cpu();
trace_svc_xprt_do_enqueue(xprt, rqstp);
}
EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue);
/*
* Queue up a transport with data pending. If there are idle nfsd
* processes, wake 'em up.
*
*/
void svc_xprt_enqueue(struct svc_xprt *xprt)
{
if (test_bit(XPT_BUSY, &xprt->xpt_flags))
return;
xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt);
}
EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
/*
* Dequeue the first transport, if there is one.
*/
static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
{
struct svc_xprt *xprt = NULL;
if (list_empty(&pool->sp_sockets))
goto out;
spin_lock_bh(&pool->sp_lock);
if (likely(!list_empty(&pool->sp_sockets))) {
xprt = list_first_entry(&pool->sp_sockets,
struct svc_xprt, xpt_ready);
list_del_init(&xprt->xpt_ready);
svc_xprt_get(xprt);
}
spin_unlock_bh(&pool->sp_lock);
out:
return xprt;
}
/**
* svc_reserve - change the space reserved for the reply to a request.
* @rqstp: The request in question
* @space: new max space to reserve
*
* Each request reserves some space on the output queue of the transport
* to make sure the reply fits. This function reduces that reserved
* space to be the amount of space used already, plus @space.
*
*/
void svc_reserve(struct svc_rqst *rqstp, int space)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
space += rqstp->rq_res.head[0].iov_len;
if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
smp_wmb(); /* See smp_rmb() in svc_xprt_ready() */
svc_xprt_enqueue(xprt);
}
}
EXPORT_SYMBOL_GPL(svc_reserve);
static void svc_xprt_release(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
xprt->xpt_ops->xpo_release_rqst(rqstp);
kfree(rqstp->rq_deferred);
rqstp->rq_deferred = NULL;
svc_free_res_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
/* Reset response buffer and release
* the reservation.
* But first, check that enough space was reserved
* for the reply, otherwise we have a bug!
*/
if ((rqstp->rq_res.len) > rqstp->rq_reserved)
printk(KERN_ERR "RPC request reserved %d but used %d\n",
rqstp->rq_reserved,
rqstp->rq_res.len);
rqstp->rq_res.head[0].iov_len = 0;
svc_reserve(rqstp, 0);
svc_xprt_release_slot(rqstp);
rqstp->rq_xprt = NULL;
svc_xprt_put(xprt);
}
/*
* Some svc_serv's will have occasional work to do, even when a xprt is not
* waiting to be serviced. This function is there to "kick" a task in one of
* those services so that it can wake up and do that work. Note that we only
* bother with pool 0 as we don't need to wake up more than one thread for
* this purpose.
*/
void svc_wake_up(struct svc_serv *serv)
{
struct svc_rqst *rqstp;
struct svc_pool *pool;
pool = &serv->sv_pools[0];
rcu_read_lock();
list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
/* skip any that aren't queued */
if (test_bit(RQ_BUSY, &rqstp->rq_flags))
continue;
rcu_read_unlock();
wake_up_process(rqstp->rq_task);
trace_svc_wake_up(rqstp->rq_task->pid);
return;
}
rcu_read_unlock();
/* No free entries available */
set_bit(SP_TASK_PENDING, &pool->sp_flags);
smp_wmb();
trace_svc_wake_up(0);
}
EXPORT_SYMBOL_GPL(svc_wake_up);
int svc_port_is_privileged(struct sockaddr *sin)
{
switch (sin->sa_family) {
case AF_INET:
return ntohs(((struct sockaddr_in *)sin)->sin_port)
< PROT_SOCK;
case AF_INET6:
return ntohs(((struct sockaddr_in6 *)sin)->sin6_port)
< PROT_SOCK;
default:
return 0;
}
}
/*
* Make sure that we don't have too many active connections. If we have,
* something must be dropped. It's not clear what will happen if we allow
* "too many" connections, but when dealing with network-facing software,
* we have to code defensively. Here we do that by imposing hard limits.
*
* There's no point in trying to do random drop here for DoS
* prevention. The NFS clients does 1 reconnect in 15 seconds. An
* attacker can easily beat that.
*
* The only somewhat efficient mechanism would be if drop old
* connections from the same IP first. But right now we don't even
* record the client IP in svc_sock.
*
* single-threaded services that expect a lot of clients will probably
* need to set sv_maxconn to override the default value which is based
* on the number of threads
*/
static void svc_check_conn_limits(struct svc_serv *serv)
{
unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
(serv->sv_nrthreads+3) * 20;
if (serv->sv_tmpcnt > limit) {
struct svc_xprt *xprt = NULL;
spin_lock_bh(&serv->sv_lock);
if (!list_empty(&serv->sv_tempsocks)) {
/* Try to help the admin */
net_notice_ratelimited("%s: too many open connections, consider increasing the %s\n",
serv->sv_name, serv->sv_maxconn ?
"max number of connections" :
"number of threads");
/*
* Always select the oldest connection. It's not fair,
* but so is life
*/
xprt = list_entry(serv->sv_tempsocks.prev,
struct svc_xprt,
xpt_list);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_get(xprt);
}
spin_unlock_bh(&serv->sv_lock);
if (xprt) {
svc_xprt_enqueue(xprt);
svc_xprt_put(xprt);
}
}
}
static int svc_alloc_arg(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct xdr_buf *arg;
int pages;
int i;
/* now allocate needed pages. If we get a failure, sleep briefly */
pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
if (pages > RPCSVC_MAXPAGES) {
pr_warn_once("svc: warning: pages=%u > RPCSVC_MAXPAGES=%lu\n",
pages, RPCSVC_MAXPAGES);
/* use as many pages as possible */
pages = RPCSVC_MAXPAGES;
}
for (i = 0; i < pages ; i++)
while (rqstp->rq_pages[i] == NULL) {
struct page *p = alloc_page(GFP_KERNEL);
if (!p) {
set_current_state(TASK_INTERRUPTIBLE);
if (signalled() || kthread_should_stop()) {
set_current_state(TASK_RUNNING);
return -EINTR;
}
schedule_timeout(msecs_to_jiffies(500));
}
rqstp->rq_pages[i] = p;
}
rqstp->rq_page_end = &rqstp->rq_pages[i];
rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
/* Make arg->head point to first page and arg->pages point to rest */
arg = &rqstp->rq_arg;
arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
arg->head[0].iov_len = PAGE_SIZE;
arg->pages = rqstp->rq_pages + 1;
arg->page_base = 0;
/* save at least one page for response */
arg->page_len = (pages-2)*PAGE_SIZE;
arg->len = (pages-1)*PAGE_SIZE;
arg->tail[0].iov_len = 0;
return 0;
}
static bool
rqst_should_sleep(struct svc_rqst *rqstp)
{
struct svc_pool *pool = rqstp->rq_pool;
/* did someone call svc_wake_up? */
if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags))
return false;
/* was a socket queued? */
if (!list_empty(&pool->sp_sockets))
return false;
/* are we shutting down? */
if (signalled() || kthread_should_stop())
return false;
/* are we freezing? */
if (freezing(current))
return false;
return true;
}
static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
{
struct svc_pool *pool = rqstp->rq_pool;
long time_left = 0;
/* rq_xprt should be clear on entry */
WARN_ON_ONCE(rqstp->rq_xprt);
rqstp->rq_xprt = svc_xprt_dequeue(pool);
if (rqstp->rq_xprt)
goto out_found;
/*
* We have to be able to interrupt this wait
* to bring down the daemons ...
*/
set_current_state(TASK_INTERRUPTIBLE);
smp_mb__before_atomic();
clear_bit(SP_CONGESTED, &pool->sp_flags);
clear_bit(RQ_BUSY, &rqstp->rq_flags);
smp_mb__after_atomic();
if (likely(rqst_should_sleep(rqstp)))
time_left = schedule_timeout(timeout);
else
__set_current_state(TASK_RUNNING);
try_to_freeze();
set_bit(RQ_BUSY, &rqstp->rq_flags);
smp_mb__after_atomic();
rqstp->rq_xprt = svc_xprt_dequeue(pool);
if (rqstp->rq_xprt)
goto out_found;
if (!time_left)
atomic_long_inc(&pool->sp_stats.threads_timedout);
if (signalled() || kthread_should_stop())
return ERR_PTR(-EINTR);
return ERR_PTR(-EAGAIN);
out_found:
/* Normally we will wait up to 5 seconds for any required
* cache information to be provided.
*/
if (!test_bit(SP_CONGESTED, &pool->sp_flags))
rqstp->rq_chandle.thread_wait = 5*HZ;
else
rqstp->rq_chandle.thread_wait = 1*HZ;
trace_svc_xprt_dequeue(rqstp);
return rqstp->rq_xprt;
}
static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
{
spin_lock_bh(&serv->sv_lock);
set_bit(XPT_TEMP, &newxpt->xpt_flags);
list_add(&newxpt->xpt_list, &serv->sv_tempsocks);
serv->sv_tmpcnt++;
if (serv->sv_temptimer.function == NULL) {
/* setup timer to age temp transports */
serv->sv_temptimer.function = svc_age_temp_xprts;
mod_timer(&serv->sv_temptimer,
jiffies + svc_conn_age_period * HZ);
}
spin_unlock_bh(&serv->sv_lock);
svc_xprt_received(newxpt);
}
static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
struct svc_serv *serv = rqstp->rq_server;
int len = 0;
if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
dprintk("svc_recv: found XPT_CLOSE\n");
if (test_and_clear_bit(XPT_KILL_TEMP, &xprt->xpt_flags))
xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
svc_delete_xprt(xprt);
/* Leave XPT_BUSY set on the dead xprt: */
goto out;
}
if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
struct svc_xprt *newxpt;
/*
* We know this module_get will succeed because the
* listener holds a reference too
*/
__module_get(xprt->xpt_class->xcl_owner);
svc_check_conn_limits(xprt->xpt_server);
newxpt = xprt->xpt_ops->xpo_accept(xprt);
if (newxpt) {
newxpt->xpt_cred = get_cred(xprt->xpt_cred);
svc_add_new_temp_xprt(serv, newxpt);
} else
module_put(xprt->xpt_class->xcl_owner);
} else if (svc_xprt_reserve_slot(rqstp, xprt)) {
/* XPT_DATA|XPT_DEFERRED case: */
dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
rqstp, rqstp->rq_pool->sp_id, xprt,
kref_read(&xprt->xpt_ref));
rqstp->rq_deferred = svc_deferred_dequeue(xprt);
if (rqstp->rq_deferred)
len = svc_deferred_recv(rqstp);
else
len = xprt->xpt_ops->xpo_recvfrom(rqstp);
rqstp->rq_stime = ktime_get();
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
}
/* clear XPT_BUSY: */
svc_xprt_received(xprt);
out:
trace_svc_handle_xprt(xprt, len);
return len;
}
/*
* Receive the next request on any transport. This code is carefully
* organised not to touch any cachelines in the shared svc_serv
* structure, only cachelines in the local svc_pool.
*/
int svc_recv(struct svc_rqst *rqstp, long timeout)
{
struct svc_xprt *xprt = NULL;
struct svc_serv *serv = rqstp->rq_server;
int len, err;
dprintk("svc: server %p waiting for data (to = %ld)\n",
rqstp, timeout);
if (rqstp->rq_xprt)
printk(KERN_ERR
"svc_recv: service %p, transport not NULL!\n",
rqstp);
err = svc_alloc_arg(rqstp);
if (err)
goto out;
try_to_freeze();
cond_resched();
err = -EINTR;
if (signalled() || kthread_should_stop())
goto out;
xprt = svc_get_next_xprt(rqstp, timeout);
if (IS_ERR(xprt)) {
err = PTR_ERR(xprt);
goto out;
}
len = svc_handle_xprt(rqstp, xprt);
/* No data, incomplete (TCP) read, or accept() */
err = -EAGAIN;
if (len <= 0)
goto out_release;
clear_bit(XPT_OLD, &xprt->xpt_flags);
xprt->xpt_ops->xpo_secure_port(rqstp);
rqstp->rq_chandle.defer = svc_defer;
rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]);
if (serv->sv_stats)
serv->sv_stats->netcnt++;
trace_svc_recv(rqstp, len);
return len;
out_release:
rqstp->rq_res.len = 0;
svc_xprt_release(rqstp);
out:
return err;
}
EXPORT_SYMBOL_GPL(svc_recv);
/*
* Drop request
*/
void svc_drop(struct svc_rqst *rqstp)
{
trace_svc_drop(rqstp);
dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt);
svc_xprt_release(rqstp);
}
EXPORT_SYMBOL_GPL(svc_drop);
/*
* Return reply to client.
*/
int svc_send(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt;
int len = -EFAULT;
struct xdr_buf *xb;
xprt = rqstp->rq_xprt;
if (!xprt)
goto out;
/* release the receive skb before sending the reply */
xprt->xpt_ops->xpo_release_rqst(rqstp);
/* calculate over-all length */
xb = &rqstp->rq_res;
xb->len = xb->head[0].iov_len +
xb->page_len +
xb->tail[0].iov_len;
/* Grab mutex to serialize outgoing data. */
mutex_lock(&xprt->xpt_mutex);
trace_svc_stats_latency(rqstp);
if (test_bit(XPT_DEAD, &xprt->xpt_flags)
|| test_bit(XPT_CLOSE, &xprt->xpt_flags))
len = -ENOTCONN;
else
len = xprt->xpt_ops->xpo_sendto(rqstp);
mutex_unlock(&xprt->xpt_mutex);
trace_svc_send(rqstp, len);
svc_xprt_release(rqstp);
if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
len = 0;
out:
return len;
}
/*
* Timer function to close old temporary transports, using
* a mark-and-sweep algorithm.
*/
static void svc_age_temp_xprts(struct timer_list *t)
{
struct svc_serv *serv = from_timer(serv, t, sv_temptimer);
struct svc_xprt *xprt;
struct list_head *le, *next;
dprintk("svc_age_temp_xprts\n");
if (!spin_trylock_bh(&serv->sv_lock)) {
/* busy, try again 1 sec later */
dprintk("svc_age_temp_xprts: busy\n");
mod_timer(&serv->sv_temptimer, jiffies + HZ);
return;
}
list_for_each_safe(le, next, &serv->sv_tempsocks) {
xprt = list_entry(le, struct svc_xprt, xpt_list);
/* First time through, just mark it OLD. Second time
* through, close it. */
if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags))
continue;
if (kref_read(&xprt->xpt_ref) > 1 ||
test_bit(XPT_BUSY, &xprt->xpt_flags))
continue;
list_del_init(le);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
dprintk("queuing xprt %p for closing\n", xprt);
/* a thread will dequeue and close it soon */
svc_xprt_enqueue(xprt);
}
spin_unlock_bh(&serv->sv_lock);
mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
}
/* Close temporary transports whose xpt_local matches server_addr immediately
* instead of waiting for them to be picked up by the timer.
*
* This is meant to be called from a notifier_block that runs when an ip
* address is deleted.
*/
void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
{
struct svc_xprt *xprt;
struct list_head *le, *next;
LIST_HEAD(to_be_closed);
spin_lock_bh(&serv->sv_lock);
list_for_each_safe(le, next, &serv->sv_tempsocks) {
xprt = list_entry(le, struct svc_xprt, xpt_list);
if (rpc_cmp_addr(server_addr, (struct sockaddr *)
&xprt->xpt_local)) {
dprintk("svc_age_temp_xprts_now: found %p\n", xprt);
list_move(le, &to_be_closed);
}
}
spin_unlock_bh(&serv->sv_lock);
while (!list_empty(&to_be_closed)) {
le = to_be_closed.next;
list_del_init(le);
xprt = list_entry(le, struct svc_xprt, xpt_list);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
set_bit(XPT_KILL_TEMP, &xprt->xpt_flags);
dprintk("svc_age_temp_xprts_now: queuing xprt %p for closing\n",
xprt);
svc_xprt_enqueue(xprt);
}