summaryrefslogtreecommitdiff
path: root/net/sunrpc/xprt.c
blob: c64c0ef519b594320ff688f3881579d2926be21d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
/*
 *  linux/net/sunrpc/xprt.c
 *
 *  This is a generic RPC call interface supporting congestion avoidance,
 *  and asynchronous calls.
 *
 *  The interface works like this:
 *
 *  -	When a process places a call, it allocates a request slot if
 *	one is available. Otherwise, it sleeps on the backlog queue
 *	(xprt_reserve).
 *  -	Next, the caller puts together the RPC message, stuffs it into
 *	the request struct, and calls xprt_transmit().
 *  -	xprt_transmit sends the message and installs the caller on the
 *	transport's wait list. At the same time, if a reply is expected,
 *	it installs a timer that is run after the packet's timeout has
 *	expired.
 *  -	When a packet arrives, the data_ready handler walks the list of
 *	pending requests for that transport. If a matching XID is found, the
 *	caller is woken up, and the timer removed.
 *  -	When no reply arrives within the timeout interval, the timer is
 *	fired by the kernel and runs xprt_timer(). It either adjusts the
 *	timeout values (minor timeout) or wakes up the caller with a status
 *	of -ETIMEDOUT.
 *  -	When the caller receives a notification from RPC that a reply arrived,
 *	it should release the RPC slot, and process the reply.
 *	If the call timed out, it may choose to retry the operation by
 *	adjusting the initial timeout value, and simply calling rpc_call
 *	again.
 *
 *  Support for async RPC is done through a set of RPC-specific scheduling
 *  primitives that `transparently' work for processes as well as async
 *  tasks that rely on callbacks.
 *
 *  Copyright (C) 1995-1997, Olaf Kirch <okir@monad.swb.de>
 *
 *  Transport switch API copyright (C) 2005, Chuck Lever <cel@netapp.com>
 */

#include <linux/module.h>

#include <linux/types.h>
#include <linux/interrupt.h>
#include <linux/workqueue.h>
#include <linux/net.h>
#include <linux/ktime.h>

#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/metrics.h>
#include <linux/sunrpc/bc_xprt.h>

#include "sunrpc.h"

/*
 * Local variables
 */

#ifdef RPC_DEBUG
# define RPCDBG_FACILITY	RPCDBG_XPRT
#endif

/*
 * Local functions
 */
static void	 xprt_init(struct rpc_xprt *xprt, struct net *net);
static void	xprt_request_init(struct rpc_task *, struct rpc_xprt *);
static void	xprt_connect_status(struct rpc_task *task);
static int      __xprt_get_cong(struct rpc_xprt *, struct rpc_task *);

static DEFINE_SPINLOCK(xprt_list_lock);
static LIST_HEAD(xprt_list);

/*
 * The transport code maintains an estimate on the maximum number of out-
 * standing RPC requests, using a smoothed version of the congestion
 * avoidance implemented in 44BSD. This is basically the Van Jacobson
 * congestion algorithm: If a retransmit occurs, the congestion window is
 * halved; otherwise, it is incremented by 1/cwnd when
 *
 *	-	a reply is received and
 *	-	a full number of requests are outstanding and
 *	-	the congestion window hasn't been updated recently.
 */
#define RPC_CWNDSHIFT		(8U)
#define RPC_CWNDSCALE		(1U << RPC_CWNDSHIFT)
#define RPC_INITCWND		RPC_CWNDSCALE
#define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)

#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)

/**
 * xprt_register_transport - register a transport implementation
 * @transport: transport to register
 *
 * If a transport implementation is loaded as a kernel module, it can
 * call this interface to make itself known to the RPC client.
 *
 * Returns:
 * 0:		transport successfully registered
 * -EEXIST:	transport already registered
 * -EINVAL:	transport module being unloaded
 */
int xprt_register_transport(struct xprt_class *transport)
{
	struct xprt_class *t;
	int result;

	result = -EEXIST;
	spin_lock(&xprt_list_lock);
	list_for_each_entry(t, &xprt_list, list) {
		/* don't register the same transport class twice */
		if (t->ident == transport->ident)
			goto out;
	}

	list_add_tail(&transport->list, &xprt_list);
	printk(KERN_INFO "RPC: Registered %s transport module.\n",
	       transport->name);
	result = 0;

out:
	spin_unlock(&xprt_list_lock);
	return result;
}
EXPORT_SYMBOL_GPL(xprt_register_transport);

/**
 * xprt_unregister_transport - unregister a transport implementation
 * @transport: transport to unregister
 *
 * Returns:
 * 0:		transport successfully unregistered
 * -ENOENT:	transport never registered
 */
int xprt_unregister_transport(struct xprt_class *transport)
{
	struct xprt_class *t;
	int result;

	result = 0;
	spin_lock(&xprt_list_lock);
	list_for_each_entry(t, &xprt_list, list) {
		if (t == transport) {
			printk(KERN_INFO
				"RPC: Unregistered %s transport module.\n",
				transport->name);
			list_del_init(&transport->list);
			goto out;
		}
	}
	result = -ENOENT;

out:
	spin_unlock(&xprt_list_lock);
	return result;
}
EXPORT_SYMBOL_GPL(xprt_unregister_transport);

/**
 * xprt_load_transport - load a transport implementation
 * @transport_name: transport to load
 *
 * Returns:
 * 0:		transport successfully loaded
 * -ENOENT:	transport module not available
 */
int xprt_load_transport(const char *transport_name)
{
	struct xprt_class *t;
	int result;

	result = 0;
	spin_lock(&xprt_list_lock);
	list_for_each_entry(t, &xprt_list, list) {
		if (strcmp(t->name, transport_name) == 0) {
			spin_unlock(&xprt_list_lock);
			goto out;
		}
	}
	spin_unlock(&xprt_list_lock);
	result = request_module("xprt%s", transport_name);
out:
	return result;
}
EXPORT_SYMBOL_GPL(xprt_load_transport);

/**
 * xprt_reserve_xprt - serialize write access to transports
 * @task: task that is requesting access to the transport
 * @xprt: pointer to the target transport
 *
 * This prevents mixing the payload of separate requests, and prevents
 * transport connects from colliding with writes.  No congestion control
 * is provided.
 */
int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	int priority;

	if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) {
		if (task == xprt->snd_task)
			return 1;
		goto out_sleep;
	}
	xprt->snd_task = task;
	if (req != NULL) {
		req->rq_bytes_sent = 0;
		req->rq_ntrans++;
	}

	return 1;

out_sleep:
	dprintk("RPC: %5u failed to lock transport %p\n",
			task->tk_pid, xprt);
	task->tk_timeout = 0;
	task->tk_status = -EAGAIN;
	if (req == NULL)
		priority = RPC_PRIORITY_LOW;
	else if (!req->rq_ntrans)
		priority = RPC_PRIORITY_NORMAL;
	else
		priority = RPC_PRIORITY_HIGH;
	rpc_sleep_on_priority(&xprt->sending, task, NULL, priority);
	return 0;
}
EXPORT_SYMBOL_GPL(xprt_reserve_xprt);

static void xprt_clear_locked(struct rpc_xprt *xprt)
{
	xprt->snd_task = NULL;
	if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state) || xprt->shutdown) {
		smp_mb__before_clear_bit();
		clear_bit(XPRT_LOCKED, &xprt->state);
		smp_mb__after_clear_bit();
	} else
		queue_work(rpciod_workqueue, &xprt->task_cleanup);
}

/*
 * xprt_reserve_xprt_cong - serialize write access to transports
 * @task: task that is requesting access to the transport
 *
 * Same as xprt_reserve_xprt, but Van Jacobson congestion control is
 * integrated into the decision of whether a request is allowed to be
 * woken up and given access to the transport.
 */
int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	int priority;

	if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) {
		if (task == xprt->snd_task)
			return 1;
		goto out_sleep;
	}
	if (req == NULL) {
		xprt->snd_task = task;
		return 1;
	}
	if (__xprt_get_cong(xprt, task)) {
		xprt->snd_task = task;
		req->rq_bytes_sent = 0;
		req->rq_ntrans++;
		return 1;
	}
	xprt_clear_locked(xprt);
out_sleep:
	dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt);
	task->tk_timeout = 0;
	task->tk_status = -EAGAIN;
	if (req == NULL)
		priority = RPC_PRIORITY_LOW;
	else if (!req->rq_ntrans)
		priority = RPC_PRIORITY_NORMAL;
	else
		priority = RPC_PRIORITY_HIGH;
	rpc_sleep_on_priority(&xprt->sending, task, NULL, priority);
	return 0;
}
EXPORT_SYMBOL_GPL(xprt_reserve_xprt_cong);

static inline int xprt_lock_write(struct rpc_xprt *xprt, struct rpc_task *task)
{
	int retval;

	spin_lock_bh(&xprt->transport_lock);
	retval = xprt->ops->reserve_xprt(xprt, task);
	spin_unlock_bh(&xprt->transport_lock);
	return retval;
}

static void __xprt_lock_write_next(struct rpc_xprt *xprt)
{
	struct rpc_task *task;
	struct rpc_rqst *req;

	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
		return;

	task = rpc_wake_up_next(&xprt->sending);
	if (task == NULL)
		goto out_unlock;

	req = task->tk_rqstp;
	xprt->snd_task = task;
	if (req) {
		req->rq_bytes_sent = 0;
		req->rq_ntrans++;
	}
	return;

out_unlock:
	xprt_clear_locked(xprt);
}

static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt)
{
	struct rpc_task *task;
	struct rpc_rqst *req;

	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
		return;
	if (RPCXPRT_CONGESTED(xprt))
		goto out_unlock;
	task = rpc_wake_up_next(&xprt->sending);
	if (task == NULL)
		goto out_unlock;

	req = task->tk_rqstp;
	if (req == NULL) {
		xprt->snd_task = task;
		return;
	}
	if (__xprt_get_cong(xprt, task)) {
		xprt->snd_task = task;
		req->rq_bytes_sent = 0;
		req->rq_ntrans++;
		return;
	}
out_unlock:
	xprt_clear_locked(xprt);
}

/**
 * xprt_release_xprt - allow other requests to use a transport
 * @xprt: transport with other tasks potentially waiting
 * @task: task that is releasing access to the transport
 *
 * Note that "task" can be NULL.  No congestion control is provided.
 */
void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
{
	if (xprt->snd_task == task) {
		xprt_clear_locked(xprt);
		__xprt_lock_write_next(xprt);
	}
}
EXPORT_SYMBOL_GPL(xprt_release_xprt);

/**
 * xprt_release_xprt_cong - allow other requests to use a transport
 * @xprt: transport with other tasks potentially waiting
 * @task: task that is releasing access to the transport
 *
 * Note that "task" can be NULL.  Another task is awoken to use the
 * transport if the transport's congestion window allows it.
 */
void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
{
	if (xprt->snd_task == task) {
		xprt_clear_locked(xprt);
		__xprt_lock_write_next_cong(xprt);
	}
}
EXPORT_SYMBOL_GPL(xprt_release_xprt_cong);

static inline void xprt_release_write(struct rpc_xprt *xprt, struct rpc_task *task)
{
	spin_lock_bh(&xprt->transport_lock);
	xprt->ops->release_xprt(xprt, task);
	spin_unlock_bh(&xprt->transport_lock);
}

/*
 * Van Jacobson congestion avoidance. Check if the congestion window
 * overflowed. Put the task to sleep if this is the case.
 */
static int
__xprt_get_cong(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;

	if (req->rq_cong)
		return 1;
	dprintk("RPC: %5u xprt_cwnd_limited cong = %lu cwnd = %lu\n",
			task->tk_pid, xprt->cong, xprt->cwnd);
	if (RPCXPRT_CONGESTED(xprt))
		return 0;
	req->rq_cong = 1;
	xprt->cong += RPC_CWNDSCALE;
	return 1;
}

/*
 * Adjust the congestion window, and wake up the next task
 * that has been sleeping due to congestion
 */
static void
__xprt_put_cong(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
	if (!req->rq_cong)
		return;
	req->rq_cong = 0;
	xprt->cong -= RPC_CWNDSCALE;
	__xprt_lock_write_next_cong(xprt);
}

/**
 * xprt_release_rqst_cong - housekeeping when request is complete
 * @task: RPC request that recently completed
 *
 * Useful for transports that require congestion control.
 */
void xprt_release_rqst_cong(struct rpc_task *task)
{
	__xprt_put_cong(task->tk_xprt, task->tk_rqstp);
}
EXPORT_SYMBOL_GPL(xprt_release_rqst_cong);

/**
 * xprt_adjust_cwnd - adjust transport congestion window
 * @task: recently completed RPC request used to adjust window
 * @result: result code of completed RPC request
 *
 * We use a time-smoothed congestion estimator to avoid heavy oscillation.
 */
void xprt_adjust_cwnd(struct rpc_task *task, int result)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = task->tk_xprt;
	unsigned long cwnd = xprt->cwnd;

	if (result >= 0 && cwnd <= xprt->cong) {
		/* The (cwnd >> 1) term makes sure
		 * the result gets rounded properly. */
		cwnd += (RPC_CWNDSCALE * RPC_CWNDSCALE + (cwnd >> 1)) / cwnd;
		if (cwnd > RPC_MAXCWND(xprt))
			cwnd = RPC_MAXCWND(xprt);
		__xprt_lock_write_next_cong(xprt);
	} else if (result == -ETIMEDOUT) {
		cwnd >>= 1;
		if (cwnd < RPC_CWNDSCALE)
			cwnd = RPC_CWNDSCALE;
	}
	dprintk("RPC:       cong %ld, cwnd was %ld, now %ld\n",
			xprt->cong, xprt->cwnd, cwnd);
	xprt->cwnd = cwnd;
	__xprt_put_cong(xprt, req);
}
EXPORT_SYMBOL_GPL(xprt_adjust_cwnd);

/**
 * xprt_wake_pending_tasks - wake all tasks on a transport's pending queue
 * @xprt: transport with waiting tasks
 * @status: result code to plant in each task before waking it
 *
 */
void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status)
{
	if (status < 0)
		rpc_wake_up_status(&xprt->pending, status);
	else
		rpc_wake_up(&xprt->pending);
}
EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks);

/**
 * xprt_wait_for_buffer_space - wait for transport output buffer to clear
 * @task: task to be put to sleep
 * @action: function pointer to be executed after wait
 */
void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;

	task->tk_timeout = req->rq_timeout;
	rpc_sleep_on(&xprt->pending, task, action);
}
EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space);

/**
 * xprt_write_space - wake the task waiting for transport output buffer space
 * @xprt: transport with waiting tasks
 *
 * Can be called in a soft IRQ context, so xprt_write_space never sleeps.
 */
void xprt_write_space(struct rpc_xprt *xprt)
{
	if (unlikely(xprt->shutdown))
		return;

	spin_lock_bh(&xprt->transport_lock);
	if (xprt->snd_task) {
		dprintk("RPC:       write space: waking waiting task on "
				"xprt %p\n", xprt);
		rpc_wake_up_queued_task(&xprt->pending, xprt->snd_task);
	}
	spin_unlock_bh(&xprt->transport_lock);
}
EXPORT_SYMBOL_GPL(xprt_write_space);

/**
 * xprt_set_retrans_timeout_def - set a request's retransmit timeout
 * @task: task whose timeout is to be set
 *
 * Set a request's retransmit timeout based on the transport's
 * default timeout parameters.  Used by transports that don't adjust
 * the retransmit timeout based on round-trip time estimation.
 */
void xprt_set_retrans_timeout_def(struct rpc_task *task)
{
	task->tk_timeout = task->tk_rqstp->rq_timeout;
}
EXPORT_SYMBOL_GPL(xprt_set_retrans_timeout_def);

/*
 * xprt_set_retrans_timeout_rtt - set a request's retransmit timeout
 * @task: task whose timeout is to be set
 *
 * Set a request's retransmit timeout using the RTT estimator.
 */
void xprt_set_retrans_timeout_rtt(struct rpc_task *task)
{
	int timer = task->tk_msg.rpc_proc->p_timer;
	struct rpc_clnt *clnt = task->tk_client;
	struct rpc_rtt *rtt = clnt->cl_rtt;
	struct rpc_rqst *req = task->tk_rqstp;
	unsigned long max_timeout = clnt->cl_timeout->to_maxval;

	task->tk_timeout = rpc_calc_rto(rtt, timer);
	task->tk_timeout <<= rpc_ntimeo(rtt, timer) + req->rq_retries;
	if (task->tk_timeout > max_timeout || task->tk_timeout == 0)
		task->tk_timeout = max_timeout;
}
EXPORT_SYMBOL_GPL(xprt_set_retrans_timeout_rtt);

static void xprt_reset_majortimeo(struct rpc_rqst *req)
{
	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;

	req->rq_majortimeo = req->rq_timeout;
	if (to->to_exponential)
		req->rq_majortimeo <<= to->to_retries;
	else
		req->rq_majortimeo += to->to_increment * to->to_retries;
	if (req->rq_majortimeo > to->to_maxval || req->rq_majortimeo == 0)
		req->rq_majortimeo = to->to_maxval;
	req->rq_majortimeo += jiffies;
}

/**
 * xprt_adjust_timeout - adjust timeout values for next retransmit
 * @req: RPC request containing parameters to use for the adjustment
 *
 */
int xprt_adjust_timeout(struct rpc_rqst *req)
{
	struct rpc_xprt *xprt = req->rq_xprt;
	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
	int status = 0;

	if (time_before(jiffies, req->rq_majortimeo)) {
		if (to->to_exponential)
			req->rq_timeout <<= 1;
		else
			req->rq_timeout += to->to_increment;
		if (to->to_maxval && req->rq_timeout >= to->to_maxval)
			req->rq_timeout = to->to_maxval;
		req->rq_retries++;
	} else {
		req->rq_timeout = to->to_initval;
		req->rq_retries = 0;
		xprt_reset_majortimeo(req);
		/* Reset the RTT counters == "slow start" */
		spin_lock_bh(&xprt->transport_lock);
		rpc_init_rtt(req->rq_task->tk_client->cl_rtt, to->to_initval);
		spin_unlock_bh(&xprt->transport_lock);
		status = -ETIMEDOUT;
	}

	if (req->rq_timeout == 0) {
		printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
		req->rq_timeout = 5 * HZ;
	}
	return status;
}

static void xprt_autoclose(struct work_struct *work)
{
	struct rpc_xprt *xprt =
		container_of(work, struct rpc_xprt, task_cleanup);

	xprt->ops->close(xprt);
	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
	xprt_release_write(xprt, NULL);
}

/**
 * xprt_disconnect_done - mark a transport as disconnected
 * @xprt: transport to flag for disconnect
 *
 */
void xprt_disconnect_done(struct rpc_xprt *xprt)
{
	dprintk("RPC:       disconnected transport %p\n", xprt);
	spin_lock_bh(&xprt->transport_lock);
	xprt_clear_connected(xprt);
	xprt_wake_pending_tasks(xprt, -EAGAIN);
	spin_unlock_bh(&xprt->transport_lock);
}
EXPORT_SYMBOL_GPL(xprt_disconnect_done);

/**
 * xprt_force_disconnect - force a transport to disconnect
 * @xprt: transport to disconnect
 *
 */
void xprt_force_disconnect(struct rpc_xprt *xprt)
{
	/* Don't race with the test_bit() in xprt_clear_locked() */
	spin_lock_bh(&xprt->transport_lock);
	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
	/* Try to schedule an autoclose RPC call */
	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
		queue_work(rpciod_workqueue, &xprt->task_cleanup);
	xprt_wake_pending_tasks(xprt, -EAGAIN);
	spin_unlock_bh(&xprt->transport_lock);
}

/**
 * xprt_conditional_disconnect - force a transport to disconnect
 * @xprt: transport to disconnect
 * @cookie: 'connection cookie'
 *
 * This attempts to break the connection if and only if 'cookie' matches
 * the current transport 'connection cookie'. It ensures that we don't
 * try to break the connection more than once when we need to retransmit
 * a batch of RPC requests.
 *
 */
void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
{
	/* Don't race with the test_bit() in xprt_clear_locked() */
	spin_lock_bh(&xprt->transport_lock);
	if (cookie != xprt->connect_cookie)
		goto out;
	if (test_bit(XPRT_CLOSING, &xprt->state) || !xprt_connected(xprt))
		goto out;
	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
	/* Try to schedule an autoclose RPC call */
	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
		queue_work(rpciod_workqueue, &xprt->task_cleanup);
	xprt_wake_pending_tasks(xprt, -EAGAIN);
out:
	spin_unlock_bh(&xprt->transport_lock);
}

static void
xprt_init_autodisconnect(unsigned long data)
{
	struct rpc_xprt *xprt = (struct rpc_xprt *)data;

	spin_lock(&xprt->transport_lock);
	if (!list_empty(&xprt->recv) || xprt->shutdown)
		goto out_abort;
	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
		goto out_abort;
	spin_unlock(&xprt->transport_lock);
	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
	queue_work(rpciod_workqueue, &xprt->task_cleanup);
	return;
out_abort:
	spin_unlock(&xprt->transport_lock);
}

/**
 * xprt_connect - schedule a transport connect operation
 * @task: RPC task that is requesting the connect
 *
 */
void xprt_connect(struct rpc_task *task)
{
	struct rpc_xprt	*xprt = task->tk_xprt;

	dprintk("RPC: %5u xprt_connect xprt %p %s connected\n", task->tk_pid,
			xprt, (xprt_connected(xprt) ? "is" : "is not"));

	if (!xprt_bound(xprt)) {
		task->tk_status = -EAGAIN;
		return;
	}
	if (!xprt_lock_write(xprt, task))
		return;

	if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state))
		xprt->ops->close(xprt);

	if (xprt_connected(xprt))
		xprt_release_write(xprt, task);
	else {
		if (task->tk_rqstp)
			task->tk_rqstp->rq_bytes_sent = 0;

		task->tk_timeout = task->tk_rqstp->rq_timeout;
		rpc_sleep_on(&xprt->pending, task, xprt_connect_status);

		if (test_bit(XPRT_CLOSING, &xprt->state))
			return;
		if (xprt_test_and_set_connecting(xprt))
			return;
		xprt->stat.connect_start = jiffies;
		xprt->ops->connect(task);
	}
}

static void xprt_connect_status(struct rpc_task *task)
{
	struct rpc_xprt	*xprt = task->tk_xprt;

	if (task->tk_status == 0) {
		xprt->stat.connect_count++;
		xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start;
		dprintk("RPC: %5u xprt_connect_status: connection established\n",
				task->tk_pid);
		return;
	}

	switch (task->tk_status) {
	case -EAGAIN:
		dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid);
		break;
	case -ETIMEDOUT:
		dprintk("RPC: %5u xprt_connect_status: connect attempt timed "
				"out\n", task->tk_pid);
		break;
	default:
		dprintk("RPC: %5u xprt_connect_status: error %d connecting to "
				"server %s\n", task->tk_pid, -task->tk_status,
				task->tk_client->cl_server);
		xprt_release_write(xprt, task);
		task->tk_status = -EIO;
	}
}

/**
 * xprt_lookup_rqst - find an RPC request corresponding to an XID
 * @xprt: transport on which the original request was transmitted
 * @xid: RPC XID of incoming reply
 *
 */
struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
{
	struct rpc_rqst *entry;

	list_for_each_entry(entry, &xprt->recv, rq_list)
		if (entry->rq_xid == xid)
			return entry;

	dprintk("RPC:       xprt_lookup_rqst did not find xid %08x\n",
			ntohl(xid));
	xprt->stat.bad_xids++;
	return NULL;
}
EXPORT_SYMBOL_GPL(xprt_lookup_rqst);

static void xprt_update_rtt(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_rtt *rtt = task->tk_client->cl_rtt;
	unsigned timer = task->tk_msg.rpc_proc->p_timer;
	long m = usecs_to_jiffies(ktime_to_us(req->rq_rtt));

	if (timer) {
		if (req->rq_ntrans == 1)
			rpc_update_rtt(rtt, timer, m);
		rpc_set_timeo(rtt, timer, req->rq_ntrans - 1);
	}
}

/**
 * xprt_complete_rqst - called when reply processing is complete
 * @task: RPC request that recently completed
 * @copied: actual number of bytes received from the transport
 *
 * Caller holds transport lock.
 */
void xprt_complete_rqst(struct rpc_task *task, int copied)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;

	dprintk("RPC: %5u xid %08x complete (%d bytes received)\n",
			task->tk_pid, ntohl(req->rq_xid), copied);

	xprt->stat.recvs++;
	req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime);
	if (xprt->ops->timer != NULL)
		xprt_update_rtt(task);

	list_del_init(&req->rq_list);
	req->rq_private_buf.len = copied;
	/* Ensure all writes are done before we update */
	/* req->rq_reply_bytes_recvd */
	smp_wmb();
	req->rq_reply_bytes_recvd = copied;
	rpc_wake_up_queued_task(&xprt->pending, task);
}
EXPORT_SYMBOL_GPL(xprt_complete_rqst);

static void xprt_timer(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;

	if (task->tk_status != -ETIMEDOUT)
		return;
	dprintk("RPC: %5u xprt_timer\n", task->tk_pid);

	spin_lock_bh(&xprt->transport_lock);
	if (!req->rq_reply_bytes_recvd) {
		if (xprt->ops->timer)
			xprt->ops->timer(task);
	} else
		task->tk_status = 0;
	spin_unlock_bh(&xprt->transport_lock);
}

static inline int xprt_has_timer(struct rpc_xprt *xprt)
{
	return xprt->idle_timeout != 0;
}

/**
 * xprt_prepare_transmit - reserve the transport before sending a request
 * @task: RPC task about to send a request
 *
 */
int xprt_prepare_transmit(struct rpc_task *task)
{
	struct rpc_rqst	*req = task->tk_rqstp;
	struct rpc_xprt	*xprt = req->rq_xprt;
	int err = 0;

	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);

	spin_lock_bh(&xprt->transport_lock);
	if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) {
		err = req->rq_reply_bytes_recvd;
		goto out_unlock;
	}
	if (!xprt->ops->reserve_xprt(xprt, task))
		err = -EAGAIN;
out_unlock:
	spin_unlock_bh(&xprt->transport_lock);
	return err;
}

void xprt_end_transmit(struct rpc_task *task)
{
	xprt_release_write(task->tk_rqstp->rq_xprt, task);
}

/**
 * xprt_transmit - send an RPC request on a transport
 * @task: controlling RPC task
 *
 * We have to copy the iovec because sendmsg fiddles with its contents.
 */
void xprt_transmit(struct rpc_task *task)
{
	struct rpc_rqst	*req = task->tk_rqstp;
	struct rpc_xprt	*xprt = req->rq_xprt;
	int status;

	dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen);

	if (!req->rq_reply_bytes_recvd) {
		if (list_empty(&req->rq_list) && rpc_reply_expected(task)) {
			/*
			 * Add to the list only if we're expecting a reply
			 */
			spin_lock_bh(&xprt->transport_lock);
			/* Update the softirq receive buffer */
			memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
					sizeof(req->rq_private_buf));
			/* Add request to the receive list */
			list_add_tail(&req->rq_list, &xprt->recv);
			spin_unlock_bh(&xprt->transport_lock);
			xprt_reset_majortimeo(req);
			/* Turn off autodisconnect */
			del_singleshot_timer_sync(&xprt->timer);
		}
	} else if (!req->rq_bytes_sent)
		return;

	req->rq_connect_cookie = xprt->connect_cookie;
	req->rq_xtime = ktime_get();
	status = xprt->ops->send_request(task);
	if (status != 0) {
		task->tk_status = status;
		return;
	}

	dprintk("RPC: %5u xmit complete\n", task->tk_pid);
	task->tk_flags |= RPC_TASK_SENT;
	spin_lock_bh(&xprt->transport_lock);

	xprt->ops->set_retrans_timeout(task);

	xprt->stat.sends++;
	xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs;
	xprt->stat.bklog_u += xprt->backlog.qlen;

	/* Don't race with disconnect */
	if (!xprt_connected(xprt))
		task->tk_status = -ENOTCONN;
	else if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) {
		/*
		 * Sleep on the pending queue since
		 * we're expecting a reply.
		 */
		rpc_sleep_on(&xprt->pending, task, xprt_timer);
	}
	spin_unlock_bh(&xprt->transport_lock);
}

static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt, gfp_t gfp_flags)
{
	struct rpc_rqst *req = ERR_PTR(-EAGAIN);

	if (!atomic_add_unless(&xprt->num_reqs, 1, xprt->max_reqs))
		goto out;
	req = kzalloc(sizeof(struct rpc_rqst), gfp_flags);
	if (req != NULL)
		goto out;
	atomic_dec(&xprt->num_reqs);
	req = ERR_PTR(-ENOMEM);
out:
	return req;
}

static bool xprt_dynamic_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
	if (atomic_add_unless(&xprt->num_reqs, -1, xprt->min_reqs)) {
		kfree(req);
		return true;
	}
	return false;
}

static void xprt_alloc_slot(struct rpc_task *task)
{
	struct rpc_xprt	*xprt = task->tk_xprt;
	struct rpc_rqst *req;

	if (!list_empty(&xprt->free)) {
		req = list_entry(xprt->free.next, struct rpc_rqst, rq_list);
		list_del(&req->rq_list);
		goto out_init_req;
	}
	req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT);
	if (!IS_ERR(req))
		goto out_init_req;
	switch (PTR_ERR(req)) {
	case -ENOMEM:
		rpc_delay(task, HZ >> 2);
		dprintk("RPC:       dynamic allocation of request slot "
				"failed! Retrying\n");
		break;
	case -EAGAIN:
		rpc_sleep_on(&xprt->backlog, task, NULL);
		dprintk("RPC:       waiting for request slot\n");
	}
	task->tk_status = -EAGAIN;
	return;
out_init_req:
	task->tk_status = 0;
	task->tk_rqstp = req;
	xprt_request_init(task, xprt);
}

static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
	spin_lock(&xprt->reserve_lock);
	if (!xprt_dynamic_free_slot(xprt, req)) {
		memset(req, 0, sizeof(*req));	/* mark unused */
		list_add(&req->rq_list, &xprt->free);
	}
	rpc_wake_up_next(&xprt->backlog);
	spin_unlock(&xprt->reserve_lock);
}

static void xprt_free_all_slots(struct rpc_xprt *xprt)
{
	struct rpc_rqst *req;
	while (!list_empty(&xprt->free)) {
		req = list_first_entry(&xprt->free, struct rpc_rqst, rq_list);
		list_del(&req->rq_list);
		kfree(req);
	}
}

struct rpc_xprt *xprt_alloc(struct net *net, size_t size,
		unsigned int num_prealloc,
		unsigned int max_alloc)
{
	struct rpc_xprt *xprt;
	struct rpc_rqst *req;
	int i;

	xprt = kzalloc(size, GFP_KERNEL);
	if (xprt == NULL)
		goto out;

	xprt_init(xprt, net);

	for (i = 0; i < num_prealloc; i++) {
		req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL);
		if (!req)
			break;
		list_add(&req->rq_list, &xprt->free);
	}
	if (i < num_prealloc)
		goto out_free;
	if (max_alloc > num_prealloc)
		xprt->max_reqs = max_alloc;
	else
		xprt->max_reqs = num_prealloc;
	xprt->min_reqs = num_prealloc;
	atomic_set(&xprt->num_reqs, num_prealloc);

	return xprt;

out_free:
	xprt_free(xprt);
out:
	return NULL;
}
EXPORT_SYMBOL_GPL(xprt_alloc);

void xprt_free(struct rpc_xprt *xprt)
{
	put_net(xprt->xprt_net);
	xprt_free_all_slots(xprt);
	kfree(xprt);
}
EXPORT_SYMBOL_GPL(xprt_free);

/**
 * xprt_reserve - allocate an RPC request slot
 * @task: RPC task requesting a slot allocation
 *
 * If no more slots are available, place the task on the transport's
 * backlog queue.
 */
void xprt_reserve(struct rpc_task *task)
{
	struct rpc_xprt	*xprt = task->tk_xprt;

	task->tk_status = 0;
	if (task->tk_rqstp != NULL)
		return;

	/* Note: grabbing the xprt_lock_write() here is not strictly needed,
	 * but ensures that we throttle new slot allocation if the transport
	 * is congested (e.g. if reconnecting or if we're out of socket
	 * write buffer space).
	 */
	task->tk_timeout = 0;
	task->tk_status = -EAGAIN;
	if (!xprt_lock_write(xprt, task))
		return;

	spin_lock(&xprt->reserve_lock);
	xprt_alloc_slot(task);
	spin_unlock(&xprt->reserve_lock);
	xprt_release_write(xprt, task);
}

static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
{
	return (__force __be32)xprt->xid++;
}

static inline void xprt_init_xid(struct rpc_xprt *xprt)
{
	xprt->xid = net_random();
}

static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
{
	struct rpc_rqst	*req = task->tk_rqstp;

	INIT_LIST_HEAD(&req->rq_list);
	req->rq_timeout = task->tk_client->cl_timeout->to_initval;
	req->rq_task	= task;
	req->rq_xprt    = xprt;
	req->rq_buffer  = NULL;
	req->rq_xid     = xprt_alloc_xid(xprt);
	req->rq_release_snd_buf = NULL;
	xprt_reset_majortimeo(req);
	dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid,
			req, ntohl(req->rq_xid));
}

/**
 * xprt_release - release an RPC request slot
 * @task: task which is finished with the slot
 *
 */
void xprt_release(struct rpc_task *task)
{
	struct rpc_xprt	*xprt;
	struct rpc_rqst	*req;

	if (!(req = task->tk_rqstp))
		return;

	xprt = req->rq_xprt;
	rpc_count_iostats(task);
	spin_lock_bh(&xprt->transport_lock);
	xprt->ops->release_xprt(xprt, task);
	if (xprt->ops->release_request)
		xprt->ops->release_request(task);
	if (!list_empty(&req->rq_list))
		list_del(&req->rq_list);
	xprt->last_used = jiffies;
	if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
		mod_timer(&xprt->timer,
				xprt->last_used + xprt->idle_timeout);
	spin_unlock_bh(&xprt->transport_lock);
	if (req->rq_buffer)
		xprt->ops->buf_free(req->rq_buffer);
	if (req->rq_cred != NULL)
		put_rpccred(req->rq_cred);
	task->tk_rqstp = NULL;
	if (req->rq_release_snd_buf)
		req->rq_release_snd_buf(req);

	dprintk("RPC: %5u release request %p\n", task->tk_pid, req);
	if (likely(!bc_prealloc(req)))
		xprt_free_slot(xprt, req);
	else
		xprt_free_bc_request(req);
}

static void xprt_init(struct rpc_xprt *xprt, struct net *net)
{
	atomic_set(&xprt->count, 1);

	spin_lock_init(&xprt->transport_lock);
	spin_lock_init(&xprt->reserve_lock);

	INIT_LIST_HEAD(&xprt->free);
	INIT_LIST_HEAD(&xprt->recv);
#if defined(CONFIG_SUNRPC_BACKCHANNEL)
	spin_lock_init(&xprt->bc_pa_lock);
	INIT_LIST_HEAD(&xprt->bc_pa_list);
#endif /* CONFIG_SUNRPC_BACKCHANNEL */

	xprt->last_used = jiffies;
	xprt->cwnd = RPC_INITCWND;
	xprt->bind_index = 0;

	rpc_init_wait_queue(&xprt->binding, "xprt_binding");
	rpc_init_wait_queue(&xprt->pending, "xprt_pending");
	rpc_init_priority_wait_queue(&xprt->sending, "xprt_sending");
	rpc_init_priority_wait_queue(&xprt->backlog, "xprt_backlog");

	xprt_init_xid(xprt);

	xprt->xprt_net = get_net(net);
}

/**
 * xprt_create_transport - create an RPC transport
 * @args: rpc transport creation arguments
 *
 */
struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
{
	struct rpc_xprt	*xprt;
	struct xprt_class *t;

	spin_lock(&xprt_list_lock);
	list_for_each_entry(t, &xprt_list, list) {
		if (t->ident == args->ident) {
			spin_unlock(&xprt_list_lock);
			goto found;
		}
	}
	spin_unlock(&xprt_list_lock);
	printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident);
	return ERR_PTR(-EIO);

found:
	xprt = t->setup(args);
	if (IS_ERR(xprt)) {
		dprintk("RPC:       xprt_create_transport: failed, %ld\n",
				-PTR_ERR(xprt));
		goto out;
	}
	INIT_WORK(&xprt->task_cleanup, xprt_autoclose);
	if (xprt_has_timer(xprt))
		setup_timer(&xprt->timer, xprt_init_autodisconnect,
			    (unsigned long)xprt);
	else
		init_timer(&xprt->timer);
	dprintk("RPC:       created transport %p with %u slots\n", xprt,
			xprt->max_reqs);
out:
	return xprt;
}

/**
 * xprt_destroy - destroy an RPC transport, killing off all requests.
 * @xprt: transport to destroy
 *
 */
static void xprt_destroy(struct rpc_xprt *xprt)
{
	dprintk("RPC:       destroying transport %p\n", xprt);
	xprt->shutdown = 1;
	del_timer_sync(&xprt->timer);

	rpc_destroy_wait_queue(&xprt->binding);
	rpc_destroy_wait_queue(&xprt->pending);
	rpc_destroy_wait_queue(&xprt->sending);
	rpc_destroy_wait_queue(&xprt->backlog);
	cancel_work_sync(&xprt->task_cleanup);
	/*
	 * Tear down transport state and free the rpc_xprt
	 */
	xprt->ops->destroy(xprt);
}

/**
 * xprt_put - release a reference to an RPC transport.
 * @xprt: pointer to the transport
 *
 */
void xprt_put(struct rpc_xprt *xprt)
{
	if (atomic_dec_and_test(&xprt->count))
		xprt_destroy(xprt);
}

/**
 * xprt_get - return a reference to an RPC transport.
 * @xprt: pointer to the transport
 *
 */
struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
{
	if (atomic_inc_not_zero(&xprt->count))
		return xprt;
	return NULL;
}