aboutsummaryrefslogtreecommitdiff
path: root/net/9p/trans_fd.c
blob: 180163b3e8f9d58f2ea45059b005803e97e768f0 (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
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
/*
 * linux/fs/9p/trans_fd.c
 *
 * Fd transport layer.  Includes deprecated socket layer.
 *
 *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
 *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
 *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
 *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License version 2
 *  as published by the Free Software Foundation.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to:
 *  Free Software Foundation
 *  51 Franklin Street, Fifth Floor
 *  Boston, MA  02111-1301  USA
 *
 */

#include <linux/in.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/ipv6.h>
#include <linux/kthread.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/un.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/idr.h>
#include <linux/file.h>
#include <linux/parser.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include <net/9p/transport.h>

#define P9_PORT 564
#define MAX_SOCK_BUF (64*1024)
#define ERREQFLUSH	1
#define MAXPOLLWADDR	2

/**
 * struct p9_fd_opts - per-transport options
 * @rfd: file descriptor for reading (trans=fd)
 * @wfd: file descriptor for writing (trans=fd)
 * @port: port to connect to (trans=tcp)
 *
 */

struct p9_fd_opts {
	int rfd;
	int wfd;
	u16 port;
};

/**
 * struct p9_trans_fd - transport state
 * @rd: reference to file to read from
 * @wr: reference of file to write to
 * @conn: connection state reference
 *
 */

struct p9_trans_fd {
	struct file *rd;
	struct file *wr;
	struct p9_conn *conn;
};

/*
  * Option Parsing (code inspired by NFS code)
  *  - a little lazy - parse all fd-transport options
  */

enum {
	/* Options that take integer arguments */
	Opt_port, Opt_rfdno, Opt_wfdno, Opt_err,
};

static const match_table_t tokens = {
	{Opt_port, "port=%u"},
	{Opt_rfdno, "rfdno=%u"},
	{Opt_wfdno, "wfdno=%u"},
	{Opt_err, NULL},
};

enum {
	Rworksched = 1,		/* read work scheduled or running */
	Rpending = 2,		/* can read */
	Wworksched = 4,		/* write work scheduled or running */
	Wpending = 8,		/* can write */
};

enum {
	None,
	Flushing,
	Flushed,
};

/**
 * struct p9_req - fd mux encoding of an rpc transaction
 * @lock: protects req_list
 * @tag: numeric tag for rpc transaction
 * @tcall: request &p9_fcall structure
 * @rcall: response &p9_fcall structure
 * @err: error state
 * @flush: flag to indicate RPC has been flushed
 * @req_list: list link for higher level objects to chain requests
 * @m: connection this request was issued on
 * @wqueue: wait queue that client is blocked on for this rpc
 *
 */

struct p9_req {
	spinlock_t lock;
	int tag;
	struct p9_fcall *tcall;
	struct p9_fcall *rcall;
	int err;
	int flush;
	struct list_head req_list;
	struct p9_conn *m;
	wait_queue_head_t wqueue;
};

struct p9_poll_wait {
	struct p9_conn *conn;
	wait_queue_t wait;
	wait_queue_head_t *wait_addr;
};

/**
 * struct p9_conn - fd mux connection state information
 * @lock: protects mux_list (?)
 * @mux_list: list link for mux to manage multiple connections (?)
 * @client: reference to client instance for this connection
 * @tagpool: id accounting for transactions
 * @err: error state
 * @req_list: accounting for requests which have been sent
 * @unsent_req_list: accounting for requests that haven't been sent
 * @rcall: current response &p9_fcall structure
 * @rpos: read position in current frame
 * @rbuf: current read buffer
 * @wpos: write position for current frame
 * @wsize: amount of data to write for current frame
 * @wbuf: current write buffer
 * @poll_wait: array of wait_q's for various worker threads
 * @poll_waddr: ????
 * @pt: poll state
 * @rq: current read work
 * @wq: current write work
 * @wsched: ????
 *
 */

struct p9_conn {
	spinlock_t lock; /* protect lock structure */
	struct list_head mux_list;
	struct p9_client *client;
	struct p9_idpool *tagpool;
	int err;
	struct list_head req_list;
	struct list_head unsent_req_list;
	struct p9_fcall *rcall;
	int rpos;
	char *rbuf;
	int wpos;
	int wsize;
	char *wbuf;
	struct list_head poll_pending_link;
	struct p9_poll_wait poll_wait[MAXPOLLWADDR];
	poll_table pt;
	struct work_struct rq;
	struct work_struct wq;
	unsigned long wsched;
};

static DEFINE_SPINLOCK(p9_poll_lock);
static LIST_HEAD(p9_poll_pending_list);
static struct workqueue_struct *p9_mux_wq;
static struct task_struct *p9_poll_task;

static u16 p9_mux_get_tag(struct p9_conn *m)
{
	int tag;

	tag = p9_idpool_get(m->tagpool);
	if (tag < 0)
		return P9_NOTAG;
	else
		return (u16) tag;
}

static void p9_mux_put_tag(struct p9_conn *m, u16 tag)
{
	if (tag != P9_NOTAG && p9_idpool_check(tag, m->tagpool))
		p9_idpool_put(tag, m->tagpool);
}

static void p9_mux_poll_stop(struct p9_conn *m)
{
	unsigned long flags;
	int i;

	for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
		struct p9_poll_wait *pwait = &m->poll_wait[i];

		if (pwait->wait_addr) {
			remove_wait_queue(pwait->wait_addr, &pwait->wait);
			pwait->wait_addr = NULL;
		}
	}

	spin_lock_irqsave(&p9_poll_lock, flags);
	list_del_init(&m->poll_pending_link);
	spin_unlock_irqrestore(&p9_poll_lock, flags);
}

static void p9_mux_free_request(struct p9_conn *m, struct p9_req *req)
{
	p9_mux_put_tag(m, req->tag);
	kfree(req);
}

static void p9_conn_rpc_cb(struct p9_req *req);

static void p9_mux_flush_cb(struct p9_req *freq)
{
	int tag;
	struct p9_conn *m = freq->m;
	struct p9_req *req, *rreq, *rptr;

	P9_DPRINTK(P9_DEBUG_MUX, "mux %p tc %p rc %p err %d oldtag %d\n", m,
		freq->tcall, freq->rcall, freq->err,
		freq->tcall->params.tflush.oldtag);

	spin_lock(&m->lock);
	tag = freq->tcall->params.tflush.oldtag;
	req = NULL;
	list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
		if (rreq->tag == tag) {
			req = rreq;
			list_del(&req->req_list);
			break;
		}
	}
	spin_unlock(&m->lock);

	if (req) {
		spin_lock(&req->lock);
		req->flush = Flushed;
		spin_unlock(&req->lock);

		p9_conn_rpc_cb(req);
	}

	kfree(freq->tcall);
	kfree(freq->rcall);
	p9_mux_free_request(m, freq);
}

static void p9_conn_rpc_cb(struct p9_req *req)
{
	P9_DPRINTK(P9_DEBUG_MUX, "req %p\n", req);

	if (req->tcall->id == P9_TFLUSH) { /* flush callback */
		P9_DPRINTK(P9_DEBUG_MUX, "flush req %p\n", req);
		p9_mux_flush_cb(req);
	} else {			/* normal wakeup path */
		P9_DPRINTK(P9_DEBUG_MUX, "normal req %p\n", req);
		if (req->flush != None && !req->err)
			req->err = -ERESTARTSYS;

		wake_up(&req->wqueue);
	}
}

/**
 * p9_conn_cancel - cancel all pending requests with error
 * @m: mux data
 * @err: error code
 *
 */

void p9_conn_cancel(struct p9_conn *m, int err)
{
	struct p9_req *req, *rtmp;
	LIST_HEAD(cancel_list);

	P9_DPRINTK(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);
	m->err = err;
	spin_lock(&m->lock);
	list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
		list_move(&req->req_list, &cancel_list);
	}
	list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
		list_move(&req->req_list, &cancel_list);
	}
	spin_unlock(&m->lock);

	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
		list_del(&req->req_list);
		if (!req->err)
			req->err = err;

		p9_conn_rpc_cb(req);
	}
}

static void process_request(struct p9_conn *m, struct p9_req *req)
{
	int ecode;
	struct p9_str *ename;

	if (!req->err && req->rcall->id == P9_RERROR) {
		ecode = req->rcall->params.rerror.errno;
		ename = &req->rcall->params.rerror.error;

		P9_DPRINTK(P9_DEBUG_MUX, "Rerror %.*s\n", ename->len,
								ename->str);

		if (m->client->dotu)
			req->err = -ecode;

		if (!req->err) {
			req->err = p9_errstr2errno(ename->str, ename->len);

			/* string match failed */
			if (!req->err) {
				PRINT_FCALL_ERROR("unknown error", req->rcall);
				req->err = -ESERVERFAULT;
			}
		}
	} else if (req->tcall && req->rcall->id != req->tcall->id + 1) {
		P9_DPRINTK(P9_DEBUG_ERROR,
				"fcall mismatch: expected %d, got %d\n",
				req->tcall->id + 1, req->rcall->id);
		if (!req->err)
			req->err = -EIO;
	}
}

static unsigned int
p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt)
{
	int ret, n;
	struct p9_trans_fd *ts = NULL;

	if (client && client->status == Connected)
		ts = client->trans;

	if (!ts)
		return -EREMOTEIO;

	if (!ts->rd->f_op || !ts->rd->f_op->poll)
		return -EIO;

	if (!ts->wr->f_op || !ts->wr->f_op->poll)
		return -EIO;

	ret = ts->rd->f_op->poll(ts->rd, pt);
	if (ret < 0)
		return ret;

	if (ts->rd != ts->wr) {
		n = ts->wr->f_op->poll(ts->wr, pt);
		if (n < 0)
			return n;
		ret = (ret & ~POLLOUT) | (n & ~POLLIN);
	}

	return ret;
}

/**
 * p9_fd_read- read from a fd
 * @client: client instance
 * @v: buffer to receive data into
 * @len: size of receive buffer
 *
 */

static int p9_fd_read(struct p9_client *client, void *v, int len)
{
	int ret;
	struct p9_trans_fd *ts = NULL;

	if (client && client->status != Disconnected)
		ts = client->trans;

	if (!ts)
		return -EREMOTEIO;

	if (!(ts->rd->f_flags & O_NONBLOCK))
		P9_DPRINTK(P9_DEBUG_ERROR, "blocking read ...\n");

	ret = kernel_read(ts->rd, ts->rd->f_pos, v, len);
	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
		client->status = Disconnected;
	return ret;
}

/**
 * p9_read_work - called when there is some data to be read from a transport
 * @work: container of work to be done
 *
 */

static void p9_read_work(struct work_struct *work)
{
	int n, err;
	struct p9_conn *m;
	struct p9_req *req, *rptr, *rreq;
	struct p9_fcall *rcall;
	char *rbuf;

	m = container_of(work, struct p9_conn, rq);

	if (m->err < 0)
		return;

	rcall = NULL;
	P9_DPRINTK(P9_DEBUG_MUX, "start mux %p pos %d\n", m, m->rpos);

	if (!m->rcall) {
		m->rcall =
		    kmalloc(sizeof(struct p9_fcall) + m->client->msize,
								GFP_KERNEL);
		if (!m->rcall) {
			err = -ENOMEM;
			goto error;
		}

		m->rbuf = (char *)m->rcall + sizeof(struct p9_fcall);
		m->rpos = 0;
	}

	clear_bit(Rpending, &m->wsched);
	err = p9_fd_read(m->client, m->rbuf + m->rpos,
						m->client->msize - m->rpos);
	P9_DPRINTK(P9_DEBUG_MUX, "mux %p got %d bytes\n", m, err);
	if (err == -EAGAIN) {
		clear_bit(Rworksched, &m->wsched);
		return;
	}

	if (err <= 0)
		goto error;

	m->rpos += err;
	while (m->rpos > 4) {
		n = le32_to_cpu(*(__le32 *) m->rbuf);
		if (n >= m->client->msize) {
			P9_DPRINTK(P9_DEBUG_ERROR,
				"requested packet size too big: %d\n", n);
			err = -EIO;
			goto error;
		}

		if (m->rpos < n)
			break;

		err =
		    p9_deserialize_fcall(m->rbuf, n, m->rcall, m->client->dotu);
		if (err < 0)
			goto error;

#ifdef CONFIG_NET_9P_DEBUG
		if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
			char buf[150];

			p9_printfcall(buf, sizeof(buf), m->rcall,
				m->client->dotu);
			printk(KERN_NOTICE ">>> %p %s\n", m, buf);
		}
#endif

		rcall = m->rcall;
		rbuf = m->rbuf;
		if (m->rpos > n) {
			m->rcall = kmalloc(sizeof(struct p9_fcall) +
						m->client->msize, GFP_KERNEL);
			if (!m->rcall) {
				err = -ENOMEM;
				goto error;
			}

			m->rbuf = (char *)m->rcall + sizeof(struct p9_fcall);
			memmove(m->rbuf, rbuf + n, m->rpos - n);
			m->rpos -= n;
		} else {
			m->rcall = NULL;
			m->rbuf = NULL;
			m->rpos = 0;
		}

		P9_DPRINTK(P9_DEBUG_MUX, "mux %p fcall id %d tag %d\n", m,
							rcall->id, rcall->tag);

		req = NULL;
		spin_lock(&m->lock);
		list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
			if (rreq->tag == rcall->tag) {
				req = rreq;
				if (req->flush != Flushing)
					list_del(&req->req_list);
				break;
			}
		}
		spin_unlock(&m->lock);

		if (req) {
			req->rcall = rcall;
			process_request(m, req);

			if (req->flush != Flushing)
				p9_conn_rpc_cb(req);
		} else {
			if (err >= 0 && rcall->id != P9_RFLUSH)
				P9_DPRINTK(P9_DEBUG_ERROR,
				  "unexpected response mux %p id %d tag %d\n",
				  m, rcall->id, rcall->tag);
			kfree(rcall);
		}
	}

	if (!list_empty(&m->req_list)) {
		if (test_and_clear_bit(Rpending, &m->wsched))
			n = POLLIN;
		else
			n = p9_fd_poll(m->client, NULL);

		if (n & POLLIN) {
			P9_DPRINTK(P9_DEBUG_MUX, "schedule read work %p\n", m);
			queue_work(p9_mux_wq, &m->rq);
		} else
			clear_bit(Rworksched, &m->wsched);
	} else
		clear_bit(Rworksched, &m->wsched);

	return;

error:
	p9_conn_cancel(m, err);
	clear_bit(Rworksched, &m->wsched);
}

/**
 * p9_fd_write - write to a socket
 * @client: client instance
 * @v: buffer to send data from
 * @len: size of send buffer
 *
 */

static int p9_fd_write(struct p9_client *client, void *v, int len)
{
	int ret;
	mm_segment_t oldfs;
	struct p9_trans_fd *ts = NULL;

	if (client && client->status != Disconnected)
		ts = client->trans;

	if (!ts)
		return -EREMOTEIO;

	if (!(ts->wr->f_flags & O_NONBLOCK))
		P9_DPRINTK(P9_DEBUG_ERROR, "blocking write ...\n");

	oldfs = get_fs();
	set_fs(get_ds());
	/* The cast to a user pointer is valid due to the set_fs() */
	ret = vfs_write(ts->wr, (void __user *)v, len, &ts->wr->f_pos);
	set_fs(oldfs);

	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
		client->status = Disconnected;
	return ret;
}

/**
 * p9_write_work - called when a transport can send some data
 * @work: container for work to be done
 *
 */

static void p9_write_work(struct work_struct *work)
{
	int n, err;
	struct p9_conn *m;
	struct p9_req *req;

	m = container_of(work, struct p9_conn, wq);

	if (m->err < 0) {
		clear_bit(Wworksched, &m->wsched);
		return;
	}

	if (!m->wsize) {
		if (list_empty(&m->unsent_req_list)) {
			clear_bit(Wworksched, &m->wsched);
			return;
		}

		spin_lock(&m->lock);
again:
		req = list_entry(m->unsent_req_list.next, struct p9_req,
			       req_list);
		list_move_tail(&req->req_list, &m->req_list);
		if (req->err == ERREQFLUSH)
			goto again;

		m->wbuf = req->tcall->sdata;
		m->wsize = req->tcall->size;
		m->wpos = 0;
		spin_unlock(&m->lock);
	}

	P9_DPRINTK(P9_DEBUG_MUX, "mux %p pos %d size %d\n", m, m->wpos,
								m->wsize);
	clear_bit(Wpending, &m->wsched);
	err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
	P9_DPRINTK(P9_DEBUG_MUX, "mux %p sent %d bytes\n", m, err);
	if (err == -EAGAIN) {
		clear_bit(Wworksched, &m->wsched);
		return;
	}

	if (err < 0)
		goto error;
	else if (err == 0) {
		err = -EREMOTEIO;
		goto error;
	}

	m->wpos += err;
	if (m->wpos == m->wsize)
		m->wpos = m->wsize = 0;

	if (m->wsize == 0 && !list_empty(&m->unsent_req_list)) {
		if (test_and_clear_bit(Wpending, &m->wsched))
			n = POLLOUT;
		else
			n = p9_fd_poll(m->client, NULL);

		if (n & POLLOUT) {
			P9_DPRINTK(P9_DEBUG_MUX, "schedule write work %p\n", m);
			queue_work(p9_mux_wq, &m->wq);
		} else
			clear_bit(Wworksched, &m->wsched);
	} else
		clear_bit(Wworksched, &m->wsched);

	return;

error:
	p9_conn_cancel(m, err);
	clear_bit(Wworksched, &m->wsched);
}

static int p9_pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	struct p9_poll_wait *pwait =
		container_of(wait, struct p9_poll_wait, wait);
	struct p9_conn *m = pwait->conn;
	unsigned long flags;
	DECLARE_WAITQUEUE(dummy_wait, p9_poll_task);

	spin_lock_irqsave(&p9_poll_lock, flags);
	if (list_empty(&m->poll_pending_link))
		list_add_tail(&m->poll_pending_link, &p9_poll_pending_list);
	spin_unlock_irqrestore(&p9_poll_lock, flags);

	/* perform the default wake up operation */
	return default_wake_function(&dummy_wait, mode, sync, key);
}

/**
 * p9_pollwait - add poll task to the wait queue
 * @filp: file pointer being polled
 * @wait_address: wait_q to block on
 * @p: poll state
 *
 * called by files poll operation to add v9fs-poll task to files wait queue
 */

static void
p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p)
{
	struct p9_conn *m = container_of(p, struct p9_conn, pt);
	struct p9_poll_wait *pwait = NULL;
	int i;

	for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
		if (m->poll_wait[i].wait_addr == NULL) {
			pwait = &m->poll_wait[i];
			break;
		}
	}

	if (!pwait) {
		P9_DPRINTK(P9_DEBUG_ERROR, "not enough wait_address slots\n");
		return;
	}

	if (!wait_address) {
		P9_DPRINTK(P9_DEBUG_ERROR, "no wait_address\n");
		pwait->wait_addr = ERR_PTR(-EIO);
		return;
	}

	pwait->conn = m;
	pwait->wait_addr = wait_address;
	init_waitqueue_func_entry(&pwait->wait, p9_pollwake);
	add_wait_queue(wait_address, &pwait->wait);
}

/**
 * p9_conn_create - allocate and initialize the per-session mux data
 * @client: client instance
 *
 * Note: Creates the polling task if this is the first session.
 */

static struct p9_conn *p9_conn_create(struct p9_client *client)
{
	int i, n;
	struct p9_conn *m;

	P9_DPRINTK(P9_DEBUG_MUX, "client %p msize %d\n", client, client->msize);
	m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL);
	if (!m)
		return ERR_PTR(-ENOMEM);

	spin_lock_init(&m->lock);
	INIT_LIST_HEAD(&m->mux_list);
	m->client = client;
	m->tagpool = p9_idpool_create();
	if (IS_ERR(m->tagpool)) {
		kfree(m);
		return ERR_PTR(-ENOMEM);
	}

	INIT_LIST_HEAD(&m->req_list);
	INIT_LIST_HEAD(&m->unsent_req_list);
	INIT_WORK(&m->rq, p9_read_work);
	INIT_WORK(&m->wq, p9_write_work);
	INIT_LIST_HEAD(&m->poll_pending_link);
	init_poll_funcptr(&m->pt, p9_pollwait);

	n = p9_fd_poll(client, &m->pt);
	if (n & POLLIN) {
		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can read\n", m);
		set_bit(Rpending, &m->wsched);
	}

	if (n & POLLOUT) {
		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can write\n", m);
		set_bit(Wpending, &m->wsched);
	}

	for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
		if (IS_ERR(m->poll_wait[i].wait_addr)) {
			p9_mux_poll_stop(m);
			kfree(m);
			/* return the error code */
			return (void *)m->poll_wait[i].wait_addr;
		}
	}

	return m;
}

/**
 * p9_poll_mux - polls a mux and schedules read or write works if necessary
 * @m: connection to poll
 *
 */

static void p9_poll_mux(struct p9_conn *m)
{
	int n;

	if (m->err < 0)
		return;

	n = p9_fd_poll(m->client, NULL);
	if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
		P9_DPRINTK(P9_DEBUG_MUX, "error mux %p err %d\n", m, n);
		if (n >= 0)
			n = -ECONNRESET;
		p9_conn_cancel(m, n);
	}

	if (n & POLLIN) {
		set_bit(Rpending, &m->wsched);
		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can read\n", m);
		if (!test_and_set_bit(Rworksched, &m->wsched)) {
			P9_DPRINTK(P9_DEBUG_MUX, "schedule read work %p\n", m);
			queue_work(p9_mux_wq, &m->rq);
		}
	}

	if (n & POLLOUT) {
		set_bit(Wpending, &m->wsched);
		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can write\n", m);
		if ((m->wsize || !list_empty(&m->unsent_req_list))
		    && !test_and_set_bit(Wworksched, &m->wsched)) {
			P9_DPRINTK(P9_DEBUG_MUX, "schedule write work %p\n", m);
			queue_work(p9_mux_wq, &m->wq);
		}
	}
}

/**
 * p9_send_request - send 9P request
 * The function can sleep until the request is scheduled for sending.
 * The function can be interrupted. Return from the function is not
 * a guarantee that the request is sent successfully. Can return errors
 * that can be retrieved by PTR_ERR macros.
 *
 * @m: mux data
 * @tc: request to be sent
 *
 */

static struct p9_req *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
{
	int n;
	struct p9_req *req;

	P9_DPRINTK(P9_DEBUG_MUX, "mux %p task %p tcall %p id %d\n", m, current,
		tc, tc->id);
	if (m->err < 0)
		return ERR_PTR(m->err);

	req = kmalloc(sizeof(struct p9_req), GFP_KERNEL);
	if (!req)
		return ERR_PTR(-ENOMEM);

	if (tc->id == P9_TVERSION)
		n = P9_NOTAG;
	else
		n = p9_mux_get_tag(m);

	if (n < 0) {
		kfree(req);
		return ERR_PTR(-ENOMEM);
	}

	p9_set_tag(tc, n);

#ifdef CONFIG_NET_9P_DEBUG
	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
		char buf[150];

		p9_printfcall(buf, sizeof(buf), tc, m->client->dotu);
		printk(KERN_NOTICE "<<< %p %s\n", m, buf);
	}
#endif

	spin_lock_init(&req->lock);
	req->m = m;
	init_waitqueue_head(&req->wqueue);
	req->tag = n;
	req->tcall = tc;
	req->rcall = NULL;
	req->err = 0;
	req->flush = None;

	spin_lock(&m->lock);
	list_add_tail(&req->req_list, &m->unsent_req_list);
	spin_unlock(&m->lock);

	if (test_and_clear_bit(Wpending, &m->wsched))
		n = POLLOUT;
	else
		n = p9_fd_poll(m->client, NULL);

	if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
		queue_work(p9_mux_wq, &m->wq);

	return req;
}

static int
p9_mux_flush_request(struct p9_conn *m, struct p9_req *req)
{
	struct p9_fcall *fc;
	struct p9_req *rreq, *rptr;

	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p tag %d\n", m, req, req->tag);

	/* if a response was received for a request, do nothing */
	spin_lock(&req->lock);
	if (req->rcall || req->err) {
		spin_unlock(&req->lock);
		P9_DPRINTK(P9_DEBUG_MUX,
			"mux %p req %p response already received\n", m, req);
		return 0;
	}

	req->flush = Flushing;
	spin_unlock(&req->lock);

	spin_lock(&m->lock);
	/* if the request is not sent yet, just remove it from the list */
	list_for_each_entry_safe(rreq, rptr, &m->unsent_req_list, req_list) {
		if (rreq->tag == req->tag) {
			P9_DPRINTK(P9_DEBUG_MUX,
			   "mux %p req %p request is not sent yet\n", m, req);
			list_del(&rreq->req_list);
			req->flush = Flushed;
			spin_unlock(&m->lock);
			p9_conn_rpc_cb(req);
			return 0;
		}
	}
	spin_unlock(&m->lock);

	clear_thread_flag(TIF_SIGPENDING);
	fc = p9_create_tflush(req->tag);
	p9_send_request(m, fc);
	return 1;
}

/**
 * p9_fd_rpc- sends 9P request and waits until a response is available.
 *	The function can be interrupted.
 * @client: client instance
 * @tc: request to be sent
 * @rc: pointer where a pointer to the response is stored
 *
 */

int
p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
{
	struct p9_trans_fd *p = client->trans;
	struct p9_conn *m = p->conn;
	int err, sigpending;
	unsigned long flags;
	struct p9_req *req;

	if (rc)
		*rc = NULL;

	sigpending = 0;
	if (signal_pending(current)) {
		sigpending = 1;
		clear_thread_flag(TIF_SIGPENDING);
	}

	req = p9_send_request(m, tc);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		P9_DPRINTK(P9_DEBUG_MUX, "error %d\n", err);
		return err;
	}

	err = wait_event_interruptible(req->wqueue, req->rcall != NULL ||
								req->err < 0);
	if (req->err < 0)
		err = req->err;

	if (err == -ERESTARTSYS && client->status == Connected
							&& m->err == 0) {
		if (p9_mux_flush_request(m, req)) {
			/* wait until we get response of the flush message */
			do {
				clear_thread_flag(TIF_SIGPENDING);
				err = wait_event_interruptible(req->wqueue,
					req->rcall || req->err);
			} while (!req->rcall && !req->err &&
					err == -ERESTARTSYS &&
					client->status == Connected && !m->err);

			err = -ERESTARTSYS;
		}
		sigpending = 1;
	}

	if (sigpending) {
		spin_lock_irqsave(&current->sighand->siglock, flags);
		recalc_sigpending();
		spin_unlock_irqrestore(&current->sighand->siglock, flags);
	}

	if (rc)
		*rc = req->rcall;
	else
		kfree(req->rcall);

	p9_mux_free_request(m, req);
	if (err > 0)
		err = -EIO;

	return err;
}

/**
 * parse_options - parse mount options into session structure
 * @options: options string passed from mount
 * @opts: transport-specific structure to parse options into
 *
 * Returns 0 upon success, -ERRNO upon failure
 */

static int parse_opts(char *params, struct p9_fd_opts *opts)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	char *options;
	int ret;

	opts->port = P9_PORT;
	opts->rfd = ~0;
	opts->wfd = ~0;

	if (!params)
		return 0;

	options = kstrdup(params, GFP_KERNEL);
	if (!options) {
		P9_DPRINTK(P9_DEBUG_ERROR,
				"failed to allocate copy of option string\n");
		return -ENOMEM;
	}

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		int r;
		if (!*p)
			continue;
		token = match_token(p, tokens, args);
		r = match_int(&args[0], &option);
		if (r < 0) {
			P9_DPRINTK(P9_DEBUG_ERROR,
			 "integer field, but no integer?\n");
			ret = r;
			continue;
		}
		switch (token) {
		case Opt_port:
			opts->port = option;
			break;
		case Opt_rfdno:
			opts->rfd = option;
			break;
		case Opt_wfdno:
			opts->wfd = option;
			break;
		default:
			continue;
		}
	}
	kfree(options);
	return 0;
}

static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
{
	struct p9_trans_fd *ts = kmalloc(sizeof(struct p9_trans_fd),
					   GFP_KERNEL);
	if (!ts)
		return -ENOMEM;

	ts->rd = fget(rfd);
	ts->wr = fget(wfd);
	if (!ts->rd || !ts->wr) {
		if (ts->rd)
			fput(ts->rd);
		if (ts->wr)
			fput(ts->wr);
		kfree(ts);
		return -EIO;
	}

	client->trans = ts;
	client->status = Connected;

	return 0;
}

static int p9_socket_open(struct p9_client *client, struct socket *csocket)
{
	int fd, ret;

	csocket->sk->sk_allocation = GFP_NOIO;
	fd = sock_map_fd(csocket, 0);
	if (fd < 0) {
		P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to map fd\n");
		return fd;
	}

	ret = p9_fd_open(client, fd, fd);
	if (ret < 0) {
		P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to open fd\n");
		sockfd_put(csocket);
		return ret;
	}

	((struct p9_trans_fd *)client->trans)->rd->f_flags |= O_NONBLOCK;

	return 0;
}

/**
 * p9_mux_destroy - cancels all pending requests and frees mux resources
 * @m: mux to destroy
 *
 */

static void p9_conn_destroy(struct p9_conn *m)
{
	P9_DPRINTK(P9_DEBUG_MUX, "mux %p prev %p next %p\n", m,
		m->mux_list.prev, m->mux_list.next);

	p9_mux_poll_stop(m);
	cancel_work_sync(&m->rq);
	cancel_work_sync(&m->wq);

	p9_conn_cancel(m, -ECONNRESET);

	m->client = NULL;
	p9_idpool_destroy(m->tagpool);
	kfree(m);
}

/**
 * p9_fd_close - shutdown file descriptor transport
 * @client: client instance
 *
 */

static void p9_fd_close(struct p9_client *client)
{
	struct p9_trans_fd *ts;

	if (!client)
		return;

	ts = client->trans;
	if (!ts)
		return;

	client->status = Disconnected;

	p9_conn_destroy(ts->conn);

	if (ts->rd)
		fput(ts->rd);
	if (ts->wr)
		fput(ts->wr);

	kfree(ts);
}

/*
 * stolen from NFS - maybe should be made a generic function?
 */
static inline int valid_ipaddr4(const char *buf)
{
	int rc, count, in[4];

	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
	if (rc != 4)
		return -EINVAL;
	for (count = 0; count < 4; count++) {
		if (in[count] > 255)
			return -EINVAL;
	}
	return 0;
}

static int
p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
{
	int err;
	struct socket *csocket;
	struct sockaddr_in sin_server;
	struct p9_fd_opts opts;
	struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */

	err = parse_opts(args, &opts);
	if (err < 0)
		return err;

	if (valid_ipaddr4(addr) < 0)
		return -EINVAL;

	csocket = NULL;

	sin_server.sin_family = AF_INET;
	sin_server.sin_addr.s_addr = in_aton(addr);
	sin_server.sin_port = htons(opts.port);
	sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket);

	if (!csocket) {
		P9_EPRINTK(KERN_ERR, "p9_trans_tcp: problem creating socket\n");
		err = -EIO;
		goto error;
	}

	err = csocket->ops->connect(csocket,
				    (struct sockaddr *)&sin_server,
				    sizeof(struct sockaddr_in), 0);
	if (err < 0) {
		P9_EPRINTK(KERN_ERR,
			"p9_trans_tcp: problem connecting socket to %s\n",
			addr);
		goto error;
	}

	err = p9_socket_open(client, csocket);
	if (err < 0)
		goto error;

	p = (struct p9_trans_fd *) client->trans;
	p->conn = p9_conn_create(client);
	if (IS_ERR(p->conn)) {
		err = PTR_ERR(p->conn);
		p->conn = NULL;
		goto error;
	}

	return 0;

error:
	if (csocket)
		sock_release(csocket);

	kfree(p);

	return err;
}

static int
p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
{
	int err;
	struct socket *csocket;
	struct sockaddr_un sun_server;
	struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */

	csocket = NULL;

	if (strlen(addr) > UNIX_PATH_MAX) {
		P9_EPRINTK(KERN_ERR, "p9_trans_unix: address too long: %s\n",
			addr);
		err = -ENAMETOOLONG;
		goto error;
	}

	sun_server.sun_family = PF_UNIX;
	strcpy(sun_server.sun_path, addr);
	sock_create_kern(PF_UNIX, SOCK_STREAM, 0, &csocket);
	err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server,
			sizeof(struct sockaddr_un) - 1, 0);
	if (err < 0) {
		P9_EPRINTK(KERN_ERR,
			"p9_trans_unix: problem connecting socket: %s: %d\n",
			addr, err);
		goto error;
	}

	err = p9_socket_open(client, csocket);
	if (err < 0)
		goto error;

	p = (struct p9_trans_fd *) client->trans;
	p->conn = p9_conn_create(client);
	if (IS_ERR(p->conn)) {
		err = PTR_ERR(p->conn);
		p->conn = NULL;
		goto error;
	}

	return 0;

error:
	if (csocket)
		sock_release(csocket);

	kfree(p);
	return err;
}

static int
p9_fd_create(struct p9_client *client, const char *addr, char *args)
{
	int err;
	struct p9_fd_opts opts;
	struct p9_trans_fd *p = NULL; /* this get allocated in p9_fd_open */

	parse_opts(args, &opts);

	if (opts.rfd == ~0 || opts.wfd == ~0) {
		printk(KERN_ERR "v9fs: Insufficient options for proto=fd\n");
		return -ENOPROTOOPT;
	}

	err = p9_fd_open(client, opts.rfd, opts.wfd);
	if (err < 0)
		goto error;

	p = (struct p9_trans_fd *) client->trans;
	p->conn = p9_conn_create(client);
	if (IS_ERR(p->conn)) {
		err = PTR_ERR(p->conn);
		p->conn = NULL;
		goto error;
	}

	return 0;

error:
	kfree(p);
	return err;
}

static struct p9_trans_module p9_tcp_trans = {
	.name = "tcp",
	.maxsize = MAX_SOCK_BUF,
	.def = 1,
	.create = p9_fd_create_tcp,
	.close = p9_fd_close,
	.rpc = p9_fd_rpc,
	.owner = THIS_MODULE,
};

static struct p9_trans_module p9_unix_trans = {
	.name = "unix",
	.maxsize = MAX_SOCK_BUF,
	.def = 0,
	.create = p9_fd_create_unix,
	.close = p9_fd_close,
	.rpc = p9_fd_rpc,
	.owner = THIS_MODULE,
};

static struct p9_trans_module p9_fd_trans = {
	.name = "fd",
	.maxsize = MAX_SOCK_BUF,
	.def = 0,
	.create = p9_fd_create,
	.close = p9_fd_close,
	.rpc = p9_fd_rpc,
	.owner = THIS_MODULE,
};

/**
 * p9_poll_proc - poll worker thread
 * @a: thread state and arguments
 *
 * polls all v9fs transports for new events and queues the appropriate
 * work to the work queue
 *
 */

static int p9_poll_proc(void *a)
{
	unsigned long flags;

	P9_DPRINTK(P9_DEBUG_MUX, "start %p\n", current);
 repeat:
	spin_lock_irqsave(&p9_poll_lock, flags);
	while (!list_empty(&p9_poll_pending_list)) {
		struct p9_conn *conn = list_first_entry(&p9_poll_pending_list,
							struct p9_conn,
							poll_pending_link);
		list_del_init(&conn->poll_pending_link);
		spin_unlock_irqrestore(&p9_poll_lock, flags);

		p9_poll_mux(conn);

		spin_lock_irqsave(&p9_poll_lock, flags);
	}
	spin_unlock_irqrestore(&p9_poll_lock, flags);

	set_current_state(TASK_INTERRUPTIBLE);
	if (list_empty(&p9_poll_pending_list)) {
		P9_DPRINTK(P9_DEBUG_MUX, "sleeping...\n");
		schedule();
	}
	__set_current_state(TASK_RUNNING);

	if (!kthread_should_stop())
		goto repeat;

	P9_DPRINTK(P9_DEBUG_MUX, "finish\n");
	return 0;
}

int p9_trans_fd_init(void)
{
	p9_mux_wq = create_workqueue("v9fs");
	if (!p9_mux_wq) {
		printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n");
		return -ENOMEM;
	}

	p9_poll_task = kthread_run(p9_poll_proc, NULL, "v9fs-poll");
	if (IS_ERR(p9_poll_task)) {
		destroy_workqueue(p9_mux_wq);
		printk(KERN_WARNING "v9fs: mux: creating poll task failed\n");
		return PTR_ERR(p9_poll_task);
	}

	v9fs_register_trans(&p9_tcp_trans);
	v9fs_register_trans(&p9_unix_trans);
	v9fs_register_trans(&p9_fd_trans);

	return 0;
}

void p9_trans_fd_exit(void)
{
	kthread_stop(p9_poll_task);
	v9fs_unregister_trans(&p9_tcp_trans);
	v9fs_unregister_trans(&p9_unix_trans);
	v9fs_unregister_trans(&p9_fd_trans);

	destroy_workqueue(p9_mux_wq);
}