aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/user_mad.c
blob: 268a2d23b7c9a8e9092877ca319989891e99e90d (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
/*
 * Copyright (c) 2004 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2008 Cisco. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/dma-mapping.h>
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/kref.h>
#include <linux/compat.h>
#include <linux/semaphore.h>

#include <asm/uaccess.h>

#include <rdma/ib_mad.h>
#include <rdma/ib_user_mad.h>

MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("InfiniBand userspace MAD packet access");
MODULE_LICENSE("Dual BSD/GPL");

enum {
	IB_UMAD_MAX_PORTS  = 64,
	IB_UMAD_MAX_AGENTS = 32,

	IB_UMAD_MAJOR      = 231,
	IB_UMAD_MINOR_BASE = 0
};

/*
 * Our lifetime rules for these structs are the following: each time a
 * device special file is opened, we look up the corresponding struct
 * ib_umad_port by minor in the umad_port[] table while holding the
 * port_lock.  If this lookup succeeds, we take a reference on the
 * ib_umad_port's struct ib_umad_device while still holding the
 * port_lock; if the lookup fails, we fail the open().  We drop these
 * references in the corresponding close().
 *
 * In addition to references coming from open character devices, there
 * is one more reference to each ib_umad_device representing the
 * module's reference taken when allocating the ib_umad_device in
 * ib_umad_add_one().
 *
 * When destroying an ib_umad_device, we clear all of its
 * ib_umad_ports from umad_port[] while holding port_lock before
 * dropping the module's reference to the ib_umad_device.  This is
 * always safe because any open() calls will either succeed and obtain
 * a reference before we clear the umad_port[] entries, or fail after
 * we clear the umad_port[] entries.
 */

struct ib_umad_port {
	struct cdev           *cdev;
	struct device	      *dev;

	struct cdev           *sm_cdev;
	struct device	      *sm_dev;
	struct semaphore       sm_sem;

	struct mutex	       file_mutex;
	struct list_head       file_list;

	struct ib_device      *ib_dev;
	struct ib_umad_device *umad_dev;
	int                    dev_num;
	u8                     port_num;
};

struct ib_umad_device {
	int                  start_port, end_port;
	struct kref          ref;
	struct ib_umad_port  port[0];
};

struct ib_umad_file {
	struct mutex		mutex;
	struct ib_umad_port    *port;
	struct list_head	recv_list;
	struct list_head	send_list;
	struct list_head	port_list;
	spinlock_t		send_lock;
	wait_queue_head_t	recv_wait;
	struct ib_mad_agent    *agent[IB_UMAD_MAX_AGENTS];
	int			agents_dead;
	u8			use_pkey_index;
	u8			already_used;
};

struct ib_umad_packet {
	struct ib_mad_send_buf *msg;
	struct ib_mad_recv_wc  *recv_wc;
	struct list_head   list;
	int		   length;
	struct ib_user_mad mad;
};

static struct class *umad_class;

static const dev_t base_dev = MKDEV(IB_UMAD_MAJOR, IB_UMAD_MINOR_BASE);

static DEFINE_SPINLOCK(port_lock);
static struct ib_umad_port *umad_port[IB_UMAD_MAX_PORTS];
static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS);

static void ib_umad_add_one(struct ib_device *device);
static void ib_umad_remove_one(struct ib_device *device);

static void ib_umad_release_dev(struct kref *ref)
{
	struct ib_umad_device *dev =
		container_of(ref, struct ib_umad_device, ref);

	kfree(dev);
}

static int hdr_size(struct ib_umad_file *file)
{
	return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
		sizeof (struct ib_user_mad_hdr_old);
}

/* caller must hold file->mutex */
static struct ib_mad_agent *__get_agent(struct ib_umad_file *file, int id)
{
	return file->agents_dead ? NULL : file->agent[id];
}

static int queue_packet(struct ib_umad_file *file,
			struct ib_mad_agent *agent,
			struct ib_umad_packet *packet)
{
	int ret = 1;

	mutex_lock(&file->mutex);

	for (packet->mad.hdr.id = 0;
	     packet->mad.hdr.id < IB_UMAD_MAX_AGENTS;
	     packet->mad.hdr.id++)
		if (agent == __get_agent(file, packet->mad.hdr.id)) {
			list_add_tail(&packet->list, &file->recv_list);
			wake_up_interruptible(&file->recv_wait);
			ret = 0;
			break;
		}

	mutex_unlock(&file->mutex);

	return ret;
}

static void dequeue_send(struct ib_umad_file *file,
			 struct ib_umad_packet *packet)
{
	spin_lock_irq(&file->send_lock);
	list_del(&packet->list);
	spin_unlock_irq(&file->send_lock);
}

static void send_handler(struct ib_mad_agent *agent,
			 struct ib_mad_send_wc *send_wc)
{
	struct ib_umad_file *file = agent->context;
	struct ib_umad_packet *packet = send_wc->send_buf->context[0];

	dequeue_send(file, packet);
	ib_destroy_ah(packet->msg->ah);
	ib_free_send_mad(packet->msg);

	if (send_wc->status == IB_WC_RESP_TIMEOUT_ERR) {
		packet->length = IB_MGMT_MAD_HDR;
		packet->mad.hdr.status = ETIMEDOUT;
		if (!queue_packet(file, agent, packet))
			return;
	}
	kfree(packet);
}

static void recv_handler(struct ib_mad_agent *agent,
			 struct ib_mad_recv_wc *mad_recv_wc)
{
	struct ib_umad_file *file = agent->context;
	struct ib_umad_packet *packet;

	if (mad_recv_wc->wc->status != IB_WC_SUCCESS)
		goto err1;

	packet = kzalloc(sizeof *packet, GFP_KERNEL);
	if (!packet)
		goto err1;

	packet->length = mad_recv_wc->mad_len;
	packet->recv_wc = mad_recv_wc;

	packet->mad.hdr.status	   = 0;
	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
	packet->mad.hdr.lid	   = cpu_to_be16(mad_recv_wc->wc->slid);
	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;
	packet->mad.hdr.grh_present = !!(mad_recv_wc->wc->wc_flags & IB_WC_GRH);
	if (packet->mad.hdr.grh_present) {
		struct ib_ah_attr ah_attr;

		ib_init_ah_from_wc(agent->device, agent->port_num,
				   mad_recv_wc->wc, mad_recv_wc->recv_buf.grh,
				   &ah_attr);

		packet->mad.hdr.gid_index = ah_attr.grh.sgid_index;
		packet->mad.hdr.hop_limit = ah_attr.grh.hop_limit;
		packet->mad.hdr.traffic_class = ah_attr.grh.traffic_class;
		memcpy(packet->mad.hdr.gid, &ah_attr.grh.dgid, 16);
		packet->mad.hdr.flow_label = cpu_to_be32(ah_attr.grh.flow_label);
	}

	if (queue_packet(file, agent, packet))
		goto err2;
	return;

err2:
	kfree(packet);
err1:
	ib_free_recv_mad(mad_recv_wc);
}

static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
			     struct ib_umad_packet *packet, size_t count)
{
	struct ib_mad_recv_buf *recv_buf;
	int left, seg_payload, offset, max_seg_payload;

	/* We need enough room to copy the first (or only) MAD segment. */
	recv_buf = &packet->recv_wc->recv_buf;
	if ((packet->length <= sizeof (*recv_buf->mad) &&
	     count < hdr_size(file) + packet->length) ||
	    (packet->length > sizeof (*recv_buf->mad) &&
	     count < hdr_size(file) + sizeof (*recv_buf->mad)))
		return -EINVAL;

	if (copy_to_user(buf, &packet->mad, hdr_size(file)))
		return -EFAULT;

	buf += hdr_size(file);
	seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
	if (copy_to_user(buf, recv_buf->mad, seg_payload))
		return -EFAULT;

	if (seg_payload < packet->length) {
		/*
		 * Multipacket RMPP MAD message. Copy remainder of message.
		 * Note that last segment may have a shorter payload.
		 */
		if (count < hdr_size(file) + packet->length) {
			/*
			 * The buffer is too small, return the first RMPP segment,
			 * which includes the RMPP message length.
			 */
			return -ENOSPC;
		}
		offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class);
		max_seg_payload = sizeof (struct ib_mad) - offset;

		for (left = packet->length - seg_payload, buf += seg_payload;
		     left; left -= seg_payload, buf += seg_payload) {
			recv_buf = container_of(recv_buf->list.next,
						struct ib_mad_recv_buf, list);
			seg_payload = min(left, max_seg_payload);
			if (copy_to_user(buf, ((void *) recv_buf->mad) + offset,
					 seg_payload))
				return -EFAULT;
		}
	}
	return hdr_size(file) + packet->length;
}

static ssize_t copy_send_mad(struct ib_umad_file *file, char __user *buf,
			     struct ib_umad_packet *packet, size_t count)
{
	ssize_t size = hdr_size(file) + packet->length;

	if (count < size)
		return -EINVAL;

	if (copy_to_user(buf, &packet->mad, hdr_size(file)))
		return -EFAULT;

	buf += hdr_size(file);

	if (copy_to_user(buf, packet->mad.data, packet->length))
		return -EFAULT;

	return size;
}

static ssize_t ib_umad_read(struct file *filp, char __user *buf,
			    size_t count, loff_t *pos)
{
	struct ib_umad_file *file = filp->private_data;
	struct ib_umad_packet *packet;
	ssize_t ret;

	if (count < hdr_size(file))
		return -EINVAL;

	mutex_lock(&file->mutex);

	while (list_empty(&file->recv_list)) {
		mutex_unlock(&file->mutex);

		if (filp->f_flags & O_NONBLOCK)
			return -EAGAIN;

		if (wait_event_interruptible(file->recv_wait,
					     !list_empty(&file->recv_list)))
			return -ERESTARTSYS;

		mutex_lock(&file->mutex);
	}

	packet = list_entry(file->recv_list.next, struct ib_umad_packet, list);
	list_del(&packet->list);

	mutex_unlock(&file->mutex);

	if (packet->recv_wc)
		ret = copy_recv_mad(file, buf, packet, count);
	else
		ret = copy_send_mad(file, buf, packet, count);

	if (ret < 0) {
		/* Requeue packet */
		mutex_lock(&file->mutex);
		list_add(&packet->list, &file->recv_list);
		mutex_unlock(&file->mutex);
	} else {
		if (packet->recv_wc)
			ib_free_recv_mad(packet->recv_wc);
		kfree(packet);
	}
	return ret;
}

static int copy_rmpp_mad(struct ib_mad_send_buf *msg, const char __user *buf)
{
	int left, seg;

	/* Copy class specific header */
	if ((msg->hdr_len > IB_MGMT_RMPP_HDR) &&
	    copy_from_user(msg->mad + IB_MGMT_RMPP_HDR, buf + IB_MGMT_RMPP_HDR,
			   msg->hdr_len - IB_MGMT_RMPP_HDR))
		return -EFAULT;

	/* All headers are in place.  Copy data segments. */
	for (seg = 1, left = msg->data_len, buf += msg->hdr_len; left > 0;
	     seg++, left -= msg->seg_size, buf += msg->seg_size) {
		if (copy_from_user(ib_get_rmpp_segment(msg, seg), buf,
				   min(left, msg->seg_size)))
			return -EFAULT;
	}
	return 0;
}

static int same_destination(struct ib_user_mad_hdr *hdr1,
			    struct ib_user_mad_hdr *hdr2)
{
	if (!hdr1->grh_present && !hdr2->grh_present)
	   return (hdr1->lid == hdr2->lid);

	if (hdr1->grh_present && hdr2->grh_present)
	   return !memcmp(hdr1->gid, hdr2->gid, 16);

	return 0;
}

static int is_duplicate(struct ib_umad_file *file,
			struct ib_umad_packet *packet)
{
	struct ib_umad_packet *sent_packet;
	struct ib_mad_hdr *sent_hdr, *hdr;

	hdr = (struct ib_mad_hdr *) packet->mad.data;
	list_for_each_entry(sent_packet, &file->send_list, list) {
		sent_hdr = (struct ib_mad_hdr *) sent_packet->mad.data;

		if ((hdr->tid != sent_hdr->tid) ||
		    (hdr->mgmt_class != sent_hdr->mgmt_class))
			continue;

		/*
		 * No need to be overly clever here.  If two new operations have
		 * the same TID, reject the second as a duplicate.  This is more
		 * restrictive than required by the spec.
		 */
		if (!ib_response_mad((struct ib_mad *) hdr)) {
			if (!ib_response_mad((struct ib_mad *) sent_hdr))
				return 1;
			continue;
		} else if (!ib_response_mad((struct ib_mad *) sent_hdr))
			continue;

		if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr))
			return 1;
	}

	return 0;
}

static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
			     size_t count, loff_t *pos)
{
	struct ib_umad_file *file = filp->private_data;
	struct ib_umad_packet *packet;
	struct ib_mad_agent *agent;
	struct ib_ah_attr ah_attr;
	struct ib_ah *ah;
	struct ib_rmpp_mad *rmpp_mad;
	__be64 *tid;
	int ret, data_len, hdr_len, copy_offset, rmpp_active;

	if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
		return -EINVAL;

	packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
	if (!packet)
		return -ENOMEM;

	if (copy_from_user(&packet->mad, buf, hdr_size(file))) {
		ret = -EFAULT;
		goto err;
	}

	if (packet->mad.hdr.id < 0 ||
	    packet->mad.hdr.id >= IB_UMAD_MAX_AGENTS) {
		ret = -EINVAL;
		goto err;
	}

	buf += hdr_size(file);

	if (copy_from_user(packet->mad.data, buf, IB_MGMT_RMPP_HDR)) {
		ret = -EFAULT;
		goto err;
	}

	mutex_lock(&file->mutex);

	agent = __get_agent(file, packet->mad.hdr.id);
	if (!agent) {
		ret = -EINVAL;
		goto err_up;
	}

	memset(&ah_attr, 0, sizeof ah_attr);
	ah_attr.dlid          = be16_to_cpu(packet->mad.hdr.lid);
	ah_attr.sl            = packet->mad.hdr.sl;
	ah_attr.src_path_bits = packet->mad.hdr.path_bits;
	ah_attr.port_num      = file->port->port_num;
	if (packet->mad.hdr.grh_present) {
		ah_attr.ah_flags = IB_AH_GRH;
		memcpy(ah_attr.grh.dgid.raw, packet->mad.hdr.gid, 16);
		ah_attr.grh.sgid_index	   = packet->mad.hdr.gid_index;
		ah_attr.grh.flow_label 	   = be32_to_cpu(packet->mad.hdr.flow_label);
		ah_attr.grh.hop_limit  	   = packet->mad.hdr.hop_limit;
		ah_attr.grh.traffic_class  = packet->mad.hdr.traffic_class;
	}

	ah = ib_create_ah(agent->qp->pd, &ah_attr);
	if (IS_ERR(ah)) {
		ret = PTR_ERR(ah);
		goto err_up;
	}

	rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data;
	hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
	if (!ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class)) {
		copy_offset = IB_MGMT_MAD_HDR;
		rmpp_active = 0;
	} else {
		copy_offset = IB_MGMT_RMPP_HDR;
		rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
			      IB_MGMT_RMPP_FLAG_ACTIVE;
	}

	data_len = count - hdr_size(file) - hdr_len;
	packet->msg = ib_create_send_mad(agent,
					 be32_to_cpu(packet->mad.hdr.qpn),
					 packet->mad.hdr.pkey_index, rmpp_active,
					 hdr_len, data_len, GFP_KERNEL);
	if (IS_ERR(packet->msg)) {
		ret = PTR_ERR(packet->msg);
		goto err_ah;
	}

	packet->msg->ah 	= ah;
	packet->msg->timeout_ms = packet->mad.hdr.timeout_ms;
	packet->msg->retries 	= packet->mad.hdr.retries;
	packet->msg->context[0] = packet;

	/* Copy MAD header.  Any RMPP header is already in place. */
	memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);

	if (!rmpp_active) {
		if (copy_from_user(packet->msg->mad + copy_offset,
				   buf + copy_offset,
				   hdr_len + data_len - copy_offset)) {
			ret = -EFAULT;
			goto err_msg;
		}
	} else {
		ret = copy_rmpp_mad(packet->msg, buf);
		if (ret)
			goto err_msg;
	}

	/*
	 * Set the high-order part of the transaction ID to make MADs from
	 * different agents unique, and allow routing responses back to the
	 * original requestor.
	 */
	if (!ib_response_mad(packet->msg->mad)) {
		tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid;
		*tid = cpu_to_be64(((u64) agent->hi_tid) << 32 |
				   (be64_to_cpup(tid) & 0xffffffff));
		rmpp_mad->mad_hdr.tid = *tid;
	}

	spin_lock_irq(&file->send_lock);
	ret = is_duplicate(file, packet);
	if (!ret)
		list_add_tail(&packet->list, &file->send_list);
	spin_unlock_irq(&file->send_lock);
	if (ret) {
		ret = -EINVAL;
		goto err_msg;
	}

	ret = ib_post_send_mad(packet->msg, NULL);
	if (ret)
		goto err_send;

	mutex_unlock(&file->mutex);
	return count;

err_send:
	dequeue_send(file, packet);
err_msg:
	ib_free_send_mad(packet->msg);
err_ah:
	ib_destroy_ah(ah);
err_up:
	mutex_unlock(&file->mutex);
err:
	kfree(packet);
	return ret;
}

static unsigned int ib_umad_poll(struct file *filp, struct poll_table_struct *wait)
{
	struct ib_umad_file *file = filp->private_data;

	/* we will always be able to post a MAD send */
	unsigned int mask = POLLOUT | POLLWRNORM;

	poll_wait(filp, &file->recv_wait, wait);

	if (!list_empty(&file->recv_list))
		mask |= POLLIN | POLLRDNORM;

	return mask;
}

static int ib_umad_reg_agent(struct ib_umad_file *file, void __user *arg,
			     int compat_method_mask)
{
	struct ib_user_mad_reg_req ureq;
	struct ib_mad_reg_req req;
	struct ib_mad_agent *agent = NULL;
	int agent_id;
	int ret;

	mutex_lock(&file->port->file_mutex);
	mutex_lock(&file->mutex);

	if (!file->port->ib_dev) {
		ret = -EPIPE;
		goto out;
	}

	if (copy_from_user(&ureq, arg, sizeof ureq)) {
		ret = -EFAULT;
		goto out;
	}

	if (ureq.qpn != 0 && ureq.qpn != 1) {
		ret = -EINVAL;
		goto out;
	}

	for (agent_id = 0; agent_id < IB_UMAD_MAX_AGENTS; ++agent_id)
		if (!__get_agent(file, agent_id))
			goto found;

	ret = -ENOMEM;
	goto out;

found:
	if (ureq.mgmt_class) {
		req.mgmt_class         = ureq.mgmt_class;
		req.mgmt_class_version = ureq.mgmt_class_version;
		memcpy(req.oui, ureq.oui, sizeof req.oui);

		if (compat_method_mask) {
			u32 *umm = (u32 *) ureq.method_mask;
			int i;

			for (i = 0; i < BITS_TO_LONGS(IB_MGMT_MAX_METHODS); ++i)
				req.method_mask[i] =
					umm[i * 2] | ((u64) umm[i * 2 + 1] << 32);
		} else
			memcpy(req.method_mask, ureq.method_mask,
			       sizeof req.method_mask);
	}

	agent = ib_register_mad_agent(file->port->ib_dev, file->port->port_num,
				      ureq.qpn ? IB_QPT_GSI : IB_QPT_SMI,
				      ureq.mgmt_class ? &req : NULL,
				      ureq.rmpp_version,
				      send_handler, recv_handler, file);
	if (IS_ERR(agent)) {
		ret = PTR_ERR(agent);
		agent = NULL;
		goto out;
	}

	if (put_user(agent_id,
		     (u32 __user *) (arg + offsetof(struct ib_user_mad_reg_req, id)))) {
		ret = -EFAULT;
		goto out;
	}

	if (!file->already_used) {
		file->already_used = 1;
		if (!file->use_pkey_index) {
			printk(KERN_WARNING "user_mad: process %s did not enable "
			       "P_Key index support.\n", current->comm);
			printk(KERN_WARNING "user_mad:   Documentation/infiniband/user_mad.txt "
			       "has info on the new ABI.\n");
		}
	}

	file->agent[agent_id] = agent;
	ret = 0;

out:
	mutex_unlock(&file->mutex);

	if (ret && agent)
		ib_unregister_mad_agent(agent);

	mutex_unlock(&file->port->file_mutex);

	return ret;
}

static int ib_umad_unreg_agent(struct ib_umad_file *file, u32 __user *arg)
{
	struct ib_mad_agent *agent = NULL;
	u32 id;
	int ret = 0;

	if (get_user(id, arg))
		return -EFAULT;

	mutex_lock(&file->port->file_mutex);
	mutex_lock(&file->mutex);

	if (id < 0 || id >= IB_UMAD_MAX_AGENTS || !__get_agent(file, id)) {
		ret = -EINVAL;
		goto out;
	}

	agent = file->agent[id];
	file->agent[id] = NULL;

out:
	mutex_unlock(&file->mutex);

	if (agent)
		ib_unregister_mad_agent(agent);

	mutex_unlock(&file->port->file_mutex);

	return ret;
}

static long ib_umad_enable_pkey(struct ib_umad_file *file)
{
	int ret = 0;

	mutex_lock(&file->mutex);
	if (file->already_used)
		ret = -EINVAL;
	else
		file->use_pkey_index = 1;
	mutex_unlock(&file->mutex);

	return ret;
}

static long ib_umad_ioctl(struct file *filp, unsigned int cmd,
			  unsigned long arg)
{
	switch (cmd) {
	case IB_USER_MAD_REGISTER_AGENT:
		return ib_umad_reg_agent(filp->private_data, (void __user *) arg, 0);
	case IB_USER_MAD_UNREGISTER_AGENT:
		return ib_umad_unreg_agent(filp->private_data, (__u32 __user *) arg);
	case IB_USER_MAD_ENABLE_PKEY:
		return ib_umad_enable_pkey(filp->private_data);
	default:
		return -ENOIOCTLCMD;
	}
}

#ifdef CONFIG_COMPAT
static long ib_umad_compat_ioctl(struct file *filp, unsigned int cmd,
				 unsigned long arg)
{
	switch (cmd) {
	case IB_USER_MAD_REGISTER_AGENT:
		return ib_umad_reg_agent(filp->private_data, compat_ptr(arg), 1);
	case IB_USER_MAD_UNREGISTER_AGENT:
		return ib_umad_unreg_agent(filp->private_data, compat_ptr(arg));
	case IB_USER_MAD_ENABLE_PKEY:
		return ib_umad_enable_pkey(filp->private_data);
	default:
		return -ENOIOCTLCMD;
	}
}
#endif

/*
 * ib_umad_open() does not need the BKL:
 *
 *  - umad_port[] accesses are protected by port_lock, the
 *    ib_umad_port structures are properly reference counted, and
 *    everything else is purely local to the file being created, so
 *    races against other open calls are not a problem;
 *  - the ioctl method does not affect any global state outside of the
 *    file structure being operated on;
 *  - the port is added to umad_port[] as the last part of module
 *    initialization so the open method will either immediately run
 *    -ENXIO, or all required initialization will be done.
 */
static int ib_umad_open(struct inode *inode, struct file *filp)
{
	struct ib_umad_port *port;
	struct ib_umad_file *file;
	int ret = 0;

	spin_lock(&port_lock);
	port = umad_port[iminor(inode) - IB_UMAD_MINOR_BASE];
	if (port)
		kref_get(&port->umad_dev->ref);
	spin_unlock(&port_lock);

	if (!port)
		return -ENXIO;

	mutex_lock(&port->file_mutex);

	if (!port->ib_dev) {
		ret = -ENXIO;
		goto out;
	}

	file = kzalloc(sizeof *file, GFP_KERNEL);
	if (!file) {
		kref_put(&port->umad_dev->ref, ib_umad_release_dev);
		ret = -ENOMEM;
		goto out;
	}

	mutex_init(&file->mutex);
	spin_lock_init(&file->send_lock);
	INIT_LIST_HEAD(&file->recv_list);
	INIT_LIST_HEAD(&file->send_list);
	init_waitqueue_head(&file->recv_wait);

	file->port = port;
	filp->private_data = file;

	list_add_tail(&file->port_list, &port->file_list);

out:
	mutex_unlock(&port->file_mutex);
	return ret;
}

static int ib_umad_close(struct inode *inode, struct file *filp)
{
	struct ib_umad_file *file = filp->private_data;
	struct ib_umad_device *dev = file->port->umad_dev;
	struct ib_umad_packet *packet, *tmp;
	int already_dead;
	int i;

	mutex_lock(&file->port->file_mutex);
	mutex_lock(&file->mutex);

	already_dead = file->agents_dead;
	file->agents_dead = 1;

	list_for_each_entry_safe(packet, tmp, &file->recv_list, list) {
		if (packet->recv_wc)
			ib_free_recv_mad(packet->recv_wc);
		kfree(packet);
	}

	list_del(&file->port_list);

	mutex_unlock(&file->mutex);

	if (!already_dead)
		for (i = 0; i < IB_UMAD_MAX_AGENTS; ++i)
			if (file->agent[i])
				ib_unregister_mad_agent(file->agent[i]);

	mutex_unlock(&file->port->file_mutex);

	kfree(file);
	kref_put(&dev->ref, ib_umad_release_dev);

	return 0;
}

static const struct file_operations umad_fops = {
	.owner 	 	= THIS_MODULE,
	.read 	 	= ib_umad_read,
	.write 	 	= ib_umad_write,
	.poll 	 	= ib_umad_poll,
	.unlocked_ioctl = ib_umad_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl 	= ib_umad_compat_ioctl,
#endif
	.open 	 	= ib_umad_open,
	.release 	= ib_umad_close
};

static int ib_umad_sm_open(struct inode *inode, struct file *filp)
{
	struct ib_umad_port *port;
	struct ib_port_modify props = {
		.set_port_cap_mask = IB_PORT_SM
	};
	int ret;

	spin_lock(&port_lock);
	port = umad_port[iminor(inode) - IB_UMAD_MINOR_BASE - IB_UMAD_MAX_PORTS];
	if (port)
		kref_get(&port->umad_dev->ref);
	spin_unlock(&port_lock);

	if (!port)
		return -ENXIO;

	if (filp->f_flags & O_NONBLOCK) {
		if (down_trylock(&port->sm_sem)) {
			ret = -EAGAIN;
			goto fail;
		}
	} else {
		if (down_interruptible(&port->sm_sem)) {
			ret = -ERESTARTSYS;
			goto fail;
		}
	}

	ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
	if (ret) {
		up(&port->sm_sem);
		goto fail;
	}

	filp->private_data = port;

	return 0;

fail:
	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
	return ret;
}

static int ib_umad_sm_close(struct inode *inode, struct file *filp)
{
	struct ib_umad_port *port = filp->private_data;
	struct ib_port_modify props = {
		.clr_port_cap_mask = IB_PORT_SM
	};
	int ret = 0;

	mutex_lock(&port->file_mutex);
	if (port->ib_dev)
		ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
	mutex_unlock(&port->file_mutex);

	up(&port->sm_sem);

	kref_put(&port->umad_dev->ref, ib_umad_release_dev);

	return ret;
}

static const struct file_operations umad_sm_fops = {
	.owner 	 = THIS_MODULE,
	.open 	 = ib_umad_sm_open,
	.release = ib_umad_sm_close
};

static struct ib_client umad_client = {
	.name   = "umad",
	.add    = ib_umad_add_one,
	.remove = ib_umad_remove_one
};

static ssize_t show_ibdev(struct device *dev, struct device_attribute *attr,
			  char *buf)
{
	struct ib_umad_port *port = dev_get_drvdata(dev);

	if (!port)
		return -ENODEV;

	return sprintf(buf, "%s\n", port->ib_dev->name);
}
static DEVICE_ATTR(ibdev, S_IRUGO, show_ibdev, NULL);

static ssize_t show_port(struct device *dev, struct device_attribute *attr,
			 char *buf)
{
	struct ib_umad_port *port = dev_get_drvdata(dev);

	if (!port)
		return -ENODEV;

	return sprintf(buf, "%d\n", port->port_num);
}
static DEVICE_ATTR(port, S_IRUGO, show_port, NULL);

static ssize_t show_abi_version(struct class *class, char *buf)
{
	return sprintf(buf, "%d\n", IB_USER_MAD_ABI_VERSION);
}
static CLASS_ATTR(abi_version, S_IRUGO, show_abi_version, NULL);

static int ib_umad_init_port(struct ib_device *device, int port_num,
			     struct ib_umad_port *port)
{
	spin_lock(&port_lock);
	port->dev_num = find_first_zero_bit(dev_map, IB_UMAD_MAX_PORTS);
	if (port->dev_num >= IB_UMAD_MAX_PORTS) {
		spin_unlock(&port_lock);
		return -1;
	}
	set_bit(port->dev_num, dev_map);
	spin_unlock(&port_lock);

	port->ib_dev   = device;
	port->port_num = port_num;
	init_MUTEX(&port->sm_sem);
	mutex_init(&port->file_mutex);
	INIT_LIST_HEAD(&port->file_list);

	port->cdev = cdev_alloc();
	if (!port->cdev)
		return -1;
	port->cdev->owner = THIS_MODULE;
	port->cdev->ops   = &umad_fops;
	kobject_set_name(&port->cdev->kobj, "umad%d", port->dev_num);
	if (cdev_add(port->cdev, base_dev + port->dev_num, 1))
		goto err_cdev;

	port->dev = device_create_drvdata(umad_class, device->dma_device,
					  port->cdev->dev, port,
					  "umad%d", port->dev_num);
	if (IS_ERR(port->dev))
		goto err_cdev;

	if (device_create_file(port->dev, &dev_attr_ibdev))
		goto err_dev;
	if (device_create_file(port->dev, &dev_attr_port))
		goto err_dev;

	port->sm_cdev = cdev_alloc();
	if (!port->sm_cdev)
		goto err_dev;
	port->sm_cdev->owner = THIS_MODULE;
	port->sm_cdev->ops   = &umad_sm_fops;
	kobject_set_name(&port->sm_cdev->kobj, "issm%d", port->dev_num);
	if (cdev_add(port->sm_cdev, base_dev + port->dev_num + IB_UMAD_MAX_PORTS, 1))
		goto err_sm_cdev;

	port->sm_dev = device_create_drvdata(umad_class, device->dma_device,
					     port->sm_cdev->dev, port,
					     "issm%d", port->dev_num);
	if (IS_ERR(port->sm_dev))
		goto err_sm_cdev;

	if (device_create_file(port->sm_dev, &dev_attr_ibdev))
		goto err_sm_dev;
	if (device_create_file(port->sm_dev, &dev_attr_port))
		goto err_sm_dev;

	spin_lock(&port_lock);
	umad_port[port->dev_num] = port;
	spin_unlock(&port_lock);

	return 0;

err_sm_dev:
	device_destroy(umad_class, port->sm_cdev->dev);

err_sm_cdev:
	cdev_del(port->sm_cdev);

err_dev:
	device_destroy(umad_class, port->cdev->dev);

err_cdev:
	cdev_del(port->cdev);
	clear_bit(port->dev_num, dev_map);

	return -1;
}

static void ib_umad_kill_port(struct ib_umad_port *port)
{
	struct ib_umad_file *file;
	int already_dead;
	int id;

	dev_set_drvdata(port->dev,    NULL);
	dev_set_drvdata(port->sm_dev, NULL);

	device_destroy(umad_class, port->cdev->dev);
	device_destroy(umad_class, port->sm_cdev->dev);

	cdev_del(port->cdev);
	cdev_del(port->sm_cdev);

	spin_lock(&port_lock);
	umad_port[port->dev_num] = NULL;
	spin_unlock(&port_lock);

	mutex_lock(&port->file_mutex);

	port->ib_dev = NULL;

	list_for_each_entry(file, &port->file_list, port_list) {
		mutex_lock(&file->mutex);
		already_dead = file->agents_dead;
		file->agents_dead = 1;
		mutex_unlock(&file->mutex);

		for (id = 0; id < IB_UMAD_MAX_AGENTS; ++id)
			if (file->agent[id])
				ib_unregister_mad_agent(file->agent[id]);
	}

	mutex_unlock(&port->file_mutex);

	clear_bit(port->dev_num, dev_map);
}

static void ib_umad_add_one(struct ib_device *device)
{
	struct ib_umad_device *umad_dev;
	int s, e, i;

	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
		return;

	if (device->node_type == RDMA_NODE_IB_SWITCH)
		s = e = 0;
	else {
		s = 1;
		e = device->phys_port_cnt;
	}

	umad_dev = kzalloc(sizeof *umad_dev +
			   (e - s + 1) * sizeof (struct ib_umad_port),
			   GFP_KERNEL);
	if (!umad_dev)
		return;

	kref_init(&umad_dev->ref);

	umad_dev->start_port = s;
	umad_dev->end_port   = e;

	for (i = s; i <= e; ++i) {
		umad_dev->port[i - s].umad_dev = umad_dev;

		if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
			goto err;
	}

	ib_set_client_data(device, &umad_client, umad_dev);

	return;

err:
	while (--i >= s)
		ib_umad_kill_port(&umad_dev->port[i - s]);

	kref_put(&umad_dev->ref, ib_umad_release_dev);
}

static void ib_umad_remove_one(struct ib_device *device)
{
	struct ib_umad_device *umad_dev = ib_get_client_data(device, &umad_client);
	int i;

	if (!umad_dev)
		return;

	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
		ib_umad_kill_port(&umad_dev->port[i]);

	kref_put(&umad_dev->ref, ib_umad_release_dev);
}

static int __init ib_umad_init(void)
{
	int ret;

	ret = register_chrdev_region(base_dev, IB_UMAD_MAX_PORTS * 2,
				     "infiniband_mad");
	if (ret) {
		printk(KERN_ERR "user_mad: couldn't register device number\n");
		goto out;
	}

	umad_class = class_create(THIS_MODULE, "infiniband_mad");
	if (IS_ERR(umad_class)) {
		ret = PTR_ERR(umad_class);
		printk(KERN_ERR "user_mad: couldn't create class infiniband_mad\n");
		goto out_chrdev;
	}

	ret = class_create_file(umad_class, &class_attr_abi_version);
	if (ret) {
		printk(KERN_ERR "user_mad: couldn't create abi_version attribute\n");
		goto out_class;
	}

	ret = ib_register_client(&umad_client);
	if (ret) {
		printk(KERN_ERR "user_mad: couldn't register ib_umad client\n");
		goto out_class;
	}

	return 0;

out_class:
	class_destroy(umad_class);

out_chrdev:
	unregister_chrdev_region(base_dev, IB_UMAD_MAX_PORTS * 2);

out:
	return ret;
}

static void __exit ib_umad_cleanup(void)
{
	ib_unregister_client(&umad_client);
	class_destroy(umad_class);
	unregister_chrdev_region(base_dev, IB_UMAD_MAX_PORTS * 2);
}

module_init(ib_umad_init);
module_exit(ib_umad_cleanup);