forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
qrtr.c
1317 lines (1097 loc) · 30.1 KB
/
qrtr.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2015, Sony Mobile Communications Inc.
* Copyright (c) 2013, The Linux Foundation. All rights reserved.
*/
#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/qrtr.h>
#include <linux/termios.h> /* For TIOCINQ/OUTQ */
#include <linux/spinlock.h>
#include <linux/wait.h>
#include <net/sock.h>
#include "qrtr.h"
#define QRTR_PROTO_VER_1 1
#define QRTR_PROTO_VER_2 3
/* auto-bind range */
#define QRTR_MIN_EPH_SOCKET 0x4000
#define QRTR_MAX_EPH_SOCKET 0x7fff
#define QRTR_EPH_PORT_RANGE \
XA_LIMIT(QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET)
/**
* struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1
* @version: protocol version
* @type: packet type; one of QRTR_TYPE_*
* @src_node_id: source node
* @src_port_id: source port
* @confirm_rx: boolean; whether a resume-tx packet should be send in reply
* @size: length of packet, excluding this header
* @dst_node_id: destination node
* @dst_port_id: destination port
*/
struct qrtr_hdr_v1 {
__le32 version;
__le32 type;
__le32 src_node_id;
__le32 src_port_id;
__le32 confirm_rx;
__le32 size;
__le32 dst_node_id;
__le32 dst_port_id;
} __packed;
/**
* struct qrtr_hdr_v2 - (I|R)PCrouter packet header later versions
* @version: protocol version
* @type: packet type; one of QRTR_TYPE_*
* @flags: bitmask of QRTR_FLAGS_*
* @optlen: length of optional header data
* @size: length of packet, excluding this header and optlen
* @src_node_id: source node
* @src_port_id: source port
* @dst_node_id: destination node
* @dst_port_id: destination port
*/
struct qrtr_hdr_v2 {
u8 version;
u8 type;
u8 flags;
u8 optlen;
__le32 size;
__le16 src_node_id;
__le16 src_port_id;
__le16 dst_node_id;
__le16 dst_port_id;
};
#define QRTR_FLAGS_CONFIRM_RX BIT(0)
struct qrtr_cb {
u32 src_node;
u32 src_port;
u32 dst_node;
u32 dst_port;
u8 type;
u8 confirm_rx;
};
#define QRTR_HDR_MAX_SIZE max_t(size_t, sizeof(struct qrtr_hdr_v1), \
sizeof(struct qrtr_hdr_v2))
struct qrtr_sock {
/* WARNING: sk must be the first member */
struct sock sk;
struct sockaddr_qrtr us;
struct sockaddr_qrtr peer;
};
static inline struct qrtr_sock *qrtr_sk(struct sock *sk)
{
BUILD_BUG_ON(offsetof(struct qrtr_sock, sk) != 0);
return container_of(sk, struct qrtr_sock, sk);
}
static unsigned int qrtr_local_nid = 1;
/* for node ids */
static RADIX_TREE(qrtr_nodes, GFP_ATOMIC);
static DEFINE_SPINLOCK(qrtr_nodes_lock);
/* broadcast list */
static LIST_HEAD(qrtr_all_nodes);
/* lock for qrtr_all_nodes and node reference */
static DEFINE_MUTEX(qrtr_node_lock);
/* local port allocation management */
static DEFINE_XARRAY_ALLOC(qrtr_ports);
/**
* struct qrtr_node - endpoint node
* @ep_lock: lock for endpoint management and callbacks
* @ep: endpoint
* @ref: reference count for node
* @nid: node id
* @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port
* @qrtr_tx_lock: lock for qrtr_tx_flow inserts
* @rx_queue: receive queue
* @item: list item for broadcast list
*/
struct qrtr_node {
struct mutex ep_lock;
struct qrtr_endpoint *ep;
struct kref ref;
unsigned int nid;
struct radix_tree_root qrtr_tx_flow;
struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */
struct sk_buff_head rx_queue;
struct list_head item;
};
/**
* struct qrtr_tx_flow - tx flow control
* @resume_tx: waiters for a resume tx from the remote
* @pending: number of waiting senders
* @tx_failed: indicates that a message with confirm_rx flag was lost
*/
struct qrtr_tx_flow {
struct wait_queue_head resume_tx;
int pending;
int tx_failed;
};
#define QRTR_TX_FLOW_HIGH 10
#define QRTR_TX_FLOW_LOW 5
static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to);
static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to);
static struct qrtr_sock *qrtr_port_lookup(int port);
static void qrtr_port_put(struct qrtr_sock *ipc);
/* Release node resources and free the node.
*
* Do not call directly, use qrtr_node_release. To be used with
* kref_put_mutex. As such, the node mutex is expected to be locked on call.
*/
static void __qrtr_node_release(struct kref *kref)
{
struct qrtr_node *node = container_of(kref, struct qrtr_node, ref);
struct radix_tree_iter iter;
struct qrtr_tx_flow *flow;
unsigned long flags;
void __rcu **slot;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
/* If the node is a bridge for other nodes, there are possibly
* multiple entries pointing to our released node, delete them all.
*/
radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
if (*slot == node)
radix_tree_iter_delete(&qrtr_nodes, &iter, slot);
}
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
list_del(&node->item);
mutex_unlock(&qrtr_node_lock);
skb_queue_purge(&node->rx_queue);
/* Free tx flow counters */
radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
flow = *slot;
radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot);
kfree(flow);
}
kfree(node);
}
/* Increment reference to node. */
static struct qrtr_node *qrtr_node_acquire(struct qrtr_node *node)
{
if (node)
kref_get(&node->ref);
return node;
}
/* Decrement reference to node and release as necessary. */
static void qrtr_node_release(struct qrtr_node *node)
{
if (!node)
return;
kref_put_mutex(&node->ref, __qrtr_node_release, &qrtr_node_lock);
}
/**
* qrtr_tx_resume() - reset flow control counter
* @node: qrtr_node that the QRTR_TYPE_RESUME_TX packet arrived on
* @skb: resume_tx packet
*/
static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb)
{
struct qrtr_ctrl_pkt *pkt = (struct qrtr_ctrl_pkt *)skb->data;
u64 remote_node = le32_to_cpu(pkt->client.node);
u32 remote_port = le32_to_cpu(pkt->client.port);
struct qrtr_tx_flow *flow;
unsigned long key;
key = remote_node << 32 | remote_port;
rcu_read_lock();
flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
rcu_read_unlock();
if (flow) {
spin_lock(&flow->resume_tx.lock);
flow->pending = 0;
spin_unlock(&flow->resume_tx.lock);
wake_up_interruptible_all(&flow->resume_tx);
}
consume_skb(skb);
}
/**
* qrtr_tx_wait() - flow control for outgoing packets
* @node: qrtr_node that the packet is to be send to
* @dest_node: node id of the destination
* @dest_port: port number of the destination
* @type: type of message
*
* The flow control scheme is based around the low and high "watermarks". When
* the low watermark is passed the confirm_rx flag is set on the outgoing
* message, which will trigger the remote to send a control message of the type
* QRTR_TYPE_RESUME_TX to reset the counter. If the high watermark is hit
* further transmision should be paused.
*
* Return: 1 if confirm_rx should be set, 0 otherwise or errno failure
*/
static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port,
int type)
{
unsigned long key = (u64)dest_node << 32 | dest_port;
struct qrtr_tx_flow *flow;
int confirm_rx = 0;
int ret;
/* Never set confirm_rx on non-data packets */
if (type != QRTR_TYPE_DATA)
return 0;
mutex_lock(&node->qrtr_tx_lock);
flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
if (!flow) {
flow = kzalloc(sizeof(*flow), GFP_KERNEL);
if (flow) {
init_waitqueue_head(&flow->resume_tx);
if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) {
kfree(flow);
flow = NULL;
}
}
}
mutex_unlock(&node->qrtr_tx_lock);
/* Set confirm_rx if we where unable to find and allocate a flow */
if (!flow)
return 1;
spin_lock_irq(&flow->resume_tx.lock);
ret = wait_event_interruptible_locked_irq(flow->resume_tx,
flow->pending < QRTR_TX_FLOW_HIGH ||
flow->tx_failed ||
!node->ep);
if (ret < 0) {
confirm_rx = ret;
} else if (!node->ep) {
confirm_rx = -EPIPE;
} else if (flow->tx_failed) {
flow->tx_failed = 0;
confirm_rx = 1;
} else {
flow->pending++;
confirm_rx = flow->pending == QRTR_TX_FLOW_LOW;
}
spin_unlock_irq(&flow->resume_tx.lock);
return confirm_rx;
}
/**
* qrtr_tx_flow_failed() - flag that tx of confirm_rx flagged messages failed
* @node: qrtr_node that the packet is to be send to
* @dest_node: node id of the destination
* @dest_port: port number of the destination
*
* Signal that the transmission of a message with confirm_rx flag failed. The
* flow's "pending" counter will keep incrementing towards QRTR_TX_FLOW_HIGH,
* at which point transmission would stall forever waiting for the resume TX
* message associated with the dropped confirm_rx message.
* Work around this by marking the flow as having a failed transmission and
* cause the next transmission attempt to be sent with the confirm_rx.
*/
static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node,
int dest_port)
{
unsigned long key = (u64)dest_node << 32 | dest_port;
struct qrtr_tx_flow *flow;
rcu_read_lock();
flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
rcu_read_unlock();
if (flow) {
spin_lock_irq(&flow->resume_tx.lock);
flow->tx_failed = 1;
spin_unlock_irq(&flow->resume_tx.lock);
}
}
/* Pass an outgoing packet socket buffer to the endpoint driver. */
static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to)
{
struct qrtr_hdr_v1 *hdr;
size_t len = skb->len;
int rc, confirm_rx;
confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type);
if (confirm_rx < 0) {
kfree_skb(skb);
return confirm_rx;
}
hdr = skb_push(skb, sizeof(*hdr));
hdr->version = cpu_to_le32(QRTR_PROTO_VER_1);
hdr->type = cpu_to_le32(type);
hdr->src_node_id = cpu_to_le32(from->sq_node);
hdr->src_port_id = cpu_to_le32(from->sq_port);
if (to->sq_port == QRTR_PORT_CTRL) {
hdr->dst_node_id = cpu_to_le32(node->nid);
hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL);
} else {
hdr->dst_node_id = cpu_to_le32(to->sq_node);
hdr->dst_port_id = cpu_to_le32(to->sq_port);
}
hdr->size = cpu_to_le32(len);
hdr->confirm_rx = !!confirm_rx;
rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
if (!rc) {
mutex_lock(&node->ep_lock);
rc = -ENODEV;
if (node->ep)
rc = node->ep->xmit(node->ep, skb);
else
kfree_skb(skb);
mutex_unlock(&node->ep_lock);
}
/* Need to ensure that a subsequent message carries the otherwise lost
* confirm_rx flag if we dropped this one */
if (rc && confirm_rx)
qrtr_tx_flow_failed(node, to->sq_node, to->sq_port);
return rc;
}
/* Lookup node by id.
*
* callers must release with qrtr_node_release()
*/
static struct qrtr_node *qrtr_node_lookup(unsigned int nid)
{
struct qrtr_node *node;
unsigned long flags;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
node = radix_tree_lookup(&qrtr_nodes, nid);
node = qrtr_node_acquire(node);
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
return node;
}
/* Assign node id to node.
*
* This is mostly useful for automatic node id assignment, based on
* the source id in the incoming packet.
*/
static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid)
{
unsigned long flags;
if (nid == QRTR_EP_NID_AUTO)
return;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
radix_tree_insert(&qrtr_nodes, nid, node);
if (node->nid == QRTR_EP_NID_AUTO)
node->nid = nid;
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
}
/**
* qrtr_endpoint_post() - post incoming data
* @ep: endpoint handle
* @data: data pointer
* @len: size of data in bytes
*
* Return: 0 on success; negative error code on failure
*/
int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
{
struct qrtr_node *node = ep->node;
const struct qrtr_hdr_v1 *v1;
const struct qrtr_hdr_v2 *v2;
struct qrtr_sock *ipc;
struct sk_buff *skb;
struct qrtr_cb *cb;
size_t size;
unsigned int ver;
size_t hdrlen;
if (len == 0 || len & 3)
return -EINVAL;
skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN);
if (!skb)
return -ENOMEM;
cb = (struct qrtr_cb *)skb->cb;
/* Version field in v1 is little endian, so this works for both cases */
ver = *(u8*)data;
switch (ver) {
case QRTR_PROTO_VER_1:
if (len < sizeof(*v1))
goto err;
v1 = data;
hdrlen = sizeof(*v1);
cb->type = le32_to_cpu(v1->type);
cb->src_node = le32_to_cpu(v1->src_node_id);
cb->src_port = le32_to_cpu(v1->src_port_id);
cb->confirm_rx = !!v1->confirm_rx;
cb->dst_node = le32_to_cpu(v1->dst_node_id);
cb->dst_port = le32_to_cpu(v1->dst_port_id);
size = le32_to_cpu(v1->size);
break;
case QRTR_PROTO_VER_2:
if (len < sizeof(*v2))
goto err;
v2 = data;
hdrlen = sizeof(*v2) + v2->optlen;
cb->type = v2->type;
cb->confirm_rx = !!(v2->flags & QRTR_FLAGS_CONFIRM_RX);
cb->src_node = le16_to_cpu(v2->src_node_id);
cb->src_port = le16_to_cpu(v2->src_port_id);
cb->dst_node = le16_to_cpu(v2->dst_node_id);
cb->dst_port = le16_to_cpu(v2->dst_port_id);
if (cb->src_port == (u16)QRTR_PORT_CTRL)
cb->src_port = QRTR_PORT_CTRL;
if (cb->dst_port == (u16)QRTR_PORT_CTRL)
cb->dst_port = QRTR_PORT_CTRL;
size = le32_to_cpu(v2->size);
break;
default:
pr_err("qrtr: Invalid version %d\n", ver);
goto err;
}
if (!size || len != ALIGN(size, 4) + hdrlen)
goto err;
if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA &&
cb->type != QRTR_TYPE_RESUME_TX)
goto err;
skb_put_data(skb, data + hdrlen, size);
qrtr_node_assign(node, cb->src_node);
if (cb->type == QRTR_TYPE_NEW_SERVER) {
/* Remote node endpoint can bridge other distant nodes */
const struct qrtr_ctrl_pkt *pkt = data + hdrlen;
qrtr_node_assign(node, le32_to_cpu(pkt->server.node));
}
if (cb->type == QRTR_TYPE_RESUME_TX) {
qrtr_tx_resume(node, skb);
} else {
ipc = qrtr_port_lookup(cb->dst_port);
if (!ipc)
goto err;
if (sock_queue_rcv_skb(&ipc->sk, skb)) {
qrtr_port_put(ipc);
goto err;
}
qrtr_port_put(ipc);
}
return 0;
err:
kfree_skb(skb);
return -EINVAL;
}
EXPORT_SYMBOL_GPL(qrtr_endpoint_post);
/**
* qrtr_alloc_ctrl_packet() - allocate control packet skb
* @pkt: reference to qrtr_ctrl_pkt pointer
* @flags: the type of memory to allocate
*
* Returns newly allocated sk_buff, or NULL on failure
*
* This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and
* on success returns a reference to the control packet in @pkt.
*/
static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt,
gfp_t flags)
{
const int pkt_len = sizeof(struct qrtr_ctrl_pkt);
struct sk_buff *skb;
skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, flags);
if (!skb)
return NULL;
skb_reserve(skb, QRTR_HDR_MAX_SIZE);
*pkt = skb_put_zero(skb, pkt_len);
return skb;
}
/**
* qrtr_endpoint_register() - register a new endpoint
* @ep: endpoint to register
* @nid: desired node id; may be QRTR_EP_NID_AUTO for auto-assignment
* Return: 0 on success; negative error code on failure
*
* The specified endpoint must have the xmit function pointer set on call.
*/
int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid)
{
struct qrtr_node *node;
if (!ep || !ep->xmit)
return -EINVAL;
node = kzalloc(sizeof(*node), GFP_KERNEL);
if (!node)
return -ENOMEM;
kref_init(&node->ref);
mutex_init(&node->ep_lock);
skb_queue_head_init(&node->rx_queue);
node->nid = QRTR_EP_NID_AUTO;
node->ep = ep;
INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL);
mutex_init(&node->qrtr_tx_lock);
qrtr_node_assign(node, nid);
mutex_lock(&qrtr_node_lock);
list_add(&node->item, &qrtr_all_nodes);
mutex_unlock(&qrtr_node_lock);
ep->node = node;
return 0;
}
EXPORT_SYMBOL_GPL(qrtr_endpoint_register);
/**
* qrtr_endpoint_unregister - unregister endpoint
* @ep: endpoint to unregister
*/
void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
{
struct qrtr_node *node = ep->node;
struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL};
struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL};
struct radix_tree_iter iter;
struct qrtr_ctrl_pkt *pkt;
struct qrtr_tx_flow *flow;
struct sk_buff *skb;
unsigned long flags;
void __rcu **slot;
mutex_lock(&node->ep_lock);
node->ep = NULL;
mutex_unlock(&node->ep_lock);
/* Notify the local controller about the event */
spin_lock_irqsave(&qrtr_nodes_lock, flags);
radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
if (*slot != node)
continue;
src.sq_node = iter.index;
skb = qrtr_alloc_ctrl_packet(&pkt, GFP_ATOMIC);
if (skb) {
pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
}
}
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
/* Wake up any transmitters waiting for resume-tx from the node */
mutex_lock(&node->qrtr_tx_lock);
radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
flow = *slot;
wake_up_interruptible_all(&flow->resume_tx);
}
mutex_unlock(&node->qrtr_tx_lock);
qrtr_node_release(node);
ep->node = NULL;
}
EXPORT_SYMBOL_GPL(qrtr_endpoint_unregister);
/* Lookup socket by port.
*
* Callers must release with qrtr_port_put()
*/
static struct qrtr_sock *qrtr_port_lookup(int port)
{
struct qrtr_sock *ipc;
if (port == QRTR_PORT_CTRL)
port = 0;
rcu_read_lock();
ipc = xa_load(&qrtr_ports, port);
if (ipc)
sock_hold(&ipc->sk);
rcu_read_unlock();
return ipc;
}
/* Release acquired socket. */
static void qrtr_port_put(struct qrtr_sock *ipc)
{
sock_put(&ipc->sk);
}
/* Remove port assignment. */
static void qrtr_port_remove(struct qrtr_sock *ipc)
{
struct qrtr_ctrl_pkt *pkt;
struct sk_buff *skb;
int port = ipc->us.sq_port;
struct sockaddr_qrtr to;
to.sq_family = AF_QIPCRTR;
to.sq_node = QRTR_NODE_BCAST;
to.sq_port = QRTR_PORT_CTRL;
skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
if (skb) {
pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
pkt->client.node = cpu_to_le32(ipc->us.sq_node);
pkt->client.port = cpu_to_le32(ipc->us.sq_port);
skb_set_owner_w(skb, &ipc->sk);
qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us,
&to);
}
if (port == QRTR_PORT_CTRL)
port = 0;
__sock_put(&ipc->sk);
xa_erase(&qrtr_ports, port);
/* Ensure that if qrtr_port_lookup() did enter the RCU read section we
* wait for it to up increment the refcount */
synchronize_rcu();
}
/* Assign port number to socket.
*
* Specify port in the integer pointed to by port, and it will be adjusted
* on return as necesssary.
*
* Port may be:
* 0: Assign ephemeral port in [QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET]
* <QRTR_MIN_EPH_SOCKET: Specified; requires CAP_NET_ADMIN
* >QRTR_MIN_EPH_SOCKET: Specified; available to all
*/
static int qrtr_port_assign(struct qrtr_sock *ipc, int *port)
{
int rc;
if (!*port) {
rc = xa_alloc(&qrtr_ports, port, ipc, QRTR_EPH_PORT_RANGE,
GFP_KERNEL);
} else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) {
rc = -EACCES;
} else if (*port == QRTR_PORT_CTRL) {
rc = xa_insert(&qrtr_ports, 0, ipc, GFP_KERNEL);
} else {
rc = xa_insert(&qrtr_ports, *port, ipc, GFP_KERNEL);
}
if (rc == -EBUSY)
return -EADDRINUSE;
else if (rc < 0)
return rc;
sock_hold(&ipc->sk);
return 0;
}
/* Reset all non-control ports */
static void qrtr_reset_ports(void)
{
struct qrtr_sock *ipc;
unsigned long index;
rcu_read_lock();
xa_for_each_start(&qrtr_ports, index, ipc, 1) {
sock_hold(&ipc->sk);
ipc->sk.sk_err = ENETRESET;
sk_error_report(&ipc->sk);
sock_put(&ipc->sk);
}
rcu_read_unlock();
}
/* Bind socket to address.
*
* Socket should be locked upon call.
*/
static int __qrtr_bind(struct socket *sock,
const struct sockaddr_qrtr *addr, int zapped)
{
struct qrtr_sock *ipc = qrtr_sk(sock->sk);
struct sock *sk = sock->sk;
int port;
int rc;
/* rebinding ok */
if (!zapped && addr->sq_port == ipc->us.sq_port)
return 0;
port = addr->sq_port;
rc = qrtr_port_assign(ipc, &port);
if (rc)
return rc;
/* unbind previous, if any */
if (!zapped)
qrtr_port_remove(ipc);
ipc->us.sq_port = port;
sock_reset_flag(sk, SOCK_ZAPPED);
/* Notify all open ports about the new controller */
if (port == QRTR_PORT_CTRL)
qrtr_reset_ports();
return 0;
}
/* Auto bind to an ephemeral port. */
static int qrtr_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct sockaddr_qrtr addr;
if (!sock_flag(sk, SOCK_ZAPPED))
return 0;
addr.sq_family = AF_QIPCRTR;
addr.sq_node = qrtr_local_nid;
addr.sq_port = 0;
return __qrtr_bind(sock, &addr, 1);
}
/* Bind socket to specified sockaddr. */
static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, saddr);
struct qrtr_sock *ipc = qrtr_sk(sock->sk);
struct sock *sk = sock->sk;
int rc;
if (len < sizeof(*addr) || addr->sq_family != AF_QIPCRTR)
return -EINVAL;
if (addr->sq_node != ipc->us.sq_node)
return -EINVAL;
lock_sock(sk);
rc = __qrtr_bind(sock, addr, sock_flag(sk, SOCK_ZAPPED));
release_sock(sk);
return rc;
}
/* Queue packet to local peer socket. */
static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to)
{
struct qrtr_sock *ipc;
struct qrtr_cb *cb;
ipc = qrtr_port_lookup(to->sq_port);
if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */
if (ipc)
qrtr_port_put(ipc);
kfree_skb(skb);
return -ENODEV;
}
cb = (struct qrtr_cb *)skb->cb;
cb->src_node = from->sq_node;
cb->src_port = from->sq_port;
if (sock_queue_rcv_skb(&ipc->sk, skb)) {
qrtr_port_put(ipc);
kfree_skb(skb);
return -ENOSPC;
}
qrtr_port_put(ipc);
return 0;
}
/* Queue packet for broadcast. */
static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to)
{
struct sk_buff *skbn;
mutex_lock(&qrtr_node_lock);
list_for_each_entry(node, &qrtr_all_nodes, item) {
skbn = skb_clone(skb, GFP_KERNEL);
if (!skbn)
break;
skb_set_owner_w(skbn, skb->sk);
qrtr_node_enqueue(node, skbn, type, from, to);
}
mutex_unlock(&qrtr_node_lock);
qrtr_local_enqueue(NULL, skb, type, from, to);
return 0;
}
static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name);
int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *, int,
struct sockaddr_qrtr *, struct sockaddr_qrtr *);
__le32 qrtr_type = cpu_to_le32(QRTR_TYPE_DATA);
struct qrtr_sock *ipc = qrtr_sk(sock->sk);
struct sock *sk = sock->sk;
struct qrtr_node *node;
struct sk_buff *skb;
size_t plen;
u32 type;
int rc;
if (msg->msg_flags & ~(MSG_DONTWAIT))
return -EINVAL;
if (len > 65535)
return -EMSGSIZE;
lock_sock(sk);
if (addr) {
if (msg->msg_namelen < sizeof(*addr)) {
release_sock(sk);
return -EINVAL;
}
if (addr->sq_family != AF_QIPCRTR) {
release_sock(sk);
return -EINVAL;
}
rc = qrtr_autobind(sock);
if (rc) {
release_sock(sk);
return rc;
}
} else if (sk->sk_state == TCP_ESTABLISHED) {
addr = &ipc->peer;
} else {
release_sock(sk);
return -ENOTCONN;
}
node = NULL;
if (addr->sq_node == QRTR_NODE_BCAST) {
if (addr->sq_port != QRTR_PORT_CTRL &&
qrtr_local_nid != QRTR_NODE_BCAST) {
release_sock(sk);
return -ENOTCONN;
}
enqueue_fn = qrtr_bcast_enqueue;
} else if (addr->sq_node == ipc->us.sq_node) {
enqueue_fn = qrtr_local_enqueue;
} else {
node = qrtr_node_lookup(addr->sq_node);
if (!node) {
release_sock(sk);
return -ECONNRESET;
}
enqueue_fn = qrtr_node_enqueue;
}
plen = (len + 3) & ~3;
skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE,
msg->msg_flags & MSG_DONTWAIT, &rc);
if (!skb) {
rc = -ENOMEM;
goto out_node;
}
skb_reserve(skb, QRTR_HDR_MAX_SIZE);
rc = memcpy_from_msg(skb_put(skb, len), msg, len);
if (rc) {
kfree_skb(skb);
goto out_node;
}
if (ipc->us.sq_port == QRTR_PORT_CTRL) {
if (len < 4) {
rc = -EINVAL;
kfree_skb(skb);
goto out_node;
}
/* control messages already require the type as 'command' */
skb_copy_bits(skb, 0, &qrtr_type, 4);
}
type = le32_to_cpu(qrtr_type);
rc = enqueue_fn(node, skb, type, &ipc->us, addr);
if (rc >= 0)
rc = len;
out_node:
qrtr_node_release(node);
release_sock(sk);
return rc;
}
static int qrtr_send_resume_tx(struct qrtr_cb *cb)
{
struct sockaddr_qrtr remote = { AF_QIPCRTR, cb->src_node, cb->src_port };
struct sockaddr_qrtr local = { AF_QIPCRTR, cb->dst_node, cb->dst_port };
struct qrtr_ctrl_pkt *pkt;
struct qrtr_node *node;
struct sk_buff *skb;
int ret;
node = qrtr_node_lookup(remote.sq_node);
if (!node)