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
|
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
*/
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/netdevice.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <net/udp_tunnel.h>
#include <net/sch_generic.h>
#include <linux/netfilter.h>
#include <rdma/ib_addr.h>
#include "rxe.h"
#include "rxe_net.h"
#include "rxe_loc.h"
static struct rxe_recv_sockets recv_sockets;
static struct dst_entry *rxe_find_route4(struct rxe_qp *qp,
struct net_device *ndev,
struct in_addr *saddr,
struct in_addr *daddr)
{
struct rtable *rt;
struct flowi4 fl = { { 0 } };
memset(&fl, 0, sizeof(fl));
fl.flowi4_oif = ndev->ifindex;
memcpy(&fl.saddr, saddr, sizeof(*saddr));
memcpy(&fl.daddr, daddr, sizeof(*daddr));
fl.flowi4_proto = IPPROTO_UDP;
rt = ip_route_output_key(&init_net, &fl);
if (IS_ERR(rt)) {
rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr);
return NULL;
}
return &rt->dst;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
struct net_device *ndev,
struct in6_addr *saddr,
struct in6_addr *daddr)
{
struct dst_entry *ndst;
struct flowi6 fl6 = { { 0 } };
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = ndev->ifindex;
memcpy(&fl6.saddr, saddr, sizeof(*saddr));
memcpy(&fl6.daddr, daddr, sizeof(*daddr));
fl6.flowi6_proto = IPPROTO_UDP;
ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk),
recv_sockets.sk6->sk, &fl6,
NULL);
if (IS_ERR(ndst)) {
rxe_dbg_qp(qp, "no route to %pI6\n", daddr);
return NULL;
}
if (unlikely(ndst->error)) {
rxe_dbg_qp(qp, "no route to %pI6\n", daddr);
goto put;
}
return ndst;
put:
dst_release(ndst);
return NULL;
}
#else
static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
struct net_device *ndev,
struct in6_addr *saddr,
struct in6_addr *daddr)
{
return NULL;
}
#endif
static struct dst_entry *rxe_find_route(struct net_device *ndev,
struct rxe_qp *qp,
struct rxe_av *av)
{
struct dst_entry *dst = NULL;
if (qp_type(qp) == IB_QPT_RC)
dst = sk_dst_get(qp->sk->sk);
if (!dst || !dst_check(dst, qp->dst_cookie)) {
if (dst)
dst_release(dst);
if (av->network_type == RXE_NETWORK_TYPE_IPV4) {
struct in_addr *saddr;
struct in_addr *daddr;
saddr = &av->sgid_addr._sockaddr_in.sin_addr;
daddr = &av->dgid_addr._sockaddr_in.sin_addr;
dst = rxe_find_route4(qp, ndev, saddr, daddr);
} else if (av->network_type == RXE_NETWORK_TYPE_IPV6) {
struct in6_addr *saddr6;
struct in6_addr *daddr6;
saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr;
daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr;
dst = rxe_find_route6(qp, ndev, saddr6, daddr6);
#if IS_ENABLED(CONFIG_IPV6)
if (dst)
qp->dst_cookie =
rt6_get_cookie((struct rt6_info *)dst);
#endif
}
if (dst && (qp_type(qp) == IB_QPT_RC)) {
dst_hold(dst);
sk_dst_set(qp->sk->sk, dst);
}
}
return dst;
}
static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct udphdr *udph;
struct rxe_dev *rxe;
struct net_device *ndev = skb->dev;
struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
/* takes a reference on rxe->ib_dev
* drop when skb is freed
*/
rxe = rxe_get_dev_from_net(ndev);
if (!rxe && is_vlan_dev(ndev))
rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
if (!rxe)
goto drop;
if (skb_linearize(skb)) {
ib_device_put(&rxe->ib_dev);
goto drop;
}
udph = udp_hdr(skb);
pkt->rxe = rxe;
pkt->port_num = 1;
pkt->hdr = (u8 *)(udph + 1);
pkt->mask = RXE_GRH_MASK;
pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph);
/* remove udp header */
skb_pull(skb, sizeof(struct udphdr));
rxe_rcv(skb);
return 0;
drop:
kfree_skb(skb);
return 0;
}
static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
bool ipv6)
{
int err;
struct socket *sock;
struct udp_port_cfg udp_cfg = { };
struct udp_tunnel_sock_cfg tnl_cfg = { };
if (ipv6) {
udp_cfg.family = AF_INET6;
udp_cfg.ipv6_v6only = 1;
} else {
udp_cfg.family = AF_INET;
}
udp_cfg.local_udp_port = port;
/* Create UDP socket */
err = udp_sock_create(net, &udp_cfg, &sock);
if (err < 0)
return ERR_PTR(err);
tnl_cfg.encap_type = 1;
tnl_cfg.encap_rcv = rxe_udp_encap_recv;
/* Setup UDP tunnel */
setup_udp_tunnel_sock(net, sock, &tnl_cfg);
return sock;
}
static void rxe_release_udp_tunnel(struct socket *sk)
{
if (sk)
udp_tunnel_sock_release(sk);
}
static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port,
__be16 dst_port)
{
struct udphdr *udph;
__skb_push(skb, sizeof(*udph));
skb_reset_transport_header(skb);
udph = udp_hdr(skb);
udph->dest = dst_port;
udph->source = src_port;
udph->len = htons(skb->len);
udph->check = 0;
}
static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb,
__be32 saddr, __be32 daddr, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
struct iphdr *iph;
skb_scrub_packet(skb, xnet);
skb_clear_hash(skb);
skb_dst_set(skb, dst_clone(dst));
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = IPVERSION;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->tot_len = htons(skb->len);
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = daddr;
iph->saddr = saddr;
iph->ttl = ttl;
__ip_select_ident(dev_net(dst->dev), iph,
skb_shinfo(skb)->gso_segs ?: 1);
}
static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
struct in6_addr *saddr, struct in6_addr *daddr,
__u8 proto, __u8 prio, __u8 ttl)
{
struct ipv6hdr *ip6h;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
| IPSKB_REROUTED);
skb_dst_set(skb, dst_clone(dst));
__skb_push(skb, sizeof(*ip6h));
skb_reset_network_header(skb);
ip6h = ipv6_hdr(skb);
ip6_flow_hdr(ip6h, prio, htonl(0));
ip6h->payload_len = htons(skb->len);
ip6h->nexthdr = proto;
ip6h->hop_limit = ttl;
ip6h->daddr = *daddr;
ip6h->saddr = *saddr;
ip6h->payload_len = htons(skb->len - sizeof(*ip6h));
}
static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt,
struct sk_buff *skb)
{
struct rxe_qp *qp = pkt->qp;
struct dst_entry *dst;
bool xnet = false;
__be16 df = htons(IP_DF);
struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr;
struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr;
dst = rxe_find_route(skb->dev, qp, av);
if (!dst) {
rxe_dbg_qp(qp, "Host not reachable\n");
return -EHOSTUNREACH;
}
prepare_udp_hdr(skb, cpu_to_be16(qp->src_port),
cpu_to_be16(ROCE_V2_UDP_DPORT));
prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP,
av->grh.traffic_class, av->grh.hop_limit, df, xnet);
dst_release(dst);
return 0;
}
static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt,
struct sk_buff *skb)
{
struct rxe_qp *qp = pkt->qp;
struct dst_entry *dst;
struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr;
struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr;
dst = rxe_find_route(skb->dev, qp, av);
if (!dst) {
rxe_dbg_qp(qp, "Host not reachable\n");
return -EHOSTUNREACH;
}
prepare_udp_hdr(skb, cpu_to_be16(qp->src_port),
cpu_to_be16(ROCE_V2_UDP_DPORT));
prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP,
av->grh.traffic_class,
av->grh.hop_limit);
dst_release(dst);
return 0;
}
int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt,
struct sk_buff *skb)
{
int err = 0;
if (skb->protocol == htons(ETH_P_IP))
err = prepare4(av, pkt, skb);
else if (skb->protocol == htons(ETH_P_IPV6))
err = prepare6(av, pkt, skb);
if (ether_addr_equal(skb->dev->dev_addr, av->dmac))
pkt->mask |= RXE_LOOPBACK_MASK;
return err;
}
static void rxe_skb_tx_dtor(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct rxe_qp *qp = sk->sk_user_data;
int skb_out = atomic_dec_return(&qp->skb_out);
if (unlikely(qp->need_req_skb &&
skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
rxe_sched_task(&qp->send_task);
rxe_put(qp);
}
static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
{
int err;
skb->destructor = rxe_skb_tx_dtor;
skb->sk = pkt->qp->sk->sk;
rxe_get(pkt->qp);
atomic_inc(&pkt->qp->skb_out);
if (skb->protocol == htons(ETH_P_IP)) {
err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
} else {
rxe_dbg_qp(pkt->qp, "Unknown layer 3 protocol: %d\n",
skb->protocol);
atomic_dec(&pkt->qp->skb_out);
rxe_put(pkt->qp);
kfree_skb(skb);
return -EINVAL;
}
if (unlikely(net_xmit_eval(err))) {
rxe_dbg_qp(pkt->qp, "error sending packet: %d\n", err);
return -EAGAIN;
}
return 0;
}
/* fix up a send packet to match the packets
* received from UDP before looping them back
*/
static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
{
memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));
if (skb->protocol == htons(ETH_P_IP))
skb_pull(skb, sizeof(struct iphdr));
else
skb_pull(skb, sizeof(struct ipv6hdr));
if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) {
kfree_skb(skb);
return -EIO;
}
/* remove udp header */
skb_pull(skb, sizeof(struct udphdr));
rxe_rcv(skb);
return 0;
}
int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
struct sk_buff *skb)
{
int err;
int is_request = pkt->mask & RXE_REQ_MASK;
struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
unsigned long flags;
spin_lock_irqsave(&qp->state_lock, flags);
if ((is_request && (qp_state(qp) < IB_QPS_RTS)) ||
(!is_request && (qp_state(qp) < IB_QPS_RTR))) {
spin_unlock_irqrestore(&qp->state_lock, flags);
rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n");
goto drop;
}
spin_unlock_irqrestore(&qp->state_lock, flags);
rxe_icrc_generate(skb, pkt);
if (pkt->mask & RXE_LOOPBACK_MASK)
err = rxe_loopback(skb, pkt);
else
err = rxe_send(skb, pkt);
if (err) {
rxe_counter_inc(rxe, RXE_CNT_SEND_ERR);
return err;
}
if ((qp_type(qp) != IB_QPT_RC) &&
(pkt->mask & RXE_END_MASK)) {
pkt->wqe->state = wqe_state_done;
rxe_sched_task(&qp->send_task);
}
rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS);
goto done;
drop:
kfree_skb(skb);
err = 0;
done:
return err;
}
struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
int paylen, struct rxe_pkt_info *pkt)
{
unsigned int hdr_len;
struct sk_buff *skb = NULL;
struct net_device *ndev;
const struct ib_gid_attr *attr;
const int port_num = 1;
attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index);
if (IS_ERR(attr))
return NULL;
if (av->network_type == RXE_NETWORK_TYPE_IPV4)
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
sizeof(struct iphdr);
else
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
sizeof(struct ipv6hdr);
rcu_read_lock();
ndev = rdma_read_gid_attr_ndev_rcu(attr);
if (IS_ERR(ndev)) {
rcu_read_unlock();
goto out;
}
skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev),
GFP_ATOMIC);
if (unlikely(!skb)) {
rcu_read_unlock();
goto out;
}
skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev));
/* FIXME: hold reference to this netdev until life of this skb. */
skb->dev = ndev;
rcu_read_unlock();
if (av->network_type == RXE_NETWORK_TYPE_IPV4)
skb->protocol = htons(ETH_P_IP);
else
skb->protocol = htons(ETH_P_IPV6);
pkt->rxe = rxe;
pkt->port_num = port_num;
pkt->hdr = skb_put(skb, paylen);
pkt->mask |= RXE_GRH_MASK;
out:
rdma_put_gid_attr(attr);
return skb;
}
/*
* this is required by rxe_cfg to match rxe devices in
* /sys/class/infiniband up with their underlying ethernet devices
*/
const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num)
{
return rxe->ndev->name;
}
int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
{
int err;
struct rxe_dev *rxe = NULL;
rxe = ib_alloc_device(rxe_dev, ib_dev);
if (!rxe)
return -ENOMEM;
rxe->ndev = ndev;
err = rxe_add(rxe, ndev->mtu, ibdev_name);
if (err) {
ib_dealloc_device(&rxe->ib_dev);
return err;
}
return 0;
}
static void rxe_port_event(struct rxe_dev *rxe,
enum ib_event_type event)
{
struct ib_event ev;
ev.device = &rxe->ib_dev;
ev.element.port_num = 1;
ev.event = event;
ib_dispatch_event(&ev);
}
/* Caller must hold net_info_lock */
void rxe_port_up(struct rxe_dev *rxe)
{
struct rxe_port *port;
port = &rxe->port;
port->attr.state = IB_PORT_ACTIVE;
rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE);
dev_info(&rxe->ib_dev.dev, "set active\n");
}
/* Caller must hold net_info_lock */
void rxe_port_down(struct rxe_dev *rxe)
{
struct rxe_port *port;
port = &rxe->port;
port->attr.state = IB_PORT_DOWN;
rxe_port_event(rxe, IB_EVENT_PORT_ERR);
rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED);
dev_info(&rxe->ib_dev.dev, "set down\n");
}
void rxe_set_port_state(struct rxe_dev *rxe)
{
if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev))
rxe_port_up(rxe);
else
rxe_port_down(rxe);
}
static int rxe_notify(struct notifier_block *not_blk,
unsigned long event,
void *arg)
{
struct net_device *ndev = netdev_notifier_info_to_dev(arg);
struct rxe_dev *rxe = rxe_get_dev_from_net(ndev);
if (!rxe)
return NOTIFY_OK;
switch (event) {
case NETDEV_UNREGISTER:
ib_unregister_device_queued(&rxe->ib_dev);
break;
case NETDEV_UP:
rxe_port_up(rxe);
break;
case NETDEV_DOWN:
rxe_port_down(rxe);
break;
case NETDEV_CHANGEMTU:
rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu);
rxe_set_mtu(rxe, ndev->mtu);
break;
case NETDEV_CHANGE:
rxe_set_port_state(rxe);
break;
case NETDEV_REBOOT:
case NETDEV_GOING_DOWN:
case NETDEV_CHANGEADDR:
case NETDEV_CHANGENAME:
case NETDEV_FEAT_CHANGE:
default:
rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n",
event, ndev->name);
break;
}
ib_device_put(&rxe->ib_dev);
return NOTIFY_OK;
}
static struct notifier_block rxe_net_notifier = {
.notifier_call = rxe_notify,
};
static int rxe_net_ipv4_init(void)
{
recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
htons(ROCE_V2_UDP_DPORT), false);
if (IS_ERR(recv_sockets.sk4)) {
recv_sockets.sk4 = NULL;
pr_err("Failed to create IPv4 UDP tunnel\n");
return -1;
}
return 0;
}
static int rxe_net_ipv6_init(void)
{
#if IS_ENABLED(CONFIG_IPV6)
recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
htons(ROCE_V2_UDP_DPORT), true);
if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) {
recv_sockets.sk6 = NULL;
pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n");
return 0;
}
if (IS_ERR(recv_sockets.sk6)) {
recv_sockets.sk6 = NULL;
pr_err("Failed to create IPv6 UDP tunnel\n");
return -1;
}
#endif
return 0;
}
void rxe_net_exit(void)
{
rxe_release_udp_tunnel(recv_sockets.sk6);
rxe_release_udp_tunnel(recv_sockets.sk4);
unregister_netdevice_notifier(&rxe_net_notifier);
}
int rxe_net_init(void)
{
int err;
recv_sockets.sk6 = NULL;
err = rxe_net_ipv4_init();
if (err)
return err;
err = rxe_net_ipv6_init();
if (err)
goto err_out;
err = register_netdevice_notifier(&rxe_net_notifier);
if (err) {
pr_err("Failed to register netdev notifier\n");
goto err_out;
}
return 0;
err_out:
rxe_net_exit();
return err;
}
|