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
|
/*
* Copyright (C) 2017 Netronome Systems, Inc.
*
* This software is licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
* source tree.
*
* THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
* WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
* BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
* OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
* THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
*/
#include <linux/debugfs.h>
#include <linux/etherdevice.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/netdev_queues.h>
#include <net/page_pool/helpers.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
#include <net/rtnetlink.h>
#include <net/udp_tunnel.h>
#include "netdevsim.h"
static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct netdevsim *ns = netdev_priv(dev);
unsigned int len = skb->len;
struct netdevsim *peer_ns;
rcu_read_lock();
if (!nsim_ipsec_tx(ns, skb))
goto out_drop_free;
peer_ns = rcu_dereference(ns->peer);
if (!peer_ns)
goto out_drop_free;
skb_tx_timestamp(skb);
if (unlikely(dev_forward_skb(peer_ns->netdev, skb) == NET_RX_DROP))
goto out_drop_cnt;
rcu_read_unlock();
u64_stats_update_begin(&ns->syncp);
ns->tx_packets++;
ns->tx_bytes += len;
u64_stats_update_end(&ns->syncp);
return NETDEV_TX_OK;
out_drop_free:
dev_kfree_skb(skb);
out_drop_cnt:
rcu_read_unlock();
u64_stats_update_begin(&ns->syncp);
ns->tx_dropped++;
u64_stats_update_end(&ns->syncp);
return NETDEV_TX_OK;
}
static void nsim_set_rx_mode(struct net_device *dev)
{
}
static int nsim_change_mtu(struct net_device *dev, int new_mtu)
{
struct netdevsim *ns = netdev_priv(dev);
if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
return -EBUSY;
WRITE_ONCE(dev->mtu, new_mtu);
return 0;
}
static void
nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
struct netdevsim *ns = netdev_priv(dev);
unsigned int start;
do {
start = u64_stats_fetch_begin(&ns->syncp);
stats->tx_bytes = ns->tx_bytes;
stats->tx_packets = ns->tx_packets;
stats->tx_dropped = ns->tx_dropped;
} while (u64_stats_fetch_retry(&ns->syncp, start));
}
static int
nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
{
return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
}
static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
/* Only refuse multicast addresses, zero address can mean unset/any. */
if (vf >= nsim_dev_get_vfs(nsim_dev) || is_multicast_ether_addr(mac))
return -EINVAL;
memcpy(nsim_dev->vfconfigs[vf].vf_mac, mac, ETH_ALEN);
return 0;
}
static int nsim_set_vf_vlan(struct net_device *dev, int vf,
u16 vlan, u8 qos, __be16 vlan_proto)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev) || vlan > 4095 || qos > 7)
return -EINVAL;
nsim_dev->vfconfigs[vf].vlan = vlan;
nsim_dev->vfconfigs[vf].qos = qos;
nsim_dev->vfconfigs[vf].vlan_proto = vlan_proto;
return 0;
}
static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (nsim_esw_mode_is_switchdev(ns->nsim_dev)) {
pr_err("Not supported in switchdev mode. Please use devlink API.\n");
return -EOPNOTSUPP;
}
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
nsim_dev->vfconfigs[vf].min_tx_rate = min;
nsim_dev->vfconfigs[vf].max_tx_rate = max;
return 0;
}
static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
nsim_dev->vfconfigs[vf].spoofchk_enabled = val;
return 0;
}
static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
nsim_dev->vfconfigs[vf].rss_query_enabled = val;
return 0;
}
static int nsim_set_vf_trust(struct net_device *dev, int vf, bool val)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
nsim_dev->vfconfigs[vf].trusted = val;
return 0;
}
static int
nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
ivi->vf = vf;
ivi->linkstate = nsim_dev->vfconfigs[vf].link_state;
ivi->min_tx_rate = nsim_dev->vfconfigs[vf].min_tx_rate;
ivi->max_tx_rate = nsim_dev->vfconfigs[vf].max_tx_rate;
ivi->vlan = nsim_dev->vfconfigs[vf].vlan;
ivi->vlan_proto = nsim_dev->vfconfigs[vf].vlan_proto;
ivi->qos = nsim_dev->vfconfigs[vf].qos;
memcpy(&ivi->mac, nsim_dev->vfconfigs[vf].vf_mac, ETH_ALEN);
ivi->spoofchk = nsim_dev->vfconfigs[vf].spoofchk_enabled;
ivi->trusted = nsim_dev->vfconfigs[vf].trusted;
ivi->rss_query_en = nsim_dev->vfconfigs[vf].rss_query_enabled;
return 0;
}
static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_dev *nsim_dev = ns->nsim_dev;
if (vf >= nsim_dev_get_vfs(nsim_dev))
return -EINVAL;
switch (state) {
case IFLA_VF_LINK_STATE_AUTO:
case IFLA_VF_LINK_STATE_ENABLE:
case IFLA_VF_LINK_STATE_DISABLE:
break;
default:
return -EINVAL;
}
nsim_dev->vfconfigs[vf].link_state = state;
return 0;
}
static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats)
{
stats->window_drops = 0;
stats->tx_overruns = 0;
}
static int nsim_setup_tc_taprio(struct net_device *dev,
struct tc_taprio_qopt_offload *offload)
{
int err = 0;
switch (offload->cmd) {
case TAPRIO_CMD_REPLACE:
case TAPRIO_CMD_DESTROY:
break;
case TAPRIO_CMD_STATS:
nsim_taprio_stats(&offload->stats);
break;
default:
err = -EOPNOTSUPP;
}
return err;
}
static LIST_HEAD(nsim_block_cb_list);
static int
nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
{
struct netdevsim *ns = netdev_priv(dev);
switch (type) {
case TC_SETUP_QDISC_TAPRIO:
return nsim_setup_tc_taprio(dev, type_data);
case TC_SETUP_BLOCK:
return flow_block_cb_setup_simple(type_data,
&nsim_block_cb_list,
nsim_setup_tc_block_cb,
ns, ns, true);
default:
return -EOPNOTSUPP;
}
}
static int
nsim_set_features(struct net_device *dev, netdev_features_t features)
{
struct netdevsim *ns = netdev_priv(dev);
if ((dev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC))
return nsim_bpf_disable_tc(ns);
return 0;
}
static int nsim_get_iflink(const struct net_device *dev)
{
struct netdevsim *nsim, *peer;
int iflink;
nsim = netdev_priv(dev);
rcu_read_lock();
peer = rcu_dereference(nsim->peer);
iflink = peer ? READ_ONCE(peer->netdev->ifindex) : 0;
rcu_read_unlock();
return iflink;
}
static int nsim_open(struct net_device *dev)
{
struct netdevsim *ns = netdev_priv(dev);
struct page_pool_params pp = { 0 };
pp.pool_size = 128;
pp.dev = &dev->dev;
pp.dma_dir = DMA_BIDIRECTIONAL;
pp.netdev = dev;
ns->pp = page_pool_create(&pp);
return PTR_ERR_OR_ZERO(ns->pp);
}
static int nsim_stop(struct net_device *dev)
{
struct netdevsim *ns = netdev_priv(dev);
page_pool_destroy(ns->pp);
return 0;
}
static const struct net_device_ops nsim_netdev_ops = {
.ndo_start_xmit = nsim_start_xmit,
.ndo_set_rx_mode = nsim_set_rx_mode,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = nsim_change_mtu,
.ndo_get_stats64 = nsim_get_stats64,
.ndo_set_vf_mac = nsim_set_vf_mac,
.ndo_set_vf_vlan = nsim_set_vf_vlan,
.ndo_set_vf_rate = nsim_set_vf_rate,
.ndo_set_vf_spoofchk = nsim_set_vf_spoofchk,
.ndo_set_vf_trust = nsim_set_vf_trust,
.ndo_get_vf_config = nsim_get_vf_config,
.ndo_set_vf_link_state = nsim_set_vf_link_state,
.ndo_set_vf_rss_query_en = nsim_set_vf_rss_query_en,
.ndo_setup_tc = nsim_setup_tc,
.ndo_set_features = nsim_set_features,
.ndo_get_iflink = nsim_get_iflink,
.ndo_bpf = nsim_bpf,
.ndo_open = nsim_open,
.ndo_stop = nsim_stop,
};
static const struct net_device_ops nsim_vf_netdev_ops = {
.ndo_start_xmit = nsim_start_xmit,
.ndo_set_rx_mode = nsim_set_rx_mode,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = nsim_change_mtu,
.ndo_get_stats64 = nsim_get_stats64,
.ndo_setup_tc = nsim_setup_tc,
.ndo_set_features = nsim_set_features,
};
/* We don't have true per-queue stats, yet, so do some random fakery here.
* Only report stuff for queue 0.
*/
static void nsim_get_queue_stats_rx(struct net_device *dev, int idx,
struct netdev_queue_stats_rx *stats)
{
struct rtnl_link_stats64 rtstats = {};
if (!idx)
nsim_get_stats64(dev, &rtstats);
stats->packets = rtstats.rx_packets - !!rtstats.rx_packets;
stats->bytes = rtstats.rx_bytes;
}
static void nsim_get_queue_stats_tx(struct net_device *dev, int idx,
struct netdev_queue_stats_tx *stats)
{
struct rtnl_link_stats64 rtstats = {};
if (!idx)
nsim_get_stats64(dev, &rtstats);
stats->packets = rtstats.tx_packets - !!rtstats.tx_packets;
stats->bytes = rtstats.tx_bytes;
}
static void nsim_get_base_stats(struct net_device *dev,
struct netdev_queue_stats_rx *rx,
struct netdev_queue_stats_tx *tx)
{
struct rtnl_link_stats64 rtstats = {};
nsim_get_stats64(dev, &rtstats);
rx->packets = !!rtstats.rx_packets;
rx->bytes = 0;
tx->packets = !!rtstats.tx_packets;
tx->bytes = 0;
}
static const struct netdev_stat_ops nsim_stat_ops = {
.get_queue_stats_tx = nsim_get_queue_stats_tx,
.get_queue_stats_rx = nsim_get_queue_stats_rx,
.get_base_stats = nsim_get_base_stats,
};
static ssize_t
nsim_pp_hold_read(struct file *file, char __user *data,
size_t count, loff_t *ppos)
{
struct netdevsim *ns = file->private_data;
char buf[3] = "n\n";
if (ns->page)
buf[0] = 'y';
return simple_read_from_buffer(data, count, ppos, buf, 2);
}
static ssize_t
nsim_pp_hold_write(struct file *file, const char __user *data,
size_t count, loff_t *ppos)
{
struct netdevsim *ns = file->private_data;
ssize_t ret;
bool val;
ret = kstrtobool_from_user(data, count, &val);
if (ret)
return ret;
rtnl_lock();
ret = count;
if (val == !!ns->page)
goto exit;
if (!netif_running(ns->netdev) && val) {
ret = -ENETDOWN;
} else if (val) {
ns->page = page_pool_dev_alloc_pages(ns->pp);
if (!ns->page)
ret = -ENOMEM;
} else {
page_pool_put_full_page(ns->page->pp, ns->page, false);
ns->page = NULL;
}
rtnl_unlock();
exit:
return count;
}
static const struct file_operations nsim_pp_hold_fops = {
.open = simple_open,
.read = nsim_pp_hold_read,
.write = nsim_pp_hold_write,
.llseek = generic_file_llseek,
.owner = THIS_MODULE,
};
static void nsim_setup(struct net_device *dev)
{
ether_setup(dev);
eth_hw_addr_random(dev);
dev->tx_queue_len = 0;
dev->flags &= ~IFF_MULTICAST;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
IFF_NO_QUEUE;
dev->features |= NETIF_F_HIGHDMA |
NETIF_F_SG |
NETIF_F_FRAGLIST |
NETIF_F_HW_CSUM |
NETIF_F_TSO;
dev->hw_features |= NETIF_F_HW_TC;
dev->max_mtu = ETH_MAX_MTU;
dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
}
static int nsim_init_netdevsim(struct netdevsim *ns)
{
struct mock_phc *phc;
int err;
phc = mock_phc_create(&ns->nsim_bus_dev->dev);
if (IS_ERR(phc))
return PTR_ERR(phc);
ns->phc = phc;
ns->netdev->netdev_ops = &nsim_netdev_ops;
ns->netdev->stat_ops = &nsim_stat_ops;
err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev);
if (err)
goto err_phc_destroy;
rtnl_lock();
err = nsim_bpf_init(ns);
if (err)
goto err_utn_destroy;
nsim_macsec_init(ns);
nsim_ipsec_init(ns);
err = register_netdevice(ns->netdev);
if (err)
goto err_ipsec_teardown;
rtnl_unlock();
return 0;
err_ipsec_teardown:
nsim_ipsec_teardown(ns);
nsim_macsec_teardown(ns);
nsim_bpf_uninit(ns);
err_utn_destroy:
rtnl_unlock();
nsim_udp_tunnels_info_destroy(ns->netdev);
err_phc_destroy:
mock_phc_destroy(ns->phc);
return err;
}
static int nsim_init_netdevsim_vf(struct netdevsim *ns)
{
int err;
ns->netdev->netdev_ops = &nsim_vf_netdev_ops;
rtnl_lock();
err = register_netdevice(ns->netdev);
rtnl_unlock();
return err;
}
static void nsim_exit_netdevsim(struct netdevsim *ns)
{
nsim_udp_tunnels_info_destroy(ns->netdev);
mock_phc_destroy(ns->phc);
}
struct netdevsim *
nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
{
struct net_device *dev;
struct netdevsim *ns;
int err;
dev = alloc_netdev_mq(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup,
nsim_dev->nsim_bus_dev->num_queues);
if (!dev)
return ERR_PTR(-ENOMEM);
dev_net_set(dev, nsim_dev_net(nsim_dev));
ns = netdev_priv(dev);
ns->netdev = dev;
u64_stats_init(&ns->syncp);
ns->nsim_dev = nsim_dev;
ns->nsim_dev_port = nsim_dev_port;
ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;
SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev);
SET_NETDEV_DEVLINK_PORT(dev, &nsim_dev_port->devlink_port);
nsim_ethtool_init(ns);
if (nsim_dev_port_is_pf(nsim_dev_port))
err = nsim_init_netdevsim(ns);
else
err = nsim_init_netdevsim_vf(ns);
if (err)
goto err_free_netdev;
ns->pp_dfs = debugfs_create_file("pp_hold", 0600, nsim_dev_port->ddir,
ns, &nsim_pp_hold_fops);
return ns;
err_free_netdev:
free_netdev(dev);
return ERR_PTR(err);
}
void nsim_destroy(struct netdevsim *ns)
{
struct net_device *dev = ns->netdev;
struct netdevsim *peer;
debugfs_remove(ns->pp_dfs);
rtnl_lock();
peer = rtnl_dereference(ns->peer);
if (peer)
RCU_INIT_POINTER(peer->peer, NULL);
RCU_INIT_POINTER(ns->peer, NULL);
unregister_netdevice(dev);
if (nsim_dev_port_is_pf(ns->nsim_dev_port)) {
nsim_macsec_teardown(ns);
nsim_ipsec_teardown(ns);
nsim_bpf_uninit(ns);
}
rtnl_unlock();
if (nsim_dev_port_is_pf(ns->nsim_dev_port))
nsim_exit_netdevsim(ns);
/* Put this intentionally late to exercise the orphaning path */
if (ns->page) {
page_pool_put_full_page(ns->page->pp, ns->page, false);
ns->page = NULL;
}
free_netdev(dev);
}
bool netdev_is_nsim(struct net_device *dev)
{
return dev->netdev_ops == &nsim_netdev_ops;
}
static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
NL_SET_ERR_MSG_MOD(extack,
"Please use: echo \"[ID] [PORT_COUNT] [NUM_QUEUES]\" > /sys/bus/netdevsim/new_device");
return -EOPNOTSUPP;
}
static struct rtnl_link_ops nsim_link_ops __read_mostly = {
.kind = DRV_NAME,
.validate = nsim_validate,
};
static int __init nsim_module_init(void)
{
int err;
err = nsim_dev_init();
if (err)
return err;
err = nsim_bus_init();
if (err)
goto err_dev_exit;
err = rtnl_link_register(&nsim_link_ops);
if (err)
goto err_bus_exit;
return 0;
err_bus_exit:
nsim_bus_exit();
err_dev_exit:
nsim_dev_exit();
return err;
}
static void __exit nsim_module_exit(void)
{
rtnl_link_unregister(&nsim_link_ops);
nsim_bus_exit();
nsim_dev_exit();
}
module_init(nsim_module_init);
module_exit(nsim_module_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Simulated networking device for testing");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);
|