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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Handling of a master device, switching frames via its switch fabric CPU port
*
* Copyright (c) 2017 Savoir-faire Linux Inc.
* Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*/
#include <linux/ethtool.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <net/dsa.h>
#include "dsa.h"
#include "master.h"
#include "port.h"
#include "tag.h"
static int dsa_master_get_regs_len(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int ret = 0;
int len;
if (ops->get_regs_len) {
len = ops->get_regs_len(dev);
if (len < 0)
return len;
ret += len;
}
ret += sizeof(struct ethtool_drvinfo);
ret += sizeof(struct ethtool_regs);
if (ds->ops->get_regs_len) {
len = ds->ops->get_regs_len(ds, port);
if (len < 0)
return len;
ret += len;
}
return ret;
}
static void dsa_master_get_regs(struct net_device *dev,
struct ethtool_regs *regs, void *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
struct ethtool_drvinfo *cpu_info;
struct ethtool_regs *cpu_regs;
int port = cpu_dp->index;
int len;
if (ops->get_regs_len && ops->get_regs) {
len = ops->get_regs_len(dev);
if (len < 0)
return;
regs->len = len;
ops->get_regs(dev, regs, data);
data += regs->len;
}
cpu_info = (struct ethtool_drvinfo *)data;
strscpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver));
data += sizeof(*cpu_info);
cpu_regs = (struct ethtool_regs *)data;
data += sizeof(*cpu_regs);
if (ds->ops->get_regs_len && ds->ops->get_regs) {
len = ds->ops->get_regs_len(ds, port);
if (len < 0)
return;
cpu_regs->len = len;
ds->ops->get_regs(ds, port, cpu_regs, data);
}
}
static void dsa_master_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats,
uint64_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int count = 0;
if (ops->get_sset_count && ops->get_ethtool_stats) {
count = ops->get_sset_count(dev, ETH_SS_STATS);
ops->get_ethtool_stats(dev, stats, data);
}
if (ds->ops->get_ethtool_stats)
ds->ops->get_ethtool_stats(ds, port, data + count);
}
static void dsa_master_get_ethtool_phy_stats(struct net_device *dev,
struct ethtool_stats *stats,
uint64_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int count = 0;
if (dev->phydev && !ops->get_ethtool_phy_stats) {
count = phy_ethtool_get_sset_count(dev->phydev);
if (count >= 0)
phy_ethtool_get_stats(dev->phydev, stats, data);
} else if (ops->get_sset_count && ops->get_ethtool_phy_stats) {
count = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
ops->get_ethtool_phy_stats(dev, stats, data);
}
if (count < 0)
count = 0;
if (ds->ops->get_ethtool_phy_stats)
ds->ops->get_ethtool_phy_stats(ds, port, data + count);
}
static int dsa_master_get_sset_count(struct net_device *dev, int sset)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int count = 0;
if (sset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats)
count = phy_ethtool_get_sset_count(dev->phydev);
else if (ops->get_sset_count)
count = ops->get_sset_count(dev, sset);
if (count < 0)
count = 0;
if (ds->ops->get_sset_count)
count += ds->ops->get_sset_count(ds, cpu_dp->index, sset);
return count;
}
static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
uint8_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int len = ETH_GSTRING_LEN;
int mcount = 0, count, i;
uint8_t pfx[4];
uint8_t *ndata;
snprintf(pfx, sizeof(pfx), "p%.2d", port);
/* We do not want to be NULL-terminated, since this is a prefix */
pfx[sizeof(pfx) - 1] = '_';
if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats) {
mcount = phy_ethtool_get_sset_count(dev->phydev);
if (mcount < 0)
mcount = 0;
else
phy_ethtool_get_strings(dev->phydev, data);
} else if (ops->get_sset_count && ops->get_strings) {
mcount = ops->get_sset_count(dev, stringset);
if (mcount < 0)
mcount = 0;
ops->get_strings(dev, stringset, data);
}
if (ds->ops->get_strings) {
ndata = data + mcount * len;
/* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
* the output after to prepend our CPU port prefix we
* constructed earlier
*/
ds->ops->get_strings(ds, port, stringset, ndata);
count = ds->ops->get_sset_count(ds, port, stringset);
if (count < 0)
return;
for (i = 0; i < count; i++) {
memmove(ndata + (i * len + sizeof(pfx)),
ndata + i * len, len - sizeof(pfx));
memcpy(ndata + i * len, pfx, sizeof(pfx));
}
}
}
static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct dsa_switch *ds = cpu_dp->ds;
struct dsa_switch_tree *dst;
int err = -EOPNOTSUPP;
struct dsa_port *dp;
dst = ds->dst;
switch (cmd) {
case SIOCGHWTSTAMP:
case SIOCSHWTSTAMP:
/* Deny PTP operations on master if there is at least one
* switch in the tree that is PTP capable.
*/
list_for_each_entry(dp, &dst->ports, list)
if (dsa_port_supports_hwtstamp(dp, ifr))
return -EBUSY;
break;
}
if (dev->netdev_ops->ndo_eth_ioctl)
err = dev->netdev_ops->ndo_eth_ioctl(dev, ifr, cmd);
return err;
}
static const struct dsa_netdevice_ops dsa_netdev_ops = {
.ndo_eth_ioctl = dsa_master_ioctl,
};
static int dsa_master_ethtool_setup(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct dsa_switch *ds = cpu_dp->ds;
struct ethtool_ops *ops;
if (netif_is_lag_master(dev))
return 0;
ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL);
if (!ops)
return -ENOMEM;
cpu_dp->orig_ethtool_ops = dev->ethtool_ops;
if (cpu_dp->orig_ethtool_ops)
memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops));
ops->get_regs_len = dsa_master_get_regs_len;
ops->get_regs = dsa_master_get_regs;
ops->get_sset_count = dsa_master_get_sset_count;
ops->get_ethtool_stats = dsa_master_get_ethtool_stats;
ops->get_strings = dsa_master_get_strings;
ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats;
dev->ethtool_ops = ops;
return 0;
}
static void dsa_master_ethtool_teardown(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
if (netif_is_lag_master(dev))
return;
dev->ethtool_ops = cpu_dp->orig_ethtool_ops;
cpu_dp->orig_ethtool_ops = NULL;
}
static void dsa_netdev_ops_set(struct net_device *dev,
const struct dsa_netdevice_ops *ops)
{
if (netif_is_lag_master(dev))
return;
dev->dsa_ptr->netdev_ops = ops;
}
/* Keep the master always promiscuous if the tagging protocol requires that
* (garbles MAC DA) or if it doesn't support unicast filtering, case in which
* it would revert to promiscuous mode as soon as we call dev_uc_add() on it
* anyway.
*/
static void dsa_master_set_promiscuity(struct net_device *dev, int inc)
{
const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops;
if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_master)
return;
ASSERT_RTNL();
dev_set_promiscuity(dev, inc);
}
static ssize_t tagging_show(struct device *d, struct device_attribute *attr,
char *buf)
{
struct net_device *dev = to_net_dev(d);
struct dsa_port *cpu_dp = dev->dsa_ptr;
return sysfs_emit(buf, "%s\n",
dsa_tag_protocol_to_str(cpu_dp->tag_ops));
}
static ssize_t tagging_store(struct device *d, struct device_attribute *attr,
const char *buf, size_t count)
{
const struct dsa_device_ops *new_tag_ops, *old_tag_ops;
const char *end = strchrnul(buf, '\n'), *name;
struct net_device *dev = to_net_dev(d);
struct dsa_port *cpu_dp = dev->dsa_ptr;
size_t len = end - buf;
int err;
/* Empty string passed */
if (!len)
return -ENOPROTOOPT;
name = kstrndup(buf, len, GFP_KERNEL);
if (!name)
return -ENOMEM;
old_tag_ops = cpu_dp->tag_ops;
new_tag_ops = dsa_tag_driver_get_by_name(name);
kfree(name);
/* Bad tagger name? */
if (IS_ERR(new_tag_ops))
return PTR_ERR(new_tag_ops);
if (new_tag_ops == old_tag_ops)
/* Drop the temporarily held duplicate reference, since
* the DSA switch tree uses this tagger.
*/
goto out;
err = dsa_tree_change_tag_proto(cpu_dp->ds->dst, new_tag_ops,
old_tag_ops);
if (err) {
/* On failure the old tagger is restored, so we don't need the
* driver for the new one.
*/
dsa_tag_driver_put(new_tag_ops);
return err;
}
/* On success we no longer need the module for the old tagging protocol
*/
out:
dsa_tag_driver_put(old_tag_ops);
return count;
}
static DEVICE_ATTR_RW(tagging);
static struct attribute *dsa_slave_attrs[] = {
&dev_attr_tagging.attr,
NULL
};
static const struct attribute_group dsa_group = {
.name = "dsa",
.attrs = dsa_slave_attrs,
};
static void dsa_master_reset_mtu(struct net_device *dev)
{
int err;
err = dev_set_mtu(dev, ETH_DATA_LEN);
if (err)
netdev_dbg(dev,
"Unable to reset MTU to exclude DSA overheads\n");
}
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
struct dsa_switch *ds = cpu_dp->ds;
struct device_link *consumer_link;
int mtu, ret;
mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
/* The DSA master must use SET_NETDEV_DEV for this to work. */
if (!netif_is_lag_master(dev)) {
consumer_link = device_link_add(ds->dev, dev->dev.parent,
DL_FLAG_AUTOREMOVE_CONSUMER);
if (!consumer_link)
netdev_err(dev,
"Failed to create a device link to DSA switch %s\n",
dev_name(ds->dev));
}
/* The switch driver may not implement ->port_change_mtu(), case in
* which dsa_slave_change_mtu() will not update the master MTU either,
* so we need to do that here.
*/
ret = dev_set_mtu(dev, mtu);
if (ret)
netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
ret, mtu);
/* If we use a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point on get
* sent to the tag format's receive function.
*/
wmb();
dev->dsa_ptr = cpu_dp;
dsa_master_set_promiscuity(dev, 1);
ret = dsa_master_ethtool_setup(dev);
if (ret)
goto out_err_reset_promisc;
dsa_netdev_ops_set(dev, &dsa_netdev_ops);
ret = sysfs_create_group(&dev->dev.kobj, &dsa_group);
if (ret)
goto out_err_ndo_teardown;
return ret;
out_err_ndo_teardown:
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
out_err_reset_promisc:
dsa_master_set_promiscuity(dev, -1);
return ret;
}
void dsa_master_teardown(struct net_device *dev)
{
sysfs_remove_group(&dev->dev.kobj, &dsa_group);
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
dsa_master_reset_mtu(dev);
dsa_master_set_promiscuity(dev, -1);
dev->dsa_ptr = NULL;
/* If we used a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point get sent
* without the tag and go through the regular receive path.
*/
wmb();
}
int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp,
struct netdev_lag_upper_info *uinfo,
struct netlink_ext_ack *extack)
{
bool master_setup = false;
int err;
if (!netdev_uses_dsa(lag_dev)) {
err = dsa_master_setup(lag_dev, cpu_dp);
if (err)
return err;
master_setup = true;
}
err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack);
if (err) {
NL_SET_ERR_MSG_WEAK_MOD(extack, "CPU port failed to join LAG");
goto out_master_teardown;
}
return 0;
out_master_teardown:
if (master_setup)
dsa_master_teardown(lag_dev);
return err;
}
/* Tear down a master if there isn't any other user port on it,
* optionally also destroying LAG information.
*/
void dsa_master_lag_teardown(struct net_device *lag_dev,
struct dsa_port *cpu_dp)
{
struct net_device *upper;
struct list_head *iter;
dsa_port_lag_leave(cpu_dp, lag_dev);
netdev_for_each_upper_dev_rcu(lag_dev, upper, iter)
if (dsa_slave_dev_check(upper))
return;
dsa_master_teardown(lag_dev);
}
|