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
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <net/switchdev.h>
#include "br_private.h"
static struct static_key_false br_switchdev_tx_fwd_offload;
static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p,
const struct sk_buff *skb)
{
if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload))
return false;
return (p->flags & BR_TX_FWD_OFFLOAD) &&
(p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom);
}
bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb)
{
if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload))
return false;
return BR_INPUT_SKB_CB(skb)->tx_fwd_offload;
}
void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb)
{
skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb);
}
/* Mark the frame for TX forwarding offload if this egress port supports it */
void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p,
struct sk_buff *skb)
{
if (nbp_switchdev_can_offload_tx_fwd(p, skb))
BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true;
}
/* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms
* that the skb has been already forwarded to, to avoid further cloning to
* other ports in the same hwdom by making nbp_switchdev_allowed_egress()
* return false.
*/
void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p,
struct sk_buff *skb)
{
if (nbp_switchdev_can_offload_tx_fwd(p, skb))
set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms);
}
void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
struct sk_buff *skb)
{
if (p->hwdom)
BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom;
}
bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
const struct sk_buff *skb)
{
struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb);
return !test_bit(p->hwdom, &cb->fwd_hwdoms) &&
(!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom);
}
/* Flags that can be offloaded to hardware */
#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \
BR_MCAST_FLOOD | BR_BCAST_FLOOD)
int br_switchdev_set_port_flag(struct net_bridge_port *p,
unsigned long flags,
unsigned long mask,
struct netlink_ext_ack *extack)
{
struct switchdev_attr attr = {
.orig_dev = p->dev,
};
struct switchdev_notifier_port_attr_info info = {
.attr = &attr,
};
int err;
mask &= BR_PORT_FLAGS_HW_OFFLOAD;
if (!mask)
return 0;
attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS;
attr.u.brport_flags.val = flags;
attr.u.brport_flags.mask = mask;
/* We run from atomic context here */
err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev,
&info.info, extack);
err = notifier_to_errno(err);
if (err == -EOPNOTSUPP)
return 0;
if (err) {
if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"bridge flag offload is not supported");
return -EOPNOTSUPP;
}
attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
attr.flags = SWITCHDEV_F_DEFER;
err = switchdev_port_attr_set(p->dev, &attr, extack);
if (err) {
if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"error setting offload flag on port");
return err;
}
return 0;
}
static void br_switchdev_fdb_populate(struct net_bridge *br,
struct switchdev_notifier_fdb_info *item,
const struct net_bridge_fdb_entry *fdb,
const void *ctx)
{
const struct net_bridge_port *p = READ_ONCE(fdb->dst);
item->addr = fdb->key.addr.addr;
item->vid = fdb->key.vlan_id;
item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags);
item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags);
item->info.dev = (!p || item->is_local) ? br->dev : p->dev;
item->info.ctx = ctx;
}
void
br_switchdev_fdb_notify(struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb, int type)
{
struct switchdev_notifier_fdb_info item;
br_switchdev_fdb_populate(br, &item, fdb, NULL);
switch (type) {
case RTM_DELNEIGH:
call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE,
item.info.dev, &item.info, NULL);
break;
case RTM_NEWNEIGH:
call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE,
item.info.dev, &item.info, NULL);
break;
}
}
int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
struct netlink_ext_ack *extack)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = dev,
.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.flags = flags,
.vid = vid,
};
return switchdev_port_obj_add(dev, &v.obj, extack);
}
int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = dev,
.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.vid = vid,
};
return switchdev_port_obj_del(dev, &v.obj);
}
static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining)
{
struct net_bridge *br = joining->br;
struct net_bridge_port *p;
int hwdom;
/* joining is yet to be added to the port list. */
list_for_each_entry(p, &br->port_list, list) {
if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) {
joining->hwdom = p->hwdom;
return 0;
}
}
hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1);
if (hwdom >= BR_HWDOM_MAX)
return -EBUSY;
set_bit(hwdom, &br->busy_hwdoms);
joining->hwdom = hwdom;
return 0;
}
static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving)
{
struct net_bridge *br = leaving->br;
struct net_bridge_port *p;
/* leaving is no longer in the port list. */
list_for_each_entry(p, &br->port_list, list) {
if (p->hwdom == leaving->hwdom)
return;
}
clear_bit(leaving->hwdom, &br->busy_hwdoms);
}
static int nbp_switchdev_add(struct net_bridge_port *p,
struct netdev_phys_item_id ppid,
bool tx_fwd_offload,
struct netlink_ext_ack *extack)
{
int err;
if (p->offload_count) {
/* Prevent unsupported configurations such as a bridge port
* which is a bonding interface, and the member ports are from
* different hardware switches.
*/
if (!netdev_phys_item_id_same(&p->ppid, &ppid)) {
NL_SET_ERR_MSG_MOD(extack,
"Same bridge port cannot be offloaded by two physical switches");
return -EBUSY;
}
/* Tolerate drivers that call switchdev_bridge_port_offload()
* more than once for the same bridge port, such as when the
* bridge port is an offloaded bonding/team interface.
*/
p->offload_count++;
return 0;
}
p->ppid = ppid;
p->offload_count = 1;
err = nbp_switchdev_hwdom_set(p);
if (err)
return err;
if (tx_fwd_offload) {
p->flags |= BR_TX_FWD_OFFLOAD;
static_branch_inc(&br_switchdev_tx_fwd_offload);
}
return 0;
}
static void nbp_switchdev_del(struct net_bridge_port *p)
{
if (WARN_ON(!p->offload_count))
return;
p->offload_count--;
if (p->offload_count)
return;
if (p->hwdom)
nbp_switchdev_hwdom_put(p);
if (p->flags & BR_TX_FWD_OFFLOAD) {
p->flags &= ~BR_TX_FWD_OFFLOAD;
static_branch_dec(&br_switchdev_tx_fwd_offload);
}
}
static int br_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb,
const struct net_bridge_fdb_entry *fdb,
unsigned long action, const void *ctx)
{
struct switchdev_notifier_fdb_info item;
int err;
br_switchdev_fdb_populate(br, &item, fdb, ctx);
err = nb->notifier_call(nb, action, &item);
return notifier_to_errno(err);
}
static int br_fdb_replay(const struct net_device *br_dev, const void *ctx,
bool adding, struct notifier_block *nb)
{
struct net_bridge_fdb_entry *fdb;
struct net_bridge *br;
unsigned long action;
int err = 0;
if (!nb)
return 0;
if (!netif_is_bridge_master(br_dev))
return -EINVAL;
br = netdev_priv(br_dev);
if (adding)
action = SWITCHDEV_FDB_ADD_TO_DEVICE;
else
action = SWITCHDEV_FDB_DEL_TO_DEVICE;
rcu_read_lock();
hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) {
err = br_fdb_replay_one(br, nb, fdb, action, ctx);
if (err)
break;
}
rcu_read_unlock();
return err;
}
static int br_vlan_replay_one(struct notifier_block *nb,
struct net_device *dev,
struct switchdev_obj_port_vlan *vlan,
const void *ctx, unsigned long action,
struct netlink_ext_ack *extack)
{
struct switchdev_notifier_port_obj_info obj_info = {
.info = {
.dev = dev,
.extack = extack,
.ctx = ctx,
},
.obj = &vlan->obj,
};
int err;
err = nb->notifier_call(nb, action, &obj_info);
return notifier_to_errno(err);
}
static int br_vlan_replay(struct net_device *br_dev, struct net_device *dev,
const void *ctx, bool adding,
struct notifier_block *nb,
struct netlink_ext_ack *extack)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
struct net_bridge_port *p;
struct net_bridge *br;
unsigned long action;
int err = 0;
u16 pvid;
ASSERT_RTNL();
if (!nb)
return 0;
if (!netif_is_bridge_master(br_dev))
return -EINVAL;
if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev))
return -EINVAL;
if (netif_is_bridge_master(dev)) {
br = netdev_priv(dev);
vg = br_vlan_group(br);
p = NULL;
} else {
p = br_port_get_rtnl(dev);
if (WARN_ON(!p))
return -EINVAL;
vg = nbp_vlan_group(p);
br = p->br;
}
if (!vg)
return 0;
if (adding)
action = SWITCHDEV_PORT_OBJ_ADD;
else
action = SWITCHDEV_PORT_OBJ_DEL;
pvid = br_get_pvid(vg);
list_for_each_entry(v, &vg->vlan_list, vlist) {
struct switchdev_obj_port_vlan vlan = {
.obj.orig_dev = dev,
.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.flags = br_vlan_flags(v, pvid),
.vid = v->vid,
};
if (!br_vlan_should_use(v))
continue;
err = br_vlan_replay_one(nb, dev, &vlan, ctx, action, extack);
if (err)
return err;
}
return err;
}
static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
struct notifier_block *atomic_nb,
struct notifier_block *blocking_nb,
struct netlink_ext_ack *extack)
{
struct net_device *br_dev = p->br->dev;
struct net_device *dev = p->dev;
int err;
err = br_vlan_replay(br_dev, dev, ctx, true, blocking_nb, extack);
if (err && err != -EOPNOTSUPP)
return err;
err = br_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack);
if (err && err != -EOPNOTSUPP)
return err;
err = br_fdb_replay(br_dev, ctx, true, atomic_nb);
if (err && err != -EOPNOTSUPP)
return err;
return 0;
}
static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
const void *ctx,
struct notifier_block *atomic_nb,
struct notifier_block *blocking_nb)
{
struct net_device *br_dev = p->br->dev;
struct net_device *dev = p->dev;
br_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
br_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
br_fdb_replay(br_dev, ctx, false, atomic_nb);
}
/* Let the bridge know that this port is offloaded, so that it can assign a
* switchdev hardware domain to it.
*/
int br_switchdev_port_offload(struct net_bridge_port *p,
struct net_device *dev, const void *ctx,
struct notifier_block *atomic_nb,
struct notifier_block *blocking_nb,
bool tx_fwd_offload,
struct netlink_ext_ack *extack)
{
struct netdev_phys_item_id ppid;
int err;
err = dev_get_port_parent_id(dev, &ppid, false);
if (err)
return err;
err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack);
if (err)
return err;
err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack);
if (err)
goto out_switchdev_del;
return 0;
out_switchdev_del:
nbp_switchdev_del(p);
return err;
}
void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
struct notifier_block *atomic_nb,
struct notifier_block *blocking_nb)
{
nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb);
nbp_switchdev_del(p);
}
|