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
|
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#include <linux/if_macvlan.h>
#include <linux/if_vlan.h>
#include <net/bareudp.h>
#include <net/bonding.h>
#include "act.h"
#include "vlan.h"
#include "en/tc_tun_encap.h"
#include "en/tc_priv.h"
#include "en_rep.h"
#include "lag/lag.h"
static bool
same_vf_reps(struct mlx5e_priv *priv, struct net_device *out_dev)
{
return mlx5e_eswitch_vf_rep(priv->netdev) &&
priv->netdev == out_dev;
}
static int
verify_uplink_forwarding(struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr,
struct net_device *out_dev,
struct netlink_ext_ack *extack)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_rep_priv *rep_priv;
/* Forwarding non encapsulated traffic between
* uplink ports is allowed only if
* termination_table_raw_traffic cap is set.
*
* Input vport was stored attr->in_rep.
* In LAG case, *priv* is the private data of
* uplink which may be not the input vport.
*/
rep_priv = mlx5e_rep_to_rep_priv(attr->esw_attr->in_rep);
if (!(mlx5e_eswitch_uplink_rep(rep_priv->netdev) &&
mlx5e_eswitch_uplink_rep(out_dev)))
return 0;
if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev,
termination_table_raw_traffic)) {
NL_SET_ERR_MSG_MOD(extack,
"devices are both uplink, can't offload forwarding");
return -EOPNOTSUPP;
} else if (out_dev != rep_priv->netdev) {
NL_SET_ERR_MSG_MOD(extack,
"devices are not the same uplink, can't offload forwarding");
return -EOPNOTSUPP;
}
return 0;
}
static bool
is_duplicated_output_device(struct net_device *dev,
struct net_device *out_dev,
int *ifindexes, int if_count,
struct netlink_ext_ack *extack)
{
int i;
for (i = 0; i < if_count; i++) {
if (ifindexes[i] == out_dev->ifindex) {
NL_SET_ERR_MSG_MOD(extack, "can't duplicate output to same device");
netdev_err(dev, "can't duplicate output to same device: %s\n",
out_dev->name);
return true;
}
}
return false;
}
static struct net_device *
get_fdb_out_dev(struct net_device *uplink_dev, struct net_device *out_dev)
{
struct net_device *fdb_out_dev = out_dev;
struct net_device *uplink_upper;
rcu_read_lock();
uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev);
if (uplink_upper && netif_is_lag_master(uplink_upper) &&
uplink_upper == out_dev) {
fdb_out_dev = uplink_dev;
} else if (netif_is_lag_master(out_dev)) {
fdb_out_dev = bond_option_active_slave_get_rcu(netdev_priv(out_dev));
if (fdb_out_dev &&
(!mlx5e_eswitch_rep(fdb_out_dev) ||
!netdev_port_same_parent_id(fdb_out_dev, uplink_dev)))
fdb_out_dev = NULL;
}
rcu_read_unlock();
return fdb_out_dev;
}
static bool
tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
int act_index,
struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_tc_flow *flow = parse_state->flow;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct net_device *out_dev = act->dev;
struct mlx5e_priv *priv = flow->priv;
struct mlx5_esw_flow_attr *esw_attr;
parse_attr = attr->parse_attr;
esw_attr = attr->esw_attr;
if (!out_dev) {
/* out_dev is NULL when filters with
* non-existing mirred device are replayed to
* the driver.
*/
return false;
}
if (parse_state->mpls_push && !netif_is_bareudp(out_dev)) {
NL_SET_ERR_MSG_MOD(extack, "mpls is supported only through a bareudp device");
return false;
}
if (parse_state->eth_pop && !parse_state->mpls_push) {
NL_SET_ERR_MSG_MOD(extack, "vlan pop eth is supported only with mpls push");
return false;
}
if (flow_flag_test(parse_state->flow, L3_TO_L2_DECAP) && !parse_state->eth_push) {
NL_SET_ERR_MSG_MOD(extack, "mpls pop is only supported with vlan eth push");
return false;
}
if (mlx5e_is_ft_flow(flow) && out_dev == priv->netdev) {
/* Ignore forward to self rules generated
* by adding both mlx5 devs to the flow table
* block on a normal nft offload setup.
*/
return false;
}
if (esw_attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
NL_SET_ERR_MSG_MOD(extack,
"can't support more output ports, can't offload forwarding");
netdev_warn(priv->netdev,
"can't support more than %d output ports, can't offload forwarding\n",
esw_attr->out_count);
return false;
}
if (parse_state->encap ||
netdev_port_same_parent_id(priv->netdev, out_dev) ||
netif_is_ovs_master(out_dev))
return true;
if (parse_attr->filter_dev != priv->netdev) {
/* All mlx5 devices are called to configure
* high level device filters. Therefore, the
* *attempt* to install a filter on invalid
* eswitch should not trigger an explicit error
*/
return false;
}
NL_SET_ERR_MSG_MOD(extack, "devices are not on same switch HW, can't offload forwarding");
return false;
}
static int
parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
struct mlx5_flow_attr *attr)
{
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
struct net_device *out_dev = act->dev;
parse_attr->mirred_ifindex[esw_attr->out_count] = out_dev->ifindex;
parse_attr->tun_info[esw_attr->out_count] =
mlx5e_dup_tun_info(parse_state->tun_info);
if (!parse_attr->tun_info[esw_attr->out_count])
return -ENOMEM;
parse_state->encap = false;
if (parse_state->mpls_push) {
memcpy(&parse_attr->mpls_info[esw_attr->out_count],
&parse_state->mpls_info, sizeof(parse_state->mpls_info));
parse_state->mpls_push = false;
}
esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP;
esw_attr->out_count++;
/* attr->dests[].rep is resolved when we handle encap */
return 0;
}
static int
parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct net_device *out_dev = act->dev;
struct net_device *uplink_dev;
struct mlx5e_priv *out_priv;
struct mlx5_eswitch *esw;
bool is_uplink_rep;
int *ifindexes;
int if_count;
int err;
esw = priv->mdev->priv.eswitch;
uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
ifindexes = parse_state->ifindexes;
if_count = parse_state->if_count;
if (is_duplicated_output_device(priv->netdev, out_dev, ifindexes, if_count, extack))
return -EOPNOTSUPP;
parse_state->ifindexes[if_count] = out_dev->ifindex;
parse_state->if_count++;
is_uplink_rep = mlx5e_eswitch_uplink_rep(out_dev);
if (mlx5_lag_mpesw_do_mirred(priv->mdev, out_dev, extack))
return -EOPNOTSUPP;
out_dev = get_fdb_out_dev(uplink_dev, out_dev);
if (!out_dev)
return -ENODEV;
if (is_vlan_dev(out_dev)) {
err = mlx5e_tc_act_vlan_add_push_action(priv, attr, &out_dev, extack);
if (err)
return err;
}
if (is_vlan_dev(parse_attr->filter_dev)) {
err = mlx5e_tc_act_vlan_add_pop_action(priv, attr, extack);
if (err)
return err;
}
if (netif_is_macvlan(out_dev))
out_dev = macvlan_dev_real_dev(out_dev);
err = verify_uplink_forwarding(priv, attr, out_dev, extack);
if (err)
return err;
if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) {
NL_SET_ERR_MSG_MOD(extack,
"devices are not on same switch HW, can't offload forwarding");
return -EOPNOTSUPP;
}
if (same_vf_reps(priv, out_dev)) {
NL_SET_ERR_MSG_MOD(extack, "can't forward from a VF to itself");
return -EOPNOTSUPP;
}
out_priv = netdev_priv(out_dev);
rpriv = out_priv->ppriv;
esw_attr->dests[esw_attr->out_count].rep = rpriv->rep;
esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev;
/* If output device is bond master then rules are not explicit
* so we don't attempt to count them.
*/
if (is_uplink_rep && MLX5_CAP_PORT_SELECTION(priv->mdev, port_select_flow_table) &&
MLX5_CAP_GEN(priv->mdev, create_lag_when_not_master_up))
attr->lag.count = true;
esw_attr->out_count++;
return 0;
}
static int
parse_mirred_ovs_master(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
struct net_device *out_dev = act->dev;
int err;
err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex,
MLX5E_TC_INT_PORT_EGRESS,
&attr->action, esw_attr->out_count);
if (err)
return err;
esw_attr->out_count++;
return 0;
}
static int
tc_act_parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
struct net_device *out_dev = act->dev;
int err = -EOPNOTSUPP;
if (parse_state->encap)
err = parse_mirred_encap(parse_state, act, attr);
else if (netdev_port_same_parent_id(priv->netdev, out_dev))
err = parse_mirred(parse_state, act, priv, attr);
else if (netif_is_ovs_master(out_dev))
err = parse_mirred_ovs_master(parse_state, act, priv, attr);
if (err)
return err;
attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
return 0;
}
struct mlx5e_tc_act mlx5e_tc_act_mirred = {
.can_offload = tc_act_can_offload_mirred,
.parse_action = tc_act_parse_mirred,
.is_terminating_action = false,
};
struct mlx5e_tc_act mlx5e_tc_act_redirect = {
.can_offload = tc_act_can_offload_mirred,
.parse_action = tc_act_parse_mirred,
.is_terminating_action = true,
};
|