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
/* Copyright (C) 2019-2021, Intel Corporation. */
#include "ice.h"
#include "ice_lib.h"
#include "ice_eswitch.h"
#include "ice_eswitch_br.h"
#include "ice_fltr.h"
#include "ice_repr.h"
#include "ice_devlink.h"
#include "ice_tc_lib.h"
/**
* ice_eswitch_setup_env - configure eswitch HW filters
* @pf: pointer to PF struct
*
* This function adds HW filters configuration specific for switchdev
* mode.
*/
static int ice_eswitch_setup_env(struct ice_pf *pf)
{
struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
struct net_device *netdev = uplink_vsi->netdev;
struct ice_vsi_vlan_ops *vlan_ops;
ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
netif_addr_lock_bh(netdev);
__dev_uc_unsync(netdev, NULL);
__dev_mc_unsync(netdev, NULL);
netif_addr_unlock_bh(netdev);
if (ice_vsi_add_vlan_zero(uplink_vsi))
goto err_vlan_zero;
if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
ICE_FLTR_RX))
goto err_def_rx;
if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
ICE_FLTR_TX))
goto err_def_tx;
vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
if (vlan_ops->dis_rx_filtering(uplink_vsi))
goto err_vlan_filtering;
if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
goto err_override_uplink;
if (ice_vsi_update_local_lb(uplink_vsi, true))
goto err_override_local_lb;
return 0;
err_override_local_lb:
ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
err_override_uplink:
vlan_ops->ena_rx_filtering(uplink_vsi);
err_vlan_filtering:
ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
ICE_FLTR_TX);
err_def_tx:
ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
ICE_FLTR_RX);
err_def_rx:
ice_vsi_del_vlan_zero(uplink_vsi);
err_vlan_zero:
ice_fltr_add_mac_and_broadcast(uplink_vsi,
uplink_vsi->port_info->mac.perm_addr,
ICE_FWD_TO_VSI);
return -ENODEV;
}
/**
* ice_eswitch_release_repr - clear PR VSI configuration
* @pf: poiner to PF struct
* @repr: pointer to PR
*/
static void
ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr)
{
struct ice_vsi *vsi = repr->src_vsi;
/* Skip representors that aren't configured */
if (!repr->dst)
return;
ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
metadata_dst_free(repr->dst);
repr->dst = NULL;
ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
ICE_FWD_TO_VSI);
}
/**
* ice_eswitch_setup_repr - configure PR to run in switchdev mode
* @pf: pointer to PF struct
* @repr: pointer to PR struct
*/
static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)
{
struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
struct ice_vsi *vsi = repr->src_vsi;
struct metadata_dst *dst;
ice_remove_vsi_fltr(&pf->hw, vsi->idx);
repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
GFP_KERNEL);
if (!repr->dst)
goto err_add_mac_fltr;
if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof))
goto err_dst_free;
if (ice_vsi_add_vlan_zero(vsi))
goto err_update_security;
netif_keep_dst(uplink_vsi->netdev);
dst = repr->dst;
dst->u.port_info.port_id = vsi->vsi_num;
dst->u.port_info.lower_dev = uplink_vsi->netdev;
return 0;
err_update_security:
ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
err_dst_free:
metadata_dst_free(repr->dst);
repr->dst = NULL;
err_add_mac_fltr:
ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI);
return -ENODEV;
}
/**
* ice_eswitch_update_repr - reconfigure port representor
* @repr_id: representor ID
* @vsi: VSI for which port representor is configured
*/
void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
struct ice_repr *repr;
int ret;
if (!ice_is_switchdev_running(pf))
return;
repr = xa_load(&pf->eswitch.reprs, repr_id);
if (!repr)
return;
repr->src_vsi = vsi;
repr->dst->u.port_info.port_id = vsi->vsi_num;
if (repr->br_port)
repr->br_port->vsi = vsi;
ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof);
if (ret) {
ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
ICE_FWD_TO_VSI);
dev_err(ice_pf_to_dev(pf), "Failed to update VSI of port representor %d",
repr->id);
}
}
/**
* ice_eswitch_port_start_xmit - callback for packets transmit
* @skb: send buffer
* @netdev: network interface device structure
*
* Returns NETDEV_TX_OK if sent, else an error code
*/
netdev_tx_t
ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct ice_repr *repr = ice_netdev_to_repr(netdev);
skb_dst_drop(skb);
dst_hold((struct dst_entry *)repr->dst);
skb_dst_set(skb, (struct dst_entry *)repr->dst);
skb->dev = repr->dst->u.port_info.lower_dev;
return dev_queue_xmit(skb);
}
/**
* ice_eswitch_set_target_vsi - set eswitch context in Tx context descriptor
* @skb: pointer to send buffer
* @off: pointer to offload struct
*/
void
ice_eswitch_set_target_vsi(struct sk_buff *skb,
struct ice_tx_offload_params *off)
{
struct metadata_dst *dst = skb_metadata_dst(skb);
u64 cd_cmd, dst_vsi;
if (!dst) {
cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S;
off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX);
} else {
cd_cmd = ICE_TX_CTX_DESC_SWTCH_VSI << ICE_TXD_CTX_QW1_CMD_S;
dst_vsi = FIELD_PREP(ICE_TXD_CTX_QW1_VSI_M,
dst->u.port_info.port_id);
off->cd_qw1 = cd_cmd | dst_vsi | ICE_TX_DESC_DTYPE_CTX;
}
}
/**
* ice_eswitch_release_env - clear eswitch HW filters
* @pf: pointer to PF struct
*
* This function removes HW filters configuration specific for switchdev
* mode and restores default legacy mode settings.
*/
static void ice_eswitch_release_env(struct ice_pf *pf)
{
struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
struct ice_vsi_vlan_ops *vlan_ops;
vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
ice_vsi_update_local_lb(uplink_vsi, false);
ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
vlan_ops->ena_rx_filtering(uplink_vsi);
ice_clear_dflt_vsi(uplink_vsi);
ice_fltr_add_mac_and_broadcast(uplink_vsi,
uplink_vsi->port_info->mac.perm_addr,
ICE_FWD_TO_VSI);
}
/**
* ice_eswitch_enable_switchdev - configure eswitch in switchdev mode
* @pf: pointer to PF structure
*/
static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
{
struct ice_vsi *uplink_vsi;
uplink_vsi = ice_get_main_vsi(pf);
if (!uplink_vsi)
return -ENODEV;
if (netif_is_any_bridge_port(uplink_vsi->netdev)) {
dev_err(ice_pf_to_dev(pf),
"Uplink port cannot be a bridge port\n");
return -EINVAL;
}
pf->eswitch.uplink_vsi = uplink_vsi;
if (ice_eswitch_setup_env(pf))
return -ENODEV;
if (ice_eswitch_br_offloads_init(pf))
goto err_br_offloads;
pf->eswitch.is_running = true;
return 0;
err_br_offloads:
ice_eswitch_release_env(pf);
return -ENODEV;
}
/**
* ice_eswitch_disable_switchdev - disable eswitch resources
* @pf: pointer to PF structure
*/
static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
{
ice_eswitch_br_offloads_deinit(pf);
ice_eswitch_release_env(pf);
pf->eswitch.is_running = false;
}
/**
* ice_eswitch_mode_set - set new eswitch mode
* @devlink: pointer to devlink structure
* @mode: eswitch mode to switch to
* @extack: pointer to extack structure
*/
int
ice_eswitch_mode_set(struct devlink *devlink, u16 mode,
struct netlink_ext_ack *extack)
{
struct ice_pf *pf = devlink_priv(devlink);
if (pf->eswitch_mode == mode)
return 0;
if (ice_has_vfs(pf)) {
dev_info(ice_pf_to_dev(pf), "Changing eswitch mode is allowed only if there is no VFs created");
NL_SET_ERR_MSG_MOD(extack, "Changing eswitch mode is allowed only if there is no VFs created");
return -EOPNOTSUPP;
}
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to legacy",
pf->hw.pf_id);
xa_destroy(&pf->eswitch.reprs);
NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to legacy");
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
{
if (ice_is_adq_active(pf)) {
dev_err(ice_pf_to_dev(pf), "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root");
NL_SET_ERR_MSG_MOD(extack, "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root");
return -EOPNOTSUPP;
}
dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev",
pf->hw.pf_id);
xa_init(&pf->eswitch.reprs);
NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev");
break;
}
default:
NL_SET_ERR_MSG_MOD(extack, "Unknown eswitch mode");
return -EINVAL;
}
pf->eswitch_mode = mode;
return 0;
}
/**
* ice_eswitch_mode_get - get current eswitch mode
* @devlink: pointer to devlink structure
* @mode: output parameter for current eswitch mode
*/
int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode)
{
struct ice_pf *pf = devlink_priv(devlink);
*mode = pf->eswitch_mode;
return 0;
}
/**
* ice_is_eswitch_mode_switchdev - check if eswitch mode is set to switchdev
* @pf: pointer to PF structure
*
* Returns true if eswitch mode is set to DEVLINK_ESWITCH_MODE_SWITCHDEV,
* false otherwise.
*/
bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf)
{
return pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV;
}
/**
* ice_eswitch_start_all_tx_queues - start Tx queues of all port representors
* @pf: pointer to PF structure
*/
static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf)
{
struct ice_repr *repr;
unsigned long id;
if (test_bit(ICE_DOWN, pf->state))
return;
xa_for_each(&pf->eswitch.reprs, id, repr)
ice_repr_start_tx_queues(repr);
}
/**
* ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors
* @pf: pointer to PF structure
*/
void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
{
struct ice_repr *repr;
unsigned long id;
if (test_bit(ICE_DOWN, pf->state))
return;
xa_for_each(&pf->eswitch.reprs, id, repr)
ice_repr_stop_tx_queues(repr);
}
static void ice_eswitch_stop_reprs(struct ice_pf *pf)
{
ice_eswitch_stop_all_tx_queues(pf);
}
static void ice_eswitch_start_reprs(struct ice_pf *pf)
{
ice_eswitch_start_all_tx_queues(pf);
}
int
ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
{
struct ice_repr *repr;
int err;
if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
return 0;
if (xa_empty(&pf->eswitch.reprs)) {
err = ice_eswitch_enable_switchdev(pf);
if (err)
return err;
}
ice_eswitch_stop_reprs(pf);
repr = ice_repr_add_vf(vf);
if (IS_ERR(repr)) {
err = PTR_ERR(repr);
goto err_create_repr;
}
err = ice_eswitch_setup_repr(pf, repr);
if (err)
goto err_setup_repr;
err = xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL);
if (err)
goto err_xa_alloc;
vf->repr_id = repr->id;
ice_eswitch_start_reprs(pf);
return 0;
err_xa_alloc:
ice_eswitch_release_repr(pf, repr);
err_setup_repr:
ice_repr_rem_vf(repr);
err_create_repr:
if (xa_empty(&pf->eswitch.reprs))
ice_eswitch_disable_switchdev(pf);
ice_eswitch_start_reprs(pf);
return err;
}
void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
{
struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id);
struct devlink *devlink = priv_to_devlink(pf);
if (!repr)
return;
ice_eswitch_stop_reprs(pf);
xa_erase(&pf->eswitch.reprs, repr->id);
if (xa_empty(&pf->eswitch.reprs))
ice_eswitch_disable_switchdev(pf);
ice_eswitch_release_repr(pf, repr);
ice_repr_rem_vf(repr);
if (xa_empty(&pf->eswitch.reprs)) {
/* since all port representors are destroyed, there is
* no point in keeping the nodes
*/
ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf));
devl_lock(devlink);
devl_rate_nodes_destroy(devlink);
devl_unlock(devlink);
} else {
ice_eswitch_start_reprs(pf);
}
}
/**
* ice_eswitch_rebuild - rebuild eswitch
* @pf: pointer to PF structure
*/
void ice_eswitch_rebuild(struct ice_pf *pf)
{
struct ice_repr *repr;
unsigned long id;
if (!ice_is_switchdev_running(pf))
return;
xa_for_each(&pf->eswitch.reprs, id, repr)
ice_eswitch_detach(pf, repr->vf);
}
|