forked from intel/linux-intel-lts
-
Notifications
You must be signed in to change notification settings - Fork 0
/
veth.c
2021 lines (1678 loc) · 47 KB
/
veth.c
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
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-only
/*
* drivers/net/veth.c
*
* Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
*
* Author: Pavel Emelianov <[email protected]>
* Ethtool interface from: Eric W. Biederman <[email protected]>
*
*/
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/u64_stats_sync.h>
#include <net/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/xdp.h>
#include <linux/veth.h>
#include <linux/module.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ptr_ring.h>
#include <linux/bpf_trace.h>
#include <linux/net_tstamp.h>
#include <net/page_pool/helpers.h>
#define DRV_NAME "veth"
#define DRV_VERSION "1.0"
#define VETH_XDP_FLAG BIT(0)
#define VETH_RING_SIZE 256
#define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN)
#define VETH_XDP_TX_BULK_SIZE 16
#define VETH_XDP_BATCH 16
struct veth_stats {
u64 rx_drops;
/* xdp */
u64 xdp_packets;
u64 xdp_bytes;
u64 xdp_redirect;
u64 xdp_drops;
u64 xdp_tx;
u64 xdp_tx_err;
u64 peer_tq_xdp_xmit;
u64 peer_tq_xdp_xmit_err;
};
struct veth_rq_stats {
struct veth_stats vs;
struct u64_stats_sync syncp;
};
struct veth_rq {
struct napi_struct xdp_napi;
struct napi_struct __rcu *napi; /* points to xdp_napi when the latter is initialized */
struct net_device *dev;
struct bpf_prog __rcu *xdp_prog;
struct xdp_mem_info xdp_mem;
struct veth_rq_stats stats;
bool rx_notify_masked;
struct ptr_ring xdp_ring;
struct xdp_rxq_info xdp_rxq;
struct page_pool *page_pool;
};
struct veth_priv {
struct net_device __rcu *peer;
atomic64_t dropped;
struct bpf_prog *_xdp_prog;
struct veth_rq *rq;
unsigned int requested_headroom;
};
struct veth_xdp_tx_bq {
struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE];
unsigned int count;
};
/*
* ethtool interface
*/
struct veth_q_stat_desc {
char desc[ETH_GSTRING_LEN];
size_t offset;
};
#define VETH_RQ_STAT(m) offsetof(struct veth_stats, m)
static const struct veth_q_stat_desc veth_rq_stats_desc[] = {
{ "xdp_packets", VETH_RQ_STAT(xdp_packets) },
{ "xdp_bytes", VETH_RQ_STAT(xdp_bytes) },
{ "drops", VETH_RQ_STAT(rx_drops) },
{ "xdp_redirect", VETH_RQ_STAT(xdp_redirect) },
{ "xdp_drops", VETH_RQ_STAT(xdp_drops) },
{ "xdp_tx", VETH_RQ_STAT(xdp_tx) },
{ "xdp_tx_errors", VETH_RQ_STAT(xdp_tx_err) },
};
#define VETH_RQ_STATS_LEN ARRAY_SIZE(veth_rq_stats_desc)
static const struct veth_q_stat_desc veth_tq_stats_desc[] = {
{ "xdp_xmit", VETH_RQ_STAT(peer_tq_xdp_xmit) },
{ "xdp_xmit_errors", VETH_RQ_STAT(peer_tq_xdp_xmit_err) },
};
#define VETH_TQ_STATS_LEN ARRAY_SIZE(veth_tq_stats_desc)
static struct {
const char string[ETH_GSTRING_LEN];
} ethtool_stats_keys[] = {
{ "peer_ifindex" },
};
struct veth_xdp_buff {
struct xdp_buff xdp;
struct sk_buff *skb;
};
static int veth_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd)
{
cmd->base.speed = SPEED_10000;
cmd->base.duplex = DUPLEX_FULL;
cmd->base.port = PORT_TP;
cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
strscpy(info->driver, DRV_NAME, sizeof(info->driver));
strscpy(info->version, DRV_VERSION, sizeof(info->version));
}
static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
{
u8 *p = buf;
int i, j;
switch(stringset) {
case ETH_SS_STATS:
memcpy(p, ðtool_stats_keys, sizeof(ethtool_stats_keys));
p += sizeof(ethtool_stats_keys);
for (i = 0; i < dev->real_num_rx_queues; i++)
for (j = 0; j < VETH_RQ_STATS_LEN; j++)
ethtool_sprintf(&p, "rx_queue_%u_%.18s",
i, veth_rq_stats_desc[j].desc);
for (i = 0; i < dev->real_num_tx_queues; i++)
for (j = 0; j < VETH_TQ_STATS_LEN; j++)
ethtool_sprintf(&p, "tx_queue_%u_%.18s",
i, veth_tq_stats_desc[j].desc);
page_pool_ethtool_stats_get_strings(p);
break;
}
}
static int veth_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(ethtool_stats_keys) +
VETH_RQ_STATS_LEN * dev->real_num_rx_queues +
VETH_TQ_STATS_LEN * dev->real_num_tx_queues +
page_pool_ethtool_stats_get_count();
default:
return -EOPNOTSUPP;
}
}
static void veth_get_page_pool_stats(struct net_device *dev, u64 *data)
{
#ifdef CONFIG_PAGE_POOL_STATS
struct veth_priv *priv = netdev_priv(dev);
struct page_pool_stats pp_stats = {};
int i;
for (i = 0; i < dev->real_num_rx_queues; i++) {
if (!priv->rq[i].page_pool)
continue;
page_pool_get_stats(priv->rq[i].page_pool, &pp_stats);
}
page_pool_ethtool_stats_get(data, &pp_stats);
#endif /* CONFIG_PAGE_POOL_STATS */
}
static void veth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
int i, j, idx, pp_idx;
data[0] = peer ? peer->ifindex : 0;
idx = 1;
for (i = 0; i < dev->real_num_rx_queues; i++) {
const struct veth_rq_stats *rq_stats = &priv->rq[i].stats;
const void *stats_base = (void *)&rq_stats->vs;
unsigned int start;
size_t offset;
do {
start = u64_stats_fetch_begin(&rq_stats->syncp);
for (j = 0; j < VETH_RQ_STATS_LEN; j++) {
offset = veth_rq_stats_desc[j].offset;
data[idx + j] = *(u64 *)(stats_base + offset);
}
} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
idx += VETH_RQ_STATS_LEN;
}
pp_idx = idx;
if (!peer)
goto page_pool_stats;
rcv_priv = netdev_priv(peer);
for (i = 0; i < peer->real_num_rx_queues; i++) {
const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats;
const void *base = (void *)&rq_stats->vs;
unsigned int start, tx_idx = idx;
size_t offset;
tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN;
do {
start = u64_stats_fetch_begin(&rq_stats->syncp);
for (j = 0; j < VETH_TQ_STATS_LEN; j++) {
offset = veth_tq_stats_desc[j].offset;
data[tx_idx + j] += *(u64 *)(base + offset);
}
} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
}
pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN;
page_pool_stats:
veth_get_page_pool_stats(dev, &data[pp_idx]);
}
static void veth_get_channels(struct net_device *dev,
struct ethtool_channels *channels)
{
channels->tx_count = dev->real_num_tx_queues;
channels->rx_count = dev->real_num_rx_queues;
channels->max_tx = dev->num_tx_queues;
channels->max_rx = dev->num_rx_queues;
}
static int veth_set_channels(struct net_device *dev,
struct ethtool_channels *ch);
static const struct ethtool_ops veth_ethtool_ops = {
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_strings = veth_get_strings,
.get_sset_count = veth_get_sset_count,
.get_ethtool_stats = veth_get_ethtool_stats,
.get_link_ksettings = veth_get_link_ksettings,
.get_ts_info = ethtool_op_get_ts_info,
.get_channels = veth_get_channels,
.set_channels = veth_set_channels,
};
/* general routines */
static bool veth_is_xdp_frame(void *ptr)
{
return (unsigned long)ptr & VETH_XDP_FLAG;
}
static struct xdp_frame *veth_ptr_to_xdp(void *ptr)
{
return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
}
static void *veth_xdp_to_ptr(struct xdp_frame *xdp)
{
return (void *)((unsigned long)xdp | VETH_XDP_FLAG);
}
static void veth_ptr_free(void *ptr)
{
if (veth_is_xdp_frame(ptr))
xdp_return_frame(veth_ptr_to_xdp(ptr));
else
kfree_skb(ptr);
}
static void __veth_xdp_flush(struct veth_rq *rq)
{
/* Write ptr_ring before reading rx_notify_masked */
smp_mb();
if (!READ_ONCE(rq->rx_notify_masked) &&
napi_schedule_prep(&rq->xdp_napi)) {
WRITE_ONCE(rq->rx_notify_masked, true);
__napi_schedule(&rq->xdp_napi);
}
}
static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
{
if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
dev_kfree_skb_any(skb);
return NET_RX_DROP;
}
return NET_RX_SUCCESS;
}
static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
struct veth_rq *rq, bool xdp)
{
return __dev_forward_skb(dev, skb) ?: xdp ?
veth_xdp_rx(rq, skb) :
__netif_rx(skb);
}
/* return true if the specified skb has chances of GRO aggregation
* Don't strive for accuracy, but try to avoid GRO overhead in the most
* common scenarios.
* When XDP is enabled, all traffic is considered eligible, as the xmit
* device has TSO off.
* When TSO is enabled on the xmit device, we are likely interested only
* in UDP aggregation, explicitly check for that if the skb is suspected
* - the sock_wfree destructor is used by UDP, ICMP and XDP sockets -
* to belong to locally generated UDP traffic.
*/
static bool veth_skb_is_eligible_for_gro(const struct net_device *dev,
const struct net_device *rcv,
const struct sk_buff *skb)
{
return !(dev->features & NETIF_F_ALL_TSO) ||
(skb->destructor == sock_wfree &&
rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD));
}
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct veth_rq *rq = NULL;
int ret = NETDEV_TX_OK;
struct net_device *rcv;
int length = skb->len;
bool use_napi = false;
int rxq;
rcu_read_lock();
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) {
kfree_skb(skb);
goto drop;
}
rcv_priv = netdev_priv(rcv);
rxq = skb_get_queue_mapping(skb);
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
/* The napi pointer is available when an XDP program is
* attached or when GRO is enabled
* Don't bother with napi/GRO if the skb can't be aggregated
*/
use_napi = rcu_access_pointer(rq->napi) &&
veth_skb_is_eligible_for_gro(dev, rcv, skb);
}
skb_tx_timestamp(skb);
if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
if (!use_napi)
dev_sw_netstats_tx_add(dev, 1, length);
else
__veth_xdp_flush(rq);
} else {
drop:
atomic64_inc(&priv->dropped);
ret = NET_XMIT_DROP;
}
rcu_read_unlock();
return ret;
}
static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
result->peer_tq_xdp_xmit_err = 0;
result->xdp_packets = 0;
result->xdp_tx_err = 0;
result->xdp_bytes = 0;
result->rx_drops = 0;
for (i = 0; i < dev->num_rx_queues; i++) {
u64 packets, bytes, drops, xdp_tx_err, peer_tq_xdp_xmit_err;
struct veth_rq_stats *stats = &priv->rq[i].stats;
unsigned int start;
do {
start = u64_stats_fetch_begin(&stats->syncp);
peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err;
xdp_tx_err = stats->vs.xdp_tx_err;
packets = stats->vs.xdp_packets;
bytes = stats->vs.xdp_bytes;
drops = stats->vs.rx_drops;
} while (u64_stats_fetch_retry(&stats->syncp, start));
result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err;
result->xdp_tx_err += xdp_tx_err;
result->xdp_packets += packets;
result->xdp_bytes += bytes;
result->rx_drops += drops;
}
}
static void veth_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer;
struct veth_stats rx;
tot->tx_dropped = atomic64_read(&priv->dropped);
dev_fetch_sw_netstats(tot, dev->tstats);
veth_stats_rx(&rx, dev);
tot->tx_dropped += rx.xdp_tx_err;
tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err;
tot->rx_bytes += rx.xdp_bytes;
tot->rx_packets += rx.xdp_packets;
rcu_read_lock();
peer = rcu_dereference(priv->peer);
if (peer) {
struct rtnl_link_stats64 tot_peer = {};
dev_fetch_sw_netstats(&tot_peer, peer->tstats);
tot->rx_bytes += tot_peer.tx_bytes;
tot->rx_packets += tot_peer.tx_packets;
veth_stats_rx(&rx, peer);
tot->tx_dropped += rx.peer_tq_xdp_xmit_err;
tot->rx_dropped += rx.xdp_tx_err;
tot->tx_bytes += rx.xdp_bytes;
tot->tx_packets += rx.xdp_packets;
}
rcu_read_unlock();
}
/* fake multicast ability */
static void veth_set_multicast_list(struct net_device *dev)
{
}
static int veth_select_rxq(struct net_device *dev)
{
return smp_processor_id() % dev->real_num_rx_queues;
}
static struct net_device *veth_peer_dev(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
/* Callers must be under RCU read side. */
return rcu_dereference(priv->peer);
}
static int veth_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames,
u32 flags, bool ndo_xmit)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
int i, ret = -ENXIO, nxmit = 0;
struct net_device *rcv;
unsigned int max_len;
struct veth_rq *rq;
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
rcu_read_lock();
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv))
goto out;
rcv_priv = netdev_priv(rcv);
rq = &rcv_priv->rq[veth_select_rxq(rcv)];
/* The napi pointer is set if NAPI is enabled, which ensures that
* xdp_ring is initialized on receive side and the peer device is up.
*/
if (!rcu_access_pointer(rq->napi))
goto out;
max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
spin_lock(&rq->xdp_ring.producer_lock);
for (i = 0; i < n; i++) {
struct xdp_frame *frame = frames[i];
void *ptr = veth_xdp_to_ptr(frame);
if (unlikely(xdp_get_frame_len(frame) > max_len ||
__ptr_ring_produce(&rq->xdp_ring, ptr)))
break;
nxmit++;
}
spin_unlock(&rq->xdp_ring.producer_lock);
if (flags & XDP_XMIT_FLUSH)
__veth_xdp_flush(rq);
ret = nxmit;
if (ndo_xmit) {
u64_stats_update_begin(&rq->stats.syncp);
rq->stats.vs.peer_tq_xdp_xmit += nxmit;
rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit;
u64_stats_update_end(&rq->stats.syncp);
}
out:
rcu_read_unlock();
return ret;
}
static int veth_ndo_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames, u32 flags)
{
int err;
err = veth_xdp_xmit(dev, n, frames, flags, true);
if (err < 0) {
struct veth_priv *priv = netdev_priv(dev);
atomic64_add(n, &priv->dropped);
}
return err;
}
static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq)
{
int sent, i, err = 0, drops;
sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false);
if (sent < 0) {
err = sent;
sent = 0;
}
for (i = sent; unlikely(i < bq->count); i++)
xdp_return_frame(bq->q[i]);
drops = bq->count - sent;
trace_xdp_bulk_tx(rq->dev, sent, drops, err);
u64_stats_update_begin(&rq->stats.syncp);
rq->stats.vs.xdp_tx += sent;
rq->stats.vs.xdp_tx_err += drops;
u64_stats_update_end(&rq->stats.syncp);
bq->count = 0;
}
static void veth_xdp_flush(struct veth_rq *rq, struct veth_xdp_tx_bq *bq)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(rq->dev);
struct net_device *rcv;
struct veth_rq *rcv_rq;
rcu_read_lock();
veth_xdp_flush_bq(rq, bq);
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv))
goto out;
rcv_priv = netdev_priv(rcv);
rcv_rq = &rcv_priv->rq[veth_select_rxq(rcv)];
/* xdp_ring is initialized on receive side? */
if (unlikely(!rcu_access_pointer(rcv_rq->xdp_prog)))
goto out;
__veth_xdp_flush(rcv_rq);
out:
rcu_read_unlock();
}
static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp,
struct veth_xdp_tx_bq *bq)
{
struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp);
if (unlikely(!frame))
return -EOVERFLOW;
if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE))
veth_xdp_flush_bq(rq, bq);
bq->q[bq->count++] = frame;
return 0;
}
static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
struct xdp_frame *frame,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
struct xdp_frame orig_frame;
struct bpf_prog *xdp_prog;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (likely(xdp_prog)) {
struct veth_xdp_buff vxbuf;
struct xdp_buff *xdp = &vxbuf.xdp;
u32 act;
xdp_convert_frame_to_buff(frame, xdp);
xdp->rxq = &rq->xdp_rxq;
vxbuf.skb = NULL;
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
if (xdp_update_frame_from_buff(xdp, frame))
goto err_xdp;
break;
case XDP_TX:
orig_frame = *frame;
xdp->rxq->mem = frame->mem;
if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) {
trace_xdp_exception(rq->dev, xdp_prog, act);
frame = &orig_frame;
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_tx++;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
orig_frame = *frame;
xdp->rxq->mem = frame->mem;
if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) {
frame = &orig_frame;
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_redirect++;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
stats->xdp_drops++;
goto err_xdp;
}
}
rcu_read_unlock();
return frame;
err_xdp:
rcu_read_unlock();
xdp_return_frame(frame);
xdp_xmit:
return NULL;
}
/* frames array contains VETH_XDP_BATCH at most */
static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
int n_xdpf, struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
void *skbs[VETH_XDP_BATCH];
int i;
if (xdp_alloc_skb_bulk(skbs, n_xdpf,
GFP_ATOMIC | __GFP_ZERO) < 0) {
for (i = 0; i < n_xdpf; i++)
xdp_return_frame(frames[i]);
stats->rx_drops += n_xdpf;
return;
}
for (i = 0; i < n_xdpf; i++) {
struct sk_buff *skb = skbs[i];
skb = __xdp_build_skb_from_frame(frames[i], skb,
rq->dev);
if (!skb) {
xdp_return_frame(frames[i]);
stats->rx_drops++;
continue;
}
napi_gro_receive(&rq->xdp_napi, skb);
}
}
static void veth_xdp_get(struct xdp_buff *xdp)
{
struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
int i;
get_page(virt_to_page(xdp->data));
if (likely(!xdp_buff_has_frags(xdp)))
return;
for (i = 0; i < sinfo->nr_frags; i++)
__skb_frag_ref(&sinfo->frags[i]);
}
static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
struct xdp_buff *xdp,
struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
u32 frame_sz;
if (skb_shared(skb) || skb_head_is_locked(skb) ||
skb_shinfo(skb)->nr_frags ||
skb_headroom(skb) < XDP_PACKET_HEADROOM) {
u32 size, len, max_head_size, off;
struct sk_buff *nskb;
struct page *page;
int i, head_off;
/* We need a private copy of the skb and data buffers since
* the ebpf program can modify it. We segment the original skb
* into order-0 pages without linearize it.
*
* Make sure we have enough space for linear and paged area
*/
max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE -
VETH_XDP_HEADROOM);
if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size)
goto drop;
/* Allocate skb head */
page = page_pool_dev_alloc_pages(rq->page_pool);
if (!page)
goto drop;
nskb = napi_build_skb(page_address(page), PAGE_SIZE);
if (!nskb) {
page_pool_put_full_page(rq->page_pool, page, true);
goto drop;
}
skb_reserve(nskb, VETH_XDP_HEADROOM);
skb_copy_header(nskb, skb);
skb_mark_for_recycle(nskb);
size = min_t(u32, skb->len, max_head_size);
if (skb_copy_bits(skb, 0, nskb->data, size)) {
consume_skb(nskb);
goto drop;
}
skb_put(nskb, size);
head_off = skb_headroom(nskb) - skb_headroom(skb);
skb_headers_offset_update(nskb, head_off);
/* Allocate paged area of new skb */
off = size;
len = skb->len - off;
for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
page = page_pool_dev_alloc_pages(rq->page_pool);
if (!page) {
consume_skb(nskb);
goto drop;
}
size = min_t(u32, len, PAGE_SIZE);
skb_add_rx_frag(nskb, i, page, 0, size, PAGE_SIZE);
if (skb_copy_bits(skb, off, page_address(page),
size)) {
consume_skb(nskb);
goto drop;
}
len -= size;
off += size;
}
consume_skb(skb);
skb = nskb;
}
/* SKB "head" area always have tailroom for skb_shared_info */
frame_sz = skb_end_pointer(skb) - skb->head;
frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq);
xdp_prepare_buff(xdp, skb->head, skb_headroom(skb),
skb_headlen(skb), true);
if (skb_is_nonlinear(skb)) {
skb_shinfo(skb)->xdp_frags_size = skb->data_len;
xdp_buff_set_frags_flag(xdp);
} else {
xdp_buff_clear_frags_flag(xdp);
}
*pskb = skb;
return 0;
drop:
consume_skb(skb);
*pskb = NULL;
return -ENOMEM;
}
static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
struct sk_buff *skb,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
void *orig_data, *orig_data_end;
struct bpf_prog *xdp_prog;
struct veth_xdp_buff vxbuf;
struct xdp_buff *xdp = &vxbuf.xdp;
u32 act, metalen;
int off;
skb_prepare_for_gro(skb);
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (unlikely(!xdp_prog)) {
rcu_read_unlock();
goto out;
}
__skb_push(skb, skb->data - skb_mac_header(skb));
if (veth_convert_skb_to_xdp_buff(rq, xdp, &skb))
goto drop;
vxbuf.skb = skb;
orig_data = xdp->data;
orig_data_end = xdp->data_end;
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
break;
case XDP_TX:
veth_xdp_get(xdp);
consume_skb(skb);
xdp->rxq->mem = rq->xdp_mem;
if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) {
trace_xdp_exception(rq->dev, xdp_prog, act);
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_tx++;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
veth_xdp_get(xdp);
consume_skb(skb);
xdp->rxq->mem = rq->xdp_mem;
if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) {
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_redirect++;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
stats->xdp_drops++;
goto xdp_drop;
}
rcu_read_unlock();
/* check if bpf_xdp_adjust_head was used */
off = orig_data - xdp->data;
if (off > 0)
__skb_push(skb, off);
else if (off < 0)
__skb_pull(skb, -off);
skb_reset_mac_header(skb);
/* check if bpf_xdp_adjust_tail was used */
off = xdp->data_end - orig_data_end;
if (off != 0)
__skb_put(skb, off); /* positive on grow, negative on shrink */
/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
* (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
*/
if (xdp_buff_has_frags(xdp))
skb->data_len = skb_shinfo(skb)->xdp_frags_size;
else
skb->data_len = 0;
skb->protocol = eth_type_trans(skb, rq->dev);
metalen = xdp->data - xdp->data_meta;
if (metalen)
skb_metadata_set(skb, metalen);
out:
return skb;
drop:
stats->rx_drops++;
xdp_drop:
rcu_read_unlock();
kfree_skb(skb);
return NULL;
err_xdp:
rcu_read_unlock();
xdp_return_buff(xdp);
xdp_xmit:
return NULL;
}
static int veth_xdp_rcv(struct veth_rq *rq, int budget,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
int i, done = 0, n_xdpf = 0;
void *xdpf[VETH_XDP_BATCH];
for (i = 0; i < budget; i++) {
void *ptr = __ptr_ring_consume(&rq->xdp_ring);
if (!ptr)
break;
if (veth_is_xdp_frame(ptr)) {
/* ndo_xdp_xmit */
struct xdp_frame *frame = veth_ptr_to_xdp(ptr);
stats->xdp_bytes += xdp_get_frame_len(frame);
frame = veth_xdp_rcv_one(rq, frame, bq, stats);
if (frame) {
/* XDP_PASS */
xdpf[n_xdpf++] = frame;
if (n_xdpf == VETH_XDP_BATCH) {
veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf,
bq, stats);
n_xdpf = 0;
}
}
} else {
/* ndo_start_xmit */
struct sk_buff *skb = ptr;
stats->xdp_bytes += skb->len;
skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
if (skb) {
if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC))
netif_receive_skb(skb);
else
napi_gro_receive(&rq->xdp_napi, skb);
}
}
done++;
}
if (n_xdpf)
veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats);
u64_stats_update_begin(&rq->stats.syncp);
rq->stats.vs.xdp_redirect += stats->xdp_redirect;
rq->stats.vs.xdp_bytes += stats->xdp_bytes;
rq->stats.vs.xdp_drops += stats->xdp_drops;
rq->stats.vs.rx_drops += stats->rx_drops;
rq->stats.vs.xdp_packets += done;
u64_stats_update_end(&rq->stats.syncp);
return done;
}
static int veth_poll(struct napi_struct *napi, int budget)
{
struct veth_rq *rq =
container_of(napi, struct veth_rq, xdp_napi);
struct veth_stats stats = {};
struct veth_xdp_tx_bq bq;
int done;
bq.count = 0;