forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
virtio_net.c
2864 lines (2370 loc) · 72.9 KB
/
virtio_net.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
/* A network driver using virtio.
*
* Copyright 2007 Rusty Russell <[email protected]> IBM Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
//#define DEBUG
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_net.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/scatterlist.h>
#include <linux/if_vlan.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
#include <linux/filter.h>
#include <net/route.h>
static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);
static bool csum = true, gso = true, napi_tx;
module_param(csum, bool, 0444);
module_param(gso, bool, 0444);
module_param(napi_tx, bool, 0644);
/* FIXME: MTU in config. */
#define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
#define GOOD_COPY_LEN 128
#define VIRTNET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
/* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
#define VIRTIO_XDP_HEADROOM 256
/* RX packet size EWMA. The average packet size is used to determine the packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
* at once, the weight is chosen so that the EWMA will be insensitive to short-
* term, transient changes in packet size.
*/
DECLARE_EWMA(pkt_len, 0, 64)
#define VIRTNET_DRIVER_VERSION "1.0.0"
static const unsigned long guest_offloads[] = {
VIRTIO_NET_F_GUEST_TSO4,
VIRTIO_NET_F_GUEST_TSO6,
VIRTIO_NET_F_GUEST_ECN,
VIRTIO_NET_F_GUEST_UFO
};
struct virtnet_stats {
struct u64_stats_sync tx_syncp;
struct u64_stats_sync rx_syncp;
u64 tx_bytes;
u64 tx_packets;
u64 rx_bytes;
u64 rx_packets;
};
/* Internal representation of a send virtqueue */
struct send_queue {
/* Virtqueue associated with this send _queue */
struct virtqueue *vq;
/* TX: fragments + linear part + virtio header */
struct scatterlist sg[MAX_SKB_FRAGS + 2];
/* Name of the send queue: output.$index */
char name[40];
struct napi_struct napi;
};
/* Internal representation of a receive virtqueue */
struct receive_queue {
/* Virtqueue associated with this receive_queue */
struct virtqueue *vq;
struct napi_struct napi;
struct bpf_prog __rcu *xdp_prog;
/* Chain pages by the private ptr. */
struct page *pages;
/* Average packet length for mergeable receive buffers. */
struct ewma_pkt_len mrg_avg_pkt_len;
/* Page frag for packet buffer allocation. */
struct page_frag alloc_frag;
/* RX: fragments + linear part + virtio header */
struct scatterlist sg[MAX_SKB_FRAGS + 2];
/* Min single buffer size for mergeable buffers case. */
unsigned int min_buf_len;
/* Name of this receive queue: input.$index */
char name[40];
};
struct virtnet_info {
struct virtio_device *vdev;
struct virtqueue *cvq;
struct net_device *dev;
struct send_queue *sq;
struct receive_queue *rq;
unsigned int status;
/* Max # of queue pairs supported by the device */
u16 max_queue_pairs;
/* # of queue pairs currently used by the driver */
u16 curr_queue_pairs;
/* # of XDP queue pairs currently used by the driver */
u16 xdp_queue_pairs;
/* I like... big packets and I cannot lie! */
bool big_packets;
/* Host will merge rx buffers for big packets (shake it! shake it!) */
bool mergeable_rx_bufs;
/* Has control virtqueue */
bool has_cvq;
/* Host can handle any s/g split between our header and packet data */
bool any_header_sg;
/* Packet virtio header size */
u8 hdr_len;
/* Active statistics */
struct virtnet_stats __percpu *stats;
/* Work struct for refilling if we run low on memory. */
struct delayed_work refill;
/* Work struct for config space updates */
struct work_struct config_work;
/* Does the affinity hint is set for virtqueues? */
bool affinity_hint_set;
/* CPU hotplug instances for online & dead */
struct hlist_node node;
struct hlist_node node_dead;
/* Control VQ buffers: protected by the rtnl lock */
struct virtio_net_ctrl_hdr ctrl_hdr;
virtio_net_ctrl_ack ctrl_status;
struct virtio_net_ctrl_mq ctrl_mq;
u8 ctrl_promisc;
u8 ctrl_allmulti;
u16 ctrl_vid;
u64 ctrl_offloads;
/* Ethtool settings */
u8 duplex;
u32 speed;
unsigned long guest_offloads;
};
struct padded_vnet_hdr {
struct virtio_net_hdr_mrg_rxbuf hdr;
/*
* hdr is in a separate sg buffer, and data sg buffer shares same page
* with this header sg. This padding makes next sg 16 byte aligned
* after the header.
*/
char padding[4];
};
/* Converting between virtqueue no. and kernel tx/rx queue no.
* 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
*/
static int vq2txq(struct virtqueue *vq)
{
return (vq->index - 1) / 2;
}
static int txq2vq(int txq)
{
return txq * 2 + 1;
}
static int vq2rxq(struct virtqueue *vq)
{
return vq->index / 2;
}
static int rxq2vq(int rxq)
{
return rxq * 2;
}
static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb)
{
return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb;
}
/*
* private is used to chain pages for big packets, put the whole
* most recent used list in the beginning for reuse
*/
static void give_pages(struct receive_queue *rq, struct page *page)
{
struct page *end;
/* Find end of list, sew whole thing into vi->rq.pages. */
for (end = page; end->private; end = (struct page *)end->private);
end->private = (unsigned long)rq->pages;
rq->pages = page;
}
static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
{
struct page *p = rq->pages;
if (p) {
rq->pages = (struct page *)p->private;
/* clear private here, it is used to chain pages */
p->private = 0;
} else
p = alloc_page(gfp_mask);
return p;
}
static void virtqueue_napi_schedule(struct napi_struct *napi,
struct virtqueue *vq)
{
if (napi_schedule_prep(napi)) {
virtqueue_disable_cb(vq);
__napi_schedule(napi);
}
}
static void virtqueue_napi_complete(struct napi_struct *napi,
struct virtqueue *vq, int processed)
{
int opaque;
opaque = virtqueue_enable_cb_prepare(vq);
if (napi_complete_done(napi, processed) &&
unlikely(virtqueue_poll(vq, opaque)))
virtqueue_napi_schedule(napi, vq);
}
static void skb_xmit_done(struct virtqueue *vq)
{
struct virtnet_info *vi = vq->vdev->priv;
struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi;
/* Suppress further interrupts. */
virtqueue_disable_cb(vq);
if (napi->weight)
virtqueue_napi_schedule(napi, vq);
else
/* We were probably waiting for more output buffers. */
netif_wake_subqueue(vi->dev, vq2txq(vq));
}
#define MRG_CTX_HEADER_SHIFT 22
static void *mergeable_len_to_ctx(unsigned int truesize,
unsigned int headroom)
{
return (void *)(unsigned long)((headroom << MRG_CTX_HEADER_SHIFT) | truesize);
}
static unsigned int mergeable_ctx_to_headroom(void *mrg_ctx)
{
return (unsigned long)mrg_ctx >> MRG_CTX_HEADER_SHIFT;
}
static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
{
return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1);
}
/* Called from bottom half context */
static struct sk_buff *page_to_skb(struct virtnet_info *vi,
struct receive_queue *rq,
struct page *page, unsigned int offset,
unsigned int len, unsigned int truesize)
{
struct sk_buff *skb;
struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int copy, hdr_len, hdr_padded_len;
char *p;
p = page_address(page) + offset;
/* copy small packet so we can reuse these pages for small data */
skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN);
if (unlikely(!skb))
return NULL;
hdr = skb_vnet_hdr(skb);
hdr_len = vi->hdr_len;
if (vi->mergeable_rx_bufs)
hdr_padded_len = sizeof(*hdr);
else
hdr_padded_len = sizeof(struct padded_vnet_hdr);
memcpy(hdr, p, hdr_len);
len -= hdr_len;
offset += hdr_padded_len;
p += hdr_padded_len;
copy = len;
if (copy > skb_tailroom(skb))
copy = skb_tailroom(skb);
skb_put_data(skb, p, copy);
len -= copy;
offset += copy;
if (vi->mergeable_rx_bufs) {
if (len)
skb_add_rx_frag(skb, 0, page, offset, len, truesize);
else
put_page(page);
return skb;
}
/*
* Verify that we can indeed put this data into a skb.
* This is here to handle cases when the device erroneously
* tries to receive more than is possible. This is usually
* the case of a broken device.
*/
if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) {
net_dbg_ratelimited("%s: too much data\n", skb->dev->name);
dev_kfree_skb(skb);
return NULL;
}
BUG_ON(offset >= PAGE_SIZE);
while (len) {
unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset,
frag_size, truesize);
len -= frag_size;
page = (struct page *)page->private;
offset = 0;
}
if (page)
give_pages(rq, page);
return skb;
}
static void virtnet_xdp_flush(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
struct send_queue *sq;
unsigned int qp;
qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
sq = &vi->sq[qp];
virtqueue_kick(sq->vq);
}
static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
struct xdp_buff *xdp)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int len;
struct send_queue *sq;
unsigned int qp;
void *xdp_sent;
int err;
qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
sq = &vi->sq[qp];
/* Free up any pending old buffers before queueing new ones. */
while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
struct page *sent_page = virt_to_head_page(xdp_sent);
put_page(sent_page);
}
xdp->data -= vi->hdr_len;
/* Zero header and leave csum up to XDP layers */
hdr = xdp->data;
memset(hdr, 0, vi->hdr_len);
sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);
err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp->data, GFP_ATOMIC);
if (unlikely(err)) {
struct page *page = virt_to_head_page(xdp->data);
put_page(page);
return false;
}
return true;
}
static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
{
struct virtnet_info *vi = netdev_priv(dev);
bool sent = __virtnet_xdp_xmit(vi, xdp);
if (!sent)
return -ENOSPC;
return 0;
}
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
{
return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
}
/* We copy the packet for XDP in the following cases:
*
* 1) Packet is scattered across multiple rx buffers.
* 2) Headroom space is insufficient.
*
* This is inefficient but it's a temporary condition that
* we hit right after XDP is enabled and until queue is refilled
* with large buffers with sufficient headroom - so it should affect
* at most queue size packets.
* Afterwards, the conditions to enable
* XDP should preclude the underlying device from sending packets
* across multiple buffers (num_buf > 1), and we make sure buffers
* have enough headroom.
*/
static struct page *xdp_linearize_page(struct receive_queue *rq,
u16 *num_buf,
struct page *p,
int offset,
int page_off,
unsigned int *len)
{
struct page *page = alloc_page(GFP_ATOMIC);
if (!page)
return NULL;
memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
page_off += *len;
while (--*num_buf) {
unsigned int buflen;
void *buf;
int off;
buf = virtqueue_get_buf(rq->vq, &buflen);
if (unlikely(!buf))
goto err_buf;
p = virt_to_head_page(buf);
off = buf - page_address(p);
/* guard against a misconfigured or uncooperative backend that
* is sending packet larger than the MTU.
*/
if ((page_off + buflen) > PAGE_SIZE) {
put_page(p);
goto err_buf;
}
memcpy(page_address(page) + page_off,
page_address(p) + off, buflen);
page_off += buflen;
put_page(p);
}
/* Headroom does not contribute to packet length */
*len = page_off - VIRTIO_XDP_HEADROOM;
return page;
err_buf:
__free_pages(page, 0);
return NULL;
}
static struct sk_buff *receive_small(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf, void *ctx,
unsigned int len,
bool *xdp_xmit)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
unsigned int xdp_headroom = (unsigned long)ctx;
unsigned int header_offset = VIRTNET_RX_PAD + xdp_headroom;
unsigned int headroom = vi->hdr_len + header_offset;
unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
struct page *page = virt_to_head_page(buf);
unsigned int delta = 0, err;
struct page *xdp_page;
len -= vi->hdr_len;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
struct xdp_buff xdp;
void *orig_data;
u32 act;
if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
goto err_xdp;
if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) {
int offset = buf - page_address(page) + header_offset;
unsigned int tlen = len + vi->hdr_len;
u16 num_buf = 1;
xdp_headroom = virtnet_get_headroom(vi);
header_offset = VIRTNET_RX_PAD + xdp_headroom;
headroom = vi->hdr_len + header_offset;
buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
xdp_page = xdp_linearize_page(rq, &num_buf, page,
offset, header_offset,
&tlen);
if (!xdp_page)
goto err_xdp;
buf = page_address(xdp_page);
put_page(page);
page = xdp_page;
}
xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
xdp.data = xdp.data_hard_start + xdp_headroom;
xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
orig_data = xdp.data;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
/* Recalculate length in case bpf program changed it */
delta = orig_data - xdp.data;
break;
case XDP_TX:
if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
else
*xdp_xmit = true;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
err = xdp_do_redirect(dev, &xdp, xdp_prog);
if (!err)
*xdp_xmit = true;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
trace_xdp_exception(vi->dev, xdp_prog, act);
case XDP_DROP:
goto err_xdp;
}
}
rcu_read_unlock();
skb = build_skb(buf, buflen);
if (!skb) {
put_page(page);
goto err;
}
skb_reserve(skb, headroom - delta);
skb_put(skb, len + delta);
if (!delta) {
buf += header_offset;
memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
} /* keep zeroed vnet hdr since packet was changed by bpf */
err:
return skb;
err_xdp:
rcu_read_unlock();
dev->stats.rx_dropped++;
put_page(page);
xdp_xmit:
return NULL;
}
static struct sk_buff *receive_big(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf,
unsigned int len)
{
struct page *page = buf;
struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
if (unlikely(!skb))
goto err;
return skb;
err:
dev->stats.rx_dropped++;
give_pages(rq, page);
return NULL;
}
static struct sk_buff *receive_mergeable(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf,
void *ctx,
unsigned int len,
bool *xdp_xmit)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
struct page *page = virt_to_head_page(buf);
int offset = buf - page_address(page);
struct sk_buff *head_skb, *curr_skb;
struct bpf_prog *xdp_prog;
unsigned int truesize;
unsigned int headroom = mergeable_ctx_to_headroom(ctx);
int err;
head_skb = NULL;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
struct page *xdp_page;
struct xdp_buff xdp;
void *data;
u32 act;
/* This happens when rx buffer size is underestimated */
if (unlikely(num_buf > 1 ||
headroom < virtnet_get_headroom(vi))) {
/* linearize data for XDP */
xdp_page = xdp_linearize_page(rq, &num_buf,
page, offset,
VIRTIO_XDP_HEADROOM,
&len);
if (!xdp_page)
goto err_xdp;
offset = VIRTIO_XDP_HEADROOM;
} else {
xdp_page = page;
}
/* Transient failure which in theory could occur if
* in-flight packets from before XDP was enabled reach
* the receive path after XDP is loaded. In practice I
* was not able to create this condition.
*/
if (unlikely(hdr->hdr.gso_type))
goto err_xdp;
/* Allow consuming headroom but reserve enough space to push
* the descriptor on if we get an XDP_TX return code.
*/
data = page_address(xdp_page) + offset;
xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
xdp.data = data + vi->hdr_len;
xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + (len - vi->hdr_len);
act = bpf_prog_run_xdp(xdp_prog, &xdp);
if (act != XDP_PASS)
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
switch (act) {
case XDP_PASS:
/* recalculate offset to account for any header
* adjustments. Note other cases do not build an
* skb and avoid using offset
*/
offset = xdp.data -
page_address(xdp_page) - vi->hdr_len;
/* We can only create skb based on xdp_page. */
if (unlikely(xdp_page != page)) {
rcu_read_unlock();
put_page(page);
head_skb = page_to_skb(vi, rq, xdp_page,
offset, len, PAGE_SIZE);
return head_skb;
}
break;
case XDP_TX:
if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
else
*xdp_xmit = true;
if (unlikely(xdp_page != page))
goto err_xdp;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
err = xdp_do_redirect(dev, &xdp, xdp_prog);
if (!err)
*xdp_xmit = true;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
trace_xdp_exception(vi->dev, xdp_prog, act);
case XDP_DROP:
if (unlikely(xdp_page != page))
__free_pages(xdp_page, 0);
goto err_xdp;
}
}
rcu_read_unlock();
truesize = mergeable_ctx_to_truesize(ctx);
if (unlikely(len > truesize)) {
pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
dev->name, len, (unsigned long)ctx);
dev->stats.rx_length_errors++;
goto err_skb;
}
head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
curr_skb = head_skb;
if (unlikely(!curr_skb))
goto err_skb;
while (--num_buf) {
int num_skb_frags;
buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
dev->name, num_buf,
virtio16_to_cpu(vi->vdev,
hdr->num_buffers));
dev->stats.rx_length_errors++;
goto err_buf;
}
page = virt_to_head_page(buf);
truesize = mergeable_ctx_to_truesize(ctx);
if (unlikely(len > truesize)) {
pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
dev->name, len, (unsigned long)ctx);
dev->stats.rx_length_errors++;
goto err_skb;
}
num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC);
if (unlikely(!nskb))
goto err_skb;
if (curr_skb == head_skb)
skb_shinfo(curr_skb)->frag_list = nskb;
else
curr_skb->next = nskb;
curr_skb = nskb;
head_skb->truesize += nskb->truesize;
num_skb_frags = 0;
}
if (curr_skb != head_skb) {
head_skb->data_len += len;
head_skb->len += len;
head_skb->truesize += truesize;
}
offset = buf - page_address(page);
if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
put_page(page);
skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
len, truesize);
} else {
skb_add_rx_frag(curr_skb, num_skb_frags, page,
offset, len, truesize);
}
}
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len);
return head_skb;
err_xdp:
rcu_read_unlock();
err_skb:
put_page(page);
while (--num_buf) {
buf = virtqueue_get_buf(rq->vq, &len);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers missing\n",
dev->name, num_buf);
dev->stats.rx_length_errors++;
break;
}
page = virt_to_head_page(buf);
put_page(page);
}
err_buf:
dev->stats.rx_dropped++;
dev_kfree_skb(head_skb);
xdp_xmit:
return NULL;
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
struct virtio_net_hdr_mrg_rxbuf *hdr;
int ret;
if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
pr_debug("%s: short packet %i\n", dev->name, len);
dev->stats.rx_length_errors++;
if (vi->mergeable_rx_bufs) {
put_page(virt_to_head_page(buf));
} else if (vi->big_packets) {
give_pages(rq, buf);
} else {
put_page(virt_to_head_page(buf));
}
return 0;
}
if (vi->mergeable_rx_bufs)
skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
else if (vi->big_packets)
skb = receive_big(dev, vi, rq, buf, len);
else
skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
if (unlikely(!skb))
return 0;
hdr = skb_vnet_hdr(skb);
ret = skb->len;
if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
virtio_is_little_endian(vi->vdev))) {
net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n",
dev->name, hdr->hdr.gso_type,
hdr->hdr.gso_size);
goto frame_err;
}
skb->protocol = eth_type_trans(skb, dev);
pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
ntohs(skb->protocol), skb->len, skb->pkt_type);
napi_gro_receive(&rq->napi, skb);
return ret;
frame_err:
dev->stats.rx_frame_errors++;
dev_kfree_skb(skb);
return 0;
}
/* Unlike mergeable buffers, all buffers are allocated to the
* same size, except for the headroom. For this reason we do
* not need to use mergeable_len_to_ctx here - it is enough
* to store the headroom as the context ignoring the truesize.
*/
static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
gfp_t gfp)
{
struct page_frag *alloc_frag = &rq->alloc_frag;
char *buf;
unsigned int xdp_headroom = virtnet_get_headroom(vi);
void *ctx = (void *)(unsigned long)xdp_headroom;
int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom;
int err;
len = SKB_DATA_ALIGN(len) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
return -ENOMEM;
buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
get_page(alloc_frag->page);
alloc_frag->offset += len;
sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom,
vi->hdr_len + GOOD_PACKET_LEN);
err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
if (err < 0)
put_page(virt_to_head_page(buf));
return err;
}
static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
gfp_t gfp)
{
struct page *first, *list = NULL;
char *p;
int i, err, offset;
sg_init_table(rq->sg, MAX_SKB_FRAGS + 2);
/* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
first = get_a_page(rq, gfp);
if (!first) {
if (list)
give_pages(rq, list);
return -ENOMEM;
}
sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE);
/* chain new page in list head to match sg */
first->private = (unsigned long)list;
list = first;
}
first = get_a_page(rq, gfp);
if (!first) {
give_pages(rq, list);
return -ENOMEM;
}
p = page_address(first);
/* rq->sg[0], rq->sg[1] share the same page */
/* a separated rq->sg[0] for header - required in case !any_header_sg */
sg_set_buf(&rq->sg[0], p, vi->hdr_len);
/* rq->sg[1] for data packet, from offset */
offset = sizeof(struct padded_vnet_hdr);
sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset);
/* chain first in list head */
first->private = (unsigned long)list;
err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
first, gfp);
if (err < 0)
give_pages(rq, first);
return err;
}
static unsigned int get_mergeable_buf_len(struct receive_queue *rq,
struct ewma_pkt_len *avg_pkt_len)
{
const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
unsigned int len;
len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len),
rq->min_buf_len, PAGE_SIZE - hdr_len);
return ALIGN(len, L1_CACHE_BYTES);
}
static int add_recvbuf_mergeable(struct virtnet_info *vi,
struct receive_queue *rq, gfp_t gfp)
{
struct page_frag *alloc_frag = &rq->alloc_frag;
unsigned int headroom = virtnet_get_headroom(vi);
char *buf;
void *ctx;
int err;
unsigned int len, hole;
len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len);
if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
return -ENOMEM;
buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
buf += headroom; /* advance address leaving hole at front of pkt */
get_page(alloc_frag->page);
alloc_frag->offset += len + headroom;