forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathaf_packet.c
4707 lines (4024 loc) · 110 KB
/
af_packet.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-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* PACKET - implements raw packet sockets.
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Alan Cox, <[email protected]>
*
* Fixes:
* Alan Cox : verify_area() now used correctly
* Alan Cox : new skbuff lists, look ma no backlogs!
* Alan Cox : tidied skbuff lists.
* Alan Cox : Now uses generic datagram routines I
* added. Also fixed the peek/read crash
* from all old Linux datagram code.
* Alan Cox : Uses the improved datagram code.
* Alan Cox : Added NULL's for socket options.
* Alan Cox : Re-commented the code.
* Alan Cox : Use new kernel side addressing
* Rob Janssen : Correct MTU usage.
* Dave Platt : Counter leaks caused by incorrect
* interrupt locking and some slightly
* dubious gcc output. Can you read
* compiler: it said _VOLATILE_
* Richard Kooijman : Timestamp fixes.
* Alan Cox : New buffers. Use sk->mac.raw.
* Alan Cox : sendmsg/recvmsg support.
* Alan Cox : Protocol setting support
* Alexey Kuznetsov : Untied from IPv4 stack.
* Cyrus Durgin : Fixed kerneld for kmod.
* Michal Ostrowski : Module initialization cleanup.
* Ulises Alonso : Frame number limit removal and
* packet_set_ring memory leak.
* Eric Biederman : Allow for > 8 byte hardware addresses.
* The convention is that longer addresses
* will simply extend the hardware address
* byte arrays at the end of sockaddr_ll
* and packet_mreq.
* Johann Baudy : Added TX RING.
* Chetan Loke : Implemented TPACKET_V3 block abstraction
* layer.
* Copyright (C) 2011, <[email protected]>
*/
#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_packet.h>
#include <linux/wireless.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
#include <linux/errqueue.h>
#include <linux/net_tstamp.h>
#include <linux/percpu.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
#endif
#include <linux/bpf.h>
#include <net/compat.h>
#include "internal.h"
/*
Assumptions:
- If the device has no dev->header_ops->create, there is no LL header
visible above the device. In this case, its hard_header_len should be 0.
The device may prepend its own header internally. In this case, its
needed_headroom should be set to the space needed for it to add its
internal header.
For example, a WiFi driver pretending to be an Ethernet driver should
set its hard_header_len to be the Ethernet header length, and set its
needed_headroom to be (the real WiFi header length - the fake Ethernet
header length).
- packet socket receives packets with pulled ll header,
so that SOCK_RAW should push it back.
On receive:
-----------
Incoming, dev_has_header(dev) == true
mac_header -> ll header
data -> data
Outgoing, dev_has_header(dev) == true
mac_header -> ll header
data -> ll header
Incoming, dev_has_header(dev) == false
mac_header -> data
However drivers often make it point to the ll header.
This is incorrect because the ll header should be invisible to us.
data -> data
Outgoing, dev_has_header(dev) == false
mac_header -> data. ll header is invisible to us.
data -> data
Resume
If dev_has_header(dev) == false we are unable to restore the ll header,
because it is invisible to us.
On transmit:
------------
dev_has_header(dev) == true
mac_header -> ll header
data -> ll header
dev_has_header(dev) == false (ll header is invisible to us)
mac_header -> data
data -> data
We should set network_header on output to the correct position,
packet classifier depends on it.
*/
/* Private packet socket structures. */
/* identical to struct packet_mreq except it has
* a longer address field.
*/
struct packet_mreq_max {
int mr_ifindex;
unsigned short mr_type;
unsigned short mr_alen;
unsigned char mr_address[MAX_ADDR_LEN];
};
union tpacket_uhdr {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
struct tpacket3_hdr *h3;
void *raw;
};
static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
int closing, int tx_ring);
#define V3_ALIGNMENT (8)
#define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT))
#define BLK_PLUS_PRIV(sz_of_priv) \
(BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT))
#define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status)
#define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts)
#define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt)
#define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len)
#define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num)
#define BLOCK_O2PRIV(x) ((x)->offset_to_priv)
struct packet_sock;
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev);
static void *packet_previous_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status);
static void packet_increment_head(struct packet_ring_buffer *buff);
static int prb_curr_blk_in_use(struct tpacket_block_desc *);
static void *prb_dispatch_next_block(struct tpacket_kbdq_core *,
struct packet_sock *);
static void prb_retire_current_block(struct tpacket_kbdq_core *,
struct packet_sock *, unsigned int status);
static int prb_queue_frozen(struct tpacket_kbdq_core *);
static void prb_open_block(struct tpacket_kbdq_core *,
struct tpacket_block_desc *);
static void prb_retire_rx_blk_timer_expired(struct timer_list *);
static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *);
static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
static void prb_clear_rxhash(struct tpacket_kbdq_core *,
struct tpacket3_hdr *);
static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
struct tpacket3_hdr *);
static void packet_flush_mclist(struct sock *sk);
static u16 packet_pick_tx_queue(struct sk_buff *skb);
struct packet_skb_cb {
union {
struct sockaddr_pkt pkt;
union {
/* Trick: alias skb original length with
* ll.sll_family and ll.protocol in order
* to save room.
*/
unsigned int origlen;
struct sockaddr_ll ll;
};
} sa;
};
#define vio_le() virtio_legacy_is_little_endian()
#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb))
#define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc))
#define GET_PBLOCK_DESC(x, bid) \
((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer))
#define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \
((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer))
#define GET_NEXT_PRB_BLK_NUM(x) \
(((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \
((x)->kactive_blk_num+1) : 0)
static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
static void __fanout_link(struct sock *sk, struct packet_sock *po);
static int packet_direct_xmit(struct sk_buff *skb)
{
return dev_direct_xmit(skb, packet_pick_tx_queue(skb));
}
static struct net_device *packet_cached_dev_get(struct packet_sock *po)
{
struct net_device *dev;
rcu_read_lock();
dev = rcu_dereference(po->cached_dev);
if (likely(dev))
dev_hold(dev);
rcu_read_unlock();
return dev;
}
static void packet_cached_dev_assign(struct packet_sock *po,
struct net_device *dev)
{
rcu_assign_pointer(po->cached_dev, dev);
}
static void packet_cached_dev_reset(struct packet_sock *po)
{
RCU_INIT_POINTER(po->cached_dev, NULL);
}
static bool packet_use_direct_xmit(const struct packet_sock *po)
{
return po->xmit == packet_direct_xmit;
}
static u16 packet_pick_tx_queue(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
const struct net_device_ops *ops = dev->netdev_ops;
int cpu = raw_smp_processor_id();
u16 queue_index;
#ifdef CONFIG_XPS
skb->sender_cpu = cpu + 1;
#endif
skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues);
if (ops->ndo_select_queue) {
queue_index = ops->ndo_select_queue(dev, skb, NULL);
queue_index = netdev_cap_txqueue(dev, queue_index);
} else {
queue_index = netdev_pick_tx(dev, skb, NULL);
}
return queue_index;
}
/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
if (!po->running) {
if (po->fanout)
__fanout_link(sk, po);
else
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
}
}
static void register_prot_hook(struct sock *sk)
{
lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
__register_prot_hook(sk);
}
/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
* callers responsibility to take care of this.
*/
static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
lockdep_assert_held_once(&po->bind_lock);
po->running = 0;
if (po->fanout)
__fanout_unlink(sk, po);
else
__dev_remove_pack(&po->prot_hook);
__sock_put(sk);
if (sync) {
spin_unlock(&po->bind_lock);
synchronize_net();
spin_lock(&po->bind_lock);
}
}
static void unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
if (po->running)
__unregister_prot_hook(sk, sync);
}
static inline struct page * __pure pgv_to_page(void *addr)
{
if (is_vmalloc_addr(addr))
return vmalloc_to_page(addr);
return virt_to_page(addr);
}
static void __packet_set_status(struct packet_sock *po, void *frame, int status)
{
union tpacket_uhdr h;
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
h.h1->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
break;
case TPACKET_V2:
h.h2->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
break;
case TPACKET_V3:
h.h3->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
break;
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
}
smp_wmb();
}
static int __packet_get_status(const struct packet_sock *po, void *frame)
{
union tpacket_uhdr h;
smp_rmb();
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
return h.h1->tp_status;
case TPACKET_V2:
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
return h.h2->tp_status;
case TPACKET_V3:
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
return h.h3->tp_status;
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
return 0;
}
}
static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts,
unsigned int flags)
{
struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
if (shhwtstamps &&
(flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts))
return TP_STATUS_TS_RAW_HARDWARE;
if ((flags & SOF_TIMESTAMPING_SOFTWARE) &&
ktime_to_timespec64_cond(skb->tstamp, ts))
return TP_STATUS_TS_SOFTWARE;
return 0;
}
static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
struct sk_buff *skb)
{
union tpacket_uhdr h;
struct timespec64 ts;
__u32 ts_status;
if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
return 0;
h.raw = frame;
/*
* versions 1 through 3 overflow the timestamps in y2106, since they
* all store the seconds in a 32-bit unsigned integer.
* If we create a version 4, that should have a 64-bit timestamp,
* either 64-bit seconds + 32-bit nanoseconds, or just 64-bit
* nanoseconds.
*/
switch (po->tp_version) {
case TPACKET_V1:
h.h1->tp_sec = ts.tv_sec;
h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC;
break;
case TPACKET_V2:
h.h2->tp_sec = ts.tv_sec;
h.h2->tp_nsec = ts.tv_nsec;
break;
case TPACKET_V3:
h.h3->tp_sec = ts.tv_sec;
h.h3->tp_nsec = ts.tv_nsec;
break;
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
}
/* one flush is safe, as both fields always lie on the same cacheline */
flush_dcache_page(pgv_to_page(&h.h1->tp_sec));
smp_wmb();
return ts_status;
}
static void *packet_lookup_frame(const struct packet_sock *po,
const struct packet_ring_buffer *rb,
unsigned int position,
int status)
{
unsigned int pg_vec_pos, frame_offset;
union tpacket_uhdr h;
pg_vec_pos = position / rb->frames_per_block;
frame_offset = position % rb->frames_per_block;
h.raw = rb->pg_vec[pg_vec_pos].buffer +
(frame_offset * rb->frame_size);
if (status != __packet_get_status(po, h.raw))
return NULL;
return h.raw;
}
static void *packet_current_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
return packet_lookup_frame(po, rb, rb->head, status);
}
static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
{
del_timer_sync(&pkc->retire_blk_timer);
}
static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
struct sk_buff_head *rb_queue)
{
struct tpacket_kbdq_core *pkc;
pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
spin_lock_bh(&rb_queue->lock);
pkc->delete_blk_timer = 1;
spin_unlock_bh(&rb_queue->lock);
prb_del_retire_blk_timer(pkc);
}
static void prb_setup_retire_blk_timer(struct packet_sock *po)
{
struct tpacket_kbdq_core *pkc;
pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired,
0);
pkc->retire_blk_timer.expires = jiffies;
}
static int prb_calc_retire_blk_tmo(struct packet_sock *po,
int blk_size_in_bytes)
{
struct net_device *dev;
unsigned int mbits, div;
struct ethtool_link_ksettings ecmd;
int err;
rtnl_lock();
dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex);
if (unlikely(!dev)) {
rtnl_unlock();
return DEFAULT_PRB_RETIRE_TOV;
}
err = __ethtool_get_link_ksettings(dev, &ecmd);
rtnl_unlock();
if (err)
return DEFAULT_PRB_RETIRE_TOV;
/* If the link speed is so slow you don't really
* need to worry about perf anyways
*/
if (ecmd.base.speed < SPEED_1000 ||
ecmd.base.speed == SPEED_UNKNOWN)
return DEFAULT_PRB_RETIRE_TOV;
div = ecmd.base.speed / 1000;
mbits = (blk_size_in_bytes * 8) / (1024 * 1024);
if (div)
mbits /= div;
if (div)
return mbits + 1;
return mbits;
}
static void prb_init_ft_ops(struct tpacket_kbdq_core *p1,
union tpacket_req_u *req_u)
{
p1->feature_req_word = req_u->req3.tp_feature_req_word;
}
static void init_prb_bdqc(struct packet_sock *po,
struct packet_ring_buffer *rb,
struct pgv *pg_vec,
union tpacket_req_u *req_u)
{
struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb);
struct tpacket_block_desc *pbd;
memset(p1, 0x0, sizeof(*p1));
p1->knxt_seq_num = 1;
p1->pkbdq = pg_vec;
pbd = (struct tpacket_block_desc *)pg_vec[0].buffer;
p1->pkblk_start = pg_vec[0].buffer;
p1->kblk_size = req_u->req3.tp_block_size;
p1->knum_blocks = req_u->req3.tp_block_nr;
p1->hdrlen = po->tp_hdrlen;
p1->version = po->tp_version;
p1->last_kactive_blk_num = 0;
po->stats.stats3.tp_freeze_q_cnt = 0;
if (req_u->req3.tp_retire_blk_tov)
p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov;
else
p1->retire_blk_tov = prb_calc_retire_blk_tmo(po,
req_u->req3.tp_block_size);
p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
rwlock_init(&p1->blk_fill_in_prog_lock);
p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
prb_init_ft_ops(p1, req_u);
prb_setup_retire_blk_timer(po);
prb_open_block(p1, pbd);
}
/* Do NOT update the last_blk_num first.
* Assumes sk_buff_head lock is held.
*/
static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc)
{
mod_timer(&pkc->retire_blk_timer,
jiffies + pkc->tov_in_jiffies);
pkc->last_kactive_blk_num = pkc->kactive_blk_num;
}
/*
* Timer logic:
* 1) We refresh the timer only when we open a block.
* By doing this we don't waste cycles refreshing the timer
* on packet-by-packet basis.
*
* With a 1MB block-size, on a 1Gbps line, it will take
* i) ~8 ms to fill a block + ii) memcpy etc.
* In this cut we are not accounting for the memcpy time.
*
* So, if the user sets the 'tmo' to 10ms then the timer
* will never fire while the block is still getting filled
* (which is what we want). However, the user could choose
* to close a block early and that's fine.
*
* But when the timer does fire, we check whether or not to refresh it.
* Since the tmo granularity is in msecs, it is not too expensive
* to refresh the timer, lets say every '8' msecs.
* Either the user can set the 'tmo' or we can derive it based on
* a) line-speed and b) block-size.
* prb_calc_retire_blk_tmo() calculates the tmo.
*
*/
static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
{
struct packet_sock *po =
from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer);
struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
unsigned int frozen;
struct tpacket_block_desc *pbd;
spin_lock(&po->sk.sk_receive_queue.lock);
frozen = prb_queue_frozen(pkc);
pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
if (unlikely(pkc->delete_blk_timer))
goto out;
/* We only need to plug the race when the block is partially filled.
* tpacket_rcv:
* lock(); increment BLOCK_NUM_PKTS; unlock()
* copy_bits() is in progress ...
* timer fires on other cpu:
* we can't retire the current block because copy_bits
* is in progress.
*
*/
if (BLOCK_NUM_PKTS(pbd)) {
/* Waiting for skb_copy_bits to finish... */
write_lock(&pkc->blk_fill_in_prog_lock);
write_unlock(&pkc->blk_fill_in_prog_lock);
}
if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) {
if (!frozen) {
if (!BLOCK_NUM_PKTS(pbd)) {
/* An empty block. Just refresh the timer. */
goto refresh_timer;
}
prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO);
if (!prb_dispatch_next_block(pkc, po))
goto refresh_timer;
else
goto out;
} else {
/* Case 1. Queue was frozen because user-space was
* lagging behind.
*/
if (prb_curr_blk_in_use(pbd)) {
/*
* Ok, user-space is still behind.
* So just refresh the timer.
*/
goto refresh_timer;
} else {
/* Case 2. queue was frozen,user-space caught up,
* now the link went idle && the timer fired.
* We don't have a block to close.So we open this
* block and restart the timer.
* opening a block thaws the queue,restarts timer
* Thawing/timer-refresh is a side effect.
*/
prb_open_block(pkc, pbd);
goto out;
}
}
}
refresh_timer:
_prb_refresh_rx_retire_blk_timer(pkc);
out:
spin_unlock(&po->sk.sk_receive_queue.lock);
}
static void prb_flush_block(struct tpacket_kbdq_core *pkc1,
struct tpacket_block_desc *pbd1, __u32 status)
{
/* Flush everything minus the block header */
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
u8 *start, *end;
start = (u8 *)pbd1;
/* Skip the block header(we know header WILL fit in 4K) */
start += PAGE_SIZE;
end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end);
for (; start < end; start += PAGE_SIZE)
flush_dcache_page(pgv_to_page(start));
smp_wmb();
#endif
/* Now update the block status. */
BLOCK_STATUS(pbd1) = status;
/* Flush the block header */
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
start = (u8 *)pbd1;
flush_dcache_page(pgv_to_page(start));
smp_wmb();
#endif
}
/*
* Side effect:
*
* 1) flush the block
* 2) Increment active_blk_num
*
* Note:We DONT refresh the timer on purpose.
* Because almost always the next block will be opened.
*/
static void prb_close_block(struct tpacket_kbdq_core *pkc1,
struct tpacket_block_desc *pbd1,
struct packet_sock *po, unsigned int stat)
{
__u32 status = TP_STATUS_USER | stat;
struct tpacket3_hdr *last_pkt;
struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
struct sock *sk = &po->sk;
if (atomic_read(&po->tp_drops))
status |= TP_STATUS_LOSING;
last_pkt = (struct tpacket3_hdr *)pkc1->prev;
last_pkt->tp_next_offset = 0;
/* Get the ts of the last pkt */
if (BLOCK_NUM_PKTS(pbd1)) {
h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec;
} else {
/* Ok, we tmo'd - so get the current time.
*
* It shouldn't really happen as we don't close empty
* blocks. See prb_retire_rx_blk_timer_expired().
*/
struct timespec64 ts;
ktime_get_real_ts64(&ts);
h1->ts_last_pkt.ts_sec = ts.tv_sec;
h1->ts_last_pkt.ts_nsec = ts.tv_nsec;
}
smp_wmb();
/* Flush the block */
prb_flush_block(pkc1, pbd1, status);
sk->sk_data_ready(sk);
pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
}
static void prb_thaw_queue(struct tpacket_kbdq_core *pkc)
{
pkc->reset_pending_on_curr_blk = 0;
}
/*
* Side effect of opening a block:
*
* 1) prb_queue is thawed.
* 2) retire_blk_timer is refreshed.
*
*/
static void prb_open_block(struct tpacket_kbdq_core *pkc1,
struct tpacket_block_desc *pbd1)
{
struct timespec64 ts;
struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
smp_rmb();
/* We could have just memset this but we will lose the
* flexibility of making the priv area sticky
*/
BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++;
BLOCK_NUM_PKTS(pbd1) = 0;
BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
ktime_get_real_ts64(&ts);
h1->ts_first_pkt.ts_sec = ts.tv_sec;
h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
pkc1->pkblk_start = (char *)pbd1;
pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN;
pbd1->version = pkc1->version;
pkc1->prev = pkc1->nxt_offset;
pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size;
prb_thaw_queue(pkc1);
_prb_refresh_rx_retire_blk_timer(pkc1);
smp_wmb();
}
/*
* Queue freeze logic:
* 1) Assume tp_block_nr = 8 blocks.
* 2) At time 't0', user opens Rx ring.
* 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7
* 4) user-space is either sleeping or processing block '0'.
* 5) tpacket_rcv is currently filling block '7', since there is no space left,
* it will close block-7,loop around and try to fill block '0'.
* call-flow:
* __packet_lookup_frame_in_block
* prb_retire_current_block()
* prb_dispatch_next_block()
* |->(BLOCK_STATUS == USER) evaluates to true
* 5.1) Since block-0 is currently in-use, we just freeze the queue.
* 6) Now there are two cases:
* 6.1) Link goes idle right after the queue is frozen.
* But remember, the last open_block() refreshed the timer.
* When this timer expires,it will refresh itself so that we can
* re-open block-0 in near future.
* 6.2) Link is busy and keeps on receiving packets. This is a simple
* case and __packet_lookup_frame_in_block will check if block-0
* is free and can now be re-used.
*/
static void prb_freeze_queue(struct tpacket_kbdq_core *pkc,
struct packet_sock *po)
{
pkc->reset_pending_on_curr_blk = 1;
po->stats.stats3.tp_freeze_q_cnt++;
}
#define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT))
/*
* If the next block is free then we will dispatch it
* and return a good offset.
* Else, we will freeze the queue.
* So, caller must check the return value.
*/
static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc,
struct packet_sock *po)
{
struct tpacket_block_desc *pbd;
smp_rmb();
/* 1. Get current block num */
pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
/* 2. If this block is currently in_use then freeze the queue */
if (TP_STATUS_USER & BLOCK_STATUS(pbd)) {
prb_freeze_queue(pkc, po);
return NULL;
}
/*
* 3.
* open this block and return the offset where the first packet
* needs to get stored.
*/
prb_open_block(pkc, pbd);
return (void *)pkc->nxt_offset;
}
static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
struct packet_sock *po, unsigned int status)
{
struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
/* retire/close the current block */
if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) {
/*
* Plug the case where copy_bits() is in progress on
* cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't
* have space to copy the pkt in the current block and
* called prb_retire_current_block()
*
* We don't need to worry about the TMO case because
* the timer-handler already handled this case.
*/
if (!(status & TP_STATUS_BLK_TMO)) {
/* Waiting for skb_copy_bits to finish... */
write_lock(&pkc->blk_fill_in_prog_lock);
write_unlock(&pkc->blk_fill_in_prog_lock);
}
prb_close_block(pkc, pbd, po, status);
return;
}
}
static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd)
{
return TP_STATUS_USER & BLOCK_STATUS(pbd);
}
static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
{
return pkc->reset_pending_on_curr_blk;
}
static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
__releases(&pkc->blk_fill_in_prog_lock)
{
struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb);
read_unlock(&pkc->blk_fill_in_prog_lock);
}
static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb);
}
static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
ppd->hv1.tp_rxhash = 0;
}
static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
if (skb_vlan_tag_present(pkc->skb)) {
ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
} else {
ppd->hv1.tp_vlan_tci = 0;
ppd->hv1.tp_vlan_tpid = 0;
ppd->tp_status = TP_STATUS_AVAILABLE;
}
}
static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
ppd->hv1.tp_padding = 0;
prb_fill_vlan_info(pkc, ppd);
if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
prb_fill_rxhash(pkc, ppd);
else
prb_clear_rxhash(pkc, ppd);
}
static void prb_fill_curr_block(char *curr,
struct tpacket_kbdq_core *pkc,
struct tpacket_block_desc *pbd,
unsigned int len)
__acquires(&pkc->blk_fill_in_prog_lock)
{
struct tpacket3_hdr *ppd;