aboutsummaryrefslogtreecommitdiff
path: root/net/core/skmsg.c
blob: 25cdbb20f3a037e3c9f324a41449034001f3b48d (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */

#include <linux/skmsg.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>

#include <net/sock.h>
#include <net/tcp.h>
#include <net/tls.h>

static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
{
	if (msg->sg.end > msg->sg.start &&
	    elem_first_coalesce < msg->sg.end)
		return true;

	if (msg->sg.end < msg->sg.start &&
	    (elem_first_coalesce > msg->sg.start ||
	     elem_first_coalesce < msg->sg.end))
		return true;

	return false;
}

int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
		 int elem_first_coalesce)
{
	struct page_frag *pfrag = sk_page_frag(sk);
	int ret = 0;

	len -= msg->sg.size;
	while (len > 0) {
		struct scatterlist *sge;
		u32 orig_offset;
		int use, i;

		if (!sk_page_frag_refill(sk, pfrag))
			return -ENOMEM;

		orig_offset = pfrag->offset;
		use = min_t(int, len, pfrag->size - orig_offset);
		if (!sk_wmem_schedule(sk, use))
			return -ENOMEM;

		i = msg->sg.end;
		sk_msg_iter_var_prev(i);
		sge = &msg->sg.data[i];

		if (sk_msg_try_coalesce_ok(msg, elem_first_coalesce) &&
		    sg_page(sge) == pfrag->page &&
		    sge->offset + sge->length == orig_offset) {
			sge->length += use;
		} else {
			if (sk_msg_full(msg)) {
				ret = -ENOSPC;
				break;
			}

			sge = &msg->sg.data[msg->sg.end];
			sg_unmark_end(sge);
			sg_set_page(sge, pfrag->page, use, orig_offset);
			get_page(pfrag->page);
			sk_msg_iter_next(msg, end);
		}

		sk_mem_charge(sk, use);
		msg->sg.size += use;
		pfrag->offset += use;
		len -= use;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_alloc);

int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
		 u32 off, u32 len)
{
	int i = src->sg.start;
	struct scatterlist *sge = sk_msg_elem(src, i);
	struct scatterlist *sgd = NULL;
	u32 sge_len, sge_off;

	while (off) {
		if (sge->length > off)
			break;
		off -= sge->length;
		sk_msg_iter_var_next(i);
		if (i == src->sg.end && off)
			return -ENOSPC;
		sge = sk_msg_elem(src, i);
	}

	while (len) {
		sge_len = sge->length - off;
		if (sge_len > len)
			sge_len = len;

		if (dst->sg.end)
			sgd = sk_msg_elem(dst, dst->sg.end - 1);

		if (sgd &&
		    (sg_page(sge) == sg_page(sgd)) &&
		    (sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) {
			sgd->length += sge_len;
			dst->sg.size += sge_len;
		} else if (!sk_msg_full(dst)) {
			sge_off = sge->offset + off;
			sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off);
		} else {
			return -ENOSPC;
		}

		off = 0;
		len -= sge_len;
		sk_mem_charge(sk, sge_len);
		sk_msg_iter_var_next(i);
		if (i == src->sg.end && len)
			return -ENOSPC;
		sge = sk_msg_elem(src, i);
	}

	return 0;
}
EXPORT_SYMBOL_GPL(sk_msg_clone);

void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes)
{
	int i = msg->sg.start;

	do {
		struct scatterlist *sge = sk_msg_elem(msg, i);

		if (bytes < sge->length) {
			sge->length -= bytes;
			sge->offset += bytes;
			sk_mem_uncharge(sk, bytes);
			break;
		}

		sk_mem_uncharge(sk, sge->length);
		bytes -= sge->length;
		sge->length = 0;
		sge->offset = 0;
		sk_msg_iter_var_next(i);
	} while (bytes && i != msg->sg.end);
	msg->sg.start = i;
}
EXPORT_SYMBOL_GPL(sk_msg_return_zero);

void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes)
{
	int i = msg->sg.start;

	do {
		struct scatterlist *sge = &msg->sg.data[i];
		int uncharge = (bytes < sge->length) ? bytes : sge->length;

		sk_mem_uncharge(sk, uncharge);
		bytes -= uncharge;
		sk_msg_iter_var_next(i);
	} while (i != msg->sg.end);
}
EXPORT_SYMBOL_GPL(sk_msg_return);

static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
			    bool charge)
{
	struct scatterlist *sge = sk_msg_elem(msg, i);
	u32 len = sge->length;

	/* When the skb owns the memory we free it from consume_skb path. */
	if (!msg->skb) {
		if (charge)
			sk_mem_uncharge(sk, len);
		put_page(sg_page(sge));
	}
	memset(sge, 0, sizeof(*sge));
	return len;
}

static int __sk_msg_free(struct sock *sk, struct sk_msg *msg, u32 i,
			 bool charge)
{
	struct scatterlist *sge = sk_msg_elem(msg, i);
	int freed = 0;

	while (msg->sg.size) {
		msg->sg.size -= sge->length;
		freed += sk_msg_free_elem(sk, msg, i, charge);
		sk_msg_iter_var_next(i);
		sk_msg_check_to_free(msg, i, msg->sg.size);
		sge = sk_msg_elem(msg, i);
	}
	consume_skb(msg->skb);
	sk_msg_init(msg);
	return freed;
}

int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg)
{
	return __sk_msg_free(sk, msg, msg->sg.start, false);
}
EXPORT_SYMBOL_GPL(sk_msg_free_nocharge);

int sk_msg_free(struct sock *sk, struct sk_msg *msg)
{
	return __sk_msg_free(sk, msg, msg->sg.start, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free);

static void __sk_msg_free_partial(struct sock *sk, struct sk_msg *msg,
				  u32 bytes, bool charge)
{
	struct scatterlist *sge;
	u32 i = msg->sg.start;

	while (bytes) {
		sge = sk_msg_elem(msg, i);
		if (!sge->length)
			break;
		if (bytes < sge->length) {
			if (charge)
				sk_mem_uncharge(sk, bytes);
			sge->length -= bytes;
			sge->offset += bytes;
			msg->sg.size -= bytes;
			break;
		}

		msg->sg.size -= sge->length;
		bytes -= sge->length;
		sk_msg_free_elem(sk, msg, i, charge);
		sk_msg_iter_var_next(i);
		sk_msg_check_to_free(msg, i, bytes);
	}
	msg->sg.start = i;
}

void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes)
{
	__sk_msg_free_partial(sk, msg, bytes, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free_partial);

void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
				  u32 bytes)
{
	__sk_msg_free_partial(sk, msg, bytes, false);
}

void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
{
	int trim = msg->sg.size - len;
	u32 i = msg->sg.end;

	if (trim <= 0) {
		WARN_ON(trim < 0);
		return;
	}

	sk_msg_iter_var_prev(i);
	msg->sg.size = len;
	while (msg->sg.data[i].length &&
	       trim >= msg->sg.data[i].length) {
		trim -= msg->sg.data[i].length;
		sk_msg_free_elem(sk, msg, i, true);
		sk_msg_iter_var_prev(i);
		if (!trim)
			goto out;
	}

	msg->sg.data[i].length -= trim;
	sk_mem_uncharge(sk, trim);
	/* Adjust copybreak if it falls into the trimmed part of last buf */
	if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
		msg->sg.copybreak = msg->sg.data[i].length;
out:
	sk_msg_iter_var_next(i);
	msg->sg.end = i;

	/* If we trim data a full sg elem before curr pointer update
	 * copybreak and current so that any future copy operations
	 * start at new copy location.
	 * However trimed data that has not yet been used in a copy op
	 * does not require an update.
	 */
	if (!msg->sg.size) {
		msg->sg.curr = msg->sg.start;
		msg->sg.copybreak = 0;
	} else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
		   sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
		sk_msg_iter_var_prev(i);
		msg->sg.curr = i;
		msg->sg.copybreak = msg->sg.data[i].length;
	}
}
EXPORT_SYMBOL_GPL(sk_msg_trim);

int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
			      struct sk_msg *msg, u32 bytes)
{
	int i, maxpages, ret = 0, num_elems = sk_msg_elem_used(msg);
	const int to_max_pages = MAX_MSG_FRAGS;
	struct page *pages[MAX_MSG_FRAGS];
	ssize_t orig, copied, use, offset;

	orig = msg->sg.size;
	while (bytes > 0) {
		i = 0;
		maxpages = to_max_pages - num_elems;
		if (maxpages == 0) {
			ret = -EFAULT;
			goto out;
		}

		copied = iov_iter_get_pages(from, pages, bytes, maxpages,
					    &offset);
		if (copied <= 0) {
			ret = -EFAULT;
			goto out;
		}

		iov_iter_advance(from, copied);
		bytes -= copied;
		msg->sg.size += copied;

		while (copied) {
			use = min_t(int, copied, PAGE_SIZE - offset);
			sg_set_page(&msg->sg.data[msg->sg.end],
				    pages[i], use, offset);
			sg_unmark_end(&msg->sg.data[msg->sg.end]);
			sk_mem_charge(sk, use);

			offset = 0;
			copied -= use;
			sk_msg_iter_next(msg, end);
			num_elems++;
			i++;
		}
		/* When zerocopy is mixed with sk_msg_*copy* operations we
		 * may have a copybreak set in this case clear and prefer
		 * zerocopy remainder when possible.
		 */
		msg->sg.copybreak = 0;
		msg->sg.curr = msg->sg.end;
	}
out:
	/* Revert iov_iter updates, msg will need to use 'trim' later if it
	 * also needs to be cleared.
	 */
	if (ret)
		iov_iter_revert(from, msg->sg.size - orig);
	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_zerocopy_from_iter);

int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
			     struct sk_msg *msg, u32 bytes)
{
	int ret = -ENOSPC, i = msg->sg.curr;
	struct scatterlist *sge;
	u32 copy, buf_size;
	void *to;

	do {
		sge = sk_msg_elem(msg, i);
		/* This is possible if a trim operation shrunk the buffer */
		if (msg->sg.copybreak >= sge->length) {
			msg->sg.copybreak = 0;
			sk_msg_iter_var_next(i);
			if (i == msg->sg.end)
				break;
			sge = sk_msg_elem(msg, i);
		}

		buf_size = sge->length - msg->sg.copybreak;
		copy = (buf_size > bytes) ? bytes : buf_size;
		to = sg_virt(sge) + msg->sg.copybreak;
		msg->sg.copybreak += copy;
		if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY)
			ret = copy_from_iter_nocache(to, copy, from);
		else
			ret = copy_from_iter(to, copy, from);
		if (ret != copy) {
			ret = -EFAULT;
			goto out;
		}
		bytes -= copy;
		if (!bytes)
			break;
		msg->sg.copybreak = 0;
		sk_msg_iter_var_next(i);
	} while (i != msg->sg.end);
out:
	msg->sg.curr = i;
	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);

static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
						  struct sk_buff *skb)
{
	struct sk_msg *msg;

	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
		return NULL;

	if (!sk_rmem_schedule(sk, skb, skb->truesize))
		return NULL;

	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
	if (unlikely(!msg))
		return NULL;

	sk_msg_init(msg);
	return msg;
}

static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
					struct sk_psock *psock,
					struct sock *sk,
					struct sk_msg *msg)
{
	int num_sge, copied;

	/* skb linearize may fail with ENOMEM, but lets simply try again
	 * later if this happens. Under memory pressure we don't want to
	 * drop the skb. We need to linearize the skb so that the mapping
	 * in skb_to_sgvec can not error.
	 */
	if (skb_linearize(skb))
		return -EAGAIN;
	num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
	if (unlikely(num_sge < 0)) {
		kfree(msg);
		return num_sge;
	}

	copied = skb->len;
	msg->sg.start = 0;
	msg->sg.size = copied;
	msg->sg.end = num_sge;
	msg->skb = skb;

	sk_psock_queue_msg(psock, msg);
	sk_psock_data_ready(sk, psock);
	return copied;
}

static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);

static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
{
	struct sock *sk = psock->sk;
	struct sk_msg *msg;

	/* If we are receiving on the same sock skb->sk is already assigned,
	 * skip memory accounting and owner transition seeing it already set
	 * correctly.
	 */
	if (unlikely(skb->sk == sk))
		return sk_psock_skb_ingress_self(psock, skb);
	msg = sk_psock_create_ingress_msg(sk, skb);
	if (!msg)
		return -EAGAIN;

	/* This will transition ownership of the data from the socket where
	 * the BPF program was run initiating the redirect to the socket
	 * we will eventually receive this data on. The data will be released
	 * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
	 * into user buffers.
	 */
	skb_set_owner_r(skb, sk);
	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
}

/* Puts an skb on the ingress queue of the socket already assigned to the
 * skb. In this case we do not need to check memory limits or skb_set_owner_r
 * because the skb is already accounted for here.
 */
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
{
	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
	struct sock *sk = psock->sk;

	if (unlikely(!msg))
		return -EAGAIN;
	sk_msg_init(msg);
	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
}

static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
			       u32 off, u32 len, bool ingress)
{
	if (!ingress) {
		if (!sock_writeable(psock->sk))
			return -EAGAIN;
		return skb_send_sock_locked(psock->sk, skb, off, len);
	}
	return sk_psock_skb_ingress(psock, skb);
}

static void sk_psock_backlog(struct work_struct *work)
{
	struct sk_psock *psock = container_of(work, struct sk_psock, work);
	struct sk_psock_work_state *state = &psock->work_state;
	struct sk_buff *skb;
	bool ingress;
	u32 len, off;
	int ret;

	/* Lock sock to avoid losing sk_socket during loop. */
	lock_sock(psock->sk);
	if (state->skb) {
		skb = state->skb;
		len = state->len;
		off = state->off;
		state->skb = NULL;
		goto start;
	}

	while ((skb = skb_dequeue(&psock->ingress_skb))) {
		len = skb->len;
		off = 0;
start:
		ingress = tcp_skb_bpf_ingress(skb);
		do {
			ret = -EIO;
			if (likely(psock->sk->sk_socket))
				ret = sk_psock_handle_skb(psock, skb, off,
							  len, ingress);
			if (ret <= 0) {
				if (ret == -EAGAIN) {
					state->skb = skb;
					state->len = len;
					state->off = off;
					goto end;
				}
				/* Hard errors break pipe and stop xmit. */
				sk_psock_report_error(psock, ret ? -ret : EPIPE);
				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
				kfree_skb(skb);
				goto end;
			}
			off += ret;
			len -= ret;
		} while (len);

		if (!ingress)
			kfree_skb(skb);
	}
end:
	release_sock(psock->sk);
}

struct sk_psock *sk_psock_init(struct sock *sk, int node)
{
	struct sk_psock *psock;
	struct proto *prot;

	write_lock_bh(&sk->sk_callback_lock);

	if (inet_csk_has_ulp(sk)) {
		psock = ERR_PTR(-EINVAL);
		goto out;
	}

	if (sk->sk_user_data) {
		psock = ERR_PTR(-EBUSY);
		goto out;
	}

	psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
	if (!psock) {
		psock = ERR_PTR(-ENOMEM);
		goto out;
	}

	prot = READ_ONCE(sk->sk_prot);
	psock->sk = sk;
	psock->eval = __SK_NONE;
	psock->sk_proto = prot;
	psock->saved_unhash = prot->unhash;
	psock->saved_close = prot->close;
	psock->saved_write_space = sk->sk_write_space;

	INIT_LIST_HEAD(&psock->link);
	spin_lock_init(&psock->link_lock);

	INIT_WORK(&psock->work, sk_psock_backlog);
	INIT_LIST_HEAD(&psock->ingress_msg);
	skb_queue_head_init(&psock->ingress_skb);

	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
	refcount_set(&psock->refcnt, 1);

	rcu_assign_sk_user_data_nocopy(sk, psock);
	sock_hold(sk);

out:
	write_unlock_bh(&sk->sk_callback_lock);
	return psock;
}
EXPORT_SYMBOL_GPL(sk_psock_init);

struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock)
{
	struct sk_psock_link *link;

	spin_lock_bh(&psock->link_lock);
	link = list_first_entry_or_null(&psock->link, struct sk_psock_link,
					list);
	if (link)
		list_del(&link->list);
	spin_unlock_bh(&psock->link_lock);
	return link;
}

void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
{
	struct sk_msg *msg, *tmp;

	list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
		list_del(&msg->list);
		sk_msg_free(psock->sk, msg);
		kfree(msg);
	}
}

static void sk_psock_zap_ingress(struct sk_psock *psock)
{
	__skb_queue_purge(&psock->ingress_skb);
	__sk_psock_purge_ingress_msg(psock);
}

static void sk_psock_link_destroy(struct sk_psock *psock)
{
	struct sk_psock_link *link, *tmp;

	list_for_each_entry_safe(link, tmp, &psock->link, list) {
		list_del(&link->list);
		sk_psock_free_link(link);
	}
}

static void sk_psock_destroy_deferred(struct work_struct *gc)
{
	struct sk_psock *psock = container_of(gc, struct sk_psock, gc);

	/* No sk_callback_lock since already detached. */

	/* Parser has been stopped */
	if (psock->progs.skb_parser)
		strp_done(&psock->parser.strp);

	cancel_work_sync(&psock->work);

	psock_progs_drop(&psock->progs);

	sk_psock_link_destroy(psock);
	sk_psock_cork_free(psock);
	sk_psock_zap_ingress(psock);

	if (psock->sk_redir)
		sock_put(psock->sk_redir);
	sock_put(psock->sk);
	kfree(psock);
}

void sk_psock_destroy(struct rcu_head *rcu)
{
	struct sk_psock *psock = container_of(rcu, struct sk_psock, rcu);

	INIT_WORK(&psock->gc, sk_psock_destroy_deferred);
	schedule_work(&psock->gc);
}
EXPORT_SYMBOL_GPL(sk_psock_destroy);

void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
	sk_psock_cork_free(psock);
	sk_psock_zap_ingress(psock);

	write_lock_bh(&sk->sk_callback_lock);
	sk_psock_restore_proto(sk, psock);
	rcu_assign_sk_user_data(sk, NULL);
	if (psock->progs.skb_parser)
		sk_psock_stop_strp(sk, psock);
	else if (psock->progs.skb_verdict)
		sk_psock_stop_verdict(sk, psock);
	write_unlock_bh(&sk->sk_callback_lock);
	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);

	call_rcu(&psock->rcu, sk_psock_destroy);
}
EXPORT_SYMBOL_GPL(sk_psock_drop);

static int sk_psock_map_verd(int verdict, bool redir)
{
	switch (verdict) {
	case SK_PASS:
		return redir ? __SK_REDIRECT : __SK_PASS;
	case SK_DROP:
	default:
		break;
	}

	return __SK_DROP;
}

int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
			 struct sk_msg *msg)
{
	struct bpf_prog *prog;
	int ret;

	rcu_read_lock();
	prog = READ_ONCE(psock->progs.msg_parser);
	if (unlikely(!prog)) {
		ret = __SK_PASS;
		goto out;
	}

	sk_msg_compute_data_pointers(msg);
	msg->sk = sk;
	ret = bpf_prog_run_pin_on_cpu(prog, msg);
	ret = sk_psock_map_verd(ret, msg->sk_redir);
	psock->apply_bytes = msg->apply_bytes;
	if (ret == __SK_REDIRECT) {
		if (psock->sk_redir)
			sock_put(psock->sk_redir);
		psock->sk_redir = msg->sk_redir;
		if (!psock->sk_redir) {
			ret = __SK_DROP;
			goto out;
		}
		sock_hold(psock->sk_redir);
	}
out:
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);

static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog,
			    struct sk_buff *skb)
{
	bpf_compute_data_end_sk_skb(skb);
	return bpf_prog_run_pin_on_cpu(prog, skb);
}

static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
{
	struct sk_psock_parser *parser;

	parser = container_of(strp, struct sk_psock_parser, strp);
	return container_of(parser, struct sk_psock, parser);
}

static void sk_psock_skb_redirect(struct sk_buff *skb)
{
	struct sk_psock *psock_other;
	struct sock *sk_other;

	sk_other = tcp_skb_bpf_redirect_fetch(skb);
	/* This error is a buggy BPF program, it returned a redirect
	 * return code, but then didn't set a redirect interface.
	 */
	if (unlikely(!sk_other)) {
		kfree_skb(skb);
		return;
	}
	psock_other = sk_psock(sk_other);
	/* This error indicates the socket is being torn down or had another
	 * error that caused the pipe to break. We can't send a packet on
	 * a socket that is in this state so we drop the skb.
	 */
	if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
	    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
		kfree_skb(skb);
		return;
	}

	skb_queue_tail(&psock_other->ingress_skb, skb);
	schedule_work(&psock_other->work);
}

static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
{
	switch (verdict) {
	case __SK_REDIRECT:
		skb_set_owner_r(skb, sk);
		sk_psock_skb_redirect(skb);
		break;
	case __SK_PASS:
	case __SK_DROP:
	default:
		break;
	}
}

int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
{
	struct bpf_prog *prog;
	int ret = __SK_PASS;

	rcu_read_lock();
	prog = READ_ONCE(psock->progs.skb_verdict);
	if (likely(prog)) {
		/* We skip full set_owner_r here because if we do a SK_PASS
		 * or SK_DROP we can skip skb memory accounting and use the
		 * TLS context.
		 */
		skb->sk = psock->sk;
		tcp_skb_bpf_redirect_clear(skb);
		ret = sk_psock_bpf_run(psock, prog, skb);
		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
		skb->sk = NULL;
	}
	sk_psock_tls_verdict_apply(skb, psock->sk, ret);
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);

static void sk_psock_verdict_apply(struct sk_psock *psock,
				   struct sk_buff *skb, int verdict)
{
	struct tcp_skb_cb *tcp;
	struct sock *sk_other;
	int err = -EIO;

	switch (verdict) {
	case __SK_PASS:
		sk_other = psock->sk;
		if (sock_flag(sk_other, SOCK_DEAD) ||
		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
			goto out_free;
		}

		tcp = TCP_SKB_CB(skb);
		tcp->bpf.flags |= BPF_F_INGRESS;

		/* If the queue is empty then we can submit directly
		 * into the msg queue. If its not empty we have to
		 * queue work otherwise we may get OOO data. Otherwise,
		 * if sk_psock_skb_ingress errors will be handled by
		 * retrying later from workqueue.
		 */
		if (skb_queue_empty(&psock->ingress_skb)) {
			err = sk_psock_skb_ingress_self(psock, skb);
		}
		if (err < 0) {
			skb_queue_tail(&psock->ingress_skb, skb);
			schedule_work(&psock->work);
		}
		break;
	case __SK_REDIRECT:
		sk_psock_skb_redirect(skb);
		break;
	case __SK_DROP:
	default:
out_free:
		kfree_skb(skb);
	}
}

static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
	struct sk_psock *psock;
	struct bpf_prog *prog;
	int ret = __SK_DROP;
	struct sock *sk;

	rcu_read_lock();
	sk = strp->sk;
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
		kfree_skb(skb);
		goto out;
	}
	skb_set_owner_r(skb, sk);
	prog = READ_ONCE(psock->progs.skb_verdict);
	if (likely(prog)) {
		tcp_skb_bpf_redirect_clear(skb);
		ret = sk_psock_bpf_run(psock, prog, skb);
		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
	}
	sk_psock_verdict_apply(psock, skb, ret);
out:
	rcu_read_unlock();
}

static int sk_psock_strp_read_done(struct strparser *strp, int err)
{
	return err;
}

static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
{
	struct sk_psock *psock = sk_psock_from_strp(strp);
	struct bpf_prog *prog;
	int ret = skb->len;

	rcu_read_lock();
	prog = READ_ONCE(psock->progs.skb_parser);
	if (likely(prog)) {
		skb->sk = psock->sk;
		ret = sk_psock_bpf_run(psock, prog, skb);
		skb->sk = NULL;
	}
	rcu_read_unlock();
	return ret;
}

/* Called with socket lock held. */
static void sk_psock_strp_data_ready(struct sock *sk)
{
	struct sk_psock *psock;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock)) {
		if (tls_sw_has_ctx_rx(sk)) {
			psock->parser.saved_data_ready(sk);
		} else {
			write_lock_bh(&sk->sk_callback_lock);
			strp_data_ready(&psock->parser.strp);
			write_unlock_bh(&sk->sk_callback_lock);
		}
	}
	rcu_read_unlock();
}

static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
				 unsigned int offset, size_t orig_len)
{
	struct sock *sk = (struct sock *)desc->arg.data;
	struct sk_psock *psock;
	struct bpf_prog *prog;
	int ret = __SK_DROP;
	int len = skb->len;

	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb) {
		desc->error = -ENOMEM;
		return 0;
	}

	rcu_read_lock();
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
		len = 0;
		kfree_skb(skb);
		goto out;
	}
	skb_set_owner_r(skb, sk);
	prog = READ_ONCE(psock->progs.skb_verdict);
	if (likely(prog)) {
		tcp_skb_bpf_redirect_clear(skb);
		ret = sk_psock_bpf_run(psock, prog, skb);
		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
	}
	sk_psock_verdict_apply(psock, skb, ret);
out:
	rcu_read_unlock();
	return len;
}

static void sk_psock_verdict_data_ready(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;
	read_descriptor_t desc;

	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
		return;

	desc.arg.data = sk;
	desc.error = 0;
	desc.count = 1;

	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
}

static void sk_psock_write_space(struct sock *sk)
{
	struct sk_psock *psock;
	void (*write_space)(struct sock *sk) = NULL;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock)) {
		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
			schedule_work(&psock->work);
		write_space = psock->saved_write_space;
	}
	rcu_read_unlock();
	if (write_space)
		write_space(sk);
}

int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
{
	static const struct strp_callbacks cb = {
		.rcv_msg	= sk_psock_strp_read,
		.read_sock_done	= sk_psock_strp_read_done,
		.parse_msg	= sk_psock_strp_parse,
	};

	psock->parser.enabled = false;
	return strp_init(&psock->parser.strp, sk, &cb);
}

void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
{
	struct sk_psock_parser *parser = &psock->parser;

	if (parser->enabled)
		return;

	parser->saved_data_ready = sk->sk_data_ready;
	sk->sk_data_ready = sk_psock_verdict_data_ready;
	sk->sk_write_space = sk_psock_write_space;
	parser->enabled = true;
}

void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
{
	struct sk_psock_parser *parser = &psock->parser;

	if (parser->enabled)
		return;

	parser->saved_data_ready = sk->sk_data_ready;
	sk->sk_data_ready = sk_psock_strp_data_ready;
	sk->sk_write_space = sk_psock_write_space;
	parser->enabled = true;
}

void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
{
	struct sk_psock_parser *parser = &psock->parser;

	if (!parser->enabled)
		return;

	sk->sk_data_ready = parser->saved_data_ready;
	parser->saved_data_ready = NULL;
	strp_stop(&parser->strp);
	parser->enabled = false;
}

void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
{
	struct sk_psock_parser *parser = &psock->parser;

	if (!parser->enabled)
		return;

	sk->sk_data_ready = parser->saved_data_ready;
	parser->saved_data_ready = NULL;
	parser->enabled = false;
}