summaryrefslogtreecommitdiff
path: root/kernel/bpf/trampoline.c
blob: ac021bc43a66b7e2225597b9969de675bfe7c32a (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2019 Facebook */
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ftrace.h>
#include <linux/rbtree_latch.h>
#include <linux/perf_event.h>
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/rcupdate_wait.h>
#include <linux/static_call.h>
#include <linux/bpf_verifier.h>
#include <linux/bpf_lsm.h>
#include <linux/delay.h>

/* dummy _ops. The verifier will operate on target program's ops. */
const struct bpf_verifier_ops bpf_extension_verifier_ops = {
};
const struct bpf_prog_ops bpf_extension_prog_ops = {
};

/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)

static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];

/* serializes access to trampoline_table */
static DEFINE_MUTEX(trampoline_mutex);

#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex);

static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, enum ftrace_ops_cmd cmd)
{
	struct bpf_trampoline *tr = ops->private;
	int ret = 0;

	if (cmd == FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF) {
		/* This is called inside register_ftrace_direct_multi(), so
		 * tr->mutex is already locked.
		 */
		lockdep_assert_held_once(&tr->mutex);

		/* Instead of updating the trampoline here, we propagate
		 * -EAGAIN to register_ftrace_direct(). Then we can
		 * retry register_ftrace_direct() after updating the
		 * trampoline.
		 */
		if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) &&
		    !(tr->flags & BPF_TRAMP_F_ORIG_STACK)) {
			if (WARN_ON_ONCE(tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY))
				return -EBUSY;

			tr->flags |= BPF_TRAMP_F_SHARE_IPMODIFY;
			return -EAGAIN;
		}

		return 0;
	}

	/* The normal locking order is
	 *    tr->mutex => direct_mutex (ftrace.c) => ftrace_lock (ftrace.c)
	 *
	 * The following two commands are called from
	 *
	 *   prepare_direct_functions_for_ipmodify
	 *   cleanup_direct_functions_after_ipmodify
	 *
	 * In both cases, direct_mutex is already locked. Use
	 * mutex_trylock(&tr->mutex) to avoid deadlock in race condition
	 * (something else is making changes to this same trampoline).
	 */
	if (!mutex_trylock(&tr->mutex)) {
		/* sleep 1 ms to make sure whatever holding tr->mutex makes
		 * some progress.
		 */
		msleep(1);
		return -EAGAIN;
	}

	switch (cmd) {
	case FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER:
		tr->flags |= BPF_TRAMP_F_SHARE_IPMODIFY;

		if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) &&
		    !(tr->flags & BPF_TRAMP_F_ORIG_STACK))
			ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */);
		break;
	case FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER:
		tr->flags &= ~BPF_TRAMP_F_SHARE_IPMODIFY;

		if (tr->flags & BPF_TRAMP_F_ORIG_STACK)
			ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	mutex_unlock(&tr->mutex);
	return ret;
}
#endif

bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
{
	enum bpf_attach_type eatype = prog->expected_attach_type;
	enum bpf_prog_type ptype = prog->type;

	return (ptype == BPF_PROG_TYPE_TRACING &&
		(eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
		 eatype == BPF_MODIFY_RETURN)) ||
		(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
}

void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
{
	ksym->start = (unsigned long) data;
	ksym->end = ksym->start + PAGE_SIZE;
	bpf_ksym_add(ksym);
	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
			   PAGE_SIZE, false, ksym->name);
}

void bpf_image_ksym_del(struct bpf_ksym *ksym)
{
	bpf_ksym_del(ksym);
	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
			   PAGE_SIZE, true, ksym->name);
}

static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
{
	struct bpf_trampoline *tr;
	struct hlist_head *head;
	int i;

	mutex_lock(&trampoline_mutex);
	head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)];
	hlist_for_each_entry(tr, head, hlist) {
		if (tr->key == key) {
			refcount_inc(&tr->refcnt);
			goto out;
		}
	}
	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
	if (!tr)
		goto out;
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
	tr->fops = kzalloc(sizeof(struct ftrace_ops), GFP_KERNEL);
	if (!tr->fops) {
		kfree(tr);
		tr = NULL;
		goto out;
	}
	tr->fops->private = tr;
	tr->fops->ops_func = bpf_tramp_ftrace_ops_func;
#endif

	tr->key = key;
	INIT_HLIST_NODE(&tr->hlist);
	hlist_add_head(&tr->hlist, head);
	refcount_set(&tr->refcnt, 1);
	mutex_init(&tr->mutex);
	for (i = 0; i < BPF_TRAMP_MAX; i++)
		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
out:
	mutex_unlock(&trampoline_mutex);
	return tr;
}

static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
{
	void *ip = tr->func.addr;
	int ret;

	if (tr->func.ftrace_managed)
		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
	else
		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);

	return ret;
}

static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr,
			 bool lock_direct_mutex)
{
	void *ip = tr->func.addr;
	int ret;

	if (tr->func.ftrace_managed) {
		if (lock_direct_mutex)
			ret = modify_ftrace_direct(tr->fops, (long)new_addr);
		else
			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
	} else {
		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
	}
	return ret;
}

/* first time registering */
static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
{
	void *ip = tr->func.addr;
	unsigned long faddr;
	int ret;

	faddr = ftrace_location((unsigned long)ip);
	if (faddr) {
		if (!tr->fops)
			return -ENOTSUPP;
		tr->func.ftrace_managed = true;
	}

	if (tr->func.ftrace_managed) {
		ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
		ret = register_ftrace_direct(tr->fops, (long)new_addr);
	} else {
		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
	}

	return ret;
}

static struct bpf_tramp_links *
bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
{
	struct bpf_tramp_link *link;
	struct bpf_tramp_links *tlinks;
	struct bpf_tramp_link **links;
	int kind;

	*total = 0;
	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
	if (!tlinks)
		return ERR_PTR(-ENOMEM);

	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
		tlinks[kind].nr_links = tr->progs_cnt[kind];
		*total += tr->progs_cnt[kind];
		links = tlinks[kind].links;

		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
			*ip_arg |= link->link.prog->call_get_func_ip;
			*links++ = link;
		}
	}
	return tlinks;
}

static void __bpf_tramp_image_put_deferred(struct work_struct *work)
{
	struct bpf_tramp_image *im;

	im = container_of(work, struct bpf_tramp_image, work);
	bpf_image_ksym_del(&im->ksym);
	bpf_jit_free_exec(im->image);
	bpf_jit_uncharge_modmem(PAGE_SIZE);
	percpu_ref_exit(&im->pcref);
	kfree_rcu(im, rcu);
}

/* callback, fexit step 3 or fentry step 2 */
static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu)
{
	struct bpf_tramp_image *im;

	im = container_of(rcu, struct bpf_tramp_image, rcu);
	INIT_WORK(&im->work, __bpf_tramp_image_put_deferred);
	schedule_work(&im->work);
}

/* callback, fexit step 2. Called after percpu_ref_kill confirms. */
static void __bpf_tramp_image_release(struct percpu_ref *pcref)
{
	struct bpf_tramp_image *im;

	im = container_of(pcref, struct bpf_tramp_image, pcref);
	call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
}

/* callback, fexit or fentry step 1 */
static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu)
{
	struct bpf_tramp_image *im;

	im = container_of(rcu, struct bpf_tramp_image, rcu);
	if (im->ip_after_call)
		/* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */
		percpu_ref_kill(&im->pcref);
	else
		/* the case of fentry trampoline */
		call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
}

static void bpf_tramp_image_put(struct bpf_tramp_image *im)
{
	/* The trampoline image that calls original function is using:
	 * rcu_read_lock_trace to protect sleepable bpf progs
	 * rcu_read_lock to protect normal bpf progs
	 * percpu_ref to protect trampoline itself
	 * rcu tasks to protect trampoline asm not covered by percpu_ref
	 * (which are few asm insns before __bpf_tramp_enter and
	 *  after __bpf_tramp_exit)
	 *
	 * The trampoline is unreachable before bpf_tramp_image_put().
	 *
	 * First, patch the trampoline to avoid calling into fexit progs.
	 * The progs will be freed even if the original function is still
	 * executing or sleeping.
	 * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on
	 * first few asm instructions to execute and call into
	 * __bpf_tramp_enter->percpu_ref_get.
	 * Then use percpu_ref_kill to wait for the trampoline and the original
	 * function to finish.
	 * Then use call_rcu_tasks() to make sure few asm insns in
	 * the trampoline epilogue are done as well.
	 *
	 * In !PREEMPT case the task that got interrupted in the first asm
	 * insns won't go through an RCU quiescent state which the
	 * percpu_ref_kill will be waiting for. Hence the first
	 * call_rcu_tasks() is not necessary.
	 */
	if (im->ip_after_call) {
		int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
					     NULL, im->ip_epilogue);
		WARN_ON(err);
		if (IS_ENABLED(CONFIG_PREEMPTION))
			call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
		else
			percpu_ref_kill(&im->pcref);
		return;
	}

	/* The trampoline without fexit and fmod_ret progs doesn't call original
	 * function and doesn't use percpu_ref.
	 * Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
	 * Then use call_rcu_tasks() to wait for the rest of trampoline asm
	 * and normal progs.
	 */
	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
}

static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
{
	struct bpf_tramp_image *im;
	struct bpf_ksym *ksym;
	void *image;
	int err = -ENOMEM;

	im = kzalloc(sizeof(*im), GFP_KERNEL);
	if (!im)
		goto out;

	err = bpf_jit_charge_modmem(PAGE_SIZE);
	if (err)
		goto out_free_im;

	err = -ENOMEM;
	im->image = image = bpf_jit_alloc_exec(PAGE_SIZE);
	if (!image)
		goto out_uncharge;
	set_vm_flush_reset_perms(image);

	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
	if (err)
		goto out_free_image;

	ksym = &im->ksym;
	INIT_LIST_HEAD_RCU(&ksym->lnode);
	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx);
	bpf_image_ksym_add(image, ksym);
	return im;

out_free_image:
	bpf_jit_free_exec(im->image);
out_uncharge:
	bpf_jit_uncharge_modmem(PAGE_SIZE);
out_free_im:
	kfree(im);
out:
	return ERR_PTR(err);
}

static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex)
{
	struct bpf_tramp_image *im;
	struct bpf_tramp_links *tlinks;
	u32 orig_flags = tr->flags;
	bool ip_arg = false;
	int err, total;

	tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
	if (IS_ERR(tlinks))
		return PTR_ERR(tlinks);

	if (total == 0) {
		err = unregister_fentry(tr, tr->cur_image->image);
		bpf_tramp_image_put(tr->cur_image);
		tr->cur_image = NULL;
		tr->selector = 0;
		goto out;
	}

	im = bpf_tramp_image_alloc(tr->key, tr->selector);
	if (IS_ERR(im)) {
		err = PTR_ERR(im);
		goto out;
	}

	/* clear all bits except SHARE_IPMODIFY */
	tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY;

	if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
	    tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) {
		/* NOTE: BPF_TRAMP_F_RESTORE_REGS and BPF_TRAMP_F_SKIP_FRAME
		 * should not be set together.
		 */
		tr->flags |= BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
	} else {
		tr->flags |= BPF_TRAMP_F_RESTORE_REGS;
	}

	if (ip_arg)
		tr->flags |= BPF_TRAMP_F_IP_ARG;

#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
again:
	if ((tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) &&
	    (tr->flags & BPF_TRAMP_F_CALL_ORIG))
		tr->flags |= BPF_TRAMP_F_ORIG_STACK;
#endif

	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
					  &tr->func.model, tr->flags, tlinks,
					  tr->func.addr);
	if (err < 0)
		goto out;

	set_memory_rox((long)im->image, 1);

	WARN_ON(tr->cur_image && tr->selector == 0);
	WARN_ON(!tr->cur_image && tr->selector);
	if (tr->cur_image)
		/* progs already running at this address */
		err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex);
	else
		/* first time registering */
		err = register_fentry(tr, im->image);

#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
	if (err == -EAGAIN) {
		/* -EAGAIN from bpf_tramp_ftrace_ops_func. Now
		 * BPF_TRAMP_F_SHARE_IPMODIFY is set, we can generate the
		 * trampoline again, and retry register.
		 */
		/* reset fops->func and fops->trampoline for re-register */
		tr->fops->func = NULL;
		tr->fops->trampoline = 0;

		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
		set_memory_nx((long)im->image, 1);
		set_memory_rw((long)im->image, 1);
		goto again;
	}
#endif
	if (err)
		goto out;

	if (tr->cur_image)
		bpf_tramp_image_put(tr->cur_image);
	tr->cur_image = im;
	tr->selector++;
out:
	/* If any error happens, restore previous flags */
	if (err)
		tr->flags = orig_flags;
	kfree(tlinks);
	return err;
}

static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
{
	switch (prog->expected_attach_type) {
	case BPF_TRACE_FENTRY:
		return BPF_TRAMP_FENTRY;
	case BPF_MODIFY_RETURN:
		return BPF_TRAMP_MODIFY_RETURN;
	case BPF_TRACE_FEXIT:
		return BPF_TRAMP_FEXIT;
	case BPF_LSM_MAC:
		if (!prog->aux->attach_func_proto->type)
			/* The function returns void, we cannot modify its
			 * return value.
			 */
			return BPF_TRAMP_FEXIT;
		else
			return BPF_TRAMP_MODIFY_RETURN;
	default:
		return BPF_TRAMP_REPLACE;
	}
}

static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
{
	enum bpf_tramp_prog_type kind;
	struct bpf_tramp_link *link_exiting;
	int err = 0;
	int cnt = 0, i;

	kind = bpf_attach_type_to_tramp(link->link.prog);
	if (tr->extension_prog)
		/* cannot attach fentry/fexit if extension prog is attached.
		 * cannot overwrite extension prog either.
		 */
		return -EBUSY;

	for (i = 0; i < BPF_TRAMP_MAX; i++)
		cnt += tr->progs_cnt[i];

	if (kind == BPF_TRAMP_REPLACE) {
		/* Cannot attach extension if fentry/fexit are in use. */
		if (cnt)
			return -EBUSY;
		tr->extension_prog = link->link.prog;
		return bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
					  link->link.prog->bpf_func);
	}
	if (cnt >= BPF_MAX_TRAMP_LINKS)
		return -E2BIG;
	if (!hlist_unhashed(&link->tramp_hlist))
		/* prog already linked */
		return -EBUSY;
	hlist_for_each_entry(link_exiting, &tr->progs_hlist[kind], tramp_hlist) {
		if (link_exiting->link.prog != link->link.prog)
			continue;
		/* prog already linked */
		return -EBUSY;
	}

	hlist_add_head(&link->tramp_hlist, &tr->progs_hlist[kind]);
	tr->progs_cnt[kind]++;
	err = bpf_trampoline_update(tr, true /* lock_direct_mutex */);
	if (err) {
		hlist_del_init(&link->tramp_hlist);
		tr->progs_cnt[kind]--;
	}
	return err;
}

int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
{
	int err;

	mutex_lock(&tr->mutex);
	err = __bpf_trampoline_link_prog(link, tr);
	mutex_unlock(&tr->mutex);
	return err;
}

static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
{
	enum bpf_tramp_prog_type kind;
	int err;

	kind = bpf_attach_type_to_tramp(link->link.prog);
	if (kind == BPF_TRAMP_REPLACE) {
		WARN_ON_ONCE(!tr->extension_prog);
		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
					 tr->extension_prog->bpf_func, NULL);
		tr->extension_prog = NULL;
		return err;
	}
	hlist_del_init(&link->tramp_hlist);
	tr->progs_cnt[kind]--;
	return bpf_trampoline_update(tr, true /* lock_direct_mutex */);
}

/* bpf_trampoline_unlink_prog() should never fail. */
int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
{
	int err;

	mutex_lock(&tr->mutex);
	err = __bpf_trampoline_unlink_prog(link, tr);
	mutex_unlock(&tr->mutex);
	return err;
}

#if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
	struct bpf_shim_tramp_link *shim_link =
		container_of(link, struct bpf_shim_tramp_link, link.link);

	/* paired with 'shim_link->trampoline = tr' in bpf_trampoline_link_cgroup_shim */
	if (!shim_link->trampoline)
		return;

	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline));
	bpf_trampoline_put(shim_link->trampoline);
}

static void bpf_shim_tramp_link_dealloc(struct bpf_link *link)
{
	struct bpf_shim_tramp_link *shim_link =
		container_of(link, struct bpf_shim_tramp_link, link.link);

	kfree(shim_link);
}

static const struct bpf_link_ops bpf_shim_tramp_link_lops = {
	.release = bpf_shim_tramp_link_release,
	.dealloc = bpf_shim_tramp_link_dealloc,
};

static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog,
						     bpf_func_t bpf_func,
						     int cgroup_atype)
{
	struct bpf_shim_tramp_link *shim_link = NULL;
	struct bpf_prog *p;

	shim_link = kzalloc(sizeof(*shim_link), GFP_USER);
	if (!shim_link)
		return NULL;

	p = bpf_prog_alloc(1, 0);
	if (!p) {
		kfree(shim_link);
		return NULL;
	}

	p->jited = false;
	p->bpf_func = bpf_func;

	p->aux->cgroup_atype = cgroup_atype;
	p->aux->attach_func_proto = prog->aux->attach_func_proto;
	p->aux->attach_btf_id = prog->aux->attach_btf_id;
	p->aux->attach_btf = prog->aux->attach_btf;
	btf_get(p->aux->attach_btf);
	p->type = BPF_PROG_TYPE_LSM;
	p->expected_attach_type = BPF_LSM_MAC;
	bpf_prog_inc(p);
	bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
		      &bpf_shim_tramp_link_lops, p);
	bpf_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype);

	return shim_link;
}

static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
						    bpf_func_t bpf_func)
{
	struct bpf_tramp_link *link;
	int kind;

	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
			struct bpf_prog *p = link->link.prog;

			if (p->bpf_func == bpf_func)
				return container_of(link, struct bpf_shim_tramp_link, link);
		}
	}

	return NULL;
}

int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
				    int cgroup_atype)
{
	struct bpf_shim_tramp_link *shim_link = NULL;
	struct bpf_attach_target_info tgt_info = {};
	struct bpf_trampoline *tr;
	bpf_func_t bpf_func;
	u64 key;
	int err;

	err = bpf_check_attach_target(NULL, prog, NULL,
				      prog->aux->attach_btf_id,
				      &tgt_info);
	if (err)
		return err;

	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
					 prog->aux->attach_btf_id);

	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
	tr = bpf_trampoline_get(key, &tgt_info);
	if (!tr)
		return  -ENOMEM;

	mutex_lock(&tr->mutex);

	shim_link = cgroup_shim_find(tr, bpf_func);
	if (shim_link) {
		/* Reusing existing shim attached by the other program. */
		bpf_link_inc(&shim_link->link.link);

		mutex_unlock(&tr->mutex);
		bpf_trampoline_put(tr); /* bpf_trampoline_get above */
		return 0;
	}

	/* Allocate and install new shim. */

	shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype);
	if (!shim_link) {
		err = -ENOMEM;
		goto err;
	}

	err = __bpf_trampoline_link_prog(&shim_link->link, tr);
	if (err)
		goto err;

	shim_link->trampoline = tr;
	/* note, we're still holding tr refcnt from above */

	mutex_unlock(&tr->mutex);

	return 0;
err:
	mutex_unlock(&tr->mutex);

	if (shim_link)
		bpf_link_put(&shim_link->link.link);

	/* have to release tr while _not_ holding its mutex */
	bpf_trampoline_put(tr); /* bpf_trampoline_get above */

	return err;
}

void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
{
	struct bpf_shim_tramp_link *shim_link = NULL;
	struct bpf_trampoline *tr;
	bpf_func_t bpf_func;
	u64 key;

	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
					 prog->aux->attach_btf_id);

	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
	tr = bpf_trampoline_lookup(key);
	if (WARN_ON_ONCE(!tr))
		return;

	mutex_lock(&tr->mutex);
	shim_link = cgroup_shim_find(tr, bpf_func);
	mutex_unlock(&tr->mutex);

	if (shim_link)
		bpf_link_put(&shim_link->link.link);

	bpf_trampoline_put(tr); /* bpf_trampoline_lookup above */
}
#endif

struct bpf_trampoline *bpf_trampoline_get(u64 key,
					  struct bpf_attach_target_info *tgt_info)
{
	struct bpf_trampoline *tr;

	tr = bpf_trampoline_lookup(key);
	if (!tr)
		return NULL;

	mutex_lock(&tr->mutex);
	if (tr->func.addr)
		goto out;

	memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel));
	tr->func.addr = (void *)tgt_info->tgt_addr;
out:
	mutex_unlock(&tr->mutex);
	return tr;
}

void bpf_trampoline_put(struct bpf_trampoline *tr)
{
	int i;

	if (!tr)
		return;
	mutex_lock(&trampoline_mutex);
	if (!refcount_dec_and_test(&tr->refcnt))
		goto out;
	WARN_ON_ONCE(mutex_is_locked(&tr->mutex));

	for (i = 0; i < BPF_TRAMP_MAX; i++)
		if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i])))
			goto out;

	/* This code will be executed even when the last bpf_tramp_image
	 * is alive. All progs are detached from the trampoline and the
	 * trampoline image is patched with jmp into epilogue to skip
	 * fexit progs. The fentry-only trampoline will be freed via
	 * multiple rcu callbacks.
	 */
	hlist_del(&tr->hlist);
	if (tr->fops) {
		ftrace_free_filter(tr->fops);
		kfree(tr->fops);
	}
	kfree(tr);
out:
	mutex_unlock(&trampoline_mutex);
}

#define NO_START_TIME 1
static __always_inline u64 notrace bpf_prog_start_time(void)
{
	u64 start = NO_START_TIME;

	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
		start = sched_clock();
		if (unlikely(!start))
			start = NO_START_TIME;
	}
	return start;
}

/* The logic is similar to bpf_prog_run(), but with an explicit
 * rcu_read_lock() and migrate_disable() which are required
 * for the trampoline. The macro is split into
 * call __bpf_prog_enter
 * call prog->bpf_func
 * call __bpf_prog_exit
 *
 * __bpf_prog_enter returns:
 * 0 - skip execution of the bpf prog
 * 1 - execute bpf prog
 * [2..MAX_U64] - execute bpf prog and record execution time.
 *     This is start time.
 */
static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
	__acquires(RCU)
{
	rcu_read_lock();
	migrate_disable();

	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);

	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
		bpf_prog_inc_misses_counter(prog);
		return 0;
	}
	return bpf_prog_start_time();
}

static void notrace update_prog_stats(struct bpf_prog *prog,
				      u64 start)
{
	struct bpf_prog_stats *stats;

	if (static_branch_unlikely(&bpf_stats_enabled_key) &&
	    /* static_key could be enabled in __bpf_prog_enter*
	     * and disabled in __bpf_prog_exit*.
	     * And vice versa.
	     * Hence check that 'start' is valid.
	     */
	    start > NO_START_TIME) {
		unsigned long flags;

		stats = this_cpu_ptr(prog->stats);
		flags = u64_stats_update_begin_irqsave(&stats->syncp);
		u64_stats_inc(&stats->cnt);
		u64_stats_add(&stats->nsecs, sched_clock() - start);
		u64_stats_update_end_irqrestore(&stats->syncp, flags);
	}
}

static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
					  struct bpf_tramp_run_ctx *run_ctx)
	__releases(RCU)
{
	bpf_reset_run_ctx(run_ctx->saved_run_ctx);

	update_prog_stats(prog, start);
	this_cpu_dec(*(prog->active));
	migrate_enable();
	rcu_read_unlock();
}

static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
					       struct bpf_tramp_run_ctx *run_ctx)
	__acquires(RCU)
{
	/* Runtime stats are exported via actual BPF_LSM_CGROUP
	 * programs, not the shims.
	 */
	rcu_read_lock();
	migrate_disable();

	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);

	return NO_START_TIME;
}

static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
					       struct bpf_tramp_run_ctx *run_ctx)
	__releases(RCU)
{
	bpf_reset_run_ctx(run_ctx->saved_run_ctx);

	migrate_enable();
	rcu_read_unlock();
}

u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
					     struct bpf_tramp_run_ctx *run_ctx)
{
	rcu_read_lock_trace();
	migrate_disable();
	might_fault();

	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
		bpf_prog_inc_misses_counter(prog);
		return 0;
	}

	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);

	return bpf_prog_start_time();
}

void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
					     struct bpf_tramp_run_ctx *run_ctx)
{
	bpf_reset_run_ctx(run_ctx->saved_run_ctx);

	update_prog_stats(prog, start);
	this_cpu_dec(*(prog->active));
	migrate_enable();
	rcu_read_unlock_trace();
}

static u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog,
					      struct bpf_tramp_run_ctx *run_ctx)
{
	rcu_read_lock_trace();
	migrate_disable();
	might_fault();

	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);

	return bpf_prog_start_time();
}

static void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
					      struct bpf_tramp_run_ctx *run_ctx)
{
	bpf_reset_run_ctx(run_ctx->saved_run_ctx);

	update_prog_stats(prog, start);
	migrate_enable();
	rcu_read_unlock_trace();
}

static u64 notrace __bpf_prog_enter(struct bpf_prog *prog,
				    struct bpf_tramp_run_ctx *run_ctx)
	__acquires(RCU)
{
	rcu_read_lock();
	migrate_disable();

	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);

	return bpf_prog_start_time();
}

static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start,
				    struct bpf_tramp_run_ctx *run_ctx)
	__releases(RCU)
{
	bpf_reset_run_ctx(run_ctx->saved_run_ctx);

	update_prog_stats(prog, start);
	migrate_enable();
	rcu_read_unlock();
}

void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr)
{
	percpu_ref_get(&tr->pcref);
}

void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
{
	percpu_ref_put(&tr->pcref);
}

bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog)
{
	bool sleepable = prog->aux->sleepable;

	if (bpf_prog_check_recur(prog))
		return sleepable ? __bpf_prog_enter_sleepable_recur :
			__bpf_prog_enter_recur;

	if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM &&
	    prog->expected_attach_type == BPF_LSM_CGROUP)
		return __bpf_prog_enter_lsm_cgroup;

	return sleepable ? __bpf_prog_enter_sleepable : __bpf_prog_enter;
}

bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
{
	bool sleepable = prog->aux->sleepable;

	if (bpf_prog_check_recur(prog))
		return sleepable ? __bpf_prog_exit_sleepable_recur :
			__bpf_prog_exit_recur;

	if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM &&
	    prog->expected_attach_type == BPF_LSM_CGROUP)
		return __bpf_prog_exit_lsm_cgroup;

	return sleepable ? __bpf_prog_exit_sleepable : __bpf_prog_exit;
}

int __weak
arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
			    const struct btf_func_model *m, u32 flags,
			    struct bpf_tramp_links *tlinks,
			    void *orig_call)
{
	return -ENOTSUPP;
}

static int __init init_trampolines(void)
{
	int i;

	for (i = 0; i < TRAMPOLINE_TABLE_SIZE; i++)
		INIT_HLIST_HEAD(&trampoline_table[i]);
	return 0;
}
late_initcall(init_trampolines);