summaryrefslogtreecommitdiff
path: root/include/linux/bpf_verifier.h
blob: 24213a99cc79db4c41ad17f8b28d23bcc7a8be9f (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
/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 */
#ifndef _LINUX_BPF_VERIFIER_H
#define _LINUX_BPF_VERIFIER_H 1

#include <linux/bpf.h> /* for enum bpf_reg_type */
#include <linux/btf.h> /* for struct btf and btf_id() */
#include <linux/filter.h> /* for MAX_BPF_STACK */
#include <linux/tnum.h>

/* Maximum variable offset umax_value permitted when resolving memory accesses.
 * In practice this is far bigger than any realistic pointer offset; this limit
 * ensures that umax_value + (int)off + (int)size cannot overflow a u64.
 */
#define BPF_MAX_VAR_OFF	(1 << 29)
/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO].  This ensures
 * that converting umax_value to int cannot overflow.
 */
#define BPF_MAX_VAR_SIZ	(1 << 29)
/* size of tmp_str_buf in bpf_verifier.
 * we need at least 306 bytes to fit full stack mask representation
 * (in the "-8,-16,...,-512" form)
 */
#define TMP_STR_BUF_LEN 320

/* Liveness marks, used for registers and spilled-regs (in stack slots).
 * Read marks propagate upwards until they find a write mark; they record that
 * "one of this state's descendants read this reg" (and therefore the reg is
 * relevant for states_equal() checks).
 * Write marks collect downwards and do not propagate; they record that "the
 * straight-line code that reached this state (from its parent) wrote this reg"
 * (and therefore that reads propagated from this state or its descendants
 * should not propagate to its parent).
 * A state with a write mark can receive read marks; it just won't propagate
 * them to its parent, since the write mark is a property, not of the state,
 * but of the link between it and its parent.  See mark_reg_read() and
 * mark_stack_slot_read() in kernel/bpf/verifier.c.
 */
enum bpf_reg_liveness {
	REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
	REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */
	REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */
	REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64,
	REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */
	REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */
};

/* For every reg representing a map value or allocated object pointer,
 * we consider the tuple of (ptr, id) for them to be unique in verifier
 * context and conside them to not alias each other for the purposes of
 * tracking lock state.
 */
struct bpf_active_lock {
	/* This can either be reg->map_ptr or reg->btf. If ptr is NULL,
	 * there's no active lock held, and other fields have no
	 * meaning. If non-NULL, it indicates that a lock is held and
	 * id member has the reg->id of the register which can be >= 0.
	 */
	void *ptr;
	/* This will be reg->id */
	u32 id;
};

#define ITER_PREFIX "bpf_iter_"

enum bpf_iter_state {
	BPF_ITER_STATE_INVALID, /* for non-first slot */
	BPF_ITER_STATE_ACTIVE,
	BPF_ITER_STATE_DRAINED,
};

struct bpf_reg_state {
	/* Ordering of fields matters.  See states_equal() */
	enum bpf_reg_type type;
	/* Fixed part of pointer offset, pointer types only */
	s32 off;
	union {
		/* valid when type == PTR_TO_PACKET */
		int range;

		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
		 *   PTR_TO_MAP_VALUE_OR_NULL
		 */
		struct {
			struct bpf_map *map_ptr;
			/* To distinguish map lookups from outer map
			 * the map_uid is non-zero for registers
			 * pointing to inner maps.
			 */
			u32 map_uid;
		};

		/* for PTR_TO_BTF_ID */
		struct {
			struct btf *btf;
			u32 btf_id;
		};

		struct { /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
			u32 mem_size;
			u32 dynptr_id; /* for dynptr slices */
		};

		/* For dynptr stack slots */
		struct {
			enum bpf_dynptr_type type;
			/* A dynptr is 16 bytes so it takes up 2 stack slots.
			 * We need to track which slot is the first slot
			 * to protect against cases where the user may try to
			 * pass in an address starting at the second slot of the
			 * dynptr.
			 */
			bool first_slot;
		} dynptr;

		/* For bpf_iter stack slots */
		struct {
			/* BTF container and BTF type ID describing
			 * struct bpf_iter_<type> of an iterator state
			 */
			struct btf *btf;
			u32 btf_id;
			/* packing following two fields to fit iter state into 16 bytes */
			enum bpf_iter_state state:2;
			int depth:30;
		} iter;

		/* Max size from any of the above. */
		struct {
			unsigned long raw1;
			unsigned long raw2;
		} raw;

		u32 subprogno; /* for PTR_TO_FUNC */
	};
	/* For scalar types (SCALAR_VALUE), this represents our knowledge of
	 * the actual value.
	 * For pointer types, this represents the variable part of the offset
	 * from the pointed-to object, and is shared with all bpf_reg_states
	 * with the same id as us.
	 */
	struct tnum var_off;
	/* Used to determine if any memory access using this register will
	 * result in a bad access.
	 * These refer to the same value as var_off, not necessarily the actual
	 * contents of the register.
	 */
	s64 smin_value; /* minimum possible (s64)value */
	s64 smax_value; /* maximum possible (s64)value */
	u64 umin_value; /* minimum possible (u64)value */
	u64 umax_value; /* maximum possible (u64)value */
	s32 s32_min_value; /* minimum possible (s32)value */
	s32 s32_max_value; /* maximum possible (s32)value */
	u32 u32_min_value; /* minimum possible (u32)value */
	u32 u32_max_value; /* maximum possible (u32)value */
	/* For PTR_TO_PACKET, used to find other pointers with the same variable
	 * offset, so they can share range knowledge.
	 * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
	 * came from, when one is tested for != NULL.
	 * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation
	 * for the purpose of tracking that it's freed.
	 * For PTR_TO_SOCKET this is used to share which pointers retain the
	 * same reference to the socket, to determine proper reference freeing.
	 * For stack slots that are dynptrs, this is used to track references to
	 * the dynptr to determine proper reference freeing.
	 * Similarly to dynptrs, we use ID to track "belonging" of a reference
	 * to a specific instance of bpf_iter.
	 */
	u32 id;
	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
	 * from a pointer-cast helper, bpf_sk_fullsock() and
	 * bpf_tcp_sock().
	 *
	 * Consider the following where "sk" is a reference counted
	 * pointer returned from "sk = bpf_sk_lookup_tcp();":
	 *
	 * 1: sk = bpf_sk_lookup_tcp();
	 * 2: if (!sk) { return 0; }
	 * 3: fullsock = bpf_sk_fullsock(sk);
	 * 4: if (!fullsock) { bpf_sk_release(sk); return 0; }
	 * 5: tp = bpf_tcp_sock(fullsock);
	 * 6: if (!tp) { bpf_sk_release(sk); return 0; }
	 * 7: bpf_sk_release(sk);
	 * 8: snd_cwnd = tp->snd_cwnd;  // verifier will complain
	 *
	 * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and
	 * "tp" ptr should be invalidated also.  In order to do that,
	 * the reg holding "fullsock" and "sk" need to remember
	 * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id
	 * such that the verifier can reset all regs which have
	 * ref_obj_id matching the sk_reg->id.
	 *
	 * sk_reg->ref_obj_id is set to sk_reg->id at line 1.
	 * sk_reg->id will stay as NULL-marking purpose only.
	 * After NULL-marking is done, sk_reg->id can be reset to 0.
	 *
	 * After "fullsock = bpf_sk_fullsock(sk);" at line 3,
	 * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id.
	 *
	 * After "tp = bpf_tcp_sock(fullsock);" at line 5,
	 * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id
	 * which is the same as sk_reg->ref_obj_id.
	 *
	 * From the verifier perspective, if sk, fullsock and tp
	 * are not NULL, they are the same ptr with different
	 * reg->type.  In particular, bpf_sk_release(tp) is also
	 * allowed and has the same effect as bpf_sk_release(sk).
	 */
	u32 ref_obj_id;
	/* parentage chain for liveness checking */
	struct bpf_reg_state *parent;
	/* Inside the callee two registers can be both PTR_TO_STACK like
	 * R1=fp-8 and R2=fp-8, but one of them points to this function stack
	 * while another to the caller's stack. To differentiate them 'frameno'
	 * is used which is an index in bpf_verifier_state->frame[] array
	 * pointing to bpf_func_state.
	 */
	u32 frameno;
	/* Tracks subreg definition. The stored value is the insn_idx of the
	 * writing insn. This is safe because subreg_def is used before any insn
	 * patching which only happens after main verification finished.
	 */
	s32 subreg_def;
	enum bpf_reg_liveness live;
	/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
	bool precise;
};

enum bpf_stack_slot_type {
	STACK_INVALID,    /* nothing was stored in this stack slot */
	STACK_SPILL,      /* register spilled into stack */
	STACK_MISC,	  /* BPF program wrote some data into this slot */
	STACK_ZERO,	  /* BPF program wrote constant zero */
	/* A dynptr is stored in this stack slot. The type of dynptr
	 * is stored in bpf_stack_state->spilled_ptr.dynptr.type
	 */
	STACK_DYNPTR,
	STACK_ITER,
};

#define BPF_REG_SIZE 8	/* size of eBPF register in bytes */

#define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \
			  (1 << BPF_REG_3) | (1 << BPF_REG_4) | \
			  (1 << BPF_REG_5))

#define BPF_DYNPTR_SIZE		sizeof(struct bpf_dynptr_kern)
#define BPF_DYNPTR_NR_SLOTS		(BPF_DYNPTR_SIZE / BPF_REG_SIZE)

struct bpf_stack_state {
	struct bpf_reg_state spilled_ptr;
	u8 slot_type[BPF_REG_SIZE];
};

struct bpf_reference_state {
	/* Track each reference created with a unique id, even if the same
	 * instruction creates the reference multiple times (eg, via CALL).
	 */
	int id;
	/* Instruction where the allocation of this reference occurred. This
	 * is used purely to inform the user of a reference leak.
	 */
	int insn_idx;
	/* There can be a case like:
	 * main (frame 0)
	 *  cb (frame 1)
	 *   func (frame 3)
	 *    cb (frame 4)
	 * Hence for frame 4, if callback_ref just stored boolean, it would be
	 * impossible to distinguish nested callback refs. Hence store the
	 * frameno and compare that to callback_ref in check_reference_leak when
	 * exiting a callback function.
	 */
	int callback_ref;
};

/* state of the program:
 * type of all registers and stack info
 */
struct bpf_func_state {
	struct bpf_reg_state regs[MAX_BPF_REG];
	/* index of call instruction that called into this func */
	int callsite;
	/* stack frame number of this function state from pov of
	 * enclosing bpf_verifier_state.
	 * 0 = main function, 1 = first callee.
	 */
	u32 frameno;
	/* subprog number == index within subprog_info
	 * zero == main subprog
	 */
	u32 subprogno;
	/* Every bpf_timer_start will increment async_entry_cnt.
	 * It's used to distinguish:
	 * void foo(void) { for(;;); }
	 * void foo(void) { bpf_timer_set_callback(,foo); }
	 */
	u32 async_entry_cnt;
	bool in_callback_fn;
	struct tnum callback_ret_range;
	bool in_async_callback_fn;
	bool in_exception_callback_fn;

	/* The following fields should be last. See copy_func_state() */
	int acquired_refs;
	struct bpf_reference_state *refs;
	int allocated_stack;
	struct bpf_stack_state *stack;
};

struct bpf_idx_pair {
	u32 prev_idx;
	u32 idx;
};

#define MAX_CALL_FRAMES 8
/* Maximum number of register states that can exist at once */
#define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES)
struct bpf_verifier_state {
	/* call stack tracking */
	struct bpf_func_state *frame[MAX_CALL_FRAMES];
	struct bpf_verifier_state *parent;
	/*
	 * 'branches' field is the number of branches left to explore:
	 * 0 - all possible paths from this state reached bpf_exit or
	 * were safely pruned
	 * 1 - at least one path is being explored.
	 * This state hasn't reached bpf_exit
	 * 2 - at least two paths are being explored.
	 * This state is an immediate parent of two children.
	 * One is fallthrough branch with branches==1 and another
	 * state is pushed into stack (to be explored later) also with
	 * branches==1. The parent of this state has branches==1.
	 * The verifier state tree connected via 'parent' pointer looks like:
	 * 1
	 * 1
	 * 2 -> 1 (first 'if' pushed into stack)
	 * 1
	 * 2 -> 1 (second 'if' pushed into stack)
	 * 1
	 * 1
	 * 1 bpf_exit.
	 *
	 * Once do_check() reaches bpf_exit, it calls update_branch_counts()
	 * and the verifier state tree will look:
	 * 1
	 * 1
	 * 2 -> 1 (first 'if' pushed into stack)
	 * 1
	 * 1 -> 1 (second 'if' pushed into stack)
	 * 0
	 * 0
	 * 0 bpf_exit.
	 * After pop_stack() the do_check() will resume at second 'if'.
	 *
	 * If is_state_visited() sees a state with branches > 0 it means
	 * there is a loop. If such state is exactly equal to the current state
	 * it's an infinite loop. Note states_equal() checks for states
	 * equivalency, so two states being 'states_equal' does not mean
	 * infinite loop. The exact comparison is provided by
	 * states_maybe_looping() function. It's a stronger pre-check and
	 * much faster than states_equal().
	 *
	 * This algorithm may not find all possible infinite loops or
	 * loop iteration count may be too high.
	 * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in.
	 */
	u32 branches;
	u32 insn_idx;
	u32 curframe;

	struct bpf_active_lock active_lock;
	bool speculative;
	bool active_rcu_lock;
	/* If this state was ever pointed-to by other state's loop_entry field
	 * this flag would be set to true. Used to avoid freeing such states
	 * while they are still in use.
	 */
	bool used_as_loop_entry;

	/* first and last insn idx of this verifier state */
	u32 first_insn_idx;
	u32 last_insn_idx;
	/* If this state is a part of states loop this field points to some
	 * parent of this state such that:
	 * - it is also a member of the same states loop;
	 * - DFS states traversal starting from initial state visits loop_entry
	 *   state before this state.
	 * Used to compute topmost loop entry for state loops.
	 * State loops might appear because of open coded iterators logic.
	 * See get_loop_entry() for more information.
	 */
	struct bpf_verifier_state *loop_entry;
	/* jmp history recorded from first to last.
	 * backtracking is using it to go from last to first.
	 * For most states jmp_history_cnt is [0-3].
	 * For loops can go up to ~40.
	 */
	struct bpf_idx_pair *jmp_history;
	u32 jmp_history_cnt;
	u32 dfs_depth;
};

#define bpf_get_spilled_reg(slot, frame, mask)				\
	(((slot < frame->allocated_stack / BPF_REG_SIZE) &&		\
	  ((1 << frame->stack[slot].slot_type[0]) & (mask))) \
	 ? &frame->stack[slot].spilled_ptr : NULL)

/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */
#define bpf_for_each_spilled_reg(iter, frame, reg, mask)			\
	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask);		\
	     iter < frame->allocated_stack / BPF_REG_SIZE;		\
	     iter++, reg = bpf_get_spilled_reg(iter, frame, mask))

#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr)   \
	({                                                               \
		struct bpf_verifier_state *___vstate = __vst;            \
		int ___i, ___j;                                          \
		for (___i = 0; ___i <= ___vstate->curframe; ___i++) {    \
			struct bpf_reg_state *___regs;                   \
			__state = ___vstate->frame[___i];                \
			___regs = __state->regs;                         \
			for (___j = 0; ___j < MAX_BPF_REG; ___j++) {     \
				__reg = &___regs[___j];                  \
				(void)(__expr);                          \
			}                                                \
			bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \
				if (!__reg)                              \
					continue;                        \
				(void)(__expr);                          \
			}                                                \
		}                                                        \
	})

/* Invoke __expr over regsiters in __vst, setting __state and __reg */
#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \
	bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr)

/* linked list of verifier states used to prune search */
struct bpf_verifier_state_list {
	struct bpf_verifier_state state;
	struct bpf_verifier_state_list *next;
	int miss_cnt, hit_cnt;
};

struct bpf_loop_inline_state {
	unsigned int initialized:1; /* set to true upon first entry */
	unsigned int fit_for_inline:1; /* true if callback function is the same
					* at each call and flags are always zero
					*/
	u32 callback_subprogno; /* valid when fit_for_inline is true */
};

/* Possible states for alu_state member. */
#define BPF_ALU_SANITIZE_SRC		(1U << 0)
#define BPF_ALU_SANITIZE_DST		(1U << 1)
#define BPF_ALU_NEG_VALUE		(1U << 2)
#define BPF_ALU_NON_POINTER		(1U << 3)
#define BPF_ALU_IMMEDIATE		(1U << 4)
#define BPF_ALU_SANITIZE		(BPF_ALU_SANITIZE_SRC | \
					 BPF_ALU_SANITIZE_DST)

struct bpf_insn_aux_data {
	union {
		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
		unsigned long map_ptr_state;	/* pointer/poison value for maps */
		s32 call_imm;			/* saved imm field of call insn */
		u32 alu_limit;			/* limit for add/sub register with pointer */
		struct {
			u32 map_index;		/* index into used_maps[] */
			u32 map_off;		/* offset from value base address */
		};
		struct {
			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
			union {
				struct {
					struct btf *btf;
					u32 btf_id;	/* btf_id for struct typed var */
				};
				u32 mem_size;	/* mem_size for non-struct typed var */
			};
		} btf_var;
		/* if instruction is a call to bpf_loop this field tracks
		 * the state of the relevant registers to make decision about inlining
		 */
		struct bpf_loop_inline_state loop_inline_state;
	};
	union {
		/* remember the size of type passed to bpf_obj_new to rewrite R1 */
		u64 obj_new_size;
		/* remember the offset of node field within type to rewrite */
		u64 insert_off;
	};
	struct btf_struct_meta *kptr_struct_meta;
	u64 map_key_state; /* constant (32 bit) key tracking for maps */
	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
	bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
	bool zext_dst; /* this insn zero extends dst reg */
	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
	u8 alu_state; /* used in combination with alu_limit */

	/* below fields are initialized once */
	unsigned int orig_idx; /* original instruction index */
	bool jmp_point;
	bool prune_point;
	/* ensure we check state equivalence and save state checkpoint and
	 * this instruction, regardless of any heuristics
	 */
	bool force_checkpoint;
};

#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */

#define BPF_VERIFIER_TMP_LOG_SIZE	1024

struct bpf_verifier_log {
	/* Logical start and end positions of a "log window" of the verifier log.
	 * start_pos == 0 means we haven't truncated anything.
	 * Once truncation starts to happen, start_pos + len_total == end_pos,
	 * except during log reset situations, in which (end_pos - start_pos)
	 * might get smaller than len_total (see bpf_vlog_reset()).
	 * Generally, (end_pos - start_pos) gives number of useful data in
	 * user log buffer.
	 */
	u64 start_pos;
	u64 end_pos;
	char __user *ubuf;
	u32 level;
	u32 len_total;
	u32 len_max;
	char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
};

#define BPF_LOG_LEVEL1	1
#define BPF_LOG_LEVEL2	2
#define BPF_LOG_STATS	4
#define BPF_LOG_FIXED	8
#define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
#define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED)
#define BPF_LOG_KERNEL	(BPF_LOG_MASK + 1) /* kernel internal flag */
#define BPF_LOG_MIN_ALIGNMENT 8U
#define BPF_LOG_ALIGNMENT 40U

static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
{
	return log && log->level;
}

#define BPF_MAX_SUBPROGS 256

struct bpf_subprog_info {
	/* 'start' has to be the first field otherwise find_subprog() won't work */
	u32 start; /* insn idx of function entry point */
	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
	u16 stack_depth; /* max. stack depth used by this function */
	bool has_tail_call;
	bool tail_call_reachable;
	bool has_ld_abs;
	bool is_cb;
	bool is_async_cb;
	bool is_exception_cb;
};

struct bpf_verifier_env;

struct backtrack_state {
	struct bpf_verifier_env *env;
	u32 frame;
	u32 reg_masks[MAX_CALL_FRAMES];
	u64 stack_masks[MAX_CALL_FRAMES];
};

struct bpf_id_pair {
	u32 old;
	u32 cur;
};

struct bpf_idmap {
	u32 tmp_id_gen;
	struct bpf_id_pair map[BPF_ID_MAP_SIZE];
};

struct bpf_idset {
	u32 count;
	u32 ids[BPF_ID_MAP_SIZE];
};

/* single container for all structs
 * one verifier_env per bpf_check() call
 */
struct bpf_verifier_env {
	u32 insn_idx;
	u32 prev_insn_idx;
	struct bpf_prog *prog;		/* eBPF program being verified */
	const struct bpf_verifier_ops *ops;
	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
	int stack_size;			/* number of states to be processed */
	bool strict_alignment;		/* perform strict pointer alignment checks */
	bool test_state_freq;		/* test verifier with different pruning frequency */
	struct bpf_verifier_state *cur_state; /* current verifier state */
	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
	struct bpf_verifier_state_list *free_list;
	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
	struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */
	u32 used_map_cnt;		/* number of used maps */
	u32 used_btf_cnt;		/* number of used BTF objects */
	u32 id_gen;			/* used to generate unique reg IDs */
	u32 hidden_subprog_cnt;		/* number of hidden subprogs */
	int exception_callback_subprog;
	bool explore_alu_limits;
	bool allow_ptr_leaks;
	bool allow_uninit_stack;
	bool bpf_capable;
	bool bypass_spec_v1;
	bool bypass_spec_v4;
	bool seen_direct_write;
	bool seen_exception;
	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
	const struct bpf_line_info *prev_linfo;
	struct bpf_verifier_log log;
	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */
	union {
		struct bpf_idmap idmap_scratch;
		struct bpf_idset idset_scratch;
	};
	struct {
		int *insn_state;
		int *insn_stack;
		int cur_stack;
	} cfg;
	struct backtrack_state bt;
	u32 pass_cnt; /* number of times do_check() was called */
	u32 subprog_cnt;
	/* number of instructions analyzed by the verifier */
	u32 prev_insn_processed, insn_processed;
	/* number of jmps, calls, exits analyzed so far */
	u32 prev_jmps_processed, jmps_processed;
	/* total verification time */
	u64 verification_time;
	/* maximum number of verifier states kept in 'branching' instructions */
	u32 max_states_per_insn;
	/* total number of allocated verifier states */
	u32 total_states;
	/* some states are freed during program analysis.
	 * this is peak number of states. this number dominates kernel
	 * memory consumption during verification
	 */
	u32 peak_states;
	/* longest register parentage chain walked for liveness marking */
	u32 longest_mark_read_walk;
	bpfptr_t fd_array;

	/* bit mask to keep track of whether a register has been accessed
	 * since the last time the function state was printed
	 */
	u32 scratched_regs;
	/* Same as scratched_regs but for stack slots */
	u64 scratched_stack_slots;
	u64 prev_log_pos, prev_insn_print_pos;
	/* buffer used to generate temporary string representations,
	 * e.g., in reg_type_str() to generate reg_type string
	 */
	char tmp_str_buf[TMP_STR_BUF_LEN];
};

__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
				      const char *fmt, va_list args);
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
					   const char *fmt, ...);
__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
			    const char *fmt, ...);
int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level,
		  char __user *log_buf, u32 log_size);
void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos);
int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual);

static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *cur = env->cur_state;

	return cur->frame[cur->curframe];
}

static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
{
	return cur_func(env)->regs;
}

int bpf_prog_offload_verifier_prep(struct bpf_prog *prog);
int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
				 int insn_idx, int prev_insn_idx);
int bpf_prog_offload_finalize(struct bpf_verifier_env *env);
void
bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
			      struct bpf_insn *insn);
void
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);

int check_ptr_off_reg(struct bpf_verifier_env *env,
		      const struct bpf_reg_state *reg, int regno);
int check_func_arg_reg_off(struct bpf_verifier_env *env,
			   const struct bpf_reg_state *reg, int regno,
			   enum bpf_arg_type arg_type);
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
		   u32 regno, u32 mem_size);

/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
					     struct btf *btf, u32 btf_id)
{
	if (tgt_prog)
		return ((u64)tgt_prog->aux->id << 32) | btf_id;
	else
		return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id;
}

/* unpack the IDs from the key as constructed above */
static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id)
{
	if (obj_id)
		*obj_id = key >> 32;
	if (btf_id)
		*btf_id = key & 0x7FFFFFFF;
}

int bpf_check_attach_target(struct bpf_verifier_log *log,
			    const struct bpf_prog *prog,
			    const struct bpf_prog *tgt_prog,
			    u32 btf_id,
			    struct bpf_attach_target_info *tgt_info);
void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab);

int mark_chain_precision(struct bpf_verifier_env *env, int regno);

#define BPF_BASE_TYPE_MASK	GENMASK(BPF_BASE_TYPE_BITS - 1, 0)

/* extract base type from bpf_{arg, return, reg}_type. */
static inline u32 base_type(u32 type)
{
	return type & BPF_BASE_TYPE_MASK;
}

/* extract flags from an extended type. See bpf_type_flag in bpf.h. */
static inline u32 type_flag(u32 type)
{
	return type & ~BPF_BASE_TYPE_MASK;
}

/* only use after check_attach_btf_id() */
static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
{
	return prog->type == BPF_PROG_TYPE_EXT ?
		prog->aux->dst_prog->type : prog->type;
}

static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
{
	switch (resolve_prog_type(prog)) {
	case BPF_PROG_TYPE_TRACING:
		return prog->expected_attach_type != BPF_TRACE_ITER;
	case BPF_PROG_TYPE_STRUCT_OPS:
	case BPF_PROG_TYPE_LSM:
		return false;
	default:
		return true;
	}
}

#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF)

static inline bool bpf_type_has_unsafe_modifiers(u32 type)
{
	return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS;
}

#endif /* _LINUX_BPF_VERIFIER_H */