summaryrefslogtreecommitdiff
path: root/include/linux/bpf_verifier.h
blob: 26e40de9ef55f881a2282291670e810bff8318be (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
/* 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/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)

/* 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 */
};

struct bpf_reg_state {
	/* Ordering of fields matters.  See states_equal() */
	enum bpf_reg_type type;
	union {
		/* valid when type == PTR_TO_PACKET */
		u16 range;

		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
		 *   PTR_TO_MAP_VALUE_OR_NULL
		 */
		struct bpf_map *map_ptr;

		u32 btf_id; /* for PTR_TO_BTF_ID */

		/* Max size from any of the above. */
		unsigned long raw;
	};
	/* Fixed part of pointer offset, pointer types only */
	s32 off;
	/* 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_SOCKET this is used to share which pointers retain the
	 * same reference to the socket, to determine proper reference freeing.
	 */
	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;
	/* 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 */
	/* 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 */
};

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

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;
};

/* 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_stack_depth
	 * zero == main subprog
	 */
	u32 subprogno;

	/* 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
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
	 * equvalency, 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;
	u32 active_spin_lock;
	bool speculative;

	/* first and last insn idx of this verifier state */
	u32 first_insn_idx;
	u32 last_insn_idx;
	/* 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;
};

#define bpf_get_spilled_reg(slot, frame)				\
	(((slot < frame->allocated_stack / BPF_REG_SIZE) &&		\
	  (frame->stack[slot].slot_type[0] == STACK_SPILL))		\
	 ? &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)			\
	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame);		\
	     iter < frame->allocated_stack / BPF_REG_SIZE;		\
	     iter++, reg = bpf_get_spilled_reg(iter, frame))

/* 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;
};

/* Possible states for alu_state member. */
#define BPF_ALU_SANITIZE_SRC		1U
#define BPF_ALU_SANITIZE_DST		2U
#define BPF_ALU_NEG_VALUE		(1U << 2)
#define BPF_ALU_NON_POINTER		(1U << 3)
#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 */
		};
	};
	u64 map_key_state; /* constant (32 bit) key tracking for maps */
	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
	int sanitize_stack_off; /* stack slot to be cleared */
	bool seen; /* this insn was processed by the verifier */
	bool zext_dst; /* this insn zero extends dst reg */
	u8 alu_state; /* used in combination with alu_limit */
	bool prune_point;
	unsigned int orig_idx; /* original instruction index */
};

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

#define BPF_VERIFIER_TMP_LOG_SIZE	1024

struct bpf_verifier_log {
	u32 level;
	char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
	char __user *ubuf;
	u32 len_used;
	u32 len_total;
};

static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
{
	return log->len_used >= log->len_total - 1;
}

#define BPF_LOG_LEVEL1	1
#define BPF_LOG_LEVEL2	2
#define BPF_LOG_STATS	4
#define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
#define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS)
#define BPF_LOG_KERNEL	(BPF_LOG_MASK + 1) /* kernel internal flag */

static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
{
	return (log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
		log->level == BPF_LOG_KERNEL;
}

#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 */
};

/* 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 */
	u32 used_map_cnt;		/* number of used maps */
	u32 id_gen;			/* used to generate unique reg IDs */
	bool allow_ptr_leaks;
	bool seen_direct_write;
	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 + 1];
	struct {
		int *insn_state;
		int *insn_stack;
		int cur_stack;
	} cfg;
	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;
};

__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, ...);

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);

#endif /* _LINUX_BPF_VERIFIER_H */