verifier.c 100.8 KB
Newer Older
A
Alexei Starovoitov 已提交
1
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
A
Alexei Starovoitov 已提交
2
 * Copyright (c) 2016 Facebook
A
Alexei Starovoitov 已提交
3 4 5 6 7 8 9 10 11 12 13 14 15 16
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
17
#include <linux/bpf_verifier.h>
A
Alexei Starovoitov 已提交
18 19 20 21
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
22
#include <linux/stringify.h>
A
Alexei Starovoitov 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35

/* bpf_check() is a static code analyzer that walks eBPF program
 * instruction by instruction and updates register/stack state.
 * All paths of conditional branches are analyzed until 'bpf_exit' insn.
 *
 * The first pass is depth-first-search to check that the program is a DAG.
 * It rejects the following programs:
 * - larger than BPF_MAXINSNS insns
 * - if loop is present (detected via back-edge)
 * - unreachable insns exist (shouldn't be a forest. program = one function)
 * - out of bounds or malformed jumps
 * The second pass is all possible path descent from the 1st insn.
 * Since it's analyzing all pathes through the program, the length of the
36
 * analysis is limited to 64k insn, which may be hit even if total number of
A
Alexei Starovoitov 已提交
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
 * insn is less then 4K, but there are too many branches that change stack/regs.
 * Number of 'branches to be analyzed' is limited to 1k
 *
 * On entry to each instruction, each register has a type, and the instruction
 * changes the types of the registers depending on instruction semantics.
 * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
 * copied to R1.
 *
 * All registers are 64-bit.
 * R0 - return register
 * R1-R5 argument passing registers
 * R6-R9 callee saved registers
 * R10 - frame pointer read-only
 *
 * At the start of BPF program the register R1 contains a pointer to bpf_context
 * and has type PTR_TO_CTX.
 *
 * Verifier tracks arithmetic operations on pointers in case:
 *    BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
 * 1st insn copies R10 (which has FRAME_PTR) type into R1
 * and 2nd arithmetic instruction is pattern matched to recognize
 * that it wants to construct a pointer to some element within stack.
 * So after 2nd insn, the register R1 has type PTR_TO_STACK
 * (and -20 constant is saved for further stack bounds checking).
 * Meaning that this reg is a pointer to stack plus known immediate constant.
 *
 * Most of the time the registers have UNKNOWN_VALUE type, which
 * means the register has some value, but it's not a valid pointer.
 * (like pointer plus pointer becomes UNKNOWN_VALUE type)
 *
 * When verifier sees load or store instructions the type of base register
 * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer
 * types recognized by check_mem_access() function.
 *
 * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
 * and the range of [ptr, ptr + map's value_size) is accessible.
 *
 * registers used to pass values to function calls are checked against
 * function argument constraints.
 *
 * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
 * It means that the register type passed to this function must be
 * PTR_TO_STACK and it will be used inside the function as
 * 'pointer to map element key'
 *
 * For example the argument constraints for bpf_map_lookup_elem():
 *   .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 *   .arg1_type = ARG_CONST_MAP_PTR,
 *   .arg2_type = ARG_PTR_TO_MAP_KEY,
 *
 * ret_type says that this function returns 'pointer to map elem value or null'
 * function expects 1st argument to be a const pointer to 'struct bpf_map' and
 * 2nd argument should be a pointer to stack, which will be used inside
 * the helper function as a pointer to map element key.
 *
 * On the kernel side the helper function looks like:
 * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 * {
 *    struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 *    void *key = (void *) (unsigned long) r2;
 *    void *value;
 *
 *    here kernel can access 'key' and 'map' pointers safely, knowing that
 *    [key, key + map->key_size) bytes are valid and were initialized on
 *    the stack of eBPF program.
 * }
 *
 * Corresponding eBPF program may look like:
 *    BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),  // after this insn R2 type is FRAME_PTR
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
 *    BPF_LD_MAP_FD(BPF_REG_1, map_fd),      // after this insn R1 type is CONST_PTR_TO_MAP
 *    BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 * here verifier looks at prototype of map_lookup_elem() and sees:
 * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
 * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
 *
 * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
 * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
 * and were initialized prior to this call.
 * If it's ok, then verifier allows this BPF_CALL insn and looks at
 * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
 * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
 * returns ether pointer to map value or NULL.
 *
 * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
 * insn, the register holding that pointer in the true branch changes state to
 * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
 * branch. See check_cond_jmp_op().
 *
 * After the call R0 is set to return type of the function and registers R1-R5
 * are set to NOT_INIT to indicate that they are no longer readable.
 */

131
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
132
struct bpf_verifier_stack_elem {
133 134 135 136
	/* verifer state is 'st'
	 * before processing instruction 'insn_idx'
	 * and after processing instruction 'prev_insn_idx'
	 */
137
	struct bpf_verifier_state st;
138 139
	int insn_idx;
	int prev_insn_idx;
140
	struct bpf_verifier_stack_elem *next;
141 142
};

143 144 145
#define BPF_COMPLEXITY_LIMIT_INSNS	65536
#define BPF_COMPLEXITY_LIMIT_STACK	1024

146 147
#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)

148 149
struct bpf_call_arg_meta {
	struct bpf_map *map_ptr;
150
	bool raw_mode;
151
	bool pkt_access;
152 153
	int regno;
	int access_size;
154 155
};

156 157 158 159 160 161 162 163 164 165 166 167
/* verbose verifier prints what it's seeing
 * bpf_check() is called under lock, so no race to access these global vars
 */
static u32 log_level, log_size, log_len;
static char *log_buf;

static DEFINE_MUTEX(bpf_verifier_lock);

/* log_level controls verbosity level of eBPF verifier.
 * verbose() is used to dump the verification trace to the log, so the user
 * can figure out what's wrong with the program
 */
168
static __printf(1, 2) void verbose(const char *fmt, ...)
169 170 171 172 173 174 175 176 177 178 179
{
	va_list args;

	if (log_level == 0 || log_len >= log_size - 1)
		return;

	va_start(args, fmt);
	log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
	va_end(args);
}

180 181 182 183 184 185 186 187
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
	[NOT_INIT]		= "?",
	[UNKNOWN_VALUE]		= "inv",
	[PTR_TO_CTX]		= "ctx",
	[CONST_PTR_TO_MAP]	= "map_ptr",
	[PTR_TO_MAP_VALUE]	= "map_value",
	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
188
	[PTR_TO_MAP_VALUE_ADJ]	= "map_value_adj",
189 190 191
	[FRAME_PTR]		= "fp",
	[PTR_TO_STACK]		= "fp",
	[CONST_IMM]		= "imm",
A
Alexei Starovoitov 已提交
192 193
	[PTR_TO_PACKET]		= "pkt",
	[PTR_TO_PACKET_END]	= "pkt_end",
194 195
};

196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211
#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
static const char * const func_id_str[] = {
	__BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
};
#undef __BPF_FUNC_STR_FN

static const char *func_id_name(int id)
{
	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);

	if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
		return func_id_str[id];
	else
		return "unknown";
}

212
static void print_verifier_state(struct bpf_verifier_state *state)
213
{
214
	struct bpf_reg_state *reg;
215 216 217 218
	enum bpf_reg_type t;
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
A
Alexei Starovoitov 已提交
219 220
		reg = &state->regs[i];
		t = reg->type;
221 222 223 224
		if (t == NOT_INIT)
			continue;
		verbose(" R%d=%s", i, reg_type_str[t]);
		if (t == CONST_IMM || t == PTR_TO_STACK)
A
Alexei Starovoitov 已提交
225 226 227 228 229 230
			verbose("%lld", reg->imm);
		else if (t == PTR_TO_PACKET)
			verbose("(id=%d,off=%d,r=%d)",
				reg->id, reg->off, reg->range);
		else if (t == UNKNOWN_VALUE && reg->imm)
			verbose("%lld", reg->imm);
231
		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
232 233
			 t == PTR_TO_MAP_VALUE_OR_NULL ||
			 t == PTR_TO_MAP_VALUE_ADJ)
234
			verbose("(ks=%d,vs=%d,id=%u)",
A
Alexei Starovoitov 已提交
235
				reg->map_ptr->key_size,
236 237
				reg->map_ptr->value_size,
				reg->id);
238
		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
239 240
			verbose(",min_value=%lld",
				(long long)reg->min_value);
241 242 243
		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
			verbose(",max_value=%llu",
				(unsigned long long)reg->max_value);
244
	}
245
	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
A
Alexei Starovoitov 已提交
246
		if (state->stack_slot_type[i] == STACK_SPILL)
247
			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
A
Alexei Starovoitov 已提交
248
				reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
249 250 251 252
	}
	verbose("\n");
}

253 254 255 256 257 258 259 260 261 262 263
static const char *const bpf_class_string[] = {
	[BPF_LD]    = "ld",
	[BPF_LDX]   = "ldx",
	[BPF_ST]    = "st",
	[BPF_STX]   = "stx",
	[BPF_ALU]   = "alu",
	[BPF_JMP]   = "jmp",
	[BPF_RET]   = "BUG",
	[BPF_ALU64] = "alu64",
};

264
static const char *const bpf_alu_string[16] = {
265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
	[BPF_ADD >> 4]  = "+=",
	[BPF_SUB >> 4]  = "-=",
	[BPF_MUL >> 4]  = "*=",
	[BPF_DIV >> 4]  = "/=",
	[BPF_OR  >> 4]  = "|=",
	[BPF_AND >> 4]  = "&=",
	[BPF_LSH >> 4]  = "<<=",
	[BPF_RSH >> 4]  = ">>=",
	[BPF_NEG >> 4]  = "neg",
	[BPF_MOD >> 4]  = "%=",
	[BPF_XOR >> 4]  = "^=",
	[BPF_MOV >> 4]  = "=",
	[BPF_ARSH >> 4] = "s>>=",
	[BPF_END >> 4]  = "endian",
};

static const char *const bpf_ldst_string[] = {
	[BPF_W >> 3]  = "u32",
	[BPF_H >> 3]  = "u16",
	[BPF_B >> 3]  = "u8",
	[BPF_DW >> 3] = "u64",
};

288
static const char *const bpf_jmp_string[16] = {
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
	[BPF_JA >> 4]   = "jmp",
	[BPF_JEQ >> 4]  = "==",
	[BPF_JGT >> 4]  = ">",
	[BPF_JGE >> 4]  = ">=",
	[BPF_JSET >> 4] = "&",
	[BPF_JNE >> 4]  = "!=",
	[BPF_JSGT >> 4] = "s>",
	[BPF_JSGE >> 4] = "s>=",
	[BPF_CALL >> 4] = "call",
	[BPF_EXIT >> 4] = "exit",
};

static void print_bpf_insn(struct bpf_insn *insn)
{
	u8 class = BPF_CLASS(insn->code);

	if (class == BPF_ALU || class == BPF_ALU64) {
		if (BPF_SRC(insn->code) == BPF_X)
			verbose("(%02x) %sr%d %s %sr%d\n",
				insn->code, class == BPF_ALU ? "(u32) " : "",
				insn->dst_reg,
				bpf_alu_string[BPF_OP(insn->code) >> 4],
				class == BPF_ALU ? "(u32) " : "",
				insn->src_reg);
		else
			verbose("(%02x) %sr%d %s %s%d\n",
				insn->code, class == BPF_ALU ? "(u32) " : "",
				insn->dst_reg,
				bpf_alu_string[BPF_OP(insn->code) >> 4],
				class == BPF_ALU ? "(u32) " : "",
				insn->imm);
	} else if (class == BPF_STX) {
		if (BPF_MODE(insn->code) == BPF_MEM)
			verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->dst_reg,
				insn->off, insn->src_reg);
		else if (BPF_MODE(insn->code) == BPF_XADD)
			verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->dst_reg, insn->off,
				insn->src_reg);
		else
			verbose("BUG_%02x\n", insn->code);
	} else if (class == BPF_ST) {
		if (BPF_MODE(insn->code) != BPF_MEM) {
			verbose("BUG_st_%02x\n", insn->code);
			return;
		}
		verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
			insn->code,
			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
			insn->dst_reg,
			insn->off, insn->imm);
	} else if (class == BPF_LDX) {
		if (BPF_MODE(insn->code) != BPF_MEM) {
			verbose("BUG_ldx_%02x\n", insn->code);
			return;
		}
		verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
			insn->code, insn->dst_reg,
			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
			insn->src_reg, insn->off);
	} else if (class == BPF_LD) {
		if (BPF_MODE(insn->code) == BPF_ABS) {
			verbose("(%02x) r0 = *(%s *)skb[%d]\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->imm);
		} else if (BPF_MODE(insn->code) == BPF_IND) {
			verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->src_reg, insn->imm);
		} else if (BPF_MODE(insn->code) == BPF_IMM) {
			verbose("(%02x) r%d = 0x%x\n",
				insn->code, insn->dst_reg, insn->imm);
		} else {
			verbose("BUG_ld_%02x\n", insn->code);
			return;
		}
	} else if (class == BPF_JMP) {
		u8 opcode = BPF_OP(insn->code);

		if (opcode == BPF_CALL) {
376 377
			verbose("(%02x) call %s#%d\n", insn->code,
				func_id_name(insn->imm), insn->imm);
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
		} else if (insn->code == (BPF_JMP | BPF_JA)) {
			verbose("(%02x) goto pc%+d\n",
				insn->code, insn->off);
		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
			verbose("(%02x) exit\n", insn->code);
		} else if (BPF_SRC(insn->code) == BPF_X) {
			verbose("(%02x) if r%d %s r%d goto pc%+d\n",
				insn->code, insn->dst_reg,
				bpf_jmp_string[BPF_OP(insn->code) >> 4],
				insn->src_reg, insn->off);
		} else {
			verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
				insn->code, insn->dst_reg,
				bpf_jmp_string[BPF_OP(insn->code) >> 4],
				insn->imm, insn->off);
		}
	} else {
		verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
	}
}

399
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx)
400
{
401
	struct bpf_verifier_stack_elem *elem;
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
	int insn_idx;

	if (env->head == NULL)
		return -1;

	memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
	insn_idx = env->head->insn_idx;
	if (prev_insn_idx)
		*prev_insn_idx = env->head->prev_insn_idx;
	elem = env->head->next;
	kfree(env->head);
	env->head = elem;
	env->stack_size--;
	return insn_idx;
}

418 419
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
					     int insn_idx, int prev_insn_idx)
420
{
421
	struct bpf_verifier_stack_elem *elem;
422

423
	elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
424 425 426 427 428 429 430 431 432
	if (!elem)
		goto err;

	memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
	elem->insn_idx = insn_idx;
	elem->prev_insn_idx = prev_insn_idx;
	elem->next = env->head;
	env->head = elem;
	env->stack_size++;
433
	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
		verbose("BPF program is too complex\n");
		goto err;
	}
	return &elem->st;
err:
	/* pop all elements and return */
	while (pop_stack(env, NULL) >= 0);
	return NULL;
}

#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};

449
static void init_reg_state(struct bpf_reg_state *regs)
450 451 452 453 454 455
{
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
		regs[i].type = NOT_INIT;
		regs[i].imm = 0;
456 457
		regs[i].min_value = BPF_REGISTER_MIN_RANGE;
		regs[i].max_value = BPF_REGISTER_MAX_RANGE;
458 459 460 461 462 463 464 465 466
	}

	/* frame pointer */
	regs[BPF_REG_FP].type = FRAME_PTR;

	/* 1st arg to a function */
	regs[BPF_REG_1].type = PTR_TO_CTX;
}

467
static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
468 469
{
	regs[regno].type = UNKNOWN_VALUE;
470
	regs[regno].id = 0;
471 472 473
	regs[regno].imm = 0;
}

474 475 476 477 478 479
static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
{
	BUG_ON(regno >= MAX_BPF_REG);
	__mark_reg_unknown_value(regs, regno);
}

480 481 482 483 484 485
static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
{
	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
	regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
}

486 487 488 489 490 491 492
static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
					     u32 regno)
{
	mark_reg_unknown_value(regs, regno);
	reset_reg_range_values(regs, regno);
}

493 494 495 496 497 498
enum reg_arg_type {
	SRC_OP,		/* register is used as source operand */
	DST_OP,		/* register is used as destination operand */
	DST_OP_NO_MARK	/* same as above, check only, don't mark */
};

499
static int check_reg_arg(struct bpf_reg_state *regs, u32 regno,
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
			 enum reg_arg_type t)
{
	if (regno >= MAX_BPF_REG) {
		verbose("R%d is invalid\n", regno);
		return -EINVAL;
	}

	if (t == SRC_OP) {
		/* check whether register used as source operand can be read */
		if (regs[regno].type == NOT_INIT) {
			verbose("R%d !read_ok\n", regno);
			return -EACCES;
		}
	} else {
		/* check whether register used as dest operand can be written to */
		if (regno == BPF_REG_FP) {
			verbose("frame pointer is read only\n");
			return -EACCES;
		}
		if (t == DST_OP)
			mark_reg_unknown_value(regs, regno);
	}
	return 0;
}

static int bpf_size_to_bytes(int bpf_size)
{
	if (bpf_size == BPF_W)
		return 4;
	else if (bpf_size == BPF_H)
		return 2;
	else if (bpf_size == BPF_B)
		return 1;
	else if (bpf_size == BPF_DW)
		return 8;
	else
		return -EINVAL;
}

539 540 541 542 543
static bool is_spillable_regtype(enum bpf_reg_type type)
{
	switch (type) {
	case PTR_TO_MAP_VALUE:
	case PTR_TO_MAP_VALUE_OR_NULL:
544
	case PTR_TO_MAP_VALUE_ADJ:
545 546
	case PTR_TO_STACK:
	case PTR_TO_CTX:
A
Alexei Starovoitov 已提交
547 548
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_END:
549 550 551 552 553 554 555 556
	case FRAME_PTR:
	case CONST_PTR_TO_MAP:
		return true;
	default:
		return false;
	}
}

557 558 559
/* check_stack_read/write functions track spill/fill of registers,
 * stack boundary and alignment are checked in check_mem_access()
 */
560 561
static int check_stack_write(struct bpf_verifier_state *state, int off,
			     int size, int value_regno)
562 563
{
	int i;
564 565 566
	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
	 * so it's aligned access and [off, off + size) are within stack limits
	 */
567 568

	if (value_regno >= 0 &&
569
	    is_spillable_regtype(state->regs[value_regno].type)) {
570 571

		/* register containing pointer is being spilled into stack */
572
		if (size != BPF_REG_SIZE) {
573 574 575 576 577
			verbose("invalid size of register spill\n");
			return -EACCES;
		}

		/* save register state */
578 579
		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
			state->regs[value_regno];
580

581 582 583
		for (i = 0; i < BPF_REG_SIZE; i++)
			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
	} else {
584
		/* regular write of data into stack */
585
		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
586
			(struct bpf_reg_state) {};
587 588 589

		for (i = 0; i < size; i++)
			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
590 591 592 593
	}
	return 0;
}

594
static int check_stack_read(struct bpf_verifier_state *state, int off, int size,
595 596
			    int value_regno)
{
597
	u8 *slot_type;
598 599
	int i;

600
	slot_type = &state->stack_slot_type[MAX_BPF_STACK + off];
601

602 603
	if (slot_type[0] == STACK_SPILL) {
		if (size != BPF_REG_SIZE) {
604 605 606
			verbose("invalid size of register spill\n");
			return -EACCES;
		}
607 608
		for (i = 1; i < BPF_REG_SIZE; i++) {
			if (slot_type[i] != STACK_SPILL) {
609 610 611 612 613 614 615
				verbose("corrupted spill memory\n");
				return -EACCES;
			}
		}

		if (value_regno >= 0)
			/* restore register state from stack */
616 617
			state->regs[value_regno] =
				state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE];
618 619 620
		return 0;
	} else {
		for (i = 0; i < size; i++) {
621
			if (slot_type[i] != STACK_MISC) {
622 623 624 625 626 627 628
				verbose("invalid read from stack off %d+%d size %d\n",
					off, i, size);
				return -EACCES;
			}
		}
		if (value_regno >= 0)
			/* have read misc data from the stack */
629 630
			mark_reg_unknown_value_and_range(state->regs,
							 value_regno);
631 632 633 634 635
		return 0;
	}
}

/* check read/write into map element returned by bpf_map_lookup_elem() */
636
static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
637 638 639 640
			    int size)
{
	struct bpf_map *map = env->cur_state.regs[regno].map_ptr;

641
	if (off < 0 || size <= 0 || off + size > map->value_size) {
642 643 644 645 646 647 648
		verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
			map->value_size, off, size);
		return -EACCES;
	}
	return 0;
}

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
/* check read/write into an adjusted map element */
static int check_map_access_adj(struct bpf_verifier_env *env, u32 regno,
				int off, int size)
{
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *reg = &state->regs[regno];
	int err;

	/* We adjusted the register to this map value, so we
	 * need to change off and size to min_value and max_value
	 * respectively to make sure our theoretical access will be
	 * safe.
	 */
	if (log_level)
		print_verifier_state(state);
	env->varlen_map_value_access = true;
	/* The minimum value is only important with signed
	 * comparisons where we can't assume the floor of a
	 * value is 0.  If we are using signed variables for our
	 * index'es we need to make sure that whatever we use
	 * will have a set floor within our range.
	 */
	if (reg->min_value < 0) {
		verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
			regno);
		return -EACCES;
	}
	err = check_map_access(env, regno, reg->min_value + off, size);
	if (err) {
		verbose("R%d min value is outside of the array range\n",
			regno);
		return err;
	}

	/* If we haven't set a max value then we need to bail
	 * since we can't be sure we won't do bad things.
	 */
	if (reg->max_value == BPF_REGISTER_MAX_RANGE) {
		verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n",
			regno);
		return -EACCES;
	}
	return check_map_access(env, regno, reg->max_value + off, size);
}

A
Alexei Starovoitov 已提交
694 695
#define MAX_PACKET_OFF 0xffff

696
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
697 698
				       const struct bpf_call_arg_meta *meta,
				       enum bpf_access_type t)
699
{
700
	switch (env->prog->type) {
701 702 703 704 705
	case BPF_PROG_TYPE_LWT_IN:
	case BPF_PROG_TYPE_LWT_OUT:
		/* dst_input() and dst_output() can't write for now */
		if (t == BPF_WRITE)
			return false;
706
		/* fallthrough */
707 708
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
709
	case BPF_PROG_TYPE_XDP:
710
	case BPF_PROG_TYPE_LWT_XMIT:
711 712 713 714
		if (meta)
			return meta->pkt_access;

		env->seen_direct_write = true;
715 716 717 718 719 720
		return true;
	default:
		return false;
	}
}

721
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
A
Alexei Starovoitov 已提交
722 723
			       int size)
{
724 725
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *reg = &regs[regno];
A
Alexei Starovoitov 已提交
726

727
	off += reg->off;
728
	if (off < 0 || size <= 0 || off + size > reg->range) {
729 730
		verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
			off, size, regno, reg->id, reg->off, reg->range);
A
Alexei Starovoitov 已提交
731 732 733 734 735
		return -EACCES;
	}
	return 0;
}

736
/* check access to 'struct bpf_context' fields */
737
static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
738
			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
739
{
740 741 742 743
	/* for analyzer ctx accesses are already validated and converted */
	if (env->analyzer_ops)
		return 0;

744
	if (env->prog->aux->ops->is_valid_access &&
745
	    env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
746 747 748
		/* remember the offset of last byte accessed in ctx */
		if (env->prog->aux->max_ctx_offset < off + size)
			env->prog->aux->max_ctx_offset = off + size;
749
		return 0;
750
	}
751 752 753 754 755

	verbose("invalid bpf_context access off=%d size=%d\n", off, size);
	return -EACCES;
}

756
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
757 758 759 760 761 762 763 764 765 766 767 768 769
{
	if (env->allow_ptr_leaks)
		return false;

	switch (env->cur_state.regs[regno].type) {
	case UNKNOWN_VALUE:
	case CONST_IMM:
		return false;
	default:
		return true;
	}
}

770 771
static int check_ptr_alignment(struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg, int off, int size)
A
Alexei Starovoitov 已提交
772
{
773
	if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
A
Alexei Starovoitov 已提交
774
		if (off % size != 0) {
775 776
			verbose("misaligned access off %d size %d\n",
				off, size);
A
Alexei Starovoitov 已提交
777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792
			return -EACCES;
		} else {
			return 0;
		}
	}

	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
		/* misaligned access to packet is ok on x86,arm,arm64 */
		return 0;

	if (reg->id && size != 1) {
		verbose("Unknown packet alignment. Only byte-sized access allowed\n");
		return -EACCES;
	}

	/* skb->data is NET_IP_ALIGN-ed */
793 794
	if (reg->type == PTR_TO_PACKET &&
	    (NET_IP_ALIGN + reg->off + off) % size != 0) {
A
Alexei Starovoitov 已提交
795 796 797 798 799 800 801
		verbose("misaligned packet access off %d+%d+%d size %d\n",
			NET_IP_ALIGN, reg->off, off, size);
		return -EACCES;
	}
	return 0;
}

802 803 804 805 806 807
/* check whether memory at (regno + off) is accessible for t = (read | write)
 * if t==write, value_regno is a register which value is stored into memory
 * if t==read, value_regno is a register which will receive the value from memory
 * if t==write && value_regno==-1, some unknown value is stored into memory
 * if t==read && value_regno==-1, don't care what we read from memory
 */
808
static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
809 810 811
			    int bpf_size, enum bpf_access_type t,
			    int value_regno)
{
812 813
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *reg = &state->regs[regno];
814 815
	int size, err = 0;

A
Alexei Starovoitov 已提交
816 817
	if (reg->type == PTR_TO_STACK)
		off += reg->imm;
818

819 820 821 822
	size = bpf_size_to_bytes(bpf_size);
	if (size < 0)
		return size;

A
Alexei Starovoitov 已提交
823 824 825
	err = check_ptr_alignment(env, reg, off, size);
	if (err)
		return err;
826

827 828
	if (reg->type == PTR_TO_MAP_VALUE ||
	    reg->type == PTR_TO_MAP_VALUE_ADJ) {
829 830 831 832 833
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose("R%d leaks addr into map\n", value_regno);
			return -EACCES;
		}
834

835 836 837 838
		if (reg->type == PTR_TO_MAP_VALUE_ADJ)
			err = check_map_access_adj(env, regno, off, size);
		else
			err = check_map_access(env, regno, off, size);
839
		if (!err && t == BPF_READ && value_regno >= 0)
840 841
			mark_reg_unknown_value_and_range(state->regs,
							 value_regno);
842

A
Alexei Starovoitov 已提交
843
	} else if (reg->type == PTR_TO_CTX) {
844 845
		enum bpf_reg_type reg_type = UNKNOWN_VALUE;

846 847 848 849 850
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose("R%d leaks addr into ctx\n", value_regno);
			return -EACCES;
		}
851
		err = check_ctx_access(env, off, size, t, &reg_type);
A
Alexei Starovoitov 已提交
852
		if (!err && t == BPF_READ && value_regno >= 0) {
853 854
			mark_reg_unknown_value_and_range(state->regs,
							 value_regno);
855 856
			/* note that reg.[id|off|range] == 0 */
			state->regs[value_regno].type = reg_type;
A
Alexei Starovoitov 已提交
857
		}
858

A
Alexei Starovoitov 已提交
859
	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
860 861 862 863
		if (off >= 0 || off < -MAX_BPF_STACK) {
			verbose("invalid stack off=%d size=%d\n", off, size);
			return -EACCES;
		}
864 865 866 867 868 869 870
		if (t == BPF_WRITE) {
			if (!env->allow_ptr_leaks &&
			    state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL &&
			    size != BPF_REG_SIZE) {
				verbose("attempt to corrupt spilled pointer on stack\n");
				return -EACCES;
			}
871
			err = check_stack_write(state, off, size, value_regno);
872
		} else {
873
			err = check_stack_read(state, off, size, value_regno);
874
		}
A
Alexei Starovoitov 已提交
875
	} else if (state->regs[regno].type == PTR_TO_PACKET) {
876
		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
A
Alexei Starovoitov 已提交
877 878 879
			verbose("cannot write into packet\n");
			return -EACCES;
		}
880 881 882 883 884
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose("R%d leaks addr into packet\n", value_regno);
			return -EACCES;
		}
A
Alexei Starovoitov 已提交
885 886
		err = check_packet_access(env, regno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
887 888
			mark_reg_unknown_value_and_range(state->regs,
							 value_regno);
889 890
	} else {
		verbose("R%d invalid mem access '%s'\n",
A
Alexei Starovoitov 已提交
891
			regno, reg_type_str[reg->type]);
892 893
		return -EACCES;
	}
A
Alexei Starovoitov 已提交
894 895 896 897 898 899 900 901 902

	if (!err && size <= 2 && value_regno >= 0 && env->allow_ptr_leaks &&
	    state->regs[value_regno].type == UNKNOWN_VALUE) {
		/* 1 or 2 byte load zero-extends, determine the number of
		 * zero upper bits. Not doing it fo 4 byte load, since
		 * such values cannot be added to ptr_to_packet anyway.
		 */
		state->regs[value_regno].imm = 64 - size * 8;
	}
903 904 905
	return err;
}

906
static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
907
{
908
	struct bpf_reg_state *regs = env->cur_state.regs;
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
	int err;

	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
	    insn->imm != 0) {
		verbose("BPF_XADD uses reserved fields\n");
		return -EINVAL;
	}

	/* check src1 operand */
	err = check_reg_arg(regs, insn->src_reg, SRC_OP);
	if (err)
		return err;

	/* check src2 operand */
	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	/* check whether atomic_add can read the memory */
	err = check_mem_access(env, insn->dst_reg, insn->off,
			       BPF_SIZE(insn->code), BPF_READ, -1);
	if (err)
		return err;

	/* check whether atomic_add can write into the same memory */
	return check_mem_access(env, insn->dst_reg, insn->off,
				BPF_SIZE(insn->code), BPF_WRITE, -1);
}

/* when register 'regno' is passed into function that will read 'access_size'
 * bytes from that pointer, make sure that it's within stack boundary
 * and all elements of stack are initialized
 */
942
static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
943 944
				int access_size, bool zero_size_allowed,
				struct bpf_call_arg_meta *meta)
945
{
946 947
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *regs = state->regs;
948 949
	int off, i;

950 951 952 953 954 955 956 957 958
	if (regs[regno].type != PTR_TO_STACK) {
		if (zero_size_allowed && access_size == 0 &&
		    regs[regno].type == CONST_IMM &&
		    regs[regno].imm  == 0)
			return 0;

		verbose("R%d type=%s expected=%s\n", regno,
			reg_type_str[regs[regno].type],
			reg_type_str[PTR_TO_STACK]);
959
		return -EACCES;
960
	}
961 962 963 964 965 966 967 968 969

	off = regs[regno].imm;
	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
	    access_size <= 0) {
		verbose("invalid stack type R%d off=%d access_size=%d\n",
			regno, off, access_size);
		return -EACCES;
	}

970 971 972 973 974 975
	if (meta && meta->raw_mode) {
		meta->access_size = access_size;
		meta->regno = regno;
		return 0;
	}

976
	for (i = 0; i < access_size; i++) {
977
		if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
978 979 980 981 982 983 984 985
			verbose("invalid indirect read from stack off %d+%d size %d\n",
				off, i, access_size);
			return -EACCES;
		}
	}
	return 0;
}

986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
				   int access_size, bool zero_size_allowed,
				   struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *regs = env->cur_state.regs;

	switch (regs[regno].type) {
	case PTR_TO_PACKET:
		return check_packet_access(env, regno, 0, access_size);
	case PTR_TO_MAP_VALUE:
		return check_map_access(env, regno, 0, access_size);
	case PTR_TO_MAP_VALUE_ADJ:
		return check_map_access_adj(env, regno, 0, access_size);
	default: /* const_imm|ptr_to_stack or invalid ptr */
		return check_stack_boundary(env, regno, access_size,
					    zero_size_allowed, meta);
	}
}

1005
static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
1006 1007
			  enum bpf_arg_type arg_type,
			  struct bpf_call_arg_meta *meta)
1008
{
1009
	struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
1010
	enum bpf_reg_type expected_type, type = reg->type;
1011 1012
	int err = 0;

1013
	if (arg_type == ARG_DONTCARE)
1014 1015
		return 0;

1016
	if (type == NOT_INIT) {
1017 1018 1019 1020
		verbose("R%d !read_ok\n", regno);
		return -EACCES;
	}

1021 1022 1023 1024 1025
	if (arg_type == ARG_ANYTHING) {
		if (is_pointer_value(env, regno)) {
			verbose("R%d leaks addr into helper function\n", regno);
			return -EACCES;
		}
1026
		return 0;
1027
	}
1028

1029 1030
	if (type == PTR_TO_PACKET &&
	    !may_access_direct_pkt_data(env, meta, BPF_READ)) {
1031
		verbose("helper access to the packet is not allowed\n");
1032 1033 1034
		return -EACCES;
	}

1035
	if (arg_type == ARG_PTR_TO_MAP_KEY ||
1036 1037
	    arg_type == ARG_PTR_TO_MAP_VALUE) {
		expected_type = PTR_TO_STACK;
1038 1039
		if (type != PTR_TO_PACKET && type != expected_type)
			goto err_type;
1040 1041
	} else if (arg_type == ARG_CONST_SIZE ||
		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
1042
		expected_type = CONST_IMM;
1043 1044 1045 1046
		/* One exception. Allow UNKNOWN_VALUE registers when the
		 * boundaries are known and don't cause unsafe memory accesses
		 */
		if (type != UNKNOWN_VALUE && type != expected_type)
1047
			goto err_type;
1048 1049
	} else if (arg_type == ARG_CONST_MAP_PTR) {
		expected_type = CONST_PTR_TO_MAP;
1050 1051
		if (type != expected_type)
			goto err_type;
1052 1053
	} else if (arg_type == ARG_PTR_TO_CTX) {
		expected_type = PTR_TO_CTX;
1054 1055
		if (type != expected_type)
			goto err_type;
1056 1057
	} else if (arg_type == ARG_PTR_TO_MEM ||
		   arg_type == ARG_PTR_TO_UNINIT_MEM) {
1058 1059 1060 1061 1062
		expected_type = PTR_TO_STACK;
		/* One exception here. In case function allows for NULL to be
		 * passed in as argument, it's a CONST_IMM type. Final test
		 * happens during stack boundary checking.
		 */
1063 1064
		if (type == CONST_IMM && reg->imm == 0)
			/* final test in check_stack_boundary() */;
1065 1066
		else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE &&
			 type != PTR_TO_MAP_VALUE_ADJ && type != expected_type)
1067
			goto err_type;
1068
		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
1069 1070 1071 1072 1073 1074 1075
	} else {
		verbose("unsupported arg_type %d\n", arg_type);
		return -EFAULT;
	}

	if (arg_type == ARG_CONST_MAP_PTR) {
		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
1076
		meta->map_ptr = reg->map_ptr;
1077 1078 1079 1080 1081
	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
		/* bpf_map_xxx(..., map_ptr, ..., key) call:
		 * check that [key, key + map->key_size) are within
		 * stack limits and initialized
		 */
1082
		if (!meta->map_ptr) {
1083 1084 1085 1086 1087 1088 1089 1090
			/* in function declaration map_ptr must come before
			 * map_key, so that it's verified and known before
			 * we have to check map_key here. Otherwise it means
			 * that kernel subsystem misconfigured verifier
			 */
			verbose("invalid map_ptr to access map->key\n");
			return -EACCES;
		}
1091 1092 1093 1094 1095 1096 1097
		if (type == PTR_TO_PACKET)
			err = check_packet_access(env, regno, 0,
						  meta->map_ptr->key_size);
		else
			err = check_stack_boundary(env, regno,
						   meta->map_ptr->key_size,
						   false, NULL);
1098 1099 1100 1101
	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
		/* bpf_map_xxx(..., map_ptr, ..., value) call:
		 * check [value, value + map->value_size) validity
		 */
1102
		if (!meta->map_ptr) {
1103 1104 1105 1106
			/* kernel subsystem misconfigured verifier */
			verbose("invalid map_ptr to access map->value\n");
			return -EACCES;
		}
1107 1108 1109 1110 1111 1112 1113
		if (type == PTR_TO_PACKET)
			err = check_packet_access(env, regno, 0,
						  meta->map_ptr->value_size);
		else
			err = check_stack_boundary(env, regno,
						   meta->map_ptr->value_size,
						   false, NULL);
1114 1115 1116
	} else if (arg_type == ARG_CONST_SIZE ||
		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
1117 1118 1119 1120 1121 1122 1123

		/* bpf_xxx(..., buf, len) call will access 'len' bytes
		 * from stack pointer 'buf'. Check it
		 * note: regno == len, regno - 1 == buf
		 */
		if (regno == 0) {
			/* kernel subsystem misconfigured verifier */
1124
			verbose("ARG_CONST_SIZE cannot be first argument\n");
1125 1126
			return -EACCES;
		}
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167

		/* If the register is UNKNOWN_VALUE, the access check happens
		 * using its boundaries. Otherwise, just use its imm
		 */
		if (type == UNKNOWN_VALUE) {
			/* For unprivileged variable accesses, disable raw
			 * mode so that the program is required to
			 * initialize all the memory that the helper could
			 * just partially fill up.
			 */
			meta = NULL;

			if (reg->min_value < 0) {
				verbose("R%d min value is negative, either use unsigned or 'var &= const'\n",
					regno);
				return -EACCES;
			}

			if (reg->min_value == 0) {
				err = check_helper_mem_access(env, regno - 1, 0,
							      zero_size_allowed,
							      meta);
				if (err)
					return err;
			}

			if (reg->max_value == BPF_REGISTER_MAX_RANGE) {
				verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
					regno);
				return -EACCES;
			}
			err = check_helper_mem_access(env, regno - 1,
						      reg->max_value,
						      zero_size_allowed, meta);
			if (err)
				return err;
		} else {
			/* register is CONST_IMM */
			err = check_helper_mem_access(env, regno - 1, reg->imm,
						      zero_size_allowed, meta);
		}
1168 1169 1170
	}

	return err;
1171 1172 1173 1174
err_type:
	verbose("R%d type=%s expected=%s\n", regno,
		reg_type_str[type], reg_type_str[expected_type]);
	return -EACCES;
1175 1176
}

1177 1178 1179 1180 1181
static int check_map_func_compatibility(struct bpf_map *map, int func_id)
{
	if (!map)
		return 0;

1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196
	/* We need a two way check, first is from map perspective ... */
	switch (map->map_type) {
	case BPF_MAP_TYPE_PROG_ARRAY:
		if (func_id != BPF_FUNC_tail_call)
			goto error;
		break;
	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
		if (func_id != BPF_FUNC_perf_event_read &&
		    func_id != BPF_FUNC_perf_event_output)
			goto error;
		break;
	case BPF_MAP_TYPE_STACK_TRACE:
		if (func_id != BPF_FUNC_get_stackid)
			goto error;
		break;
1197
	case BPF_MAP_TYPE_CGROUP_ARRAY:
1198
		if (func_id != BPF_FUNC_skb_under_cgroup &&
1199
		    func_id != BPF_FUNC_current_task_under_cgroup)
1200 1201
			goto error;
		break;
1202 1203 1204
	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
		if (func_id != BPF_FUNC_map_lookup_elem)
			goto error;
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223
	default:
		break;
	}

	/* ... and second from the function itself. */
	switch (func_id) {
	case BPF_FUNC_tail_call:
		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
			goto error;
		break;
	case BPF_FUNC_perf_event_read:
	case BPF_FUNC_perf_event_output:
		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
			goto error;
		break;
	case BPF_FUNC_get_stackid:
		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
			goto error;
		break;
1224
	case BPF_FUNC_current_task_under_cgroup:
1225
	case BPF_FUNC_skb_under_cgroup:
1226 1227 1228
		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
			goto error;
		break;
1229 1230
	default:
		break;
1231 1232 1233
	}

	return 0;
1234
error:
1235 1236
	verbose("cannot pass map_type %d into func %s#%d\n",
		map->map_type, func_id_name(func_id), func_id);
1237
	return -EINVAL;
1238 1239
}

1240 1241 1242 1243
static int check_raw_mode(const struct bpf_func_proto *fn)
{
	int count = 0;

1244
	if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
1245
		count++;
1246
	if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
1247
		count++;
1248
	if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
1249
		count++;
1250
	if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
1251
		count++;
1252
	if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
1253 1254 1255 1256 1257
		count++;

	return count > 1 ? -EINVAL : 0;
}

1258
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
A
Alexei Starovoitov 已提交
1259
{
1260 1261
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *regs = state->regs, *reg;
A
Alexei Starovoitov 已提交
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280
	int i;

	for (i = 0; i < MAX_BPF_REG; i++)
		if (regs[i].type == PTR_TO_PACKET ||
		    regs[i].type == PTR_TO_PACKET_END)
			mark_reg_unknown_value(regs, i);

	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
		if (state->stack_slot_type[i] != STACK_SPILL)
			continue;
		reg = &state->spilled_regs[i / BPF_REG_SIZE];
		if (reg->type != PTR_TO_PACKET &&
		    reg->type != PTR_TO_PACKET_END)
			continue;
		reg->type = UNKNOWN_VALUE;
		reg->imm = 0;
	}
}

1281
static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
1282
{
1283
	struct bpf_verifier_state *state = &env->cur_state;
1284
	const struct bpf_func_proto *fn = NULL;
1285 1286
	struct bpf_reg_state *regs = state->regs;
	struct bpf_reg_state *reg;
1287
	struct bpf_call_arg_meta meta;
A
Alexei Starovoitov 已提交
1288
	bool changes_data;
1289 1290 1291 1292
	int i, err;

	/* find function prototype */
	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
1293
		verbose("invalid func %s#%d\n", func_id_name(func_id), func_id);
1294 1295 1296 1297 1298 1299 1300
		return -EINVAL;
	}

	if (env->prog->aux->ops->get_func_proto)
		fn = env->prog->aux->ops->get_func_proto(func_id);

	if (!fn) {
1301
		verbose("unknown func %s#%d\n", func_id_name(func_id), func_id);
1302 1303 1304 1305
		return -EINVAL;
	}

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
1306
	if (!env->prog->gpl_compatible && fn->gpl_only) {
1307 1308 1309 1310
		verbose("cannot call GPL only function from proprietary program\n");
		return -EINVAL;
	}

1311
	changes_data = bpf_helper_changes_pkt_data(fn->func);
A
Alexei Starovoitov 已提交
1312

1313
	memset(&meta, 0, sizeof(meta));
1314
	meta.pkt_access = fn->pkt_access;
1315

1316 1317 1318 1319 1320
	/* We only support one arg being in raw mode at the moment, which
	 * is sufficient for the helper functions we have right now.
	 */
	err = check_raw_mode(fn);
	if (err) {
1321 1322
		verbose("kernel subsystem misconfigured func %s#%d\n",
			func_id_name(func_id), func_id);
1323 1324 1325
		return err;
	}

1326
	/* check args */
1327
	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
1328 1329
	if (err)
		return err;
1330
	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
1331 1332
	if (err)
		return err;
1333
	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
1334 1335
	if (err)
		return err;
1336
	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
1337 1338
	if (err)
		return err;
1339
	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
1340 1341 1342
	if (err)
		return err;

1343 1344 1345 1346 1347 1348 1349 1350 1351
	/* Mark slots with STACK_MISC in case of raw mode, stack offset
	 * is inferred from register state.
	 */
	for (i = 0; i < meta.access_size; i++) {
		err = check_mem_access(env, meta.regno, i, BPF_B, BPF_WRITE, -1);
		if (err)
			return err;
	}

1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364
	/* reset caller saved regs */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		reg = regs + caller_saved[i];
		reg->type = NOT_INIT;
		reg->imm = 0;
	}

	/* update return register */
	if (fn->ret_type == RET_INTEGER) {
		regs[BPF_REG_0].type = UNKNOWN_VALUE;
	} else if (fn->ret_type == RET_VOID) {
		regs[BPF_REG_0].type = NOT_INIT;
	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
1365 1366
		struct bpf_insn_aux_data *insn_aux;

1367
		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
1368
		regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0;
1369 1370 1371 1372
		/* remember map_ptr, so that check_map_access()
		 * can check 'value_size' boundary of memory access
		 * to map element returned from bpf_map_lookup_elem()
		 */
1373
		if (meta.map_ptr == NULL) {
1374 1375 1376
			verbose("kernel subsystem misconfigured verifier\n");
			return -EINVAL;
		}
1377
		regs[BPF_REG_0].map_ptr = meta.map_ptr;
1378
		regs[BPF_REG_0].id = ++env->id_gen;
1379 1380 1381 1382 1383
		insn_aux = &env->insn_aux_data[insn_idx];
		if (!insn_aux->map_ptr)
			insn_aux->map_ptr = meta.map_ptr;
		else if (insn_aux->map_ptr != meta.map_ptr)
			insn_aux->map_ptr = BPF_MAP_PTR_POISON;
1384
	} else {
1385 1386
		verbose("unknown return type %d of func %s#%d\n",
			fn->ret_type, func_id_name(func_id), func_id);
1387 1388
		return -EINVAL;
	}
1389

1390
	err = check_map_func_compatibility(meta.map_ptr, func_id);
1391 1392
	if (err)
		return err;
1393

A
Alexei Starovoitov 已提交
1394 1395 1396 1397 1398
	if (changes_data)
		clear_all_pkt_pointers(env);
	return 0;
}

1399 1400
static int check_packet_ptr_add(struct bpf_verifier_env *env,
				struct bpf_insn *insn)
A
Alexei Starovoitov 已提交
1401
{
1402 1403 1404 1405
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
	struct bpf_reg_state tmp_reg;
A
Alexei Starovoitov 已提交
1406 1407 1408 1409 1410 1411 1412
	s32 imm;

	if (BPF_SRC(insn->code) == BPF_K) {
		/* pkt_ptr += imm */
		imm = insn->imm;

add_imm:
1413
		if (imm < 0) {
A
Alexei Starovoitov 已提交
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427
			verbose("addition of negative constant to packet pointer is not allowed\n");
			return -EACCES;
		}
		if (imm >= MAX_PACKET_OFF ||
		    imm + dst_reg->off >= MAX_PACKET_OFF) {
			verbose("constant %d is too large to add to packet pointer\n",
				imm);
			return -EACCES;
		}
		/* a constant was added to pkt_ptr.
		 * Remember it while keeping the same 'id'
		 */
		dst_reg->off += imm;
	} else {
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
		if (src_reg->type == PTR_TO_PACKET) {
			/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
			tmp_reg = *dst_reg;  /* save r7 state */
			*dst_reg = *src_reg; /* copy pkt_ptr state r6 into r7 */
			src_reg = &tmp_reg;  /* pretend it's src_reg state */
			/* if the checks below reject it, the copy won't matter,
			 * since we're rejecting the whole program. If all ok,
			 * then imm22 state will be added to r7
			 * and r7 will be pkt(id=0,off=22,r=62) while
			 * r6 will stay as pkt(id=0,off=0,r=62)
			 */
		}

A
Alexei Starovoitov 已提交
1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463
		if (src_reg->type == CONST_IMM) {
			/* pkt_ptr += reg where reg is known constant */
			imm = src_reg->imm;
			goto add_imm;
		}
		/* disallow pkt_ptr += reg
		 * if reg is not uknown_value with guaranteed zero upper bits
		 * otherwise pkt_ptr may overflow and addition will become
		 * subtraction which is not allowed
		 */
		if (src_reg->type != UNKNOWN_VALUE) {
			verbose("cannot add '%s' to ptr_to_packet\n",
				reg_type_str[src_reg->type]);
			return -EACCES;
		}
		if (src_reg->imm < 48) {
			verbose("cannot add integer value with %lld upper zero bits to ptr_to_packet\n",
				src_reg->imm);
			return -EACCES;
		}
		/* dst_reg stays as pkt_ptr type and since some positive
		 * integer value was added to the pointer, increment its 'id'
		 */
1464
		dst_reg->id = ++env->id_gen;
A
Alexei Starovoitov 已提交
1465 1466 1467 1468 1469 1470 1471 1472

		/* something was added to pkt_ptr, set range and off to zero */
		dst_reg->off = 0;
		dst_reg->range = 0;
	}
	return 0;
}

1473
static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn)
A
Alexei Starovoitov 已提交
1474
{
1475 1476
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
A
Alexei Starovoitov 已提交
1477 1478 1479 1480 1481 1482 1483 1484 1485
	u8 opcode = BPF_OP(insn->code);
	s64 imm_log2;

	/* for type == UNKNOWN_VALUE:
	 * imm > 0 -> number of zero upper bits
	 * imm == 0 -> don't track which is the same as all bits can be non-zero
	 */

	if (BPF_SRC(insn->code) == BPF_X) {
1486
		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
A
Alexei Starovoitov 已提交
1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574

		if (src_reg->type == UNKNOWN_VALUE && src_reg->imm > 0 &&
		    dst_reg->imm && opcode == BPF_ADD) {
			/* dreg += sreg
			 * where both have zero upper bits. Adding them
			 * can only result making one more bit non-zero
			 * in the larger value.
			 * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
			 *     0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
			 */
			dst_reg->imm = min(dst_reg->imm, src_reg->imm);
			dst_reg->imm--;
			return 0;
		}
		if (src_reg->type == CONST_IMM && src_reg->imm > 0 &&
		    dst_reg->imm && opcode == BPF_ADD) {
			/* dreg += sreg
			 * where dreg has zero upper bits and sreg is const.
			 * Adding them can only result making one more bit
			 * non-zero in the larger value.
			 */
			imm_log2 = __ilog2_u64((long long)src_reg->imm);
			dst_reg->imm = min(dst_reg->imm, 63 - imm_log2);
			dst_reg->imm--;
			return 0;
		}
		/* all other cases non supported yet, just mark dst_reg */
		dst_reg->imm = 0;
		return 0;
	}

	/* sign extend 32-bit imm into 64-bit to make sure that
	 * negative values occupy bit 63. Note ilog2() would have
	 * been incorrect, since sizeof(insn->imm) == 4
	 */
	imm_log2 = __ilog2_u64((long long)insn->imm);

	if (dst_reg->imm && opcode == BPF_LSH) {
		/* reg <<= imm
		 * if reg was a result of 2 byte load, then its imm == 48
		 * which means that upper 48 bits are zero and shifting this reg
		 * left by 4 would mean that upper 44 bits are still zero
		 */
		dst_reg->imm -= insn->imm;
	} else if (dst_reg->imm && opcode == BPF_MUL) {
		/* reg *= imm
		 * if multiplying by 14 subtract 4
		 * This is conservative calculation of upper zero bits.
		 * It's not trying to special case insn->imm == 1 or 0 cases
		 */
		dst_reg->imm -= imm_log2 + 1;
	} else if (opcode == BPF_AND) {
		/* reg &= imm */
		dst_reg->imm = 63 - imm_log2;
	} else if (dst_reg->imm && opcode == BPF_ADD) {
		/* reg += imm */
		dst_reg->imm = min(dst_reg->imm, 63 - imm_log2);
		dst_reg->imm--;
	} else if (opcode == BPF_RSH) {
		/* reg >>= imm
		 * which means that after right shift, upper bits will be zero
		 * note that verifier already checked that
		 * 0 <= imm < 64 for shift insn
		 */
		dst_reg->imm += insn->imm;
		if (unlikely(dst_reg->imm > 64))
			/* some dumb code did:
			 * r2 = *(u32 *)mem;
			 * r2 >>= 32;
			 * and all bits are zero now */
			dst_reg->imm = 64;
	} else {
		/* all other alu ops, means that we don't know what will
		 * happen to the value, mark it with unknown number of zero bits
		 */
		dst_reg->imm = 0;
	}

	if (dst_reg->imm < 0) {
		/* all 64 bits of the register can contain non-zero bits
		 * and such value cannot be added to ptr_to_packet, since it
		 * may overflow, mark it as unknown to avoid further eval
		 */
		dst_reg->imm = 0;
	}
	return 0;
}

1575 1576
static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
				struct bpf_insn *insn)
A
Alexei Starovoitov 已提交
1577
{
1578 1579 1580
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
A
Alexei Starovoitov 已提交
1581
	u8 opcode = BPF_OP(insn->code);
1582
	u64 dst_imm = dst_reg->imm;
A
Alexei Starovoitov 已提交
1583

1584 1585 1586
	/* dst_reg->type == CONST_IMM here. Simulate execution of insns
	 * containing ALU ops. Don't care about overflow or negative
	 * values, just add/sub/... them; registers are in u64.
A
Alexei Starovoitov 已提交
1587
	 */
1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623
	if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_K) {
		dst_imm += insn->imm;
	} else if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm += src_reg->imm;
	} else if (opcode == BPF_SUB && BPF_SRC(insn->code) == BPF_K) {
		dst_imm -= insn->imm;
	} else if (opcode == BPF_SUB && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm -= src_reg->imm;
	} else if (opcode == BPF_MUL && BPF_SRC(insn->code) == BPF_K) {
		dst_imm *= insn->imm;
	} else if (opcode == BPF_MUL && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm *= src_reg->imm;
	} else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_K) {
		dst_imm |= insn->imm;
	} else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm |= src_reg->imm;
	} else if (opcode == BPF_AND && BPF_SRC(insn->code) == BPF_K) {
		dst_imm &= insn->imm;
	} else if (opcode == BPF_AND && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm &= src_reg->imm;
	} else if (opcode == BPF_RSH && BPF_SRC(insn->code) == BPF_K) {
		dst_imm >>= insn->imm;
	} else if (opcode == BPF_RSH && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm >>= src_reg->imm;
	} else if (opcode == BPF_LSH && BPF_SRC(insn->code) == BPF_K) {
		dst_imm <<= insn->imm;
	} else if (opcode == BPF_LSH && BPF_SRC(insn->code) == BPF_X &&
		   src_reg->type == CONST_IMM) {
		dst_imm <<= src_reg->imm;
	} else {
A
Alexei Starovoitov 已提交
1624
		mark_reg_unknown_value(regs, insn->dst_reg);
1625 1626 1627 1628 1629
		goto out;
	}

	dst_reg->imm = dst_imm;
out:
1630 1631 1632
	return 0;
}

1633 1634 1635 1636
static void check_reg_overflow(struct bpf_reg_state *reg)
{
	if (reg->max_value > BPF_REGISTER_MAX_RANGE)
		reg->max_value = BPF_REGISTER_MAX_RANGE;
1637 1638
	if (reg->min_value < BPF_REGISTER_MIN_RANGE ||
	    reg->min_value > BPF_REGISTER_MAX_RANGE)
1639 1640 1641 1642 1643 1644 1645
		reg->min_value = BPF_REGISTER_MIN_RANGE;
}

static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
				    struct bpf_insn *insn)
{
	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
1646 1647
	s64 min_val = BPF_REGISTER_MIN_RANGE;
	u64 max_val = BPF_REGISTER_MAX_RANGE;
1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680
	u8 opcode = BPF_OP(insn->code);

	dst_reg = &regs[insn->dst_reg];
	if (BPF_SRC(insn->code) == BPF_X) {
		check_reg_overflow(&regs[insn->src_reg]);
		min_val = regs[insn->src_reg].min_value;
		max_val = regs[insn->src_reg].max_value;

		/* If the source register is a random pointer then the
		 * min_value/max_value values represent the range of the known
		 * accesses into that value, not the actual min/max value of the
		 * register itself.  In this case we have to reset the reg range
		 * values so we know it is not safe to look at.
		 */
		if (regs[insn->src_reg].type != CONST_IMM &&
		    regs[insn->src_reg].type != UNKNOWN_VALUE) {
			min_val = BPF_REGISTER_MIN_RANGE;
			max_val = BPF_REGISTER_MAX_RANGE;
		}
	} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
		   (s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
		min_val = max_val = insn->imm;
	}

	/* We don't know anything about what was done to this register, mark it
	 * as unknown.
	 */
	if (min_val == BPF_REGISTER_MIN_RANGE &&
	    max_val == BPF_REGISTER_MAX_RANGE) {
		reset_reg_range_values(regs, insn->dst_reg);
		return;
	}

1681 1682 1683 1684 1685 1686 1687 1688 1689
	/* If one of our values was at the end of our ranges then we can't just
	 * do our normal operations to the register, we need to set the values
	 * to the min/max since they are undefined.
	 */
	if (min_val == BPF_REGISTER_MIN_RANGE)
		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
	if (max_val == BPF_REGISTER_MAX_RANGE)
		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;

1690 1691
	switch (opcode) {
	case BPF_ADD:
1692 1693 1694 1695
		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
			dst_reg->min_value += min_val;
		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
			dst_reg->max_value += max_val;
1696 1697
		break;
	case BPF_SUB:
1698 1699 1700 1701
		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
			dst_reg->min_value -= min_val;
		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
			dst_reg->max_value -= max_val;
1702 1703
		break;
	case BPF_MUL:
1704 1705 1706 1707
		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
			dst_reg->min_value *= min_val;
		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
			dst_reg->max_value *= max_val;
1708 1709
		break;
	case BPF_AND:
1710 1711 1712 1713 1714 1715 1716 1717
		/* Disallow AND'ing of negative numbers, ain't nobody got time
		 * for that.  Otherwise the minimum is 0 and the max is the max
		 * value we could AND against.
		 */
		if (min_val < 0)
			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
		else
			dst_reg->min_value = 0;
1718 1719 1720 1721 1722 1723 1724 1725 1726
		dst_reg->max_value = max_val;
		break;
	case BPF_LSH:
		/* Gotta have special overflow logic here, if we're shifting
		 * more than MAX_RANGE then just assume we have an invalid
		 * range.
		 */
		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
1727
		else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
1728 1729 1730 1731
			dst_reg->min_value <<= min_val;

		if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
1732
		else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
1733 1734 1735
			dst_reg->max_value <<= max_val;
		break;
	case BPF_RSH:
1736 1737
		/* RSH by a negative number is undefined, and the BPF_RSH is an
		 * unsigned shift, so make the appropriate casts.
1738
		 */
1739 1740 1741 1742 1743 1744 1745
		if (min_val < 0 || dst_reg->min_value < 0)
			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
		else
			dst_reg->min_value =
				(u64)(dst_reg->min_value) >> min_val;
		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
			dst_reg->max_value >>= max_val;
1746 1747 1748 1749 1750 1751 1752 1753 1754
		break;
	default:
		reset_reg_range_values(regs, insn->dst_reg);
		break;
	}

	check_reg_overflow(dst_reg);
}

1755
/* check validity of 32-bit and 64-bit arithmetic operations */
1756
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
1757
{
1758
	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode == BPF_END || opcode == BPF_NEG) {
		if (opcode == BPF_NEG) {
			if (BPF_SRC(insn->code) != 0 ||
			    insn->src_reg != BPF_REG_0 ||
			    insn->off != 0 || insn->imm != 0) {
				verbose("BPF_NEG uses reserved fields\n");
				return -EINVAL;
			}
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
				verbose("BPF_END uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src operand */
		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
		if (err)
			return err;

1783 1784 1785 1786 1787 1788
		if (is_pointer_value(env, insn->dst_reg)) {
			verbose("R%d pointer arithmetic prohibited\n",
				insn->dst_reg);
			return -EACCES;
		}

1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817
		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
		if (err)
			return err;

	} else if (opcode == BPF_MOV) {

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose("BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}

			/* check src operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose("BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
		if (err)
			return err;

1818 1819 1820 1821 1822
		/* we are setting our register to something new, we need to
		 * reset its range values.
		 */
		reset_reg_range_values(regs, insn->dst_reg);

1823 1824 1825 1826 1827 1828 1829
		if (BPF_SRC(insn->code) == BPF_X) {
			if (BPF_CLASS(insn->code) == BPF_ALU64) {
				/* case: R1 = R2
				 * copy register state to dest reg
				 */
				regs[insn->dst_reg] = regs[insn->src_reg];
			} else {
1830 1831 1832 1833 1834
				if (is_pointer_value(env, insn->src_reg)) {
					verbose("R%d partial copy of pointer\n",
						insn->src_reg);
					return -EACCES;
				}
1835
				mark_reg_unknown_value(regs, insn->dst_reg);
1836 1837 1838 1839 1840 1841 1842
			}
		} else {
			/* case: R = imm
			 * remember the value we stored into this reg
			 */
			regs[insn->dst_reg].type = CONST_IMM;
			regs[insn->dst_reg].imm = insn->imm;
1843 1844
			regs[insn->dst_reg].max_value = insn->imm;
			regs[insn->dst_reg].min_value = insn->imm;
1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879
		}

	} else if (opcode > BPF_END) {
		verbose("invalid BPF_ALU opcode %x\n", opcode);
		return -EINVAL;

	} else {	/* all other ALU ops: and, sub, xor, add, ... */

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose("BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
			/* check src1 operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose("BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src2 operand */
		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
		    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
			verbose("div by zero\n");
			return -EINVAL;
		}

R
Rabin Vincent 已提交
1880 1881 1882 1883 1884 1885 1886 1887 1888 1889
		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;

			if (insn->imm < 0 || insn->imm >= size) {
				verbose("invalid shift %d\n", insn->imm);
				return -EINVAL;
			}
		}

A
Alexei Starovoitov 已提交
1890 1891 1892 1893 1894 1895 1896
		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK);
		if (err)
			return err;

		dst_reg = &regs[insn->dst_reg];

1897 1898 1899
		/* first we want to adjust our ranges. */
		adjust_reg_min_max_vals(env, insn);

1900 1901
		/* pattern match 'bpf_add Rx, imm' instruction */
		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
A
Alexei Starovoitov 已提交
1902 1903 1904 1905
		    dst_reg->type == FRAME_PTR && BPF_SRC(insn->code) == BPF_K) {
			dst_reg->type = PTR_TO_STACK;
			dst_reg->imm = insn->imm;
			return 0;
A
Alexei Starovoitov 已提交
1906 1907
		} else if (opcode == BPF_ADD &&
			   BPF_CLASS(insn->code) == BPF_ALU64 &&
1908 1909 1910
			   (dst_reg->type == PTR_TO_PACKET ||
			    (BPF_SRC(insn->code) == BPF_X &&
			     regs[insn->src_reg].type == PTR_TO_PACKET))) {
A
Alexei Starovoitov 已提交
1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922
			/* ptr_to_packet += K|X */
			return check_packet_ptr_add(env, insn);
		} else if (BPF_CLASS(insn->code) == BPF_ALU64 &&
			   dst_reg->type == UNKNOWN_VALUE &&
			   env->allow_ptr_leaks) {
			/* unknown += K|X */
			return evaluate_reg_alu(env, insn);
		} else if (BPF_CLASS(insn->code) == BPF_ALU64 &&
			   dst_reg->type == CONST_IMM &&
			   env->allow_ptr_leaks) {
			/* reg_imm += K|X */
			return evaluate_reg_imm_alu(env, insn);
1923 1924 1925 1926 1927 1928 1929 1930 1931 1932
		} else if (is_pointer_value(env, insn->dst_reg)) {
			verbose("R%d pointer arithmetic prohibited\n",
				insn->dst_reg);
			return -EACCES;
		} else if (BPF_SRC(insn->code) == BPF_X &&
			   is_pointer_value(env, insn->src_reg)) {
			verbose("R%d pointer arithmetic prohibited\n",
				insn->src_reg);
			return -EACCES;
		}
1933

1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
		/* If we did pointer math on a map value then just set it to our
		 * PTR_TO_MAP_VALUE_ADJ type so we can deal with any stores or
		 * loads to this register appropriately, otherwise just mark the
		 * register as unknown.
		 */
		if (env->allow_ptr_leaks &&
		    (dst_reg->type == PTR_TO_MAP_VALUE ||
		     dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
			dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
		else
			mark_reg_unknown_value(regs, insn->dst_reg);
1945 1946 1947 1948 1949
	}

	return 0;
}

1950 1951
static void find_good_pkt_pointers(struct bpf_verifier_state *state,
				   struct bpf_reg_state *dst_reg)
A
Alexei Starovoitov 已提交
1952
{
1953
	struct bpf_reg_state *regs = state->regs, *reg;
A
Alexei Starovoitov 已提交
1954
	int i;
1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983

	/* LLVM can generate two kind of checks:
	 *
	 * Type 1:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (r2 > pkt_end) goto <handle exception>
	 *   <access okay>
	 *
	 *   Where:
	 *     r2 == dst_reg, pkt_end == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * Type 2:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (pkt_end >= r2) goto <access okay>
	 *   <handle exception>
	 *
	 *   Where:
	 *     pkt_end == dst_reg, r2 == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
	 * so that range of bytes [r3, r3 + 8) is safe to access.
A
Alexei Starovoitov 已提交
1984
	 */
1985

A
Alexei Starovoitov 已提交
1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998
	for (i = 0; i < MAX_BPF_REG; i++)
		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
			regs[i].range = dst_reg->off;

	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
		if (state->stack_slot_type[i] != STACK_SPILL)
			continue;
		reg = &state->spilled_regs[i / BPF_REG_SIZE];
		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
			reg->range = dst_reg->off;
	}
}

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
/* Adjusts the register min/max values in the case that the dst_reg is the
 * variable register that we are working on, and src_reg is a constant or we're
 * simply doing a BPF_K check.
 */
static void reg_set_min_max(struct bpf_reg_state *true_reg,
			    struct bpf_reg_state *false_reg, u64 val,
			    u8 opcode)
{
	switch (opcode) {
	case BPF_JEQ:
		/* If this is false then we know nothing Jon Snow, but if it is
		 * true then we know for sure.
		 */
		true_reg->max_value = true_reg->min_value = val;
		break;
	case BPF_JNE:
		/* If this is true we know nothing Jon Snow, but if it is false
		 * we know the value for sure;
		 */
		false_reg->max_value = false_reg->min_value = val;
		break;
	case BPF_JGT:
		/* Unsigned comparison, the minimum value is 0. */
		false_reg->min_value = 0;
2023
		/* fallthrough */
2024 2025 2026 2027 2028 2029 2030 2031 2032 2033
	case BPF_JSGT:
		/* If this is false then we know the maximum val is val,
		 * otherwise we know the min val is val+1.
		 */
		false_reg->max_value = val;
		true_reg->min_value = val + 1;
		break;
	case BPF_JGE:
		/* Unsigned comparison, the minimum value is 0. */
		false_reg->min_value = 0;
2034
		/* fallthrough */
2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072
	case BPF_JSGE:
		/* If this is false then we know the maximum value is val - 1,
		 * otherwise we know the mimimum value is val.
		 */
		false_reg->max_value = val - 1;
		true_reg->min_value = val;
		break;
	default:
		break;
	}

	check_reg_overflow(false_reg);
	check_reg_overflow(true_reg);
}

/* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg
 * is the variable reg.
 */
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
				struct bpf_reg_state *false_reg, u64 val,
				u8 opcode)
{
	switch (opcode) {
	case BPF_JEQ:
		/* If this is false then we know nothing Jon Snow, but if it is
		 * true then we know for sure.
		 */
		true_reg->max_value = true_reg->min_value = val;
		break;
	case BPF_JNE:
		/* If this is true we know nothing Jon Snow, but if it is false
		 * we know the value for sure;
		 */
		false_reg->max_value = false_reg->min_value = val;
		break;
	case BPF_JGT:
		/* Unsigned comparison, the minimum value is 0. */
		true_reg->min_value = 0;
2073
		/* fallthrough */
2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084
	case BPF_JSGT:
		/*
		 * If this is false, then the val is <= the register, if it is
		 * true the register <= to the val.
		 */
		false_reg->min_value = val;
		true_reg->max_value = val - 1;
		break;
	case BPF_JGE:
		/* Unsigned comparison, the minimum value is 0. */
		true_reg->min_value = 0;
2085
		/* fallthrough */
2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100
	case BPF_JSGE:
		/* If this is false then constant < register, if it is true then
		 * the register < constant.
		 */
		false_reg->min_value = val + 1;
		true_reg->max_value = val;
		break;
	default:
		break;
	}

	check_reg_overflow(false_reg);
	check_reg_overflow(true_reg);
}

2101 2102 2103 2104 2105 2106
static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
			 enum bpf_reg_type type)
{
	struct bpf_reg_state *reg = &regs[regno];

	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
2107 2108 2109 2110 2111 2112 2113 2114
		if (type == UNKNOWN_VALUE) {
			__mark_reg_unknown_value(regs, regno);
		} else if (reg->map_ptr->inner_map_meta) {
			reg->type = CONST_PTR_TO_MAP;
			reg->map_ptr = reg->map_ptr->inner_map_meta;
		} else {
			reg->type = type;
		}
2115 2116 2117 2118 2119
		/* We don't need id from this point onwards anymore, thus we
		 * should better reset it, so that state pruning has chances
		 * to take effect.
		 */
		reg->id = 0;
2120 2121 2122 2123 2124 2125 2126 2127 2128 2129
	}
}

/* The logic is similar to find_good_pkt_pointers(), both could eventually
 * be folded together at some point.
 */
static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
			  enum bpf_reg_type type)
{
	struct bpf_reg_state *regs = state->regs;
2130
	u32 id = regs[regno].id;
2131 2132 2133
	int i;

	for (i = 0; i < MAX_BPF_REG; i++)
2134
		mark_map_reg(regs, i, id, type);
2135 2136 2137 2138

	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
		if (state->stack_slot_type[i] != STACK_SPILL)
			continue;
2139
		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type);
2140 2141 2142
	}
}

2143
static int check_cond_jmp_op(struct bpf_verifier_env *env,
2144 2145
			     struct bpf_insn *insn, int *insn_idx)
{
2146 2147
	struct bpf_verifier_state *other_branch, *this_branch = &env->cur_state;
	struct bpf_reg_state *regs = this_branch->regs, *dst_reg;
2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode > BPF_EXIT) {
		verbose("invalid BPF_JMP opcode %x\n", opcode);
		return -EINVAL;
	}

	if (BPF_SRC(insn->code) == BPF_X) {
		if (insn->imm != 0) {
			verbose("BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}

		/* check src1 operand */
		err = check_reg_arg(regs, insn->src_reg, SRC_OP);
		if (err)
			return err;
2166 2167 2168 2169 2170 2171

		if (is_pointer_value(env, insn->src_reg)) {
			verbose("R%d pointer comparison prohibited\n",
				insn->src_reg);
			return -EACCES;
		}
2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183
	} else {
		if (insn->src_reg != BPF_REG_0) {
			verbose("BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}
	}

	/* check src2 operand */
	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
	if (err)
		return err;

A
Alexei Starovoitov 已提交
2184 2185
	dst_reg = &regs[insn->dst_reg];

2186 2187 2188
	/* detect if R == 0 where R was initialized to zero earlier */
	if (BPF_SRC(insn->code) == BPF_K &&
	    (opcode == BPF_JEQ || opcode == BPF_JNE) &&
A
Alexei Starovoitov 已提交
2189
	    dst_reg->type == CONST_IMM && dst_reg->imm == insn->imm) {
2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208
		if (opcode == BPF_JEQ) {
			/* if (imm == imm) goto pc+off;
			 * only follow the goto, ignore fall-through
			 */
			*insn_idx += insn->off;
			return 0;
		} else {
			/* if (imm != imm) goto pc+off;
			 * only follow fall-through branch, since
			 * that's where the program will go
			 */
			return 0;
		}
	}

	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
	if (!other_branch)
		return -EFAULT;

2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225
	/* detect if we are comparing against a constant value so we can adjust
	 * our min/max values for our dst register.
	 */
	if (BPF_SRC(insn->code) == BPF_X) {
		if (regs[insn->src_reg].type == CONST_IMM)
			reg_set_min_max(&other_branch->regs[insn->dst_reg],
					dst_reg, regs[insn->src_reg].imm,
					opcode);
		else if (dst_reg->type == CONST_IMM)
			reg_set_min_max_inv(&other_branch->regs[insn->src_reg],
					    &regs[insn->src_reg], dst_reg->imm,
					    opcode);
	} else {
		reg_set_min_max(&other_branch->regs[insn->dst_reg],
					dst_reg, insn->imm, opcode);
	}

2226
	/* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
2227
	if (BPF_SRC(insn->code) == BPF_K &&
A
Alexei Starovoitov 已提交
2228 2229
	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
	    dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
2230 2231 2232 2233 2234 2235 2236
		/* Mark all identical map registers in each branch as either
		 * safe or unknown depending R == 0 or R != 0 conditional.
		 */
		mark_map_regs(this_branch, insn->dst_reg,
			      opcode == BPF_JEQ ? PTR_TO_MAP_VALUE : UNKNOWN_VALUE);
		mark_map_regs(other_branch, insn->dst_reg,
			      opcode == BPF_JEQ ? UNKNOWN_VALUE : PTR_TO_MAP_VALUE);
A
Alexei Starovoitov 已提交
2237 2238 2239
	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
		   dst_reg->type == PTR_TO_PACKET &&
		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
2240 2241 2242 2243 2244
		find_good_pkt_pointers(this_branch, dst_reg);
	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
		   dst_reg->type == PTR_TO_PACKET_END &&
		   regs[insn->src_reg].type == PTR_TO_PACKET) {
		find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
2245 2246 2247
	} else if (is_pointer_value(env, insn->dst_reg)) {
		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
		return -EACCES;
2248 2249
	}
	if (log_level)
2250
		print_verifier_state(this_branch);
2251 2252 2253
	return 0;
}

2254 2255 2256 2257 2258 2259 2260 2261
/* return the map pointer stored inside BPF_LD_IMM64 instruction */
static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
{
	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;

	return (struct bpf_map *) (unsigned long) imm64;
}

2262
/* verify BPF_LD_IMM64 instruction */
2263
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
2264
{
2265
	struct bpf_reg_state *regs = env->cur_state.regs;
2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280
	int err;

	if (BPF_SIZE(insn->code) != BPF_DW) {
		verbose("invalid BPF_LD_IMM insn\n");
		return -EINVAL;
	}
	if (insn->off != 0) {
		verbose("BPF_LD_IMM64 uses reserved fields\n");
		return -EINVAL;
	}

	err = check_reg_arg(regs, insn->dst_reg, DST_OP);
	if (err)
		return err;

2281 2282 2283 2284 2285
	if (insn->src_reg == 0) {
		u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;

		regs[insn->dst_reg].type = CONST_IMM;
		regs[insn->dst_reg].imm = imm;
2286
		return 0;
2287
	}
2288 2289 2290 2291 2292 2293 2294 2295 2296

	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);

	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
	return 0;
}

2297 2298 2299 2300 2301
static bool may_access_skb(enum bpf_prog_type type)
{
	switch (type) {
	case BPF_PROG_TYPE_SOCKET_FILTER:
	case BPF_PROG_TYPE_SCHED_CLS:
2302
	case BPF_PROG_TYPE_SCHED_ACT:
2303 2304 2305 2306 2307 2308
		return true;
	default:
		return false;
	}
}

2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323
/* verify safety of LD_ABS|LD_IND instructions:
 * - they can only appear in the programs where ctx == skb
 * - since they are wrappers of function calls, they scratch R1-R5 registers,
 *   preserve R6-R9, and store return value into R0
 *
 * Implicit input:
 *   ctx == skb == R6 == CTX
 *
 * Explicit input:
 *   SRC == any register
 *   IMM == 32-bit immediate
 *
 * Output:
 *   R0 - 8/16/32-bit skb data converted to cpu endianness
 */
2324
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
2325
{
2326
	struct bpf_reg_state *regs = env->cur_state.regs;
2327
	u8 mode = BPF_MODE(insn->code);
2328
	struct bpf_reg_state *reg;
2329 2330
	int i, err;

2331
	if (!may_access_skb(env->prog->type)) {
A
Alexei Starovoitov 已提交
2332
		verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
2333 2334 2335 2336
		return -EINVAL;
	}

	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
2337
	    BPF_SIZE(insn->code) == BPF_DW ||
2338
	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
A
Alexei Starovoitov 已提交
2339
		verbose("BPF_LD_[ABS|IND] uses reserved fields\n");
2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373
		return -EINVAL;
	}

	/* check whether implicit source operand (register R6) is readable */
	err = check_reg_arg(regs, BPF_REG_6, SRC_OP);
	if (err)
		return err;

	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
		verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
		return -EINVAL;
	}

	if (mode == BPF_IND) {
		/* check explicit source operand */
		err = check_reg_arg(regs, insn->src_reg, SRC_OP);
		if (err)
			return err;
	}

	/* reset caller saved regs to unreadable */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		reg = regs + caller_saved[i];
		reg->type = NOT_INIT;
		reg->imm = 0;
	}

	/* mark destination R0 register as readable, since it contains
	 * the value fetched from the packet
	 */
	regs[BPF_REG_0].type = UNKNOWN_VALUE;
	return 0;
}

2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413
/* non-recursive DFS pseudo code
 * 1  procedure DFS-iterative(G,v):
 * 2      label v as discovered
 * 3      let S be a stack
 * 4      S.push(v)
 * 5      while S is not empty
 * 6            t <- S.pop()
 * 7            if t is what we're looking for:
 * 8                return t
 * 9            for all edges e in G.adjacentEdges(t) do
 * 10               if edge e is already labelled
 * 11                   continue with the next edge
 * 12               w <- G.adjacentVertex(t,e)
 * 13               if vertex w is not discovered and not explored
 * 14                   label e as tree-edge
 * 15                   label w as discovered
 * 16                   S.push(w)
 * 17                   continue at 5
 * 18               else if vertex w is discovered
 * 19                   label e as back-edge
 * 20               else
 * 21                   // vertex w is explored
 * 22                   label e as forward- or cross-edge
 * 23           label t as explored
 * 24           S.pop()
 *
 * convention:
 * 0x10 - discovered
 * 0x11 - discovered and fall-through edge labelled
 * 0x12 - discovered and fall-through and branch edges labelled
 * 0x20 - explored
 */

enum {
	DISCOVERED = 0x10,
	EXPLORED = 0x20,
	FALLTHROUGH = 1,
	BRANCH = 2,
};

2414
#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
2415

2416 2417 2418 2419 2420 2421 2422 2423 2424
static int *insn_stack;	/* stack of insns to process */
static int cur_stack;	/* current stack index */
static int *insn_state;

/* t, w, e - match pseudo-code above:
 * t - index of current instruction
 * w - next instruction
 * e - edge
 */
2425
static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437
{
	if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
		return 0;

	if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
		return 0;

	if (w < 0 || w >= env->prog->len) {
		verbose("jump out of range from insn %d to %d\n", t, w);
		return -EINVAL;
	}

2438 2439 2440 2441
	if (e == BRANCH)
		/* mark branch target for state pruning */
		env->explored_states[w] = STATE_LIST_MARK;

2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465
	if (insn_state[w] == 0) {
		/* tree-edge */
		insn_state[t] = DISCOVERED | e;
		insn_state[w] = DISCOVERED;
		if (cur_stack >= env->prog->len)
			return -E2BIG;
		insn_stack[cur_stack++] = w;
		return 1;
	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
		verbose("back-edge from insn %d to %d\n", t, w);
		return -EINVAL;
	} else if (insn_state[w] == EXPLORED) {
		/* forward- or cross-edge */
		insn_state[t] = DISCOVERED | e;
	} else {
		verbose("insn state internal bug\n");
		return -EFAULT;
	}
	return 0;
}

/* non-recursive depth-first-search to detect loops in BPF program
 * loop == back-edge in directed graph
 */
2466
static int check_cfg(struct bpf_verifier_env *env)
2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502
{
	struct bpf_insn *insns = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int ret = 0;
	int i, t;

	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_state)
		return -ENOMEM;

	insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_stack) {
		kfree(insn_state);
		return -ENOMEM;
	}

	insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
	insn_stack[0] = 0; /* 0 is the first instruction */
	cur_stack = 1;

peek_stack:
	if (cur_stack == 0)
		goto check_state;
	t = insn_stack[cur_stack - 1];

	if (BPF_CLASS(insns[t].code) == BPF_JMP) {
		u8 opcode = BPF_OP(insns[t].code);

		if (opcode == BPF_EXIT) {
			goto mark_explored;
		} else if (opcode == BPF_CALL) {
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
2503 2504
			if (t + 1 < insn_cnt)
				env->explored_states[t + 1] = STATE_LIST_MARK;
2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516
		} else if (opcode == BPF_JA) {
			if (BPF_SRC(insns[t].code) != BPF_K) {
				ret = -EINVAL;
				goto err_free;
			}
			/* unconditional jump with single edge */
			ret = push_insn(t, t + insns[t].off + 1,
					FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
2517 2518 2519
			/* tell verifier to check for equivalent states
			 * after every call and jump
			 */
2520 2521
			if (t + 1 < insn_cnt)
				env->explored_states[t + 1] = STATE_LIST_MARK;
2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571
		} else {
			/* conditional jump with two edges */
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;

			ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
		}
	} else {
		/* all other non-branch instructions with single
		 * fall-through edge
		 */
		ret = push_insn(t, t + 1, FALLTHROUGH, env);
		if (ret == 1)
			goto peek_stack;
		else if (ret < 0)
			goto err_free;
	}

mark_explored:
	insn_state[t] = EXPLORED;
	if (cur_stack-- <= 0) {
		verbose("pop stack internal bug\n");
		ret = -EFAULT;
		goto err_free;
	}
	goto peek_stack;

check_state:
	for (i = 0; i < insn_cnt; i++) {
		if (insn_state[i] != EXPLORED) {
			verbose("unreachable insn %d\n", i);
			ret = -EINVAL;
			goto err_free;
		}
	}
	ret = 0; /* cfg looks good */

err_free:
	kfree(insn_state);
	kfree(insn_stack);
	return ret;
}

A
Alexei Starovoitov 已提交
2572 2573 2574
/* the following conditions reduce the number of explored insns
 * from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet
 */
2575 2576
static bool compare_ptrs_to_packet(struct bpf_reg_state *old,
				   struct bpf_reg_state *cur)
A
Alexei Starovoitov 已提交
2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624
{
	if (old->id != cur->id)
		return false;

	/* old ptr_to_packet is more conservative, since it allows smaller
	 * range. Ex:
	 * old(off=0,r=10) is equal to cur(off=0,r=20), because
	 * old(off=0,r=10) means that with range=10 the verifier proceeded
	 * further and found no issues with the program. Now we're in the same
	 * spot with cur(off=0,r=20), so we're safe too, since anything further
	 * will only be looking at most 10 bytes after this pointer.
	 */
	if (old->off == cur->off && old->range < cur->range)
		return true;

	/* old(off=20,r=10) is equal to cur(off=22,re=22 or 5 or 0)
	 * since both cannot be used for packet access and safe(old)
	 * pointer has smaller off that could be used for further
	 * 'if (ptr > data_end)' check
	 * Ex:
	 * old(off=20,r=10) and cur(off=22,r=22) and cur(off=22,r=0) mean
	 * that we cannot access the packet.
	 * The safe range is:
	 * [ptr, ptr + range - off)
	 * so whenever off >=range, it means no safe bytes from this pointer.
	 * When comparing old->off <= cur->off, it means that older code
	 * went with smaller offset and that offset was later
	 * used to figure out the safe range after 'if (ptr > data_end)' check
	 * Say, 'old' state was explored like:
	 * ... R3(off=0, r=0)
	 * R4 = R3 + 20
	 * ... now R4(off=20,r=0)  <-- here
	 * if (R4 > data_end)
	 * ... R4(off=20,r=20), R3(off=0,r=20) and R3 can be used to access.
	 * ... the code further went all the way to bpf_exit.
	 * Now the 'cur' state at the mark 'here' has R4(off=30,r=0).
	 * old_R4(off=20,r=0) equal to cur_R4(off=30,r=0), since if the verifier
	 * goes further, such cur_R4 will give larger safe packet range after
	 * 'if (R4 > data_end)' and all further insn were already good with r=20,
	 * so they will be good with r=30 and we can prune the search.
	 */
	if (old->off <= cur->off &&
	    old->off >= old->range && cur->off >= cur->range)
		return true;

	return false;
}

2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650
/* compare two verifier states
 *
 * all states stored in state_list are known to be valid, since
 * verifier reached 'bpf_exit' instruction through them
 *
 * this function is called when verifier exploring different branches of
 * execution popped from the state stack. If it sees an old state that has
 * more strict register state and more strict stack state then this execution
 * branch doesn't need to be explored further, since verifier already
 * concluded that more strict state leads to valid finish.
 *
 * Therefore two states are equivalent if register state is more conservative
 * and explored stack state is more conservative than the current one.
 * Example:
 *       explored                   current
 * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
 * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
 *
 * In other words if current stack state (one being explored) has more
 * valid slots than old one that already passed validation, it means
 * the verifier can stop exploring and conclude that current state is valid too
 *
 * Similarly with registers. If explored state has register type as invalid
 * whereas register type in current state is meaningful, it means that
 * the current state will reach 'bpf_exit' instruction safely
 */
2651 2652
static bool states_equal(struct bpf_verifier_env *env,
			 struct bpf_verifier_state *old,
2653
			 struct bpf_verifier_state *cur)
2654
{
2655
	bool varlen_map_access = env->varlen_map_value_access;
2656
	struct bpf_reg_state *rold, *rcur;
2657 2658 2659
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
A
Alexei Starovoitov 已提交
2660 2661 2662 2663 2664 2665
		rold = &old->regs[i];
		rcur = &cur->regs[i];

		if (memcmp(rold, rcur, sizeof(*rold)) == 0)
			continue;

2666 2667 2668
		/* If the ranges were not the same, but everything else was and
		 * we didn't do a variable access into a map then we are a-ok.
		 */
2669
		if (!varlen_map_access &&
A
Alexei Starovoitov 已提交
2670
		    memcmp(rold, rcur, offsetofend(struct bpf_reg_state, id)) == 0)
2671 2672
			continue;

2673 2674 2675 2676
		/* If we didn't map access then again we don't care about the
		 * mismatched range values and it's ok if our old type was
		 * UNKNOWN and we didn't go to a NOT_INIT'ed reg.
		 */
A
Alexei Starovoitov 已提交
2677
		if (rold->type == NOT_INIT ||
2678 2679
		    (!varlen_map_access && rold->type == UNKNOWN_VALUE &&
		     rcur->type != NOT_INIT))
A
Alexei Starovoitov 已提交
2680 2681
			continue;

A
Alexei Starovoitov 已提交
2682 2683 2684 2685
		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
		    compare_ptrs_to_packet(rold, rcur))
			continue;

A
Alexei Starovoitov 已提交
2686
		return false;
2687 2688 2689
	}

	for (i = 0; i < MAX_BPF_STACK; i++) {
2690 2691 2692 2693 2694 2695 2696 2697
		if (old->stack_slot_type[i] == STACK_INVALID)
			continue;
		if (old->stack_slot_type[i] != cur->stack_slot_type[i])
			/* Ex: old explored (safe) state has STACK_SPILL in
			 * this stack slot, but current has has STACK_MISC ->
			 * this verifier states are not equivalent,
			 * return false to continue verification of this path
			 */
2698
			return false;
2699 2700 2701 2702 2703 2704 2705 2706 2707
		if (i % BPF_REG_SIZE)
			continue;
		if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE],
			   &cur->spilled_regs[i / BPF_REG_SIZE],
			   sizeof(old->spilled_regs[0])))
			/* when explored and current stack slot types are
			 * the same, check that stored pointers types
			 * are the same as well.
			 * Ex: explored safe path could have stored
2708
			 * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -8}
2709
			 * but current path has stored:
2710
			 * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -16}
2711 2712 2713 2714 2715 2716
			 * such verifier states are not equivalent.
			 * return false to continue verification of this path
			 */
			return false;
		else
			continue;
2717 2718 2719 2720
	}
	return true;
}

2721
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
2722
{
2723 2724
	struct bpf_verifier_state_list *new_sl;
	struct bpf_verifier_state_list *sl;
2725 2726 2727 2728 2729 2730 2731 2732 2733

	sl = env->explored_states[insn_idx];
	if (!sl)
		/* this 'insn_idx' instruction wasn't marked, so we will not
		 * be doing state search here
		 */
		return 0;

	while (sl != STATE_LIST_MARK) {
2734
		if (states_equal(env, &sl->state, &env->cur_state))
2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747
			/* reached equivalent register/stack state,
			 * prune the search
			 */
			return 1;
		sl = sl->next;
	}

	/* there were no equivalent states, remember current one.
	 * technically the current state is not proven to be safe yet,
	 * but it will either reach bpf_exit (which means it's safe) or
	 * it will be rejected. Since there are no loops, we won't be
	 * seeing this 'insn_idx' instruction again on the way to bpf_exit
	 */
2748
	new_sl = kmalloc(sizeof(struct bpf_verifier_state_list), GFP_USER);
2749 2750 2751 2752 2753 2754 2755 2756 2757 2758
	if (!new_sl)
		return -ENOMEM;

	/* add new state to the head of linked list */
	memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state));
	new_sl->next = env->explored_states[insn_idx];
	env->explored_states[insn_idx] = new_sl;
	return 0;
}

2759 2760 2761 2762 2763 2764 2765 2766 2767
static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
				  int insn_idx, int prev_insn_idx)
{
	if (!env->analyzer_ops || !env->analyzer_ops->insn_hook)
		return 0;

	return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx);
}

2768
static int do_check(struct bpf_verifier_env *env)
2769
{
2770
	struct bpf_verifier_state *state = &env->cur_state;
2771
	struct bpf_insn *insns = env->prog->insnsi;
2772
	struct bpf_reg_state *regs = state->regs;
2773 2774 2775 2776 2777 2778 2779
	int insn_cnt = env->prog->len;
	int insn_idx, prev_insn_idx = 0;
	int insn_processed = 0;
	bool do_print_state = false;

	init_reg_state(regs);
	insn_idx = 0;
2780
	env->varlen_map_value_access = false;
2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794
	for (;;) {
		struct bpf_insn *insn;
		u8 class;
		int err;

		if (insn_idx >= insn_cnt) {
			verbose("invalid insn idx %d insn_cnt %d\n",
				insn_idx, insn_cnt);
			return -EFAULT;
		}

		insn = &insns[insn_idx];
		class = BPF_CLASS(insn->code);

2795
		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
2796
			verbose("BPF program is too large. Processed %d insn\n",
2797 2798 2799 2800
				insn_processed);
			return -E2BIG;
		}

2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815
		err = is_state_visited(env, insn_idx);
		if (err < 0)
			return err;
		if (err == 1) {
			/* found equivalent state, can prune the search */
			if (log_level) {
				if (do_print_state)
					verbose("\nfrom %d to %d: safe\n",
						prev_insn_idx, insn_idx);
				else
					verbose("%d: safe\n", insn_idx);
			}
			goto process_bpf_exit;
		}

2816 2817
		if (log_level && do_print_state) {
			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
A
Alexei Starovoitov 已提交
2818
			print_verifier_state(&env->cur_state);
2819 2820 2821 2822 2823 2824 2825 2826
			do_print_state = false;
		}

		if (log_level) {
			verbose("%d: ", insn_idx);
			print_bpf_insn(insn);
		}

2827 2828 2829 2830
		err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
		if (err)
			return err;

2831
		if (class == BPF_ALU || class == BPF_ALU64) {
2832
			err = check_alu_op(env, insn);
2833 2834 2835 2836
			if (err)
				return err;

		} else if (class == BPF_LDX) {
2837
			enum bpf_reg_type *prev_src_type, src_reg_type;
2838 2839 2840

			/* check for reserved fields is already done */

2841 2842 2843 2844 2845 2846 2847 2848 2849
			/* check src operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;

			err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK);
			if (err)
				return err;

2850 2851
			src_reg_type = regs[insn->src_reg].type;

2852 2853 2854 2855 2856 2857 2858 2859 2860
			/* check that memory (src_reg + off) is readable,
			 * the state of dst_reg will be updated by this func
			 */
			err = check_mem_access(env, insn->src_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_READ,
					       insn->dst_reg);
			if (err)
				return err;

2861 2862
			if (BPF_SIZE(insn->code) != BPF_W &&
			    BPF_SIZE(insn->code) != BPF_DW) {
2863 2864 2865
				insn_idx++;
				continue;
			}
2866

2867 2868 2869
			prev_src_type = &env->insn_aux_data[insn_idx].ptr_type;

			if (*prev_src_type == NOT_INIT) {
2870 2871
				/* saw a valid insn
				 * dst_reg = *(u32 *)(src_reg + off)
2872
				 * save type to validate intersecting paths
2873
				 */
2874
				*prev_src_type = src_reg_type;
2875

2876
			} else if (src_reg_type != *prev_src_type &&
2877
				   (src_reg_type == PTR_TO_CTX ||
2878
				    *prev_src_type == PTR_TO_CTX)) {
2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889
				/* ABuser program is trying to use the same insn
				 * dst_reg = *(u32*) (src_reg + off)
				 * with different pointer types:
				 * src_reg == ctx in one branch and
				 * src_reg == stack|map in some other branch.
				 * Reject it.
				 */
				verbose("same insn cannot be used with different pointers\n");
				return -EINVAL;
			}

2890
		} else if (class == BPF_STX) {
2891
			enum bpf_reg_type *prev_dst_type, dst_reg_type;
2892

2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909
			if (BPF_MODE(insn->code) == BPF_XADD) {
				err = check_xadd(env, insn);
				if (err)
					return err;
				insn_idx++;
				continue;
			}

			/* check src1 operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
			/* check src2 operand */
			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
			if (err)
				return err;

2910 2911
			dst_reg_type = regs[insn->dst_reg].type;

2912 2913 2914 2915 2916 2917 2918
			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, insn->dst_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_WRITE,
					       insn->src_reg);
			if (err)
				return err;

2919 2920 2921 2922 2923
			prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type;

			if (*prev_dst_type == NOT_INIT) {
				*prev_dst_type = dst_reg_type;
			} else if (dst_reg_type != *prev_dst_type &&
2924
				   (dst_reg_type == PTR_TO_CTX ||
2925
				    *prev_dst_type == PTR_TO_CTX)) {
2926 2927 2928 2929
				verbose("same insn cannot be used with different pointers\n");
				return -EINVAL;
			}

2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959
		} else if (class == BPF_ST) {
			if (BPF_MODE(insn->code) != BPF_MEM ||
			    insn->src_reg != BPF_REG_0) {
				verbose("BPF_ST uses reserved fields\n");
				return -EINVAL;
			}
			/* check src operand */
			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
			if (err)
				return err;

			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, insn->dst_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_WRITE,
					       -1);
			if (err)
				return err;

		} else if (class == BPF_JMP) {
			u8 opcode = BPF_OP(insn->code);

			if (opcode == BPF_CALL) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->off != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_CALL uses reserved fields\n");
					return -EINVAL;
				}

2960
				err = check_call(env, insn->imm, insn_idx);
2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994
				if (err)
					return err;

			} else if (opcode == BPF_JA) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_JA uses reserved fields\n");
					return -EINVAL;
				}

				insn_idx += insn->off + 1;
				continue;

			} else if (opcode == BPF_EXIT) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_EXIT uses reserved fields\n");
					return -EINVAL;
				}

				/* eBPF calling convetion is such that R0 is used
				 * to return the value from eBPF program.
				 * Make sure that it's readable at this time
				 * of bpf_exit, which means that program wrote
				 * something into it earlier
				 */
				err = check_reg_arg(regs, BPF_REG_0, SRC_OP);
				if (err)
					return err;

2995 2996 2997 2998 2999
				if (is_pointer_value(env, BPF_REG_0)) {
					verbose("R0 leaks addr as return value\n");
					return -EACCES;
				}

3000
process_bpf_exit:
3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016
				insn_idx = pop_stack(env, &prev_insn_idx);
				if (insn_idx < 0) {
					break;
				} else {
					do_print_state = true;
					continue;
				}
			} else {
				err = check_cond_jmp_op(env, insn, &insn_idx);
				if (err)
					return err;
			}
		} else if (class == BPF_LD) {
			u8 mode = BPF_MODE(insn->code);

			if (mode == BPF_ABS || mode == BPF_IND) {
3017 3018 3019 3020
				err = check_ld_abs(env, insn);
				if (err)
					return err;

3021 3022 3023 3024 3025 3026 3027 3028 3029 3030
			} else if (mode == BPF_IMM) {
				err = check_ld_imm(env, insn);
				if (err)
					return err;

				insn_idx++;
			} else {
				verbose("invalid BPF_LD mode\n");
				return -EINVAL;
			}
3031
			reset_reg_range_values(regs, insn->dst_reg);
3032 3033 3034 3035 3036 3037 3038 3039
		} else {
			verbose("unknown insn class %d\n", class);
			return -EINVAL;
		}

		insn_idx++;
	}

A
Alexei Starovoitov 已提交
3040
	verbose("processed %d insns\n", insn_processed);
3041 3042 3043
	return 0;
}

3044 3045 3046 3047 3048 3049 3050
static int check_map_prealloc(struct bpf_map *map)
{
	return (map->map_type != BPF_MAP_TYPE_HASH &&
		map->map_type != BPF_MAP_TYPE_PERCPU_HASH) ||
		!(map->map_flags & BPF_F_NO_PREALLOC);
}

3051 3052 3053 3054
static int check_map_prog_compatibility(struct bpf_map *map,
					struct bpf_prog *prog)

{
3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069
	/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
	 * preallocated hash maps, since doing memory allocation
	 * in overflow_handler can crash depending on where nmi got
	 * triggered.
	 */
	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
		if (!check_map_prealloc(map)) {
			verbose("perf_event programs can only use preallocated hash map\n");
			return -EINVAL;
		}
		if (map->inner_map_meta &&
		    !check_map_prealloc(map->inner_map_meta)) {
			verbose("perf_event programs can only use preallocated inner hash map\n");
			return -EINVAL;
		}
3070 3071 3072 3073
	}
	return 0;
}

3074 3075 3076
/* look for pseudo eBPF instructions that access map FDs and
 * replace them with actual map pointers
 */
3077
static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
3078 3079 3080
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
3081
	int i, j, err;
3082

3083
	err = bpf_prog_calc_tag(env->prog);
3084 3085 3086
	if (err)
		return err;

3087
	for (i = 0; i < insn_cnt; i++, insn++) {
3088
		if (BPF_CLASS(insn->code) == BPF_LDX &&
3089
		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
3090 3091 3092 3093
			verbose("BPF_LDX uses reserved fields\n");
			return -EINVAL;
		}

3094 3095 3096 3097 3098 3099 3100
		if (BPF_CLASS(insn->code) == BPF_STX &&
		    ((BPF_MODE(insn->code) != BPF_MEM &&
		      BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
			verbose("BPF_STX uses reserved fields\n");
			return -EINVAL;
		}

3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121
		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
			struct bpf_map *map;
			struct fd f;

			if (i == insn_cnt - 1 || insn[1].code != 0 ||
			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
			    insn[1].off != 0) {
				verbose("invalid bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			if (insn->src_reg == 0)
				/* valid generic load 64-bit imm */
				goto next_insn;

			if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
				verbose("unrecognized bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			f = fdget(insn->imm);
3122
			map = __bpf_map_get(f);
3123 3124 3125 3126 3127 3128
			if (IS_ERR(map)) {
				verbose("fd %d is not pointing to valid bpf_map\n",
					insn->imm);
				return PTR_ERR(map);
			}

3129 3130 3131 3132 3133 3134
			err = check_map_prog_compatibility(map, env->prog);
			if (err) {
				fdput(f);
				return err;
			}

3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155
			/* store map pointer inside BPF_LD_IMM64 instruction */
			insn[0].imm = (u32) (unsigned long) map;
			insn[1].imm = ((u64) (unsigned long) map) >> 32;

			/* check whether we recorded this map already */
			for (j = 0; j < env->used_map_cnt; j++)
				if (env->used_maps[j] == map) {
					fdput(f);
					goto next_insn;
				}

			if (env->used_map_cnt >= MAX_USED_MAPS) {
				fdput(f);
				return -E2BIG;
			}

			/* hold the map. If the program is rejected by verifier,
			 * the map will be released by release_maps() or it
			 * will be used by the valid program until it's unloaded
			 * and all maps are released in free_bpf_prog_info()
			 */
A
Alexei Starovoitov 已提交
3156 3157 3158 3159 3160 3161 3162
			map = bpf_map_inc(map, false);
			if (IS_ERR(map)) {
				fdput(f);
				return PTR_ERR(map);
			}
			env->used_maps[env->used_map_cnt++] = map;

3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177
			fdput(f);
next_insn:
			insn++;
			i++;
		}
	}

	/* now all pseudo BPF_LD_IMM64 instructions load valid
	 * 'struct bpf_map *' into a register instead of user map_fd.
	 * These pointers will be used later by verifier to validate map access.
	 */
	return 0;
}

/* drop refcnt of maps used by the rejected program */
3178
static void release_maps(struct bpf_verifier_env *env)
3179 3180 3181 3182 3183 3184 3185 3186
{
	int i;

	for (i = 0; i < env->used_map_cnt; i++)
		bpf_map_put(env->used_maps[i]);
}

/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
3187
static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
3188 3189 3190 3191 3192 3193 3194 3195 3196 3197
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++, insn++)
		if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
			insn->src_reg = 0;
}

3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232
/* single env->prog->insni[off] instruction was replaced with the range
 * insni[off, off + cnt).  Adjust corresponding insn_aux_data by copying
 * [0, off) and [off, end) to new locations, so the patched range stays zero
 */
static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
				u32 off, u32 cnt)
{
	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;

	if (cnt == 1)
		return 0;
	new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
	if (!new_data)
		return -ENOMEM;
	memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
	memcpy(new_data + off + cnt - 1, old_data + off,
	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
	env->insn_aux_data = new_data;
	vfree(old_data);
	return 0;
}

static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
					    const struct bpf_insn *patch, u32 len)
{
	struct bpf_prog *new_prog;

	new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
	if (!new_prog)
		return NULL;
	if (adjust_insn_aux_data(env, new_prog->len, off, len))
		return NULL;
	return new_prog;
}

3233 3234 3235
/* convert load instructions that access fields of 'struct __sk_buff'
 * into sequence of instructions that access fields of 'struct sk_buff'
 */
3236
static int convert_ctx_accesses(struct bpf_verifier_env *env)
3237
{
3238
	const struct bpf_verifier_ops *ops = env->prog->aux->ops;
3239
	const int insn_cnt = env->prog->len;
3240
	struct bpf_insn insn_buf[16], *insn;
3241
	struct bpf_prog *new_prog;
3242
	enum bpf_access_type type;
3243
	int i, cnt, delta = 0;
3244

3245 3246 3247 3248 3249 3250 3251
	if (ops->gen_prologue) {
		cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
					env->prog);
		if (cnt >= ARRAY_SIZE(insn_buf)) {
			verbose("bpf verifier is misconfigured\n");
			return -EINVAL;
		} else if (cnt) {
3252
			new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
3253 3254
			if (!new_prog)
				return -ENOMEM;
3255

3256
			env->prog = new_prog;
3257
			delta += cnt - 1;
3258 3259 3260 3261
		}
	}

	if (!ops->convert_ctx_access)
3262 3263
		return 0;

3264
	insn = env->prog->insnsi + delta;
3265

3266
	for (i = 0; i < insn_cnt; i++, insn++) {
3267 3268 3269
		if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
		    insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
		    insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
3270
		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
3271
			type = BPF_READ;
3272 3273 3274
		else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
			 insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
			 insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
3275
			 insn->code == (BPF_STX | BPF_MEM | BPF_DW))
3276 3277
			type = BPF_WRITE;
		else
3278 3279
			continue;

3280
		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
3281 3282
			continue;

3283
		cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog);
3284 3285 3286 3287 3288
		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
			verbose("bpf verifier is misconfigured\n");
			return -EINVAL;
		}

3289
		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
3290 3291 3292
		if (!new_prog)
			return -ENOMEM;

3293
		delta += cnt - 1;
3294 3295 3296

		/* keep walking new program and skip insns we just inserted */
		env->prog = new_prog;
3297
		insn      = new_prog->insnsi + i + delta;
3298 3299 3300 3301 3302
	}

	return 0;
}

3303
/* fixup insn->imm field of bpf_call instructions
3304
 * and inline eligible helpers as explicit sequence of BPF instructions
3305 3306 3307
 *
 * this function is called after eBPF program passed verification
 */
3308
static int fixup_bpf_calls(struct bpf_verifier_env *env)
3309
{
3310 3311
	struct bpf_prog *prog = env->prog;
	struct bpf_insn *insn = prog->insnsi;
3312
	const struct bpf_func_proto *fn;
3313
	const int insn_cnt = prog->len;
3314 3315 3316 3317
	struct bpf_insn insn_buf[16];
	struct bpf_prog *new_prog;
	struct bpf_map *map_ptr;
	int i, cnt, delta = 0;
3318

3319 3320 3321
	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn->code != (BPF_JMP | BPF_CALL))
			continue;
3322

3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333
		if (insn->imm == BPF_FUNC_get_route_realm)
			prog->dst_needed = 1;
		if (insn->imm == BPF_FUNC_get_prandom_u32)
			bpf_user_rnd_init_once();
		if (insn->imm == BPF_FUNC_xdp_adjust_head)
			prog->xdp_adjust_head = 1;
		if (insn->imm == BPF_FUNC_tail_call) {
			/* mark bpf_tail_call as different opcode to avoid
			 * conditional branch in the interpeter for every normal
			 * call and to prevent accidental JITing by JIT compiler
			 * that doesn't support bpf_tail_call yet
3334
			 */
3335 3336 3337 3338
			insn->imm = 0;
			insn->code |= BPF_X;
			continue;
		}
3339

3340 3341
		if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) {
			map_ptr = env->insn_aux_data[i + delta].map_ptr;
3342 3343
			if (map_ptr == BPF_MAP_PTR_POISON ||
			    !map_ptr->ops->map_gen_lookup)
3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365
				goto patch_call_imm;

			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
				verbose("bpf verifier is misconfigured\n");
				return -EINVAL;
			}

			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
						       cnt);
			if (!new_prog)
				return -ENOMEM;

			delta += cnt - 1;

			/* keep walking new program and skip insns we just inserted */
			env->prog = prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

patch_call_imm:
3366 3367 3368 3369 3370 3371 3372 3373
		fn = prog->aux->ops->get_func_proto(insn->imm);
		/* all functions that have prototype and verifier allowed
		 * programs to call them, must be real in-kernel functions
		 */
		if (!fn->func) {
			verbose("kernel subsystem misconfigured func %s#%d\n",
				func_id_name(insn->imm), insn->imm);
			return -EFAULT;
3374
		}
3375
		insn->imm = fn->func - __bpf_call_base;
3376 3377
	}

3378 3379
	return 0;
}
3380

3381
static void free_states(struct bpf_verifier_env *env)
3382
{
3383
	struct bpf_verifier_state_list *sl, *sln;
3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402
	int i;

	if (!env->explored_states)
		return;

	for (i = 0; i < env->prog->len; i++) {
		sl = env->explored_states[i];

		if (sl)
			while (sl != STATE_LIST_MARK) {
				sln = sl->next;
				kfree(sl);
				sl = sln;
			}
	}

	kfree(env->explored_states);
}

3403
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
A
Alexei Starovoitov 已提交
3404
{
3405
	char __user *log_ubuf = NULL;
3406
	struct bpf_verifier_env *env;
A
Alexei Starovoitov 已提交
3407 3408
	int ret = -EINVAL;

3409
	/* 'struct bpf_verifier_env' can be global, but since it's not small,
3410 3411
	 * allocate/free it every time bpf_check() is called
	 */
3412
	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
3413 3414 3415
	if (!env)
		return -ENOMEM;

3416 3417 3418 3419 3420
	env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
				     (*prog)->len);
	ret = -ENOMEM;
	if (!env->insn_aux_data)
		goto err_free_env;
3421
	env->prog = *prog;
3422

3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438
	/* grab the mutex to protect few globals used by verifier */
	mutex_lock(&bpf_verifier_lock);

	if (attr->log_level || attr->log_buf || attr->log_size) {
		/* user requested verbose verifier output
		 * and supplied buffer to store the verification trace
		 */
		log_level = attr->log_level;
		log_ubuf = (char __user *) (unsigned long) attr->log_buf;
		log_size = attr->log_size;
		log_len = 0;

		ret = -EINVAL;
		/* log_* values have to be sane */
		if (log_size < 128 || log_size > UINT_MAX >> 8 ||
		    log_level == 0 || log_ubuf == NULL)
3439
			goto err_unlock;
3440 3441 3442 3443

		ret = -ENOMEM;
		log_buf = vmalloc(log_size);
		if (!log_buf)
3444
			goto err_unlock;
3445 3446 3447 3448
	} else {
		log_level = 0;
	}

3449 3450 3451 3452
	ret = replace_map_fd_with_map_ptr(env);
	if (ret < 0)
		goto skip_full_check;

3453
	env->explored_states = kcalloc(env->prog->len,
3454
				       sizeof(struct bpf_verifier_state_list *),
3455 3456 3457 3458 3459
				       GFP_USER);
	ret = -ENOMEM;
	if (!env->explored_states)
		goto skip_full_check;

3460 3461 3462 3463
	ret = check_cfg(env);
	if (ret < 0)
		goto skip_full_check;

3464 3465
	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);

3466
	ret = do_check(env);
3467

3468
skip_full_check:
3469
	while (pop_stack(env, NULL) >= 0);
3470
	free_states(env);
3471

3472 3473 3474 3475
	if (ret == 0)
		/* program is valid, convert *(u32*)(ctx + off) accesses */
		ret = convert_ctx_accesses(env);

3476
	if (ret == 0)
3477
		ret = fixup_bpf_calls(env);
3478

3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491
	if (log_level && log_len >= log_size - 1) {
		BUG_ON(log_len >= log_size);
		/* verifier log exceeded user supplied buffer */
		ret = -ENOSPC;
		/* fall through to return what was recorded */
	}

	/* copy verifier log back to user space including trailing zero */
	if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
		ret = -EFAULT;
		goto free_log_buf;
	}

3492 3493
	if (ret == 0 && env->used_map_cnt) {
		/* if program passed verifier, update used_maps in bpf_prog_info */
3494 3495 3496
		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
							  sizeof(env->used_maps[0]),
							  GFP_KERNEL);
3497

3498
		if (!env->prog->aux->used_maps) {
3499 3500 3501 3502
			ret = -ENOMEM;
			goto free_log_buf;
		}

3503
		memcpy(env->prog->aux->used_maps, env->used_maps,
3504
		       sizeof(env->used_maps[0]) * env->used_map_cnt);
3505
		env->prog->aux->used_map_cnt = env->used_map_cnt;
3506 3507 3508 3509 3510 3511

		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
		 * bpf_ld_imm64 instructions
		 */
		convert_pseudo_ld_imm64(env);
	}
3512 3513 3514 3515

free_log_buf:
	if (log_level)
		vfree(log_buf);
3516
	if (!env->prog->aux->used_maps)
3517 3518 3519 3520
		/* if we didn't copy map pointers into bpf_prog_info, release
		 * them now. Otherwise free_bpf_prog_info() will release them.
		 */
		release_maps(env);
3521
	*prog = env->prog;
3522
err_unlock:
3523
	mutex_unlock(&bpf_verifier_lock);
3524 3525 3526
	vfree(env->insn_aux_data);
err_free_env:
	kfree(env);
A
Alexei Starovoitov 已提交
3527 3528
	return ret;
}
3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579

int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
		 void *priv)
{
	struct bpf_verifier_env *env;
	int ret;

	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
	if (!env)
		return -ENOMEM;

	env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
				     prog->len);
	ret = -ENOMEM;
	if (!env->insn_aux_data)
		goto err_free_env;
	env->prog = prog;
	env->analyzer_ops = ops;
	env->analyzer_priv = priv;

	/* grab the mutex to protect few globals used by verifier */
	mutex_lock(&bpf_verifier_lock);

	log_level = 0;

	env->explored_states = kcalloc(env->prog->len,
				       sizeof(struct bpf_verifier_state_list *),
				       GFP_KERNEL);
	ret = -ENOMEM;
	if (!env->explored_states)
		goto skip_full_check;

	ret = check_cfg(env);
	if (ret < 0)
		goto skip_full_check;

	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);

	ret = do_check(env);

skip_full_check:
	while (pop_stack(env, NULL) >= 0);
	free_states(env);

	mutex_unlock(&bpf_verifier_lock);
	vfree(env->insn_aux_data);
err_free_env:
	kfree(env);
	return ret;
}
EXPORT_SYMBOL_GPL(bpf_analyzer);