verifier.c 92.4 KB
Newer Older
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
Alexei Starovoitov's avatar
Alexei Starovoitov committed
2
 * Copyright (c) 2016 Facebook
Alexei Starovoitov's avatar
Alexei Starovoitov committed
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>
Alexei Starovoitov's avatar
Alexei Starovoitov committed
18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>

/* 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
 * analysis is limited to 32k insn, which may be hit even if total number of
 * 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.
 */

130
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
131
struct bpf_verifier_stack_elem {
132 133 134 135
	/* verifer state is 'st'
	 * before processing instruction 'insn_idx'
	 * and after processing instruction 'prev_insn_idx'
	 */
136
	struct bpf_verifier_state st;
137 138
	int insn_idx;
	int prev_insn_idx;
139
	struct bpf_verifier_stack_elem *next;
140 141
};

142 143 144
#define BPF_COMPLEXITY_LIMIT_INSNS	65536
#define BPF_COMPLEXITY_LIMIT_STACK	1024

145 146
struct bpf_call_arg_meta {
	struct bpf_map *map_ptr;
147
	bool raw_mode;
148
	bool pkt_access;
149 150
	int regno;
	int access_size;
151 152
};

153 154 155 156 157 158 159 160 161 162 163 164
/* 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
 */
165
static __printf(1, 2) void verbose(const char *fmt, ...)
166 167 168 169 170 171 172 173 174 175 176
{
	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);
}

177 178 179 180 181 182 183 184
/* 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",
185
	[PTR_TO_MAP_VALUE_ADJ]	= "map_value_adj",
186 187 188
	[FRAME_PTR]		= "fp",
	[PTR_TO_STACK]		= "fp",
	[CONST_IMM]		= "imm",
Alexei Starovoitov's avatar
Alexei Starovoitov committed
189 190
	[PTR_TO_PACKET]		= "pkt",
	[PTR_TO_PACKET_END]	= "pkt_end",
191 192
};

193
static void print_verifier_state(struct bpf_verifier_state *state)
194
{
195
	struct bpf_reg_state *reg;
196 197 198 199
	enum bpf_reg_type t;
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
200 201
		reg = &state->regs[i];
		t = reg->type;
202 203 204 205
		if (t == NOT_INIT)
			continue;
		verbose(" R%d=%s", i, reg_type_str[t]);
		if (t == CONST_IMM || t == PTR_TO_STACK)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
206 207 208 209 210 211
			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);
212
		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
213 214
			 t == PTR_TO_MAP_VALUE_OR_NULL ||
			 t == PTR_TO_MAP_VALUE_ADJ)
215
			verbose("(ks=%d,vs=%d,id=%u)",
216
				reg->map_ptr->key_size,
217 218
				reg->map_ptr->value_size,
				reg->id);
219
		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
220 221
			verbose(",min_value=%lld",
				(long long)reg->min_value);
222 223 224
		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
			verbose(",max_value=%llu",
				(unsigned long long)reg->max_value);
225
	}
226
	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
227
		if (state->stack_slot_type[i] == STACK_SPILL)
228
			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
229
				reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
230 231 232 233
	}
	verbose("\n");
}

234 235 236 237 238 239 240 241 242 243 244
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",
};

245
static const char *const bpf_alu_string[16] = {
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
	[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",
};

269
static const char *const bpf_jmp_string[16] = {
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
	[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) {
			verbose("(%02x) call %d\n", insn->code, insn->imm);
		} 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]);
	}
}

379
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx)
380
{
381
	struct bpf_verifier_stack_elem *elem;
382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397
	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;
}

398 399
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
					     int insn_idx, int prev_insn_idx)
400
{
401
	struct bpf_verifier_stack_elem *elem;
402

403
	elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
404 405 406 407 408 409 410 411 412
	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++;
413
	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
		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
};

429
static void init_reg_state(struct bpf_reg_state *regs)
430 431 432 433 434 435
{
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
		regs[i].type = NOT_INIT;
		regs[i].imm = 0;
436 437
		regs[i].min_value = BPF_REGISTER_MIN_RANGE;
		regs[i].max_value = BPF_REGISTER_MAX_RANGE;
438 439 440 441 442 443 444 445 446
	}

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

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

447
static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
448 449
{
	regs[regno].type = UNKNOWN_VALUE;
450
	regs[regno].id = 0;
451 452 453
	regs[regno].imm = 0;
}

454 455 456 457 458 459
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);
}

460 461 462 463 464 465
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;
}

466 467 468 469 470 471
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 */
};

472
static int check_reg_arg(struct bpf_reg_state *regs, u32 regno,
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
			 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;
}

512 513 514 515 516 517 518
static bool is_spillable_regtype(enum bpf_reg_type type)
{
	switch (type) {
	case PTR_TO_MAP_VALUE:
	case PTR_TO_MAP_VALUE_OR_NULL:
	case PTR_TO_STACK:
	case PTR_TO_CTX:
Alexei Starovoitov's avatar
Alexei Starovoitov committed
519 520
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_END:
521 522 523 524 525 526 527 528
	case FRAME_PTR:
	case CONST_PTR_TO_MAP:
		return true;
	default:
		return false;
	}
}

529 530 531
/* check_stack_read/write functions track spill/fill of registers,
 * stack boundary and alignment are checked in check_mem_access()
 */
532 533
static int check_stack_write(struct bpf_verifier_state *state, int off,
			     int size, int value_regno)
534 535
{
	int i;
536 537 538
	/* 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
	 */
539 540

	if (value_regno >= 0 &&
541
	    is_spillable_regtype(state->regs[value_regno].type)) {
542 543

		/* register containing pointer is being spilled into stack */
544
		if (size != BPF_REG_SIZE) {
545 546 547 548 549
			verbose("invalid size of register spill\n");
			return -EACCES;
		}

		/* save register state */
550 551
		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
			state->regs[value_regno];
552

553 554 555
		for (i = 0; i < BPF_REG_SIZE; i++)
			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
	} else {
556
		/* regular write of data into stack */
557
		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
558
			(struct bpf_reg_state) {};
559 560 561

		for (i = 0; i < size; i++)
			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
562 563 564 565
	}
	return 0;
}

566
static int check_stack_read(struct bpf_verifier_state *state, int off, int size,
567 568
			    int value_regno)
{
569
	u8 *slot_type;
570 571
	int i;

572
	slot_type = &state->stack_slot_type[MAX_BPF_STACK + off];
573

574 575
	if (slot_type[0] == STACK_SPILL) {
		if (size != BPF_REG_SIZE) {
576 577 578
			verbose("invalid size of register spill\n");
			return -EACCES;
		}
579 580
		for (i = 1; i < BPF_REG_SIZE; i++) {
			if (slot_type[i] != STACK_SPILL) {
581 582 583 584 585 586 587
				verbose("corrupted spill memory\n");
				return -EACCES;
			}
		}

		if (value_regno >= 0)
			/* restore register state from stack */
588 589
			state->regs[value_regno] =
				state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE];
590 591 592
		return 0;
	} else {
		for (i = 0; i < size; i++) {
593
			if (slot_type[i] != STACK_MISC) {
594 595 596 597 598 599 600 601 602 603 604 605 606
				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 */
			mark_reg_unknown_value(state->regs, value_regno);
		return 0;
	}
}

/* check read/write into map element returned by bpf_map_lookup_elem() */
607
static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
608 609 610 611 612 613 614 615 616 617 618 619
			    int size)
{
	struct bpf_map *map = env->cur_state.regs[regno].map_ptr;

	if (off < 0 || off + size > map->value_size) {
		verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
			map->value_size, off, size);
		return -EACCES;
	}
	return 0;
}

Alexei Starovoitov's avatar
Alexei Starovoitov committed
620 621
#define MAX_PACKET_OFF 0xffff

622
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
623
				       const struct bpf_call_arg_meta *meta)
624
{
625 626 627
	switch (env->prog->type) {
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
628
	case BPF_PROG_TYPE_XDP:
629 630 631 632
		if (meta)
			return meta->pkt_access;

		env->seen_direct_write = true;
633 634 635 636 637 638
		return true;
	default:
		return false;
	}
}

639
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
Alexei Starovoitov's avatar
Alexei Starovoitov committed
640 641
			       int size)
{
642 643
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *reg = &regs[regno];
Alexei Starovoitov's avatar
Alexei Starovoitov committed
644

645
	off += reg->off;
646
	if (off < 0 || size <= 0 || off + size > reg->range) {
647 648
		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);
Alexei Starovoitov's avatar
Alexei Starovoitov committed
649 650 651 652 653
		return -EACCES;
	}
	return 0;
}

654
/* check access to 'struct bpf_context' fields */
655
static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
656
			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
657
{
658 659 660 661
	/* for analyzer ctx accesses are already validated and converted */
	if (env->analyzer_ops)
		return 0;

662
	if (env->prog->aux->ops->is_valid_access &&
663
	    env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
664 665 666
		/* 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;
667
		return 0;
668
	}
669 670 671 672 673

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

674
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
675 676 677 678 679 680 681 682 683 684 685 686 687
{
	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;
	}
}

688 689
static int check_ptr_alignment(struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg, int off, int size)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
690
{
691
	if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
Alexei Starovoitov's avatar
Alexei Starovoitov committed
692
		if (off % size != 0) {
693 694
			verbose("misaligned access off %d size %d\n",
				off, size);
Alexei Starovoitov's avatar
Alexei Starovoitov committed
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
			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 */
711 712
	if (reg->type == PTR_TO_PACKET &&
	    (NET_IP_ALIGN + reg->off + off) % size != 0) {
Alexei Starovoitov's avatar
Alexei Starovoitov committed
713 714 715 716 717 718 719
		verbose("misaligned packet access off %d+%d+%d size %d\n",
			NET_IP_ALIGN, reg->off, off, size);
		return -EACCES;
	}
	return 0;
}

720 721 722 723 724 725
/* 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
 */
726
static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
727 728 729
			    int bpf_size, enum bpf_access_type t,
			    int value_regno)
{
730 731
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *reg = &state->regs[regno];
732 733
	int size, err = 0;

734 735
	if (reg->type == PTR_TO_STACK)
		off += reg->imm;
736

737 738 739 740
	size = bpf_size_to_bytes(bpf_size);
	if (size < 0)
		return size;

Alexei Starovoitov's avatar
Alexei Starovoitov committed
741 742 743
	err = check_ptr_alignment(env, reg, off, size);
	if (err)
		return err;
744

745 746
	if (reg->type == PTR_TO_MAP_VALUE ||
	    reg->type == PTR_TO_MAP_VALUE_ADJ) {
747 748 749 750 751
		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;
		}
752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767

		/* If we adjusted the register to this map value at all then we
		 * need to change off and size to min_value and max_value
		 * respectively to make sure our theoretical access will be
		 * safe.
		 */
		if (reg->type == PTR_TO_MAP_VALUE_ADJ) {
			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.
			 */
768
			if (reg->min_value < 0) {
769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
				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;
			}
			off += reg->max_value;
		}
791 792 793 794
		err = check_map_access(env, regno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown_value(state->regs, value_regno);

795
	} else if (reg->type == PTR_TO_CTX) {
796 797
		enum bpf_reg_type reg_type = UNKNOWN_VALUE;

798 799 800 801 802
		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;
		}
803
		err = check_ctx_access(env, off, size, t, &reg_type);
Alexei Starovoitov's avatar
Alexei Starovoitov committed
804
		if (!err && t == BPF_READ && value_regno >= 0) {
805
			mark_reg_unknown_value(state->regs, value_regno);
806 807
			/* note that reg.[id|off|range] == 0 */
			state->regs[value_regno].type = reg_type;
Alexei Starovoitov's avatar
Alexei Starovoitov committed
808
		}
809

810
	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
811 812 813 814
		if (off >= 0 || off < -MAX_BPF_STACK) {
			verbose("invalid stack off=%d size=%d\n", off, size);
			return -EACCES;
		}
815 816 817 818 819 820 821
		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;
			}
822
			err = check_stack_write(state, off, size, value_regno);
823
		} else {
824
			err = check_stack_read(state, off, size, value_regno);
825
		}
Alexei Starovoitov's avatar
Alexei Starovoitov committed
826
	} else if (state->regs[regno].type == PTR_TO_PACKET) {
827
		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) {
Alexei Starovoitov's avatar
Alexei Starovoitov committed
828 829 830
			verbose("cannot write into packet\n");
			return -EACCES;
		}
831 832 833 834 835
		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;
		}
Alexei Starovoitov's avatar
Alexei Starovoitov committed
836 837 838
		err = check_packet_access(env, regno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown_value(state->regs, value_regno);
839 840
	} else {
		verbose("R%d invalid mem access '%s'\n",
841
			regno, reg_type_str[reg->type]);
842 843
		return -EACCES;
	}
Alexei Starovoitov's avatar
Alexei Starovoitov committed
844 845 846 847 848 849 850 851 852

	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;
	}
853 854 855
	return err;
}

856
static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
857
{
858
	struct bpf_reg_state *regs = env->cur_state.regs;
859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891
	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
 */
892
static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
893 894
				int access_size, bool zero_size_allowed,
				struct bpf_call_arg_meta *meta)
895
{
896 897
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *regs = state->regs;
898 899
	int off, i;

900 901 902 903 904 905 906 907 908
	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]);
909
		return -EACCES;
910
	}
911 912 913 914 915 916 917 918 919

	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;
	}

920 921 922 923 924 925
	if (meta && meta->raw_mode) {
		meta->access_size = access_size;
		meta->regno = regno;
		return 0;
	}

926
	for (i = 0; i < access_size; i++) {
927
		if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
928 929 930 931 932 933 934 935
			verbose("invalid indirect read from stack off %d+%d size %d\n",
				off, i, access_size);
			return -EACCES;
		}
	}
	return 0;
}

936
static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
937 938
			  enum bpf_arg_type arg_type,
			  struct bpf_call_arg_meta *meta)
939
{
940
	struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
941
	enum bpf_reg_type expected_type, type = reg->type;
942 943
	int err = 0;

944
	if (arg_type == ARG_DONTCARE)
945 946
		return 0;

947
	if (type == NOT_INIT) {
948 949 950 951
		verbose("R%d !read_ok\n", regno);
		return -EACCES;
	}

952 953 954 955 956
	if (arg_type == ARG_ANYTHING) {
		if (is_pointer_value(env, regno)) {
			verbose("R%d leaks addr into helper function\n", regno);
			return -EACCES;
		}
957
		return 0;
958
	}
959

960 961
	if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) {
		verbose("helper access to the packet is not allowed\n");
962 963 964
		return -EACCES;
	}

965
	if (arg_type == ARG_PTR_TO_MAP_KEY ||
966 967
	    arg_type == ARG_PTR_TO_MAP_VALUE) {
		expected_type = PTR_TO_STACK;
968 969
		if (type != PTR_TO_PACKET && type != expected_type)
			goto err_type;
970 971
	} else if (arg_type == ARG_CONST_STACK_SIZE ||
		   arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
972
		expected_type = CONST_IMM;
973 974
		if (type != expected_type)
			goto err_type;
975 976
	} else if (arg_type == ARG_CONST_MAP_PTR) {
		expected_type = CONST_PTR_TO_MAP;
977 978
		if (type != expected_type)
			goto err_type;
979 980
	} else if (arg_type == ARG_PTR_TO_CTX) {
		expected_type = PTR_TO_CTX;
981 982
		if (type != expected_type)
			goto err_type;
983 984
	} else if (arg_type == ARG_PTR_TO_STACK ||
		   arg_type == ARG_PTR_TO_RAW_STACK) {
985 986 987 988 989
		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.
		 */
990 991 992 993
		if (type == CONST_IMM && reg->imm == 0)
			/* final test in check_stack_boundary() */;
		else if (type != PTR_TO_PACKET && type != expected_type)
			goto err_type;
994
		meta->raw_mode = arg_type == ARG_PTR_TO_RAW_STACK;
995 996 997 998 999 1000 1001
	} 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 */
1002
		meta->map_ptr = reg->map_ptr;
1003 1004 1005 1006 1007
	} 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
		 */
1008
		if (!meta->map_ptr) {
1009 1010 1011 1012 1013 1014 1015 1016
			/* 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;
		}
1017 1018 1019 1020 1021 1022 1023
		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);
1024 1025 1026 1027
	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
		/* bpf_map_xxx(..., map_ptr, ..., value) call:
		 * check [value, value + map->value_size) validity
		 */
1028
		if (!meta->map_ptr) {
1029 1030 1031 1032
			/* kernel subsystem misconfigured verifier */
			verbose("invalid map_ptr to access map->value\n");
			return -EACCES;
		}
1033 1034 1035 1036 1037 1038 1039
		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);
1040 1041 1042
	} else if (arg_type == ARG_CONST_STACK_SIZE ||
		   arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
		bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO);
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052

		/* 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 */
			verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
			return -EACCES;
		}
1053 1054 1055 1056 1057
		if (regs[regno - 1].type == PTR_TO_PACKET)
			err = check_packet_access(env, regno - 1, 0, reg->imm);
		else
			err = check_stack_boundary(env, regno - 1, reg->imm,
						   zero_size_allowed, meta);
1058 1059 1060
	}

	return err;
1061 1062 1063 1064
err_type:
	verbose("R%d type=%s expected=%s\n", regno,
		reg_type_str[type], reg_type_str[expected_type]);
	return -EACCES;
1065 1066
}

1067 1068 1069 1070 1071
static int check_map_func_compatibility(struct bpf_map *map, int func_id)
{
	if (!map)
		return 0;

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086
	/* 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;
1087
	case BPF_MAP_TYPE_CGROUP_ARRAY:
1088
		if (func_id != BPF_FUNC_skb_under_cgroup &&
1089
		    func_id != BPF_FUNC_current_task_under_cgroup)
1090 1091
			goto error;
		break;
1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110
	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;
1111
	case BPF_FUNC_current_task_under_cgroup:
1112
	case BPF_FUNC_skb_under_cgroup:
1113 1114 1115
		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
			goto error;
		break;
1116 1117
	default:
		break;
1118 1119 1120
	}

	return 0;
1121 1122 1123 1124
error:
	verbose("cannot pass map_type %d into func %d\n",
		map->map_type, func_id);
	return -EINVAL;
1125 1126
}

1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144
static int check_raw_mode(const struct bpf_func_proto *fn)
{
	int count = 0;

	if (fn->arg1_type == ARG_PTR_TO_RAW_STACK)
		count++;
	if (fn->arg2_type == ARG_PTR_TO_RAW_STACK)
		count++;
	if (fn->arg3_type == ARG_PTR_TO_RAW_STACK)
		count++;
	if (fn->arg4_type == ARG_PTR_TO_RAW_STACK)
		count++;
	if (fn->arg5_type == ARG_PTR_TO_RAW_STACK)
		count++;

	return count > 1 ? -EINVAL : 0;
}

1145
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1146
{
1147 1148
	struct bpf_verifier_state *state = &env->cur_state;
	struct bpf_reg_state *regs = state->regs, *reg;
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167
	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;
	}
}

1168
static int check_call(struct bpf_verifier_env *env, int func_id)
1169
{
1170
	struct bpf_verifier_state *state = &env->cur_state;
1171
	const struct bpf_func_proto *fn = NULL;
1172 1173
	struct bpf_reg_state *regs = state->regs;
	struct bpf_reg_state *reg;
1174
	struct bpf_call_arg_meta meta;
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1175
	bool changes_data;
1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
	int i, err;

	/* find function prototype */
	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
		verbose("invalid func %d\n", func_id);
		return -EINVAL;
	}

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

	if (!fn) {
		verbose("unknown func %d\n", func_id);
		return -EINVAL;
	}

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
1193
	if (!env->prog->gpl_compatible && fn->gpl_only) {
1194 1195 1196 1197
		verbose("cannot call GPL only function from proprietary program\n");
		return -EINVAL;
	}

Alexei Starovoitov's avatar
Alexei Starovoitov committed
1198 1199
	changes_data = bpf_helper_changes_skb_data(fn->func);

1200
	memset(&meta, 0, sizeof(meta));
1201
	meta.pkt_access = fn->pkt_access;
1202

1203 1204 1205 1206 1207 1208 1209 1210 1211
	/* 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) {
		verbose("kernel subsystem misconfigured func %d\n", func_id);
		return err;
	}

1212
	/* check args */
1213
	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
1214 1215
	if (err)
		return err;
1216
	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
1217 1218
	if (err)
		return err;
1219
	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
1220 1221
	if (err)
		return err;
1222
	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
1223 1224
	if (err)
		return err;
1225
	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
1226 1227 1228
	if (err)
		return err;

1229 1230 1231 1232 1233 1234 1235 1236 1237
	/* 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;
	}

1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
	/* 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) {
		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
1252
		regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0;
1253 1254 1255 1256
		/* 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()
		 */
1257
		if (meta.map_ptr == NULL) {
1258 1259 1260
			verbose("kernel subsystem misconfigured verifier\n");
			return -EINVAL;
		}
1261
		regs[BPF_REG_0].map_ptr = meta.map_ptr;
1262
		regs[BPF_REG_0].id = ++env->id_gen;
1263 1264 1265 1266 1267
	} else {
		verbose("unknown return type %d of func %d\n",
			fn->ret_type, func_id);
		return -EINVAL;
	}
1268

1269
	err = check_map_func_compatibility(meta.map_ptr, func_id);
1270 1271
	if (err)
		return err;
1272

Alexei Starovoitov's avatar
Alexei Starovoitov committed
1273 1274 1275 1276 1277
	if (changes_data)
		clear_all_pkt_pointers(env);
	return 0;
}

1278 1279
static int check_packet_ptr_add(struct bpf_verifier_env *env,
				struct bpf_insn *insn)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1280
{
1281 1282 1283 1284
	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;
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306
	s32 imm;

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

add_imm:
		if (imm <= 0) {
			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 {
1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
		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)
			 */
		}

Alexei Starovoitov's avatar
Alexei Starovoitov committed
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
		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'
		 */
1343
		dst_reg->id = ++env->id_gen;
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1344 1345 1346 1347 1348 1349 1350 1351

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

1352
static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1353
{
1354 1355
	struct bpf_reg_state *regs = env->cur_state.regs;
	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1356 1357 1358 1359 1360 1361 1362 1363 1364
	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) {
1365
		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453

		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;
}

1454 1455
static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
				struct bpf_insn *insn)
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1456
{
1457 1458 1459
	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];
Alexei Starovoitov's avatar
Alexei Starovoitov committed
1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471
	u8 opcode = BPF_OP(insn->code);

	/* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn.
	 * Don't care about overflow or negative values, just add them
	 */
	if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_K)
		dst_reg->imm += insn->imm;
	else if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_X &&
		 src_reg->type == CONST_IMM)
		dst_reg->imm += src_reg->imm;
	else
		mark_reg_unknown_value(regs, insn->dst_reg);
1472 1473 1474
	return 0;
}

1475 1476 1477 1478
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;
1479 1480
	if (reg->min_value < BPF_REGISTER_MIN_RANGE ||
	    reg->min_value > BPF_REGISTER_MAX_RANGE)
1481 1482 1483 1484 1485 1486 1487
		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;
1488 1489
	s64 min_val = BPF_REGISTER_MIN_RANGE;
	u64 max_val = BPF_REGISTER_MAX_RANGE;
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
	bool min_set = false, max_set = false;
	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;
		min_set = max_set = true;
	}

	/* 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;
	}

1525 1526 1527 1528 1529 1530 1531 1532 1533
	/* 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;

1534 1535
	switch (opcode) {
	case BPF_ADD:
1536 1537 1538 1539
		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;
1540 1541
		break;
	case BPF_SUB:
1542 1543 1544 1545
		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;
1546 1547
		break;
	case BPF_MUL:
1548 1549 1550 1551
		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;
1552 1553
		break;
	case BPF_AND:
1554 1555 1556 1557 1558 1559 1560 1561