blob: 56674a7c377884b17d8296b6cf6f6e31a8158916 [file] [log] [blame]
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
* Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*
* 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 <uapi/linux/btf.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>
#include <linux/ctype.h>
#include "disasm.h"
static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#define BPF_PROG_TYPE(_id, _name) \
[_id] = & _name ## _verifier_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};
/* 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 64k 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 SCALAR_VALUE type, which
* means the register has some value, but it's not a valid pointer.
* (like pointer plus pointer becomes SCALAR_VALUE type)
*
* When verifier sees load or store instructions the type of base register
* can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are
* four 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.
*
* The following reference types represent a potential reference to a kernel
* resource which, after first being allocated, must be checked and freed by
* the BPF program:
* - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET
*
* When the verifier sees a helper call return a reference type, it allocates a
* pointer id for the reference and stores it in the current function state.
* Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into
* PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
* passes through a NULL-check conditional. For the branch wherein the state is
* changed to CONST_IMM, the verifier releases the reference.
*
* For each helper function that allocates a reference, such as
* bpf_sk_lookup_tcp(), there is a corresponding release function, such as
* bpf_sk_release(). When a reference type passes into the release function,
* the verifier also releases the reference. If any unchecked or unreleased
* reference remains at the end of the program, the verifier rejects it.
*/
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
/* verifer state is 'st'
* before processing instruction 'insn_idx'
* and after processing instruction 'prev_insn_idx'
*/
struct bpf_verifier_state st;
int insn_idx;
int prev_insn_idx;
struct bpf_verifier_stack_elem *next;
};
#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_COMPLEXITY_LIMIT_STATES 64
#define BPF_MAP_PTR_UNPRIV 1UL
#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
POISON_POINTER_DELTA))
#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
}
static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
{
return aux->map_state & BPF_MAP_PTR_UNPRIV;
}
static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
const struct bpf_map *map, bool unpriv)
{
BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
unpriv |= bpf_map_ptr_unpriv(aux);
aux->map_state = (unsigned long)map |
(unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
}
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
bool raw_mode;
bool pkt_access;
int regno;
int access_size;
s64 msize_smax_value;
u64 msize_umax_value;
int ptr_id;
};
static DEFINE_MUTEX(bpf_verifier_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
{
const struct bpf_line_info *linfo;
const struct bpf_prog *prog;
u32 i, nr_linfo;
prog = env->prog;
nr_linfo = prog->aux->nr_linfo;
if (!nr_linfo || insn_off >= prog->len)
return NULL;
linfo = prog->aux->linfo;
for (i = 1; i < nr_linfo; i++)
if (insn_off < linfo[i].insn_off)
break;
return &linfo[i - 1];
}
void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
va_list args)
{
unsigned int n;
n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
"verifier log line truncated - local buffer too short\n");
n = min(log->len_total - log->len_used - 1, n);
log->kbuf[n] = '\0';
if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
log->len_used += n;
else
log->ubuf = NULL;
}
/* log_level controls verbosity level of eBPF verifier.
* bpf_verifier_log_write() is used to dump the verification trace to the log,
* so the user can figure out what's wrong with the program
*/
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
const char *fmt, ...)
{
va_list args;
if (!bpf_verifier_log_needed(&env->log))
return;
va_start(args, fmt);
bpf_verifier_vlog(&env->log, fmt, args);
va_end(args);
}
EXPORT_SYMBOL_GPL(bpf_verifier_log_write);
__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
{
struct bpf_verifier_env *env = private_data;
va_list args;
if (!bpf_verifier_log_needed(&env->log))
return;
va_start(args, fmt);
bpf_verifier_vlog(&env->log, fmt, args);
va_end(args);
}
static const char *ltrim(const char *s)
{
while (isspace(*s))
s++;
return s;
}
__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
u32 insn_off,
const char *prefix_fmt, ...)
{
const struct bpf_line_info *linfo;
if (!bpf_verifier_log_needed(&env->log))
return;
linfo = find_linfo(env, insn_off);
if (!linfo || linfo == env->prev_linfo)
return;
if (prefix_fmt) {
va_list args;
va_start(args, prefix_fmt);
bpf_verifier_vlog(&env->log, prefix_fmt, args);
va_end(args);
}
verbose(env, "%s\n",
ltrim(btf_name_by_offset(env->prog->aux->btf,
linfo->line_off)));
env->prev_linfo = linfo;
}
static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_PACKET ||
type == PTR_TO_PACKET_META;
}
static bool reg_type_may_be_null(enum bpf_reg_type type)
{
return type == PTR_TO_MAP_VALUE_OR_NULL ||
type == PTR_TO_SOCKET_OR_NULL;
}
static bool type_is_refcounted(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET;
}
static bool type_is_refcounted_or_null(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL;
}
static bool reg_is_refcounted(const struct bpf_reg_state *reg)
{
return type_is_refcounted(reg->type);
}
static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg)
{
return type_is_refcounted_or_null(reg->type);
}
static bool arg_type_is_refcounted(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_SOCKET;
}
/* Determine whether the function releases some resources allocated by another
* function call. The first reference type argument will be assumed to be
* released by release_reference().
*/
static bool is_release_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_release;
}
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
[SCALAR_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",
[PTR_TO_STACK] = "fp",
[PTR_TO_PACKET] = "pkt",
[PTR_TO_PACKET_META] = "pkt_meta",
[PTR_TO_PACKET_END] = "pkt_end",
[PTR_TO_FLOW_KEYS] = "flow_keys",
[PTR_TO_SOCKET] = "sock",
[PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
};
static char slot_type_char[] = {
[STACK_INVALID] = '?',
[STACK_SPILL] = 'r',
[STACK_MISC] = 'm',
[STACK_ZERO] = '0',
};
static void print_liveness(struct bpf_verifier_env *env,
enum bpf_reg_liveness live)
{
if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
verbose(env, "_");
if (live & REG_LIVE_READ)
verbose(env, "r");
if (live & REG_LIVE_WRITTEN)
verbose(env, "w");
if (live & REG_LIVE_DONE)
verbose(env, "D");
}
static struct bpf_func_state *func(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg)
{
struct bpf_verifier_state *cur = env->cur_state;
return cur->frame[reg->frameno];
}
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state)
{
const struct bpf_reg_state *reg;
enum bpf_reg_type t;
int i;
if (state->frameno)
verbose(env, " frame%d:", state->frameno);
for (i = 0; i < MAX_BPF_REG; i++) {
reg = &state->regs[i];
t = reg->type;
if (t == NOT_INIT)
continue;
verbose(env, " R%d", i);
print_liveness(env, reg->live);
verbose(env, "=%s", reg_type_str[t]);
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
tnum_is_const(reg->var_off)) {
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
if (t == PTR_TO_STACK)
verbose(env, ",call_%d", func(env, reg)->callsite);
} else {
verbose(env, "(id=%d", reg->id);
if (t != SCALAR_VALUE)
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
else if (t == CONST_PTR_TO_MAP ||
t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
if (tnum_is_const(reg->var_off)) {
/* Typically an immediate SCALAR_VALUE, but
* could be a pointer whose offset is too big
* for reg->off
*/
verbose(env, ",imm=%llx", reg->var_off.value);
} else {
if (reg->smin_value != reg->umin_value &&
reg->smin_value != S64_MIN)
verbose(env, ",smin_value=%lld",
(long long)reg->smin_value);
if (reg->smax_value != reg->umax_value &&
reg->smax_value != S64_MAX)
verbose(env, ",smax_value=%lld",
(long long)reg->smax_value);
if (reg->umin_value != 0)
verbose(env, ",umin_value=%llu",
(unsigned long long)reg->umin_value);
if (reg->umax_value != U64_MAX)
verbose(env, ",umax_value=%llu",
(unsigned long long)reg->umax_value);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, ",var_off=%s", tn_buf);
}
}
verbose(env, ")");
}
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
char types_buf[BPF_REG_SIZE + 1];
bool valid = false;
int j;
for (j = 0; j < BPF_REG_SIZE; j++) {
if (state->stack[i].slot_type[j] != STACK_INVALID)
valid = true;
types_buf[j] = slot_type_char[
state->stack[i].slot_type[j]];
}
types_buf[BPF_REG_SIZE] = 0;
if (!valid)
continue;
verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
print_liveness(env, state->stack[i].spilled_ptr.live);
if (state->stack[i].slot_type[0] == STACK_SPILL)
verbose(env, "=%s",
reg_type_str[state->stack[i].spilled_ptr.type]);
else
verbose(env, "=%s", types_buf);
}
if (state->acquired_refs && state->refs[0].id) {
verbose(env, " refs=%d", state->refs[0].id);
for (i = 1; i < state->acquired_refs; i++)
if (state->refs[i].id)
verbose(env, ",%d", state->refs[i].id);
}
verbose(env, "\n");
}
#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \
static int copy_##NAME##_state(struct bpf_func_state *dst, \
const struct bpf_func_state *src) \
{ \
if (!src->FIELD) \
return 0; \
if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \
/* internal bug, make state invalid to reject the program */ \
memset(dst, 0, sizeof(*dst)); \
return -EFAULT; \
} \
memcpy(dst->FIELD, src->FIELD, \
sizeof(*src->FIELD) * (src->COUNT / SIZE)); \
return 0; \
}
/* copy_reference_state() */
COPY_STATE_FN(reference, acquired_refs, refs, 1)
/* copy_stack_state() */
COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
#undef COPY_STATE_FN
#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \
static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \
bool copy_old) \
{ \
u32 old_size = state->COUNT; \
struct bpf_##NAME##_state *new_##FIELD; \
int slot = size / SIZE; \
\
if (size <= old_size || !size) { \
if (copy_old) \
return 0; \
state->COUNT = slot * SIZE; \
if (!size && old_size) { \
kfree(state->FIELD); \
state->FIELD = NULL; \
} \
return 0; \
} \
new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \
GFP_KERNEL); \
if (!new_##FIELD) \
return -ENOMEM; \
if (copy_old) { \
if (state->FIELD) \
memcpy(new_##FIELD, state->FIELD, \
sizeof(*new_##FIELD) * (old_size / SIZE)); \
memset(new_##FIELD + old_size / SIZE, 0, \
sizeof(*new_##FIELD) * (size - old_size) / SIZE); \
} \
state->COUNT = slot * SIZE; \
kfree(state->FIELD); \
state->FIELD = new_##FIELD; \
return 0; \
}
/* realloc_reference_state() */
REALLOC_STATE_FN(reference, acquired_refs, refs, 1)
/* realloc_stack_state() */
REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
#undef REALLOC_STATE_FN
/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
* make it consume minimal amount of memory. check_stack_write() access from
* the program calls into realloc_func_state() to grow the stack size.
* Note there is a non-zero 'parent' pointer inside bpf_verifier_state
* which realloc_stack_state() copies over. It points to previous
* bpf_verifier_state which is never reallocated.
*/
static int realloc_func_state(struct bpf_func_state *state, int stack_size,
int refs_size, bool copy_old)
{
int err = realloc_reference_state(state, refs_size, copy_old);
if (err)
return err;
return realloc_stack_state(state, stack_size, copy_old);
}
/* Acquire a pointer id from the env and update the state->refs to include
* this new pointer reference.
* On success, returns a valid pointer id to associate with the register
* On failure, returns a negative errno.
*/
static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_func_state *state = cur_func(env);
int new_ofs = state->acquired_refs;
int id, err;
err = realloc_reference_state(state, state->acquired_refs + 1, true);
if (err)
return err;
id = ++env->id_gen;
state->refs[new_ofs].id = id;
state->refs[new_ofs].insn_idx = insn_idx;
return id;
}
/* release function corresponding to acquire_reference_state(). Idempotent. */
static int __release_reference_state(struct bpf_func_state *state, int ptr_id)
{
int i, last_idx;
if (!ptr_id)
return -EFAULT;
last_idx = state->acquired_refs - 1;
for (i = 0; i < state->acquired_refs; i++) {
if (state->refs[i].id == ptr_id) {
if (last_idx && i != last_idx)
memcpy(&state->refs[i], &state->refs[last_idx],
sizeof(*state->refs));
memset(&state->refs[last_idx], 0, sizeof(*state->refs));
state->acquired_refs--;
return 0;
}
}
return -EFAULT;
}
/* variation on the above for cases where we expect that there must be an
* outstanding reference for the specified ptr_id.
*/
static int release_reference_state(struct bpf_verifier_env *env, int ptr_id)
{
struct bpf_func_state *state = cur_func(env);
int err;
err = __release_reference_state(state, ptr_id);
if (WARN_ON_ONCE(err != 0))
verbose(env, "verifier internal error: can't release reference\n");
return err;
}
static int transfer_reference_state(struct bpf_func_state *dst,
struct bpf_func_state *src)
{
int err = realloc_reference_state(dst, src->acquired_refs, false);
if (err)
return err;
err = copy_reference_state(dst, src);
if (err)
return err;
return 0;
}
static void free_func_state(struct bpf_func_state *state)
{
if (!state)
return;
kfree(state->refs);
kfree(state->stack);
kfree(state);
}
static void free_verifier_state(struct bpf_verifier_state *state,
bool free_self)
{
int i;
for (i = 0; i <= state->curframe; i++) {
free_func_state(state->frame[i]);
state->frame[i] = NULL;
}
if (free_self)
kfree(state);
}
/* copy verifier state from src to dst growing dst stack space
* when necessary to accommodate larger src stack
*/
static int copy_func_state(struct bpf_func_state *dst,
const struct bpf_func_state *src)
{
int err;
err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs,
false);
if (err)
return err;
memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs));
err = copy_reference_state(dst, src);
if (err)
return err;
return copy_stack_state(dst, src);
}
static int copy_verifier_state(struct bpf_verifier_state *dst_state,
const struct bpf_verifier_state *src)
{
struct bpf_func_state *dst;
int i, err;
/* if dst has more stack frames then src frame, free them */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
}
dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (!dst)
return -ENOMEM;
dst_state->frame[i] = dst;
}
err = copy_func_state(dst, src->frame[i]);
if (err)
return err;
}
return 0;
}
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
int *insn_idx)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem, *head = env->head;
int err;
if (env->head == NULL)
return -ENOENT;
if (cur) {
err = copy_verifier_state(cur, &head->st);
if (err)
return err;
}
if (insn_idx)
*insn_idx = head->insn_idx;
if (prev_insn_idx)
*prev_insn_idx = head->prev_insn_idx;
elem = head->next;
free_verifier_state(&head->st, false);
kfree(head);
env->head = elem;
env->stack_size--;
return 0;
}
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx,
bool speculative)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem;
int err;
elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
if (!elem)
goto err;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
elem->next = env->head;
env->head = elem;
env->stack_size++;
err = copy_verifier_state(&elem->st, cur);
if (err)
goto err;
elem->st.speculative |= speculative;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
verbose(env, "BPF program is too complex\n");
goto err;
}
return &elem->st;
err:
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
/* pop all elements and return */
while (!pop_stack(env, NULL, NULL));
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
};
static void __mark_reg_not_init(struct bpf_reg_state *reg);
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
*/
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
/* Clear id, off, and union(map_ptr, range) */
memset(((u8 *)reg) + sizeof(reg->type), 0,
offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
reg->var_off = tnum_const(imm);
reg->smin_value = (s64)imm;
reg->smax_value = (s64)imm;
reg->umin_value = imm;
reg->umax_value = imm;
}
/* Mark the 'variable offset' part of a register as zero. This should be
* used only on registers holding a pointer type.
*/
static void __mark_reg_known_zero(struct bpf_reg_state *reg)
{
__mark_reg_known(reg, 0);
}
static void __mark_reg_const_zero(struct bpf_reg_state *reg)
{
__mark_reg_known(reg, 0);
reg->type = SCALAR_VALUE;
}
static void mark_reg_known_zero(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
}
static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
{
return type_is_pkt_pointer(reg->type);
}
static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
{
return reg_is_pkt_pointer(reg) ||
reg->type == PTR_TO_PACKET_END;
}
/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
enum bpf_reg_type which)
{
/* The register can already have a range from prior markings.
* This is fine as long as it hasn't been advanced from its
* origin.
*/
return reg->type == which &&
reg->id == 0 &&
reg->off == 0 &&
tnum_equals_const(reg->var_off, 0);
}
/* Attempts to improve min/max values based on var_off information */
static void __update_reg_bounds(struct bpf_reg_state *reg)
{
/* min signed is max(sign bit) | min(other bits) */
reg->smin_value = max_t(s64, reg->smin_value,
reg->var_off.value | (reg->var_off.mask & S64_MIN));
/* max signed is min(sign bit) | max(other bits) */
reg->smax_value = min_t(s64, reg->smax_value,
reg->var_off.value | (reg->var_off.mask & S64_MAX));
reg->umin_value = max(reg->umin_value, reg->var_off.value);
reg->umax_value = min(reg->umax_value,
reg->var_off.value | reg->var_off.mask);
}
/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
/* Learn sign from signed bounds.
* If we cannot cross the sign boundary, then signed and unsigned bounds
* are the same, so combine. This works even in the negative case, e.g.
* -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
if (reg->smin_value >= 0 || reg->smax_value < 0) {
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
return;
}
/* Learn sign from unsigned bounds. Signed bounds cross the sign
* boundary, so we must be careful.
*/
if ((s64)reg->umax_value >= 0) {
/* Positive. We can't learn anything from the smin, but smax
* is positive, hence safe.
*/
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
} else if ((s64)reg->umin_value < 0) {
/* Negative. We can't learn anything from the smax, but smin
* is negative, hence safe.
*/
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value;
}
}
/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
reg->var_off = tnum_intersect(reg->var_off,
tnum_range(reg->umin_value,
reg->umax_value));
}
/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
reg->smin_value = S64_MIN;
reg->smax_value = S64_MAX;
reg->umin_value = 0;
reg->umax_value = U64_MAX;
}
/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(struct bpf_reg_state *reg)
{
/*
* Clear type, id, off, and union(map_ptr, range) and
* padding between 'type' and union
*/
memset(reg, 0, offsetof(struct bpf_reg_state, var_off));
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
__mark_reg_unbounded(reg);
}
static void mark_reg_unknown(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_unknown(regs + regno);
}
static void __mark_reg_not_init(struct bpf_reg_state *reg)
{
__mark_reg_unknown(reg);
reg->type = NOT_INIT;
}
static void mark_reg_not_init(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_not_init(regs + regno);
}
static void init_reg_state(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
regs[i].parent = NULL;
}
/* frame pointer */
regs[BPF_REG_FP].type = PTR_TO_STACK;
mark_reg_known_zero(env, regs, BPF_REG_FP);
regs[BPF_REG_FP].frameno = state->frameno;
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, BPF_REG_1);
}
#define BPF_MAIN_FUNC (-1)
static void init_func_state(struct bpf_verifier_env *env,
struct bpf_func_state *state,
int callsite, int frameno, int subprogno)
{
state->callsite = callsite;
state->frameno = frameno;
state->subprogno = subprogno;
init_reg_state(env, state);
}
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 */
};
static int cmp_subprogs(const void *a, const void *b)
{
return ((struct bpf_subprog_info *)a)->start -
((struct bpf_subprog_info *)b)->start;
}
static int find_subprog(struct bpf_verifier_env *env, int off)
{
struct bpf_subprog_info *p;
p = bsearch(&off, env->subprog_info, env->subprog_cnt,
sizeof(env->subprog_info[0]), cmp_subprogs);
if (!p)
return -ENOENT;
return p - env->subprog_info;
}
static int add_subprog(struct bpf_verifier_env *env, int off)
{
int insn_cnt = env->prog->len;
int ret;
if (off >= insn_cnt || off < 0) {
verbose(env, "call to invalid destination\n");
return -EINVAL;
}
ret = find_subprog(env, off);
if (ret >= 0)
return 0;
if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
verbose(env, "too many subprograms\n");
return -E2BIG;
}
env->subprog_info[env->subprog_cnt++].start = off;
sort(env->subprog_info, env->subprog_cnt,
sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
return 0;
}
static int check_subprogs(struct bpf_verifier_env *env)
{
int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
/* Add entry function. */
ret = add_subprog(env, 0);
if (ret < 0)
return ret;
/* determine subprog starts. The end is one before the next starts */
for (i = 0; i < insn_cnt; i++) {
if (insn[i].code != (BPF_JMP | BPF_CALL))
continue;
if (insn[i].src_reg != BPF_PSEUDO_CALL)
continue;
if (!env->allow_ptr_leaks) {
verbose(env, "function calls to other bpf functions are allowed for root only\n");
return -EPERM;
}
ret = add_subprog(env, i + insn[i].imm + 1);
if (ret < 0)
return ret;
}
/* Add a fake 'exit' subprog which could simplify subprog iteration
* logic. 'subprog_cnt' should not be increased.
*/
subprog[env->subprog_cnt].start = insn_cnt;
if (env->log.level > 1)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, subprog[i].start);
/* now check that all jumps are within the same subprog */
subprog_start = subprog[cur_subprog].start;
subprog_end = subprog[cur_subprog + 1].start;
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
if (BPF_CLASS(code) != BPF_JMP)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
}
next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
* or unconditional jump back
*/
if (code != (BPF_JMP | BPF_EXIT) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
}
subprog_start = subprog_end;
cur_subprog++;
if (cur_subprog < env->subprog_cnt)
subprog_end = subprog[cur_subprog + 1].start;
}
}
return 0;
}
/* Parentage chain of this register (or stack slot) should take care of all
* issues like callee-saved registers, stack slot allocation time, etc.
*/
static int mark_reg_read(struct bpf_verifier_env *env,
const struct bpf_reg_state *state,
struct bpf_reg_state *parent)
{
bool writes = parent == state->parent; /* Observe write marks */
while (parent) {
/* if read wasn't screened by an earlier write ... */
if (writes && state->live & REG_LIVE_WRITTEN)
break;
if (parent->live & REG_LIVE_DONE) {
verbose(env, "verifier BUG type %s var_off %lld off %d\n",
reg_type_str[parent->type],
parent->var_off.value, parent->off);
return -EFAULT;
}
/* ... then we depend on parent's value */
parent->live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
}
return 0;
}
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
enum reg_arg_type t)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs;
if (regno >= MAX_BPF_REG) {
verbose(env, "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(env, "R%d !read_ok\n", regno);
return -EACCES;
}
/* We don't need to worry about FP liveness because it's read-only */
if (regno != BPF_REG_FP)
return mark_reg_read(env, &regs[regno],
regs[regno].parent);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose(env, "frame pointer is read only\n");
return -EACCES;
}
regs[regno].live |= REG_LIVE_WRITTEN;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
return 0;
}
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:
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
case PTR_TO_FLOW_KEYS:
case CONST_PTR_TO_MAP:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
return true;
default:
return false;
}
}
/* Does this register contain a constant zero? */
static bool register_is_null(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
static int check_stack_write(struct bpf_verifier_env *env,
struct bpf_func_state *state, /* func where register points to */
int off, int size, int value_regno, int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
enum bpf_reg_type type;
err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
state->acquired_refs, true);
if (err)
return err;
/* 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
*/
if (!env->allow_ptr_leaks &&
state->stack[spi].slot_type[0] == STACK_SPILL &&
size != BPF_REG_SIZE) {
verbose(env, "attempt to corrupt spilled pointer on stack\n");
return -EACCES;
}
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0 &&
is_spillable_regtype((type = cur->regs[value_regno].type))) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
if (state != cur && type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
/* save register state */
state->stack[spi].spilled_ptr = cur->regs[value_regno];
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++) {
if (state->stack[spi].slot_type[i] == STACK_MISC &&
!env->allow_ptr_leaks) {
int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
int soff = (-spi - 1) * BPF_REG_SIZE;
/* detected reuse of integer stack slot with a pointer
* which means either llvm is reusing stack slot or
* an attacker is trying to exploit CVE-2018-3639
* (speculative store bypass)
* Have to sanitize that slot with preemptive
* store of zero.
*/
if (*poff && *poff != soff) {
/* disallow programs where single insn stores
* into two different stack slots, since verifier
* cannot sanitize them
*/
verbose(env,
"insn %d cannot access two stack slots fp%d and fp%d",
insn_idx, *poff, soff);
return -EINVAL;
}
*poff = soff;
}
state->stack[spi].slot_type[i] = STACK_SPILL;
}
} else {
u8 type = STACK_MISC;
/* regular write of data into stack destroys any spilled ptr */
state->stack[spi].spilled_ptr.type = NOT_INIT;
/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
if (state->stack[spi].slot_type[0] == STACK_SPILL)
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack[spi].slot_type[i] = STACK_MISC;
/* only mark the slot as written if all 8 bytes were written
* otherwise read propagation may incorrectly stop too soon
* when stack slots are partially written.
* This heuristic means that read propagation will be
* conservative, since it will add reg_live_read marks
* to stack slots all the way to first state when programs
* writes+reads less than 8 bytes
*/
if (size == BPF_REG_SIZE)
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
/* when we zero initialize stack slots mark them as such */
if (value_regno >= 0 &&
register_is_null(&cur->regs[value_regno]))
type = STACK_ZERO;
/* Mark slots affected by this stack write. */
for (i = 0; i < size; i++)
state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
type;
}
return 0;
}
static int check_stack_read(struct bpf_verifier_env *env,
struct bpf_func_state *reg_state /* func where register points to */,
int off, int size, int value_regno)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
u8 *stype;
if (reg_state->allocated_stack <= slot) {
verbose(env, "invalid read from stack off %d+0 size %d\n",
off, size);
return -EACCES;
}
stype = reg_state->stack[spi].slot_type;
if (stype[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
for (i = 1; i < BPF_REG_SIZE; i++) {
if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
verbose(env, "corrupted spill memory\n");
return -EACCES;
}
}
if (value_regno >= 0) {
/* restore register state from stack */
state->regs[value_regno] = reg_state->stack[spi].spilled_ptr;
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
*/
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
mark_reg_read(env, &reg_state->stack[spi].spilled_ptr,
reg_state->stack[spi].spilled_ptr.parent);
return 0;
} else {
int zeros = 0;
for (i = 0; i < size; i++) {
if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
continue;
if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
zeros++;
continue;
}
verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
mark_reg_read(env, &reg_state->stack[spi].spilled_ptr,
reg_state->stack[spi].spilled_ptr.parent);
if (value_regno >= 0) {
if (zeros == size) {
/* any size read into register is zero extended,
* so the whole register == const_zero
*/
__mark_reg_const_zero(&state->regs[value_regno]);
} else {
/* have read misc data from the stack */
mark_reg_unknown(env, state->regs, value_regno);
}
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
return 0;
}
}
static int check_stack_access(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int off, int size)
{
/* Stack accesses must be at a fixed offset, so that we
* can determine what type of data were returned. See
* check_stack_read().
*/
if (!tnum_is_const(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "variable stack access var_off=%s off=%d size=%d",
tn_buf, off, size);
return -EACCES;
}
if (off >= 0 || off < -MAX_BPF_STACK) {
verbose(env, "invalid stack off=%d size=%d\n", off, size);
return -EACCES;
}
return 0;
}
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_map *map = regs[regno].map_ptr;
if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
off + size > map->value_size) {
verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
return 0;
}
/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, bool zero_size_allowed)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regno];
int err;
/* We may have adjusted the register to this map value, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
if (env->log.level)
print_verifier_state(env, state);
/* 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->smin_value < 0 &&
(reg->smin_value == S64_MIN ||
(off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) ||
reg->smin_value + off < 0)) {
verbose(env, "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->smin_value + off, size,
zero_size_allowed);
if (err) {
verbose(env, "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->umax_value + off could overflow, treat that as unbounded too.
*/
if (reg->umax_value >= BPF_MAX_VAR_OFF) {
verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
regno);
return -EACCES;
}
err = __check_map_access(env, regno, reg->umax_value + off, size,
zero_size_allowed);
if (err)
verbose(env, "R%d max value is outside of the array range\n",
regno);
return err;
}
#define MAX_PACKET_OFF 0xffff
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_access_type t)
{
switch (env->prog->type) {
/* Program types only with direct read access go here! */
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
/* fallthrough */
/* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_LWT_XMIT:
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
if (meta)
return meta->pkt_access;
env->seen_direct_write = true;
return true;
default:
return false;
}
}
static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
(u64)off + size > reg->range) {
verbose(env, "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);
return -EACCES;
}
return 0;
}
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
int err;
/* We may have added a variable offset to the packet pointer; but any
* reg->range we have comes after that. We are only checking the fixed
* offset.
*/
/* We don't allow negative numbers, because we aren't tracking enough
* detail to prove they're safe.
*/
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
err = __check_packet_access(env, regno, off, size, zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
/* __check_packet_access has made sure "off + size - 1" is within u16.
* reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
* otherwise find_good_pkt_pointers would have refused to set range info
* that __check_packet_access would have rejected this pkt access.
* Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
*/
env->prog->aux->max_pkt_offset =
max_t(u32, env->prog->aux->max_pkt_offset,
off + reg->umax_value + size - 1);
return err;
}
/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
};
if (env->ops->is_valid_access &&
env->ops->is_valid_access(off, size, t, env->prog, &info)) {
/* A non zero info.ctx_field_size indicates that this field is a
* candidate for later verifier transformation to load the whole
* field and then apply a mask when accessed with a narrower
* access than actual ctx access size. A zero info.ctx_field_size
* will only allow for whole field access and rejects any other
* type of narrower access.
*/
*reg_type = info.reg_type;
env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
/* 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;
return 0;
}
verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
return -EACCES;
}
static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
int size)
{
if (size < 0 || off < 0 ||
(u64)off + size > sizeof(struct bpf_flow_keys)) {
verbose(env, "invalid access to flow keys off=%d size=%d\n",
off, size);
return -EACCES;
}
return 0;
}
static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, enum bpf_access_type t)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
struct bpf_insn_access_aux info;
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
if (!bpf_sock_is_valid_access(off, size, t, &info)) {
verbose(env, "invalid bpf_sock access off=%d size=%d\n",
off, size);
return -EACCES;
}
return 0;
}
static bool __is_pointer_value(bool allow_ptr_leaks,
const struct bpf_reg_state *reg)
{
if (allow_ptr_leaks)
return false;
return reg->type != SCALAR_VALUE;
}
static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
{
return cur_regs(env) + regno;
}
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
}
static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return reg->type == PTR_TO_CTX ||
reg->type == PTR_TO_SOCKET;
}
static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return type_is_pkt_pointer(reg->type);
}
static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
/* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */
return reg->type == PTR_TO_FLOW_KEYS;
}
static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int off, int size, bool strict)
{
struct tnum reg_off;
int ip_align;
/* Byte size accesses are always allowed. */
if (!strict || size == 1)
return 0;
/* For platforms that do not have a Kconfig enabling
* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
* NET_IP_ALIGN is universally set to '2'. And on platforms
* that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
* to this code only in strict mode where we want to emulate
* the NET_IP_ALIGN==2 checking. Therefore use an
* unconditional IP align value of '2'.
*/
ip_align = 2;
reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off));
if (!tnum_is_aligned(reg_off, size)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env,
"misaligned packet access off %d+%s+%d+%d size %d\n",
ip_align, tn_buf, reg->off, off, size);
return -EACCES;
}
return 0;
}
static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
const char *pointer_desc,
int off, int size, bool strict)
{
struct tnum reg_off;
/* Byte size accesses are always allowed. */
if (!strict || size == 1)
return 0;
reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off));
if (!tnum_is_aligned(reg_off, size)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
pointer_desc, tn_buf, reg->off, off, size);
return -EACCES;
}
return 0;
}
static int check_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int off,
int size, bool strict_alignment_once)
{
bool strict = env->strict_alignment || strict_alignment_once;
const char *pointer_desc = "";
switch (reg->type) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
/* Special case, because of NET_IP_ALIGN. Given metadata sits
* right in front, treat it the very same way.
*/
return check_pkt_ptr_alignment(env, reg, off, size, strict);
case PTR_TO_FLOW_KEYS:
pointer_desc = "flow keys ";
break;
case PTR_TO_MAP_VALUE:
pointer_desc = "value ";
break;
case PTR_TO_CTX:
pointer_desc = "context ";
break;
case PTR_TO_STACK:
pointer_desc = "stack ";
/* The stack spill tracking logic in check_stack_write()
* and check_stack_read() relies on stack accesses being
* aligned.
*/
strict = true;
break;
case PTR_TO_SOCKET:
pointer_desc = "sock ";
break;
default:
break;
}
return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
strict);
}
static int update_stack_depth(struct bpf_verifier_env *env,
const struct bpf_func_state *func,
int off)
{
u16 stack = env->subprog_info[func->subprogno].stack_depth;
if (stack >= -off)
return 0;
/* update known max for given subprogram */
env->subprog_info[func->subprogno].stack_depth = -off;
return 0;
}
/* starting from main bpf function walk all instructions of the function
* and recursively walk all callees that given function can call.
* Ignore jump and exit insns.
* Since recursion is prevented by check_cfg() this algorithm
* only needs a local stack of MAX_CALL_FRAMES to remember callsites
*/
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
process_func:
/* round up to 32-bytes, since this is granularity
* of interpreter stack size
*/
depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
if (depth > MAX_BPF_STACK) {
verbose(env, "combined stack size of %d calls is %d. Too large\n",
frame + 1, depth);
return -EACCES;
}
continue_func:
subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
if (insn[i].code != (BPF_JMP | BPF_CALL))
continue;
if (insn[i].src_reg != BPF_PSEUDO_CALL)
continue;
/* remember insn and function to return to */
ret_insn[frame] = i + 1;
ret_prog[frame] = idx;
/* find the callee */
i = i + insn[i].imm + 1;
idx = find_subprog(env, i);
if (idx < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i);
return -EFAULT;
}
frame++;
if (frame >= MAX_CALL_FRAMES) {
WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
return -EFAULT;
}
goto process_func;
}
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
*/
if (frame == 0)
return 0;
depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
frame--;
i = ret_insn[frame];
idx = ret_prog[frame];
goto continue_func;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int idx)
{
int start = idx + insn->imm + 1, subprog;
subprog = find_subprog(env, start);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
start);
return -EFAULT;
}
return env->subprog_info[subprog].stack_depth;
}
#endif
static int check_ctx_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno)
{
/* Access to ctx or passing it to a helper is only allowed in
* its original, unmodified form.
*/
if (reg->off) {
verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
regno, reg->off);
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
return -EACCES;
}
return 0;
}
/* truncate register to smaller size (in bytes)
* must be called with size < BPF_REG_SIZE
*/
static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
{
u64 mask;
/* clear high bits in bit representation */
reg->var_off = tnum_cast(reg->var_off, size);
/* fix arithmetic bounds */
mask = ((u64)1 << (size * 8)) - 1;
if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
reg->umin_value &= mask;
reg->umax_value &= mask;
} else {
reg->umin_value = 0;
reg->umax_value = mask;
}
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value;
}
/* 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
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
int value_regno, bool strict_alignment_once)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
struct bpf_func_state *state;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
if (size < 0)
return size;
/* alignment checks will add in reg->off themselves */
err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
if (err)
return err;
/* for access checks, reg->off is just part of off */
off += reg->off;
if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
* PTR_TO_PACKET[_META,_END]. In the latter
* case, we know the offset is zero.
*/
if (reg_type == SCALAR_VALUE)
mark_reg_unknown(env, regs, value_regno);
else
mark_reg_known_zero(env, regs,
value_regno);
regs[value_regno].type = reg_type;
}
} else if (reg->type == PTR_TO_STACK) {
off += reg->var_off.value;
err = check_stack_access(env, reg, off, size);
if (err)
return err;
state = func(env, reg);
err = update_stack_depth(env, state, off);
if (err)
return err;
if (t == BPF_WRITE)
err = check_stack_write(env, state, off, size,
value_regno, insn_idx);
else
err = check_stack_read(env, state, off, size,
value_regno);
} else if (reg_is_pkt_pointer(reg)) {
if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
verbose(env, "cannot write into packet\n");
return -EACCES;
}
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into packet\n",
value_regno);
return -EACCES;
}
err = check_packet_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_FLOW_KEYS) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into flow keys\n",
value_regno);
return -EACCES;
}
err = check_flow_keys_access(env, off, size);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_SOCKET) {
if (t == BPF_WRITE) {
verbose(env, "cannot write into socket\n");
return -EACCES;
}
err = check_sock_access(env, regno, off, size, t);
if (!err && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
reg_type_str[reg->type]);
return -EACCES;
}
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
/* b/h/w load zero-extends, mark upper bits as known 0 */
coerce_reg_to_size(&regs[value_regno], size);
}
return err;
}
static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
int err;
if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
insn->imm != 0) {
verbose(env, "BPF_XADD uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
return -EACCES;
}
if (is_ctx_reg(env, insn->dst_reg) ||
is_pkt_reg(env, insn->dst_reg) ||
is_flow_key_reg(env, insn->dst_reg)) {
verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
insn->dst_reg,
reg_type_str[reg_state(env, insn->dst_reg)->type]);
return -EACCES;
}
/* check whether atomic_add can read the memory */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1, true);
if (err)
return err;
/* check whether atomic_add can write into the same memory */
return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}
/* 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.
* Unlike most pointer bounds-checking functions, this one doesn't take an
* 'off' argument, so it has to add in reg->off itself.
*/
static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *reg = reg_state(env, regno);
struct bpf_func_state *state = func(env, reg);
int off, i, slot, spi;
if (reg->type != PTR_TO_STACK) {
/* Allow zero-byte read from NULL, regardless of pointer type */
if (zero_size_allowed && access_size == 0 &&
register_is_null(reg))
return 0;
verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[reg->type],
reg_type_str[PTR_TO_STACK]);
return -EACCES;
}
/* Only allow fixed-offset stack reads */
if (!tnum_is_const(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "invalid variable stack read R%d var_off=%s\n",
regno, tn_buf);
return -EACCES;
}
off = reg->off + reg->var_off.value;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
regno, off, access_size);
return -EACCES;
}
if (meta && meta->raw_mode) {
meta->access_size = access_size;
meta->regno = regno;
return 0;
}
for (i = 0; i < access_size; i++) {
u8 *stype;
slot = -(off + i) - 1;
spi = slot / BPF_REG_SIZE;
if (state->allocated_stack <= slot)
goto err;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
if (*stype == STACK_MISC)
goto mark;
if (*stype == STACK_ZERO) {
/* helper can write anything into the stack */
*stype = STACK_MISC;
goto mark;
}
err:
verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
off, i, access_size);
return -EACCES;
mark:
/* reading any byte out of 8-byte 'spill_slot' will cause
* the whole slot to be marked as 'read'
*/
mark_reg_read(env, &state->stack[spi].spilled_ptr,
state->stack[spi].spilled_ptr.parent);
}
return update_stack_depth(env, state, off);
}
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 = cur_regs(env), *reg = &regs[regno];
switch (reg->type) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_VALUE:
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
default: /* scalar_value|ptr_to_stack or invalid ptr */
return check_stack_boundary(env, regno, access_size,
zero_size_allowed, meta);
}
}
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MEM ||
type == ARG_PTR_TO_MEM_OR_NULL ||
type == ARG_PTR_TO_UNINIT_MEM;
}
static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
return type == ARG_CONST_SIZE ||
type == ARG_CONST_SIZE_OR_ZERO;
}
static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
enum bpf_reg_type expected_type, type = reg->type;
int err = 0;
if (arg_type == ARG_DONTCARE)
return 0;
err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
if (arg_type == ARG_ANYTHING) {
if (is_pointer_value(env, regno)) {
verbose(env, "R%d leaks addr into helper function\n",
regno);
return -EACCES;
}
return 0;
}
if (type_is_pkt_pointer(type) &&
!may_access_direct_pkt_data(env, meta, BPF_READ)) {
verbose(env, "helper access to the packet is not allowed\n");
return -EACCES;
}
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE ||
arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
expected_type = PTR_TO_STACK;
if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
arg_type == ARG_CONST_SIZE_OR_ZERO) {
expected_type = SCALAR_VALUE;
if (type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_MAP_PTR) {
expected_type = CONST_PTR_TO_MAP;
if (type != expected_type)
goto err_type;
} else if (arg_type == ARG_PTR_TO_CTX) {
expected_type = PTR_TO_CTX;
if (type != expected_type)
goto err_type;
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
} else if (arg_type == ARG_PTR_TO_SOCKET) {
expected_type = PTR_TO_SOCKET;
if (type != expected_type)
goto err_type;
if (meta->ptr_id || !reg->id) {
verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n",
meta->ptr_id, reg->id);
return -EFAULT;
}
meta->ptr_id = reg->id;
} else if (arg_type_is_mem_ptr(arg_type)) {
expected_type = PTR_TO_STACK;
/* One exception here. In case function allows for NULL to be
* passed in as argument, it's a SCALAR_VALUE type. Final test
* happens during stack boundary checking.
*/
if (register_is_null(reg) &&
arg_type == ARG_PTR_TO_MEM_OR_NULL)
/* final test in check_stack_boundary() */;
else if (!type_is_pkt_pointer(type) &&
type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
} else {
verbose(env, "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 */
meta->map_ptr = reg->map_ptr;
} 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
*/
if (!meta->map_ptr) {
/* 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(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
err = check_helper_mem_access(env, regno,
meta->map_ptr->value_size, false,
meta);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
/* remember the mem_size which may be used later
* to refine return values.
*/
meta->msize_smax_value = reg->smax_value;
meta->msize_umax_value = reg->umax_value;
/* The register is SCALAR_VALUE; the access check
* happens using its boundaries.
*/
if (!tnum_is_const(reg->var_off))
/* 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->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
regno);
return -EACCES;
}
if (reg->umin_value == 0) {
err = check_helper_mem_access(env, regno - 1, 0,
zero_size_allowed,
meta);
if (err)
return err;
}
if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
verbose(env, "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->umax_value,
zero_size_allowed, meta);
}
return err;
err_type:
verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[type], reg_type_str[expected_type]);
return -EACCES;
}
static int check_map_func_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map, int func_id)
{
if (!map)
return 0;
/* 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 &&
func_id != BPF_FUNC_perf_event_read_value)
goto error;
break;
case BPF_MAP_TYPE_STACK_TRACE:
if (func_id != BPF_FUNC_get_stackid)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
if (func_id != BPF_FUNC_skb_under_cgroup &&
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
if (func_id != BPF_FUNC_get_local_storage)
goto error;
break;
/* devmap returns a pointer to a live net_device ifindex that we cannot
* allow to be modified from bpf side. So do not allow lookup elements
* for now.
*/
case BPF_MAP_TYPE_DEVMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
/* Restrict bpf side of cpumap and xskmap, open when use-cases
* appear.
*/
case BPF_MAP_TYPE_CPUMAP:
case BPF_MAP_TYPE_XSKMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
case BPF_MAP_TYPE_SOCKMAP:
if (func_id != BPF_FUNC_sk_redirect_map &&
func_id != BPF_FUNC_sock_map_update &&
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_msg_redirect_map)
goto error;
break;
case BPF_MAP_TYPE_SOCKHASH:
if (func_id != BPF_FUNC_sk_redirect_hash &&
func_id != BPF_FUNC_sock_hash_update &&
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_msg_redirect_hash)
goto error;
break;
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
if (func_id != BPF_FUNC_sk_select_reuseport)
goto error;
break;
case BPF_MAP_TYPE_QUEUE:
case BPF_MAP_TYPE_STACK:
if (func_id != BPF_FUNC_map_peek_elem &&
func_id != BPF_FUNC_map_pop_elem &&
func_id != BPF_FUNC_map_push_elem)
goto error;
break;
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;
if (env->subprog_cnt > 1) {
verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
return -EINVAL;
}
break;
case BPF_FUNC_perf_event_read:
case BPF_FUNC_perf_event_output:
case BPF_FUNC_perf_event_read_value:
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;
case BPF_FUNC_current_task_under_cgroup:
case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
case BPF_FUNC_redirect_map:
if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
map->map_type != BPF_MAP_TYPE_CPUMAP &&
map->map_type != BPF_MAP_TYPE_XSKMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
case BPF_FUNC_msg_redirect_map:
case BPF_FUNC_sock_map_update:
if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_hash:
case BPF_FUNC_msg_redirect_hash:
case BPF_FUNC_sock_hash_update:
if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
case BPF_FUNC_get_local_storage:
if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
goto error;
break;
case BPF_FUNC_sk_select_reuseport:
if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
goto error;
break;
case BPF_FUNC_map_peek_elem:
case BPF_FUNC_map_pop_elem:
case BPF_FUNC_map_push_elem:
if (map->map_type != BPF_MAP_TYPE_QUEUE &&
map->map_type != BPF_MAP_TYPE_STACK)
goto error;
break;
default:
break;
}
return 0;
error:
verbose(env, "cannot pass map_type %d into func %s#%d\n",
map->map_type, func_id_name(func_id), func_id);
return -EINVAL;
}
static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
{
int count = 0;
if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
count++;
/* We only support one arg being in raw mode at the moment,
* which is sufficient for the helper functions we have
* right now.
*/
return count <= 1;
}
static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
enum bpf_arg_type arg_next)
{
return (arg_type_is_mem_ptr(arg_curr) &&
!arg_type_is_mem_size(arg_next)) ||
(!arg_type_is_mem_ptr(arg_curr) &&
arg_type_is_mem_size(arg_next));
}
static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
{
/* bpf_xxx(..., buf, len) call will access 'len'
* bytes from memory 'buf'. Both arg types need
* to be paired, so make sure there's no buggy
* helper function specification.
*/
if (arg_type_is_mem_size(fn->arg1_type) ||
arg_type_is_mem_ptr(fn->arg5_type) ||
check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
return false;
return true;
}
static bool check_refcount_ok(const struct bpf_func_proto *fn)
{
int count = 0;
if (arg_type_is_refcounted(fn->arg1_type))
count++;
if (arg_type_is_refcounted(fn->arg2_type))
count++;
if (arg_type_is_refcounted(fn->arg3_type))
count++;
if (arg_type_is_refcounted(fn->arg4_type))
count++;
if (arg_type_is_refcounted(fn->arg5_type))
count++;
/* We only support one arg being unreferenced at the moment,
* which is sufficient for the helper functions we have right now.
*/
return count <= 1;
}
static int check_func_proto(const struct bpf_func_proto *fn)
{
return check_raw_mode_ok(fn) &&
check_arg_pair_ok(fn) &&
check_refcount_ok(fn) ? 0 : -EINVAL;
}
/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
* are now invalid, so turn them into unknown SCALAR_VALUE.
*/
static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (reg_is_pkt_pointer_any(&regs[i]))
mark_reg_unknown(env, regs, i);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
if (reg_is_pkt_pointer_any(reg))
__mark_reg_unknown(reg);
}
}
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *vstate = env->cur_state;
int i;
for (i = 0; i <= vstate->curframe; i++)
__clear_all_pkt_pointers(env, vstate->frame[i]);
}
static void release_reg_references(struct bpf_verifier_env *env,
struct bpf_func_state *state, int id)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].id == id)
mark_reg_unknown(env, regs, i);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
if (reg_is_refcounted(reg) && reg->id == id)
__mark_reg_unknown(reg);
}
}
/* The pointer with the specified id has released its reference to kernel
* resources. Identify all copies of the same pointer and clear the reference.
*/
static int release_reference(struct bpf_verifier_env *env,
struct bpf_call_arg_meta *meta)
{
struct bpf_verifier_state *vstate = env->cur_state;
int i;
for (i = 0; i <= vstate->curframe; i++)
release_reg_references(env, vstate->frame[i], meta->ptr_id);
return release_reference_state(env, meta->ptr_id);
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
int i, err, subprog, target_insn;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
state->curframe + 2);
return -E2BIG;
}
target_insn = *insn_idx + insn->imm;