// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
* Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*/
#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_JMP_SEQ 8192
#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;
u64 msize_max_value;
int ref_obj_id;
int func_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 type_is_sk_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET ||
type == PTR_TO_SOCK_COMMON ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_XDP_SOCK;
}
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 ||
type == PTR_TO_SOCK_COMMON_OR_NULL ||
type == PTR_TO_TCP_SOCK_OR_NULL;
}
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return reg->type == PTR_TO_MAP_VALUE &&
map_value_has_spin_lock(reg->map_ptr);
}
static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET ||
type == PTR_TO_SOCKET_OR_NULL ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_TCP_SOCK_OR_NULL;
}
static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_SOCK_COMMON;
}
/* 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;
}
static bool is_acquire_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_lookup_tcp ||
func_id == BPF_FUNC_sk_lookup_udp ||
func_id == BPF_FUNC_skc_lookup_tcp;
}
static bool is_ptr_cast_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_tcp_sock ||
func_id == BPF_FUNC_sk_fullsock;
}
/* 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",
[PTR_TO_SOCK_COMMON] = "sock_common",
[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
[PTR_TO_TCP_SOCK] = "tcp_sock",
[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
[PTR_TO_TP_BUFFER] = "tp_buffer",
[PTR_TO_XDP_SOCK] = "xdp_sock",
};
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 && reg->precise)
verbose(env, "P");
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);
} else {
verbose(env, "(id=%d", reg->id);
if (reg_type_may_be_refcounted_or_null(t))
verbose(env, ",ref_obj_id=%d", reg->ref_obj_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) {
reg = &state->stack[i].spilled_ptr;
t = reg->type;
verbose(env, "=%s", reg_type_str[t]);
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
verbose(env, "%lld", reg->var_off.value + reg->off);
} 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;
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 -EINVAL;
}
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 clear_jmp_history(struct bpf_verifier_state *state)
{
kfree(state->jmp_history);
state->jmp_history = NULL;
state->jmp_history_cnt = 0;
}
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;
}
clear_jmp_history(state);
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;
u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt;
int i, err;
if (dst_state->jmp_history_cnt < src->jmp_history_cnt) {
kfree(dst_state->jmp_history);
dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER);
if (!dst_state->jmp_history)
return -ENOMEM;
}
memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz);
dst_state->jmp_history_cnt = src->jmp_history_cnt;
/* 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;
dst_state->active_spin_lock = src->active_spin_lock;
dst_state->branches = src->branches;
dst_state->parent = src->parent;
dst_state->first_insn_idx = src->first_insn_idx;
dst_state->last_insn_idx = src->last_insn_idx;
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 void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
while (st) {
u32 br = --st->branches;
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
WARN_ONCE((int)br < 0,
"BUG update_branch_counts:branches_to_explore=%d\n",
br);
if (br)
break;
st = st->parent;
}
}
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_JMP_SEQ) {
verbose(env, "The sequence of %d jumps is too complex.\n",
env->stack_size);
goto err;
}
if (elem->st.parent) {
++elem->st.parent->branches;
/* WARN_ON(branches > 2) technically makes sense here,
* but
* 1. speculative states will bump 'branches' for non-branch
* instructions
* 2. is_state_visited() heuristics may decide not to create
* a new state for a sequence of branches and all such current
* and cloned states will be pointing to a single parent state
* which might have large 'branches' count.
*/
}
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(const struct bpf_verifier_env *env,
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(env, 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(const struct bpf_verifier_env *env,
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;
reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
true : false;
__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(env, regs + regno);
return;
}
__mark_reg_unknown(env, regs + regno);
}
static void __mark_reg_not_init(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
__mark_reg_unknown(env, 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(env, regs + regno);
return;
}
__mark_reg_not_init(env, regs + regno);
}
#define DEF_NOT_SUBREG (0)
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;
regs[i].subreg_def = DEF_NOT_SUBREG;
}
/* 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 & BPF_LOG_LEVEL2)
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 && BPF_CLASS(code) != BPF_JMP32)
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, u8 flag)
{
bool writes = parent == state->parent; /* Observe write marks */
int cnt = 0;
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;
}
/* The first condition is more likely to be true than the
* second, checked it first.
*/
if ((parent->live & REG_LIVE_READ) == flag ||
parent->live & REG_LIVE_READ64)
/* The parentage chain never changes and
* this parent was already marked as LIVE_READ.
* There is no need to keep walking the chain again and
* keep re-marking all parents as LIVE_READ.
* This case happens when the same register is read
* multiple times without writes into it in-between.
* Also, if parent has the stronger REG_LIVE_READ64 set,
* then no need to set the weak REG_LIVE_READ32.
*/
break;
/* ... then we depend on parent's value */
parent->live |= flag;
/* REG_LIVE_READ64 overrides REG_LIVE_READ32. */
if (flag == REG_LIVE_READ64)
parent->live &= ~REG_LIVE_READ32;
state = parent;
parent = state->parent;
writes = true;
cnt++;
}
if (env->longest_mark_read_walk < cnt)
env->longest_mark_read_walk = cnt;
return 0;
}
/* This function is supposed to be used by the following 32-bit optimization
* code only. It returns TRUE if the source or destination register operates
* on 64-bit, otherwise return FALSE.
*/
static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t)
{
u8 code, class, op;
code = insn->code;
class = BPF_CLASS(code);
op = BPF_OP(code);
if (class == BPF_JMP) {
/* BPF_EXIT for "main" will reach here. Return TRUE
* conservatively.
*/
if (op == BPF_EXIT)
return true;
if (op == BPF_CALL) {
/* BPF to BPF call will reach here because of marking
* caller saved clobber with DST_OP_NO_MARK for which we
* don't care the register def because they are anyway
* marked as NOT_INIT already.
*/
if (insn->src_reg == BPF_PSEUDO_CALL)
return false;
/* Helper call will reach here because of arg type
* check, conservatively return TRUE.
*/
if (t == SRC_OP)
return true;
return false;
}
}
if (class == BPF_ALU64 || class == BPF_JMP ||
/* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
if (class == BPF_ALU || class == BPF_JMP32)
return false;
if (class == BPF_LDX) {
if (t != SRC_OP)
return BPF_SIZE(code) == BPF_DW;
/* LDX source must be ptr. */
return true;
}
if (class == BPF_STX) {
if (reg->type != SCALAR_VALUE)
return true;
return BPF_SIZE(code) == BPF_DW;
}
if (class == BPF_LD) {
u8 mode = BPF_MODE(code);
/* LD_IMM64 */
if (mode == BPF_IMM)
return true;
/* Both LD_IND and LD_ABS return 32-bit data. */
if (t != SRC_OP)
return false;
/* Implicit ctx ptr. */
if (regno == BPF_REG_6)
return true;
/* Explicit source could be any width. */
return true;
}
if (class == BPF_ST)
/* The only source register for BPF_ST is a ptr. */
return true;
/* Conservatively return true at default. */
return true;
}
/* Return TRUE if INSN doesn't have explicit value define. */
static bool insn_no_def(struct bpf_insn *insn)
{
u8 class = BPF_CLASS(insn->code);
return (class == BPF_JMP || class == BPF_JMP32 ||
class == BPF_STX || class == BPF_ST);
}
/* Return TRUE if INSN has defined any 32-bit value explicitly. */
static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *<