blob: 7d530ce8719d8d06efc9498f70e13f35c700ccd9 [file] [log] [blame]
// 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, prog_ctx_type, kern_ctx_type) \
[_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_KEY_POISON (1ULL << 63)
#define BPF_MAP_KEY_SEEN (1ULL << 62)
#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_ptr_state) == BPF_MAP_PTR_POISON;
}
static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
{
return aux->map_ptr_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_ptr_state = (unsigned long)map |
(unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
}
static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux)
{
return aux->map_key_state & BPF_MAP_KEY_POISON;
}
static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux)
{
return !(aux->map_key_state & BPF_MAP_KEY_SEEN);
}
static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux)
{
return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON);
}
static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
{
bool poisoned = bpf_map_key_poisoned(aux);
aux->map_key_state = state | BPF_MAP_KEY_SEEN |
(poisoned ? BPF_MAP_KEY_POISON : 0ULL);
}
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 ref_obj_id;
int func_id;
u32 btf_id;
};
struct btf *btf_vmlinux;
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 (log->level == BPF_LOG_KERNEL) {
pr_err("BPF:%s\n", log->kbuf);
return;
}
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);
}
__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
const char *fmt, ...)
{
va_list args;
if (!bpf_verifier_log_needed(log))
return;
va_start(args, fmt);
bpf_verifier_vlog(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",
[PTR_TO_BTF_ID] = "ptr_",
};
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];
}
const char *kernel_type_name(u32 id)
{
return btf_name_by_offset(btf_vmlinux,
btf_type_by_id(btf_vmlinux, id)->name_off);
}
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 {
if (t == PTR_TO_BTF_ID)
verbose(env, "%s", kernel_type_name(reg->btf_id));
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));
}
static void __reg_bound_offset32(struct bpf_reg_state *reg)
{
u64 mask = 0xffffFFFF;
struct tnum range = tnum_range(reg->umin_value & mask,
reg->umax_value & mask);
struct tnum lo32 = tnum_cast(reg->var_off, 4);
struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32);
reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range));
}
/* 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 *insn)
{
if (insn_no_def(insn))
return false;
return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP);
}
static void mark_insn_zext(struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
s32 def_idx = reg->subreg_def;
if (def_idx == DEF_NOT_SUBREG)
return;
env->insn_aux_data[def_idx - 1].zext_dst = true;
/* The dst will be zero extended, so won't be sub-register anymore. */
reg->subreg_def = DEF_NOT_SUBREG;
}
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_insn *insn = env->prog->insnsi + env->insn_idx;
struct bpf_reg_state *reg, *regs = state->regs;
bool rw64;
if (regno >= MAX_BPF_REG) {
verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
reg = &regs[regno];
rw64 = is_reg64(env, insn, regno, reg, t);
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
if (reg->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 0;
if (rw64)
mark_insn_zext(env, reg);
return mark_reg_read(env, reg, reg->parent,
rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32);
} 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;
}
reg->live |= REG_LIVE_WRITTEN;
reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
return 0;
}
/* for any branch, call, exit record the history of jmps in the given state */
static int push_jmp_history(struct bpf_verifier_env *env,
struct bpf_verifier_state *cur)
{
u32 cnt = cur->jmp_history_cnt;
struct bpf_idx_pair *p;
cnt++;
p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER);
if (!p)
return -ENOMEM;
p[cnt - 1].idx = env->insn_idx;
p[cnt - 1].prev_idx = env->prev_insn_idx;
cur->jmp_history = p;
cur->jmp_history_cnt = cnt;
return 0;
}
/* Backtrack one insn at a time. If idx is not at the top of recorded
* history then previous instruction came from straight line execution.
*/
static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
u32 *history)
{
u32 cnt = *history;
if (cnt && st->jmp_history[cnt - 1].idx == i) {
i = st->jmp_history[cnt - 1].prev_idx;
(*history)--;
} else {
i--;
}
return i;
}
/* For given verifier state backtrack_insn() is called from the last insn to
* the first insn. Its purpose is to compute a bitmask of registers and
* stack slots that needs precision in the parent verifier state.
*/
static int backtrack_insn(struct bpf_verifier_env *env, int idx,
u32 *reg_mask, u64 *stack_mask)
{
const struct bpf_insn_cbs cbs = {
.cb_print = verbose,
.private_data = env,
};
struct bpf_insn *insn = env->prog->insnsi + idx;
u8 class = BPF_CLASS(insn->code);
u8 opcode = BPF_OP(insn->code);
u8 mode = BPF_MODE(insn->code);
u32 dreg = 1u << insn->dst_reg;
u32 sreg = 1u << insn->src_reg;
u32 spi;
if (insn->code == 0)
return 0;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
verbose(env, "%d: ", idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
if (class == BPF_ALU || class == BPF_ALU64) {
if (!(*reg_mask & dreg))
return 0;
if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
/* dreg = sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
*reg_mask &= ~dreg;
*reg_mask |= sreg;
} else {
/* dreg = K
* dreg needs precision after this insn.
* Corresponding register is already marked
* as precise=true in this verifier state.
* No further markings in parent are necessary
*/
*reg_mask &= ~dreg;
}
} else {
if (BPF_SRC(insn->code) == BPF_X) {
/* dreg += sreg
* both dreg and sreg need precision
* before this insn
*/
*reg_mask |= sreg;
} /* else dreg += K
* dreg still needs precision before this insn
*/
}
} else if (class == BPF_LDX) {
if (!(*reg_mask & dreg))
return 0;
*reg_mask &= ~dreg;
/* scalars can only be spilled into stack w/o losing precision.
* Load from any other memory can be zero extended.
* The desire to keep that precision is already indicated
* by 'precise' mark in corresponding register of this state.
* No further tracking necessary.
*/
if (insn->src_reg != BPF_REG_FP)
return 0;
if (BPF_SIZE(insn->code) != BPF_DW)
return 0;
/* dreg = *(u64 *)[fp - off] was a fill from the stack.
* that [fp - off] slot contains scalar that needs to be
* tracked with precision
*/
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
*stack_mask |= 1ull << spi;
} else if (class == BPF_STX || class == BPF_ST) {
if (*reg_mask & dreg)
/* stx & st shouldn't be using _scalar_ dst_reg
* to access memory. It means backtracking
* encountered a case of pointer subtraction.
*/
return -ENOTSUPP;
/* scalars can only be spilled into stack */
if (insn->dst_reg != BPF_REG_FP)
return 0;
if (BPF_SIZE(insn->code) != BPF_DW)
return 0;
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
if (!(*stack_mask & (1ull << spi)))
return 0;
*stack_mask &= ~(1ull << spi);
if (class == BPF_STX)
*reg_mask |= sreg;
} else if (class == BPF_JMP || class == BPF_JMP32) {
if (opcode == BPF_CALL) {
if (insn->src_reg == BPF_PSEUDO_CALL)
return -ENOTSUPP;
/* regular helper call sets R0 */
*reg_mask &= ~1;
if (*reg_mask & 0x3f) {
/* if backtracing was looking for registers R1-R5
* they should have been found already.
*/
verbose(env, "BUG regs %x\n", *reg_mask);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
} else if (opcode == BPF_EXIT) {
return -ENOTSUPP;
}
} else if (class == BPF_LD) {
if (!(*reg_mask & dreg))
return 0;
*reg_mask &= ~dreg;
/* It's ld_imm64 or ld_abs or ld_ind.
* For ld_imm64 no further tracking of precision
* into parent is necessary
*/
if (mode == BPF_IND || mode == BPF_ABS)
/* to be analyzed */
return -ENOTSUPP;
}
return 0;
}
/* the scalar precision tracking algorithm:
* . at the start all registers have precise=false.
* . scalar ranges are tracked as normal through alu and jmp insns.
* . once precise value of the scalar register is used in:
* . ptr + scalar alu
* . if (scalar cond K|scalar)
* . helper_call(.., scalar, ...) where ARG_CONST is expected
* backtrack through the verifier states and mark all registers and
* stack slots with spilled constants that these scalar regisers
* should be precise.
* . during state pruning two registers (or spilled stack slots)
* are equivalent if both are not precise.
*
* Note the verifier cannot simply walk register parentage chain,
* since many different registers and stack slots could have been
* used to compute single precise scalar.
*
* The approach of starting with precise=true for all registers and then
* backtrack to mark a register as not precise when the verifier detects
* that program doesn't care about specific value (e.g., when helper
* takes register as ARG_ANYTHING parameter) is not safe.
*
* It's ok to walk single parentage chain of the verifier states.
* It's possible that this backtracking will go all the way till 1st insn.
* All other branches will be explored for needing precision later.
*
* The backtracking needs to deal with cases like:
* R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0)
* r9 -= r8
* r5 = r9
* if r5 > 0x79f goto pc+7
* R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff))
* r5 += 1
* ...
* call bpf_perf_event_output#25
* where .arg5_type = ARG_CONST_SIZE_OR_ZERO
*
* and this case:
* r6 = 1
* call foo // uses callee's r6 inside to compute r0
* r0 += r6
* if r0 == 0 goto
*
* to track above reg_mask/stack_mask needs to be independent for each frame.
*
* Also if parent's curframe > frame where backtracking started,
* the verifier need to mark registers in both frames, otherwise callees
* may incorrectly prune callers. This is similar to
* commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences")
*
* For now backtracking falls back into conservative marking.
*/
static void mark_all_scalars_precise(struct bpf_verifier_env *env,
struct bpf_verifier_state *st)
{
struct bpf_func_state *func;
struct bpf_reg_state *reg;
int i, j;
/* big hammer: mark all scalars precise in this path.
* pop_stack may still get !precise scalars.
*/
for (; st; st = st->parent)
for (i = 0; i <= st->curframe; i++) {
func = st->frame[i];
for (j = 0; j < BPF_REG_FP; j++) {
reg = &func->regs[j];
if (reg->type != SCALAR_VALUE)
continue;
reg->precise = true;
}
for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
if (func->stack[j].slot_type[0] != STACK_SPILL)
continue;
reg = &func->stack[j].spilled_ptr;
if (reg->type != SCALAR_VALUE)
continue;
reg->precise = true;
}
}
}
static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
int spi)
{
struct bpf_verifier_state *st = env->cur_state;
int first_idx = st->first_insn_idx;
int last_idx = env->insn_idx;
struct bpf_func_state *func;
struct bpf_reg_state *reg;
u32 reg_mask = regno >= 0 ? 1u << regno : 0;
u64 stack_mask = spi >= 0 ? 1ull << spi : 0;
bool skip_first = true;
bool new_marks = false;
int i, err;
if (!env->allow_ptr_leaks)
/* backtracking is root only for now */
return 0;
func = st->frame[st->curframe];
if (regno >= 0) {
reg = &func->regs[regno];
if (reg->type != SCALAR_VALUE) {
WARN_ONCE(1, "backtracing misuse");
return -EFAULT;
}
if (!reg->precise)
new_marks = true;
else
reg_mask = 0;
reg->precise = true;
}
while (spi >= 0) {
if (func->stack[spi].slot_type[0] != STACK_SPILL) {
stack_mask = 0;
break;
}
reg = &func->stack[spi].spilled_ptr;
if (reg->type != SCALAR_VALUE) {
stack_mask = 0;
break;
}
if (!reg->precise)
new_marks = true;
else
stack_mask = 0;
reg->precise = true;
break;
}
if (!new_marks)
return 0;
if (!reg_mask && !stack_mask)
return 0;
for (;;) {
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
if (env->log.level & BPF_LOG_LEVEL)
verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
for (i = last_idx;;) {
if (skip_first) {
err = 0;
skip_first = false;
} else {
err = backtrack_insn(env, i, &reg_mask, &stack_mask);
}
if (err == -ENOTSUPP) {
mark_all_scalars_precise(env, st);
return 0;
} else if (err) {
return err;
}
if (!reg_mask && !stack_mask)
/* Found assignment(s) into tracked register in this state.
* Since this state is already marked, just return.
* Nothing to be tracked further in the parent state.
*/
return 0;
if (i == first_idx)
break;
i = get_prev_insn_idx(st, i, &history);
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
* and there are still reg_mask or stack_mask
* to backtrack.
* It means the backtracking missed the spot where
* particular register was initialized with a constant.
*/
verbose(env, "BUG backtracking idx %d\n", i);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
}
st = st->parent;
if (!st)
break;
new_marks = false;
func = st->frame[st->curframe];
bitmap_from_u64(mask, reg_mask);
for_each_set_bit(i, mask, 32) {
reg = &func->regs[i];
if (reg->type != SCALAR_VALUE) {
reg_mask &= ~(1u << i);
continue;
}
if (!reg->precise)
new_marks = true;
reg->precise = true;
}
bitmap_from_u64(mask, stack_mask);
for_each_set_bit(i, mask, 64) {
if (i >= func->allocated_stack / BPF_REG_SIZE) {
/* the sequence of instructions:
* 2: (bf) r3 = r10
* 3: (7b) *(u64 *)(r3 -8) = r0
* 4: (79) r4 = *(u64 *)(r10 -8)
* doesn't contain jmps. It's backtracked
* as a single block.
* During backtracking insn 3 is not recognized as
* stack access, so at the end of backtracking
* stack slot fp-8 is still marked in stack_mask.
* However the parent state may not have accessed
* fp-8 and it's "unallocated" stack space.
* In such case fallback to conservative.
*/
mark_all_scalars_precise(env, st);
return 0;
}
if (func->stack[i].slot_type[0] != STACK_SPILL) {
stack_mask &= ~(1ull << i);
continue;
}
reg = &func->stack[i].spilled_ptr;
if (reg->type != SCALAR_VALUE) {
stack_mask &= ~(1ull << i);
continue;
}
if (!reg->precise)
new_marks = true;
reg->precise = true;
}
if (env->log.level & BPF_LOG_LEVEL) {
print_verifier_state(env, func);
verbose(env, "parent %s regs=%x stack=%llx marks\n",
new_marks ? "didn't have" : "already had",
reg_mask, stack_mask);
}
if (!reg_mask && !stack_mask)
break;
if (!new_marks)
break;
last_idx = st->last_insn_idx;
first_idx = st->first_insn_idx;
}
return 0;
}
static int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
return __mark_chain_precision(env, regno, -1);
}
static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi)
{
return __mark_chain_precision(env, -1, spi);
}
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:
case PTR_TO_SOCK_COMMON:
case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
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);
}
static bool register_is_const(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
}
static void save_register_state(struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg)
{
int i;
state->stack[spi].spilled_ptr = *reg;
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack[spi].slot_type[i] = STACK_SPILL;
}
/* 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;
u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg;
struct bpf_reg_state *reg = NULL;
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)
reg = &cur->regs[value_regno];
if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
!register_is_null(reg) && env->allow_ptr_leaks) {
if (dst_reg != BPF_REG_FP) {
/* The backtracking logic can only recognize explicit
* stack slot address like [fp - 8]. Other spill of
* scalar via different register has to be conervative.
* Backtrack from here and mark all registers as precise
* that contributed into 'reg' being a constant.
*/
err = mark_chain_precision(env, value_regno);
if (err)
return err;
}
save_register_state(state, spi, reg);
} else if (reg && is_spillable_regtype(reg->type)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
verbose_linfo(env, insn_idx, "; ");
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
if (!env->allow_ptr_leaks) {
bool sanitize = false;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
register_is_const(&state->stack[spi].spilled_ptr))
sanitize = true;
for (i = 0; i < BPF_REG_SIZE; i++)
if (state->stack[spi].slot_type[i] == STACK_MISC) {
sanitize = true;
break;
}
if (sanitize) {
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;
}
}
save_register_state(state, spi, reg);
} 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 (reg && register_is_null(reg)) {
/* backtracking doesn't work for STACK_ZERO yet. */
err = mark_chain_precision(env, value_regno);
if (err)
return err;
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;
struct bpf_reg_state *reg;
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;
reg = &reg_state->stack[spi].spilled_ptr;
if (stype[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
if (reg->type != SCALAR_VALUE) {
verbose_linfo(env, env->insn_idx, "; ");
verbose(env, "invalid size of register fill\n");
return -EACCES;
}
if (value_regno >= 0) {
mark_reg_unknown(env, state->regs, value_regno);
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
return 0;
}
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;
/* 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, reg->parent, REG_LIVE_READ64);
} 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, reg->parent, REG_LIVE_READ64);
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]);
/* backtracking doesn't support STACK_ZERO yet,
* so mark it precise here, so that later
* backtracking can stop here.
* Backtracking may not need this if this register
* doesn't participate in pointer adjustment.
* Forward propagation of precise flag is not
* necessary either. This mark is only to stop
* backtracking. Any register that contributed
* to const 0 was marked precise before spill.
*/
state->regs[value_regno].precise = true;
} 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\n",
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;
}
static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
int off, int size, enum bpf_access_type type)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_map *map = regs[regno].map_ptr;
u32 cap = bpf_map_flags_to_cap(map);
if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
map->value_size, 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 & BPF_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);
if (map_value_has_spin_lock(reg->map_ptr)) {
u32 lock = reg->map_ptr->spin_lock_off;
/* if any part of struct bpf_spin_lock can be touched by
* load/store reject this program.
* To check that [x1, x2) overlaps with [y1, y2)
* it is sufficient to check x1 < y2 && y1 < x2.
*/
if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) &&
lock < reg->umax_value + off + size) {
verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n");
return -EACCES;
}
}
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;
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
if (t == BPF_WRITE)
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,
u32 *btf_id)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
.log = &env->log,
};
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;
if (*reg_type == PTR_TO_BTF_ID)
*btf_id = info.btf_id;
else
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, int insn_idx,
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 = {};
bool valid;
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;
}
switch (reg->type) {
case PTR_TO_SOCK_COMMON:
valid = bpf_sock_common_is_valid_access(off, size, t, &info);
break;
case PTR_TO_SOCKET:
valid = bpf_sock_is_valid_access(off, size, t, &info);
break;
case PTR_TO_TCP_SOCK:
valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
break;
case PTR_TO_XDP_SOCK:
valid = bpf_xdp_sock_is_valid_access(off, size, t, &info);
break;
default:
valid = false;
}
if (valid) {
env->insn_aux_data[insn_idx].ctx_field_size =
info.ctx_field_size;
return 0;
}
verbose(env, "R%d invalid %s access off=%d size=%d\n",
regno, reg_type_str[reg->type], off, size);
return -EACCES;
}
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;
}
static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return type_is_sk_pointer(reg->type);
}
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;
case PTR_TO_SOCK_COMMON:
pointer_desc = "sock_common ";
break;
case PTR_TO_TCP_SOCK:
pointer_desc = "tcp_sock ";
break;
case PTR_TO_XDP_SOCK:
pointer_desc = "xdp_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;
</