FEX-Emu/linux
1
0
Fork 0
mirror of https://github.com/FEX-Emu/linux.git synced 2024-12-28 20:37:27 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
f6b1b3bf0d
linux/kernel/bpf/verifier.c
Daniel Borkmann f6b1b3bf0d bpf: fix subprog verifier bypass by div/mod by 0 exception 
One of the ugly leftovers from the early eBPF days is that div/mod
operations based on registers have a hard-coded src_reg == 0 test
in the interpreter as well as in JIT code generators that would
return from the BPF program with exit code 0. This was basically
adopted from cBPF interpreter for historical reasons.

There are multiple reasons why this is very suboptimal and prone
to bugs. To name one: the return code mapping for such abnormal
program exit of 0 does not always match with a suitable program
type's exit code mapping. For example, '0' in tc means action 'ok'
where the packet gets passed further up the stack, which is just
undesirable for such cases (e.g. when implementing policy) and
also does not match with other program types.

While trying to work out an exception handling scheme, I also
noticed that programs crafted like the following will currently
pass the verifier:

  0: (bf) r6 = r1
  1: (85) call pc+8
  caller:
   R6=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
  callee:
   frame1: R1=ctx(id=0,off=0,imm=0) R10=fp0,call_1
  10: (b4) (u32) r2 = (u32) 0
  11: (b4) (u32) r3 = (u32) 1
  12: (3c) (u32) r3 /= (u32) r2
  13: (61) r0 = *(u32 *)(r1 +76)
  14: (95) exit
  returning from callee:
   frame1: R0_w=pkt(id=0,off=0,r=0,imm=0)
           R1=ctx(id=0,off=0,imm=0) R2_w=inv0
           R3_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff))
           R10=fp0,call_1
  to caller at 2:
   R0_w=pkt(id=0,off=0,r=0,imm=0) R6=ctx(id=0,off=0,imm=0)
   R10=fp0,call_-1

  from 14 to 2: R0=pkt(id=0,off=0,r=0,imm=0)
                R6=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
  2: (bf) r1 = r6
  3: (61) r1 = *(u32 *)(r1 +80)
  4: (bf) r2 = r0
  5: (07) r2 += 8
  6: (2d) if r2 > r1 goto pc+1
   R0=pkt(id=0,off=0,r=8,imm=0) R1=pkt_end(id=0,off=0,imm=0)
   R2=pkt(id=0,off=8,r=8,imm=0) R6=ctx(id=0,off=0,imm=0)
   R10=fp0,call_-1
  7: (71) r0 = *(u8 *)(r0 +0)
  8: (b7) r0 = 1
  9: (95) exit

  from 6 to 8: safe
  processed 16 insns (limit 131072), stack depth 0+0

Basically what happens is that in the subprog we make use of a
div/mod by 0 exception and in the 'normal' subprog's exit path
we just return skb->data back to the main prog. This has the
implication that the verifier thinks we always get a pkt pointer
in R0 while we still have the implicit 'return 0' from the div
as an alternative unconditional return path earlier. Thus, R0
then contains 0, meaning back in the parent prog we get the
address range of [0x0, skb->data_end] as read and writeable.
Similar can be crafted with other pointer register types.

Since i) BPF_ABS/IND is not allowed in programs that contain
BPF to BPF calls (and generally it's also disadvised to use in
native eBPF context), ii) unknown opcodes don't return zero
anymore, iii) we don't return an exception code in dead branches,
the only last missing case affected and to fix is the div/mod
handling.

What we would really need is some infrastructure to propagate
exceptions all the way to the original prog unwinding the
current stack and returning that code to the caller of the
BPF program. In user space such exception handling for similar
runtimes is typically implemented with setjmp(3) and longjmp(3)
as one possibility which is not available in the kernel,
though (kgdb used to implement it in kernel long time ago). I
implemented a PoC exception handling mechanism into the BPF
interpreter with porting setjmp()/longjmp() into x86_64 and
adding a new internal BPF_ABRT opcode that can use a program
specific exception code for all exception cases we have (e.g.
div/mod by 0, unknown opcodes, etc). While this seems to work
in the constrained BPF environment (meaning, here, we don't
need to deal with state e.g. from memory allocations that we
would need to undo before going into exception state), it still
has various drawbacks: i) we would need to implement the
setjmp()/longjmp() for every arch supported in the kernel and
for x86_64, arm64, sparc64 JITs currently supporting calls,
ii) it has unconditional additional cost on main program
entry to store CPU register state in initial setjmp() call,
and we would need some way to pass the jmp_buf down into
___bpf_prog_run() for main prog and all subprogs, but also
storing on stack is not really nice (other option would be
per-cpu storage for this, but it also has the drawback that
we need to disable preemption for every BPF program types).
All in all this approach would add a lot of complexity.

Another poor-man's solution would be to have some sort of
additional shared register or scratch buffer to hold state
for exceptions, and test that after every call return to
chain returns and pass R0 all the way down to BPF prog caller.
This is also problematic in various ways: i) an additional
register doesn't map well into JITs, and some other scratch
space could only be on per-cpu storage, which, again has the
side-effect that this only works when we disable preemption,
or somewhere in the input context which is not available
everywhere either, and ii) this adds significant runtime
overhead by putting conditionals after each and every call,
as well as implementation complexity.

Yet another option is to teach verifier that div/mod can
return an integer, which however is also complex to implement
as verifier would need to walk such fake 'mov r0,<code>; exit;'
sequeuence and there would still be no guarantee for having
propagation of this further down to the BPF caller as proper
exception code. For parent prog, it is also is not distinguishable
from a normal return of a constant scalar value.

The approach taken here is a completely different one with
little complexity and no additional overhead involved in
that we make use of the fact that a div/mod by 0 is undefined
behavior. Instead of bailing out, we adapt the same behavior
as on some major archs like ARMv8 [0] into eBPF as well:
X div 0 results in 0, and X mod 0 results in X. aarch64 and
aarch32 ISA do not generate any traps or otherwise aborts
of program execution for unsigned divides. I verified this
also with a test program compiled by gcc and clang, and the
behavior matches with the spec. Going forward we adapt the
eBPF verifier to emit such rewrites once div/mod by register
was seen. cBPF is not touched and will keep existing 'return 0'
semantics. Given the options, it seems the most suitable from
all of them, also since major archs have similar schemes in
place. Given this is all in the realm of undefined behavior,
we still have the option to adapt if deemed necessary and
this way we would also have the option of more flexibility
from LLVM code generation side (which is then fully visible
to verifier). Thus, this patch i) fixes the panic seen in
above program and ii) doesn't bypass the verifier observations.

  [0] ARM Architecture Reference Manual, ARMv8 [ARM DDI 0487B.b]
      http://infocenter.arm.com/help/topic/com.arm.doc.ddi0487b.b/DDI0487B_b_armv8_arm.pdf
      1) aarch64 instruction set: section C3.4.7 and C6.2.279 (UDIV)
         "A division by zero results in a zero being written to
          the destination register, without any indication that
          the division by zero occurred."
      2) aarch32 instruction set: section F1.4.8 and F5.1.263 (UDIV)
         "For the SDIV and UDIV instructions, division by zero
          always returns a zero result."

Fixes: f4d7e40a5b ("bpf: introduce function calls (verification)")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-01-26 16:42:05 -08:00

5731 lines
167 KiB
C
Raw Blame History

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#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 "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. These are three pointer
* types recognized by check_mem_access() function.
*
* PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
* and the range of [ptr, ptr + map's value_size) is accessible.
*
* registers used to pass values to function calls are checked against
* function argument constraints.
*
* ARG_PTR_TO_MAP_KEY is one of such argument constraints.
* It means that the register type passed to this function must be
* PTR_TO_STACK and it will be used inside the function as
* 'pointer to map element key'
*
* For example the argument constraints for bpf_map_lookup_elem():
* .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
* .arg1_type = ARG_CONST_MAP_PTR,
* .arg2_type = ARG_PTR_TO_MAP_KEY,
*
* ret_type says that this function returns 'pointer to map elem value or null'
* function expects 1st argument to be a const pointer to 'struct bpf_map' and
* 2nd argument should be a pointer to stack, which will be used inside
* the helper function as a pointer to map element key.
*
* On the kernel side the helper function looks like:
* u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
* {
* struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
* void *key = (void *) (unsigned long) r2;
* void *value;
*
* here kernel can access 'key' and 'map' pointers safely, knowing that
* [key, key + map->key_size) bytes are valid and were initialized on
* the stack of eBPF program.
* }
*
* Corresponding eBPF program may look like:
* BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR
* BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
* BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP
* BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
* here verifier looks at prototype of map_lookup_elem() and sees:
* .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
* Now verifier knows that this map has key of R1->map_ptr->key_size bytes
*
* Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
* Now verifier checks that [R2, R2 + map's key_size) are within stack limits
* and were initialized prior to this call.
* If it's ok, then verifier allows this BPF_CALL insn and looks at
* .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
* R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
* returns ether pointer to map value or NULL.
*
* When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
* insn, the register holding that pointer in the true branch changes state to
* PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
* branch. See check_cond_jmp_op().
*
* After the call R0 is set to return type of the function and registers R1-R5
* are set to NOT_INIT to indicate that they are no longer readable.
*/
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
/* verifer state is 'st'
* before processing instruction 'insn_idx'
* and after processing instruction 'prev_insn_idx'
*/
struct bpf_verifier_state st;
int insn_idx;
int prev_insn_idx;
struct bpf_verifier_stack_elem *next;
};
#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
bool raw_mode;
bool pkt_access;
int regno;
int access_size;
};
static DEFINE_MUTEX(bpf_verifier_lock);
/* 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, ...)
{
struct bpf_verifer_log *log = &env->log;
unsigned int n;
va_list args;
if (!log->level || !log->ubuf || bpf_verifier_log_full(log))
return;
va_start(args, fmt);
n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
va_end(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;
}
EXPORT_SYMBOL_GPL(bpf_verifier_log_write);
/* Historically bpf_verifier_log_write was called verbose, but the name was too
* generic for symbol export. The function was renamed, but not the calls in
* the verifier to avoid complicating backports. Hence the alias below.
*/
static __printf(2, 3) void verbose(struct bpf_verifier_env *env,
const char *fmt, ...)
__attribute__((alias("bpf_verifier_log_write")));
static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_PACKET ||
type == PTR_TO_PACKET_META;
}
/* 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",
};
static void print_liveness(struct bpf_verifier_env *env,
enum bpf_reg_liveness live)
{
if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
verbose(env, "_");
if (live & REG_LIVE_READ)
verbose(env, "r");
if (live & REG_LIVE_WRITTEN)
verbose(env, "w");
}
static struct bpf_func_state *func(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg)
{
struct bpf_verifier_state *cur = env->cur_state;
return cur->frame[reg->frameno];
}
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state)
{
const struct bpf_reg_state *reg;
enum bpf_reg_type t;
int i;
if (state->frameno)
verbose(env, " frame%d:", state->frameno);
for (i = 0; i < MAX_BPF_REG; i++) {
reg = &state->regs[i];
t = reg->type;
if (t == NOT_INIT)
continue;
verbose(env, " R%d", i);
print_liveness(env, reg->live);
verbose(env, "=%s", reg_type_str[t]);
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
tnum_is_const(reg->var_off)) {
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
if (t == PTR_TO_STACK)
verbose(env, ",call_%d", func(env, reg)->callsite);
} else {
verbose(env, "(id=%d", reg->id);
if (t != SCALAR_VALUE)
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
else if (t == CONST_PTR_TO_MAP ||
t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
if (tnum_is_const(reg->var_off)) {
/* Typically an immediate SCALAR_VALUE, but
* could be a pointer whose offset is too big
* for reg->off
*/
verbose(env, ",imm=%llx", reg->var_off.value);
} else {
if (reg->smin_value != reg->umin_value &&
reg->smin_value != S64_MIN)
verbose(env, ",smin_value=%lld",
(long long)reg->smin_value);
if (reg->smax_value != reg->umax_value &&
reg->smax_value != S64_MAX)
verbose(env, ",smax_value=%lld",
(long long)reg->smax_value);
if (reg->umin_value != 0)
verbose(env, ",umin_value=%llu",
(unsigned long long)reg->umin_value);
if (reg->umax_value != U64_MAX)
verbose(env, ",umax_value=%llu",
(unsigned long long)reg->umax_value);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, ",var_off=%s", tn_buf);
}
}
verbose(env, ")");
}
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
if (state->stack[i].slot_type[0] == STACK_SPILL) {
verbose(env, " fp%d",
(-i - 1) * BPF_REG_SIZE);
print_liveness(env, state->stack[i].spilled_ptr.live);
verbose(env, "=%s",
reg_type_str[state->stack[i].spilled_ptr.type]);
}
if (state->stack[i].slot_type[0] == STACK_ZERO)
verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
}
verbose(env, "\n");
}
static int copy_stack_state(struct bpf_func_state *dst,
const struct bpf_func_state *src)
{
if (!src->stack)
return 0;
if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
/* internal bug, make state invalid to reject the program */
memset(dst, 0, sizeof(*dst));
return -EFAULT;
}
memcpy(dst->stack, src->stack,
sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
return 0;
}
/* 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 this function copies over. It points to previous bpf_verifier_state
* which is never reallocated
*/
static int realloc_func_state(struct bpf_func_state *state, int size,
bool copy_old)
{
u32 old_size = state->allocated_stack;
struct bpf_stack_state *new_stack;
int slot = size / BPF_REG_SIZE;
if (size <= old_size || !size) {
if (copy_old)
return 0;
state->allocated_stack = slot * BPF_REG_SIZE;
if (!size && old_size) {
kfree(state->stack);
state->stack = NULL;
}
return 0;
}
new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
GFP_KERNEL);
if (!new_stack)
return -ENOMEM;
if (copy_old) {
if (state->stack)
memcpy(new_stack, state->stack,
sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
memset(new_stack + old_size / BPF_REG_SIZE, 0,
sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
}
state->allocated_stack = slot * BPF_REG_SIZE;
kfree(state->stack);
state->stack = new_stack;
return 0;
}
static void free_func_state(struct bpf_func_state *state)
{
if (!state)
return;
kfree(state->stack);
kfree(state);
}
static void free_verifier_state(struct bpf_verifier_state *state,
bool free_self)
{
int i;
for (i = 0; i <= state->curframe; i++) {
free_func_state(state->frame[i]);
state->frame[i] = NULL;
}
if (free_self)
kfree(state);
}
/* copy verifier state from src to dst growing dst stack space
* when necessary to accommodate larger src stack
*/
static int copy_func_state(struct bpf_func_state *dst,
const struct bpf_func_state *src)
{
int err;
err = realloc_func_state(dst, src->allocated_stack, false);
if (err)
return err;
memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
return copy_stack_state(dst, src);
}
static int copy_verifier_state(struct bpf_verifier_state *dst_state,
const struct bpf_verifier_state *src)
{
struct bpf_func_state *dst;
int i, err;
/* if dst has more stack frames then src frame, free them */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
}
dst_state->curframe = src->curframe;
dst_state->parent = src->parent;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (!dst)
return -ENOMEM;
dst_state->frame[i] = dst;
}
err = copy_func_state(dst, src->frame[i]);
if (err)
return err;
}
return 0;
}
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
int *insn_idx)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem, *head = env->head;
int err;
if (env->head == NULL)
return -ENOENT;
if (cur) {
err = copy_verifier_state(cur, &head->st);
if (err)
return err;
}
if (insn_idx)
*insn_idx = head->insn_idx;
if (prev_insn_idx)
*prev_insn_idx = head->prev_insn_idx;
elem = head->next;
free_verifier_state(&head->st, false);
kfree(head);
env->head = elem;
env->stack_size--;
return 0;
}
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx)
{
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;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
verbose(env, "BPF program is too complex\n");
goto err;
}
return &elem->st;
err:
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
/* pop all elements and return */
while (!pop_stack(env, NULL, NULL));
return NULL;
}
#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
#define CALLEE_SAVED_REGS 5
static const int callee_saved[CALLEE_SAVED_REGS] = {
BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9
};
static void __mark_reg_not_init(struct bpf_reg_state *reg);
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
*/
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
reg->id = 0;
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->off = 0;
reg->type = SCALAR_VALUE;
}
static void mark_reg_known_zero(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
}
static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
{
return type_is_pkt_pointer(reg->type);
}
static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
{
return reg_is_pkt_pointer(reg) ||
reg->type == PTR_TO_PACKET_END;
}
/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
enum bpf_reg_type which)
{
/* The register can already have a range from prior markings.
* This is fine as long as it hasn't been advanced from its
* origin.
*/
return reg->type == which &&
reg->id == 0 &&
reg->off == 0 &&
tnum_equals_const(reg->var_off, 0);
}
/* Attempts to improve min/max values based on var_off information */
static void __update_reg_bounds(struct bpf_reg_state *reg)
{
/* min signed is max(sign bit) | min(other bits) */
reg->smin_value = max_t(s64, reg->smin_value,
reg->var_off.value | (reg->var_off.mask & S64_MIN));
/* max signed is min(sign bit) | max(other bits) */
reg->smax_value = min_t(s64, reg->smax_value,
reg->var_off.value | (reg->var_off.mask & S64_MAX));
reg->umin_value = max(reg->umin_value, reg->var_off.value);
reg->umax_value = min(reg->umax_value,
reg->var_off.value | reg->var_off.mask);
}
/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
/* Learn sign from signed bounds.
* If we cannot cross the sign boundary, then signed and unsigned bounds
* are the same, so combine. This works even in the negative case, e.g.
* -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
if (reg->smin_value >= 0 || reg->smax_value < 0) {
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
return;
}
/* Learn sign from unsigned bounds. Signed bounds cross the sign
* boundary, so we must be careful.
*/
if ((s64)reg->umax_value >= 0) {
/* Positive. We can't learn anything from the smin, but smax
* is positive, hence safe.
*/
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
} else if ((s64)reg->umin_value < 0) {
/* Negative. We can't learn anything from the smax, but smin
* is negative, hence safe.
*/
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value;
}
}
/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
reg->var_off = tnum_intersect(reg->var_off,
tnum_range(reg->umin_value,
reg->umax_value));
}
/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
reg->smin_value = S64_MIN;
reg->smax_value = S64_MAX;
reg->umin_value = 0;
reg->umax_value = U64_MAX;
}
/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(struct bpf_reg_state *reg)
{
reg->type = SCALAR_VALUE;
reg->id = 0;
reg->off = 0;
reg->var_off = tnum_unknown;
reg->frameno = 0;
__mark_reg_unbounded(reg);
}
static void mark_reg_unknown(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_unknown(regs + regno);
}
static void __mark_reg_not_init(struct bpf_reg_state *reg)
{
__mark_reg_unknown(reg);
reg->type = NOT_INIT;
}
static void mark_reg_not_init(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(regs + regno);
return;
}
__mark_reg_not_init(regs + regno);
}
static void init_reg_state(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
}
/* 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 *(int *)a - *(int *)b;
}
static int find_subprog(struct bpf_verifier_env *env, int off)
{
u32 *p;
p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
sizeof(env->subprog_starts[0]), cmp_subprogs);
if (!p)
return -ENOENT;
return p - env->subprog_starts;
}
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_starts[env->subprog_cnt++] = off;
sort(env->subprog_starts, env->subprog_cnt,
sizeof(env->subprog_starts[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_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
/* 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;
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
verbose(env, "function calls in offloaded programs are not supported yet\n");
return -EINVAL;
}
ret = add_subprog(env, i + insn[i].imm + 1);
if (ret < 0)
return ret;
}
if (env->log.level > 1)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);
/* now check that all jumps are within the same subprog */
subprog_start = 0;
if (env->subprog_cnt == cur_subprog)
subprog_end = insn_cnt;
else
subprog_end = env->subprog_starts[cur_subprog++];
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
if (BPF_CLASS(code) != BPF_JMP)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
}
next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
* or unconditional jump back
*/
if (code != (BPF_JMP | BPF_EXIT) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
}
subprog_start = subprog_end;
if (env->subprog_cnt == cur_subprog)
subprog_end = insn_cnt;
else
subprog_end = env->subprog_starts[cur_subprog++];
}
}
return 0;
}
static
struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
const struct bpf_verifier_state *state,
struct bpf_verifier_state *parent,
u32 regno)
{
struct bpf_verifier_state *tmp = NULL;
/* 'parent' could be a state of caller and
* 'state' could be a state of callee. In such case
* parent->curframe < state->curframe
* and it's ok for r1 - r5 registers
*
* 'parent' could be a callee's state after it bpf_exit-ed.
* In such case parent->curframe > state->curframe
* and it's ok for r0 only
*/
if (parent->curframe == state->curframe ||
(parent->curframe < state->curframe &&
regno >= BPF_REG_1 && regno <= BPF_REG_5) ||
(parent->curframe > state->curframe &&
regno == BPF_REG_0))
return parent;
if (parent->curframe > state->curframe &&
regno >= BPF_REG_6) {
/* for callee saved regs we have to skip the whole chain
* of states that belong to callee and mark as LIVE_READ
* the registers before the call
*/
tmp = parent;
while (tmp && tmp->curframe != state->curframe) {
tmp = tmp->parent;
}
if (!tmp)
goto bug;
parent = tmp;
} else {
goto bug;
}
return parent;
bug:
verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
verbose(env, "regno %d parent frame %d current frame %d\n",
regno, parent->curframe, state->curframe);
return NULL;
}
static int mark_reg_read(struct bpf_verifier_env *env,
const struct bpf_verifier_state *state,
struct bpf_verifier_state *parent,
u32 regno)
{
bool writes = parent == state->parent; /* Observe write marks */
if (regno == BPF_REG_FP)
/* We don't need to worry about FP liveness because it's read-only */
return 0;
while (parent) {
/* if read wasn't screened by an earlier write ... */
if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN)
break;
parent = skip_callee(env, state, parent, regno);
if (!parent)
return -EFAULT;
/* ... then we depend on parent's value */
parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
}
return 0;
}
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
enum reg_arg_type t)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs;
if (regno >= MAX_BPF_REG) {
verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
if (regs[regno].type == NOT_INIT) {
verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
return mark_reg_read(env, vstate, vstate->parent, regno);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose(env, "frame pointer is read only\n");
return -EACCES;
}
regs[regno].live |= REG_LIVE_WRITTEN;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
return 0;
}
static bool is_spillable_regtype(enum bpf_reg_type type)
{
switch (type) {
case PTR_TO_MAP_VALUE:
case PTR_TO_MAP_VALUE_OR_NULL:
case PTR_TO_STACK:
case PTR_TO_CTX:
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
case CONST_PTR_TO_MAP:
return true;
default:
return false;
}
}
/* Does this register contain a constant zero? */
static bool register_is_null(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
static int check_stack_write(struct bpf_verifier_env *env,
struct bpf_func_state *state, /* func where register points to */
int off, int size, int value_regno)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
enum bpf_reg_type type;
err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
true);
if (err)
return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
if (!env->allow_ptr_leaks &&
state->stack[spi].slot_type[0] == STACK_SPILL &&
size != BPF_REG_SIZE) {
verbose(env, "attempt to corrupt spilled pointer on stack\n");
return -EACCES;
}
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0 &&
is_spillable_regtype((type = cur->regs[value_regno].type))) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
if (state != cur && type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
/* save register state */
state->stack[spi].spilled_ptr = cur->regs[value_regno];
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack[spi].slot_type[i] = STACK_SPILL;
} else {
u8 type = STACK_MISC;
/* regular write of data into stack */
state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};
/* only mark the slot as written if all 8 bytes were written
* otherwise read propagation may incorrectly stop too soon
* when stack slots are partially written.
* This heuristic means that read propagation will be
* conservative, since it will add reg_live_read marks
* to stack slots all the way to first state when programs
* writes+reads less than 8 bytes
*/
if (size == BPF_REG_SIZE)
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
/* when we zero initialize stack slots mark them as such */
if (value_regno >= 0 &&
register_is_null(&cur->regs[value_regno]))
type = STACK_ZERO;
for (i = 0; i < size; i++)
state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
type;
}
return 0;
}
/* registers of every function are unique and mark_reg_read() propagates
* the liveness in the following cases:
* - from callee into caller for R1 - R5 that were used as arguments
* - from caller into callee for R0 that used as result of the call
* - from caller to the same caller skipping states of the callee for R6 - R9,
* since R6 - R9 are callee saved by implicit function prologue and
* caller's R6 != callee's R6, so when we propagate liveness up to
* parent states we need to skip callee states for R6 - R9.
*
* stack slot marking is different, since stacks of caller and callee are
* accessible in both (since caller can pass a pointer to caller's stack to
* callee which can pass it to another function), hence mark_stack_slot_read()
* has to propagate the stack liveness to all parent states at given frame number.
* Consider code:
* f1() {
* ptr = fp - 8;
* *ptr = ctx;
* call f2 {
* .. = *ptr;
* }
* .. = *ptr;
* }
* First *ptr is reading from f1's stack and mark_stack_slot_read() has
* to mark liveness at the f1's frame and not f2's frame.
* Second *ptr is also reading from f1's stack and mark_stack_slot_read() has
* to propagate liveness to f2 states at f1's frame level and further into
* f1 states at f1's frame level until write into that stack slot
*/
static void mark_stack_slot_read(struct bpf_verifier_env *env,
const struct bpf_verifier_state *state,
struct bpf_verifier_state *parent,
int slot, int frameno)
{
bool writes = parent == state->parent; /* Observe write marks */
while (parent) {
if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE)
/* since LIVE_WRITTEN mark is only done for full 8-byte
* write the read marks are conservative and parent
* state may not even have the stack allocated. In such case
* end the propagation, since the loop reached beginning
* of the function
*/
break;
/* if read wasn't screened by an earlier write ... */
if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
break;
/* ... then we depend on parent's value */
parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
}
}
static int check_stack_read(struct bpf_verifier_env *env,
struct bpf_func_state *reg_state /* func where register points to */,
int off, int size, int value_regno)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
u8 *stype;
if (reg_state->allocated_stack <= slot) {
verbose(env, "invalid read from stack off %d+0 size %d\n",
off, size);
return -EACCES;
}
stype = reg_state->stack[spi].slot_type;
if (stype[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
for (i = 1; i < BPF_REG_SIZE; i++) {
if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
verbose(env, "corrupted spill memory\n");
return -EACCES;
}
}
if (value_regno >= 0) {
/* restore register state from stack */
state->regs[value_regno] = reg_state->stack[spi].spilled_ptr;
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
*/
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
mark_stack_slot_read(env, vstate, vstate->parent, spi,
reg_state->frameno);
return 0;
} else {
int zeros = 0;
for (i = 0; i < size; i++) {
if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
continue;
if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
zeros++;
continue;
}
verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
mark_stack_slot_read(env, vstate, vstate->parent, spi,
reg_state->frameno);
if (value_regno >= 0) {
if (zeros == size) {
/* any size read into register is zero extended,
* so the whole register == const_zero
*/
__mark_reg_const_zero(&state->regs[value_regno]);
} else {
/* have read misc data from the stack */
mark_reg_unknown(env, state->regs, value_regno);
}
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
return 0;
}
}
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_map *map = regs[regno].map_ptr;
if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
off + size > map->value_size) {
verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
return 0;
}
/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, bool zero_size_allowed)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regno];
int err;
/* We may have adjusted the register to this map value, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
if (env->log.level)
print_verifier_state(env, state);
/* The minimum value is only important with signed
* comparisons where we can't assume the floor of a
* value is 0. If we are using signed variables for our
* index'es we need to make sure that whatever we use
* will have a set floor within our range.
*/
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
err = __check_map_access(env, regno, reg->smin_value + off, size,
zero_size_allowed);
if (err) {
verbose(env, "R%d min value is outside of the array range\n",
regno);
return err;
}
/* If we haven't set a max value then we need to bail since we can't be
* sure we won't do bad things.
* If reg->umax_value + off could overflow, treat that as unbounded too.
*/
if (reg->umax_value >= BPF_MAX_VAR_OFF) {
verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
regno);
return -EACCES;
}
err = __check_map_access(env, regno, reg->umax_value + off, size,
zero_size_allowed);
if (err)
verbose(env, "R%d max value is outside of the array range\n",
regno);
return err;
}
#define MAX_PACKET_OFF 0xffff
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_access_type t)
{
switch (env->prog->type) {
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
/* dst_input() and dst_output() can't write for now */
if (t == BPF_WRITE)
return false;
/* fallthrough */
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:
if (meta)
return meta->pkt_access;
env->seen_direct_write = true;
return true;
default:
return false;
}
}
static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
(u64)off + size > reg->range) {
verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
off, size, regno, reg->id, reg->off, reg->range);
return -EACCES;
}
return 0;
}
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = &regs[regno];
int err;
/* We may have added a variable offset to the packet pointer; but any
* reg->range we have comes after that. We are only checking the fixed
* offset.
*/
/* We don't allow negative numbers, because we aren't tracking enough
* detail to prove they're safe.
*/
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
err = __check_packet_access(env, regno, off, size, zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
return err;
}
/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
};
if (env->ops->is_valid_access &&
env->ops->is_valid_access(off, size, t, &info)) {
/* A non zero info.ctx_field_size indicates that this field is a
* candidate for later verifier transformation to load the whole
* field and then apply a mask when accessed with a narrower
* access than actual ctx access size. A zero info.ctx_field_size
* will only allow for whole field access and rejects any other
* type of narrower access.
*/
*reg_type = info.reg_type;
env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
return 0;
}
verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
return -EACCES;
}
static 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 bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
}
static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = cur_regs(env) + regno;
return reg->type == PTR_TO_CTX;
}
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 = env->strict_alignment;
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_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;
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_stack_depth[func->subprogno];
if (stack >= -off)
return 0;
/* update known max for given subprogram */
env->subprog_stack_depth[func->subprogno] = -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, subprog = 0, i = 0, subprog_end;
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
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, env->subprog_stack_depth[subprog], 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:
if (env->subprog_cnt == subprog)
subprog_end = insn_cnt;
else
subprog_end = env->subprog_starts[subprog];
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] = subprog;
/* find the callee */
i = i + insn[i].imm + 1;
subprog = find_subprog(env, i);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i);
return -EFAULT;
}
subprog++;
frame++;
if (frame >= MAX_CALL_FRAMES) {
WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
return -EFAULT;
}
goto process_func;
}
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
*/
if (frame == 0)
return 0;
depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
frame--;
i = ret_insn[frame];
subprog = ret_prog[frame];
goto continue_func;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int idx)
{
int start = idx + insn->imm + 1, subprog;
subprog = find_subprog(env, start);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
start);
return -EFAULT;
}
subprog++;
return env->subprog_stack_depth[subprog];
}
#endif
/* truncate register to smaller size (in bytes)
* must be called with size < BPF_REG_SIZE
*/
static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
{
u64 mask;
/* clear high bits in bit representation */
reg->var_off = tnum_cast(reg->var_off, size);
/* fix arithmetic bounds */
mask = ((u64)1 << (size * 8)) - 1;
if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
reg->umin_value &= mask;
reg->umax_value &= mask;
} else {
reg->umin_value = 0;
reg->umax_value = mask;
}
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value;
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
* if t==write && value_regno==-1, some unknown value is stored into memory
* if t==read && value_regno==-1, don't care what we read from memory
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off,
int bpf_size, enum bpf_access_type t,
int value_regno)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
struct bpf_func_state *state;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
if (size < 0)
return size;
/* alignment checks will add in reg->off themselves */
err = check_ptr_alignment(env, reg, off, size);
if (err)
return err;
/* for access checks, reg->off is just part of off */
off += reg->off;
if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
/* ctx accesses must be at a fixed offset, so that we can
* determine what type of data were returned.
*/
if (reg->off) {
verbose(env,
"dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
regno, reg->off, off - reg->off);
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env,
"variable ctx access var_off=%s off=%d size=%d",
tn_buf, off, size);
return -EACCES;
}
err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
* PTR_TO_PACKET[_META,_END]. In the latter
* case, we know the offset is zero.
*/
if (reg_type == SCALAR_VALUE)
mark_reg_unknown(env, regs, value_regno);
else
mark_reg_known_zero(env, regs,
value_regno);
regs[value_regno].id = 0;
regs[value_regno].off = 0;
regs[value_regno].range = 0;
regs[value_regno].type = reg_type;
}
} else if (reg->type == PTR_TO_STACK) {
/* stack accesses must be at a fixed offset, so that we can
* determine what type of data were returned.
* See check_stack_read().
*/
if (!tnum_is_const(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "variable stack access var_off=%s off=%d size=%d",
tn_buf, off, size);
return -EACCES;
}
off += reg->var_off.value;
if (off >= 0 || off < -MAX_BPF_STACK) {
verbose(env, "invalid stack off=%d size=%d\n", off,
size);
return -EACCES;
}
state = func(env, reg);
err = update_stack_depth(env, state, off);
if (err)
return err;
if (t == BPF_WRITE)
err = check_stack_write(env, state, off, size,
value_regno);
else
err = check_stack_read(env, state, off, size,
value_regno);
} else if (reg_is_pkt_pointer(reg)) {
if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
verbose(env, "cannot write into packet\n");
return -EACCES;
}
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into packet\n",
value_regno);
return -EACCES;
}
err = check_packet_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
reg_type_str[reg->type]);
return -EACCES;
}
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
/* b/h/w load zero-extends, mark upper bits as known 0 */
coerce_reg_to_size(&regs[value_regno], size);
}
return err;
}
static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
int err;
if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
insn->imm != 0) {
verbose(env, "BPF_XADD uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
return -EACCES;
}
if (is_ctx_reg(env, insn->dst_reg)) {
verbose(env, "BPF_XADD stores into R%d context is not allowed\n",
insn->dst_reg);
return -EACCES;
}
/* check whether atomic_add can read the memory */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
if (err)
return err;
/* check whether atomic_add can write into the same memory */
return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1);
}
/* when register 'regno' is passed into function that will read 'access_size'
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized.
* Unlike most pointer bounds-checking functions, this one doesn't take an
* 'off' argument, so it has to add in reg->off itself.
*/
static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *reg = cur_regs(env) + regno;
struct bpf_func_state *state = func(env, reg);
int off, i, slot, spi;
if (reg->type != PTR_TO_STACK) {
/* Allow zero-byte read from NULL, regardless of pointer type */
if (zero_size_allowed && access_size == 0 &&
register_is_null(reg))
return 0;
verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[reg->type],
reg_type_str[PTR_TO_STACK]);
return -EACCES;
}
/* Only allow fixed-offset stack reads */
if (!tnum_is_const(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "invalid variable stack read R%d var_off=%s\n",
regno, tn_buf);
return -EACCES;
}
off = reg->off + reg->var_off.value;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
regno, off, access_size);
return -EACCES;
}
if (meta && meta->raw_mode) {
meta->access_size = access_size;
meta->regno = regno;
return 0;
}
for (i = 0; i < access_size; i++) {
u8 *stype;
slot = -(off + i) - 1;
spi = slot / BPF_REG_SIZE;
if (state->allocated_stack <= slot)
goto err;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
if (*stype == STACK_MISC)
goto mark;
if (*stype == STACK_ZERO) {
/* helper can write anything into the stack */
*stype = STACK_MISC;
goto mark;
}
err:
verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
off, i, access_size);
return -EACCES;
mark:
/* reading any byte out of 8-byte 'spill_slot' will cause
* the whole slot to be marked as 'read'
*/
mark_stack_slot_read(env, env->cur_state, env->cur_state->parent,
spi, state->frameno);
}
return update_stack_depth(env, state, off);
}
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
switch (reg->type) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_VALUE:
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
default: /* scalar_value|ptr_to_stack or invalid ptr */
return check_stack_boundary(env, regno, access_size,
zero_size_allowed, meta);
}
}
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MEM ||
type == ARG_PTR_TO_MEM_OR_NULL ||
type == ARG_PTR_TO_UNINIT_MEM;
}
static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
return type == ARG_CONST_SIZE ||
type == ARG_CONST_SIZE_OR_ZERO;
}
static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
enum bpf_reg_type expected_type, type = reg->type;
int err = 0;
if (arg_type == ARG_DONTCARE)
return 0;
err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
if (arg_type == ARG_ANYTHING) {
if (is_pointer_value(env, regno)) {
verbose(env, "R%d leaks addr into helper function\n",
regno);
return -EACCES;
}
return 0;
}
if (type_is_pkt_pointer(type) &&
!may_access_direct_pkt_data(env, meta, BPF_READ)) {
verbose(env, "helper access to the packet is not allowed\n");
return -EACCES;
}
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
if (!type_is_pkt_pointer(type) &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
arg_type == ARG_CONST_SIZE_OR_ZERO) {
expected_type = SCALAR_VALUE;
if (type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_MAP_PTR) {
expected_type = CONST_PTR_TO_MAP;
if (type != expected_type)
goto err_type;
} else if (arg_type == ARG_PTR_TO_CTX) {
expected_type = PTR_TO_CTX;
if (type != expected_type)
goto err_type;
} else if (arg_type_is_mem_ptr(arg_type)) {
expected_type = PTR_TO_STACK;
/* One exception here. In case function allows for NULL to be
* passed in as argument, it's a SCALAR_VALUE type. Final test
* happens during stack boundary checking.
*/
if (register_is_null(reg) &&
arg_type == ARG_PTR_TO_MEM_OR_NULL)
/* final test in check_stack_boundary() */;
else if (!type_is_pkt_pointer(type) &&
type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
} else {
verbose(env, "unsupported arg_type %d\n", arg_type);
return -EFAULT;
}
if (arg_type == ARG_CONST_MAP_PTR) {
/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
meta->map_ptr = reg->map_ptr;
} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
/* bpf_map_xxx(..., map_ptr, ..., key) call:
* check that [key, key + map->key_size) are within
* stack limits and initialized
*/
if (!meta->map_ptr) {
/* in function declaration map_ptr must come before
* map_key, so that it's verified and known before
* we have to check map_key here. Otherwise it means
* that kernel subsystem misconfigured verifier
*/
verbose(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
meta->map_ptr->key_size,
false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->key_size,
false, NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
meta->map_ptr->value_size,
false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->value_size,
false, NULL);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
/* The register is SCALAR_VALUE; the access check
* happens using its boundaries.
*/
if (!tnum_is_const(reg->var_off))
/* For unprivileged variable accesses, disable raw
* mode so that the program is required to
* initialize all the memory that the helper could
* just partially fill up.
*/
meta = NULL;
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
regno);
return -EACCES;
}
if (reg->umin_value == 0) {
err = check_helper_mem_access(env, regno - 1, 0,
zero_size_allowed,
meta);
if (err)
return err;
}
if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
regno);
return -EACCES;
}
err = check_helper_mem_access(env, regno - 1,
reg->umax_value,
zero_size_allowed, meta);
}
return err;
err_type:
verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[type], reg_type_str[expected_type]);
return -EACCES;
}
static int check_map_func_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map, int func_id)
{
if (!map)
return 0;
/* We need a two way check, first is from map perspective ... */
switch (map->map_type) {
case BPF_MAP_TYPE_PROG_ARRAY:
if (func_id != BPF_FUNC_tail_call)
goto error;
break;
case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
if (func_id != BPF_FUNC_perf_event_read &&
func_id != BPF_FUNC_perf_event_output &&
func_id != BPF_FUNC_perf_event_read_value)
goto error;
break;
case BPF_MAP_TYPE_STACK_TRACE:
if (func_id != BPF_FUNC_get_stackid)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
if (func_id != BPF_FUNC_skb_under_cgroup &&
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
/* devmap returns a pointer to a live net_device ifindex that we cannot
* allow to be modified from bpf side. So do not allow lookup elements
* for now.
*/
case BPF_MAP_TYPE_DEVMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
/* Restrict bpf side of cpumap, open when use-cases appear */
case BPF_MAP_TYPE_CPUMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
case BPF_MAP_TYPE_SOCKMAP:
if (func_id != BPF_FUNC_sk_redirect_map &&
func_id != BPF_FUNC_sock_map_update &&
func_id != BPF_FUNC_map_delete_elem)
goto error;
break;
default:
break;
}
/* ... and second from the function itself. */
switch (func_id) {
case BPF_FUNC_tail_call:
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
goto error;
if (env->subprog_cnt) {
verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
return -EINVAL;
}
break;
case BPF_FUNC_perf_event_read:
case BPF_FUNC_perf_event_output:
case BPF_FUNC_perf_event_read_value:
if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
goto error;
break;
case BPF_FUNC_get_stackid:
if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
goto error;
break;
case BPF_FUNC_current_task_under_cgroup:
case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
case BPF_FUNC_redirect_map:
if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
map->map_type != BPF_MAP_TYPE_CPUMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
goto error;
break;
case BPF_FUNC_sock_map_update:
if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
goto error;
break;
default:
break;
}
return 0;
error:
verbose(env, "cannot pass map_type %d into func %s#%d\n",
map->map_type, func_id_name(func_id), func_id);
return -EINVAL;
}
static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
{
int count = 0;
if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
count++;
/* We only support one arg being in raw mode at the moment,
* which is sufficient for the helper functions we have
* right now.
*/
return count <= 1;
}
static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
enum bpf_arg_type arg_next)
{
return (arg_type_is_mem_ptr(arg_curr) &&
!arg_type_is_mem_size(arg_next)) ||
(!arg_type_is_mem_ptr(arg_curr) &&
arg_type_is_mem_size(arg_next));
}
static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
{
/* bpf_xxx(..., buf, len) call will access 'len'
* bytes from memory 'buf'. Both arg types need
* to be paired, so make sure there's no buggy
* helper function specification.
*/
if (arg_type_is_mem_size(fn->arg1_type) ||
arg_type_is_mem_ptr(fn->arg5_type) ||
check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
return false;
return true;
}
static int check_func_proto(const struct bpf_func_proto *fn)
{
return check_raw_mode_ok(fn) &&
check_arg_pair_ok(fn) ? 0 : -EINVAL;
}
/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
* are now invalid, so turn them into unknown SCALAR_VALUE.
*/
static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (reg_is_pkt_pointer_any(&regs[i]))
mark_reg_unknown(env, regs, i);
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
reg = &state->stack[i].spilled_ptr;
if (reg_is_pkt_pointer_any(reg))
__mark_reg_unknown(reg);
}
}
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *vstate = env->cur_state;
int i;
for (i = 0; i <= vstate->curframe; i++)
__clear_all_pkt_pointers(env, vstate->frame[i]);
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
int i, subprog, target_insn;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
state->curframe + 2);
return -E2BIG;
}
target_insn = *insn_idx + insn->imm;
subprog = find_subprog(env, target_insn + 1);
if (subprog < 0) {
verbose(env, "verifier bug. No program starts at insn %d\n",
target_insn + 1);
return -EFAULT;
}
caller = state->frame[state->curframe];
if (state->frame[state->curframe + 1]) {
verbose(env, "verifier bug. Frame %d already allocated\n",
state->curframe + 1);
return -EFAULT;
}
callee = kzalloc(sizeof(*callee), GFP_KERNEL);
if (!callee)
return -ENOMEM;
state->frame[state->curframe + 1] = callee;
/* callee cannot access r0, r6 - r9 for reading and has to write
* into its own stack before reading from it.
* callee can read/write into caller's stack
*/
init_func_state(env, callee,
/* remember the callsite, it will be used by bpf_exit */
*insn_idx /* callsite */,
state->curframe + 1 /* frameno within this callchain */,
subprog + 1 /* subprog number within this prog */);
/* copy r1 - r5 args that callee can access */
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
/* after the call regsiters r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, caller->regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* only increment it after check_reg_arg() finished */
state->curframe++;
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
if (env->log.level) {
verbose(env, "caller:\n");
print_verifier_state(env, caller);
verbose(env, "callee:\n");
print_verifier_state(env, callee);
}
return 0;
}
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
struct bpf_reg_state *r0;
callee = state->frame[state->curframe];
r0 = &callee->regs[BPF_REG_0];
if (r0->type == PTR_TO_STACK) {
/* technically it's ok to return caller's stack pointer
* (or caller's caller's pointer) back to the caller,
* since these pointers are valid. Only current stack
* pointer will be invalid as soon as function exits,
* but let's be conservative
*/
verbose(env, "cannot return stack pointer to the caller\n");
return -EINVAL;
}
state->curframe--;
caller = state->frame[state->curframe];
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
*insn_idx = callee->callsite + 1;
if (env->log.level) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee);
verbose(env, "to caller at %d:\n", *insn_idx);
print_verifier_state(env, caller);
}
/* clear everything in the callee */
free_func_state(callee);
state->frame[state->curframe + 1] = NULL;
return 0;
}
static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
const struct bpf_func_proto *fn = NULL;
struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
bool changes_data;
int i, err;
/* find function prototype */
if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
func_id);
return -EINVAL;
}
if (env->ops->get_func_proto)
fn = env->ops->get_func_proto(func_id);
if (!fn) {
verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
func_id);
return -EINVAL;
}
/* eBPF programs must be GPL compatible to use GPL-ed functions */
if (!env->prog->gpl_compatible && fn->gpl_only) {
verbose(env, "cannot call GPL only function from proprietary program\n");
return -EINVAL;
}
/* With LD_ABS/IND some JITs save/restore skb from r1. */
changes_data = bpf_helper_changes_pkt_data(fn->func);
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
func_id_name(func_id), func_id);
return -EINVAL;
}
memset(&meta, 0, sizeof(meta));
meta.pkt_access = fn->pkt_access;
err = check_func_proto(fn);
if (err) {
verbose(env, "kernel subsystem misconfigured func %s#%d\n",
func_id_name(func_id), func_id);
return err;
}
/* check args */
err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
if (err)
return err;
err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
if (err)
return err;
if (func_id == BPF_FUNC_tail_call) {
if (meta.map_ptr == NULL) {
verbose(env, "verifier bug\n");
return -EINVAL;
}
env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
}
err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
if (err)
return err;
err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
if (err)
return err;
err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
if (err)
return err;
/* Mark slots with STACK_MISC in case of raw mode, stack offset
* is inferred from register state.
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1);
if (err)
return err;
}
regs = cur_regs(env);
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* update return register (already marked as written above) */
if (fn->ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
struct bpf_insn_aux_data *insn_aux;
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].off = 0;
/* remember map_ptr, so that check_map_access()
* can check 'value_size' boundary of memory access
* to map element returned from bpf_map_lookup_elem()
*/
if (meta.map_ptr == NULL) {
verbose(env,
"kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
regs[BPF_REG_0].id = ++env->id_gen;
insn_aux = &env->insn_aux_data[insn_idx];
if (!insn_aux->map_ptr)
insn_aux->map_ptr = meta.map_ptr;
else if (insn_aux->map_ptr != meta.map_ptr)
insn_aux->map_ptr = BPF_MAP_PTR_POISON;
} else {
verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
return -EINVAL;
}
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
return err;
if (changes_data)
clear_all_pkt_pointers(env);
return 0;
}
static bool signed_add_overflows(s64 a, s64 b)
{
/* Do the add in u64, where overflow is well-defined */
s64 res = (s64)((u64)a + (u64)b);
if (b < 0)
return res > a;
return res < a;
}
static bool signed_sub_overflows(s64 a, s64 b)
{
/* Do the sub in u64, where overflow is well-defined */
s64 res = (s64)((u64)a - (u64)b);
if (b < 0)
return res < a;
return res > a;
}
static bool check_reg_sane_offset(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
enum bpf_reg_type type)
{
bool known = tnum_is_const(reg->var_off);
s64 val = reg->var_off.value;
s64 smin = reg->smin_value;
if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
verbose(env, "math between %s pointer and %lld is not allowed\n",
reg_type_str[type], val);
return false;
}
if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
verbose(env, "%s pointer offset %d is not allowed\n",
reg_type_str[type], reg->off);
return false;
}
if (smin == S64_MIN) {
verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
reg_type_str[type]);
return false;
}
if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
verbose(env, "value %lld makes %s pointer be out of bounds\n",
smin, reg_type_str[type]);
return false;
}
return true;
}
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
* If we return -EACCES, caller may want to try again treating pointer as a
* scalar. So we only emit a diagnostic if !env->allow_ptr_leaks.
*/
static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
const struct bpf_reg_state *off_reg)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs, *dst_reg;
bool known = tnum_is_const(off_reg->var_off);
s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
u8 opcode = BPF_OP(insn->code);
u32 dst = insn->dst_reg;
dst_reg = &regs[dst];
if ((known && (smin_val != smax_val || umin_val != umax_val)) ||
smin_val > smax_val || umin_val > umax_val) {
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
__mark_reg_unknown(dst_reg);
return 0;
}
if (BPF_CLASS(insn->code) != BPF_ALU64) {
/* 32-bit ALU ops on pointers produce (meaningless) scalars */
verbose(env,
"R%d 32-bit pointer arithmetic prohibited\n",
dst);
return -EACCES;
}
if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
dst);
return -EACCES;
}
if (ptr_reg->type == CONST_PTR_TO_MAP) {
verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
dst);
return -EACCES;
}
if (ptr_reg->type == PTR_TO_PACKET_END) {
verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
dst);
return -EACCES;
}
/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
* The id may be overwritten later if we create a new variable offset.
*/
dst_reg->type = ptr_reg->type;
dst_reg->id = ptr_reg->id;
if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
!check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
return -EINVAL;
switch (opcode) {
case BPF_ADD:
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
if (known && (ptr_reg->off + smin_val ==
(s64)(s32)(ptr_reg->off + smin_val))) {
/* pointer += K. Accumulate it into fixed offset */
dst_reg->smin_value = smin_ptr;
dst_reg->smax_value = smax_ptr;
dst_reg->umin_value = umin_ptr;
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->off = ptr_reg->off + smin_val;
dst_reg->range = ptr_reg->range;
break;
}
/* A new variable offset is created. Note that off_reg->off
* == 0, since it's a scalar.
* dst_reg gets the pointer type and since some positive
* integer value was added to the pointer, give it a new 'id'
* if it's a PTR_TO_PACKET.
* this creates a new 'base' pointer, off_reg (variable) gets
* added into the variable offset, and we copy the fixed offset
* from ptr_reg.
*/
if (signed_add_overflows(smin_ptr, smin_val) ||
signed_add_overflows(smax_ptr, smax_val)) {
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = smin_ptr + smin_val;
dst_reg->smax_value = smax_ptr + smax_val;
}
if (umin_ptr + umin_val < umin_ptr ||
umax_ptr + umax_val < umax_ptr) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value = umin_ptr + umin_val;
dst_reg->umax_value = umax_ptr + umax_val;
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
dst_reg->range = 0;
}
break;
case BPF_SUB:
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
dst);
return -EACCES;
}
/* We don't allow subtraction from FP, because (according to
* test_verifier.c test "invalid fp arithmetic", JITs might not
* be able to deal with it.
*/
if (ptr_reg->type == PTR_TO_STACK) {
verbose(env, "R%d subtraction from stack pointer prohibited\n",
dst);
return -EACCES;
}
if (known && (ptr_reg->off - smin_val ==
(s64)(s32)(ptr_reg->off - smin_val))) {
/* pointer -= K. Subtract it from fixed offset */
dst_reg->smin_value = smin_ptr;
dst_reg->smax_value = smax_ptr;
dst_reg->umin_value = umin_ptr;
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->id = ptr_reg->id;
dst_reg->off = ptr_reg->off - smin_val;
dst_reg->range = ptr_reg->range;
break;
}
/* A new variable offset is created. If the subtrahend is known
* nonnegative, then any reg->range we had before is still good.
*/
if (signed_sub_overflows(smin_ptr, smax_val) ||
signed_sub_overflows(smax_ptr, smin_val)) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = smin_ptr - smax_val;
dst_reg->smax_value = smax_ptr - smin_val;
}
if (umin_ptr < umax_val) {
/* Overflow possible, we know nothing */
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
/* Cannot overflow (as long as bounds are consistent) */
dst_reg->umin_value = umin_ptr - umax_val;
dst_reg->umax_value = umax_ptr - umin_val;
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
dst_reg->range = 0;
}
break;
case BPF_AND:
case BPF_OR:
case BPF_XOR:
/* bitwise ops on pointers are troublesome, prohibit. */
verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
default:
/* other operators (e.g. MUL,LSH) produce non-pointer results */
verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
}
if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
return -EINVAL;
__update_reg_bounds(dst_reg);
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
return 0;
}
/* WARNING: This function does calculations on 64-bit values, but the actual
* execution may occur on 32-bit values. Therefore, things like bitshifts
* need extra checks in the 32-bit case.
*/
static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn,
struct bpf_reg_state *dst_reg,
struct bpf_reg_state src_reg)
{
struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
bool src_known, dst_known;
s64 smin_val, smax_val;
u64 umin_val, umax_val;
u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
umin_val = src_reg.umin_value;
umax_val = src_reg.umax_value;
src_known = tnum_is_const(src_reg.var_off);
dst_known = tnum_is_const(dst_reg->var_off);
if ((src_known && (smin_val != smax_val || umin_val != umax_val)) ||
smin_val > smax_val || umin_val > umax_val) {
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
__mark_reg_unknown(dst_reg);
return 0;
}
if (!src_known &&
opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
__mark_reg_unknown(dst_reg);
return 0;
}
switch (opcode) {
case BPF_ADD:
if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
signed_add_overflows(dst_reg->smax_value, smax_val)) {
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value += smin_val;
dst_reg->smax_value += smax_val;
}
if (dst_reg->umin_value + umin_val < umin_val ||
dst_reg->umax_value + umax_val < umax_val) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value += umin_val;
dst_reg->umax_value += umax_val;
}
dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
break;
case BPF_SUB:
if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
signed_sub_overflows(dst_reg->smax_value, smin_val)) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value -= smax_val;
dst_reg->smax_value -= smin_val;
}
if (dst_reg->umin_value < umax_val) {
/* Overflow possible, we know nothing */
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
/* Cannot overflow (as long as bounds are consistent) */
dst_reg->umin_value -= umax_val;
dst_reg->umax_value -= umin_val;
}
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
break;
case BPF_MUL:
dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
if (smin_val < 0 || dst_reg->smin_value < 0) {
/* Ain't nobody got time to multiply that sign */
__mark_reg_unbounded(dst_reg);
__update_reg_bounds(dst_reg);
break;
}
/* Both values are positive, so we can work with unsigned and
* copy the result to signed (unless it exceeds S64_MAX).
*/
if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
/* Potential overflow, we know nothing */
__mark_reg_unbounded(dst_reg);
/* (except what we can learn from the var_off) */
__update_reg_bounds(dst_reg);
break;
}
dst_reg->umin_value *= umin_val;
dst_reg->umax_value *= umax_val;
if (dst_reg->umax_value > S64_MAX) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
break;
case BPF_AND:
if (src_known && dst_known) {
__mark_reg_known(dst_reg, dst_reg->var_off.value &
src_reg.var_off.value);
break;
}
/* We get our minimum from the var_off, since that's inherently
* bitwise. Our maximum is the minimum of the operands' maxima.
*/
dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
dst_reg->umin_value = dst_reg->var_off.value;
dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
if (dst_reg->smin_value < 0 || smin_val < 0) {
/* Lose signed bounds when ANDing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
/* ANDing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
case BPF_OR:
if (src_known && dst_known) {
__mark_reg_known(dst_reg, dst_reg->var_off.value |
src_reg.var_off.value);
break;
}
/* We get our maximum from the var_off, and our minimum is the
* maximum of the operands' minima
*/
dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
dst_reg->umax_value = dst_reg->var_off.value |
dst_reg->var_off.mask;
if (dst_reg->smin_value < 0 || smin_val < 0) {
/* Lose signed bounds when ORing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
case BPF_LSH:
if (umax_val >= insn_bitness) {
/* Shifts greater than 31 or 63 are undefined.
* This includes shifts by a negative number.
*/
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
/* We lose all sign bit information (except what we can pick
* up from var_off)
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
/* If we might shift our top bit out, then we know nothing */
if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value <<= umin_val;
dst_reg->umax_value <<= umax_val;
}
if (src_known)
dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
else
dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val);
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
case BPF_RSH:
if (umax_val >= insn_bitness) {
/* Shifts greater than 31 or 63 are undefined.
* This includes shifts by a negative number.
*/
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
/* BPF_RSH is an unsigned shift. If the value in dst_reg might
* be negative, then either:
* 1) src_reg might be zero, so the sign bit of the result is
* unknown, so we lose our signed bounds
* 2) it's known negative, thus the unsigned bounds capture the
* signed bounds
* 3) the signed bounds cross zero, so they tell us nothing
* about the result
* If the value in dst_reg is known nonnegative, then again the
* unsigned bounts capture the signed bounds.
* Thus, in all cases it suffices to blow away our signed bounds
* and rely on inferring new ones from the unsigned bounds and
* var_off of the result.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
if (src_known)
dst_reg->var_off = tnum_rshift(dst_reg->var_off,
umin_val);
else
dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val);
dst_reg->umin_value >>= umax_val;
dst_reg->umax_value >>= umin_val;
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
default:
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
if (BPF_CLASS(insn->code) != BPF_ALU64) {
/* 32-bit ALU ops are (32,32)->32 */
coerce_reg_to_size(dst_reg, 4);
coerce_reg_to_size(&src_reg, 4);
}
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
return 0;
}
/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max
* and var_off.
*/
static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
u8 opcode = BPF_OP(insn->code);
dst_reg = &regs[insn->dst_reg];
src_reg = NULL;
if (dst_reg->type != SCALAR_VALUE)
ptr_reg = dst_reg;
if (BPF_SRC(insn->code) == BPF_X) {
src_reg = &regs[insn->src_reg];
if (src_reg->type != SCALAR_VALUE) {
if (dst_reg->type != SCALAR_VALUE) {
/* Combining two pointers by any ALU op yields
* an arbitrary scalar. Disallow all math except
* pointer subtraction
*/
if (opcode == BPF_SUB){
mark_reg_unknown(env, regs, insn->dst_reg);
return 0;
}
verbose(env, "R%d pointer %s pointer prohibited\n",
insn->dst_reg,
bpf_alu_string[opcode >> 4]);
return -EACCES;
} else {
/* scalar += pointer
* This is legal, but we have to reverse our
* src/dest handling in computing the range
*/
return adjust_ptr_min_max_vals(env, insn,
src_reg, dst_reg);
}
} else if (ptr_reg) {
/* pointer += scalar */
return adjust_ptr_min_max_vals(env, insn,
dst_reg, src_reg);
}
} else {
/* Pretend the src is a reg with a known value, since we only
* need to be able to read from this state.
*/
off_reg.type = SCALAR_VALUE;
__mark_reg_known(&off_reg, insn->imm);
src_reg = &off_reg;
if (ptr_reg) /* pointer += K */
return adjust_ptr_min_max_vals(env, insn,
ptr_reg, src_reg);
}
/* Got here implies adding two SCALAR_VALUEs */
if (WARN_ON_ONCE(ptr_reg)) {
print_verifier_state(env, state);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
return -EINVAL;
}
if (WARN_ON(!src_reg)) {
print_verifier_state(env, state);
verbose(env, "verifier internal error: no src_reg\n");
return -EINVAL;
}
return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
}
/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
int err;
if (opcode == BPF_END || opcode == BPF_NEG) {
if (opcode == BPF_NEG) {
if (BPF_SRC(insn->code) != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->off != 0 || insn->imm != 0) {
verbose(env, "BPF_NEG uses reserved fields\n");
return -EINVAL;
}
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
BPF_CLASS(insn->code) == BPF_ALU64) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
}
/* check src operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->dst_reg)) {
verbose(env, "R%d pointer arithmetic prohibited\n",
insn->dst_reg);
return -EACCES;
}
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP);
if (err)
return err;
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
}
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP);
if (err)
return err;
if (BPF_SRC(insn->code) == BPF_X) {
if (BPF_CLASS(insn->code) == BPF_ALU64) {
/* case: R1 = R2
* copy register state to dest reg
*/
regs[insn->dst_reg] = regs[insn->src_reg];
regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
verbose(env,
"R%d partial copy of pointer\n",
insn->src_reg);
return -EACCES;
}
mark_reg_unknown(env, regs, insn->dst_reg);
coerce_reg_to_size(&regs[insn->dst_reg], 4);
}
} else {
/* case: R = imm
* remember the value we stored into this reg
*/
regs[insn->dst_reg].type = SCALAR_VALUE;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
__mark_reg_known(regs + insn->dst_reg,
insn->imm);
} else {
__mark_reg_known(regs + insn->dst_reg,
(u32)insn->imm);
}
}
} else if (opcode > BPF_END) {
verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
return -EINVAL;
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
}
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
verbose(env, "div by zero\n");
return -EINVAL;
}
if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
return -EINVAL;
}
if ((opcode == BPF_LSH || opcode == BPF_RSH ||
opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
if (insn->imm < 0 || insn->imm >= size) {
verbose(env, "invalid shift %d\n", insn->imm);
return -EINVAL;
}
}
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
return adjust_reg_min_max_vals(env, insn);
}
return 0;
}
static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
struct bpf_reg_state *dst_reg,
enum bpf_reg_type type,
bool range_right_open)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs, *reg;
u16 new_range;
int i, j;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
/* This doesn't give us any range */
return;
if (dst_reg->umax_value > MAX_PACKET_OFF ||
dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF)
/* Risk of overflow. For instance, ptr + (1<<63) may be less
* than pkt_end, but that's because it's also less than pkt.
*/
return;
new_range = dst_reg->off;
if (range_right_open)
new_range--;
/* Examples for register markings:
*
* pkt_data in dst register:
*
* r2 = r3;
* r2 += 8;
* if (r2 > pkt_end) goto <handle exception>
* <access okay>
*
* r2 = r3;
* r2 += 8;
* if (r2 < pkt_end) goto <access okay>
* <handle exception>
*
* Where:
* r2 == dst_reg, pkt_end == src_reg
* r2=pkt(id=n,off=8,r=0)
* r3=pkt(id=n,off=0,r=0)
*
* pkt_data in src register:
*
* r2 = r3;
* r2 += 8;
* if (pkt_end >= r2) goto <access okay>
* <handle exception>
*
* r2 = r3;
* r2 += 8;
* if (pkt_end <= r2) goto <handle exception>
* <access okay>
*
* Where:
* pkt_end == dst_reg, r2 == src_reg
* r2=pkt(id=n,off=8,r=0)
* r3=pkt(id=n,off=0,r=0)
*
* Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
* or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
* and [r3, r3 + 8-1) respectively is safe to access depending on
* the check.
*/
/* If our ids match, then we must have the same max_value. And we
* don't care about the other reg's fixed offset, since if it's too big
* the range won't allow anything.
* dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
*/
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].type == type && regs[i].id == dst_reg->id)
/* keep the maximum range already checked */
regs[i].range = max(regs[i].range, new_range);
for (j = 0; j <= vstate->curframe; j++) {
state = vstate->frame[j];
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
reg = &state->stack[i].spilled_ptr;
if (reg->type == type && reg->id == dst_reg->id)
reg->range = max(reg->range, new_range);
}
}
}
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
* In JEQ/JNE cases we also adjust the var_off values.
*/
static void reg_set_min_max(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg, u64 val,
u8 opcode)
{
/* If the dst_reg is a pointer, we can't learn anything about its
* variable offset from the compare (unless src_reg were a pointer into
* the same object, but we don't bother with that.
* Since false_reg and true_reg have the same type by construction, we
* only need to check one of them for pointerness.
*/
if (__is_pointer_value(false, false_reg))
return;
switch (opcode) {
case BPF_JEQ:
/* If this is false then we know nothing Jon Snow, but if it is
* true then we know for sure.
*/
__mark_reg_known(true_reg, val);
break;
case BPF_JNE:
/* If this is true we know nothing Jon Snow, but if it is false
* we know the value for sure;
*/
__mark_reg_known(false_reg, val);
break;
case BPF_JGT:
false_reg->umax_value = min(false_reg->umax_value, val);
true_reg->umin_value = max(true_reg->umin_value, val + 1);
break;
case BPF_JSGT:
false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
break;
case BPF_JLT:
false_reg->umin_value = max(false_reg->umin_value, val);
true_reg->umax_value = min(true_reg->umax_value, val - 1);
break;
case BPF_JSLT:
false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
break;
case BPF_JGE:
false_reg->umax_value = min(false_reg->umax_value, val - 1);
true_reg->umin_value = max(true_reg->umin_value, val);
break;
case BPF_JSGE:
false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
break;
case BPF_JLE:
false_reg->umin_value = max(false_reg->umin_value, val + 1);
true_reg->umax_value = min(true_reg->umax_value, val);
break;
case BPF_JSLE:
false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
break;
default:
break;
}
__reg_deduce_bounds(false_reg);
__reg_deduce_bounds(true_reg);
/* We might have learned some bits from the bounds. */
__reg_bound_offset(false_reg);
__reg_bound_offset(true_reg);
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__update_reg_bounds(false_reg);
__update_reg_bounds(true_reg);
}
/* Same as above, but for the case that dst_reg holds a constant and src_reg is
* the variable reg.
*/
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg, u64 val,
u8 opcode)
{
if (__is_pointer_value(false, false_reg))
return;
switch (opcode) {
case BPF_JEQ:
/* If this is false then we know nothing Jon Snow, but if it is
* true then we know for sure.
*/
__mark_reg_known(true_reg, val);
break;
case BPF_JNE:
/* If this is true we know nothing Jon Snow, but if it is false
* we know the value for sure;
*/
__mark_reg_known(false_reg, val);
break;
case BPF_JGT:
true_reg->umax_value = min(true_reg->umax_value, val - 1);
false_reg->umin_value = max(false_reg->umin_value, val);
break;
case BPF_JSGT:
true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
break;
case BPF_JLT:
true_reg->umin_value = max(true_reg->umin_value, val + 1);
false_reg->umax_value = min(false_reg->umax_value, val);
break;
case BPF_JSLT:
true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
break;
case BPF_JGE:
true_reg->umax_value = min(true_reg->umax_value, val);
false_reg->umin_value = max(false_reg->umin_value, val + 1);
break;
case BPF_JSGE:
true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
break;
case BPF_JLE:
true_reg->umin_value = max(true_reg->umin_value, val);
false_reg->umax_value = min(false_reg->umax_value, val - 1);
break;
case BPF_JSLE:
true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
break;
default:
break;
}
__reg_deduce_bounds(false_reg);
__reg_deduce_bounds(true_reg);
/* We might have learned some bits from the bounds. */
__reg_bound_offset(false_reg);
__reg_bound_offset(true_reg);
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__update_reg_bounds(false_reg);
__update_reg_bounds(true_reg);
}
/* Regs are known to be equal, so intersect their min/max/var_off */
static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
struct bpf_reg_state *dst_reg)
{
src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
dst_reg->umin_value);
src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
dst_reg->umax_value);
src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
dst_reg->smin_value);
src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
dst_reg->smax_value);
src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
dst_reg->var_off);
/* We might have learned new bounds from the var_off. */
__update_reg_bounds(src_reg);
__update_reg_bounds(dst_reg);
/* We might have learned something about the sign bit. */
__reg_deduce_bounds(src_reg);
__reg_deduce_bounds(dst_reg);
/* We might have learned some bits from the bounds. */
__reg_bound_offset(src_reg);
__reg_bound_offset(dst_reg);
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__update_reg_bounds(src_reg);
__update_reg_bounds(dst_reg);
}
static void reg_combine_min_max(struct bpf_reg_state *true_src,
struct bpf_reg_state *true_dst,
struct bpf_reg_state *false_src,
struct bpf_reg_state *false_dst,
u8 opcode)
{
switch (opcode) {
case BPF_JEQ:
__reg_combine_min_max(true_src, true_dst);
break;
case BPF_JNE:
__reg_combine_min_max(false_src, false_dst);
break;
}
}
static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
bool is_null)
{
struct bpf_reg_state *reg = &regs[regno];
if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
* arithmetic on pointers that might be NULL.
*/
if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
!tnum_equals_const(reg->var_off, 0) ||
reg->off)) {
__mark_reg_known_zero(reg);
reg->off = 0;
}
if (is_null) {
reg->type = SCALAR_VALUE;
} else if (reg->map_ptr->inner_map_meta) {
reg->type = CONST_PTR_TO_MAP;
reg->map_ptr = reg->map_ptr->inner_map_meta;
} else {
reg->type = PTR_TO_MAP_VALUE;
}
/* We don't need id from this point onwards anymore, thus we
* should better reset it, so that state pruning has chances
* to take effect.
*/
reg->id = 0;
}
}
/* The logic is similar to find_good_pkt_pointers(), both could eventually
* be folded together at some point.
*/
static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno,
bool is_null)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs;
u32 id = regs[regno].id;
int i, j;
for (i = 0; i < MAX_BPF_REG; i++)
mark_map_reg(regs, i, id, is_null);
for (j = 0; j <= vstate->curframe; j++) {
state = vstate->frame[j];
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
}
}
}
static bool try_match_pkt_pointers(const struct bpf_insn *insn,
struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg,
struct bpf_verifier_state *this_branch,
struct bpf_verifier_state *other_branch)
{
if (BPF_SRC(insn->code) != BPF_X)
return false;
switch (BPF_OP(insn->code)) {
case BPF_JGT:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end > pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, true);
} else {
return false;
}
break;
case BPF_JLT:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end < pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, false);
} else {
return false;
}
break;
case BPF_JGE:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, false);
} else {
return false;
}
break;
case BPF_JLE:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, true);
} else {
return false;
}
break;
default:
return false;
}
return true;
}
static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
struct bpf_verifier_state *this_branch = env->cur_state;
struct bpf_verifier_state *other_branch;
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs;
u8 opcode = BPF_OP(insn->code);
int err;
if (opcode > BPF_JSLE) {
verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
return -EINVAL;
}
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
verbose(env, "BPF_JMP uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
} else {
if (insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_JMP uses reserved fields\n");
return -EINVAL;
}
}
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
dst_reg = &regs[insn->dst_reg];
/* detect if R == 0 where R was initialized to zero earlier */
if (BPF_SRC(insn->code) == BPF_K &&
(opcode == BPF_JEQ || opcode == BPF_JNE) &&
dst_reg->type == SCALAR_VALUE &&
tnum_is_const(dst_reg->var_off)) {
if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) ||
(opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) {
/* if (imm == imm) goto pc+off;
* only follow the goto, ignore fall-through
*/
*insn_idx += insn->off;
return 0;
} else {
/* if (imm != imm) goto pc+off;
* only follow fall-through branch, since
* that's where the program will go
*/
return 0;
}
}
other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
if (!other_branch)
return -EFAULT;
other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
/* detect if we are comparing against a constant value so we can adjust
* our min/max values for our dst register.
* this is only legit if both are scalars (or pointers to the same
* object, I suppose, but we don't support that right now), because
* otherwise the different base pointers mean the offsets aren't
* comparable.
*/
if (BPF_SRC(insn->code) == BPF_X) {
if (dst_reg->type == SCALAR_VALUE &&
regs[insn->src_reg].type == SCALAR_VALUE) {
if (tnum_is_const(regs[insn->src_reg].var_off))
reg_set_min_max(&other_branch_regs[insn->dst_reg],
dst_reg, regs[insn->src_reg].var_off.value,
opcode);
else if (tnum_is_const(dst_reg->var_off))
reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
&regs[insn->src_reg],
dst_reg->var_off.value, opcode);
else if (opcode == BPF_JEQ || opcode == BPF_JNE)
/* Comparing for equality, we can combine knowledge */
reg_combine_min_max(&other_branch_regs[insn->src_reg],
&other_branch_regs[insn->dst_reg],
&regs[insn->src_reg],
&regs[insn->dst_reg], opcode);
}
} else if (dst_reg->type == SCALAR_VALUE) {
reg_set_min_max(&other_branch_regs[insn->dst_reg],
dst_reg, insn->imm, opcode);
}
/* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
if (BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
/* Mark all identical map registers in each branch as either
* safe or unknown depending R == 0 or R != 0 conditional.
*/
mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
} else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
this_branch, other_branch) &&
is_pointer_value(env, insn->dst_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->dst_reg);
return -EACCES;
}
if (env->log.level)
print_verifier_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
/* return the map pointer stored inside BPF_LD_IMM64 instruction */
static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
{
u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
return (struct bpf_map *) (unsigned long) imm64;
}
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
verbose(env, "invalid BPF_LD_IMM insn\n");
return -EINVAL;
}
if (insn->off != 0) {
verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
return -EINVAL;
}
err = check_reg_arg(env, insn->dst_reg, DST_OP);
if (err)
return err;
if (insn->src_reg == 0) {
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
regs[insn->dst_reg].type = SCALAR_VALUE;
__mark_reg_known(&regs[insn->dst_reg], imm);
return 0;
}
/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
return 0;
}
static bool may_access_skb(enum bpf_prog_type type)
{
switch (type) {
case BPF_PROG_TYPE_SOCKET_FILTER:
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
return true;
default:
return false;
}
}
/* verify safety of LD_ABS|LD_IND instructions:
* - they can only appear in the programs where ctx == skb
* - since they are wrappers of function calls, they scratch R1-R5 registers,
* preserve R6-R9, and store return value into R0
*
* Implicit input:
* ctx == skb == R6 == CTX
*
* Explicit input:
* SRC == any register
* IMM == 32-bit immediate
*
* Output:
* R0 - 8/16/32-bit skb data converted to cpu endianness
*/
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
u8 mode = BPF_MODE(insn->code);
int i, err;
if (!may_access_skb(env->prog->type)) {
verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
return -EINVAL;
}
if (env->subprog_cnt) {
/* when program has LD_ABS insn JITs and interpreter assume
* that r1 == ctx == skb which is not the case for callees
* that can have arbitrary arguments. It's problematic
* for main prog as well since JITs would need to analyze
* all functions in order to make proper register save/restore
* decisions in the main prog. Hence disallow LD_ABS with calls
*/
verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
return -EINVAL;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
BPF_SIZE(insn->code) == BPF_DW ||
(mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
return -EINVAL;
}
/* check whether implicit source operand (register R6) is readable */
err = check_reg_arg(env, BPF_REG_6, SRC_OP);
if (err)
return err;
if (regs[BPF_REG_6].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
}
if (mode == BPF_IND) {
/* check explicit source operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
}
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* mark destination R0 register as readable, since it contains
* the value fetched from the packet.
* Already marked as written above.
*/
mark_reg_unknown(env, regs, BPF_REG_0);
return 0;
}
static int check_return_code(struct bpf_verifier_env *env)
{
struct bpf_reg_state *reg;
struct tnum range = tnum_range(0, 1);
switch (env->prog->type) {
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
break;
default:
return 0;
}
reg = cur_regs(env) + BPF_REG_0;
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
reg_type_str[reg->type]);
return -EINVAL;
}
if (!tnum_in(range, reg->var_off)) {
verbose(env, "At program exit the register R0 ");
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "has value %s", tn_buf);
} else {
verbose(env, "has unknown scalar value");
}
verbose(env, " should have been 0 or 1\n");
return -EINVAL;
}
return 0;
}
/* non-recursive DFS pseudo code
* 1 procedure DFS-iterative(G,v):
* 2 label v as discovered
* 3 let S be a stack
* 4 S.push(v)
* 5 while S is not empty
* 6 t <- S.pop()
* 7 if t is what we're looking for:
* 8 return t
* 9 for all edges e in G.adjacentEdges(t) do
* 10 if edge e is already labelled
* 11 continue with the next edge
* 12 w <- G.adjacentVertex(t,e)
* 13 if vertex w is not discovered and not explored
* 14 label e as tree-edge
* 15 label w as discovered
* 16 S.push(w)
* 17 continue at 5
* 18 else if vertex w is discovered
* 19 label e as back-edge
* 20 else
* 21 // vertex w is explored
* 22 label e as forward- or cross-edge
* 23 label t as explored
* 24 S.pop()
*
* convention:
* 0x10 - discovered
* 0x11 - discovered and fall-through edge labelled
* 0x12 - discovered and fall-through and branch edges labelled
* 0x20 - explored
*/
enum {
DISCOVERED = 0x10,
EXPLORED = 0x20,
FALLTHROUGH = 1,
BRANCH = 2,
};
#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
static int *insn_stack; /* stack of insns to process */
static int cur_stack; /* current stack index */
static int *insn_state;
/* t, w, e - match pseudo-code above:
* t - index of current instruction
* w - next instruction
* e - edge
*/
static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
return 0;
if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
return 0;
if (w < 0 || w >= env->prog->len) {
verbose(env, "jump out of range from insn %d to %d\n", t, w);
return -EINVAL;
}
if (e == BRANCH)
/* mark branch target for state pruning */
env->explored_states[w] = STATE_LIST_MARK;
if (insn_state[w] == 0) {
/* tree-edge */
insn_state[t] = DISCOVERED | e;
insn_state[w] = DISCOVERED;
if (cur_stack >= env->prog->len)
return -E2BIG;
insn_stack[cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
verbose(env, "back-edge from insn %d to %d\n", t, w);
return -EINVAL;
} else if (insn_state[w] == EXPLORED) {
/* forward- or cross-edge */
insn_state[t] = DISCOVERED | e;
} else {
verbose(env, "insn state internal bug\n");
return -EFAULT;
}
return 0;
}
/* non-recursive depth-first-search to detect loops in BPF program
* loop == back-edge in directed graph
*/
static int check_cfg(struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi;
int insn_cnt = env->prog->len;
int ret = 0;
int i, t;
ret = check_subprogs(env);
if (ret < 0)
return ret;
insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_stack) {
kfree(insn_state);
return -ENOMEM;
}
insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
insn_stack[0] = 0; /* 0 is the first instruction */
cur_stack = 1;
peek_stack:
if (cur_stack == 0)
goto check_state;
t = insn_stack[cur_stack - 1];
if (BPF_CLASS(insns[t].code) == BPF_JMP) {
u8 opcode = BPF_OP(insns[t].code);
if (opcode == BPF_EXIT) {
goto mark_explored;
} else if (opcode == BPF_CALL) {
ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
if (t + 1 < insn_cnt)
env->explored_states[t + 1] = STATE_LIST_MARK;
if (insns[t].src_reg == BPF_PSEUDO_CALL) {
env->explored_states[t] = STATE_LIST_MARK;
ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
}
} else if (opcode == BPF_JA) {
if (BPF_SRC(insns[t].code) != BPF_K) {
ret = -EINVAL;
goto err_free;
}
/* unconditional jump with single edge */
ret = push_insn(t, t + insns[t].off + 1,
FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
/* tell verifier to check for equivalent states
* after every call and jump
*/
if (t + 1 < insn_cnt)
env->explored_states[t + 1] = STATE_LIST_MARK;
} else {
/* conditional jump with two edges */
env->explored_states[t] = STATE_LIST_MARK;
ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
}
} else {
/* all other non-branch instructions with single
* fall-through edge
*/
ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
}
mark_explored:
insn_state[t] = EXPLORED;
if (cur_stack-- <= 0) {
verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
}
goto peek_stack;
check_state:
for (i = 0; i < insn_cnt; i++) {
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
}
ret = 0; /* cfg looks good */
err_free:
kfree(insn_state);
kfree(insn_stack);
return ret;
}
/* check %cur's range satisfies %old's */
static bool range_within(struct bpf_reg_state *old,
struct bpf_reg_state *cur)
{
return old->umin_value <= cur->umin_value &&
old->umax_value >= cur->umax_value &&
old->smin_value <= cur->smin_value &&
old->smax_value >= cur->smax_value;
}
/* Maximum number of register states that can exist at once */
#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
struct idpair {
u32 old;
u32 cur;
};
/* If in the old state two registers had the same id, then they need to have
* the same id in the new state as well. But that id could be different from
* the old state, so we need to track the mapping from old to new ids.
* Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent
* regs with old id 5 must also have new id 9 for the new state to be safe. But
* regs with a different old id could still have new id 9, we don't care about
* that.
* So we look through our idmap to see if this old id has been seen before. If
* so, we require the new id to match; otherwise, we add the id pair to the map.
*/
static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
{
unsigned int i;
for (i = 0; i < ID_MAP_SIZE; i++) {
if (!idmap[i].old) {
/* Reached an empty slot; haven't seen this id before */
idmap[i].old = old_id;
idmap[i].cur = cur_id;
return true;
}
if (idmap[i].old == old_id)
return idmap[i].cur == cur_id;
}
/* We ran out of idmap slots, which should be impossible */
WARN_ON_ONCE(1);
return false;
}
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
struct idpair *idmap)
{
bool equal;
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
return true;
equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0;
if (rold->type == PTR_TO_STACK)
/* two stack pointers are equal only if they're pointing to
* the same stack frame, since fp-8 in foo != fp-8 in bar
*/
return equal && rold->frameno == rcur->frameno;
if (equal)
return true;
if (rold->type == NOT_INIT)
/* explored state can't have used this */
return true;
if (rcur->type == NOT_INIT)
return false;
switch (rold->type) {
case SCALAR_VALUE:
if (rcur->type == SCALAR_VALUE) {
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
} else {
/* We're trying to use a pointer in place of a scalar.
* Even if the scalar was unbounded, this could lead to
* pointer leaks because scalars are allowed to leak
* while pointers are not. We could make this safe in
* special cases if root is calling us, but it's
* probably not worth the hassle.
*/
return false;
}
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
* We don't care about the 'id' value, because nothing
* uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
*/
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
case PTR_TO_MAP_VALUE_OR_NULL:
/* a PTR_TO_MAP_VALUE could be safe to use as a
* PTR_TO_MAP_VALUE_OR_NULL into the same map.
* However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
* checked, doing so could have affected others with the same
* id, and we can't check for that because we lost the id when
* we converted to a PTR_TO_MAP_VALUE.
*/
if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
return false;
if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
return false;
/* Check our ids match any regs they're supposed to */
return check_ids(rold->id, rcur->id, idmap);
case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
if (rcur->type != rold->type)
return false;
/* We must have at least as much range as the old ptr
* did, so that any accesses which were safe before are
* still safe. This is true even if old range < old off,
* since someone could have accessed through (ptr - k), or
* even done ptr -= k in a register, to get a safe access.
*/
if (rold->range > rcur->range)
return false;
/* If the offsets don't match, we can't trust our alignment;
* nor can we be sure that we won't fall out of range.
*/
if (rold->off != rcur->off)
return false;
/* id relations must be preserved */
if (rold->id && !check_ids(rold->id, rcur->id, idmap))
return false;
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
case PTR_TO_CTX:
case CONST_PTR_TO_MAP:
case PTR_TO_PACKET_END:
/* Only valid matches are exact, which memcmp() above
* would have accepted
*/
default:
/* Don't know what's going on, just say it's not safe */
return false;
}
/* Shouldn't get here; if we do, say it's not safe */
WARN_ON_ONCE(1);
return false;
}
static bool stacksafe(struct bpf_func_state *old,
struct bpf_func_state *cur,
struct idpair *idmap)
{
int i, spi;
/* if explored stack has more populated slots than current stack
* such stacks are not equivalent
*/
if (old->allocated_stack > cur->allocated_stack)
return false;
/* walk slots of the explored stack and ignore any additional
* slots in the current stack, since explored(safe) state
* didn't use them
*/
for (i = 0; i < old->allocated_stack; i++) {
spi = i / BPF_REG_SIZE;
if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
/* explored state didn't use this */
continue;
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
continue;
/* if old state was safe with misc data in the stack
* it will be safe with zero-initialized stack.
* The opposite is not true
*/
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC &&
cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO)
continue;
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
cur->stack[spi].slot_type[i % BPF_REG_SIZE])
/* Ex: old explored (safe) state has STACK_SPILL in
* this stack slot, but current has has STACK_MISC ->
* this verifier states are not equivalent,
* return false to continue verification of this path
*/
return false;
if (i % BPF_REG_SIZE)
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
if (!regsafe(&old->stack[spi].spilled_ptr,
&cur->stack[spi].spilled_ptr,
idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
* Ex: explored safe path could have stored
* (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
* but current path has stored:
* (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
* such verifier states are not equivalent.
* return false to continue verification of this path
*/
return false;
}
return true;
}
/* compare two verifier states
*
* all states stored in state_list are known to be valid, since
* verifier reached 'bpf_exit' instruction through them
*
* this function is called when verifier exploring different branches of
* execution popped from the state stack. If it sees an old state that has
* more strict register state and more strict stack state then this execution
* branch doesn't need to be explored further, since verifier already
* concluded that more strict state leads to valid finish.
*
* Therefore two states are equivalent if register state is more conservative
* and explored stack state is more conservative than the current one.
* Example:
* explored current
* (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
* (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
*
* In other words if current stack state (one being explored) has more
* valid slots than old one that already passed validation, it means
* the verifier can stop exploring and conclude that current state is valid too
*
* Similarly with registers. If explored state has register type as invalid
* whereas register type in current state is meaningful, it means that
* the current state will reach 'bpf_exit' instruction safely
*/
static bool func_states_equal(struct bpf_func_state *old,
struct bpf_func_state *cur)
{
struct idpair *idmap;
bool ret = false;
int i;
idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL);
/* If we failed to allocate the idmap, just say it's not safe */
if (!idmap)
return false;
for (i = 0; i < MAX_BPF_REG; i++) {
if (!regsafe(&old->regs[i], &cur->regs[i], idmap))
goto out_free;
}
if (!stacksafe(old, cur, idmap))
goto out_free;
ret = true;
out_free:
kfree(idmap);
return ret;
}
static bool states_equal(struct bpf_verifier_env *env,
struct bpf_verifier_state *old,
struct bpf_verifier_state *cur)
{
int i;
if (old->curframe != cur->curframe)
return false;
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
for (i = 0; i <= old->curframe; i++) {
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
if (!func_states_equal(old->frame[i], cur->frame[i]))
return false;
}
return true;
}
/* A write screens off any subsequent reads; but write marks come from the
* straight-line code between a state and its parent. When we arrive at an
* equivalent state (jump target or such) we didn't arrive by the straight-line
* code, so read marks in the state must propagate to the parent regardless
* of the state's write marks. That's what 'parent == state->parent' comparison
* in mark_reg_read() and mark_stack_slot_read() is for.
*/
static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
struct bpf_verifier_state *vparent)
{
int i, frame, err = 0;
struct bpf_func_state *state, *parent;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
vparent->curframe, vstate->curframe);
return -EFAULT;
}
/* Propagate read liveness of registers... */
BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
/* We don't need to worry about FP liveness because it's read-only */
for (i = 0; i < BPF_REG_FP; i++) {
if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
continue;
if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
err = mark_reg_read(env, vstate, vparent, i);
if (err)
return err;
}
}
/* ... and stack slots */
for (frame = 0; frame <= vstate->curframe; frame++) {
state = vstate->frame[frame];
parent = vparent->frame[frame];
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
i < parent->allocated_stack / BPF_REG_SIZE; i++) {
if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
continue;
if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
mark_stack_slot_read(env, vstate, vparent, i, frame);
}
}
return err;
}
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl;
struct bpf_verifier_state *cur = env->cur_state;
int i, j, err;
sl = env->explored_states[insn_idx];
if (!sl)
/* this 'insn_idx' instruction wasn't marked, so we will not
* be doing state search here
*/
return 0;
while (sl != STATE_LIST_MARK) {
if (states_equal(env, &sl->state, cur)) {
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
* If we have any write marks in env->cur_state, they
* will prevent corresponding reads in the continuation
* from reaching our parent (an explored_state). Our
* own state will get the read marks recorded, but
* they'll be immediately forgotten as we're pruning
* this state and will pop a new one.
*/
err = propagate_liveness(env, &sl->state, cur);
if (err)
return err;
return 1;
}
sl = sl->next;
}
/* there were no equivalent states, remember current one.
* technically the current state is not proven to be safe yet,
* but it will either reach outer most bpf_exit (which means it's safe)
* or it will be rejected. Since there are no loops, we won't be
* seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
* again on the way to bpf_exit
*/
new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
/* add new state to the head of linked list */
err = copy_verifier_state(&new_sl->state, cur);
if (err) {
free_verifier_state(&new_sl->state, false);
kfree(new_sl);
return err;
}
new_sl->next = env->explored_states[insn_idx];
env->explored_states[insn_idx] = new_sl;
/* connect new state to parentage chain */
cur->parent = &new_sl->state;
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
* their parent and current state never has children yet. Only
* explored_states can get read marks.)
*/
for (i = 0; i < BPF_REG_FP; i++)
cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;
/* all stack frames are accessible from callee, clear them all */
for (j = 0; j <= cur->curframe; j++) {
struct bpf_func_state *frame = cur->frame[j];
for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++)
frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
}
return 0;
}
static int do_check(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
int insn_cnt = env->prog->len, i;
int insn_idx, prev_insn_idx = 0;
int insn_processed = 0;
bool do_print_state = false;
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->parent = NULL;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
}
env->cur_state = state;
init_func_state(env, state->frame[0],
BPF_MAIN_FUNC /* callsite */,
0 /* frameno */,
0 /* subprogno, zero == main subprog */);
insn_idx = 0;
for (;;) {
struct bpf_insn *insn;
u8 class;
int err;
if (insn_idx >= insn_cnt) {
verbose(env, "invalid insn idx %d insn_cnt %d\n",
insn_idx, insn_cnt);
return -EFAULT;
}
insn = &insns[insn_idx];
class = BPF_CLASS(insn->code);
if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
"BPF program is too large. Processed %d insn\n",
insn_processed);
return -E2BIG;
}
err = is_state_visited(env, insn_idx);
if (err < 0)
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
if (env->log.level) {
if (do_print_state)
verbose(env, "\nfrom %d to %d: safe\n",
prev_insn_idx, insn_idx);
else
verbose(env, "%d: safe\n", insn_idx);
}
goto process_bpf_exit;
}
if (need_resched())
cond_resched();
if (env->log.level > 1 || (env->log.level && do_print_state)) {
if (env->log.level > 1)
verbose(env, "%d:", insn_idx);
else
verbose(env, "\nfrom %d to %d:",
prev_insn_idx, insn_idx);
print_verifier_state(env, state->frame[state->curframe]);
do_print_state = false;
}
if (env->log.level) {
const struct bpf_insn_cbs cbs = {
.cb_print = verbose,
};
verbose(env, "%d: ", insn_idx);
print_bpf_insn(&cbs, env, insn, env->allow_ptr_leaks);
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
err = bpf_prog_offload_verify_insn(env, insn_idx,
prev_insn_idx);
if (err)
return err;
}
regs = cur_regs(env);
env->insn_aux_data[insn_idx].seen = true;
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
if (err)
return err;
} else if (class == BPF_LDX) {
enum bpf_reg_type *prev_src_type, src_reg_type;
/* check for reserved fields is already done */
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
src_reg_type = regs[insn->src_reg].type;
/* check that memory (src_reg + off) is readable,
* the state of dst_reg will be updated by this func
*/
err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ,
insn->dst_reg);
if (err)
return err;
prev_src_type = &env->insn_aux_data[insn_idx].ptr_type;
if (*prev_src_type == NOT_INIT) {
/* saw a valid insn
* dst_reg = *(u32 *)(src_reg + off)
* save type to validate intersecting paths
*/
*prev_src_type = src_reg_type;
} else if (src_reg_type != *prev_src_type &&
(src_reg_type == PTR_TO_CTX ||
*prev_src_type == PTR_TO_CTX)) {
/* ABuser program is trying to use the same insn
* dst_reg = *(u32*) (src_reg + off)
* with different pointer types:
* src_reg == ctx in one branch and
* src_reg == stack|map in some other branch.
* Reject it.
*/
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
} else if (class == BPF_STX) {
enum bpf_reg_type *prev_dst_type, dst_reg_type;
if (BPF_MODE(insn->code) == BPF_XADD) {
err = check_xadd(env, insn_idx, insn);
if (err)
return err;
insn_idx++;
continue;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
dst_reg_type = regs[insn->dst_reg].type;
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
insn->src_reg);
if (err)
return err;
prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type;
if (*prev_dst_type == NOT_INIT) {
*prev_dst_type = dst_reg_type;
} else if (dst_reg_type != *prev_dst_type &&
(dst_reg_type == PTR_TO_CTX ||
*prev_dst_type == PTR_TO_CTX)) {
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
} else if (class == BPF_ST) {
if (BPF_MODE(insn->code) != BPF_MEM ||
insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_ST uses reserved fields\n");
return -EINVAL;
}
/* check src operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_ctx_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ST stores into R%d context is not allowed\n",
insn->dst_reg);
return -EACCES;
}
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
-1);
if (err)
return err;
} else if (class == BPF_JMP) {
u8 opcode = BPF_OP(insn->code);
if (opcode == BPF_CALL) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->off != 0 ||
(insn->src_reg != BPF_REG_0 &&
insn->src_reg != BPF_PSEUDO_CALL) ||
insn->dst_reg != BPF_REG_0) {
verbose(env, "BPF_CALL uses reserved fields\n");
return -EINVAL;
}
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &insn_idx);
else
err = check_helper_call(env, insn->imm, insn_idx);
if (err)
return err;
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
insn_idx += insn->off + 1;
continue;
} else if (opcode == BPF_EXIT) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0) {
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
if (state->curframe) {
/* exit from nested function */
prev_insn_idx = insn_idx;
err = prepare_func_exit(env, &insn_idx);
if (err)
return err;
do_print_state = true;
continue;
}
/* eBPF calling convetion is such that R0 is used
* to return the value from eBPF program.
* Make sure that it's readable at this time
* of bpf_exit, which means that program wrote
* something into it earlier
*/
err = check_reg_arg(env, BPF_REG_0, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, BPF_REG_0)) {
verbose(env, "R0 leaks addr as return value\n");
return -EACCES;
}
err = check_return_code(env);
if (err)
return err;
process_bpf_exit:
err = pop_stack(env, &prev_insn_idx, &insn_idx);
if (err < 0) {
if (err != -ENOENT)
return err;
break;
} else {
do_print_state = true;
continue;
}
} else {
err = check_cond_jmp_op(env, insn, &insn_idx);
if (err)
return err;
}
} else if (class == BPF_LD) {
u8 mode = BPF_MODE(insn->code);
if (mode == BPF_ABS || mode == BPF_IND) {
err = check_ld_abs(env, insn);
if (err)
return err;
} else if (mode == BPF_IMM) {
err = check_ld_imm(env, insn);
if (err)
return err;
insn_idx++;
env->insn_aux_data[insn_idx].seen = true;
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
}
} else {
verbose(env, "unknown insn class %d\n", class);
return -EINVAL;
}
insn_idx++;
}
verbose(env, "processed %d insns (limit %d), stack depth ",
insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
for (i = 0; i < env->subprog_cnt + 1; i++) {
u32 depth = env->subprog_stack_depth[i];
verbose(env, "%d", depth);
if (i + 1 < env->subprog_cnt + 1)
verbose(env, "+");
}
verbose(env, "\n");
env->prog->aux->stack_depth = env->subprog_stack_depth[0];
return 0;
}
static int check_map_prealloc(struct bpf_map *map)
{
return (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
!(map->map_flags & BPF_F_NO_PREALLOC);
}
static int check_map_prog_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map,
struct bpf_prog *prog)
{
/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
* preallocated hash maps, since doing memory allocation
* in overflow_handler can crash depending on where nmi got
* triggered.
*/
if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
if (!check_map_prealloc(map)) {
verbose(env, "perf_event programs can only use preallocated hash map\n");
return -EINVAL;
}
if (map->inner_map_meta &&
!check_map_prealloc(map->inner_map_meta)) {
verbose(env, "perf_event programs can only use preallocated inner hash map\n");
return -EINVAL;
}
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_dev_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
return -EINVAL;
}
return 0;
}
/* look for pseudo eBPF instructions that access map FDs and
* replace them with actual map pointers
*/
static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
int i, j, err;
err = bpf_prog_calc_tag(env->prog);
if (err)
return err;
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
(BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
if (BPF_CLASS(insn->code) == BPF_STX &&
((BPF_MODE(insn->code) != BPF_MEM &&
BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
verbose(env, "BPF_STX uses reserved fields\n");
return -EINVAL;
}
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
struct bpf_map *map;
struct fd f;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
insn[1].off != 0) {
verbose(env, "invalid bpf_ld_imm64 insn\n");
return -EINVAL;
}
if (insn->src_reg == 0)
/* valid generic load 64-bit imm */
goto next_insn;
if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
verbose(env,
"unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
f = fdget(insn->imm);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
verbose(env, "fd %d is not pointing to valid bpf_map\n",
insn->imm);
return PTR_ERR(map);
}
err = check_map_prog_compatibility(env, map, env->prog);
if (err) {
fdput(f);
return err;
}
/* store map pointer inside BPF_LD_IMM64 instruction */
insn[0].imm = (u32) (unsigned long) map;
insn[1].imm = ((u64) (unsigned long) map) >> 32;
/* check whether we recorded this map already */
for (j = 0; j < env->used_map_cnt; j++)
if (env->used_maps[j] == map) {
fdput(f);
goto next_insn;
}
if (env->used_map_cnt >= MAX_USED_MAPS) {
fdput(f);
return -E2BIG;
}
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
* and all maps are released in free_bpf_prog_info()
*/
map = bpf_map_inc(map, false);
if (IS_ERR(map)) {
fdput(f);
return PTR_ERR(map);
}
env->used_maps[env->used_map_cnt++] = map;
fdput(f);
next_insn:
insn++;
i++;
continue;
}
/* Basic sanity check before we invest more work here. */
if (!bpf_opcode_in_insntable(insn->code)) {
verbose(env, "unknown opcode %02x\n", insn->code);
return -EINVAL;
}
}
/* now all pseudo BPF_LD_IMM64 instructions load valid
* 'struct bpf_map *' into a register instead of user map_fd.
* These pointers will be used later by verifier to validate map access.
*/
return 0;
}
/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
int i;
for (i = 0; i < env->used_map_cnt; i++)
bpf_map_put(env->used_maps[i]);
}
/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++, insn++)
if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
insn->src_reg = 0;
}
/* single env->prog->insni[off] instruction was replaced with the range
* insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
* [0, off) and [off, end) to new locations, so the patched range stays zero
*/
static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
u32 off, u32 cnt)
{
struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
int i;
if (cnt == 1)
return 0;
new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
if (!new_data)
return -ENOMEM;
memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++)
new_data[i].seen = true;
env->insn_aux_data = new_data;
vfree(old_data);
return 0;
}
static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
{
int i;
if (len == 1)
return;
for (i = 0; i < env->subprog_cnt; i++) {
if (env->subprog_starts[i] < off)
continue;
env->subprog_starts[i] += len - 1;
}
}
static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
const struct bpf_insn *patch, u32 len)
{
struct bpf_prog *new_prog;
new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
if (!new_prog)
return NULL;
if (adjust_insn_aux_data(env, new_prog->len, off, len))
return NULL;
adjust_subprog_starts(env, off, len);
return new_prog;
}
/* The verifier does more data flow analysis than llvm and will not
* explore branches that are dead at run time. Malicious programs can
* have dead code too. Therefore replace all dead at-run-time code
* with 'ja -1'.
*
* Just nops are not optimal, e.g. if they would sit at the end of the
* program and through another bug we would manage to jump there, then
* we'd execute beyond program memory otherwise. Returning exception
* code also wouldn't work since we can have subprogs where the dead
* code could be located.
*/
static void sanitize_dead_code(struct bpf_verifier_env *env)
{
struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
struct bpf_insn *insn = env->prog->insnsi;
const int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++) {
if (aux_data[i].seen)
continue;
memcpy(insn + i, &trap, sizeof(trap));
}
}
/* convert load instructions that access fields of 'struct __sk_buff'
* into sequence of instructions that access fields of 'struct sk_buff'
*/
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
const struct bpf_verifier_ops *ops = env->ops;
int i, cnt, size, ctx_field_size, delta = 0;
const int insn_cnt = env->prog->len;
struct bpf_insn insn_buf[16], *insn;
struct bpf_prog *new_prog;
enum bpf_access_type type;
bool is_narrower_load;
u32 target_size;
if (ops->gen_prologue) {
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
} else if (cnt) {
new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
env->prog = new_prog;
delta += cnt - 1;
}
}
if (!ops->convert_ctx_access)
return 0;
insn = env->prog->insnsi + delta;
for (i = 0; i < insn_cnt; i++, insn++) {
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
type = BPF_READ;
else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
insn->code == (BPF_STX | BPF_MEM | BPF_DW))
type = BPF_WRITE;
else
continue;
if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
* convert_ctx_access changes. If conversion is successful,
* we will apply proper mask to the result.
*/
is_narrower_load = size < ctx_field_size;
if (is_narrower_load) {
u32 off = insn->off;
u8 size_code;
if (type == BPF_WRITE) {
verbose(env, "bpf verifier narrow ctx access misconfigured\n");
return -EINVAL;
}
size_code = BPF_H;
if (ctx_field_size == 4)
size_code = BPF_W;
else if (ctx_field_size == 8)
size_code = BPF_DW;
insn->off = off & ~(ctx_field_size - 1);
insn->code = BPF_LDX | BPF_MEM | size_code;
}
target_size = 0;
cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog,
&target_size);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
(ctx_field_size && !target_size)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
if (is_narrower_load && size < target_size) {
if (ctx_field_size <= 4)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
(1 << size * 8) - 1);
else
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
(1 << size * 8) - 1);
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
/* keep walking new program and skip insns we just inserted */
env->prog = new_prog;
insn = new_prog->insnsi + i + delta;
}
return 0;
}
static int jit_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog, **func, *tmp;
int i, j, subprog_start, subprog_end = 0, len, subprog;
struct bpf_insn *insn;
void *old_bpf_func;
int err = -ENOMEM;
if (env->subprog_cnt == 0)
return 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i + insn->imm + 1);
return -EFAULT;
}
/* temporarily remember subprog id inside insn instead of
* aux_data, since next loop will split up all insns into funcs
*/
insn->off = subprog + 1;
/* remember original imm in case JIT fails and fallback
* to interpreter will be needed
*/
env->insn_aux_data[i].call_imm = insn->imm;
/* point imm to __bpf_call_base+1 from JITs point of view */
insn->imm = 1;
}
func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL);
if (!func)
return -ENOMEM;
for (i = 0; i <= env->subprog_cnt; i++) {
subprog_start = subprog_end;
if (env->subprog_cnt == i)
subprog_end = prog->len;
else
subprog_end = env->subprog_starts[i];
len = subprog_end - subprog_start;
func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
if (!func[i])
goto out_free;
memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
len * sizeof(struct bpf_insn));
func[i]->type = prog->type;
func[i]->len = len;
if (bpf_prog_calc_tag(func[i]))
goto out_free;
func[i]->is_func = 1;
/* Use bpf_prog_F_tag to indicate functions in stack traces.
* Long term would need debug info to populate names
*/
func[i]->aux->name[0] = 'F';
func[i]->aux->stack_depth = env->subprog_stack_depth[i];
func[i]->jit_requested = 1;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
goto out_free;
}
cond_resched();
}
/* at this point all bpf functions were successfully JITed
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
*/
for (i = 0; i <= env->subprog_cnt; i++) {
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
subprog = insn->off;
insn->off = 0;
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
func[subprog]->bpf_func -
__bpf_call_base;
}
}
for (i = 0; i <= env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
err = -EFAULT;
goto out_free;
}
cond_resched();
}
/* finally lock prog and jit images for all functions and
* populate kallsysm
*/
for (i = 0; i <= env->subprog_cnt; i++) {
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
/* Last step: make now unused interpreter insns from main
* prog consistent for later dump requests, so they can
* later look the same as if they were interpreted only.
*/
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
unsigned long addr;
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
insn->off = env->insn_aux_data[i].call_imm;
subprog = find_subprog(env, i + insn->off + 1);
addr = (unsigned long)func[subprog + 1]->bpf_func;
addr &= PAGE_MASK;
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
addr - __bpf_call_base;
}
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
prog->aux->func_cnt = env->subprog_cnt + 1;
return 0;
out_free:
for (i = 0; i <= env->subprog_cnt; i++)
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
insn->off = 0;
insn->imm = env->insn_aux_data[i].call_imm;
}
return err;
}
static int fixup_call_args(struct bpf_verifier_env *env)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
struct bpf_prog *prog = env->prog;
struct bpf_insn *insn = prog->insnsi;
int i, depth;
#endif
int err;
err = 0;
if (env->prog->jit_requested) {
err = jit_subprogs(env);
if (err == 0)
return 0;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
depth = get_callee_stack_depth(env, insn, i);
if (depth < 0)
return depth;
bpf_patch_call_args(insn, depth);
}
err = 0;
#endif
return err;
}
/* fixup insn->imm field of bpf_call instructions
* and inline eligible helpers as explicit sequence of BPF instructions
*
* this function is called after eBPF program passed verification
*/
static int fixup_bpf_calls(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
struct bpf_insn *insn = prog->insnsi;
const struct bpf_func_proto *fn;
const int insn_cnt = prog->len;
struct bpf_insn insn_buf[16];
struct bpf_prog *new_prog;
struct bpf_map *map_ptr;
int i, cnt, delta = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
struct bpf_insn mask_and_div[] = {
BPF_MOV32_REG(insn->src_reg, insn->src_reg),
/* Rx div 0 -> 0 */
BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2),
BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
*insn,
};
struct bpf_insn mask_and_mod[] = {
BPF_MOV32_REG(insn->src_reg, insn->src_reg),
/* Rx mod 0 -> Rx */
BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1),
*insn,
};
struct bpf_insn *patchlet;
if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
patchlet = mask_and_div + (is64 ? 1 : 0);
cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0);
} else {
patchlet = mask_and_mod + (is64 ? 1 : 0);
cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0);
}
new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
if (insn->code != (BPF_JMP | BPF_CALL))
continue;
if (insn->src_reg == BPF_PSEUDO_CALL)
continue;
if (insn->imm == BPF_FUNC_get_route_realm)
prog->dst_needed = 1;
if (insn->imm == BPF_FUNC_get_prandom_u32)
bpf_user_rnd_init_once();
if (insn->imm == BPF_FUNC_override_return)
prog->kprobe_override = 1;
if (insn->imm == BPF_FUNC_tail_call) {
/* If we tail call into other programs, we
* cannot make any assumptions since they can
* be replaced dynamically during runtime in
* the program array.
*/
prog->cb_access = 1;
env->prog->aux->stack_depth = MAX_BPF_STACK;
/* mark bpf_tail_call as different opcode to avoid
* conditional branch in the interpeter for every normal
* call and to prevent accidental JITing by JIT compiler
* that doesn't support bpf_tail_call yet
*/
insn->imm = 0;
insn->code = BPF_JMP | BPF_TAIL_CALL;
/* instead of changing every JIT dealing with tail_call
* emit two extra insns:
* if (index >= max_entries) goto out;
* index &= array->index_mask;
* to avoid out-of-bounds cpu speculation
*/
map_ptr = env->insn_aux_data[i + delta].map_ptr;
if (map_ptr == BPF_MAP_PTR_POISON) {
verbose(env, "tail_call abusing map_ptr\n");
return -EINVAL;
}
if (!map_ptr->unpriv_array)
continue;
insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
map_ptr->max_entries, 2);
insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
container_of(map_ptr,
struct bpf_array,
map)->index_mask);
insn_buf[2] = *insn;
cnt = 3;
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
* handlers are currently limited to 64 bit only.
*/
if (prog->jit_requested && BITS_PER_LONG == 64 &&
insn->imm == BPF_FUNC_map_lookup_elem) {
map_ptr = env->insn_aux_data[i + delta].map_ptr;
if (map_ptr == BPF_MAP_PTR_POISON ||
!map_ptr->ops->map_gen_lookup)
goto patch_call_imm;
cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
/* keep walking new program and skip insns we just inserted */
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
if (insn->imm == BPF_FUNC_redirect_map) {
/* Note, we cannot use prog directly as imm as subsequent
* rewrites would still change the prog pointer. The only
* stable address we can use is aux, which also works with
* prog clones during blinding.
*/
u64 addr = (unsigned long)prog->aux;
struct bpf_insn r4_ld[] = {
BPF_LD_IMM64(BPF_REG_4, addr),
*insn,
};
cnt = ARRAY_SIZE(r4_ld);
new_prog = bpf_patch_insn_data(env, i + delta, r4_ld, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
}
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
if (!fn->func) {
verbose(env,
"kernel subsystem misconfigured func %s#%d\n",
func_id_name(insn->imm), insn->imm);
return -EFAULT;
}
insn->imm = fn->func - __bpf_call_base;
}
return 0;
}
static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl, *sln;
int i;
if (!env->explored_states)
return;
for (i = 0; i < env->prog->len; i++) {
sl = env->explored_states[i];
if (sl)
while (sl != STATE_LIST_MARK) {
sln = sl->next;
free_verifier_state(&sl->state, false);
kfree(sl);
sl = sln;
}
}
kfree(env->explored_states);
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
{
struct bpf_verifier_env *env;
struct bpf_verifer_log *log;
int ret = -EINVAL;
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
return -EINVAL;
/* 'struct bpf_verifier_env' can be global, but since it's not small,
* allocate/free it every time bpf_check() is called
*/
env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
if (!env)
return -ENOMEM;
log = &env->log;
env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
(*prog)->len);
ret = -ENOMEM;
if (!env->insn_aux_data)
goto err_free_env;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
/* grab the mutex to protect few globals used by verifier */
mutex_lock(&bpf_verifier_lock);
if (attr->log_level || attr->log_buf || attr->log_size) {
/* user requested verbose verifier output
* and supplied buffer to store the verification trace
*/
log->level = attr->log_level;
log->ubuf = (char __user *) (unsigned long) attr->log_buf;
log->len_total = attr->log_size;
ret = -EINVAL;
/* log attributes have to be sane */
if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
!log->level || !log->ubuf)
goto err_unlock;
}
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env);
if (ret)
goto err_unlock;
}
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
goto skip_full_check;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
ret = -ENOMEM;
if (!env->explored_states)
goto skip_full_check;
env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
ret = do_check(env);
if (env->cur_state) {
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
}
skip_full_check:
while (!pop_stack(env, NULL, NULL));
free_states(env);
if (ret == 0)
sanitize_dead_code(env);
if (ret == 0)
ret = check_max_stack_depth(env);
if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
if (ret == 0)
ret = fixup_bpf_calls(env);
if (ret == 0)
ret = fixup_call_args(env);
if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
if (log->level && !log->ubuf) {
ret = -EFAULT;
goto err_release_maps;
}
if (ret == 0 && env->used_map_cnt) {
/* if program passed verifier, update used_maps in bpf_prog_info */
env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
sizeof(env->used_maps[0]),
GFP_KERNEL);
if (!env->prog->aux->used_maps) {
ret = -ENOMEM;
goto err_release_maps;
}
memcpy(env->prog->aux->used_maps, env->used_maps,
sizeof(env->used_maps[0]) * env->used_map_cnt);
env->prog->aux->used_map_cnt = env->used_map_cnt;
/* program is valid. Convert pseudo bpf_ld_imm64 into generic
* bpf_ld_imm64 instructions
*/
convert_pseudo_ld_imm64(env);
}
err_release_maps:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
* them now. Otherwise free_bpf_prog_info() will release them.
*/
release_maps(env);
*prog = env->prog;
err_unlock:
mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
err_free_env:
kfree(env);
return ret;
}
Reference in New Issue View Git Blame Copy Permalink