summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/verifier.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/verifier.c')
-rw-r--r--kernel/bpf/verifier.c262
1 files changed, 189 insertions, 73 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1eddb713b815..6a86723c5b64 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -463,19 +463,22 @@ static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
+static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
+{
+ BUG_ON(regno >= MAX_BPF_REG);
+
+ memset(&regs[regno], 0, sizeof(regs[regno]));
+ regs[regno].type = NOT_INIT;
+ regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
+ regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+}
+
static void init_reg_state(struct bpf_reg_state *regs)
{
int i;
- for (i = 0; i < MAX_BPF_REG; i++) {
- regs[i].type = NOT_INIT;
- regs[i].imm = 0;
- regs[i].min_value = BPF_REGISTER_MIN_RANGE;
- regs[i].max_value = BPF_REGISTER_MAX_RANGE;
- regs[i].min_align = 0;
- regs[i].aux_off = 0;
- regs[i].aux_off_align = 0;
- }
+ for (i = 0; i < MAX_BPF_REG; i++)
+ mark_reg_not_init(regs, i);
/* frame pointer */
regs[BPF_REG_FP].type = FRAME_PTR;
@@ -543,20 +546,6 @@ static int check_reg_arg(struct bpf_reg_state *regs, u32 regno,
return 0;
}
-static int bpf_size_to_bytes(int bpf_size)
-{
- if (bpf_size == BPF_W)
- return 4;
- else if (bpf_size == BPF_H)
- return 2;
- else if (bpf_size == BPF_B)
- return 1;
- else if (bpf_size == BPF_DW)
- return 8;
- else
- return -EINVAL;
-}
-
static bool is_spillable_regtype(enum bpf_reg_type type)
{
switch (type) {
@@ -755,15 +744,29 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
}
/* check access to 'struct bpf_context' fields */
-static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
+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,
+ };
+
/* for analyzer ctx accesses are already validated and converted */
if (env->analyzer_ops)
return 0;
if (env->prog->aux->ops->is_valid_access &&
- env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
+ env->prog->aux->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.
+ */
+ env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+ *reg_type = info.reg_type;
+
/* 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;
@@ -808,11 +811,15 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
reg_off += reg->aux_off;
}
- /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
- * we force this to 2 which is universally what architectures use
- * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ /* 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 = strict ? 2 : NET_IP_ALIGN;
+ ip_align = 2;
if ((ip_align + reg_off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
ip_align, reg_off, off, size);
@@ -839,9 +846,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
{
bool strict = env->strict_alignment;
- if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- strict = true;
-
switch (reg->type) {
case PTR_TO_PACKET:
return check_pkt_ptr_alignment(reg, off, size, strict);
@@ -864,7 +868,7 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
* 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, u32 regno, int off,
+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)
{
@@ -907,7 +911,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
verbose("R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
- err = check_ctx_access(env, off, size, t, &reg_type);
+ err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
mark_reg_unknown_value_and_range(state->regs,
value_regno);
@@ -922,6 +926,10 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
verbose("invalid stack off=%d size=%d\n", off, size);
return -EACCES;
}
+
+ if (env->prog->aux->stack_depth < -off)
+ env->prog->aux->stack_depth = -off;
+
if (t == BPF_WRITE) {
if (!env->allow_ptr_leaks &&
state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL &&
@@ -964,7 +972,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
return err;
}
-static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
+static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = env->cur_state.regs;
int err;
@@ -985,14 +993,19 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose("R%d leaks addr into mem\n", insn->src_reg);
+ return -EACCES;
+ }
+
/* check whether atomic_add can read the memory */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ 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->dst_reg, insn->off,
+ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1);
}
@@ -1028,6 +1041,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
return -EACCES;
}
+ if (env->prog->aux->stack_depth < -off)
+ env->prog->aux->stack_depth = -off;
+
if (meta && meta->raw_mode) {
meta->access_size = access_size;
meta->regno = regno;
@@ -1335,8 +1351,8 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
if (reg->type != PTR_TO_PACKET &&
reg->type != PTR_TO_PACKET_END)
continue;
- reg->type = UNKNOWN_VALUE;
- reg->imm = 0;
+ __mark_reg_unknown_value(state->spilled_regs,
+ i / BPF_REG_SIZE);
}
}
@@ -1345,7 +1361,6 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
struct bpf_verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
struct bpf_reg_state *regs = state->regs;
- struct bpf_reg_state *reg;
struct bpf_call_arg_meta meta;
bool changes_data;
int i, err;
@@ -1406,17 +1421,14 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
* is inferred from register state.
*/
for (i = 0; i < meta.access_size; i++) {
- err = check_mem_access(env, meta.regno, i, BPF_B, BPF_WRITE, -1);
+ err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1);
if (err)
return err;
}
/* reset caller saved regs */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- reg = regs + caller_saved[i];
- reg->type = NOT_INIT;
- reg->imm = 0;
- }
+ for (i = 0; i < CALLER_SAVED_REGS; i++)
+ mark_reg_not_init(regs, caller_saved[i]);
/* update return register */
if (fn->ret_type == RET_INTEGER) {
@@ -1645,6 +1657,65 @@ static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
+static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env,
+ struct bpf_insn *insn)
+{
+ struct bpf_reg_state *regs = env->cur_state.regs;
+ struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
+ struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+ u8 opcode = BPF_OP(insn->code);
+ s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm);
+
+ /* BPF_X code with src_reg->type UNKNOWN_VALUE here. */
+ if (src_reg->imm > 0 && dst_reg->imm) {
+ switch (opcode) {
+ case BPF_ADD:
+ /* dreg += sreg
+ * where both have zero upper bits. Adding them
+ * can only result making one more bit non-zero
+ * in the larger value.
+ * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
+ * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
+ */
+ dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+ dst_reg->imm--;
+ break;
+ case BPF_AND:
+ /* dreg &= sreg
+ * AND can not extend zero bits only shrink
+ * Ex. 0x00..00ffffff
+ * & 0x0f..ffffffff
+ * ----------------
+ * 0x00..00ffffff
+ */
+ dst_reg->imm = max(src_reg->imm, 63 - imm_log2);
+ break;
+ case BPF_OR:
+ /* dreg |= sreg
+ * OR can only extend zero bits
+ * Ex. 0x00..00ffffff
+ * | 0x0f..ffffffff
+ * ----------------
+ * 0x0f..00ffffff
+ */
+ dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+ break;
+ case BPF_SUB:
+ case BPF_MUL:
+ case BPF_RSH:
+ case BPF_LSH:
+ /* These may be flushed out later */
+ default:
+ mark_reg_unknown_value(regs, insn->dst_reg);
+ }
+ } else {
+ mark_reg_unknown_value(regs, insn->dst_reg);
+ }
+
+ dst_reg->type = UNKNOWN_VALUE;
+ return 0;
+}
+
static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
@@ -1654,6 +1725,9 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
u8 opcode = BPF_OP(insn->code);
u64 dst_imm = dst_reg->imm;
+ if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE)
+ return evaluate_reg_imm_alu_unknown(env, insn);
+
/* dst_reg->type == CONST_IMM here. Simulate execution of insns
* containing ALU ops. Don't care about overflow or negative
* values, just add/sub/... them; registers are in u64.
@@ -1945,6 +2019,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
*/
regs[insn->dst_reg].type = CONST_IMM;
regs[insn->dst_reg].imm = insn->imm;
+ regs[insn->dst_reg].id = 0;
regs[insn->dst_reg].max_value = insn->imm;
regs[insn->dst_reg].min_value = insn->imm;
regs[insn->dst_reg].min_align = calc_align(insn->imm);
@@ -2402,6 +2477,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
regs[insn->dst_reg].type = CONST_IMM;
regs[insn->dst_reg].imm = imm;
+ regs[insn->dst_reg].id = 0;
return 0;
}
@@ -2444,7 +2520,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = env->cur_state.regs;
u8 mode = BPF_MODE(insn->code);
- struct bpf_reg_state *reg;
int i, err;
if (!may_access_skb(env->prog->type)) {
@@ -2477,11 +2552,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* reset caller saved regs to unreadable */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- reg = regs + caller_saved[i];
- reg->type = NOT_INIT;
- reg->imm = 0;
- }
+ for (i = 0; i < CALLER_SAVED_REGS; i++)
+ mark_reg_not_init(regs, caller_saved[i]);
/* mark destination R0 register as readable, since it contains
* the value fetched from the packet
@@ -2692,7 +2764,8 @@ err_free:
/* the following conditions reduce the number of explored insns
* from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet
*/
-static bool compare_ptrs_to_packet(struct bpf_reg_state *old,
+static bool compare_ptrs_to_packet(struct bpf_verifier_env *env,
+ struct bpf_reg_state *old,
struct bpf_reg_state *cur)
{
if (old->id != cur->id)
@@ -2735,7 +2808,7 @@ static bool compare_ptrs_to_packet(struct bpf_reg_state *old,
* 'if (R4 > data_end)' and all further insn were already good with r=20,
* so they will be good with r=30 and we can prune the search.
*/
- if (old->off <= cur->off &&
+ if (!env->strict_alignment && old->off <= cur->off &&
old->off >= old->range && cur->off >= cur->range)
return true;
@@ -2806,7 +2879,7 @@ static bool states_equal(struct bpf_verifier_env *env,
continue;
if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
- compare_ptrs_to_packet(rold, rcur))
+ compare_ptrs_to_packet(env, rold, rcur))
continue;
return false;
@@ -2824,6 +2897,8 @@ static bool states_equal(struct bpf_verifier_env *env,
return false;
if (i % BPF_REG_SIZE)
continue;
+ if (old->stack_slot_type[i] != STACK_SPILL)
+ continue;
if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE],
&cur->spilled_regs[i / BPF_REG_SIZE],
sizeof(old->spilled_regs[0])))
@@ -2985,18 +3060,12 @@ static int do_check(struct bpf_verifier_env *env)
/* 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->src_reg, insn->off,
+ 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;
- if (BPF_SIZE(insn->code) != BPF_W &&
- BPF_SIZE(insn->code) != BPF_DW) {
- insn_idx++;
- continue;
- }
-
prev_src_type = &env->insn_aux_data[insn_idx].ptr_type;
if (*prev_src_type == NOT_INIT) {
@@ -3024,7 +3093,7 @@ static int do_check(struct bpf_verifier_env *env)
enum bpf_reg_type *prev_dst_type, dst_reg_type;
if (BPF_MODE(insn->code) == BPF_XADD) {
- err = check_xadd(env, insn);
+ err = check_xadd(env, insn_idx, insn);
if (err)
return err;
insn_idx++;
@@ -3043,7 +3112,7 @@ static int do_check(struct bpf_verifier_env *env)
dst_reg_type = regs[insn->dst_reg].type;
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
insn->src_reg);
if (err)
@@ -3072,7 +3141,7 @@ static int do_check(struct bpf_verifier_env *env)
return err;
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
-1);
if (err)
@@ -3170,7 +3239,8 @@ process_bpf_exit:
insn_idx++;
}
- verbose("processed %d insns\n", insn_processed);
+ verbose("processed %d insns, stack depth %d\n",
+ insn_processed, env->prog->aux->stack_depth);
return 0;
}
@@ -3370,11 +3440,13 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
const struct bpf_verifier_ops *ops = env->prog->aux->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;
- int i, cnt, delta = 0;
+ bool is_narrower_load;
+ u32 target_size;
if (ops->gen_prologue) {
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
@@ -3414,12 +3486,52 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
- cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog);
- if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ 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("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("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;
@@ -3465,6 +3577,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
* 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
@@ -3472,7 +3585,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
* that doesn't support bpf_tail_call yet
*/
insn->imm = 0;
- insn->code |= BPF_X;
+ insn->code = BPF_JMP | BPF_TAIL_CALL;
continue;
}
@@ -3584,10 +3697,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
} else {
log_level = 0;
}
- if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+
+ env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
- else
- env->strict_alignment = false;
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
@@ -3693,7 +3806,10 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
mutex_lock(&bpf_verifier_lock);
log_level = 0;
+
env->strict_alignment = false;
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ env->strict_alignment = true;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-04 03:11:49 +0100