From: Alexei Starovoitov <ast@xxxxxxxxxx> Compilers can generate the code r1 = r2 r1 += 0x1 if r2 < 1000 goto ... use knowledge of r2 range in subsequent r1 operations So remember constant delta between r2 and r1 and update r1 after 'if' condition. Unfortunately LLVM still uses this pattern for loops with 'can_loop' construct: for (i = 0; i < 1000 && can_loop; i++) The "undo" pass was introduced in LLVM https://reviews.llvm.org/D121937 to prevent this optimization, but it cannot cover all cases. Instead of fighting middle end optimizer in BPF backend teach the verifier about this pattern. Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx> --- include/linux/bpf_verifier.h | 12 ++++- kernel/bpf/log.c | 4 +- kernel/bpf/verifier.c | 90 ++++++++++++++++++++++++++++++++---- 3 files changed, 95 insertions(+), 11 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 50aa87f8d77f..2b54e25d2364 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -73,7 +73,10 @@ enum bpf_iter_state { struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; - /* Fixed part of pointer offset, pointer types only */ + /* + * Fixed part of pointer offset, pointer types only. + * Or constant delta between "linked" scalars with the same ID. + */ s32 off; union { /* valid when type == PTR_TO_PACKET */ @@ -167,6 +170,13 @@ struct bpf_reg_state { * Similarly to dynptrs, we use ID to track "belonging" of a reference * to a specific instance of bpf_iter. */ + /* + * Upper bit of ID is used to remember relationship between "linked" + * registers. Example: + * r1 = r2; both will have r1->id == r2->id == N + * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->off == 10 + */ +#define BPF_ADD_CONST (1U << 31) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 4bd8f17a9f24..3f4ae92e549f 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -708,7 +708,9 @@ static void print_reg_state(struct bpf_verifier_env *env, verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); verbose(env, "("); if (reg->id) - verbose_a("id=%d", reg->id); + verbose_a("id=%d", reg->id & ~BPF_ADD_CONST); + if (reg->id & BPF_ADD_CONST) + verbose(env, "%+d", reg->off); if (reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); if (type_is_non_owning_ref(reg->type)) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 81a3d2ced78d..e282625995fc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4438,8 +4438,20 @@ static bool __is_pointer_value(bool allow_ptr_leaks, static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, struct bpf_reg_state *src_reg) { - if (src_reg->type == SCALAR_VALUE && !src_reg->id && - !tnum_is_const(src_reg->var_off)) + if (src_reg->type != SCALAR_VALUE) + return; + + if (src_reg->id & BPF_ADD_CONST) { + /* + * The verifier is processing rX = rY insn and + * rY->id has special linked register already. + * Cleared it, since multiple rX += const are not supported. + */ + src_reg->id = 0; + src_reg->off = 0; + } + + if (!src_reg->id && !tnum_is_const(src_reg->var_off)) /* Ensure that src_reg has a valid ID that will be copied to * dst_reg and then will be used by find_equal_scalars() to * propagate min/max range. @@ -14026,6 +14038,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, 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}; + bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); u8 opcode = BPF_OP(insn->code); int err; @@ -14048,11 +14061,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; - else - /* Make sure ID is cleared otherwise dst_reg min/max could be - * incorrectly propagated into other registers by find_equal_scalars() - */ - dst_reg->id = 0; + if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { @@ -14116,7 +14125,40 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } - return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); + err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); + if (err) + return err; + /* + * Compilers can generate the code + * r1 = r2 + * r1 += 0x1 + * if r2 < 1000 goto ... + * use r1 in memory access + * So remember constant delta between r2 and r1 and update r1 after + * 'if' condition. + */ + if (BPF_OP(insn->code) == BPF_ADD && dst_reg->id && is_reg_const(src_reg, alu32)) { + u64 val = reg_const_value(src_reg, alu32); + + if ((dst_reg->id & BPF_ADD_CONST) || val > (u32)S32_MAX) { + /* + * If the register already went through rX += val + * we cannot accumulate another val into rx->off. + */ + dst_reg->off = 0; + dst_reg->id = 0; + } else { + dst_reg->id |= BPF_ADD_CONST; + dst_reg->off = val; + } + } else { + /* + * Make sure ID is cleared otherwise dst_reg min/max could be + * incorrectly propagated into other registers by find_equal_scalars() + */ + dst_reg->id = 0; + } + return 0; } /* check validity of 32-bit and 64-bit arithmetic operations */ @@ -15088,13 +15130,43 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, static void find_equal_scalars(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg) { + struct bpf_reg_state fake_reg; struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(vstate, state, reg, ({ - if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) + if (reg->type != SCALAR_VALUE || reg == known_reg) + continue; + if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST)) + continue; + if ((reg->id & BPF_ADD_CONST) == (known_reg->id & BPF_ADD_CONST)) { copy_register_state(reg, known_reg); + } else if ((reg->id & BPF_ADD_CONST) && reg->off) { + /* reg = known_reg; reg += const */ + copy_register_state(reg, known_reg); + + fake_reg.type = SCALAR_VALUE; + __mark_reg_known(&fake_reg, reg->off); + scalar32_min_max_add(reg, &fake_reg); + scalar_min_max_add(reg, &fake_reg); + reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); + reg->off = 0; + reg->id &= ~BPF_ADD_CONST; + } else if ((known_reg->id & BPF_ADD_CONST) && known_reg->off) { + /* reg = known_reg; reg -= const' */ + copy_register_state(reg, known_reg); + + fake_reg.type = SCALAR_VALUE; + __mark_reg_known(&fake_reg, known_reg->off); + scalar32_min_max_sub(reg, &fake_reg); + scalar_min_max_sub(reg, &fake_reg); + reg->var_off = tnum_sub(reg->var_off, fake_reg.var_off); + } })); + if (known_reg->id & BPF_ADD_CONST) { + known_reg->id = 0; + known_reg->off = 0; + } } static int check_cond_jmp_op(struct bpf_verifier_env *env, -- 2.43.0
