Date:   Wed, 18 Apr 2018 21:33:24 -0700
From:   Alexei Starovoitov <alexei.starovoitov@...il.com>
To:     Yonghong Song <yhs@...com>
Cc:     ast@...com, daniel@...earbox.net, netdev@...r.kernel.org,
        kernel-team@...com
Subject: Re: [PATCH bpf-next v2 3/9] bpf/verifier: refine retval R0 state for
 bpf_get_stack helper

On Wed, Apr 18, 2018 at 09:54:38AM -0700, Yonghong Song wrote:
> The special property of return values for helpers bpf_get_stack
> and bpf_probe_read_str are captured in verifier.
> Both helpers return a negative error code or
> a length, which is equal to or smaller than the buffer
> size argument. This additional information in the
> verifier can avoid the condition such as "retval > bufsize"
> in the bpf program. For example, for the code blow,
>     usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
>     if (usize < 0 || usize > max_len)
>         return 0;
> The verifier may have the following errors:
>     52: (85) call bpf_get_stack#65
>      R0=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R1_w=ctx(id=0,off=0,imm=0)
>      R2_w=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R3_w=inv800 R4_w=inv256
>      R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0)
>      R9_w=inv800 R10=fp0,call_-1
>     53: (bf) r8 = r0
>     54: (bf) r1 = r8
>     55: (67) r1 <<= 32
>     56: (bf) r2 = r1
>     57: (77) r2 >>= 32
>     58: (25) if r2 > 0x31f goto pc+33
>      R0=inv(id=0) R1=inv(id=0,smax_value=9223372032559808512,
>                          umax_value=18446744069414584320,
>                          var_off=(0x0; 0xffffffff00000000))
>      R2=inv(id=0,umax_value=799,var_off=(0x0; 0x3ff))
>      R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0)
>      R8=inv(id=0) R9=inv800 R10=fp0,call_-1
>     59: (1f) r9 -= r8
>     60: (c7) r1 s>>= 32
>     61: (bf) r2 = r7
>     62: (0f) r2 += r1
>     math between map_value pointer and register with unbounded
>     min value is not allowed
> The failure is due to llvm compiler optimization where register "r2",
> which is a copy of "r1", is tested for condition while later on "r1"
> is used for map_ptr operation. The verifier is not able to track such
> inst sequence effectively.
> 
> Without the "usize > max_len" condition, there is no llvm optimization
> and the below generated code passed verifier:
>     52: (85) call bpf_get_stack#65
>      R0=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R1_w=ctx(id=0,off=0,imm=0)
>      R2_w=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R3_w=inv800 R4_w=inv256
>      R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0)
>      R9_w=inv800 R10=fp0,call_-1
>     53: (b7) r1 = 0
>     54: (bf) r8 = r0
>     55: (67) r8 <<= 32
>     56: (c7) r8 s>>= 32
>     57: (6d) if r1 s> r8 goto pc+24
>      R0=inv(id=0,umax_value=800) R1=inv0 R6=ctx(id=0,off=0,imm=0)
>      R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0)
>      R8=inv(id=0,umax_value=800,var_off=(0x0; 0x3ff)) R9=inv800
>      R10=fp0,call_-1
>     58: (bf) r2 = r7
>     59: (0f) r2 += r8
>     60: (1f) r9 -= r8
>     61: (bf) r1 = r6
> 
> Signed-off-by: Yonghong Song <yhs@...com>
> ---
>  kernel/bpf/verifier.c | 31 ++++++++++++++++++++++++++++++-
>  1 file changed, 30 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index aba9425..a8302c3 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -2333,10 +2333,32 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
>  	return 0;
>  }
>  
> +static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
> +				   int func_id,
> +				   struct bpf_reg_state *retval_state,
> +				   bool is_check)
> +{
> +	struct bpf_reg_state *src_reg, *dst_reg;
> +
> +	if (ret_type != RET_INTEGER ||
> +	    (func_id != BPF_FUNC_get_stack &&
> +	     func_id != BPF_FUNC_probe_read_str))
> +		return;
> +
> +	dst_reg = is_check ? retval_state : &regs[BPF_REG_0];
> +	if (func_id == BPF_FUNC_get_stack)
> +		src_reg = is_check ? &regs[BPF_REG_3] : retval_state;
> +	else
> +		src_reg = is_check ? &regs[BPF_REG_2] : retval_state;
> +
> +	dst_reg->smax_value = src_reg->smax_value;
> +	dst_reg->umax_value = src_reg->umax_value;
> +}

I think this part can be made more generic, by using 'meta' logic.
check_func_arg(.. &meta);
can remember smax/umax into meta for arg_type_is_mem_size()
and later refine_retval_range() can be applied to r0.
This will help avoid mistakes with specifying reg by position (r2 or r3)
like above snippet is doing.

> +
>  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_reg_state *regs, retval_state;
>  	struct bpf_call_arg_meta meta;
>  	bool changes_data;
>  	int i, err;
> @@ -2415,6 +2437,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
>  	}
>  
>  	regs = cur_regs(env);
> +
> +	/* before reset caller saved regs, check special ret value */
> +	do_refine_retval_range(regs, fn->ret_type, func_id, &retval_state, 1);
> +
>  	/* reset caller saved regs */
>  	for (i = 0; i < CALLER_SAVED_REGS; i++) {
>  		mark_reg_not_init(env, regs, caller_saved[i]);
> @@ -2456,6 +2482,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
>  		return -EINVAL;
>  	}
>  
> +	/* apply additional constraints to ret value */
> +	do_refine_retval_range(regs, fn->ret_type, func_id, &retval_state, 0);
> +
>  	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
>  	if (err)
>  		return err;
> -- 
> 2.9.5
> 

Powered by blists - more mailing lists