netdev - Re: [PATCH bpf-next]: add sock_ops R/W access to ipv4 tos

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 28 Mar 2018 15:47:41 +0200
From:   Daniel Borkmann <daniel@...earbox.net>
To:     "Nikita V. Shirokov" <tehnerd@...com>, brakmo@...com,
        ast@...nel.org, netdev@...r.kernel.org
Cc:     kernel-team@...com
Subject: Re: [PATCH bpf-next]: add sock_ops R/W access to ipv4 tos

On 03/26/2018 05:36 PM, Nikita V. Shirokov wrote:
>     bpf: Add sock_ops R/W access to ipv4 tos
> 
>     Sample usage for tos:
> 
>       bpf_getsockopt(skops, SOL_IP, IP_TOS, &v, sizeof(v))
> 
>     where skops is a pointer to the ctx (struct bpf_sock_ops).
> 
> Signed-off-by: Nikita V. Shirokov <tehnerd@...com>
> ---
>  net/core/filter.c | 35 +++++++++++++++++++++++++++++++++++
>  1 file changed, 35 insertions(+)
> 
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 00c711c..afd8255 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3462,6 +3462,27 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
>  			ret = -EINVAL;
>  		}
>  #ifdef CONFIG_INET
> +	} else if (level == SOL_IP) {
> +		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
> +			return -EINVAL;
> +
> +		val = *((int *)optval);
> +		/* Only some options are supported */
> +		switch (optname) {
> +		case IP_TOS:
> +			if (val < -1 || val > 0xff) {
> +				ret = -EINVAL;
> +			} else {
> +				struct inet_sock *inet = inet_sk(sk);
> +
> +				if (val == -1)
> +					val = 0;
> +				inet->tos = val;

Should this not have the exact same semantics given the helper resembles
the normal setsockopt? do_ip_setsockopt() does the following when setting
IP_TOS:

        case IP_TOS:    /* This sets both TOS and Precedence */
                if (sk->sk_type == SOCK_STREAM) {
                        val &= ~INET_ECN_MASK;
                        val |= inet->tos & INET_ECN_MASK;
                }
                if (inet->tos != val) {
                        inet->tos = val;
                        sk->sk_priority = rt_tos2priority(val);
                        sk_dst_reset(sk);
                }
                break;

E.g. why we don't need to set sk->sk_priority as well or reset the dst
entry here?

> +			}
> +			break;
> +		default:
> +			ret = -EINVAL;
> +		}
>  #if IS_ENABLED(CONFIG_IPV6)
>  	} else if (level == SOL_IPV6) {
>  		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
> @@ -3561,6 +3582,20 @@ BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
>  		} else {
>  			goto err_clear;
>  		}
> +	} else if (level == SOL_IP) {
> +		struct inet_sock *inet = inet_sk(sk);
> +
> +		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
> +			goto err_clear;
> +
> +		/* Only some options are supported */
> +		switch (optname) {
> +		case IP_TOS:
> +			*((int *)optval) = (int)inet->tos;

This part is fine though, same as in do_ip_getsockopt().

> +			break;
> +		default:
> +			goto err_clear;
> +		}
>  #if IS_ENABLED(CONFIG_IPV6)
>  	} else if (level == SOL_IPV6) {
>  		struct ipv6_pinfo *np = inet6_sk(sk);
>