Re: [RFC PATCH 2/3] ipv6: Run a reverse sk_lookup on sendmsg.

[Martin KaFai Lau]

On 9/13/24 2:39 AM, Tiago Lam wrote:
> This follows the same rationale provided for the ipv4 counterpart, where
> it now runs a reverse socket lookup when source addresses and/or ports
> are changed, on sendmsg, to check whether egress traffic should be
> allowed to go through or not.
>
> As with ipv4, the ipv6 sendmsg path is also extended here to support the
> IPV6_ORIGDSTADDR ancilliary message to be able to specify a source
> address/port.
>
> Suggested-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
> Signed-off-by: Tiago Lam <tiagolam@xxxxxxxxxxxxxx>
> ---
>   net/ipv6/datagram.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>   net/ipv6/udp.c      |  8 ++++--
>   2 files changed, 82 insertions(+), 2 deletions(-)
>
> diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
> index fff78496803d..4214dda1c320 100644
> --- a/net/ipv6/datagram.c
> +++ b/net/ipv6/datagram.c
> @@ -756,6 +756,27 @@ void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
>   }
>   EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
>   
> +static inline bool reverse_sk_lookup(struct flowi6 *fl6, struct sock *sk,
> +				     struct in6_addr *saddr, __be16 sport)
> +{
> +	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
> +	    (saddr && sport) &&
> +	    (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, saddr) || inet_sk(sk)->inet_sport != sport)) {
> +		struct sock *sk_egress;
> +
> +		bpf_sk_lookup_run_v6(sock_net(sk), IPPROTO_UDP, &fl6->daddr, fl6->fl6_dport,
> +				     saddr, ntohs(sport), 0, &sk_egress);

iirc, in the ingress path, the sk could also be selected by a tc bpf prog doing 
bpf_sk_assign. Then this re-run on sk_lookup may give an incorrect result?

In general, is it necessary to rerun any bpf prog if the user space has 
specified the IP[v6]_ORIGDSTADDR.

> +		if (!IS_ERR_OR_NULL(sk_egress) &&
> +		    atomic64_read(&sk_egress->sk_cookie) == atomic64_read(&sk->sk_cookie))
> +			return true;
> +
> +		net_info_ratelimited("No reverse socket lookup match for local addr %pI6:%d remote addr %pI6:%d\n",
> +				     &saddr, ntohs(sport), &fl6->daddr, ntohs(fl6->fl6_dport));
> +	}
> +
> +	return false;
> +}
> +
>   int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
>   			  struct msghdr *msg, struct flowi6 *fl6,
>   			  struct ipcm6_cookie *ipc6)
> @@ -844,7 +865,62 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
>   
>   			break;
>   		    }
> +		case IPV6_ORIGDSTADDR:
> +			{
> +			struct sockaddr_in6 *sockaddr_in;
> +			struct net_device *dev = NULL;
> +
> +			if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct sockaddr_in6))) {
> +				err = -EINVAL;
> +				goto exit_f;
> +			}
> +
> +			sockaddr_in = (struct sockaddr_in6 *)CMSG_DATA(cmsg);
> +
> +			addr_type = __ipv6_addr_type(&sockaddr_in->sin6_addr);
> +
> +			if (addr_type & IPV6_ADDR_LINKLOCAL)
> +				return -EINVAL;
> +
> +			/* If we're egressing with a different source address and/or port, we
> +			 * perform a reverse socket lookup.  The rationale behind this is that we
> +			 * can allow return UDP traffic that has ingressed through sk_lookup to
> +			 * also egress correctly. In case the reverse lookup fails, we
> +			 * continue with the normal path.
> +			 *
> +			 * The lookup is performed if either source address and/or port changed, and
> +			 * neither is "0".
> +			 */
> +			if (reverse_sk_lookup(fl6, sk, &sockaddr_in->sin6_addr,
> +					      sockaddr_in->sin6_port)) {
> +				/* Override the source port and address to use with the one we
> +				 * got in cmsg and bail early.
> +				 */
> +				fl6->saddr = sockaddr_in->sin6_addr;
> +				fl6->fl6_sport = sockaddr_in->sin6_port;
> +				break;
> +			}
>   
> +			if (addr_type != IPV6_ADDR_ANY) {
> +				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
> +
> +				if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) &&
> +				    !ipv6_chk_addr_and_flags(net,
> +							     &sockaddr_in->sin6_addr,
> +							     dev, !strict, 0,
> +							     IFA_F_TENTATIVE) &&
> +				    !ipv6_chk_acast_addr_src(net, dev,
> +							     &sockaddr_in->sin6_addr))
> +					err = -EINVAL;
> +				else
> +					fl6->saddr = sockaddr_in->sin6_addr;
> +			}
> +
> +			if (err)
> +				goto exit_f;
> +
> +			break;
> +			}
>   		case IPV6_FLOWINFO:
>   			if (cmsg->cmsg_len < CMSG_LEN(4)) {
>   				err = -EINVAL;
> diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
> index 6602a2e9cdb5..6121cbb71ad3 100644
> --- a/net/ipv6/udp.c
> +++ b/net/ipv6/udp.c
> @@ -1476,6 +1476,12 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
>   
>   	fl6->flowi6_uid = sk->sk_uid;
>   
> +	/* We use fl6's daddr and fl6_sport in the reverse sk_lookup done
> +	 * within ip6_datagram_send_ctl() now.
> +	 */
> +	fl6->daddr = *daddr;
> +	fl6->fl6_sport = inet->inet_sport;
> +
>   	if (msg->msg_controllen) {
>   		opt = &opt_space;
>   		memset(opt, 0, sizeof(struct ipv6_txoptions));
> @@ -1511,10 +1517,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
>   
>   	fl6->flowi6_proto = sk->sk_protocol;
>   	fl6->flowi6_mark = ipc6.sockc.mark;
> -	fl6->daddr = *daddr;
>   	if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr))
>   		fl6->saddr = np->saddr;
> -	fl6->fl6_sport = inet->inet_sport;
>   
>   	if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
>   		err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,