[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <66ee8e42a8744_35dcb1294a0@willemb.c.googlers.com.notmuch>
Date: Sat, 21 Sep 2024 05:13:38 -0400
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: Tiago Lam <tiagolam@...udflare.com>,
"David S. Miller" <davem@...emloft.net>,
David Ahern <dsahern@...nel.org>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Eduard Zingerman <eddyz87@...il.com>,
Song Liu <song@...nel.org>,
Yonghong Song <yonghong.song@...ux.dev>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...ichev.me>,
Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>,
Mykola Lysenko <mykolal@...com>,
Shuah Khan <shuah@...nel.org>
Cc: netdev@...r.kernel.org,
linux-kernel@...r.kernel.org,
bpf@...r.kernel.org,
linux-kselftest@...r.kernel.org,
Jakub Sitnicki <jakub@...udflare.com>,
Tiago Lam <tiagolam@...udflare.com>,
kernel-team@...udflare.com
Subject: Re: [RFC PATCH v2 2/3] ipv6: Support setting src port in sendmsg().
Tiago Lam wrote:
> This follows the same rationale provided for the ipv4 counterpart, where
> the sendmsg() path is also extended here to support the IPV6_ORIGDSTADDR
> ancillary message to be able to specify a source address/port. This
> allows users to configure the source address and/or port egress traffic
> should be sent from.
>
> To limit its usage, a reverse socket lookup is performed to check if the
> configured egress source address and/or port have any ingress sk_lookup
> match. If it does, traffic is allowed to proceed, otherwise it falls
> back to the regular egress path.
>
> Suggested-by: Jakub Sitnicki <jakub@...udflare.com>
> Signed-off-by: Tiago Lam <tiagolam@...udflare.com>
> ---
> net/ipv6/datagram.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++++
> net/ipv6/udp.c | 8 ++++--
> 2 files changed, 85 insertions(+), 2 deletions(-)
>
> diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
> index fff78496803d..369c64a478ec 100644
> --- a/net/ipv6/datagram.c
> +++ b/net/ipv6/datagram.c
> @@ -756,6 +756,29 @@ 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);
> + if (!IS_ERR_OR_NULL(sk_egress) && sk_egress == sk)
> + 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 +867,63 @@ 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;
> + }
How come IPv6 runs the check in the cmsg handler, but ipv4 in sendmsg
directly? Can the two be symmetric?
> 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,
>
> --
> 2.34.1
>
Powered by blists - more mailing lists