The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to stable@vger.kernel.org.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 3632679d9e4f879f49949bb5b050e0de553e4739 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to 'stable@vger.kernel.org' --in-reply-to '2023052635-styling-unbutton-ac91@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..

Possible dependencies:

3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol") 91d0b78c5177 ("inet: Add IP_LOCAL_PORT_RANGE socket option") 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") d2c135619cb8 ("inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict()") ca7af0402550 ("tcp: add small random increments to the source port") ffa84b5ffb37 ("net: add netns refcount tracker to struct sock") 938cca9e4109 ("sock: fix /proc/net/sockstat underflow in sk_clone_lock()") 990c74e3f41d ("memcg: enable accounting for inet_bin_bucket cache") 333bb73f620e ("tcp: Keep TCP_CLOSE sockets in the reuseport group.") 5c040eaf5d17 ("tcp: Add num_closed_socks to struct sock_reuseport.") c579bd1b4021 ("tcp: add some entropy in __inet_hash_connect()") 190cc82489f4 ("tcp: change source port randomizarion at connect() time") bbc20b70424a ("net: reduce indentation level in sk_clone_lock()") 62ffc589abb1 ("net: refactor bind_bucket fastreuse into helper") 47ec5303d73e ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel nicolas.dichtel@6wind.com Date: Mon, 22 May 2023 14:08:20 +0200 Subject: [PATCH] ipv{4,6}/raw: fix output xfrm lookup wrt protocol

With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the protocol field of the flow structure, build by raw_sendmsg() / rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy lookup when some policies are defined with a protocol in the selector.

For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to specify the protocol. Just accept all values for IPPROTO_RAW socket.

For ipv4, the sin_port field of 'struct sockaddr_in' could not be used without breaking backward compatibility (the value of this field was never checked). Let's add a new kind of control message, so that the userland could specify which protocol is used.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com Signed-off-by: Paolo Abeni pabeni@redhat.com

diff --git a/include/net/ip.h b/include/net/ip.h index c3fffaa92d6e..acec504c469a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; }

#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52

#define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..eadf1c9ef7e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }

ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW;

if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL;

if (proto > 255)