bpf: Implement cgroup sockaddr hooks for unix sockets

These hooks allows intercepting connect(), getsockname(),
getpeername(), sendmsg() and recvmsg() for unix sockets. The unix
socket hooks get write access to the address length because the
address length is not fixed when dealing with unix sockets and
needs to be modified when a unix socket address is modified by
the hook. Because abstract socket unix addresses start with a
NUL byte, we cannot recalculate the socket address in kernelspace
after running the hook by calculating the length of the unix socket
path using strlen().

These hooks can be used when users want to multiplex syscall to a
single unix socket to multiple different processes behind the scenes
by redirecting the connect() and other syscalls to process specific
sockets.

We do not implement support for intercepting bind() because when
using bind() with unix sockets with a pathname address, this creates
an inode in the filesystem which must be cleaned up. If we rewrite
the address, the user might try to clean up the wrong file, leaking
the socket in the filesystem where it is never cleaned up. Until we
figure out a solution for this (and a use case for intercepting bind()),
we opt to not allow rewriting the sockaddr in bind() calls.

We also implement recvmsg() support for connected streams so that
after a connect() that is modified by a sockaddr hook, any corresponding
recmvsg() on the connected socket can also be modified to make the
connected program think it is connected to the "intended" remote.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

2 files changed, 46 insertions, 3 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index ff0bd9f20b95..cc2e4babc85f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7875,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_setsockopt_proto;
 		default:
 			return NULL;
@@ -7893,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_getsockopt_proto;
 		default:
 			return NULL;
@@ -8948,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size,
 	if (off % size != 0)
 		return false;
 
-	/* Disallow access to IPv6 fields from IPv4 contex and vise
-	 * versa.
+	/* Disallow access to fields not belonging to the attach type's address
+	 * family.
 	 */
 	switch (off) {
 	case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3e8a04a13668..e10d07c76044 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -116,6 +116,7 @@
 #include <linux/freezer.h>
 #include <linux/file.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf-cgroup.h>
 
 #include "scm.h"
 
@@ -1381,6 +1382,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
+		err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen);
+		if (err)
+			goto out;
+
 		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
 		    !unix_sk(sk)->addr) {
@@ -1490,6 +1495,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	if (err)
 		goto out;
 
+	err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len);
+	if (err)
+		goto out;
+
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
 		err = unix_autobind(sk);
@@ -1770,6 +1779,13 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	} else {
 		err = addr->len;
 		memcpy(sunaddr, addr->name, addr->len);
+
+		if (peer)
+			BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err,
+					       CGROUP_UNIX_GETPEERNAME);
+		else
+			BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err,
+					       CGROUP_UNIX_GETSOCKNAME);
 	}
 	sock_put(sk);
 out:
@@ -1922,6 +1938,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 		err = unix_validate_addr(sunaddr, msg->msg_namelen);
 		if (err)
 			goto out;
+
+		err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk,
+							    msg->msg_name,
+							    &msg->msg_namelen,
+							    NULL);
+		if (err)
+			goto out;
 	} else {
 		sunaddr = NULL;
 		err = -ENOTCONN;
@@ -2390,9 +2413,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
 						EPOLLOUT | EPOLLWRNORM |
 						EPOLLWRBAND);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
 		unix_copy_addr(msg, skb->sk);
 
+		BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk,
+						      msg->msg_name,
+						      &msg->msg_namelen);
+	}
+
 	if (size > skb->len - skip)
 		size = skb->len - skip;
 	else if (size < skb->len - skip)
@@ -2744,6 +2772,11 @@ unlock:
 			DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr,
 					 state->msg->msg_name);
 			unix_copy_addr(state->msg, skb->sk);
+
+			BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk,
+							      state->msg->msg_name,
+							      &state->msg->msg_namelen);
+
 			sunaddr = NULL;
 		}