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>

1 files changed, 17 insertions, 0 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 31561e789715..98b8cea904fe 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 	CGROUP_ATYPE(CGROUP_INET6_BIND);
 	CGROUP_ATYPE(CGROUP_INET4_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET6_CONNECT);
+	CGROUP_ATYPE(CGROUP_UNIX_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET4_POST_BIND);
 	CGROUP_ATYPE(CGROUP_INET6_POST_BIND);
 	CGROUP_ATYPE(CGROUP_UDP4_SENDMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_SENDMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_SENDMSG);
 	CGROUP_ATYPE(CGROUP_SYSCTL);
 	CGROUP_ATYPE(CGROUP_UDP4_RECVMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_RECVMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_RECVMSG);
 	CGROUP_ATYPE(CGROUP_GETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_SETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE);
 	default:
 		return CGROUP_BPF_ATTACH_TYPE_INVALID;
@@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL)
+
 #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx)
 
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx)
+
 #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL)
 
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL)
+
 /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
  * fullsock and its parent fullsock cannot be traced by
  * sk_to_full_sk().
@@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })