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>

3 files changed, 28 insertions, 3 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac37bd53aee0..74ad2215e1ba 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  * @flags: Pointer to u32 which contains higher bits of BPF program
  *         return value (OR'ed together).
  *
- * socket is expected to be of type INET or INET6.
+ * socket is expected to be of type INET, INET6 or UNIX.
  *
  * This function will return %-EPERM if an attached program is found and
  * returned value != 1 during execution. In all other cases, 0 is returned.
@@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	/* Check socket family since not all sockets represent network
 	 * endpoint (e.g. AF_UNIX).
 	 */
-	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 &&
+	    sk->sk_family != AF_UNIX)
 		return 0;
 
 	if (!ctx.uaddr) {
@@ -2533,10 +2534,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_SOCK_OPS:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		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 NULL;
 		default:
 			return &bpf_get_retval_proto;
@@ -2548,10 +2552,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_SOCK_OPS:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		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 NULL;
 		default:
 			return &bpf_set_retval_proto;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6b5280f14a53..8677837f3deb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2446,14 +2446,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		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:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 			return 0;
 		default:
 			return -EINVAL;
@@ -3678,14 +3683,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_UNIX_CONNECT:
 	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:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UNIX_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
 	case BPF_CGROUP_UDP6_RECVMSG:
+	case BPF_CGROUP_UNIX_RECVMSG:
 		return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 	case BPF_CGROUP_SOCK_OPS:
 		return BPF_PROG_TYPE_SOCK_OPS;
@@ -3942,14 +3952,19 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET6_POST_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_UNIX_CONNECT:
 	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:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UNIX_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
 	case BPF_CGROUP_UDP6_RECVMSG:
+	case BPF_CGROUP_UNIX_RECVMSG:
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 	case BPF_CGROUP_SYSCTL:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eed7350e15f4..e777f50401b6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -14797,10 +14797,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
 		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
-		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
 			range = tnum_range(1, 1);
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)