Re: [PATCH v3 net-next 8/9] af_unix: Introduce SO_PASSRIGHTS.

As long as recvmsg() or recvmmsg() is used with cmsg, it is not
possible to avoid receiving file descriptors via SCM_RIGHTS.

This behaviour has occasionally been flagged as problematic, as
it can be (ab)used to trigger DoS during close(), for example, by
passing a FUSE-controlled fd or a hung NFS fd.

For instance, as noted on the uAPI Group page [0], an untrusted peer
could send a file descriptor pointing to a hung NFS mount and then
close it.  Once the receiver calls recvmsg() with msg_control, the
descriptor is automatically installed, and then the responsibility
for the final close() now falls on the receiver, which may result
in blocking the process for a long time.

Regarding this, systemd calls cmsg_close_all() [1] after each
recvmsg() to close() unwanted file descriptors sent via SCM_RIGHTS.

However, this cannot work around the issue at all, because the final
fput() may still occur on the receiver's side once sendmsg() with
SCM_RIGHTS succeeds.  Also, even filtering by LSM at recvmsg() does
not work for the same reason.

Thus, we need a better way to refuse SCM_RIGHTS at sendmsg().

Let's introduce SO_PASSRIGHTS to disable SCM_RIGHTS.

Note that this option is enabled by default for backward
compatibility.

Link: https://uapi-group.org/kernel-features/#disabling-reception-of-scm_rights-for-af_unix-sockets #[0]
Link: https://github.com/systemd/systemd/blob/v257.5/src/basic/fd-util.c#L612-L628 #[1]
Signed-off-by: Kuniyuki Iwashima <redacted>
---
v3: Return -EOPNOTSUPP for getsockopt()
---
 arch/alpha/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h     |  2 ++
 arch/parisc/include/uapi/asm/socket.h   |  2 ++
 arch/sparc/include/uapi/asm/socket.h    |  2 ++
 include/net/sock.h                      |  4 +++-
 include/uapi/asm-generic/socket.h       |  2 ++
 net/core/sock.c                         | 14 ++++++++++++++
 net/unix/af_unix.c                      | 22 ++++++++++++++++++++--
 tools/include/uapi/asm-generic/socket.h |  2 ++
 9 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 3df5f2dd4c0f..8f1f18adcdb5 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h

@@ -150,6 +150,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 22fa8f19924a..31ac655b7837 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h

@@ -161,6 +161,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 96831c988606..1f2d5b7a7f5d 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h

@@ -142,6 +142,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	0x4050
 
+#define SO_PASSRIGHTS		0x4051
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 5b464a568664..adcba7329386 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h

@@ -143,6 +143,8 @@
 
 #define SO_RCVPRIORITY           0x005b
 
+#define SO_PASSRIGHTS            0x005c
+
 #if !defined(__KERNEL__)
 
 

diff --git a/include/net/sock.h b/include/net/sock.h
index 77232a098934..17fb6b8c4b6e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h

@@ -341,6 +341,7 @@ struct sk_filter;
   *	@sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS
   *	@sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY
   *	@sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD
+  *	@sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS
   *	@sk_scm_unused: unused flags for scm_recv()
   *	@ns_tracker: tracker for netns reference
   *	@sk_user_frags: xarray of pages the user is holding a reference on.

@@ -534,7 +535,8 @@ struct sock {
 		u8		sk_scm_credentials : 1,
 				sk_scm_security : 1,
 				sk_scm_pidfd : 1,
-				sk_scm_unused : 5;
+				sk_scm_rights : 1,
+				sk_scm_unused : 4;
 	};
 	u8			sk_clockid;
 	u8			sk_txtime_deadline_mode : 1,

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index aa5016ff3d91..f333a0ac4ee4 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h

@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

diff --git a/net/core/sock.c b/net/core/sock.c
index 381abf8f25b7..0cb52e590094 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c

@@ -1571,6 +1571,13 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 			ret = -EOPNOTSUPP;
 		break;
 
+	case SO_PASSRIGHTS:
+		if (sk_is_unix(sk))
+			sk->sk_scm_rights = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
+
 	case SO_INCOMING_CPU:
 		reuseport_update_incoming_cpu(sk, val);
 		break;

@@ -1879,6 +1886,13 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = sk->sk_scm_pidfd;
 		break;
 
+	case SO_PASSRIGHTS:
+		if (!sk_is_unix(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_rights;