[PATCH net-next v7 1/4] scm: add SO_PASSPIDFD and SCM_PIDFD
From: Alexander Mikhalitsyn
Date: Thu Jun 08 2023 - 16:27:04 EST
Implement SCM_PIDFD, a new type of CMSG type analogical to SCM_CREDENTIALS,
but it contains pidfd instead of plain pid, which allows programmers not
to care about PID reuse problem.
We mask SO_PASSPIDFD feature if CONFIG_UNIX is not builtin because
it depends on a pidfd_prepare() API which is not exported to the kernel
modules.
Idea comes from UAPI kernel group:
https://uapi-group.org/kernel-features/
Big thanks to Christian Brauner and Lennart Poettering for productive
discussions about this.
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Jakub Kicinski <kuba@xxxxxxxxxx>
Cc: Paolo Abeni <pabeni@xxxxxxxxxx>
Cc: Leon Romanovsky <leon@xxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx>
Cc: Lennart Poettering <mzxreary@xxxxxxxxxxx>
Cc: Luca Boccassi <bluca@xxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: netdev@xxxxxxxxxxxxxxx
Cc: linux-arch@xxxxxxxxxxxxxxx
Tested-by: Luca Boccassi <bluca@xxxxxxxxxx>
Reviewed-by: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx>
Reviewed-by: Christian Brauner <brauner@xxxxxxxxxx>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx>
---
v7:
- removed CONFIG_UNIX checks, because we've converted CONFIG_UNIX to be boolean
v6:
- disable feature when CONFIG_UNIX=n/m (pidfd_prepare API is not exported to modules)
v5:
- no changes
v4:
- fixed silent fd_install if writting of CMSG to the userspace fails (pointed by Christian)
v2:
According to review comments from Kuniyuki Iwashima and Christian Brauner:
- use pidfd_create(..) retval as a result
- whitespace change
---
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/linux/net.h | 1 +
include/linux/socket.h | 1 +
include/net/scm.h | 39 +++++++++++++++++++++++--
include/uapi/asm-generic/socket.h | 2 ++
net/core/sock.c | 11 +++++++
net/mptcp/sockopt.c | 1 +
net/unix/af_unix.c | 18 ++++++++----
tools/include/uapi/asm-generic/socket.h | 2 ++
12 files changed, 76 insertions(+), 7 deletions(-)
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 739891b94136..ff310613ae64 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -137,6 +137,8 @@
#define SO_RCVMARK 75
+#define SO_PASSPIDFD 76
+
#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 18f3d95ecfec..762dcb80e4ec 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -148,6 +148,8 @@
#define SO_RCVMARK 75
+#define SO_PASSPIDFD 76
+
#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 f486d3dfb6bb..df16a3e16d64 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -129,6 +129,8 @@
#define SO_RCVMARK 0x4049
+#define SO_PASSPIDFD 0x404A
+
#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 2fda57a3ea86..6e2847804fea 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -130,6 +130,8 @@
#define SO_RCVMARK 0x0054
+#define SO_PASSPIDFD 0x0055
+
#if !defined(__KERNEL__)
diff --git a/include/linux/net.h b/include/linux/net.h
index b73ad8e3c212..c234dfbe7a30 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -43,6 +43,7 @@ struct net;
#define SOCK_PASSSEC 4
#define SOCK_SUPPORT_ZC 5
#define SOCK_CUSTOM_SOCKOPT 6
+#define SOCK_PASSPIDFD 7
#ifndef ARCH_HAS_SOCKET_TYPES
/**
diff --git a/include/linux/socket.h b/include/linux/socket.h
index bd1cc3238851..3451a08f70d1 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -177,6 +177,7 @@ static inline size_t msg_data_left(struct msghdr *msg)
#define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */
#define SCM_CREDENTIALS 0x02 /* rw: struct ucred */
#define SCM_SECURITY 0x03 /* rw: security label */
+#define SCM_PIDFD 0x04 /* ro: pidfd (int) */
struct ucred {
__u32 pid;
diff --git a/include/net/scm.h b/include/net/scm.h
index 585adc1346bd..c67f765a165b 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -120,12 +120,44 @@ static inline bool scm_has_secdata(struct socket *sock)
}
#endif /* CONFIG_SECURITY_NETWORK */
+static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
+{
+ struct file *pidfd_file = NULL;
+ int pidfd;
+
+ /*
+ * put_cmsg() doesn't return an error if CMSG is truncated,
+ * that's why we need to opencode these checks here.
+ */
+ if ((msg->msg_controllen <= sizeof(struct cmsghdr)) ||
+ (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) {
+ msg->msg_flags |= MSG_CTRUNC;
+ return;
+ }
+
+ WARN_ON_ONCE(!scm->pid);
+ pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file);
+
+ if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) {
+ if (pidfd_file) {
+ put_unused_fd(pidfd);
+ fput(pidfd_file);
+ }
+
+ return;
+ }
+
+ if (pidfd_file)
+ fd_install(pidfd, pidfd_file);
+}
+
static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg,
struct scm_cookie *scm, int flags)
{
if (!msg->msg_control) {
- if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp ||
- scm_has_secdata(sock))
+ if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags) ||
+ scm->fp || scm_has_secdata(sock))
msg->msg_flags |= MSG_CTRUNC;
scm_destroy(scm);
return;
@@ -141,6 +173,9 @@ static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg,
put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds);
}
+ if (test_bit(SOCK_PASSPIDFD, &sock->flags))
+ scm_pidfd_recv(msg, scm);
+
scm_destroy_cred(scm);
scm_passec(sock, msg, scm);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 638230899e98..b76169fdb80b 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -132,6 +132,8 @@
#define SO_RCVMARK 75
+#define SO_PASSPIDFD 76
+
#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 24f2761bdb1d..ed4eb4ba738b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1246,6 +1246,13 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ if (valbool)
+ set_bit(SOCK_PASSPIDFD, &sock->flags);
+ else
+ clear_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_TIMESTAMP_OLD:
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
@@ -1732,6 +1739,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_PEERCRED:
{
struct ucred peercred;
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index d4258869ac48..e172a5848b0d 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -355,6 +355,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_BROADCAST:
case SO_BSDCOMPAT:
case SO_PASSCRED:
+ case SO_PASSPIDFD:
case SO_PASSSEC:
case SO_RXQ_OVFL:
case SO_WIFI_STATUS:
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 653136d68b32..c46c2f5d860c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1361,7 +1361,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) &&
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
!unix_sk(sk)->addr) {
err = unix_autobind(sk);
if (err)
@@ -1469,7 +1470,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -1670,6 +1672,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
{
if (test_bit(SOCK_PASSCRED, &old->flags))
set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSPIDFD, &old->flags))
+ set_bit(SOCK_PASSPIDFD, &new->flags);
if (test_bit(SOCK_PASSSEC, &old->flags))
set_bit(SOCK_PASSSEC, &new->flags);
}
@@ -1819,8 +1823,10 @@ static bool unix_passcred_enabled(const struct socket *sock,
const struct sock *other)
{
return test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags) ||
!other->sk_socket ||
- test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags) ||
+ test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags);
}
/*
@@ -1904,7 +1910,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
goto out;
}
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -2718,7 +2725,8 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
/* Never glue messages from different writers */
if (!unix_skb_scm_eq(skb, &scm))
break;
- } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
+ } else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) {
/* Copy credentials */
scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
unix_set_secdata(&scm, skb);
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index 8756df13be50..fbbc4bf53ee3 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -121,6 +121,8 @@
#define SO_RCVMARK 75
+#define SO_PASSPIDFD 76
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
--
2.34.1