1 files changed, 185 insertions, 113 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 34945de1fb1f..2e2e9997a68e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -77,46 +77,40 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/sched/signal.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/stat.h>
+#include <linux/bpf-cgroup.h>
+#include <linux/btf_ids.h>
 #include <linux/dcache.h>
-#include <linux/namei.h>
-#include <linux/socket.h>
-#include <linux/un.h>
+#include <linux/errno.h>
 #include <linux/fcntl.h>
+#include <linux/file.h>
 #include <linux/filter.h>
-#include <linux/termios.h>
-#include <linux/sockios.h>
-#include <linux/net.h>
-#include <linux/in.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <net/net_namespace.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/af_unix.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <net/scm.h>
+#include <linux/fs_struct.h>
 #include <linux/init.h>
-#include <linux/poll.h>
-#include <linux/rtnetlink.h>
+#include <linux/kernel.h>
 #include <linux/mount.h>
-#include <net/checksum.h>
+#include <linux/namei.h>
+#include <linux/net.h>
+#include <linux/pidfs.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/sched/signal.h>
 #include <linux/security.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
 #include <linux/splice.h>
-#include <linux/freezer.h>
-#include <linux/file.h>
-#include <linux/btf_ids.h>
-#include <linux/bpf-cgroup.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <net/af_unix.h>
+#include <net/net_namespace.h>
+#include <net/scm.h>
+#include <net/tcp_states.h>
+#include <uapi/linux/sockios.h>
+#include <uapi/linux/termios.h>
+
+#include "af_unix.h"
 
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
@@ -652,6 +646,9 @@ static void unix_sock_destructor(struct sock *sk)
 		return;
 	}
 
+	if (sk->sk_peer_pid)
+		pidfs_put_pid(sk->sk_peer_pid);
+
 	if (u->addr)
 		unix_release_addr(u->addr);
 
@@ -743,13 +740,48 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		unix_gc();		/* Garbage collect fds */
 }
 
-static void init_peercred(struct sock *sk)
+struct unix_peercred {
+	struct pid *peer_pid;
+	const struct cred *peer_cred;
+};
+
+static inline int prepare_peercred(struct unix_peercred *peercred)
 {
-	sk->sk_peer_pid = get_pid(task_tgid(current));
-	sk->sk_peer_cred = get_current_cred();
+	struct pid *pid;
+	int err;
+
+	pid = task_tgid(current);
+	err = pidfs_register_pid(pid);
+	if (likely(!err)) {
+		peercred->peer_pid = get_pid(pid);
+		peercred->peer_cred = get_current_cred();
+	}
+	return err;
+}
+
+static void drop_peercred(struct unix_peercred *peercred)
+{
+	const struct cred *cred = NULL;
+	struct pid *pid = NULL;
+
+	might_sleep();
+
+	swap(peercred->peer_pid, pid);
+	swap(peercred->peer_cred, cred);
+
+	pidfs_put_pid(pid);
+	put_pid(pid);
+	put_cred(cred);
 }
 
-static void update_peercred(struct sock *sk)
+static inline void init_peercred(struct sock *sk,
+				 const struct unix_peercred *peercred)
+{
+	sk->sk_peer_pid = peercred->peer_pid;
+	sk->sk_peer_cred = peercred->peer_cred;
+}
+
+static void update_peercred(struct sock *sk, struct unix_peercred *peercred)
 {
 	const struct cred *old_cred;
 	struct pid *old_pid;
@@ -757,11 +789,11 @@ static void update_peercred(struct sock *sk)
 	spin_lock(&sk->sk_peer_lock);
 	old_pid = sk->sk_peer_pid;
 	old_cred = sk->sk_peer_cred;
-	init_peercred(sk);
+	init_peercred(sk, peercred);
 	spin_unlock(&sk->sk_peer_lock);
 
-	put_pid(old_pid);
-	put_cred(old_cred);
+	peercred->peer_pid = old_pid;
+	peercred->peer_cred = old_cred;
 }
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
@@ -770,15 +802,22 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
 
 	spin_lock(&sk->sk_peer_lock);
 	sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
+	pidfs_get_pid(sk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
 	spin_unlock(&sk->sk_peer_lock);
 }
 
+static bool unix_may_passcred(const struct sock *sk)
+{
+	return sk->sk_scm_credentials || sk->sk_scm_pidfd;
+}
+
 static int unix_listen(struct socket *sock, int backlog)
 {
 	int err;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
+	struct unix_peercred peercred = {};
 
 	err = -EOPNOTSUPP;
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
@@ -786,6 +825,9 @@ static int unix_listen(struct socket *sock, int backlog)
 	err = -EINVAL;
 	if (!READ_ONCE(u->addr))
 		goto out;	/* No listens on an unbound socket */
+	err = prepare_peercred(&peercred);
+	if (err)
+		goto out;
 	unix_state_lock(sk);
 	if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
 		goto out_unlock;
@@ -795,11 +837,12 @@ static int unix_listen(struct socket *sock, int backlog)
 	WRITE_ONCE(sk->sk_state, TCP_LISTEN);
 
 	/* set credentials so connect can copy them */
-	update_peercred(sk);
+	update_peercred(sk, &peercred);
 	err = 0;
 
 out_unlock:
 	unix_state_unlock(sk);
+	drop_peercred(&peercred);
 out:
 	return err;
 }
@@ -959,13 +1002,6 @@ static void unix_close(struct sock *sk, long timeout)
 	 */
 }
 
-static void unix_unhash(struct sock *sk)
-{
-	/* Nothing to do here, unix socket does not need a ->unhash().
-	 * This is merely for sockmap.
-	 */
-}
-
 static bool unix_bpf_bypass_getsockopt(int level, int optname)
 {
 	if (level == SOL_SOCKET) {
@@ -996,7 +1032,6 @@ struct proto unix_stream_proto = {
 	.owner			= THIS_MODULE,
 	.obj_size		= sizeof(struct unix_sock),
 	.close			= unix_close,
-	.unhash			= unix_unhash,
 	.bpf_bypass_getsockopt	= unix_bpf_bypass_getsockopt,
 #ifdef CONFIG_BPF_SYSCALL
 	.psock_update_sk_prot	= unix_stream_bpf_update_proto,
@@ -1027,6 +1062,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 
 	sock_init_data(sock, sk);
 
+	sk->sk_scm_rights	= 1;
 	sk->sk_hash		= unix_unbound_hash(sk);
 	sk->sk_allocation	= GFP_KERNEL_ACCOUNT;
 	sk->sk_write_space	= unix_write_space;
@@ -1110,7 +1146,7 @@ static int unix_release(struct socket *sock)
 }
 
 static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len,
-				  int type)
+				  int type, int flags)
 {
 	struct inode *inode;
 	struct path path;
@@ -1118,13 +1154,39 @@ static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len,
 	int err;
 
 	unix_mkname_bsd(sunaddr, addr_len);
-	err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path);
-	if (err)
-		goto fail;
 
-	err = path_permission(&path, MAY_WRITE);
-	if (err)
-		goto path_put;
+	if (flags & SOCK_COREDUMP) {
+		const struct cred *cred;
+		struct cred *kcred;
+		struct path root;
+
+		kcred = prepare_kernel_cred(&init_task);
+		if (!kcred) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		task_lock(&init_task);
+		get_fs_root(init_task.fs, &root);
+		task_unlock(&init_task);
+
+		cred = override_creds(kcred);
+		err = vfs_path_lookup(root.dentry, root.mnt, sunaddr->sun_path,
+				      LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS |
+				      LOOKUP_NO_MAGICLINKS, &path);
+		put_cred(revert_creds(cred));
+		path_put(&root);
+		if (err)
+			goto fail;
+	} else {
+		err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path);
+		if (err)
+			goto fail;
+
+		err = path_permission(&path, MAY_WRITE);
+		if (err)
+			goto path_put;
+	}
 
 	err = -ECONNREFUSED;
 	inode = d_backing_inode(path.dentry);
@@ -1174,12 +1236,12 @@ static struct sock *unix_find_abstract(struct net *net,
 
 static struct sock *unix_find_other(struct net *net,
 				    struct sockaddr_un *sunaddr,
-				    int addr_len, int type)
+				    int addr_len, int type, int flags)
 {
 	struct sock *sk;
 
 	if (sunaddr->sun_path[0])
-		sk = unix_find_bsd(sunaddr, addr_len, type);
+		sk = unix_find_bsd(sunaddr, addr_len, type, flags);
 	else
 		sk = unix_find_abstract(net, sunaddr, addr_len, type);
 
@@ -1428,16 +1490,14 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
-		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-		    !READ_ONCE(unix_sk(sk)->addr)) {
+		if (unix_may_passcred(sk) && !READ_ONCE(unix_sk(sk)->addr)) {
 			err = unix_autobind(sk);
 			if (err)
 				goto out;
 		}
 
 restart:
-		other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type);
+		other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type, 0);
 		if (IS_ERR(other)) {
 			err = PTR_ERR(other);
 			goto out;
@@ -1508,7 +1568,6 @@ out:
 }
 
 static long unix_wait_for_peer(struct sock *other, long timeo)
-	__releases(&unix_sk(other)->lock)
 {
 	struct unix_sock *u = unix_sk(other);
 	int sched;
@@ -1535,6 +1594,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	struct sock *sk = sock->sk, *newsk = NULL, *other = NULL;
 	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
+	struct unix_peercred peercred = {};
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb = NULL;
 	unsigned char state;
@@ -1549,9 +1609,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	if (err)
 		goto out;
 
-	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-	    !READ_ONCE(u->addr)) {
+	if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -1571,6 +1629,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 	}
 
+	err = prepare_peercred(&peercred);
+	if (err)
+		goto out;
+
 	/* Allocate skb for sending to listening sock */
 	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
 	if (!skb) {
@@ -1580,7 +1642,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 
 restart:
 	/*  Find listening sock. */
-	other = unix_find_other(net, sunaddr, addr_len, sk->sk_type);
+	other = unix_find_other(net, sunaddr, addr_len, sk->sk_type, flags);
 	if (IS_ERR(other)) {
 		err = PTR_ERR(other);
 		goto out_free_skb;
@@ -1643,10 +1705,12 @@ restart:
 	/* The way is open! Fastly set all the necessary fields... */
 
 	sock_hold(sk);
-	unix_peer(newsk)	= sk;
-	newsk->sk_state		= TCP_ESTABLISHED;
-	newsk->sk_type		= sk->sk_type;
-	init_peercred(newsk);
+	unix_peer(newsk) = sk;
+	newsk->sk_state = TCP_ESTABLISHED;
+	newsk->sk_type = sk->sk_type;
+	newsk->sk_scm_recv_flags = other->sk_scm_recv_flags;
+	init_peercred(newsk, &peercred);
+
 	newu = unix_sk(newsk);
 	newu->listener = other;
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
@@ -1705,20 +1769,33 @@ out_free_skb:
 out_free_sk:
 	unix_release_sock(newsk, 0);
 out:
+	drop_peercred(&peercred);
 	return err;
 }
 
 static int unix_socketpair(struct socket *socka, struct socket *sockb)
 {
+	struct unix_peercred ska_peercred = {}, skb_peercred = {};
 	struct sock *ska = socka->sk, *skb = sockb->sk;
+	int err;
+
+	err = prepare_peercred(&ska_peercred);
+	if (err)
+		return err;
+
+	err = prepare_peercred(&skb_peercred);
+	if (err) {
+		drop_peercred(&ska_peercred);
+		return err;
+	}
 
 	/* Join our sockets back to back */
 	sock_hold(ska);
 	sock_hold(skb);
 	unix_peer(ska) = skb;
 	unix_peer(skb) = ska;
-	init_peercred(ska);
-	init_peercred(skb);
+	init_peercred(ska, &ska_peercred);
+	init_peercred(skb, &skb_peercred);
 
 	ska->sk_state = TCP_ESTABLISHED;
 	skb->sk_state = TCP_ESTABLISHED;
@@ -1727,17 +1804,6 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
 	return 0;
 }
 
-static void unix_sock_inherit_flags(const struct socket *old,
-				    struct socket *new)
-{
-	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);
-}
-
 static int unix_accept(struct socket *sock, struct socket *newsock,
 		       struct proto_accept_arg *arg)
 {
@@ -1774,7 +1840,6 @@ static int unix_accept(struct socket *sock, struct socket *newsock,
 	unix_state_lock(tsk);
 	unix_update_edges(unix_sk(tsk));
 	newsock->state = SS_CONNECTED;
-	unix_sock_inherit_flags(sock, newsock);
 	sock_graft(tsk, newsock);
 	unix_state_unlock(tsk);
 	return 0;
@@ -1883,7 +1948,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 {
 	int err = 0;
 
-	UNIXCB(skb).pid  = get_pid(scm->pid);
+	UNIXCB(skb).pid = get_pid(scm->pid);
 	UNIXCB(skb).uid = scm->creds.uid;
 	UNIXCB(skb).gid = scm->creds.gid;
 	UNIXCB(skb).fp = NULL;
@@ -1895,28 +1960,19 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 	return err;
 }
 
-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_PASSPIDFD, &other->sk_socket->flags);
-}
-
 /*
  * Some apps rely on write() giving SCM_CREDENTIALS
  * We include credentials if source or destination socket
  * asserted SOCK_PASSCRED.
  */
-static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
-			    const struct sock *other)
+static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
+				 const struct sock *other)
 {
 	if (UNIXCB(skb).pid)
 		return;
-	if (unix_passcred_enabled(sock, other)) {
-		UNIXCB(skb).pid  = get_pid(task_tgid(current));
+
+	if (unix_may_passcred(sk) || unix_may_passcred(other)) {
+		UNIXCB(skb).pid = get_pid(task_tgid(current));
 		current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
 	}
 }
@@ -1992,9 +2048,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out;
 	}
 
-	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-	    !READ_ONCE(u->addr)) {
+	if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -2036,7 +2090,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_namelen) {
 lookup:
 		other = unix_find_other(sock_net(sk), msg->msg_name,
-					msg->msg_namelen, sk->sk_type);
+					msg->msg_namelen, sk->sk_type, 0);
 		if (IS_ERR(other)) {
 			err = PTR_ERR(other);
 			goto out_free;
@@ -2102,6 +2156,7 @@ restart_locked:
 			goto out_sock_put;
 		}
 
+		sock_put(other);
 		goto lookup;
 	}
 
@@ -2110,6 +2165,11 @@ restart_locked:
 		goto out_unlock;
 	}
 
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+
 	if (sk->sk_type != SOCK_SEQPACKET) {
 		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
 		if (err)
@@ -2156,7 +2216,8 @@ restart_locked:
 
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
-	maybe_add_creds(skb, sock, other);
+
+	unix_maybe_add_creds(skb, sk, other);
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
 	unix_state_unlock(other);
@@ -2184,14 +2245,14 @@ out:
 #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768))
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other,
+static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 		     struct scm_cookie *scm, bool fds_sent)
 {
 	struct unix_sock *ousk = unix_sk(other);
 	struct sk_buff *skb;
 	int err;
 
-	skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err);
+	skb = sock_alloc_send_skb(sk, 1, msg->msg_flags & MSG_DONTWAIT, &err);
 
 	if (!skb)
 		return err;
@@ -2210,12 +2271,16 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 
 	if (sock_flag(other, SOCK_DEAD) ||
 	    (other->sk_shutdown & RCV_SHUTDOWN)) {
-		unix_state_unlock(other);
 		err = -EPIPE;
-		goto out;
+		goto out_unlock;
+	}
+
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
 	}
 
-	maybe_add_creds(skb, sock, other);
+	unix_maybe_add_creds(skb, sk, other);
 	scm_stat_add(other, skb);
 
 	spin_lock(&other->sk_receive_queue.lock);
@@ -2228,6 +2293,8 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	other->sk_data_ready(other);
 
 	return 0;
+out_unlock:
+	unix_state_unlock(other);
 out:
 	consume_skb(skb);
 	return err;
@@ -2331,7 +2398,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		    (other->sk_shutdown & RCV_SHUTDOWN))
 			goto out_pipe_unlock;
 
-		maybe_add_creds(skb, sock, other);
+		if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+			unix_state_unlock(other);
+			err = -EPERM;
+			goto out_free;
+		}
+
+		unix_maybe_add_creds(skb, sk, other);
 		scm_stat_add(other, skb);
 		skb_queue_tail(&other->sk_receive_queue, skb);
 		unix_state_unlock(other);
@@ -2341,7 +2414,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 	if (msg->msg_flags & MSG_OOB) {
-		err = queue_oob(sock, msg, other, &scm, fds_sent);
+		err = queue_oob(sk, msg, other, &scm, fds_sent);
 		if (err)
 			goto out_err;
 		sent++;
@@ -2863,8 +2936,7 @@ unlock:
 			/* Never glue messages from different writers */
 			if (!unix_skb_scm_eq(skb, &scm))
 				break;
-		} else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-			   test_bit(SOCK_PASSPIDFD, &sock->flags)) {
+		} else if (unix_may_passcred(sk)) {
 			/* Copy credentials */
 			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			unix_set_secdata(&scm, skb);