missing barriers in some of unix_sock ->addr and ->path accesses

[ Upstream commit ae3b564179bfd06f32d051b9e5d72ce4b2a07c37 ]

Several u->addr and u->path users are not holding any locks in
common with unix_bind().  unix_state_lock() is useless for those
purposes.

u->addr is assign-once and *(u->addr) is fully set up by the time
we set u->addr (all under unix_table_lock).  u->path is also
set in the same critical area, also before setting u->addr, and
any unix_sock with ->path filled will have non-NULL ->addr.

So setting ->addr with smp_store_release() is all we need for those
"lockless" users - just have them fetch ->addr with smp_load_acquire()
and don't even bother looking at ->path if they see NULL ->addr.

Users of ->addr and ->path fall into several classes now:
    1) ones that do smp_load_acquire(u->addr) and access *(u->addr)
and u->path only if smp_load_acquire() has returned non-NULL.
    2) places holding unix_table_lock.  These are guaranteed that
*(u->addr) is seen fully initialized.  If unix_sock is in one of the
"bound" chains, so's ->path.
    3) unix_sock_destructor() using ->addr is safe.  All places
that set u->addr are guaranteed to have seen all stores *(u->addr)
while holding a reference to u and unix_sock_destructor() is called
when (atomic) refcount hits zero.
    4) unix_release_sock() using ->path is safe.  unix_bind()
is serialized wrt unix_release() (normally - by struct file
refcount), and for the instances that had ->path set by unix_bind()
unix_release_sock() comes from unix_release(), so they are fine.
Instances that had it set in unix_stream_connect() either end up
attached to a socket (in unix_accept()), in which case the call
chain to unix_release_sock() and serialization are the same as in
the previous case, or they never get accept'ed and unix_release_sock()
is called when the listener is shut down and its queue gets purged.
In that case the listener's queue lock provides the barriers needed -
unix_stream_connect() shoves our unix_sock into listener's queue
under that lock right after having set ->path and eventual
unix_release_sock() caller picks them from that queue under the
same lock right before calling unix_release_sock().
    5) unix_find_other() use of ->path is pointless, but safe -
it happens with successful lookup by (abstract) name, so ->path.dentry
is guaranteed to be NULL there.

earlier-variant-reviewed-by: "Paul E. McKenney" <paulmck@linux.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 31 insertions, 20 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 915abe98174e..cecf51a5aec4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -891,7 +891,7 @@ retry:
 	addr->hash ^= sk->sk_type;
 
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
 	spin_unlock(&unix_table_lock);
 	err = 0;
@@ -1061,7 +1061,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	err = 0;
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(list, sk);
 
 out_unlock:
@@ -1332,15 +1332,29 @@ restart:
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
-	/* copy address information from listening to new sock*/
-	if (otheru->addr) {
-		atomic_inc(&otheru->addr->refcnt);
-		newu->addr = otheru->addr;
-	}
+	/* copy address information from listening to new sock
+	 *
+	 * The contents of *(otheru->addr) and otheru->path
+	 * are seen fully set up here, since we have found
+	 * otheru in hash under unix_table_lock.  Insertion
+	 * into the hash chain we'd found it in had been done
+	 * in an earlier critical area protected by unix_table_lock,
+	 * the same one where we'd set *(otheru->addr) contents,
+	 * as well as otheru->path and otheru->addr itself.
+	 *
+	 * Using smp_store_release() here to set newu->addr
+	 * is enough to make those stores, as well as stores
+	 * to newu->path visible to anyone who gets newu->addr
+	 * by smp_load_acquire().  IOW, the same warranties
+	 * as for unix_sock instances bound in unix_bind() or
+	 * in unix_autobind().
+	 */
 	if (otheru->path.dentry) {
 		path_get(&otheru->path);
 		newu->path = otheru->path;
 	}
+	atomic_inc(&otheru->addr->refcnt);
+	smp_store_release(&newu->addr, otheru->addr);
 
 	/* Set credentials */
 	copy_peercred(sk, other);
@@ -1453,7 +1467,7 @@ out:
 static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer)
 {
 	struct sock *sk = sock->sk;
-	struct unix_sock *u;
+	struct unix_address *addr;
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
 	int err = 0;
 
@@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_
 		sock_hold(sk);
 	}
 
-	u = unix_sk(sk);
-	unix_state_lock(sk);
-	if (!u->addr) {
+	addr = smp_load_acquire(&unix_sk(sk)->addr);
+	if (!addr) {
 		sunaddr->sun_family = AF_UNIX;
 		sunaddr->sun_path[0] = 0;
 		*uaddr_len = sizeof(short);
 	} else {
-		struct unix_address *addr = u->addr;
-
 		*uaddr_len = addr->len;
 		memcpy(sunaddr, addr->name, *uaddr_len);
 	}
-	unix_state_unlock(sk);
 	sock_put(sk);
 out:
 	return err;
@@ -2094,11 +2104,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
 
 static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 {
-	struct unix_sock *u = unix_sk(sk);
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
-	if (u->addr) {
-		msg->msg_namelen = u->addr->len;
-		memcpy(msg->msg_name, u->addr->name, u->addr->len);
+	if (addr) {
+		msg->msg_namelen = addr->len;
+		memcpy(msg->msg_name, addr->name, addr->len);
 	}
 }
 
@@ -2814,7 +2824,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
 			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
 			sock_i_ino(s));
 
-		if (u->addr) {
+		if (u->addr) {	// under unix_table_lock here
 			int i, len;
 			seq_putc(seq, ' ');
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 384c84e83462..3183d9b8ab33 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -10,7 +10,8 @@
 
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
-	struct unix_address *addr = unix_sk(sk)->addr;
+	/* might or might not have unix_table_lock */
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
 	if (!addr)
 		return 0;