Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "Hopefully the last pull request for this release. Fingers crossed:

   1) Only refcount ESP stats on full sockets, from Martin Willi.

   2) Missing barriers in AF_UNIX, from Al Viro.

   3) RCU protection fixes in ipv6 route code, from Paolo Abeni.

   4) Avoid false positives in untrusted GSO validation, from Willem de
      Bruijn.

   5) Forwarded mesh packets in mac80211 need more tailroom allocated,
      from Felix Fietkau.

   6) Use operstate consistently for linkup in team driver, from George
      Wilkie.

   7) ThunderX bug fixes from Vadim Lomovtsev. Mostly races between VF
      and PF code paths.

   8) Purge ipv6 exceptions during netdevice removal, from Paolo Abeni.

   9) nfp eBPF code gen fixes from Jiong Wang.

  10) bnxt_en firmware timeout fix from Michael Chan.

  11) Use after free in udp/udpv6 error handlers, from Paolo Abeni.

  12) Fix a race in x25_bind triggerable by syzbot, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (65 commits)
  net: phy: realtek: Dummy IRQ calls for RTL8366RB
  tcp: repaired skbs must init their tso_segs
  net/x25: fix a race in x25_bind()
  net: dsa: Remove documentation for port_fdb_prepare
  Revert "bridge: do not add port to router list when receives query with source 0.0.0.0"
  selftests: fib_tests: sleep after changing carrier. again.
  net: set static variable an initial value in atl2_probe()
  net: phy: marvell10g: Fix Multi-G advertisement to only advertise 10G
  bpf, doc: add bpf list as secondary entry to maintainers file
  udp: fix possible user after free in error handler
  udpv6: fix possible user after free in error handler
  fou6: fix proto error handler argument type
  udpv6: add the required annotation to mib type
  mdio_bus: Fix use-after-free on device_register fails
  net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255
  bnxt_en: Wait longer for the firmware message response to complete.
  bnxt_en: Fix typo in firmware message timeout logic.
  nfp: bpf: fix ALU32 high bits clearance bug
  nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K
  Documentation: networking: switchdev: Update port parent ID section
  ...

2 files changed, 35 insertions, 25 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 74d1eed7cbd4..a95d479caeea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -890,7 +890,7 @@ 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;
@@ -1060,7 +1060,7 @@ 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:
@@ -1331,15 +1331,29 @@ 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) {
-		refcount_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;
 	}
+	refcount_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 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 peer)
 		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;
 		err = sizeof(short);
 	} else {
-		struct unix_address *addr = u->addr;
-
 		err = addr->len;
 		memcpy(sunaddr, addr->name, addr->len);
 	}
-	unix_state_unlock(sk);
 	sock_put(sk);
 out:
 	return err;
@@ -2073,11 +2083,11 @@ 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);
 	}
 }
 
@@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk)
 	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	unix_state_lock(sk);
+	if (!smp_load_acquire(&unix_sk(sk)->addr))
+		return -ENOENT;
+
 	path = unix_sk(sk)->path;
-	if (!path.dentry) {
-		unix_state_unlock(sk);
+	if (!path.dentry)
 		return -ENOENT;
-	}
 
 	path_get(&path);
-	unix_state_unlock(sk);
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0)
@@ -2830,7 +2839,7 @@ 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;