Merge tag 'net-5.15-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes, including fixes from mac80211, netfilter and bpf.

  Current release - regressions:

   - bpf, cgroup: assign cgroup in cgroup_sk_alloc when called from
     interrupt

   - mdio: revert mechanical patches which broke handling of optional
     resources

   - dev_addr_list: prevent address duplication

  Previous releases - regressions:

   - sctp: break out if skb_header_pointer returns NULL in sctp_rcv_ootb
     (NULL deref)

   - Revert "mac80211: do not use low data rates for data frames with no
     ack flag", fixing broadcast transmissions

   - mac80211: fix use-after-free in CCMP/GCMP RX

   - netfilter: include zone id in tuple hash again, minimize collisions

   - netfilter: nf_tables: unlink table before deleting it (race -> UAF)

   - netfilter: log: work around missing softdep backend module

   - mptcp: don't return sockets in foreign netns

   - sched: flower: protect fl_walk() with rcu (race -> UAF)

   - ixgbe: fix NULL pointer dereference in ixgbe_xdp_setup

   - smsc95xx: fix stalled rx after link change

   - enetc: fix the incorrect clearing of IF_MODE bits

   - ipv4: fix rtnexthop len when RTA_FLOW is present

   - dsa: mv88e6xxx: 6161: use correct MAX MTU config method for this
     SKU

   - e100: fix length calculation & buffer overrun in ethtool::get_regs

  Previous releases - always broken:

   - mac80211: fix using stale frag_tail skb pointer in A-MSDU tx

   - mac80211: drop frames from invalid MAC address in ad-hoc mode

   - af_unix: fix races in sk_peer_pid and sk_peer_cred accesses (race
     -> UAF)

   - bpf, x86: Fix bpf mapping of atomic fetch implementation

   - bpf: handle return value of BPF_PROG_TYPE_STRUCT_OPS prog

   - netfilter: ip6_tables: zero-initialize fragment offset

   - mhi: fix error path in mhi_net_newlink

   - af_unix: return errno instead of NULL in unix_create1() when over
     the fs.file-max limit

  Misc:

   - bpf: exempt CAP_BPF from checks against bpf_jit_limit

   - netfilter: conntrack: make max chain length random, prevent
     guessing buckets by attackers

   - netfilter: nf_nat_masquerade: make async masq_inet6_event handling
     generic, defer conntrack walk to work queue (prevent hogging RTNL
     lock)"

* tag 'net-5.15-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (77 commits)
  af_unix: fix races in sk_peer_pid and sk_peer_cred accesses
  net: stmmac: fix EEE init issue when paired with EEE capable PHYs
  net: dev_addr_list: handle first address in __hw_addr_add_ex
  net: sched: flower: protect fl_walk() with rcu
  net: introduce and use lock_sock_fast_nested()
  net: phy: bcm7xxx: Fixed indirect MMD operations
  net: hns3: disable firmware compatible features when uninstall PF
  net: hns3: fix always enable rx vlan filter problem after selftest
  net: hns3: PF enable promisc for VF when mac table is overflow
  net: hns3: fix show wrong state when add existing uc mac address
  net: hns3: fix mixed flag HCLGE_FLAG_MQPRIO_ENABLE and HCLGE_FLAG_DCB_ENABLE
  net: hns3: don't rollback when destroy mqprio fail
  net: hns3: remove tc enable checking
  net: hns3: do not allow call hns3_nic_net_open repeatedly
  ixgbe: Fix NULL pointer dereference in ixgbe_xdp_setup
  net: bridge: mcast: Associate the seqcount with its protecting lock.
  net: mdio-ipq4019: Fix the error for an optional regs resource
  net: hns3: fix hclge_dbg_dump_tm_pg() stack usage
  net: mdio: mscc-miim: Fix the mdio controller
  af_unix: Return errno instead of NULL in unix_create1().
  ...

1 files changed, 60 insertions, 23 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 92345c9bb60c..efac5989edb5 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 static void init_peercred(struct sock *sk)
 {
-	put_pid(sk->sk_peer_pid);
-	if (sk->sk_peer_cred)
-		put_cred(sk->sk_peer_cred);
+	const struct cred *old_cred;
+	struct pid *old_pid;
+
+	spin_lock(&sk->sk_peer_lock);
+	old_pid = sk->sk_peer_pid;
+	old_cred = sk->sk_peer_cred;
 	sk->sk_peer_pid  = get_pid(task_tgid(current));
 	sk->sk_peer_cred = get_current_cred();
+	spin_unlock(&sk->sk_peer_lock);
+
+	put_pid(old_pid);
+	put_cred(old_cred);
 }
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
 {
-	put_pid(sk->sk_peer_pid);
-	if (sk->sk_peer_cred)
-		put_cred(sk->sk_peer_cred);
+	const struct cred *old_cred;
+	struct pid *old_pid;
+
+	if (sk < peersk) {
+		spin_lock(&sk->sk_peer_lock);
+		spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock(&peersk->sk_peer_lock);
+		spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+	}
+	old_pid = sk->sk_peer_pid;
+	old_cred = sk->sk_peer_cred;
 	sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
+
+	spin_unlock(&sk->sk_peer_lock);
+	spin_unlock(&peersk->sk_peer_lock);
+
+	put_pid(old_pid);
+	put_cred(old_cred);
 }
 
 static int unix_listen(struct socket *sock, int backlog)
@@ -828,20 +850,25 @@ struct proto unix_stream_proto = {
 
 static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type)
 {
-	struct sock *sk = NULL;
 	struct unix_sock *u;
+	struct sock *sk;
+	int err;
 
 	atomic_long_inc(&unix_nr_socks);
-	if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
-		goto out;
+	if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) {
+		err = -ENFILE;
+		goto err;
+	}
 
 	if (type == SOCK_STREAM)
 		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
 	else /*dgram and  seqpacket */
 		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
 
-	if (!sk)
-		goto out;
+	if (!sk) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	sock_init_data(sock, sk);
 
@@ -861,20 +888,23 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	memset(&u->scm_stat, 0, sizeof(struct scm_stat));
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
-out:
-	if (sk == NULL)
-		atomic_long_dec(&unix_nr_socks);
-	else {
-		local_bh_disable();
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-		local_bh_enable();
-	}
+
+	local_bh_disable();
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+	local_bh_enable();
+
 	return sk;
+
+err:
+	atomic_long_dec(&unix_nr_socks);
+	return ERR_PTR(err);
 }
 
 static int unix_create(struct net *net, struct socket *sock, int protocol,
 		       int kern)
 {
+	struct sock *sk;
+
 	if (protocol && protocol != PF_UNIX)
 		return -EPROTONOSUPPORT;
 
@@ -901,7 +931,11 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		return -ESOCKTNOSUPPORT;
 	}
 
-	return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM;
+	sk = unix_create1(net, sock, kern, sock->type);
+	if (IS_ERR(sk))
+		return PTR_ERR(sk);
+
+	return 0;
 }
 
 static int unix_release(struct socket *sock)
@@ -1314,12 +1348,15 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	   we will have to recheck all again in any case.
 	 */
 
-	err = -ENOMEM;
-
 	/* create new sock for complete connection */
 	newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
-	if (newsk == NULL)
+	if (IS_ERR(newsk)) {
+		err = PTR_ERR(newsk);
+		newsk = NULL;
 		goto out;
+	}
+
+	err = -ENOMEM;
 
 	/* Allocate skb for sending to listening sock */
 	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);