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, 28 insertions, 24 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 512e629f9780..c1601f75ec4b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1376,6 +1376,16 @@ set_sndbuf:
 }
 EXPORT_SYMBOL(sock_setsockopt);
 
+static const struct cred *sk_get_peer_cred(struct sock *sk)
+{
+	const struct cred *cred;
+
+	spin_lock(&sk->sk_peer_lock);
+	cred = get_cred(sk->sk_peer_cred);
+	spin_unlock(&sk->sk_peer_lock);
+
+	return cred;
+}
 
 static void cred_to_ucred(struct pid *pid, const struct cred *cred,
 			  struct ucred *ucred)
@@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		struct ucred peercred;
 		if (len > sizeof(peercred))
 			len = sizeof(peercred);
+
+		spin_lock(&sk->sk_peer_lock);
 		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
+		spin_unlock(&sk->sk_peer_lock);
+
 		if (copy_to_user(optval, &peercred, len))
 			return -EFAULT;
 		goto lenout;
@@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	case SO_PEERGROUPS:
 	{
+		const struct cred *cred;
 		int ret, n;
 
-		if (!sk->sk_peer_cred)
+		cred = sk_get_peer_cred(sk);
+		if (!cred)
 			return -ENODATA;
 
-		n = sk->sk_peer_cred->group_info->ngroups;
+		n = cred->group_info->ngroups;
 		if (len < n * sizeof(gid_t)) {
 			len = n * sizeof(gid_t);
+			put_cred(cred);
 			return put_user(len, optlen) ? -EFAULT : -ERANGE;
 		}
 		len = n * sizeof(gid_t);
 
-		ret = groups_to_user((gid_t __user *)optval,
-				     sk->sk_peer_cred->group_info);
+		ret = groups_to_user((gid_t __user *)optval, cred->group_info);
+		put_cred(cred);
 		if (ret)
 			return ret;
 		goto lenout;
@@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head)
 		sk->sk_frag.page = NULL;
 	}
 
-	if (sk->sk_peer_cred)
-		put_cred(sk->sk_peer_cred);
+	/* We do not need to acquire sk->sk_peer_lock, we are the last user. */
+	put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
+
 	if (likely(sk->sk_net_refcnt))
 		put_net(sock_net(sk));
 	sk_prot_free(sk->sk_prot_creator, sk);
@@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_peer_pid 	=	NULL;
 	sk->sk_peer_cred	=	NULL;
+	spin_lock_init(&sk->sk_peer_lock);
+
 	sk->sk_write_pending	=	0;
 	sk->sk_rcvlowat		=	1;
 	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
@@ -3210,24 +3230,8 @@ void release_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(release_sock);
 
-/**
- * lock_sock_fast - fast version of lock_sock
- * @sk: socket
- *
- * This version should be used for very small section, where process wont block
- * return false if fast path is taken:
- *
- *   sk_lock.slock locked, owned = 0, BH disabled
- *
- * return true if slow path is taken:
- *
- *   sk_lock.slock unlocked, owned = 1, BH enabled
- */
-bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
+bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
 {
-	/* The sk_lock has mutex_lock() semantics here. */
-	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
-
 	might_sleep();
 	spin_lock_bh(&sk->sk_lock.slock);
 
@@ -3256,7 +3260,7 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
 	spin_unlock_bh(&sk->sk_lock.slock);
 	return true;
 }
-EXPORT_SYMBOL(lock_sock_fast);
+EXPORT_SYMBOL(__lock_sock_fast);
 
 int sock_gettstamp(struct socket *sock, void __user *userstamp,
 		   bool timeval, bool time32)