Merge tag 'net-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter, and wifi.

Current release - regressions:

   - Revert "net/sched: taprio: make qdisc_leaf() see the
     per-netdev-queue pfifo child qdiscs", it may cause crashes when the
     qdisc is reconfigured

   - inet: ping: fix splat due to packet allocation refactoring in inet

   - tcp: clean up kernel listener's reqsk in inet_twsk_purge(), fix UAF
     due to races when per-netns hash table is used

  Current release - new code bugs:

   - eth: adin1110: check in netdev_event that netdev belongs to driver

   - fixes for PTR_ERR() vs NULL bugs in driver code, from Dan and co.

  Previous releases - regressions:

   - ipv4: handle attempt to delete multipath route when fib_info
     contains an nh reference, avoid oob access

   - wifi: fix handful of bugs in the new Multi-BSSID code

   - wifi: mt76: fix rate reporting / throughput regression on mt7915
     and newer, fix checksum offload

   - wifi: iwlwifi: mvm: fix double list_add at
     iwl_mvm_mac_wake_tx_queue (other cases)

   - wifi: mac80211: do not drop packets smaller than the LLC-SNAP
     header on fast-rx

  Previous releases - always broken:

   - ieee802154: don't warn zero-sized raw_sendmsg()

   - ipv6: ping: fix wrong checksum for large frames

   - mctp: prevent double key removal and unref

   - tcp/udp: fix memory leaks and races around IPV6_ADDRFORM

   - hv_netvsc: fix race between VF offering and VF association message

  Misc:

   - remove -Warray-bounds silencing in the drivers, compilers fixed"

* tag 'net-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (73 commits)
  sunhme: fix an IS_ERR() vs NULL check in probe
  net: marvell: prestera: fix a couple NULL vs IS_ERR() checks
  kcm: avoid potential race in kcm_tx_work
  tcp: Clean up kernel listener's reqsk in inet_twsk_purge()
  net: phy: micrel: Fixes FIELD_GET assertion
  openvswitch: add nf_ct_is_confirmed check before assigning the helper
  tcp: Fix data races around icsk->icsk_af_ops.
  ipv6: Fix data races around sk->sk_prot.
  tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct().
  udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM).
  tcp/udp: Fix memory leak in ipv6_renew_options().
  mctp: prevent double key removal and unref
  selftests: netfilter: Fix nft_fib.sh for all.rp_filter=1
  netfilter: rpfilter/fib: Populate flowic_l3mdev field
  selftests: netfilter: Test reverse path filtering
  net/mlx5: Make ASO poll CQ usable in atomic context
  tcp: cdg: allow tcp_cdg_release() to be called multiple times
  inet: ping: fix recent breakage
  ipv6: ping: fix wrong checksum for large frames
  net: ethernet: ti: am65-cpsw: set correct devlink flavour for unused ports
  ...

1 files changed, 19 insertions, 15 deletions

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 2d2f4dd9e5df..532f4478c884 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -419,15 +419,18 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		rtnl_lock();
 	sockopt_lock_sock(sk);
 
+	/* Another thread has converted the socket into IPv4 with
+	 * IPV6_ADDRFORM concurrently.
+	 */
+	if (unlikely(sk->sk_family != AF_INET6))
+		goto unlock;
+
 	switch (optname) {
 
 	case IPV6_ADDRFORM:
 		if (optlen < sizeof(int))
 			goto e_inval;
 		if (val == PF_INET) {
-			struct ipv6_txoptions *opt;
-			struct sk_buff *pktopt;
-
 			if (sk->sk_type == SOCK_RAW)
 				break;
 
@@ -458,7 +461,6 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				break;
 			}
 
-			fl6_free_socklist(sk);
 			__ipv6_sock_mc_close(sk);
 			__ipv6_sock_ac_close(sk);
 
@@ -475,9 +477,10 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sock_prot_inuse_add(net, sk->sk_prot, -1);
 				sock_prot_inuse_add(net, &tcp_prot, 1);
 
-				/* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+				/* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */
 				WRITE_ONCE(sk->sk_prot, &tcp_prot);
-				icsk->icsk_af_ops = &ipv4_specific;
+				/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
+				WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific);
 				sk->sk_socket->ops = &inet_stream_ops;
 				sk->sk_family = PF_INET;
 				tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
@@ -490,19 +493,19 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sock_prot_inuse_add(net, sk->sk_prot, -1);
 				sock_prot_inuse_add(net, prot, 1);
 
-				/* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+				/* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */
 				WRITE_ONCE(sk->sk_prot, prot);
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
-				   NULL);
-			if (opt) {
-				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
-				txopt_put(opt);
-			}
-			pktopt = xchg(&np->pktoptions, NULL);
-			kfree_skb(pktopt);
+
+			/* Disable all options not to allocate memory anymore,
+			 * but there is still a race.  See the lockless path
+			 * in udpv6_sendmsg() and ipv6_local_rxpmtu().
+			 */
+			np->rxopt.all = 0;
+
+			inet6_cleanup_sock(sk);
 
 			/*
 			 * ... and add it to the refcnt debug socks count
@@ -994,6 +997,7 @@ done:
 		break;
 	}
 
+unlock:
 	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();