Merge tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - af_unix: fix another unix GC hangup

  Previous releases - regressions:

   - core: fix a possible AF_UNIX deadlock

   - bpf: fix NULL pointer dereference in sk_psock_verdict_data_ready()

   - netfilter: nft_flow_offload: release dst in case direct xmit path
     is used

   - bridge: switchdev: ensure MDB events are delivered exactly once

   - l2tp: pass correct message length to ip6_append_data

   - dccp/tcp: unhash sk from ehash for tb2 alloc failure after
     check_estalblished()

   - tls: fixes for record type handling with PEEK

   - devlink: fix possible use-after-free and memory leaks in
     devlink_init()

  Previous releases - always broken:

   - bpf: fix an oops when attempting to read the vsyscall page through
     bpf_probe_read_kernel

   - sched: act_mirred: use the backlog for mirred ingress

   - netfilter: nft_flow_offload: fix dst refcount underflow

   - ipv6: sr: fix possible use-after-free and null-ptr-deref

   - mptcp: fix several data races

   - phonet: take correct lock to peek at the RX queue

  Misc:

   - handful of fixes and reliability improvements for selftests"

* tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (72 commits)
  l2tp: pass correct message length to ip6_append_data
  net: phy: realtek: Fix rtl8211f_config_init() for RTL8211F(D)(I)-VD-CG PHY
  selftests: ioam: refactoring to align with the fix
  Fix write to cloned skb in ipv6_hop_ioam()
  phonet/pep: fix racy skb_queue_empty() use
  phonet: take correct lock to peek at the RX queue
  net: sparx5: Add spinlock for frame transmission from CPU
  net/sched: flower: Add lock protection when remove filter handle
  devlink: fix port dump cmd type
  net: stmmac: Fix EST offset for dwmac 5.10
  tools: ynl: don't leak mcast_groups on init error
  tools: ynl: make sure we always pass yarg to mnl_cb_run
  net: mctp: put sock on tag allocation failure
  netfilter: nf_tables: use kzalloc for hook allocation
  netfilter: nf_tables: register hooks last when adding new chain/flowtable
  netfilter: nft_flow_offload: release dst in case direct xmit path is used
  netfilter: nft_flow_offload: reset dst in route object after setting up flow
  netfilter: nf_tables: set dormant flag on hook register failure
  selftests: tls: add test for peeking past a record of a different type
  selftests: tls: add test for merging of same-type control messages
  ...

4 files changed, 44 insertions, 12 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9456f5bb35e5..0d0d725b46ad 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	if (neigh) {
 		if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) {
 			read_lock_bh(&neigh->lock);
-			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			memcpy(r->arp_ha.sa_data, neigh->ha,
+			       min(dev->addr_len, sizeof(r->arp_ha.sa_data_min)));
 			r->arp_flags = arp_state_to_flags(neigh);
 			read_unlock_bh(&neigh->lock);
 			r->arp_ha.sa_family = dev->type;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ca0ff15dc8fa..bc74f131fe4d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1825,6 +1825,21 @@ done:
 	return err;
 }
 
+/* Combine dev_addr_genid and dev_base_seq to detect changes.
+ */
+static u32 inet_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->ipv4.dev_addr_genid) +
+		  net->dev_base_seq;
+
+	/* Must not return 0 (see nl_dump_check_consistent()).
+	 * Chose a value far away from 0.
+	 */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
 static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = cb->nlh;
@@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 		idx = 0;
 		head = &tgt_net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^
-			  tgt_net->dev_base_seq;
+		cb->seq = inet_base_seq(tgt_net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
-			  net->dev_base_seq;
+		cb->seq = inet_base_seq(net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 93e9193df544..308ff34002ea 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1130,10 +1130,33 @@ ok:
 	return 0;
 
 error:
+	if (sk_hashed(sk)) {
+		spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash);
+
+		sock_prot_inuse_add(net, sk->sk_prot, -1);
+
+		spin_lock(lock);
+		sk_nulls_del_node_init_rcu(sk);
+		spin_unlock(lock);
+
+		sk->sk_hash = 0;
+		inet_sk(sk)->inet_sport = 0;
+		inet_sk(sk)->inet_num = 0;
+
+		if (tw)
+			inet_twsk_bind_unhash(tw, hinfo);
+	}
+
 	spin_unlock(&head2->lock);
 	if (tb_created)
 		inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
-	spin_unlock_bh(&head->lock);
+	spin_unlock(&head->lock);
+
+	if (tw)
+		inet_twsk_deschedule_put(tw);
+
+	local_bh_enable();
+
 	return -ENOMEM;
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f631b0a21af4..e474b201900f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk)
 
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 {
-	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
-		bool slow = lock_sock_fast(sk);
-
-		sk_peek_offset_bwd(sk, len);
-		unlock_sock_fast(sk, slow);
-	}
+	sk_peek_offset_bwd(sk, len);
 
 	if (!skb_unref(skb))
 		return;