Merge tag 'net-6.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - bpf: fix nullness propagation for reg to reg comparisons, avoid
     null-deref

   - inet: control sockets should not use current thread task_frag

   - bpf: always use maximal size for copy_array()

   - eth: bnxt_en: don't link netdev to a devlink port for VFs

  Current release - new code bugs:

   - rxrpc: fix a couple of potential use-after-frees

   - netfilter: conntrack: fix IPv6 exthdr error check

   - wifi: iwlwifi: fw: skip PPAG for JF, avoid FW crashes

   - eth: dsa: qca8k: various fixes for the in-band register access

   - eth: nfp: fix schedule in atomic context when sync mc address

   - eth: renesas: rswitch: fix getting mac address from device tree

   - mobile: ipa: use proper endpoint mask for suspend

  Previous releases - regressions:

   - tcp: add TIME_WAIT sockets in bhash2, fix regression caught by
     Jiri / python tests

   - net: tc: don't intepret cls results when asked to drop, fix
     oob-access

   - vrf: determine the dst using the original ifindex for multicast

   - eth: bnxt_en:
      - fix XDP RX path if BPF adjusted packet length
      - fix HDS (header placement) and jumbo thresholds for RX packets

   - eth: ice: xsk: do not use xdp_return_frame() on tx_buf->raw_buf,
     avoid memory corruptions

  Previous releases - always broken:

   - ulp: prevent ULP without clone op from entering the LISTEN status

   - veth: fix race with AF_XDP exposing old or uninitialized
     descriptors

   - bpf:
      - pull before calling skb_postpull_rcsum() (fix checksum support
        and avoid a WARN())
      - fix panic due to wrong pageattr of im->image (when livepatch and
        kretfunc coexist)
      - keep a reference to the mm, in case the task is dead

   - mptcp: fix deadlock in fastopen error path

   - netfilter:
      - nf_tables: perform type checking for existing sets
      - nf_tables: honor set timeout and garbage collection updates
      - ipset: fix hash:net,port,net hang with /0 subnet
      - ipset: avoid hung task warning when adding/deleting entries

   - selftests: net:
      - fix cmsg_so_mark.sh test hang on non-x86 systems
      - fix the arp_ndisc_evict_nocarrier test for IPv6

   - usb: rndis_host: secure rndis_query check against int overflow

   - eth: r8169: fix dmar pte write access during suspend/resume with
     WOL

   - eth: lan966x: fix configuration of the PCS

   - eth: sparx5: fix reading of the MAC address

   - eth: qed: allow sleep in qed_mcp_trace_dump()

   - eth: hns3:
      - fix interrupts re-initialization after VF FLR
      - fix handling of promisc when MAC addr table gets full
      - refine the handling for VF heartbeat

   - eth: mlx5:
      - properly handle ingress QinQ-tagged packets on VST
      - fix io_eq_size and event_eq_size params validation on big endian
      - fix RoCE setting at HCA level if not supported at all
      - don't turn CQE compression on by default for IPoIB

   - eth: ena:
      - fix toeplitz initial hash key value
      - account for the number of XDP-processed bytes in interface stats
      - fix rx_copybreak value update

  Misc:

   - ethtool: harden phy stat handling against buggy drivers

   - docs: netdev: convert maintainer's doc from FAQ to a normal
     document"

* tag 'net-6.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (112 commits)
  caif: fix memory leak in cfctrl_linkup_request()
  inet: control sockets should not use current thread task_frag
  net/ulp: prevent ULP without clone op from entering the LISTEN status
  qed: allow sleep in qed_mcp_trace_dump()
  MAINTAINERS: Update maintainers for ptp_vmw driver
  usb: rndis_host: Secure rndis_query check against int overflow
  net: dpaa: Fix dtsec check for PCS availability
  octeontx2-pf: Fix lmtst ID used in aura free
  drivers/net/bonding/bond_3ad: return when there's no aggregator
  netfilter: ipset: Rework long task execution when adding/deleting entries
  netfilter: ipset: fix hash:net,port,net hang with /0 subnet
  net: sparx5: Fix reading of the MAC address
  vxlan: Fix memory leaks in error path
  net: sched: htb: fix htb_classify() kernel-doc
  net: sched: cbq: dont intepret cls results when asked to drop
  net: sched: atm: dont intepret cls results when asked to drop
  dt-bindings: net: marvell,orion-mdio: Fix examples
  dt-bindings: net: sun8i-emac: Add phy-supply property
  net: ipa: use proper endpoint mask for suspend
  selftests: net: return non-zero for failures reported in arp_ndisc_evict_nocarrier
  ...

5 files changed, 75 insertions, 9 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ab4a06be489b..6c0ec2789943 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1665,6 +1665,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 	if (rc == 0) {
 		*sk = sock->sk;
 		(*sk)->sk_allocation = GFP_ATOMIC;
+		(*sk)->sk_use_task_frag = false;
 		/*
 		 * Unhash it so that IP input processing does not even see it,
 		 * we do not wish this socket to see incoming packets.
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b366ab9148f2..d1f837579398 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -173,22 +173,40 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 	return false;
 }
 
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+				   kuid_t sk_uid, bool relax,
+				   bool reuseport_cb_ok, bool reuseport_ok)
+{
+	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+		return false;
+
+	return inet_bind_conflict(sk, sk2, sk_uid, relax,
+				  reuseport_cb_ok, reuseport_ok);
+}
+
 static bool inet_bhash2_conflict(const struct sock *sk,
 				 const struct inet_bind2_bucket *tb2,
 				 kuid_t sk_uid,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
+	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
 	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
-		if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
-			continue;
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
+			return true;
+	}
 
-		if (inet_bind_conflict(sk, sk2, sk_uid, relax,
-				       reuseport_cb_ok, reuseport_ok))
+	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+		sk2 = (struct sock *)tw2;
+
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
 			return true;
 	}
+
 	return false;
 }
 
@@ -1182,12 +1200,26 @@ void inet_csk_prepare_forced_close(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_prepare_forced_close);
 
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+		return -EINVAL;
+
+	return 0;
+}
+
 int inet_csk_listen_start(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	int err;
 
+	err = inet_ulp_can_listen(sk);
+	if (unlikely(err))
+		return err;
+
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
 	sk->sk_ack_backlog = 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d039b4e732a3..24a38b56fab9 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -116,6 +116,7 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
 #endif
 		tb->rcv_saddr = sk->sk_rcv_saddr;
 	INIT_HLIST_HEAD(&tb->owners);
+	INIT_HLIST_HEAD(&tb->deathrow);
 	hlist_add_head(&tb->node, &head->chain);
 }
 
@@ -137,7 +138,7 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
 		__hlist_del(&tb->node);
 		kmem_cache_free(cachep, tb);
 	}
@@ -1103,15 +1104,16 @@ ok:
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);
 
-	spin_unlock(&head2->lock);
-
 	if (sk_unhashed(sk)) {
 		inet_sk(sk)->inet_sport = htons(port);
 		inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
 	}
 	if (tw)
 		inet_twsk_bind_unhash(tw, hinfo);
+
+	spin_unlock(&head2->lock);
 	spin_unlock(&head->lock);
+
 	if (tw)
 		inet_twsk_deschedule_put(tw);
 	local_bh_enable();
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 66fc940f9521..1d77d992e6e7 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -29,6 +29,7 @@
 void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 			  struct inet_hashinfo *hashinfo)
 {
+	struct inet_bind2_bucket *tb2 = tw->tw_tb2;
 	struct inet_bind_bucket *tb = tw->tw_tb;
 
 	if (!tb)
@@ -37,6 +38,11 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 	__hlist_del(&tw->tw_bind_node);
 	tw->tw_tb = NULL;
 	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+
+	__hlist_del(&tw->tw_bind2_node);
+	tw->tw_tb2 = NULL;
+	inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+
 	__sock_put((struct sock *)tw);
 }
 
@@ -45,7 +51,7 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
-	struct inet_bind_hashbucket *bhead;
+	struct inet_bind_hashbucket *bhead, *bhead2;
 
 	spin_lock(lock);
 	sk_nulls_del_node_init_rcu((struct sock *)tw);
@@ -54,9 +60,13 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
 	/* Disassociate with bind bucket. */
 	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
 			hashinfo->bhash_size)];
+	bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw,
+				       twsk_net(tw), tw->tw_num);
 
 	spin_lock(&bhead->lock);
+	spin_lock(&bhead2->lock);
 	inet_twsk_bind_unhash(tw, hashinfo);
+	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
 
 	refcount_dec(&tw->tw_dr->tw_refcount);
@@ -93,6 +103,12 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
 	hlist_add_head(&tw->tw_bind_node, list);
 }
 
+static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
+				     struct hlist_head *list)
+{
+	hlist_add_head(&tw->tw_bind2_node, list);
+}
+
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -105,17 +121,28 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
-	struct inet_bind_hashbucket *bhead;
+	struct inet_bind_hashbucket *bhead, *bhead2;
+
 	/* Step 1: Put TW into bind hash. Original socket stays there too.
 	   Note, that any socket with inet->num != 0 MUST be bound in
 	   binding cache, even if it is closed.
 	 */
 	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
 			hashinfo->bhash_size)];
+	bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+
 	spin_lock(&bhead->lock);
+	spin_lock(&bhead2->lock);
+
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
 	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
+
+	tw->tw_tb2 = icsk->icsk_bind2_hash;
+	WARN_ON(!icsk->icsk_bind2_hash);
+	inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+
+	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
 
 	spin_lock(lock);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 9ae50b1bd844..05b6077b9f2c 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -139,6 +139,10 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
 	if (sk->sk_socket)
 		clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 
+	err = -EINVAL;
+	if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
+		goto out_err;
+
 	err = ulp_ops->init(sk);
 	if (err)
 		goto out_err;