Merge tag 'net-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from Bluetooth, CAN, IPsec and Netfilter.

  Notably, this includes the fix for the Bluetooth regression that you
  were notified about. I'm not aware of any other pending regressions.

  Current release - regressions:

    - bluetooth:
       - fix stack-out-of-bounds read in l2cap_ecred_conn_req
       - fix regressions caused by reusing ident

    - netfilter: revisit array resize logic

    - eth: ice: set max queues in alloc_etherdev_mqs()

  Previous releases - regressions:

    - core: correctly handle tunneled traffic on IPV6_CSUM GSO fallback

    - bluetooth:
       - fix dangling pointer on mgmt_add_adv_patterns_monitor_complete
       - fix deadlock in l2cap_conn_del()

    - sched: codel: fix stale state for empty flows in fq_codel

    - ipv6: remove permanent routes from tb6_gc_hlist when all exceptions expire.

    - xfrm: fix skb_put() panic on non-linear skb during reassembly

    - openvswitch:
       - avoid releasing netdev before teardown completes
       - validate MPLS set/set_masked payload length

    - eth: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats()

  Previous releases - always broken:

    - bluetooth: fix null-ptr-deref on l2cap_sock_ready_cb

    - udp: fix wildcard bind conflict check when using hash2

    - netfilter: fix use of uninitialized rtp_addr in process_sdp

    - tls: Purge async_hold in tls_decrypt_async_wait()

    - xfrm:
       - prevent policy_hthresh.work from racing with netns teardown
       - fix skb leak with espintcp and async crypto

    - smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer

    - can:
       - add missing error handling to call can_ctrlmode_changelink()
       - fix OOB heap access in cgw_csum_crc8_rel()

    - eth:
       - mana: fix use-after-free in add_adev() error path
       - virtio-net: fix for VIRTIO_NET_F_GUEST_HDRLEN
       - bcmasp: fix double free of WoL irq"

* tag 'net-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (90 commits)
  net: macb: use the current queue number for stats
  netfilter: ctnetlink: use netlink policy range checks
  netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp
  netfilter: nf_conntrack_expect: skip expectations in other netns via proc
  netfilter: nf_conntrack_expect: store netns and zone in expectation
  netfilter: ctnetlink: ensure safe access to master conntrack
  netfilter: nf_conntrack_expect: use expect->helper
  netfilter: nf_conntrack_expect: honor expectation helper field
  netfilter: nft_set_rbtree: revisit array resize logic
  netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check()
  netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD
  tls: Purge async_hold in tls_decrypt_async_wait()
  selftests: netfilter: nft_concat_range.sh: add check for flush+reload bug
  netfilter: nft_set_pipapo_avx2: don't return non-matching entry on expiry
  Bluetooth: btusb: clamp SCO altsetting table indices
  Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop
  Bluetooth: L2CAP: Fix deadlock in l2cap_conn_del()
  Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock
  Bluetooth: L2CAP: Fix send LE flow credits in ACL link
  net: mana: fix use-after-free in add_adev() error path
  ...

9 files changed, 113 insertions, 8 deletions

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 75dabb763c65..f36d21b5bc19 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -207,6 +207,39 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
 }
 
+/* This function must be called after virtio_net_hdr_from_skb(). */
+static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb,
+					   struct virtio_net_hdr *hdr,
+					   bool little_endian)
+{
+	u16 hdr_len;
+
+	hdr_len = skb_transport_offset(skb);
+
+	if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4)
+		hdr_len += sizeof(struct udphdr);
+	else
+		hdr_len += tcp_hdrlen(skb);
+
+	hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len);
+}
+
+/* This function must be called after virtio_net_hdr_from_skb(). */
+static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb,
+					       struct virtio_net_hdr *hdr)
+{
+	u16 hdr_len;
+
+	hdr_len = skb_inner_transport_offset(skb);
+
+	if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4)
+		hdr_len += sizeof(struct udphdr);
+	else
+		hdr_len += inner_tcp_hdrlen(skb);
+
+	hdr->hdr_len = __cpu_to_virtio16(true, hdr_len);
+}
+
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
@@ -385,7 +418,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 			    bool tnl_hdr_negotiated,
 			    bool little_endian,
 			    int vlan_hlen,
-			    bool has_data_valid)
+			    bool has_data_valid,
+			    bool feature_hdrlen)
 {
 	struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr;
 	unsigned int inner_nh, outer_th;
@@ -394,9 +428,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 
 	tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL |
 						    SKB_GSO_UDP_TUNNEL_CSUM);
-	if (!tnl_gso_type)
-		return virtio_net_hdr_from_skb(skb, hdr, little_endian,
-					       has_data_valid, vlan_hlen);
+	if (!tnl_gso_type) {
+		ret = virtio_net_hdr_from_skb(skb, hdr, little_endian,
+					      has_data_valid, vlan_hlen);
+		if (ret)
+			return ret;
+
+		if (feature_hdrlen && hdr->hdr_len)
+			__virtio_net_set_hdrlen(skb, hdr, little_endian);
+
+		return ret;
+	}
 
 	/* Tunnel support not negotiated but skb ask for it. */
 	if (!tnl_hdr_negotiated)
@@ -414,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 	if (ret)
 		return ret;
 
+	if (feature_hdrlen && hdr->hdr_len)
+		__virtio_net_set_tnl_hdrlen(skb, hdr);
+
 	if (skb->protocol == htons(ETH_P_IPV6))
 		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
 	else
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 010f1a8fd15f..5172afee5494 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -658,6 +658,7 @@ struct l2cap_conn {
 	struct sk_buff		*rx_skb;
 	__u32			rx_len;
 	struct ida		tx_ida;
+	__u8			tx_ident;
 
 	struct sk_buff_head	pending_rx;
 	struct work_struct	pending_rx_work;
diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h
index 78a27ac73070..b2c359c6dd1b 100644
--- a/include/net/codel_impl.h
+++ b/include/net/codel_impl.h
@@ -158,6 +158,7 @@ static struct sk_buff *codel_dequeue(void *ctx,
 	bool drop;
 
 	if (!skb) {
+		vars->first_above_time = 0;
 		vars->dropping = false;
 		return skb;
 	}
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 5a979dcab538..6d936e9f2fd3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk,
 	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
+static inline bool inet_use_hash2_on_bind(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			return false;
+
+		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return true;
+	}
+#endif
+	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
+}
+
 struct inet_bind_hashbucket *
 inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port);
 
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 88b0dd4d8e09..9f8b6814a96a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -507,12 +507,14 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int flags);
 
+void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
+			 unsigned long now);
 void fib6_run_gc(unsigned long expires, struct net *net, bool force);
-
 void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* Add the route to the gc list if it is not already there
  *
  * The callers should hold f6i->fib6_table->tb6_lock.
@@ -545,6 +547,23 @@ static inline void fib6_remove_gc_list(struct fib6_info *f6i)
 		hlist_del_init(&f6i->gc_link);
 }
 
+static inline void fib6_may_remove_gc_list(struct net *net,
+					   struct fib6_info *f6i)
+{
+	struct fib6_gc_args gc_args;
+
+	if (hlist_unhashed(&f6i->gc_link))
+		return;
+
+	gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval);
+	gc_args.more = 0;
+
+	rcu_read_lock();
+	fib6_age_exceptions(f6i, &gc_args, jiffies);
+	rcu_read_unlock();
+}
+#endif
+
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 3384859a8921..8883575adcc1 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -83,6 +83,11 @@ void nf_conntrack_lock(spinlock_t *lock);
 
 extern spinlock_t nf_conntrack_expect_lock;
 
+static inline void lockdep_nfct_expect_lock_held(void)
+{
+	lockdep_assert_held(&nf_conntrack_expect_lock);
+}
+
 /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
 
 static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout)
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 165e7a03b8e9..e9a8350e7ccf 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -22,10 +22,16 @@ struct nf_conntrack_expect {
 	/* Hash member */
 	struct hlist_node hnode;
 
+	/* Network namespace */
+	possible_net_t net;
+
 	/* We expect this tuple, with the following mask */
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_mask mask;
 
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	struct nf_conntrack_zone zone;
+#endif
 	/* Usage count. */
 	refcount_t use;
 
@@ -40,7 +46,7 @@ struct nf_conntrack_expect {
 			 struct nf_conntrack_expect *this);
 
 	/* Helper to assign to new connection */
-	struct nf_conntrack_helper *helper;
+	struct nf_conntrack_helper __rcu *helper;
 
 	/* The conntrack of the master connection */
 	struct nf_conn *master;
@@ -62,7 +68,17 @@ struct nf_conntrack_expect {
 
 static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp)
 {
-	return nf_ct_net(exp->master);
+	return read_pnet(&exp->net);
+}
+
+static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a,
+					    const struct nf_conntrack_zone *b)
+{
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	return a->zone.id == b->id;
+#else
+	return true;
+#endif
 }
 
 #define NF_CT_EXP_POLICY_NAME_LEN	16
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 23dd647fe024..b73983a17e08 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -59,7 +59,7 @@ struct netns_xfrm {
 	struct list_head	inexact_bins;
 
 
-	struct sock		*nlsk;
+	struct sock		__rcu *nlsk;
 	struct sock		*nlsk_stash;
 
 	u32			sysctl_aevent_etime;
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 26071021e986..56b6b60a814f 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -159,5 +159,9 @@ enum ip_conntrack_expect_events {
 #define NF_CT_EXPECT_INACTIVE		0x2
 #define NF_CT_EXPECT_USERSPACE		0x4
 
+#ifdef __KERNEL__
+#define NF_CT_EXPECT_MASK	(NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \
+				 NF_CT_EXPECT_USERSPACE)
+#endif
 
 #endif /* _UAPI_NF_CONNTRACK_COMMON_H */