Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Various netfilter fixlets from Pablo and the netfilter team.

 2) Fix regression in IPVS caused by lack of PMTU exceptions on local
    routes in ipv6, from Julian Anastasov.

 3) Check pskb_trim_rcsum for failure in DSA, from Zhouyang Jia.

 4) Don't crash on poll in TLS, from Daniel Borkmann.

 5) Revert SO_REUSE{ADDR,PORT} change, it regresses various things
    including Avahi mDNS. From Bart Van Assche.

 6) Missing of_node_put in qcom/emac driver, from Yue Haibing.

 7) We lack checking of the TCP checking in one special case during SYN
    receive, from Frank van der Linden.

 8) Fix module init error paths of mac80211 hwsim, from Johannes Berg.

 9) Handle 802.1ad properly in stmmac driver, from Elad Nachman.

10) Must grab HW caps before doing quirk checks in stmmac driver, from
    Jose Abreu.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (81 commits)
  net: stmmac: Run HWIF Quirks after getting HW caps
  neighbour: skip NTF_EXT_LEARNED entries during forced gc
  net: cxgb3: add error handling for sysfs_create_group
  tls: fix waitall behavior in tls_sw_recvmsg
  tls: fix use-after-free in tls_push_record
  l2tp: filter out non-PPP sessions in pppol2tp_tunnel_ioctl()
  l2tp: reject creation of non-PPP sessions on L2TPv2 tunnels
  mlxsw: spectrum_switchdev: Fix port_vlan refcounting
  mlxsw: spectrum_router: Align with new route replace logic
  mlxsw: spectrum_router: Allow appending to dev-only routes
  ipv6: Only emit append events for appended routes
  stmmac: added support for 802.1ad vlan stripping
  cfg80211: fix rcu in cfg80211_unregister_wdev
  mac80211: Move up init of TXQs
  mac80211_hwsim: fix module init error paths
  cfg80211: initialize sinfo in cfg80211_get_station
  nl80211: fix some kernel doc tag mistakes
  hv_netvsc: Fix the variable sizes in ipsecv2 and rsc offload
  rds: avoid unenecessary cong_update in loop transport
  l2tp: clean up stale tunnel or session in pppol2tp_connect's error path
  ...

10 files changed, 70 insertions, 38 deletions

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 04551af2ff23..dd2052f0efb7 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -345,7 +345,7 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 
 	rcu_read_lock();
 	nat_hook = rcu_dereference(nf_nat_hook);
-	if (nat_hook->decode_session)
+	if (nat_hook && nat_hook->decode_session)
 		nat_hook->decode_session(skb, fl);
 	rcu_read_unlock();
 #endif
diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h
index bfb3531fd88a..8ce271e187b6 100644
--- a/include/linux/netfilter/ipset/ip_set_timeout.h
+++ b/include/linux/netfilter/ipset/ip_set_timeout.h
@@ -23,6 +23,9 @@
 /* Set is defined with timeout support: timeout value may be 0 */
 #define IPSET_NO_TIMEOUT	UINT_MAX
 
+/* Max timeout value, see msecs_to_jiffies() in jiffies.h */
+#define IPSET_MAX_TIMEOUT	(UINT_MAX >> 1)/MSEC_PER_SEC
+
 #define ip_set_adt_opt_timeout(opt, set)	\
 ((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout)
 
@@ -32,11 +35,10 @@ ip_set_timeout_uget(struct nlattr *tb)
 	unsigned int timeout = ip_set_get_h32(tb);
 
 	/* Normalize to fit into jiffies */
-	if (timeout > UINT_MAX/MSEC_PER_SEC)
-		timeout = UINT_MAX/MSEC_PER_SEC;
+	if (timeout > IPSET_MAX_TIMEOUT)
+		timeout = IPSET_MAX_TIMEOUT;
 
-	/* Userspace supplied TIMEOUT parameter: adjust crazy size */
-	return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout;
+	return timeout;
 }
 
 static inline bool
@@ -65,8 +67,14 @@ ip_set_timeout_set(unsigned long *timeout, u32 value)
 static inline u32
 ip_set_timeout_get(const unsigned long *timeout)
 {
-	return *timeout == IPSET_ELEM_PERMANENT ? 0 :
-		jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+	u32 t;
+
+	if (*timeout == IPSET_ELEM_PERMANENT)
+		return 0;
+
+	t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+	/* Zero value in userspace means no timeout */
+	return t == 0 ? 1 : t;
 }
 
 #endif	/* __KERNEL__ */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 6d6e21dee462..a0bec23c6d5e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -631,6 +631,7 @@ struct ip_vs_service {
 
 	/* alternate persistence engine */
 	struct ip_vs_pe __rcu	*pe;
+	int			conntrack_afmask;
 
 	struct rcu_head		rcu_head;
 };
@@ -1611,6 +1612,35 @@ static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
 	return false;
 }
 
+static inline int ip_vs_register_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	int afmask = (svc->af == AF_INET6) ? 2 : 1;
+	int ret = 0;
+
+	if (!(svc->conntrack_afmask & afmask)) {
+		ret = nf_ct_netns_get(svc->ipvs->net, svc->af);
+		if (ret >= 0)
+			svc->conntrack_afmask |= afmask;
+	}
+	return ret;
+#else
+	return 0;
+#endif
+}
+
+static inline void ip_vs_unregister_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	int afmask = (svc->af == AF_INET6) ? 2 : 1;
+
+	if (svc->conntrack_afmask & afmask) {
+		nf_ct_netns_put(svc->ipvs->net, svc->af);
+		svc->conntrack_afmask &= ~afmask;
+	}
+#endif
+}
+
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 1910b6572430..3a188a0923a3 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -20,7 +20,8 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 				 bool *addit);
 
 bool nf_conncount_add(struct hlist_head *head,
-		      const struct nf_conntrack_tuple *tuple);
+		      const struct nf_conntrack_tuple *tuple,
+		      const struct nf_conntrack_zone *zone);
 
 void nf_conncount_cache_free(struct hlist_head *hhead);
 
diff --git a/include/net/netfilter/nft_dup.h b/include/net/netfilter/nft_dup.h
deleted file mode 100644
index 4d9d512984b2..000000000000
--- a/include/net/netfilter/nft_dup.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_DUP_H_
-#define _NFT_DUP_H_
-
-struct nft_dup_inet {
-	enum nft_registers	sreg_addr:8;
-	enum nft_registers	sreg_dev:8;
-};
-
-#endif /* _NFT_DUP_H_ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ebf809eed33a..dbe1b911a24d 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1133,6 +1133,11 @@ struct sctp_input_cb {
 };
 #define SCTP_INPUT_CB(__skb)	((struct sctp_input_cb *)&((__skb)->cb[0]))
 
+struct sctp_output_cb {
+	struct sk_buff *last;
+};
+#define SCTP_OUTPUT_CB(__skb)	((struct sctp_output_cb *)&((__skb)->cb[0]))
+
 static inline const struct sk_buff *sctp_gso_headskb(const struct sk_buff *skb)
 {
 	const struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
diff --git a/include/net/tls.h b/include/net/tls.h
index 70c273777fe9..7f84ea3e217c 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -109,8 +109,7 @@ struct tls_sw_context_rx {
 
 	struct strparser strp;
 	void (*saved_data_ready)(struct sock *sk);
-	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
-				struct poll_table_struct *wait);
+	__poll_t (*sk_poll_mask)(struct socket *sock, __poll_t events);
 	struct sk_buff *recv_pkt;
 	u8 control;
 	bool decrypted;
@@ -225,8 +224,7 @@ void tls_sw_free_resources_tx(struct sock *sk);
 void tls_sw_free_resources_rx(struct sock *sk);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
-unsigned int tls_sw_poll(struct file *file, struct socket *sock,
-			 struct poll_table_struct *wait);
+__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index c712eb6879f1..336014bf8868 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -112,7 +112,7 @@ enum ip_conntrack_status {
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
 				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
 
-	__IPS_MAX_BIT = 14,
+	__IPS_MAX_BIT = 15,
 };
 
 /* Connection tracking event types */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c9bf74b94f37..89438e68dc03 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -266,7 +266,7 @@ enum nft_rule_compat_attributes {
  * @NFT_SET_INTERVAL: set contains intervals
  * @NFT_SET_MAP: set is used as a dictionary
  * @NFT_SET_TIMEOUT: set uses timeouts
- * @NFT_SET_EVAL: set contains expressions for evaluation
+ * @NFT_SET_EVAL: set can be updated from the evaluation path
  * @NFT_SET_OBJECT: set contains stateful objects
  */
 enum nft_set_flags {
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 28b36545de24..27e4e441caac 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -981,18 +981,18 @@
  *	only the %NL80211_ATTR_IE data is used and updated with this command.
  *
  * @NL80211_CMD_SET_PMK: For offloaded 4-Way handshake, set the PMK or PMK-R0
- *	for the given authenticator address (specified with &NL80211_ATTR_MAC).
- *	When &NL80211_ATTR_PMKR0_NAME is set, &NL80211_ATTR_PMK specifies the
+ *	for the given authenticator address (specified with %NL80211_ATTR_MAC).
+ *	When %NL80211_ATTR_PMKR0_NAME is set, %NL80211_ATTR_PMK specifies the
  *	PMK-R0, otherwise it specifies the PMK.
  * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
  *	configured PMK for the authenticator address identified by
- *	&NL80211_ATTR_MAC.
+ *	%NL80211_ATTR_MAC.
  * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way
  *	handshake was completed successfully by the driver. The BSSID is
- *	specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake
+ *	specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake
  *	offload should send this event after indicating 802.11 association with
- *	&NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed
- *	&NL80211_CMD_DISCONNECT should be indicated instead.
+ *	%NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed
+ *	%NL80211_CMD_DISCONNECT should be indicated instead.
  *
  * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
  *	and RX notification.  This command is used both as a request to transmit
@@ -1029,9 +1029,9 @@
  *	initiated the connection through the connect request.
  *
  * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's
- *	ht opmode or vht opmode changes using any of &NL80211_ATTR_SMPS_MODE,
- *	&NL80211_ATTR_CHANNEL_WIDTH,&NL80211_ATTR_NSS attributes with its
- *	address(specified in &NL80211_ATTR_MAC).
+ *	ht opmode or vht opmode changes using any of %NL80211_ATTR_SMPS_MODE,
+ *	%NL80211_ATTR_CHANNEL_WIDTH,%NL80211_ATTR_NSS attributes with its
+ *	address(specified in %NL80211_ATTR_MAC).
  *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
@@ -2218,7 +2218,7 @@ enum nl80211_commands {
  * @NL80211_ATTR_EXTERNAL_AUTH_ACTION: Identify the requested external
  *     authentication operation (u32 attribute with an
  *     &enum nl80211_external_auth_action value). This is used with the
- *     &NL80211_CMD_EXTERNAL_AUTH request event.
+ *     %NL80211_CMD_EXTERNAL_AUTH request event.
  * @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user
  *     space supports external authentication. This attribute shall be used
  *     only with %NL80211_CMD_CONNECT request. The driver may offload
@@ -3491,7 +3491,7 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated
  *	base on contiguous rules and wider channels will be allowed to cross
  *	multiple contiguous/overlapping frequency ranges.
- * @NL80211_RRF_IR_CONCURRENT: See &NL80211_FREQUENCY_ATTR_IR_CONCURRENT
+ * @NL80211_RRF_IR_CONCURRENT: See %NL80211_FREQUENCY_ATTR_IR_CONCURRENT
  * @NL80211_RRF_NO_HT40MINUS: channels can't be used in HT40- operation
  * @NL80211_RRF_NO_HT40PLUS: channels can't be used in HT40+ operation
  * @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed
@@ -5643,11 +5643,11 @@ enum nl80211_nan_func_attributes {
  * @NL80211_NAN_SRF_INCLUDE: present if the include bit of the SRF set.
  *	This is a flag.
  * @NL80211_NAN_SRF_BF: Bloom Filter. Present if and only if
- *	&NL80211_NAN_SRF_MAC_ADDRS isn't present. This attribute is binary.
+ *	%NL80211_NAN_SRF_MAC_ADDRS isn't present. This attribute is binary.
  * @NL80211_NAN_SRF_BF_IDX: index of the Bloom Filter. Mandatory if
- *	&NL80211_NAN_SRF_BF is present. This is a u8.
+ *	%NL80211_NAN_SRF_BF is present. This is a u8.
  * @NL80211_NAN_SRF_MAC_ADDRS: list of MAC addresses for the SRF. Present if
- *	and only if &NL80211_NAN_SRF_BF isn't present. This is a nested
+ *	and only if %NL80211_NAN_SRF_BF isn't present. This is a nested
  *	attribute. Each nested attribute is a MAC address.
  * @NUM_NL80211_NAN_SRF_ATTR: internal
  * @NL80211_NAN_SRF_ATTR_MAX: highest NAN SRF attribute