Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

1 files changed, 101 insertions, 29 deletions

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c6eeaf3e8dcb..60b27d44c184 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -89,6 +89,7 @@
 #define MPTCP_SEND_SPACE	1
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
+#define MPTCP_FALLBACK_DONE	4
 
 struct mptcp_options_received {
 	u64	sndr_key;
@@ -173,8 +174,6 @@ struct mptcp_pm_data {
 	u8		local_addr_max;
 	u8		subflows_max;
 	u8		status;
-
-	struct		work_struct work;
 };
 
 struct mptcp_data_frag {
@@ -194,11 +193,15 @@ struct mptcp_sock {
 	u64		remote_key;
 	u64		write_seq;
 	u64		ack_seq;
+	u64		rcv_data_fin_seq;
 	atomic64_t	snd_una;
 	unsigned long	timer_ival;
 	u32		token;
 	unsigned long	flags;
 	bool		can_ack;
+	bool		fully_established;
+	bool		rcv_data_fin;
+	bool		snd_data_fin_enable;
 	spinlock_t	join_list_lock;
 	struct work_struct work;
 	struct list_head conn_list;
@@ -208,6 +211,12 @@ struct mptcp_sock {
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
+	struct {
+		u32	space;	/* bytes copied in last measurement window */
+		u32	copied; /* bytes copied in this measurement window */
+		u64	time;	/* start time of measurement window */
+		u64	rtt_us; /* last maximum rtt of subflows */
+	} rcvq_space;
 };
 
 #define mptcp_for_each_subflow(__msk, __subflow)			\
@@ -250,6 +259,7 @@ struct mptcp_subflow_request_sock {
 	u32	local_nonce;
 	u32	remote_nonce;
 	struct mptcp_sock	*msk;
+	struct hlist_nulls_node token_node;
 };
 
 static inline struct mptcp_subflow_request_sock *
@@ -284,10 +294,8 @@ struct mptcp_subflow_context {
 		backup : 1,
 		data_avail : 1,
 		rx_eof : 1,
-		data_fin_tx_enable : 1,
 		use_64bit_ack : 1, /* Set when we received a 64-bit DSN */
 		can_ack : 1;	    /* only after processing the remote a key */
-	u64	data_fin_tx_seq;
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
@@ -336,8 +344,10 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
 }
 
 int mptcp_is_enabled(struct net *net);
+void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
+				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
-void mptcp_subflow_init(void);
+void __init mptcp_subflow_init(void);
 
 /* called with sk socket lock held */
 int __mptcp_subflow_connect(struct sock *sk, int ifindex,
@@ -355,14 +365,9 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 	inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
 }
 
-extern const struct inet_connection_sock_af_ops ipv4_specific;
+void __init mptcp_proto_init(void);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-extern const struct inet_connection_sock_af_ops ipv6_specific;
-#endif
-
-void mptcp_proto_init(void);
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-int mptcp_proto_v6_init(void);
+int __init mptcp_proto_v6_init(void);
 #endif
 
 struct sock *mptcp_sk_clone(const struct sock *sk,
@@ -372,36 +377,41 @@ void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
+static inline bool mptcp_is_fully_established(struct sock *sk)
+{
+	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
+	       READ_ONCE(mptcp_sk(sk)->fully_established);
+}
+void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
 void mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
+bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq);
+
+void __init mptcp_token_init(void);
+static inline void mptcp_token_init_request(struct request_sock *req)
+{
+	mptcp_subflow_rsk(req)->token_node.pprev = NULL;
+}
 
 int mptcp_token_new_request(struct request_sock *req);
-void mptcp_token_destroy_request(u32 token);
+void mptcp_token_destroy_request(struct request_sock *req);
 int mptcp_token_new_connect(struct sock *sk);
-int mptcp_token_new_accept(u32 token, struct sock *conn);
+void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
+			struct mptcp_sock *msk);
+bool mptcp_token_exists(u32 token);
 struct mptcp_sock *mptcp_token_get_sock(u32 token);
-void mptcp_token_destroy(u32 token);
+struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
+					 long *s_num);
+void mptcp_token_destroy(struct mptcp_sock *msk);
 
 void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
-static inline void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn)
-{
-	/* we might consider a faster version that computes the key as a
-	 * hash of some information available in the MPTCP socket. Use
-	 * random data at the moment, as it's probably the safest option
-	 * in case multiple sockets are opened in different namespaces at
-	 * the same time.
-	 */
-	get_random_bytes(key, sizeof(u64));
-	mptcp_crypto_key_sha(*key, token, idsn);
-}
 
 void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
 
-void mptcp_pm_init(void);
+void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
-void mptcp_pm_close(struct mptcp_sock *msk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
@@ -433,7 +443,7 @@ bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			  struct mptcp_addr_info *saddr);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
-void mptcp_pm_nl_init(void);
+void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
 void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
@@ -454,4 +464,66 @@ static inline bool before64(__u64 seq1, __u64 seq2)
 
 void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
 
+static inline bool __mptcp_check_fallback(struct mptcp_sock *msk)
+{
+	return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+}
+
+static inline bool mptcp_check_fallback(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	return __mptcp_check_fallback(msk);
+}
+
+static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
+{
+	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) {
+		pr_debug("TCP fallback already done (msk=%p)", msk);
+		return;
+	}
+	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+}
+
+static inline void mptcp_do_fallback(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	__mptcp_do_fallback(msk);
+}
+
+#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
+
+static inline bool subflow_simultaneous_connect(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct sock *parent = subflow->conn;
+
+	return sk->sk_state == TCP_ESTABLISHED &&
+	       !mptcp_sk(parent)->pm.server_side &&
+	       !subflow->conn_finished;
+}
+
+#ifdef CONFIG_SYN_COOKIES
+void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
+				       struct sk_buff *skb);
+bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
+					struct sk_buff *skb);
+void __init mptcp_join_cookie_init(void);
+#else
+static inline void
+subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
+				  struct sk_buff *skb) {}
+static inline bool
+mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
+				   struct sk_buff *skb)
+{
+	return false;
+}
+
+static inline void mptcp_join_cookie_init(void) {}
+#endif
+
 #endif /* __MPTCP_PROTOCOL_H */