Merge tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Enable memcg accounting for various networking objects.

  BPF:

   - Introduce bpf timers.

   - Add perf link and opaque bpf_cookie which the program can read out
     again, to be used in libbpf-based USDT library.

   - Add bpf_task_pt_regs() helper to access user space pt_regs in
     kprobes, to help user space stack unwinding.

   - Add support for UNIX sockets for BPF sockmap.

   - Extend BPF iterator support for UNIX domain sockets.

   - Allow BPF TCP congestion control progs and bpf iterators to call
     bpf_setsockopt(), e.g. to switch to another congestion control
     algorithm.

  Protocols:

   - Support IOAM Pre-allocated Trace with IPv6.

   - Support Management Component Transport Protocol.

   - bridge: multicast: add vlan support.

   - netfilter: add hooks for the SRv6 lightweight tunnel driver.

   - tcp:
       - enable mid-stream window clamping (by user space or BPF)
       - allow data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD
       - more accurate DSACK processing for RACK-TLP

   - mptcp:
       - add full mesh path manager option
       - add partial support for MP_FAIL
       - improve use of backup subflows
       - optimize option processing

   - af_unix: add OOB notification support.

   - ipv6: add IFLA_INET6_RA_MTU to expose MTU value advertised by the
     router.

   - mac80211: Target Wake Time support in AP mode.

   - can: j1939: extend UAPI to notify about RX status.

  Driver APIs:

   - Add page frag support in page pool API.

   - Many improvements to the DSA (distributed switch) APIs.

   - ethtool: extend IRQ coalesce uAPI with timer reset modes.

   - devlink: control which auxiliary devices are created.

   - Support CAN PHYs via the generic PHY subsystem.

   - Proper cross-chip support for tag_8021q.

   - Allow TX forwarding for the software bridge data path to be
     offloaded to capable devices.

  Drivers:

   - veth: more flexible channels number configuration.

   - openvswitch: introduce per-cpu upcall dispatch.

   - Add internet mix (IMIX) mode to pktgen.

   - Transparently handle XDP operations in the bonding driver.

   - Add LiteETH network driver.

   - Renesas (ravb):
       - support Gigabit Ethernet IP

   - NXP Ethernet switch (sja1105):
       - fast aging support
       - support for "H" switch topologies
       - traffic termination for ports under VLAN-aware bridge

   - Intel 1G Ethernet
       - support getcrosststamp() with PCIe PTM (Precision Time
         Measurement) for better time sync
       - support Credit-Based Shaper (CBS) offload, enabling HW traffic
         prioritization and bandwidth reservation

   - Broadcom Ethernet (bnxt)
       - support pulse-per-second output
       - support larger Rx rings

   - Mellanox Ethernet (mlx5)
       - support ethtool RSS contexts and MQPRIO channel mode
       - support LAG offload with bridging
       - support devlink rate limit API
       - support packet sampling on tunnels

   - Huawei Ethernet (hns3):
       - basic devlink support
       - add extended IRQ coalescing support
       - report extended link state

   - Netronome Ethernet (nfp):
       - add conntrack offload support

   - Broadcom WiFi (brcmfmac):
       - add WPA3 Personal with FT to supported cipher suites
       - support 43752 SDIO device

   - Intel WiFi (iwlwifi):
       - support scanning hidden 6GHz networks
       - support for a new hardware family (Bz)

   - Xen pv driver:
       - harden netfront against malicious backends

   - Qualcomm mobile
       - ipa: refactor power management and enable automatic suspend
       - mhi: move MBIM to WWAN subsystem interfaces

  Refactor:

   - Ambient BPF run context and cgroup storage cleanup.

   - Compat rework for ndo_ioctl.

  Old code removal:

   - prism54 remove the obsoleted driver, deprecated by the p54 driver.

   - wan: remove sbni/granch driver"

* tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1715 commits)
  net: Add depends on OF_NET for LiteX's LiteETH
  ipv6: seg6: remove duplicated include
  net: hns3: remove unnecessary spaces
  net: hns3: add some required spaces
  net: hns3: clean up a type mismatch warning
  net: hns3: refine function hns3_set_default_feature()
  ipv6: remove duplicated 'net/lwtunnel.h' include
  net: w5100: check return value after calling platform_get_resource()
  net/mlxbf_gige: Make use of devm_platform_ioremap_resourcexxx()
  net: mdio: mscc-miim: Make use of the helper function devm_platform_ioremap_resource()
  net: mdio-ipq4019: Make use of devm_platform_ioremap_resource()
  fou: remove sparse errors
  ipv4: fix endianness issue in inet_rtm_getroute_build_skb()
  octeontx2-af: Set proper errorcode for IPv4 checksum errors
  octeontx2-af: Fix static code analyzer reported issues
  octeontx2-af: Fix mailbox errors in nix_rss_flowkey_cfg
  octeontx2-af: Fix loop in free and unmap counter
  af_unix: fix potential NULL deref in unix_dgram_connect()
  dpaa2-eth: Replace strlcpy with strscpy
  octeontx2-af: Use NDC TX for transmit packet data
  ...

1 files changed, 73 insertions, 41 deletions

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0f0c026c5f8b..d7aba1c4dc48 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -26,6 +26,15 @@
 #define OPTION_MPTCP_FASTCLOSE	BIT(8)
 #define OPTION_MPTCP_PRIO	BIT(9)
 #define OPTION_MPTCP_RST	BIT(10)
+#define OPTION_MPTCP_DSS	BIT(11)
+#define OPTION_MPTCP_FAIL	BIT(12)
+
+#define OPTION_MPTCP_CSUMREQD	BIT(13)
+
+#define OPTIONS_MPTCP_MPC	(OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | \
+				 OPTION_MPTCP_MPC_ACK)
+#define OPTIONS_MPTCP_MPJ	(OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \
+				 OPTION_MPTCP_MPJ_SYNACK)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0
@@ -67,6 +76,7 @@
 #define TCPOLEN_MPTCP_PRIO_ALIGN	4
 #define TCPOLEN_MPTCP_FASTCLOSE		12
 #define TCPOLEN_MPTCP_RST		4
+#define TCPOLEN_MPTCP_FAIL		12
 
 #define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM	(TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA)
 
@@ -129,35 +139,28 @@ struct mptcp_options_received {
 	u32	subflow_seq;
 	u16	data_len;
 	__sum16	csum;
-	u16	mp_capable : 1,
-		mp_join : 1,
-		fastclose : 1,
-		reset : 1,
-		dss : 1,
-		add_addr : 1,
-		rm_addr : 1,
-		mp_prio : 1,
-		echo : 1,
-		csum_reqd : 1,
-		backup : 1,
-		deny_join_id0 : 1;
+	u16	suboptions;
 	u32	token;
 	u32	nonce;
-	u64	thmac;
-	u8	hmac[MPTCPOPT_HMAC_LEN];
-	u8	join_id;
-	u8	use_map:1,
+	u16	use_map:1,
 		dsn64:1,
 		data_fin:1,
 		use_ack:1,
 		ack64:1,
 		mpc_map:1,
+		reset_reason:4,
+		reset_transient:1,
+		echo:1,
+		backup:1,
+		deny_join_id0:1,
 		__unused:2;
+	u8	join_id;
+	u64	thmac;
+	u8	hmac[MPTCPOPT_HMAC_LEN];
 	struct mptcp_addr_info addr;
 	struct mptcp_rm_list rm_list;
 	u64	ahmac;
-	u8	reset_reason:4;
-	u8	reset_transient:1;
+	u64	fail_seq;
 };
 
 static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
@@ -178,8 +181,6 @@ enum mptcp_pm_status {
 enum mptcp_addr_signal_status {
 	MPTCP_ADD_ADDR_SIGNAL,
 	MPTCP_ADD_ADDR_ECHO,
-	MPTCP_ADD_ADDR_IPV6,
-	MPTCP_ADD_ADDR_PORT,
 	MPTCP_RM_ADDR_SIGNAL,
 };
 
@@ -230,12 +231,17 @@ struct mptcp_sock {
 	struct sock	*last_snd;
 	int		snd_burst;
 	int		old_wspace;
+	u64		recovery_snd_nxt;	/* in recovery mode accept up to this seq;
+						 * recovery related fields are under data_lock
+						 * protection
+						 */
 	u64		snd_una;
 	u64		wnd_end;
 	unsigned long	timer_ival;
 	u32		token;
 	int		rmem_released;
 	unsigned long	flags;
+	bool		recovery;		/* closing subflow write queue reinjected */
 	bool		can_ack;
 	bool		fully_established;
 	bool		rcv_data_fin;
@@ -425,9 +431,11 @@ struct mptcp_subflow_context {
 		mpc_map : 1,
 		backup : 1,
 		send_mp_prio : 1,
+		send_mp_fail : 1,
 		rx_eof : 1,
 		can_ack : 1,        /* only after processing the remote a key */
-		disposable : 1;	    /* ctx can be free at ulp release time */
+		disposable : 1,	    /* ctx can be free at ulp release time */
+		stale : 1;	    /* unable to snd/rcv data, do not use for xmit */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -439,11 +447,13 @@ struct mptcp_subflow_context {
 	u8	reset_seen:1;
 	u8	reset_transient:1;
 	u8	reset_reason:4;
+	u8	stale_count;
 
 	long	delegated_status;
 	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */
 
-	u32 setsockopt_seq;
+	u32	setsockopt_seq;
+	u32	stale_rcv_tstamp;
 
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */
@@ -549,12 +559,15 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su
 	clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
 }
 
-int mptcp_is_enabled(struct net *net);
-unsigned int mptcp_get_add_addr_timeout(struct net *net);
-int mptcp_is_checksum_enabled(struct net *net);
-int mptcp_allow_join_id0(struct net *net);
+int mptcp_is_enabled(const struct net *net);
+unsigned int mptcp_get_add_addr_timeout(const struct net *net);
+int mptcp_is_checksum_enabled(const struct net *net);
+int mptcp_allow_join_id0(const struct net *net);
+unsigned int mptcp_stale_loss_cnt(const struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
+bool __mptcp_retransmit_pending_data(struct sock *sk);
+void __mptcp_push_pending(struct sock *sk, unsigned int flags);
 bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
 void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
@@ -566,14 +579,13 @@ struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
 
 /* called with sk socket lock held */
 int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
-			    const struct mptcp_addr_info *remote,
-			    u8 flags, int ifindex);
+			    const struct mptcp_addr_info *remote);
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
 
-static inline bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
 	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -585,6 +597,10 @@ static inline bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
 }
 
+void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow);
+
+bool mptcp_subflow_active(struct mptcp_subflow_context *subflow);
+
 static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 					      struct mptcp_subflow_context *ctx)
 {
@@ -596,6 +612,19 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 	inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
 }
 
+static inline bool mptcp_has_another_subflow(struct sock *ssk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk), *tmp;
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	mptcp_for_each_subflow(msk, tmp) {
+		if (tmp != subflow)
+			return true;
+	}
+
+	return false;
+}
+
 void __init mptcp_proto_init(void);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 int __init mptcp_proto_v6_init(void);
@@ -690,6 +719,8 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
 
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
+void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
+void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
@@ -708,6 +739,7 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
 int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 				 struct mptcp_addr_info *addr,
 				 u8 bkup);
+void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
 struct mptcp_pm_add_entry *
@@ -716,6 +748,8 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 struct mptcp_pm_add_entry *
 mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
 				struct mptcp_addr_info *addr);
+int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id,
+					 u8 *flags, int *ifindex);
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
@@ -730,22 +764,18 @@ void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
+	return READ_ONCE(msk->pm.addr_signal) &
+		(BIT(MPTCP_ADD_ADDR_SIGNAL) | BIT(MPTCP_ADD_ADDR_ECHO));
 }
 
-static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
-{
-	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
-}
-
-static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
+static inline bool mptcp_pm_should_add_signal_addr(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
 }
 
-static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk)
+static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT);
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
 }
 
 static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
@@ -776,8 +806,10 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list)
 	return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1;
 }
 
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			      struct mptcp_addr_info *saddr, bool *echo, bool *port);
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb,
+			      unsigned int opt_size, unsigned int remaining,
+			      struct mptcp_addr_info *addr, bool *echo,
+			      bool *port, bool *drop_other_suboptions);
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);