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, 112 insertions, 93 deletions

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 10cf7c3dcbb3..3468d6b177a0 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -1,6 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * L2TP internal definitions.
+/* L2TP internal definitions.
  *
  * Copyright (c) 2008,2009 Katalix Systems Ltd
  */
@@ -16,17 +15,17 @@
 #include <net/xfrm.h>
 #endif
 
-/* Just some random numbers */
+/* Random numbers used for internal consistency checks of tunnel and session structures */
 #define L2TP_TUNNEL_MAGIC	0x42114DDA
 #define L2TP_SESSION_MAGIC	0x0C04EB7D
 
-/* Per tunnel, session hash table size */
+/* Per tunnel session hash table size */
 #define L2TP_HASH_BITS	4
-#define L2TP_HASH_SIZE	(1 << L2TP_HASH_BITS)
+#define L2TP_HASH_SIZE	BIT(L2TP_HASH_BITS)
 
-/* System-wide, session hash table size */
+/* System-wide session hash table size */
 #define L2TP_HASH_BITS_2	8
-#define L2TP_HASH_SIZE_2	(1 << L2TP_HASH_BITS_2)
+#define L2TP_HASH_SIZE_2	BIT(L2TP_HASH_BITS_2)
 
 struct sk_buff;
 
@@ -44,37 +43,34 @@ struct l2tp_stats {
 
 struct l2tp_tunnel;
 
-/* Describes a session. Contains information to determine incoming
- * packets and transmit outgoing ones.
- */
+/* L2TP session configuration */
 struct l2tp_session_cfg {
 	enum l2tp_pwtype	pw_type;
-	unsigned int		recv_seq:1;	/* expect receive packets with
-						 * sequence numbers? */
-	unsigned int		send_seq:1;	/* send packets with sequence
-						 * numbers? */
-	unsigned int		lns_mode:1;	/* behave as LNS? LAC enables
-						 * sequence numbers under
-						 * control of LNS. */
-	int			debug;		/* bitmask of debug message
-						 * categories */
+	unsigned int		recv_seq:1;	/* expect receive packets with sequence numbers? */
+	unsigned int		send_seq:1;	/* send packets with sequence numbers? */
+	unsigned int		lns_mode:1;	/* behave as LNS?
+						 * LAC enables sequence numbers under LNS control.
+						 */
+	int			debug;		/* bitmask of debug message categories */
 	u16			l2specific_type; /* Layer 2 specific type */
 	u8			cookie[8];	/* optional cookie */
 	int			cookie_len;	/* 0, 4 or 8 bytes */
 	u8			peer_cookie[8];	/* peer's cookie */
 	int			peer_cookie_len; /* 0, 4 or 8 bytes */
-	int			reorder_timeout; /* configured reorder timeout
-						  * (in jiffies) */
+	int			reorder_timeout; /* configured reorder timeout (in jiffies) */
 	char			*ifname;
 };
 
+/* Represents a session (pseudowire) instance.
+ * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics.
+ * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into
+ * an additional per-net ("global") hashlist.
+ */
 struct l2tp_session {
-	int			magic;		/* should be
-						 * L2TP_SESSION_MAGIC */
+	int			magic;		/* should be L2TP_SESSION_MAGIC */
 	long			dead;
 
-	struct l2tp_tunnel	*tunnel;	/* back pointer to tunnel
-						 * context */
+	struct l2tp_tunnel	*tunnel;	/* back pointer to tunnel context */
 	u32			session_id;
 	u32			peer_session_id;
 	u8			cookie[8];
@@ -89,42 +85,53 @@ struct l2tp_session {
 	u32			nr_max;		/* max NR. Depends on tunnel */
 	u32			nr_window_size;	/* NR window size */
 	u32			nr_oos;		/* NR of last OOS packet */
-	int			nr_oos_count;	/* For OOS recovery */
+	int			nr_oos_count;	/* for OOS recovery */
 	int			nr_oos_count_max;
-	struct hlist_node	hlist;		/* Hash list node */
+	struct hlist_node	hlist;		/* hash list node */
 	refcount_t		ref_count;
 
 	char			name[32];	/* for logging */
 	char			ifname[IFNAMSIZ];
-	unsigned int		recv_seq:1;	/* expect receive packets with
-						 * sequence numbers? */
-	unsigned int		send_seq:1;	/* send packets with sequence
-						 * numbers? */
-	unsigned int		lns_mode:1;	/* behave as LNS? LAC enables
-						 * sequence numbers under
-						 * control of LNS. */
-	int			debug;		/* bitmask of debug message
-						 * categories */
-	int			reorder_timeout; /* configured reorder timeout
-						  * (in jiffies) */
+	unsigned int		recv_seq:1;	/* expect receive packets with sequence numbers? */
+	unsigned int		send_seq:1;	/* send packets with sequence numbers? */
+	unsigned int		lns_mode:1;	/* behave as LNS?
+						 * LAC enables sequence numbers under LNS control.
+						 */
+	int			debug;		/* bitmask of debug message categories */
+	int			reorder_timeout; /* configured reorder timeout (in jiffies) */
 	int			reorder_skip;	/* set if skip to next nr */
 	enum l2tp_pwtype	pwtype;
 	struct l2tp_stats	stats;
-	struct hlist_node	global_hlist;	/* Global hash list node */
+	struct hlist_node	global_hlist;	/* global hash list node */
 
-	int (*build_header)(struct l2tp_session *session, void *buf);
+	/* Session receive handler for data packets.
+	 * Each pseudowire implementation should implement this callback in order to
+	 * handle incoming packets.  Packets are passed to the pseudowire handler after
+	 * reordering, if data sequence numbers are enabled for the session.
+	 */
 	void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
+
+	/* Session close handler.
+	 * Each pseudowire implementation may implement this callback in order to carry
+	 * out pseudowire-specific shutdown actions.
+	 * The callback is called by core after unhashing the session and purging its
+	 * reorder queue.
+	 */
 	void (*session_close)(struct l2tp_session *session);
+
+	/* Session show handler.
+	 * Pseudowire-specific implementation of debugfs session rendering.
+	 * The callback is called by l2tp_debugfs.c after rendering core session
+	 * information.
+	 */
 	void (*show)(struct seq_file *m, void *priv);
-	u8			priv[];	/* private data */
+
+	u8			priv[];		/* private data */
 };
 
-/* Describes the tunnel. It contains info to track all the associated
- * sessions so incoming packets can be sorted out
- */
+/* L2TP tunnel configuration */
 struct l2tp_tunnel_cfg {
-	int			debug;		/* bitmask of debug message
-						 * categories */
+	int			debug;		/* bitmask of debug message categories */
 	enum l2tp_encap_type	encap;
 
 	/* Used only for kernel-created sockets */
@@ -141,6 +148,12 @@ struct l2tp_tunnel_cfg {
 				udp6_zero_rx_checksums:1;
 };
 
+/* Represents a tunnel instance.
+ * Tracks runtime state including IO statistics.
+ * Holds the tunnel socket (either passed from userspace or directly created by the kernel).
+ * Maintains a hashlist of sessions belonging to the tunnel instance.
+ * Is linked into a per-net list of tunnels.
+ */
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
 
@@ -148,40 +161,51 @@ struct l2tp_tunnel {
 
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
-	bool			acpt_newsess;	/* Indicates whether this
-						 * tunnel accepts new sessions.
-						 * Protected by hlist_lock.
+	bool			acpt_newsess;	/* indicates whether this tunnel accepts
+						 * new sessions. Protected by hlist_lock.
 						 */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
-						/* hashed list of sessions,
-						 * hashed by id */
+						/* hashed list of sessions, hashed by id */
 	u32			tunnel_id;
 	u32			peer_tunnel_id;
 	int			version;	/* 2=>L2TPv2, 3=>L2TPv3 */
 
 	char			name[20];	/* for logging */
-	int			debug;		/* bitmask of debug message
-						 * categories */
+	int			debug;		/* bitmask of debug message categories */
 	enum l2tp_encap_type	encap;
 	struct l2tp_stats	stats;
 
-	struct list_head	list;		/* Keep a list of all tunnels */
+	struct list_head	list;		/* list node on per-namespace list of tunnels */
 	struct net		*l2tp_net;	/* the net we belong to */
 
 	refcount_t		ref_count;
-	void (*old_sk_destruct)(struct sock *);
-	struct sock		*sock;		/* Parent socket */
-	int			fd;		/* Parent fd, if tunnel socket
-						 * was created by userspace */
+	void (*old_sk_destruct)(struct sock *sk);
+	struct sock		*sock;		/* parent socket */
+	int			fd;		/* parent fd, if tunnel socket was created
+						 * by userspace
+						 */
 
 	struct work_struct	del_work;
 };
 
+/* Pseudowire ops callbacks for use with the l2tp genetlink interface */
 struct l2tp_nl_cmd_ops {
+	/* The pseudowire session create callback is responsible for creating a session
+	 * instance for a specific pseudowire type.
+	 * It must call l2tp_session_create and l2tp_session_register to register the
+	 * session instance, as well as carry out any pseudowire-specific initialisation.
+	 * It must return >= 0 on success, or an appropriate negative errno value on failure.
+	 */
 	int (*session_create)(struct net *net, struct l2tp_tunnel *tunnel,
 			      u32 session_id, u32 peer_session_id,
 			      struct l2tp_session_cfg *cfg);
-	int (*session_delete)(struct l2tp_session *session);
+
+	/* The pseudowire session delete callback is responsible for initiating the deletion
+	 * of a session instance.
+	 * It must call l2tp_session_delete, as well as carry out any pseudowire-specific
+	 * teardown actions.
+	 */
+	void (*session_delete)(struct l2tp_session *session);
 };
 
 static inline void *l2tp_session_priv(struct l2tp_session *session)
@@ -189,73 +213,68 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 	return &session->priv[0];
 }
 
+/* Tunnel and session refcounts */
+void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel);
+void l2tp_session_inc_refcount(struct l2tp_session *session);
+void l2tp_session_dec_refcount(struct l2tp_session *session);
+
+/* Tunnel and session lookup.
+ * These functions take a reference on the instances they return, so
+ * the caller must ensure that the reference is dropped appropriately.
+ */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
 struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel,
 					     u32 session_id);
 
-void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
-
 struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id);
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
 
+/* Tunnel and session lifetime management.
+ * Creation of a new instance is a two-step process: create, then register.
+ * Destruction is triggered using the *_delete functions, and completes asynchronously.
+ */
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			 struct l2tp_tunnel_cfg *cfg);
-
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
 					 struct l2tp_session_cfg *cfg);
 int l2tp_session_register(struct l2tp_session *session,
 			  struct l2tp_tunnel *tunnel);
+void l2tp_session_delete(struct l2tp_session *session);
 
-void __l2tp_session_unhash(struct l2tp_session *session);
-int l2tp_session_delete(struct l2tp_session *session);
-void l2tp_session_free(struct l2tp_session *session);
+/* Receive path helpers.  If data sequencing is enabled for the session these
+ * functions handle queuing and reordering prior to passing packets to the
+ * pseudowire code to be passed to userspace.
+ */
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
 		      int length);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
-void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
+/* Transmit path helpers for sending packets over the tunnel socket. */
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 		  int hdr_len);
 
-int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
-			 const struct l2tp_nl_cmd_ops *ops);
-void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
-int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
-
-static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
-{
-	refcount_inc(&tunnel->ref_count);
-}
-
-static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
-{
-	if (refcount_dec_and_test(&tunnel->ref_count))
-		l2tp_tunnel_free(tunnel);
-}
-
-/* Session reference counts. Incremented when code obtains a reference
- * to a session.
+/* Pseudowire management.
+ * Pseudowires should register with l2tp core on module init, and unregister
+ * on module exit.
  */
-static inline void l2tp_session_inc_refcount(struct l2tp_session *session)
-{
-	refcount_inc(&session->ref_count);
-}
+int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops);
+void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
 
-static inline void l2tp_session_dec_refcount(struct l2tp_session *session)
-{
-	if (refcount_dec_and_test(&session->ref_count))
-		l2tp_session_free(session);
-}
+/* IOCTL helper for IP encap modules. */
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
 static inline int l2tp_get_l2specific_len(struct l2tp_session *session)
 {