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

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 203 insertions, 0 deletions

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
new file mode 100644
index 000000000000..d035183c8d03
--- /dev/null
+++ b/include/net/flow_offload.h
@@ -0,0 +1,203 @@
+#ifndef _NET_FLOW_OFFLOAD_H
+#define _NET_FLOW_OFFLOAD_H
+
+#include <net/flow_dissector.h>
+
+struct flow_match {
+	struct flow_dissector	*dissector;
+	void			*mask;
+	void			*key;
+};
+
+struct flow_match_basic {
+	struct flow_dissector_key_basic *key, *mask;
+};
+
+struct flow_match_control {
+	struct flow_dissector_key_control *key, *mask;
+};
+
+struct flow_match_eth_addrs {
+	struct flow_dissector_key_eth_addrs *key, *mask;
+};
+
+struct flow_match_vlan {
+	struct flow_dissector_key_vlan *key, *mask;
+};
+
+struct flow_match_ipv4_addrs {
+	struct flow_dissector_key_ipv4_addrs *key, *mask;
+};
+
+struct flow_match_ipv6_addrs {
+	struct flow_dissector_key_ipv6_addrs *key, *mask;
+};
+
+struct flow_match_ip {
+	struct flow_dissector_key_ip *key, *mask;
+};
+
+struct flow_match_ports {
+	struct flow_dissector_key_ports *key, *mask;
+};
+
+struct flow_match_icmp {
+	struct flow_dissector_key_icmp *key, *mask;
+};
+
+struct flow_match_tcp {
+	struct flow_dissector_key_tcp *key, *mask;
+};
+
+struct flow_match_mpls {
+	struct flow_dissector_key_mpls *key, *mask;
+};
+
+struct flow_match_enc_keyid {
+	struct flow_dissector_key_keyid *key, *mask;
+};
+
+struct flow_match_enc_opts {
+	struct flow_dissector_key_enc_opts *key, *mask;
+};
+
+struct flow_rule;
+
+void flow_rule_match_basic(const struct flow_rule *rule,
+			   struct flow_match_basic *out);
+void flow_rule_match_control(const struct flow_rule *rule,
+			     struct flow_match_control *out);
+void flow_rule_match_eth_addrs(const struct flow_rule *rule,
+			       struct flow_match_eth_addrs *out);
+void flow_rule_match_vlan(const struct flow_rule *rule,
+			  struct flow_match_vlan *out);
+void flow_rule_match_ipv4_addrs(const struct flow_rule *rule,
+				struct flow_match_ipv4_addrs *out);
+void flow_rule_match_ipv6_addrs(const struct flow_rule *rule,
+				struct flow_match_ipv6_addrs *out);
+void flow_rule_match_ip(const struct flow_rule *rule,
+			struct flow_match_ip *out);
+void flow_rule_match_ports(const struct flow_rule *rule,
+			   struct flow_match_ports *out);
+void flow_rule_match_tcp(const struct flow_rule *rule,
+			 struct flow_match_tcp *out);
+void flow_rule_match_icmp(const struct flow_rule *rule,
+			  struct flow_match_icmp *out);
+void flow_rule_match_mpls(const struct flow_rule *rule,
+			  struct flow_match_mpls *out);
+void flow_rule_match_enc_control(const struct flow_rule *rule,
+				 struct flow_match_control *out);
+void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule,
+				    struct flow_match_ipv4_addrs *out);
+void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule,
+				    struct flow_match_ipv6_addrs *out);
+void flow_rule_match_enc_ip(const struct flow_rule *rule,
+			    struct flow_match_ip *out);
+void flow_rule_match_enc_ports(const struct flow_rule *rule,
+			       struct flow_match_ports *out);
+void flow_rule_match_enc_keyid(const struct flow_rule *rule,
+			       struct flow_match_enc_keyid *out);
+void flow_rule_match_enc_opts(const struct flow_rule *rule,
+			      struct flow_match_enc_opts *out);
+
+enum flow_action_id {
+	FLOW_ACTION_ACCEPT		= 0,
+	FLOW_ACTION_DROP,
+	FLOW_ACTION_TRAP,
+	FLOW_ACTION_GOTO,
+	FLOW_ACTION_REDIRECT,
+	FLOW_ACTION_MIRRED,
+	FLOW_ACTION_VLAN_PUSH,
+	FLOW_ACTION_VLAN_POP,
+	FLOW_ACTION_VLAN_MANGLE,
+	FLOW_ACTION_TUNNEL_ENCAP,
+	FLOW_ACTION_TUNNEL_DECAP,
+	FLOW_ACTION_MANGLE,
+	FLOW_ACTION_ADD,
+	FLOW_ACTION_CSUM,
+	FLOW_ACTION_MARK,
+	FLOW_ACTION_WAKE,
+	FLOW_ACTION_QUEUE,
+};
+
+/* This is mirroring enum pedit_header_type definition for easy mapping between
+ * tc pedit action. Legacy TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK is mapped to
+ * FLOW_ACT_MANGLE_UNSPEC, which is supported by no driver.
+ */
+enum flow_action_mangle_base {
+	FLOW_ACT_MANGLE_UNSPEC		= 0,
+	FLOW_ACT_MANGLE_HDR_TYPE_ETH,
+	FLOW_ACT_MANGLE_HDR_TYPE_IP4,
+	FLOW_ACT_MANGLE_HDR_TYPE_IP6,
+	FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+	FLOW_ACT_MANGLE_HDR_TYPE_UDP,
+};
+
+struct flow_action_entry {
+	enum flow_action_id		id;
+	union {
+		u32			chain_index;	/* FLOW_ACTION_GOTO */
+		struct net_device	*dev;		/* FLOW_ACTION_REDIRECT */
+		struct {				/* FLOW_ACTION_VLAN */
+			u16		vid;
+			__be16		proto;
+			u8		prio;
+		} vlan;
+		struct {				/* FLOW_ACTION_PACKET_EDIT */
+			enum flow_action_mangle_base htype;
+			u32		offset;
+			u32		mask;
+			u32		val;
+		} mangle;
+		const struct ip_tunnel_info *tunnel;	/* FLOW_ACTION_TUNNEL_ENCAP */
+		u32			csum_flags;	/* FLOW_ACTION_CSUM */
+		u32			mark;		/* FLOW_ACTION_MARK */
+		struct {				/* FLOW_ACTION_QUEUE */
+			u32		ctx;
+			u32		index;
+			u8		vf;
+		} queue;
+	};
+};
+
+struct flow_action {
+	unsigned int			num_entries;
+	struct flow_action_entry 	entries[0];
+};
+
+static inline bool flow_action_has_entries(const struct flow_action *action)
+{
+	return action->num_entries;
+}
+
+#define flow_action_for_each(__i, __act, __actions)			\
+        for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i])
+
+struct flow_rule {
+	struct flow_match	match;
+	struct flow_action	action;
+};
+
+struct flow_rule *flow_rule_alloc(unsigned int num_actions);
+
+static inline bool flow_rule_match_key(const struct flow_rule *rule,
+				       enum flow_dissector_key_id key)
+{
+	return dissector_uses_key(rule->match.dissector, key);
+}
+
+struct flow_stats {
+	u64	pkts;
+	u64	bytes;
+	u64	lastused;
+};
+
+static inline void flow_stats_update(struct flow_stats *flow_stats,
+				     u64 bytes, u64 pkts, u64 lastused)
+{
+	flow_stats->pkts	+= pkts;
+	flow_stats->bytes	+= bytes;
+	flow_stats->lastused	= max_t(u64, flow_stats->lastused, lastused);
+}
+
+#endif /* _NET_FLOW_OFFLOAD_H */