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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

5 files changed, 193 insertions, 6 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 489e118b69d2..f506c68b2612 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -170,6 +170,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 };
 
 enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_SYSCTL,
 	BPF_CGROUP_UDP4_RECVMSG,
 	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -262,6 +265,24 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
+/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
+ * Verifier does sub-register def/use analysis and identifies instructions whose
+ * def only matters for low 32-bit, high 32-bit is never referenced later
+ * through implicit zero extension. Therefore verifier notifies JIT back-ends
+ * that it is safe to ignore clearing high 32-bit for these instructions. This
+ * saves some back-ends a lot of code-gen. However such optimization is not
+ * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
+ * hence hasn't used verifier's analysis result. But, we really want to have a
+ * way to be able to verify the correctness of the described optimization on
+ * x86_64 on which testsuites are frequently exercised.
+ *
+ * So, this flag is introduced. Once it is set, verifier will randomize high
+ * 32-bit for those instructions who has been identified as safe to ignore them.
+ * Then, if verifier is not doing correct analysis, such randomization will
+ * regress tests to expose bugs.
+ */
+#define BPF_F_TEST_RND_HI32	(1U << 2)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
@@ -1746,6 +1767,7 @@ union bpf_attr {
  * 		* **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
  * 		* **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
  * 		* **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ * 		* **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
  *
  * 		Therefore, this function can be used to clear a callback flag by
  * 		setting the appropriate bit to zero. e.g. to disable the RTO
@@ -2674,6 +2696,20 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *
+ * int bpf_send_signal(u32 sig)
+ *	Description
+ *		Send signal *sig* to the current task.
+ *	Return
+ *		0 on success or successfully queued.
+ *
+ *		**-EBUSY** if work queue under nmi is full.
+ *
+ *		**-EINVAL** if *sig* is invalid.
+ *
+ *		**-EPERM** if no permission to send the *sig*.
+ *
+ *		**-EAGAIN** if bpf program can try again.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2784,7 +2820,8 @@ union bpf_attr {
 	FN(strtol),			\
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
-	FN(sk_storage_delete),
+	FN(sk_storage_delete),		\
+	FN(send_signal),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3033,6 +3070,12 @@ struct bpf_tcp_sock {
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	__u32 dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
+				 * total number of DSACK blocks received
+				 */
+	__u32 delivered;	/* Total data packets delivered incl. rexmits */
+	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
+	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
 };
 
 struct bpf_sock_tuple {
@@ -3052,6 +3095,10 @@ struct bpf_sock_tuple {
 	};
 };
 
+struct bpf_xdp_sock {
+	__u32 queue_id;
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
@@ -3143,6 +3190,7 @@ struct bpf_prog_info {
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
 	__u32 gpl_compatible:1;
+	__u32 :31; /* alignment pad */
 	__u64 netns_dev;
 	__u64 netns_ino;
 	__u32 nr_jited_ksyms;
@@ -3197,7 +3245,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3206,12 +3254,13 @@ struct bpf_sock_addr {
 	__u32 family;		/* Allows 4-byte read, but no write */
 	__u32 type;		/* Allows 4-byte read, but no write */
 	__u32 protocol;		/* Allows 4-byte read, but no write */
-	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -3263,13 +3312,15 @@ struct bpf_sock_ops {
 	__u32 sk_txhash;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
 #define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
 #define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
+#define BPF_SOCK_OPS_RTT_CB_FLAG	(1<<3)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0xF		/* Mask of all currently
 							 * supported cb flags
 							 */
 
@@ -3324,6 +3375,8 @@ enum {
 	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
 					 * socket transition to LISTEN state.
 					 */
+	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -3502,4 +3555,15 @@ struct bpf_sysctl {
 				 */
 };
 
+struct bpf_sockopt {
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(void *, optval);
+	__bpf_md_ptr(void *, optval_end);
+
+	__s32	level;
+	__s32	optname;
+	__s32	optlen;
+	__s32	retval;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 5b225ff63b48..7d113a9602f0 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -636,6 +636,7 @@ enum {
 	IFLA_BOND_AD_USER_PORT_KEY,
 	IFLA_BOND_AD_ACTOR_SYSTEM,
 	IFLA_BOND_TLB_DYNAMIC_LB,
+	IFLA_BOND_PEER_NOTIF_DELAY,
 	__IFLA_BOND_MAX,
 };
 
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
new file mode 100644
index 000000000000..454ae31b93c7
--- /dev/null
+++ b/tools/include/uapi/linux/if_tun.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  Universal TUN/TAP device driver.
+ *  Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ *  GNU General Public License for more details.
+ */
+
+#ifndef _UAPI__IF_TUN_H
+#define _UAPI__IF_TUN_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/filter.h>
+
+/* Read queue size */
+#define TUN_READQ_SIZE	500
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV 	IFF_TUN
+#define TUN_TAP_DEV	IFF_TAP
+#define TUN_TYPE_MASK   0x000f
+
+/* Ioctl defines */
+#define TUNSETNOCSUM  _IOW('T', 200, int) 
+#define TUNSETDEBUG   _IOW('T', 201, int) 
+#define TUNSETIFF     _IOW('T', 202, int) 
+#define TUNSETPERSIST _IOW('T', 203, int) 
+#define TUNSETOWNER   _IOW('T', 204, int)
+#define TUNSETLINK    _IOW('T', 205, int)
+#define TUNSETGROUP   _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD  _IOW('T', 208, unsigned int)
+#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
+#define TUNGETIFF      _IOR('T', 210, unsigned int)
+#define TUNGETSNDBUF   _IOR('T', 211, int)
+#define TUNSETSNDBUF   _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE  _IOW('T', 217, int)
+#define TUNSETIFINDEX	_IOW('T', 218, unsigned int)
+#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
+#define TUNSETSTEERINGEBPF _IOR('T', 224, int)
+#define TUNSETFILTEREBPF _IOR('T', 225, int)
+#define TUNSETCARRIER _IOW('T', 226, int)
+#define TUNGETDEVNETNS _IO('T', 227)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TUN		0x0001
+#define IFF_TAP		0x0002
+#define IFF_NAPI	0x0010
+#define IFF_NAPI_FRAGS	0x0020
+#define IFF_NO_PI	0x1000
+/* This flag has no real effect */
+#define IFF_ONE_QUEUE	0x2000
+#define IFF_VNET_HDR	0x4000
+#define IFF_TUN_EXCL	0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+/* read-only flag */
+#define IFF_PERSIST	0x0800
+#define IFF_NOFILTER	0x1000
+
+/* Socket options */
+#define TUN_TX_TIMESTAMP 1
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM	0x01	/* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4	0x02	/* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6	0x04	/* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN	0x08	/* I can handle TSO with ECN bits. */
+#define TUN_F_UFO	0x10	/* I can handle UFO packets */
+
+/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
+#define TUN_PKT_STRIP	0x0001
+struct tun_pi {
+	__u16  flags;
+	__be16 proto;
+};
+
+/*
+ * Filter spec (used for SETXXFILTER ioctls)
+ * This stuff is applicable only to the TAP (Ethernet) devices.
+ * If the count is zero the filter is disabled and the driver accepts
+ * all packets (promisc mode).
+ * If the filter is enabled in order to accept broadcast packets
+ * broadcast addr must be explicitly included in the addr list.
+ */
+#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
+struct tun_filter {
+	__u16  flags; /* TUN_FLT_ flags see above */
+	__u16  count; /* Number of addresses */
+	__u8   addr[0][ETH_ALEN];
+};
+
+#endif /* _UAPI__IF_TUN_H */
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index caed8b1614ff..faaa5ca2a117 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -46,6 +46,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_FILL_RING		5
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
+#define XDP_OPTIONS			8
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */
@@ -60,6 +61,13 @@ struct xdp_statistics {
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
 };
 
+struct xdp_options {
+	__u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
 /* Pgoff for mmaping the rings */
 #define XDP_PGOFF_RX_RING			  0
 #define XDP_PGOFF_TX_RING		 0x80000000
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
index 401d0c1e612d..12153771396a 100644
--- a/tools/include/uapi/linux/pkt_cls.h
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -257,7 +257,7 @@ enum {
 	TCA_FW_UNSPEC,
 	TCA_FW_CLASSID,
 	TCA_FW_POLICE,
-	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_INDEV,
 	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
 	TCA_FW_MASK,
 	__TCA_FW_MAX