Merge tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Wrap datapath globals into net_aligned_data, to avoid false sharing

   - Preserve MSG_ZEROCOPY in forwarding (e.g. out of a container)

   - Add SO_INQ and SCM_INQ support to AF_UNIX

   - Add SIOCINQ support to AF_VSOCK

   - Add TCP_MAXSEG sockopt to MPTCP

   - Add IPv6 force_forwarding sysctl to enable forwarding per interface

   - Make TCP validation of whether packet fully fits in the receive
     window and the rcv_buf more strict. With increased use of HW
     aggregation a single "packet" can be multiple 100s of kB

   - Add MSG_MORE flag to optimize large TCP transmissions via sockmap,
     improves latency up to 33% for sockmap users

   - Convert TCP send queue handling from tasklet to BH workque

   - Improve BPF iteration over TCP sockets to see each socket exactly
     once

   - Remove obsolete and unused TCP RFC3517/RFC6675 loss recovery code

   - Support enabling kernel threads for NAPI processing on per-NAPI
     instance basis rather than a whole device. Fully stop the kernel
     NAPI thread when threaded NAPI gets disabled. Previously thread
     would stick around until ifdown due to tricky synchronization

   - Allow multicast routing to take effect on locally-generated packets

   - Add output interface argument for End.X in segment routing

   - MCTP: add support for gateway routing, improve bind() handling

   - Don't require rtnl_lock when fetching an IPv6 neighbor over Netlink

   - Add a new neighbor flag ("extern_valid"), which cedes refresh
     responsibilities to userspace. This is needed for EVPN multi-homing
     where a neighbor entry for a multi-homed host needs to be synced
     across all the VTEPs among which the host is multi-homed

   - Support NUD_PERMANENT for proxy neighbor entries

   - Add a new queuing discipline for IETF RFC9332 DualQ Coupled AQM

   - Add sequence numbers to netconsole messages. Unregister
     netconsole's console when all net targets are removed. Code
     refactoring. Add a number of selftests

   - Align IPSec inbound SA lookup to RFC 4301. Only SPI and protocol
     should be used for an inbound SA lookup

   - Support inspecting ref_tracker state via DebugFS

   - Don't force bonding advertisement frames tx to ~333 ms boundaries.
     Add broadcast_neighbor option to send ARP/ND on all bonded links

   - Allow providing upcall pid for the 'execute' command in openvswitch

   - Remove DCCP support from Netfilter's conntrack

   - Disallow multiple packet duplications in the queuing layer

   - Prevent use of deprecated iptables code on PREEMPT_RT

  Driver API:

   - Support RSS and hashing configuration over ethtool Netlink

   - Add dedicated ethtool callbacks for getting and setting hashing
     fields

   - Add support for power budget evaluation strategy in PSE /
     Power-over-Ethernet. Generate Netlink events for overcurrent etc

   - Support DPLL phase offset monitoring across all device inputs.
     Support providing clock reference and SYNC over separate DPLL
     inputs

   - Support traffic classes in devlink rate API for bandwidth
     management

   - Remove rtnl_lock dependency from UDP tunnel port configuration

  Device drivers:

   - Add a new Broadcom driver for 800G Ethernet (bnge)

   - Add a standalone driver for Microchip ZL3073x DPLL

   - Remove IBM's NETIUCV device driver

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - support zero-copy Tx of DMABUF memory
         - take page size into account for page pool recycling rings
      - Intel (100G, ice, idpf):
         - idpf: XDP and AF_XDP support preparations
         - idpf: add flow steering
         - add link_down_events statistic
         - clean up the TSPLL code
         - preparations for live VM migration
      - nVidia/Mellanox:
         - support zero-copy Rx/Tx interfaces (DMABUF and io_uring)
         - optimize context memory usage for matchers
         - expose serial numbers in devlink info
         - support PCIe congestion metrics
      - Meta (fbnic):
         - add 25G, 50G, and 100G link modes to phylink
         - support dumping FW logs
      - Marvell/Cavium:
         - support for CN20K generation of the Octeon chips
      - Amazon:
         - add HW clock (without timestamping, just hypervisor time access)

   - Ethernet virtual:
      - VirtIO net:
         - support segmentation of UDP-tunnel-encapsulated packets
      - Google (gve):
         - support packet timestamping and clock synchronization
      - Microsoft vNIC:
         - add handler for device-originated servicing events
         - allow dynamic MSI-X vector allocation
         - support Tx bandwidth clamping

   - Ethernet NICs consumer, and embedded:
      - AMD:
         - amd-xgbe: hardware timestamping and PTP clock support
      - Broadcom integrated MACs (bcmgenet, bcmasp):
         - use napi_complete_done() return value to support NAPI polling
         - add support for re-starting auto-negotiation
      - Broadcom switches (b53):
         - support BCM5325 switches
         - add bcm63xx EPHY power control
      - Synopsys (stmmac):
         - lots of code refactoring and cleanups
      - TI:
         - icssg-prueth: read firmware-names from device tree
         - icssg: PRP offload support
      - Microchip:
         - lan78xx: convert to PHYLINK for improved PHY and MAC management
         - ksz: add KSZ8463 switch support
      - Intel:
         - support similar queue priority scheme in multi-queue and
           time-sensitive networking (taprio)
         - support packet pre-emption in both
      - RealTek (r8169):
         - enable EEE at 5Gbps on RTL8126
      - Airoha:
         - add PPPoE offload support
         - MDIO bus controller for Airoha AN7583

   - Ethernet PHYs:
      - support for the IPQ5018 internal GE PHY
      - micrel KSZ9477 switch-integrated PHYs:
         - add MDI/MDI-X control support
         - add RX error counters
         - add cable test support
         - add Signal Quality Indicator (SQI) reporting
      - dp83tg720: improve reset handling and reduce link recovery time
      - support bcm54811 (and its MII-Lite interface type)
      - air_en8811h: support resume/suspend
      - support PHY counters for QCA807x and QCA808x
      - support WoL for QCA807x

   - CAN drivers:
      - rcar_canfd: support for Transceiver Delay Compensation
      - kvaser: report FW versions via devlink dev info

   - WiFi:
      - extended regulatory info support (6 GHz)
      - add statistics and beacon monitor for Multi-Link Operation (MLO)
      - support S1G aggregation, improve S1G support
      - add Radio Measurement action fields
      - support per-radio RTS threshold
      - some work around how FIPS affects wifi, which was wrong (RC4 is
        used by TKIP, not only WEP)
      - improvements for unsolicited probe response handling

   - WiFi drivers:
      - RealTek (rtw88):
         - IBSS mode for SDIO devices
      - RealTek (rtw89):
         - BT coexistence for MLO/WiFi7
         - concurrent station + P2P support
         - support for USB devices RTL8851BU/RTL8852BU
      - Intel (iwlwifi):
         - use embedded PNVM in (to be released) FW images to fix
           compatibility issues
         - many cleanups (unused FW APIs, PCIe code, WoWLAN)
         - some FIPS interoperability
      - MediaTek (mt76):
         - firmware recovery improvements
         - more MLO work
      - Qualcomm/Atheros (ath12k):
         - fix scan on multi-radio devices
         - more EHT/Wi-Fi 7 features
         - encapsulation/decapsulation offload
      - Broadcom (brcm80211):
         - support SDIO 43751 device

   - Bluetooth:
      - hci_event: add support for handling LE BIG Sync Lost event
      - ISO: add socket option to report packet seqnum via CMSG
      - ISO: support SCM_TIMESTAMPING for ISO TS

   - Bluetooth drivers:
      - intel_pcie: support Function Level Reset
      - nxpuart: add support for 4M baudrate
      - nxpuart: implement powerup sequence, reset, FW dump, and FW loading"

* tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1742 commits)
  dpll: zl3073x: Fix build failure
  selftests: bpf: fix legacy netfilter options
  ipv6: annotate data-races around rt->fib6_nsiblings
  ipv6: fix possible infinite loop in fib6_info_uses_dev()
  ipv6: prevent infinite loop in rt6_nlmsg_size()
  ipv6: add a retry logic in net6_rt_notify()
  vrf: Drop existing dst reference in vrf_ip6_input_dst
  net/sched: taprio: align entry index attr validation with mqprio
  net: fsl_pq_mdio: use dev_err_probe
  selftests: rtnetlink.sh: remove esp4_offload after test
  vsock: remove unnecessary null check in vsock_getname()
  igb: xsk: solve negative overflow of nb_pkts in zerocopy mode
  stmmac: xsk: fix negative overflow of budget in zerocopy mode
  dt-bindings: ieee802154: Convert at86rf230.txt yaml format
  net: dsa: microchip: Disable PTP function of KSZ8463
  net: dsa: microchip: Setup fiber ports for KSZ8463
  net: dsa: microchip: Write switch MAC address differently for KSZ8463
  net: dsa: microchip: Use different registers for KSZ8463
  net: dsa: microchip: Add KSZ8463 switch support to KSZ DSA driver
  dt-bindings: net: dsa: microchip: Add KSZ8463 switch support
  ...

include/uapi/asm-generic/socket.h

@@ -147,6 +147,9 @@
 
 #define SO_PASSRIGHTS		83
 
+#define SO_INQ			84
+#define SCM_INQ			SO_INQ
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

include/uapi/linux/devlink.h

@@ -221,6 +221,11 @@ enum devlink_port_flavour {
 				      */
 };
 
+/* IEEE 802.1Qaz standard supported values. */
+
+#define DEVLINK_RATE_TCS_MAX 8
+#define DEVLINK_RATE_TC_INDEX_MAX (DEVLINK_RATE_TCS_MAX - 1)
+
 enum devlink_rate_type {
 	DEVLINK_RATE_TYPE_LEAF,
 	DEVLINK_RATE_TYPE_NODE,
@@ -629,6 +634,8 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_REGION_DIRECT,		/* flag */
 
+	DEVLINK_ATTR_RATE_TC_BWS,		/* nested */
+
 	/* Add new attributes above here, update the spec in
 	 * Documentation/netlink/specs/devlink.yaml and re-generate
 	 * net/devlink/netlink_gen.c.
@@ -638,6 +645,15 @@ enum devlink_attr {
 	DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
 };
 
+enum devlink_rate_tc_attr {
+	DEVLINK_RATE_TC_ATTR_UNSPEC,
+	DEVLINK_RATE_TC_ATTR_INDEX,		/* u8 */
+	DEVLINK_RATE_TC_ATTR_BW,		/* u32 */
+
+	__DEVLINK_RATE_TC_ATTR_MAX,
+	DEVLINK_RATE_TC_ATTR_MAX = __DEVLINK_RATE_TC_ATTR_MAX - 1
+};
+
 /* Mapping between internal resource described by the field and system
  * structure
  */

include/uapi/linux/dpll.h

@@ -192,6 +192,17 @@ enum dpll_pin_capabilities {
 
 #define DPLL_PHASE_OFFSET_DIVIDER	1000
 
+/**
+ * enum dpll_feature_state - Allow control (enable/disable) and status checking
+ *   over features.
+ * @DPLL_FEATURE_STATE_DISABLE: feature shall be disabled
+ * @DPLL_FEATURE_STATE_ENABLE: feature shall be enabled
+ */
+enum dpll_feature_state {
+	DPLL_FEATURE_STATE_DISABLE,
+	DPLL_FEATURE_STATE_ENABLE,
+};
+
 enum dpll_a {
 	DPLL_A_ID = 1,
 	DPLL_A_MODULE_NAME,
@@ -204,6 +215,7 @@ enum dpll_a {
 	DPLL_A_TYPE,
 	DPLL_A_LOCK_STATUS_ERROR,
 	DPLL_A_CLOCK_QUALITY_LEVEL,
+	DPLL_A_PHASE_OFFSET_MONITOR,
 
 	__DPLL_A_MAX,
 	DPLL_A_MAX = (__DPLL_A_MAX - 1)
@@ -237,6 +249,7 @@ enum dpll_a_pin {
 	DPLL_A_PIN_ESYNC_FREQUENCY,
 	DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED,
 	DPLL_A_PIN_ESYNC_PULSE,
+	DPLL_A_PIN_REFERENCE_SYNC,
 
 	__DPLL_A_PIN_MAX,
 	DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1)

include/uapi/linux/ethtool.h

@@ -2314,7 +2314,7 @@ enum {
 	IPV6_USER_FLOW	= 0x0e, /* spec only (usr_ip6_spec; nfc only) */
 	IPV4_FLOW	= 0x10, /* hash only */
 	IPV6_FLOW	= 0x11, /* hash only */
-	ETHER_FLOW	= 0x12, /* spec only (ether_spec) */
+	ETHER_FLOW	= 0x12, /* hash or spec (ether_spec) */
 
 	/* Used for GTP-U IPv4 and IPv6.
 	 * The format of GTP packets only includes
@@ -2371,7 +2371,7 @@ enum {
 /* Flag to enable RSS spreading of traffic matching rule (nfc only) */
 #define	FLOW_RSS	0x20000000
 
-/* L3-L4 network traffic flow hash options */
+/* L2-L4 network traffic flow hash options */
 #define	RXH_L2DA	(1 << 1)
 #define	RXH_VLAN	(1 << 2)
 #define	RXH_L3_PROTO	(1 << 3)

include/uapi/linux/ethtool_netlink.h

@@ -208,6 +208,4 @@ enum {
 	ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1)
 };
 
-#define ETHTOOL_MCGRP_MONITOR_NAME "monitor"
-
 #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */

include/uapi/linux/ethtool_netlink_generated.h

@@ -49,6 +49,34 @@ enum hwtstamp_source {
 	HWTSTAMP_SOURCE_PHYLIB,
 };
 
+/**
+ * enum ethtool_pse_event - PSE event list for the PSE controller
+ * @ETHTOOL_PSE_EVENT_OVER_CURRENT: PSE output current is too high
+ * @ETHTOOL_PSE_EVENT_OVER_TEMP: PSE in over temperature state
+ * @ETHTOOL_C33_PSE_EVENT_DETECTION: detection process occur on the PSE. IEEE
+ *   802.3-2022 33.2.5 and 145.2.6 PSE detection of PDs. IEEE 802.3-202
+ *   30.9.1.1.5 aPSEPowerDetectionStatus
+ * @ETHTOOL_C33_PSE_EVENT_CLASSIFICATION: classification process occur on the
+ *   PSE. IEEE 802.3-2022 33.2.6 and 145.2.8 classification of PDs mutual
+ *   identification. IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification.
+ * @ETHTOOL_C33_PSE_EVENT_DISCONNECTION: PD has been disconnected on the PSE.
+ *   IEEE 802.3-2022 33.3.8 and 145.3.9 PD Maintain Power Signature. IEEE
+ *   802.3-2022 33.5.1.2.9 MPS Absent. IEEE 802.3-2022 30.9.1.1.20
+ *   aPSEMPSAbsentCounter.
+ * @ETHTOOL_PSE_EVENT_OVER_BUDGET: PSE turned off due to over budget situation
+ * @ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR: PSE faced an error managing the
+ *   power control from software
+ */
+enum ethtool_pse_event {
+	ETHTOOL_PSE_EVENT_OVER_CURRENT = 1,
+	ETHTOOL_PSE_EVENT_OVER_TEMP = 2,
+	ETHTOOL_C33_PSE_EVENT_DETECTION = 4,
+	ETHTOOL_C33_PSE_EVENT_CLASSIFICATION = 8,
+	ETHTOOL_C33_PSE_EVENT_DISCONNECTION = 16,
+	ETHTOOL_PSE_EVENT_OVER_BUDGET = 32,
+	ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR = 64,
+};
+
 enum {
 	ETHTOOL_A_HEADER_UNSPEC,
 	ETHTOOL_A_HEADER_DEV_INDEX,
@@ -642,11 +670,47 @@ enum {
 	ETHTOOL_A_C33_PSE_EXT_SUBSTATE,
 	ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT,
 	ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES,
+	ETHTOOL_A_PSE_PW_D_ID,
+	ETHTOOL_A_PSE_PRIO_MAX,
+	ETHTOOL_A_PSE_PRIO,
 
 	__ETHTOOL_A_PSE_CNT,
 	ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_FLOW_ETHER = 1,
+	ETHTOOL_A_FLOW_IP4,
+	ETHTOOL_A_FLOW_IP6,
+	ETHTOOL_A_FLOW_TCP4,
+	ETHTOOL_A_FLOW_TCP6,
+	ETHTOOL_A_FLOW_UDP4,
+	ETHTOOL_A_FLOW_UDP6,
+	ETHTOOL_A_FLOW_SCTP4,
+	ETHTOOL_A_FLOW_SCTP6,
+	ETHTOOL_A_FLOW_AH4,
+	ETHTOOL_A_FLOW_AH6,
+	ETHTOOL_A_FLOW_ESP4,
+	ETHTOOL_A_FLOW_ESP6,
+	ETHTOOL_A_FLOW_AH_ESP4,
+	ETHTOOL_A_FLOW_AH_ESP6,
+	ETHTOOL_A_FLOW_GTPU4,
+	ETHTOOL_A_FLOW_GTPU6,
+	ETHTOOL_A_FLOW_GTPC4,
+	ETHTOOL_A_FLOW_GTPC6,
+	ETHTOOL_A_FLOW_GTPC_TEID4,
+	ETHTOOL_A_FLOW_GTPC_TEID6,
+	ETHTOOL_A_FLOW_GTPU_EH4,
+	ETHTOOL_A_FLOW_GTPU_EH6,
+	ETHTOOL_A_FLOW_GTPU_UL4,
+	ETHTOOL_A_FLOW_GTPU_UL6,
+	ETHTOOL_A_FLOW_GTPU_DL4,
+	ETHTOOL_A_FLOW_GTPU_DL6,
+
+	__ETHTOOL_A_FLOW_CNT,
+	ETHTOOL_A_FLOW_MAX = (__ETHTOOL_A_FLOW_CNT - 1)
+};
+
 enum {
 	ETHTOOL_A_RSS_UNSPEC,
 	ETHTOOL_A_RSS_HEADER,
@@ -656,6 +720,7 @@ enum {
 	ETHTOOL_A_RSS_HKEY,
 	ETHTOOL_A_RSS_INPUT_XFRM,
 	ETHTOOL_A_RSS_START_CONTEXT,
+	ETHTOOL_A_RSS_FLOW_HASH,
 
 	__ETHTOOL_A_RSS_CNT,
 	ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1)
@@ -718,6 +783,14 @@ enum {
 	ETHTOOL_A_TSCONFIG_MAX = (__ETHTOOL_A_TSCONFIG_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PSE_NTF_HEADER = 1,
+	ETHTOOL_A_PSE_NTF_EVENTS,
+
+	__ETHTOOL_A_PSE_NTF_CNT,
+	ETHTOOL_A_PSE_NTF_MAX = (__ETHTOOL_A_PSE_NTF_CNT - 1)
+};
+
 enum {
 	ETHTOOL_MSG_USER_NONE = 0,
 	ETHTOOL_MSG_STRSET_GET = 1,
@@ -767,6 +840,9 @@ enum {
 	ETHTOOL_MSG_PHY_GET,
 	ETHTOOL_MSG_TSCONFIG_GET,
 	ETHTOOL_MSG_TSCONFIG_SET,
+	ETHTOOL_MSG_RSS_SET,
+	ETHTOOL_MSG_RSS_CREATE_ACT,
+	ETHTOOL_MSG_RSS_DELETE_ACT,
 
 	__ETHTOOL_MSG_USER_CNT,
 	ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1)
@@ -822,9 +898,16 @@ enum {
 	ETHTOOL_MSG_PHY_NTF,
 	ETHTOOL_MSG_TSCONFIG_GET_REPLY,
 	ETHTOOL_MSG_TSCONFIG_SET_REPLY,
+	ETHTOOL_MSG_PSE_NTF,
+	ETHTOOL_MSG_RSS_NTF,
+	ETHTOOL_MSG_RSS_CREATE_ACT_REPLY,
+	ETHTOOL_MSG_RSS_CREATE_NTF,
+	ETHTOOL_MSG_RSS_DELETE_NTF,
 
 	__ETHTOOL_MSG_KERNEL_CNT,
 	ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1)
 };
 
+#define ETHTOOL_MCGRP_MONITOR_NAME	"monitor"
+
 #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H */

include/uapi/linux/handshake.h

@@ -45,6 +45,7 @@ enum {
 	HANDSHAKE_A_ACCEPT_PEER_IDENTITY,
 	HANDSHAKE_A_ACCEPT_CERTIFICATE,
 	HANDSHAKE_A_ACCEPT_PEERNAME,
+	HANDSHAKE_A_ACCEPT_KEYRING,
 
 	__HANDSHAKE_A_ACCEPT_MAX,
 	HANDSHAKE_A_ACCEPT_MAX = (__HANDSHAKE_A_ACCEPT_MAX - 1)

include/uapi/linux/if_link.h

@@ -1398,6 +1398,7 @@ enum {
 	IFLA_VXLAN_LOCALBYPASS,
 	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	IFLA_VXLAN_RESERVED_BITS,
+	IFLA_VXLAN_MC_ROUTE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -1534,6 +1535,7 @@ enum {
 	IFLA_BOND_MISSED_MAX,
 	IFLA_BOND_NS_IP6_TARGET,
 	IFLA_BOND_COUPLED_CONTROL,
+	IFLA_BOND_BROADCAST_NEIGH,
 	__IFLA_BOND_MAX,
 };
 

include/uapi/linux/if_tun.h

@@ -93,6 +93,15 @@
 #define TUN_F_USO4	0x20	/* I can handle USO for IPv4 packets */
 #define TUN_F_USO6	0x40	/* I can handle USO for IPv6 packets */
 
+/* I can handle TSO/USO for UDP tunneled packets */
+#define TUN_F_UDP_TUNNEL_GSO		0x080
+
+/*
+ * I can handle TSO/USO for UDP tunneled packets requiring csum offload for
+ * the outer header
+ */
+#define TUN_F_UDP_TUNNEL_GSO_CSUM	0x100
+
 /* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
 #define TUN_PKT_STRIP	0x0001
 struct tun_pi {

include/uapi/linux/if_xdp.h

@@ -79,6 +79,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
 #define XDP_OPTIONS			8
+#define XDP_MAX_TX_SKB_BUDGET		9
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */

include/uapi/linux/in6.h

@@ -152,7 +152,6 @@ struct in6_flowlabel_req {
 /*
  *	IPV6 socket options
  */
-#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADDRFORM		1
 #define IPV6_2292PKTINFO	2
 #define IPV6_2292HOPOPTS	3
@@ -169,8 +168,10 @@ struct in6_flowlabel_req {
 #define IPV6_MULTICAST_IF	17
 #define IPV6_MULTICAST_HOPS	18
 #define IPV6_MULTICAST_LOOP	19
+#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADD_MEMBERSHIP	20
 #define IPV6_DROP_MEMBERSHIP	21
+#endif
 #define IPV6_ROUTER_ALERT	22
 #define IPV6_MTU_DISCOVER	23
 #define IPV6_MTU		24
@@ -203,7 +204,6 @@ struct in6_flowlabel_req {
 #define IPV6_IPSEC_POLICY	34
 #define IPV6_XFRM_POLICY	35
 #define IPV6_HDRINCL		36
-#endif
 
 /*
  * Multicast:

include/uapi/linux/ipv6.h

@@ -199,6 +199,7 @@ enum {
 	DEVCONF_NDISC_EVICT_NOCARRIER,
 	DEVCONF_ACCEPT_UNTRACKED_NA,
 	DEVCONF_ACCEPT_RA_MIN_LFT,
+	DEVCONF_FORCE_FORWARDING,
 	DEVCONF_MAX
 };
 

include/uapi/linux/mctp.h

@@ -37,6 +37,14 @@ struct sockaddr_mctp_ext {
 	__u8			smctp_haddr[MAX_ADDR_LEN];
 };
 
+/* A "fully qualified" MCTP address, which includes the system-local network ID,
+ * required to uniquely resolve a routable EID.
+ */
+struct mctp_fq_addr {
+	unsigned int	net;
+	mctp_eid_t	eid;
+};
+
 #define MCTP_NET_ANY		0x0
 
 #define MCTP_ADDR_NULL		0x00

include/uapi/linux/neighbour.h

@@ -54,6 +54,7 @@ enum {
 /* Extended flags under NDA_FLAGS_EXT: */
 #define NTF_EXT_MANAGED		(1 << 0)
 #define NTF_EXT_LOCKED		(1 << 1)
+#define NTF_EXT_EXT_VALIDATED	(1 << 2)
 
 /*
  *	Neighbor Cache Entry States.
@@ -92,6 +93,10 @@ enum {
  * bridge in response to a host trying to communicate via a locked bridge port
  * with MAB enabled. Their purpose is to notify user space that a host requires
  * authentication.
+ *
+ * NTF_EXT_EXT_VALIDATED flagged neighbor entries were externally validated by
+ * a user space control plane. The kernel will not remove or invalidate them,
+ * but it can probe them and notify user space when they become reachable.
  */
 
 struct nda_cacheinfo {

include/uapi/linux/net_dropmon.h

@@ -10,13 +10,6 @@ struct net_dm_drop_point {
 	__u32 count;
 };
 
-#define is_drop_point_hw(x) do {\
-	int ____i, ____j;\
-	for (____i = 0; ____i < 8; i ____i++)\
-		____j |= x[____i];\
-	____j;\
-} while (0)
-
 #define NET_DM_CFG_VERSION  0
 #define NET_DM_CFG_ALERT_COUNT  1
 #define NET_DM_CFG_ALERT_DELAY 2

include/uapi/linux/netconf.h

@@ -19,6 +19,7 @@ enum {
 	NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 	NETCONFA_INPUT,
 	NETCONFA_BC_FORWARDING,
+	NETCONFA_FORCE_FORWARDING,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)

include/uapi/linux/netdev.h

@@ -77,6 +77,11 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLED,
+	NETDEV_NAPI_THREADED_ENABLED,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
@@ -134,6 +139,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)

include/uapi/linux/netfilter/nfnetlink_hook.h

@@ -61,10 +61,12 @@ enum nfnl_hook_chain_desc_attributes {
  *
  * @NFNL_HOOK_TYPE_NFTABLES: nf_tables base chain
  * @NFNL_HOOK_TYPE_BPF: bpf program
+ * @NFNL_HOOK_TYPE_NFT_FLOWTABLE: nf_tables flowtable
  */
 enum nfnl_hook_chaintype {
 	NFNL_HOOK_TYPE_NFTABLES = 0x1,
 	NFNL_HOOK_TYPE_BPF,
+	NFNL_HOOK_TYPE_NFT_FLOWTABLE,
 };
 
 /**

include/uapi/linux/nl80211.h

@@ -1330,7 +1330,15 @@
  *      TID to Link mapping for downlink/uplink traffic.
  *
  * @NL80211_CMD_ASSOC_MLO_RECONF: For a non-AP MLD station, request to
- *      add/remove links to/from the association.
+ *      add/remove links to/from the association. To indicate link
+ *      reconfiguration request results from the driver, this command is also
+ *      used as an event to notify userspace about the added links information.
+ *      For notifying the removed links information, the existing
+ *      %NL80211_CMD_LINKS_REMOVED command is used. This command is also used to
+ *      notify userspace about newly added links for the current connection in
+ *      case of AP-initiated link recommendation requests, received via
+ *      a BTM (BSS Transition Management) request or a link reconfig notify
+ *      frame, where the driver handles the link recommendation offload.
  *
  * @NL80211_CMD_EPCS_CFG: EPCS configuration for a station. Used by userland to
  *	control EPCS configuration. Used to notify userland on the current state
@@ -2899,6 +2907,27 @@ enum nl80211_commands {
  *	APs Support". Drivers may set additional flags that they support
  *	in the kernel or device.
  *
+ * @NL80211_ATTR_WIPHY_RADIO_INDEX: (int) Integer attribute denoting the index
+ *	of the radio in interest. Internally a value of -1 is used to
+ *	indicate that the radio id is not given in user-space. This means
+ *	that all the attributes are applicable to all the radios. If there is
+ *	a radio index provided in user-space, the attributes will be
+ *	applicable to that specific radio only. If the radio id is greater
+ *	thank the number of radios, error denoting invalid value is returned.
+ *
+ * @NL80211_ATTR_S1G_LONG_BEACON_PERIOD: (u8) Integer attribute that represents
+ *	the number of beacon intervals between each long beacon transmission
+ *	for an S1G BSS with short beaconing enabled. This is a required
+ *	attribute for initialising an S1G short beaconing BSS. When updating
+ *	the short beacon data, this is not required. It has a minimum value of
+ *	2 (i.e 2 beacon intervals).
+ *
+ * @NL80211_ATTR_S1G_SHORT_BEACON: Nested attribute containing the short beacon
+ *	head and tail used to set or update the short beacon templates. When
+ *	bringing up a new interface, %NL80211_ATTR_S1G_LONG_BEACON_PERIOD is
+ *	required alongside this attribute. Refer to
+ *	@enum nl80211_s1g_short_beacon_attrs for the attribute definitions.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3456,6 +3485,11 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS,
 
+	NL80211_ATTR_WIPHY_RADIO_INDEX,
+
+	NL80211_ATTR_S1G_LONG_BEACON_PERIOD,
+	NL80211_ATTR_S1G_SHORT_BEACON,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -8088,6 +8122,7 @@ enum nl80211_ap_settings_flags {
  *	and contains attributes defined in &enum nl80211_if_combination_attrs.
  * @NL80211_WIPHY_RADIO_ATTR_ANTENNA_MASK: bitmask (u32) of antennas
  *	connected to this radio.
+ * @NL80211_WIPHY_RADIO_ATTR_RTS_THRESHOLD: RTS threshold (u32) of this radio.
  *
  * @__NL80211_WIPHY_RADIO_ATTR_LAST: Internal
  * @NL80211_WIPHY_RADIO_ATTR_MAX: Highest attribute
@@ -8099,6 +8134,7 @@ enum nl80211_wiphy_radio_attrs {
 	NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE,
 	NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION,
 	NL80211_WIPHY_RADIO_ATTR_ANTENNA_MASK,
+	NL80211_WIPHY_RADIO_ATTR_RTS_THRESHOLD,
 
 	/* keep last */
 	__NL80211_WIPHY_RADIO_ATTR_LAST,
@@ -8128,4 +8164,27 @@ enum nl80211_wiphy_radio_freq_range {
 	NL80211_WIPHY_RADIO_FREQ_ATTR_MAX = __NL80211_WIPHY_RADIO_FREQ_ATTR_LAST - 1,
 };
 
+/**
+ * enum nl80211_s1g_short_beacon_attrs - S1G short beacon data
+ *
+ * @__NL80211_S1G_SHORT_BEACON_ATTR_INVALID: Invalid
+ *
+ * @NL80211_S1G_SHORT_BEACON_ATTR_HEAD: Short beacon head (binary).
+ * @NL80211_S1G_SHORT_BEACON_ATTR_TAIL: Short beacon tail (binary).
+ *
+ * @__NL80211_S1G_SHORT_BEACON_ATTR_LAST: Internal
+ * @NL80211_S1G_SHORT_BEACON_ATTR_MAX: Highest attribute
+ */
+enum nl80211_s1g_short_beacon_attrs {
+	__NL80211_S1G_SHORT_BEACON_ATTR_INVALID,
+
+	NL80211_S1G_SHORT_BEACON_ATTR_HEAD,
+	NL80211_S1G_SHORT_BEACON_ATTR_TAIL,
+
+	/* keep last */
+	__NL80211_S1G_SHORT_BEACON_ATTR_LAST,
+	NL80211_S1G_SHORT_BEACON_ATTR_MAX =
+		__NL80211_S1G_SHORT_BEACON_ATTR_LAST - 1
+};
+
 #endif /* __LINUX_NL80211_H */

include/uapi/linux/openvswitch.h

@@ -186,6 +186,11 @@ enum ovs_packet_cmd {
  * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
  * size.
  * @OVS_PACKET_ATTR_HASH: Packet hash info (e.g. hash, sw_hash and l4_hash in skb).
+ * @OVS_PACKET_ATTR_UPCALL_PID: Netlink PID to use for upcalls while
+ * processing %OVS_PACKET_CMD_EXECUTE.  Takes precedence over all other ways
+ * to determine the Netlink PID including %OVS_USERSPACE_ATTR_PID,
+ * %OVS_DP_ATTR_UPCALL_PID, %OVS_DP_ATTR_PER_CPU_PIDS and the
+ * %OVS_VPORT_ATTR_UPCALL_PID.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_PACKET_* commands.
@@ -205,6 +210,7 @@ enum ovs_packet_attr {
 	OVS_PACKET_ATTR_MRU,	    /* Maximum received IP fragment size. */
 	OVS_PACKET_ATTR_LEN,	    /* Packet size before truncation. */
 	OVS_PACKET_ATTR_HASH,	    /* Packet hash. */
+	OVS_PACKET_ATTR_UPCALL_PID, /* u32 Netlink PID. */
 	__OVS_PACKET_ATTR_MAX
 };
 

include/uapi/linux/pkt_sched.h

@@ -1211,4 +1211,72 @@ enum {
 
 #define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
 
+/* DUALPI2 */
+enum tc_dualpi2_drop_overload {
+	TC_DUALPI2_DROP_OVERLOAD_OVERFLOW = 0,
+	TC_DUALPI2_DROP_OVERLOAD_DROP = 1,
+	__TCA_DUALPI2_DROP_OVERLOAD_MAX,
+};
+#define TCA_DUALPI2_DROP_OVERLOAD_MAX (__TCA_DUALPI2_DROP_OVERLOAD_MAX - 1)
+
+enum tc_dualpi2_drop_early {
+	TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE = 0,
+	TC_DUALPI2_DROP_EARLY_DROP_ENQUEUE = 1,
+	__TCA_DUALPI2_DROP_EARLY_MAX,
+};
+#define TCA_DUALPI2_DROP_EARLY_MAX (__TCA_DUALPI2_DROP_EARLY_MAX - 1)
+
+enum tc_dualpi2_ecn_mask {
+	TC_DUALPI2_ECN_MASK_L4S_ECT = 1,
+	TC_DUALPI2_ECN_MASK_CLA_ECT = 2,
+	TC_DUALPI2_ECN_MASK_ANY_ECT = 3,
+	__TCA_DUALPI2_ECN_MASK_MAX,
+};
+#define TCA_DUALPI2_ECN_MASK_MAX (__TCA_DUALPI2_ECN_MASK_MAX - 1)
+
+enum tc_dualpi2_split_gso {
+	TC_DUALPI2_SPLIT_GSO_NO_SPLIT_GSO = 0,
+	TC_DUALPI2_SPLIT_GSO_SPLIT_GSO = 1,
+	__TCA_DUALPI2_SPLIT_GSO_MAX,
+};
+#define TCA_DUALPI2_SPLIT_GSO_MAX (__TCA_DUALPI2_SPLIT_GSO_MAX - 1)
+
+enum {
+	TCA_DUALPI2_UNSPEC,
+	TCA_DUALPI2_LIMIT,		/* Packets */
+	TCA_DUALPI2_MEMORY_LIMIT,	/* Bytes */
+	TCA_DUALPI2_TARGET,		/* us */
+	TCA_DUALPI2_TUPDATE,		/* us */
+	TCA_DUALPI2_ALPHA,		/* Hz scaled up by 256 */
+	TCA_DUALPI2_BETA,		/* Hz scaled up by 256 */
+	TCA_DUALPI2_STEP_THRESH_PKTS,	/* Step threshold in packets */
+	TCA_DUALPI2_STEP_THRESH_US,	/* Step threshold in microseconds */
+	TCA_DUALPI2_MIN_QLEN_STEP,	/* Minimum qlen to apply STEP_THRESH */
+	TCA_DUALPI2_COUPLING,		/* Coupling factor between queues */
+	TCA_DUALPI2_DROP_OVERLOAD,	/* Whether to drop on overload */
+	TCA_DUALPI2_DROP_EARLY,		/* Whether to drop on enqueue */
+	TCA_DUALPI2_C_PROTECTION,	/* Percentage */
+	TCA_DUALPI2_ECN_MASK,		/* L4S queue classification mask */
+	TCA_DUALPI2_SPLIT_GSO,		/* Split GSO packets at enqueue */
+	TCA_DUALPI2_PAD,
+	__TCA_DUALPI2_MAX
+};
+
+#define TCA_DUALPI2_MAX   (__TCA_DUALPI2_MAX - 1)
+
+struct tc_dualpi2_xstats {
+	__u32 prob;		/* current probability */
+	__u32 delay_c;		/* current delay in C queue */
+	__u32 delay_l;		/* current delay in L queue */
+	__u32 packets_in_c;	/* number of packets enqueued in C queue */
+	__u32 packets_in_l;	/* number of packets enqueued in L queue */
+	__u32 maxq;		/* maximum queue size */
+	__u32 ecn_mark;		/* packets marked with ecn*/
+	__u32 step_marks;	/* ECN marks due to the step AQM */
+	__s32 credit;		/* current c_protection credit */
+	__u32 memory_used;	/* Memory used by both queues */
+	__u32 max_memory_used;	/* Maximum used memory */
+	__u32 memory_limit;	/* Memory limit of both queues */
+};
+
 #endif

include/uapi/linux/snmp.h

@@ -186,6 +186,7 @@ enum
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
+	LINUX_MIB_BEYOND_WINDOW,		/* BeyondWindow */
 	LINUX_MIB_TSECRREJECTED,		/* TSEcrRejected */
 	LINUX_MIB_PAWS_OLD_ACK,			/* PAWSOldAck */
 	LINUX_MIB_PAWS_TW_REJECTED,		/* PAWSTimewait */

include/uapi/linux/sysctl.h

@@ -573,6 +573,7 @@ enum {
 	NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
 	NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
 	NET_IPV6_RA_DEFRTR_METRIC=28,
+	NET_IPV6_FORCE_FORWARDING=29,
 	__NET_IPV6_MAX
 };
 

include/uapi/linux/vhost.h

@@ -235,4 +235,11 @@
  */
 #define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
 					      struct vhost_vring_state)
+
+/* Extended features manipulation */
+#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+
 #endif

include/uapi/linux/vhost_types.h

@@ -110,6 +110,11 @@ struct vhost_msg_v2 {
 	};
 };
 
+struct vhost_features_array {
+	__u64 count; /* number of entries present in features array */
+	__u64 features[] __counted_by(count);
+};
+
 struct vhost_memory_region {
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */

include/uapi/linux/virtio_net.h

@@ -70,6 +70,28 @@
 					 * with the same MAC.
 					 */
 #define VIRTIO_NET_F_SPEED_DUPLEX 63	/* Device set linkspeed and duplex */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO 65 /* Driver can receive
+					      * GSO-over-UDP-tunnel packets
+					      */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM 66 /* Driver handles
+						   * GSO-over-UDP-tunnel
+						   * packets with partial csum
+						   * for the outer header
+						   */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO 67 /* Device can receive
+					     * GSO-over-UDP-tunnel packets
+					     */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM 68 /* Device handles
+						  * GSO-over-UDP-tunnel
+						  * packets with partial csum
+						  * for the outer header
+						  */
+
+/* Offloads bits corresponding to VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO{,_CSUM}
+ * features
+ */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED	46
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED	47
 
 #ifndef VIRTIO_NET_NO_LEGACY
 #define VIRTIO_NET_F_GSO	6	/* Host handles pkts w/ any GSO type */
@@ -131,12 +153,17 @@ struct virtio_net_hdr_v1 {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	/* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
 #define VIRTIO_NET_HDR_F_RSC_INFO	4	/* rsc info in csum_ fields */
+#define VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM 8	/* UDP tunnel csum offload */
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	/* Not a GSO frame */
 #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
 #define VIRTIO_NET_HDR_GSO_UDP		3	/* GSO frame, IPv4 UDP (UFO) */
 #define VIRTIO_NET_HDR_GSO_TCPV6	4	/* GSO frame, IPv6 TCP */
 #define VIRTIO_NET_HDR_GSO_UDP_L4	5	/* GSO frame, IPv4& IPv6 UDP (USO) */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 0x20 /* UDPv4 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 0x40 /* UDPv6 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 | \
+				       VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6)
 #define VIRTIO_NET_HDR_GSO_ECN		0x80	/* TCP has ECN set */
 	__u8 gso_type;
 	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
@@ -181,6 +208,12 @@ struct virtio_net_hdr_v1_hash {
 	__le16 padding;
 };
 
+struct virtio_net_hdr_v1_hash_tunnel {
+	struct virtio_net_hdr_v1_hash hash_hdr;
+	__le16 outer_th_offset;
+	__le16 inner_nh_offset;
+};
+
 #ifndef VIRTIO_NET_NO_LEGACY
 /* This header comes first in the scatter-gather list.
  * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must