Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 524 insertions, 0 deletions

diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
new file mode 100644
index 000000000..012fc27c5
--- /dev/null
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
@@ -0,0 +1,524 @@
+#ifndef _OPA_VNIC_ENCAP_H
+#define _OPA_VNIC_ENCAP_H
+/*
+ * Copyright(c) 2017 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * BSD LICENSE
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * This file contains all OPA VNIC declaration required for encapsulation
+ * and decapsulation of Ethernet packets
+ */
+
+#include <linux/types.h>
+#include <rdma/ib_mad.h>
+
+/* EMA class version */
+#define OPA_EMA_CLASS_VERSION               0x80
+
+/*
+ * Define the Intel vendor management class for OPA
+ * ETHERNET MANAGEMENT
+ */
+#define OPA_MGMT_CLASS_INTEL_EMA            0x34
+
+/* EM attribute IDs */
+#define OPA_EM_ATTR_CLASS_PORT_INFO                 0x0001
+#define OPA_EM_ATTR_VESWPORT_INFO                   0x0011
+#define OPA_EM_ATTR_VESWPORT_MAC_ENTRIES            0x0012
+#define OPA_EM_ATTR_IFACE_UCAST_MACS                0x0013
+#define OPA_EM_ATTR_IFACE_MCAST_MACS                0x0014
+#define OPA_EM_ATTR_DELETE_VESW                     0x0015
+#define OPA_EM_ATTR_VESWPORT_SUMMARY_COUNTERS       0x0020
+#define OPA_EM_ATTR_VESWPORT_ERROR_COUNTERS         0x0022
+
+/* VNIC configured and operational state values */
+#define OPA_VNIC_STATE_DROP_ALL        0x1
+#define OPA_VNIC_STATE_FORWARDING      0x3
+
+#define OPA_VESW_MAX_NUM_DEF_PORT   16
+#define OPA_VNIC_MAX_NUM_PCP        8
+
+#define OPA_VNIC_EMA_DATA    (OPA_MGMT_MAD_SIZE - IB_MGMT_VENDOR_HDR)
+
+/* Defines for vendor specific notice(trap) attributes */
+#define OPA_INTEL_EMA_NOTICE_TYPE_INFO 0x04
+
+/* INTEL OUI */
+#define INTEL_OUI_1 0x00
+#define INTEL_OUI_2 0x06
+#define INTEL_OUI_3 0x6a
+
+/* Trap opcodes sent from VNIC */
+#define OPA_VESWPORT_TRAP_IFACE_UCAST_MAC_CHANGE 0x1
+#define OPA_VESWPORT_TRAP_IFACE_MCAST_MAC_CHANGE 0x2
+#define OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE 0x3
+
+#define OPA_VNIC_DLID_SD_IS_SRC_MAC(dlid_sd)  (!!((dlid_sd) & 0x20))
+#define OPA_VNIC_DLID_SD_GET_DLID(dlid_sd)    ((dlid_sd) >> 8)
+
+/* VNIC Ethernet link status */
+#define OPA_VNIC_ETH_LINK_UP     1
+#define OPA_VNIC_ETH_LINK_DOWN   2
+
+/* routing control */
+#define OPA_VNIC_ENCAP_RC_DEFAULT   0
+#define OPA_VNIC_ENCAP_RC_IPV4      4
+#define OPA_VNIC_ENCAP_RC_IPV4_UDP  8
+#define OPA_VNIC_ENCAP_RC_IPV4_TCP  12
+#define OPA_VNIC_ENCAP_RC_IPV6      16
+#define OPA_VNIC_ENCAP_RC_IPV6_TCP  20
+#define OPA_VNIC_ENCAP_RC_IPV6_UDP  24
+
+#define OPA_VNIC_ENCAP_RC_EXT(w, b) (((w) >> OPA_VNIC_ENCAP_RC_ ## b) & 0x7)
+
+/**
+ * struct opa_vesw_info - OPA vnic switch information
+ * @fabric_id: 10-bit fabric id
+ * @vesw_id: 12-bit virtual ethernet switch id
+ * @rsvd0: reserved bytes
+ * @def_port_mask: bitmask of default ports
+ * @rsvd1: reserved bytes
+ * @pkey: partition key
+ * @rsvd2: reserved bytes
+ * @u_mcast_dlid: unknown multicast dlid
+ * @u_ucast_dlid: array of unknown unicast dlids
+ * @rsvd3: reserved bytes
+ * @rc: routing control
+ * @eth_mtu: Ethernet MTU
+ * @rsvd4: reserved bytes
+ */
+struct opa_vesw_info {
+	__be16  fabric_id;
+	__be16  vesw_id;
+
+	u8      rsvd0[6];
+	__be16  def_port_mask;
+
+	u8      rsvd1[2];
+	__be16  pkey;
+
+	u8      rsvd2[4];
+	__be32  u_mcast_dlid;
+	__be32  u_ucast_dlid[OPA_VESW_MAX_NUM_DEF_PORT];
+
+	__be32  rc;
+
+	u8      rsvd3[56];
+	__be16  eth_mtu;
+	u8      rsvd4[2];
+} __packed;
+
+/**
+ * struct opa_per_veswport_info - OPA vnic per port information
+ * @port_num: port number
+ * @eth_link_status: current ethernet link state
+ * @rsvd0: reserved bytes
+ * @base_mac_addr: base mac address
+ * @config_state: configured port state
+ * @oper_state: operational port state
+ * @max_mac_tbl_ent: max number of mac table entries
+ * @max_smac_ent: max smac entries in mac table
+ * @mac_tbl_digest: mac table digest
+ * @rsvd1: reserved bytes
+ * @encap_slid: base slid for the port
+ * @pcp_to_sc_uc: sc by pcp index for unicast ethernet packets
+ * @pcp_to_vl_uc: vl by pcp index for unicast ethernet packets
+ * @pcp_to_sc_mc: sc by pcp index for multicast ethernet packets
+ * @pcp_to_vl_mc: vl by pcp index for multicast ethernet packets
+ * @non_vlan_sc_uc: sc for non-vlan unicast ethernet packets
+ * @non_vlan_vl_uc: vl for non-vlan unicast ethernet packets
+ * @non_vlan_sc_mc: sc for non-vlan multicast ethernet packets
+ * @non_vlan_vl_mc: vl for non-vlan multicast ethernet packets
+ * @rsvd2: reserved bytes
+ * @uc_macs_gen_count: generation count for unicast macs list
+ * @mc_macs_gen_count: generation count for multicast macs list
+ * @rsvd3: reserved bytes
+ */
+struct opa_per_veswport_info {
+	__be32  port_num;
+
+	u8      eth_link_status;
+	u8      rsvd0[3];
+
+	u8      base_mac_addr[ETH_ALEN];
+	u8      config_state;
+	u8      oper_state;
+
+	__be16  max_mac_tbl_ent;
+	__be16  max_smac_ent;
+	__be32  mac_tbl_digest;
+	u8      rsvd1[4];
+
+	__be32  encap_slid;
+
+	u8      pcp_to_sc_uc[OPA_VNIC_MAX_NUM_PCP];
+	u8      pcp_to_vl_uc[OPA_VNIC_MAX_NUM_PCP];
+	u8      pcp_to_sc_mc[OPA_VNIC_MAX_NUM_PCP];
+	u8      pcp_to_vl_mc[OPA_VNIC_MAX_NUM_PCP];
+
+	u8      non_vlan_sc_uc;
+	u8      non_vlan_vl_uc;
+	u8      non_vlan_sc_mc;
+	u8      non_vlan_vl_mc;
+
+	u8      rsvd2[48];
+
+	__be16  uc_macs_gen_count;
+	__be16  mc_macs_gen_count;
+
+	u8      rsvd3[8];
+} __packed;
+
+/**
+ * struct opa_veswport_info - OPA vnic port information
+ * @vesw: OPA vnic switch information
+ * @vport: OPA vnic per port information
+ *
+ * On host, each of the virtual ethernet ports belongs
+ * to a different virtual ethernet switches.
+ */
+struct opa_veswport_info {
+	struct opa_vesw_info          vesw;
+	struct opa_per_veswport_info  vport;
+};
+
+/**
+ * struct opa_veswport_mactable_entry - single entry in the forwarding table
+ * @mac_addr: MAC address
+ * @mac_addr_mask: MAC address bit mask
+ * @dlid_sd: Matching DLID and side data
+ *
+ * On the host each virtual ethernet port will have
+ * a forwarding table. These tables are used to
+ * map a MAC to a LID and other data. For more
+ * details see struct opa_veswport_mactable_entries.
+ * This is the structure of a single mactable entry
+ */
+struct opa_veswport_mactable_entry {
+	u8      mac_addr[ETH_ALEN];
+	u8      mac_addr_mask[ETH_ALEN];
+	__be32  dlid_sd;
+} __packed;
+
+/**
+ * struct opa_veswport_mactable - Forwarding table array
+ * @offset: mac table starting offset
+ * @num_entries: Number of entries to get or set
+ * @mac_tbl_digest: mac table digest
+ * @tbl_entries: Array of table entries
+ *
+ * The EM sends down this structure in a MAD indicating
+ * the starting offset in the forwarding table that this
+ * entry is to be loaded into and the number of entries
+ * that that this MAD instance contains
+ * The mac_tbl_digest has been added to this MAD structure. It will be set by
+ * the EM and it will be used by the EM to check if there are any
+ * discrepancies with this value and the value
+ * maintained by the EM in the case of VNIC port being deleted or unloaded
+ * A new instantiation of a VNIC will always have a value of zero.
+ * This value is stored as part of the vnic adapter structure and will be
+ * accessed by the GET and SET routines for both the mactable entries and the
+ * veswport info.
+ */
+struct opa_veswport_mactable {
+	__be16                              offset;
+	__be16                              num_entries;
+	__be32                              mac_tbl_digest;
+	struct opa_veswport_mactable_entry  tbl_entries[];
+} __packed;
+
+/**
+ * struct opa_veswport_summary_counters - summary counters
+ * @vp_instance: vport instance on the OPA port
+ * @vesw_id: virtual ethernet switch id
+ * @veswport_num: virtual ethernet switch port number
+ * @tx_errors: transmit errors
+ * @rx_errors: receive errors
+ * @tx_packets: transmit packets
+ * @rx_packets: receive packets
+ * @tx_bytes: transmit bytes
+ * @rx_bytes: receive bytes
+ * @tx_unicast: unicast packets transmitted
+ * @tx_mcastbcast: multicast/broadcast packets transmitted
+ * @tx_untagged: non-vlan packets transmitted
+ * @tx_vlan: vlan packets transmitted
+ * @tx_64_size: transmit packet length is 64 bytes
+ * @tx_65_127: transmit packet length is >=65 and < 127 bytes
+ * @tx_128_255: transmit packet length is >=128 and < 255 bytes
+ * @tx_256_511: transmit packet length is >=256 and < 511 bytes
+ * @tx_512_1023: transmit packet length is >=512 and < 1023 bytes
+ * @tx_1024_1518: transmit packet length is >=1024 and < 1518 bytes
+ * @tx_1519_max: transmit packet length >= 1519 bytes
+ * @rx_unicast: unicast packets received
+ * @rx_mcastbcast: multicast/broadcast packets received
+ * @rx_untagged: non-vlan packets received
+ * @rx_vlan: vlan packets received
+ * @rx_64_size: received packet length is 64 bytes
+ * @rx_65_127: received packet length is >=65 and < 127 bytes
+ * @rx_128_255: received packet length is >=128 and < 255 bytes
+ * @rx_256_511: received packet length is >=256 and < 511 bytes
+ * @rx_512_1023: received packet length is >=512 and < 1023 bytes
+ * @rx_1024_1518: received packet length is >=1024 and < 1518 bytes
+ * @rx_1519_max: received packet length >= 1519 bytes
+ * @reserved: reserved bytes
+ *
+ * All the above are counters of corresponding conditions.
+ */
+struct opa_veswport_summary_counters {
+	__be16  vp_instance;
+	__be16  vesw_id;
+	__be32  veswport_num;
+
+	__be64  tx_errors;
+	__be64  rx_errors;
+	__be64  tx_packets;
+	__be64  rx_packets;
+	__be64  tx_bytes;
+	__be64  rx_bytes;
+
+	__be64  tx_unicast;
+	__be64  tx_mcastbcast;
+
+	__be64  tx_untagged;
+	__be64  tx_vlan;
+
+	__be64  tx_64_size;
+	__be64  tx_65_127;
+	__be64  tx_128_255;
+	__be64  tx_256_511;
+	__be64  tx_512_1023;
+	__be64  tx_1024_1518;
+	__be64  tx_1519_max;
+
+	__be64  rx_unicast;
+	__be64  rx_mcastbcast;
+
+	__be64  rx_untagged;
+	__be64  rx_vlan;
+
+	__be64  rx_64_size;
+	__be64  rx_65_127;
+	__be64  rx_128_255;
+	__be64  rx_256_511;
+	__be64  rx_512_1023;
+	__be64  rx_1024_1518;
+	__be64  rx_1519_max;
+
+	__be64  reserved[16];
+} __packed;
+
+/**
+ * struct opa_veswport_error_counters - error counters
+ * @vp_instance: vport instance on the OPA port
+ * @vesw_id: virtual ethernet switch id
+ * @veswport_num: virtual ethernet switch port number
+ * @tx_errors: transmit errors
+ * @rx_errors: receive errors
+ * @rsvd0: reserved bytes
+ * @tx_smac_filt: smac filter errors
+ * @rsvd1: reserved bytes
+ * @rsvd2: reserved bytes
+ * @rsvd3: reserved bytes
+ * @tx_dlid_zero: transmit packets with invalid dlid
+ * @rsvd4: reserved bytes
+ * @tx_logic: other transmit errors
+ * @rsvd5: reserved bytes
+ * @tx_drop_state: packet tansmission in non-forward port state
+ * @rx_bad_veswid: received packet with invalid vesw id
+ * @rsvd6: reserved bytes
+ * @rx_runt: received ethernet packet with length < 64 bytes
+ * @rx_oversize: received ethernet packet with length > MTU size
+ * @rsvd7: reserved bytes
+ * @rx_eth_down: received packets when interface is down
+ * @rx_drop_state: received packets in non-forwarding port state
+ * @rx_logic: other receive errors
+ * @rsvd8: reserved bytes
+ * @rsvd9: reserved bytes
+ *
+ * All the above are counters of corresponding error conditions.
+ */
+struct opa_veswport_error_counters {
+	__be16  vp_instance;
+	__be16  vesw_id;
+	__be32  veswport_num;
+
+	__be64  tx_errors;
+	__be64  rx_errors;
+
+	__be64  rsvd0;
+	__be64  tx_smac_filt;
+	__be64  rsvd1;
+	__be64  rsvd2;
+	__be64  rsvd3;
+	__be64  tx_dlid_zero;
+	__be64  rsvd4;
+	__be64  tx_logic;
+	__be64  rsvd5;
+	__be64  tx_drop_state;
+
+	__be64  rx_bad_veswid;
+	__be64  rsvd6;
+	__be64  rx_runt;
+	__be64  rx_oversize;
+	__be64  rsvd7;
+	__be64  rx_eth_down;
+	__be64  rx_drop_state;
+	__be64  rx_logic;
+	__be64  rsvd8;
+
+	__be64  rsvd9[16];
+} __packed;
+
+/**
+ * struct opa_veswport_trap - Trap message sent to EM by VNIC
+ * @fabric_id: 10 bit fabric id
+ * @veswid: 12 bit virtual ethernet switch id
+ * @veswportnum: logical port number on the Virtual switch
+ * @opaportnum: physical port num (redundant on host)
+ * @veswportindex: switch port index on opa port 0 based
+ * @opcode: operation
+ * @reserved: 32 bit for alignment
+ *
+ * The VNIC will send trap messages to the Ethernet manager to
+ * inform it about changes to the VNIC config, behaviour etc.
+ * This is the format of the trap payload.
+ */
+struct opa_veswport_trap {
+	__be16  fabric_id;
+	__be16  veswid;
+	__be32  veswportnum;
+	__be16  opaportnum;
+	u8      veswportindex;
+	u8      opcode;
+	__be32  reserved;
+} __packed;
+
+/**
+ * struct opa_vnic_iface_mac_entry - single entry in the mac list
+ * @mac_addr: MAC address
+ */
+struct opa_vnic_iface_mac_entry {
+	u8 mac_addr[ETH_ALEN];
+};
+
+/**
+ * struct opa_veswport_iface_macs - Msg to set globally administered MAC
+ * @start_idx: position of first entry (0 based)
+ * @num_macs_in_msg: number of MACs in this message
+ * @tot_macs_in_lst: The total number of MACs the agent has
+ * @gen_count: gen_count to indicate change
+ * @entry: The mac list entry
+ *
+ * Same attribute IDS and attribute modifiers as in locally administered
+ * addresses used to set globally administered addresses
+ */
+struct opa_veswport_iface_macs {
+	__be16 start_idx;
+	__be16 num_macs_in_msg;
+	__be16 tot_macs_in_lst;
+	__be16 gen_count;
+	struct opa_vnic_iface_mac_entry entry[];
+} __packed;
+
+/**
+ * struct opa_vnic_vema_mad - Generic VEMA MAD
+ * @mad_hdr: Generic MAD header
+ * @rmpp_hdr: RMPP header for vendor specific MADs
+ * @reserved: reserved bytes
+ * @oui: Unique org identifier
+ * @data: MAD data
+ */
+struct opa_vnic_vema_mad {
+	struct ib_mad_hdr  mad_hdr;
+	struct ib_rmpp_hdr rmpp_hdr;
+	u8                 reserved;
+	u8                 oui[3];
+	u8                 data[OPA_VNIC_EMA_DATA];
+};
+
+/**
+ * struct opa_vnic_notice_attr - Generic Notice MAD
+ * @gen_type: Generic/Specific bit and type of notice
+ * @oui_1: Vendor ID byte 1
+ * @oui_2: Vendor ID byte 2
+ * @oui_3: Vendor ID byte 3
+ * @trap_num: Trap number
+ * @toggle_count: Notice toggle bit and count value
+ * @issuer_lid: Trap issuer's lid
+ * @reserved: reserved bytes
+ * @issuer_gid: Issuer GID (only if Report method)
+ * @raw_data: Trap message body
+ */
+struct opa_vnic_notice_attr {
+	u8     gen_type;
+	u8     oui_1;
+	u8     oui_2;
+	u8     oui_3;
+	__be16 trap_num;
+	__be16 toggle_count;
+	__be32 issuer_lid;
+	__be32 reserved;
+	u8     issuer_gid[16];
+	u8     raw_data[64];
+} __packed;
+
+/**
+ * struct opa_vnic_vema_mad_trap - Generic VEMA MAD Trap
+ * @mad_hdr: Generic MAD header
+ * @rmpp_hdr: RMPP header for vendor specific MADs
+ * @reserved: reserved bytes
+ * @oui: Unique org identifier
+ * @notice: Notice structure
+ */
+struct opa_vnic_vema_mad_trap {
+	struct ib_mad_hdr            mad_hdr;
+	struct ib_rmpp_hdr           rmpp_hdr;
+	u8                           reserved;
+	u8                           oui[3];
+	struct opa_vnic_notice_attr  notice;
+};
+
+#endif /* _OPA_VNIC_ENCAP_H */