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, 513 insertions, 0 deletions

diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
new file mode 100644
index 000000000..31cd36141
--- /dev/null
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
@@ -0,0 +1,513 @@
+/*
+ * 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 OPA VNIC encapsulation/decapsulation function.
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+
+#include "opa_vnic_internal.h"
+
+/* OPA 16B Header fields */
+#define OPA_16B_LID_MASK        0xFFFFFull
+#define OPA_16B_SLID_HIGH_SHFT  8
+#define OPA_16B_SLID_MASK       0xF00ull
+#define OPA_16B_DLID_MASK       0xF000ull
+#define OPA_16B_DLID_HIGH_SHFT  12
+#define OPA_16B_LEN_SHFT        20
+#define OPA_16B_SC_SHFT         20
+#define OPA_16B_RC_SHFT         25
+#define OPA_16B_PKEY_SHFT       16
+
+#define OPA_VNIC_L4_HDR_SHFT    16
+
+/* L2+L4 hdr len is 20 bytes (5 quad words) */
+#define OPA_VNIC_HDR_QW_LEN   5
+
+static inline void opa_vnic_make_header(u8 *hdr, u32 slid, u32 dlid, u16 len,
+					u16 pkey, u16 entropy, u8 sc, u8 rc,
+					u8 l4_type, u16 l4_hdr)
+{
+	/* h[1]: LT=1, 16B L2=10 */
+	u32 h[OPA_VNIC_HDR_QW_LEN] = {0, 0xc0000000, 0, 0, 0};
+
+	h[2] = l4_type;
+	h[3] = entropy;
+	h[4] = l4_hdr << OPA_VNIC_L4_HDR_SHFT;
+
+	/* Extract and set 4 upper bits and 20 lower bits of the lids */
+	h[0] |= (slid & OPA_16B_LID_MASK);
+	h[2] |= ((slid >> (20 - OPA_16B_SLID_HIGH_SHFT)) & OPA_16B_SLID_MASK);
+
+	h[1] |= (dlid & OPA_16B_LID_MASK);
+	h[2] |= ((dlid >> (20 - OPA_16B_DLID_HIGH_SHFT)) & OPA_16B_DLID_MASK);
+
+	h[0] |= (len << OPA_16B_LEN_SHFT);
+	h[1] |= (rc << OPA_16B_RC_SHFT);
+	h[1] |= (sc << OPA_16B_SC_SHFT);
+	h[2] |= ((u32)pkey << OPA_16B_PKEY_SHFT);
+
+	memcpy(hdr, h, OPA_VNIC_HDR_LEN);
+}
+
+/*
+ * Using a simple hash table for mac table implementation with the last octet
+ * of mac address as a key.
+ */
+static void opa_vnic_free_mac_tbl(struct hlist_head *mactbl)
+{
+	struct opa_vnic_mac_tbl_node *node;
+	struct hlist_node *tmp;
+	int bkt;
+
+	if (!mactbl)
+		return;
+
+	vnic_hash_for_each_safe(mactbl, bkt, tmp, node, hlist) {
+		hash_del(&node->hlist);
+		kfree(node);
+	}
+	kfree(mactbl);
+}
+
+static struct hlist_head *opa_vnic_alloc_mac_tbl(void)
+{
+	u32 size = sizeof(struct hlist_head) * OPA_VNIC_MAC_TBL_SIZE;
+	struct hlist_head *mactbl;
+
+	mactbl = kzalloc(size, GFP_KERNEL);
+	if (!mactbl)
+		return ERR_PTR(-ENOMEM);
+
+	vnic_hash_init(mactbl);
+	return mactbl;
+}
+
+/* opa_vnic_release_mac_tbl - empty and free the mac table */
+void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter)
+{
+	struct hlist_head *mactbl;
+
+	mutex_lock(&adapter->mactbl_lock);
+	mactbl = rcu_access_pointer(adapter->mactbl);
+	rcu_assign_pointer(adapter->mactbl, NULL);
+	synchronize_rcu();
+	opa_vnic_free_mac_tbl(mactbl);
+	adapter->info.vport.mac_tbl_digest = 0;
+	mutex_unlock(&adapter->mactbl_lock);
+}
+
+/*
+ * opa_vnic_query_mac_tbl - query the mac table for a section
+ *
+ * This function implements query of specific function of the mac table.
+ * The function also expects the requested range to be valid.
+ */
+void opa_vnic_query_mac_tbl(struct opa_vnic_adapter *adapter,
+			    struct opa_veswport_mactable *tbl)
+{
+	struct opa_vnic_mac_tbl_node *node;
+	struct hlist_head *mactbl;
+	int bkt;
+	u16 loffset, lnum_entries;
+
+	rcu_read_lock();
+	mactbl = rcu_dereference(adapter->mactbl);
+	if (!mactbl)
+		goto get_mac_done;
+
+	loffset = be16_to_cpu(tbl->offset);
+	lnum_entries = be16_to_cpu(tbl->num_entries);
+
+	vnic_hash_for_each(mactbl, bkt, node, hlist) {
+		struct __opa_vnic_mactable_entry *nentry = &node->entry;
+		struct opa_veswport_mactable_entry *entry;
+
+		if ((node->index < loffset) ||
+		    (node->index >= (loffset + lnum_entries)))
+			continue;
+
+		/* populate entry in the tbl corresponding to the index */
+		entry = &tbl->tbl_entries[node->index - loffset];
+		memcpy(entry->mac_addr, nentry->mac_addr,
+		       ARRAY_SIZE(entry->mac_addr));
+		memcpy(entry->mac_addr_mask, nentry->mac_addr_mask,
+		       ARRAY_SIZE(entry->mac_addr_mask));
+		entry->dlid_sd = cpu_to_be32(nentry->dlid_sd);
+	}
+	tbl->mac_tbl_digest = cpu_to_be32(adapter->info.vport.mac_tbl_digest);
+get_mac_done:
+	rcu_read_unlock();
+}
+
+/*
+ * opa_vnic_update_mac_tbl - update mac table section
+ *
+ * This function updates the specified section of the mac table.
+ * The procedure includes following steps.
+ *  - Allocate a new mac (hash) table.
+ *  - Add the specified entries to the new table.
+ *    (except the ones that are requested to be deleted).
+ *  - Add all the other entries from the old mac table.
+ *  - If there is a failure, free the new table and return.
+ *  - Switch to the new table.
+ *  - Free the old table and return.
+ *
+ * The function also expects the requested range to be valid.
+ */
+int opa_vnic_update_mac_tbl(struct opa_vnic_adapter *adapter,
+			    struct opa_veswport_mactable *tbl)
+{
+	struct opa_vnic_mac_tbl_node *node, *new_node;
+	struct hlist_head *new_mactbl, *old_mactbl;
+	int i, bkt, rc = 0;
+	u8 key;
+	u16 loffset, lnum_entries;
+
+	mutex_lock(&adapter->mactbl_lock);
+	/* allocate new mac table */
+	new_mactbl = opa_vnic_alloc_mac_tbl();
+	if (IS_ERR(new_mactbl)) {
+		mutex_unlock(&adapter->mactbl_lock);
+		return PTR_ERR(new_mactbl);
+	}
+
+	loffset = be16_to_cpu(tbl->offset);
+	lnum_entries = be16_to_cpu(tbl->num_entries);
+
+	/* add updated entries to the new mac table */
+	for (i = 0; i < lnum_entries; i++) {
+		struct __opa_vnic_mactable_entry *nentry;
+		struct opa_veswport_mactable_entry *entry =
+							&tbl->tbl_entries[i];
+		u8 *mac_addr = entry->mac_addr;
+		u8 empty_mac[ETH_ALEN] = { 0 };
+
+		v_dbg("new mac entry %4d: %02x:%02x:%02x:%02x:%02x:%02x %x\n",
+		      loffset + i, mac_addr[0], mac_addr[1], mac_addr[2],
+		      mac_addr[3], mac_addr[4], mac_addr[5],
+		      entry->dlid_sd);
+
+		/* if the entry is being removed, do not add it */
+		if (!memcmp(mac_addr, empty_mac, ARRAY_SIZE(empty_mac)))
+			continue;
+
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node) {
+			rc = -ENOMEM;
+			goto updt_done;
+		}
+
+		node->index = loffset + i;
+		nentry = &node->entry;
+		memcpy(nentry->mac_addr, entry->mac_addr,
+		       ARRAY_SIZE(nentry->mac_addr));
+		memcpy(nentry->mac_addr_mask, entry->mac_addr_mask,
+		       ARRAY_SIZE(nentry->mac_addr_mask));
+		nentry->dlid_sd = be32_to_cpu(entry->dlid_sd);
+		key = node->entry.mac_addr[OPA_VNIC_MAC_HASH_IDX];
+		vnic_hash_add(new_mactbl, &node->hlist, key);
+	}
+
+	/* add other entries from current mac table to new mac table */
+	old_mactbl = rcu_access_pointer(adapter->mactbl);
+	if (!old_mactbl)
+		goto switch_tbl;
+
+	vnic_hash_for_each(old_mactbl, bkt, node, hlist) {
+		if ((node->index >= loffset) &&
+		    (node->index < (loffset + lnum_entries)))
+			continue;
+
+		new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
+		if (!new_node) {
+			rc = -ENOMEM;
+			goto updt_done;
+		}
+
+		new_node->index = node->index;
+		memcpy(&new_node->entry, &node->entry, sizeof(node->entry));
+		key = new_node->entry.mac_addr[OPA_VNIC_MAC_HASH_IDX];
+		vnic_hash_add(new_mactbl, &new_node->hlist, key);
+	}
+
+switch_tbl:
+	/* switch to new table */
+	rcu_assign_pointer(adapter->mactbl, new_mactbl);
+	synchronize_rcu();
+
+	adapter->info.vport.mac_tbl_digest = be32_to_cpu(tbl->mac_tbl_digest);
+updt_done:
+	/* upon failure, free the new table; otherwise, free the old table */
+	if (rc)
+		opa_vnic_free_mac_tbl(new_mactbl);
+	else
+		opa_vnic_free_mac_tbl(old_mactbl);
+
+	mutex_unlock(&adapter->mactbl_lock);
+	return rc;
+}
+
+/* opa_vnic_chk_mac_tbl - check mac table for dlid */
+static uint32_t opa_vnic_chk_mac_tbl(struct opa_vnic_adapter *adapter,
+				     struct ethhdr *mac_hdr)
+{
+	struct opa_vnic_mac_tbl_node *node;
+	struct hlist_head *mactbl;
+	u32 dlid = 0;
+	u8 key;
+
+	rcu_read_lock();
+	mactbl = rcu_dereference(adapter->mactbl);
+	if (unlikely(!mactbl))
+		goto chk_done;
+
+	key = mac_hdr->h_dest[OPA_VNIC_MAC_HASH_IDX];
+	vnic_hash_for_each_possible(mactbl, node, hlist, key) {
+		struct __opa_vnic_mactable_entry *entry = &node->entry;
+
+		/* if related to source mac, skip */
+		if (unlikely(OPA_VNIC_DLID_SD_IS_SRC_MAC(entry->dlid_sd)))
+			continue;
+
+		if (!memcmp(node->entry.mac_addr, mac_hdr->h_dest,
+			    ARRAY_SIZE(node->entry.mac_addr))) {
+			/* mac address found */
+			dlid = OPA_VNIC_DLID_SD_GET_DLID(node->entry.dlid_sd);
+			break;
+		}
+	}
+
+chk_done:
+	rcu_read_unlock();
+	return dlid;
+}
+
+/* opa_vnic_get_dlid - find and return the DLID */
+static uint32_t opa_vnic_get_dlid(struct opa_vnic_adapter *adapter,
+				  struct sk_buff *skb, u8 def_port)
+{
+	struct __opa_veswport_info *info = &adapter->info;
+	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+	u32 dlid;
+
+	dlid = opa_vnic_chk_mac_tbl(adapter, mac_hdr);
+	if (dlid)
+		return dlid;
+
+	if (is_multicast_ether_addr(mac_hdr->h_dest)) {
+		dlid = info->vesw.u_mcast_dlid;
+	} else {
+		if (is_local_ether_addr(mac_hdr->h_dest)) {
+			dlid = ((uint32_t)mac_hdr->h_dest[5] << 16) |
+				((uint32_t)mac_hdr->h_dest[4] << 8)  |
+				mac_hdr->h_dest[3];
+			if (unlikely(!dlid))
+				v_warn("Null dlid in MAC address\n");
+		} else if (def_port != OPA_VNIC_INVALID_PORT) {
+			if (def_port < OPA_VESW_MAX_NUM_DEF_PORT)
+				dlid = info->vesw.u_ucast_dlid[def_port];
+		}
+	}
+
+	return dlid;
+}
+
+/* opa_vnic_get_sc - return the service class */
+static u8 opa_vnic_get_sc(struct __opa_veswport_info *info,
+			  struct sk_buff *skb)
+{
+	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+	u16 vlan_tci;
+	u8 sc;
+
+	if (!__vlan_get_tag(skb, &vlan_tci)) {
+		u8 pcp = OPA_VNIC_VLAN_PCP(vlan_tci);
+
+		if (is_multicast_ether_addr(mac_hdr->h_dest))
+			sc = info->vport.pcp_to_sc_mc[pcp];
+		else
+			sc = info->vport.pcp_to_sc_uc[pcp];
+	} else {
+		if (is_multicast_ether_addr(mac_hdr->h_dest))
+			sc = info->vport.non_vlan_sc_mc;
+		else
+			sc = info->vport.non_vlan_sc_uc;
+	}
+
+	return sc;
+}
+
+u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb)
+{
+	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+	struct __opa_veswport_info *info = &adapter->info;
+	u8 vl;
+
+	if (skb_vlan_tag_present(skb)) {
+		u8 pcp = skb_vlan_tag_get(skb) >> VLAN_PRIO_SHIFT;
+
+		if (is_multicast_ether_addr(mac_hdr->h_dest))
+			vl = info->vport.pcp_to_vl_mc[pcp];
+		else
+			vl = info->vport.pcp_to_vl_uc[pcp];
+	} else {
+		if (is_multicast_ether_addr(mac_hdr->h_dest))
+			vl = info->vport.non_vlan_vl_mc;
+		else
+			vl = info->vport.non_vlan_vl_uc;
+	}
+
+	return vl;
+}
+
+/* opa_vnic_get_rc - return the routing control */
+static u8 opa_vnic_get_rc(struct __opa_veswport_info *info,
+			  struct sk_buff *skb)
+{
+	u8 proto, rout_ctrl;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IPV6):
+		proto = ipv6_hdr(skb)->nexthdr;
+		if (proto == IPPROTO_TCP)
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
+							  IPV6_TCP);
+		else if (proto == IPPROTO_UDP)
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
+							  IPV6_UDP);
+		else
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV6);
+		break;
+	case htons(ETH_P_IP):
+		proto = ip_hdr(skb)->protocol;
+		if (proto == IPPROTO_TCP)
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
+							  IPV4_TCP);
+		else if (proto == IPPROTO_UDP)
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
+							  IPV4_UDP);
+		else
+			rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV4);
+		break;
+	default:
+		rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, DEFAULT);
+	}
+
+	return rout_ctrl;
+}
+
+/* opa_vnic_calc_entropy - calculate the packet entropy */
+u8 opa_vnic_calc_entropy(struct sk_buff *skb)
+{
+	u32 hash = skb_get_hash(skb);
+
+	/* store XOR of all bytes in lower 8 bits */
+	hash ^= hash >> 8;
+	hash ^= hash >> 16;
+
+	/* return lower 8 bits as entropy */
+	return (u8)(hash & 0xFF);
+}
+
+/* opa_vnic_get_def_port - get default port based on entropy */
+static inline u8 opa_vnic_get_def_port(struct opa_vnic_adapter *adapter,
+				       u8 entropy)
+{
+	u8 flow_id;
+
+	/* Add the upper and lower 4-bits of entropy to get the flow id */
+	flow_id = ((entropy & 0xf) + (entropy >> 4));
+	return adapter->flow_tbl[flow_id & (OPA_VNIC_FLOW_TBL_SIZE - 1)];
+}
+
+/* Calculate packet length including OPA header, crc and padding */
+static inline int opa_vnic_wire_length(struct sk_buff *skb)
+{
+	u32 pad_len;
+
+	/* padding for 8 bytes size alignment */
+	pad_len = -(skb->len + OPA_VNIC_ICRC_TAIL_LEN) & 0x7;
+	pad_len += OPA_VNIC_ICRC_TAIL_LEN;
+
+	return (skb->len + pad_len) >> 3;
+}
+
+/* opa_vnic_encap_skb - encapsulate skb packet with OPA header and meta data */
+void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb)
+{
+	struct __opa_veswport_info *info = &adapter->info;
+	struct opa_vnic_skb_mdata *mdata;
+	u8 def_port, sc, rc, entropy, *hdr;
+	u16 len, l4_hdr;
+	u32 dlid;
+
+	hdr = skb_push(skb, OPA_VNIC_HDR_LEN);
+
+	entropy = opa_vnic_calc_entropy(skb);
+	def_port = opa_vnic_get_def_port(adapter, entropy);
+	len = opa_vnic_wire_length(skb);
+	dlid = opa_vnic_get_dlid(adapter, skb, def_port);
+	sc = opa_vnic_get_sc(info, skb);
+	rc = opa_vnic_get_rc(info, skb);
+	l4_hdr = info->vesw.vesw_id;
+
+	mdata = skb_push(skb, sizeof(*mdata));
+	mdata->vl = opa_vnic_get_vl(adapter, skb);
+	mdata->entropy = entropy;
+	mdata->flags = 0;
+	if (unlikely(!dlid)) {
+		mdata->flags = OPA_VNIC_SKB_MDATA_ENCAP_ERR;
+		return;
+	}
+
+	opa_vnic_make_header(hdr, info->vport.encap_slid, dlid, len,
+			     info->vesw.pkey, entropy, sc, rc,
+			     OPA_VNIC_L4_ETHR, l4_hdr);
+}