@@ -5628,6 +5628,13 @@ F: drivers/block/cciss*
F: include/linux/cciss_ioctl.h
F: include/uapi/linux/cciss_ioctl.h
+HFI-VNIC DRIVER
+M: Dennis Dalessandro <dennis.dalessandro@intel.com>
+M: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
+L: linux-rdma@vger.kernel.org
+S: Supported
+F: drivers/infiniband/sw/intel/hfi_vnic
+
HFI1 DRIVER
M: Mike Marciniszyn <mike.marciniszyn@intel.com>
M: Dennis Dalessandro <dennis.dalessandro@intel.com>
@@ -85,6 +85,7 @@ source "drivers/infiniband/ulp/srpt/Kconfig"
source "drivers/infiniband/ulp/iser/Kconfig"
source "drivers/infiniband/ulp/isert/Kconfig"
+source "drivers/infiniband/sw/intel/hfi_vnic/Kconfig"
source "drivers/infiniband/sw/rdmavt/Kconfig"
source "drivers/infiniband/sw/rxe/Kconfig"
@@ -1,2 +1,3 @@
obj-$(CONFIG_INFINIBAND_RDMAVT) += rdmavt/
obj-$(CONFIG_RDMA_RXE) += rxe/
+obj-$(CONFIG_HFI_VNIC) += intel/hfi_vnic/
new file mode 100644
@@ -0,0 +1,8 @@
+config HFI_VNIC
+ tristate "Intel HFI VNIC support"
+ depends on X86_64 && INFINIBAND
+ ---help---
+ This is HFI Virtual Network Interface Controller (VNIC) driver
+ for Ethernet over HFI feature. It implements the HW independent
+ VNIC functionality. It interfaces with Linux stack for data path
+ and IB MAD for the control path.
new file mode 100644
@@ -0,0 +1,6 @@
+# Makefile - Intel HFI Virtual Network Controller driver
+# Copyright(c) 2016, Intel Corporation.
+#
+obj-$(CONFIG_HFI_VNIC) += hfi_vnic.o
+
+hfi_vnic-y := hfi_vnic_netdev.o hfi_vnic_encap.o hfi_vnic_ethtool.o
new file mode 100644
@@ -0,0 +1,238 @@
+/*
+ * Copyright(c) 2016 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 HFI VNIC encapsulation/decapsulation function.
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+
+#include "hfi_vnic_internal.h"
+
+/**
+ * union hfi_vnic_bypass_hdr - VNIC bypass header
+ * @slid: source lid
+ * @length: length of packet
+ * @becn: backward explicit congestion notification
+ * @dlid: destination lid
+ * @sc: service class
+ * @fecn: forward explicit congestion notification
+ * @l2: L2 type (2=16B)
+ * @lt: link transfer field
+ * @l4: L4 type
+ * @slid_high: upper 4 bits of source lid
+ * @dlid_high: upper 4 bits of destination lid
+ * @pkey: partition key
+ * @entropy: entropy
+ * @age: packet age
+ * @l4_hdr: L4 header
+ */
+union hfi_vnic_bypass_hdr {
+ struct {
+ struct {
+ uint64_t slid : 20;
+ uint64_t length : 11;
+ uint64_t becn : 1;
+ uint64_t dlid : 20;
+ uint64_t sc : 5;
+ uint64_t rsvd : 3;
+ uint64_t fecn : 1;
+ uint64_t l2 : 2;
+ uint64_t lt : 1;
+ };
+ struct {
+ uint64_t l4 : 8;
+ uint64_t slid_high : 4;
+ uint64_t dlid_high : 4;
+ uint64_t pkey : 16;
+ uint64_t entropy : 16;
+ uint64_t age : 8;
+ uint64_t rsvd1 : 8;
+ };
+ struct {
+ uint32_t rsvd2 : 16;
+ uint32_t l4_hdr : 16;
+ };
+ } __packed;
+ u32 dw[5];
+};
+
+#define HFI_VNIC_SC_MASK 0x1f
+
+/* hfi_vnic_get_dlid - find and return the DLID */
+static uint32_t hfi_vnic_get_dlid(struct hfi_vnic_adapter *adapter,
+ struct sk_buff *skb, u8 def_port)
+{
+ struct __hfi_veswport_info *info = &adapter->info;
+ struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+ u32 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 != HFI_VNIC_INVALID_PORT) {
+ dlid = info->vesw.u_ucast_dlid[def_port];
+ }
+ }
+
+ return dlid;
+}
+
+/* hfi_vnic_get_sc - return the service class */
+static u8 hfi_vnic_get_sc(struct __hfi_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 = HFI_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 & HFI_VNIC_SC_MASK;
+}
+
+/* hfi_vnic_calc_entropy - calculate the packet entropy */
+u8 hfi_vnic_calc_entropy(struct hfi_vnic_adapter *adapter, struct sk_buff *skb)
+{
+ u16 hash16;
+
+ /*
+ * Get flow based 16-bit hash and then XOR the upper and lower bytes
+ * to get the entropy.
+ * __skb_tx_hash limits qcount to 16 bits. Hence, get 15-bit hash.
+ */
+ hash16 = __skb_tx_hash(adapter->netdev, skb, BIT(15));
+ return (u8)((hash16 >> 8) ^ (hash16 & 0xff));
+}
+
+/* hfi_vnic_get_def_port - get default port based on entropy */
+static inline u8 hfi_vnic_get_def_port(struct hfi_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 & (HFI_VNIC_FLOW_TBL_SIZE - 1)];
+}
+
+/* Calculate packet length including OPA header, crc and padding */
+static inline int hfi_vnic_wire_length(struct sk_buff *skb)
+{
+ u32 pad_len, hlen = HFI_VNIC_HDR_LEN;
+
+ /* padding for 8 bytes size alignment */
+ pad_len = -(skb->len + hlen + HFI_VNIC_ICRC_TAIL_LEN) & 0x7;
+ pad_len += HFI_VNIC_ICRC_TAIL_LEN;
+
+ return (skb->len + hlen + pad_len) >> 3;
+}
+
+/* hfi_vnic_encap_skb - encapsulate skb (ethernet) packet with OPA header */
+int hfi_vnic_encap_skb(struct hfi_vnic_adapter *adapter, struct sk_buff *skb)
+{
+ struct __hfi_veswport_info *info = &adapter->info;
+ union hfi_vnic_bypass_hdr *hdr;
+ u32 dlid;
+ u8 def_port;
+
+ hdr = (union hfi_vnic_bypass_hdr *)(skb->data - HFI_VNIC_HDR_LEN);
+ memset(hdr, 0, HFI_VNIC_HDR_LEN);
+
+ hdr->entropy = hfi_vnic_calc_entropy(adapter, skb);
+ def_port = hfi_vnic_get_def_port(adapter, hdr->entropy);
+
+ hdr->slid = info->vport.encap_slid;
+ hdr->slid_high = info->vport.encap_slid >> 20;
+
+ dlid = hfi_vnic_get_dlid(adapter, skb, def_port);
+ if (unlikely(!dlid))
+ return -EFAULT;
+
+ hdr->dlid = dlid;
+ hdr->dlid_high = dlid >> 20;
+
+ hdr->length = hfi_vnic_wire_length(skb);
+ hdr->sc = hfi_vnic_get_sc(info, skb);
+
+ hdr->l2 = HFI_VNIC_L2_TYPE;
+ hdr->lt = 1;
+
+ hdr->pkey = info->vesw.pkey;
+
+ hdr->l4 = HFI_VNIC_L4_ETHR;
+ hdr->l4_hdr = info->vesw.vesw_id;
+
+ skb_push(skb, HFI_VNIC_HDR_LEN);
+ return 0;
+}
+
+/* hfi_vnic_decap_skb - strip OPA header from the skb (ethernet) packet */
+int hfi_vnic_decap_skb(struct hfi_vnic_rx_queue *rxq, struct sk_buff *skb)
+{
+ skb_pull(skb, HFI_VNIC_HDR_LEN);
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,62 @@
+#ifndef _HFI_VNIC_ENCAP_H
+#define _HFI_VNIC_ENCAP_H
+/*
+ * Copyright(c) 2016 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 HFI VNIC declaration required for encapsulation
+ * and decapsulation of Ethernet packets
+ */
+
+#define HFI_VESW_MAX_NUM_DEF_PORT 16
+#define HFI_VNIC_MAX_NUM_PCP 8
+
+/* VNIC configured and operational state values */
+#define HFI_VNIC_STATE_DROP_ALL 0x1
+#define HFI_VNIC_STATE_FORWARDING 0x3
+
+#endif /* _HFI_VNIC_ENCAP_H */
new file mode 100644
@@ -0,0 +1,65 @@
+/*
+ * Copyright(c) 2016 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 HFI VNIC ethtool functions
+ */
+
+#include <linux/ethtool.h>
+
+#include "hfi_vnic_internal.h"
+
+/* ethtool ops */
+static const struct ethtool_ops hfi_vnic_ethtool_ops = {
+ .get_link = ethtool_op_get_link,
+};
+
+/* hfi_vnic_set_ethtool_ops - set ethtool ops */
+void hfi_vnic_set_ethtool_ops(struct net_device *netdev)
+{
+ netdev->ethtool_ops = &hfi_vnic_ethtool_ops;
+}
new file mode 100644
@@ -0,0 +1,220 @@
+#ifndef _HFI_VNIC_INTERNAL_H
+#define _HFI_VNIC_INTERNAL_H
+/*
+ * Copyright(c) 2016 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 HFI VNIC driver internal declarations
+ */
+
+#include <linux/bitops.h>
+#include <linux/etherdevice.h>
+#include <linux/hashtable.h>
+#include <linux/sizes.h>
+#include <rdma/opa_hfi.h>
+
+#include "hfi_vnic_encap.h"
+
+/* VNIC uses 16B header format */
+#define HFI_VNIC_L2_TYPE 0x2
+
+/* 16 header bytes + 2 reserved bytes */
+#define HFI_VNIC_L2_HDR_LEN (16 + 2)
+
+#define HFI_VNIC_L4_HDR_LEN 2
+
+#define HFI_VNIC_HDR_LEN (HFI_VNIC_L2_HDR_LEN + \
+ HFI_VNIC_L4_HDR_LEN)
+
+#define HFI_VNIC_L4_ETHR 0x78
+
+#define HFI_VNIC_ICRC_LEN 4
+#define HFI_VNIC_TAIL_LEN 1
+#define HFI_VNIC_ICRC_TAIL_LEN (HFI_VNIC_ICRC_LEN + HFI_VNIC_TAIL_LEN)
+
+#define HFI_VNIC_VLAN_PCP(vlan_tci) \
+ (((vlan_tci) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
+
+#define HFI_VNIC_SKB_HEADROOM ALIGN(HFI_VNIC_HDR_LEN, 8)
+
+/* Flow to default port redirection table size */
+#define HFI_VNIC_FLOW_TBL_SIZE 32
+
+/* Invalid port number */
+#define HFI_VNIC_INVALID_PORT 0xff
+
+enum hfi_vnic_flags_t {
+ HFI_VNIC_UP,
+ HFI_VNIC_OPEN,
+};
+
+struct hfi_vnic_adapter;
+
+/**
+ * struct __hfi_vesw_info - HFI vnic virtual switch info
+ */
+struct __hfi_vesw_info {
+ u16 fabric_id;
+ u16 vesw_id;
+
+ u8 rsvd0[6];
+ u16 def_port_mask;
+
+ u8 rsvd1[2];
+ u16 pkey;
+
+ u8 rsvd2[4];
+ u32 u_mcast_dlid;
+ u32 u_ucast_dlid[HFI_VESW_MAX_NUM_DEF_PORT];
+
+ u8 rsvd3[44];
+ u16 eth_mtu[HFI_VNIC_MAX_NUM_PCP];
+ u16 eth_mtu_non_vlan;
+ u8 rsvd4[2];
+} __packed;
+
+/**
+ * struct __hfi_per_veswport_info - HFI vnic per port info
+ */
+struct __hfi_per_veswport_info {
+ u32 port_num;
+
+ u8 eth_link_status;
+ u8 rsvd0[3];
+
+ u8 base_mac_addr[ETH_ALEN];
+ u8 config_state;
+ u8 oper_state;
+
+ u16 max_mac_tbl_ent;
+ u16 max_smac_ent;
+ u32 mac_tbl_digest;
+ u8 rsvd1[4];
+
+ u32 encap_slid;
+
+ u8 pcp_to_sc_uc[HFI_VNIC_MAX_NUM_PCP];
+ u8 pcp_to_vl_uc[HFI_VNIC_MAX_NUM_PCP];
+ u8 pcp_to_sc_mc[HFI_VNIC_MAX_NUM_PCP];
+ u8 pcp_to_vl_mc[HFI_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];
+
+ u16 uc_macs_gen_count;
+ u16 mc_macs_gen_count;
+
+ u8 rsvd3[8];
+} __packed;
+
+/**
+ * struct __hfi_veswport_info - HFI vnic port info
+ */
+struct __hfi_veswport_info {
+ struct __hfi_vesw_info vesw;
+ struct __hfi_per_veswport_info vport;
+};
+
+/**
+ * struct hfi_vnic_rx_queue - HFI VNIC receive queue
+ * @idx: queue index
+ * @adapter: netdev adapter
+ * @napi: netdev napi structure
+ */
+struct hfi_vnic_rx_queue {
+ u8 idx;
+ struct hfi_vnic_adapter *adapter;
+ struct napi_struct napi;
+};
+
+/**
+ * struct hfi_vnic_adapter - HFI VNIC netdev private data structure
+ * @netdev: pointer to associated netdev
+ * @vport: pointer to hfi vnic port
+ * @flags: flags indicating various states
+ * @lock: adapter lock
+ * @rxq: receive queue array
+ * @info: virtual ethernet switch port information
+ * @flow_tbl: flow to default port redirection table
+ */
+struct hfi_vnic_adapter {
+ struct net_device *netdev;
+ struct hfi_vnic_port *vport;
+ unsigned long flags;
+
+ /* Lock used around state updates */
+ struct mutex lock;
+
+ struct hfi_vnic_rx_queue rxq[HFI_VNIC_MAX_QUEUE];
+
+ struct __hfi_veswport_info info;
+
+ u8 flow_tbl[HFI_VNIC_FLOW_TBL_SIZE];
+};
+
+#define v_dbg(format, arg...) \
+ netdev_dbg(adapter->netdev, format, ## arg)
+#define v_err(format, arg...) \
+ netdev_err(adapter->netdev, format, ## arg)
+#define v_info(format, arg...) \
+ netdev_info(adapter->netdev, format, ## arg)
+#define v_warn(format, arg...) \
+ netdev_warn(adapter->netdev, format, ## arg)
+
+struct hfi_vnic_adapter *hfi_vnic_add_netdev(struct hfi_vnic_port *vport,
+ struct device *parent);
+void hfi_vnic_rem_netdev(struct hfi_vnic_port *vport);
+int hfi_vnic_encap_skb(struct hfi_vnic_adapter *adapter, struct sk_buff *skb);
+int hfi_vnic_decap_skb(struct hfi_vnic_rx_queue *rxq, struct sk_buff *skb);
+u8 hfi_vnic_calc_entropy(struct hfi_vnic_adapter *adapter, struct sk_buff *skb);
+void hfi_vnic_set_ethtool_ops(struct net_device *netdev);
+
+#endif /* _HFI_VNIC_INTERNAL_H */
new file mode 100644
@@ -0,0 +1,409 @@
+/*
+ * Copyright(c) 2016 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 HFI Virtual Network Interface Controller (VNIC) driver
+ */
+
+#include <linux/module.h>
+#include <linux/if_vlan.h>
+
+#include "hfi_vnic_internal.h"
+
+#define HFI_TX_TIMEOUT_MS 1000
+
+#define HFI_VNIC_MIN_ETH_MTU (ETH_ZLEN - ETH_HLEN)
+
+/* hfi_vnic_maybe_stop_tx - stop tx queue if required */
+static void hfi_vnic_maybe_stop_tx(struct hfi_vnic_adapter *adapter, u8 q_idx)
+{
+ struct hfi_vnic_port *vport = adapter->vport;
+
+ netif_stop_subqueue(vport->netdev, q_idx);
+ if (!vport->ops->get_write_avail(vport, q_idx))
+ return;
+
+ netif_start_subqueue(vport->netdev, q_idx);
+}
+
+/* hfi_netdev_start_xmit - transmit function */
+static netdev_tx_t hfi_netdev_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+ struct hfi_vnic_port *vport = adapter->vport;
+ u8 q_idx = skb->queue_mapping;
+ bool skip_skb_free = false;
+ int rc = -1;
+
+ v_dbg("xmit: queue %d skb len %d\n", q_idx, skb->len);
+ if (unlikely(adapter->info.vport.oper_state !=
+ HFI_VNIC_STATE_FORWARDING))
+ goto tx_finish;
+
+ /* pad to ensure mininum ethernet packet length */
+ if (unlikely(skb->len < ETH_ZLEN)) {
+ if (skb_padto(skb, ETH_ZLEN)) {
+ skip_skb_free = true;
+ goto tx_finish;
+ }
+ skb_put(skb, ETH_ZLEN - skb->len);
+ }
+
+ rc = hfi_vnic_encap_skb(adapter, skb);
+ if (unlikely(rc))
+ goto tx_finish;
+
+ /* Get reference to skb as hfi driver might release it */
+ skb_get(skb);
+ rc = vport->ops->put_skb(vport, q_idx, skb);
+ /* remove the header */
+ skb_pull(skb, HFI_VNIC_HDR_LEN);
+
+tx_finish:
+ if (unlikely(rc == -EBUSY)) {
+ hfi_vnic_maybe_stop_tx(adapter, q_idx);
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_BUSY;
+ }
+
+ if (!skip_skb_free)
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+}
+
+/* vnic_handle_rx - handle skb receive */
+static void vnic_handle_rx(struct hfi_vnic_rx_queue *rxq,
+ int *work_done, int work_to_do)
+{
+ struct hfi_vnic_adapter *adapter = rxq->adapter;
+ struct hfi_vnic_port *vport = adapter->vport;
+ struct sk_buff *skb;
+
+ while (1) {
+ if (*work_done >= work_to_do)
+ break;
+
+ skb = vport->ops->get_skb(vport, rxq->idx);
+ if (!skb)
+ break;
+
+ if (hfi_vnic_decap_skb(rxq, skb)) {
+ dev_kfree_skb_any(skb);
+ continue;
+ }
+
+ skb_checksum_none_assert(skb);
+ skb->protocol = eth_type_trans(skb, vport->netdev);
+
+ napi_gro_receive(&rxq->napi, skb);
+ (*work_done)++;
+ }
+}
+
+/* vnic_napi - napi receive polling callback function */
+static int vnic_napi(struct napi_struct *napi, int budget)
+{
+ struct hfi_vnic_rx_queue *rxq = container_of(napi,
+ struct hfi_vnic_rx_queue, napi);
+ struct hfi_vnic_adapter *adapter = rxq->adapter;
+ struct hfi_vnic_port *vport = adapter->vport;
+ u8 evt = rxq->idx + HFI_VNIC_EVT_RX0;
+ int work_done = 0;
+
+ v_dbg("napi %d budget %d\n", rxq->idx, budget);
+ vnic_handle_rx(rxq, &work_done, budget);
+
+ v_dbg("napi %d work_done %d\n", rxq->idx, work_done);
+ if (work_done < budget) {
+ napi_complete(napi);
+ vport->ops->config_notify(vport, evt, true);
+ }
+
+ return work_done;
+}
+
+/* vnic_event_cb - handle events from vnic hfi driver */
+static void vnic_event_cb(struct hfi_vnic_port *vport, u8 evt)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(vport->netdev);
+ struct hfi_vnic_rx_queue *rxq;
+ u8 q_idx;
+
+ v_dbg("received event %d\n", evt);
+ if (evt < vport->hfi_info.num_rx_q) {
+ q_idx = evt;
+ if (unlikely(adapter->info.vport.oper_state !=
+ HFI_VNIC_STATE_FORWARDING))
+ return;
+
+ rxq = &adapter->rxq[q_idx];
+ if (napi_schedule_prep(&rxq->napi)) {
+ v_dbg("napi %d scheduling\n", q_idx);
+ vport->ops->config_notify(vport, evt, false);
+ __napi_schedule(&rxq->napi);
+ }
+ return;
+ }
+ if ((evt >= HFI_VNIC_EVT_TX0) &&
+ (evt < (HFI_VNIC_EVT_TX0 + vport->hfi_info.num_tx_q))) {
+ q_idx = evt - HFI_VNIC_EVT_TX0;
+
+ if (__netif_subqueue_stopped(vport->netdev, q_idx))
+ netif_wake_subqueue(vport->netdev, q_idx);
+
+ return;
+ }
+ v_err("Invalid event\n");
+}
+
+static u16 hfi_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
+ void *accel_priv,
+ select_queue_fallback_t fallback)
+{
+ struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+ struct __hfi_veswport_info *info = &adapter->info;
+ struct hfi_vnic_port *vport = adapter->vport;
+ u8 vl, entropy;
+
+ 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;
+ }
+
+ entropy = hfi_vnic_calc_entropy(adapter, skb);
+ return vport->ops->select_queue(vport, vl, entropy);
+}
+
+/* hfi_netdev_change_mtu - change the MTU */
+static int hfi_netdev_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+ struct __hfi_veswport_info *info = &adapter->info;
+ u16 min_mtu = HFI_VNIC_MIN_ETH_MTU;
+ u16 max_mtu = max(min_mtu, info->vesw.eth_mtu_non_vlan);
+
+ /* Supported MTUs */
+ if ((new_mtu < min_mtu) || (new_mtu > max_mtu)) {
+ v_err("Unsupported MTU setting\n");
+ return -EINVAL;
+ }
+
+ v_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
+ netdev->mtu = new_mtu;
+ return 0;
+}
+
+/* hfi_vnic_up - enable vnic data flow */
+static int hfi_vnic_up(struct hfi_vnic_adapter *adapter)
+{
+ struct hfi_vnic_port *vport = adapter->vport;
+ int i, rc;
+
+ rc = vport->ops->open(vport, vnic_event_cb);
+ if (rc) {
+ v_dbg("hfi_open failed %d\n", rc);
+ return rc;
+ }
+
+ netif_carrier_on(adapter->netdev);
+ netif_tx_start_all_queues(adapter->netdev);
+ for (i = 0; i < vport->hfi_info.num_rx_q; i++)
+ napi_enable(&adapter->rxq[i].napi);
+
+ set_bit(HFI_VNIC_UP, &adapter->flags);
+ return 0;
+}
+
+/* hfi_vnic_down - disable vnic data flow */
+static void hfi_vnic_down(struct hfi_vnic_adapter *adapter)
+{
+ struct hfi_vnic_port *vport = adapter->vport;
+ int i;
+
+ netif_carrier_off(adapter->netdev);
+ netif_tx_disable(adapter->netdev);
+ for (i = 0; i < vport->hfi_info.num_rx_q; i++)
+ napi_disable(&adapter->rxq[i].napi);
+
+ vport->ops->close(vport);
+ clear_bit(HFI_VNIC_UP, &adapter->flags);
+}
+
+/* hfi_vnic_set_mac_addr - change mac address */
+static int hfi_vnic_set_mac_addr(struct net_device *netdev, void *addr)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+ struct sockaddr *sa = addr;
+ int rc;
+
+ if (!memcmp(netdev->dev_addr, sa->sa_data, ETH_ALEN))
+ return 0;
+
+ mutex_lock(&adapter->lock);
+ rc = eth_mac_addr(netdev, addr);
+ mutex_unlock(&adapter->lock);
+
+ return rc;
+}
+
+/* hfi_netdev_open - activate network interface */
+static int hfi_netdev_open(struct net_device *netdev)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+ int rc;
+
+ mutex_lock(&adapter->lock);
+ rc = hfi_vnic_up(adapter);
+ if (rc)
+ goto open_done;
+
+ set_bit(HFI_VNIC_OPEN, &adapter->flags);
+ v_info("opened\n");
+open_done:
+ mutex_unlock(&adapter->lock);
+ return rc;
+}
+
+/* hfi_netdev_close - disable network interface */
+static int hfi_netdev_close(struct net_device *netdev)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(netdev);
+
+ mutex_lock(&adapter->lock);
+ if (test_bit(HFI_VNIC_UP, &adapter->flags))
+ hfi_vnic_down(adapter);
+
+ clear_bit(HFI_VNIC_OPEN, &adapter->flags);
+ mutex_unlock(&adapter->lock);
+ v_info("closed\n");
+ return 0;
+}
+
+/* netdev ops */
+static const struct net_device_ops hfi_netdev_ops = {
+ .ndo_open = hfi_netdev_open,
+ .ndo_stop = hfi_netdev_close,
+ .ndo_start_xmit = hfi_netdev_start_xmit,
+ .ndo_change_mtu = hfi_netdev_change_mtu,
+ .ndo_select_queue = hfi_vnic_select_queue,
+ .ndo_set_mac_address = hfi_vnic_set_mac_addr,
+};
+
+/* hfi_vnic_add_netdev - create vnic netdev interface */
+struct hfi_vnic_adapter *hfi_vnic_add_netdev(struct hfi_vnic_port *vport,
+ struct device *parent)
+{
+ struct net_device *netdev;
+ struct hfi_vnic_adapter *adapter;
+ int i, rc;
+
+ netdev = alloc_etherdev_mqs(sizeof(struct hfi_vnic_adapter),
+ vport->hfi_info.num_tx_q,
+ vport->hfi_info.num_rx_q);
+ if (!netdev)
+ return ERR_PTR(-ENOMEM);
+ adapter = netdev_priv(netdev);
+ adapter->netdev = netdev;
+ adapter->vport = vport;
+ vport->netdev = netdev;
+ netdev->features = NETIF_F_HIGHDMA;
+ if (vport->hfi_info.cap & HFI_VNIC_CAP_SG)
+ netdev->features |= NETIF_F_SG;
+ netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ netdev->hw_features = netdev->features;
+ netdev->vlan_features = netdev->features;
+ netdev->watchdog_timeo = msecs_to_jiffies(HFI_TX_TIMEOUT_MS);
+ netdev->netdev_ops = &hfi_netdev_ops;
+ netdev->hard_header_len += HFI_VNIC_SKB_HEADROOM;
+ mutex_init(&adapter->lock);
+ strcpy(netdev->name, "veth%d");
+
+ SET_NETDEV_DEV(netdev, parent);
+
+ hfi_vnic_set_ethtool_ops(netdev);
+ for (i = 0; i < vport->hfi_info.num_rx_q; i++) {
+ adapter->rxq[i].idx = i;
+ adapter->rxq[i].adapter = adapter;
+ netif_napi_add(netdev, &adapter->rxq[i].napi, vnic_napi, 64);
+ }
+
+ rc = register_netdev(netdev);
+ if (rc)
+ goto netdev_err;
+
+ netif_carrier_off(netdev);
+ v_info("initialized\n");
+
+ return adapter;
+netdev_err:
+ mutex_destroy(&adapter->lock);
+ free_netdev(netdev);
+
+ return ERR_PTR(rc);
+}
+
+/* hfi_vnic_rem_netdev - remove vnic netdev interface */
+void hfi_vnic_rem_netdev(struct hfi_vnic_port *vport)
+{
+ struct hfi_vnic_adapter *adapter = netdev_priv(vport->netdev);
+
+ v_info("removing\n");
+ unregister_netdev(vport->netdev);
+ mutex_destroy(&adapter->lock);
+ free_netdev(vport->netdev);
+}