IB/hfi1: OPA_VNIC RDMA netdev support

Add support to create and free OPA_VNIC rdma netdev devices.
Implement netstack interface functionality including xmit_skb,
receive side NAPI etc. Also implement rdma netdev control functions.
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/Makefile

@@ -12,7 +12,7 @@ hfi1-y := affinity.o chip.o device.o driver.o efivar.o \
 	init.o intr.o mad.o mmu_rb.o pcie.o pio.o pio_copy.o platform.o \
 	qp.o qsfp.o rc.o ruc.o sdma.o sysfs.o trace.o \
 	uc.o ud.o user_exp_rcv.o user_pages.o user_sdma.o verbs.o \
-	verbs_txreq.o
+	verbs_txreq.o vnic_main.o
 hfi1-$(CONFIG_DEBUG_FS) += debugfs.o
 
 CFLAGS_trace.o = -I$(src)

drivers/infiniband/hw/hfi1/driver.c

 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015-2017 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.
@@ -60,6 +60,7 @@
 #include "qp.h"
 #include "sdma.h"
 #include "debugfs.h"
+#include "vnic.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
@@ -1381,15 +1382,31 @@ int process_receive_ib(struct hfi1_packet *packet)
 	return RHF_RCV_CONTINUE;
 }
 
+static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
+{
+	/* Packet received in VNIC context via RSM */
+	if (packet->rcd->is_vnic)
+		return true;
+
+	if ((HFI1_GET_L2_TYPE(packet->ebuf) == OPA_VNIC_L2_TYPE) &&
+	    (HFI1_GET_L4_TYPE(packet->ebuf) == OPA_VNIC_L4_ETHR))
+		return true;
+
+	return false;
+}
+
 int process_receive_bypass(struct hfi1_packet *packet)
 {
 	struct hfi1_devdata *dd = packet->rcd->dd;
 
-	if (unlikely(rhf_err_flags(packet->rhf)))
+	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
+	} else if (hfi1_is_vnic_packet(packet)) {
+		hfi1_vnic_bypass_rcv(packet);
+		return RHF_RCV_CONTINUE;
+	}
 
-	dd_dev_err(dd,
-		   "Bypass packets are not supported in normal operation. Dropping\n");
+	dd_dev_err(dd, "Unsupported bypass packet. Dropping\n");
 	incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
 	if (!(dd->err_info_rcvport.status_and_code & OPA_EI_STATUS_SMASK)) {
 		u64 *flits = packet->ebuf;

drivers/infiniband/hw/hfi1/hfi.h

 #ifndef _HFI1_KERNEL_H
 #define _HFI1_KERNEL_H
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015-2017 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.
@@ -337,6 +337,12 @@ struct hfi1_ctxtdata {
 	 * packets with the wrong interrupt handler.
 	 */
 	int (*do_interrupt)(struct hfi1_ctxtdata *rcd, int threaded);
+
+	/* Indicates that this is vnic context */
+	bool is_vnic;
+
+	/* vnic queue index this context is mapped to */
+	u8 vnic_q_idx;
 };
 
 /*
@@ -808,6 +814,19 @@ struct hfi1_asic_data {
 	struct hfi1_i2c_bus *i2c_bus1;
 };
 
+/*
+ * Number of VNIC contexts used. Ensure it is less than or equal to
+ * max queues supported by VNIC (HFI1_VNIC_MAX_QUEUE).
+ */
+#define HFI1_NUM_VNIC_CTXT   8
+
+/* Virtual NIC information */
+struct hfi1_vnic_data {
+	struct idr vesw_idr;
+};
+
+struct hfi1_vnic_vport_info;
+
 /* device data struct now contains only "general per-device" info.
  * fields related to a physical IB port are in a hfi1_pportdata struct.
  */
@@ -1115,6 +1134,9 @@ struct hfi1_devdata {
 	send_routine process_dma_send;
 	void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf,
 				u64 pbc, const void *from, size_t count);
+	int (*process_vnic_dma_send)(struct hfi1_devdata *dd, u8 q_idx,
+				     struct hfi1_vnic_vport_info *vinfo,
+				     struct sk_buff *skb, u64 pbc, u8 plen);
 	/* hfi1_pportdata, points to array of (physical) port-specific
 	 * data structs, indexed by pidx (0..n-1)
 	 */
@@ -1170,6 +1192,9 @@ struct hfi1_devdata {
 	struct rhashtable *sdma_rht;
 
 	struct kobject kobj;
+
+	/* vnic data */
+	struct hfi1_vnic_data vnic;
 };
 
 /* 8051 firmware version helper */

drivers/infiniband/hw/hfi1/init.c

 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015-2017 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.
@@ -65,6 +65,7 @@
 #include "verbs.h"
 #include "aspm.h"
 #include "affinity.h"
+#include "vnic.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
@@ -1498,6 +1499,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* do the generic initialization */
 	initfail = hfi1_init(dd, 0);
 
+	/* setup vnic */
+	hfi1_vnic_setup(dd);
+
 	ret = hfi1_register_ib_device(dd);
 
 	/*
@@ -1575,6 +1579,9 @@ static void remove_one(struct pci_dev *pdev)
 	/* unregister from IB core */
 	hfi1_unregister_ib_device(dd);
 
+	/* cleanup vnic */
+	hfi1_vnic_cleanup(dd);
+
 	/*
 	 * Disable the IB link, disable interrupts on the device,
 	 * clear dma engines, etc.

drivers/infiniband/hw/hfi1/vnic.h

+#ifndef _HFI1_VNIC_H
+#define _HFI1_VNIC_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.
+ *
+ */
+
+#include <rdma/opa_vnic.h>
+#include "hfi.h"
+
+#define HFI1_VNIC_MAX_TXQ     16
+#define HFI1_VNIC_MAX_PAD     12
+
+/* L2 header definitions */
+#define HFI1_L2_TYPE_OFFSET     0x7
+#define HFI1_L2_TYPE_SHFT       0x5
+#define HFI1_L2_TYPE_MASK       0x3
+
+#define HFI1_GET_L2_TYPE(hdr)                                            \
+	((*((u8 *)(hdr) + HFI1_L2_TYPE_OFFSET) >> HFI1_L2_TYPE_SHFT) &   \
+	 HFI1_L2_TYPE_MASK)
+
+/* L4 type definitions */
+#define HFI1_L4_TYPE_OFFSET 8
+
+#define HFI1_GET_L4_TYPE(data)   \
+	(*((u8 *)(data) + HFI1_L4_TYPE_OFFSET))
+
+/* L4 header definitions */
+#define HFI1_VNIC_L4_HDR_OFFSET  OPA_VNIC_L2_HDR_LEN
+
+#define HFI1_VNIC_GET_L4_HDR(data)   \
+	(*((u16 *)((u8 *)(data) + HFI1_VNIC_L4_HDR_OFFSET)))
+
+#define HFI1_VNIC_GET_VESWID(data)   \
+	(HFI1_VNIC_GET_L4_HDR(data) & 0xFFF)
+
+/* Service class */
+#define HFI1_VNIC_SC_OFFSET_LOW 6
+#define HFI1_VNIC_SC_OFFSET_HI  7
+#define HFI1_VNIC_SC_SHIFT      4
+
+#define HFI1_VNIC_MAX_QUEUE 16
+
+/**
+ * struct hfi1_vnic_rx_queue - HFI1 VNIC receive queue
+ * @idx: queue index
+ * @vinfo: pointer to vport information
+ * @netdev: network device
+ * @napi: netdev napi structure
+ * @skbq: queue of received socket buffers
+ */
+struct hfi1_vnic_rx_queue {
+	u8                           idx;
+	struct hfi1_vnic_vport_info *vinfo;
+	struct net_device           *netdev;
+	struct napi_struct           napi;
+	struct sk_buff_head          skbq;
+};
+
+/**
+ * struct hfi1_vnic_vport_info - HFI1 VNIC virtual port information
+ * @dd: device data pointer
+ * @netdev: net device pointer
+ * @flags: state flags
+ * @lock: vport lock
+ * @num_tx_q: number of transmit queues
+ * @num_rx_q: number of receive queues
+ * @vesw_id: virtual switch id
+ * @rxq: Array of receive queues
+ * @stats: per queue stats
+ */
+struct hfi1_vnic_vport_info {
+	struct hfi1_devdata *dd;
+	struct net_device   *netdev;
+	unsigned long        flags;
+
+	/* Lock used around state updates */
+	struct mutex         lock;
+
+	u8  num_tx_q;
+	u8  num_rx_q;
+	u16 vesw_id;
+	struct hfi1_vnic_rx_queue rxq[HFI1_NUM_VNIC_CTXT];
+
+	struct opa_vnic_stats  stats[HFI1_VNIC_MAX_QUEUE];
+};
+
+#define v_dbg(format, arg...) \
+	netdev_dbg(vinfo->netdev, format, ## arg)
+#define v_err(format, arg...) \
+	netdev_err(vinfo->netdev, format, ## arg)
+#define v_info(format, arg...) \
+	netdev_info(vinfo->netdev, format, ## arg)
+
+/* vnic hfi1 internal functions */
+void hfi1_vnic_setup(struct hfi1_devdata *dd);
+void hfi1_vnic_cleanup(struct hfi1_devdata *dd);
+
+void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet);
+
+/* vnic rdma netdev operations */
+struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
+				      u8 port_num,
+				      enum rdma_netdev_t type,
+				      const char *name,
+				      unsigned char name_assign_type,
+				      void (*setup)(struct net_device *));
+void hfi1_vnic_free_rn(struct net_device *netdev);
+
+#endif /* _HFI1_VNIC_H */