RDMA/ocrdma: Add driver for Emulex OneConnect IBoE RDMA adapter

Signed-off-by: Parav Pandit <parav.pandit@emulex.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/infiniband/Kconfig

@@ -51,6 +51,7 @@ source "drivers/infiniband/hw/cxgb3/Kconfig"
 source "drivers/infiniband/hw/cxgb4/Kconfig"
 source "drivers/infiniband/hw/mlx4/Kconfig"
 source "drivers/infiniband/hw/nes/Kconfig"
+source "drivers/infiniband/hw/ocrdma/Kconfig"
 
 source "drivers/infiniband/ulp/ipoib/Kconfig"
 

drivers/infiniband/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_INFINIBAND_CXGB3)		+= hw/cxgb3/
 obj-$(CONFIG_INFINIBAND_CXGB4)		+= hw/cxgb4/
 obj-$(CONFIG_MLX4_INFINIBAND)		+= hw/mlx4/
 obj-$(CONFIG_INFINIBAND_NES)		+= hw/nes/
+obj-$(CONFIG_INFINIBAND_OCRDMA)		+= hw/ocrdma/
 obj-$(CONFIG_INFINIBAND_IPOIB)		+= ulp/ipoib/
 obj-$(CONFIG_INFINIBAND_SRP)		+= ulp/srp/
 obj-$(CONFIG_INFINIBAND_SRPT)		+= ulp/srpt/

drivers/infiniband/hw/ocrdma/Kconfig

@@ -0,0 +1,8 @@
+config INFINIBAND_OCRDMA
+	tristate "Emulex One Connect HCA support"
+	depends on ETHERNET && NETDEVICES && PCI
+	select NET_VENDOR_EMULEX
+	select BE2NET
+	---help---
+	  This driver provides low-level InfiniBand over Ethernet
+	  support for Emulex One Connect host channel adapters (HCAs).

drivers/infiniband/hw/ocrdma/Makefile

@@ -0,0 +1,5 @@
+ccflags-y := -Idrivers/net/ethernet/emulex/benet
+
+obj-$(CONFIG_INFINIBAND_OCRDMA)	+= ocrdma.o
+
+ocrdma-y :=	ocrdma_main.o ocrdma_verbs.o ocrdma_hw.o ocrdma_ah.o

drivers/infiniband/hw/ocrdma/ocrdma.h

@@ -0,0 +1,392 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#ifndef __OCRDMA_H__
+#define __OCRDMA_H__
+
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+
+#include <be_roce.h>
+#include "ocrdma_sli.h"
+
+#define OCRDMA_ROCE_DEV_VERSION "1.0.0"
+#define OCRDMA_NODE_DESC "Emulex OneConnect RoCE HCA"
+
+#define ocrdma_err(format, arg...) printk(KERN_ERR format, ##arg)
+
+#define OCRDMA_MAX_AH 512
+
+#define OCRDMA_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME)
+
+struct ocrdma_dev_attr {
+	u8 fw_ver[32];
+	u32 vendor_id;
+	u32 device_id;
+	u16 max_pd;
+	u16 max_cq;
+	u16 max_cqe;
+	u16 max_qp;
+	u16 max_wqe;
+	u16 max_rqe;
+	u32 max_inline_data;
+	int max_send_sge;
+	int max_recv_sge;
+	int max_mr;
+	u64 max_mr_size;
+	u32 max_num_mr_pbl;
+	int max_fmr;
+	int max_map_per_fmr;
+	int max_pages_per_frmr;
+	u16 max_ord_per_qp;
+	u16 max_ird_per_qp;
+
+	int device_cap_flags;
+	u8 cq_overflow_detect;
+	u8 srq_supported;
+
+	u32 wqe_size;
+	u32 rqe_size;
+	u32 ird_page_size;
+	u8 local_ca_ack_delay;
+	u8 ird;
+	u8 num_ird_pages;
+};
+
+struct ocrdma_pbl {
+	void *va;
+	dma_addr_t pa;
+};
+
+struct ocrdma_queue_info {
+	void *va;
+	dma_addr_t dma;
+	u32 size;
+	u16 len;
+	u16 entry_size;		/* Size of an element in the queue */
+	u16 id;			/* qid, where to ring the doorbell. */
+	u16 head, tail;
+	bool created;
+	atomic_t used;		/* Number of valid elements in the queue */
+};
+
+struct ocrdma_eq {
+	struct ocrdma_queue_info q;
+	u32 vector;
+	int cq_cnt;
+	struct ocrdma_dev *dev;
+	char irq_name[32];
+};
+
+struct ocrdma_mq {
+	struct ocrdma_queue_info sq;
+	struct ocrdma_queue_info cq;
+	bool rearm_cq;
+};
+
+struct mqe_ctx {
+	struct mutex lock; /* for serializing mailbox commands on MQ */
+	wait_queue_head_t cmd_wait;
+	u32 tag;
+	u16 cqe_status;
+	u16 ext_status;
+	bool cmd_done;
+};
+
+struct ocrdma_dev {
+	struct ib_device ibdev;
+	struct ocrdma_dev_attr attr;
+
+	struct mutex dev_lock; /* provides syncronise access to device data */
+	spinlock_t flush_q_lock ____cacheline_aligned;
+
+	struct ocrdma_cq **cq_tbl;
+	struct ocrdma_qp **qp_tbl;
+
+	struct ocrdma_eq meq;
+	struct ocrdma_eq *qp_eq_tbl;
+	int eq_cnt;
+	u16 base_eqid;
+	u16 max_eq;
+
+	union ib_gid *sgid_tbl;
+	/* provided synchronization to sgid table for
+	 * updating gid entries triggered by notifier.
+	 */
+	spinlock_t sgid_lock;
+
+	int gsi_qp_created;
+	struct ocrdma_cq *gsi_sqcq;
+	struct ocrdma_cq *gsi_rqcq;
+
+	struct {
+		struct ocrdma_av *va;
+		dma_addr_t pa;
+		u32 size;
+		u32 num_ah;
+		/* provide synchronization for av
+		 * entry allocations.
+		 */
+		spinlock_t lock;
+		u32 ahid;
+		struct ocrdma_pbl pbl;
+	} av_tbl;
+
+	void *mbx_cmd;
+	struct ocrdma_mq mq;
+	struct mqe_ctx mqe_ctx;
+
+	struct be_dev_info nic_info;
+
+	struct list_head entry;
+	int id;
+};
+
+struct ocrdma_cq {
+	struct ib_cq ibcq;
+	struct ocrdma_dev *dev;
+	struct ocrdma_cqe *va;
+	u32 phase;
+	u32 getp;	/* pointer to pending wrs to
+			 * return to stack, wrap arounds
+			 * at max_hw_cqe
+			 */
+	u32 max_hw_cqe;
+	bool phase_change;
+	bool armed, solicited;
+	bool arm_needed;
+
+	spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization
+						   * to cq polling
+						   */
+	/* syncronizes cq completion handler invoked from multiple context */
+	spinlock_t comp_handler_lock ____cacheline_aligned;
+	u16 id;
+	u16 eqn;
+
+	struct ocrdma_ucontext *ucontext;
+	dma_addr_t pa;
+	u32 len;
+	atomic_t use_cnt;
+
+	/* head of all qp's sq and rq for which cqes need to be flushed
+	 * by the software.
+	 */
+	struct list_head sq_head, rq_head;
+};
+
+struct ocrdma_pd {
+	struct ib_pd ibpd;
+	struct ocrdma_dev *dev;
+	struct ocrdma_ucontext *uctx;
+	atomic_t use_cnt;
+	u32 id;
+	int num_dpp_qp;
+	u32 dpp_page;
+	bool dpp_enabled;
+};
+
+struct ocrdma_ah {
+	struct ib_ah ibah;
+	struct ocrdma_dev *dev;
+	struct ocrdma_av *av;
+	u16 sgid_index;
+	u32 id;
+};
+
+struct ocrdma_qp_hwq_info {
+	u8 *va;			/* virtual address */
+	u32 max_sges;
+	u32 head, tail;
+	u32 entry_size;
+	u32 max_cnt;
+	u32 max_wqe_idx;
+	u32 free_delta;
+	u16 dbid;		/* qid, where to ring the doorbell. */
+	u32 len;
+	dma_addr_t pa;
+};
+
+struct ocrdma_srq {
+	struct ib_srq ibsrq;
+	struct ocrdma_dev *dev;
+	u8 __iomem *db;
+	/* provide synchronization to multiple context(s) posting rqe */
+	spinlock_t q_lock ____cacheline_aligned;
+
+	struct ocrdma_qp_hwq_info rq;
+	struct ocrdma_pd *pd;
+	atomic_t use_cnt;
+	u32 id;
+	u64 *rqe_wr_id_tbl;
+	u32 *idx_bit_fields;
+	u32 bit_fields_len;
+};
+
+struct ocrdma_qp {
+	struct ib_qp ibqp;
+	struct ocrdma_dev *dev;
+
+	u8 __iomem *sq_db;
+	/* provide synchronization to multiple context(s) posting wqe, rqe */
+	spinlock_t q_lock ____cacheline_aligned;
+	struct ocrdma_qp_hwq_info sq;
+	struct {
+		uint64_t wrid;
+		uint16_t dpp_wqe_idx;
+		uint16_t dpp_wqe;
+		uint8_t  signaled;
+		uint8_t  rsvd[3];
+	} *wqe_wr_id_tbl;
+	u32 max_inline_data;
+	struct ocrdma_cq *sq_cq;
+	/* list maintained per CQ to flush SQ errors */
+	struct list_head sq_entry;
+
+	u8 __iomem *rq_db;
+	struct ocrdma_qp_hwq_info rq;
+	u64 *rqe_wr_id_tbl;
+	struct ocrdma_cq *rq_cq;
+	struct ocrdma_srq *srq;
+	/* list maintained per CQ to flush RQ errors */
+	struct list_head rq_entry;
+
+	enum ocrdma_qp_state state;	/*  QP state */
+	int cap_flags;
+	u32 max_ord, max_ird;
+
+	u32 id;
+	struct ocrdma_pd *pd;
+
+	enum ib_qp_type qp_type;
+
+	int sgid_idx;
+	u32 qkey;
+	bool dpp_enabled;
+	u8 *ird_q_va;
+};
+
+#define OCRDMA_GET_NUM_POSTED_SHIFT_VAL(qp) \
+	(((qp->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) && \
+		(qp->id < 64)) ? 24 : 16)
+
+struct ocrdma_hw_mr {
+	struct ocrdma_dev *dev;
+	u32 lkey;
+	u8 fr_mr;
+	u8 remote_atomic;
+	u8 remote_rd;
+	u8 remote_wr;
+	u8 local_rd;
+	u8 local_wr;
+	u8 mw_bind;
+	u8 rsvd;
+	u64 len;
+	struct ocrdma_pbl *pbl_table;
+	u32 num_pbls;
+	u32 num_pbes;
+	u32 pbl_size;
+	u32 pbe_size;
+	u64 fbo;
+	u64 va;
+};
+
+struct ocrdma_mr {
+	struct ib_mr ibmr;
+	struct ib_umem *umem;
+	struct ocrdma_hw_mr hwmr;
+	struct ocrdma_pd *pd;
+};
+
+struct ocrdma_ucontext {
+	struct ib_ucontext ibucontext;
+	struct ocrdma_dev *dev;
+
+	struct list_head mm_head;
+	struct mutex mm_list_lock; /* protects list entries of mm type */
+	struct {
+		u32 *va;
+		dma_addr_t pa;
+		u32 len;
+	} ah_tbl;
+};
+
+struct ocrdma_mm {
+	struct {
+		u64 phy_addr;
+		unsigned long len;
+	} key;
+	struct list_head entry;
+};
+
+static inline struct ocrdma_dev *get_ocrdma_dev(struct ib_device *ibdev)
+{
+	return container_of(ibdev, struct ocrdma_dev, ibdev);
+}
+
+static inline struct ocrdma_ucontext *get_ocrdma_ucontext(struct ib_ucontext
+							  *ibucontext)
+{
+	return container_of(ibucontext, struct ocrdma_ucontext, ibucontext);
+}
+
+static inline struct ocrdma_pd *get_ocrdma_pd(struct ib_pd *ibpd)
+{
+	return container_of(ibpd, struct ocrdma_pd, ibpd);
+}
+
+static inline struct ocrdma_cq *get_ocrdma_cq(struct ib_cq *ibcq)
+{
+	return container_of(ibcq, struct ocrdma_cq, ibcq);
+}
+
+static inline struct ocrdma_qp *get_ocrdma_qp(struct ib_qp *ibqp)
+{
+	return container_of(ibqp, struct ocrdma_qp, ibqp);
+}
+
+static inline struct ocrdma_mr *get_ocrdma_mr(struct ib_mr *ibmr)
+{
+	return container_of(ibmr, struct ocrdma_mr, ibmr);
+}
+
+static inline struct ocrdma_ah *get_ocrdma_ah(struct ib_ah *ibah)
+{
+	return container_of(ibah, struct ocrdma_ah, ibah);
+}
+
+static inline struct ocrdma_srq *get_ocrdma_srq(struct ib_srq *ibsrq)
+{
+	return container_of(ibsrq, struct ocrdma_srq, ibsrq);
+}
+
+#endif

drivers/infiniband/hw/ocrdma/ocrdma_abi.h

@@ -0,0 +1,134 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#ifndef __OCRDMA_ABI_H__
+#define __OCRDMA_ABI_H__
+
+struct ocrdma_alloc_ucontext_resp {
+	u32 dev_id;
+	u32 wqe_size;
+	u32 max_inline_data;
+	u32 dpp_wqe_size;
+	u64 ah_tbl_page;
+	u32 ah_tbl_len;
+	u32 rsvd;
+	u8 fw_ver[32];
+	u32 rqe_size;
+	u64 rsvd1;
+} __packed;
+
+/* user kernel communication data structures. */
+struct ocrdma_alloc_pd_ureq {
+	u64 rsvd1;
+} __packed;
+
+struct ocrdma_alloc_pd_uresp {
+	u32 id;
+	u32 dpp_enabled;
+	u32 dpp_page_addr_hi;
+	u32 dpp_page_addr_lo;
+	u64 rsvd1;
+} __packed;
+
+struct ocrdma_create_cq_ureq {
+	u32 dpp_cq;
+	u32 rsvd;
+} __packed;
+
+#define MAX_CQ_PAGES 8
+struct ocrdma_create_cq_uresp {
+	u32 cq_id;
+	u32 page_size;
+	u32 num_pages;
+	u32 max_hw_cqe;
+	u64 page_addr[MAX_CQ_PAGES];
+	u64 db_page_addr;
+	u32 db_page_size;
+	u32 phase_change;
+	u64 rsvd1;
+	u64 rsvd2;
+} __packed;
+
+#define MAX_QP_PAGES 8
+#define MAX_UD_AV_PAGES 8
+
+struct ocrdma_create_qp_ureq {
+	u8 enable_dpp_cq;
+	u8 rsvd;
+	u16 dpp_cq_id;
+	u32 rsvd1;
+};
+
+struct ocrdma_create_qp_uresp {
+	u16 qp_id;
+	u16 sq_dbid;
+	u16 rq_dbid;
+	u16 resv0;
+	u32 sq_page_size;
+	u32 rq_page_size;
+	u32 num_sq_pages;
+	u32 num_rq_pages;
+	u64 sq_page_addr[MAX_QP_PAGES];
+	u64 rq_page_addr[MAX_QP_PAGES];
+	u64 db_page_addr;
+	u32 db_page_size;
+	u32 dpp_credit;
+	u32 dpp_offset;
+	u32 rsvd1;
+	u32 num_wqe_allocated;
+	u32 num_rqe_allocated;
+	u32 free_wqe_delta;
+	u32 free_rqe_delta;
+	u32 db_sq_offset;
+	u32 db_rq_offset;
+	u32 db_shift;
+	u64 rsvd2;
+	u64 rsvd3;
+} __packed;
+
+struct ocrdma_create_srq_uresp {
+	u16 rq_dbid;
+	u16 resv0;
+	u32 resv1;
+
+	u32 rq_page_size;
+	u32 num_rq_pages;
+
+	u64 rq_page_addr[MAX_QP_PAGES];
+	u64 db_page_addr;
+
+	u32 db_page_size;
+	u32 num_rqe_allocated;
+	u32 db_rq_offset;
+	u32 db_shift;
+
+	u32 free_rqe_delta;
+	u32 rsvd2;
+	u64 rsvd3;
+} __packed;
+
+#endif				/* __OCRDMA_ABI_H__ */

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -0,0 +1,172 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#include <net/neighbour.h>
+#include <net/netevent.h>
+
+#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
+
+#include "ocrdma.h"
+#include "ocrdma_verbs.h"
+#include "ocrdma_ah.h"
+#include "ocrdma_hw.h"
+
+static inline int set_av_attr(struct ocrdma_ah *ah,
+				struct ib_ah_attr *attr, int pdid)
+{
+	int status = 0;
+	u16 vlan_tag; bool vlan_enabled = false;
+	struct ocrdma_dev *dev = ah->dev;
+	struct ocrdma_eth_vlan eth;
+	struct ocrdma_grh grh;
+	int eth_sz;
+
+	memset(&eth, 0, sizeof(eth));
+	memset(&grh, 0, sizeof(grh));
+
+	ah->sgid_index = attr->grh.sgid_index;
+
+	vlan_tag = rdma_get_vlan_id(&attr->grh.dgid);
+	if (vlan_tag && (vlan_tag < 0x1000)) {
+		eth.eth_type = cpu_to_be16(0x8100);
+		eth.roce_eth_type = cpu_to_be16(OCRDMA_ROCE_ETH_TYPE);
+		vlan_tag |= (attr->sl & 7) << 13;
+		eth.vlan_tag = cpu_to_be16(vlan_tag);
+		eth_sz = sizeof(struct ocrdma_eth_vlan);
+		vlan_enabled = true;
+	} else {
+		eth.eth_type = cpu_to_be16(OCRDMA_ROCE_ETH_TYPE);
+		eth_sz = sizeof(struct ocrdma_eth_basic);
+	}
+	memcpy(&eth.smac[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
+	status = ocrdma_resolve_dgid(dev, &attr->grh.dgid, &eth.dmac[0]);
+	if (status)
+		return status;
+	status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index,
+			(union ib_gid *)&grh.sgid[0]);
+	if (status)
+		return status;
+
+	grh.tclass_flow = cpu_to_be32((6 << 28) |
+			(attr->grh.traffic_class << 24) |
+			attr->grh.flow_label);
+	/* 0x1b is next header value in GRH */
+	grh.pdid_hoplimit = cpu_to_be32((pdid << 16) |
+			(0x1b << 8) | attr->grh.hop_limit);
+
+	memcpy(&grh.dgid[0], attr->grh.dgid.raw, sizeof(attr->grh.dgid.raw));
+	memcpy(&ah->av->eth_hdr, &eth, eth_sz);
+	memcpy((u8 *)ah->av + eth_sz, &grh, sizeof(struct ocrdma_grh));
+	if (vlan_enabled)
+		ah->av->valid |= OCRDMA_AV_VLAN_VALID;
+	return status;
+}
+
+struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+{
+	u32 *ahid_addr;
+	int status;
+	struct ocrdma_ah *ah;
+	struct ocrdma_pd *pd = get_ocrdma_pd(ibpd);
+	struct ocrdma_dev *dev = pd->dev;
+
+	if (!(attr->ah_flags & IB_AH_GRH))
+		return ERR_PTR(-EINVAL);
+
+	ah = kzalloc(sizeof *ah, GFP_ATOMIC);
+	if (!ah)
+		return ERR_PTR(-ENOMEM);
+	ah->dev = pd->dev;
+
+	status = ocrdma_alloc_av(dev, ah);
+	if (status)
+		goto av_err;
+	status = set_av_attr(ah, attr, pd->id);
+	if (status)
+		goto av_conf_err;
+
+	/* if pd is for the user process, pass the ah_id to user space */
+	if ((pd->uctx) && (pd->uctx->ah_tbl.va)) {
+		ahid_addr = pd->uctx->ah_tbl.va + attr->dlid;
+		*ahid_addr = ah->id;
+	}
+	return &ah->ibah;
+
+av_conf_err:
+	ocrdma_free_av(dev, ah);
+av_err:
+	kfree(ah);
+	return ERR_PTR(status);
+}
+
+int ocrdma_destroy_ah(struct ib_ah *ibah)
+{
+	struct ocrdma_ah *ah = get_ocrdma_ah(ibah);
+	ocrdma_free_av(ah->dev, ah);
+	kfree(ah);
+	return 0;
+}
+
+int ocrdma_query_ah(struct ib_ah *ibah, struct ib_ah_attr *attr)
+{
+	struct ocrdma_ah *ah = get_ocrdma_ah(ibah);
+	struct ocrdma_av *av = ah->av;
+	struct ocrdma_grh *grh;
+	attr->ah_flags |= IB_AH_GRH;
+	if (ah->av->valid & Bit(1)) {
+		grh = (struct ocrdma_grh *)((u8 *)ah->av +
+				sizeof(struct ocrdma_eth_vlan));
+		attr->sl = be16_to_cpu(av->eth_hdr.vlan_tag) >> 13;
+	} else {
+		grh = (struct ocrdma_grh *)((u8 *)ah->av +
+					sizeof(struct ocrdma_eth_basic));
+		attr->sl = 0;
+	}
+	memcpy(&attr->grh.dgid.raw[0], &grh->dgid[0], sizeof(grh->dgid));
+	attr->grh.sgid_index = ah->sgid_index;
+	attr->grh.hop_limit = be32_to_cpu(grh->pdid_hoplimit) & 0xff;
+	attr->grh.traffic_class = be32_to_cpu(grh->tclass_flow) >> 24;
+	attr->grh.flow_label = be32_to_cpu(grh->tclass_flow) & 0x00ffffffff;
+	return 0;
+}
+
+int ocrdma_modify_ah(struct ib_ah *ibah, struct ib_ah_attr *attr)
+{
+	/* modify_ah is unsupported */
+	return -ENOSYS;
+}
+
+int ocrdma_process_mad(struct ib_device *ibdev,
+		       int process_mad_flags,
+		       u8 port_num,
+		       struct ib_wc *in_wc,
+		       struct ib_grh *in_grh,
+		       struct ib_mad *in_mad, struct ib_mad *out_mad)
+{
+	return IB_MAD_RESULT_SUCCESS;
+}

drivers/infiniband/hw/ocrdma/ocrdma_ah.h

@@ -0,0 +1,42 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#ifndef __OCRDMA_AH_H__
+#define __OCRDMA_AH_H__
+
+struct ib_ah *ocrdma_create_ah(struct ib_pd *, struct ib_ah_attr *);
+int ocrdma_destroy_ah(struct ib_ah *);
+int ocrdma_query_ah(struct ib_ah *, struct ib_ah_attr *);
+int ocrdma_modify_ah(struct ib_ah *, struct ib_ah_attr *);
+
+int ocrdma_process_mad(struct ib_device *,
+		       int process_mad_flags,
+		       u8 port_num,
+		       struct ib_wc *in_wc,
+		       struct ib_grh *in_grh,
+		       struct ib_mad *in_mad, struct ib_mad *out_mad);
+#endif				/* __OCRDMA_AH_H__ */

drivers/infiniband/hw/ocrdma/ocrdma_hw.h

@@ -0,0 +1,132 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#ifndef __OCRDMA_HW_H__
+#define __OCRDMA_HW_H__
+
+#include "ocrdma_sli.h"
+
+static inline void ocrdma_cpu_to_le32(void *dst, u32 len)
+{
+#ifdef __BIG_ENDIAN
+	int i = 0;
+	u32 *src_ptr = dst;
+	u32 *dst_ptr = dst;
+	for (; i < (len / 4); i++)
+		*(dst_ptr + i) = cpu_to_le32p(src_ptr + i);
+#endif
+}
+
+static inline void ocrdma_le32_to_cpu(void *dst, u32 len)
+{
+#ifdef __BIG_ENDIAN
+	int i = 0;
+	u32 *src_ptr = dst;
+	u32 *dst_ptr = dst;
+	for (; i < (len / sizeof(u32)); i++)
+		*(dst_ptr + i) = le32_to_cpu(*(src_ptr + i));
+#endif
+}
+
+static inline void ocrdma_copy_cpu_to_le32(void *dst, void *src, u32 len)
+{
+#ifdef __BIG_ENDIAN
+	int i = 0;
+	u32 *src_ptr = src;
+	u32 *dst_ptr = dst;
+	for (; i < (len / sizeof(u32)); i++)
+		*(dst_ptr + i) = cpu_to_le32p(src_ptr + i);
+#else
+	memcpy(dst, src, len);
+#endif
+}
+
+static inline void ocrdma_copy_le32_to_cpu(void *dst, void *src, u32 len)
+{
+#ifdef __BIG_ENDIAN
+	int i = 0;
+	u32 *src_ptr = src;
+	u32 *dst_ptr = dst;
+	for (; i < len / sizeof(u32); i++)
+		*(dst_ptr + i) = le32_to_cpu(*(src_ptr + i));
+#else
+	memcpy(dst, src, len);
+#endif
+}
+
+int ocrdma_init_hw(struct ocrdma_dev *);
+void ocrdma_cleanup_hw(struct ocrdma_dev *);
+
+enum ib_qp_state get_ibqp_state(enum ocrdma_qp_state qps);
+void ocrdma_ring_cq_db(struct ocrdma_dev *, u16 cq_id, bool armed,
+		       bool solicited, u16 cqe_popped);
+
+/* verbs specific mailbox commands */
+int ocrdma_query_config(struct ocrdma_dev *,
+			struct ocrdma_mbx_query_config *config);
+int ocrdma_resolve_dgid(struct ocrdma_dev *, union ib_gid *dgid, u8 *mac_addr);
+
+int ocrdma_mbx_alloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);
+int ocrdma_mbx_dealloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);
+
+int ocrdma_mbx_alloc_lkey(struct ocrdma_dev *, struct ocrdma_hw_mr *hwmr,
+			  u32 pd_id, int addr_check);
+int ocrdma_mbx_dealloc_lkey(struct ocrdma_dev *, int fmr, u32 lkey);
+
+int ocrdma_reg_mr(struct ocrdma_dev *, struct ocrdma_hw_mr *hwmr,
+			u32 pd_id, int acc);
+int ocrdma_mbx_create_cq(struct ocrdma_dev *, struct ocrdma_cq *,
+				int entries, int dpp_cq);
+int ocrdma_mbx_destroy_cq(struct ocrdma_dev *, struct ocrdma_cq *);
+
+int ocrdma_mbx_create_qp(struct ocrdma_qp *, struct ib_qp_init_attr *attrs,
+			 u8 enable_dpp_cq, u16 dpp_cq_id, u16 *dpp_offset,
+			 u16 *dpp_credit_lmt);
+int ocrdma_mbx_modify_qp(struct ocrdma_dev *, struct ocrdma_qp *,
+			 struct ib_qp_attr *attrs, int attr_mask,
+			 enum ib_qp_state old_qps);
+int ocrdma_mbx_query_qp(struct ocrdma_dev *, struct ocrdma_qp *,
+			struct ocrdma_qp_params *param);
+int ocrdma_mbx_destroy_qp(struct ocrdma_dev *, struct ocrdma_qp *);
+
+int ocrdma_mbx_create_srq(struct ocrdma_srq *,
+			  struct ib_srq_init_attr *,
+			  struct ocrdma_pd *);
+int ocrdma_mbx_modify_srq(struct ocrdma_srq *, struct ib_srq_attr *);
+int ocrdma_mbx_query_srq(struct ocrdma_srq *, struct ib_srq_attr *);
+int ocrdma_mbx_destroy_srq(struct ocrdma_dev *, struct ocrdma_srq *);
+
+int ocrdma_alloc_av(struct ocrdma_dev *, struct ocrdma_ah *);
+int ocrdma_free_av(struct ocrdma_dev *, struct ocrdma_ah *);
+
+int ocrdma_qp_state_machine(struct ocrdma_qp *, enum ib_qp_state new_state,
+			    enum ib_qp_state *old_ib_state);
+bool ocrdma_is_qp_in_sq_flushlist(struct ocrdma_cq *, struct ocrdma_qp *);
+bool ocrdma_is_qp_in_rq_flushlist(struct ocrdma_cq *, struct ocrdma_qp *);
+void ocrdma_flush_qp(struct ocrdma_qp *);
+
+#endif				/* __OCRDMA_HW_H__ */

drivers/infiniband/hw/ocrdma/ocrdma_main.c

@@ -0,0 +1,558 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/idr.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+
+#include <linux/netdevice.h>
+#include <net/addrconf.h>
+
+#include "ocrdma.h"
+#include "ocrdma_verbs.h"
+#include "ocrdma_ah.h"
+#include "be_roce.h"
+#include "ocrdma_hw.h"
+
+MODULE_VERSION(OCRDMA_ROCE_DEV_VERSION);
+MODULE_DESCRIPTION("Emulex RoCE HCA Driver");
+MODULE_AUTHOR("Emulex Corporation");
+MODULE_LICENSE("GPL");
+
+static LIST_HEAD(ocrdma_dev_list);
+static DEFINE_MUTEX(ocrdma_devlist_lock);
+static DEFINE_IDR(ocrdma_dev_id);
+
+static union ib_gid ocrdma_zero_sgid;
+static int ocrdma_inet6addr_event(struct notifier_block *,
+				  unsigned long, void *);
+
+static struct notifier_block ocrdma_inet6addr_notifier = {
+	.notifier_call = ocrdma_inet6addr_event
+};
+
+int ocrdma_get_instance(void)
+{
+	int instance = 0;
+
+	/* Assign an unused number */
+	if (!idr_pre_get(&ocrdma_dev_id, GFP_KERNEL))
+		return -1;
+	if (idr_get_new(&ocrdma_dev_id, NULL, &instance))
+		return -1;
+	return instance;
+}
+
+void ocrdma_get_guid(struct ocrdma_dev *dev, u8 *guid)
+{
+	u8 mac_addr[6];
+
+	memcpy(&mac_addr[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
+	guid[0] = mac_addr[0] ^ 2;
+	guid[1] = mac_addr[1];
+	guid[2] = mac_addr[2];
+	guid[3] = 0xff;
+	guid[4] = 0xfe;
+	guid[5] = mac_addr[3];
+	guid[6] = mac_addr[4];
+	guid[7] = mac_addr[5];
+}
+
+static void ocrdma_build_sgid_mac(union ib_gid *sgid, unsigned char *mac_addr,
+				  bool is_vlan, u16 vlan_id)
+{
+	sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	sgid->raw[8] = mac_addr[0] ^ 2;
+	sgid->raw[9] = mac_addr[1];
+	sgid->raw[10] = mac_addr[2];
+	if (is_vlan) {
+		sgid->raw[11] = vlan_id >> 8;
+		sgid->raw[12] = vlan_id & 0xff;
+	} else {
+		sgid->raw[11] = 0xff;
+		sgid->raw[12] = 0xfe;
+	}
+	sgid->raw[13] = mac_addr[3];
+	sgid->raw[14] = mac_addr[4];
+	sgid->raw[15] = mac_addr[5];
+}
+
+static void ocrdma_add_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
+			    bool is_vlan, u16 vlan_id)
+{
+	int i;
+	bool found = false;
+	union ib_gid new_sgid;
+	int free_idx = OCRDMA_MAX_SGID;
+	unsigned long flags;
+
+	memset(&ocrdma_zero_sgid, 0, sizeof(union ib_gid));
+
+	ocrdma_build_sgid_mac(&new_sgid, mac_addr, is_vlan, vlan_id);
+
+	spin_lock_irqsave(&dev->sgid_lock, flags);
+	for (i = 0; i < OCRDMA_MAX_SGID; i++) {
+		if (!memcmp(&dev->sgid_tbl[i], &ocrdma_zero_sgid,
+			    sizeof(union ib_gid))) {
+			/* found free entry */
+			if (!found) {
+				free_idx = i;
+				found = true;
+				break;
+			}
+		} else if (!memcmp(&dev->sgid_tbl[i], &new_sgid,
+				   sizeof(union ib_gid))) {
+			/* entry already present, no addition is required. */
+			spin_unlock_irqrestore(&dev->sgid_lock, flags);
+			return;
+		}
+	}
+	/* if entry doesn't exist and if table has some space, add entry */
+	if (found)
+		memcpy(&dev->sgid_tbl[free_idx], &new_sgid,
+		       sizeof(union ib_gid));
+	spin_unlock_irqrestore(&dev->sgid_lock, flags);
+}
+
+static bool ocrdma_del_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
+			    bool is_vlan, u16 vlan_id)
+{
+	int found = false;
+	int i;
+	union ib_gid sgid;
+	unsigned long flags;
+
+	ocrdma_build_sgid_mac(&sgid, mac_addr, is_vlan, vlan_id);
+
+	spin_lock_irqsave(&dev->sgid_lock, flags);
+	/* first is default sgid, which cannot be deleted. */
+	for (i = 1; i < OCRDMA_MAX_SGID; i++) {
+		if (!memcmp(&dev->sgid_tbl[i], &sgid, sizeof(union ib_gid))) {
+			/* found matching entry */
+			memset(&dev->sgid_tbl[i], 0, sizeof(union ib_gid));
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&dev->sgid_lock, flags);
+	return found;
+}
+
+static void ocrdma_add_default_sgid(struct ocrdma_dev *dev)
+{
+	/* GID Index 0 - Invariant manufacturer-assigned EUI-64 */
+	union ib_gid *sgid = &dev->sgid_tbl[0];
+
+	sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	ocrdma_get_guid(dev, &sgid->raw[8]);
+}
+
+static int ocrdma_build_sgid_tbl(struct ocrdma_dev *dev)
+{
+	struct net_device *netdev, *tmp;
+	u16 vlan_id;
+	bool is_vlan;
+
+	netdev = dev->nic_info.netdev;
+
+	ocrdma_add_default_sgid(dev);
+
+	rcu_read_lock();
+	for_each_netdev_rcu(&init_net, tmp) {
+		if (netdev == tmp || vlan_dev_real_dev(tmp) == netdev) {
+			if (!netif_running(tmp) || !netif_oper_up(tmp))
+				continue;
+			if (netdev != tmp) {
+				vlan_id = vlan_dev_vlan_id(tmp);
+				is_vlan = true;
+			} else {
+				is_vlan = false;
+				vlan_id = 0;
+				tmp = netdev;
+			}
+			ocrdma_add_sgid(dev, tmp->dev_addr, is_vlan, vlan_id);
+		}
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+static int ocrdma_inet6addr_event(struct notifier_block *notifier,
+				  unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	struct net_device *event_netdev = ifa->idev->dev;
+	struct net_device *netdev = NULL;
+	struct ib_event gid_event;
+	struct ocrdma_dev *dev;
+	bool found = false;
+	bool is_vlan = false;
+	u16 vid = 0;
+
+	netdev = vlan_dev_real_dev(event_netdev);
+	if (netdev != event_netdev) {
+		is_vlan = true;
+		vid = vlan_dev_vlan_id(event_netdev);
+	}
+	mutex_lock(&ocrdma_devlist_lock);
+	list_for_each_entry(dev, &ocrdma_dev_list, entry) {
+		if (dev->nic_info.netdev == netdev) {
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&ocrdma_devlist_lock);
+
+	if (!found)
+		return NOTIFY_DONE;
+	if (!rdma_link_local_addr((struct in6_addr *)&ifa->addr))
+		return NOTIFY_DONE;
+
+	mutex_lock(&dev->dev_lock);
+	switch (event) {
+	case NETDEV_UP:
+		ocrdma_add_sgid(dev, netdev->dev_addr, is_vlan, vid);
+		break;
+	case NETDEV_DOWN:
+		found = ocrdma_del_sgid(dev, netdev->dev_addr, is_vlan, vid);
+		if (found) {
+			/* found the matching entry, notify
+			 * the consumers about it
+			 */
+			gid_event.device = &dev->ibdev;
+			gid_event.element.port_num = 1;
+			gid_event.event = IB_EVENT_GID_CHANGE;
+			ib_dispatch_event(&gid_event);
+		}
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&dev->dev_lock);
+	return NOTIFY_OK;
+}
+
+static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device,
+					      u8 port_num)
+{
+	return IB_LINK_LAYER_ETHERNET;
+}
+
+int ocrdma_register_device(struct ocrdma_dev *dev)
+{
+	strlcpy(dev->ibdev.name, "ocrdma%d", IB_DEVICE_NAME_MAX);
+	ocrdma_get_guid(dev, (u8 *)&dev->ibdev.node_guid);
+	memcpy(dev->ibdev.node_desc, OCRDMA_NODE_DESC,
+	       sizeof(OCRDMA_NODE_DESC));
+	dev->ibdev.owner = THIS_MODULE;
+	dev->ibdev.uverbs_cmd_mask =
+	    OCRDMA_UVERBS(GET_CONTEXT) |
+	    OCRDMA_UVERBS(QUERY_DEVICE) |
+	    OCRDMA_UVERBS(QUERY_PORT) |
+	    OCRDMA_UVERBS(ALLOC_PD) |
+	    OCRDMA_UVERBS(DEALLOC_PD) |
+	    OCRDMA_UVERBS(REG_MR) |
+	    OCRDMA_UVERBS(DEREG_MR) |
+	    OCRDMA_UVERBS(CREATE_COMP_CHANNEL) |
+	    OCRDMA_UVERBS(CREATE_CQ) |
+	    OCRDMA_UVERBS(RESIZE_CQ) |
+	    OCRDMA_UVERBS(DESTROY_CQ) |
+	    OCRDMA_UVERBS(REQ_NOTIFY_CQ) |
+	    OCRDMA_UVERBS(CREATE_QP) |
+	    OCRDMA_UVERBS(MODIFY_QP) |
+	    OCRDMA_UVERBS(QUERY_QP) |
+	    OCRDMA_UVERBS(DESTROY_QP) |
+	    OCRDMA_UVERBS(POLL_CQ) |
+	    OCRDMA_UVERBS(POST_SEND) |
+	    OCRDMA_UVERBS(POST_RECV);
+
+	dev->ibdev.uverbs_cmd_mask |=
+	    OCRDMA_UVERBS(CREATE_AH) |
+	     OCRDMA_UVERBS(MODIFY_AH) |
+	     OCRDMA_UVERBS(QUERY_AH) |
+	     OCRDMA_UVERBS(DESTROY_AH);
+
+	dev->ibdev.node_type = RDMA_NODE_IB_CA;
+	dev->ibdev.phys_port_cnt = 1;
+	dev->ibdev.num_comp_vectors = 1;
+
+	/* mandatory verbs. */
+	dev->ibdev.query_device = ocrdma_query_device;
+	dev->ibdev.query_port = ocrdma_query_port;
+	dev->ibdev.modify_port = ocrdma_modify_port;
+	dev->ibdev.query_gid = ocrdma_query_gid;
+	dev->ibdev.get_link_layer = ocrdma_link_layer;
+	dev->ibdev.alloc_pd = ocrdma_alloc_pd;
+	dev->ibdev.dealloc_pd = ocrdma_dealloc_pd;
+
+	dev->ibdev.create_cq = ocrdma_create_cq;
+	dev->ibdev.destroy_cq = ocrdma_destroy_cq;
+	dev->ibdev.resize_cq = ocrdma_resize_cq;
+
+	dev->ibdev.create_qp = ocrdma_create_qp;
+	dev->ibdev.modify_qp = ocrdma_modify_qp;
+	dev->ibdev.query_qp = ocrdma_query_qp;
+	dev->ibdev.destroy_qp = ocrdma_destroy_qp;
+
+	dev->ibdev.query_pkey = ocrdma_query_pkey;
+	dev->ibdev.create_ah = ocrdma_create_ah;
+	dev->ibdev.destroy_ah = ocrdma_destroy_ah;
+	dev->ibdev.query_ah = ocrdma_query_ah;
+	dev->ibdev.modify_ah = ocrdma_modify_ah;
+
+	dev->ibdev.poll_cq = ocrdma_poll_cq;
+	dev->ibdev.post_send = ocrdma_post_send;
+	dev->ibdev.post_recv = ocrdma_post_recv;
+	dev->ibdev.req_notify_cq = ocrdma_arm_cq;
+
+	dev->ibdev.get_dma_mr = ocrdma_get_dma_mr;
+	dev->ibdev.dereg_mr = ocrdma_dereg_mr;
+	dev->ibdev.reg_user_mr = ocrdma_reg_user_mr;
+
+	/* mandatory to support user space verbs consumer. */
+	dev->ibdev.alloc_ucontext = ocrdma_alloc_ucontext;
+	dev->ibdev.dealloc_ucontext = ocrdma_dealloc_ucontext;
+	dev->ibdev.mmap = ocrdma_mmap;
+	dev->ibdev.dma_device = &dev->nic_info.pdev->dev;
+
+	dev->ibdev.process_mad = ocrdma_process_mad;
+
+	if (dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) {
+		dev->ibdev.uverbs_cmd_mask |=
+		     OCRDMA_UVERBS(CREATE_SRQ) |
+		     OCRDMA_UVERBS(MODIFY_SRQ) |
+		     OCRDMA_UVERBS(QUERY_SRQ) |
+		     OCRDMA_UVERBS(DESTROY_SRQ) |
+		     OCRDMA_UVERBS(POST_SRQ_RECV);
+
+		dev->ibdev.create_srq = ocrdma_create_srq;
+		dev->ibdev.modify_srq = ocrdma_modify_srq;
+		dev->ibdev.query_srq = ocrdma_query_srq;
+		dev->ibdev.destroy_srq = ocrdma_destroy_srq;
+		dev->ibdev.post_srq_recv = ocrdma_post_srq_recv;
+	}
+	return ib_register_device(&dev->ibdev, NULL);
+}
+
+static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
+{
+	mutex_init(&dev->dev_lock);
+	dev->sgid_tbl = kzalloc(sizeof(union ib_gid) *
+				OCRDMA_MAX_SGID, GFP_KERNEL);
+	if (!dev->sgid_tbl)
+		goto alloc_err;
+	spin_lock_init(&dev->sgid_lock);
+
+	dev->cq_tbl = kzalloc(sizeof(struct ocrdma_cq *) *
+			      OCRDMA_MAX_CQ, GFP_KERNEL);
+	if (!dev->cq_tbl)
+		goto alloc_err;
+
+	if (dev->attr.max_qp) {
+		dev->qp_tbl = kzalloc(sizeof(struct ocrdma_qp *) *
+				      OCRDMA_MAX_QP, GFP_KERNEL);
+		if (!dev->qp_tbl)
+			goto alloc_err;
+	}
+	spin_lock_init(&dev->av_tbl.lock);
+	spin_lock_init(&dev->flush_q_lock);
+	return 0;
+alloc_err:
+	ocrdma_err("%s(%d) error.\n", __func__, dev->id);
+	return -ENOMEM;
+}
+
+static void ocrdma_free_resources(struct ocrdma_dev *dev)
+{
+	kfree(dev->qp_tbl);
+	kfree(dev->cq_tbl);
+	kfree(dev->sgid_tbl);
+}
+
+static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info)
+{
+	int status = 0;
+	struct ocrdma_dev *dev;
+
+	dev = (struct ocrdma_dev *)ib_alloc_device(sizeof(struct ocrdma_dev));
+	if (!dev) {
+		ocrdma_err("Unable to allocate ib device\n");
+		return NULL;
+	}
+	dev->mbx_cmd = kzalloc(sizeof(struct ocrdma_mqe_emb_cmd), GFP_KERNEL);
+	if (!dev->mbx_cmd)
+		goto idr_err;
+
+	memcpy(&dev->nic_info, dev_info, sizeof(*dev_info));
+	dev->id = ocrdma_get_instance();
+	if (dev->id < 0)
+		goto idr_err;
+
+	status = ocrdma_init_hw(dev);
+	if (status)
+		goto init_err;
+
+	status = ocrdma_alloc_resources(dev);
+	if (status)
+		goto alloc_err;
+
+	status = ocrdma_build_sgid_tbl(dev);
+	if (status)
+		goto alloc_err;
+
+	status = ocrdma_register_device(dev);
+	if (status)
+		goto alloc_err;
+
+	mutex_lock(&ocrdma_devlist_lock);
+	list_add_tail(&dev->entry, &ocrdma_dev_list);
+	mutex_unlock(&ocrdma_devlist_lock);
+	return dev;
+
+alloc_err:
+	ocrdma_free_resources(dev);
+	ocrdma_cleanup_hw(dev);
+init_err:
+	idr_remove(&ocrdma_dev_id, dev->id);
+idr_err:
+	kfree(dev->mbx_cmd);
+	ib_dealloc_device(&dev->ibdev);
+	ocrdma_err("%s() leaving. ret=%d\n", __func__, status);
+	return NULL;
+}
+
+static void ocrdma_remove(struct ocrdma_dev *dev)
+{
+	/* first unregister with stack to stop all the active traffic
+	 * of the registered clients.
+	 */
+	ib_unregister_device(&dev->ibdev);
+
+	mutex_lock(&ocrdma_devlist_lock);
+	list_del(&dev->entry);
+	mutex_unlock(&ocrdma_devlist_lock);
+
+	ocrdma_free_resources(dev);
+	ocrdma_cleanup_hw(dev);
+
+	idr_remove(&ocrdma_dev_id, dev->id);
+	kfree(dev->mbx_cmd);
+	ib_dealloc_device(&dev->ibdev);
+}
+
+static int ocrdma_open(struct ocrdma_dev *dev)
+{
+	struct ib_event port_event;
+
+	port_event.event = IB_EVENT_PORT_ACTIVE;
+	port_event.element.port_num = 1;
+	port_event.device = &dev->ibdev;
+	ib_dispatch_event(&port_event);
+	return 0;
+}
+
+static int ocrdma_close(struct ocrdma_dev *dev)
+{
+	int i;
+	struct ocrdma_qp *qp, **cur_qp;
+	struct ib_event err_event;
+	struct ib_qp_attr attrs;
+	int attr_mask = IB_QP_STATE;
+
+	attrs.qp_state = IB_QPS_ERR;
+	mutex_lock(&dev->dev_lock);
+	if (dev->qp_tbl) {
+		cur_qp = dev->qp_tbl;
+		for (i = 0; i < OCRDMA_MAX_QP; i++) {
+			qp = cur_qp[i];
+			if (qp) {
+				/* change the QP state to ERROR */
+				_ocrdma_modify_qp(&qp->ibqp, &attrs, attr_mask);
+
+				err_event.event = IB_EVENT_QP_FATAL;
+				err_event.element.qp = &qp->ibqp;
+				err_event.device = &dev->ibdev;
+				ib_dispatch_event(&err_event);
+			}
+		}
+	}
+	mutex_unlock(&dev->dev_lock);
+
+	err_event.event = IB_EVENT_PORT_ERR;
+	err_event.element.port_num = 1;
+	err_event.device = &dev->ibdev;
+	ib_dispatch_event(&err_event);
+	return 0;
+}
+
+/* event handling via NIC driver ensures that all the NIC specific
+ * initialization done before RoCE driver notifies
+ * event to stack.
+ */
+static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event)
+{
+	switch (event) {
+	case BE_DEV_UP:
+		ocrdma_open(dev);
+		break;
+	case BE_DEV_DOWN:
+		ocrdma_close(dev);
+		break;
+	};
+}
+
+struct ocrdma_driver ocrdma_drv = {
+	.name			= "ocrdma_driver",
+	.add			= ocrdma_add,
+	.remove			= ocrdma_remove,
+	.state_change_handler	= ocrdma_event_handler,
+};
+
+static int __init ocrdma_init_module(void)
+{
+	int status;
+
+	status = register_inet6addr_notifier(&ocrdma_inet6addr_notifier);
+	if (status)
+		return status;
+	status = be_roce_register_driver(&ocrdma_drv);
+	if (status)
+		unregister_inet6addr_notifier(&ocrdma_inet6addr_notifier);
+	return status;
+}
+
+static void __exit ocrdma_exit_module(void)
+{
+	be_roce_unregister_driver(&ocrdma_drv);
+	unregister_inet6addr_notifier(&ocrdma_inet6addr_notifier);
+}
+
+module_init(ocrdma_init_module);
+module_exit(ocrdma_exit_module);

drivers/infiniband/hw/ocrdma/ocrdma_verbs.h

@@ -0,0 +1,94 @@
+/*******************************************************************
+ * This file is part of the Emulex RoCE Device Driver for          *
+ * RoCE (RDMA over Converged Ethernet) adapters.                   *
+ * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ *                                                                 *
+ * 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. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ *******************************************************************/
+
+#ifndef __OCRDMA_VERBS_H__
+#define __OCRDMA_VERBS_H__
+
+#include <linux/version.h>
+int ocrdma_post_send(struct ib_qp *, struct ib_send_wr *,
+		     struct ib_send_wr **bad_wr);
+int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *,
+		     struct ib_recv_wr **bad_wr);
+
+int ocrdma_poll_cq(struct ib_cq *, int num_entries, struct ib_wc *wc);
+int ocrdma_arm_cq(struct ib_cq *, enum ib_cq_notify_flags flags);
+
+int ocrdma_query_device(struct ib_device *, struct ib_device_attr *props);
+int ocrdma_query_port(struct ib_device *, u8 port, struct ib_port_attr *props);
+int ocrdma_modify_port(struct ib_device *, u8 port, int mask,
+		       struct ib_port_modify *props);
+
+void ocrdma_get_guid(struct ocrdma_dev *, u8 *guid);
+int ocrdma_query_gid(struct ib_device *, u8 port,
+		     int index, union ib_gid *gid);
+int ocrdma_query_pkey(struct ib_device *, u8 port, u16 index, u16 *pkey);
+
+struct ib_ucontext *ocrdma_alloc_ucontext(struct ib_device *,
+					  struct ib_udata *);
+int ocrdma_dealloc_ucontext(struct ib_ucontext *);
+
+int ocrdma_mmap(struct ib_ucontext *, struct vm_area_struct *vma);
+
+struct ib_pd *ocrdma_alloc_pd(struct ib_device *,
+			      struct ib_ucontext *, struct ib_udata *);
+int ocrdma_dealloc_pd(struct ib_pd *pd);
+
+struct ib_cq *ocrdma_create_cq(struct ib_device *, int entries, int vector,
+			       struct ib_ucontext *, struct ib_udata *);
+int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
+int ocrdma_destroy_cq(struct ib_cq *);
+
+struct ib_qp *ocrdma_create_qp(struct ib_pd *,
+			       struct ib_qp_init_attr *attrs,
+			       struct ib_udata *);
+int _ocrdma_modify_qp(struct ib_qp *, struct ib_qp_attr *attr,
+		      int attr_mask);
+int ocrdma_modify_qp(struct ib_qp *, struct ib_qp_attr *attr,
+		     int attr_mask, struct ib_udata *udata);
+int ocrdma_query_qp(struct ib_qp *,
+		    struct ib_qp_attr *qp_attr,
+		    int qp_attr_mask, struct ib_qp_init_attr *);
+int ocrdma_destroy_qp(struct ib_qp *);
+
+struct ib_srq *ocrdma_create_srq(struct ib_pd *, struct ib_srq_init_attr *,
+				 struct ib_udata *);
+int ocrdma_modify_srq(struct ib_srq *, struct ib_srq_attr *,
+		      enum ib_srq_attr_mask, struct ib_udata *);
+int ocrdma_query_srq(struct ib_srq *, struct ib_srq_attr *);
+int ocrdma_destroy_srq(struct ib_srq *);
+int ocrdma_post_srq_recv(struct ib_srq *, struct ib_recv_wr *,
+			 struct ib_recv_wr **bad_recv_wr);
+
+int ocrdma_dereg_mr(struct ib_mr *);
+struct ib_mr *ocrdma_get_dma_mr(struct ib_pd *, int acc);
+struct ib_mr *ocrdma_reg_kernel_mr(struct ib_pd *,
+				   struct ib_phys_buf *buffer_list,
+				   int num_phys_buf, int acc, u64 *iova_start);
+struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *, u64 start, u64 length,
+				 u64 virt, int acc, struct ib_udata *);
+
+#endif				/* __OCRDMA_VERBS_H__ */