Resguardo inicial

linux-7.2.3/drivers/infiniband/hw/erdma/Kconfig

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config INFINIBAND_ERDMA
+	tristate "Alibaba Elastic RDMA Adapter (ERDMA) support"
+	depends on PCI_MSI && 64BIT
+	depends on INFINIBAND_ADDR_TRANS
+	depends on INFINIBAND_USER_ACCESS
+	help
+	  This is a RDMA driver for Alibaba Elastic RDMA Adapter(ERDMA),
+	  which supports RDMA features in Alibaba cloud environment.
+
+	  To compile this driver as module, choose M here. The module will be
+	  called erdma.

linux-7.2.3/drivers/infiniband/hw/erdma/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_INFINIBAND_ERDMA) := erdma.o
+
+erdma-y := erdma_cm.o erdma_main.o erdma_cmdq.o erdma_cq.o erdma_verbs.o erdma_qp.o erdma_eq.o

linux-7.2.3/drivers/infiniband/hw/erdma/erdma.h

@@ -0,0 +1,282 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#ifndef __ERDMA_H__
+#define __ERDMA_H__
+
+#include <linux/bitfield.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+#include <linux/xarray.h>
+#include <rdma/ib_verbs.h>
+
+#include "erdma_hw.h"
+
+#define DRV_MODULE_NAME "erdma"
+#define ERDMA_NODE_DESC "Elastic RDMA Adapter stack"
+
+struct erdma_eq {
+	void *qbuf;
+	dma_addr_t qbuf_dma_addr;
+
+	spinlock_t lock;
+
+	u32 depth;
+
+	u16 ci;
+	u16 rsvd;
+
+	atomic64_t event_num;
+	atomic64_t notify_num;
+
+	void __iomem *db;
+	u64 *dbrec;
+	dma_addr_t dbrec_dma;
+};
+
+struct erdma_cmdq_sq {
+	void *qbuf;
+	dma_addr_t qbuf_dma_addr;
+
+	spinlock_t lock;
+
+	u32 depth;
+	u16 ci;
+	u16 pi;
+
+	u16 wqebb_cnt;
+
+	u64 *dbrec;
+	dma_addr_t dbrec_dma;
+};
+
+struct erdma_cmdq_cq {
+	void *qbuf;
+	dma_addr_t qbuf_dma_addr;
+
+	spinlock_t lock;
+
+	u32 depth;
+	u32 ci;
+	u32 cmdsn;
+
+	u64 *dbrec;
+	dma_addr_t dbrec_dma;
+
+	atomic64_t armed_num;
+};
+
+enum {
+	ERDMA_CMD_STATUS_INIT,
+	ERDMA_CMD_STATUS_ISSUED,
+	ERDMA_CMD_STATUS_FINISHED,
+	ERDMA_CMD_STATUS_TIMEOUT
+};
+
+struct erdma_comp_wait {
+	struct completion wait_event;
+	u32 cmd_status;
+	u32 ctx_id;
+	u16 sq_pi;
+	u8 comp_status;
+	u8 rsvd;
+	u32 comp_data[4];
+};
+
+enum {
+	ERDMA_CMDQ_STATE_OK_BIT = 0,
+	ERDMA_CMDQ_STATE_TIMEOUT_BIT = 1,
+	ERDMA_CMDQ_STATE_CTX_ERR_BIT = 2,
+};
+
+#define ERDMA_CMDQ_TIMEOUT_MS 15000
+#define ERDMA_REG_ACCESS_WAIT_MS 20
+#define ERDMA_WAIT_DEV_DONE_CNT 500
+
+struct erdma_cmdq {
+	unsigned long *comp_wait_bitmap;
+	struct erdma_comp_wait *wait_pool;
+	spinlock_t lock;
+
+	struct erdma_cmdq_sq sq;
+	struct erdma_cmdq_cq cq;
+	struct erdma_eq eq;
+
+	unsigned long state;
+
+	struct semaphore credits;
+	u16 max_outstandings;
+};
+
+#define COMPROMISE_CC ERDMA_CC_CUBIC
+enum erdma_cc_alg {
+	ERDMA_CC_NEWRENO = 0,
+	ERDMA_CC_CUBIC,
+	ERDMA_CC_HPCC_RTT,
+	ERDMA_CC_HPCC_ECN,
+	ERDMA_CC_HPCC_INT,
+	ERDMA_CC_METHODS_NUM
+};
+
+struct erdma_devattr {
+	u32 fw_version;
+
+	unsigned char peer_addr[ETH_ALEN];
+	unsigned long cap_flags;
+
+	enum erdma_cc_alg cc;
+	u32 irq_num;
+
+	u32 max_qp;
+	u32 max_send_wr;
+	u32 max_recv_wr;
+	u32 max_ord;
+	u32 max_ird;
+
+	u32 max_send_sge;
+	u32 max_recv_sge;
+	u32 max_sge_rd;
+	u32 max_cq;
+	u32 max_cqe;
+	u64 max_mr_size;
+	u32 max_mr;
+	u32 max_pd;
+	u32 max_mw;
+	u32 max_gid;
+	u32 max_ah;
+	u32 local_dma_key;
+};
+
+#define ERDMA_IRQNAME_SIZE 50
+
+struct erdma_irq {
+	char name[ERDMA_IRQNAME_SIZE];
+	u32 msix_vector;
+	cpumask_t affinity_hint_mask;
+};
+
+struct erdma_eq_cb {
+	bool ready;
+	void *dev; /* All EQs use this fields to get erdma_dev struct */
+	struct erdma_irq irq;
+	struct erdma_eq eq;
+	struct tasklet_struct tasklet;
+};
+
+struct erdma_resource_cb {
+	unsigned long *bitmap;
+	spinlock_t lock;
+	u32 next_alloc_idx;
+	u32 max_cap;
+};
+
+enum {
+	ERDMA_RES_TYPE_PD = 0,
+	ERDMA_RES_TYPE_STAG_IDX = 1,
+	ERDMA_RES_TYPE_AH = 2,
+	ERDMA_RES_CNT = 3,
+};
+
+struct erdma_dev {
+	struct ib_device ibdev;
+	struct net_device *netdev;
+	struct pci_dev *pdev;
+	struct notifier_block netdev_nb;
+	struct workqueue_struct *reflush_wq;
+
+	resource_size_t func_bar_addr;
+	resource_size_t func_bar_len;
+	u8 __iomem *func_bar;
+
+	struct erdma_devattr attrs;
+	u32 mtu;
+
+	/* cmdq and aeq use the same msix vector */
+	struct erdma_irq comm_irq;
+	struct erdma_cmdq cmdq;
+	struct erdma_eq aeq;
+	struct erdma_eq_cb ceqs[ERDMA_NUM_MSIX_VEC - 1];
+
+	spinlock_t lock;
+	struct erdma_resource_cb res_cb[ERDMA_RES_CNT];
+	struct xarray qp_xa;
+	struct xarray cq_xa;
+
+	u32 next_alloc_qpn;
+	u32 next_alloc_cqn;
+
+	atomic_t num_ctx;
+	struct list_head cep_list;
+
+	struct dma_pool *db_pool;
+	struct dma_pool *resp_pool;
+	enum erdma_proto_type proto;
+};
+
+static inline void *get_queue_entry(void *qbuf, u32 idx, u32 depth, u32 shift)
+{
+	idx &= (depth - 1);
+
+	return qbuf + (idx << shift);
+}
+
+static inline struct erdma_dev *to_edev(struct ib_device *ibdev)
+{
+	return container_of(ibdev, struct erdma_dev, ibdev);
+}
+
+static inline u32 erdma_reg_read32(struct erdma_dev *dev, u32 reg)
+{
+	return readl(dev->func_bar + reg);
+}
+
+static inline u64 erdma_reg_read64(struct erdma_dev *dev, u32 reg)
+{
+	return readq(dev->func_bar + reg);
+}
+
+static inline void erdma_reg_write32(struct erdma_dev *dev, u32 reg, u32 value)
+{
+	writel(value, dev->func_bar + reg);
+}
+
+static inline void erdma_reg_write64(struct erdma_dev *dev, u32 reg, u64 value)
+{
+	writeq(value, dev->func_bar + reg);
+}
+
+static inline u32 erdma_reg_read32_filed(struct erdma_dev *dev, u32 reg,
+					 u32 filed_mask)
+{
+	u32 val = erdma_reg_read32(dev, reg);
+
+	return FIELD_GET(filed_mask, val);
+}
+
+#define ERDMA_GET(val, name) FIELD_GET(ERDMA_CMD_##name##_MASK, val)
+
+int erdma_cmdq_init(struct erdma_dev *dev);
+void erdma_finish_cmdq_init(struct erdma_dev *dev);
+void erdma_cmdq_destroy(struct erdma_dev *dev);
+
+void erdma_cmdq_build_reqhdr(u64 *hdr, u32 mod, u32 op);
+int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size,
+			u64 *resp0, u64 *resp1, bool sleepable);
+void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq);
+
+int erdma_ceqs_init(struct erdma_dev *dev);
+void erdma_ceqs_uninit(struct erdma_dev *dev);
+void notify_eq(struct erdma_eq *eq);
+void *get_next_valid_eqe(struct erdma_eq *eq);
+
+int erdma_aeq_init(struct erdma_dev *dev);
+int erdma_eq_common_init(struct erdma_dev *dev, struct erdma_eq *eq, u32 depth);
+void erdma_eq_destroy(struct erdma_dev *dev, struct erdma_eq *eq);
+
+void erdma_aeq_event_handler(struct erdma_dev *dev);
+void erdma_ceq_completion_handler(struct erdma_eq_cb *ceq_cb);
+
+#endif

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_cm.h

@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+/* Authors: Bernard Metzler <bmt@zurich.ibm.com> */
+/*          Greg Joyce <greg@opengridcomputing.com> */
+/* Copyright (c) 2008-2019, IBM Corporation */
+/* Copyright (c) 2017, Open Grid Computing, Inc. */
+
+#ifndef __ERDMA_CM_H__
+#define __ERDMA_CM_H__
+
+#include <linux/tcp.h>
+#include <net/sock.h>
+#include <rdma/iw_cm.h>
+
+/* iWarp MPA protocol defs */
+#define MPA_REVISION_EXT_1 129
+#define MPA_MAX_PRIVDATA RDMA_MAX_PRIVATE_DATA
+#define MPA_KEY_REQ "MPA ID Req Frame"
+#define MPA_KEY_REP "MPA ID Rep Frame"
+#define MPA_KEY_SIZE 16
+#define MPA_DEFAULT_HDR_LEN 28
+
+struct mpa_rr_params {
+	__be16 bits;
+	__be16 pd_len;
+};
+
+/*
+ * MPA request/response Hdr bits & fields
+ */
+enum {
+	MPA_RR_FLAG_MARKERS = cpu_to_be16(0x8000),
+	MPA_RR_FLAG_CRC = cpu_to_be16(0x4000),
+	MPA_RR_FLAG_REJECT = cpu_to_be16(0x2000),
+	MPA_RR_RESERVED = cpu_to_be16(0x1f00),
+	MPA_RR_MASK_REVISION = cpu_to_be16(0x00ff)
+};
+
+/*
+ * MPA request/reply header
+ */
+struct mpa_rr {
+	u8 key[16];
+	struct mpa_rr_params params;
+};
+
+struct erdma_mpa_ext {
+	__be32 cookie;
+	__be32 bits;
+};
+
+enum {
+	MPA_EXT_FLAG_CC = cpu_to_be32(0x0000000f),
+};
+
+struct erdma_mpa_info {
+	struct mpa_rr hdr; /* peer mpa hdr in host byte order */
+	struct erdma_mpa_ext ext_data;
+	char *pdata;
+	int bytes_rcvd;
+};
+
+struct erdma_sk_upcalls {
+	void (*sk_state_change)(struct sock *sk);
+	void (*sk_data_ready)(struct sock *sk, int bytes);
+	void (*sk_error_report)(struct sock *sk);
+};
+
+struct erdma_dev;
+
+enum erdma_cep_state {
+	ERDMA_EPSTATE_IDLE = 1,
+	ERDMA_EPSTATE_LISTENING,
+	ERDMA_EPSTATE_CONNECTING,
+	ERDMA_EPSTATE_AWAIT_MPAREQ,
+	ERDMA_EPSTATE_RECVD_MPAREQ,
+	ERDMA_EPSTATE_AWAIT_MPAREP,
+	ERDMA_EPSTATE_RDMA_MODE,
+	ERDMA_EPSTATE_CLOSED
+};
+
+struct erdma_cep {
+	struct iw_cm_id *cm_id;
+	struct erdma_dev *dev;
+	struct list_head devq;
+	spinlock_t lock;
+	struct kref ref;
+	int in_use;
+	wait_queue_head_t waitq;
+	enum erdma_cep_state state;
+
+	struct list_head listenq;
+	struct erdma_cep *listen_cep;
+
+	struct erdma_qp *qp;
+	struct socket *sock;
+
+	struct erdma_cm_work *mpa_timer;
+	struct list_head work_freelist;
+
+	struct erdma_mpa_info mpa;
+	int ord;
+	int ird;
+
+	int pd_len;
+	/* hold user's private data. */
+	void *private_data;
+
+	/* Saved upcalls of socket llp.sock */
+	void (*sk_state_change)(struct sock *sk);
+	void (*sk_data_ready)(struct sock *sk);
+	void (*sk_error_report)(struct sock *sk);
+};
+
+#define MPAREQ_TIMEOUT (HZ * 20)
+#define MPAREP_TIMEOUT (HZ * 10)
+#define CONNECT_TIMEOUT (HZ * 10)
+
+enum erdma_work_type {
+	ERDMA_CM_WORK_ACCEPT = 1,
+	ERDMA_CM_WORK_READ_MPAHDR,
+	ERDMA_CM_WORK_CLOSE_LLP, /* close socket */
+	ERDMA_CM_WORK_PEER_CLOSE, /* socket indicated peer close */
+	ERDMA_CM_WORK_MPATIMEOUT,
+	ERDMA_CM_WORK_CONNECTED,
+	ERDMA_CM_WORK_CONNECTTIMEOUT
+};
+
+struct erdma_cm_work {
+	struct delayed_work work;
+	struct list_head list;
+	enum erdma_work_type type;
+	struct erdma_cep *cep;
+};
+
+#define to_sockaddr_in(a) (*(struct sockaddr_in *)(&(a)))
+
+static inline int getname_peer(struct socket *s, struct sockaddr_storage *a)
+{
+	return s->ops->getname(s, (struct sockaddr *)a, 1);
+}
+
+static inline int getname_local(struct socket *s, struct sockaddr_storage *a)
+{
+	return s->ops->getname(s, (struct sockaddr *)a, 0);
+}
+
+int erdma_connect(struct iw_cm_id *id, struct iw_cm_conn_param *param);
+int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *param);
+int erdma_reject(struct iw_cm_id *id, const void *pdata, u8 plen);
+int erdma_create_listen(struct iw_cm_id *id, int backlog);
+int erdma_destroy_listen(struct iw_cm_id *id);
+
+void erdma_cep_get(struct erdma_cep *ceq);
+void erdma_cep_put(struct erdma_cep *ceq);
+int erdma_cm_queue_work(struct erdma_cep *ceq, enum erdma_work_type type);
+
+int erdma_cm_init(void);
+void erdma_cm_exit(void);
+
+#define sk_to_cep(sk) ((struct erdma_cep *)((sk)->sk_user_data))
+
+#endif

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_cmdq.c

@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#include "erdma.h"
+
+static void arm_cmdq_cq(struct erdma_cmdq *cmdq)
+{
+	struct erdma_dev *dev = container_of(cmdq, struct erdma_dev, cmdq);
+	u64 db_data = FIELD_PREP(ERDMA_CQDB_CI_MASK, cmdq->cq.ci) |
+		      FIELD_PREP(ERDMA_CQDB_ARM_MASK, 1) |
+		      FIELD_PREP(ERDMA_CQDB_CMDSN_MASK, cmdq->cq.cmdsn) |
+		      FIELD_PREP(ERDMA_CQDB_IDX_MASK, cmdq->cq.cmdsn);
+
+	*cmdq->cq.dbrec = db_data;
+	writeq(db_data, dev->func_bar + ERDMA_CMDQ_CQDB_REG);
+
+	atomic64_inc(&cmdq->cq.armed_num);
+}
+
+static void kick_cmdq_db(struct erdma_cmdq *cmdq)
+{
+	struct erdma_dev *dev = container_of(cmdq, struct erdma_dev, cmdq);
+	u64 db_data = FIELD_PREP(ERDMA_CMD_HDR_WQEBB_INDEX_MASK, cmdq->sq.pi);
+
+	*cmdq->sq.dbrec = db_data;
+	writeq(db_data, dev->func_bar + ERDMA_CMDQ_SQDB_REG);
+}
+
+static struct erdma_comp_wait *get_comp_wait(struct erdma_cmdq *cmdq)
+{
+	int comp_idx;
+
+	spin_lock(&cmdq->lock);
+	comp_idx = find_first_zero_bit(cmdq->comp_wait_bitmap,
+				       cmdq->max_outstandings);
+	if (comp_idx == cmdq->max_outstandings) {
+		spin_unlock(&cmdq->lock);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	__set_bit(comp_idx, cmdq->comp_wait_bitmap);
+	spin_unlock(&cmdq->lock);
+
+	return &cmdq->wait_pool[comp_idx];
+}
+
+static void put_comp_wait(struct erdma_cmdq *cmdq,
+			  struct erdma_comp_wait *comp_wait)
+{
+	int used;
+
+	cmdq->wait_pool[comp_wait->ctx_id].cmd_status = ERDMA_CMD_STATUS_INIT;
+	spin_lock(&cmdq->lock);
+	used = __test_and_clear_bit(comp_wait->ctx_id, cmdq->comp_wait_bitmap);
+	spin_unlock(&cmdq->lock);
+
+	WARN_ON(!used);
+}
+
+static int erdma_cmdq_wait_res_init(struct erdma_dev *dev,
+				    struct erdma_cmdq *cmdq)
+{
+	int i;
+
+	cmdq->wait_pool =
+		devm_kcalloc(&dev->pdev->dev, cmdq->max_outstandings,
+			     sizeof(struct erdma_comp_wait), GFP_KERNEL);
+	if (!cmdq->wait_pool)
+		return -ENOMEM;
+
+	spin_lock_init(&cmdq->lock);
+	cmdq->comp_wait_bitmap = devm_bitmap_zalloc(
+		&dev->pdev->dev, cmdq->max_outstandings, GFP_KERNEL);
+	if (!cmdq->comp_wait_bitmap)
+		return -ENOMEM;
+
+	for (i = 0; i < cmdq->max_outstandings; i++) {
+		init_completion(&cmdq->wait_pool[i].wait_event);
+		cmdq->wait_pool[i].ctx_id = i;
+	}
+
+	return 0;
+}
+
+static int erdma_cmdq_sq_init(struct erdma_dev *dev)
+{
+	struct erdma_cmdq *cmdq = &dev->cmdq;
+	struct erdma_cmdq_sq *sq = &cmdq->sq;
+
+	sq->wqebb_cnt = SQEBB_COUNT(ERDMA_CMDQ_SQE_SIZE);
+	sq->depth = cmdq->max_outstandings * sq->wqebb_cnt;
+
+	sq->qbuf = dma_alloc_coherent(&dev->pdev->dev, sq->depth << SQEBB_SHIFT,
+				      &sq->qbuf_dma_addr, GFP_KERNEL);
+	if (!sq->qbuf)
+		return -ENOMEM;
+
+	sq->dbrec = dma_pool_zalloc(dev->db_pool, GFP_KERNEL, &sq->dbrec_dma);
+	if (!sq->dbrec)
+		goto err_out;
+
+	spin_lock_init(&sq->lock);
+
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_SQ_ADDR_H_REG,
+			  upper_32_bits(sq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_SQ_ADDR_L_REG,
+			  lower_32_bits(sq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_DEPTH_REG, sq->depth);
+	erdma_reg_write64(dev, ERDMA_CMDQ_SQ_DB_HOST_ADDR_REG, sq->dbrec_dma);
+
+	return 0;
+
+err_out:
+	dma_free_coherent(&dev->pdev->dev, sq->depth << SQEBB_SHIFT,
+			  sq->qbuf, sq->qbuf_dma_addr);
+
+	return -ENOMEM;
+}
+
+static int erdma_cmdq_cq_init(struct erdma_dev *dev)
+{
+	struct erdma_cmdq *cmdq = &dev->cmdq;
+	struct erdma_cmdq_cq *cq = &cmdq->cq;
+
+	cq->depth = cmdq->sq.depth;
+	cq->qbuf = dma_alloc_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT,
+				      &cq->qbuf_dma_addr, GFP_KERNEL);
+	if (!cq->qbuf)
+		return -ENOMEM;
+
+	spin_lock_init(&cq->lock);
+
+	cq->dbrec = dma_pool_zalloc(dev->db_pool, GFP_KERNEL, &cq->dbrec_dma);
+	if (!cq->dbrec)
+		goto err_out;
+
+	atomic64_set(&cq->armed_num, 0);
+
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_CQ_ADDR_H_REG,
+			  upper_32_bits(cq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_CQ_ADDR_L_REG,
+			  lower_32_bits(cq->qbuf_dma_addr));
+	erdma_reg_write64(dev, ERDMA_CMDQ_CQ_DB_HOST_ADDR_REG, cq->dbrec_dma);
+
+	return 0;
+
+err_out:
+	dma_free_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT, cq->qbuf,
+			  cq->qbuf_dma_addr);
+
+	return -ENOMEM;
+}
+
+static int erdma_cmdq_eq_init(struct erdma_dev *dev)
+{
+	struct erdma_cmdq *cmdq = &dev->cmdq;
+	struct erdma_eq *eq = &cmdq->eq;
+	int ret;
+
+	ret = erdma_eq_common_init(dev, eq, cmdq->max_outstandings);
+	if (ret)
+		return ret;
+
+	eq->db = dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG;
+
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_ADDR_H_REG,
+			  upper_32_bits(eq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_ADDR_L_REG,
+			  lower_32_bits(eq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_DEPTH_REG, eq->depth);
+	erdma_reg_write64(dev, ERDMA_CMDQ_EQ_DB_HOST_ADDR_REG, eq->dbrec_dma);
+
+	return 0;
+}
+
+int erdma_cmdq_init(struct erdma_dev *dev)
+{
+	struct erdma_cmdq *cmdq = &dev->cmdq;
+	int err;
+
+	cmdq->max_outstandings = ERDMA_CMDQ_MAX_OUTSTANDING;
+
+	sema_init(&cmdq->credits, cmdq->max_outstandings);
+
+	err = erdma_cmdq_wait_res_init(dev, cmdq);
+	if (err)
+		return err;
+
+	err = erdma_cmdq_sq_init(dev);
+	if (err)
+		return err;
+
+	err = erdma_cmdq_cq_init(dev);
+	if (err)
+		goto err_destroy_sq;
+
+	err = erdma_cmdq_eq_init(dev);
+	if (err)
+		goto err_destroy_cq;
+
+	set_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state);
+
+	return 0;
+
+err_destroy_cq:
+	dma_free_coherent(&dev->pdev->dev, cmdq->cq.depth << CQE_SHIFT,
+			  cmdq->cq.qbuf, cmdq->cq.qbuf_dma_addr);
+
+	dma_pool_free(dev->db_pool, cmdq->cq.dbrec, cmdq->cq.dbrec_dma);
+
+err_destroy_sq:
+	dma_free_coherent(&dev->pdev->dev, cmdq->sq.depth << SQEBB_SHIFT,
+			  cmdq->sq.qbuf, cmdq->sq.qbuf_dma_addr);
+
+	dma_pool_free(dev->db_pool, cmdq->sq.dbrec, cmdq->sq.dbrec_dma);
+
+	return err;
+}
+
+void erdma_finish_cmdq_init(struct erdma_dev *dev)
+{
+	arm_cmdq_cq(&dev->cmdq);
+}
+
+void erdma_cmdq_destroy(struct erdma_dev *dev)
+{
+	struct erdma_cmdq *cmdq = &dev->cmdq;
+
+	clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state);
+
+	erdma_eq_destroy(dev, &cmdq->eq);
+
+	dma_free_coherent(&dev->pdev->dev, cmdq->sq.depth << SQEBB_SHIFT,
+			  cmdq->sq.qbuf, cmdq->sq.qbuf_dma_addr);
+
+	dma_pool_free(dev->db_pool, cmdq->sq.dbrec, cmdq->sq.dbrec_dma);
+
+	dma_free_coherent(&dev->pdev->dev, cmdq->cq.depth << CQE_SHIFT,
+			  cmdq->cq.qbuf, cmdq->cq.qbuf_dma_addr);
+
+	dma_pool_free(dev->db_pool, cmdq->cq.dbrec, cmdq->cq.dbrec_dma);
+}
+
+static void *get_next_valid_cmdq_cqe(struct erdma_cmdq *cmdq)
+{
+	__be32 *cqe = get_queue_entry(cmdq->cq.qbuf, cmdq->cq.ci,
+				      cmdq->cq.depth, CQE_SHIFT);
+	u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK,
+			      be32_to_cpu(READ_ONCE(*cqe)));
+
+	return owner ^ !!(cmdq->cq.ci & cmdq->cq.depth) ? cqe : NULL;
+}
+
+static void push_cmdq_sqe(struct erdma_cmdq *cmdq, u64 *req, size_t req_len,
+			  struct erdma_comp_wait *comp_wait)
+{
+	__le64 *wqe;
+	u64 hdr = *req;
+
+	comp_wait->cmd_status = ERDMA_CMD_STATUS_ISSUED;
+	reinit_completion(&comp_wait->wait_event);
+	comp_wait->sq_pi = cmdq->sq.pi;
+
+	wqe = get_queue_entry(cmdq->sq.qbuf, cmdq->sq.pi, cmdq->sq.depth,
+			      SQEBB_SHIFT);
+	memcpy(wqe, req, req_len);
+
+	cmdq->sq.pi += cmdq->sq.wqebb_cnt;
+	hdr |= FIELD_PREP(ERDMA_CMD_HDR_WQEBB_INDEX_MASK, cmdq->sq.pi) |
+	       FIELD_PREP(ERDMA_CMD_HDR_CONTEXT_COOKIE_MASK,
+			  comp_wait->ctx_id) |
+	       FIELD_PREP(ERDMA_CMD_HDR_WQEBB_CNT_MASK, cmdq->sq.wqebb_cnt - 1);
+	*wqe = cpu_to_le64(hdr);
+
+	kick_cmdq_db(cmdq);
+}
+
+static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq)
+{
+	struct erdma_comp_wait *comp_wait;
+	u32 hdr0, sqe_idx;
+	__be32 *cqe;
+	u16 ctx_id;
+	u64 *sqe;
+
+	cqe = get_next_valid_cmdq_cqe(cmdq);
+	if (!cqe)
+		return -EAGAIN;
+
+	cmdq->cq.ci++;
+
+	dma_rmb();
+	hdr0 = be32_to_cpu(*cqe);
+	sqe_idx = be32_to_cpu(*(cqe + 1));
+
+	sqe = get_queue_entry(cmdq->sq.qbuf, sqe_idx, cmdq->sq.depth,
+			      SQEBB_SHIFT);
+	ctx_id = FIELD_GET(ERDMA_CMD_HDR_CONTEXT_COOKIE_MASK, *sqe);
+	comp_wait = &cmdq->wait_pool[ctx_id];
+	if (comp_wait->cmd_status != ERDMA_CMD_STATUS_ISSUED)
+		return -EIO;
+
+	comp_wait->cmd_status = ERDMA_CMD_STATUS_FINISHED;
+	comp_wait->comp_status = FIELD_GET(ERDMA_CQE_HDR_SYNDROME_MASK, hdr0);
+	cmdq->sq.ci += cmdq->sq.wqebb_cnt;
+	/* Copy 16B comp data after cqe hdr to outer */
+	be32_to_cpu_array(comp_wait->comp_data, cqe + 2, 4);
+
+	complete(&comp_wait->wait_event);
+
+	return 0;
+}
+
+static void erdma_polling_cmd_completions(struct erdma_cmdq *cmdq)
+{
+	unsigned long flags;
+	u16 comp_num;
+
+	spin_lock_irqsave(&cmdq->cq.lock, flags);
+
+	/* We must have less than # of max_outstandings
+	 * completions at one time.
+	 */
+	for (comp_num = 0; comp_num < cmdq->max_outstandings; comp_num++)
+		if (erdma_poll_single_cmd_completion(cmdq))
+			break;
+
+	spin_unlock_irqrestore(&cmdq->cq.lock, flags);
+}
+
+void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq)
+{
+	int got_event = 0;
+
+	if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state))
+		return;
+
+	while (get_next_valid_eqe(&cmdq->eq)) {
+		cmdq->eq.ci++;
+		got_event++;
+	}
+
+	if (got_event) {
+		cmdq->cq.cmdsn++;
+		erdma_polling_cmd_completions(cmdq);
+		arm_cmdq_cq(cmdq);
+	}
+
+	notify_eq(&cmdq->eq);
+}
+
+static int erdma_poll_cmd_completion(struct erdma_comp_wait *comp_ctx,
+				     struct erdma_cmdq *cmdq, u32 timeout)
+{
+	unsigned long comp_timeout = jiffies + msecs_to_jiffies(timeout);
+
+	while (1) {
+		erdma_polling_cmd_completions(cmdq);
+		if (comp_ctx->cmd_status != ERDMA_CMD_STATUS_ISSUED)
+			break;
+
+		if (time_is_before_jiffies(comp_timeout))
+			return -ETIME;
+
+		udelay(20);
+	}
+
+	return 0;
+}
+
+static int erdma_wait_cmd_completion(struct erdma_comp_wait *comp_ctx,
+				     struct erdma_cmdq *cmdq, u32 timeout)
+{
+	unsigned long flags = 0;
+
+	wait_for_completion_timeout(&comp_ctx->wait_event,
+				    msecs_to_jiffies(timeout));
+
+	if (unlikely(comp_ctx->cmd_status != ERDMA_CMD_STATUS_FINISHED)) {
+		spin_lock_irqsave(&cmdq->cq.lock, flags);
+		comp_ctx->cmd_status = ERDMA_CMD_STATUS_TIMEOUT;
+		spin_unlock_irqrestore(&cmdq->cq.lock, flags);
+		return -ETIME;
+	}
+
+	return 0;
+}
+
+void erdma_cmdq_build_reqhdr(u64 *hdr, u32 mod, u32 op)
+{
+	*hdr = FIELD_PREP(ERDMA_CMD_HDR_SUB_MOD_MASK, mod) |
+	       FIELD_PREP(ERDMA_CMD_HDR_OPCODE_MASK, op);
+}
+
+int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size,
+			u64 *resp0, u64 *resp1, bool sleepable)
+{
+	struct erdma_comp_wait *comp_wait;
+	int ret;
+
+	if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state))
+		return -ENODEV;
+
+	if (!sleepable) {
+		while (down_trylock(&cmdq->credits))
+			;
+	} else {
+		down(&cmdq->credits);
+	}
+
+	comp_wait = get_comp_wait(cmdq);
+	if (IS_ERR(comp_wait)) {
+		clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state);
+		set_bit(ERDMA_CMDQ_STATE_CTX_ERR_BIT, &cmdq->state);
+		up(&cmdq->credits);
+		return PTR_ERR(comp_wait);
+	}
+
+	spin_lock(&cmdq->sq.lock);
+	push_cmdq_sqe(cmdq, req, req_size, comp_wait);
+	spin_unlock(&cmdq->sq.lock);
+
+	if (sleepable)
+		ret = erdma_wait_cmd_completion(comp_wait, cmdq,
+						ERDMA_CMDQ_TIMEOUT_MS);
+	else
+		ret = erdma_poll_cmd_completion(comp_wait, cmdq,
+						ERDMA_CMDQ_TIMEOUT_MS);
+
+	if (ret) {
+		set_bit(ERDMA_CMDQ_STATE_TIMEOUT_BIT, &cmdq->state);
+		clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state);
+		goto out;
+	}
+
+	if (comp_wait->comp_status)
+		ret = -EIO;
+
+	if (resp0 && resp1) {
+		*resp0 = *((u64 *)&comp_wait->comp_data[0]);
+		*resp1 = *((u64 *)&comp_wait->comp_data[2]);
+	}
+	put_comp_wait(cmdq, comp_wait);
+
+out:
+	up(&cmdq->credits);
+
+	return ret;
+}

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_cq.c

@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#include "erdma_verbs.h"
+
+static void *get_next_valid_cqe(struct erdma_cq *cq)
+{
+	__be32 *cqe = get_queue_entry(cq->kern_cq.qbuf, cq->kern_cq.ci,
+				      cq->depth, CQE_SHIFT);
+	u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK,
+			      be32_to_cpu(READ_ONCE(*cqe)));
+
+	return owner ^ !!(cq->kern_cq.ci & cq->depth) ? cqe : NULL;
+}
+
+static void notify_cq(struct erdma_cq *cq, u8 solcitied)
+{
+	u64 db_data =
+		FIELD_PREP(ERDMA_CQDB_IDX_MASK, (cq->kern_cq.notify_cnt)) |
+		FIELD_PREP(ERDMA_CQDB_CQN_MASK, cq->cqn) |
+		FIELD_PREP(ERDMA_CQDB_ARM_MASK, 1) |
+		FIELD_PREP(ERDMA_CQDB_SOL_MASK, solcitied) |
+		FIELD_PREP(ERDMA_CQDB_CMDSN_MASK, cq->kern_cq.cmdsn) |
+		FIELD_PREP(ERDMA_CQDB_CI_MASK, cq->kern_cq.ci);
+
+	*cq->kern_cq.dbrec = db_data;
+	writeq(db_data, cq->kern_cq.db);
+}
+
+int erdma_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
+{
+	struct erdma_cq *cq = to_ecq(ibcq);
+	unsigned long irq_flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&cq->kern_cq.lock, irq_flags);
+
+	notify_cq(cq, (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED);
+
+	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && get_next_valid_cqe(cq))
+		ret = 1;
+
+	cq->kern_cq.notify_cnt++;
+
+	spin_unlock_irqrestore(&cq->kern_cq.lock, irq_flags);
+
+	return ret;
+}
+
+static const enum ib_wc_opcode wc_mapping_table[ERDMA_NUM_OPCODES] = {
+	[ERDMA_OP_WRITE] = IB_WC_RDMA_WRITE,
+	[ERDMA_OP_READ] = IB_WC_RDMA_READ,
+	[ERDMA_OP_SEND] = IB_WC_SEND,
+	[ERDMA_OP_SEND_WITH_IMM] = IB_WC_SEND,
+	[ERDMA_OP_RECEIVE] = IB_WC_RECV,
+	[ERDMA_OP_RECV_IMM] = IB_WC_RECV_RDMA_WITH_IMM,
+	[ERDMA_OP_RECV_INV] = IB_WC_RECV,
+	[ERDMA_OP_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE,
+	[ERDMA_OP_RSP_SEND_IMM] = IB_WC_RECV,
+	[ERDMA_OP_SEND_WITH_INV] = IB_WC_SEND,
+	[ERDMA_OP_REG_MR] = IB_WC_REG_MR,
+	[ERDMA_OP_LOCAL_INV] = IB_WC_LOCAL_INV,
+	[ERDMA_OP_READ_WITH_INV] = IB_WC_RDMA_READ,
+	[ERDMA_OP_ATOMIC_CAS] = IB_WC_COMP_SWAP,
+	[ERDMA_OP_ATOMIC_FAA] = IB_WC_FETCH_ADD,
+};
+
+static const struct {
+	enum erdma_wc_status erdma;
+	enum ib_wc_status base;
+	enum erdma_vendor_err vendor;
+} map_cqe_status[ERDMA_NUM_WC_STATUS] = {
+	{ ERDMA_WC_SUCCESS, IB_WC_SUCCESS, ERDMA_WC_VENDOR_NO_ERR },
+	{ ERDMA_WC_GENERAL_ERR, IB_WC_GENERAL_ERR, ERDMA_WC_VENDOR_NO_ERR },
+	{ ERDMA_WC_RECV_WQE_FORMAT_ERR, IB_WC_GENERAL_ERR,
+	  ERDMA_WC_VENDOR_INVALID_RQE },
+	{ ERDMA_WC_RECV_STAG_INVALID_ERR, IB_WC_REM_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_RQE_INVALID_STAG },
+	{ ERDMA_WC_RECV_ADDR_VIOLATION_ERR, IB_WC_REM_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_RQE_ADDR_VIOLATION },
+	{ ERDMA_WC_RECV_RIGHT_VIOLATION_ERR, IB_WC_REM_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_RQE_ACCESS_RIGHT_ERR },
+	{ ERDMA_WC_RECV_PDID_ERR, IB_WC_REM_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_RQE_INVALID_PD },
+	{ ERDMA_WC_RECV_WARRPING_ERR, IB_WC_REM_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_RQE_WRAP_ERR },
+	{ ERDMA_WC_SEND_WQE_FORMAT_ERR, IB_WC_LOC_QP_OP_ERR,
+	  ERDMA_WC_VENDOR_INVALID_SQE },
+	{ ERDMA_WC_SEND_WQE_ORD_EXCEED, IB_WC_GENERAL_ERR,
+	  ERDMA_WC_VENDOR_ZERO_ORD },
+	{ ERDMA_WC_SEND_STAG_INVALID_ERR, IB_WC_LOC_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_SQE_INVALID_STAG },
+	{ ERDMA_WC_SEND_ADDR_VIOLATION_ERR, IB_WC_LOC_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_SQE_ADDR_VIOLATION },
+	{ ERDMA_WC_SEND_RIGHT_VIOLATION_ERR, IB_WC_LOC_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_SQE_ACCESS_ERR },
+	{ ERDMA_WC_SEND_PDID_ERR, IB_WC_LOC_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_SQE_INVALID_PD },
+	{ ERDMA_WC_SEND_WARRPING_ERR, IB_WC_LOC_ACCESS_ERR,
+	  ERDMA_WC_VENDOR_SQE_WARP_ERR },
+	{ ERDMA_WC_FLUSH_ERR, IB_WC_WR_FLUSH_ERR, ERDMA_WC_VENDOR_NO_ERR },
+	{ ERDMA_WC_RETRY_EXC_ERR, IB_WC_RETRY_EXC_ERR, ERDMA_WC_VENDOR_NO_ERR },
+};
+
+static void erdma_process_ud_cqe(struct erdma_cqe *cqe, struct ib_wc *wc)
+{
+	u32 ud_info;
+
+	wc->wc_flags |= (IB_WC_GRH | IB_WC_WITH_NETWORK_HDR_TYPE);
+	ud_info = be32_to_cpu(cqe->ud.info);
+	wc->network_hdr_type = FIELD_GET(ERDMA_CQE_NTYPE_MASK, ud_info);
+	if (wc->network_hdr_type == ERDMA_NETWORK_TYPE_IPV4)
+		wc->network_hdr_type = RDMA_NETWORK_IPV4;
+	else
+		wc->network_hdr_type = RDMA_NETWORK_IPV6;
+	wc->src_qp = FIELD_GET(ERDMA_CQE_SQPN_MASK, ud_info);
+	wc->sl = FIELD_GET(ERDMA_CQE_SL_MASK, ud_info);
+	wc->pkey_index = 0;
+}
+
+#define ERDMA_POLLCQ_NO_QP 1
+
+static int erdma_poll_one_cqe(struct erdma_cq *cq, struct ib_wc *wc)
+{
+	struct erdma_dev *dev = to_edev(cq->ibcq.device);
+	u8 opcode, syndrome, qtype;
+	struct erdma_kqp *kern_qp;
+	struct erdma_cqe *cqe;
+	struct erdma_qp *qp;
+	u16 wqe_idx, depth;
+	u32 qpn, cqe_hdr;
+	u64 *id_table;
+	u64 *wqe_hdr;
+
+	cqe = get_next_valid_cqe(cq);
+	if (!cqe)
+		return -EAGAIN;
+
+	cq->kern_cq.ci++;
+
+	/* cqbuf should be ready when we poll */
+	dma_rmb();
+
+	qpn = be32_to_cpu(cqe->qpn);
+	wqe_idx = be32_to_cpu(cqe->qe_idx);
+	cqe_hdr = be32_to_cpu(cqe->hdr);
+
+	qp = find_qp_by_qpn(dev, qpn);
+	if (!qp)
+		return ERDMA_POLLCQ_NO_QP;
+
+	kern_qp = &qp->kern_qp;
+
+	qtype = FIELD_GET(ERDMA_CQE_HDR_QTYPE_MASK, cqe_hdr);
+	syndrome = FIELD_GET(ERDMA_CQE_HDR_SYNDROME_MASK, cqe_hdr);
+	opcode = FIELD_GET(ERDMA_CQE_HDR_OPCODE_MASK, cqe_hdr);
+
+	if (qtype == ERDMA_CQE_QTYPE_SQ) {
+		id_table = kern_qp->swr_tbl;
+		depth = qp->attrs.sq_size;
+		wqe_hdr = get_queue_entry(qp->kern_qp.sq_buf, wqe_idx,
+					  qp->attrs.sq_size, SQEBB_SHIFT);
+		kern_qp->sq_ci =
+			FIELD_GET(ERDMA_SQE_HDR_WQEBB_CNT_MASK, *wqe_hdr) +
+			wqe_idx + 1;
+	} else {
+		id_table = kern_qp->rwr_tbl;
+		depth = qp->attrs.rq_size;
+	}
+	wc->wr_id = id_table[wqe_idx & (depth - 1)];
+	wc->byte_len = be32_to_cpu(cqe->size);
+
+	wc->wc_flags = 0;
+
+	wc->opcode = wc_mapping_table[opcode];
+	if (opcode == ERDMA_OP_RECV_IMM || opcode == ERDMA_OP_RSP_SEND_IMM) {
+		wc->ex.imm_data = cpu_to_be32(le32_to_cpu(cqe->imm_data));
+		wc->wc_flags |= IB_WC_WITH_IMM;
+	} else if (opcode == ERDMA_OP_RECV_INV) {
+		wc->ex.invalidate_rkey = be32_to_cpu(cqe->inv_rkey);
+		wc->wc_flags |= IB_WC_WITH_INVALIDATE;
+	}
+
+	if (erdma_device_rocev2(dev) &&
+	    (qp->ibqp.qp_type == IB_QPT_UD || qp->ibqp.qp_type == IB_QPT_GSI))
+		erdma_process_ud_cqe(cqe, wc);
+
+	if (syndrome >= ERDMA_NUM_WC_STATUS)
+		syndrome = ERDMA_WC_GENERAL_ERR;
+
+	wc->status = map_cqe_status[syndrome].base;
+	wc->vendor_err = map_cqe_status[syndrome].vendor;
+	wc->qp = &qp->ibqp;
+
+	return 0;
+}
+
+int erdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
+{
+	struct erdma_cq *cq = to_ecq(ibcq);
+	unsigned long flags;
+	int npolled, ret;
+
+	spin_lock_irqsave(&cq->kern_cq.lock, flags);
+
+	for (npolled = 0; npolled < num_entries;) {
+		ret = erdma_poll_one_cqe(cq, wc + npolled);
+
+		if (ret == -EAGAIN) /* no received new CQEs. */
+			break;
+		else if (ret) /* ignore invalid CQEs. */
+			continue;
+
+		npolled++;
+	}
+
+	spin_unlock_irqrestore(&cq->kern_cq.lock, flags);
+
+	return npolled;
+}
+
+void erdma_remove_cqes_of_qp(struct ib_cq *ibcq, u32 qpn)
+{
+	struct erdma_cq *cq = to_ecq(ibcq);
+	struct erdma_cqe *cqe, *dst_cqe;
+	u32 prev_cq_ci, cur_cq_ci;
+	u32 ncqe = 0, nqp_cqe = 0;
+	unsigned long flags;
+	u8 owner;
+
+	spin_lock_irqsave(&cq->kern_cq.lock, flags);
+
+	prev_cq_ci = cq->kern_cq.ci;
+
+	while (ncqe < cq->depth && (cqe = get_next_valid_cqe(cq)) != NULL) {
+		++cq->kern_cq.ci;
+		++ncqe;
+	}
+
+	while (ncqe > 0) {
+		cur_cq_ci = prev_cq_ci + ncqe - 1;
+		cqe = get_queue_entry(cq->kern_cq.qbuf, cur_cq_ci, cq->depth,
+				      CQE_SHIFT);
+
+		if (be32_to_cpu(cqe->qpn) == qpn) {
+			++nqp_cqe;
+		} else if (nqp_cqe) {
+			dst_cqe = get_queue_entry(cq->kern_cq.qbuf,
+						  cur_cq_ci + nqp_cqe,
+						  cq->depth, CQE_SHIFT);
+			owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK,
+					  be32_to_cpu(dst_cqe->hdr));
+			cqe->hdr = cpu_to_be32(
+				(be32_to_cpu(cqe->hdr) &
+				 ~ERDMA_CQE_HDR_OWNER_MASK) |
+				FIELD_PREP(ERDMA_CQE_HDR_OWNER_MASK, owner));
+			memcpy(dst_cqe, cqe, sizeof(*cqe));
+		}
+
+		--ncqe;
+	}
+
+	cq->kern_cq.ci = prev_cq_ci + nqp_cqe;
+	spin_unlock_irqrestore(&cq->kern_cq.lock, flags);
+}

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_eq.c

@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#include "erdma_verbs.h"
+
+#define MAX_POLL_CHUNK_SIZE 16
+
+void notify_eq(struct erdma_eq *eq)
+{
+	u64 db_data = FIELD_PREP(ERDMA_EQDB_CI_MASK, eq->ci) |
+		      FIELD_PREP(ERDMA_EQDB_ARM_MASK, 1);
+
+	*eq->dbrec = db_data;
+	writeq(db_data, eq->db);
+
+	atomic64_inc(&eq->notify_num);
+}
+
+void *get_next_valid_eqe(struct erdma_eq *eq)
+{
+	u64 *eqe = get_queue_entry(eq->qbuf, eq->ci, eq->depth, EQE_SHIFT);
+	u32 owner = FIELD_GET(ERDMA_CEQE_HDR_O_MASK, READ_ONCE(*eqe));
+
+	return owner ^ !!(eq->ci & eq->depth) ? eqe : NULL;
+}
+
+void erdma_aeq_event_handler(struct erdma_dev *dev)
+{
+	struct erdma_aeqe *aeqe;
+	u32 cqn, qpn;
+	struct erdma_qp *qp;
+	struct erdma_cq *cq;
+	struct ib_event event;
+	u32 poll_cnt = 0;
+
+	memset(&event, 0, sizeof(event));
+
+	while (poll_cnt < MAX_POLL_CHUNK_SIZE) {
+		aeqe = get_next_valid_eqe(&dev->aeq);
+		if (!aeqe)
+			break;
+
+		dma_rmb();
+
+		dev->aeq.ci++;
+		atomic64_inc(&dev->aeq.event_num);
+		poll_cnt++;
+
+		if (FIELD_GET(ERDMA_AEQE_HDR_TYPE_MASK,
+			      le32_to_cpu(aeqe->hdr)) == ERDMA_AE_TYPE_CQ_ERR) {
+			cqn = le32_to_cpu(aeqe->event_data0);
+			cq = find_cq_by_cqn(dev, cqn);
+			if (!cq)
+				continue;
+
+			event.device = cq->ibcq.device;
+			event.element.cq = &cq->ibcq;
+			event.event = IB_EVENT_CQ_ERR;
+			if (cq->ibcq.event_handler)
+				cq->ibcq.event_handler(&event,
+						       cq->ibcq.cq_context);
+		} else {
+			qpn = le32_to_cpu(aeqe->event_data0);
+			qp = find_qp_by_qpn(dev, qpn);
+			if (!qp)
+				continue;
+
+			event.device = qp->ibqp.device;
+			event.element.qp = &qp->ibqp;
+			event.event = IB_EVENT_QP_FATAL;
+			if (qp->ibqp.event_handler)
+				qp->ibqp.event_handler(&event,
+						       qp->ibqp.qp_context);
+		}
+	}
+
+	notify_eq(&dev->aeq);
+}
+
+int erdma_eq_common_init(struct erdma_dev *dev, struct erdma_eq *eq, u32 depth)
+{
+	u32 buf_size = depth << EQE_SHIFT;
+
+	eq->qbuf = dma_alloc_coherent(&dev->pdev->dev, buf_size,
+				      &eq->qbuf_dma_addr, GFP_KERNEL);
+	if (!eq->qbuf)
+		return -ENOMEM;
+
+	eq->dbrec = dma_pool_zalloc(dev->db_pool, GFP_KERNEL, &eq->dbrec_dma);
+	if (!eq->dbrec)
+		goto err_free_qbuf;
+
+	spin_lock_init(&eq->lock);
+	atomic64_set(&eq->event_num, 0);
+	atomic64_set(&eq->notify_num, 0);
+	eq->ci = 0;
+	eq->depth = depth;
+
+	return 0;
+
+err_free_qbuf:
+	dma_free_coherent(&dev->pdev->dev, buf_size, eq->qbuf,
+			  eq->qbuf_dma_addr);
+
+	return -ENOMEM;
+}
+
+void erdma_eq_destroy(struct erdma_dev *dev, struct erdma_eq *eq)
+{
+	dma_pool_free(dev->db_pool, eq->dbrec, eq->dbrec_dma);
+	dma_free_coherent(&dev->pdev->dev, eq->depth << EQE_SHIFT, eq->qbuf,
+			  eq->qbuf_dma_addr);
+}
+
+int erdma_aeq_init(struct erdma_dev *dev)
+{
+	struct erdma_eq *eq = &dev->aeq;
+	int ret;
+
+	ret = erdma_eq_common_init(dev, &dev->aeq, ERDMA_DEFAULT_EQ_DEPTH);
+	if (ret)
+		return ret;
+
+	eq->db = dev->func_bar + ERDMA_REGS_AEQ_DB_REG;
+
+	erdma_reg_write32(dev, ERDMA_REGS_AEQ_ADDR_H_REG,
+			  upper_32_bits(eq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_AEQ_ADDR_L_REG,
+			  lower_32_bits(eq->qbuf_dma_addr));
+	erdma_reg_write32(dev, ERDMA_REGS_AEQ_DEPTH_REG, eq->depth);
+	erdma_reg_write64(dev, ERDMA_AEQ_DB_HOST_ADDR_REG, eq->dbrec_dma);
+
+	return 0;
+}
+
+void erdma_ceq_completion_handler(struct erdma_eq_cb *ceq_cb)
+{
+	struct erdma_dev *dev = ceq_cb->dev;
+	struct erdma_cq *cq;
+	u32 poll_cnt = 0;
+	u64 *ceqe;
+	int cqn;
+
+	if (!ceq_cb->ready)
+		return;
+
+	while (poll_cnt < MAX_POLL_CHUNK_SIZE) {
+		ceqe = get_next_valid_eqe(&ceq_cb->eq);
+		if (!ceqe)
+			break;
+
+		dma_rmb();
+		ceq_cb->eq.ci++;
+		poll_cnt++;
+		cqn = FIELD_GET(ERDMA_CEQE_HDR_CQN_MASK, READ_ONCE(*ceqe));
+
+		cq = find_cq_by_cqn(dev, cqn);
+		if (!cq)
+			continue;
+
+		if (rdma_is_kernel_res(&cq->ibcq.res))
+			cq->kern_cq.cmdsn++;
+
+		if (cq->ibcq.comp_handler)
+			cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
+	}
+
+	notify_eq(&ceq_cb->eq);
+}
+
+static irqreturn_t erdma_intr_ceq_handler(int irq, void *data)
+{
+	struct erdma_eq_cb *ceq_cb = data;
+
+	tasklet_schedule(&ceq_cb->tasklet);
+
+	return IRQ_HANDLED;
+}
+
+static void erdma_intr_ceq_task(unsigned long data)
+{
+	erdma_ceq_completion_handler((struct erdma_eq_cb *)data);
+}
+
+static int erdma_set_ceq_irq(struct erdma_dev *dev, u16 ceqn)
+{
+	struct erdma_eq_cb *eqc = &dev->ceqs[ceqn];
+	int err;
+
+	snprintf(eqc->irq.name, ERDMA_IRQNAME_SIZE, "erdma-ceq%u@pci:%s", ceqn,
+		 pci_name(dev->pdev));
+	eqc->irq.msix_vector = pci_irq_vector(dev->pdev, ceqn + 1);
+
+	tasklet_init(&dev->ceqs[ceqn].tasklet, erdma_intr_ceq_task,
+		     (unsigned long)&dev->ceqs[ceqn]);
+
+	cpumask_set_cpu(cpumask_local_spread(ceqn + 1,
+					     dev_to_node(&dev->pdev->dev)),
+			&eqc->irq.affinity_hint_mask);
+
+	err = request_irq(eqc->irq.msix_vector, erdma_intr_ceq_handler, 0,
+			  eqc->irq.name, eqc);
+	if (err) {
+		dev_err(&dev->pdev->dev, "failed to request_irq(%d)\n", err);
+		return err;
+	}
+
+	irq_set_affinity_hint(eqc->irq.msix_vector,
+			      &eqc->irq.affinity_hint_mask);
+
+	return 0;
+}
+
+static void erdma_free_ceq_irq(struct erdma_dev *dev, u16 ceqn)
+{
+	struct erdma_eq_cb *eqc = &dev->ceqs[ceqn];
+
+	irq_set_affinity_hint(eqc->irq.msix_vector, NULL);
+	free_irq(eqc->irq.msix_vector, eqc);
+}
+
+static int create_eq_cmd(struct erdma_dev *dev, u32 eqn, struct erdma_eq *eq)
+{
+	struct erdma_cmdq_create_eq_req req;
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_COMMON,
+				CMDQ_OPCODE_CREATE_EQ);
+	req.eqn = eqn;
+	req.depth = ilog2(eq->depth);
+	req.qbuf_addr = eq->qbuf_dma_addr;
+	req.qtype = ERDMA_EQ_TYPE_CEQ;
+	/* Vector index is the same as EQN. */
+	req.vector_idx = eqn;
+	req.db_dma_addr_l = lower_32_bits(eq->dbrec_dma);
+	req.db_dma_addr_h = upper_32_bits(eq->dbrec_dma);
+
+	return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
+				   false);
+}
+
+static int erdma_ceq_init_one(struct erdma_dev *dev, u16 ceqn)
+{
+	struct erdma_eq *eq = &dev->ceqs[ceqn].eq;
+	int ret;
+
+	ret = erdma_eq_common_init(dev, eq, ERDMA_DEFAULT_EQ_DEPTH);
+	if (ret)
+		return ret;
+
+	eq->db = dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG +
+		 (ceqn + 1) * ERDMA_DB_SIZE;
+	dev->ceqs[ceqn].dev = dev;
+	dev->ceqs[ceqn].ready = true;
+
+	/* CEQ indexed from 1, 0 rsvd for CMDQ-EQ. */
+	ret = create_eq_cmd(dev, ceqn + 1, eq);
+	if (ret) {
+		erdma_eq_destroy(dev, eq);
+		dev->ceqs[ceqn].ready = false;
+	}
+
+	return ret;
+}
+
+static void erdma_ceq_uninit_one(struct erdma_dev *dev, u16 ceqn)
+{
+	struct erdma_eq *eq = &dev->ceqs[ceqn].eq;
+	struct erdma_cmdq_destroy_eq_req req;
+	int err;
+
+	dev->ceqs[ceqn].ready = 0;
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_COMMON,
+				CMDQ_OPCODE_DESTROY_EQ);
+	/* CEQ indexed from 1, 0 rsvd for CMDQ-EQ. */
+	req.eqn = ceqn + 1;
+	req.qtype = ERDMA_EQ_TYPE_CEQ;
+	req.vector_idx = ceqn + 1;
+
+	err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
+				  false);
+	if (err)
+		return;
+
+	erdma_eq_destroy(dev, eq);
+}
+
+int erdma_ceqs_init(struct erdma_dev *dev)
+{
+	u32 i, j;
+	int err;
+
+	for (i = 0; i < dev->attrs.irq_num - 1; i++) {
+		err = erdma_ceq_init_one(dev, i);
+		if (err)
+			goto out_err;
+
+		err = erdma_set_ceq_irq(dev, i);
+		if (err) {
+			erdma_ceq_uninit_one(dev, i);
+			goto out_err;
+		}
+	}
+
+	return 0;
+
+out_err:
+	for (j = 0; j < i; j++) {
+		erdma_free_ceq_irq(dev, j);
+		erdma_ceq_uninit_one(dev, j);
+	}
+
+	return err;
+}
+
+void erdma_ceqs_uninit(struct erdma_dev *dev)
+{
+	u32 i;
+
+	for (i = 0; i < dev->attrs.irq_num - 1; i++) {
+		erdma_free_ceq_irq(dev, i);
+		erdma_ceq_uninit_one(dev, i);
+	}
+}

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_hw.h

@@ -0,0 +1,753 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#ifndef __ERDMA_HW_H__
+#define __ERDMA_HW_H__
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/* PCIe device related definition. */
+#define ERDMA_PCI_WIDTH 64
+#define ERDMA_FUNC_BAR 0
+#define ERDMA_MISX_BAR 2
+
+#define ERDMA_BAR_MASK (BIT(ERDMA_FUNC_BAR) | BIT(ERDMA_MISX_BAR))
+
+/* MSI-X related. */
+#define ERDMA_NUM_MSIX_VEC 32U
+#define ERDMA_MSIX_VECTOR_CMDQ 0
+
+/* RoCEv2 related */
+#define ERDMA_ROCEV2_GID_SIZE 16
+#define ERDMA_MAX_PKEYS 1
+#define ERDMA_DEFAULT_PKEY 0xFFFF
+
+/* erdma device protocol type */
+enum erdma_proto_type {
+	ERDMA_PROTO_IWARP = 0,
+	ERDMA_PROTO_ROCEV2 = 1,
+	ERDMA_PROTO_COUNT = 2,
+};
+
+/* PCIe Bar0 Registers. */
+#define ERDMA_REGS_VERSION_REG 0x0
+#define ERDMA_REGS_DEV_PROTO_REG 0xC
+#define ERDMA_REGS_DEV_CTRL_REG 0x10
+#define ERDMA_REGS_DEV_ST_REG 0x14
+#define ERDMA_REGS_NETDEV_MAC_L_REG 0x18
+#define ERDMA_REGS_NETDEV_MAC_H_REG 0x1C
+#define ERDMA_REGS_CMDQ_SQ_ADDR_L_REG 0x20
+#define ERDMA_REGS_CMDQ_SQ_ADDR_H_REG 0x24
+#define ERDMA_REGS_CMDQ_CQ_ADDR_L_REG 0x28
+#define ERDMA_REGS_CMDQ_CQ_ADDR_H_REG 0x2C
+#define ERDMA_REGS_CMDQ_DEPTH_REG 0x30
+#define ERDMA_REGS_CMDQ_EQ_DEPTH_REG 0x34
+#define ERDMA_REGS_CMDQ_EQ_ADDR_L_REG 0x38
+#define ERDMA_REGS_CMDQ_EQ_ADDR_H_REG 0x3C
+#define ERDMA_REGS_AEQ_ADDR_L_REG 0x40
+#define ERDMA_REGS_AEQ_ADDR_H_REG 0x44
+#define ERDMA_REGS_AEQ_DEPTH_REG 0x48
+#define ERDMA_REGS_GRP_NUM_REG 0x4c
+#define ERDMA_REGS_AEQ_DB_REG 0x50
+#define ERDMA_CMDQ_SQ_DB_HOST_ADDR_REG 0x60
+#define ERDMA_CMDQ_CQ_DB_HOST_ADDR_REG 0x68
+#define ERDMA_CMDQ_EQ_DB_HOST_ADDR_REG 0x70
+#define ERDMA_AEQ_DB_HOST_ADDR_REG 0x78
+#define ERDMA_REGS_STATS_TSO_IN_PKTS_REG 0x80
+#define ERDMA_REGS_STATS_TSO_OUT_PKTS_REG 0x88
+#define ERDMA_REGS_STATS_TSO_OUT_BYTES_REG 0x90
+#define ERDMA_REGS_STATS_TX_DROP_PKTS_REG 0x98
+#define ERDMA_REGS_STATS_TX_BPS_METER_DROP_PKTS_REG 0xa0
+#define ERDMA_REGS_STATS_TX_PPS_METER_DROP_PKTS_REG 0xa8
+#define ERDMA_REGS_STATS_RX_PKTS_REG 0xc0
+#define ERDMA_REGS_STATS_RX_BYTES_REG 0xc8
+#define ERDMA_REGS_STATS_RX_DROP_PKTS_REG 0xd0
+#define ERDMA_REGS_STATS_RX_BPS_METER_DROP_PKTS_REG 0xd8
+#define ERDMA_REGS_STATS_RX_PPS_METER_DROP_PKTS_REG 0xe0
+#define ERDMA_REGS_CEQ_DB_BASE_REG 0x100
+#define ERDMA_CMDQ_SQDB_REG 0x200
+#define ERDMA_CMDQ_CQDB_REG 0x300
+
+/* DEV_CTRL_REG details. */
+#define ERDMA_REG_DEV_CTRL_RESET_MASK 0x00000001
+#define ERDMA_REG_DEV_CTRL_INIT_MASK 0x00000002
+
+/* DEV_ST_REG details. */
+#define ERDMA_REG_DEV_ST_RESET_DONE_MASK 0x00000001U
+#define ERDMA_REG_DEV_ST_INIT_DONE_MASK 0x00000002U
+
+/* eRDMA PCIe DBs definition. */
+#define ERDMA_BAR_DB_SPACE_BASE 4096
+
+#define ERDMA_BAR_SQDB_SPACE_OFFSET ERDMA_BAR_DB_SPACE_BASE
+#define ERDMA_BAR_SQDB_SPACE_SIZE (384 * 1024)
+
+#define ERDMA_BAR_RQDB_SPACE_OFFSET \
+	(ERDMA_BAR_SQDB_SPACE_OFFSET + ERDMA_BAR_SQDB_SPACE_SIZE)
+#define ERDMA_BAR_RQDB_SPACE_SIZE (96 * 1024)
+
+#define ERDMA_BAR_CQDB_SPACE_OFFSET \
+	(ERDMA_BAR_RQDB_SPACE_OFFSET + ERDMA_BAR_RQDB_SPACE_SIZE)
+
+#define ERDMA_SDB_SHARED_PAGE_INDEX 95
+
+/* Doorbell related. */
+#define ERDMA_DB_SIZE 8
+
+#define ERDMA_CQDB_IDX_MASK GENMASK_ULL(63, 56)
+#define ERDMA_CQDB_CQN_MASK GENMASK_ULL(55, 32)
+#define ERDMA_CQDB_ARM_MASK BIT_ULL(31)
+#define ERDMA_CQDB_SOL_MASK BIT_ULL(30)
+#define ERDMA_CQDB_CMDSN_MASK GENMASK_ULL(29, 28)
+#define ERDMA_CQDB_CI_MASK GENMASK_ULL(23, 0)
+
+#define ERDMA_EQDB_ARM_MASK BIT(31)
+#define ERDMA_EQDB_CI_MASK GENMASK_ULL(23, 0)
+
+#define ERDMA_PAGE_SIZE_SUPPORT 0x7FFFF000
+
+/* Hardware page size definition */
+#define ERDMA_HW_PAGE_SHIFT 12
+#define ERDMA_HW_PAGE_SIZE 4096
+
+/* WQE related. */
+#define EQE_SIZE 16
+#define EQE_SHIFT 4
+#define RQE_SIZE 32
+#define RQE_SHIFT 5
+#define CQE_SIZE 32
+#define CQE_SHIFT 5
+#define SQEBB_SIZE 32
+#define SQEBB_SHIFT 5
+#define SQEBB_MASK (~(SQEBB_SIZE - 1))
+#define SQEBB_ALIGN(size) ((size + SQEBB_SIZE - 1) & SQEBB_MASK)
+#define SQEBB_COUNT(size) (SQEBB_ALIGN(size) >> SQEBB_SHIFT)
+
+#define ERDMA_MAX_SQE_SIZE 128
+#define ERDMA_MAX_WQEBB_PER_SQE 4
+
+/* CMDQ related. */
+#define ERDMA_CMDQ_MAX_OUTSTANDING 128
+#define ERDMA_CMDQ_SQE_SIZE 128
+
+/* cmdq sub module definition. */
+enum CMDQ_WQE_SUB_MOD {
+	CMDQ_SUBMOD_RDMA = 0,
+	CMDQ_SUBMOD_COMMON = 1
+};
+
+enum CMDQ_RDMA_OPCODE {
+	CMDQ_OPCODE_QUERY_DEVICE = 0,
+	CMDQ_OPCODE_CREATE_QP = 1,
+	CMDQ_OPCODE_DESTROY_QP = 2,
+	CMDQ_OPCODE_MODIFY_QP = 3,
+	CMDQ_OPCODE_CREATE_CQ = 4,
+	CMDQ_OPCODE_DESTROY_CQ = 5,
+	CMDQ_OPCODE_REFLUSH = 6,
+	CMDQ_OPCODE_REG_MR = 8,
+	CMDQ_OPCODE_DEREG_MR = 9,
+	CMDQ_OPCODE_SET_GID = 14,
+	CMDQ_OPCODE_CREATE_AH = 15,
+	CMDQ_OPCODE_DESTROY_AH = 16,
+	CMDQ_OPCODE_QUERY_QP = 17,
+};
+
+enum CMDQ_COMMON_OPCODE {
+	CMDQ_OPCODE_CREATE_EQ = 0,
+	CMDQ_OPCODE_DESTROY_EQ = 1,
+	CMDQ_OPCODE_QUERY_FW_INFO = 2,
+	CMDQ_OPCODE_CONF_MTU = 3,
+	CMDQ_OPCODE_GET_STATS = 4,
+	CMDQ_OPCODE_CONF_DEVICE = 5,
+	CMDQ_OPCODE_ALLOC_DB = 8,
+	CMDQ_OPCODE_FREE_DB = 9,
+};
+
+/* cmdq-SQE HDR */
+#define ERDMA_CMD_HDR_WQEBB_CNT_MASK GENMASK_ULL(54, 52)
+#define ERDMA_CMD_HDR_CONTEXT_COOKIE_MASK GENMASK_ULL(47, 32)
+#define ERDMA_CMD_HDR_SUB_MOD_MASK GENMASK_ULL(25, 24)
+#define ERDMA_CMD_HDR_OPCODE_MASK GENMASK_ULL(23, 16)
+#define ERDMA_CMD_HDR_WQEBB_INDEX_MASK GENMASK_ULL(15, 0)
+
+struct erdma_cmdq_destroy_cq_req {
+	u64 hdr;
+	u32 cqn;
+};
+
+#define ERDMA_EQ_TYPE_AEQ 0
+#define ERDMA_EQ_TYPE_CEQ 1
+
+struct erdma_cmdq_create_eq_req {
+	u64 hdr;
+	u64 qbuf_addr;
+	u8 vector_idx;
+	u8 eqn;
+	u8 depth;
+	u8 qtype;
+	u32 db_dma_addr_l;
+	u32 db_dma_addr_h;
+};
+
+struct erdma_cmdq_destroy_eq_req {
+	u64 hdr;
+	u64 rsvd0;
+	u8 vector_idx;
+	u8 eqn;
+	u8 rsvd1;
+	u8 qtype;
+};
+
+/* config device cfg */
+#define ERDMA_CMD_CONFIG_DEVICE_PS_EN_MASK BIT(31)
+#define ERDMA_CMD_CONFIG_DEVICE_PGSHIFT_MASK GENMASK(4, 0)
+
+struct erdma_cmdq_config_device_req {
+	u64 hdr;
+	u32 cfg;
+	u32 rsvd[5];
+};
+
+struct erdma_cmdq_config_mtu_req {
+	u64 hdr;
+	u32 mtu;
+};
+
+/* ext db requests(alloc and free) cfg */
+#define ERDMA_CMD_EXT_DB_CQ_EN_MASK BIT(2)
+#define ERDMA_CMD_EXT_DB_RQ_EN_MASK BIT(1)
+#define ERDMA_CMD_EXT_DB_SQ_EN_MASK BIT(0)
+
+struct erdma_cmdq_ext_db_req {
+	u64 hdr;
+	u32 cfg;
+	u16 rdb_off;
+	u16 sdb_off;
+	u16 rsvd0;
+	u16 cdb_off;
+	u32 rsvd1[3];
+};
+
+/* alloc db response qword 0 definition */
+#define ERDMA_CMD_ALLOC_DB_RESP_RDB_MASK GENMASK_ULL(63, 48)
+#define ERDMA_CMD_ALLOC_DB_RESP_CDB_MASK GENMASK_ULL(47, 32)
+#define ERDMA_CMD_ALLOC_DB_RESP_SDB_MASK GENMASK_ULL(15, 0)
+
+/* create_cq cfg0 */
+#define ERDMA_CMD_CREATE_CQ_DEPTH_MASK GENMASK(31, 24)
+#define ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK GENMASK(23, 20)
+#define ERDMA_CMD_CREATE_CQ_CQN_MASK GENMASK(19, 0)
+
+/* create_cq cfg1 */
+#define ERDMA_CMD_CREATE_CQ_MTT_CNT_MASK GENMASK(31, 16)
+#define ERDMA_CMD_CREATE_CQ_MTT_LEVEL_MASK BIT(15)
+#define ERDMA_CMD_CREATE_CQ_MTT_DB_CFG_MASK BIT(11)
+#define ERDMA_CMD_CREATE_CQ_EQN_MASK GENMASK(9, 0)
+
+/* create_cq cfg2 */
+#define ERDMA_CMD_CREATE_CQ_DB_CFG_MASK GENMASK(15, 0)
+
+struct erdma_cmdq_create_cq_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 qbuf_addr_l;
+	u32 qbuf_addr_h;
+	u32 cfg1;
+	u64 cq_dbrec_dma;
+	u32 first_page_offset;
+	u32 cfg2;
+};
+
+/* regmr/deregmr cfg0 */
+#define ERDMA_CMD_MR_VALID_MASK BIT(31)
+#define ERDMA_CMD_MR_VERSION_MASK GENMASK(30, 28)
+#define ERDMA_CMD_MR_KEY_MASK GENMASK(27, 20)
+#define ERDMA_CMD_MR_MPT_IDX_MASK GENMASK(19, 0)
+
+/* regmr cfg1 */
+#define ERDMA_CMD_REGMR_PD_MASK GENMASK(31, 12)
+#define ERDMA_CMD_REGMR_TYPE_MASK GENMASK(7, 6)
+#define ERDMA_CMD_REGMR_RIGHT_MASK GENMASK(5, 1)
+
+/* regmr cfg2 */
+#define ERDMA_CMD_REGMR_PAGESIZE_MASK GENMASK(31, 27)
+#define ERDMA_CMD_REGMR_MTT_PAGESIZE_MASK GENMASK(26, 24)
+#define ERDMA_CMD_REGMR_MTT_LEVEL_MASK GENMASK(21, 20)
+#define ERDMA_CMD_REGMR_MTT_CNT_MASK GENMASK(19, 0)
+
+struct erdma_cmdq_reg_mr_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 cfg1;
+	u64 start_va;
+	u32 size;
+	u32 cfg2;
+	union {
+		u64 phy_addr[4];
+		struct {
+			u64 rsvd;
+			u32 size_h;
+			u32 mtt_cnt_h;
+		};
+	};
+};
+
+struct erdma_cmdq_dereg_mr_req {
+	u64 hdr;
+	u32 cfg;
+};
+
+/* create_av cfg0 */
+#define ERDMA_CMD_CREATE_AV_FL_MASK GENMASK(19, 0)
+#define ERDMA_CMD_CREATE_AV_NTYPE_MASK BIT(20)
+
+struct erdma_av_cfg {
+	u32 cfg0;
+	u8 traffic_class;
+	u8 hop_limit;
+	u8 sl;
+	u8 rsvd;
+	u16 udp_sport;
+	u16 sgid_index;
+	u8 dmac[ETH_ALEN];
+	u8 padding[2];
+	u8 dgid[ERDMA_ROCEV2_GID_SIZE];
+};
+
+struct erdma_cmdq_create_ah_req {
+	u64 hdr;
+	u32 pdn;
+	u32 ahn;
+	struct erdma_av_cfg av_cfg;
+};
+
+struct erdma_cmdq_destroy_ah_req {
+	u64 hdr;
+	u32 pdn;
+	u32 ahn;
+};
+
+/* modify qp cfg */
+#define ERDMA_CMD_MODIFY_QP_STATE_MASK GENMASK(31, 24)
+#define ERDMA_CMD_MODIFY_QP_CC_MASK GENMASK(23, 20)
+#define ERDMA_CMD_MODIFY_QP_QPN_MASK GENMASK(19, 0)
+
+struct erdma_cmdq_modify_qp_req {
+	u64 hdr;
+	u32 cfg;
+	u32 cookie;
+	__be32 dip;
+	__be32 sip;
+	__be16 sport;
+	__be16 dport;
+	u32 send_nxt;
+	u32 recv_nxt;
+};
+
+/* modify qp cfg1 for roce device */
+#define ERDMA_CMD_MODIFY_QP_DQPN_MASK GENMASK(19, 0)
+
+struct erdma_cmdq_mod_qp_req_rocev2 {
+	u64 hdr;
+	u32 cfg0;
+	u32 cfg1;
+	u32 attr_mask;
+	u32 qkey;
+	u32 rq_psn;
+	u32 sq_psn;
+	struct erdma_av_cfg av_cfg;
+};
+
+/* query qp response mask */
+#define ERDMA_CMD_QUERY_QP_RESP_SQ_PSN_MASK GENMASK_ULL(23, 0)
+#define ERDMA_CMD_QUERY_QP_RESP_RQ_PSN_MASK GENMASK_ULL(47, 24)
+#define ERDMA_CMD_QUERY_QP_RESP_QP_STATE_MASK GENMASK_ULL(55, 48)
+#define ERDMA_CMD_QUERY_QP_RESP_SQ_DRAINING_MASK GENMASK_ULL(56, 56)
+
+struct erdma_cmdq_query_qp_req_rocev2 {
+	u64 hdr;
+	u32 qpn;
+};
+
+enum erdma_qp_type {
+	ERDMA_QPT_RC = 0,
+	ERDMA_QPT_UD = 1,
+};
+
+/* create qp cfg0 */
+#define ERDMA_CMD_CREATE_QP_SQ_DEPTH_MASK GENMASK(31, 20)
+#define ERDMA_CMD_CREATE_QP_QPN_MASK GENMASK(19, 0)
+
+/* create qp cfg1 */
+#define ERDMA_CMD_CREATE_QP_RQ_DEPTH_MASK GENMASK(31, 20)
+#define ERDMA_CMD_CREATE_QP_PD_MASK GENMASK(19, 0)
+
+/* create qp cfg2 */
+#define ERDMA_CMD_CREATE_QP_TYPE_MASK GENMASK(3, 0)
+
+/* create qp cqn_mtt_cfg */
+#define ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK GENMASK(31, 28)
+#define ERDMA_CMD_CREATE_QP_DB_CFG_MASK BIT(25)
+#define ERDMA_CMD_CREATE_QP_CQN_MASK GENMASK(23, 0)
+
+/* create qp mtt_cfg */
+#define ERDMA_CMD_CREATE_QP_PAGE_OFFSET_MASK GENMASK(31, 12)
+#define ERDMA_CMD_CREATE_QP_MTT_CNT_MASK GENMASK(11, 1)
+#define ERDMA_CMD_CREATE_QP_MTT_LEVEL_MASK BIT(0)
+
+/* create qp db cfg */
+#define ERDMA_CMD_CREATE_QP_SQDB_CFG_MASK GENMASK(31, 16)
+#define ERDMA_CMD_CREATE_QP_RQDB_CFG_MASK GENMASK(15, 0)
+
+#define ERDMA_CMDQ_CREATE_QP_RESP_COOKIE_MASK GENMASK_ULL(31, 0)
+
+struct erdma_cmdq_create_qp_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 cfg1;
+	u32 sq_cqn_mtt_cfg;
+	u32 rq_cqn_mtt_cfg;
+	u64 sq_buf_addr;
+	u64 rq_buf_addr;
+	u32 sq_mtt_cfg;
+	u32 rq_mtt_cfg;
+	u64 sq_dbrec_dma;
+	u64 rq_dbrec_dma;
+
+	u64 sq_mtt_entry[3];
+	u64 rq_mtt_entry[3];
+
+	u32 db_cfg;
+	u32 cfg2;
+};
+
+struct erdma_cmdq_destroy_qp_req {
+	u64 hdr;
+	u32 qpn;
+};
+
+struct erdma_cmdq_reflush_req {
+	u64 hdr;
+	u32 qpn;
+	u32 sq_pi;
+	u32 rq_pi;
+};
+
+#define ERDMA_HW_RESP_SIZE 256
+
+struct erdma_cmdq_query_req {
+	u64 hdr;
+	u32 rsvd;
+	u32 index;
+
+	u64 target_addr;
+	u32 target_length;
+};
+
+#define ERDMA_HW_RESP_MAGIC 0x5566
+
+struct erdma_cmdq_query_resp_hdr {
+	u16 magic;
+	u8 ver;
+	u8 length;
+
+	u32 index;
+	u32 rsvd[2];
+};
+
+struct erdma_cmdq_query_stats_resp {
+	struct erdma_cmdq_query_resp_hdr hdr;
+
+	u64 tx_req_cnt;
+	u64 tx_packets_cnt;
+	u64 tx_bytes_cnt;
+	u64 tx_drop_packets_cnt;
+	u64 tx_bps_meter_drop_packets_cnt;
+	u64 tx_pps_meter_drop_packets_cnt;
+	u64 rx_packets_cnt;
+	u64 rx_bytes_cnt;
+	u64 rx_drop_packets_cnt;
+	u64 rx_bps_meter_drop_packets_cnt;
+	u64 rx_pps_meter_drop_packets_cnt;
+};
+
+enum erdma_network_type {
+	ERDMA_NETWORK_TYPE_IPV4 = 0,
+	ERDMA_NETWORK_TYPE_IPV6 = 1,
+};
+
+enum erdma_set_gid_op {
+	ERDMA_SET_GID_OP_ADD = 0,
+	ERDMA_SET_GID_OP_DEL = 1,
+};
+
+/* set gid cfg */
+#define ERDMA_CMD_SET_GID_SGID_IDX_MASK GENMASK(15, 0)
+#define ERDMA_CMD_SET_GID_NTYPE_MASK BIT(16)
+#define ERDMA_CMD_SET_GID_OP_MASK BIT(31)
+
+struct erdma_cmdq_set_gid_req {
+	u64 hdr;
+	u32 cfg;
+	u8 gid[ERDMA_ROCEV2_GID_SIZE];
+};
+
+/* cap qword 0 definition */
+#define ERDMA_CMD_DEV_CAP_MAX_GID_MASK GENMASK_ULL(51, 48)
+#define ERDMA_CMD_DEV_CAP_MAX_CQE_MASK GENMASK_ULL(47, 40)
+#define ERDMA_CMD_DEV_CAP_FLAGS_MASK GENMASK_ULL(31, 24)
+#define ERDMA_CMD_DEV_CAP_MAX_RECV_WR_MASK GENMASK_ULL(23, 16)
+#define ERDMA_CMD_DEV_CAP_MAX_AH_MASK GENMASK_ULL(15, 8)
+#define ERDMA_CMD_DEV_CAP_MAX_MR_SIZE_MASK GENMASK_ULL(7, 0)
+
+/* cap qword 1 definition */
+#define ERDMA_CMD_DEV_CAP_DMA_LOCAL_KEY_MASK GENMASK_ULL(63, 32)
+#define ERDMA_CMD_DEV_CAP_DEFAULT_CC_MASK GENMASK_ULL(31, 28)
+#define ERDMA_CMD_DEV_CAP_QBLOCK_MASK GENMASK_ULL(27, 16)
+#define ERDMA_CMD_DEV_CAP_MAX_MW_MASK GENMASK_ULL(7, 0)
+
+#define ERDMA_NQP_PER_QBLOCK 1024
+
+enum {
+	ERDMA_DEV_CAP_FLAGS_ATOMIC = 1 << 7,
+	ERDMA_DEV_CAP_FLAGS_MTT_VA = 1 << 5,
+	ERDMA_DEV_CAP_FLAGS_EXTEND_DB = 1 << 3,
+};
+
+#define ERDMA_CMD_INFO0_FW_VER_MASK GENMASK_ULL(31, 0)
+
+/* CQE hdr */
+#define ERDMA_CQE_HDR_OWNER_MASK BIT(31)
+#define ERDMA_CQE_HDR_OPCODE_MASK GENMASK(23, 16)
+#define ERDMA_CQE_HDR_QTYPE_MASK GENMASK(15, 8)
+#define ERDMA_CQE_HDR_SYNDROME_MASK GENMASK(7, 0)
+
+#define ERDMA_CQE_QTYPE_SQ 0
+#define ERDMA_CQE_QTYPE_RQ 1
+#define ERDMA_CQE_QTYPE_CMDQ 2
+
+#define ERDMA_CQE_NTYPE_MASK BIT(31)
+#define ERDMA_CQE_SL_MASK GENMASK(27, 20)
+#define ERDMA_CQE_SQPN_MASK GENMASK(19, 0)
+
+struct erdma_cqe {
+	__be32 hdr;
+	__be32 qe_idx;
+	__be32 qpn;
+	union {
+		__le32 imm_data;
+		__be32 inv_rkey;
+	};
+	__be32 size;
+	union {
+		struct {
+			__be32 rsvd[3];
+		} rc;
+
+		struct {
+			__be32 rsvd[2];
+			__be32 info;
+		} ud;
+	};
+};
+
+struct erdma_sge {
+	__aligned_le64 addr;
+	__le32 length;
+	__le32 key;
+};
+
+/* Receive Queue Element */
+struct erdma_rqe {
+	__le16 qe_idx;
+	__le16 rsvd0;
+	__le32 qpn;
+	__le32 rsvd1;
+	__le32 rsvd2;
+	__le64 to;
+	__le32 length;
+	__le32 stag;
+};
+
+/* SQE */
+#define ERDMA_SQE_HDR_SGL_LEN_MASK GENMASK_ULL(63, 56)
+#define ERDMA_SQE_HDR_WQEBB_CNT_MASK GENMASK_ULL(54, 52)
+#define ERDMA_SQE_HDR_QPN_MASK GENMASK_ULL(51, 32)
+#define ERDMA_SQE_HDR_OPCODE_MASK GENMASK_ULL(31, 27)
+#define ERDMA_SQE_HDR_DWQE_MASK BIT_ULL(26)
+#define ERDMA_SQE_HDR_INLINE_MASK BIT_ULL(25)
+#define ERDMA_SQE_HDR_FENCE_MASK BIT_ULL(24)
+#define ERDMA_SQE_HDR_SE_MASK BIT_ULL(23)
+#define ERDMA_SQE_HDR_CE_MASK BIT_ULL(22)
+#define ERDMA_SQE_HDR_WQEBB_INDEX_MASK GENMASK_ULL(15, 0)
+
+/* REG MR attrs */
+#define ERDMA_SQE_MR_ACCESS_MASK GENMASK(5, 1)
+#define ERDMA_SQE_MR_MTT_TYPE_MASK GENMASK(7, 6)
+#define ERDMA_SQE_MR_MTT_CNT_MASK GENMASK(31, 12)
+
+struct erdma_write_sqe {
+	__le64 hdr;
+	__be32 imm_data;
+	__le32 length;
+
+	__le32 sink_stag;
+	__le32 sink_to_l;
+	__le32 sink_to_h;
+
+	__le32 rsvd;
+
+	struct erdma_sge sgl[];
+};
+
+struct erdma_send_sqe_rc {
+	__le64 hdr;
+	union {
+		__be32 imm_data;
+		__le32 invalid_stag;
+	};
+
+	__le32 length;
+	struct erdma_sge sgl[];
+};
+
+struct erdma_send_sqe_ud {
+	__le64 hdr;
+	__be32 imm_data;
+	__le32 length;
+	__le32 qkey;
+	__le32 dst_qpn;
+	__le32 ahn;
+	__le32 rsvd;
+	struct erdma_sge sgl[];
+};
+
+struct erdma_readreq_sqe {
+	__le64 hdr;
+	__le32 invalid_stag;
+	__le32 length;
+	__le32 sink_stag;
+	__le32 sink_to_l;
+	__le32 sink_to_h;
+	__le32 rsvd;
+};
+
+struct erdma_atomic_sqe {
+	__le64 hdr;
+	__le64 rsvd;
+	__le64 fetchadd_swap_data;
+	__le64 cmp_data;
+
+	struct erdma_sge remote;
+	struct erdma_sge sgl;
+};
+
+struct erdma_reg_mr_sqe {
+	__le64 hdr;
+	__le64 addr;
+	__le32 length;
+	__le32 stag;
+	__le32 attrs;
+	__le32 rsvd;
+};
+
+/* EQ related. */
+#define ERDMA_DEFAULT_EQ_DEPTH 4096
+
+/* ceqe */
+#define ERDMA_CEQE_HDR_DB_MASK BIT_ULL(63)
+#define ERDMA_CEQE_HDR_PI_MASK GENMASK_ULL(55, 32)
+#define ERDMA_CEQE_HDR_O_MASK BIT_ULL(31)
+#define ERDMA_CEQE_HDR_CQN_MASK GENMASK_ULL(19, 0)
+
+/* aeqe */
+#define ERDMA_AEQE_HDR_O_MASK BIT(31)
+#define ERDMA_AEQE_HDR_TYPE_MASK GENMASK(23, 16)
+#define ERDMA_AEQE_HDR_SUBTYPE_MASK GENMASK(7, 0)
+
+#define ERDMA_AE_TYPE_QP_FATAL_EVENT 0
+#define ERDMA_AE_TYPE_QP_ERQ_ERR_EVENT 1
+#define ERDMA_AE_TYPE_ACC_ERR_EVENT 2
+#define ERDMA_AE_TYPE_CQ_ERR 3
+#define ERDMA_AE_TYPE_OTHER_ERROR 4
+
+struct erdma_aeqe {
+	__le32 hdr;
+	__le32 event_data0;
+	__le32 event_data1;
+	__le32 rsvd;
+};
+
+enum erdma_opcode {
+	ERDMA_OP_WRITE = 0,
+	ERDMA_OP_READ = 1,
+	ERDMA_OP_SEND = 2,
+	ERDMA_OP_SEND_WITH_IMM = 3,
+
+	ERDMA_OP_RECEIVE = 4,
+	ERDMA_OP_RECV_IMM = 5,
+	ERDMA_OP_RECV_INV = 6,
+
+	ERDMA_OP_RSVD0 = 7,
+	ERDMA_OP_RSVD1 = 8,
+	ERDMA_OP_WRITE_WITH_IMM = 9,
+
+	ERDMA_OP_RSVD2 = 10,
+	ERDMA_OP_RSVD3 = 11,
+
+	ERDMA_OP_RSP_SEND_IMM = 12,
+	ERDMA_OP_SEND_WITH_INV = 13,
+
+	ERDMA_OP_REG_MR = 14,
+	ERDMA_OP_LOCAL_INV = 15,
+	ERDMA_OP_READ_WITH_INV = 16,
+	ERDMA_OP_ATOMIC_CAS = 17,
+	ERDMA_OP_ATOMIC_FAA = 18,
+	ERDMA_NUM_OPCODES = 19,
+	ERDMA_OP_INVALID = ERDMA_NUM_OPCODES + 1
+};
+
+enum erdma_wc_status {
+	ERDMA_WC_SUCCESS = 0,
+	ERDMA_WC_GENERAL_ERR = 1,
+	ERDMA_WC_RECV_WQE_FORMAT_ERR = 2,
+	ERDMA_WC_RECV_STAG_INVALID_ERR = 3,
+	ERDMA_WC_RECV_ADDR_VIOLATION_ERR = 4,
+	ERDMA_WC_RECV_RIGHT_VIOLATION_ERR = 5,
+	ERDMA_WC_RECV_PDID_ERR = 6,
+	ERDMA_WC_RECV_WARRPING_ERR = 7,
+	ERDMA_WC_SEND_WQE_FORMAT_ERR = 8,
+	ERDMA_WC_SEND_WQE_ORD_EXCEED = 9,
+	ERDMA_WC_SEND_STAG_INVALID_ERR = 10,
+	ERDMA_WC_SEND_ADDR_VIOLATION_ERR = 11,
+	ERDMA_WC_SEND_RIGHT_VIOLATION_ERR = 12,
+	ERDMA_WC_SEND_PDID_ERR = 13,
+	ERDMA_WC_SEND_WARRPING_ERR = 14,
+	ERDMA_WC_FLUSH_ERR = 15,
+	ERDMA_WC_RETRY_EXC_ERR = 16,
+	ERDMA_NUM_WC_STATUS
+};
+
+enum erdma_vendor_err {
+	ERDMA_WC_VENDOR_NO_ERR = 0,
+	ERDMA_WC_VENDOR_INVALID_RQE = 1,
+	ERDMA_WC_VENDOR_RQE_INVALID_STAG = 2,
+	ERDMA_WC_VENDOR_RQE_ADDR_VIOLATION = 3,
+	ERDMA_WC_VENDOR_RQE_ACCESS_RIGHT_ERR = 4,
+	ERDMA_WC_VENDOR_RQE_INVALID_PD = 5,
+	ERDMA_WC_VENDOR_RQE_WRAP_ERR = 6,
+	ERDMA_WC_VENDOR_INVALID_SQE = 0x20,
+	ERDMA_WC_VENDOR_ZERO_ORD = 0x21,
+	ERDMA_WC_VENDOR_SQE_INVALID_STAG = 0x30,
+	ERDMA_WC_VENDOR_SQE_ADDR_VIOLATION = 0x31,
+	ERDMA_WC_VENDOR_SQE_ACCESS_ERR = 0x32,
+	ERDMA_WC_VENDOR_SQE_INVALID_PD = 0x33,
+	ERDMA_WC_VENDOR_SQE_WARP_ERR = 0x34
+};
+
+#endif

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_main.c

@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#include <linux/module.h>
+#include <net/addrconf.h>
+#include <rdma/erdma-abi.h>
+
+#include "erdma.h"
+#include "erdma_cm.h"
+#include "erdma_verbs.h"
+
+MODULE_AUTHOR("Cheng Xu <chengyou@linux.alibaba.com>");
+MODULE_DESCRIPTION("Alibaba elasticRDMA adapter driver");
+MODULE_LICENSE("Dual BSD/GPL");
+
+static int erdma_netdev_event(struct notifier_block *nb, unsigned long event,
+			      void *arg)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(arg);
+	struct erdma_dev *dev = container_of(nb, struct erdma_dev, netdev_nb);
+
+	if (dev->netdev == NULL || dev->netdev != netdev)
+		goto done;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU:
+		if (dev->mtu != netdev->mtu) {
+			erdma_set_mtu(dev, netdev->mtu);
+			dev->mtu = netdev->mtu;
+		}
+		break;
+	case NETDEV_REGISTER:
+	case NETDEV_UNREGISTER:
+	case NETDEV_CHANGEADDR:
+	case NETDEV_GOING_DOWN:
+	case NETDEV_CHANGE:
+	default:
+		break;
+	}
+
+done:
+	return NOTIFY_OK;
+}
+
+static int erdma_enum_and_get_netdev(struct erdma_dev *dev)
+{
+	struct net_device *netdev;
+	int ret = -EPROBE_DEFER;
+
+	/* Already binded to a net_device, so we skip. */
+	if (dev->netdev)
+		return 0;
+
+	rtnl_lock();
+	for_each_netdev(&init_net, netdev) {
+		/*
+		 * In erdma, the paired netdev and ibdev should have the same
+		 * MAC address. erdma can get the value from its PCIe bar
+		 * registers. Since erdma can not get the paired netdev
+		 * reference directly, we do a traverse here to get the paired
+		 * netdev.
+		 */
+		if (ether_addr_equal_unaligned(netdev->perm_addr,
+					       dev->attrs.peer_addr)) {
+			ret = ib_device_set_netdev(&dev->ibdev, netdev, 1);
+			if (ret) {
+				rtnl_unlock();
+				ibdev_warn(&dev->ibdev,
+					   "failed (%d) to link netdev", ret);
+				return ret;
+			}
+
+			dev->netdev = netdev;
+			break;
+		}
+	}
+
+	rtnl_unlock();
+
+	return ret;
+}
+
+static int erdma_device_register(struct erdma_dev *dev)
+{
+	struct ib_device *ibdev = &dev->ibdev;
+	int ret;
+
+	ret = erdma_enum_and_get_netdev(dev);
+	if (ret)
+		return ret;
+
+	dev->mtu = dev->netdev->mtu;
+	addrconf_addr_eui48((u8 *)&ibdev->node_guid, dev->netdev->dev_addr);
+
+	ret = ib_register_device(ibdev, "erdma_%d", &dev->pdev->dev);
+	if (ret) {
+		dev_err(&dev->pdev->dev,
+			"ib_register_device failed: ret = %d\n", ret);
+		return ret;
+	}
+
+	dev->netdev_nb.notifier_call = erdma_netdev_event;
+	ret = register_netdevice_notifier(&dev->netdev_nb);
+	if (ret) {
+		ibdev_err(&dev->ibdev, "failed to register notifier.\n");
+		ib_unregister_device(ibdev);
+	}
+
+	return ret;
+}
+
+static irqreturn_t erdma_comm_irq_handler(int irq, void *data)
+{
+	struct erdma_dev *dev = data;
+
+	erdma_cmdq_completion_handler(&dev->cmdq);
+	erdma_aeq_event_handler(dev);
+
+	return IRQ_HANDLED;
+}
+
+static int erdma_request_vectors(struct erdma_dev *dev)
+{
+	int expect_irq_num = min(num_possible_cpus() + 1, ERDMA_NUM_MSIX_VEC);
+	int ret;
+
+	ret = pci_alloc_irq_vectors(dev->pdev, 1, expect_irq_num, PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(&dev->pdev->dev, "request irq vectors failed(%d)\n",
+			ret);
+		return ret;
+	}
+	dev->attrs.irq_num = ret;
+
+	return 0;
+}
+
+static int erdma_comm_irq_init(struct erdma_dev *dev)
+{
+	snprintf(dev->comm_irq.name, ERDMA_IRQNAME_SIZE, "erdma-common@pci:%s",
+		 pci_name(dev->pdev));
+	dev->comm_irq.msix_vector =
+		pci_irq_vector(dev->pdev, ERDMA_MSIX_VECTOR_CMDQ);
+
+	cpumask_set_cpu(cpumask_first(cpumask_of_pcibus(dev->pdev->bus)),
+			&dev->comm_irq.affinity_hint_mask);
+	irq_set_affinity_hint(dev->comm_irq.msix_vector,
+			      &dev->comm_irq.affinity_hint_mask);
+
+	return request_irq(dev->comm_irq.msix_vector, erdma_comm_irq_handler, 0,
+			   dev->comm_irq.name, dev);
+}
+
+static void erdma_comm_irq_uninit(struct erdma_dev *dev)
+{
+	irq_set_affinity_hint(dev->comm_irq.msix_vector, NULL);
+	free_irq(dev->comm_irq.msix_vector, dev);
+}
+
+static int erdma_device_init(struct erdma_dev *dev, struct pci_dev *pdev)
+{
+	int ret;
+
+	dev->proto = erdma_reg_read32(dev, ERDMA_REGS_DEV_PROTO_REG);
+
+	dev->resp_pool = dma_pool_create("erdma_resp_pool", &pdev->dev,
+					 ERDMA_HW_RESP_SIZE, ERDMA_HW_RESP_SIZE,
+					 0);
+	if (!dev->resp_pool)
+		return -ENOMEM;
+
+	dev->db_pool = dma_pool_create("erdma_db_pool", &pdev->dev,
+				       ERDMA_DB_SIZE, ERDMA_DB_SIZE, 0);
+	if (!dev->db_pool) {
+		ret = -ENOMEM;
+		goto destroy_resp_pool;
+	}
+
+	ret = dma_set_mask_and_coherent(&pdev->dev,
+					DMA_BIT_MASK(ERDMA_PCI_WIDTH));
+	if (ret)
+		goto destroy_db_pool;
+
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
+
+	return 0;
+
+destroy_db_pool:
+	dma_pool_destroy(dev->db_pool);
+
+destroy_resp_pool:
+	dma_pool_destroy(dev->resp_pool);
+
+	return ret;
+}
+
+static void erdma_device_uninit(struct erdma_dev *dev)
+{
+	dma_pool_destroy(dev->db_pool);
+	dma_pool_destroy(dev->resp_pool);
+}
+
+static void erdma_hw_reset(struct erdma_dev *dev)
+{
+	u32 ctrl = FIELD_PREP(ERDMA_REG_DEV_CTRL_RESET_MASK, 1);
+
+	erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG, ctrl);
+}
+
+static int erdma_wait_hw_init_done(struct erdma_dev *dev)
+{
+	int i;
+
+	erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG,
+			  FIELD_PREP(ERDMA_REG_DEV_CTRL_INIT_MASK, 1));
+
+	for (i = 0; i < ERDMA_WAIT_DEV_DONE_CNT; i++) {
+		if (erdma_reg_read32_filed(dev, ERDMA_REGS_DEV_ST_REG,
+					   ERDMA_REG_DEV_ST_INIT_DONE_MASK))
+			break;
+
+		msleep(ERDMA_REG_ACCESS_WAIT_MS);
+	}
+
+	if (i == ERDMA_WAIT_DEV_DONE_CNT) {
+		dev_err(&dev->pdev->dev, "wait init done failed.\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static const struct pci_device_id erdma_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_ALIBABA, 0x107f) },
+	{}
+};
+
+static int erdma_probe_dev(struct pci_dev *pdev)
+{
+	struct erdma_dev *dev;
+	int bars, err;
+	u32 version;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "pci_enable_device failed(%d)\n", err);
+		return err;
+	}
+
+	pci_set_master(pdev);
+
+	dev = ib_alloc_device(erdma_dev, ibdev);
+	if (!dev) {
+		dev_err(&pdev->dev, "ib_alloc_device failed\n");
+		err = -ENOMEM;
+		goto err_disable_device;
+	}
+
+	pci_set_drvdata(pdev, dev);
+	dev->pdev = pdev;
+
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	err = pci_request_selected_regions(pdev, bars, DRV_MODULE_NAME);
+	if (bars != ERDMA_BAR_MASK || err) {
+		err = err ? err : -EINVAL;
+		goto err_ib_device_release;
+	}
+
+	dev->func_bar_addr = pci_resource_start(pdev, ERDMA_FUNC_BAR);
+	dev->func_bar_len = pci_resource_len(pdev, ERDMA_FUNC_BAR);
+
+	dev->func_bar =
+		devm_ioremap(&pdev->dev, dev->func_bar_addr, dev->func_bar_len);
+	if (!dev->func_bar) {
+		dev_err(&pdev->dev, "devm_ioremap failed.\n");
+		err = -EFAULT;
+		goto err_release_bars;
+	}
+
+	version = erdma_reg_read32(dev, ERDMA_REGS_VERSION_REG);
+	if (version == 0) {
+		/* we knows that it is a non-functional function. */
+		err = -ENODEV;
+		goto err_iounmap_func_bar;
+	}
+
+	err = erdma_device_init(dev, pdev);
+	if (err)
+		goto err_iounmap_func_bar;
+
+	err = erdma_request_vectors(dev);
+	if (err)
+		goto err_uninit_device;
+
+	err = erdma_comm_irq_init(dev);
+	if (err)
+		goto err_free_vectors;
+
+	err = erdma_aeq_init(dev);
+	if (err)
+		goto err_uninit_comm_irq;
+
+	err = erdma_cmdq_init(dev);
+	if (err)
+		goto err_uninit_aeq;
+
+	err = erdma_wait_hw_init_done(dev);
+	if (err)
+		goto err_uninit_cmdq;
+
+	err = erdma_ceqs_init(dev);
+	if (err)
+		goto err_reset_hw;
+
+	erdma_finish_cmdq_init(dev);
+
+	return 0;
+
+err_reset_hw:
+	erdma_hw_reset(dev);
+
+err_uninit_cmdq:
+	erdma_cmdq_destroy(dev);
+
+err_uninit_aeq:
+	erdma_eq_destroy(dev, &dev->aeq);
+
+err_uninit_comm_irq:
+	erdma_comm_irq_uninit(dev);
+
+err_free_vectors:
+	pci_free_irq_vectors(dev->pdev);
+
+err_uninit_device:
+	erdma_device_uninit(dev);
+
+err_iounmap_func_bar:
+	devm_iounmap(&pdev->dev, dev->func_bar);
+
+err_release_bars:
+	pci_release_selected_regions(pdev, bars);
+
+err_ib_device_release:
+	ib_dealloc_device(&dev->ibdev);
+
+err_disable_device:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+static void erdma_remove_dev(struct pci_dev *pdev)
+{
+	struct erdma_dev *dev = pci_get_drvdata(pdev);
+
+	erdma_ceqs_uninit(dev);
+	erdma_hw_reset(dev);
+	erdma_cmdq_destroy(dev);
+	erdma_eq_destroy(dev, &dev->aeq);
+	erdma_comm_irq_uninit(dev);
+	pci_free_irq_vectors(dev->pdev);
+	erdma_device_uninit(dev);
+
+	devm_iounmap(&pdev->dev, dev->func_bar);
+	pci_release_selected_regions(pdev, ERDMA_BAR_MASK);
+
+	ib_dealloc_device(&dev->ibdev);
+
+	pci_disable_device(pdev);
+}
+
+#define ERDMA_GET_CAP(name, cap) FIELD_GET(ERDMA_CMD_DEV_CAP_##name##_MASK, cap)
+
+static int erdma_dev_attrs_init(struct erdma_dev *dev)
+{
+	int err;
+	u64 req_hdr, cap0, cap1;
+
+	erdma_cmdq_build_reqhdr(&req_hdr, CMDQ_SUBMOD_RDMA,
+				CMDQ_OPCODE_QUERY_DEVICE);
+
+	err = erdma_post_cmd_wait(&dev->cmdq, &req_hdr, sizeof(req_hdr), &cap0,
+				  &cap1, true);
+	if (err)
+		return err;
+
+	dev->attrs.max_cqe = 1 << ERDMA_GET_CAP(MAX_CQE, cap0);
+	dev->attrs.max_mr_size = 1ULL << ERDMA_GET_CAP(MAX_MR_SIZE, cap0);
+	dev->attrs.max_mw = 1 << ERDMA_GET_CAP(MAX_MW, cap1);
+	dev->attrs.max_recv_wr = 1 << ERDMA_GET_CAP(MAX_RECV_WR, cap0);
+	dev->attrs.max_gid = 1 << ERDMA_GET_CAP(MAX_GID, cap0);
+	dev->attrs.max_ah = 1 << ERDMA_GET_CAP(MAX_AH, cap0);
+	dev->attrs.local_dma_key = ERDMA_GET_CAP(DMA_LOCAL_KEY, cap1);
+	dev->attrs.cc = ERDMA_GET_CAP(DEFAULT_CC, cap1);
+	dev->attrs.max_qp = ERDMA_NQP_PER_QBLOCK * ERDMA_GET_CAP(QBLOCK, cap1);
+	dev->attrs.max_mr = dev->attrs.max_qp << 1;
+	dev->attrs.max_cq = dev->attrs.max_qp << 1;
+	dev->attrs.cap_flags = ERDMA_GET_CAP(FLAGS, cap0);
+
+	dev->attrs.max_send_wr = ERDMA_MAX_SEND_WR;
+	dev->attrs.max_ord = ERDMA_MAX_ORD;
+	dev->attrs.max_ird = ERDMA_MAX_IRD;
+	dev->attrs.max_send_sge = ERDMA_MAX_SEND_SGE;
+	dev->attrs.max_recv_sge = ERDMA_MAX_RECV_SGE;
+	dev->attrs.max_sge_rd = ERDMA_MAX_SGE_RD;
+	dev->attrs.max_pd = ERDMA_MAX_PD;
+
+	dev->res_cb[ERDMA_RES_TYPE_PD].max_cap = ERDMA_MAX_PD;
+	dev->res_cb[ERDMA_RES_TYPE_STAG_IDX].max_cap = dev->attrs.max_mr;
+	dev->res_cb[ERDMA_RES_TYPE_AH].max_cap = dev->attrs.max_ah;
+
+	erdma_cmdq_build_reqhdr(&req_hdr, CMDQ_SUBMOD_COMMON,
+				CMDQ_OPCODE_QUERY_FW_INFO);
+
+	err = erdma_post_cmd_wait(&dev->cmdq, &req_hdr, sizeof(req_hdr), &cap0,
+				  &cap1, true);
+	if (!err)
+		dev->attrs.fw_version =
+			FIELD_GET(ERDMA_CMD_INFO0_FW_VER_MASK, cap0);
+
+	return err;
+}
+
+static int erdma_device_config(struct erdma_dev *dev)
+{
+	struct erdma_cmdq_config_device_req req = {};
+
+	if (!(dev->attrs.cap_flags & ERDMA_DEV_CAP_FLAGS_EXTEND_DB))
+		return 0;
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_COMMON,
+				CMDQ_OPCODE_CONF_DEVICE);
+
+	req.cfg = FIELD_PREP(ERDMA_CMD_CONFIG_DEVICE_PGSHIFT_MASK, PAGE_SHIFT) |
+		  FIELD_PREP(ERDMA_CMD_CONFIG_DEVICE_PS_EN_MASK, 1);
+
+	return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
+				   true);
+}
+
+static int erdma_res_cb_init(struct erdma_dev *dev)
+{
+	int i, j;
+
+	for (i = 0; i < ERDMA_RES_CNT; i++) {
+		dev->res_cb[i].next_alloc_idx = 1;
+		spin_lock_init(&dev->res_cb[i].lock);
+		dev->res_cb[i].bitmap =
+			bitmap_zalloc(dev->res_cb[i].max_cap, GFP_KERNEL);
+		if (!dev->res_cb[i].bitmap)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (j = 0; j < i; j++)
+		bitmap_free(dev->res_cb[j].bitmap);
+
+	return -ENOMEM;
+}
+
+static void erdma_res_cb_free(struct erdma_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < ERDMA_RES_CNT; i++)
+		bitmap_free(dev->res_cb[i].bitmap);
+}
+
+static const struct ib_device_ops erdma_device_ops_rocev2 = {
+	.get_link_layer = erdma_get_link_layer,
+	.add_gid = erdma_add_gid,
+	.del_gid = erdma_del_gid,
+	.query_pkey = erdma_query_pkey,
+	.create_ah = erdma_create_ah,
+	.destroy_ah = erdma_destroy_ah,
+	.query_ah = erdma_query_ah,
+
+	INIT_RDMA_OBJ_SIZE(ib_ah, erdma_ah, ibah),
+};
+
+static const struct ib_device_ops erdma_device_ops_iwarp = {
+	.iw_accept = erdma_accept,
+	.iw_add_ref = erdma_qp_get_ref,
+	.iw_connect = erdma_connect,
+	.iw_create_listen = erdma_create_listen,
+	.iw_destroy_listen = erdma_destroy_listen,
+	.iw_get_qp = erdma_get_ibqp,
+	.iw_reject = erdma_reject,
+	.iw_rem_ref = erdma_qp_put_ref,
+};
+
+static const struct ib_device_ops erdma_device_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_ERDMA,
+	.uverbs_abi_ver = ERDMA_ABI_VERSION,
+
+	.alloc_hw_port_stats = erdma_alloc_hw_port_stats,
+	.alloc_mr = erdma_ib_alloc_mr,
+	.alloc_pd = erdma_alloc_pd,
+	.alloc_ucontext = erdma_alloc_ucontext,
+	.create_cq = erdma_create_cq,
+	.create_qp = erdma_create_qp,
+	.dealloc_pd = erdma_dealloc_pd,
+	.dealloc_ucontext = erdma_dealloc_ucontext,
+	.dereg_mr = erdma_dereg_mr,
+	.destroy_cq = erdma_destroy_cq,
+	.destroy_qp = erdma_destroy_qp,
+	.disassociate_ucontext = erdma_disassociate_ucontext,
+	.get_dma_mr = erdma_get_dma_mr,
+	.get_hw_stats = erdma_get_hw_stats,
+	.get_port_immutable = erdma_get_port_immutable,
+	.map_mr_sg = erdma_map_mr_sg,
+	.mmap = erdma_mmap,
+	.mmap_free = erdma_mmap_free,
+	.post_recv = erdma_post_recv,
+	.post_send = erdma_post_send,
+	.poll_cq = erdma_poll_cq,
+	.query_device = erdma_query_device,
+	.query_gid = erdma_query_gid,
+	.query_port = erdma_query_port,
+	.query_qp = erdma_query_qp,
+	.req_notify_cq = erdma_req_notify_cq,
+	.reg_user_mr = erdma_reg_user_mr,
+	.modify_qp = erdma_modify_qp,
+
+	INIT_RDMA_OBJ_SIZE(ib_cq, erdma_cq, ibcq),
+	INIT_RDMA_OBJ_SIZE(ib_pd, erdma_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_ucontext, erdma_ucontext, ibucontext),
+	INIT_RDMA_OBJ_SIZE(ib_qp, erdma_qp, ibqp),
+};
+
+static int erdma_ib_device_add(struct pci_dev *pdev)
+{
+	struct erdma_dev *dev = pci_get_drvdata(pdev);
+	struct ib_device *ibdev = &dev->ibdev;
+	u64 mac;
+	int ret;
+
+	ret = erdma_dev_attrs_init(dev);
+	if (ret)
+		return ret;
+
+	ret = erdma_device_config(dev);
+	if (ret)
+		return ret;
+
+	if (erdma_device_iwarp(dev)) {
+		ibdev->node_type = RDMA_NODE_RNIC;
+		ib_set_device_ops(ibdev, &erdma_device_ops_iwarp);
+	} else {
+		ibdev->node_type = RDMA_NODE_IB_CA;
+		ib_set_device_ops(ibdev, &erdma_device_ops_rocev2);
+	}
+
+	memcpy(ibdev->node_desc, ERDMA_NODE_DESC, sizeof(ERDMA_NODE_DESC));
+
+	/*
+	 * Current model (one-to-one device association):
+	 * One ERDMA device per net_device or, equivalently,
+	 * per physical port.
+	 */
+	ibdev->phys_port_cnt = 1;
+	ibdev->num_comp_vectors = dev->attrs.irq_num - 1;
+
+	ib_set_device_ops(ibdev, &erdma_device_ops);
+
+	INIT_LIST_HEAD(&dev->cep_list);
+
+	spin_lock_init(&dev->lock);
+	xa_init_flags(&dev->qp_xa, XA_FLAGS_ALLOC1);
+	xa_init_flags(&dev->cq_xa, XA_FLAGS_ALLOC1);
+	dev->next_alloc_cqn = 1;
+	dev->next_alloc_qpn = 1;
+
+	ret = erdma_res_cb_init(dev);
+	if (ret)
+		return ret;
+
+	atomic_set(&dev->num_ctx, 0);
+
+	mac = erdma_reg_read32(dev, ERDMA_REGS_NETDEV_MAC_L_REG);
+	mac |= (u64)erdma_reg_read32(dev, ERDMA_REGS_NETDEV_MAC_H_REG) << 32;
+
+	u64_to_ether_addr(mac, dev->attrs.peer_addr);
+
+	dev->reflush_wq = alloc_workqueue("erdma-reflush-wq", WQ_UNBOUND,
+					  WQ_UNBOUND_MAX_ACTIVE);
+	if (!dev->reflush_wq) {
+		ret = -ENOMEM;
+		goto err_alloc_workqueue;
+	}
+
+	ret = erdma_device_register(dev);
+	if (ret)
+		goto err_register;
+
+	return 0;
+
+err_register:
+	destroy_workqueue(dev->reflush_wq);
+err_alloc_workqueue:
+	xa_destroy(&dev->qp_xa);
+	xa_destroy(&dev->cq_xa);
+
+	erdma_res_cb_free(dev);
+
+	return ret;
+}
+
+static void erdma_ib_device_remove(struct pci_dev *pdev)
+{
+	struct erdma_dev *dev = pci_get_drvdata(pdev);
+
+	unregister_netdevice_notifier(&dev->netdev_nb);
+	ib_unregister_device(&dev->ibdev);
+
+	destroy_workqueue(dev->reflush_wq);
+	erdma_res_cb_free(dev);
+	xa_destroy(&dev->qp_xa);
+	xa_destroy(&dev->cq_xa);
+}
+
+static int erdma_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int ret;
+
+	ret = erdma_probe_dev(pdev);
+	if (ret)
+		return ret;
+
+	ret = erdma_ib_device_add(pdev);
+	if (ret) {
+		erdma_remove_dev(pdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void erdma_remove(struct pci_dev *pdev)
+{
+	erdma_ib_device_remove(pdev);
+	erdma_remove_dev(pdev);
+}
+
+static struct pci_driver erdma_pci_driver = {
+	.name = DRV_MODULE_NAME,
+	.id_table = erdma_pci_tbl,
+	.probe = erdma_probe,
+	.remove = erdma_remove
+};
+
+MODULE_DEVICE_TABLE(pci, erdma_pci_tbl);
+
+static __init int erdma_init_module(void)
+{
+	int ret;
+
+	ret = erdma_cm_init();
+	if (ret)
+		return ret;
+
+	ret = pci_register_driver(&erdma_pci_driver);
+	if (ret)
+		erdma_cm_exit();
+
+	return ret;
+}
+
+static void __exit erdma_exit_module(void)
+{
+	pci_unregister_driver(&erdma_pci_driver);
+
+	erdma_cm_exit();
+}
+
+module_init(erdma_init_module);
+module_exit(erdma_exit_module);

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_qp.c

@@ -0,0 +1,757 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2021, Alibaba Group */
+/* Authors: Bernard Metzler <bmt@zurich.ibm.com> */
+/* Copyright (c) 2008-2019, IBM Corporation */
+
+#include "erdma_cm.h"
+#include "erdma_verbs.h"
+
+void erdma_qp_llp_close(struct erdma_qp *qp)
+{
+	struct erdma_mod_qp_params_iwarp params;
+
+	down_write(&qp->state_lock);
+
+	switch (qp->attrs.iwarp.state) {
+	case ERDMA_QPS_IWARP_RTS:
+	case ERDMA_QPS_IWARP_RTR:
+	case ERDMA_QPS_IWARP_IDLE:
+	case ERDMA_QPS_IWARP_TERMINATE:
+		params.state = ERDMA_QPS_IWARP_CLOSING;
+		erdma_modify_qp_state_iwarp(qp, &params, ERDMA_QPA_IWARP_STATE);
+		break;
+	case ERDMA_QPS_IWARP_CLOSING:
+		qp->attrs.iwarp.state = ERDMA_QPS_IWARP_IDLE;
+		break;
+	default:
+		break;
+	}
+
+	if (qp->cep) {
+		erdma_cep_put(qp->cep);
+		qp->cep = NULL;
+	}
+
+	up_write(&qp->state_lock);
+}
+
+struct ib_qp *erdma_get_ibqp(struct ib_device *ibdev, int id)
+{
+	struct erdma_qp *qp = find_qp_by_qpn(to_edev(ibdev), id);
+
+	if (qp)
+		return &qp->ibqp;
+
+	return NULL;
+}
+
+static int
+erdma_modify_qp_state_to_rts(struct erdma_qp *qp,
+			     struct erdma_mod_qp_params_iwarp *params,
+			     enum erdma_qpa_mask_iwarp mask)
+{
+	int ret;
+	struct erdma_dev *dev = qp->dev;
+	struct erdma_cmdq_modify_qp_req req;
+	struct tcp_sock *tp;
+	struct erdma_cep *cep = qp->cep;
+	struct sockaddr_storage local_addr, remote_addr;
+
+	if (!(mask & ERDMA_QPA_IWARP_LLP_HANDLE))
+		return -EINVAL;
+
+	if (!(mask & ERDMA_QPA_IWARP_MPA))
+		return -EINVAL;
+
+	if (!(mask & ERDMA_QPA_IWARP_CC))
+		params->cc = qp->attrs.cc;
+
+	ret = getname_local(cep->sock, &local_addr);
+	if (ret < 0)
+		return ret;
+
+	ret = getname_peer(cep->sock, &remote_addr);
+	if (ret < 0)
+		return ret;
+
+	tp = tcp_sk(qp->cep->sock->sk);
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA,
+				CMDQ_OPCODE_MODIFY_QP);
+
+	req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, params->state) |
+		  FIELD_PREP(ERDMA_CMD_MODIFY_QP_CC_MASK, params->cc) |
+		  FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp));
+
+	req.cookie = be32_to_cpu(cep->mpa.ext_data.cookie);
+	req.dip = to_sockaddr_in(remote_addr).sin_addr.s_addr;
+	req.sip = to_sockaddr_in(local_addr).sin_addr.s_addr;
+	req.dport = to_sockaddr_in(remote_addr).sin_port;
+	req.sport = to_sockaddr_in(local_addr).sin_port;
+
+	req.send_nxt = tp->snd_nxt;
+	/* rsvd tcp seq for mpa-rsp in server. */
+	if (params->qp_type == ERDMA_QP_PASSIVE)
+		req.send_nxt += MPA_DEFAULT_HDR_LEN + params->pd_len;
+	req.recv_nxt = tp->rcv_nxt;
+
+	ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
+				  true);
+	if (ret)
+		return ret;
+
+	if (mask & ERDMA_QPA_IWARP_IRD)
+		qp->attrs.irq_size = params->irq_size;
+
+	if (mask & ERDMA_QPA_IWARP_ORD)
+		qp->attrs.orq_size = params->orq_size;
+
+	if (mask & ERDMA_QPA_IWARP_CC)
+		qp->attrs.cc = params->cc;
+
+	qp->attrs.iwarp.state = ERDMA_QPS_IWARP_RTS;
+
+	return 0;
+}
+
+static int
+erdma_modify_qp_state_to_stop(struct erdma_qp *qp,
+			      struct erdma_mod_qp_params_iwarp *params,
+			      enum erdma_qpa_mask_iwarp mask)
+{
+	struct erdma_dev *dev = qp->dev;
+	struct erdma_cmdq_modify_qp_req req;
+	int ret;
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA,
+				CMDQ_OPCODE_MODIFY_QP);
+
+	req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, params->state) |
+		  FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp));
+
+	ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
+				  true);
+	if (ret)
+		return ret;
+
+	qp->attrs.iwarp.state = params->state;
+
+	return 0;
+}
+
+int erdma_modify_qp_state_iwarp(struct erdma_qp *qp,
+				struct erdma_mod_qp_params_iwarp *params,
+				int mask)
+{
+	bool need_reflush = false;
+	int drop_conn, ret = 0;
+
+	if (!mask)
+		return 0;
+
+	if (!(mask & ERDMA_QPA_IWARP_STATE))
+		return 0;
+
+	switch (qp->attrs.iwarp.state) {
+	case ERDMA_QPS_IWARP_IDLE:
+	case ERDMA_QPS_IWARP_RTR:
+		if (params->state == ERDMA_QPS_IWARP_RTS) {
+			ret = erdma_modify_qp_state_to_rts(qp, params, mask);
+		} else if (params->state == ERDMA_QPS_IWARP_ERROR) {
+			qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR;
+			need_reflush = true;
+			if (qp->cep) {
+				erdma_cep_put(qp->cep);
+				qp->cep = NULL;
+			}
+			ret = erdma_modify_qp_state_to_stop(qp, params, mask);
+		}
+		break;
+	case ERDMA_QPS_IWARP_RTS:
+		drop_conn = 0;
+
+		if (params->state == ERDMA_QPS_IWARP_CLOSING ||
+		    params->state == ERDMA_QPS_IWARP_TERMINATE ||
+		    params->state == ERDMA_QPS_IWARP_ERROR) {
+			ret = erdma_modify_qp_state_to_stop(qp, params, mask);
+			drop_conn = 1;
+			need_reflush = true;
+		}
+
+		if (drop_conn)
+			erdma_qp_cm_drop(qp);
+
+		break;
+	case ERDMA_QPS_IWARP_TERMINATE:
+		if (params->state == ERDMA_QPS_IWARP_ERROR)
+			qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR;
+		break;
+	case ERDMA_QPS_IWARP_CLOSING:
+		if (params->state == ERDMA_QPS_IWARP_IDLE) {
+			qp->attrs.iwarp.state = ERDMA_QPS_IWARP_IDLE;
+		} else if (params->state == ERDMA_QPS_IWARP_ERROR) {
+			ret = erdma_modify_qp_state_to_stop(qp, params, mask);
+			qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR;
+		} else if (params->state != ERDMA_QPS_IWARP_CLOSING) {
+			return -ECONNABORTED;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (need_reflush && !ret && rdma_is_kernel_res(&qp->ibqp.res)) {
+		qp->flags |= ERDMA_QP_IN_FLUSHING;
+		mod_delayed_work(qp->dev->reflush_wq, &qp->reflush_dwork,
+				 usecs_to_jiffies(100));
+	}
+
+	return ret;
+}
+
+static int modify_qp_cmd_rocev2(struct erdma_qp *qp,
+				struct erdma_mod_qp_params_rocev2 *params,
+				enum erdma_qpa_mask_rocev2 attr_mask)
+{
+	struct erdma_cmdq_mod_qp_req_rocev2 req;
+
+	memset(&req, 0, sizeof(req));
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA,
+				CMDQ_OPCODE_MODIFY_QP);
+
+	req.cfg0 = FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp));
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_STATE)
+		req.cfg0 |= FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK,
+				       params->state);
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_DST_QPN)
+		req.cfg1 = FIELD_PREP(ERDMA_CMD_MODIFY_QP_DQPN_MASK,
+				      params->dst_qpn);
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_QKEY)
+		req.qkey = params->qkey;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_AV)
+		erdma_set_av_cfg(&req.av_cfg, &params->av);
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_SQ_PSN)
+		req.sq_psn = params->sq_psn;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_RQ_PSN)
+		req.rq_psn = params->rq_psn;
+
+	req.attr_mask = attr_mask;
+
+	return erdma_post_cmd_wait(&qp->dev->cmdq, &req, sizeof(req), NULL,
+				   NULL, true);
+}
+
+static void erdma_reset_qp(struct erdma_qp *qp)
+{
+	qp->kern_qp.sq_pi = 0;
+	qp->kern_qp.sq_ci = 0;
+	qp->kern_qp.rq_pi = 0;
+	qp->kern_qp.rq_ci = 0;
+	memset(qp->kern_qp.swr_tbl, 0, qp->attrs.sq_size * sizeof(u64));
+	memset(qp->kern_qp.rwr_tbl, 0, qp->attrs.rq_size * sizeof(u64));
+	memset(qp->kern_qp.sq_buf, 0, qp->attrs.sq_size << SQEBB_SHIFT);
+	memset(qp->kern_qp.rq_buf, 0, qp->attrs.rq_size << RQE_SHIFT);
+	erdma_remove_cqes_of_qp(&qp->scq->ibcq, QP_ID(qp));
+	if (qp->rcq != qp->scq)
+		erdma_remove_cqes_of_qp(&qp->rcq->ibcq, QP_ID(qp));
+}
+
+int erdma_modify_qp_state_rocev2(struct erdma_qp *qp,
+				 struct erdma_mod_qp_params_rocev2 *params,
+				 int attr_mask)
+{
+	struct erdma_dev *dev = to_edev(qp->ibqp.device);
+	int ret;
+
+	ret = modify_qp_cmd_rocev2(qp, params, attr_mask);
+	if (ret)
+		return ret;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_STATE)
+		qp->attrs.rocev2.state = params->state;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_QKEY)
+		qp->attrs.rocev2.qkey = params->qkey;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_DST_QPN)
+		qp->attrs.rocev2.dst_qpn = params->dst_qpn;
+
+	if (attr_mask & ERDMA_QPA_ROCEV2_AV)
+		memcpy(&qp->attrs.rocev2.av, &params->av,
+		       sizeof(struct erdma_av));
+
+	if (rdma_is_kernel_res(&qp->ibqp.res) &&
+	    params->state == ERDMA_QPS_ROCEV2_RESET)
+		erdma_reset_qp(qp);
+
+	if (rdma_is_kernel_res(&qp->ibqp.res) &&
+	    params->state == ERDMA_QPS_ROCEV2_ERROR) {
+		qp->flags |= ERDMA_QP_IN_FLUSHING;
+		mod_delayed_work(dev->reflush_wq, &qp->reflush_dwork,
+				 usecs_to_jiffies(100));
+	}
+
+	return 0;
+}
+
+static void erdma_qp_safe_free(struct kref *ref)
+{
+	struct erdma_qp *qp = container_of(ref, struct erdma_qp, ref);
+
+	complete(&qp->safe_free);
+}
+
+void erdma_qp_put(struct erdma_qp *qp)
+{
+	WARN_ON(kref_read(&qp->ref) < 1);
+	kref_put(&qp->ref, erdma_qp_safe_free);
+}
+
+void erdma_qp_get(struct erdma_qp *qp)
+{
+	kref_get(&qp->ref);
+}
+
+static int fill_inline_data(struct erdma_qp *qp,
+			    const struct ib_send_wr *send_wr, u16 wqe_idx,
+			    u32 sgl_offset, __le32 *length_field)
+{
+	u32 remain_size, copy_size, data_off, bytes = 0;
+	char *data;
+	int i = 0;
+
+	wqe_idx += (sgl_offset >> SQEBB_SHIFT);
+	sgl_offset &= (SQEBB_SIZE - 1);
+	data = get_queue_entry(qp->kern_qp.sq_buf, wqe_idx, qp->attrs.sq_size,
+			       SQEBB_SHIFT);
+
+	while (i < send_wr->num_sge) {
+		bytes += send_wr->sg_list[i].length;
+		if (bytes > (int)ERDMA_MAX_INLINE)
+			return -EINVAL;
+
+		remain_size = send_wr->sg_list[i].length;
+		data_off = 0;
+
+		while (1) {
+			copy_size = min(remain_size, SQEBB_SIZE - sgl_offset);
+
+			memcpy(data + sgl_offset,
+			       (void *)(uintptr_t)send_wr->sg_list[i].addr +
+				       data_off,
+			       copy_size);
+			remain_size -= copy_size;
+			data_off += copy_size;
+			sgl_offset += copy_size;
+			wqe_idx += (sgl_offset >> SQEBB_SHIFT);
+			sgl_offset &= (SQEBB_SIZE - 1);
+
+			data = get_queue_entry(qp->kern_qp.sq_buf, wqe_idx,
+					       qp->attrs.sq_size, SQEBB_SHIFT);
+			if (!remain_size)
+				break;
+		}
+
+		i++;
+	}
+	*length_field = cpu_to_le32(bytes);
+
+	return bytes;
+}
+
+static int fill_sgl(struct erdma_qp *qp, const struct ib_send_wr *send_wr,
+		    u16 wqe_idx, u32 sgl_offset, __le32 *length_field)
+{
+	int i = 0;
+	u32 bytes = 0;
+	char *sgl;
+
+	if (send_wr->num_sge > qp->dev->attrs.max_send_sge)
+		return -EINVAL;
+
+	if (sgl_offset & 0xF)
+		return -EINVAL;
+
+	while (i < send_wr->num_sge) {
+		wqe_idx += (sgl_offset >> SQEBB_SHIFT);
+		sgl_offset &= (SQEBB_SIZE - 1);
+		sgl = get_queue_entry(qp->kern_qp.sq_buf, wqe_idx,
+				      qp->attrs.sq_size, SQEBB_SHIFT);
+
+		bytes += send_wr->sg_list[i].length;
+		memcpy(sgl + sgl_offset, &send_wr->sg_list[i],
+		       sizeof(struct ib_sge));
+
+		sgl_offset += sizeof(struct ib_sge);
+		i++;
+	}
+
+	*length_field = cpu_to_le32(bytes);
+	return 0;
+}
+
+static void init_send_sqe_rc(struct erdma_qp *qp, struct erdma_send_sqe_rc *sqe,
+			     const struct ib_send_wr *wr, u32 *hw_op)
+{
+	u32 op = ERDMA_OP_SEND;
+
+	if (wr->opcode == IB_WR_SEND_WITH_IMM) {
+		op = ERDMA_OP_SEND_WITH_IMM;
+		sqe->imm_data = wr->ex.imm_data;
+	} else if (wr->opcode == IB_WR_SEND_WITH_INV) {
+		op = ERDMA_OP_SEND_WITH_INV;
+		sqe->invalid_stag = cpu_to_le32(wr->ex.invalidate_rkey);
+	}
+
+	*hw_op = op;
+}
+
+static void init_send_sqe_ud(struct erdma_qp *qp, struct erdma_send_sqe_ud *sqe,
+			     const struct ib_send_wr *wr, u32 *hw_op)
+{
+	const struct ib_ud_wr *uwr = ud_wr(wr);
+	struct erdma_ah *ah = to_eah(uwr->ah);
+	u32 op = ERDMA_OP_SEND;
+
+	if (wr->opcode == IB_WR_SEND_WITH_IMM) {
+		op = ERDMA_OP_SEND_WITH_IMM;
+		sqe->imm_data = wr->ex.imm_data;
+	}
+
+	*hw_op = op;
+
+	sqe->ahn = cpu_to_le32(ah->ahn);
+	sqe->dst_qpn = cpu_to_le32(uwr->remote_qpn);
+	/* Not allowed to send control qkey */
+	if (uwr->remote_qkey & 0x80000000)
+		sqe->qkey = cpu_to_le32(qp->attrs.rocev2.qkey);
+	else
+		sqe->qkey = cpu_to_le32(uwr->remote_qkey);
+}
+
+static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi,
+			      const struct ib_send_wr *send_wr)
+{
+	u32 wqe_size, wqebb_cnt, hw_op, flags, sgl_offset;
+	u32 idx = *pi & (qp->attrs.sq_size - 1);
+	enum ib_wr_opcode op = send_wr->opcode;
+	struct erdma_send_sqe_rc *rc_send_sqe;
+	struct erdma_send_sqe_ud *ud_send_sqe;
+	struct erdma_atomic_sqe *atomic_sqe;
+	struct erdma_readreq_sqe *read_sqe;
+	struct erdma_reg_mr_sqe *regmr_sge;
+	struct erdma_write_sqe *write_sqe;
+	struct ib_rdma_wr *rdma_wr;
+	struct erdma_sge *sge;
+	__le32 *length_field;
+	struct erdma_mr *mr;
+	u64 wqe_hdr, *entry;
+	u32 attrs;
+	int ret;
+
+	if (qp->ibqp.qp_type != IB_QPT_RC && send_wr->opcode != IB_WR_SEND &&
+	    send_wr->opcode != IB_WR_SEND_WITH_IMM)
+		return -EINVAL;
+
+	entry = get_queue_entry(qp->kern_qp.sq_buf, idx, qp->attrs.sq_size,
+				SQEBB_SHIFT);
+
+	/* Clear the SQE header section. */
+	*entry = 0;
+
+	qp->kern_qp.swr_tbl[idx] = send_wr->wr_id;
+	flags = send_wr->send_flags;
+	wqe_hdr = FIELD_PREP(
+		ERDMA_SQE_HDR_CE_MASK,
+		((flags & IB_SEND_SIGNALED) || qp->kern_qp.sig_all) ? 1 : 0);
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_SE_MASK,
+			      flags & IB_SEND_SOLICITED ? 1 : 0);
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_FENCE_MASK,
+			      flags & IB_SEND_FENCE ? 1 : 0);
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_INLINE_MASK,
+			      flags & IB_SEND_INLINE ? 1 : 0);
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_QPN_MASK, QP_ID(qp));
+
+	switch (op) {
+	case IB_WR_RDMA_WRITE:
+	case IB_WR_RDMA_WRITE_WITH_IMM:
+		hw_op = ERDMA_OP_WRITE;
+		if (op == IB_WR_RDMA_WRITE_WITH_IMM)
+			hw_op = ERDMA_OP_WRITE_WITH_IMM;
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, hw_op);
+		rdma_wr = container_of(send_wr, struct ib_rdma_wr, wr);
+		write_sqe = (struct erdma_write_sqe *)entry;
+
+		write_sqe->imm_data = send_wr->ex.imm_data;
+		write_sqe->sink_stag = cpu_to_le32(rdma_wr->rkey);
+		write_sqe->sink_to_h =
+			cpu_to_le32(upper_32_bits(rdma_wr->remote_addr));
+		write_sqe->sink_to_l =
+			cpu_to_le32(lower_32_bits(rdma_wr->remote_addr));
+
+		length_field = &write_sqe->length;
+		wqe_size = sizeof(struct erdma_write_sqe);
+		sgl_offset = wqe_size;
+		break;
+	case IB_WR_RDMA_READ:
+	case IB_WR_RDMA_READ_WITH_INV:
+		read_sqe = (struct erdma_readreq_sqe *)entry;
+		if (unlikely(send_wr->num_sge != 1))
+			return -EINVAL;
+		hw_op = ERDMA_OP_READ;
+		if (op == IB_WR_RDMA_READ_WITH_INV) {
+			hw_op = ERDMA_OP_READ_WITH_INV;
+			read_sqe->invalid_stag =
+				cpu_to_le32(send_wr->ex.invalidate_rkey);
+		}
+
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, hw_op);
+		rdma_wr = container_of(send_wr, struct ib_rdma_wr, wr);
+		read_sqe->length = cpu_to_le32(send_wr->sg_list[0].length);
+		read_sqe->sink_stag = cpu_to_le32(send_wr->sg_list[0].lkey);
+		read_sqe->sink_to_l =
+			cpu_to_le32(lower_32_bits(send_wr->sg_list[0].addr));
+		read_sqe->sink_to_h =
+			cpu_to_le32(upper_32_bits(send_wr->sg_list[0].addr));
+
+		sge = get_queue_entry(qp->kern_qp.sq_buf, idx + 1,
+				      qp->attrs.sq_size, SQEBB_SHIFT);
+		sge->addr = cpu_to_le64(rdma_wr->remote_addr);
+		sge->key = cpu_to_le32(rdma_wr->rkey);
+		sge->length = cpu_to_le32(send_wr->sg_list[0].length);
+		wqe_size = sizeof(struct erdma_readreq_sqe) +
+			   send_wr->num_sge * sizeof(struct ib_sge);
+
+		goto out;
+	case IB_WR_SEND:
+	case IB_WR_SEND_WITH_IMM:
+	case IB_WR_SEND_WITH_INV:
+		if (qp->ibqp.qp_type == IB_QPT_RC) {
+			rc_send_sqe = (struct erdma_send_sqe_rc *)entry;
+			init_send_sqe_rc(qp, rc_send_sqe, send_wr, &hw_op);
+			length_field = &rc_send_sqe->length;
+			wqe_size = sizeof(struct erdma_send_sqe_rc);
+		} else {
+			ud_send_sqe = (struct erdma_send_sqe_ud *)entry;
+			init_send_sqe_ud(qp, ud_send_sqe, send_wr, &hw_op);
+			length_field = &ud_send_sqe->length;
+			wqe_size = sizeof(struct erdma_send_sqe_ud);
+		}
+
+		sgl_offset = wqe_size;
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, hw_op);
+		break;
+	case IB_WR_REG_MR:
+		wqe_hdr |=
+			FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, ERDMA_OP_REG_MR);
+		regmr_sge = (struct erdma_reg_mr_sqe *)entry;
+		mr = to_emr(reg_wr(send_wr)->mr);
+
+		mr->access = ERDMA_MR_ACC_LR |
+			     to_erdma_access_flags(reg_wr(send_wr)->access);
+		regmr_sge->addr = cpu_to_le64(mr->ibmr.iova);
+		regmr_sge->length = cpu_to_le32(mr->ibmr.length);
+		regmr_sge->stag = cpu_to_le32(reg_wr(send_wr)->key);
+		attrs = FIELD_PREP(ERDMA_SQE_MR_ACCESS_MASK, mr->access) |
+			FIELD_PREP(ERDMA_SQE_MR_MTT_CNT_MASK,
+				   mr->mem.mtt_nents);
+
+		if (mr->mem.mtt_nents <= ERDMA_MAX_INLINE_MTT_ENTRIES) {
+			attrs |= FIELD_PREP(ERDMA_SQE_MR_MTT_TYPE_MASK, 0);
+			/* Copy SGLs to SQE content to accelerate */
+			memcpy(get_queue_entry(qp->kern_qp.sq_buf, idx + 1,
+					       qp->attrs.sq_size, SQEBB_SHIFT),
+			       mr->mem.mtt->buf, MTT_SIZE(mr->mem.mtt_nents));
+			wqe_size = sizeof(struct erdma_reg_mr_sqe) +
+				   MTT_SIZE(mr->mem.mtt_nents);
+		} else {
+			attrs |= FIELD_PREP(ERDMA_SQE_MR_MTT_TYPE_MASK, 1);
+			wqe_size = sizeof(struct erdma_reg_mr_sqe);
+		}
+
+		regmr_sge->attrs = cpu_to_le32(attrs);
+		goto out;
+	case IB_WR_LOCAL_INV:
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK,
+				      ERDMA_OP_LOCAL_INV);
+		regmr_sge = (struct erdma_reg_mr_sqe *)entry;
+		regmr_sge->stag = cpu_to_le32(send_wr->ex.invalidate_rkey);
+		wqe_size = sizeof(struct erdma_reg_mr_sqe);
+		goto out;
+	case IB_WR_ATOMIC_CMP_AND_SWP:
+	case IB_WR_ATOMIC_FETCH_AND_ADD:
+		atomic_sqe = (struct erdma_atomic_sqe *)entry;
+		if (op == IB_WR_ATOMIC_CMP_AND_SWP) {
+			wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK,
+					      ERDMA_OP_ATOMIC_CAS);
+			atomic_sqe->fetchadd_swap_data =
+				cpu_to_le64(atomic_wr(send_wr)->swap);
+			atomic_sqe->cmp_data =
+				cpu_to_le64(atomic_wr(send_wr)->compare_add);
+		} else {
+			wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK,
+					      ERDMA_OP_ATOMIC_FAA);
+			atomic_sqe->fetchadd_swap_data =
+				cpu_to_le64(atomic_wr(send_wr)->compare_add);
+		}
+
+		sge = get_queue_entry(qp->kern_qp.sq_buf, idx + 1,
+				      qp->attrs.sq_size, SQEBB_SHIFT);
+		sge->addr = cpu_to_le64(atomic_wr(send_wr)->remote_addr);
+		sge->key = cpu_to_le32(atomic_wr(send_wr)->rkey);
+		sge++;
+
+		sge->addr = cpu_to_le64(send_wr->sg_list[0].addr);
+		sge->key = cpu_to_le32(send_wr->sg_list[0].lkey);
+		sge->length = cpu_to_le32(send_wr->sg_list[0].length);
+
+		wqe_size = sizeof(*atomic_sqe);
+		goto out;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (flags & IB_SEND_INLINE) {
+		ret = fill_inline_data(qp, send_wr, idx, sgl_offset,
+				       length_field);
+		if (ret < 0)
+			return -EINVAL;
+		wqe_size += ret;
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_SGL_LEN_MASK, ret);
+	} else {
+		ret = fill_sgl(qp, send_wr, idx, sgl_offset, length_field);
+		if (ret)
+			return -EINVAL;
+		wqe_size += send_wr->num_sge * sizeof(struct ib_sge);
+		wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_SGL_LEN_MASK,
+				      send_wr->num_sge);
+	}
+
+out:
+	wqebb_cnt = SQEBB_COUNT(wqe_size);
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_WQEBB_CNT_MASK, wqebb_cnt - 1);
+	*pi += wqebb_cnt;
+	wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_WQEBB_INDEX_MASK, *pi);
+
+	*entry = wqe_hdr;
+
+	return 0;
+}
+
+static void kick_sq_db(struct erdma_qp *qp, u16 pi)
+{
+	u64 db_data = FIELD_PREP(ERDMA_SQE_HDR_QPN_MASK, QP_ID(qp)) |
+		      FIELD_PREP(ERDMA_SQE_HDR_WQEBB_INDEX_MASK, pi);
+
+	*(u64 *)qp->kern_qp.sq_dbrec = db_data;
+	writeq(db_data, qp->kern_qp.hw_sq_db);
+}
+
+int erdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *send_wr,
+		    const struct ib_send_wr **bad_send_wr)
+{
+	struct erdma_qp *qp = to_eqp(ibqp);
+	int ret = 0;
+	const struct ib_send_wr *wr = send_wr;
+	unsigned long flags;
+	u16 sq_pi;
+
+	if (!send_wr)
+		return -EINVAL;
+
+	spin_lock_irqsave(&qp->lock, flags);
+	sq_pi = qp->kern_qp.sq_pi;
+
+	while (wr) {
+		if ((u16)(sq_pi - qp->kern_qp.sq_ci) >= qp->attrs.sq_size) {
+			ret = -ENOMEM;
+			*bad_send_wr = send_wr;
+			break;
+		}
+
+		ret = erdma_push_one_sqe(qp, &sq_pi, wr);
+		if (ret) {
+			*bad_send_wr = wr;
+			break;
+		}
+		qp->kern_qp.sq_pi = sq_pi;
+		kick_sq_db(qp, sq_pi);
+
+		wr = wr->next;
+	}
+	spin_unlock_irqrestore(&qp->lock, flags);
+
+	if (unlikely(qp->flags & ERDMA_QP_IN_FLUSHING))
+		mod_delayed_work(qp->dev->reflush_wq, &qp->reflush_dwork,
+				 usecs_to_jiffies(100));
+
+	return ret;
+}
+
+static int erdma_post_recv_one(struct erdma_qp *qp,
+			       const struct ib_recv_wr *recv_wr)
+{
+	struct erdma_rqe *rqe =
+		get_queue_entry(qp->kern_qp.rq_buf, qp->kern_qp.rq_pi,
+				qp->attrs.rq_size, RQE_SHIFT);
+
+	rqe->qe_idx = cpu_to_le16(qp->kern_qp.rq_pi + 1);
+	rqe->qpn = cpu_to_le32(QP_ID(qp));
+
+	if (recv_wr->num_sge == 0) {
+		rqe->length = 0;
+	} else if (recv_wr->num_sge == 1) {
+		rqe->stag = cpu_to_le32(recv_wr->sg_list[0].lkey);
+		rqe->to = cpu_to_le64(recv_wr->sg_list[0].addr);
+		rqe->length = cpu_to_le32(recv_wr->sg_list[0].length);
+	} else {
+		return -EINVAL;
+	}
+
+	*(u64 *)qp->kern_qp.rq_dbrec = *(u64 *)rqe;
+	writeq(*(u64 *)rqe, qp->kern_qp.hw_rq_db);
+
+	qp->kern_qp.rwr_tbl[qp->kern_qp.rq_pi & (qp->attrs.rq_size - 1)] =
+		recv_wr->wr_id;
+	qp->kern_qp.rq_pi++;
+
+	return 0;
+}
+
+int erdma_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *recv_wr,
+		    const struct ib_recv_wr **bad_recv_wr)
+{
+	const struct ib_recv_wr *wr = recv_wr;
+	struct erdma_qp *qp = to_eqp(ibqp);
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&qp->lock, flags);
+
+	while (wr) {
+		ret = erdma_post_recv_one(qp, wr);
+		if (ret) {
+			*bad_recv_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+
+	spin_unlock_irqrestore(&qp->lock, flags);
+
+	if (unlikely(qp->flags & ERDMA_QP_IN_FLUSHING))
+		mod_delayed_work(qp->dev->reflush_wq, &qp->reflush_dwork,
+				 usecs_to_jiffies(100));
+
+	return ret;
+}

linux-7.2.3/drivers/infiniband/hw/erdma/erdma_verbs.h

@@ -0,0 +1,491 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#ifndef __ERDMA_VERBS_H__
+#define __ERDMA_VERBS_H__
+
+#include "erdma.h"
+
+/* RDMA Capability. */
+#define ERDMA_MAX_PD (128 * 1024)
+#define ERDMA_MAX_SEND_WR 8192
+#define ERDMA_MAX_ORD 128
+#define ERDMA_MAX_IRD 128
+#define ERDMA_MAX_SGE_RD 1
+#define ERDMA_MAX_CONTEXT (128 * 1024)
+#define ERDMA_MAX_SEND_SGE 6
+#define ERDMA_MAX_RECV_SGE 1
+#define ERDMA_MAX_INLINE (sizeof(struct erdma_sge) * (ERDMA_MAX_SEND_SGE))
+#define ERDMA_MAX_FRMR_PA 512
+
+enum {
+	ERDMA_MMAP_IO_NC = 0, /* no cache */
+};
+
+struct erdma_user_mmap_entry {
+	struct rdma_user_mmap_entry rdma_entry;
+	u64 address;
+	u8 mmap_flag;
+};
+
+struct erdma_ext_db_info {
+	bool enable;
+	u16 sdb_off;
+	u16 rdb_off;
+	u16 cdb_off;
+};
+
+struct erdma_ucontext {
+	struct ib_ucontext ibucontext;
+
+	struct erdma_ext_db_info ext_db;
+
+	u64 sdb;
+	u64 rdb;
+	u64 cdb;
+
+	struct rdma_user_mmap_entry *sq_db_mmap_entry;
+	struct rdma_user_mmap_entry *rq_db_mmap_entry;
+	struct rdma_user_mmap_entry *cq_db_mmap_entry;
+
+	/* doorbell records */
+	struct list_head dbrecords_page_list;
+	struct mutex dbrecords_page_mutex;
+};
+
+struct erdma_pd {
+	struct ib_pd ibpd;
+	u32 pdn;
+};
+
+/*
+ * MemoryRegion definition.
+ */
+#define ERDMA_MAX_INLINE_MTT_ENTRIES 4
+#define MTT_SIZE(mtt_cnt) ((mtt_cnt) << 3) /* per mtt entry takes 8 Bytes. */
+#define ERDMA_MR_MAX_MTT_CNT 524288
+#define ERDMA_MTT_ENTRY_SIZE 8
+
+#define ERDMA_MR_TYPE_NORMAL 0
+#define ERDMA_MR_TYPE_FRMR 1
+#define ERDMA_MR_TYPE_DMA 2
+
+#define ERDMA_MR_MTT_0LEVEL 0
+#define ERDMA_MR_MTT_1LEVEL 1
+
+#define ERDMA_MR_ACC_RA BIT(0)
+#define ERDMA_MR_ACC_LR BIT(1)
+#define ERDMA_MR_ACC_LW BIT(2)
+#define ERDMA_MR_ACC_RR BIT(3)
+#define ERDMA_MR_ACC_RW BIT(4)
+
+static inline u8 to_erdma_access_flags(int access)
+{
+	return (access & IB_ACCESS_REMOTE_READ ? ERDMA_MR_ACC_RR : 0) |
+	       (access & IB_ACCESS_LOCAL_WRITE ? ERDMA_MR_ACC_LW : 0) |
+	       (access & IB_ACCESS_REMOTE_WRITE ? ERDMA_MR_ACC_RW : 0) |
+	       (access & IB_ACCESS_REMOTE_ATOMIC ? ERDMA_MR_ACC_RA : 0);
+}
+
+/* Hierarchical storage structure for MTT entries */
+struct erdma_mtt {
+	u64 *buf;
+	size_t size;
+
+	bool continuous;
+	union {
+		dma_addr_t buf_dma;
+		struct {
+			dma_addr_t *dma_addrs;
+			u32 npages;
+			u32 level;
+		};
+	};
+
+	struct erdma_mtt *low_level;
+};
+
+struct erdma_mem {
+	struct ib_umem *umem;
+	struct erdma_mtt *mtt;
+
+	u32 page_size;
+	u32 page_offset;
+	u32 page_cnt;
+	u32 mtt_nents;
+
+	u64 va;
+	u64 len;
+};
+
+struct erdma_mr {
+	struct ib_mr ibmr;
+	struct erdma_mem mem;
+	u8 type;
+	u8 access;
+	u8 valid;
+};
+
+struct erdma_user_dbrecords_page {
+	struct list_head list;
+	struct ib_umem *umem;
+	u64 va;
+	int refcnt;
+};
+
+struct erdma_av {
+	u8 port;
+	u8 hop_limit;
+	u8 traffic_class;
+	u8 sl;
+	u8 sgid_index;
+	u16 udp_sport;
+	u32 flow_label;
+	u8 dmac[ETH_ALEN];
+	u8 dgid[ERDMA_ROCEV2_GID_SIZE];
+	enum erdma_network_type ntype;
+};
+
+struct erdma_ah {
+	struct ib_ah ibah;
+	struct erdma_av av;
+	u32 ahn;
+};
+
+struct erdma_uqp {
+	struct erdma_mem sq_mem;
+	struct erdma_mem rq_mem;
+
+	dma_addr_t sq_dbrec_dma;
+	dma_addr_t rq_dbrec_dma;
+
+	struct erdma_user_dbrecords_page *user_dbr_page;
+
+	u32 rq_offset;
+};
+
+struct erdma_kqp {
+	u16 sq_pi;
+	u16 sq_ci;
+
+	u16 rq_pi;
+	u16 rq_ci;
+
+	u64 *swr_tbl;
+	u64 *rwr_tbl;
+
+	void __iomem *hw_sq_db;
+	void __iomem *hw_rq_db;
+
+	void *sq_buf;
+	dma_addr_t sq_buf_dma_addr;
+
+	void *rq_buf;
+	dma_addr_t rq_buf_dma_addr;
+
+	void *sq_dbrec;
+	void *rq_dbrec;
+
+	dma_addr_t sq_dbrec_dma;
+	dma_addr_t rq_dbrec_dma;
+
+	u8 sig_all;
+};
+
+enum erdma_qps_iwarp {
+	ERDMA_QPS_IWARP_IDLE = 0,
+	ERDMA_QPS_IWARP_RTR = 1,
+	ERDMA_QPS_IWARP_RTS = 2,
+	ERDMA_QPS_IWARP_CLOSING = 3,
+	ERDMA_QPS_IWARP_TERMINATE = 4,
+	ERDMA_QPS_IWARP_ERROR = 5,
+	ERDMA_QPS_IWARP_UNDEF = 6,
+	ERDMA_QPS_IWARP_COUNT = 7,
+};
+
+enum erdma_qpa_mask_iwarp {
+	ERDMA_QPA_IWARP_STATE = (1 << 0),
+	ERDMA_QPA_IWARP_LLP_HANDLE = (1 << 2),
+	ERDMA_QPA_IWARP_ORD = (1 << 3),
+	ERDMA_QPA_IWARP_IRD = (1 << 4),
+	ERDMA_QPA_IWARP_SQ_SIZE = (1 << 5),
+	ERDMA_QPA_IWARP_RQ_SIZE = (1 << 6),
+	ERDMA_QPA_IWARP_MPA = (1 << 7),
+	ERDMA_QPA_IWARP_CC = (1 << 8),
+};
+
+enum erdma_qps_rocev2 {
+	ERDMA_QPS_ROCEV2_RESET = 0,
+	ERDMA_QPS_ROCEV2_INIT = 1,
+	ERDMA_QPS_ROCEV2_RTR = 2,
+	ERDMA_QPS_ROCEV2_RTS = 3,
+	ERDMA_QPS_ROCEV2_SQD = 4,
+	ERDMA_QPS_ROCEV2_SQE = 5,
+	ERDMA_QPS_ROCEV2_ERROR = 6,
+	ERDMA_QPS_ROCEV2_COUNT = 7,
+};
+
+enum erdma_qpa_mask_rocev2 {
+	ERDMA_QPA_ROCEV2_STATE = (1 << 0),
+	ERDMA_QPA_ROCEV2_QKEY = (1 << 1),
+	ERDMA_QPA_ROCEV2_AV = (1 << 2),
+	ERDMA_QPA_ROCEV2_SQ_PSN = (1 << 3),
+	ERDMA_QPA_ROCEV2_RQ_PSN = (1 << 4),
+	ERDMA_QPA_ROCEV2_DST_QPN = (1 << 5),
+};
+
+enum erdma_qp_flags {
+	ERDMA_QP_IN_FLUSHING = (1 << 0),
+};
+
+#define ERDMA_QP_ACTIVE 0
+#define ERDMA_QP_PASSIVE 1
+
+struct erdma_mod_qp_params_iwarp {
+	enum erdma_qps_iwarp state;
+	enum erdma_cc_alg cc;
+	u8 qp_type;
+	u8 pd_len;
+	u32 irq_size;
+	u32 orq_size;
+};
+
+struct erdma_qp_attrs_iwarp {
+	enum erdma_qps_iwarp state;
+	u32 cookie;
+};
+
+struct erdma_mod_qp_params_rocev2 {
+	enum erdma_qps_rocev2 state;
+	u32 qkey;
+	u32 sq_psn;
+	u32 rq_psn;
+	u32 dst_qpn;
+	struct erdma_av av;
+};
+
+union erdma_mod_qp_params {
+	struct erdma_mod_qp_params_iwarp iwarp;
+	struct erdma_mod_qp_params_rocev2 rocev2;
+};
+
+struct erdma_qp_attrs_rocev2 {
+	enum erdma_qps_rocev2 state;
+	u32 qkey;
+	u32 dst_qpn;
+	struct erdma_av av;
+};
+
+struct erdma_qp_attrs {
+	enum erdma_cc_alg cc; /* Congestion control algorithm */
+	u32 sq_size;
+	u32 rq_size;
+	u32 orq_size;
+	u32 irq_size;
+	u32 max_send_sge;
+	u32 max_recv_sge;
+	union {
+		struct erdma_qp_attrs_iwarp iwarp;
+		struct erdma_qp_attrs_rocev2 rocev2;
+	};
+};
+
+struct erdma_qp {
+	struct ib_qp ibqp;
+	struct kref ref;
+	struct completion safe_free;
+	struct erdma_dev *dev;
+	struct erdma_cep *cep;
+	struct rw_semaphore state_lock;
+
+	unsigned long flags;
+	struct delayed_work reflush_dwork;
+
+	union {
+		struct erdma_kqp kern_qp;
+		struct erdma_uqp user_qp;
+	};
+
+	struct erdma_cq *scq;
+	struct erdma_cq *rcq;
+
+	struct erdma_qp_attrs attrs;
+	spinlock_t lock;
+};
+
+struct erdma_kcq_info {
+	void *qbuf;
+	dma_addr_t qbuf_dma_addr;
+	u32 ci;
+	u32 cmdsn;
+	u32 notify_cnt;
+
+	spinlock_t lock;
+	u8 __iomem *db;
+	u64 *dbrec;
+	dma_addr_t dbrec_dma;
+};
+
+struct erdma_ucq_info {
+	struct erdma_mem qbuf_mem;
+	struct erdma_user_dbrecords_page *user_dbr_page;
+	dma_addr_t dbrec_dma;
+};
+
+struct erdma_cq {
+	struct ib_cq ibcq;
+	u32 cqn;
+
+	u32 depth;
+	u32 assoc_eqn;
+
+	union {
+		struct erdma_kcq_info kern_cq;
+		struct erdma_ucq_info user_cq;
+	};
+};
+
+#define QP_ID(qp) ((qp)->ibqp.qp_num)
+
+static inline struct erdma_qp *find_qp_by_qpn(struct erdma_dev *dev, int id)
+{
+	return (struct erdma_qp *)xa_load(&dev->qp_xa, id);
+}
+
+static inline struct erdma_cq *find_cq_by_cqn(struct erdma_dev *dev, int id)
+{
+	return (struct erdma_cq *)xa_load(&dev->cq_xa, id);
+}
+
+void erdma_qp_get(struct erdma_qp *qp);
+void erdma_qp_put(struct erdma_qp *qp);
+int erdma_modify_qp_state_iwarp(struct erdma_qp *qp,
+				struct erdma_mod_qp_params_iwarp *params,
+				int mask);
+int erdma_modify_qp_state_rocev2(struct erdma_qp *qp,
+				 struct erdma_mod_qp_params_rocev2 *params,
+				 int attr_mask);
+void erdma_qp_llp_close(struct erdma_qp *qp);
+void erdma_qp_cm_drop(struct erdma_qp *qp);
+
+static inline bool erdma_device_iwarp(struct erdma_dev *dev)
+{
+	return dev->proto == ERDMA_PROTO_IWARP;
+}
+
+static inline bool erdma_device_rocev2(struct erdma_dev *dev)
+{
+	return dev->proto == ERDMA_PROTO_ROCEV2;
+}
+
+static inline struct erdma_ucontext *to_ectx(struct ib_ucontext *ibctx)
+{
+	return container_of(ibctx, struct erdma_ucontext, ibucontext);
+}
+
+static inline struct erdma_pd *to_epd(struct ib_pd *pd)
+{
+	return container_of(pd, struct erdma_pd, ibpd);
+}
+
+static inline struct erdma_mr *to_emr(struct ib_mr *ibmr)
+{
+	return container_of(ibmr, struct erdma_mr, ibmr);
+}
+
+static inline struct erdma_qp *to_eqp(struct ib_qp *qp)
+{
+	return container_of(qp, struct erdma_qp, ibqp);
+}
+
+static inline struct erdma_cq *to_ecq(struct ib_cq *ibcq)
+{
+	return container_of(ibcq, struct erdma_cq, ibcq);
+}
+
+static inline struct erdma_ah *to_eah(struct ib_ah *ibah)
+{
+	return container_of(ibah, struct erdma_ah, ibah);
+}
+
+static inline int erdma_check_gid_attr(const struct ib_gid_attr *attr)
+{
+	u8 ntype = rdma_gid_attr_network_type(attr);
+
+	if (ntype != RDMA_NETWORK_IPV4 && ntype != RDMA_NETWORK_IPV6)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline struct erdma_user_mmap_entry *
+to_emmap(struct rdma_user_mmap_entry *ibmmap)
+{
+	return container_of(ibmmap, struct erdma_user_mmap_entry, rdma_entry);
+}
+
+int erdma_alloc_ucontext(struct ib_ucontext *ibctx, struct ib_udata *data);
+void erdma_dealloc_ucontext(struct ib_ucontext *ibctx);
+int erdma_query_device(struct ib_device *dev, struct ib_device_attr *attr,
+		       struct ib_udata *data);
+int erdma_get_port_immutable(struct ib_device *dev, u32 port,
+			     struct ib_port_immutable *ib_port_immutable);
+int erdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		    struct uverbs_attr_bundle *attrs);
+int erdma_query_port(struct ib_device *dev, u32 port,
+		     struct ib_port_attr *attr);
+int erdma_query_gid(struct ib_device *dev, u32 port, int idx,
+		    union ib_gid *gid);
+int erdma_alloc_pd(struct ib_pd *ibpd, struct ib_udata *data);
+int erdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
+		    struct ib_udata *data);
+int erdma_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int mask,
+		   struct ib_qp_init_attr *init_attr);
+int erdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int mask,
+		    struct ib_udata *data);
+int erdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata);
+int erdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+void erdma_disassociate_ucontext(struct ib_ucontext *ibcontext);
+int erdma_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
+struct ib_mr *erdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
+				u64 virt, int access, struct ib_dmah *dmah,
+				struct ib_udata *udata);
+struct ib_mr *erdma_get_dma_mr(struct ib_pd *ibpd, int rights);
+int erdma_dereg_mr(struct ib_mr *ibmr, struct ib_udata *data);
+int erdma_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma);
+void erdma_mmap_free(struct rdma_user_mmap_entry *rdma_entry);
+void erdma_qp_get_ref(struct ib_qp *ibqp);
+void erdma_qp_put_ref(struct ib_qp *ibqp);
+struct ib_qp *erdma_get_ibqp(struct ib_device *dev, int id);
+int erdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *send_wr,
+		    const struct ib_send_wr **bad_send_wr);
+int erdma_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *recv_wr,
+		    const struct ib_recv_wr **bad_recv_wr);
+int erdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
+void erdma_remove_cqes_of_qp(struct ib_cq *ibcq, u32 qpn);
+struct ib_mr *erdma_ib_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
+				u32 max_num_sg);
+int erdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
+		    unsigned int *sg_offset);
+void erdma_port_event(struct erdma_dev *dev, enum ib_event_type reason);
+void erdma_set_mtu(struct erdma_dev *dev, u32 mtu);
+struct rdma_hw_stats *erdma_alloc_hw_port_stats(struct ib_device *device,
+						u32 port_num);
+int erdma_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+		       u32 port, int index);
+enum rdma_link_layer erdma_get_link_layer(struct ib_device *ibdev,
+					  u32 port_num);
+int erdma_add_gid(const struct ib_gid_attr *attr, void **context);
+int erdma_del_gid(const struct ib_gid_attr *attr, void **context);
+int erdma_query_pkey(struct ib_device *ibdev, u32 port, u16 index, u16 *pkey);
+void erdma_set_av_cfg(struct erdma_av_cfg *av_cfg, struct erdma_av *av);
+int erdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
+		    struct ib_udata *udata);
+int erdma_destroy_ah(struct ib_ah *ibah, u32 flags);
+int erdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
+
+#endif