rdma/siw: application interface

Broken up commit to add the Soft iWarp RDMA driver.

Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/sw/siw/siw_verbs.h

@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+
+/* Authors: Bernard Metzler <bmt@zurich.ibm.com> */
+/* Copyright (c) 2008-2019, IBM Corporation */
+
+#ifndef _SIW_VERBS_H
+#define _SIW_VERBS_H
+
+#include <linux/errno.h>
+
+#include <rdma/iw_cm.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+
+#include "siw.h"
+#include "siw_cm.h"
+
+/*
+ * siw_copy_sgl()
+ *
+ * Copy SGL from RDMA core representation to local
+ * representation.
+ */
+static inline void siw_copy_sgl(struct ib_sge *sge, struct siw_sge *siw_sge,
+				int num_sge)
+{
+	while (num_sge--) {
+		siw_sge->laddr = sge->addr;
+		siw_sge->length = sge->length;
+		siw_sge->lkey = sge->lkey;
+
+		siw_sge++;
+		sge++;
+	}
+}
+
+int siw_alloc_ucontext(struct ib_ucontext *base_ctx, struct ib_udata *udata);
+void siw_dealloc_ucontext(struct ib_ucontext *base_ctx);
+int siw_query_port(struct ib_device *base_dev, u8 port,
+		   struct ib_port_attr *attr);
+int siw_get_port_immutable(struct ib_device *base_dev, u8 port,
+			   struct ib_port_immutable *port_immutable);
+int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr,
+		     struct ib_udata *udata);
+int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr,
+		  struct ib_udata *udata);
+int siw_query_port(struct ib_device *base_dev, u8 port,
+		   struct ib_port_attr *attr);
+int siw_query_pkey(struct ib_device *base_dev, u8 port, u16 idx, u16 *pkey);
+int siw_query_gid(struct ib_device *base_dev, u8 port, int idx,
+		  union ib_gid *gid);
+int siw_alloc_pd(struct ib_pd *base_pd, struct ib_udata *udata);
+void siw_dealloc_pd(struct ib_pd *base_pd, struct ib_udata *udata);
+struct ib_qp *siw_create_qp(struct ib_pd *base_pd,
+			    struct ib_qp_init_attr *attr,
+			    struct ib_udata *udata);
+int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr,
+		 int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
+int siw_verbs_modify_qp(struct ib_qp *base_qp, struct ib_qp_attr *attr,
+			int attr_mask, struct ib_udata *udata);
+int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata);
+int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr,
+		  const struct ib_send_wr **bad_wr);
+int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
+		     const struct ib_recv_wr **bad_wr);
+void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata);
+int siw_poll_cq(struct ib_cq *base_cq, int num_entries, struct ib_wc *wc);
+int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags);
+struct ib_mr *siw_reg_user_mr(struct ib_pd *base_pd, u64 start, u64 len,
+			      u64 rnic_va, int rights, struct ib_udata *udata);
+struct ib_mr *siw_alloc_mr(struct ib_pd *base_pd, enum ib_mr_type mr_type,
+			   u32 max_sge, struct ib_udata *udata);
+struct ib_mr *siw_get_dma_mr(struct ib_pd *base_pd, int rights);
+int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle,
+		  unsigned int *sg_off);
+int siw_dereg_mr(struct ib_mr *base_mr, struct ib_udata *udata);
+int siw_create_srq(struct ib_srq *base_srq, struct ib_srq_init_attr *attr,
+		   struct ib_udata *udata);
+int siw_modify_srq(struct ib_srq *base_srq, struct ib_srq_attr *attr,
+		   enum ib_srq_attr_mask mask, struct ib_udata *udata);
+int siw_query_srq(struct ib_srq *base_srq, struct ib_srq_attr *attr);
+void siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata);
+int siw_post_srq_recv(struct ib_srq *base_srq, const struct ib_recv_wr *wr,
+		      const struct ib_recv_wr **bad_wr);
+int siw_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma);
+void siw_qp_event(struct siw_qp *qp, enum ib_event_type type);
+void siw_cq_event(struct siw_cq *cq, enum ib_event_type type);
+void siw_srq_event(struct siw_srq *srq, enum ib_event_type type);
+void siw_port_event(struct siw_device *dev, u8 port, enum ib_event_type type);
+
+#endif

include/uapi/rdma/rdma_user_ioctl_cmds.h

@@ -103,6 +103,7 @@ enum rdma_driver_id {
 	RDMA_DRIVER_HFI1,
 	RDMA_DRIVER_QIB,
 	RDMA_DRIVER_EFA,
+	RDMA_DRIVER_SIW,
 };
 
 #endif

include/uapi/rdma/siw-abi.h

@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+
+/* Authors: Bernard Metzler <bmt@zurich.ibm.com> */
+/* Copyright (c) 2008-2019, IBM Corporation */
+
+#ifndef _SIW_USER_H
+#define _SIW_USER_H
+
+#include <linux/types.h>
+
+#define SIW_NODE_DESC_COMMON "Software iWARP stack"
+#define SIW_ABI_VERSION 1
+#define SIW_MAX_SGE 6
+#define SIW_UOBJ_MAX_KEY 0x08FFFF
+#define SIW_INVAL_UOBJ_KEY (SIW_UOBJ_MAX_KEY + 1)
+
+struct siw_uresp_create_cq {
+	__u32 cq_id;
+	__u32 num_cqe;
+	__aligned_u64 cq_key;
+};
+
+struct siw_uresp_create_qp {
+	__u32 qp_id;
+	__u32 num_sqe;
+	__u32 num_rqe;
+	__u32 pad;
+	__aligned_u64 sq_key;
+	__aligned_u64 rq_key;
+};
+
+struct siw_ureq_reg_mr {
+	__u8 stag_key;
+	__u8 reserved[3];
+	__u32 pad;
+};
+
+struct siw_uresp_reg_mr {
+	__u32 stag;
+	__u32 pad;
+};
+
+struct siw_uresp_create_srq {
+	__u32 num_rqe;
+	__u32 pad;
+	__aligned_u64 srq_key;
+};
+
+struct siw_uresp_alloc_ctx {
+	__u32 dev_id;
+	__u32 pad;
+};
+
+enum siw_opcode {
+	SIW_OP_WRITE,
+	SIW_OP_READ,
+	SIW_OP_READ_LOCAL_INV,
+	SIW_OP_SEND,
+	SIW_OP_SEND_WITH_IMM,
+	SIW_OP_SEND_REMOTE_INV,
+
+	/* Unsupported */
+	SIW_OP_FETCH_AND_ADD,
+	SIW_OP_COMP_AND_SWAP,
+
+	SIW_OP_RECEIVE,
+	/* provider internal SQE */
+	SIW_OP_READ_RESPONSE,
+	/*
+	 * below opcodes valid for
+	 * in-kernel clients only
+	 */
+	SIW_OP_INVAL_STAG,
+	SIW_OP_REG_MR,
+	SIW_NUM_OPCODES
+};
+
+/* Keep it same as ibv_sge to allow for memcpy */
+struct siw_sge {
+	__aligned_u64 laddr;
+	__u32 length;
+	__u32 lkey;
+};
+
+/*
+ * Inline data are kept within the work request itself occupying
+ * the space of sge[1] .. sge[n]. Therefore, inline data cannot be
+ * supported if SIW_MAX_SGE is below 2 elements.
+ */
+#define SIW_MAX_INLINE (sizeof(struct siw_sge) * (SIW_MAX_SGE - 1))
+
+#if SIW_MAX_SGE < 2
+#error "SIW_MAX_SGE must be at least 2"
+#endif
+
+enum siw_wqe_flags {
+	SIW_WQE_VALID = 1,
+	SIW_WQE_INLINE = (1 << 1),
+	SIW_WQE_SIGNALLED = (1 << 2),
+	SIW_WQE_SOLICITED = (1 << 3),
+	SIW_WQE_READ_FENCE = (1 << 4),
+	SIW_WQE_REM_INVAL = (1 << 5),
+	SIW_WQE_COMPLETED = (1 << 6)
+};
+
+/* Send Queue Element */
+struct siw_sqe {
+	__aligned_u64 id;
+	__u16 flags;
+	__u8 num_sge;
+	/* Contains enum siw_opcode values */
+	__u8 opcode;
+	__u32 rkey;
+	union {
+		__aligned_u64 raddr;
+		__aligned_u64 base_mr;
+	};
+	union {
+		struct siw_sge sge[SIW_MAX_SGE];
+		__aligned_u64 access;
+	};
+};
+
+/* Receive Queue Element */
+struct siw_rqe {
+	__aligned_u64 id;
+	__u16 flags;
+	__u8 num_sge;
+	/*
+	 * only used by kernel driver,
+	 * ignored if set by user
+	 */
+	__u8 opcode;
+	__u32 unused;
+	struct siw_sge sge[SIW_MAX_SGE];
+};
+
+enum siw_notify_flags {
+	SIW_NOTIFY_NOT = (0),
+	SIW_NOTIFY_SOLICITED = (1 << 0),
+	SIW_NOTIFY_NEXT_COMPLETION = (1 << 1),
+	SIW_NOTIFY_MISSED_EVENTS = (1 << 2),
+	SIW_NOTIFY_ALL = SIW_NOTIFY_SOLICITED | SIW_NOTIFY_NEXT_COMPLETION |
+			 SIW_NOTIFY_MISSED_EVENTS
+};
+
+enum siw_wc_status {
+	SIW_WC_SUCCESS,
+	SIW_WC_LOC_LEN_ERR,
+	SIW_WC_LOC_PROT_ERR,
+	SIW_WC_LOC_QP_OP_ERR,
+	SIW_WC_WR_FLUSH_ERR,
+	SIW_WC_BAD_RESP_ERR,
+	SIW_WC_LOC_ACCESS_ERR,
+	SIW_WC_REM_ACCESS_ERR,
+	SIW_WC_REM_INV_REQ_ERR,
+	SIW_WC_GENERAL_ERR,
+	SIW_NUM_WC_STATUS
+};
+
+struct siw_cqe {
+	__aligned_u64 id;
+	__u8 flags;
+	__u8 opcode;
+	__u16 status;
+	__u32 bytes;
+	union {
+		__aligned_u64 imm_data;
+		__u32 inval_stag;
+	};
+	/* QP number or QP pointer */
+	union {
+		struct ib_qp *base_qp;
+		__aligned_u64 qp_id;
+	};
+};
+
+/*
+ * Shared structure between user and kernel
+ * to control CQ arming.
+ */
+struct siw_cq_ctrl {
+	__aligned_u64 notify;
+};
+#endif