Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A smaller cycle this time. Notably we see another new driver, 'Soft
  iWarp', and the deletion of an ancient unused driver for nes.

   - Revise and simplify the signature offload RDMA MR APIs

   - More progress on hoisting object allocation boiler plate code out
     of the drivers

   - Driver bug fixes and revisions for hns, hfi1, efa, cxgb4, qib,
     i40iw

   - Tree wide cleanups: struct_size, put_user_page, xarray, rst doc
     conversion

   - Removal of obsolete ib_ucm chardev and nes driver

   - netlink based discovery of chardevs and autoloading of the modules
     providing them

   - Move more of the rdamvt/hfi1 uapi to include/uapi/rdma

   - New driver 'siw' for software based iWarp running on top of netdev,
     much like rxe's software RoCE.

   - mlx5 feature to report events in their raw devx format to userspace

   - Expose per-object counters through rdma tool

   - Adaptive interrupt moderation for RDMA (DIM), sharing the DIM core
     from netdev"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (194 commits)
  RMDA/siw: Require a 64 bit arch
  RDMA/siw: Mark expected switch fall-throughs
  RDMA/core: Fix -Wunused-const-variable warnings
  rdma/siw: Remove set but not used variable 's'
  rdma/siw: Add missing dependencies on LIBCRC32C and DMA_VIRT_OPS
  RDMA/siw: Add missing rtnl_lock around access to ifa
  rdma/siw: Use proper enumerated type in map_cqe_status
  RDMA/siw: Remove unnecessary kthread create/destroy printouts
  IB/rdmavt: Fix variable shadowing issue in rvt_create_cq
  RDMA/core: Fix race when resolving IP address
  RDMA/core: Make rdma_counter.h compile stand alone
  IB/core: Work on the caller socket net namespace in nldev_newlink()
  RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
  RDMA/mlx5: Set RDMA DIM to be enabled by default
  RDMA/nldev: Added configuration of RDMA dynamic interrupt moderation to netlink
  RDMA/core: Provide RDMA DIM support for ULPs
  linux/dim: Implement RDMA adaptive moderation (DIM)
  IB/mlx5: Report correctly tag matching rendezvous capability
  docs: infiniband: add it to the driver-api bookset
  IB/mlx5: Implement VHCA tunnel mechanism in DEVX
  ...

7 files changed, 362 insertions, 330 deletions

diff --git a/include/uapi/rdma/ib_user_cm.h b/include/uapi/rdma/ib_user_cm.h
deleted file mode 100644
index e2709bb8cb18..000000000000
--- a/include/uapi/rdma/ib_user_cm.h
+++ /dev/null
@@ -1,326 +0,0 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
-/*
- * Copyright (c) 2005 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005 Intel Corporation.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_USER_CM_H
-#define IB_USER_CM_H
-
-#include <linux/types.h>
-#include <rdma/ib_user_sa.h>
-
-#define IB_USER_CM_ABI_VERSION 5
-
-enum {
-	IB_USER_CM_CMD_CREATE_ID,
-	IB_USER_CM_CMD_DESTROY_ID,
-	IB_USER_CM_CMD_ATTR_ID,
-
-	IB_USER_CM_CMD_LISTEN,
-	IB_USER_CM_CMD_NOTIFY,
-
-	IB_USER_CM_CMD_SEND_REQ,
-	IB_USER_CM_CMD_SEND_REP,
-	IB_USER_CM_CMD_SEND_RTU,
-	IB_USER_CM_CMD_SEND_DREQ,
-	IB_USER_CM_CMD_SEND_DREP,
-	IB_USER_CM_CMD_SEND_REJ,
-	IB_USER_CM_CMD_SEND_MRA,
-	IB_USER_CM_CMD_SEND_LAP,
-	IB_USER_CM_CMD_SEND_APR,
-	IB_USER_CM_CMD_SEND_SIDR_REQ,
-	IB_USER_CM_CMD_SEND_SIDR_REP,
-
-	IB_USER_CM_CMD_EVENT,
-	IB_USER_CM_CMD_INIT_QP_ATTR,
-};
-/*
- * command ABI structures.
- */
-struct ib_ucm_cmd_hdr {
-	__u32 cmd;
-	__u16 in;
-	__u16 out;
-};
-
-struct ib_ucm_create_id {
-	__aligned_u64 uid;
-	__aligned_u64 response;
-};
-
-struct ib_ucm_create_id_resp {
-	__u32 id;
-};
-
-struct ib_ucm_destroy_id {
-	__aligned_u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_destroy_id_resp {
-	__u32 events_reported;
-};
-
-struct ib_ucm_attr_id {
-	__aligned_u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_attr_id_resp {
-	__be64 service_id;
-	__be64 service_mask;
-	__be32 local_id;
-	__be32 remote_id;
-};
-
-struct ib_ucm_init_qp_attr {
-	__aligned_u64 response;
-	__u32 id;
-	__u32 qp_state;
-};
-
-struct ib_ucm_listen {
-	__be64 service_id;
-	__be64 service_mask;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_notify {
-	__u32 id;
-	__u32 event;
-};
-
-struct ib_ucm_private_data {
-	__aligned_u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_req {
-	__u32 id;
-	__u32 qpn;
-	__u32 qp_type;
-	__u32 psn;
-	__be64 sid;
-	__aligned_u64 data;
-	__aligned_u64 primary_path;
-	__aligned_u64 alternate_path;
-	__u8  len;
-	__u8  peer_to_peer;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  remote_cm_response_timeout;
-	__u8  flow_control;
-	__u8  local_cm_response_timeout;
-	__u8  retry_count;
-	__u8  rnr_retry_count;
-	__u8  max_cm_retries;
-	__u8  srq;
-	__u8  reserved[5];
-};
-
-struct ib_ucm_rep {
-	__aligned_u64 uid;
-	__aligned_u64 data;
-	__u32 id;
-	__u32 qpn;
-	__u32 psn;
-	__u8  len;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  target_ack_delay;
-	__u8  failover_accepted;
-	__u8  flow_control;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  reserved[4];
-};
-
-struct ib_ucm_info {
-	__u32 id;
-	__u32 status;
-	__aligned_u64 info;
-	__aligned_u64 data;
-	__u8  info_len;
-	__u8  data_len;
-	__u8  reserved[6];
-};
-
-struct ib_ucm_mra {
-	__aligned_u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  timeout;
-	__u8  reserved[2];
-};
-
-struct ib_ucm_lap {
-	__aligned_u64 path;
-	__aligned_u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_sidr_req {
-	__u32 id;
-	__u32 timeout;
-	__be64 sid;
-	__aligned_u64 data;
-	__aligned_u64 path;
-	__u16 reserved_pkey;
-	__u8  len;
-	__u8  max_cm_retries;
-	__u8  reserved[4];
-};
-
-struct ib_ucm_sidr_rep {
-	__u32 id;
-	__u32 qpn;
-	__u32 qkey;
-	__u32 status;
-	__aligned_u64 info;
-	__aligned_u64 data;
-	__u8  info_len;
-	__u8  data_len;
-	__u8  reserved[6];
-};
-/*
- * event notification ABI structures.
- */
-struct ib_ucm_event_get {
-	__aligned_u64 response;
-	__aligned_u64 data;
-	__aligned_u64 info;
-	__u8  data_len;
-	__u8  info_len;
-	__u8  reserved[6];
-};
-
-struct ib_ucm_req_event_resp {
-	struct ib_user_path_rec primary_path;
-	struct ib_user_path_rec alternate_path;
-	__be64                 remote_ca_guid;
-	__u32                  remote_qkey;
-	__u32                  remote_qpn;
-	__u32                  qp_type;
-	__u32                  starting_psn;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  local_cm_response_timeout;
-	__u8  flow_control;
-	__u8  remote_cm_response_timeout;
-	__u8  retry_count;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  port;
-	__u8  reserved[7];
-};
-
-struct ib_ucm_rep_event_resp {
-	__be64 remote_ca_guid;
-	__u32 remote_qkey;
-	__u32 remote_qpn;
-	__u32 starting_psn;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  target_ack_delay;
-	__u8  failover_accepted;
-	__u8  flow_control;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  reserved[5];
-};
-
-struct ib_ucm_rej_event_resp {
-	__u32 reason;
-	/* ari in ib_ucm_event_get info field. */
-};
-
-struct ib_ucm_mra_event_resp {
-	__u8  timeout;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_lap_event_resp {
-	struct ib_user_path_rec path;
-};
-
-struct ib_ucm_apr_event_resp {
-	__u32 status;
-	/* apr info in ib_ucm_event_get info field. */
-};
-
-struct ib_ucm_sidr_req_event_resp {
-	__u16 pkey;
-	__u8  port;
-	__u8  reserved;
-};
-
-struct ib_ucm_sidr_rep_event_resp {
-	__u32 status;
-	__u32 qkey;
-	__u32 qpn;
-	/* info in ib_ucm_event_get info field. */
-};
-
-#define IB_UCM_PRES_DATA      0x01
-#define IB_UCM_PRES_INFO      0x02
-#define IB_UCM_PRES_PRIMARY   0x04
-#define IB_UCM_PRES_ALTERNATE 0x08
-
-struct ib_ucm_event_resp {
-	__aligned_u64 uid;
-	__u32 id;
-	__u32 event;
-	__u32 present;
-	__u32 reserved;
-	union {
-		struct ib_ucm_req_event_resp req_resp;
-		struct ib_ucm_rep_event_resp rep_resp;
-		struct ib_ucm_rej_event_resp rej_resp;
-		struct ib_ucm_mra_event_resp mra_resp;
-		struct ib_ucm_lap_event_resp lap_resp;
-		struct ib_ucm_apr_event_resp apr_resp;
-
-		struct ib_ucm_sidr_req_event_resp sidr_req_resp;
-		struct ib_ucm_sidr_rep_event_resp sidr_rep_resp;
-
-		__u32                             send_status;
-	} u;
-};
-
-#endif /* IB_USER_CM_H */
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index d404c951954c..d0da070cf0ab 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -51,6 +51,7 @@ enum mlx5_ib_devx_methods {
 	MLX5_IB_METHOD_DEVX_OTHER  = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_METHOD_DEVX_QUERY_UAR,
 	MLX5_IB_METHOD_DEVX_QUERY_EQN,
+	MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT,
 };
 
 enum  mlx5_ib_devx_other_attrs {
@@ -93,6 +94,14 @@ enum mlx5_ib_devx_obj_query_async_attrs {
 	MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_OUT_LEN,
 };
 
+enum mlx5_ib_devx_subscribe_event_attrs {
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_OBJ_HANDLE,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE,
+};
+
 enum  mlx5_ib_devx_query_eqn_attrs {
 	MLX5_IB_ATTR_DEVX_QUERY_EQN_USER_VEC = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_ATTR_DEVX_QUERY_EQN_DEV_EQN,
@@ -127,16 +136,26 @@ enum mlx5_ib_devx_async_cmd_fd_alloc_attrs {
 	MLX5_IB_ATTR_DEVX_ASYNC_CMD_FD_ALLOC_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
 };
 
+enum mlx5_ib_devx_async_event_fd_alloc_attrs {
+	MLX5_IB_ATTR_DEVX_ASYNC_EVENT_FD_ALLOC_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_DEVX_ASYNC_EVENT_FD_ALLOC_FLAGS,
+};
+
 enum mlx5_ib_devx_async_cmd_fd_methods {
 	MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC = (1U << UVERBS_ID_NS_SHIFT),
 };
 
+enum mlx5_ib_devx_async_event_fd_methods {
+	MLX5_IB_METHOD_DEVX_ASYNC_EVENT_FD_ALLOC = (1U << UVERBS_ID_NS_SHIFT),
+};
+
 enum mlx5_ib_objects {
 	MLX5_IB_OBJECT_DEVX = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_OBJECT_DEVX_OBJ,
 	MLX5_IB_OBJECT_DEVX_UMEM,
 	MLX5_IB_OBJECT_FLOW_MATCHER,
 	MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD,
+	MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD,
 };
 
 enum mlx5_ib_flow_matcher_create_attrs {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index a8f34c237458..7e9900b0e746 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -63,5 +63,14 @@ enum mlx5_ib_uapi_dm_type {
 	MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM,
 };
 
+enum mlx5_ib_uapi_devx_create_event_channel_flags {
+	MLX5_IB_UAPI_DEVX_CR_EV_CH_FLAGS_OMIT_DATA = 1 << 0,
+};
+
+struct mlx5_ib_uapi_devx_async_event_hdr {
+	__aligned_u64	cookie;
+	__u8		out_data[];
+};
+
 #endif
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 41db51367efa..8e277783fa96 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -147,6 +147,18 @@ enum {
 	IWPM_NLA_HELLO_MAX
 };
 
+/* For RDMA_NLDEV_ATTR_DEV_NODE_TYPE */
+enum {
+	/* IB values map to NodeInfo:NodeType. */
+	RDMA_NODE_IB_CA = 1,
+	RDMA_NODE_IB_SWITCH,
+	RDMA_NODE_IB_ROUTER,
+	RDMA_NODE_RNIC,
+	RDMA_NODE_USNIC,
+	RDMA_NODE_USNIC_UDP,
+	RDMA_NODE_UNSPECIFIED,
+};
+
 /*
  * Local service operations:
  *   RESOLVE - The client requests the local service to resolve a path.
@@ -267,11 +279,15 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_PD_GET, /* can dump */
 
-	RDMA_NLDEV_NUM_OPS
-};
+	RDMA_NLDEV_CMD_GET_CHARDEV,
 
-enum {
-	RDMA_NLDEV_ATTR_ENTRY_STRLEN = 16,
+	RDMA_NLDEV_CMD_STAT_SET,
+
+	RDMA_NLDEV_CMD_STAT_GET, /* can dump */
+
+	RDMA_NLDEV_CMD_STAT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
 };
 
 enum rdma_nldev_print_type {
@@ -478,10 +494,72 @@ enum rdma_nldev_attr {
 	 * File descriptor handle of the net namespace object
 	 */
 	RDMA_NLDEV_NET_NS_FD,			/* u32 */
+	/*
+	 * Information about a chardev.
+	 * CHARDEV_TYPE is the name of the chardev ABI (ie uverbs, umad, etc)
+	 * CHARDEV_ABI signals the ABI revision (historical)
+	 * CHARDEV_NAME is the kernel name for the /dev/ file (no directory)
+	 * CHARDEV is the 64 bit dev_t for the inode
+	 */
+	RDMA_NLDEV_ATTR_CHARDEV_TYPE,		/* string */
+	RDMA_NLDEV_ATTR_CHARDEV_NAME,		/* string */
+	RDMA_NLDEV_ATTR_CHARDEV_ABI,		/* u64 */
+	RDMA_NLDEV_ATTR_CHARDEV,		/* u64 */
+	RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID,       /* u64 */
+	/*
+	 * Counter-specific attributes.
+	 */
+	RDMA_NLDEV_ATTR_STAT_MODE,		/* u32 */
+	RDMA_NLDEV_ATTR_STAT_RES,		/* u32 */
+	RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK,	/* u32 */
+	RDMA_NLDEV_ATTR_STAT_COUNTER,		/* nested table */
+	RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_COUNTER_ID,	/* u32 */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTERS,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME,	/* string */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE,	/* u64 */
+
+	/*
+	 * CQ adaptive moderatio (DIM)
+	 */
+	RDMA_NLDEV_ATTR_DEV_DIM,                /* u8 */
 
 	/*
 	 * Always the end
 	 */
 	RDMA_NLDEV_ATTR_MAX
 };
+
+/*
+ * Supported counter bind modes. All modes are mutual-exclusive.
+ */
+enum rdma_nl_counter_mode {
+	RDMA_COUNTER_MODE_NONE,
+
+	/*
+	 * A qp is bound with a counter automatically during initialization
+	 * based on the auto mode (e.g., qp type, ...)
+	 */
+	RDMA_COUNTER_MODE_AUTO,
+
+	/*
+	 * Which qp are bound with which counter is explicitly specified
+	 * by the user
+	 */
+	RDMA_COUNTER_MODE_MANUAL,
+
+	/*
+	 * Always the end
+	 */
+	RDMA_COUNTER_MODE_MAX,
+};
+
+/*
+ * Supported criteria in counter auto mode.
+ * Currently only "qp type" is supported
+ */
+enum rdma_nl_counter_mask {
+	RDMA_COUNTER_MASK_QP_TYPE = 1,
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
diff --git a/include/uapi/rdma/rdma_user_ioctl_cmds.h b/include/uapi/rdma/rdma_user_ioctl_cmds.h
index 26213f49f5c8..64c14cb0022f 100644
--- a/include/uapi/rdma/rdma_user_ioctl_cmds.h
+++ b/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
diff --git a/include/uapi/rdma/rvt-abi.h b/include/uapi/rdma/rvt-abi.h
new file mode 100644
index 000000000000..7328293c715c
--- /dev/null
+++ b/include/uapi/rdma/rvt-abi.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+
+/*
+ * This file contains defines, structures, etc. that are used
+ * to communicate between kernel and user code.
+ */
+
+#ifndef RVT_ABI_USER_H
+#define RVT_ABI_USER_H
+
+#include <linux/types.h>
+#include <rdma/ib_user_verbs.h>
+#ifndef RDMA_ATOMIC_UAPI
+#define RDMA_ATOMIC_UAPI(_type, _name) struct{ _type val; } _name
+#endif
+
+struct rvt_wqe_sge {
+	__aligned_u64 addr;
+	__u32 length;
+	__u32 lkey;
+};
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and completion queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ */
+struct rvt_cq_wc {
+	/* index of next entry to fill */
+	RDMA_ATOMIC_UAPI(__u32, head);
+	/* index of next ib_poll_cq() entry */
+	RDMA_ATOMIC_UAPI(__u32, tail);
+
+	/* these are actually size ibcq.cqe + 1 */
+	struct ib_uverbs_wc uqueue[];
+};
+
+/*
+ * Receive work request queue entry.
+ * The size of the sg_list is determined when the QP (or SRQ) is created
+ * and stored in qp->r_rq.max_sge (or srq->rq.max_sge).
+ */
+struct rvt_rwqe {
+	__u64 wr_id;
+	__u8 num_sge;
+	__u8 padding[7];
+	struct rvt_wqe_sge sg_list[];
+};
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and receive work queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ * Note that the wq array elements are variable size so you can't
+ * just index into the array to get the N'th element;
+ * use get_rwqe_ptr() for user space and rvt_get_rwqe_ptr()
+ * for kernel space.
+ */
+struct rvt_rwq {
+	/* new work requests posted to the head */
+	RDMA_ATOMIC_UAPI(__u32, head);
+	/* receives pull requests from here. */
+	RDMA_ATOMIC_UAPI(__u32, tail);
+	struct rvt_rwqe wq[];
+};
+#endif /* RVT_ABI_USER_H */
diff --git a/include/uapi/rdma/siw-abi.h b/include/uapi/rdma/siw-abi.h
new file mode 100644
index 000000000000..3dd8071ace7b
--- /dev/null
+++ b/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