Merge branch 'siw' into rdma.git for-next

Bernard Metzler says:

====================
This patch set contributes the SoftiWarp driver rebased for latest
rdma-next. SoftiWarp (siw) implements the iWarp RDMA protocol over kernel
TCP sockets. The driver integrates with the linux-rdma framework.

A matching userlevel driver is available as PR at
https://github.com/linux-rdma/rdma-core/pull/536

Many thanks for reviewing and testing the driver, especially to Leon,
Jason, Steve, Doug, Olga, Dennis, Gal. You all helped to significantly
improve the driver over the last year.

Please find below a list of changes and comments, compared to older
versions of the siw driver.

Many thanks!
Bernard.

CHANGES:
========

v3 (this version)
-----------------

- Rebased to rdma-next

- Removed unneccessary initialization of enums in siw-abi.h

- Added comment on sizing of all work queues to power of two.

v2
-----------------

- Changed recieve path CRC calculation to compute CRC32c not
  on target buffer after placement, but on original skbuf.
  This change severely hurts performance, if CRC is switched
  on, since skb must now be walked twice. It is planned to
  work on an extension to skb_copy_bits() to fold in CRC
  computation.

- Moved debugging to using ibdev_dbg().

- Dropped detailed packet debug printing.

- Removed siw_debug.[ch] files.

- Removed resource tracking, code now relies on restrack of
  RDMA midlayer. Only object counting to enforce reported
  device limits is left in place.

- Removed all nested switch-case statements.

- Cleaned up header file #include's

- Moved CQ create/destroy to new semantics,
  where midlayer creates/destroys containing object.

- Set siw's ABI version to 1 (was 0 before)

- Removed all enum initialization where not needed.

- Fixed MAINTANERS entry for siw driver

- This version stays with the current siw specific
  management of user memory (siw_umem_get() vs.
  ib_umem_get(), etc.). This, since the current ib_umem
  implementation is less efficient for user page lookup
  on the fast path, where effciency is important for a
  SW RDMA driver.
  It is planned to contribute enhancements to the ib_umem
  framework, wich makes it suitable for SW drivers as well.

v1 (first version after v9 of siw RFC)
--------------------------------------

- Rebased to 5.2-rc1

- All IDR code got removed.

- Both MR and QP deallocation verbs now synchronously
  free the resources referenced by the RDMA mid-layer.

- IPv6 support was added.

- For compatibility with Chelsio iWarp hardware, the RX
  path was slightly reworked. It now allows packet intersection
  between tagged and untagged RDMAP operations. While not
  a defined behavior as of IETF RFC 5040/5041, some RDMA hardware
  may intersect an ongoing outbound (large) tagged message, such
  as an multisegment RDMA Read Response with sending an untagged
  message, such as an RDMA Send frame. This behavior was only
  detected in an NVMeF setup, where siw was used at target side,
  and RDMA hardware at client side (during file write). siw now
  implements two input paths for tagged and untagged messages each,
  and allows the intersected placement of both messages.

- The siw kernel abi file got renamed from siw_user.h to siw-abi.h.
====================

* branch 'siw':
  SIW addition to kernel build environment
  SIW completion queue methods
  SIW receive path
  SIW transmit path
  SIW queue pair methods
  SIW application buffer management
  SIW application interface
  SIW connection management
  SIW network and RDMA core interface
  SIW main include file
  iWarp wire packet format

2 files changed, 186 insertions, 0 deletions

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/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 <[email protected]> */
+/* 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