RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter

Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).
Co-developed-by: Ajay Sharma <sharmaajay@microsoft.com>
Signed-off-by: Ajay Sharma <sharmaajay@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
Link: https://lore.kernel.org/r/1667502990-2559-13-git-send-email-longli@linuxonhyperv.comSigned-off-by: Leon Romanovsky <leon@kernel.org>

MAINTAINERS

@@ -13669,6 +13669,15 @@ F:	drivers/scsi/smartpqi/smartpqi*.[ch]
 F:	include/linux/cciss*.h
 F:	include/uapi/linux/cciss*.h
 
+MICROSOFT MANA RDMA DRIVER
+M:	Long Li <longli@microsoft.com>
+M:	Ajay Sharma <sharmaajay@microsoft.com>
+L:	linux-rdma@vger.kernel.org
+S:	Supported
+F:	drivers/infiniband/hw/mana/
+F:	include/net/mana
+F:	include/uapi/rdma/mana-abi.h
+
 MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH
 M:	Maximilian Luz <luzmaximilian@gmail.com>
 L:	platform-driver-x86@vger.kernel.org

drivers/infiniband/Kconfig

@@ -85,6 +85,7 @@ source "drivers/infiniband/hw/erdma/Kconfig"
 source "drivers/infiniband/hw/hfi1/Kconfig"
 source "drivers/infiniband/hw/hns/Kconfig"
 source "drivers/infiniband/hw/irdma/Kconfig"
+source "drivers/infiniband/hw/mana/Kconfig"
 source "drivers/infiniband/hw/mlx4/Kconfig"
 source "drivers/infiniband/hw/mlx5/Kconfig"
 source "drivers/infiniband/hw/mthca/Kconfig"

drivers/infiniband/hw/Makefile

@@ -4,6 +4,7 @@ obj-$(CONFIG_INFINIBAND_QIB)		+= qib/
 obj-$(CONFIG_INFINIBAND_CXGB4)		+= cxgb4/
 obj-$(CONFIG_INFINIBAND_EFA)		+= efa/
 obj-$(CONFIG_INFINIBAND_IRDMA)		+= irdma/
+obj-$(CONFIG_MANA_INFINIBAND)		+= mana/
 obj-$(CONFIG_MLX4_INFINIBAND)		+= mlx4/
 obj-$(CONFIG_MLX5_INFINIBAND)		+= mlx5/
 obj-$(CONFIG_INFINIBAND_OCRDMA)		+= ocrdma/

drivers/infiniband/hw/mana/Kconfig

+# SPDX-License-Identifier: GPL-2.0-only
+config MANA_INFINIBAND
+	tristate "Microsoft Azure Network Adapter support"
+	depends on NETDEVICES && ETHERNET && PCI && MICROSOFT_MANA
+	help
+	  This driver provides low-level RDMA support for Microsoft Azure
+	  Network Adapter (MANA). MANA supports RDMA features that can be used
+	  for workloads (e.g. DPDK, MPI etc) that uses RDMA verbs to directly
+	  access hardware from user-mode processes in Microsoft Azure cloud
+	  environment.

drivers/infiniband/hw/mana/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
+
+mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o

drivers/infiniband/hw/mana/cq.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata)
+{
+	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+	struct ib_device *ibdev = ibcq->device;
+	struct mana_ib_create_cq ucmd = {};
+	struct mana_ib_dev *mdev;
+	int err;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	if (udata->inlen < sizeof(ucmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
+	if (err) {
+		ibdev_dbg(ibdev,
+			  "Failed to copy from udata for create cq, %d\n", err);
+		return err;
+	}
+
+	if (attr->cqe > MAX_SEND_BUFFERS_PER_QUEUE) {
+		ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
+		return -EINVAL;
+	}
+
+	cq->cqe = attr->cqe;
+	cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE,
+			       IB_ACCESS_LOCAL_WRITE);
+	if (IS_ERR(cq->umem)) {
+		err = PTR_ERR(cq->umem);
+		ibdev_dbg(ibdev, "Failed to get umem for create cq, err %d\n",
+			  err);
+		return err;
+	}
+
+	err = mana_ib_gd_create_dma_region(mdev, cq->umem, &cq->gdma_region);
+	if (err) {
+		ibdev_dbg(ibdev,
+			  "Failed to create dma region for create cq, %d\n",
+			  err);
+		goto err_release_umem;
+	}
+
+	ibdev_dbg(ibdev,
+		  "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n",
+		  err, cq->gdma_region);
+
+	/*
+	 * The CQ ID is not known at this time. The ID is generated at create_qp
+	 */
+
+	return 0;
+
+err_release_umem:
+	ib_umem_release(cq->umem);
+	return err;
+}
+
+int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+{
+	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+	struct ib_device *ibdev = ibcq->device;
+	struct mana_ib_dev *mdev;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	mana_ib_gd_destroy_dma_region(mdev, cq->gdma_region);
+	ib_umem_release(cq->umem);
+
+	return 0;
+}

drivers/infiniband/hw/mana/device.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+#include <net/mana/mana_auxiliary.h>
+
+MODULE_DESCRIPTION("Microsoft Azure Network Adapter IB driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(NET_MANA);
+
+static const struct ib_device_ops mana_ib_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_MANA,
+	.uverbs_abi_ver = MANA_IB_UVERBS_ABI_VERSION,
+
+	.alloc_pd = mana_ib_alloc_pd,
+	.alloc_ucontext = mana_ib_alloc_ucontext,
+	.create_cq = mana_ib_create_cq,
+	.create_qp = mana_ib_create_qp,
+	.create_rwq_ind_table = mana_ib_create_rwq_ind_table,
+	.create_wq = mana_ib_create_wq,
+	.dealloc_pd = mana_ib_dealloc_pd,
+	.dealloc_ucontext = mana_ib_dealloc_ucontext,
+	.dereg_mr = mana_ib_dereg_mr,
+	.destroy_cq = mana_ib_destroy_cq,
+	.destroy_qp = mana_ib_destroy_qp,
+	.destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table,
+	.destroy_wq = mana_ib_destroy_wq,
+	.disassociate_ucontext = mana_ib_disassociate_ucontext,
+	.get_port_immutable = mana_ib_get_port_immutable,
+	.mmap = mana_ib_mmap,
+	.modify_qp = mana_ib_modify_qp,
+	.modify_wq = mana_ib_modify_wq,
+	.query_device = mana_ib_query_device,
+	.query_gid = mana_ib_query_gid,
+	.query_port = mana_ib_query_port,
+	.reg_user_mr = mana_ib_reg_user_mr,
+
+	INIT_RDMA_OBJ_SIZE(ib_cq, mana_ib_cq, ibcq),
+	INIT_RDMA_OBJ_SIZE(ib_pd, mana_ib_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, mana_ib_qp, ibqp),
+	INIT_RDMA_OBJ_SIZE(ib_ucontext, mana_ib_ucontext, ibucontext),
+	INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mana_ib_rwq_ind_table,
+			   ib_ind_table),
+};
+
+static int mana_ib_probe(struct auxiliary_device *adev,
+			 const struct auxiliary_device_id *id)
+{
+	struct mana_adev *madev = container_of(adev, struct mana_adev, adev);
+	struct gdma_dev *mdev = madev->mdev;
+	struct mana_context *mc;
+	struct mana_ib_dev *dev;
+	int ret;
+
+	mc = mdev->driver_data;
+
+	dev = ib_alloc_device(mana_ib_dev, ib_dev);
+	if (!dev)
+		return -ENOMEM;
+
+	ib_set_device_ops(&dev->ib_dev, &mana_ib_dev_ops);
+
+	dev->ib_dev.phys_port_cnt = mc->num_ports;
+
+	ibdev_dbg(&dev->ib_dev, "mdev=%p id=%d num_ports=%d\n", mdev,
+		  mdev->dev_id.as_uint32, dev->ib_dev.phys_port_cnt);
+
+	dev->gdma_dev = mdev;
+	dev->ib_dev.node_type = RDMA_NODE_IB_CA;
+
+	/*
+	 * num_comp_vectors needs to set to the max MSIX index
+	 * when interrupts and event queues are implemented
+	 */
+	dev->ib_dev.num_comp_vectors = 1;
+	dev->ib_dev.dev.parent = mdev->gdma_context->dev;
+
+	ret = ib_register_device(&dev->ib_dev, "mana_%d",
+				 mdev->gdma_context->dev);
+	if (ret) {
+		ib_dealloc_device(&dev->ib_dev);
+		return ret;
+	}
+
+	dev_set_drvdata(&adev->dev, dev);
+
+	return 0;
+}
+
+static void mana_ib_remove(struct auxiliary_device *adev)
+{
+	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
+
+	ib_unregister_device(&dev->ib_dev);
+	ib_dealloc_device(&dev->ib_dev);
+}
+
+static const struct auxiliary_device_id mana_id_table[] = {
+	{
+		.name = "mana.rdma",
+	},
+	{},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mana_id_table);
+
+static struct auxiliary_driver mana_driver = {
+	.name = "rdma",
+	.probe = mana_ib_probe,
+	.remove = mana_ib_remove,
+	.id_table = mana_id_table,
+};
+
+module_auxiliary_driver(mana_driver);

drivers/infiniband/hw/mana/mana_ib.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _MANA_IB_H_
+#define _MANA_IB_H_
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_mad.h>
+#include <rdma/ib_umem.h>
+#include <rdma/mana-abi.h>
+#include <rdma/uverbs_ioctl.h>
+
+#include <net/mana/mana.h>
+
+#define PAGE_SZ_BM                                                             \
+	(SZ_4K | SZ_8K | SZ_16K | SZ_32K | SZ_64K | SZ_128K | SZ_256K |        \
+	 SZ_512K | SZ_1M | SZ_2M)
+
+/* MANA doesn't have any limit for MR size */
+#define MANA_IB_MAX_MR_SIZE	U64_MAX
+
+/*
+ * The hardware limit of number of MRs is greater than maximum number of MRs
+ * that can possibly represent in 24 bits
+ */
+#define MANA_IB_MAX_MR		0xFFFFFFu
+
+struct mana_ib_dev {
+	struct ib_device ib_dev;
+	struct gdma_dev *gdma_dev;
+};
+
+struct mana_ib_wq {
+	struct ib_wq ibwq;
+	struct ib_umem *umem;
+	int wqe;
+	u32 wq_buf_size;
+	u64 gdma_region;
+	u64 id;
+	mana_handle_t rx_object;
+};
+
+struct mana_ib_pd {
+	struct ib_pd ibpd;
+	u32 pdn;
+	mana_handle_t pd_handle;
+
+	/* Mutex for sharing access to vport_use_count */
+	struct mutex vport_mutex;
+	int vport_use_count;
+
+	bool tx_shortform_allowed;
+	u32 tx_vp_offset;
+};
+
+struct mana_ib_mr {
+	struct ib_mr ibmr;
+	struct ib_umem *umem;
+	mana_handle_t mr_handle;
+};
+
+struct mana_ib_cq {
+	struct ib_cq ibcq;
+	struct ib_umem *umem;
+	int cqe;
+	u64 gdma_region;
+	u64 id;
+};
+
+struct mana_ib_qp {
+	struct ib_qp ibqp;
+
+	/* Work queue info */
+	struct ib_umem *sq_umem;
+	int sqe;
+	u64 sq_gdma_region;
+	u64 sq_id;
+	mana_handle_t tx_object;
+
+	/* The port on the IB device, starting with 1 */
+	u32 port;
+};
+
+struct mana_ib_ucontext {
+	struct ib_ucontext ibucontext;
+	u32 doorbell;
+};
+
+struct mana_ib_rwq_ind_table {
+	struct ib_rwq_ind_table ib_ind_table;
+};
+
+int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem,
+				 mana_handle_t *gdma_region);
+
+int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev,
+				  mana_handle_t gdma_region);
+
+struct ib_wq *mana_ib_create_wq(struct ib_pd *pd,
+				struct ib_wq_init_attr *init_attr,
+				struct ib_udata *udata);
+
+int mana_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+		      u32 wq_attr_mask, struct ib_udata *udata);
+
+int mana_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata);
+
+int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_table,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata);
+
+int mana_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl);
+
+struct ib_mr *mana_ib_get_dma_mr(struct ib_pd *ibpd, int access_flags);
+
+struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+				  u64 iova, int access_flags,
+				  struct ib_udata *udata);
+
+int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
+
+int mana_ib_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
+		      struct ib_udata *udata);
+
+int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+		      int attr_mask, struct ib_udata *udata);
+
+int mana_ib_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata);
+
+int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port_id,
+		      struct mana_ib_pd *pd, u32 doorbell_id);
+void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
+			 u32 port);
+
+int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata);
+
+int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+
+int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+int mana_ib_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+
+int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext,
+			   struct ib_udata *udata);
+void mana_ib_dealloc_ucontext(struct ib_ucontext *ibcontext);
+
+int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma);
+
+int mana_ib_get_port_immutable(struct ib_device *ibdev, u32 port_num,
+			       struct ib_port_immutable *immutable);
+int mana_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			 struct ib_udata *uhw);
+int mana_ib_query_port(struct ib_device *ibdev, u32 port,
+		       struct ib_port_attr *props);
+int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
+		      union ib_gid *gid);
+
+void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext);
+
+#endif

drivers/infiniband/hw/mana/mr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+#define VALID_MR_FLAGS                                                         \
+	(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ)
+
+static enum gdma_mr_access_flags
+mana_ib_verbs_to_gdma_access_flags(int access_flags)
+{
+	enum gdma_mr_access_flags flags = GDMA_ACCESS_FLAG_LOCAL_READ;
+
+	if (access_flags & IB_ACCESS_LOCAL_WRITE)
+		flags |= GDMA_ACCESS_FLAG_LOCAL_WRITE;
+
+	if (access_flags & IB_ACCESS_REMOTE_WRITE)
+		flags |= GDMA_ACCESS_FLAG_REMOTE_WRITE;
+
+	if (access_flags & IB_ACCESS_REMOTE_READ)
+		flags |= GDMA_ACCESS_FLAG_REMOTE_READ;
+
+	return flags;
+}
+
+static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr *mr,
+				struct gdma_create_mr_params *mr_params)
+{
+	struct gdma_create_mr_response resp = {};
+	struct gdma_create_mr_request req = {};
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_MR, sizeof(req),
+			     sizeof(resp));
+	req.pd_handle = mr_params->pd_handle;
+	req.mr_type = mr_params->mr_type;
+
+	switch (mr_params->mr_type) {
+	case GDMA_MR_TYPE_GVA:
+		req.gva.dma_region_handle = mr_params->gva.dma_region_handle;
+		req.gva.virtual_address = mr_params->gva.virtual_address;
+		req.gva.access_flags = mr_params->gva.access_flags;
+		break;
+
+	default:
+		ibdev_dbg(&dev->ib_dev,
+			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
+			  req.mr_type);
+		return -EINVAL;
+	}
+
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_dbg(&dev->ib_dev, "Failed to create mr %d, %u", err,
+			  resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+
+		return err;
+	}
+
+	mr->ibmr.lkey = resp.lkey;
+	mr->ibmr.rkey = resp.rkey;
+	mr->mr_handle = resp.mr_handle;
+
+	return 0;
+}
+
+static int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev,
+				 gdma_obj_handle_t mr_handle)
+{
+	struct gdma_destroy_mr_response resp = {};
+	struct gdma_destroy_mr_request req = {};
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_MR, sizeof(req),
+			     sizeof(resp));
+
+	req.mr_handle = mr_handle;
+
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+	if (err || resp.hdr.status) {
+		dev_err(gc->dev, "Failed to destroy MR: %d, 0x%x\n", err,
+			resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+		return err;
+	}
+
+	return 0;
+}
+
+struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
+				  u64 iova, int access_flags,
+				  struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct gdma_create_mr_params mr_params = {};
+	struct ib_device *ibdev = ibpd->device;
+	gdma_obj_handle_t dma_region_handle;
+	struct mana_ib_dev *dev;
+	struct mana_ib_mr *mr;
+	int err;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	ibdev_dbg(ibdev,
+		  "start 0x%llx, iova 0x%llx length 0x%llx access_flags 0x%x",
+		  start, iova, length, access_flags);
+
+	if (access_flags & ~VALID_MR_FLAGS)
+		return ERR_PTR(-EINVAL);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mr->umem = ib_umem_get(ibdev, start, length, access_flags);
+	if (IS_ERR(mr->umem)) {
+		err = PTR_ERR(mr->umem);
+		ibdev_dbg(ibdev,
+			  "Failed to get umem for register user-mr, %d\n", err);
+		goto err_free;
+	}
+
+	err = mana_ib_gd_create_dma_region(dev, mr->umem, &dma_region_handle);
+	if (err) {
+		ibdev_dbg(ibdev, "Failed create dma region for user-mr, %d\n",
+			  err);
+		goto err_umem;
+	}
+
+	ibdev_dbg(ibdev,
+		  "mana_ib_gd_create_dma_region ret %d gdma_region %llx\n", err,
+		  dma_region_handle);
+
+	mr_params.pd_handle = pd->pd_handle;
+	mr_params.mr_type = GDMA_MR_TYPE_GVA;
+	mr_params.gva.dma_region_handle = dma_region_handle;
+	mr_params.gva.virtual_address = iova;
+	mr_params.gva.access_flags =
+		mana_ib_verbs_to_gdma_access_flags(access_flags);
+
+	err = mana_ib_gd_create_mr(dev, mr, &mr_params);
+	if (err)
+		goto err_dma_region;
+
+	/*
+	 * There is no need to keep track of dma_region_handle after MR is
+	 * successfully created. The dma_region_handle is tracked in the PF
+	 * as part of the lifecycle of this MR.
+	 */
+
+	return &mr->ibmr;
+
+err_dma_region:
+	mana_gd_destroy_dma_region(dev->gdma_dev->gdma_context,
+				   dma_region_handle);
+
+err_umem:
+	ib_umem_release(mr->umem);
+
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
+{
+	struct mana_ib_mr *mr = container_of(ibmr, struct mana_ib_mr, ibmr);
+	struct ib_device *ibdev = ibmr->device;
+	struct mana_ib_dev *dev;
+	int err;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	err = mana_ib_gd_destroy_mr(dev, mr->mr_handle);
+	if (err)
+		return err;
+
+	if (mr->umem)
+		ib_umem_release(mr->umem);
+
+	kfree(mr);
+
+	return 0;
+}

drivers/infiniband/hw/mana/wq.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+struct ib_wq *mana_ib_create_wq(struct ib_pd *pd,
+				struct ib_wq_init_attr *init_attr,
+				struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev =
+		container_of(pd->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_create_wq ucmd = {};
+	struct mana_ib_wq *wq;
+	struct ib_umem *umem;
+	int err;
+
+	if (udata->inlen < sizeof(ucmd))
+		return ERR_PTR(-EINVAL);
+
+	err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
+	if (err) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Failed to copy from udata for create wq, %d\n", err);
+		return ERR_PTR(err);
+	}
+
+	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
+	if (!wq)
+		return ERR_PTR(-ENOMEM);
+
+	ibdev_dbg(&mdev->ib_dev, "ucmd wq_buf_addr 0x%llx\n", ucmd.wq_buf_addr);
+
+	umem = ib_umem_get(pd->device, ucmd.wq_buf_addr, ucmd.wq_buf_size,
+			   IB_ACCESS_LOCAL_WRITE);
+	if (IS_ERR(umem)) {
+		err = PTR_ERR(umem);
+		ibdev_dbg(&mdev->ib_dev,
+			  "Failed to get umem for create wq, err %d\n", err);
+		goto err_free_wq;
+	}
+
+	wq->umem = umem;
+	wq->wqe = init_attr->max_wr;
+	wq->wq_buf_size = ucmd.wq_buf_size;
+	wq->rx_object = INVALID_MANA_HANDLE;
+
+	err = mana_ib_gd_create_dma_region(mdev, wq->umem, &wq->gdma_region);
+	if (err) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Failed to create dma region for create wq, %d\n",
+			  err);
+		goto err_release_umem;
+	}
+
+	ibdev_dbg(&mdev->ib_dev,
+		  "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n",
+		  err, wq->gdma_region);
+
+	/* WQ ID is returned at wq_create time, doesn't know the value yet */
+
+	return &wq->ibwq;
+
+err_release_umem:
+	ib_umem_release(umem);
+
+err_free_wq:
+	kfree(wq);
+
+	return ERR_PTR(err);
+}
+
+int mana_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+		      u32 wq_attr_mask, struct ib_udata *udata)
+{
+	/* modify_wq is not supported by this version of the driver */
+	return -EOPNOTSUPP;
+}
+
+int mana_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
+{
+	struct mana_ib_wq *wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+	struct ib_device *ib_dev = ibwq->device;
+	struct mana_ib_dev *mdev;
+
+	mdev = container_of(ib_dev, struct mana_ib_dev, ib_dev);
+
+	mana_ib_gd_destroy_dma_region(mdev, wq->gdma_region);
+	ib_umem_release(wq->umem);
+
+	kfree(wq);
+
+	return 0;
+}
+
+int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_table,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata)
+{
+	/*
+	 * There is no additional data in ind_table to be maintained by this
+	 * driver, do nothing
+	 */
+	return 0;
+}
+
+int mana_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
+{
+	/*
+	 * There is no additional data in ind_table to be maintained by this
+	 * driver, do nothing
+	 */
+	return 0;
+}

include/net/mana/mana.h

@@ -412,6 +412,9 @@ int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 
 extern const struct ethtool_ops mana_ethtool_ops;
 
+/* A CQ can be created not associated with any EQ */
+#define GDMA_CQ_NO_EQ  0xffff
+
 struct mana_obj_spec {
 	u32 queue_index;
 	u64 gdma_region;

include/uapi/rdma/ib_user_ioctl_verbs.h

@@ -251,6 +251,7 @@ enum rdma_driver_id {
 	RDMA_DRIVER_EFA,
 	RDMA_DRIVER_SIW,
 	RDMA_DRIVER_ERDMA,
+	RDMA_DRIVER_MANA,
 };
 
 enum ib_uverbs_gid_type {

include/uapi/rdma/mana-abi.h

+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef MANA_ABI_USER_H
+#define MANA_ABI_USER_H
+
+#include <linux/types.h>
+#include <rdma/ib_user_ioctl_verbs.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+
+#define MANA_IB_UVERBS_ABI_VERSION 1
+
+struct mana_ib_create_cq {
+	__aligned_u64 buf_addr;
+};
+
+struct mana_ib_create_qp {
+	__aligned_u64 sq_buf_addr;
+	__u32 sq_buf_size;
+	__u32 port;
+};
+
+struct mana_ib_create_qp_resp {
+	__u32 sqid;
+	__u32 cqid;
+	__u32 tx_vp_offset;
+	__u32 reserved;
+};
+
+struct mana_ib_create_wq {
+	__aligned_u64 wq_buf_addr;
+	__u32 wq_buf_size;
+	__u32 reserved;
+};
+
+/* RX Hash function flags */
+enum mana_ib_rx_hash_function_flags {
+	MANA_IB_RX_HASH_FUNC_TOEPLITZ = 1 << 0,
+};
+
+struct mana_ib_create_qp_rss {
+	__aligned_u64 rx_hash_fields_mask;
+	__u8 rx_hash_function;
+	__u8 reserved[7];
+	__u32 rx_hash_key_len;
+	__u8 rx_hash_key[40];
+	__u32 port;
+};
+
+struct rss_resp_entry {
+	__u32 cqid;
+	__u32 wqid;
+};
+
+struct mana_ib_create_qp_rss_resp {
+	__aligned_u64 num_entries;
+	struct rss_resp_entry entries[64];
+};
+
+#endif