[v4,12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter

Commit Message

Long Li June 16, 2022, 2:07 a.m. UTC

From: Long Li <[e-mail]>

Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).

Signed-off-by: Long Li <[e-mail]>
---
Change log:
v2:
Changed coding sytles/formats
Checked undersize for udata length
Changed all logging to use ibdev_xxx()
Avoided page array copy when doing MR
Sorted driver ops
Fixed warnings reported by kernel test robot <[e-mail]>

v3:
More coding sytle/format changes

v4:
Process error on hardware vport configuration

 MAINTAINERS                             |   3 +
 drivers/infiniband/Kconfig              |   1 +
 drivers/infiniband/hw/Makefile          |   1 +
 drivers/infiniband/hw/mana/Kconfig      |   7 +
 drivers/infiniband/hw/mana/Makefile     |   4 +
 drivers/infiniband/hw/mana/cq.c         |  80 +++
 drivers/infiniband/hw/mana/main.c       | 681 ++++++++++++++++++++++++
 drivers/infiniband/hw/mana/mana_ib.h    | 145 +++++
 drivers/infiniband/hw/mana/mr.c         | 133 +++++
 drivers/infiniband/hw/mana/qp.c         | 501 +++++++++++++++++
 drivers/infiniband/hw/mana/wq.c         | 114 ++++
 include/net/mana/mana.h                 |   3 +
 include/uapi/rdma/ib_user_ioctl_verbs.h |   1 +
 include/uapi/rdma/mana-abi.h            |  66 +++
 14 files changed, 1740 insertions(+)
 create mode 100644 drivers/infiniband/hw/mana/Kconfig
 create mode 100644 drivers/infiniband/hw/mana/Makefile
 create mode 100644 drivers/infiniband/hw/mana/cq.c
 create mode 100644 drivers/infiniband/hw/mana/main.c
 create mode 100644 drivers/infiniband/hw/mana/mana_ib.h
 create mode 100644 drivers/infiniband/hw/mana/mr.c
 create mode 100644 drivers/infiniband/hw/mana/qp.c
 create mode 100644 drivers/infiniband/hw/mana/wq.c
 create mode 100644 include/uapi/rdma/mana-abi.h

Comments

Ajay Sharma June 25, 2022, 4:20 a.m. UTC | #1

Hello Maintainers,
 Any idea when these patches would make it into the next kernel release ?

Ajay

-----Original Message-----
From: [e-mail] <[e-mail]> 
Sent: Wednesday, June 15, 2022 9:07 PM
To: KY Srinivasan <[e-mail]>; Haiyang Zhang <[e-mail]>; Stephen Hemminger <[e-mail]>; Wei Liu <[e-mail]>; Dexuan Cui <[e-mail]>; David S. Miller <[e-mail]>; Jakub Kicinski <[e-mail]>; Paolo Abeni <[e-mail]>; Jason Gunthorpe <[e-mail]>; Leon Romanovsky <[e-mail]>; [e-mail]; [e-mail]; Ajay Sharma <[e-mail]>
Cc: [e-mail]; [e-mail]; [e-mail]; [e-mail]; Long Li <[e-mail]>
Subject: [EXTERNAL] [Patch v4 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter

From: Long Li <[e-mail]>

Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).

Signed-off-by: Long Li <[e-mail]>
---
Change log:
v2:
Changed coding sytles/formats
Checked undersize for udata length
Changed all logging to use ibdev_xxx()
Avoided page array copy when doing MR
Sorted driver ops
Fixed warnings reported by kernel test robot <[e-mail]>

v3:
More coding sytle/format changes

v4:
Process error on hardware vport configuration

 MAINTAINERS                             |   3 +
 drivers/infiniband/Kconfig              |   1 +
 drivers/infiniband/hw/Makefile          |   1 +
 drivers/infiniband/hw/mana/Kconfig      |   7 +
 drivers/infiniband/hw/mana/Makefile     |   4 +
 drivers/infiniband/hw/mana/cq.c         |  80 +++
 drivers/infiniband/hw/mana/main.c       | 681 ++++++++++++++++++++++++
 drivers/infiniband/hw/mana/mana_ib.h    | 145 +++++
 drivers/infiniband/hw/mana/mr.c         | 133 +++++
 drivers/infiniband/hw/mana/qp.c         | 501 +++++++++++++++++
 drivers/infiniband/hw/mana/wq.c         | 114 ++++
 include/net/mana/mana.h                 |   3 +
 include/uapi/rdma/ib_user_ioctl_verbs.h |   1 +
 include/uapi/rdma/mana-abi.h            |  66 +++
 14 files changed, 1740 insertions(+)
 create mode 100644 drivers/infiniband/hw/mana/Kconfig
 create mode 100644 drivers/infiniband/hw/mana/Makefile
 create mode 100644 drivers/infiniband/hw/mana/cq.c
 create mode 100644 drivers/infiniband/hw/mana/main.c
 create mode 100644 drivers/infiniband/hw/mana/mana_ib.h
 create mode 100644 drivers/infiniband/hw/mana/mr.c
 create mode 100644 drivers/infiniband/hw/mana/qp.c
 create mode 100644 drivers/infiniband/hw/mana/wq.c
 create mode 100644 include/uapi/rdma/mana-abi.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 51bec6d5076d..1bed8444786d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9078,6 +9078,7 @@ M:	Haiyang Zhang <[e-mail]>
 M:	Stephen Hemminger <[e-mail]>
 M:	Wei Liu <[e-mail]>
 M:	Dexuan Cui <[e-mail]>
+M:	Long Li <[e-mail]>
 L:	[e-mail]
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@@ -9095,6 +9096,7 @@ F:	arch/x86/kernel/cpu/mshyperv.c
 F:	drivers/clocksource/hyperv_timer.c
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
+F:	drivers/infiniband/hw/mana/
 F:	drivers/input/serio/hyperv-keyboard.c
 F:	drivers/iommu/hyperv-iommu.c
 F:	drivers/net/ethernet/microsoft/
@@ -9110,6 +9112,7 @@ F:	include/clocksource/hyperv_timer.h
 F:	include/linux/hyperv.h
 F:	include/net/mana
 F:	include/uapi/linux/hyperv.h
+F:	include/uapi/rdma/mana-abi.h
 F:	net/vmw_vsock/hyperv_transport.c
 F:	tools/hv/
 
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 33d3ce9c888e..a062c662ecff 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -83,6 +83,7 @@ source "drivers/infiniband/hw/qib/Kconfig"
 source "drivers/infiniband/hw/cxgb4/Kconfig"
 source "drivers/infiniband/hw/efa/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/ocrdma/Kconfig"
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index fba0b3be903e..f62e9e00c780 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/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/
diff --git a/drivers/infiniband/hw/mana/Kconfig b/drivers/infiniband/hw/mana/Kconfig
new file mode 100644
index 000000000000..b3ff03a23257
--- /dev/null
+++ b/drivers/infiniband/hw/mana/Kconfig
@@ -0,0 +1,7 @@
+# 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).
diff --git a/drivers/infiniband/hw/mana/Makefile b/drivers/infiniband/hw/mana/Makefile
new file mode 100644
index 000000000000..a799fe264c5a
--- /dev/null
+++ b/drivers/infiniband/hw/mana/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
+
+mana_ib-y := main.o wq.o qp.o cq.o mr.o
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
new file mode 100644
index 000000000000..046fd290073d
--- /dev/null
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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 -EFAULT;
+	}
+
+	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,
+					   PAGE_SIZE);
+	if (err) {
+		ibdev_err(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;
+}
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
new file mode 100644
index 000000000000..58254a0cf581
--- /dev/null
+++ b/drivers/infiniband/hw/mana/main.c
@@ -0,0 +1,681 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+MODULE_DESCRIPTION("Microsoft Azure Network Adapter IB driver");
+MODULE_LICENSE("Dual BSD/GPL");
+
+void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
+			 u32 port)
+{
+	struct gdma_dev *gd = dev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct net_device *ndev;
+	struct mana_context *mc;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[port];
+	mpc = netdev_priv(ndev);
+
+	mutex_lock(&pd->vport_mutex);
+
+	pd->vport_use_count--;
+	WARN_ON(pd->vport_use_count < 0);
+
+	if (!pd->vport_use_count)
+		mana_uncfg_vport(mpc);
+
+	mutex_unlock(&pd->vport_mutex);
+}
+
+int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd *pd,
+		      u32 doorbell_id)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	int err;
+
+	mc = mdev->driver_data;
+	ndev = mc->ports[port];
+	mpc = netdev_priv(ndev);
+
+	mutex_lock(&pd->vport_mutex);
+
+	pd->vport_use_count++;
+	if (pd->vport_use_count > 1) {
+		ibdev_dbg(&dev->ib_dev,
+			  "Skip as this PD is already configured vport\n");
+		mutex_unlock(&pd->vport_mutex);
+		return 0;
+	}
+	mutex_unlock(&pd->vport_mutex);
+
+	err = mana_cfg_vport(mpc, pd->pdn, doorbell_id);
+	if (err) {
+		mutex_lock(&pd->vport_mutex);
+		pd->vport_use_count--;
+		mutex_unlock(&pd->vport_mutex);
+
+		ibdev_err(&dev->ib_dev, "Failed to configure vPort %d\n", err);
+		return err;
+	}
+
+	pd->tx_shortform_allowed = mpc->tx_shortform_allowed;
+	pd->tx_vp_offset = mpc->tx_vp_offset;
+
+	ibdev_dbg(&dev->ib_dev,
+		  "vport handle %llx pdid %x doorbell_id %x "
+		  "tx_shortform_allowed %d tx_vp_offset %u\n",
+		  mpc->port_handle, pd->pdn, doorbell_id,
+		  pd->tx_shortform_allowed, pd->tx_vp_offset);
+
+	return 0;
+}
+
+static int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct ib_device *ibdev = ibpd->device;
+	enum gdma_pd_flags flags = 0;
+	struct mana_ib_dev *dev;
+	int ret;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	/* Set flags if this is a kernel request */
+	if (!ibpd->uobject)
+		flags = GDMA_PD_FLAG_ALLOW_GPA_MR | GDMA_PD_FLAG_ALLOW_FMR_MR;
+
+	ret = mana_ib_gd_create_pd(dev, &pd->pd_handle, &pd->pdn, flags);
+	if (ret) {
+		ibdev_err(ibdev, "Failed to get pd id, err %d\n", ret);
+		return ret;
+	}
+
+	mutex_init(&pd->vport_mutex);
+	pd->vport_use_count = 0;
+	return 0;
+}
+
+static int mana_ib_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct ib_device *ibdev = ibpd->device;
+	struct mana_ib_dev *dev;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	return mana_ib_gd_destroy_pd(dev, pd->pd_handle);
+}
+
+static int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext,
+				  struct ib_udata *udata)
+{
+	struct mana_ib_ucontext *ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	struct gdma_dev *dev;
+	int doorbell_page;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	dev = mdev->gdma_dev;
+	gc = dev->gdma_context;
+
+	/* Allocate a doorbell page index */
+	ret = mana_gd_allocate_doorbell_page(gc, &doorbell_page);
+	if (ret) {
+		ibdev_err(ibdev, "Failed to allocate doorbell page %d\n", ret);
+		return -ENOMEM;
+	}
+
+	ibdev_dbg(ibdev, "Doorbell page allocated %d\n", doorbell_page);
+
+	ucontext->doorbell = doorbell_page;
+
+	return 0;
+}
+
+static void mana_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
+{
+	struct mana_ib_ucontext *mana_ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	gc = mdev->gdma_dev->gdma_context;
+
+	ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext->doorbell);
+	if (ret)
+		ibdev_err(ibdev, "Failed to destroy doorbell page %d\n", ret);
+}
+
+int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem,
+				 mana_handle_t *gdma_region, u64 page_sz)
+{
+	size_t num_pages_total = ib_umem_num_dma_blocks(umem, page_sz);
+	struct gdma_dma_region_add_pages_req *add_req = NULL;
+	struct gdma_create_dma_region_resp create_resp = {};
+	struct gdma_create_dma_region_req *create_req;
+	size_t num_pages_cur, num_pages_to_handle;
+	unsigned int create_req_msg_size;
+	struct hw_channel_context *hwc;
+	struct ib_block_iter biter;
+	size_t max_pgs_create_cmd;
+	struct gdma_context *gc;
+	struct gdma_dev *mdev;
+	unsigned int i;
+	int err;
+
+	mdev = dev->gdma_dev;
+	gc = mdev->gdma_context;
+	hwc = gc->hwc.driver_data;
+	max_pgs_create_cmd =
+		(hwc->max_req_msg_size - sizeof(*create_req)) / sizeof(u64);
+
+	num_pages_to_handle =
+		min_t(size_t, num_pages_total, max_pgs_create_cmd);
+	create_req_msg_size =
+		struct_size(create_req, page_addr_list, num_pages_to_handle);
+
+	create_req = kzalloc(create_req_msg_size, GFP_KERNEL);
+	if (!create_req)
+		return -ENOMEM;
+
+	mana_gd_init_req_hdr(&create_req->hdr, GDMA_CREATE_DMA_REGION,
+			     create_req_msg_size, sizeof(create_resp));
+
+	create_req->length = umem->length;
+	create_req->offset_in_page = umem->address & (page_sz - 1);
+	create_req->gdma_page_type = order_base_2(page_sz) - PAGE_SHIFT;
+	create_req->page_count = num_pages_total;
+	create_req->page_addr_list_len = num_pages_to_handle;
+
+	ibdev_dbg(&dev->ib_dev,
+		  "size_dma_region %lu num_pages_total %lu, "
+		  "page_sz 0x%llx offset_in_page %u\n",
+		  umem->length, num_pages_total, page_sz,
+		  create_req->offset_in_page);
+
+	ibdev_dbg(&dev->ib_dev, "num_pages_to_handle %lu, gdma_page_type %u",
+		  num_pages_to_handle, create_req->gdma_page_type);
+
+	__rdma_umem_block_iter_start(&biter, umem, page_sz);
+
+	for (i = 0; i < num_pages_to_handle; ++i) {
+		dma_addr_t cur_addr;
+
+		__rdma_block_iter_next(&biter);
+		cur_addr = rdma_block_iter_dma_address(&biter);
+
+		create_req->page_addr_list[i] = cur_addr;
+
+		ibdev_dbg(&dev->ib_dev, "page num %u cur_addr 0x%llx\n", i,
+			  cur_addr);
+	}
+
+	err = mana_gd_send_request(gc, create_req_msg_size, create_req,
+				   sizeof(create_resp), &create_resp);
+	kfree(create_req);
+
+	if (err || create_resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to create DMA region: %d, 0x%x\n", err,
+			  create_resp.hdr.status);
+		goto error;
+	}
+
+	*gdma_region = create_resp.dma_region_handle;
+	ibdev_dbg(&dev->ib_dev, "Created DMA region with handle 0x%llx\n",
+		  *gdma_region);
+
+	num_pages_cur = num_pages_to_handle;
+
+	if (num_pages_cur < num_pages_total) {
+		unsigned int add_req_msg_size;
+		size_t max_pgs_add_cmd =
+			(hwc->max_req_msg_size - sizeof(*add_req)) /
+			sizeof(u64);
+
+		num_pages_to_handle =
+			min_t(size_t, num_pages_total - num_pages_cur,
+			      max_pgs_add_cmd);
+
+		/* Calculate the max num of pages that will be handled */
+		add_req_msg_size = struct_size(add_req, page_addr_list,
+					       num_pages_to_handle);
+
+		add_req = kmalloc(add_req_msg_size, GFP_KERNEL);
+		if (!add_req) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		while (num_pages_cur < num_pages_total) {
+			struct gdma_general_resp add_resp = {};
+			u32 expected_status = 0;
+
+			if (num_pages_cur + num_pages_to_handle <
+			    num_pages_total) {
+				/* Status indicating more pages are needed */
+				expected_status = GDMA_STATUS_MORE_ENTRIES;
+			}
+
+			memset(add_req, 0, add_req_msg_size);
+
+			mana_gd_init_req_hdr(&add_req->hdr,
+					     GDMA_DMA_REGION_ADD_PAGES,
+					     add_req_msg_size,
+					     sizeof(add_resp));
+			add_req->dma_region_handle = *gdma_region;
+			add_req->page_addr_list_len = num_pages_to_handle;
+
+			for (i = 0; i < num_pages_to_handle; ++i) {
+				dma_addr_t cur_addr =
+					rdma_block_iter_dma_address(&biter);
+				add_req->page_addr_list[i] = cur_addr;
+				__rdma_block_iter_next(&biter);
+
+				ibdev_dbg(&dev->ib_dev,
+					  "page_addr_list %lu addr 0x%llx\n",
+					  num_pages_cur + i, cur_addr);
+			}
+
+			err = mana_gd_send_request(gc, add_req_msg_size,
+						   add_req, sizeof(add_resp),
+						   &add_resp);
+			if (!err || add_resp.hdr.status != expected_status) {
+				ibdev_err(&dev->ib_dev,
+					  "Failed put DMA pages %u: %d,0x%x\n",
+					  i, err, add_resp.hdr.status);
+				err = -EPROTO;
+				goto free_req;
+			}
+
+			num_pages_cur += num_pages_to_handle;
+			num_pages_to_handle =
+				min_t(size_t, num_pages_total - num_pages_cur,
+				      max_pgs_add_cmd);
+			add_req_msg_size = sizeof(*add_req) +
+					   num_pages_to_handle * sizeof(u64);
+		}
+free_req:
+		kfree(add_req);
+	}
+
+error:
+	return err;
+}
+
+int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, u64 gdma_region)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_context *gc;
+
+	gc = mdev->gdma_context;
+	ibdev_dbg(&dev->ib_dev, "destroy dma region 0x%llx\n", gdma_region);
+
+	return mana_gd_destroy_dma_region(gc, gdma_region);
+}
+
+int mana_ib_gd_create_pd(struct mana_ib_dev *dev, u64 *pd_handle, u32 *pd_id,
+			 enum gdma_pd_flags flags)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_create_pd_resp resp = {};
+	struct gdma_create_pd_req req = {};
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_PD, sizeof(req),
+			     sizeof(resp));
+
+	req.flags = flags;
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to get pd_id err %d status %u\n", err,
+			  resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+
+		return err;
+	}
+
+	*pd_handle = resp.pd_handle;
+	*pd_id = resp.pd_id;
+	ibdev_dbg(&dev->ib_dev, "pd_handle 0x%llx pd_id %d\n", *pd_handle,
+		  *pd_id);
+
+	return 0;
+}
+
+int mana_ib_gd_destroy_pd(struct mana_ib_dev *dev, u64 pd_handle)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_destory_pd_resp resp = {};
+	struct gdma_destroy_pd_req req = {};
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_PD, sizeof(req),
+			     sizeof(resp));
+
+	req.pd_handle = pd_handle;
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to destroy pd_handle 0x%llx err %d status %u",
+			  pd_handle, err, resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+	}
+
+	return err;
+}
+
+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;
+
+	switch (mr_params->mr_type) {
+	case GDMA_MR_TYPE_GVA:
+		req.mr_type = 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;
+
+	case GDMA_MR_TYPE_GPA:
+		req.mr_type = GDMA_MR_TYPE_GPA;
+		req.gpa.access_flags = mr_params->gpa.access_flags;
+		break;
+
+	case GDMA_MR_TYPE_FMR:
+		req.mr_type = GDMA_MR_TYPE_FMR;
+		req.fmr.page_size = mr_params->fmr.page_size;
+		req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
+		break;
+
+	default:
+		ibdev_dbg(&dev->ib_dev,
+			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
+			  req.mr_type);
+		err = -EINVAL;
+		goto error;
+	}
+
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev, "Failed to create mr %d, %u", err,
+			  resp.hdr.status);
+		goto error;
+	}
+
+	mr->ibmr.lkey = resp.lkey;
+	mr->ibmr.rkey = resp.rkey;
+	mr->mr_handle = resp.mr_handle;
+
+	return 0;
+error:
+	return err;
+}
+
+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;
+}
+
+static int mana_ib_mmap(struct ib_ucontext *ibcontext,
+			struct vm_area_struct *vma)
+{
+	struct mana_ib_ucontext *mana_ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	phys_addr_t pfn;
+	pgprot_t prot;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	gc = mdev->gdma_dev->gdma_context;
+
+	if (vma->vm_pgoff != 0) {
+		ibdev_err(ibdev, "Unexpected vm_pgoff %lu\n", vma->vm_pgoff);
+		return -EINVAL;
+	}
+
+	/* Map to the page indexed by ucontext->doorbell */
+	pfn = (gc->phys_db_page_base +
+	       gc->db_page_size * mana_ucontext->doorbell) >>
+	      PAGE_SHIFT;
+	prot = pgprot_writecombine(vma->vm_page_prot);
+
+	ret = rdma_user_mmap_io(ibcontext, vma, pfn, gc->db_page_size, prot,
+				NULL);
+	if (ret)
+		ibdev_err(ibdev, "can't rdma_user_mmap_io ret %d\n", ret);
+	else
+		ibdev_dbg(ibdev, "mapped I/O pfn 0x%llx page_size %u, ret %d\n",
+			  pfn, gc->db_page_size, ret);
+
+	return ret;
+}
+
+static int mana_ib_get_port_immutable(struct ib_device *ibdev, u32 port_num,
+				      struct ib_port_immutable *immutable)
+{
+	/* This version only support RAW_PACKET
+	 * other values need to be filled for other types
+	 */
+	immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET;
+
+	return 0;
+}
+
+static int mana_ib_query_device(struct ib_device *ibdev,
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
+{
+	props->max_qp = MANA_MAX_NUM_QUEUES;
+	props->max_qp_wr = MAX_SEND_BUFFERS_PER_QUEUE;
+
+	/* max_cqe could be potentially much bigger.
+	 * As this version of driver only support RAW QP, set it to the same
+	 * value as max_qp_wr
+	 */
+	props->max_cqe = MAX_SEND_BUFFERS_PER_QUEUE;
+
+	props->max_mr_size = MANA_IB_MAX_MR_SIZE;
+	props->max_mr = INT_MAX;
+	props->max_send_sge = MAX_TX_WQE_SGL_ENTRIES;
+	props->max_recv_sge = MAX_RX_WQE_SGL_ENTRIES;
+
+	return 0;
+}
+
+static int mana_ib_query_port(struct ib_device *ibdev, u32 port,
+			      struct ib_port_attr *props)
+{
+	/* This version doesn't return port properties */
+	return 0;
+}
+
+static int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
+			     union ib_gid *gid)
+{
+	/* This version doesn't return GID properties */
+	return 0;
+}
+
+static void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
+{
+}
+
+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 = 0;
+
+	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,
+};
+
+static int __init mana_ib_init(void)
+{
+	auxiliary_driver_register(&mana_driver);
+
+	return 0;
+}
+
+static void __exit mana_ib_cleanup(void)
+{
+	auxiliary_driver_unregister(&mana_driver);
+}
+
+module_init(mana_ib_init);
+module_exit(mana_ib_cleanup);
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
new file mode 100644
index 000000000000..d3d42b11e95f
--- /dev/null
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * 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 <linux/auxiliary_bus.h>
+#include <rdma/mana-abi.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)(~(0ULL)))
+
+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, u64 page_sz);
+
+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_gd_create_pd(struct mana_ib_dev *dev, u64 *pd_handle, u32 *pd_id,
+			 enum gdma_pd_flags flags);
+
+int mana_ib_gd_destroy_pd(struct mana_ib_dev *dev, u64 pd_handle);
+
+int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr *mr,
+			 struct gdma_create_mr_params *mr_params);
+
+int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev, mana_handle_t mr_handle);
+#endif
diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
new file mode 100644
index 000000000000..962e40f2de53
--- /dev/null
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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;
+}
+
+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;
+	u64 page_sz;
+	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;
+	}
+
+	page_sz = ib_umem_find_best_pgsz(mr->umem, PAGE_SZ_BM, iova);
+	if (unlikely(!page_sz)) {
+		ibdev_err(ibdev, "Failed to get best page size\n");
+		err = -EOPNOTSUPP;
+		goto err_umem;
+	}
+	ibdev_dbg(ibdev, "Page size chosen %llu\n", page_sz);
+
+	err = mana_ib_gd_create_dma_region(dev, mr->umem, &dma_region_handle,
+					   page_sz);
+	if (err) {
+		ibdev_err(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.
+	 */
+
+	mr->ibmr.length = length;
+	mr->ibmr.page_size = page_sz;
+	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;
+}
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
new file mode 100644
index 000000000000..75100674f1cf
--- /dev/null
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -0,0 +1,501 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev,
+				      struct net_device *ndev,
+				      mana_handle_t default_rxobj,
+				      mana_handle_t ind_table[],
+				      u32 log_ind_tbl_size, u32 rx_hash_key_len,
+				      u8 *rx_hash_key)
+{
+	struct mana_port_context *mpc = netdev_priv(ndev);
+	struct mana_cfg_rx_steer_req *req = NULL;
+	struct mana_cfg_rx_steer_resp resp = {};
+	mana_handle_t *req_indir_tab;
+	struct gdma_context *gc;
+	struct gdma_dev *mdev;
+	u32 req_buf_size;
+	int i, err;
+
+	mdev = dev->gdma_dev;
+	gc = mdev->gdma_context;
+
+	req_buf_size =
+		sizeof(*req) + sizeof(mana_handle_t) * MANA_INDIRECT_TABLE_SIZE;
+	req = kzalloc(req_buf_size, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	mana_gd_init_req_hdr(&req->hdr, MANA_CONFIG_VPORT_RX, req_buf_size,
+			     sizeof(resp));
+
+	req->vport = mpc->port_handle;
+	req->rx_enable = 1;
+	req->update_default_rxobj = 1;
+	req->default_rxobj = default_rxobj;
+	req->hdr.dev_id = mdev->dev_id;
+
+	/* If there are more than 1 entries in indirection table, enable RSS */
+	if (log_ind_tbl_size)
+		req->rss_enable = true;
+
+	req->num_indir_entries = MANA_INDIRECT_TABLE_SIZE;
+	req->indir_tab_offset = sizeof(*req);
+	req->update_indir_tab = true;
+
+	req_indir_tab = (mana_handle_t *)(req + 1);
+	/* The ind table passed to the hardware must have
+	 * MANA_INDIRECT_TABLE_SIZE entries. Adjust the verb
+	 * ind_table to MANA_INDIRECT_TABLE_SIZE if required
+	 */
+	ibdev_dbg(&dev->ib_dev, "ind table size %u\n", 1 << log_ind_tbl_size);
+	for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) {
+		req_indir_tab[i] = ind_table[i % (1 << log_ind_tbl_size)];
+		ibdev_dbg(&dev->ib_dev, "index %u handle 0x%llx\n", i,
+			  req_indir_tab[i]);
+	}
+
+	req->update_hashkey = true;
+	if (rx_hash_key_len)
+		memcpy(req->hashkey, rx_hash_key, rx_hash_key_len);
+	else
+		netdev_rss_key_fill(req->hashkey, MANA_HASH_KEY_SIZE);
+
+	ibdev_dbg(&dev->ib_dev, "vport handle %llu default_rxobj 0x%llx\n",
+		  req->vport, default_rxobj);
+
+	err = mana_gd_send_request(gc, req_buf_size, req, sizeof(resp), &resp);
+	if (err) {
+		netdev_err(ndev, "Failed to configure vPort RX: %d\n", err);
+		goto out;
+	}
+
+	if (resp.hdr.status) {
+		netdev_err(ndev, "vPort RX configuration failed: 0x%x\n",
+			   resp.hdr.status);
+		err = -EPROTO;
+	}
+
+	netdev_info(ndev, "Configured steering vPort %llu log_entries %u\n",
+		    mpc->port_handle, log_ind_tbl_size);
+
+out:
+	kfree(req);
+	return err;
+}
+
+static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd,
+				 struct ib_qp_init_attr *attr,
+				 struct ib_udata *udata)
+{
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+	struct mana_ib_dev *mdev =
+		container_of(pd->device, struct mana_ib_dev, ib_dev);
+	struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl;
+	struct mana_ib_create_qp_rss_resp resp = {};
+	struct mana_ib_create_qp_rss ucmd = {};
+	struct gdma_dev *gd = mdev->gdma_dev;
+	mana_handle_t *mana_ind_table;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_cq *cq;
+	struct mana_ib_wq *wq;
+	struct ib_cq *ibcq;
+	struct ib_wq *ibwq;
+	int i = 0, ret;
+	u32 port;
+
+	mc = gd->driver_data;
+
+	if (udata->inlen < sizeof(ucmd))
+		return -EINVAL;
+
+	ret = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
+	if (ret) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Failed copy from udata for create rss-qp, err %d\n",
+			  ret);
+		return -EFAULT;
+	}
+
+	if (attr->cap.max_recv_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_recv_wr %d exceeding limit.\n",
+			  attr->cap.max_recv_wr);
+		return -EINVAL;
+	}
+
+	if (attr->cap.max_recv_sge > MAX_RX_WQE_SGL_ENTRIES) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_recv_sge %d exceeding limit.\n",
+			  attr->cap.max_recv_sge);
+		return -EINVAL;
+	}
+
+	if (ucmd.rx_hash_function != MANA_IB_RX_HASH_FUNC_TOEPLITZ) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "RX Hash function is not supported, %d\n",
+			  ucmd.rx_hash_function);
+		return -EINVAL;
+	}
+
+	/* IB ports start with 1, MANA start with 0 */
+	port = ucmd.port;
+	if (port < 1 || port > mc->num_ports) {
+		ibdev_dbg(&mdev->ib_dev, "Invalid port %u in creating qp\n",
+			  port);
+		return -EINVAL;
+	}
+	ndev = mc->ports[port - 1];
+	mpc = netdev_priv(ndev);
+
+	ibdev_dbg(&mdev->ib_dev, "rx_hash_function %d port %d\n",
+		  ucmd.rx_hash_function, port);
+
+	mana_ind_table = kzalloc(sizeof(mana_handle_t) *
+					 (1 << ind_tbl->log_ind_tbl_size),
+				 GFP_KERNEL);
+	if (!mana_ind_table) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	qp->port = port;
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		struct mana_obj_spec wq_spec = {};
+		struct mana_obj_spec cq_spec = {};
+
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+
+		ibcq = ibwq->cq;
+		cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+
+		wq_spec.gdma_region = wq->gdma_region;
+		wq_spec.queue_size = wq->wq_buf_size;
+
+		cq_spec.gdma_region = cq->gdma_region;
+		cq_spec.queue_size = cq->cqe * COMP_ENTRY_SIZE;
+		cq_spec.modr_ctx_id = 0;
+		cq_spec.attached_eq = GDMA_CQ_NO_EQ;
+
+		ret = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_RQ,
+					 &wq_spec, &cq_spec, &wq->rx_object);
+		if (ret)
+			goto fail;
+
+		/* The GDMA regions are now owned by the WQ object */
+		wq->gdma_region = GDMA_INVALID_DMA_REGION;
+		cq->gdma_region = GDMA_INVALID_DMA_REGION;
+
+		wq->id = wq_spec.queue_index;
+		cq->id = cq_spec.queue_index;
+
+		ibdev_dbg(&mdev->ib_dev,
+			  "ret %d rx_object 0x%llx wq id %llu cq id %llu\n",
+			  ret, wq->rx_object, wq->id, cq->id);
+
+		resp.entries[i].cqid = cq->id;
+		resp.entries[i].wqid = wq->id;
+
+		mana_ind_table[i] = wq->rx_object;
+	}
+	resp.num_entries = i;
+
+	ret = mana_ib_cfg_vport_steering(mdev, ndev, wq->rx_object,
+					 mana_ind_table,
+					 ind_tbl->log_ind_tbl_size,
+					 ucmd.rx_hash_key_len,
+					 ucmd.rx_hash_key);
+	if (ret)
+		goto fail;
+
+	kfree(mana_ind_table);
+
+	if (udata) {
+		ret = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (ret) {
+			ibdev_dbg(&mdev->ib_dev,
+				  "Failed to copy to udata create rss-qp, %d\n",
+				  ret);
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0) {
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+		mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
+	}
+
+	kfree(mana_ind_table);
+
+	return ret;
+}
+
+static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
+				 struct ib_qp_init_attr *attr,
+				 struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+	struct mana_ib_dev *mdev =
+		container_of(ibpd->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_cq *send_cq =
+		container_of(attr->send_cq, struct mana_ib_cq, ibcq);
+	struct ib_ucontext *ib_ucontext = ibpd->uobject->context;
+	struct mana_ib_create_qp_resp resp = {};
+	struct mana_ib_ucontext *mana_ucontext;
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct mana_ib_create_qp ucmd = {};
+	struct mana_obj_spec wq_spec = {};
+	struct mana_obj_spec cq_spec = {};
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct ib_umem *umem;
+	int err;
+	u32 port;
+
+	mana_ucontext =
+		container_of(ib_ucontext, struct mana_ib_ucontext, ibucontext);
+	mc = gd->driver_data;
+
+	if (udata->inlen < sizeof(ucmd))
+		return -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 create qp-raw, %d\n", err);
+		return -EFAULT;
+	}
+
+	/* IB ports start with 1, MANA Ethernet ports start with 0 */
+	port = ucmd.port;
+	if (ucmd.port > mc->num_ports)
+		return -EINVAL;
+
+	if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_send_wr %d exceeding limit\n",
+			  attr->cap.max_send_wr);
+		return -EINVAL;
+	}
+
+	if (attr->cap.max_send_sge > MAX_TX_WQE_SGL_ENTRIES) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_send_sge %d exceeding limit\n",
+			  attr->cap.max_send_sge);
+		return -EINVAL;
+	}
+
+	ndev = mc->ports[port - 1];
+	mpc = netdev_priv(ndev);
+	ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port, ndev, mpc);
+
+	err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext->doorbell);
+	if (err)
+		return -ENODEV;
+
+	qp->port = port;
+
+	ibdev_dbg(&mdev->ib_dev, "ucmd sq_buf_addr 0x%llx port %u\n",
+		  ucmd.sq_buf_addr, ucmd.port);
+
+	umem = ib_umem_get(ibpd->device, ucmd.sq_buf_addr, ucmd.sq_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 qp-raw, err %d\n",
+			  err);
+		goto err_free_vport;
+	}
+	qp->sq_umem = umem;
+
+	err = mana_ib_gd_create_dma_region(mdev, qp->sq_umem,
+					   &qp->sq_gdma_region, PAGE_SIZE);
+	if (err) {
+		ibdev_err(&mdev->ib_dev,
+			  "Failed to create dma region for create qp-raw, %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, qp->sq_gdma_region);
+
+	/* Create a WQ on the same port handle used by the Ethernet */
+	wq_spec.gdma_region = qp->sq_gdma_region;
+	wq_spec.queue_size = ucmd.sq_buf_size;
+
+	cq_spec.gdma_region = send_cq->gdma_region;
+	cq_spec.queue_size = send_cq->cqe * COMP_ENTRY_SIZE;
+	cq_spec.modr_ctx_id = 0;
+	cq_spec.attached_eq = GDMA_CQ_NO_EQ;
+
+	err = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_SQ, &wq_spec,
+				 &cq_spec, &qp->tx_object);
+	if (err) {
+		ibdev_err(&mdev->ib_dev,
+			  "Failed to create wq for create raw-qp, err %d\n",
+			  err);
+		goto err_destroy_dma_region;
+	}
+
+	/* The GDMA regions are now owned by the WQ object */
+	qp->sq_gdma_region = GDMA_INVALID_DMA_REGION;
+	send_cq->gdma_region = GDMA_INVALID_DMA_REGION;
+
+	qp->sq_id = wq_spec.queue_index;
+	send_cq->id = cq_spec.queue_index;
+
+	ibdev_dbg(&mdev->ib_dev,
+		  "ret %d qp->tx_object 0x%llx sq id %llu cq id %llu\n", err,
+		  qp->tx_object, qp->sq_id, send_cq->id);
+
+	resp.sqid = qp->sq_id;
+	resp.cqid = send_cq->id;
+	resp.tx_vp_offset = pd->tx_vp_offset;
+
+	if (udata) {
+		err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (err) {
+			ibdev_dbg(&mdev->ib_dev,
+				  "Failed copy udata for create qp-raw, %d\n",
+				  err);
+			goto err_destroy_wq_obj;
+		}
+	}
+
+	return 0;
+
+err_destroy_wq_obj:
+	mana_destroy_wq_obj(mpc, GDMA_SQ, qp->tx_object);
+
+err_destroy_dma_region:
+	mana_ib_gd_destroy_dma_region(mdev, qp->sq_gdma_region);
+
+err_release_umem:
+	ib_umem_release(umem);
+
+err_free_vport:
+	mana_ib_uncfg_vport(mdev, pd, port - 1);
+
+	return err;
+}
+
+int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
+		      struct ib_udata *udata)
+{
+	switch (attr->qp_type) {
+	case IB_QPT_RAW_PACKET:
+		/* When rwq_ind_tbl is used, it's for creating WQs for RSS */
+		if (attr->rwq_ind_tbl)
+			return mana_ib_create_qp_rss(ibqp, ibqp->pd, attr,
+						     udata);
+
+		return mana_ib_create_qp_raw(ibqp, ibqp->pd, attr, udata);
+	default:
+		/* Creating QP other than IB_QPT_RAW_PACKET is not supported */
+		ibdev_dbg(ibqp->device, "Creating QP type %u not supported\n",
+			  attr->qp_type);
+	}
+
+	return -EINVAL;
+}
+
+int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+		      int attr_mask, struct ib_udata *udata)
+{
+	/* modify_qp is not supported by this version of the driver */
+	return -EOPNOTSUPP;
+}
+
+static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp,
+				  struct ib_rwq_ind_table *ind_tbl,
+				  struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev =
+		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_wq *wq;
+	struct ib_wq *ibwq;
+	int i;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[qp->port - 1];
+	mpc = netdev_priv(ndev);
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+		ibdev_dbg(&mdev->ib_dev, "destroying wq->rx_object %llu\n",
+			  wq->rx_object);
+		mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
+	}
+
+	return 0;
+}
+
+static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev =
+		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct ib_pd *ibpd = qp->ibqp.pd;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_pd *pd;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[qp->port - 1];
+	mpc = netdev_priv(ndev);
+	pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+
+	mana_destroy_wq_obj(mpc, GDMA_SQ, qp->tx_object);
+
+	if (qp->sq_umem) {
+		mana_ib_gd_destroy_dma_region(mdev, qp->sq_gdma_region);
+		ib_umem_release(qp->sq_umem);
+	}
+
+	mana_ib_uncfg_vport(mdev, pd, qp->port - 1);
+
+	return 0;
+}
+
+int mana_ib_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
+{
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+	switch (ibqp->qp_type) {
+	case IB_QPT_RAW_PACKET:
+		if (ibqp->rwq_ind_tbl)
+			return mana_ib_destroy_qp_rss(qp, ibqp->rwq_ind_tbl,
+						      udata);
+
+		return mana_ib_destroy_qp_raw(qp, udata);
+
+	default:
+		ibdev_dbg(ibqp->device, "Unexpected QP type %u\n",
+			  ibqp->qp_type);
+	}
+
+	return -ENOENT;
+}
diff --git a/drivers/infiniband/hw/mana/wq.c b/drivers/infiniband/hw/mana/wq.c
new file mode 100644
index 000000000000..a11d0ae35ff7
--- /dev/null
+++ b/drivers/infiniband/hw/mana/wq.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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(-EFAULT);
+	}
+
+	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,
+					   PAGE_SIZE);
+	if (err) {
+		ibdev_err(&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;
+}
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 3a0bc6e0b730..1ff6e0d07cfd 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -406,6 +406,9 @@ 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;
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 3072e5d6b692..081aabf536dc 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -250,6 +250,7 @@ enum rdma_driver_id {
 	RDMA_DRIVER_QIB,
 	RDMA_DRIVER_EFA,
 	RDMA_DRIVER_SIW,
+	RDMA_DRIVER_MANA,
 };
 
 enum ib_uverbs_gid_type {
diff --git a/include/uapi/rdma/mana-abi.h b/include/uapi/rdma/mana-abi.h
new file mode 100644
index 000000000000..559c49b72e0d
--- /dev/null
+++ b/include/uapi/rdma/mana-abi.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * 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

Jason Gunthorpe June 26, 2022, 12:03 a.m. UTC | #2

On Sat, Jun 25, 2022 at 04:20:19AM +0000, Ajay Sharma wrote:
> Hello Maintainers,
>  Any idea when these patches would make it into the next kernel release ?

New rdma drivers typically take a long time to get merged due to their
typical huge size. Currently I'm working through ERDMA. Reviewing the
ERDMA submission would be helpful, I generally prefer it if people
proposing new drivers review other new drivers being submitted.

In this case it seems smaller, so you might make this cycle, though I
haven't even opened the userspace portion yet.

Jason

Dexuan Cui July 11, 2022, 1:42 a.m. UTC | #3

> From: [e-mail] <[e-mail]>
> Sent: Wednesday, June 15, 2022 7:07 PM
> ...
> +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct
> ib_umem *umem,
> +				 mana_handle_t *gdma_region, u64 page_sz)
> +{
> + ...
> +	err = mana_gd_send_request(gc, create_req_msg_size, create_req,
> +				   sizeof(create_resp), &create_resp);
> +	kfree(create_req);
> +
> +	if (err || create_resp.hdr.status) {
> +		ibdev_err(&dev->ib_dev,
> +			  "Failed to create DMA region: %d, 0x%x\n", err,
> +			  create_resp.hdr.status);

    if (!err)
        err = -EPROTO;

> +		goto error;
> +	}
> + ...
> +			err = mana_gd_send_request(gc, add_req_msg_size,
> +						   add_req, sizeof(add_resp),
> +						   &add_resp);
> +			if (!err || add_resp.hdr.status != expected_status) {
> +				ibdev_err(&dev->ib_dev,
> +					  "Failed put DMA pages %u: %d,0x%x\n",
> +					  i, err, add_resp.hdr.status);
> +				err = -EPROTO;

Should we try to undo what has been done by calling GDMA_DESTROY_DMA_REGION?

> +				goto free_req;
> +			}
> +
> +			num_pages_cur += num_pages_to_handle;
> +			num_pages_to_handle =
> +				min_t(size_t, num_pages_total - num_pages_cur,
> +				      max_pgs_add_cmd);
> +			add_req_msg_size = sizeof(*add_req) +
> +					   num_pages_to_handle * sizeof(u64);
> +		}
> +free_req:
> +		kfree(add_req);
> +	}
> +
> +error:
> +	return err;
> +}
> + ...
> +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;
> +
> +	switch (mr_params->mr_type) {
> +	case GDMA_MR_TYPE_GVA:
> +		req.mr_type = 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;
> +
> +	case GDMA_MR_TYPE_GPA:
> +		req.mr_type = GDMA_MR_TYPE_GPA;
> +		req.gpa.access_flags = mr_params->gpa.access_flags;
> +		break;
> +
> +	case GDMA_MR_TYPE_FMR:
> +		req.mr_type = GDMA_MR_TYPE_FMR;
> +		req.fmr.page_size = mr_params->fmr.page_size;
> +		req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
> +		break;
> +
> +	default:
> +		ibdev_dbg(&dev->ib_dev,
> +			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
> +			  req.mr_type);

Here req.mr_type is always 0.
We should remove the 3 above lines of "req.mr_type = ...", and 
add a line "req.mr_type = mr_params->mr_type;" before the "switch" line..

> +		err = -EINVAL;
> +		goto error;
> +	}
> +
> +	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
> +
> +	if (err || resp.hdr.status) {
> +		ibdev_err(&dev->ib_dev, "Failed to create mr %d, %u", err,
> +			  resp.hdr.status);

    if (!err)
        err = -EPROTO;

> +		goto error;
> +	}
> +
> +	mr->ibmr.lkey = resp.lkey;
> +	mr->ibmr.rkey = resp.rkey;
> +	mr->mr_handle = resp.mr_handle;
> +
> +	return 0;
> +error:
> +	return err;
> +}
> + ...
> +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 = 0;
No need to initialize 'ret' to 0.

> +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)

Should we return here without calling ib_umem_release() and kfree(mr)?
> +		return err;

> +
> +	if (mr->umem)
> +		ib_umem_release(mr->umem);
> +
> +	kfree(mr);
> +
> +	return 0;
> +}

Greg Kroah-Hartman July 12, 2022, 7:14 p.m. UTC | #4

On Wed, Jun 15, 2022 at 07:07:20PM -0700, [e-mail] wrote:
> --- /dev/null
> +++ b/drivers/infiniband/hw/mana/cq.c
> @@ -0,0 +1,80 @@
> +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB

Why perpetuate this mess that the OpenIB people created?  I thought that
no new drivers were going to be added with this, why does this one need
to have it as well if it is new?

thanks,

greg k-h

Long Li July 12, 2022, 11:46 p.m. UTC | #5

> Subject: Re: [Patch v4 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure
> Network Adapter
> 
> On Wed, Jun 15, 2022 at 07:07:20PM -0700, [e-mail] wrote:
> > --- /dev/null
> > +++ b/drivers/infiniband/hw/mana/cq.c
> > @@ -0,0 +1,80 @@
> > +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
> 
> Why perpetuate this mess that the OpenIB people created?  I thought that no
> new drivers were going to be added with this, why does this one need to have it
> as well if it is new?

I apologize for the incorrect license language. I followed other RDMA driver's license terms but didn't' realized their licensing language is not up to the standard.

The newly introduced EFA RDMA driver used the following license terms:
(drivers/infiniband/hw/efa/efa_main.c)
// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause

Is it acceptable that we use the same license terms?

Thanks,
Long

Ajay Sharma July 13, 2022, 4:32 a.m. UTC | #6

Please see comments inline 

-----Original Message-----
From: Dexuan Cui <[e-mail]> 
Sent: Sunday, July 10, 2022 8:43 PM
To: Long Li <[e-mail]>; KY Srinivasan <[e-mail]>; Haiyang Zhang <[e-mail]>; Stephen Hemminger <[e-mail]>; Wei Liu <[e-mail]>; David S. Miller <[e-mail]>; Jakub Kicinski <[e-mail]>; Paolo Abeni <[e-mail]>; Jason Gunthorpe <[e-mail]>; Leon Romanovsky <[e-mail]>; [e-mail]; [e-mail]; Ajay Sharma <[e-mail]>
Cc: [e-mail]; [e-mail]; [e-mail]; [e-mail]
Subject: RE: [Patch v4 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter

> From: [e-mail] <[e-mail]>
> Sent: Wednesday, June 15, 2022 7:07 PM ...
> +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct
> ib_umem *umem,
> +				 mana_handle_t *gdma_region, u64 page_sz) {  ...
> +	err = mana_gd_send_request(gc, create_req_msg_size, create_req,
> +				   sizeof(create_resp), &create_resp);
> +	kfree(create_req);
> +
> +	if (err || create_resp.hdr.status) {
> +		ibdev_err(&dev->ib_dev,
> +			  "Failed to create DMA region: %d, 0x%x\n", err,
> +			  create_resp.hdr.status);

    if (!err)
        err = -EPROTO;

> +		goto error;
> +	}
> + ...
> +			err = mana_gd_send_request(gc, add_req_msg_size,
> +						   add_req, sizeof(add_resp),
> +						   &add_resp);
> +			if (!err || add_resp.hdr.status != expected_status) {
> +				ibdev_err(&dev->ib_dev,
> +					  "Failed put DMA pages %u: %d,0x%x\n",
> +					  i, err, add_resp.hdr.status);
> +				err = -EPROTO;

Should we try to undo what has been done by calling GDMA_DESTROY_DMA_REGION?
Yes, I updated the patch.

> +				goto free_req;
> +			}
> +
> +			num_pages_cur += num_pages_to_handle;
> +			num_pages_to_handle =
> +				min_t(size_t, num_pages_total - num_pages_cur,
> +				      max_pgs_add_cmd);
> +			add_req_msg_size = sizeof(*add_req) +
> +					   num_pages_to_handle * sizeof(u64);
> +		}
> +free_req:
> +		kfree(add_req);
> +	}
> +
> +error:
> +	return err;
> +}
> + ...
> +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;
> +
> +	switch (mr_params->mr_type) {
> +	case GDMA_MR_TYPE_GVA:
> +		req.mr_type = 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;
> +
> +	case GDMA_MR_TYPE_GPA:
> +		req.mr_type = GDMA_MR_TYPE_GPA;
> +		req.gpa.access_flags = mr_params->gpa.access_flags;
> +		break;
> +
> +	case GDMA_MR_TYPE_FMR:
> +		req.mr_type = GDMA_MR_TYPE_FMR;
> +		req.fmr.page_size = mr_params->fmr.page_size;
> +		req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
> +		break;
> +
> +	default:
> +		ibdev_dbg(&dev->ib_dev,
> +			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
> +			  req.mr_type);

Here req.mr_type is always 0.
We should remove the 3 above lines of "req.mr_type = ...", and add a line "req.mr_type = mr_params->mr_type;" before the "switch" line..

No, That's incorrect. The mr_type is being explicitly set here to control what regions get exposed to the user and kernel. GPA and FMR are never exposed to user. So we cannot assign req.mr_type = mr_params->mr_type.

> +		err = -EINVAL;
> +		goto error;
> +	}
> +
> +	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), 
> +&resp);
> +
> +	if (err || resp.hdr.status) {
> +		ibdev_err(&dev->ib_dev, "Failed to create mr %d, %u", err,
> +			  resp.hdr.status);

    if (!err)
        err = -EPROTO;

> +		goto error;
> +	}
> +
> +	mr->ibmr.lkey = resp.lkey;
> +	mr->ibmr.rkey = resp.rkey;
> +	mr->mr_handle = resp.mr_handle;
> +
> +	return 0;
> +error:
> +	return err;
> +}
> + ...
> +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 = 0;
No need to initialize 'ret' to 0.
Agreed. Updated the patch.

> +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)

Should we return here without calling ib_umem_release() and kfree(mr)?
Yes, if the device fails to deallocate the resources and we release them back to kernel it will lead to unexpected results.

> +		return err;

> +
> +	if (mr->umem)
> +		ib_umem_release(mr->umem);
> +
> +	kfree(mr);
> +
> +	return 0;
> +}

Greg Kroah-Hartman July 13, 2022, 6:14 a.m. UTC | #7

On Tue, Jul 12, 2022 at 11:46:36PM +0000, Long Li wrote:
> > Subject: Re: [Patch v4 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure
> > Network Adapter
> > 
> > On Wed, Jun 15, 2022 at 07:07:20PM -0700, [e-mail] wrote:
> > > --- /dev/null
> > > +++ b/drivers/infiniband/hw/mana/cq.c
> > > @@ -0,0 +1,80 @@
> > > +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
> > 
> > Why perpetuate this mess that the OpenIB people created?  I thought that no
> > new drivers were going to be added with this, why does this one need to have it
> > as well if it is new?
> 
> I apologize for the incorrect license language. I followed other RDMA driver's license terms but didn't' realized their licensing language is not up to the standard.

You need to follow the license rules of your employer, please consult
with them as they know what to do here.

> The newly introduced EFA RDMA driver used the following license terms:
> (drivers/infiniband/hw/efa/efa_main.c)
> // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
> 
> Is it acceptable that we use the same license terms?

Again, discuss this with the lawyers at your company.  But if you are
going to use a dual-license, you must be prepared to defend why you are
doing so.

thanks,

greg k-h

Dexuan Cui July 13, 2022, 7:36 a.m. UTC | #8

> From: Ajay Sharma <[e-mail]>
> Sent: Tuesday, July 12, 2022 9:33 PM
> >  ...
> > +	switch (mr_params->mr_type) {
> > +	case GDMA_MR_TYPE_GVA:
> > +		req.mr_type = 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;
> > +
> > +	case GDMA_MR_TYPE_GPA:
> > +		req.mr_type = GDMA_MR_TYPE_GPA;
> > +		req.gpa.access_flags = mr_params->gpa.access_flags;
> > +		break;
> > +
> > +	case GDMA_MR_TYPE_FMR:
> > +		req.mr_type = GDMA_MR_TYPE_FMR;
> > +		req.fmr.page_size = mr_params->fmr.page_size;
> > +		req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
> > +		break;
> > +
> > +	default:
> > +		ibdev_dbg(&dev->ib_dev,
> > +			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
> > +			  req.mr_type);
> 
> Here req.mr_type is always 0.
> We should remove the 3 above lines of "req.mr_type = ...", and add a line
> "req.mr_type = mr_params->mr_type;" before the "switch" line..
> 
> No, That's incorrect. The mr_type is being explicitly set here to control what
> regions get exposed to the user and kernel. GPA and FMR are never exposed to
> user. So we cannot assign req.mr_type = mr_params->mr_type.

I'm not following you. I meant the below change, which should have no
functional change, right? In the "default:" branch , we just "goto error;", so
there is no functional change either.

--- drivers/infiniband/hw/mana/main.c.orig
+++ drivers/infiniband/hw/mana/main.c
@@ -394,21 +394,19 @@
                             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.mr_type = 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;

        case GDMA_MR_TYPE_GPA:
-               req.mr_type = GDMA_MR_TYPE_GPA;
                req.gpa.access_flags = mr_params->gpa.access_flags;
                break;

        case GDMA_MR_TYPE_FMR:
-               req.mr_type = GDMA_MR_TYPE_FMR;
                req.fmr.page_size = mr_params->fmr.page_size;
                req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
                break;

Jason Gunthorpe July 20, 2022, 11:49 p.m. UTC | #9

On Wed, Jun 15, 2022 at 07:07:20PM -0700, [e-mail] wrote:

> +static int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
> +{
> +	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
> +	struct ib_device *ibdev = ibpd->device;
> +	enum gdma_pd_flags flags = 0;
> +	struct mana_ib_dev *dev;
> +	int ret;
> +
> +	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
> +
> +	/* Set flags if this is a kernel request */
> +	if (!ibpd->uobject)
> +		flags = GDMA_PD_FLAG_ALLOW_GPA_MR | GDMA_PD_FLAG_ALLOW_FMR_MR;

I'm confused, this driver doesn't seem to support kverbs:

> +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,

eg there is no way to create a kernel MR..

So, why do I see so many kverbs like things - and why are things like
FMR in this driver that can never be used?

Jason

Cheng Xu July 21, 2022, 9:17 a.m. UTC | #10

On 6/16/22 10:07 AM, [e-mail] wrote:
> From: Long Li <[e-mail]>
> 

<...>

> +
> +static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
> +				 struct ib_qp_init_attr *attr,
> +				 struct ib_udata *udata)
> +{
> +	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
> +	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
> +	struct mana_ib_dev *mdev =
> +		container_of(ibpd->device, struct mana_ib_dev, ib_dev);
> +	struct mana_ib_cq *send_cq =
> +		container_of(attr->send_cq, struct mana_ib_cq, ibcq);
> +	struct ib_ucontext *ib_ucontext = ibpd->uobject->context;
> +	struct mana_ib_create_qp_resp resp = {};
> +	struct mana_ib_ucontext *mana_ucontext;
> +	struct gdma_dev *gd = mdev->gdma_dev;
> +	struct mana_ib_create_qp ucmd = {};
> +	struct mana_obj_spec wq_spec = {};
> +	struct mana_obj_spec cq_spec = {};
> +	struct mana_port_context *mpc;
> +	struct mana_context *mc;
> +	struct net_device *ndev;
> +	struct ib_umem *umem;
> +	int err;
> +	u32 port;
> +
> +	mana_ucontext =
> +		container_of(ib_ucontext, struct mana_ib_ucontext, ibucontext);
> +	mc = gd->driver_data;
> +
> +	if (udata->inlen < sizeof(ucmd))
> +		return -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 create qp-raw, %d\n", err);
> +		return -EFAULT;
> +	}
> +
> +	/* IB ports start with 1, MANA Ethernet ports start with 0 */
> +	port = ucmd.port;
> +	if (ucmd.port > mc->num_ports)
> +		return -EINVAL;
> +
> +	if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
> +		ibdev_dbg(&mdev->ib_dev,
> +			  "Requested max_send_wr %d exceeding limit\n",
> +			  attr->cap.max_send_wr);
> +		return -EINVAL;
> +	}
> +
> +	if (attr->cap.max_send_sge > MAX_TX_WQE_SGL_ENTRIES) {
> +		ibdev_dbg(&mdev->ib_dev,
> +			  "Requested max_send_sge %d exceeding limit\n",
> +			  attr->cap.max_send_sge);
> +		return -EINVAL;
> +	}
> +
> +	ndev = mc->ports[port - 1];
> +	mpc = netdev_priv(ndev);
> +	ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port, ndev, mpc);
> +
> +	err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext->doorbell);
> +	if (err)
> +		return -ENODEV;
> +
> +	qp->port = port;
> +
> +	ibdev_dbg(&mdev->ib_dev, "ucmd sq_buf_addr 0x%llx port %u\n",
> +		  ucmd.sq_buf_addr, ucmd.port);
> +
> +	umem = ib_umem_get(ibpd->device, ucmd.sq_buf_addr, ucmd.sq_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 qp-raw, err %d\n",
> +			  err);
> +		goto err_free_vport;
> +	}
> +	qp->sq_umem = umem;
> +
> +	err = mana_ib_gd_create_dma_region(mdev, qp->sq_umem,
> +					   &qp->sq_gdma_region, PAGE_SIZE);
> +	if (err) {
> +		ibdev_err(&mdev->ib_dev,
> +			  "Failed to create dma region for create qp-raw, %d\n",
> +			  err);

It is better not print in userspace-triggered paths.

There are also same issues in other paths.

Thanks,
Cheng Xu

Long Li July 21, 2022, 6:01 p.m. UTC | #11

> Subject: Re: [Patch v4 12/12] RDMA/mana_ib: Add a driver for Microsoft
> Azure Network Adapter
> 
> 
> 
> On 6/16/22 10:07 AM, [e-mail] wrote:
> > From: Long Li <[e-mail]>
> >
> 
> <...>
> 
> > +
> > +static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
> > +				 struct ib_qp_init_attr *attr,
> > +				 struct ib_udata *udata)
> > +{
> > +	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd,
> ibpd);
> > +	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp,
> ibqp);
> > +	struct mana_ib_dev *mdev =
> > +		container_of(ibpd->device, struct mana_ib_dev, ib_dev);
> > +	struct mana_ib_cq *send_cq =
> > +		container_of(attr->send_cq, struct mana_ib_cq, ibcq);
> > +	struct ib_ucontext *ib_ucontext = ibpd->uobject->context;
> > +	struct mana_ib_create_qp_resp resp = {};
> > +	struct mana_ib_ucontext *mana_ucontext;
> > +	struct gdma_dev *gd = mdev->gdma_dev;
> > +	struct mana_ib_create_qp ucmd = {};
> > +	struct mana_obj_spec wq_spec = {};
> > +	struct mana_obj_spec cq_spec = {};
> > +	struct mana_port_context *mpc;
> > +	struct mana_context *mc;
> > +	struct net_device *ndev;
> > +	struct ib_umem *umem;
> > +	int err;
> > +	u32 port;
> > +
> > +	mana_ucontext =
> > +		container_of(ib_ucontext, struct mana_ib_ucontext,
> ibucontext);
> > +	mc = gd->driver_data;
> > +
> > +	if (udata->inlen < sizeof(ucmd))
> > +		return -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 create qp-raw, %d\n",
> err);
> > +		return -EFAULT;
> > +	}
> > +
> > +	/* IB ports start with 1, MANA Ethernet ports start with 0 */
> > +	port = ucmd.port;
> > +	if (ucmd.port > mc->num_ports)
> > +		return -EINVAL;
> > +
> > +	if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
> > +		ibdev_dbg(&mdev->ib_dev,
> > +			  "Requested max_send_wr %d exceeding limit\n",
> > +			  attr->cap.max_send_wr);
> > +		return -EINVAL;
> > +	}
> > +
> > +	if (attr->cap.max_send_sge > MAX_TX_WQE_SGL_ENTRIES) {
> > +		ibdev_dbg(&mdev->ib_dev,
> > +			  "Requested max_send_sge %d exceeding limit\n",
> > +			  attr->cap.max_send_sge);
> > +		return -EINVAL;
> > +	}
> > +
> > +	ndev = mc->ports[port - 1];
> > +	mpc = netdev_priv(ndev);
> > +	ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port,
> ndev, mpc);
> > +
> > +	err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext-
> >doorbell);
> > +	if (err)
> > +		return -ENODEV;
> > +
> > +	qp->port = port;
> > +
> > +	ibdev_dbg(&mdev->ib_dev, "ucmd sq_buf_addr 0x%llx port %u\n",
> > +		  ucmd.sq_buf_addr, ucmd.port);
> > +
> > +	umem = ib_umem_get(ibpd->device, ucmd.sq_buf_addr,
> ucmd.sq_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 qp-raw, err %d\n",
> > +			  err);
> > +		goto err_free_vport;
> > +	}
> > +	qp->sq_umem = umem;
> > +
> > +	err = mana_ib_gd_create_dma_region(mdev, qp->sq_umem,
> > +					   &qp->sq_gdma_region, PAGE_SIZE);
> > +	if (err) {
> > +		ibdev_err(&mdev->ib_dev,
> > +			  "Failed to create dma region for create qp-
> raw, %d\n",
> > +			  err);
> 
> It is better not print in userspace-triggered paths.
> 
> There are also same issues in other paths.
> 
> Thanks,
> Cheng Xu


Thank you, I will scan the code and make sure user-mode can't flood error messages.

This error is a hardware/PF error. It means the hardware channel has faulted. It's logged at error level.

Long

Ajay Sharma July 21, 2022, 7:24 p.m. UTC | #12

> -----Original Message-----
> From: Jason Gunthorpe <[e-mail]>
> Sent: Wednesday, July 20, 2022 6:49 PM
> To: Long Li <[e-mail]>
> Cc: KY Srinivasan <[e-mail]>; Haiyang Zhang
> <[e-mail]>; Stephen Hemminger
> <[e-mail]>; Wei Liu <[e-mail]>; Dexuan Cui
> <[e-mail]>; David S. Miller <[e-mail]>; Jakub
> Kicinski <[e-mail]>; Paolo Abeni <[e-mail]>; Leon
> Romanovsky <[e-mail]>; [e-mail];
> [e-mail]; Ajay Sharma <[e-mail]>; linux-
> [e-mail]; [e-mail]; linux-
> [e-mail]; [e-mail]
> Subject: [EXTERNAL] Re: [Patch v4 12/12] RDMA/mana_ib: Add a driver for
> Microsoft Azure Network Adapter
> 
> On Wed, Jun 15, 2022 at 07:07:20PM -0700, [e-mail]
> wrote:
> 
> > +static int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata
> > +*udata) {
> > +	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
> > +	struct ib_device *ibdev = ibpd->device;
> > +	enum gdma_pd_flags flags = 0;
> > +	struct mana_ib_dev *dev;
> > +	int ret;
> > +
> > +	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
> > +
> > +	/* Set flags if this is a kernel request */
> > +	if (!ibpd->uobject)
> > +		flags = GDMA_PD_FLAG_ALLOW_GPA_MR |
> GDMA_PD_FLAG_ALLOW_FMR_MR;
> 
> I'm confused, this driver doesn't seem to support kverbs:
> 
> > +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,
> 
> eg there is no way to create a kernel MR..
> 
> So, why do I see so many kverbs like things - and why are things like FMR in
> this driver that can never be used?
> 
> Jason

The idea was to introduce kernel support in future. I will remove it from the code and upload the patch.

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index 51bec6d5076d..1bed8444786d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9078,6 +9078,7 @@  M:	Haiyang Zhang <[e-mail]>
 M:	Stephen Hemminger <[e-mail]>
 M:	Wei Liu <[e-mail]>
 M:	Dexuan Cui <[e-mail]>
+M:	Long Li <[e-mail]>
 L:	[e-mail]
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@@ -9095,6 +9096,7 @@  F:	arch/x86/kernel/cpu/mshyperv.c
 F:	drivers/clocksource/hyperv_timer.c
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
+F:	drivers/infiniband/hw/mana/
 F:	drivers/input/serio/hyperv-keyboard.c
 F:	drivers/iommu/hyperv-iommu.c
 F:	drivers/net/ethernet/microsoft/
@@ -9110,6 +9112,7 @@  F:	include/clocksource/hyperv_timer.h
 F:	include/linux/hyperv.h
 F:	include/net/mana
 F:	include/uapi/linux/hyperv.h
+F:	include/uapi/rdma/mana-abi.h
 F:	net/vmw_vsock/hyperv_transport.c
 F:	tools/hv/
 
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 33d3ce9c888e..a062c662ecff 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -83,6 +83,7 @@  source "drivers/infiniband/hw/qib/Kconfig"
 source "drivers/infiniband/hw/cxgb4/Kconfig"
 source "drivers/infiniband/hw/efa/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/ocrdma/Kconfig"
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index fba0b3be903e..f62e9e00c780 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/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/
diff --git a/drivers/infiniband/hw/mana/Kconfig b/drivers/infiniband/hw/mana/Kconfig
new file mode 100644
index 000000000000..b3ff03a23257
--- /dev/null
+++ b/drivers/infiniband/hw/mana/Kconfig
@@ -0,0 +1,7 @@ 
+# 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).
diff --git a/drivers/infiniband/hw/mana/Makefile b/drivers/infiniband/hw/mana/Makefile
new file mode 100644
index 000000000000..a799fe264c5a
--- /dev/null
+++ b/drivers/infiniband/hw/mana/Makefile
@@ -0,0 +1,4 @@ 
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
+
+mana_ib-y := main.o wq.o qp.o cq.o mr.o
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
new file mode 100644
index 000000000000..046fd290073d
--- /dev/null
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -0,0 +1,80 @@ 
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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 -EFAULT;
+	}
+
+	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,
+					   PAGE_SIZE);
+	if (err) {
+		ibdev_err(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;
+}
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
new file mode 100644
index 000000000000..58254a0cf581
--- /dev/null
+++ b/drivers/infiniband/hw/mana/main.c
@@ -0,0 +1,681 @@ 
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+MODULE_DESCRIPTION("Microsoft Azure Network Adapter IB driver");
+MODULE_LICENSE("Dual BSD/GPL");
+
+void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
+			 u32 port)
+{
+	struct gdma_dev *gd = dev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct net_device *ndev;
+	struct mana_context *mc;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[port];
+	mpc = netdev_priv(ndev);
+
+	mutex_lock(&pd->vport_mutex);
+
+	pd->vport_use_count--;
+	WARN_ON(pd->vport_use_count < 0);
+
+	if (!pd->vport_use_count)
+		mana_uncfg_vport(mpc);
+
+	mutex_unlock(&pd->vport_mutex);
+}
+
+int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd *pd,
+		      u32 doorbell_id)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	int err;
+
+	mc = mdev->driver_data;
+	ndev = mc->ports[port];
+	mpc = netdev_priv(ndev);
+
+	mutex_lock(&pd->vport_mutex);
+
+	pd->vport_use_count++;
+	if (pd->vport_use_count > 1) {
+		ibdev_dbg(&dev->ib_dev,
+			  "Skip as this PD is already configured vport\n");
+		mutex_unlock(&pd->vport_mutex);
+		return 0;
+	}
+	mutex_unlock(&pd->vport_mutex);
+
+	err = mana_cfg_vport(mpc, pd->pdn, doorbell_id);
+	if (err) {
+		mutex_lock(&pd->vport_mutex);
+		pd->vport_use_count--;
+		mutex_unlock(&pd->vport_mutex);
+
+		ibdev_err(&dev->ib_dev, "Failed to configure vPort %d\n", err);
+		return err;
+	}
+
+	pd->tx_shortform_allowed = mpc->tx_shortform_allowed;
+	pd->tx_vp_offset = mpc->tx_vp_offset;
+
+	ibdev_dbg(&dev->ib_dev,
+		  "vport handle %llx pdid %x doorbell_id %x "
+		  "tx_shortform_allowed %d tx_vp_offset %u\n",
+		  mpc->port_handle, pd->pdn, doorbell_id,
+		  pd->tx_shortform_allowed, pd->tx_vp_offset);
+
+	return 0;
+}
+
+static int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct ib_device *ibdev = ibpd->device;
+	enum gdma_pd_flags flags = 0;
+	struct mana_ib_dev *dev;
+	int ret;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	/* Set flags if this is a kernel request */
+	if (!ibpd->uobject)
+		flags = GDMA_PD_FLAG_ALLOW_GPA_MR | GDMA_PD_FLAG_ALLOW_FMR_MR;
+
+	ret = mana_ib_gd_create_pd(dev, &pd->pd_handle, &pd->pdn, flags);
+	if (ret) {
+		ibdev_err(ibdev, "Failed to get pd id, err %d\n", ret);
+		return ret;
+	}
+
+	mutex_init(&pd->vport_mutex);
+	pd->vport_use_count = 0;
+	return 0;
+}
+
+static int mana_ib_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct ib_device *ibdev = ibpd->device;
+	struct mana_ib_dev *dev;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	return mana_ib_gd_destroy_pd(dev, pd->pd_handle);
+}
+
+static int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext,
+				  struct ib_udata *udata)
+{
+	struct mana_ib_ucontext *ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	struct gdma_dev *dev;
+	int doorbell_page;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	dev = mdev->gdma_dev;
+	gc = dev->gdma_context;
+
+	/* Allocate a doorbell page index */
+	ret = mana_gd_allocate_doorbell_page(gc, &doorbell_page);
+	if (ret) {
+		ibdev_err(ibdev, "Failed to allocate doorbell page %d\n", ret);
+		return -ENOMEM;
+	}
+
+	ibdev_dbg(ibdev, "Doorbell page allocated %d\n", doorbell_page);
+
+	ucontext->doorbell = doorbell_page;
+
+	return 0;
+}
+
+static void mana_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
+{
+	struct mana_ib_ucontext *mana_ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	gc = mdev->gdma_dev->gdma_context;
+
+	ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext->doorbell);
+	if (ret)
+		ibdev_err(ibdev, "Failed to destroy doorbell page %d\n", ret);
+}
+
+int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem,
+				 mana_handle_t *gdma_region, u64 page_sz)
+{
+	size_t num_pages_total = ib_umem_num_dma_blocks(umem, page_sz);
+	struct gdma_dma_region_add_pages_req *add_req = NULL;
+	struct gdma_create_dma_region_resp create_resp = {};
+	struct gdma_create_dma_region_req *create_req;
+	size_t num_pages_cur, num_pages_to_handle;
+	unsigned int create_req_msg_size;
+	struct hw_channel_context *hwc;
+	struct ib_block_iter biter;
+	size_t max_pgs_create_cmd;
+	struct gdma_context *gc;
+	struct gdma_dev *mdev;
+	unsigned int i;
+	int err;
+
+	mdev = dev->gdma_dev;
+	gc = mdev->gdma_context;
+	hwc = gc->hwc.driver_data;
+	max_pgs_create_cmd =
+		(hwc->max_req_msg_size - sizeof(*create_req)) / sizeof(u64);
+
+	num_pages_to_handle =
+		min_t(size_t, num_pages_total, max_pgs_create_cmd);
+	create_req_msg_size =
+		struct_size(create_req, page_addr_list, num_pages_to_handle);
+
+	create_req = kzalloc(create_req_msg_size, GFP_KERNEL);
+	if (!create_req)
+		return -ENOMEM;
+
+	mana_gd_init_req_hdr(&create_req->hdr, GDMA_CREATE_DMA_REGION,
+			     create_req_msg_size, sizeof(create_resp));
+
+	create_req->length = umem->length;
+	create_req->offset_in_page = umem->address & (page_sz - 1);
+	create_req->gdma_page_type = order_base_2(page_sz) - PAGE_SHIFT;
+	create_req->page_count = num_pages_total;
+	create_req->page_addr_list_len = num_pages_to_handle;
+
+	ibdev_dbg(&dev->ib_dev,
+		  "size_dma_region %lu num_pages_total %lu, "
+		  "page_sz 0x%llx offset_in_page %u\n",
+		  umem->length, num_pages_total, page_sz,
+		  create_req->offset_in_page);
+
+	ibdev_dbg(&dev->ib_dev, "num_pages_to_handle %lu, gdma_page_type %u",
+		  num_pages_to_handle, create_req->gdma_page_type);
+
+	__rdma_umem_block_iter_start(&biter, umem, page_sz);
+
+	for (i = 0; i < num_pages_to_handle; ++i) {
+		dma_addr_t cur_addr;
+
+		__rdma_block_iter_next(&biter);
+		cur_addr = rdma_block_iter_dma_address(&biter);
+
+		create_req->page_addr_list[i] = cur_addr;
+
+		ibdev_dbg(&dev->ib_dev, "page num %u cur_addr 0x%llx\n", i,
+			  cur_addr);
+	}
+
+	err = mana_gd_send_request(gc, create_req_msg_size, create_req,
+				   sizeof(create_resp), &create_resp);
+	kfree(create_req);
+
+	if (err || create_resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to create DMA region: %d, 0x%x\n", err,
+			  create_resp.hdr.status);
+		goto error;
+	}
+
+	*gdma_region = create_resp.dma_region_handle;
+	ibdev_dbg(&dev->ib_dev, "Created DMA region with handle 0x%llx\n",
+		  *gdma_region);
+
+	num_pages_cur = num_pages_to_handle;
+
+	if (num_pages_cur < num_pages_total) {
+		unsigned int add_req_msg_size;
+		size_t max_pgs_add_cmd =
+			(hwc->max_req_msg_size - sizeof(*add_req)) /
+			sizeof(u64);
+
+		num_pages_to_handle =
+			min_t(size_t, num_pages_total - num_pages_cur,
+			      max_pgs_add_cmd);
+
+		/* Calculate the max num of pages that will be handled */
+		add_req_msg_size = struct_size(add_req, page_addr_list,
+					       num_pages_to_handle);
+
+		add_req = kmalloc(add_req_msg_size, GFP_KERNEL);
+		if (!add_req) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		while (num_pages_cur < num_pages_total) {
+			struct gdma_general_resp add_resp = {};
+			u32 expected_status = 0;
+
+			if (num_pages_cur + num_pages_to_handle <
+			    num_pages_total) {
+				/* Status indicating more pages are needed */
+				expected_status = GDMA_STATUS_MORE_ENTRIES;
+			}
+
+			memset(add_req, 0, add_req_msg_size);
+
+			mana_gd_init_req_hdr(&add_req->hdr,
+					     GDMA_DMA_REGION_ADD_PAGES,
+					     add_req_msg_size,
+					     sizeof(add_resp));
+			add_req->dma_region_handle = *gdma_region;
+			add_req->page_addr_list_len = num_pages_to_handle;
+
+			for (i = 0; i < num_pages_to_handle; ++i) {
+				dma_addr_t cur_addr =
+					rdma_block_iter_dma_address(&biter);
+				add_req->page_addr_list[i] = cur_addr;
+				__rdma_block_iter_next(&biter);
+
+				ibdev_dbg(&dev->ib_dev,
+					  "page_addr_list %lu addr 0x%llx\n",
+					  num_pages_cur + i, cur_addr);
+			}
+
+			err = mana_gd_send_request(gc, add_req_msg_size,
+						   add_req, sizeof(add_resp),
+						   &add_resp);
+			if (!err || add_resp.hdr.status != expected_status) {
+				ibdev_err(&dev->ib_dev,
+					  "Failed put DMA pages %u: %d,0x%x\n",
+					  i, err, add_resp.hdr.status);
+				err = -EPROTO;
+				goto free_req;
+			}
+
+			num_pages_cur += num_pages_to_handle;
+			num_pages_to_handle =
+				min_t(size_t, num_pages_total - num_pages_cur,
+				      max_pgs_add_cmd);
+			add_req_msg_size = sizeof(*add_req) +
+					   num_pages_to_handle * sizeof(u64);
+		}
+free_req:
+		kfree(add_req);
+	}
+
+error:
+	return err;
+}
+
+int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, u64 gdma_region)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_context *gc;
+
+	gc = mdev->gdma_context;
+	ibdev_dbg(&dev->ib_dev, "destroy dma region 0x%llx\n", gdma_region);
+
+	return mana_gd_destroy_dma_region(gc, gdma_region);
+}
+
+int mana_ib_gd_create_pd(struct mana_ib_dev *dev, u64 *pd_handle, u32 *pd_id,
+			 enum gdma_pd_flags flags)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_create_pd_resp resp = {};
+	struct gdma_create_pd_req req = {};
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_PD, sizeof(req),
+			     sizeof(resp));
+
+	req.flags = flags;
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to get pd_id err %d status %u\n", err,
+			  resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+
+		return err;
+	}
+
+	*pd_handle = resp.pd_handle;
+	*pd_id = resp.pd_id;
+	ibdev_dbg(&dev->ib_dev, "pd_handle 0x%llx pd_id %d\n", *pd_handle,
+		  *pd_id);
+
+	return 0;
+}
+
+int mana_ib_gd_destroy_pd(struct mana_ib_dev *dev, u64 pd_handle)
+{
+	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_destory_pd_resp resp = {};
+	struct gdma_destroy_pd_req req = {};
+	struct gdma_context *gc;
+	int err;
+
+	gc = mdev->gdma_context;
+
+	mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_PD, sizeof(req),
+			     sizeof(resp));
+
+	req.pd_handle = pd_handle;
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to destroy pd_handle 0x%llx err %d status %u",
+			  pd_handle, err, resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+	}
+
+	return err;
+}
+
+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;
+
+	switch (mr_params->mr_type) {
+	case GDMA_MR_TYPE_GVA:
+		req.mr_type = 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;
+
+	case GDMA_MR_TYPE_GPA:
+		req.mr_type = GDMA_MR_TYPE_GPA;
+		req.gpa.access_flags = mr_params->gpa.access_flags;
+		break;
+
+	case GDMA_MR_TYPE_FMR:
+		req.mr_type = GDMA_MR_TYPE_FMR;
+		req.fmr.page_size = mr_params->fmr.page_size;
+		req.fmr.reserved_pte_count = mr_params->fmr.reserved_pte_count;
+		break;
+
+	default:
+		ibdev_dbg(&dev->ib_dev,
+			  "invalid param (GDMA_MR_TYPE) passed, type %d\n",
+			  req.mr_type);
+		err = -EINVAL;
+		goto error;
+	}
+
+	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+
+	if (err || resp.hdr.status) {
+		ibdev_err(&dev->ib_dev, "Failed to create mr %d, %u", err,
+			  resp.hdr.status);
+		goto error;
+	}
+
+	mr->ibmr.lkey = resp.lkey;
+	mr->ibmr.rkey = resp.rkey;
+	mr->mr_handle = resp.mr_handle;
+
+	return 0;
+error:
+	return err;
+}
+
+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;
+}
+
+static int mana_ib_mmap(struct ib_ucontext *ibcontext,
+			struct vm_area_struct *vma)
+{
+	struct mana_ib_ucontext *mana_ucontext =
+		container_of(ibcontext, struct mana_ib_ucontext, ibucontext);
+	struct ib_device *ibdev = ibcontext->device;
+	struct mana_ib_dev *mdev;
+	struct gdma_context *gc;
+	phys_addr_t pfn;
+	pgprot_t prot;
+	int ret;
+
+	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+	gc = mdev->gdma_dev->gdma_context;
+
+	if (vma->vm_pgoff != 0) {
+		ibdev_err(ibdev, "Unexpected vm_pgoff %lu\n", vma->vm_pgoff);
+		return -EINVAL;
+	}
+
+	/* Map to the page indexed by ucontext->doorbell */
+	pfn = (gc->phys_db_page_base +
+	       gc->db_page_size * mana_ucontext->doorbell) >>
+	      PAGE_SHIFT;
+	prot = pgprot_writecombine(vma->vm_page_prot);
+
+	ret = rdma_user_mmap_io(ibcontext, vma, pfn, gc->db_page_size, prot,
+				NULL);
+	if (ret)
+		ibdev_err(ibdev, "can't rdma_user_mmap_io ret %d\n", ret);
+	else
+		ibdev_dbg(ibdev, "mapped I/O pfn 0x%llx page_size %u, ret %d\n",
+			  pfn, gc->db_page_size, ret);
+
+	return ret;
+}
+
+static int mana_ib_get_port_immutable(struct ib_device *ibdev, u32 port_num,
+				      struct ib_port_immutable *immutable)
+{
+	/* This version only support RAW_PACKET
+	 * other values need to be filled for other types
+	 */
+	immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET;
+
+	return 0;
+}
+
+static int mana_ib_query_device(struct ib_device *ibdev,
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
+{
+	props->max_qp = MANA_MAX_NUM_QUEUES;
+	props->max_qp_wr = MAX_SEND_BUFFERS_PER_QUEUE;
+
+	/* max_cqe could be potentially much bigger.
+	 * As this version of driver only support RAW QP, set it to the same
+	 * value as max_qp_wr
+	 */
+	props->max_cqe = MAX_SEND_BUFFERS_PER_QUEUE;
+
+	props->max_mr_size = MANA_IB_MAX_MR_SIZE;
+	props->max_mr = INT_MAX;
+	props->max_send_sge = MAX_TX_WQE_SGL_ENTRIES;
+	props->max_recv_sge = MAX_RX_WQE_SGL_ENTRIES;
+
+	return 0;
+}
+
+static int mana_ib_query_port(struct ib_device *ibdev, u32 port,
+			      struct ib_port_attr *props)
+{
+	/* This version doesn't return port properties */
+	return 0;
+}
+
+static int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
+			     union ib_gid *gid)
+{
+	/* This version doesn't return GID properties */
+	return 0;
+}
+
+static void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
+{
+}
+
+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 = 0;
+
+	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,
+};
+
+static int __init mana_ib_init(void)
+{
+	auxiliary_driver_register(&mana_driver);
+
+	return 0;
+}
+
+static void __exit mana_ib_cleanup(void)
+{
+	auxiliary_driver_unregister(&mana_driver);
+}
+
+module_init(mana_ib_init);
+module_exit(mana_ib_cleanup);
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
new file mode 100644
index 000000000000..d3d42b11e95f
--- /dev/null
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -0,0 +1,145 @@ 
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * 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 <linux/auxiliary_bus.h>
+#include <rdma/mana-abi.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)(~(0ULL)))
+
+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, u64 page_sz);
+
+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_gd_create_pd(struct mana_ib_dev *dev, u64 *pd_handle, u32 *pd_id,
+			 enum gdma_pd_flags flags);
+
+int mana_ib_gd_destroy_pd(struct mana_ib_dev *dev, u64 pd_handle);
+
+int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr *mr,
+			 struct gdma_create_mr_params *mr_params);
+
+int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev, mana_handle_t mr_handle);
+#endif
diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
new file mode 100644
index 000000000000..962e40f2de53
--- /dev/null
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -0,0 +1,133 @@ 
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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;
+}
+
+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;
+	u64 page_sz;
+	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;
+	}
+
+	page_sz = ib_umem_find_best_pgsz(mr->umem, PAGE_SZ_BM, iova);
+	if (unlikely(!page_sz)) {
+		ibdev_err(ibdev, "Failed to get best page size\n");
+		err = -EOPNOTSUPP;
+		goto err_umem;
+	}
+	ibdev_dbg(ibdev, "Page size chosen %llu\n", page_sz);
+
+	err = mana_ib_gd_create_dma_region(dev, mr->umem, &dma_region_handle,
+					   page_sz);
+	if (err) {
+		ibdev_err(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.
+	 */
+
+	mr->ibmr.length = length;
+	mr->ibmr.page_size = page_sz;
+	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;
+}
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
new file mode 100644
index 000000000000..75100674f1cf
--- /dev/null
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -0,0 +1,501 @@ 
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev,
+				      struct net_device *ndev,
+				      mana_handle_t default_rxobj,
+				      mana_handle_t ind_table[],
+				      u32 log_ind_tbl_size, u32 rx_hash_key_len,
+				      u8 *rx_hash_key)
+{
+	struct mana_port_context *mpc = netdev_priv(ndev);
+	struct mana_cfg_rx_steer_req *req = NULL;
+	struct mana_cfg_rx_steer_resp resp = {};
+	mana_handle_t *req_indir_tab;
+	struct gdma_context *gc;
+	struct gdma_dev *mdev;
+	u32 req_buf_size;
+	int i, err;
+
+	mdev = dev->gdma_dev;
+	gc = mdev->gdma_context;
+
+	req_buf_size =
+		sizeof(*req) + sizeof(mana_handle_t) * MANA_INDIRECT_TABLE_SIZE;
+	req = kzalloc(req_buf_size, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	mana_gd_init_req_hdr(&req->hdr, MANA_CONFIG_VPORT_RX, req_buf_size,
+			     sizeof(resp));
+
+	req->vport = mpc->port_handle;
+	req->rx_enable = 1;
+	req->update_default_rxobj = 1;
+	req->default_rxobj = default_rxobj;
+	req->hdr.dev_id = mdev->dev_id;
+
+	/* If there are more than 1 entries in indirection table, enable RSS */
+	if (log_ind_tbl_size)
+		req->rss_enable = true;
+
+	req->num_indir_entries = MANA_INDIRECT_TABLE_SIZE;
+	req->indir_tab_offset = sizeof(*req);
+	req->update_indir_tab = true;
+
+	req_indir_tab = (mana_handle_t *)(req + 1);
+	/* The ind table passed to the hardware must have
+	 * MANA_INDIRECT_TABLE_SIZE entries. Adjust the verb
+	 * ind_table to MANA_INDIRECT_TABLE_SIZE if required
+	 */
+	ibdev_dbg(&dev->ib_dev, "ind table size %u\n", 1 << log_ind_tbl_size);
+	for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) {
+		req_indir_tab[i] = ind_table[i % (1 << log_ind_tbl_size)];
+		ibdev_dbg(&dev->ib_dev, "index %u handle 0x%llx\n", i,
+			  req_indir_tab[i]);
+	}
+
+	req->update_hashkey = true;
+	if (rx_hash_key_len)
+		memcpy(req->hashkey, rx_hash_key, rx_hash_key_len);
+	else
+		netdev_rss_key_fill(req->hashkey, MANA_HASH_KEY_SIZE);
+
+	ibdev_dbg(&dev->ib_dev, "vport handle %llu default_rxobj 0x%llx\n",
+		  req->vport, default_rxobj);
+
+	err = mana_gd_send_request(gc, req_buf_size, req, sizeof(resp), &resp);
+	if (err) {
+		netdev_err(ndev, "Failed to configure vPort RX: %d\n", err);
+		goto out;
+	}
+
+	if (resp.hdr.status) {
+		netdev_err(ndev, "vPort RX configuration failed: 0x%x\n",
+			   resp.hdr.status);
+		err = -EPROTO;
+	}
+
+	netdev_info(ndev, "Configured steering vPort %llu log_entries %u\n",
+		    mpc->port_handle, log_ind_tbl_size);
+
+out:
+	kfree(req);
+	return err;
+}
+
+static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd,
+				 struct ib_qp_init_attr *attr,
+				 struct ib_udata *udata)
+{
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+	struct mana_ib_dev *mdev =
+		container_of(pd->device, struct mana_ib_dev, ib_dev);
+	struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl;
+	struct mana_ib_create_qp_rss_resp resp = {};
+	struct mana_ib_create_qp_rss ucmd = {};
+	struct gdma_dev *gd = mdev->gdma_dev;
+	mana_handle_t *mana_ind_table;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_cq *cq;
+	struct mana_ib_wq *wq;
+	struct ib_cq *ibcq;
+	struct ib_wq *ibwq;
+	int i = 0, ret;
+	u32 port;
+
+	mc = gd->driver_data;
+
+	if (udata->inlen < sizeof(ucmd))
+		return -EINVAL;
+
+	ret = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
+	if (ret) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Failed copy from udata for create rss-qp, err %d\n",
+			  ret);
+		return -EFAULT;
+	}
+
+	if (attr->cap.max_recv_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_recv_wr %d exceeding limit.\n",
+			  attr->cap.max_recv_wr);
+		return -EINVAL;
+	}
+
+	if (attr->cap.max_recv_sge > MAX_RX_WQE_SGL_ENTRIES) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_recv_sge %d exceeding limit.\n",
+			  attr->cap.max_recv_sge);
+		return -EINVAL;
+	}
+
+	if (ucmd.rx_hash_function != MANA_IB_RX_HASH_FUNC_TOEPLITZ) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "RX Hash function is not supported, %d\n",
+			  ucmd.rx_hash_function);
+		return -EINVAL;
+	}
+
+	/* IB ports start with 1, MANA start with 0 */
+	port = ucmd.port;
+	if (port < 1 || port > mc->num_ports) {
+		ibdev_dbg(&mdev->ib_dev, "Invalid port %u in creating qp\n",
+			  port);
+		return -EINVAL;
+	}
+	ndev = mc->ports[port - 1];
+	mpc = netdev_priv(ndev);
+
+	ibdev_dbg(&mdev->ib_dev, "rx_hash_function %d port %d\n",
+		  ucmd.rx_hash_function, port);
+
+	mana_ind_table = kzalloc(sizeof(mana_handle_t) *
+					 (1 << ind_tbl->log_ind_tbl_size),
+				 GFP_KERNEL);
+	if (!mana_ind_table) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	qp->port = port;
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		struct mana_obj_spec wq_spec = {};
+		struct mana_obj_spec cq_spec = {};
+
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+
+		ibcq = ibwq->cq;
+		cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+
+		wq_spec.gdma_region = wq->gdma_region;
+		wq_spec.queue_size = wq->wq_buf_size;
+
+		cq_spec.gdma_region = cq->gdma_region;
+		cq_spec.queue_size = cq->cqe * COMP_ENTRY_SIZE;
+		cq_spec.modr_ctx_id = 0;
+		cq_spec.attached_eq = GDMA_CQ_NO_EQ;
+
+		ret = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_RQ,
+					 &wq_spec, &cq_spec, &wq->rx_object);
+		if (ret)
+			goto fail;
+
+		/* The GDMA regions are now owned by the WQ object */
+		wq->gdma_region = GDMA_INVALID_DMA_REGION;
+		cq->gdma_region = GDMA_INVALID_DMA_REGION;
+
+		wq->id = wq_spec.queue_index;
+		cq->id = cq_spec.queue_index;
+
+		ibdev_dbg(&mdev->ib_dev,
+			  "ret %d rx_object 0x%llx wq id %llu cq id %llu\n",
+			  ret, wq->rx_object, wq->id, cq->id);
+
+		resp.entries[i].cqid = cq->id;
+		resp.entries[i].wqid = wq->id;
+
+		mana_ind_table[i] = wq->rx_object;
+	}
+	resp.num_entries = i;
+
+	ret = mana_ib_cfg_vport_steering(mdev, ndev, wq->rx_object,
+					 mana_ind_table,
+					 ind_tbl->log_ind_tbl_size,
+					 ucmd.rx_hash_key_len,
+					 ucmd.rx_hash_key);
+	if (ret)
+		goto fail;
+
+	kfree(mana_ind_table);
+
+	if (udata) {
+		ret = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (ret) {
+			ibdev_dbg(&mdev->ib_dev,
+				  "Failed to copy to udata create rss-qp, %d\n",
+				  ret);
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0) {
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+		mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
+	}
+
+	kfree(mana_ind_table);
+
+	return ret;
+}
+
+static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
+				 struct ib_qp_init_attr *attr,
+				 struct ib_udata *udata)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+	struct mana_ib_dev *mdev =
+		container_of(ibpd->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_cq *send_cq =
+		container_of(attr->send_cq, struct mana_ib_cq, ibcq);
+	struct ib_ucontext *ib_ucontext = ibpd->uobject->context;
+	struct mana_ib_create_qp_resp resp = {};
+	struct mana_ib_ucontext *mana_ucontext;
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct mana_ib_create_qp ucmd = {};
+	struct mana_obj_spec wq_spec = {};
+	struct mana_obj_spec cq_spec = {};
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct ib_umem *umem;
+	int err;
+	u32 port;
+
+	mana_ucontext =
+		container_of(ib_ucontext, struct mana_ib_ucontext, ibucontext);
+	mc = gd->driver_data;
+
+	if (udata->inlen < sizeof(ucmd))
+		return -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 create qp-raw, %d\n", err);
+		return -EFAULT;
+	}
+
+	/* IB ports start with 1, MANA Ethernet ports start with 0 */
+	port = ucmd.port;
+	if (ucmd.port > mc->num_ports)
+		return -EINVAL;
+
+	if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_send_wr %d exceeding limit\n",
+			  attr->cap.max_send_wr);
+		return -EINVAL;
+	}
+
+	if (attr->cap.max_send_sge > MAX_TX_WQE_SGL_ENTRIES) {
+		ibdev_dbg(&mdev->ib_dev,
+			  "Requested max_send_sge %d exceeding limit\n",
+			  attr->cap.max_send_sge);
+		return -EINVAL;
+	}
+
+	ndev = mc->ports[port - 1];
+	mpc = netdev_priv(ndev);
+	ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port, ndev, mpc);
+
+	err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext->doorbell);
+	if (err)
+		return -ENODEV;
+
+	qp->port = port;
+
+	ibdev_dbg(&mdev->ib_dev, "ucmd sq_buf_addr 0x%llx port %u\n",
+		  ucmd.sq_buf_addr, ucmd.port);
+
+	umem = ib_umem_get(ibpd->device, ucmd.sq_buf_addr, ucmd.sq_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 qp-raw, err %d\n",
+			  err);
+		goto err_free_vport;
+	}
+	qp->sq_umem = umem;
+
+	err = mana_ib_gd_create_dma_region(mdev, qp->sq_umem,
+					   &qp->sq_gdma_region, PAGE_SIZE);
+	if (err) {
+		ibdev_err(&mdev->ib_dev,
+			  "Failed to create dma region for create qp-raw, %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, qp->sq_gdma_region);
+
+	/* Create a WQ on the same port handle used by the Ethernet */
+	wq_spec.gdma_region = qp->sq_gdma_region;
+	wq_spec.queue_size = ucmd.sq_buf_size;
+
+	cq_spec.gdma_region = send_cq->gdma_region;
+	cq_spec.queue_size = send_cq->cqe * COMP_ENTRY_SIZE;
+	cq_spec.modr_ctx_id = 0;
+	cq_spec.attached_eq = GDMA_CQ_NO_EQ;
+
+	err = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_SQ, &wq_spec,
+				 &cq_spec, &qp->tx_object);
+	if (err) {
+		ibdev_err(&mdev->ib_dev,
+			  "Failed to create wq for create raw-qp, err %d\n",
+			  err);
+		goto err_destroy_dma_region;
+	}
+
+	/* The GDMA regions are now owned by the WQ object */
+	qp->sq_gdma_region = GDMA_INVALID_DMA_REGION;
+	send_cq->gdma_region = GDMA_INVALID_DMA_REGION;
+
+	qp->sq_id = wq_spec.queue_index;
+	send_cq->id = cq_spec.queue_index;
+
+	ibdev_dbg(&mdev->ib_dev,
+		  "ret %d qp->tx_object 0x%llx sq id %llu cq id %llu\n", err,
+		  qp->tx_object, qp->sq_id, send_cq->id);
+
+	resp.sqid = qp->sq_id;
+	resp.cqid = send_cq->id;
+	resp.tx_vp_offset = pd->tx_vp_offset;
+
+	if (udata) {
+		err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (err) {
+			ibdev_dbg(&mdev->ib_dev,
+				  "Failed copy udata for create qp-raw, %d\n",
+				  err);
+			goto err_destroy_wq_obj;
+		}
+	}
+
+	return 0;
+
+err_destroy_wq_obj:
+	mana_destroy_wq_obj(mpc, GDMA_SQ, qp->tx_object);
+
+err_destroy_dma_region:
+	mana_ib_gd_destroy_dma_region(mdev, qp->sq_gdma_region);
+
+err_release_umem:
+	ib_umem_release(umem);
+
+err_free_vport:
+	mana_ib_uncfg_vport(mdev, pd, port - 1);
+
+	return err;
+}
+
+int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
+		      struct ib_udata *udata)
+{
+	switch (attr->qp_type) {
+	case IB_QPT_RAW_PACKET:
+		/* When rwq_ind_tbl is used, it's for creating WQs for RSS */
+		if (attr->rwq_ind_tbl)
+			return mana_ib_create_qp_rss(ibqp, ibqp->pd, attr,
+						     udata);
+
+		return mana_ib_create_qp_raw(ibqp, ibqp->pd, attr, udata);
+	default:
+		/* Creating QP other than IB_QPT_RAW_PACKET is not supported */
+		ibdev_dbg(ibqp->device, "Creating QP type %u not supported\n",
+			  attr->qp_type);
+	}
+
+	return -EINVAL;
+}
+
+int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+		      int attr_mask, struct ib_udata *udata)
+{
+	/* modify_qp is not supported by this version of the driver */
+	return -EOPNOTSUPP;
+}
+
+static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp,
+				  struct ib_rwq_ind_table *ind_tbl,
+				  struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev =
+		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_wq *wq;
+	struct ib_wq *ibwq;
+	int i;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[qp->port - 1];
+	mpc = netdev_priv(ndev);
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		ibwq = ind_tbl->ind_tbl[i];
+		wq = container_of(ibwq, struct mana_ib_wq, ibwq);
+		ibdev_dbg(&mdev->ib_dev, "destroying wq->rx_object %llu\n",
+			  wq->rx_object);
+		mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object);
+	}
+
+	return 0;
+}
+
+static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev =
+		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
+	struct gdma_dev *gd = mdev->gdma_dev;
+	struct ib_pd *ibpd = qp->ibqp.pd;
+	struct mana_port_context *mpc;
+	struct mana_context *mc;
+	struct net_device *ndev;
+	struct mana_ib_pd *pd;
+
+	mc = gd->driver_data;
+	ndev = mc->ports[qp->port - 1];
+	mpc = netdev_priv(ndev);
+	pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+
+	mana_destroy_wq_obj(mpc, GDMA_SQ, qp->tx_object);
+
+	if (qp->sq_umem) {
+		mana_ib_gd_destroy_dma_region(mdev, qp->sq_gdma_region);
+		ib_umem_release(qp->sq_umem);
+	}
+
+	mana_ib_uncfg_vport(mdev, pd, qp->port - 1);
+
+	return 0;
+}
+
+int mana_ib_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
+{
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+
+	switch (ibqp->qp_type) {
+	case IB_QPT_RAW_PACKET:
+		if (ibqp->rwq_ind_tbl)
+			return mana_ib_destroy_qp_rss(qp, ibqp->rwq_ind_tbl,
+						      udata);
+
+		return mana_ib_destroy_qp_raw(qp, udata);
+
+	default:
+		ibdev_dbg(ibqp->device, "Unexpected QP type %u\n",
+			  ibqp->qp_type);
+	}
+
+	return -ENOENT;
+}
diff --git a/drivers/infiniband/hw/mana/wq.c b/drivers/infiniband/hw/mana/wq.c
new file mode 100644
index 000000000000..a11d0ae35ff7
--- /dev/null
+++ b/drivers/infiniband/hw/mana/wq.c
@@ -0,0 +1,114 @@ 
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * 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(-EFAULT);
+	}
+
+	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,
+					   PAGE_SIZE);
+	if (err) {
+		ibdev_err(&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;
+}
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 3a0bc6e0b730..1ff6e0d07cfd 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -406,6 +406,9 @@  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;
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 3072e5d6b692..081aabf536dc 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -250,6 +250,7 @@  enum rdma_driver_id {
 	RDMA_DRIVER_QIB,
 	RDMA_DRIVER_EFA,
 	RDMA_DRIVER_SIW,
+	RDMA_DRIVER_MANA,
 };
 
 enum ib_uverbs_gid_type {
diff --git a/include/uapi/rdma/mana-abi.h b/include/uapi/rdma/mana-abi.h
new file mode 100644
index 000000000000..559c49b72e0d
--- /dev/null
+++ b/include/uapi/rdma/mana-abi.h
@@ -0,0 +1,66 @@ 
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * 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