RDMA/uverbs: Add a common way to create CQ with umem

Add ioctl command attributes and a common handling for the option to
create CQs with memory buffers passed from userspace. When required
attributes are supplied, create umem and provide it for driver's use.
The extension enables creation of CQs on top of preallocated CPU
virtual or device memory buffers, by supplying VA or dmabuf fd, in a
common way.
Drivers can support this flow by initializing a new create_cq_umem fp
field in their ops struct, with a function that can handle the new
parameter.

Signed-off-by: Michael Margolin <mrgolin@amazon.com>
Link: https://patch.msgid.link/20250708202308.24783-2-mrgolin@amazon.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

2 files changed, 82 insertions, 6 deletions

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 1ca6a9b7ba1a..f301cdce1728 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2728,6 +2728,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_ah);
 	SET_DEVICE_OP(dev_ops, create_counters);
 	SET_DEVICE_OP(dev_ops, create_cq);
+	SET_DEVICE_OP(dev_ops, create_cq_umem);
 	SET_DEVICE_OP(dev_ops, create_flow);
 	SET_DEVICE_OP(dev_ops, create_qp);
 	SET_DEVICE_OP(dev_ops, create_rwq_ind_table);
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index 432054f0a8a4..37cd37556510 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -64,15 +64,21 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	struct ib_ucq_object *obj = container_of(
 		uverbs_attr_get_uobject(attrs, UVERBS_ATTR_CREATE_CQ_HANDLE),
 		typeof(*obj), uevent.uobject);
+	struct ib_uverbs_completion_event_file *ev_file = NULL;
 	struct ib_device *ib_dev = attrs->context->device;
-	int ret;
-	u64 user_handle;
+	struct ib_umem_dmabuf *umem_dmabuf;
 	struct ib_cq_init_attr attr = {};
-	struct ib_cq                   *cq;
-	struct ib_uverbs_completion_event_file    *ev_file = NULL;
 	struct ib_uobject *ev_file_uobj;
+	struct ib_umem *umem = NULL;
+	u64 buffer_length;
+	u64 buffer_offset;
+	struct ib_cq *cq;
+	u64 user_handle;
+	u64 buffer_va;
+	int buffer_fd;
+	int ret;
 
-	if (!ib_dev->ops.create_cq || !ib_dev->ops.destroy_cq)
+	if ((!ib_dev->ops.create_cq && !ib_dev->ops.create_cq_umem) || !ib_dev->ops.destroy_cq)
 		return -EOPNOTSUPP;
 
 	ret = uverbs_copy_from(&attr.comp_vector, attrs,
@@ -112,9 +118,66 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	INIT_LIST_HEAD(&obj->comp_list);
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_VA)) {
+
+		ret = uverbs_copy_from(&buffer_va, attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_VA);
+		if (ret)
+			goto err_event_file;
+
+		ret = uverbs_copy_from(&buffer_length, attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_LENGTH);
+		if (ret)
+			goto err_event_file;
+
+		if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_FD) ||
+		    uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_OFFSET) ||
+		    !ib_dev->ops.create_cq_umem) {
+			ret = -EINVAL;
+			goto err_event_file;
+		}
+
+		umem = ib_umem_get(ib_dev, buffer_va, buffer_length, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(umem)) {
+			ret = PTR_ERR(umem);
+			goto err_event_file;
+		}
+	} else if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_FD)) {
+
+		ret = uverbs_get_raw_fd(&buffer_fd, attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_FD);
+		if (ret)
+			goto err_event_file;
+
+		ret = uverbs_copy_from(&buffer_offset, attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_OFFSET);
+		if (ret)
+			goto err_event_file;
+
+		ret = uverbs_copy_from(&buffer_length, attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_LENGTH);
+		if (ret)
+			goto err_event_file;
+
+		if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_VA) ||
+		    !ib_dev->ops.create_cq_umem) {
+			ret = -EINVAL;
+			goto err_event_file;
+		}
+
+		umem_dmabuf = ib_umem_dmabuf_get_pinned(ib_dev, buffer_offset, buffer_length,
+							buffer_fd, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(umem_dmabuf)) {
+			ret = PTR_ERR(umem_dmabuf);
+			goto err_event_file;
+		}
+		umem = &umem_dmabuf->umem;
+	} else if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_OFFSET) ||
+		   uverbs_attr_is_valid(attrs, UVERBS_ATTR_CREATE_CQ_BUFFER_LENGTH) ||
+		   !ib_dev->ops.create_cq) {
+		ret = -EINVAL;
+		goto err_event_file;
+	}
+
 	cq = rdma_zalloc_drv_obj(ib_dev, ib_cq);
 	if (!cq) {
 		ret = -ENOMEM;
+		ib_umem_release(umem);
 		goto err_event_file;
 	}
 
@@ -128,7 +191,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	rdma_restrack_set_name(&cq->res, NULL);
 
-	ret = ib_dev->ops.create_cq(cq, &attr, attrs);
+	ret = umem ? ib_dev->ops.create_cq_umem(cq, &attr, umem, attrs) :
+		ib_dev->ops.create_cq(cq, &attr, attrs);
 	if (ret)
 		goto err_free;
 
@@ -180,6 +244,17 @@ DECLARE_UVERBS_NAMED_METHOD(
 		       UVERBS_OBJECT_ASYNC_EVENT,
 		       UVERBS_ACCESS_READ,
 		       UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_CREATE_CQ_BUFFER_VA,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_CREATE_CQ_BUFFER_LENGTH,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_OPTIONAL),
+	UVERBS_ATTR_RAW_FD(UVERBS_ATTR_CREATE_CQ_BUFFER_FD,
+			   UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_CREATE_CQ_BUFFER_OFFSET,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_OPTIONAL),
 	UVERBS_ATTR_UHW());
 
 static int UVERBS_HANDLER(UVERBS_METHOD_CQ_DESTROY)(