From 6f6bfbc595fbae95f4c1ff80c87d089604e5e6a1 Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Mon, 27 May 2024 23:11:37 -0700
Subject: RDMA/bnxt_re: Expose the MSN table capability for user library

BNXT_RE_COMP_MASK_UCNTX_HW_RETX_ENABLED was introduced to share the HW
retransmit capability between driver and lib. The main difference in
implementation for HW Retransmit support is the usage of MSN table or
PSN table . When HW retrans is enabled, HW expects MSN table to be
allocated by driver/lib, else PSN table (for older adapters).

FW expose a new field which gives MSN capability. Drivers and libs can
depend on the new field instead of HW Retrasns capability. For
adapters which support HW_RETX feature, MSN table capability will be
set. For older adapters, this value will be 0(to maintain backward
compatibility with older FW).

Rename UAPI just to capture the correct name of the HW capability
that driver/library is interested in. No functional impact even if
older rdma-core is used.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1716876697-25970-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/uapi/rdma/bnxt_re-abi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index c0c34aca90ec..e61104f35d73 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -55,7 +55,7 @@ enum {
 	BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
 	BNXT_RE_UCNTX_CMASK_DBR_PACING_ENABLED = 0x08ULL,
 	BNXT_RE_UCNTX_CMASK_POW2_DISABLED = 0x10ULL,
-	BNXT_RE_COMP_MASK_UCNTX_HW_RETX_ENABLED = 0x40,
+	BNXT_RE_UCNTX_CMASK_MSN_TABLE_ENABLED = 0x40,
 };
 
 enum bnxt_re_wqe_mode {
-- 
cgit v1.2.3


From fdefb918496235a11d6c5477c34c81aab2c1343b Mon Sep 17 00:00:00 2001
From: Konstantin Taranov <kotaranov@microsoft.com>
Date: Wed, 22 May 2024 01:24:01 -0700
Subject: RDMA/mana_ib: Implement uapi to create and destroy RC QP

Implement user requests to create and destroy an RC QP.
As the user does not have an FMR queue, it is skipped and NO_FMR flag
is used.

Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Link: https://lore.kernel.org/r/1716366242-558-3-git-send-email-kotaranov@linux.microsoft.com
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mana/mana_ib.h |  4 ++
 drivers/infiniband/hw/mana/qp.c      | 94 +++++++++++++++++++++++++++++++++++-
 include/uapi/rdma/mana-abi.h         |  9 ++++
 3 files changed, 105 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index a3e229c83c5c..5cccbe397b6d 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -248,6 +248,10 @@ struct mana_rnic_destroy_cq_resp {
 	struct gdma_resp_hdr hdr;
 }; /* HW Data */
 
+enum mana_rnic_create_rc_flags {
+	MANA_RC_FLAG_NO_FMR = 2,
+};
+
 struct mana_rnic_create_qp_req {
 	struct gdma_req_hdr hdr;
 	mana_handle_t adapter;
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index ba13c5abf8ef..7dbeba41b978 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -398,6 +398,78 @@ err_free_vport:
 	return err;
 }
 
+static int mana_ib_create_rc_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
+				struct ib_qp_init_attr *attr, struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev = container_of(ibpd->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+	struct mana_ib_create_rc_qp_resp resp = {};
+	struct mana_ib_ucontext *mana_ucontext;
+	struct mana_ib_create_rc_qp ucmd = {};
+	int i, err, j;
+	u64 flags = 0;
+	u32 doorbell;
+
+	if (!udata || udata->inlen < sizeof(ucmd))
+		return -EINVAL;
+
+	mana_ucontext = rdma_udata_to_drv_context(udata, struct mana_ib_ucontext, ibucontext);
+	doorbell = mana_ucontext->doorbell;
+	flags = MANA_RC_FLAG_NO_FMR;
+	err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
+	if (err) {
+		ibdev_dbg(&mdev->ib_dev, "Failed to copy from udata, %d\n", err);
+		return err;
+	}
+
+	for (i = 0, j = 0; i < MANA_RC_QUEUE_TYPE_MAX; ++i) {
+		/* skip FMR for user-level RC QPs */
+		if (i == MANA_RC_SEND_QUEUE_FMR) {
+			qp->rc_qp.queues[i].id = INVALID_QUEUE_ID;
+			qp->rc_qp.queues[i].gdma_region = GDMA_INVALID_DMA_REGION;
+			continue;
+		}
+		err = mana_ib_create_queue(mdev, ucmd.queue_buf[j], ucmd.queue_size[j],
+					   &qp->rc_qp.queues[i]);
+		if (err) {
+			ibdev_err(&mdev->ib_dev, "Failed to create queue %d, err %d\n", i, err);
+			goto destroy_queues;
+		}
+		j++;
+	}
+
+	err = mana_ib_gd_create_rc_qp(mdev, qp, attr, doorbell, flags);
+	if (err) {
+		ibdev_err(&mdev->ib_dev, "Failed to create rc qp  %d\n", err);
+		goto destroy_queues;
+	}
+	qp->ibqp.qp_num = qp->rc_qp.queues[MANA_RC_RECV_QUEUE_RESPONDER].id;
+	qp->port = attr->port_num;
+
+	if (udata) {
+		for (i = 0, j = 0; i < MANA_RC_QUEUE_TYPE_MAX; ++i) {
+			if (i == MANA_RC_SEND_QUEUE_FMR)
+				continue;
+			resp.queue_id[j] = qp->rc_qp.queues[i].id;
+			j++;
+		}
+		err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
+		if (err) {
+			ibdev_dbg(&mdev->ib_dev, "Failed to copy to udata, %d\n", err);
+			goto destroy_qp;
+		}
+	}
+
+	return 0;
+
+destroy_qp:
+	mana_ib_gd_destroy_rc_qp(mdev, qp);
+destroy_queues:
+	while (i-- > 0)
+		mana_ib_destroy_queue(mdev, &qp->rc_qp.queues[i]);
+	return err;
+}
+
 int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
 		      struct ib_udata *udata)
 {
@@ -409,8 +481,9 @@ int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
 						     udata);
 
 		return mana_ib_create_qp_raw(ibqp, ibqp->pd, attr, udata);
+	case IB_QPT_RC:
+		return mana_ib_create_rc_qp(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);
 	}
@@ -473,6 +546,22 @@ static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata)
 	return 0;
 }
 
+static int mana_ib_destroy_rc_qp(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);
+	int i;
+
+	/* Ignore return code as there is not much we can do about it.
+	 * The error message is printed inside.
+	 */
+	mana_ib_gd_destroy_rc_qp(mdev, qp);
+	for (i = 0; i < MANA_RC_QUEUE_TYPE_MAX; ++i)
+		mana_ib_destroy_queue(mdev, &qp->rc_qp.queues[i]);
+
+	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);
@@ -484,7 +573,8 @@ int mana_ib_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 						      udata);
 
 		return mana_ib_destroy_qp_raw(qp, udata);
-
+	case IB_QPT_RC:
+		return mana_ib_destroy_rc_qp(qp, udata);
 	default:
 		ibdev_dbg(ibqp->device, "Unexpected QP type %u\n",
 			  ibqp->qp_type);
diff --git a/include/uapi/rdma/mana-abi.h b/include/uapi/rdma/mana-abi.h
index 2c41cc315218..45c2df619f07 100644
--- a/include/uapi/rdma/mana-abi.h
+++ b/include/uapi/rdma/mana-abi.h
@@ -45,6 +45,15 @@ struct mana_ib_create_qp_resp {
 	__u32 reserved;
 };
 
+struct mana_ib_create_rc_qp {
+	__aligned_u64 queue_buf[4];
+	__u32 queue_size[4];
+};
+
+struct mana_ib_create_rc_qp_resp {
+	__u32 queue_id[4];
+};
+
 struct mana_ib_create_wq {
 	__aligned_u64 wq_buf_addr;
 	__u32 wq_buf_size;
-- 
cgit v1.2.3


From dd6d7f8574d7f8b6a0bf1aeef0b285d2706b8c2a Mon Sep 17 00:00:00 2001
From: Akiva Goldberger <agoldberger@nvidia.com>
Date: Thu, 27 Jun 2024 21:23:49 +0300
Subject: RDMA: Pass entire uverbs attr bundle to create cq function

Changes the create_cq verb signature by sending the entire uverbs attr
bundle as a parameter. This allows drivers to send driver specific attrs
through ioctl for the create_cq verb and access them in their driver
specific code.

Also adds a new enum value for driver specific ioctl attributes for
methods already supporting UHW.

Link: https://lore.kernel.org/r/ed147343987c0d43fd391c1b2f85e2f425747387.1719512393.git.leon@kernel.org
Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_cmd.c            | 2 +-
 drivers/infiniband/core/uverbs_std_types_cq.c   | 2 +-
 drivers/infiniband/hw/bnxt_re/ib_verbs.c        | 3 ++-
 drivers/infiniband/hw/bnxt_re/ib_verbs.h        | 2 +-
 drivers/infiniband/hw/cxgb4/cq.c                | 3 ++-
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h          | 2 +-
 drivers/infiniband/hw/efa/efa.h                 | 2 +-
 drivers/infiniband/hw/efa/efa_verbs.c           | 3 ++-
 drivers/infiniband/hw/erdma/erdma_verbs.c       | 3 ++-
 drivers/infiniband/hw/erdma/erdma_verbs.h       | 2 +-
 drivers/infiniband/hw/hns/hns_roce_cq.c         | 3 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h     | 2 +-
 drivers/infiniband/hw/irdma/verbs.c             | 5 +++--
 drivers/infiniband/hw/mana/cq.c                 | 3 ++-
 drivers/infiniband/hw/mana/mana_ib.h            | 2 +-
 drivers/infiniband/hw/mlx4/cq.c                 | 3 ++-
 drivers/infiniband/hw/mlx4/mlx4_ib.h            | 2 +-
 drivers/infiniband/hw/mlx5/cq.c                 | 3 ++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h            | 2 +-
 drivers/infiniband/hw/mthca/mthca_provider.c    | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c     | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h     | 2 +-
 drivers/infiniband/hw/qedr/verbs.c              | 3 ++-
 drivers/infiniband/hw/qedr/verbs.h              | 2 +-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c    | 2 +-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.h    | 2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c    | 5 +++--
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 2 +-
 drivers/infiniband/sw/rdmavt/cq.c               | 6 ++++--
 drivers/infiniband/sw/rdmavt/cq.h               | 2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c           | 3 ++-
 drivers/infiniband/sw/siw/siw_verbs.c           | 5 +++--
 drivers/infiniband/sw/siw/siw_verbs.h           | 2 +-
 include/rdma/ib_verbs.h                         | 2 +-
 include/uapi/rdma/ib_user_ioctl_cmds.h          | 7 +++----
 35 files changed, 58 insertions(+), 42 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 3d3ee3eca983..1b3ea71f2c33 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1051,7 +1051,7 @@ static int create_cq(struct uverbs_attr_bundle *attrs,
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	rdma_restrack_set_name(&cq->res, NULL);
 
-	ret = ib_dev->ops.create_cq(cq, &attr, &attrs->driver_udata);
+	ret = ib_dev->ops.create_cq(cq, &attr, attrs);
 	if (ret)
 		goto err_free;
 	rdma_restrack_add(&cq->res);
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index 370ad7c83f88..432054f0a8a4 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -128,7 +128,7 @@ 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->driver_udata);
+	ret = ib_dev->ops.create_cq(cq, &attr, attrs);
 	if (ret)
 		goto err_free;
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index d261b09025ca..e453ca701e87 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -2948,10 +2948,11 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 }
 
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata)
+		      struct uverbs_attr_bundle *attrs)
 {
 	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibcq->device, ibdev);
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct bnxt_re_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index b267d6d5975f..e98cb1717338 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -221,7 +221,7 @@ int bnxt_re_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr,
 int bnxt_re_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
 		      const struct ib_recv_wr **bad_recv_wr);
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata);
+		      struct uverbs_attr_bundle *attrs);
 int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata);
 int bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int bnxt_re_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc);
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 7e2835dcbc1c..5111421f9473 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -995,8 +995,9 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 }
 
 int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		   struct ib_udata *udata)
+		   struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	int vector = attr->comp_vector;
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index fb8a0c248866..f838bb6718af 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -978,7 +978,7 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
 int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
 void c4iw_cq_rem_ref(struct c4iw_cq *chp);
 int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		   struct ib_udata *udata);
+		   struct uverbs_attr_bundle *attrs);
 int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int c4iw_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *attr,
 		    enum ib_srq_attr_mask srq_attr_mask,
diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 926f9ff1f60f..e580e087e9da 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -161,7 +161,7 @@ int efa_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 		  struct ib_udata *udata);
 int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata);
+		  struct uverbs_attr_bundle *attrs);
 struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 			 u64 virt_addr, int access_flags,
 			 struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index cd1f735d08a7..b1e0a1b7c59d 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1080,8 +1080,9 @@ static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq,
 }
 
 int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata)
+		  struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct efa_ucontext *ucontext = rdma_udata_to_drv_context(
 		udata, struct efa_ucontext, ibucontext);
 	struct efa_com_create_cq_params params = {};
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 40c9b6e46b82..d7e1cbf9f5c2 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -1628,8 +1628,9 @@ err_out:
 }
 
 int erdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		    struct ib_udata *udata)
+		    struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct erdma_cq *cq = to_ecq(ibcq);
 	struct erdma_dev *dev = to_edev(ibcq->device);
 	unsigned int depth = attr->cqe;
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h
index 4f02ba06b210..6afdc02f5869 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.h
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.h
@@ -329,7 +329,7 @@ int erdma_query_device(struct ib_device *dev, struct ib_device_attr *attr,
 int erdma_get_port_immutable(struct ib_device *dev, u32 port,
 			     struct ib_port_immutable *ib_port_immutable);
 int erdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		    struct ib_udata *data);
+		    struct uverbs_attr_bundle *attrs);
 int erdma_query_port(struct ib_device *dev, u32 port,
 		     struct ib_port_attr *attr);
 int erdma_query_gid(struct ib_device *dev, u32 port, int idx,
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 56dc3908da2f..4ec66611a143 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -353,9 +353,10 @@ static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
 }
 
 int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
-		       struct ib_udata *udata)
+		       struct uverbs_attr_bundle *attrs)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct hns_roce_ib_create_cq_resp resp = {};
 	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index ff0b3f68ee3a..ef50cd03f489 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -1267,7 +1267,7 @@ __be32 send_ieth(const struct ib_send_wr *wr);
 int to_hr_qp_type(int qp_type);
 
 int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
-		       struct ib_udata *udata);
+		       struct uverbs_attr_bundle *attrs);
 
 int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
 int hns_roce_db_map_user(struct hns_roce_ucontext *context, unsigned long virt,
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 12704efb7b19..fc0ce35da14e 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -2035,14 +2035,15 @@ static inline int cq_validate_flags(u32 flags, u8 hw_rev)
  * irdma_create_cq - create cq
  * @ibcq: CQ allocated
  * @attr: attributes for cq
- * @udata: user data
+ * @attrs: uverbs attribute bundle
  */
 static int irdma_create_cq(struct ib_cq *ibcq,
 			   const struct ib_cq_init_attr *attr,
-			   struct ib_udata *udata)
+			   struct uverbs_attr_bundle *attrs)
 {
 #define IRDMA_CREATE_CQ_MIN_REQ_LEN offsetofend(struct irdma_create_cq_req, user_cq_buf)
 #define IRDMA_CREATE_CQ_MIN_RESP_LEN offsetofend(struct irdma_create_cq_resp, cq_size)
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	struct irdma_device *iwdev = to_iwdev(ibdev);
 	struct irdma_pci_f *rf = iwdev->rf;
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index c6a3fd57a196..f04a679d2871 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -6,8 +6,9 @@
 #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 uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
 	struct mana_ib_create_cq_resp resp = {};
 	struct mana_ib_ucontext *mana_ucontext;
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 977da9569701..b53a5b4de908 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -429,7 +429,7 @@ 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);
+		      struct uverbs_attr_bundle *attrs);
 
 int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 4cd738aae53c..aa9ea6ba26e5 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -172,8 +172,9 @@ err_buf:
 
 #define CQ_CREATE_FLAGS_SUPPORTED IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION
 int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata)
+		      struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	int vector = attr->comp_vector;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 41ca1114a995..b52bceff7d97 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -767,7 +767,7 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
 int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata);
+		      struct uverbs_attr_bundle *attrs);
 int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 9773d2a3d97f..eebfd6fa4d9b 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -942,8 +942,9 @@ static void notify_soft_wc_handler(struct work_struct *work)
 }
 
 int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata)
+		      struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	int vector = attr->comp_vector;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 74a20df8b292..20c9dbbf17bb 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1328,7 +1328,7 @@ int mlx5_ib_read_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
 int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer,
 			 size_t buflen, size_t *bc);
 int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		      struct ib_udata *udata);
+		      struct uverbs_attr_bundle *attrs);
 int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index e1325f2927d6..6a1e2e79ddc3 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -574,8 +574,9 @@ static int mthca_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
 
 static int mthca_create_cq(struct ib_cq *ibcq,
 			   const struct ib_cq_init_attr *attr,
-			   struct ib_udata *udata)
+			   struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	struct mthca_create_cq ucmd;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index c849fdbd4c99..979de8f8df14 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -963,8 +963,9 @@ err:
 }
 
 int ocrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		     struct ib_udata *udata)
+		     struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	struct ocrdma_cq *cq = get_ocrdma_cq(ibcq);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index f860b7fcef33..0644346d8d98 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -70,7 +70,7 @@ int ocrdma_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int ocrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 
 int ocrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		     struct ib_udata *udata);
+		     struct uverbs_attr_bundle *attrs);
 int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
 int ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index f118ce0a9a61..568a5b18803f 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -900,8 +900,9 @@ int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 }
 
 int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		   struct ib_udata *udata)
+		   struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	struct qedr_ucontext *ctx = rdma_udata_to_drv_context(
 		udata, struct qedr_ucontext, ibucontext);
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index 081753df79ef..5731458abb06 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -52,7 +52,7 @@ int qedr_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int qedr_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata);
 int qedr_dealloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata);
 int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		   struct ib_udata *udata);
+		   struct uverbs_attr_bundle *attrs);
 int qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int qedr_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *attrs,
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 6289238cc5af..217af34e82b3 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -577,7 +577,7 @@ out_unlock:
 }
 
 int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		       struct ib_udata *udata)
+		       struct uverbs_attr_bundle *attrs)
 {
 	if (attr->flags)
 		return -EOPNOTSUPP;
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index 6ca9ee0dddbe..53f53f2d53be 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -56,7 +56,7 @@ int usnic_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata);
 int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				int attr_mask, struct ib_udata *udata);
 int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		       struct ib_udata *udata);
+		       struct uverbs_attr_bundle *attrs);
 int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 				u64 virt_addr, int access_flags,
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index 6aa40bd2fd52..b3df6eb9b8ef 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -94,13 +94,14 @@ int pvrdma_req_notify_cq(struct ib_cq *ibcq,
  * pvrdma_create_cq - create completion queue
  * @ibcq: Allocated CQ
  * @attr: completion queue attributes
- * @udata: user data
+ * @attrs: bundle
  *
  * @return: 0 on success
  */
 int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		     struct ib_udata *udata)
+		     struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	struct pvrdma_dev *dev = to_vdev(ibdev);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index 78807b23d831..4b9edc03d73d 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -375,7 +375,7 @@ struct ib_mr *pvrdma_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 int pvrdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		     int sg_nents, unsigned int *sg_offset);
 int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		     struct ib_udata *udata);
+		     struct uverbs_attr_bundle *attrs);
 int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int pvrdma_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 82c3f5932249..0ca2743f1075 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -5,6 +5,7 @@
 
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <rdma/uverbs_ioctl.h>
 #include "cq.h"
 #include "vt.h"
 #include "trace.h"
@@ -149,15 +150,16 @@ static void send_complete(struct work_struct *work)
  * rvt_create_cq - create a completion queue
  * @ibcq: Allocated CQ
  * @attr: creation attributes
- * @udata: user data for libibverbs.so
+ * @attrs: uverbs bundle
  *
  * Called by ib_create_cq() in the generic verbs code.
  *
  * Return: 0 on success
  */
 int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata)
+		  struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *ibdev = ibcq->device;
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
 	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
diff --git a/drivers/infiniband/sw/rdmavt/cq.h b/drivers/infiniband/sw/rdmavt/cq.h
index d49b6d1a26cb..4028702a7b2f 100644
--- a/drivers/infiniband/sw/rdmavt/cq.h
+++ b/drivers/infiniband/sw/rdmavt/cq.h
@@ -10,7 +10,7 @@
 #include <rdma/rdmavt_cq.h>
 
 int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata);
+		  struct uverbs_attr_bundle *attrs);
 int rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags);
 int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index c7d4d8ab5a09..82bb7f33290c 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1053,8 +1053,9 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 /* cq */
 static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
-			 struct ib_udata *udata)
+			 struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct ib_device *dev = ibcq->device;
 	struct rxe_dev *rxe = to_rdev(dev);
 	struct rxe_cq *cq = to_rcq(ibcq);
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index ecf0444666b4..986666c19378 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -1124,12 +1124,13 @@ int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata)
  *
  * @base_cq: CQ as allocated by RDMA midlayer
  * @attr: Initial CQ attributes
- * @udata: relates to user context
+ * @attrs: uverbs bundle
  */
 
 int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata)
+		  struct uverbs_attr_bundle *attrs)
 {
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct siw_device *sdev = to_siw_dev(base_cq->device);
 	struct siw_cq *cq = to_siw_cq(base_cq);
 	int rv, size = attr->cqe;
diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h
index 4b57a4fb7237..1f1a305540af 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.h
+++ b/drivers/infiniband/sw/siw/siw_verbs.h
@@ -43,7 +43,7 @@ int siw_get_port_immutable(struct ib_device *base_dev, u32 port,
 int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr,
 		     struct ib_udata *udata);
 int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr,
-		  struct ib_udata *udata);
+		  struct uverbs_attr_bundle *attrs);
 int siw_query_port(struct ib_device *base_dev, u32 port,
 		   struct ib_port_attr *attr);
 int siw_query_gid(struct ib_device *base_dev, u32 port, int idx,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5a193008f99c..825043512b2d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2465,7 +2465,7 @@ struct ib_device_ops {
 			int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
 	int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata);
 	int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
-			 struct ib_udata *udata);
+			 struct uverbs_attr_bundle *attrs);
 	int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 	int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
 	int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index dafc7ebe545b..ec719053aab9 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -37,9 +37,6 @@
 #define UVERBS_ID_NS_MASK 0xF000
 #define UVERBS_ID_NS_SHIFT 12
 
-#define UVERBS_UDATA_DRIVER_DATA_NS	1
-#define UVERBS_UDATA_DRIVER_DATA_FLAG	(1UL << UVERBS_ID_NS_SHIFT)
-
 enum uverbs_default_objects {
 	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
 	UVERBS_OBJECT_PD,
@@ -61,8 +58,10 @@ enum uverbs_default_objects {
 };
 
 enum {
-	UVERBS_ATTR_UHW_IN = UVERBS_UDATA_DRIVER_DATA_FLAG,
+	UVERBS_ID_DRIVER_NS = 1UL << UVERBS_ID_NS_SHIFT,
+	UVERBS_ATTR_UHW_IN = UVERBS_ID_DRIVER_NS,
 	UVERBS_ATTR_UHW_OUT,
+	UVERBS_ID_DRIVER_NS_WITH_UHW,
 };
 
 enum uverbs_methods_device {
-- 
cgit v1.2.3


From 589b844f1bf04850d9fabcaa2e943325dc6768b4 Mon Sep 17 00:00:00 2001
From: Akiva Goldberger <agoldberger@nvidia.com>
Date: Thu, 27 Jun 2024 21:23:50 +0300
Subject: RDMA/mlx5: Send UAR page index as ioctl attribute

Add UAR page index as a driver ioctl attribute to increase the number of
supported indices, previously limited to 16 bits by mlx5_ib_create_cq
struct.

Link: https://lore.kernel.org/r/0e18b34d7ec3b1ae02d694b0d545aed7413c0ef7.1719512393.git.leon@kernel.org
Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/cq.c          | 28 +++++++++++++++++++++++++---
 drivers/infiniband/hw/mlx5/main.c        |  1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h     |  1 +
 include/uapi/rdma/mlx5_user_ioctl_cmds.h |  4 ++++
 4 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index eebfd6fa4d9b..4c54dc578069 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -38,6 +38,9 @@
 #include "srq.h"
 #include "qp.h"
 
+#define UVERBS_MODULE_NAME mlx5_ib
+#include <rdma/uverbs_named_ioctl.h>
+
 static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe)
 {
 	struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;
@@ -714,7 +717,8 @@ static int mini_cqe_res_format_to_hw(struct mlx5_ib_dev *dev, u8 format)
 
 static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  struct mlx5_ib_cq *cq, int entries, u32 **cqb,
-			  int *cqe_size, int *index, int *inlen)
+			  int *cqe_size, int *index, int *inlen,
+			  struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_ib_create_cq ucmd = {};
 	unsigned long page_size;
@@ -788,7 +792,11 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 		 order_base_2(page_size) - MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET(cqc, cqc, page_offset, page_offset_quantized);
 
-	if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_UAR_PAGE_INDEX) {
+	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_CREATE_CQ_UAR_INDEX)) {
+		err = uverbs_copy_from(index, attrs, MLX5_IB_ATTR_CREATE_CQ_UAR_INDEX);
+		if (err)
+			goto err_cqb;
+	} else if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_UAR_PAGE_INDEX) {
 		*index = ucmd.uar_page_index;
 	} else if (context->bfregi.lib_uar_dyn) {
 		err = -EINVAL;
@@ -981,7 +989,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 	if (udata) {
 		err = create_cq_user(dev, udata, cq, entries, &cqb, &cqe_size,
-				     &index, &inlen);
+				     &index, &inlen, attrs);
 		if (err)
 			return err;
 	} else {
@@ -1443,3 +1451,17 @@ int mlx5_ib_generate_wc(struct ib_cq *ibcq, struct ib_wc *wc)
 
 	return 0;
 }
+
+ADD_UVERBS_ATTRIBUTES_SIMPLE(
+	mlx5_ib_cq_create,
+	UVERBS_OBJECT_CQ,
+	UVERBS_METHOD_CQ_CREATE,
+	UVERBS_ATTR_PTR_IN(
+		MLX5_IB_ATTR_CREATE_CQ_UAR_INDEX,
+		UVERBS_ATTR_TYPE(u32),
+		UA_OPTIONAL));
+
+const struct uapi_definition mlx5_ib_create_cq_defs[] = {
+	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_CQ, &mlx5_ib_cq_create),
+	{},
+};
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index cee167cf310e..4adcbbafb777 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3750,6 +3750,7 @@ static const struct uapi_definition mlx5_ib_defs[] = {
 	UAPI_DEF_CHAIN(mlx5_ib_qos_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_std_types_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_dm_defs),
+	UAPI_DEF_CHAIN(mlx5_ib_create_cq_defs),
 
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_DEVICE, &mlx5_ib_query_context),
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_VAR,
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 20c9dbbf17bb..8f4618dee869 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1528,6 +1528,7 @@ extern const struct uapi_definition mlx5_ib_devx_defs[];
 extern const struct uapi_definition mlx5_ib_flow_defs[];
 extern const struct uapi_definition mlx5_ib_qos_defs[];
 extern const struct uapi_definition mlx5_ib_std_types_defs[];
+extern const struct uapi_definition mlx5_ib_create_cq_defs[];
 
 static inline int is_qp1(enum ib_qp_type qp_type)
 {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 595edad03dfe..5b74d6534899 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -270,6 +270,10 @@ enum mlx5_ib_device_query_context_attrs {
 	MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT),
 };
 
+enum mlx5_ib_create_cq_attrs {
+	MLX5_IB_ATTR_CREATE_CQ_UAR_INDEX = UVERBS_ID_DRIVER_NS_WITH_UHW,
+};
+
 #define MLX5_IB_DW_MATCH_PARAM 0xA0
 
 struct mlx5_ib_match_params {
-- 
cgit v1.2.3


From bca51197620a257e2954be99b16f05115c3b2630 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Sun, 16 Jun 2024 19:08:36 +0300
Subject: RDMA/core: Support IB sub device with type "SMI"

This patch adds 2 APIs, as well as driver operations to support adding
and deleting an IB sub device, which provides part of functionalities
of it's parent.

A sub device has a type; for a sub device with type "SMI", it provides
the smi capability through umad for its parent, meaning uverb is not
supported.

A sub device cannot live without a parent. So when a parent is
released, all it's sub devices are released as well.

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/44253f7508b21eb2caefea3980c2bc072869116c.1718553901.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/device.c      | 69 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/uverbs_main.c |  3 +-
 include/rdma/ib_verbs.h               | 43 ++++++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h      |  5 +++
 4 files changed, 119 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index e0cff28bb0ef..7b418c717f29 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -503,6 +503,7 @@ static void ib_device_release(struct device *device)
 			  rcu_head);
 	}
 
+	mutex_destroy(&dev->subdev_lock);
 	mutex_destroy(&dev->unregistration_lock);
 	mutex_destroy(&dev->compat_devs_mutex);
 
@@ -641,6 +642,11 @@ struct ib_device *_ib_alloc_device(size_t size)
 		BIT_ULL(IB_USER_VERBS_CMD_REG_MR) |
 		BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) |
 		BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ);
+
+	mutex_init(&device->subdev_lock);
+	INIT_LIST_HEAD(&device->subdev_list_head);
+	INIT_LIST_HEAD(&device->subdev_list);
+
 	return device;
 }
 EXPORT_SYMBOL(_ib_alloc_device);
@@ -1461,6 +1467,18 @@ EXPORT_SYMBOL(ib_register_device);
 /* Callers must hold a get on the device. */
 static void __ib_unregister_device(struct ib_device *ib_dev)
 {
+	struct ib_device *sub, *tmp;
+
+	mutex_lock(&ib_dev->subdev_lock);
+	list_for_each_entry_safe_reverse(sub, tmp,
+					 &ib_dev->subdev_list_head,
+					 subdev_list) {
+		list_del(&sub->subdev_list);
+		ib_dev->ops.del_sub_dev(sub);
+		ib_device_put(ib_dev);
+	}
+	mutex_unlock(&ib_dev->subdev_lock);
+
 	/*
 	 * We have a registration lock so that all the calls to unregister are
 	 * fully fenced, once any unregister returns the device is truely
@@ -2597,6 +2615,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 		ops->uverbs_no_driver_id_binding;
 
 	SET_DEVICE_OP(dev_ops, add_gid);
+	SET_DEVICE_OP(dev_ops, add_sub_dev);
 	SET_DEVICE_OP(dev_ops, advise_mr);
 	SET_DEVICE_OP(dev_ops, alloc_dm);
 	SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
@@ -2631,6 +2650,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, dealloc_ucontext);
 	SET_DEVICE_OP(dev_ops, dealloc_xrcd);
 	SET_DEVICE_OP(dev_ops, del_gid);
+	SET_DEVICE_OP(dev_ops, del_sub_dev);
 	SET_DEVICE_OP(dev_ops, dereg_mr);
 	SET_DEVICE_OP(dev_ops, destroy_ah);
 	SET_DEVICE_OP(dev_ops, destroy_counters);
@@ -2727,6 +2747,55 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 }
 EXPORT_SYMBOL(ib_set_device_ops);
 
+int ib_add_sub_device(struct ib_device *parent,
+		      enum rdma_nl_dev_type type,
+		      const char *name)
+{
+	struct ib_device *sub;
+	int ret = 0;
+
+	if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev)
+		return -EOPNOTSUPP;
+
+	if (!ib_device_try_get(parent))
+		return -EINVAL;
+
+	sub = parent->ops.add_sub_dev(parent, type, name);
+	if (IS_ERR(sub)) {
+		ib_device_put(parent);
+		return PTR_ERR(sub);
+	}
+
+	sub->type = type;
+	sub->parent = parent;
+
+	mutex_lock(&parent->subdev_lock);
+	list_add_tail(&parent->subdev_list_head, &sub->subdev_list);
+	mutex_unlock(&parent->subdev_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(ib_add_sub_device);
+
+int ib_del_sub_device_and_put(struct ib_device *sub)
+{
+	struct ib_device *parent = sub->parent;
+
+	if (!parent)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&parent->subdev_lock);
+	list_del(&sub->subdev_list);
+	mutex_unlock(&parent->subdev_lock);
+
+	ib_device_put(sub);
+	parent->ops.del_sub_dev(sub);
+	ib_device_put(parent);
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_del_sub_device_and_put);
+
 #ifdef CONFIG_INFINIBAND_VIRT_DMA
 int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents)
 {
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 495d5a5d0373..bc099287de9a 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -1114,7 +1114,8 @@ static int ib_uverbs_add_one(struct ib_device *device)
 	struct ib_uverbs_device *uverbs_dev;
 	int ret;
 
-	if (!device->ops.alloc_ucontext)
+	if (!device->ops.alloc_ucontext ||
+	    device->type == RDMA_DEVICE_TYPE_SMI)
 		return -EOPNOTSUPP;
 
 	uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 825043512b2d..d4128958908f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2663,6 +2663,18 @@ struct ib_device_ops {
 	 */
 	int (*get_numa_node)(struct ib_device *dev);
 
+	/**
+	 * add_sub_dev - Add a sub IB device
+	 */
+	struct ib_device *(*add_sub_dev)(struct ib_device *parent,
+					 enum rdma_nl_dev_type type,
+					 const char *name);
+
+	/**
+	 * del_sub_dev - Delete a sub IB device
+	 */
+	void (*del_sub_dev)(struct ib_device *sub_dev);
+
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_counters);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
@@ -2773,6 +2785,15 @@ struct ib_device {
 	char iw_ifname[IFNAMSIZ];
 	u32 iw_driver_flags;
 	u32 lag_flags;
+
+	/* A parent device has a list of sub-devices */
+	struct mutex subdev_lock;
+	struct list_head subdev_list_head;
+
+	/* A sub device has a type and a parent */
+	enum rdma_nl_dev_type type;
+	struct ib_device *parent;
+	struct list_head subdev_list;
 };
 
 static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
@@ -4822,4 +4843,26 @@ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
 
 const struct ib_port_immutable*
 ib_port_immutable_read(struct ib_device *dev, unsigned int port);
+
+/** ib_add_sub_device - Add a sub IB device on an existing one
+ *
+ * @parent: The IB device that needs to add a sub device
+ * @type: The type of the new sub device
+ * @name: The name of the new sub device
+ *
+ *
+ * Return 0 on success, an error code otherwise
+ */
+int ib_add_sub_device(struct ib_device *parent,
+		      enum rdma_nl_dev_type type,
+		      const char *name);
+
+
+/** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get'
+ *
+ * @sub: The sub device that is going to be deleted
+ *
+ * Return 0 on success, an error code otherwise
+ */
+int ib_del_sub_device_and_put(struct ib_device *sub);
 #endif /* IB_VERBS_H */
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index a214fc259f28..d15ee16be722 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -602,4 +602,9 @@ enum rdma_nl_counter_mask {
 	RDMA_COUNTER_MASK_QP_TYPE = 1,
 	RDMA_COUNTER_MASK_PID = 1 << 1,
 };
+
+/* Supported rdma device types. */
+enum rdma_nl_dev_type {
+	RDMA_DEVICE_TYPE_SMI = 1,
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3


From 060c642b2ab8b40b39f9db99c1d14c7d19ba507f Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Sun, 16 Jun 2024 19:08:40 +0300
Subject: RDMA/nldev: Add support to add/delete a sub IB device through netlink

Add new netlink commands and attributes to support adding and deleting
a sub IB device with admin privilege.

Examples:
$ rdma dev add smi1 type SMI parent ibp8s0f1
$ rdma dev del smi1

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/77cbf1b36359642be8a8d8c5c2f4e585b544282f.1718553901.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/nldev.c  | 59 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h |  6 ++++
 2 files changed, 65 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index bc79ee630d8d..b5f87e7a1cfd 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -167,6 +167,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC] = { .type = NLA_U8 },
 	[RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE] = { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DRIVER_DETAILS]	= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_DEV_TYPE]		= { .type = NLA_U8 },
 };
 
 static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -2548,6 +2549,56 @@ err:
 	return ret;
 }
 
+static int nldev_newdev(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	enum rdma_nl_dev_type type;
+	struct ib_device *parent;
+	char name[IFNAMSIZ] = {};
+	u32 parentid;
+	int ret;
+
+	ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+		!tb[RDMA_NLDEV_ATTR_DEV_NAME] || !tb[RDMA_NLDEV_ATTR_DEV_TYPE])
+		return -EINVAL;
+
+	nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], sizeof(name));
+	type = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_TYPE]);
+	parentid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	parent = ib_device_get_by_index(sock_net(skb->sk), parentid);
+	if (!parent)
+		return -EINVAL;
+
+	ret = ib_add_sub_device(parent, type, name);
+	ib_device_put(parent);
+
+	return ret;
+}
+
+static int nldev_deldev(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	u32 devid;
+	int ret;
+
+	ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	devid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = ib_device_get_by_index(sock_net(skb->sk), devid);
+	if (!device)
+		return -EINVAL;
+
+	return ib_del_sub_device_and_put(device);
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
@@ -2646,6 +2697,14 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_STAT_GET_STATUS] = {
 		.doit = nldev_stat_get_counter_status_doit,
 	},
+	[RDMA_NLDEV_CMD_NEWDEV] = {
+		.doit = nldev_newdev,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
+	[RDMA_NLDEV_CMD_DELDEV] = {
+		.doit = nldev_deldev,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
 void __init nldev_init(void)
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index d15ee16be722..bd52fb325e22 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -301,6 +301,10 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_SRQ_GET_RAW,
 
+	RDMA_NLDEV_CMD_NEWDEV,
+
+	RDMA_NLDEV_CMD_DELDEV,
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -564,6 +568,8 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_RES_SUBTYPE,		/* string */
 
+	RDMA_NLDEV_ATTR_DEV_TYPE,		/* u8 */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3


From 294424839b5ec2ecd17f4c8409796846b2b8dd31 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Sun, 16 Jun 2024 19:08:41 +0300
Subject: RDMA/nldev: Add support to dump device type and parent device if
 exists

If a device has a specific type or a parent device, dump them as well.

Example:
$ rdma dev show smi1
3: smi1: node_type ca fw 20.38.1002 node_guid 9803:9b03:009f:d5ef sys_image_guid 9803:9b03:009f:d5ee type smi parent ibp8s0f1

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/4c022e3e34b5de1254a3b367d502a362cdd0c53a.1718553901.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/nldev.c  | 10 ++++++++++
 include/uapi/rdma/rdma_netlink.h |  2 ++
 2 files changed, 12 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index b5f87e7a1cfd..025efce540a7 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -168,6 +168,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE] = { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DRIVER_DETAILS]	= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DEV_TYPE]		= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PARENT_NAME]		= { .type = NLA_NUL_STRING },
 };
 
 static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -302,6 +303,15 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, device->use_cq_dim))
 		return -EMSGSIZE;
 
+	if (device->type &&
+	    nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_TYPE, device->type))
+		return -EMSGSIZE;
+
+	if (device->parent &&
+	    nla_put_string(msg, RDMA_NLDEV_ATTR_PARENT_NAME,
+			   dev_name(&device->parent->dev)))
+		return -EMSGSIZE;
+
 	/*
 	 * Link type is determined on first port and mlx4 device
 	 * which can potentially have two different link type for the same
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index bd52fb325e22..4b69242d7848 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -570,6 +570,8 @@ enum rdma_nldev_attr {
 
 	RDMA_NLDEV_ATTR_DEV_TYPE,		/* u8 */
 
+	RDMA_NLDEV_ATTR_PARENT_NAME,		/* string */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3


From af48f95492dc1af36d9636a750ec492035c0ed7d Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Mon, 1 Jul 2024 15:40:48 +0300
Subject: RDMA/core: Introduce "name_assign_type" for an IB device

The name_assign_type indicates how the name is provided. Currently
these types are supported:
- RDMA_NAME_ASSIGN_TYPE_UNKNOWN: Unknown or not set;
- RDMA_NAME_ASSIGN_TYPE_USER: Name is provided by the user; The
  user-created sub device, rxe and siw device has this type.

When filling nl device info, it is set in the new attribute
RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE. User-space tools like udev
"rdma_rename" could check this attribute to determine if this
device needs to be renamed or not.

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/522591bef9a369cc8e5dcb77787e017bffee37fe.1719837610.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/nldev.c      | 5 +++++
 drivers/infiniband/hw/mlx5/main.c    | 5 +++--
 drivers/infiniband/sw/rxe/rxe_net.c  | 1 +
 drivers/infiniband/sw/siw/siw_main.c | 1 +
 include/rdma/ib_verbs.h              | 8 ++++++++
 include/uapi/rdma/rdma_netlink.h     | 9 +++++++++
 6 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 025efce540a7..a6b80cdc96f7 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -169,6 +169,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_DRIVER_DETAILS]	= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DEV_TYPE]		= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_PARENT_NAME]		= { .type = NLA_NUL_STRING },
+	[RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE]	= { .type = NLA_U8 },
 };
 
 static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -312,6 +313,10 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 			   dev_name(&device->parent->dev)))
 		return -EMSGSIZE;
 
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE,
+		       device->name_assign_type))
+		return -EMSGSIZE;
+
 	/*
 	 * Link type is determined on first port and mlx4 device
 	 * which can potentially have two different link type for the same
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5de0d95d1f45..33513553379c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4198,9 +4198,10 @@ static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 {
 	const char *name;
 
-	if (dev->sub_dev_name)
+	if (dev->sub_dev_name) {
 		name = dev->sub_dev_name;
-	else if (!mlx5_lag_is_active(dev->mdev))
+		ib_mark_name_assigned_by_user(&dev->ib_dev);
+	} else if (!mlx5_lag_is_active(dev->mdev))
 		name = "mlx5_%d";
 	else
 		name = "mlx5_bond_%d";
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index ca9a82e1c4c7..75d1407db52d 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -537,6 +537,7 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
 		return -ENOMEM;
 
 	rxe->ndev = ndev;
+	ib_mark_name_assigned_by_user(&rxe->ib_dev);
 
 	err = rxe_add(rxe, ndev->mtu, ibdev_name);
 	if (err) {
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index 61ad8ca3d1a2..b2b54242aa69 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -485,6 +485,7 @@ static int siw_newlink(const char *basedev_name, struct net_device *netdev)
 		else
 			sdev->state = IB_PORT_DOWN;
 
+		ib_mark_name_assigned_by_user(&sdev->base_dev);
 		rv = siw_device_register(sdev, basedev_name);
 		if (rv)
 			ib_dealloc_device(&sdev->base_dev);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e09d4f09b602..6c5712ae559d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2794,6 +2794,8 @@ struct ib_device {
 	enum rdma_nl_dev_type type;
 	struct ib_device *parent;
 	struct list_head subdev_list;
+
+	enum rdma_nl_name_assign_type name_assign_type;
 };
 
 static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
@@ -4867,4 +4869,10 @@ int ib_add_sub_device(struct ib_device *parent,
  * Return 0 on success, an error code otherwise
  */
 int ib_del_sub_device_and_put(struct ib_device *sub);
+
+static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev)
+{
+	ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER;
+}
+
 #endif /* IB_VERBS_H */
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 4b69242d7848..2f37568f5556 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -572,6 +572,8 @@ enum rdma_nldev_attr {
 
 	RDMA_NLDEV_ATTR_PARENT_NAME,		/* string */
 
+	RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE,	/* u8 */
+
 	/*
 	 * Always the end
 	 */
@@ -615,4 +617,11 @@ enum rdma_nl_counter_mask {
 enum rdma_nl_dev_type {
 	RDMA_DEVICE_TYPE_SMI = 1,
 };
+
+/* RDMA device name assignment types */
+enum rdma_nl_name_assign_type {
+	RDMA_NAME_ASSIGN_TYPE_UNKNOWN = 0,
+	RDMA_NAME_ASSIGN_TYPE_USER = 1, /* Provided by user-space */
+};
+
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3