Merge tag 'rds-odp-for-5.5' into rdma.git for-next

From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

* tag 'rds-odp-for-5.5':
  net/rds: Use prefetch for On-Demand-Paging MR
  net/rds: Handle ODP mr registration/unregistration
  net/rds: Detect need of On-Demand-Paging memory registration
  RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
  IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
  RDMA/mlx5: Don't fake udata for kernel path
  IB/mlx5: Add ODP WQE handlers for kernel QPs
  IB/core: Add interface to advise_mr for kernel users
  IB/core: Introduce ib_reg_user_mr
  IB: Allow calls to ib_umem_get from kernel ULPs

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

2 files changed, 16 insertions, 12 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 9b6ca15a183c..52b6a4d85460 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -837,7 +837,8 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
 		bytes += (qplib_qp->sq.max_wqe * psn_sz);
 	}
 	bytes = PAGE_ALIGN(bytes);
-	umem = ib_umem_get(udata, ureq.qpsva, bytes, IB_ACCESS_LOCAL_WRITE);
+	umem = ib_umem_get(&rdev->ibdev, ureq.qpsva, bytes,
+			   IB_ACCESS_LOCAL_WRITE);
 	if (IS_ERR(umem))
 		return PTR_ERR(umem);
 
@@ -850,7 +851,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
 	if (!qp->qplib_qp.srq) {
 		bytes = (qplib_qp->rq.max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
 		bytes = PAGE_ALIGN(bytes);
-		umem = ib_umem_get(udata, ureq.qprva, bytes,
+		umem = ib_umem_get(&rdev->ibdev, ureq.qprva, bytes,
 				   IB_ACCESS_LOCAL_WRITE);
 		if (IS_ERR(umem))
 			goto rqfail;
@@ -1304,7 +1305,8 @@ static int bnxt_re_init_user_srq(struct bnxt_re_dev *rdev,
 
 	bytes = (qplib_srq->max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
 	bytes = PAGE_ALIGN(bytes);
-	umem = ib_umem_get(udata, ureq.srqva, bytes, IB_ACCESS_LOCAL_WRITE);
+	umem = ib_umem_get(&rdev->ibdev, ureq.srqva, bytes,
+			   IB_ACCESS_LOCAL_WRITE);
 	if (IS_ERR(umem))
 		return PTR_ERR(umem);
 
@@ -2545,7 +2547,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 			goto fail;
 		}
 
-		cq->umem = ib_umem_get(udata, req.cq_va,
+		cq->umem = ib_umem_get(&rdev->ibdev, req.cq_va,
 				       entries * sizeof(struct cq_base),
 				       IB_ACCESS_LOCAL_WRITE);
 		if (IS_ERR(cq->umem)) {
@@ -3305,8 +3307,10 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	int rc;
 
 	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
-	if (rc)
+	if (rc) {
 		dev_err(rdev_to_dev(rdev), "Dereg MR failed: %#x\n", rc);
+		return rc;
+	}
 
 	if (mr->pages) {
 		rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
@@ -3512,7 +3516,7 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
 	/* The fixed portion of the rkey is the same as the lkey */
 	mr->ib_mr.rkey = mr->qplib_mr.rkey;
 
-	umem = ib_umem_get(udata, start, length, mr_access_flags);
+	umem = ib_umem_get(&rdev->ibdev, start, length, mr_access_flags);
 	if (IS_ERR(umem)) {
 		dev_err(rdev_to_dev(rdev), "Failed to get umem");
 		rc = -EFAULT;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 958c1ff9c515..4d07d22bfa7b 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -2283,13 +2283,13 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 			/* Add qp to flush list of the CQ */
 			bnxt_qplib_add_flush_qp(qp);
 		} else {
+			/* Before we complete, do WA 9060 */
+			if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
+				      cqe_sq_cons)) {
+				*lib_qp = qp;
+				goto out;
+			}
 			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
-				/* Before we complete, do WA 9060 */
-				if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
-					      cqe_sq_cons)) {
-					*lib_qp = qp;
-					goto out;
-				}
 				cqe->status = CQ_REQ_STATUS_OK;
 				cqe++;
 				(*budget)--;