4.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Somnath Kotur <somnath.ko...@broadcom.com>
[ Upstream commit f40f299bbe806a2e2c8b0d7cdda822fa3bdd171b ]
1. DMA-able memory allocated for Shadow QP was not being freed.
2. bnxt_qplib_alloc_qp_hdr_buf() had a bug wherein the SQ pointer was
erroneously pointing to the RQ. But since the corresponding
free_qp_hdr_buf() was correct, memory being free was less than what was
allocated.
Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Signed-off-by: Somnath Kotur <somnath.ko...@broadcom.com>
Signed-off-by: Jason Gunthorpe <j...@mellanox.com>
Signed-off-by: Sasha Levin <alexander.le...@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 ++
drivers/infiniband/hw/bnxt_re/qplib_fp.c | 2 +-
2 files changed, 3 insertions(+), 1 deletion(-)
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -844,6 +844,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_
"Failed to destroy Shadow QP");
return rc;
}
+ bnxt_qplib_free_qp_res(&rdev->qplib_res,
+ &rdev->qp1_sqp->qplib_qp);
mutex_lock(&rdev->qp_lock);
list_del(&rdev->qp1_sqp->list);
atomic_dec(&rdev->qp_count);
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(s
struct bnxt_qplib_qp *qp)
{
struct bnxt_qplib_q *rq = &qp->rq;
- struct bnxt_qplib_q *sq = &qp->rq;
+ struct bnxt_qplib_q *sq = &qp->sq;
int rc = 0;
if (qp->sq_hdr_buf_size && sq->hwq.max_elements) {
