[PATCH for-next v2] RDMA/rxe: Fix "Replace mr by rkey in responder resources"

[Bob Pearson <rpearsonhpe@gmail.com>]

The rping benchmark fails on long runs. The root cause of this
failure has been traced to a failure to compute a nonzero value of mr
in rare situations.

Fix this failure by correctly handling the computation of mr in
read_reply() in rxe_resp.c in the replay flow.

Fixes: 8a1a0be894da ("RDMA/rxe: Replace mr by rkey in responder resources")
Link: https://lore.kernel.org/linux-rdma/1a9a9190-368d-3442-0a62-443b1a6c1209@linux.dev/
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
v2
  Renamed commit
  Changed fixes line to correctly ID the bug
  Added a link to the reported mr == NULL issue

 drivers/infiniband/sw/rxe/rxe_resp.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index e2653a8721fe..2e627685e804 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -734,8 +734,14 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	}
 
 	if (res->state == rdatm_res_state_new) {
-		mr = qp->resp.mr;
-		qp->resp.mr = NULL;
+		if (!res->replay) {
+			mr = qp->resp.mr;
+			qp->resp.mr = NULL;
+		} else {
+			mr = rxe_recheck_mr(qp, res->read.rkey);
+			if (!mr)
+				return RESPST_ERR_RKEY_VIOLATION;
+		}
 
 		if (res->read.resid <= mtu)
 			opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY;

base-commit: 98c8026331ceabe1df579940b81eec75eb49cdd9
-- 
2.32.0