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: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Bob Pearson <rpearsonhpe@xxxxxxxxx>
---
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
