IB/hfi1: Don't zero out qp->s_ack_queue in rvt_reset_qp

Since rvt_reset_qp already zero's out qp->s_ack_queue head and tail
pointers, there is no need to zero out qp->s_ack_queue itself.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index c3e0d614f68bb9357bd8860523b8f56c89553044..d04f4fe522b5a9713f4027afc79004660162b78b 100644 (file)
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -576,12 +576,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
        qp->s_ssn = 1;
        qp->s_lsn = 0;
        qp->s_mig_state = IB_MIG_MIGRATED;
-       if (qp->s_ack_queue)
-               memset(
-                       qp->s_ack_queue,
-                       0,
-                       rvt_max_atomic(rdi) *
-                               sizeof(*qp->s_ack_queue));
        qp->r_head_ack_queue = 0;
        qp->s_tail_ack_queue = 0;
        qp->s_num_rd_atomic = 0;