| Message ID | 20190520065433.8734-2-leon@kernel.org |
|---|---|
| State | Awaiting Upstream |
| Delegated to: | David Miller |
| Headers | show |
| Series | [rdma-next,01/15] rds: Don't check return value from destroy CQ | expand |
On 5/19/2019 11:54 PM, Leon Romanovsky wrote: > From: Leon Romanovsky <leonro@mellanox.com> > > There is no value in checking ib_destroy_cq() result and skipping > to clear struct ic fields. This connection needs to be reinitialized > anyway. > > Signed-off-by: Leon Romanovsky <leonro@mellanox.com> > --- > net/rds/ib_cm.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c > index 66c6eb56072b..5a42ebb892cd 100644 > --- a/net/rds/ib_cm.c > +++ b/net/rds/ib_cm.c > @@ -611,11 +611,11 @@ static int rds_ib_setup_qp(struct rds_connection *conn) > qp_out: > rdma_destroy_qp(ic->i_cm_id); > recv_cq_out: > - if (!ib_destroy_cq(ic->i_recv_cq)) > - ic->i_recv_cq = NULL; > + ib_destroy_cq(ic->i_recv_cq); > + ic->i_recv_cq = NULL; > send_cq_out: > - if (!ib_destroy_cq(ic->i_send_cq)) > - ic->i_send_cq = NULL; > + ib_destroy_cq(ic->i_send_cq); > + ic->i_send_cq = NULL; This was done to ensure, you still don't get ISR delivering the CQEs while we are in shutdown path. Your patch is fine though since you don't change that behavior. Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
On Mon, May 20, 2019 at 10:17:43AM -0700, Santosh Shilimkar wrote: > On 5/19/2019 11:54 PM, Leon Romanovsky wrote: > > From: Leon Romanovsky <leonro@mellanox.com> > > > > There is no value in checking ib_destroy_cq() result and skipping > > to clear struct ic fields. This connection needs to be reinitialized > > anyway. > > > > Signed-off-by: Leon Romanovsky <leonro@mellanox.com> > > --- > > net/rds/ib_cm.c | 8 ++++---- > > 1 file changed, 4 insertions(+), 4 deletions(-) > > > > diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c > > index 66c6eb56072b..5a42ebb892cd 100644 > > --- a/net/rds/ib_cm.c > > +++ b/net/rds/ib_cm.c > > @@ -611,11 +611,11 @@ static int rds_ib_setup_qp(struct rds_connection *conn) > > qp_out: > > rdma_destroy_qp(ic->i_cm_id); > > recv_cq_out: > > - if (!ib_destroy_cq(ic->i_recv_cq)) > > - ic->i_recv_cq = NULL; > > + ib_destroy_cq(ic->i_recv_cq); > > + ic->i_recv_cq = NULL; > > send_cq_out: > > - if (!ib_destroy_cq(ic->i_send_cq)) > > - ic->i_send_cq = NULL; > > + ib_destroy_cq(ic->i_send_cq); > > + ic->i_send_cq = NULL; > This was done to ensure, you still don't get ISR delivering > the CQEs while we are in shutdown path. Your patch > is fine though since you don't change that behavior. > > Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Thanks > >
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 66c6eb56072b..5a42ebb892cd 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -611,11 +611,11 @@ static int rds_ib_setup_qp(struct rds_connection *conn) qp_out: rdma_destroy_qp(ic->i_cm_id); recv_cq_out: - if (!ib_destroy_cq(ic->i_recv_cq)) - ic->i_recv_cq = NULL; + ib_destroy_cq(ic->i_recv_cq); + ic->i_recv_cq = NULL; send_cq_out: - if (!ib_destroy_cq(ic->i_send_cq)) - ic->i_send_cq = NULL; + ib_destroy_cq(ic->i_send_cq); + ic->i_send_cq = NULL; rds_ibdev_out: rds_ib_remove_conn(rds_ibdev, conn); out: