diff options
| author | Håkon Bugge <haakon.bugge@oracle.com> | 2021-03-31 20:43:14 +0200 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@nvidia.com> | 2021-04-13 00:51:48 +0200 |
| commit | 5aa54bd28ce2b066d82cdd515269b9d562bd6e66 (patch) | |
| tree | 027b8877446b4c7af02cc319d231d32a754161ff /net/rds/rdma_transport.c | |
| parent | IB/cma: Introduce rdma_set_min_rnr_timer() (diff) | |
| download | linux-5aa54bd28ce2b066d82cdd515269b9d562bd6e66.tar.xz linux-5aa54bd28ce2b066d82cdd515269b9d562bd6e66.zip | |
rds: ib: Remove two ib_modify_qp() calls
For some HCAs, ib_modify_qp() is an expensive operation running
virtualized.
For both the active and passive side, the QP returned by the CM has the
state set to RTS, so no need for this excess RTS -> RTS transition. With
IB Core's ability to set the RNR Retry timer, we use this interface to
shave off another ib_modify_qp().
Fixes: ec16227e1414 ("RDS/IB: Infiniband transport")
Link: https://lore.kernel.org/r/1617216194-12890-3-git-send-email-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'net/rds/rdma_transport.c')
| -rw-r--r-- | net/rds/rdma_transport.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 5f741e51b4ba..a9e4ff948a7d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -87,6 +87,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_ADDR_RESOLVED: rdma_set_service_type(cm_id, conn->c_tos); + rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); /* XXX do we need to clean up if this fails? */ ret = rdma_resolve_route(cm_id, RDS_RDMA_RESOLVE_TIMEOUT_MS); |