On 10/9/2018 2:45 PM, Kamal Heib wrote:
Initialize ib_device_ops with the supported operations.
Signed-off-by: Kamal Heib <kamalheib1@xxxxxxxxx>
---
drivers/infiniband/hw/hfi1/verbs.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index bc7f00ba1988..c63f331dbf7a 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1610,6 +1610,15 @@ static int get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
return count;
}
+static struct ib_device_ops hfi1_dev_ops = {
+ .modify_device = modify_device,
+ .alloc_hw_stats = alloc_hw_stats,
+ .get_hw_stats = get_hw_stats,
+ .alloc_rdma_netdev = hfi1_vnic_alloc_rn,
+ .process_mad = hfi1_process_mad,
+ .get_dev_fw_str = hfi1_get_dev_fw_str,
+};
+
/**
* hfi1_register_ib_device - register our device with the infiniband core
* @dd: the device data structure
@@ -1662,6 +1671,8 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
ibdev->process_mad = hfi1_process_mad;
ibdev->get_dev_fw_str = hfi1_get_dev_fw_str;
+ ib_set_device_ops(ibdev, &hfi1_dev_ops);
+
strlcpy(ibdev->node_desc, init_utsname()->nodename,
sizeof(ibdev->node_desc));
Haven't had a chance to review the rest of this series yet, but this
seems wrong to me as it should probably be in rdmavt.
-Denny
