| Message ID | a2ab630d2a634547db9b581faa9d65da2edb9d05.1639554831.git.leonro@nvidia.com (mailing list archive) |
|---|---|
| State | Accepted |
| Delegated to: | Jason Gunthorpe |
| Headers | show |
| Series | [rdma-next] IB/mlx5: Expose NDR speed through MAD | expand |
On Wed, Dec 15, 2021 at 09:54:31AM +0200, Leon Romanovsky wrote: > From: Maher Sanalla <msanalla@nvidia.com> > > Under MAD query port, Report NDR speed when NDR is supported > in the port capability mask. > > Signed-off-by: Maher Sanalla <msanalla@nvidia.com> > Reviewed-by: Michael Guralnik <michaelgur@nvidia.com> > Signed-off-by: Leon Romanovsky <leonro@nvidia.com> > --- > drivers/infiniband/hw/mlx5/mad.c | 5 +++++ > include/rdma/ib_mad.h | 1 + > 2 files changed, 6 insertions(+) Applied to for-next, thanks Jason
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index ec242a5a17a3..29a888b22789 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -584,6 +584,11 @@ int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u32 port, props->port_cap_flags2 & IB_PORT_LINK_SPEED_HDR_SUP) props->active_speed = IB_SPEED_HDR; break; + case 8: + if (props->port_cap_flags & IB_PORT_CAP_MASK2_SUP && + props->port_cap_flags2 & IB_PORT_LINK_SPEED_NDR_SUP) + props->active_speed = IB_SPEED_NDR; + break; } } diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h index 465b0d0bdaf8..2e3843b761e8 100644 --- a/include/rdma/ib_mad.h +++ b/include/rdma/ib_mad.h @@ -276,6 +276,7 @@ enum ib_port_capability_mask2_bits { IB_PORT_SWITCH_PORT_STATE_TABLE_SUP = 1 << 3, IB_PORT_LINK_WIDTH_2X_SUP = 1 << 4, IB_PORT_LINK_SPEED_HDR_SUP = 1 << 5, + IB_PORT_LINK_SPEED_NDR_SUP = 1 << 10, }; #define OPA_CLASS_PORT_INFO_PR_SUPPORT BIT(26)