On Thu, Sep 17, 2020 at 08:04:42PM -0300, Jason Gunthorpe wrote: > On Thu, Sep 17, 2020 at 07:35:20PM +0300, Leon Romanovsky wrote: > > On Thu, Sep 17, 2020 at 08:41:54AM -0300, Jason Gunthorpe wrote: > > > On Thu, Sep 17, 2020 at 12:02:20PM +0300, Leon Romanovsky wrote: > > > > From: Leon Romanovsky <leonro@xxxxxxxxxx> > > > > > > > > Changelog: > > > > v2: > > > > * Changed WARN_ON casting to be saturated value instead while returning active_speed > > > > to the user. > > > > v1: https://lore.kernel.org/linux-rdma/20200902074503.743310-1-leon@xxxxxxxxxx > > > > * Changed patch #1 to fix memory corruption to help with bisect. No > > > > change in series, because the added code is changed anyway in patch > > > > #3. > > > > v0: > > > > * https://lore.kernel.org/linux-rdma/20200824105826.1093613-1-leon@xxxxxxxxxx > > > > > > > > > > > > IBTA declares speed as 16 bits, but kernel stores it in u8. This series > > > > fixes in-kernel declaration while keeping external interface intact. > > > > > > > > Thanks > > > > > > > > Aharon Landau (3): > > > > net/mlx5: Refactor query port speed functions > > > > RDMA/mlx5: Delete duplicated mlx5_ptys_width enum > > > > RDMA: Fix link active_speed size > > > > > > Look OK, can you update the shared branch? > > > > I pushed first two patches to mlx5-next branch: > > > > e27014bdb47e RDMA/mlx5: Delete duplicated mlx5_ptys_width enum > > 639bf4415cad net/mlx5: Refactor query port speed functions > > Applied to for-next, thanks Actually it needed a little help with this: diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index caa9c5966e44bd..a7e203bcb012db 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -535,7 +535,8 @@ enum ib_port_speed { IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, - IB_SPEED_HDR = 64 + IB_SPEED_HDR = 64, + IB_SPEED_NDR = 128, }; /** I fixed it Jason
