On Tue, Jun 19, 2018 at 12:32:49PM -0600, Jason Gunthorpe wrote: > On Tue, Jun 19, 2018 at 10:10:53AM +0000, Kalderon, Michal wrote: > > > From: Jason Gunthorpe [mailto:jgg@xxxxxxxx] > > > Sent: Monday, June 18, 2018 8:20 PM > > > > > > On Wed, Jun 13, 2018 at 10:22:06AM +0300, Leon Romanovsky wrote: > > > > From: Parav Pandit <parav@xxxxxxxxxxxx> > > > > > > > > The core code now ensures that all driver callbacks that receive an > > > > rdma_ah_attrs will have a sgid_attr's pointer if there is a GRH present. > > > > > > > > Drivers can use this pointer instead of calling a query function with > > > > sgid_index. This simplifies the drivers and also avoids races where a > > > > gid_index lookup may return different data if it is changed. > > > > > > > > Signed-off-by: Parav Pandit <parav@xxxxxxxxxxxx> > > > > Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx> > > > > Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx> > > > > drivers/infiniband/hw/bnxt_re/ib_verbs.c | 63 > > > > +++++++++++--------------------- drivers/infiniband/hw/hns/hns_roce_ah.c > > > | 19 ++-------- > > > > drivers/infiniband/hw/mlx4/ah.c | 16 +++----- > > > > drivers/infiniband/hw/mlx4/qp.c | 31 ++++++---------- > > > > drivers/infiniband/hw/mlx5/ah.c | 11 +----- > > > > drivers/infiniband/hw/mlx5/main.c | 32 ++-------------- > > > > drivers/infiniband/hw/mlx5/mlx5_ib.h | 6 +-- > > > > drivers/infiniband/hw/mlx5/qp.c | 10 ++--- > > > > drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 24 +++++------- > > > > drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 21 +++++------ > > > > drivers/infiniband/hw/qedr/verbs.c | 22 ++++------- > > > > drivers/infiniband/sw/rxe/rxe_av.c | 11 +++--- > > > > drivers/infiniband/sw/rxe/rxe_loc.h | 5 +-- > > > > drivers/infiniband/sw/rxe/rxe_qp.c | 23 +----------- > > > > drivers/infiniband/sw/rxe/rxe_verbs.c | 31 +++------------- > > > > include/rdma/ib_verbs.h | 8 ++-- > > > > 16 files changed, 96 insertions(+), 237 deletions(-) > > > > > > Leon, don't forget to CC the maintainers when touching drivers.. > > > > > > RDMA Driver authors: 4.19 is looking like it is going to have alot of changes to > > > the core APIs and other things. It is a good idea to be sure you test your > > > drivers and keep track of what is changing this cycle so we can have a strong > > > release. > > > > > > I'm going to apply this series since the changes are relatively straightforward. > > > If something breaks please send a fixing patch. > > > > Thanks for the heads up! Can you elaborate a bit more of what > > changes we should expect this cycle? > > Lots of stuff related to namespaces, hopefully, like the above. > Some uverbs kabi stuff > > At least.. > > > Are they already pending on some other public repo which we can take > > a look at? > > No, they are going through Mellanox QA still > > > Perhaps for core API changes a more detailed description of what was > > tested to cover the changes could help us to focus on what to test > > in our validation labs in addition to regular regressions. > > You can assume everything that passes through Leon's hands was tested > with Mellanox's regression systems and works with roce, IB and mlx5, > mlx5 hardware. + mlx4 and to some extent RXE. > > I would say iwarp is particularly at risk by this recent patch > series.. > > Jason
Attachment:
signature.asc
Description: PGP signature
