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. I would say iwarp is particularly at risk by this recent patch series.. Jason -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
