On Thu, Apr 04, 2019 at 05:31:05PM +0300, Gal Pressman wrote:
> On 04-Apr-19 17:19, Jason Gunthorpe wrote:
> > On Thu, Apr 04, 2019 at 05:18:32PM +0300, Gal Pressman wrote:
> >> On 04-Apr-19 16:50, Jason Gunthorpe wrote:
> >>> On Wed, Apr 03, 2019 at 04:42:41PM +0300, Leon Romanovsky wrote:
> >>>> From: Leon Romanovsky <leonro@xxxxxxxxxxxx>
> >>>>
> >>>> Hi,
> >>>>
> >>>> This is rebase of previously sent patches, the rebase was needed
> >>>> due to acceptance of commit ff23dfa13457 ("IB: Pass only ib_udata
> >>>> in function prototypes").
> >>>>
> >>>> Thanks
> >>>>
> >>>> Leon Romanovsky (2):
> >>>> RDMA: Handle AH allocations by IB/core
> >>>> RDMA: Handle SRQ allocations by IB/core
> >>>>
> >>>> drivers/infiniband/core/device.c | 2 +
> >>>> drivers/infiniband/core/uverbs_cmd.c | 12 +-
> >>>> drivers/infiniband/core/verbs.c | 117 ++++++++++--------
> >>>> drivers/infiniband/hw/bnxt_re/ib_verbs.c | 76 ++++--------
> >>>> drivers/infiniband/hw/bnxt_re/ib_verbs.h | 20 ++-
> >>>> drivers/infiniband/hw/bnxt_re/main.c | 2 +
> >>>> drivers/infiniband/hw/bnxt_re/qplib_fp.c | 12 +-
> >>>> drivers/infiniband/hw/bnxt_re/qplib_fp.h | 4 +-
> >>>> drivers/infiniband/hw/bnxt_re/qplib_sp.c | 12 +-
> >>>> drivers/infiniband/hw/bnxt_re/qplib_sp.h | 4 +-
> >>>> drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 7 +-
> >>>> drivers/infiniband/hw/cxgb4/provider.c | 1 +
> >>>> drivers/infiniband/hw/cxgb4/qp.c | 32 ++---
> >>>> drivers/infiniband/hw/hns/hns_roce_ah.c | 24 ++--
> >>>> drivers/infiniband/hw/hns/hns_roce_device.h | 16 ++-
> >>>> drivers/infiniband/hw/hns/hns_roce_main.c | 4 +
> >>>> drivers/infiniband/hw/hns/hns_roce_srq.c | 52 +++-----
> >>>> drivers/infiniband/hw/mlx4/ah.c | 95 ++++++--------
> >>>> drivers/infiniband/hw/mlx4/mad.c | 35 +++---
> >>>> drivers/infiniband/hw/mlx4/main.c | 3 +
> >>>> drivers/infiniband/hw/mlx4/mlx4_ib.h | 19 ++-
> >>>> drivers/infiniband/hw/mlx4/srq.c | 47 +++----
> >>>> drivers/infiniband/hw/mlx5/ah.c | 33 ++---
> >>>> drivers/infiniband/hw/mlx5/main.c | 38 ++++--
> >>>> drivers/infiniband/hw/mlx5/mlx5_ib.h | 13 +-
> >>>> drivers/infiniband/hw/mlx5/srq.c | 59 ++++-----
> >>>> drivers/infiniband/hw/mlx5/srq.h | 2 +-
> >>>> drivers/infiniband/hw/mlx5/srq_cmd.c | 8 +-
> >>>> drivers/infiniband/hw/mthca/mthca_provider.c | 82 +++++-------
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 25 ++--
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_ah.h | 6 +-
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 11 +-
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_hw.h | 6 +-
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_main.c | 4 +
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 47 +++----
> >>>> drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 6 +-
> >>>> drivers/infiniband/hw/qedr/main.c | 3 +
> >>>> drivers/infiniband/hw/qedr/verbs.c | 48 +++----
> >>>> drivers/infiniband/hw/qedr/verbs.h | 13 +-
> >>>> .../infiniband/hw/vmw_pvrdma/pvrdma_main.c | 4 +
> >>>> drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c | 40 +++---
> >>>> .../infiniband/hw/vmw_pvrdma/pvrdma_verbs.c | 36 ++----
> >>>> .../infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 13 +-
> >>>> drivers/infiniband/sw/rdmavt/ah.c | 37 ++----
> >>>> drivers/infiniband/sw/rdmavt/ah.h | 9 +-
> >>>> drivers/infiniband/sw/rdmavt/srq.c | 43 +++----
> >>>> drivers/infiniband/sw/rdmavt/srq.h | 7 +-
> >>>> drivers/infiniband/sw/rdmavt/vt.c | 3 +
> >>>> drivers/infiniband/sw/rxe/rxe_pool.c | 4 +-
> >>>> drivers/infiniband/sw/rxe/rxe_verbs.c | 61 ++++-----
> >>>> drivers/infiniband/sw/rxe/rxe_verbs.h | 4 +-
> >>>> include/rdma/ib_verbs.h | 17 +--
> >>>> 52 files changed, 540 insertions(+), 738 deletions(-)
> >>>
> >>> Applied to for-next, thanks
> >>
> >> Shamir's patch just added udata to destroy_ah and this patch removes it, is that
> >> intended?
> >
> > Shamir got a little overzealous it seems as nobody needed.. I'm
> > ambivalent one way or the other - does EFA need it?
>
> Not really, I'm just trying to chase all the API changes and got confused..
> although I don't see harm in having it there, makes things more consistent.
>
> Anyway, the removal surprised me as it doesn't seem relevant to the patch, I
> thought it's a rebase mistake.
Gal thanks for the comment. I looked again and Jason is right and
there was no immediate use for the udata in the destroy_ah path. I can
drop this from the patch set.
