On Fri, Jul 23, 2021 at 02:39:42PM +0300, Leon Romanovsky wrote:

From: Leon Romanovsky <leonro@nvidia.com>

Changelog:
v1:
 * Added ROB tags
 * Deleted already existed double rwq_ind_tbl assignment
 * Deleted hr_qp->ibqp.qp_type assignment
v0: https://lore.kernel.org/lkml/cover.1626609283.git.leonro@nvidia.com (local)

-----------------------------------------------------------------------------
Hi,

This series convert IB/core to use core allocation scheme for the QP
objects.

Thanks

Leon Romanovsky (9):
  RDMA/hns: Don't skip IB creation flow for regular RC QP
  RDMA/hns: Don't overwrite supplied QP attributes
  RDMA/efa: Remove double QP type assignment
  RDMA/mlx5: Cancel pkey work before destroying device resources
  RDMA/mlx5: Delete device resource mutex that didn't protect anything
  RDMA/mlx5: Rework custom driver QP type creation
  RDMA/rdmavt: Decouple QP and SGE lists allocations
  RDMA: Globally allocate and release QP memory
  RDMA/mlx5: Drop in-driver verbs object creations

Applied to for-next, thanks

Jason