diff options
| author | Jason Gunthorpe <jgg@mellanox.com> | 2019-10-09 13:09:32 -0300 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@mellanox.com> | 2019-10-28 16:41:14 -0300 |
| commit | 5256edcb98a14b11409a2d323f56a70a8b366363 (patch) | |
| tree | 45b6a723c59bc1f7ff6511c266375023b2095732 /include/rdma/ib_umem_odp.h | |
| parent | b70d785d237c0d3e4235c511f38f8ce64620f945 (diff) | |
RDMA/mlx5: Rework implicit ODP destroy
Use SRCU in a sensible way by removing all MRs in the implicit tree from
the two xarrays (the update operation), then a synchronize, followed by a
normal single threaded teardown.
This is only a little unusual from the normal pattern as there can still
be some work pending in the unbound wq that may also require a workqueue
flush. This is tracked with a single atomic, consolidating the redundant
existing atomics and wait queue.
For understand-ability the entire ODP implicit create/destroy flow now
largely exists in a single pair of functions within odp.c, with a few
support functions for tearing down an unused child.
Link: https://lore.kernel.org/r/20191009160934.3143-13-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Diffstat (limited to 'include/rdma/ib_umem_odp.h')
| -rw-r--r-- | include/rdma/ib_umem_odp.h | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index 28078efc3833..09b0e4494986 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -78,9 +78,7 @@ struct ib_umem_odp { bool is_implicit_odp; struct completion notifier_completion; - int dying; unsigned int page_shift; - struct work_struct work; }; static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem) |