diff options
author | Avihai Horon <avihaih@nvidia.com> | 2021-06-09 14:05:03 +0300 |
---|---|---|
committer | Jason Gunthorpe <jgg@nvidia.com> | 2021-06-21 12:33:08 -0300 |
commit | 1477d44ce47d6cf3b2bab1afbca573b4f677666c (patch) | |
tree | 2b30f6245cbbc45d1f8561f8fc1267e6dd7d6f46 /include | |
parent | 7e78dd816e458fbc2928a068d70009178d5d070d (diff) |
RDMA/mlx5: Enable Relaxed Ordering by default for kernel ULPs
Relaxed Ordering is a capability that can only benefit users that support
it. All kernel ULPs should support Relaxed Ordering, as they are designed
to read data only after observing the CQE and use the DMA API correctly.
Hence, implicitly enable Relaxed Ordering by default for MR transfers in
kernel ULPs.
Link: https://lore.kernel.org/r/b7e820aab7402b8efa63605f4ea465831b3b1e5e.1623236426.git.leonro@nvidia.com
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'include')
-rw-r--r-- | include/rdma/ib_verbs.h | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9423e70a881c..34971c7b988f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2468,6 +2468,14 @@ struct ib_device_ops { enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); + + /* + * Kernel users should universally support relaxed ordering (RO), as + * they are designed to read data only after observing the CQE and use + * the DMA API correctly. + * + * Some drivers implicitly enable RO if platform supports it. + */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, |