diff options
| author | Jason Gunthorpe <jgg@nvidia.com> | 2020-10-26 15:23:13 +0200 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@nvidia.com> | 2020-11-02 15:10:50 -0400 |
| commit | f1eaac37da20823816af274d69a9eed7444e9822 (patch) | |
| tree | 2668cc7af653d5eb8b5e92cfa0141d6c736a68a6 /tools/perf/scripts/python/stackcollapse.py | |
| parent | RDMA/mlx5: Split the WR setup out of mlx5_ib_update_xlt() (diff) | |
| download | linux-f1eaac37da20823816af274d69a9eed7444e9822.tar.gz linux-f1eaac37da20823816af274d69a9eed7444e9822.zip | |
RDMA/mlx5: Split mlx5_ib_update_xlt() into ODP and non-ODP cases
Mixing these together is just a mess, make a dedicated version,
mlx5_ib_update_mr_pas(), which directly loads the whole MTT for a non-ODP
MR.
The split out version can trivially use a simple loop with
rdma_for_each_block() which allows using the core code to compute the MR
pages and avoids seeking in the SGL list after each chunk as the
__mlx5_ib_populate_pas() call required.
Significantly speeds loading large MTTs.
Link: https://lore.kernel.org/r/20201026132314.1336717-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'tools/perf/scripts/python/stackcollapse.py')
0 files changed, 0 insertions, 0 deletions