diff options
| author | Yishai Hadas <yishaih@nvidia.com> | 2021-02-02 10:13:09 +0300 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@nvidia.com> | 2021-02-09 03:31:11 +0300 |
| commit | db72438c9319cfd37e3c237a7754ca862ae12d63 (patch) | |
| tree | c5fe461d002f4fb853f9b944da24d4423cc66bec /include/linux/mlx5/driver.h | |
| parent | a5887d62072e09a9d3b01549ac5d555bbeb9be3d (diff) | |
| download | linux-db72438c9319cfd37e3c237a7754ca862ae12d63.tar.xz | |
RDMA/mlx5: Cleanup the synchronize_srcu() from the ODP flow
Cleanup the synchronize_srcu() from the ODP flow as it was found to be a
very heavy time consumer as part of dereg_mr.
For example de-registration of 10000 ODP MRs each with size of 2M hugepage
took 19.6 sec comparing de-registration of same number of non ODP MRs that
took 172 ms.
The new locking scheme uses the wait_event() mechanism which follows the
use count of the MR instead of using synchronize_srcu().
By that change, the time required for the above test took 95 ms which is
even better than the non ODP flow.
Once fully dropped the srcu usage, had to come with a lock to protect the
XA access.
As part of using the above mechanism we could also clean the
num_deferred_work stuff and follow the use count instead.
Link: https://lore.kernel.org/r/20210202071309.2057998-1-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'include/linux/mlx5/driver.h')
| -rw-r--r-- | include/linux/mlx5/driver.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 11558c2e99f0..b0a59a18a708 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -366,6 +366,8 @@ struct mlx5_core_mkey { u32 key; u32 pd; u32 type; + struct wait_queue_head wait; + refcount_t usecount; }; #define MLX5_24BIT_MASK ((1 << 24) - 1) |