Public bug reported:

Hi,

The request is to backport 
09689703d29a RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during create 
and destroy
with it the below list (divided to four sets) is required.

most of the patches applied cleanly above focal tree four exceptions.

1. 806b101b2bfa RDMA/mlx5: Use a dedicated mkey xarray for ODP
2. b91e1751fbce RDMA/mlx5: Simplify how the MR cache bucket is located
3. 1769c4c57548 RDMA/mlx5: Always remove MRs from the cache before destroying 
them
4. b9358bdbc713 RDMA/mlx5: Fix locking in MR cache work queue
the rejected hunks need to be manually applied.
The rejected hunks are due to true<-->1 false<-->0 exchange added support for 
wc (b9358bdbc713) and other minor reasons.  

 set 0: Unrelated code cleanups (needed for applying  cleanly the mr cache set)
 https://patchwork.kernel.org/cover/11170991/
 909624d8db5b IB/cm: Use container_of() instead of typecast
 6f26b2ac699c IB/mlx5: Remove unnecessary else statement
 2d67c0798821 IB/mlx5: Remove unnecessary return statement
 4b2a67362e78 RDMA/mlx5: Group boolean parameters to take less space

 set 1: Rework the locking and datastructures for mlx5 implicit ODP
 https://patchwork.kernel.org/cover/11181509/
 46870b2391d5 RDMA/odp: Remove broken debugging call to invalidate_range
 09689703d29a RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during 
create and destroy
 d561987f34f2 RDMA/mlx5: Do not store implicit children in the odp_mkeys xarray
 5256edcb98a1 RDMA/mlx5: Rework implicit ODP destroy
 b70d785d237c RDMA/mlx5: Avoid double lookups on the pagefault path
 3389baa831b6 RDMA/mlx5: Reduce locking in implicit_mr_get_data()
 423f52d65005 RDMA/mlx5: Use an xarray for the children of an implicit ODP
 54375e738295 RDMA/mlx5: Split implicit handling from pagefault_mr
 9162420dde49 RDMA/mlx5: Set the HW IOVA of the child MRs to their place in the 
tree
 c2edcd69351f RDMA/mlx5: Lift implicit_mr_alloc() into the two routines that 
call it
 3d5f3c54e7bc RDMA/mlx5: Rework implicit_mr_get_data
 74bddb3682f6 RDMA/mlx5: Delete struct mlx5_priv->mkey_table
 806b101b2bfa RDMA/mlx5: Use a dedicated mkey xarray for ODP
 50211ec9443f RDMA/mlx5: Split sig_err MR data into its own xarray
 fb985e278a30 RDMA/mlx5: Use SRCU properly in ODP prefetch


 set 2: Consolidate the mmu notifier interval_tree and locking (only first two 
patches from this set)
 https://patchwork.kernel.org/cover/11240081/
 99cb252f5e68 mm/mmu_notifier: add an interval tree notifier
 56f434f40f05 mm/mmu_notifier: define the header pre-processor parts even if 
disabled


 also needed for applying  mr cache set cleanly.
 03232cc43cff IB/mlx5: Introduce and use mkey context setting helper routine

 set 3: MR cache fixes and refactoring
 https://www.spinics.net/lists/linux-rdma/msg89706.html
 aad719dcf379 RDMA/mlx5: Allow MRs to be created in the cache synchronously
 1c78a21a0c6f RDMA/mlx5: Revise how the hysteresis scheme works for cache 
filling
 b9358bdbc713 RDMA/mlx5: Fix locking in MR cache work queue
 ad2d3ef46d2a RDMA/mlx5: Lock access to ent->available_mrs/limit when doing 
queue_work
 a1d8854aae4e RDMA/mlx5: Fix MR cache size and limit debugfs
 1769c4c57548 RDMA/mlx5: Always remove MRs from the cache before destroying them
 b91e1751fbce RDMA/mlx5: Simplify how the MR cache bucket is located
 7c8691a396bd RDMA/mlx5: Rename the tracking variables for the MR cache
 f743ff3b37df RDMA/mlx5: Replace spinlock protected write with atomic var
 a3cfdd392811 {IB,net}/mlx5: Move asynchronous mkey creation to mlx5_ib
 fc6a9f86f08a {IB,net}/mlx5: Assign mkey variant in mlx5_ib only
 54c62e13ad76 {IB,net}/mlx5: Setup mkey variant before mr create command 
invocation

** Affects: linux (Ubuntu)
     Importance: Undecided
         Status: Incomplete

-- 
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1894977

Title:
   IBM-iobrick patches for Ubuntu 20.04

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1894977/+subscriptions

-- 
ubuntu-bugs mailing list
ubuntu-bugs@lists.ubuntu.com
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs

Reply via email to