Improvements for ODP
Status from this message: Applied to for-next, thanks
Get series with b4
b4 am [email protected]Versions newest first
Patches in v1 Applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/12 | RDMA/odp: Use the common interval tree library instead of genericdrivers/ drivers/ include/ | +31 | 0 replies | |
| 2/12 | RDMA/odp: Iterate over the whole rbtree directlydrivers/ drivers/ | +47 | 4 replies | |
| 3/12 | RDMA/odp: Make it clearer when a umem is an implicit ODP umemdrivers/ drivers/ drivers/ +1 more | +40 | 0 replies | |
| 4/12 | RMDA/odp: Consolidate umem_odp initializationdrivers/ | +86 | 0 replies | |
| 5/12 | RDMA/odp: Make the three ways to create a umem_odp cleardrivers/ drivers/ include/ | +89 | 0 replies | |
| 6/12 | RDMA/odp: Split creating a umem_odp from ib_umem_getdrivers/ drivers/ drivers/ +2 more | +86 | 0 replies | |
| 7/12 | RDMA/odp: Provide ib_umem_odp_release() to undo the allocsdrivers/ drivers/ drivers/ +1 more | +11 | 0 replies | |
| 8/12 | RDMA/odp: Check for overflow when computing the umem_odp enddrivers/ include/ | +21 | 3 replies | |
| 9/12 | RDMA/odp: Use kvcalloc for the dma_list and page_listdrivers/ | +8 | 0 replies | |
| 10/12 | RDMA/core: Make invalidate_range a device operationdrivers/ drivers/ drivers/ +3 more | +9 | 0 replies | |
| 11/12 | RDMA/mlx5: Use ib_umem_start instead of umem.addressdrivers/ | +3 | 0 replies | |
| 12/12 | RDMA/mlx5: Use odp instead of mr->umem in pagefault_mrdrivers/ | +5 | 0 replies |
Reviews trailers per patch
1 of 12 patches has a Reviewed-by or Acked-by.
| Patch | Guy Levi | Jason Gunthorpe |
|---|---|---|
| 1/12 | ||
| 2/12 | ||
| 3/12 | ||
| 4/12 | ||
| 5/12 | ||
| 6/12 | ||
| 7/12 | ||
| 8/12 | ||
| 9/12 | ||
| 10/12 | R-b | R-b |
| 11/12 | ||
| 12/12 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH rdma-next 00/12] Improvements for ODP
From: Leon Romanovsky <[email protected]>
Hi,
This series from Jason is a collection of general cleanups for ODP to clarify some of the flows around umem creation and use of the interval tree.
It is based on patch "RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB"
https://lore.kernel.org/linux-rdma/[email protected]
Thanks
Jason Gunthorpe (11):
RDMA/odp: Use the common interval tree library instead of generic RDMA/odp: Iterate over the whole rbtree directly RDMA/odp: Make it clearer when a umem is an implicit ODP umem RMDA/odp: Consolidate umem_odp initialization RDMA/odp: Make the three ways to create a umem_odp clear RDMA/odp: Split creating a umem_odp from ib_umem_get RDMA/odp: Provide ib_umem_odp_release() to undo the allocs RDMA/odp: Check for overflow when computing the umem_odp end RDMA/odp: Use kvcalloc for the dma_list and page_list RDMA/mlx5: Use ib_umem_start instead of umem.address RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
Moni Shoua (1):
RDMA/core: Make invalidate_range a device operation
drivers/infiniband/Kconfig | 1 + drivers/infiniband/core/device.c | 1 + drivers/infiniband/core/umem.c | 50 +-- drivers/infiniband/core/umem_odp.c | 448 +++++++++++++++------------ drivers/infiniband/core/uverbs_cmd.c | 2 - drivers/infiniband/hw/mlx5/main.c | 4 - drivers/infiniband/hw/mlx5/mem.c | 13 - drivers/infiniband/hw/mlx5/mr.c | 38 ++- drivers/infiniband/hw/mlx5/odp.c | 88 +++--- include/rdma/ib_umem_odp.h | 48 ++- include/rdma/ib_verbs.h | 4 +- 11 files changed, 370 insertions(+), 327 deletions(-)
--
2.20.1