Cleanup locking and events in ucma
Status from this message: Applied to for-next
Get series with b4
b4 am [email protected]Versions newest first
Patches in v1 Applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/14 | RDMA/ucma: Fix refcount 0 incr in ucma_get_ctx()drivers/ | +2 | 0 replies | |
| 2/14 | RDMA/ucma: Remove unnecessary locking of file->ctx_list in closedrivers/ | +7 | 0 replies | |
| 3/14 | RDMA/ucma: Consolidate the two destroy flowsdrivers/ | +22 | 0 replies | |
| 4/14 | RDMA/ucma: Fix error cases around ucma_alloc_ctx()drivers/ | +42 | 0 replies | |
| 5/14 | RDMA/ucma: Remove mc_list and rely on xarraydrivers/ | +22 | 0 replies | |
| 6/14 | RDMA/cma: Add missing locking to rdma_accept()drivers/ drivers/ include/ | +35 | 2 replies | |
| 7/14 | RDMA/ucma: Do not use file->mut to lock destroyingdrivers/ | +11 | 0 replies | |
| 8/14 | RDMA/ucma: Fix the locking of ctx->filedrivers/ | +5 | 0 replies | |
| 9/14 | RDMA/ucma: Fix locking for ctx->events_reporteddrivers/ | +3 | 0 replies | |
| 10/14 | RDMA/ucma: Add missing locking around rdma_leave_multicast()drivers/ | +2 | 0 replies | |
| 11/14 | RDMA/ucma: Change backlog into an atomicdrivers/ | +8 | 0 replies | |
| 12/14 | RDMA/ucma: Narrow file->mut in ucma_event_handler()drivers/ | +7 | 0 replies | |
| 13/14 | RDMA/ucma: Rework how new connections are passed through event deliverydrivers/ | +96 | 0 replies | |
| 14/14 | RDMA/ucma: Remove closing and the close_wqdrivers/ | +15 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [PATCH rdma-next 00/14] Cleanup locking and events in ucma
From: Leon Romanovsky <[email protected]>
From Jason:
Rework how the uevents for new connections are handled so all the locking ends up simpler and a work queue can be removed. This should also speed up destruction of ucma_context's as a flush_workqueue() was replaced with cancel_work_sync().
The simpler locking comes from narrowing what file->mut covers and moving other data to other locks, particularly by injecting the handler_mutex from the RDMA CM core as a construct available to ULPs. The handler_mutex directly prevents handlers from running without creating any ABBA locking problems.
Fix various error cases and data races caused by missing locking.
Thanks
Jason Gunthorpe (14):
RDMA/ucma: Fix refcount 0 incr in ucma_get_ctx() RDMA/ucma: Remove unnecessary locking of file->ctx_list in close RDMA/ucma: Consolidate the two destroy flows RDMA/ucma: Fix error cases around ucma_alloc_ctx() RDMA/ucma: Remove mc_list and rely on xarray RDMA/cma: Add missing locking to rdma_accept() RDMA/ucma: Do not use file->mut to lock destroying RDMA/ucma: Fix the locking of ctx->file
RDMA/ucma: Fix locking for ctx->events_reported RDMA/ucma: Add missing locking around rdma_leave_multicast() RDMA/ucma: Change backlog into an atomic
RDMA/ucma: Narrow file->mut in ucma_event_handler() RDMA/ucma: Rework how new connections are passed through event
delivery
RDMA/ucma: Remove closing and the close_wq
drivers/infiniband/core/cma.c | 25 +- drivers/infiniband/core/ucma.c | 444 +++++++++++++++------------------ include/rdma/rdma_cm.h | 5 + 3 files changed, 226 insertions(+), 248 deletions(-)
--
2.26.2