[PATCH v2 0/2] Last WQE Reached event treatment

Max Gurtovoy mgurtovoy at nvidia.com
Wed Jun 19 10:11:51 PDT 2024


Hi Jason/Leon/Sagi,

This series adds a support for draining a QP that is associated with a
SRQ (Shared Receive Queue).
Leakage problem can occur if we won't treat Last WQE Reached event.

In the series, that is based on some old series I've send during 2018, I
used a different approach and handled the event in the RDMA core, as was
suggested in discussion in the mailing list.

In addition to the main patch 1/2 I've added another 2/2 to remove dead
code.

I've tested this series with NVMf/RDMA on RoCE.

Changes from v1:
 1. don't withhold the LAST_WQE_REACHED from the ULPs (Sagi)
 2. Remove ULP update as a result from #1
 3. Increase the wait_for_completion_timeout to 60 seconds

Max Gurtovoy (2):
  IB/core: add support for draining Shared receive queues
  IB/isert: remove the handling of last WQE reached event

 drivers/infiniband/core/verbs.c         | 82 ++++++++++++++++++++++++-
 drivers/infiniband/ulp/isert/ib_isert.c |  3 -
 include/rdma/ib_verbs.h                 |  2 +
 3 files changed, 83 insertions(+), 4 deletions(-)

-- 
2.18.1




More information about the Linux-nvme mailing list