[PATCH rdma-next v9 0/9] RDMA/mana_ib: Add kernel RC and fast registration support

[Konstantin Taranov <kotaranov@linux.microsoft.com>]

From: Konstantin Taranov <kotaranov@microsoft.com>

Add kernel RC QPs and fast-registration MRs to the MANA RDMA driver
for kernel consumers such as NVMe/RDMA and NFS/RDMA.

Implement QP creation and state management, work request posting,
completion processing, and error handling. Use the RDMA core's generic
queue drains for kernel RC QPs, with software-flush notification in the
posting paths. Kernel RC QPs require extended-WQE and power-of-two-SQ
hardware support.

The changes were tested with krping, NVMe/RDMA, and NFS/RDMA, including
RC send and receive error recovery with krping and NVMe/RDMA.

v9:
- Patch 07 and 09: Retire acknowledged successful unsignaled WQEs with
 a full WC array to avoid deferring rearming.

v8:
- Patch 06: Annotate rc_send.immediate and immediate_ext as __le32

v7:
- Patch 09: Include GSI QPs in deferred ERR handling.
- Patch 09: Complete software-flush setup even if the deferred firmware
  ERR request fails. An error CQE guarantees whole-QP DMA shutdown for
  all QP types.
- Drop patch 10 to use the generic SQ/RQ drains for RC.

v6:
- Patch 08: Notify software flushes after posting to error-listed QPs.
  Add reporting pending software flush for IB_CQ_REPORT_MISSED_EVENTS.
- Patch 09: Check fenced WQEs on error cqes to prevent flushing completed WQEs.
  Add mana_ib_cq_clean on QP reset to discard stale CQEs. QID 0 is an invalid
  value for RNIC and safe dor discarding. Add error_pending flag to prevent
  a deffered ERR request to error reset QPs.

v5:
- Patch 01: Reject max_num_sg above MANA_MAX_FMR_PAGES.
- Patch 02: Validate kernel QP queue sizes and SGE limits to prevent
  overflows. Ensure that queue size cannnot be 0.
- Patch 06: Preserve fence flags on unsignaled WQEs. Check message
  length and read sges before posting a wqe.
- Patch 08: Remove the unused QP state field.

v4:
- Patch 01: Use an explicit 64-byte FMR MST alignment
- Patch 02: Validate that the RNIC firmware reports at least two send
  SGEs and subtract the reserved SGE only for RNIC-based mana_ib.
- Patch 07: Add missing wqe_size to shadow wqe for SEND/Write, and
  return a missed-event hint for cached CQEs when CQ is armed

v3:
- Patch 07: Mask arm_psn to 24 bits before ringing the doorbell.
- Patch 08: Exclude userspace QPs from kernel software-state handling
  and CQ error-list insertion, and unlink UC QPs during destruction.

v2:
- Patch 03: Validate fixed-WQE capacity for the header, OOB and SGEs.
- Patch 04: Preserve UC QP modification support.
- Patch 08: Skip software CQ notifications for direct-polling CQs.
- Patch 09: Flush that ERR work during QP teardown.
- Patch 10: Limit drain callbacks to RC QPs and avoid completion
  callbacks for direct-polling CQs.

Konstantin Taranov (9):
  RDMA/mana_ib: Allocate and map fast-registration MRs
  RDMA/mana: Create and destroy kernel RC QPs
  net/mana: Extend GDMA encoding for new RDMA WQEs
  RDMA/mana_ib: Maintain kernel RC QP state
  RDMA/mana_ib: Post receive WRs on kernel RC QPs
  RDMA/mana_ib: Post send and memory-management WRs on RC QPs
  RDMA/mana_ib: Poll RC completions using PSN and FSN progress
  RDMA/mana_ib: Flush and notify CQs when kernel QPs enter ERR
  RDMA/mana_ib: Handle error CQEs for kernel QPs

 drivers/infiniband/hw/mana/cq.c               | 357 ++++++++++++++-
 drivers/infiniband/hw/mana/device.c           |   2 +
 drivers/infiniband/hw/mana/main.c             |  15 +-
 drivers/infiniband/hw/mana/mana_ib.h          | 139 +++++-
 drivers/infiniband/hw/mana/mr.c               |  87 +++-
 drivers/infiniband/hw/mana/qp.c               | 327 ++++++++++++-
 drivers/infiniband/hw/mana/shadow_queue.h     |  22 +
 drivers/infiniband/hw/mana/wr.c               | 433 +++++++++++++++++-
 .../net/ethernet/microsoft/mana/gdma_main.c   |  55 ++-
 include/net/mana/gdma.h                       |  38 +-
 10 files changed, 1406 insertions(+), 69 deletions(-)

-- 
2.43.0