[PATCH rdma-next v2 0/3] IB/mad: Add Flow Control for Solicited MADs

[PATCH rdma-next v2 0/3] IB/mad: Add Flow Control for Solicited MADs

[Leon Romanovsky]

Changelog:
v2:
 * Add separate send-only agent for REPs to prevent starvation
   of REPs when runnning both service and client on the same node.
 * Instead of immediately resending a timed-out MAD, it will now   be
 * placed in backlog queue if the queue is not empty.
v1: https://lore.kernel.org/all/cover.1736258116.git.leonro@nvidia.com
 * Add a cancel state to the state machine which allows removing the
 * status field in MAD's struct.
 * Add change_mad_state function which handles all the state transition.
 * Add WARN_ONs to check MAD states
 * Reorganize patches to have only two patches in this series instead of
 * three.
v0: https://lore.kernel.org/all/cover.1733233636.git.leonro@nvidia.com

--------------------------------------------------------------------------
From Or and Vlad

This patch series introduces flow control for solicited MADs in
the MAD layer, addressing the need to avoid loss caused by insufficient
resources at the receiver side.

Both the client and the server act as receivers - the latter receives
requests, while the former receives responses.
To facilitate this flow control, the series also refactors the MAD code,
improving readability and enabling more straightforward implementation.

Patch #1: Add state machine to MAD layer
Patch #2: Add flow control for solicited MADs
Patch #3: Use separate send-only agent for REPs

The primary goal of this series is to add a flow control mechanism
to the MAD layer, reducing the number of timeouts.
The accompanying refactoring simplifies state management, making
the code more maintainable and supporting the new flow control
logic effectively.

Thanks

Or Har-Toov (2):
  IB/mad: Add state machine to MAD layer
  IB/mad: Add flow control for solicited MADs

Vlad Dumitrescu (1):
  IB/cm: Use separate agent w/o flow control for REP

 drivers/infiniband/core/cm.c       |  47 ++-
 drivers/infiniband/core/mad.c      | 468 ++++++++++++++++++++++-------
 drivers/infiniband/core/mad_priv.h |  76 ++++-
 drivers/infiniband/core/mad_rmpp.c |  41 +--
 4 files changed, 500 insertions(+), 132 deletions(-)

-- 
2.50.0

Re: [PATCH rdma-next v2 0/3] IB/mad: Add Flow Control for Solicited MADs

[Leon Romanovsky]

On Mon, 30 Jun 2025 13:16:41 +0300, Leon Romanovsky wrote:
> Changelog:
> v2:
>  * Add separate send-only agent for REPs to prevent starvation
>    of REPs when runnning both service and client on the same node.
>  * Instead of immediately resending a timed-out MAD, it will now   be
>  * placed in backlog queue if the queue is not empty.
> v1: https://lore.kernel.org/all/cover.1736258116.git.leonro@nvidia.com
>  * Add a cancel state to the state machine which allows removing the
>  * status field in MAD's struct.
>  * Add change_mad_state function which handles all the state transition.
>  * Add WARN_ONs to check MAD states
>  * Reorganize patches to have only two patches in this series instead of
>  * three.
> v0: https://lore.kernel.org/all/cover.1733233636.git.leonro@nvidia.com
> 
> [...]

Applied, thanks!

[1/3] IB/mad: Add state machine to MAD layer
      https://git.kernel.org/rdma/rdma/c/1cf0d8990155c1
[2/3] IB/mad: Add flow control for solicited MADs
      https://git.kernel.org/rdma/rdma/c/314cb74cea847d
[3/3] IB/cm: Use separate agent w/o flow control for REP
      https://git.kernel.org/rdma/rdma/c/8ab05a5456bb95

Best regards,
-- 
Leon Romanovsky <leon@kernel.org>