Re: [PATCH v2] RDMA/rtrs-clt: Fix recv repost to satisfy ib_drain_rq

[sashiko-bot@kernel.org]

> From: Quanye Yang <quanyeyang@proton.me>
> 
> On disconnect the client error recovery path calls ib_drain_qp(), which
> requires one free RQ slot and that no recv WQEs are posted while the
> queue is being drained.
> 
> When the server is loaded with always_invalidate=N, the path does not
> advertise RTRS_MSG_NEW_RKEY_F.  A client-requested invalidation is then
> a standalone SEND_WITH_INV.  The recv completion path did not repost
> that WQE; it posted two empty recv WQEs later, when the RDMA-with-IMM
> response carried RTRS_IO_RSP_W_INV_IMM.  If the invalidate receive
> never arrived, each such response increased RQ occupancy by one until
> ib_post_recv() started returning -ENOMEM and __ib_drain_rq() failed
> with:
> 
>   failed to drain recv queue: -12
> 
> Repost one empty recv WQE for every receive completion, including
> SEND_WITH_INV completions on the always_invalidate=N path, and only
> while the path is still connected so CQ polling cannot race with
> ib_drain_qp().  Size IO connection RQs to 2 * queue_depth + 1 to match
> the posted recv count and leave the drain slot.
> 
> Tested with a synthetic RTRS client flooding unpaired
> RTRS_IO_RSP_W_INV_IMM messages; error recovery no longer triggers
> __ib_drain_rq() warnings.
> 
> Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality")
> Signed-off-by: Quanye Yang <quanyeyang@proton.me>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261005-rtrs-fix-ib-drain-rq-v2-1-35535a3ed115@proton.me?part=1