Re: [PATCH net-next v11 3/4] net: mana: support concurrent HWC requests
From: Leon Romanovsky
Date: Tue Nov 17 2026 - 13:07:42 EST
On Tue, Nov 17, 2026 at 04:01:00PM +0000, Wei Hu wrote:
> From: Long Li <longli@xxxxxxxxxxxxx>
<...>
> For RDMA, leave live verbs objects and their dependencies intact on local
> rejection. Retain queue mappings on failed creation unwinds, including
> regions already transferred to a QP/CQ handle and partial multi-command
> DMA-region creation. Do not unpin their memory merely because a cleanup
> request could not acquire an HWC slot. This may deliberately retain
> resources on a failed cleanup; it is not proof of device quiescence.
This sounds wrong at first glance. Unfortunately, the entire series was
written using AI tools, making it difficult to provide meaningful feedback
based on the commit messages. However, in RDMA, object destruction should
not fail and we shouldn't leave pinned memory for the user space process
which already exited.
Thanks