[PATCH v27 15/20] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration

[Aurelien Aptel]

> Btw, just as a reminder nvme code has to go through the nvme tree, and
> there is absolutely no consesnsus on this feature yet.

The series was acked by Sagi, and the discussion with Jakub is about the
CI (which was just resolved from our side), not about the feature.

Can you please help us to understand the concerns?