On Wed, Jun 12, 2024 at 01:27:47PM -0400, Martin K. Petersen wrote:

quoted

quoted

quoted

Note that unlike the NOCHECK flag which I just cleaned up because they
were unused, this one actually does get in the way of the architecture
of the whole series :( We could add a per-bip csum_type but it would
feel really weird.

Why would it feel weird? That's how it currently works.

Because there's no way to have it set to anything but the per-queue
one.

That's what the io_uring passthrough changes enable.

The checksum type?  How is that compatible with nvme?

Anyway, I'll just leave this flag in for the resend, but if we can't
come up with a coherent user for it in a merge cycle or two (which
I very much doubt) I'll send another patch to remove it.