Also, pushback...

On Mon, 16 Aug 2021 15:49:45 -0700 Mike Kravetz [off-list ref] wrote:

Real world use cases
--------------------
There are groups today using hugetlb pages to back VMs on x86.  Their
use case is as described above.  They have experienced the issues with
performance and not necessarily getting the excepted number smaller huge

("number of")

pages after free/allocate cycle.

It really is a ton of new code.  I think we're owed much more detail
about the problem than the above.  To be confident that all this
material is truly justified?

Also, some selftests and benchmarking code in tools/testing/selftests
would be helpful?