On Thu, Apr 05, 2018 at 03:17:17PM -0700, Dan Williams wrote:
> > That means IFF ADR can fail like this we can't treat it as stable
> > storage and we must not support MAP_SYNC or equivalent device dax
> > behavior, period.
> Makes sense, we won't pursue *sync() support on device-dax it doesn't fit.

We still have other bits of this way of thinking in the tree as far as
I can tell, e.g. the nvdimm_flush calls in pmem_make_request and thus
should come up with a coherent strategy if we trust ADR, and if we don't
fully trust it how to mitigate it.
Linux-nvdimm mailing list

Reply via email to