[dm-devel] [PATCH 0/6] dax poison recovery with RWF_RECOVERY_DATA flag

[Matthew Wilcox]

On Thu, Nov 04, 2021 at 01:30:48AM -0700, Christoph Hellwig wrote:
> Well, the whole problem is that we should not have to manage this at
> all, and this is where I blame Intel.  There is no good reason to not
> slightly overprovision the nvdimms and just do internal bad page
> remapping like every other modern storage device.

What makes you think they don't?

The problem is persuading the CPU to do writes without doing reads.
That's where magic instructions or out of band IO is needed.