Re: [RFC PATCH] nvme: add an opt-in to use AWUPF

[John Garry]

On 21/08/2025 09:35, Christoph Hellwig wrote:
> > +	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry)
> > +		nvme_queue_scan(tmp);
> queueing a full rescan here seems expensive.  What about just keeping
> the awupf value in our internal data structures and always use it
> for the physical block size calculation,

is that even ok? physical block size implies atomicity also.

> but only apply it to the
> atomic limits based on a flag?

We have flag BLK_FEAT_ATOMIC_WRITES, which could be used, but in 
blk_validate_atomic_write_limits() we zero the hw limits if that flag is 
unset. So we need to fill in the hw limits like in this patch.