From: Dan Williams [mailto:firstname.lastname@example.org]
Sent: Tuesday, April 14, 2015 11:34 AM
To: Elliott, Robert (Server Storage)
>> Since it's directly mapped it should just work for most things if it's
>> at least write-through cached (UC would be a horror), and it would
>> also solve all the size problems. With write-through caching it should
>> also be pretty OK performance-wise. The 64 bytes size is ideal as
> Are the WT support patches going to make it into 4.1?
Which patches are these? Maybe I missed them, but I don't see
anything in the archives.
These have been baking in linux-mm and linux-next:
* [PATCH v3 0/6] Kernel huge I/O mapping support
* [PATCH v4 0/7] mtrr, mm, x86: Enhance MTRR checks for huge I/O mapping
I don't think this made it into a subsystem tree yet:
* [PATCH v8 0/7] Support Write-Through mapping on x86
I guess we could target 4.2 for both the WT series and
pmem patches that support the new ioremap_wt() function.
Robert Elliott, HP Server Storage