Re: [LSF/MM TOPIC] Un-addressable device memory and block/fs implications

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 12/13/2016 12:01 PM, James Bottomley wrote:
>> > Second aspect is that even if memory i am dealing with is un
>> > -addressable i still have struct page for it and i want to be able to 
>> > use regular page migration.
> Tmem keeps a struct page ... what's the problem with page migration?
> the fact that tmem locks the page when it's not addressable and you
> want to be able to migrate the page even when it's not addressable?

Hi James,

Why do you say that tmem keeps a 'struct page'?  For instance, its
->put_page operation _takes_ a 'struct page', but that's in the
delete_from_page_cache() path where the page's last reference has been
dropped and it is about to go away.  The role of 'struct page' here is
just to help create a key so that tmem can find the contents later
*without* the original 'struct page'.

Jerome's pages here are a new class of half-crippled 'struct page' which
support more VM features than ZONE_DEVICE pages, but not quite a full
feature set.  It supports (and needs to support) a heck of a lot more VM
features than memory in tmem would, though.


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>



[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]