Re: [PATCH 03/16] mm: add PG_uncached page flag

[Jens Axboe <axboe@kernel.dk>]

On 11/12/24 2:12 AM, Kirill A. Shutemov wrote:
> On Mon, Nov 11, 2024 at 04:37:30PM -0700, Jens Axboe wrote:
>> Add a page flag that file IO can use to indicate that the IO being done
>> is uncached, as in it should not persist in the page cache after the IO
>> has been completed.
> 
> I have not found a way to avoid using a new bit. I am unsure if we have
> enough bits on 32-bit systems with all possible features enabled.

I think it should be OK, at least the kernel test bot reports build
success on all the archs it tests, which has a lot of 32-bit archs. I
have to say I didn't check on numbering and if the mm subsystem has a
BUILD_BUG_ON() for bits exceeding the allowable value for unsigned long
on the host, but I'm assuming it does?

> In the worst-case scenario, we may need to make the feature 64-bit only.
> I believe it should be acceptable as long as userspace is prepared for the
> possibility that RWF_UNCACHED may fail. It is not going to be supported by
> all filesystems anyway.

Right, I would not even see that as a big issue. 32-bit would just see
-EOPNOTSUPP for any fs, even ones that support it on 64-bit archs.

-- 
Jens Axboe