Re: [PATCHv3 0/2] mm: map few pages around fault address if they are in page cache

[Linus Torvalds]

On Thu, Feb 27, 2014 at 6:10 PM, Kirill A. Shutemov
<kirill@xxxxxxxxxxxxx> wrote:
>
> Also Matthew noticed that some drivers do ugly hacks like fault in whole
> VMA on first page fault. IIUC, it's for performance reasons. See
> psbfb_vm_fault() or ttm_bo_vm_fault().

I guarantee it's not for performance reasons, it's probably some other breakage.

And if anything really does want to populate things fully, doing so at
fault time is wrong anyway, you should just use MAP_POPULATE at mmap
time.

So I'll believe the shm/tmpfs issue, and that's "mm internal" anyway.
But random crappy drivers? No way in hell.

               Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/