On Fri, May 15, 2015 at 07:57:39AM -0700, Dave Hansen wrote:
> On 05/15/2015 04:18 AM, Kirill A. Shutemov wrote:
> >> > But same question about whether it should be using hpage_nr_pages() instead
> >> > of a constant.
> > No. Compiler woundn't be able to optimize HPAGE_PMD_NR away for THP=n,
> > since compound value cross compilation unit barrier.
>
> What code are you talking about here, specifically? This?
>
> static inline int hpage_nr_pages(struct page *page)
> {
> if (unlikely(PageTransHuge(page)))
> return HPAGE_PMD_NR;
> return 1;
> }
No. See for instance mem_cgroup_try_charge(). Vlastimil would like to
replace hpage_nr_pages() call with plain HPAGE_PMD_NR.
--
Kirill A. Shutemov
--
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>