Messages in this thread | | | Date | Wed, 13 Feb 2019 09:13:14 +0100 | From | Oscar Salvador <> | Subject | Re: [PATCH] mm,memory_hotplug: Explicitly pass the head to isolate_huge_page |
| |
On Tue, Feb 12, 2019 at 04:13:05PM -0800, Mike Kravetz wrote: > Well, commit 94310cbcaa3c ("mm/madvise: enable (soft|hard) offline of > HugeTLB pages at PGD level") should have allowed migration of gigantic > pages. I believe it was added for 16GB pages on powerpc. However, due > to subsequent changes I suspsect this no longer works.
I will take a look, I am definitely interested in that. Thanks for pointing it out Mike.
> > > This check doesn't make much sense in principle. Why should we bail out > > based on a section size? We are offlining a pfn range. All that we care > > about is whether the hugetlb is migrateable. > > Yes. Do note that the do_migrate_range is only called from __offline_pages > with a start_pfn that was returned by scan_movable_pages. scan_movable_pages > has the hugepage_migration_supported check for PageHuge pages. So, it would > seem to be redundant to do another check in do_migrate_range.
Well, the thing is that if the gigantic page does not start at the very beginning of the memblock, and we do find migrateable pages before it in scan_movable_pages(), the range that we will pass to do_migrate_ranges() will contain the gigantic page. So we need the check there to cover that case too, although I agree that the current check is misleading.
I will think about it.
-- Oscar Salvador SUSE L3
| |