linux-kernel - Re: [RFC PATCH] mm,memory_hotplug: Unlock 1GB-hugetlb on x86

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190228095535.GX10588@dhcp22.suse.cz>
Date:   Thu, 28 Feb 2019 10:55:35 +0100
From:   Michal Hocko <mhocko@...nel.org>
To:     Oscar Salvador <osalvador@...e.de>
Cc:     linux-mm@...ck.org, linux-kernel@...r.kernel.org, david@...hat.com,
        mike.kravetz@...cle.com
Subject: Re: [RFC PATCH] mm,memory_hotplug: Unlock 1GB-hugetlb on x86_64

On Thu 28-02-19 10:41:08, Oscar Salvador wrote:
> On Thu, Feb 28, 2019 at 10:21:54AM +0100, Michal Hocko wrote:
> > On Thu 21-02-19 10:42:12, Oscar Salvador wrote:
> > [...]
> > > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> > > index d5f7afda67db..04f6695b648c 100644
> > > --- a/mm/memory_hotplug.c
> > > +++ b/mm/memory_hotplug.c
> > > @@ -1337,8 +1337,7 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
> > >  		if (!PageHuge(page))
> > >  			continue;
> > >  		head = compound_head(page);
> > > -		if (hugepage_migration_supported(page_hstate(head)) &&
> > > -		    page_huge_active(head))
> > > +		if (page_huge_active(head))
> > >  			return pfn;
> > >  		skip = (1 << compound_order(head)) - (page - head);
> > >  		pfn += skip - 1;
> > 
> > Is this part correct? Say we have a gigantic page which is migrateable.
> > Now scan_movable_pages would skip it and we will not migrate it, no?
> 
> All non-migrateable hugepages should have been caught in has_unmovable_pages:
> 
> <--
>                 if (PageHuge(page)) {
>                         struct page *head = compound_head(page);
>                         unsigned int skip_pages;
> 
>                         if (!hugepage_migration_supported(page_hstate(head)))
>                                 goto unmovable;
> -->
> 
> So, there is no need to check again for migrateability here, as it is something
> that does not change.
> To put it in another way, all huge pages found in scan_movable_pages() should be
> migrateable.
> In scan_movable_pages() we just need to check whether the hugepage, gigantic or not, is
> in use (aka active) to migrate it.

You seemed to miss my point or I am wrong here. If scan_movable_pages
skips over a hugetlb page then there is nothing to migrate it and it
will stay in the pfn range and the range will not become idle.

-- 
Michal Hocko
SUSE Labs