From: David Hildenbrand <david@redhat.com>
To: Minchan Kim <minchan@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>,
John Hubbard <jhubbard@nvidia.com>,
Andrew Morton <akpm@linux-foundation.org>,
syzbot <syzbot+acf65ca584991f3cc447@syzkaller.appspotmail.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
llvm@lists.linux.dev, nathan@kernel.org, ndesaulniers@google.com,
syzkaller-bugs@googlegroups.com, trix@redhat.com,
Matthew Wilcox <willy@infradead.org>,
Stephen Rothwell <sfr@canb.auug.org.au>
Subject: Re: [syzbot] WARNING in follow_hugetlb_page
Date: Sat, 21 May 2022 18:46:27 +0200 [thread overview]
Message-ID: <000a117a-694d-d3a9-a192-14d08d50c884@redhat.com> (raw)
In-Reply-To: <YokVEZbOayed5hBb@google.com>
>>>>>> It should also be noted that hugetlb code sets up the CMA area from which
>>>>>> hugetlb pages can be allocated. This area is never unreserved/freed.
>>>>>>
>>>>>> I do not think there is a reason to disallow long term pinning of hugetlb
>>>>>> pages allocated from THE hugetlb CMA area.
>>
>> Hm. We primarily use CMA for gigantic pages only IIRC. Ordinary huge
>> pages come via the buddy.
>>
>> Assume we allocated a (movable) 2MiB huge page ordinarily via the buddy
>> and it ended up on that CMA area by pure luck (as it's movable). If we'd
>> allow to pin it long-term, allocating a gigantic page from the
>> designated CMA area would fail.
>
> If we allow the longterm pin against the hugetlb page come via buddy,
> it should be migrated out of CMA before the longterm pinning by
> check_and_migrate_movable_pages, IIUC.
Yes.
> If so, what the allocating a giganitc page from the designated CMA area
> would fail?
Nothing I just summarized it.
>
>>
>> So we'd want to allow long-term pinning a gigantic page but we'd not
>> want to allow long-term pinning an ordinary huge page. We'd want to
>> migrate the latter away.
>
> Sure. Gigantic page was already CMA claimed page so there is no user
> in the future to claim the memory again so fine to allow longterm pin
> but ordinary huge page shouldn't be allowed since CMA owner could
> claim the memory some day.
>
Right.
>>
>>
>> The general rules are:
>>
>> ZONE_MOVABLE: nobody is allowed to place unmovable allocations there; it
>> could prevent memory offlining/unplug.
>>
>> CMA: nobody *but the designated owner* is allowed to place unmovable
>> memory there; it could prevent the actual owner to allocate contiguous
>> memory.
>
> I am confused what's the meaning of designated owner and actuall owner
> in your context.
designated==actual here. I just wanted to distinguish from someone
current temporary owner of the page ("allocated it via a movable
allocation") but the actual designated owner (e.g., hugetlb CMA)
The page/memory owner terminology is just confusing. Let's rephrase to:
only the CMA area owner is allowed to place unmovable allocations there.
>
> What I thought about the issue based on you explanation:
>
> HugeTLB allocates its page by two types of allocation
>
> 1. alloc_pages(GFP_MOVABLE)
>
> It could allocate the hugetlb page from CMA area but longterm pin
> should migrate them out of cma before the pinning so allowing
> the pinning on the page is no problem and current code works like
> that.
>
> check_and_migrate_movable_pages
>
Yes.
> 2. cma_alloc
>
> The cma_alloc is used only for *gigantic page* and the hugetlbfs
> is the very owner of the page. IOW, if the hugetlbfs was succeeded
> to allocate the gigantic page by cma_alloc, there is no other
> owner to be able to claim the page any longer so it's fine to
> allow longterm pinning againt the gingantic page but current.
> However, current code doesn't work like that due to
> is_pinnable_page. IOW, hugetlbfs need a way to distinguish
> whether the page owner is hugetlbfs or not.
>
> Are we on same page?
Yes, exactly. What I wanted to express is: for huge pages we have to
make a smarter decision because there are cases where we want to
migrate, and cases where we don't want to migrate.
--
Thanks,
David / dhildenb
next prev parent reply other threads:[~2022-05-21 16:46 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-13 9:03 [syzbot] WARNING in follow_hugetlb_page syzbot
2022-05-13 16:43 ` syzbot
2022-05-13 17:26 ` Andrew Morton
2022-05-13 18:09 ` Mike Kravetz
2022-05-13 22:48 ` Mike Kravetz
2022-05-13 23:19 ` Andrew Morton
2022-05-13 23:54 ` Minchan Kim
2022-05-14 0:09 ` John Hubbard
2022-05-14 0:26 ` Minchan Kim
2022-05-14 0:56 ` John Hubbard
2022-05-14 1:16 ` John Hubbard
2022-05-17 3:37 ` Mike Kravetz
2022-05-18 7:12 ` John Hubbard
2022-05-20 22:19 ` Minchan Kim
2022-05-20 22:56 ` John Hubbard
2022-05-20 23:25 ` Minchan Kim
2022-05-20 23:31 ` Mike Kravetz
2022-05-20 23:43 ` Minchan Kim
2022-05-21 0:04 ` Mike Kravetz
2022-05-21 15:24 ` Minchan Kim
2022-05-21 15:51 ` David Hildenbrand
2022-05-21 16:36 ` Minchan Kim
2022-05-21 16:46 ` David Hildenbrand [this message]
2022-05-21 18:25 ` Minchan Kim
2022-05-21 23:50 ` Mike Kravetz
2022-05-14 0:18 ` Andrew Morton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=000a117a-694d-d3a9-a192-14d08d50c884@redhat.com \
--to=david@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=llvm@lists.linux.dev \
--cc=mike.kravetz@oracle.com \
--cc=minchan@kernel.org \
--cc=nathan@kernel.org \
--cc=ndesaulniers@google.com \
--cc=sfr@canb.auug.org.au \
--cc=syzbot+acf65ca584991f3cc447@syzkaller.appspotmail.com \
--cc=syzkaller-bugs@googlegroups.com \
--cc=trix@redhat.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).