From: David Hildenbrand <david@redhat.com>
To: Mike Kravetz <mike.kravetz@oracle.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Michal Hocko <mhocko@suse.com>,
Naoya Horiguchi <naoya.horiguchi@linux.dev>,
Axel Rasmussen <axelrasmussen@google.com>,
Peter Xu <peterx@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Mina Almasry <almasrymina@google.com>,
Shuah Khan <shuah@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [RFC PATCH 0/3] Add hugetlb MADV_DONTNEED support
Date: Fri, 28 Jan 2022 10:55:00 +0100 [thread overview]
Message-ID: <2ddd0a26-33fd-9cde-3501-f0584bbffefc@redhat.com> (raw)
In-Reply-To: <21242c94-6748-b76d-f38e-5ac140c6117b@oracle.com>
On 27.01.22 18:55, Mike Kravetz wrote:
> On 1/27/22 03:57, David Hildenbrand wrote:
>> On 13.01.22 19:03, Mike Kravetz wrote:
>>> Userfaultfd selftests for hugetlb does not perform UFFD_EVENT_REMAP
>>> testing. However, mremap support was recently added in commit
>>> 550a7d60bd5e ("mm, hugepages: add mremap() support for hugepage backed
>>> vma"). While attempting to enable mremap support in the test, it was
>>> discovered that the mremap test indirectly depends on MADV_DONTNEED.
>>>
>>> hugetlb does not support MADV_DONTNEED. However, the only thing
>>> preventing support is a check in can_madv_lru_vma(). Simply removing
>>> the check will enable support.
>>>
>>> This is sent as a RFC because there is no existing use case calling
>>> for hugetlb MADV_DONTNEED support except possibly the userfaultfd test.
>>> However, adding support makes sense as it is fairly trivial and brings
>>> hugetlb functionality more in line with 'normal' memory.
>>>
>>
>> Just a note:
>>
>> QEMU doesn't use huge anonymous memory directly (MAP_ANON | MAP_HUGE...)
>> but instead always goes either via hugetlbfs or via memfd.
>>
>> For MAP_PRIVATE hugetlb mappings, fallocate(FALLOC_FL_PUNCH_HOLE) seems
>> to get the job done (IOW: also discards private anon pages). See the
>> comments in the QEMU code below. I remember that that is somewhat
>> inconsistent. For ordinary MAP_PRIVATE mapped files I remember that we
>> always need fallocate(FALLOC_FL_PUNCH_HOLE) + madvise(QEMU_MADV_DONTNEED)
>> to make sure
>>
>> a) All file pages are removed
>> b) All private anon pages are removed
>>
>> IIRC hugetlbfs really is different in that regard, but maybe other fs
>> behave similarly.
>
> Yes it is really different. And, some might even consider that a bug?
> Imagine if those private anon (COW) pages contain important data. They
> could be unmapped/freed by some other process that has write access to
> the hugetlb file on which the private mapping is based.
Right, that's also what I once worried about in QEMU code. But then I
realized that any kind of fallocate(FALLOC_FL_PUNCH_HOLE) on a file
shared by multiple parties mapped MAP_PRIVATE might be bogus already.
Assume you have a VM running with MAP_SHARED on a file. The file
contains the VM memory state. Assume you pause the VM and want to
convert it into 2 instances that will continue running independently
based on the captured file state.
You'd have to MAP_PRIVATE the file such that both VMs start with the
original state and only see their modifications.
... but if one process decides to fallocate(FALLOC_FL_PUNCH_HOLE), for
example, due to memory ballooning, even a page that's still shared by
both processes (!COW), you'd corrupt the other VM.
So my assumption is that MAP_PRIVATE in combination with
fallocate(FALLOC_FL_PUNCH_HOLE) on a file mapped by more than one
process is just bogus already.
>
> I believe this same issue exists for hugetlbfs ftruncate. When fallocate
> hole punch support was added, it was based on the ftruncate functionality.
>
> I am hesitant to change the behavior of hugetlb hole punch or truncate
> as people may be relying on that behavior today. Your QEMU example is
> one such case.
Yes, I assume we're stuck with that.
--
Thanks,
David / dhildenb
prev parent reply other threads:[~2022-01-28 9:55 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-13 18:03 [RFC PATCH 0/3] Add hugetlb MADV_DONTNEED support Mike Kravetz
2022-01-13 18:03 ` [RFC PATCH 1/3] mm: enable MADV_DONTNEED for hugetlb mappings Mike Kravetz
2022-01-27 2:58 ` Naoya Horiguchi
2022-01-27 3:19 ` Mike Kravetz
2022-01-13 18:03 ` [RFC PATCH 2/3] selftests/vm: add hugetlb madvise MADV_DONTNEED MADV_REMOVE test Mike Kravetz
2022-01-13 18:03 ` [RFC PATCH 3/3] userfaultfd/selftests: enable huegtlb remap and remove event testing Mike Kravetz
2022-01-27 11:57 ` [RFC PATCH 0/3] Add hugetlb MADV_DONTNEED support David Hildenbrand
2022-01-27 17:52 ` Axel Rasmussen
2022-01-28 9:44 ` David Hildenbrand
2022-01-27 17:55 ` Mike Kravetz
2022-01-28 9:55 ` David Hildenbrand [this message]
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=2ddd0a26-33fd-9cde-3501-f0584bbffefc@redhat.com \
--to=david@redhat.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=almasrymina@google.com \
--cc=axelrasmussen@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=naoya.horiguchi@linux.dev \
--cc=peterx@redhat.com \
--cc=shuah@kernel.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).