linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Brian Geffon <bgeffon@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>,
	Lokesh Gidra <lokeshgidra@google.com>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>,
	Peter Xu <peterx@redhat.com>, Hugh Dickins <hughd@google.com>,
	"Michael S . Tsirkin" <mst@redhat.com>,
	Brian Geffon <bgeffon@google.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Andy Lutomirski <luto@amacapital.net>,
	Vlastimil Babka <vbabka@suse.cz>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Sonny Rao <sonnyrao@google.com>, Minchan Kim <minchan@kernel.org>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	Dmitry Safonov <dima@arista.com>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Alejandro Colomar <alx.manpages@gmail.com>
Subject: [PATCH v4 1/3] mm: Extend MREMAP_DONTUNMAP to non-anonymous mappings
Date: Tue, 23 Mar 2021 09:26:08 -0700	[thread overview]
Message-ID: <20210323162611.2398613-1-bgeffon@google.com> (raw)
In-Reply-To: <20210303175235.3308220-1-bgeffon@google.com>

Currently MREMAP_DONTUNMAP only accepts private anonymous mappings.
This restriction was placed initially for simplicity and not because
there exists a technical reason to do so.

This change will widen the support to include any mappings which are not
VM_DONTEXPAND or VM_PFNMAP. The primary use case is to support
MREMAP_DONTUNMAP on mappings which may have been created from a memfd.
This change will result in mremap(MREMAP_DONTUNMAP) returning -EINVAL
if VM_DONTEXPAND or VM_PFNMAP mappings are specified.

Lokesh Gidra who works on the Android JVM, provided an explanation of how
such a feature will improve Android JVM garbage collection:
"Android is developing a new garbage collector (GC), based on userfaultfd.
The garbage collector will use userfaultfd (uffd) on the java heap during
compaction. On accessing any uncompacted page, the application threads will
find it missing, at which point the thread will create the compacted page
and then use UFFDIO_COPY ioctl to get it mapped and then resume execution.
Before starting this compaction, in a stop-the-world pause the heap will be
mremap(MREMAP_DONTUNMAP) so that the java heap is ready to receive
UFFD_EVENT_PAGEFAULT events after resuming execution.

To speedup mremap operations, pagetable movement was optimized by moving
PUD entries instead of PTE entries [1]. It was necessary as mremap of even
modest sized memory ranges also took several milliseconds, and stopping the
application for that long isn't acceptable in response-time sensitive
cases.

With UFFDIO_CONTINUE feature [2], it will be even more efficient to
implement this GC, particularly the 'non-moveable' portions of the heap.
It will also help in reducing the need to copy (UFFDIO_COPY) the pages.
However, for this to work, the java heap has to be on a 'shared' vma.
Currently MREMAP_DONTUNMAP only supports private anonymous mappings, this
patch will enable using UFFDIO_CONTINUE for the new userfaultfd-based heap
compaction."

[1] https://lore.kernel.org/linux-mm/20201215030730.NC3CU98e4%25akpm@linux-foundation.org/
[2] https://lore.kernel.org/linux-mm/20210302000133.272579-1-axelrasmussen@google.com/

Signed-off-by: Brian Geffon <bgeffon@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Tested-by: Lokesh Gidra <lokeshgidra@google.com>
---
 mm/mremap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index ec8f840399ed..db5b8b28c2dd 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -653,8 +653,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (flags & MREMAP_DONTUNMAP && (!vma_is_anonymous(vma) ||
-			vma->vm_flags & VM_SHARED))
+	if ((flags & MREMAP_DONTUNMAP) &&
+			(vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)))
 		return ERR_PTR(-EINVAL);
 
 	if (is_vm_hugetlb_page(vma))
-- 
2.31.0.rc2.261.g7f71774620-goog


  parent reply	other threads:[~2021-03-23 16:27 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-03 17:52 [PATCH] mm: Allow shmem mappings with MREMAP_DONTUNMAP Brian Geffon
2021-03-03 18:13 ` Brian Geffon
2021-03-03 19:04   ` Lokesh Gidra
2021-03-14  4:19 ` Hugh Dickins
2021-03-16 19:18   ` Brian Geffon
2021-03-16 19:31     ` Dmitry Safonov
2021-03-16 20:17   ` Peter Xu
2021-03-19  1:58     ` Hugh Dickins
2021-03-17 19:13 ` [PATCH v2 1/2] mm: Allow non-VM_DONTEXPAND and VM_PFNMAP " Brian Geffon
2021-03-17 19:13   ` [PATCH v2 2/2] Revert "mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio" Brian Geffon
2021-03-17 20:40   ` [PATCH v2 1/2] mm: Allow non-VM_DONTEXPAND and VM_PFNMAP mappings with MREMAP_DONTUNMAP Peter Xu
2021-03-17 20:44     ` Brian Geffon
2021-03-17 21:18       ` Peter Xu
2021-03-17 21:25         ` Brian Geffon
2021-03-17 21:41 ` [PATCH v3 " Brian Geffon
2021-03-17 21:41   ` [PATCH v3 2/2] Revert "mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio" Brian Geffon
2021-03-19  1:28     ` Hugh Dickins
2021-03-17 22:03   ` [PATCH v3 1/2] mm: Allow non-VM_DONTEXPAND and VM_PFNMAP mappings with MREMAP_DONTUNMAP Andrew Morton
2021-03-19  1:20   ` Hugh Dickins
2021-03-23 16:26 ` Brian Geffon [this message]
2021-03-23 16:26   ` [PATCH v4 2/3] Revert "mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio" Brian Geffon
2021-03-23 18:16     ` Hugh Dickins
2021-03-23 16:26   ` [PATCH v4 3/3] selftests: Add a MREMAP_DONTUNMAP selftest for shmem Brian Geffon
2021-03-23 16:26   ` [PATCH] mremap.2: MREMAP_DONTUNMAP to reflect to supported mappings Brian Geffon
2021-03-23 18:25 ` [PATCH v5 1/3] mm: Extend MREMAP_DONTUNMAP to non-anonymous mappings Brian Geffon
2021-03-23 18:25   ` [PATCH v5 2/3] Revert "mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio" Brian Geffon
2021-03-23 19:05     ` Dmitry Safonov
2021-03-23 18:25   ` [PATCH v5 3/3] selftests: Add a MREMAP_DONTUNMAP selftest for shmem Brian Geffon
2021-03-23 18:25   ` [PATCH] mremap.2: MREMAP_DONTUNMAP to reflect to supported mappings Brian Geffon
2021-03-25 21:34     ` Alejandro Colomar (man-pages)
2021-03-26 18:08       ` Brian Geffon
2022-05-10 20:50         ` Brian Geffon
2021-03-23 19:04   ` [PATCH v5 1/3] mm: Extend MREMAP_DONTUNMAP to non-anonymous mappings Dmitry Safonov

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=20210323162611.2398613-1-bgeffon@google.com \
    --to=bgeffon@google.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alx.manpages@gmail.com \
    --cc=axelrasmussen@google.com \
    --cc=dima@arista.com \
    --cc=hughd@google.com \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lokeshgidra@google.com \
    --cc=luto@amacapital.net \
    --cc=minchan@kernel.org \
    --cc=mst@redhat.com \
    --cc=mtk.manpages@gmail.com \
    --cc=peterx@redhat.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=sonnyrao@google.com \
    --cc=vbabka@suse.cz \
    /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).