public inbox for linux-mm@kvack.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Zi Yan <ziy@nvidia.com>
Cc: linux-kernel@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@kernel.org>,
	Vlastimil Babka <vbabka@kernel.org>,
	Brendan Jackman <jackmanb@google.com>,
	Michal Hocko <mhocko@suse.com>,
	Suren Baghdasaryan <surenb@google.com>,
	Jason Wang <jasowang@redhat.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Gregory Price <gourry@gourry.net>,
	linux-mm@kvack.org, virtualization@lists.linux.dev,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Mike Rapoport <rppt@kernel.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Matthew Wilcox <willy@infradead.org>
Subject: Re: [PATCH RFC v4 14/22] mm: page_reporting: skip redundant zeroing of host-zeroed reported pages
Date: Mon, 27 Apr 2026 11:18:00 -0400	[thread overview]
Message-ID: <20260427111724-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <DI419PSP5050.15VGMJFDMWBQU@nvidia.com>

On Mon, Apr 27, 2026 at 11:13:44AM -0400, Zi Yan wrote:
> On Sun Apr 26, 2026 at 5:48 PM EDT, Michael S. Tsirkin wrote:
> > When a guest reports free pages to the hypervisor via the page reporting
> > framework (used by virtio-balloon and hv_balloon), the host typically
> > zeros those pages when reclaiming their backing memory.  However, when
> > those pages are later allocated in the guest, post_alloc_hook()
> > unconditionally zeros them again if __GFP_ZERO is set.  This
> > double-zeroing is wasteful, especially for large pages.
> >
> > Avoid redundant zeroing:
> >
> > - Add a host_zeroes_pages flag to page_reporting_dev_info, allowing
> >   drivers to declare that their host zeros reported pages on reclaim.
> >   A static key (page_reporting_host_zeroes) gates the fast path.
> >
> > - Add PG_zeroed page flag (sharing PG_private bit) to mark pages
> >   that have been zeroed by the host.  Set it on reported pages during
> >   allocation from the buddy in page_del_and_expand().
> >
> > - Thread the zeroed bool through rmqueue -> prep_new_page ->
> >   post_alloc_hook, where it skips redundant zeroing for __GFP_ZERO
> >   allocations.
> >
> > No driver sets host_zeroes_pages yet; a follow-up patch to
> > virtio_balloon is needed to opt in.
> >
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> > Assisted-by: Claude:claude-opus-4-6
> > Assisted-by: cursor-agent:GPT-5.4-xhigh
> > ---
> >  include/linux/page-flags.h     |  9 +++++
> >  include/linux/page_reporting.h |  3 ++
> >  mm/compaction.c                |  6 ++--
> >  mm/internal.h                  |  2 +-
> >  mm/page_alloc.c                | 66 +++++++++++++++++++++++-----------
> >  mm/page_reporting.c            | 14 +++++++-
> >  mm/page_reporting.h            | 12 +++++++
> >  7 files changed, 87 insertions(+), 25 deletions(-)
> >
> > diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> > index f7a0e4af0c73..eef2499cba8b 100644
> > --- a/include/linux/page-flags.h
> > +++ b/include/linux/page-flags.h
> > @@ -135,6 +135,8 @@ enum pageflags {
> >  	PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */
> >  	/* Some filesystems */
> >  	PG_checked = PG_owner_priv_1,
> > +	/* Page contents are known to be zero */
> > +	PG_zeroed = PG_private,
> 
> +willy,
> 
> I was discussing with willy and David about removing PG_private and
> repurposing it to PG_folio to identify folios. IIUC, PG_zeroed is only
> set for PageBuddy, so it should not be an issue to set it for allocated
> pages for folio identification. Let me know if I get it wrong.
> 
> Thanks.
> 
> -- 
> Best Regards,
> Yan, Zi


Exactly. Trivial to switch to another bit, of course - most are
unused in the buddy.

-- 
MST



  reply	other threads:[~2026-04-27 15:25 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-26 21:47 [PATCH RFC v4 00/22] mm/virtio: skip redundant zeroing of host-zeroed reported pages Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 01/22] mm: move vma_alloc_folio to page_alloc.c Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 02/22] mm: add vma_alloc_folio_user_addr Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 03/22] mm: thread user_addr through page allocator for cache-friendly zeroing Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 04/22] mm: add folio_zero_user stub for configs without THP/HUGETLBFS Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 05/22] mm: page_alloc: move prep_compound_page before post_alloc_hook Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 06/22] mm: use folio_zero_user for user pages in post_alloc_hook Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 07/22] mm: use __GFP_ZERO in vma_alloc_zeroed_movable_folio Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 08/22] mm: use __GFP_ZERO in alloc_anon_folio Michael S. Tsirkin
2026-04-26 21:47 ` [PATCH RFC v4 09/22] mm: use __GFP_ZERO in vma_alloc_anon_folio_pmd Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 10/22] mm: hugetlb: use __GFP_ZERO and skip zeroing for zeroed pages Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 11/22] mm: memfd: skip zeroing for zeroed hugetlb pool pages Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 12/22] mm: remove arch vma_alloc_zeroed_movable_folio overrides Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 13/22] mm: page_alloc: propagate PageReported flag across buddy splits Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 14/22] mm: page_reporting: skip redundant zeroing of host-zeroed reported pages Michael S. Tsirkin
2026-04-27 15:13   ` Zi Yan
2026-04-27 15:18     ` Michael S. Tsirkin [this message]
2026-04-27 15:43     ` David Hildenbrand (Arm)
2026-04-26 21:48 ` [PATCH RFC v4 15/22] mm: page_alloc: clear PG_zeroed on buddy merge if not both zero Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 16/22] mm: page_alloc: preserve PG_zeroed in page_del_and_expand Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 17/22] mm: page_reporting: add per-page zeroed bitmap for host feedback Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 18/22] virtio_balloon: a hack to enable host-zeroed page optimization Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 19/22] mm: page_reporting: add flush parameter with page budget Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 20/22] mm: add free_frozen_pages_zeroed Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 21/22] mm: add put_page_zeroed and folio_put_zeroed Michael S. Tsirkin
2026-04-26 21:48 ` [PATCH RFC v4 22/22] virtio_balloon: mark deflated pages as zeroed Michael S. Tsirkin

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=20260427111724-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@kernel.org \
    --cc=gourry@gourry.net \
    --cc=hannes@cmpxchg.org \
    --cc=jackmanb@google.com \
    --cc=jasowang@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@suse.com \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=virtualization@lists.linux.dev \
    --cc=willy@infradead.org \
    --cc=ziy@nvidia.com \
    /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