From: "Michael S. Tsirkin" <mst@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@kernel.org>,
Suren Baghdasaryan <surenb@google.com>,
Michal Hocko <mhocko@suse.com>,
Brendan Jackman <jackmanb@google.com>,
Johannes Weiner <hannes@cmpxchg.org>, Zi Yan <ziy@nvidia.com>,
linux-mm@kvack.org
Subject: [PATCH v5 22/28] mm: page_alloc: propagate PG_zeroed in split_large_buddy
Date: Thu, 7 May 2026 18:23:29 -0400 [thread overview]
Message-ID: <b12478e664ffffc8b7466d771bd77275af83cf3f.1778192416.git.mst@redhat.com> (raw)
In-Reply-To: <cover.1778192416.git.mst@redhat.com>
When a large zeroed page is freed with order > pageblock_order,
split_large_buddy splits it into pageblock-sized pieces. Propagate
PG_zeroed from the head page to each sub-block head so the zeroed
hint is not lost.
The propagation reads PageZeroed from the head page (set by
__free_pages_ok before calling free_one_page) rather than from
FPI_ZEROED, to avoid incorrectly marking deferred pages that
share the same code path but may not be zeroed.
For order-0 frees this is a single-iteration no-op (the head
already has the flag). For higher-order frees it ensures all
sub-block heads inherit the zeroed hint.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Assisted-by: Claude:claude-opus-4-6
---
mm/page_alloc.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5c6ab949855a..954d86655f77 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1554,6 +1554,7 @@ static void split_large_buddy(struct zone *zone, struct page *page,
unsigned long pfn, int order, fpi_t fpi)
{
unsigned long end = pfn + (1 << order);
+ bool zeroed = PageZeroed(page);
VM_WARN_ON_ONCE(!IS_ALIGNED(pfn, 1 << order));
/* Caller removed page from freelist, buddy info cleared! */
@@ -1565,6 +1566,8 @@ static void split_large_buddy(struct zone *zone, struct page *page,
do {
int mt = get_pfnblock_migratetype(page, pfn);
+ if (zeroed)
+ __SetPageZeroed(page);
__free_one_page(page, pfn, zone, order, mt, fpi);
pfn += 1 << order;
if (pfn == end)
@@ -1624,8 +1627,11 @@ static void __free_pages_ok(struct page *page, unsigned int order,
unsigned long pfn = page_to_pfn(page);
struct zone *zone = page_zone(page);
- if (__free_pages_prepare(page, order, fpi_flags))
+ if (__free_pages_prepare(page, order, fpi_flags)) {
+ if (fpi_flags & FPI_ZEROED)
+ __SetPageZeroed(page);
free_one_page(zone, page, pfn, order, fpi_flags);
+ }
}
void __meminit __free_pages_core(struct page *page, unsigned int order,
--
MST
next prev parent reply other threads:[~2026-05-07 22:23 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <cover.1778192416.git.mst@redhat.com>
2026-05-07 22:22 ` [PATCH v5 01/28] mm: mempolicy: fix interleave index for unaligned VMA start Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 02/28] mm: thread user_addr through page allocator for cache-friendly zeroing Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 03/28] mm: add folio_zero_user stub for configs without THP/HUGETLBFS Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 04/28] mm: page_alloc: move prep_compound_page before post_alloc_hook Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 05/28] mm: use folio_zero_user for user pages in post_alloc_hook Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 06/28] mm: use __GFP_ZERO in vma_alloc_zeroed_movable_folio Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 07/28] mm: alloc_anon_folio: pass raw fault address to vma_alloc_folio Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 08/28] mm: use __GFP_ZERO in alloc_anon_folio Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 09/28] mm: vma_alloc_anon_folio_pmd: pass raw fault address to vma_alloc_folio Michael S. Tsirkin
2026-05-08 3:36 ` Dev Jain
2026-05-08 5:01 ` Lance Yang
2026-05-08 6:11 ` Michael S. Tsirkin
2026-05-08 6:10 ` Michael S. Tsirkin
2026-05-08 12:10 ` David Hildenbrand (Arm)
2026-05-09 19:32 ` Michael S. Tsirkin
2026-05-08 13:12 ` Lorenzo Stoakes
2026-05-09 19:35 ` Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 10/28] mm: use __GFP_ZERO in vma_alloc_anon_folio_pmd Michael S. Tsirkin
2026-05-07 22:22 ` [PATCH v5 11/28] mm: hugetlb: use __GFP_ZERO and skip zeroing for zeroed pages Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 12/28] mm: memfd: skip zeroing for zeroed hugetlb pool pages Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 14/28] mm: page_reporting: allow driver to set batch capacity Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 15/28] mm: page_alloc: propagate PageReported flag across buddy splits Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 16/28] mm: page_reporting: skip redundant zeroing of host-zeroed reported pages Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 17/28] mm: page_reporting: add per-page zeroed bitmap for host feedback Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 18/28] mm: page_alloc: clear PG_zeroed on buddy merge if not both zero Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 19/28] mm: page_alloc: preserve PG_zeroed in page_del_and_expand Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 21/28] mm: page_reporting: add flush parameter with page budget Michael S. Tsirkin
2026-05-07 22:23 ` Michael S. Tsirkin [this message]
2026-05-07 22:23 ` [PATCH v5 23/28] mm: add free_frozen_pages_zeroed Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 24/28] mm: add put_page_zeroed and folio_put_zeroed Michael S. Tsirkin
2026-05-07 22:23 ` [PATCH v5 26/28] mm: balloon: use put_page_zeroed for zeroed balloon pages 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=b12478e664ffffc8b7466d771bd77275af83cf3f.1778192416.git.mst@redhat.com \
--to=mst@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=jackmanb@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=surenb@google.com \
--cc=vbabka@kernel.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