From: Kiryl Shutsemau <kas@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>,
Muchun Song <muchun.song@linux.dev>,
David Hildenbrand <david@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
Usama Arif <usamaarif642@gmail.com>,
Frank van der Linden <fvdl@google.com>
Cc: Oscar Salvador <osalvador@suse.de>,
Mike Rapoport <rppt@kernel.org>, Vlastimil Babka <vbabka@suse.cz>,
Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
Zi Yan <ziy@nvidia.com>, Baoquan He <bhe@redhat.com>,
Michal Hocko <mhocko@suse.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Jonathan Corbet <corbet@lwn.net>,
kernel-team@meta.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
Kiryl Shutsemau <kas@kernel.org>
Subject: [PATCHv2 10/14] mm: Drop fake head checks
Date: Thu, 18 Dec 2025 15:09:41 +0000 [thread overview]
Message-ID: <20251218150949.721480-11-kas@kernel.org> (raw)
In-Reply-To: <20251218150949.721480-1-kas@kernel.org>
With fake head pages eliminated in the previous commit, remove the
supporting infrastructure:
- page_fixed_fake_head(): no longer needed to detect fake heads;
- page_is_fake_head(): no longer needed;
- page_count_writable(): no longer needed for RCU protection;
- RCU read_lock in page_ref_add_unless(): no longer needed;
This substantially simplifies compound_head() and page_ref_add_unless(),
removing both branches and RCU overhead from these hot paths.
Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
---
include/linux/page-flags.h | 96 ++------------------------------------
include/linux/page_ref.h | 8 +---
2 files changed, 4 insertions(+), 100 deletions(-)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index fac5f41b3b27..9d89beed9df6 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -198,105 +198,15 @@ enum pageflags {
#ifndef __GENERATING_BOUNDS_H
-#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key);
-/*
- * Return the real head page struct iff the @page is a fake head page, otherwise
- * return the @page itself. See Documentation/mm/vmemmap_dedup.rst.
- */
-static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
-{
- if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
- return page;
-
- /*
- * Fake heads only exists if size of struct page is power-of-2.
- * See hugetlb_vmemmap_optimizable_size().
- */
- if (!is_power_of_2(sizeof(struct page)))
- return page;
-
- /*
- * Only addresses aligned with PAGE_SIZE of struct page may be fake head
- * struct page. The alignment check aims to avoid access the fields (
- * e.g. compound_info) of the @page[1]. It can avoid touch a (possibly)
- * cold cacheline in some cases.
- */
- if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) &&
- test_bit(PG_head, &page->flags.f)) {
- /*
- * We can safely access the field of the @page[1] with PG_head
- * because the @page is a compound page composed with at least
- * two contiguous pages.
- */
- unsigned long info = READ_ONCE(page[1].compound_info);
-
- /* See set_compound_head() */
- if (likely(info & 1)) {
- unsigned long p = (unsigned long)page;
-
- return (const struct page *)(p & info);
- }
- }
- return page;
-}
-
-static __always_inline bool page_count_writable(const struct page *page, int u)
-{
- if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
- return true;
-
- /*
- * The refcount check is ordered before the fake-head check to prevent
- * the following race:
- * CPU 1 (HVO) CPU 2 (speculative PFN walker)
- *
- * page_ref_freeze()
- * synchronize_rcu()
- * rcu_read_lock()
- * page_is_fake_head() is false
- * vmemmap_remap_pte()
- * XXX: struct page[] becomes r/o
- *
- * page_ref_unfreeze()
- * page_ref_count() is not zero
- *
- * atomic_add_unless(&page->_refcount)
- * XXX: try to modify r/o struct page[]
- *
- * The refcount check also prevents modification attempts to other (r/o)
- * tail pages that are not fake heads.
- */
- if (atomic_read_acquire(&page->_refcount) == u)
- return false;
-
- return page_fixed_fake_head(page) == page;
-}
-#else
-static inline const struct page *page_fixed_fake_head(const struct page *page)
-{
- return page;
-}
-
-static inline bool page_count_writable(const struct page *page, int u)
-{
- return true;
-}
-#endif
-
-static __always_inline int page_is_fake_head(const struct page *page)
-{
- return page_fixed_fake_head(page) != page;
-}
-
static __always_inline unsigned long _compound_head(const struct page *page)
{
unsigned long info = READ_ONCE(page->compound_info);
/* Bit 0 encodes PageTail() */
if (!(info & 1))
- return (unsigned long)page_fixed_fake_head(page);
+ return (unsigned long)page;
/*
* If the size of struct page is not power-of-2, the rest of
@@ -378,7 +288,7 @@ static __always_inline void clear_compound_head(struct page *page)
static __always_inline int PageTail(const struct page *page)
{
- return READ_ONCE(page->compound_info) & 1 || page_is_fake_head(page);
+ return READ_ONCE(page->compound_info) & 1;
}
static __always_inline int PageCompound(const struct page *page)
@@ -905,7 +815,7 @@ static __always_inline bool folio_test_head(const struct folio *folio)
static __always_inline int PageHead(const struct page *page)
{
PF_POISONED_CHECK(page);
- return test_bit(PG_head, &page->flags.f) && !page_is_fake_head(page);
+ return test_bit(PG_head, &page->flags.f);
}
__SETPAGEFLAG(Head, head, PF_ANY)
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 544150d1d5fd..490d0ad6e56d 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -230,13 +230,7 @@ static inline int folio_ref_dec_return(struct folio *folio)
static inline bool page_ref_add_unless(struct page *page, int nr, int u)
{
- bool ret = false;
-
- rcu_read_lock();
- /* avoid writing to the vmemmap area being remapped */
- if (page_count_writable(page, u))
- ret = atomic_add_unless(&page->_refcount, nr, u);
- rcu_read_unlock();
+ bool ret = atomic_add_unless(&page->_refcount, nr, u);
if (page_ref_tracepoint_active(page_ref_mod_unless))
__page_ref_mod_unless(page, nr, ret);
--
2.51.2
next prev parent reply other threads:[~2025-12-18 15:10 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-12-18 15:09 [PATCHv2 00/14] Kiryl Shutsemau
2025-12-18 15:09 ` [PATCHv2 01/14] mm: Move MAX_FOLIO_ORDER definition to mmzone.h Kiryl Shutsemau
2025-12-18 15:09 ` [PATCHv2 02/14] mm/sparse: Check memmap alignment Kiryl Shutsemau
2025-12-22 8:34 ` Muchun Song
2025-12-22 14:02 ` Kiryl Shutsemau
2025-12-22 14:18 ` David Hildenbrand (Red Hat)
2025-12-22 14:52 ` Kiryl Shutsemau
2025-12-22 14:59 ` Muchun Song
2025-12-22 14:55 ` Muchun Song
2025-12-23 9:38 ` David Hildenbrand (Red Hat)
2025-12-23 11:26 ` Muchun Song
2025-12-24 14:13 ` Kiryl Shutsemau
2026-01-07 23:08 ` David Hildenbrand (Red Hat)
2026-01-08 12:32 ` Kiryl Shutsemau
2026-01-08 13:30 ` Kiryl Shutsemau
2026-01-09 9:40 ` Muchun Song
2026-01-09 15:24 ` David Hildenbrand (Red Hat)
2026-01-09 21:48 ` Matthew Wilcox
2026-01-13 10:24 ` David Hildenbrand (Red Hat)
2025-12-22 14:49 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 03/14] mm: Change the interface of prep_compound_tail() Kiryl Shutsemau
2025-12-22 2:55 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 04/14] mm: Rename the 'compound_head' field in the 'struct page' to 'compound_info' Kiryl Shutsemau
2025-12-22 3:00 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 05/14] mm: Move set/clear_compound_head() next to compound_head() Kiryl Shutsemau
2025-12-22 3:06 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 06/14] mm: Rework compound_head() for power-of-2 sizeof(struct page) Kiryl Shutsemau
2025-12-22 3:20 ` Muchun Song
2025-12-22 14:03 ` Kiryl Shutsemau
2025-12-23 8:37 ` Muchun Song
2025-12-22 7:57 ` Muchun Song
2025-12-22 9:45 ` Muchun Song
2025-12-22 14:49 ` Kiryl Shutsemau
2025-12-18 15:09 ` [PATCHv2 07/14] mm: Make page_zonenum() use head page Kiryl Shutsemau
2025-12-18 15:09 ` [PATCHv2 08/14] mm/hugetlb: Refactor code around vmemmap_walk Kiryl Shutsemau
2025-12-22 5:54 ` Muchun Song
2025-12-22 15:00 ` Kiryl Shutsemau
2025-12-22 15:11 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 09/14] mm/hugetlb: Remove fake head pages Kiryl Shutsemau
2025-12-22 15:46 ` kernel test robot
2025-12-18 15:09 ` Kiryl Shutsemau [this message]
2025-12-22 5:56 ` [PATCHv2 10/14] mm: Drop fake head checks Muchun Song
2025-12-18 15:09 ` [PATCHv2 11/14] hugetlb: Remove VMEMMAP_SYNCHRONIZE_RCU Kiryl Shutsemau
2025-12-22 6:00 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 12/14] mm/hugetlb: Remove hugetlb_optimize_vmemmap_key static key Kiryl Shutsemau
2025-12-22 6:03 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 13/14] mm: Remove the branch from compound_head() Kiryl Shutsemau
2025-12-22 6:30 ` Muchun Song
2025-12-18 15:09 ` [PATCHv2 14/14] hugetlb: Update vmemmap_dedup.rst Kiryl Shutsemau
2025-12-22 6:20 ` Muchun Song
2025-12-18 22:18 ` [PATCHv2 00/14] Eliminate fake head pages from vmemmap optimization Kiryl Shutsemau
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=20251218150949.721480-11-kas@kernel.org \
--to=kas@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=bhe@redhat.com \
--cc=corbet@lwn.net \
--cc=david@kernel.org \
--cc=fvdl@google.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@meta.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mhocko@suse.com \
--cc=muchun.song@linux.dev \
--cc=osalvador@suse.de \
--cc=rppt@kernel.org \
--cc=usamaarif642@gmail.com \
--cc=vbabka@suse.cz \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.