From: Johannes Weiner <hannes@cmpxchg.org>
To: linux-mm@kvack.org
Cc: Vlastimil Babka <vbabka@suse.cz>, Zi Yan <ziy@nvidia.com>,
David Hildenbrand <david@kernel.org>,
Lorenzo Stoakes <ljs@kernel.org>,
"Liam R. Howlett" <Liam.Howlett@oracle.com>,
Rik van Riel <riel@surriel.com>,
linux-kernel@vger.kernel.org, Johannes Weiner <jweiner@meta.com>
Subject: [RFC 1/2] mm: page_alloc: replace pageblock_flags bitmap with struct pageblock_data
Date: Fri, 3 Apr 2026 15:40:34 -0400 [thread overview]
Message-ID: <20260403194526.477775-2-hannes@cmpxchg.org> (raw)
In-Reply-To: <20260403194526.477775-1-hannes@cmpxchg.org>
From: Johannes Weiner <jweiner@meta.com>
Replace the packed pageblock_flags bitmap with a per-pageblock struct
containing its own flags word. This changes the storage from
NR_PAGEBLOCK_BITS bits per pageblock packed into shared unsigned longs,
to a dedicated unsigned long per pageblock.
The free path looks up migratetype (from pageblock flags) immediately
followed by looking up pageblock ownership. Colocating them in a struct
means this hot path touches one cache line instead of two.
The per-pageblock struct also eliminates all the bit-packing indexing
(pfn_to_bitidx, word selection, intra-word shifts), simplifying the
accessor code.
Memory overhead: 8 bytes per pageblock (one unsigned long). With 2MB
pageblocks on x86_64, that's 4KB per GB -- up from ~0.5-1 bytes per
pageblock with the packed bitmap, but still negligible in absolute terms.
No functional change.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
include/linux/mmzone.h | 15 ++++----
mm/internal.h | 17 +++++++++
mm/mm_init.c | 25 ++++++-------
mm/page_alloc.c | 81 ++++++------------------------------------
mm/sparse.c | 3 +-
5 files changed, 48 insertions(+), 93 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3e51190a55e4..2f202bda5ec6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -916,7 +916,7 @@ struct zone {
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
- unsigned long *pageblock_flags;
+ struct pageblock_data *pageblock_data;
#endif /* CONFIG_SPARSEMEM */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
@@ -1866,9 +1866,6 @@ static inline bool movable_only_nodes(nodemask_t *nodes)
#define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT)
#define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1))
-#define SECTION_BLOCKFLAGS_BITS \
- ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
-
#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE
#endif
@@ -1901,13 +1898,17 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
+struct pageblock_data {
+ unsigned long flags;
+};
+
struct mem_section_usage {
struct rcu_head rcu;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
#endif
/* See declaration of similar field in struct zone */
- unsigned long pageblock_flags[0];
+ struct pageblock_data pageblock_data[];
};
void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
@@ -1960,9 +1961,9 @@ extern struct mem_section **mem_section;
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
-static inline unsigned long *section_to_usemap(struct mem_section *ms)
+static inline struct pageblock_data *section_to_usemap(struct mem_section *ms)
{
- return ms->usage->pageblock_flags;
+ return ms->usage->pageblock_data;
}
static inline struct mem_section *__nr_to_section(unsigned long nr)
diff --git a/mm/internal.h b/mm/internal.h
index cb0af847d7d9..bb0e0b8a4495 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -787,6 +787,23 @@ static inline struct page *find_buddy_page_pfn(struct page *page,
return NULL;
}
+static inline struct pageblock_data *pfn_to_pageblock(const struct page *page,
+ unsigned long pfn)
+{
+#ifdef CONFIG_SPARSEMEM
+ struct mem_section *ms = __pfn_to_section(pfn);
+ unsigned long idx = (pfn & (PAGES_PER_SECTION - 1)) >> pageblock_order;
+
+ return §ion_to_usemap(ms)[idx];
+#else
+ struct zone *zone = page_zone(page);
+ unsigned long idx;
+
+ idx = (pfn - pageblock_start_pfn(zone->zone_start_pfn)) >> pageblock_order;
+ return &zone->pageblock_data[idx];
+#endif
+}
+
extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index df34797691bd..f3751fe6e5c3 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1467,36 +1467,31 @@ void __meminit init_currently_empty_zone(struct zone *zone,
#ifndef CONFIG_SPARSEMEM
/*
- * Calculate the size of the zone->pageblock_flags rounded to an unsigned long
- * Start by making sure zonesize is a multiple of pageblock_order by rounding
- * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
- * round what is now in bits to nearest long in bits, then return it in
- * bytes.
+ * Calculate the size of the zone->pageblock_data array.
+ * Round up the zone size to a pageblock boundary to get the
+ * number of pageblocks, then multiply by the struct size.
*/
static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
{
- unsigned long usemapsize;
+ unsigned long nr_pageblocks;
zonesize += zone_start_pfn & (pageblock_nr_pages-1);
- usemapsize = round_up(zonesize, pageblock_nr_pages);
- usemapsize = usemapsize >> pageblock_order;
- usemapsize *= NR_PAGEBLOCK_BITS;
- usemapsize = round_up(usemapsize, BITS_PER_LONG);
+ nr_pageblocks = round_up(zonesize, pageblock_nr_pages) >> pageblock_order;
- return usemapsize / BITS_PER_BYTE;
+ return nr_pageblocks * sizeof(struct pageblock_data);
}
static void __ref setup_usemap(struct zone *zone)
{
unsigned long usemapsize = usemap_size(zone->zone_start_pfn,
zone->spanned_pages);
- zone->pageblock_flags = NULL;
+ zone->pageblock_data = NULL;
if (usemapsize) {
- zone->pageblock_flags =
+ zone->pageblock_data =
memblock_alloc_node(usemapsize, SMP_CACHE_BYTES,
zone_to_nid(zone));
- if (!zone->pageblock_flags)
- panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n",
+ if (!zone->pageblock_data)
+ panic("Failed to allocate %ld bytes for zone %s pageblock data on node %d\n",
usemapsize, zone->name, zone_to_nid(zone));
}
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2d4b6f1a554e..900a9da2cbeb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -359,52 +359,18 @@ static inline bool _deferred_grow_zone(struct zone *zone, unsigned int order)
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
-/* Return a pointer to the bitmap storing bits affecting a block of pages */
-static inline unsigned long *get_pageblock_bitmap(const struct page *page,
- unsigned long pfn)
-{
-#ifdef CONFIG_SPARSEMEM
- return section_to_usemap(__pfn_to_section(pfn));
-#else
- return page_zone(page)->pageblock_flags;
-#endif /* CONFIG_SPARSEMEM */
-}
-
-static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn)
-{
-#ifdef CONFIG_SPARSEMEM
- pfn &= (PAGES_PER_SECTION-1);
-#else
- pfn = pfn - pageblock_start_pfn(page_zone(page)->zone_start_pfn);
-#endif /* CONFIG_SPARSEMEM */
- return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
-}
-
static __always_inline bool is_standalone_pb_bit(enum pageblock_bits pb_bit)
{
return pb_bit >= PB_compact_skip && pb_bit < __NR_PAGEBLOCK_BITS;
}
-static __always_inline void
-get_pfnblock_bitmap_bitidx(const struct page *page, unsigned long pfn,
- unsigned long **bitmap_word, unsigned long *bitidx)
+static __always_inline unsigned long *
+get_pfnblock_flags_word(const struct page *page, unsigned long pfn)
{
- unsigned long *bitmap;
- unsigned long word_bitidx;
-
-#ifdef CONFIG_MEMORY_ISOLATION
- BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 8);
-#else
- BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
-#endif
BUILD_BUG_ON(__MIGRATE_TYPE_END > MIGRATETYPE_MASK);
VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
- bitmap = get_pageblock_bitmap(page, pfn);
- *bitidx = pfn_to_bitidx(page, pfn);
- word_bitidx = *bitidx / BITS_PER_LONG;
- *bitidx &= (BITS_PER_LONG - 1);
- *bitmap_word = &bitmap[word_bitidx];
+ return &pfn_to_pageblock(page, pfn)->flags;
}
@@ -421,18 +387,14 @@ static unsigned long __get_pfnblock_flags_mask(const struct page *page,
unsigned long pfn,
unsigned long mask)
{
- unsigned long *bitmap_word;
- unsigned long bitidx;
- unsigned long word;
+ unsigned long *flags_word = get_pfnblock_flags_word(page, pfn);
- get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
/*
* This races, without locks, with set_pfnblock_migratetype(). Ensure
* a consistent read of the memory array, so that results, even though
* racy, are not corrupted.
*/
- word = READ_ONCE(*bitmap_word);
- return (word >> bitidx) & mask;
+ return READ_ONCE(*flags_word) & mask;
}
/**
@@ -446,15 +408,10 @@ static unsigned long __get_pfnblock_flags_mask(const struct page *page,
bool get_pfnblock_bit(const struct page *page, unsigned long pfn,
enum pageblock_bits pb_bit)
{
- unsigned long *bitmap_word;
- unsigned long bitidx;
-
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
return false;
- get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
-
- return test_bit(bitidx + pb_bit, bitmap_word);
+ return test_bit(pb_bit, get_pfnblock_flags_word(page, pfn));
}
/**
@@ -493,18 +450,12 @@ get_pfnblock_migratetype(const struct page *page, unsigned long pfn)
static void __set_pfnblock_flags_mask(struct page *page, unsigned long pfn,
unsigned long flags, unsigned long mask)
{
- unsigned long *bitmap_word;
- unsigned long bitidx;
+ unsigned long *flags_word = get_pfnblock_flags_word(page, pfn);
unsigned long word;
- get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
-
- mask <<= bitidx;
- flags <<= bitidx;
-
- word = READ_ONCE(*bitmap_word);
+ word = READ_ONCE(*flags_word);
do {
- } while (!try_cmpxchg(bitmap_word, &word, (word & ~mask) | flags));
+ } while (!try_cmpxchg(flags_word, &word, (word & ~mask) | flags));
}
/**
@@ -516,15 +467,10 @@ static void __set_pfnblock_flags_mask(struct page *page, unsigned long pfn,
void set_pfnblock_bit(const struct page *page, unsigned long pfn,
enum pageblock_bits pb_bit)
{
- unsigned long *bitmap_word;
- unsigned long bitidx;
-
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
return;
- get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
-
- set_bit(bitidx + pb_bit, bitmap_word);
+ set_bit(pb_bit, get_pfnblock_flags_word(page, pfn));
}
/**
@@ -536,15 +482,10 @@ void set_pfnblock_bit(const struct page *page, unsigned long pfn,
void clear_pfnblock_bit(const struct page *page, unsigned long pfn,
enum pageblock_bits pb_bit)
{
- unsigned long *bitmap_word;
- unsigned long bitidx;
-
if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
return;
- get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
-
- clear_bit(bitidx + pb_bit, bitmap_word);
+ clear_bit(pb_bit, get_pfnblock_flags_word(page, pfn));
}
/**
diff --git a/mm/sparse.c b/mm/sparse.c
index b5b2b6f7041b..c9473b9a5c24 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -298,7 +298,8 @@ static void __meminit sparse_init_one_section(struct mem_section *ms,
static unsigned long usemap_size(void)
{
- return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
+ return (1UL << (PFN_SECTION_SHIFT - pageblock_order)) *
+ sizeof(struct pageblock_data);
}
size_t mem_section_usage_size(void)
--
2.53.0
next prev parent reply other threads:[~2026-04-03 19:45 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-03 19:40 [RFC 0/2] mm: page_alloc: pcp buddy allocator Johannes Weiner
2026-04-03 19:40 ` Johannes Weiner [this message]
2026-04-04 1:43 ` [RFC 1/2] mm: page_alloc: replace pageblock_flags bitmap with struct pageblock_data Rik van Riel
2026-04-20 1:40 ` Zi Yan
2026-04-03 19:40 ` [RFC 2/2] mm: page_alloc: per-cpu pageblock buddy allocator Johannes Weiner
2026-04-04 1:42 ` Rik van Riel
2026-04-06 16:12 ` Johannes Weiner
2026-04-06 17:31 ` Frank van der Linden
2026-04-06 21:58 ` Johannes Weiner
2026-04-08 6:30 ` kernel test robot
2026-04-10 9:48 ` Vlastimil Babka (SUSE)
2026-04-10 19:12 ` Johannes Weiner
2026-04-04 2:27 ` [RFC 0/2] mm: page_alloc: pcp " Zi Yan
2026-04-06 15:24 ` Johannes Weiner
2026-04-07 2:42 ` Zi Yan
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=20260403194526.477775-2-hannes@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=Liam.Howlett@oracle.com \
--cc=david@kernel.org \
--cc=jweiner@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=riel@surriel.com \
--cc=vbabka@suse.cz \
--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.