mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Muchun Song <songmuchun@bytedance.com>
To: Alexander Potapenko <glider@google.com>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: Marco Elver <elver@google.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	Chris Down <chris@chrisdown.name>,
	David Hildenbrand <david@kernel.org>,
	"Liam R . Howlett" <liam@infradead.org>,
	Vlastimil Babka <vbabka@kernel.org>,
	Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Michal Hocko <mhocko@suse.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Brendan Jackman <brendan.jackman@linux.dev>,
	Zi Yan <ziy@nvidia.com>, Muchun Song <muchun.song@linux.dev>,
	Joerg Roedel <joerg.roedel@amd.com>,
	Lu Baolu <baolu.lu@linux.intel.com>,
	Pranjal Shrivastava <praan@google.com>,
	Ketan <ketan.kishore@oss.qualcomm.com>,
	Mostafa Saleh <smostafa@google.com>,
	Sang-Heon Jeon <ekffu200098@gmail.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Sashiko <sashiko-bot@kernel.org>,
	kasan-dev@googlegroups.com, workflows@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v2 5/7] mm/page_ext: allocate page extensions early for SPARSEMEM
Date: Tue, 17 Nov 2026 20:06:25 +0800	[thread overview]
Message-ID: <20261117120627.50601-6-songmuchun@bytedance.com> (raw)
In-Reply-To: <20261117120627.50601-1-songmuchun@bytedance.com>

KMSAN needs page extensions when kmsan_init_shadow() installs per-page
metadata, before memblock_free_all() releases memory to the buddy
allocator.  FLATMEM makes page extensions available by this point,
whereas SPARSEMEM initializes them later in boot.

Allocate boot-time SPARSEMEM page extensions from memblock to match
FLATMEM's initialization timing.  This gives early clients the same
page_ext availability guarantee across both memory models, while runtime
memory hotplug continues to use vmalloc.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
v2:
- Allocate all boot-time SPARSEMEM page extensions from memblock
  (suggested by Mike Rapoport)
- Keep memblock allocations above DMA and suppress per-section free
  messages (suggested by Chris Down)
---
 include/linux/page_ext.h |   9 +--
 mm/mm_init.c             |   4 --
 mm/page_ext.c            | 119 +++++++++++++++++++--------------------
 3 files changed, 60 insertions(+), 72 deletions(-)

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 911a84bbb3db..d00320106a58 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -61,12 +61,10 @@ static inline bool early_page_ext_enabled(void)
 	return early_page_ext;
 }
 
-#ifdef CONFIG_SPARSEMEM
-static inline void page_ext_alloc(void)
-{
-}
+void page_ext_alloc(void);
 void page_ext_init(void);
 
+#ifdef CONFIG_SPARSEMEM
 static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
 {
 	/*
@@ -76,9 +74,6 @@ static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
 	return next_pfn % PAGES_PER_SECTION;
 }
 #else
-void page_ext_alloc(void);
-void page_ext_init(void);
-
 static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
 {
 	return true;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 7344e7cb8196..baa2681857eb 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2707,10 +2707,6 @@ void __init mm_core_init(void)
 	build_all_zonelists(NULL);
 	page_alloc_init_cpuhp();
 	alloc_tag_sec_init();
-	/*
-	 * page_ext requires contiguous pages,
-	 * bigger than MAX_PAGE_ORDER unless SPARSEMEM.
-	 */
 	page_ext_alloc();
 	mem_debugging_and_hardening_init();
 	kfence_alloc_pool_and_metadata();
diff --git a/mm/page_ext.c b/mm/page_ext.c
index b41d4a957bc6..2910727e99e2 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -12,6 +12,7 @@
 #include <linux/rcupdate.h>
 #include <linux/pgalloc_tag.h>
 #include <linux/iommu-debug-pagealloc.h>
+#include <linux/slab.h>
 
 /*
  * struct page extension
@@ -180,11 +181,6 @@ static inline struct page_ext *get_entry(void *base, unsigned long index)
 }
 
 #ifndef CONFIG_SPARSEMEM
-void __init page_ext_init(void)
-{
-	invoke_init_callbacks();
-}
-
 static struct page_ext *lookup_page_ext(const struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
@@ -238,24 +234,16 @@ static int __init alloc_node_page_ext(int nid)
 	return 0;
 }
 
-void __init page_ext_alloc(void)
+static int __init __page_ext_alloc(void)
 {
-	int nid, fail;
-
-	if (!invoke_need_callbacks())
-		return;
+	int nid;
 
-	for_each_online_node(nid)  {
-		fail = alloc_node_page_ext(nid);
-		if (fail)
-			goto fail;
+	for_each_online_node(nid) {
+		if (alloc_node_page_ext(nid))
+			return -ENOMEM;
 	}
-	pr_info("allocated %ld bytes of page_ext\n", total_usage);
-	return;
 
-fail:
-	pr_crit("allocation of page_ext failed.\n");
-	panic("Out of memory");
+	return 0;
 }
 
 #else /* CONFIG_SPARSEMEM */
@@ -282,13 +270,21 @@ static struct page_ext *lookup_page_ext(const struct page *page)
 	return get_entry(page_ext, pfn);
 }
 
-static void *__meminit alloc_page_ext(size_t size, int nid)
+static __ref void *alloc_page_ext(size_t size, int nid)
 {
 	void *addr;
 
+	if (!slab_is_available()) {
+		addr = memblock_alloc_try_nid(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					      MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+		if (addr)
+			memmap_boot_pages_add(size / PAGE_SIZE);
+		return addr;
+	}
+
 	addr = vzalloc_node(size, nid);
 	if (addr)
-		memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
+		memmap_pages_add(size / PAGE_SIZE);
 
 	return addr;
 }
@@ -304,7 +300,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	if (section->page_ext)
 		return 0;
 
-	table_size = page_ext_size * PAGES_PER_SECTION;
+	table_size = PAGE_ALIGN(page_ext_size * PAGES_PER_SECTION);
 	base = alloc_page_ext(table_size, nid);
 
 	/*
@@ -331,11 +327,19 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 
 static void free_page_ext(void *addr)
 {
-	size_t table_size;
+	size_t table_size = PAGE_ALIGN(page_ext_size * PAGES_PER_SECTION);
+	long nr_pages = table_size / PAGE_SIZE;
+
+	if (is_vmalloc_addr(addr)) {
+		memmap_pages_add(-nr_pages);
+		vfree(addr);
+		return;
+	}
 
-	table_size = page_ext_size * PAGES_PER_SECTION;
-	memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE)));
-	vfree(addr);
+	VM_WARN_ON_ONCE(!PageReserved(virt_to_page(addr)));
+	memmap_boot_pages_add(-nr_pages);
+	kmemleak_free_part_phys(__pa(addr), table_size);
+	free_reserved_area(addr, addr + table_size, -1, NULL);
 }
 
 static void __free_page_ext(unsigned long pfn)
@@ -449,52 +453,45 @@ static int __meminit page_ext_callback(struct notifier_block *self,
 	return notifier_from_errno(ret);
 }
 
-void __init page_ext_init(void)
+static int __init __page_ext_alloc(void)
 {
-	unsigned long pfn;
-	int nid;
-
-	if (!invoke_need_callbacks())
-		return;
-
-	for_each_node_state(nid, N_MEMORY) {
-		unsigned long start_pfn, end_pfn;
-
-		start_pfn = node_start_pfn(nid);
-		end_pfn = node_end_pfn(nid);
-		/*
-		 * start_pfn and end_pfn may not be aligned to SECTION and the
-		 * page->flags of out of node pages are not initialized.  So we
-		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
-		 */
-		for (pfn = start_pfn; pfn < end_pfn;
-			pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
+	unsigned long start, end, pfn;
+	int i, nid;
 
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
+		for (pfn = start; pfn < end; pfn = SECTION_ALIGN_UP(pfn + 1)) {
 			if (!pfn_valid(pfn))
 				continue;
-			/*
-			 * Nodes's pfns can be overlapping.
-			 * We know some arch can have a nodes layout such as
-			 * -------------pfn-------------->
-			 * N0 | N1 | N2 | N0 | N1 | N2|....
-			 */
-			if (pfn_to_nid(pfn) != nid)
-				continue;
 			if (init_section_page_ext(pfn, nid))
-				goto oom;
-			cond_resched();
+				return -ENOMEM;
 		}
 	}
-	hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI);
-	pr_info("allocated %ld bytes of page_ext\n", total_usage);
-	invoke_init_callbacks();
-	return;
 
-oom:
-	panic("Out of memory");
+	return 0;
+}
+
+#endif
+
+void __init page_ext_alloc(void)
+{
+	if (!invoke_need_callbacks())
+		return;
+	if (__page_ext_alloc())
+		panic("Out of memory");
+
+	pr_info("allocated %ld bytes of page_ext\n", total_usage);
 }
 
+void __init page_ext_init(void)
+{
+	if (!page_ext_size)
+		return;
+
+#ifdef CONFIG_SPARSEMEM
+	hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI);
 #endif
+	invoke_init_callbacks();
+}
 
 /**
  * page_ext_lookup() - Lookup a page extension for a PFN.
-- 
2.54.0


  parent reply	other threads:[~2026-11-17 12:07 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-17 12:06 [PATCH v2 0/7] KMSAN: Move per-page metadata out of struct page Muchun Song
2026-11-17 12:06 ` [PATCH v2 1/7] kmsan: encapsulate per-page metadata access Muchun Song
2026-11-17 12:06 ` [PATCH v2 2/7] mm/page_ext: fix client data alignment Muchun Song
2026-11-17 12:06 ` [PATCH v2 3/7] mm/page_ext: always use vmalloc for section page extensions Muchun Song
2026-11-17 12:06 ` [PATCH v2 4/7] mm/page_ext: use common allocation and initialization entry points Muchun Song
2026-11-17 12:06 ` Muchun Song [this message]
2026-11-18  0:06   ` [PATCH v2 5/7] mm/page_ext: allocate page extensions early for SPARSEMEM Chris Down
2026-11-17 12:06 ` [PATCH v2 6/7] mm/page_ext: inline unchecked page extension lookup Muchun Song
2026-11-17 12:06 ` [PATCH v2 7/7] kmsan: fix metadata loss during HugeTLB struct page reinitialization Muchun Song
2026-11-18  0:06 ` [PATCH v2 0/7] KMSAN: Move per-page metadata out of struct page Chris Down

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=20261117120627.50601-6-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=baolu.lu@linux.intel.com \
    --cc=brendan.jackman@linux.dev \
    --cc=chris@chrisdown.name \
    --cc=corbet@lwn.net \
    --cc=david@kernel.org \
    --cc=dvyukov@google.com \
    --cc=ekffu200098@gmail.com \
    --cc=elver@google.com \
    --cc=glider@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=joerg.roedel@amd.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=ketan.kishore@oss.qualcomm.com \
    --cc=liam@infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=praan@google.com \
    --cc=rdunlap@infradead.org \
    --cc=rppt@kernel.org \
    --cc=sashiko-bot@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=smostafa@google.com \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=workflows@vger.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

all inboxes | Powered by JetHome®