mm: memory_hotplug: factor out bootmem core functions to bootmem_info.c

Patch series "Free some vmemmap pages of HugeTLB page", v23.

This patch series will free some vmemmap pages(struct page structures)
associated with each HugeTLB page when preallocated to save memory.

In order to reduce the difficulty of the first version of code review.  In
this version, we disable PMD/huge page mapping of vmemmap if this feature
was enabled.  This acutely eliminates a bunch of the complex code doing
page table manipulation.  When this patch series is solid, we cam add the
code of vmemmap page table manipulation in the future.

The struct page structures (page structs) are used to describe a physical
page frame.  By default, there is an one-to-one mapping from a page frame
to it's corresponding page struct.

The HugeTLB pages consist of multiple base page size pages and is
supported by many architectures.  See hugetlbpage.rst in the Documentation
directory for more details.  On the x86 architecture, HugeTLB pages of
size 2MB and 1GB are currently supported.  Since the base page size on x86
is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB
page consists of 4096 base pages.  For each base page, there is a
corresponding page struct.

Within the HugeTLB subsystem, only the first 4 page structs are used to
contain unique information about a HugeTLB page.  HUGETLB_CGROUP_MIN_ORDER
provides this upper limit.  The only 'useful' information in the remaining
page structs is the compound_head field, and this field is the same for
all tail pages.

By removing redundant page structs for HugeTLB pages, memory can returned
to the buddy allocator for other uses.

When the system boot up, every 2M HugeTLB has 512 struct page structs which
size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).

    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
 +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
 |           |                     |     0     | -------------> |     0     |
 |           |                     +-----------+                +-----------+
 |           |                     |     1     | -------------> |     1     |
 |           |                     +-----------+                +-----------+
 |           |                     |     2     | -------------> |     2     |
 |           |                     +-----------+                +-----------+
 |           |                     |     3     | -------------> |     3     |
 |           |                     +-----------+                +-----------+
 |           |                     |     4     | -------------> |     4     |
 |    2MB    |                     +-----------+                +-----------+
 |           |                     |     5     | -------------> |     5     |
 |           |                     +-----------+                +-----------+
 |           |                     |     6     | -------------> |     6     |
 |           |                     +-----------+                +-----------+
 |           |                     |     7     | -------------> |     7     |
 |           |                     +-----------+                +-----------+
 |           |
 |           |
 |           |
 +-----------+

The value of page->compound_head is the same for all tail pages.  The
first page of page structs (page 0) associated with the HugeTLB page
contains the 4 page structs necessary to describe the HugeTLB.  The only
use of the remaining pages of page structs (page 1 to page 7) is to point
to page->compound_head.  Therefore, we can remap pages 2 to 7 to page 1.
Only 2 pages of page structs will be used for each HugeTLB page.  This
will allow us to free the remaining 6 pages to the buddy allocator.

Here is how things look after remapping.

    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
 +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
 |           |                     |     0     | -------------> |     0     |
 |           |                     +-----------+                +-----------+
 |           |                     |     1     | -------------> |     1     |
 |           |                     +-----------+                +-----------+
 |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
 |           |                     +-----------+                   | | | | |
 |           |                     |     3     | ------------------+ | | | |
 |           |                     +-----------+                     | | | |
 |           |                     |     4     | --------------------+ | | |
 |    2MB    |                     +-----------+                       | | |
 |           |                     |     5     | ----------------------+ | |
 |           |                     +-----------+                         | |
 |           |                     |     6     | ------------------------+ |
 |           |                     +-----------+                           |
 |           |                     |     7     | --------------------------+
 |           |                     +-----------+
 |           |
 |           |
 |           |
 +-----------+

When a HugeTLB is freed to the buddy system, we should allocate 6 pages
for vmemmap pages and restore the previous mapping relationship.

Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page.  It is similar
to the 2MB HugeTLB page.  We also can use this approach to free the
vmemmap pages.

In this case, for the 1GB HugeTLB page, we can save 4094 pages.  This is a
very substantial gain.  On our server, run some SPDK/QEMU applications
which will use 1024GB HugeTLB page.  With this feature enabled, we can
save ~16GB (1G hugepage)/~12GB (2MB hugepage) memory.

Because there are vmemmap page tables reconstruction on the
freeing/allocating path, it increases some overhead.  Here are some
overhead analysis.

1) Allocating 10240 2MB HugeTLB pages.

   a) With this patch series applied:
   # time echo 10240 > /proc/sys/vm/nr_hugepages

   real     0m0.166s
   user     0m0.000s
   sys      0m0.166s

   # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; }
     kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs -
     @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [8K, 16K)           5476 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [16K, 32K)          4760 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@       |
   [32K, 64K)             4 |                                                    |

   b) Without this patch series:
   # time echo 10240 > /proc/sys/vm/nr_hugepages

   real     0m0.067s
   user     0m0.000s
   sys      0m0.067s

   # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; }
     kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs -
     @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [4K, 8K)           10147 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [8K, 16K)             93 |                                                    |

   Summarize: this feature is about ~2x slower than before.

2) Freeing 10240 2MB HugeTLB pages.

   a) With this patch series applied:
   # time echo 0 > /proc/sys/vm/nr_hugepages

   real     0m0.213s
   user     0m0.000s
   sys      0m0.213s

   # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; }
     kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs -
     @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [8K, 16K)              6 |                                                    |
   [16K, 32K)         10227 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [32K, 64K)             7 |                                                    |

   b) Without this patch series:
   # time echo 0 > /proc/sys/vm/nr_hugepages

   real     0m0.081s
   user     0m0.000s
   sys      0m0.081s

   # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; }
     kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs -
     @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [4K, 8K)            6805 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [8K, 16K)           3427 |@@@@@@@@@@@@@@@@@@@@@@@@@@                          |
   [16K, 32K)             8 |                                                    |

   Summary: The overhead of __free_hugepage is about ~2-3x slower than before.

Although the overhead has increased, the overhead is not significant.
Like Mike said, "However, remember that the majority of use cases create
HugeTLB pages at or shortly after boot time and add them to the pool.  So,
additional overhead is at pool creation time.  There is no change to
'normal run time' operations of getting a page from or returning a page to
the pool (think page fault/unmap)".

Despite the overhead and in addition to the memory gains from this series.
The following data is obtained by Joao Martins.  Very thanks to his
effort.

There's an additional benefit which is page (un)pinners will see an improvement
and Joao presumes because there are fewer memmap pages and thus the tail/head
pages are staying in cache more often.

Out of the box Joao saw (when comparing linux-next against linux-next +
this series) with gup_test and pinning a 16G HugeTLB file (with 1G pages):

	get_user_pages(): ~32k -> ~9k
	unpin_user_pages(): ~75k -> ~70k

Usually any tight loop fetching compound_head(), or reading tail pages
data (e.g.  compound_head) benefit a lot.  There's some unpinning
inefficiencies Joao was fixing[2], but with that in added it shows even
more:

	unpin_user_pages(): ~27k -> ~3.8k

[1] https://lore.kernel.org/linux-mm/20210409205254.242291-1-mike.kravetz@oracle.com/
[2] https://lore.kernel.org/linux-mm/20210204202500.26474-1-joao.m.martins@oracle.com/

This patch (of 9):

Move bootmem info registration common API to individual bootmem_info.c.
And we will use {get,put}_page_bootmem() to initialize the page for the
vmemmap pages or free the vmemmap pages to buddy in the later patch.  So
move them out of CONFIG_MEMORY_HOTPLUG_SPARSE.  This is just code movement
without any functional change.

Link: https://lkml.kernel.org/r/20210510030027.56044-1-songmuchun@bytedance.com
Link: https://lkml.kernel.org/r/20210510030027.56044-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Tested-by: Chen Huang <chenhuang5@huawei.com>
Tested-by: Bodeddula Balasubramaniam <bodeddub@amazon.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Mina Almasry <almasrymina@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Barry Song <song.bao.hua@hisilicon.com>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 172 insertions, 144 deletions

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 06e938d03f3b..1b23639e2fcd 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -27,6 +27,7 @@
 #include <linux/percpu.h>
 #include <linux/mmzone.h>
 #include <linux/gfp.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/head.h>
 #include <asm/page.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e527d829e1ed..3aaf1d30c777 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -33,6 +33,7 @@
 #include <linux/nmi.h>
 #include <linux/gfp.h>
 #include <linux/kcore.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1623,7 +1624,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	return err;
 }
 
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long nr_pages)
 {
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
new file mode 100644
index 000000000000..4ed6dee1adc9
--- /dev/null
+++ b/include/linux/bootmem_info.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BOOTMEM_INFO_H
+#define __LINUX_BOOTMEM_INFO_H
+
+#include <linux/mmzone.h>
+
+/*
+ * Types for free bootmem stored in page->lru.next. These have to be in
+ * some random range in unsigned long space for debugging purposes.
+ */
+enum {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
+	MIX_SECTION_INFO,
+	NODE_INFO,
+	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
+};
+
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+
+void get_page_bootmem(unsigned long info, struct page *page,
+		      unsigned long type);
+void put_page_bootmem(struct page *page);
+#else
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+
+static inline void put_page_bootmem(struct page *page)
+{
+}
+
+static inline void get_page_bootmem(unsigned long info, struct page *page,
+				    unsigned long type)
+{
+}
+#endif
+
+#endif /* __LINUX_BOOTMEM_INFO_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 28f32fd00fe9..a7fd2c3ccb77 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -18,18 +18,6 @@ struct vmem_altmap;
 #ifdef CONFIG_MEMORY_HOTPLUG
 struct page *pfn_to_online_page(unsigned long pfn);
 
-/*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
- */
-enum {
-	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
-	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
-	MIX_SECTION_INFO,
-	NODE_INFO,
-	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
-};
-
 /* Types for control the zone type of onlined and offlined memory */
 enum {
 	/* Offline the memory. */
@@ -222,17 +210,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
-#else
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-#endif
-extern void put_page_bootmem(struct page *page);
-extern void get_page_bootmem(unsigned long ingo, struct page *page,
-			     unsigned long type);
-
 void get_online_mems(void);
 void put_online_mems(void);
 
@@ -260,10 +237,6 @@ static inline void zone_span_writelock(struct zone *zone) {}
 static inline void zone_span_writeunlock(struct zone *zone) {}
 static inline void zone_seqlock_init(struct zone *zone) {}
 
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-
 static inline int try_online_node(int nid)
 {
 	return 0;
diff --git a/mm/Makefile b/mm/Makefile
index bf71e295e9f6..61ce71ddf7bb 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -125,3 +125,4 @@ obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
 obj-$(CONFIG_IO_MAPPING) += io-mapping.o
+obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
new file mode 100644
index 000000000000..5b152dba7344
--- /dev/null
+++ b/mm/bootmem_info.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Bootmem core functions.
+ *
+ * Copyright (c) 2020, Bytedance.
+ *
+ *     Author: Muchun Song <songmuchun@bytedance.com>
+ *
+ */
+#include <linux/mm.h>
+#include <linux/compiler.h>
+#include <linux/memblock.h>
+#include <linux/bootmem_info.h>
+#include <linux/memory_hotplug.h>
+
+void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
+{
+	page->freelist = (void *)type;
+	SetPagePrivate(page);
+	set_page_private(page, info);
+	page_ref_inc(page);
+}
+
+void put_page_bootmem(struct page *page)
+{
+	unsigned long type;
+
+	type = (unsigned long) page->freelist;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
+
+	if (page_ref_dec_return(page) == 1) {
+		page->freelist = NULL;
+		ClearPagePrivate(page);
+		set_page_private(page, 0);
+		INIT_LIST_HEAD(&page->lru);
+		free_reserved_page(page);
+	}
+}
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	/* Get section's memmap address */
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	/*
+	 * Get page for the memmap's phys address
+	 * XXX: need more consideration for sparse_vmemmap...
+	 */
+	page = virt_to_page(memmap);
+	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+	/* remember memmap's page */
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, SECTION_INFO);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+
+}
+#else /* CONFIG_SPARSEMEM_VMEMMAP */
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+	unsigned long i, pfn, end_pfn, nr_pages;
+	int node = pgdat->node_id;
+	struct page *page;
+
+	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
+	page = virt_to_page(pgdat);
+
+	for (i = 0; i < nr_pages; i++, page++)
+		get_page_bootmem(node, page, NODE_INFO);
+
+	pfn = pgdat->node_start_pfn;
+	end_pfn = pgdat_end_pfn(pgdat);
+
+	/* register section info */
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other nodes.
+		 */
+		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
+}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 974a565797d8..ae7a07b02049 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -154,122 +154,6 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-void get_page_bootmem(unsigned long info,  struct page *page,
-		      unsigned long type)
-{
-	page->freelist = (void *)type;
-	SetPagePrivate(page);
-	set_page_private(page, info);
-	page_ref_inc(page);
-}
-
-void put_page_bootmem(struct page *page)
-{
-	unsigned long type;
-
-	type = (unsigned long) page->freelist;
-	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
-	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
-
-	if (page_ref_dec_return(page) == 1) {
-		page->freelist = NULL;
-		ClearPagePrivate(page);
-		set_page_private(page, 0);
-		INIT_LIST_HEAD(&page->lru);
-		free_reserved_page(page);
-	}
-}
-
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	/* Get section's memmap address */
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	/*
-	 * Get page for the memmap's phys address
-	 * XXX: need more consideration for sparse_vmemmap...
-	 */
-	page = virt_to_page(memmap);
-	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
-	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
-
-	/* remember memmap's page */
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, SECTION_INFO);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-
-}
-#else /* CONFIG_SPARSEMEM_VMEMMAP */
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-}
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-
-void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-	unsigned long i, pfn, end_pfn, nr_pages;
-	int node = pgdat->node_id;
-	struct page *page;
-
-	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
-	page = virt_to_page(pgdat);
-
-	for (i = 0; i < nr_pages; i++, page++)
-		get_page_bootmem(node, page, NODE_INFO);
-
-	pfn = pgdat->node_start_pfn;
-	end_pfn = pgdat_end_pfn(pgdat);
-
-	/* register section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		/*
-		 * Some platforms can assign the same pfn to multiple nodes - on
-		 * node0 as well as nodeN.  To avoid registering a pfn against
-		 * multiple nodes we check that this pfn does not already
-		 * reside in some other nodes.
-		 */
-		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
-			register_page_bootmem_info_section(pfn);
-	}
-}
-#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
-
 static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 		const char *reason)
 {
diff --git a/mm/sparse.c b/mm/sparse.c
index 7272f7a1449d..6326cdf36c4f 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/bootmem_info.h>
 
 #include "internal.h"
 #include <asm/dma.h>