@@ -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>
@@ -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)
{
new file mode 100644
@@ -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 */
@@ -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. */
@@ -220,17 +208,6 @@ 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);
@@ -258,10 +235,6 @@ 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;
@@ -126,3 +126,4 @@ 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
new file mode 100644
@@ -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);
+ }
+}
@@ -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)
{
@@ -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>
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. 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> --- arch/sparc/mm/init_64.c | 1 + arch/x86/mm/init_64.c | 3 +- include/linux/bootmem_info.h | 40 +++++++++++++ include/linux/memory_hotplug.h | 27 --------- mm/Makefile | 1 + mm/bootmem_info.c | 127 +++++++++++++++++++++++++++++++++++++++++ mm/memory_hotplug.c | 116 ------------------------------------- mm/sparse.c | 1 + 8 files changed, 172 insertions(+), 144 deletions(-) create mode 100644 include/linux/bootmem_info.h create mode 100644 mm/bootmem_info.c