memory-hotplug: implement register_page_bootmem_info_section of sparse-vmemmap

For removing memmap region of sparse-vmemmap which is allocated bootmem,
memmap region of sparse-vmemmap needs to be registered by
get_page_bootmem().  So the patch searches pages of virtual mapping and
registers the pages by get_page_bootmem().

NOTE: register_page_bootmem_memmap() is not implemented for ia64,
      ppc, s390, and sparc.  So introduce CONFIG_HAVE_BOOTMEM_INFO_NODE
      and revert register_page_bootmem_info_node() when platform doesn't
      support it.

      It's implemented by adding a new Kconfig option named
      CONFIG_HAVE_BOOTMEM_INFO_NODE, which will be automatically selected
      by memory-hotplug feature fully supported archs(currently only on
      x86_64).

      Since we have 2 config options called MEMORY_HOTPLUG and
      MEMORY_HOTREMOVE used for memory hot-add and hot-remove separately,
      and codes in function register_page_bootmem_info_node() are only
      used for collecting infomation for hot-remove, so reside it under
      MEMORY_HOTREMOVE.

      Besides page_isolation.c selected by MEMORY_ISOLATION under
      MEMORY_HOTPLUG is also such case, move it too.

[mhocko@suse.cz: put register_page_bootmem_memmap inside CONFIG_MEMORY_HOTPLUG_SPARSE]
[linfeng@cn.fujitsu.com: introduce CONFIG_HAVE_BOOTMEM_INFO_NODE and revert register_page_bootmem_info_node()]
[mhocko@suse.cz: remove the arch specific functions without any implementation]
[linfeng@cn.fujitsu.com: mm/Kconfig: move auto selects from MEMORY_HOTPLUG to MEMORY_HOTREMOVE as needed]
[rientjes@google.com: fix defined but not used warning]
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reviewed-by: Wu Jianguo <wujianguo@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Lin Feng <linfeng@cn.fujitsu.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 111 insertions, 13 deletions

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index c641333cd997..731bf84094b6 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -822,4 +822,5 @@ int __meminit vmemmap_populate(struct page *start_page,
 {
 	return vmemmap_populate_basepages(start_page, size, node);
 }
+
 #endif
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 95a45293e5ac..42bf082f0124 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -297,5 +297,6 @@ int __meminit vmemmap_populate(struct page *start_page,
 
 	return 0;
 }
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5c2c6e61facb..59c6fcfdc782 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2235,6 +2235,7 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b6dd1c480b30..f17aa76dc1ae 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1034,6 +1034,66 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 	return 0;
 }
 
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+	unsigned long addr = (unsigned long)start_page;
+	unsigned long end = (unsigned long)(start_page + size);
+	unsigned long next;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned int nr_pages;
+	struct page *page;
+
+	for (; addr < end; addr = next) {
+		pte_t *pte = NULL;
+
+		pgd = pgd_offset_k(addr);
+		if (pgd_none(*pgd)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);
+
+		pud = pud_offset(pgd, addr);
+		if (pud_none(*pud)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
+
+		if (!cpu_has_pse) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+			get_page_bootmem(section_nr, pmd_page(*pmd),
+					 MIX_SECTION_INFO);
+
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte))
+				continue;
+			get_page_bootmem(section_nr, pte_page(*pte),
+					 SECTION_INFO);
+		} else {
+			next = pmd_addr_end(addr, end);
+
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+
+			nr_pages = 1 << (get_order(PMD_SIZE));
+			page = pmd_page(*pmd);
+			while (nr_pages--)
+				get_page_bootmem(section_nr, page++,
+						 SECTION_INFO);
+		}
+	}
+}
+#endif
+
 void __meminit vmemmap_populate_print_last(void)
 {
 	if (p_start) {
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 31a563bbd936..4d523fe75ba1 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -174,17 +174,16 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+#else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
-static inline void put_page_bootmem(struct page *page)
-{
-}
-#else
-extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
-extern void put_page_bootmem(struct page *page);
 #endif
+extern void put_page_bootmem(struct page *page);
+extern void get_page_bootmem(unsigned long ingo, struct page *page,
+			     unsigned long type);
 
 /*
  * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 95db68e34b18..060557b9764f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1718,7 +1718,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
-
+void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
+				  unsigned long size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
diff --git a/mm/Kconfig b/mm/Kconfig
index 0b23db9a8791..2c7aea7106f9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -162,10 +162,16 @@ config MOVABLE_NODE
 	  Say Y here if you want to hotplug a whole node.
 	  Say N here if you want kernel to use memory on all nodes evenly.
 
+#
+# Only be set on architectures that have completely implemented memory hotplug
+# feature. If you are not sure, don't touch it.
+#
+config HAVE_BOOTMEM_INFO_NODE
+	def_bool n
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
-	select MEMORY_ISOLATION
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
@@ -176,6 +182,8 @@ config MEMORY_HOTPLUG_SPARSE
 
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
+	select MEMORY_ISOLATION
+	select HAVE_BOOTMEM_INFO_NODE if X86_64
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 942b43f6d736..6c90d222ec0a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -91,9 +91,8 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info,  struct page *page,
-			     unsigned long type)
+void get_page_bootmem(unsigned long info,  struct page *page,
+		      unsigned long type)
 {
 	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
@@ -128,6 +127,8 @@ void __ref put_page_bootmem(struct 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 *usemap, mapsize, section_nr, i;
@@ -161,6 +162,32 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 		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 *usemap, mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+
+	if (!pfn_valid(start_pfn))
+		return;
+
+	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);
+
+	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	page = virt_to_page(usemap);
+
+	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
 void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
@@ -203,7 +230,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 			register_page_bootmem_info_section(pfn);
 	}
 }
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
 static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 			   unsigned long end_pfn)