diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 3c8cf86201c3faefe4ce28817abe026dfb1ab508..a61aede1b3911f3102f98c7060e1c95a374c4c8e 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -14,6 +14,20 @@ struct memory_block;
struct resource;
#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Return page for the valid pfn only if the page is online. All pfn
+ * walkers which rely on the fully initialized page->flags and others
+ * should use this rather than pfn_valid && pfn_to_page
+ */
+#define pfn_to_online_page(pfn) \
+({ \
+ struct page *___page = NULL; \
+ unsigned long ___nr = pfn_to_section_nr(pfn); \
+ \
+ if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
+ ___page = pfn_to_page(pfn); \
+ ___page; \
+})
/*
* Types for free bootmem stored in page->lru.next. These have to be in
@@ -203,6 +217,14 @@ extern void set_zone_contiguous(struct zone *zone);
extern void clear_zone_contiguous(struct zone *zone);
#else /* ! CONFIG_MEMORY_HOTPLUG */
+#define pfn_to_online_page(pfn) \
+({ \
+ struct page *___page = NULL; \
+ if (pfn_valid(pfn)) \
+ ___page = pfn_to_page(pfn); \
+ ___page; \
+ })
+
/*
* Stub functions for when hotplug is off
*/
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 976a1202bec113a47519b106ba0926787afe2d4a..2aaf7e08c5a85feb4403da19a68383be882c2c77 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1144,9 +1144,10 @@ extern unsigned long usemap_size(void);
*/
#define SECTION_MARKED_PRESENT (1UL<<0)
#define SECTION_HAS_MEM_MAP (1UL<<1)
-#define SECTION_MAP_LAST_BIT (1UL<<2)
+#define SECTION_IS_ONLINE (1UL<<2)
+#define SECTION_MAP_LAST_BIT (1UL<<3)
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT 2
+#define SECTION_NID_SHIFT 3
static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
@@ -1175,6 +1176,23 @@ static inline int valid_section_nr(unsigned long nr)
return valid_section(__nr_to_section(nr));
}
+static inline int online_section(struct mem_section *section)
+{
+ return (section && (section->section_mem_map & SECTION_IS_ONLINE));
+}
+
+static inline int online_section_nr(unsigned long nr)
+{
+ return online_section(__nr_to_section(nr));
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
+#ifdef CONFIG_MEMORY_HOTREMOVE
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
+#endif
+#endif
+
static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
return __nr_to_section(pfn_to_section_nr(pfn));
@@ -1253,10 +1271,15 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
/*
* pfn_valid() is meant to be able to tell if a given PFN has valid memmap
- * associated with it or not. In FLATMEM, it is expected that holes always
- * have valid memmap as long as there is valid PFNs either side of the hole.
- * In SPARSEMEM, it is assumed that a valid section has a memmap for the
- * entire section.
+ * associated with it or not. This means that a struct page exists for this
+ * pfn. The caller cannot assume the page is fully initialized in general.
+ * Hotplugable pages might not have been onlined yet. pfn_to_online_page()
+ * will ensure the struct page is fully online and initialized. Special pages
+ * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly.
+ *
+ * In FLATMEM, it is expected that holes always have valid memmap as long as
+ * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed
+ * that a valid section has a memmap for the entire section.
*
* However, an ARM, and maybe other embedded architectures in the future
* free memmap backing holes to save memory on the assumption the memmap is
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index caa58338d121e95901da14e38c7fdba33e3c6c29..b2ebe9ad7f6cd2e73f90be6ac70c54cca08ef074 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -929,12 +929,16 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
unsigned long i;
unsigned long onlined_pages = *(unsigned long *)arg;
struct page *page;
+
if (PageReserved(pfn_to_page(start_pfn)))
for (i = 0; i < nr_pages; i++) {
page = pfn_to_page(start_pfn + i);
(*online_page_callback)(page);
onlined_pages++;
}
+
+ online_mem_sections(start_pfn, start_pfn + nr_pages);
+
*(unsigned long *)arg = onlined_pages;
return 0;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 73f854344735e1bfe4e21fab0b1711dc90b9168d..387f20db217c15e039247ac539e8d5213f74e2dd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1365,7 +1365,9 @@ struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
return NULL;
- start_page = pfn_to_page(start_pfn);
+ start_page = pfn_to_online_page(start_pfn);
+ if (!start_page)
+ return NULL;
if (page_zone(start_page) != zone)
return NULL;
@@ -7656,6 +7658,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
break;
if (pfn == end_pfn)
return;
+ offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags);
pfn = start_pfn;
diff --git a/mm/sparse.c b/mm/sparse.c
index 5032c9a619de35b6b98503c70266c19ea626c0e0..9d7fd666015ee04eddb410a55a466673ba37c8ce 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -222,7 +222,8 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
ms = __nr_to_section(section);
if (!ms->section_mem_map) {
- ms->section_mem_map = sparse_encode_early_nid(nid);
+ ms->section_mem_map = sparse_encode_early_nid(nid) |
+ SECTION_IS_ONLINE;
section_mark_present(ms);
}
}
@@ -622,6 +623,48 @@ void __init sparse_init(void)
}
#ifdef CONFIG_MEMORY_HOTPLUG
+
+/* Mark all memory sections within the pfn range as online */
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ struct mem_section *ms;
+
+ /* onlining code should never touch invalid ranges */
+ if (WARN_ON(!valid_section_nr(section_nr)))
+ continue;
+
+ ms = __nr_to_section(section_nr);
+ ms->section_mem_map |= SECTION_IS_ONLINE;
+ }
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/* Mark all memory sections within the pfn range as online */
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ struct mem_section *ms;
+
+ /*
+ * TODO this needs some double checking. Offlining code makes
+ * sure to check pfn_valid but those checks might be just bogus
+ */
+ if (WARN_ON(!valid_section_nr(section_nr)))
+ continue;
+
+ ms = __nr_to_section(section_nr);
+ ms->section_mem_map &= ~SECTION_IS_ONLINE;
+ }
+}
+#endif
+
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
{