Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:
 "The rest of MM and a kernel-wide procfs cleanup.

  Summary of the more significant patches:

   - Patch series "mm/memory_hotplug: Factor out memory block
     devicehandling", v3. David Hildenbrand.

     Some spring-cleaning of the memory hotplug code, notably in
     drivers/base/memory.c

   - "mm: thp: fix false negative of shmem vma's THP eligibility". Yang
     Shi.

     Fix /proc/pid/smaps output for THP pages used in shmem.

   - "resource: fix locking in find_next_iomem_res()" + 1. Nadav Amit.

     Bugfix and speedup for kernel/resource.c

   - Patch series "mm: Further memory block device cleanups", David
     Hildenbrand.

     More spring-cleaning of the memory hotplug code.

   - Patch series "mm: Sub-section memory hotplug support". Dan
     Williams.

     Generalise the memory hotplug code so that pmem can use it more
     completely. Then remove the hacks from the libnvdimm code which
     were there to work around the memory-hotplug code's constraints.

   - "proc/sysctl: add shared variables for range check", Matteo Croce.

     We have about 250 instances of

          int zero;
          ...
                  .extra1 = &zero,

     in the tree. This is a tree-wide sweep to make all those private
     "zero"s and "one"s use global variables.

     Alas, it isn't practical to make those two global integers const"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (38 commits)
  proc/sysctl: add shared variables for range check
  mm: migrate: remove unused mode argument
  mm/sparsemem: cleanup 'section number' data types
  libnvdimm/pfn: stop padding pmem namespaces to section alignment
  libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields
  mm/devm_memremap_pages: enable sub-section remap
  mm: document ZONE_DEVICE memory-model implications
  mm/sparsemem: support sub-section hotplug
  mm/sparsemem: prepare for sub-section ranges
  mm: kill is_dev_zone() helper
  mm/hotplug: kill is_dev_zone() usage in __remove_pages()
  mm/sparsemem: convert kmalloc_section_memmap() to populate_section_memmap()
  mm/hotplug: prepare shrink_{zone, pgdat}_span for sub-section removal
  mm/sparsemem: add helpers track active portions of a section at boot
  mm/sparsemem: introduce a SECTION_IS_EARLY flag
  mm/sparsemem: introduce struct mem_section_usage
  drivers/base/memory.c: get rid of find_memory_block_hinted()
  mm/memory_hotplug: move and simplify walk_memory_blocks()
  mm/memory_hotplug: rename walk_memory_range() and pass start+size instead of pfns
  mm: make register_mem_sect_under_node() static
  ...

1 files changed, 69 insertions, 19 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 70394cabaf4e..d77d717c620c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -855,18 +855,6 @@ static inline int local_memory_node(int node_id) { return node_id; };
  */
 #define zone_idx(zone)		((zone) - (zone)->zone_pgdat->node_zones)
 
-#ifdef CONFIG_ZONE_DEVICE
-static inline bool is_dev_zone(const struct zone *zone)
-{
-	return zone_idx(zone) == ZONE_DEVICE;
-}
-#else
-static inline bool is_dev_zone(const struct zone *zone)
-{
-	return false;
-}
-#endif
-
 /*
  * Returns true if a zone has pages managed by the buddy allocator.
  * All the reclaim decisions have to use this function rather than
@@ -1160,6 +1148,29 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SECTION_ALIGN_UP(pfn)	(((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
+#define SUBSECTION_SHIFT 21
+
+#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
+#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)
+#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1))
+
+#if SUBSECTION_SHIFT > SECTION_SIZE_BITS
+#error Subsection size exceeds section size
+#else
+#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT))
+#endif
+
+#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
+#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
+
+struct mem_section_usage {
+	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
+	/* See declaration of similar field in struct zone */
+	unsigned long pageblock_flags[0];
+};
+
+void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
+
 struct page;
 struct page_ext;
 struct mem_section {
@@ -1177,8 +1188,7 @@ struct mem_section {
 	 */
 	unsigned long section_mem_map;
 
-	/* See declaration of similar field in struct zone */
-	unsigned long *pageblock_flags;
+	struct mem_section_usage *usage;
 #ifdef CONFIG_PAGE_EXTENSION
 	/*
 	 * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use
@@ -1209,6 +1219,11 @@ extern struct mem_section **mem_section;
 extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
 #endif
 
+static inline unsigned long *section_to_usemap(struct mem_section *ms)
+{
+	return ms->usage->pageblock_flags;
+}
+
 static inline struct mem_section *__nr_to_section(unsigned long nr)
 {
 #ifdef CONFIG_SPARSEMEM_EXTREME
@@ -1219,8 +1234,8 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 		return NULL;
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
-extern int __section_nr(struct mem_section* ms);
-extern unsigned long usemap_size(void);
+extern unsigned long __section_nr(struct mem_section *ms);
+extern size_t mem_section_usage_size(void);
 
 /*
  * We use the lower bits of the mem_map pointer to store
@@ -1238,7 +1253,8 @@ extern unsigned long usemap_size(void);
 #define	SECTION_MARKED_PRESENT	(1UL<<0)
 #define SECTION_HAS_MEM_MAP	(1UL<<1)
 #define SECTION_IS_ONLINE	(1UL<<2)
-#define SECTION_MAP_LAST_BIT	(1UL<<3)
+#define SECTION_IS_EARLY	(1UL<<3)
+#define SECTION_MAP_LAST_BIT	(1UL<<4)
 #define SECTION_MAP_MASK	(~(SECTION_MAP_LAST_BIT-1))
 #define SECTION_NID_SHIFT	3
 
@@ -1264,6 +1280,11 @@ static inline int valid_section(struct mem_section *section)
 	return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
 }
 
+static inline int early_section(struct mem_section *section)
+{
+	return (section && (section->section_mem_map & SECTION_IS_EARLY));
+}
+
 static inline int valid_section_nr(unsigned long nr)
 {
 	return valid_section(__nr_to_section(nr));
@@ -1291,14 +1312,42 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 	return __nr_to_section(pfn_to_section_nr(pfn));
 }
 
-extern int __highest_present_section_nr;
+extern unsigned long __highest_present_section_nr;
+
+static inline int subsection_map_index(unsigned long pfn)
+{
+	return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION;
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+	int idx = subsection_map_index(pfn);
+
+	return test_bit(idx, ms->usage->subsection_map);
+}
+#else
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+	return 1;
+}
+#endif
 
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 static inline int pfn_valid(unsigned long pfn)
 {
+	struct mem_section *ms;
+
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
-	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
+	ms = __nr_to_section(pfn_to_section_nr(pfn));
+	if (!valid_section(ms))
+		return 0;
+	/*
+	 * Traditionally early sections always returned pfn_valid() for
+	 * the entire section-sized span.
+	 */
+	return early_section(ms) || pfn_section_valid(ms, pfn);
 }
 #endif
 
@@ -1330,6 +1379,7 @@ void sparse_init(void);
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
 #define pfn_present pfn_valid
+#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
 /*