Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2 updates

 - almost all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (131 commits)
  memory hotplug: fix comments when adding section
  mm: make alloc_node_mem_map a void call if we don't have CONFIG_FLAT_NODE_MEM_MAP
  mm: simplify nodemask printing
  mm,oom_reaper: remove pointless kthread_run() error check
  mm/page_ext.c: check if page_ext is not prepared
  writeback: remove unused function parameter
  mm: do not rely on preempt_count in print_vma_addr
  mm, sparse: do not swamp log with huge vmemmap allocation failures
  mm/hmm: remove redundant variable align_end
  mm/list_lru.c: mark expected switch fall-through
  mm/shmem.c: mark expected switch fall-through
  mm/page_alloc.c: broken deferred calculation
  mm: don't warn about allocations which stall for too long
  fs: fuse: account fuse_inode slab memory as reclaimable
  mm, page_alloc: fix potential false positive in __zone_watermark_ok
  mm: mlock: remove lru_add_drain_all()
  mm, sysctl: make NUMA stats configurable
  shmem: convert shmem_init_inodecache() to void
  Unify migrate_pages and move_pages access checks
  mm, pagevec: rename pagevec drained field
  ...

arch/sparc/include/asm/pgtable_64.h

@@ -231,6 +231,36 @@ extern unsigned long _PAGE_ALL_SZ_BITS;
 extern struct page *mem_map_zero;
 #define ZERO_PAGE(vaddr)	(mem_map_zero)
 
+/* This macro must be updated when the size of struct page grows above 80
+ * or reduces below 64.
+ * The idea that compiler optimizes out switch() statement, and only
+ * leaves clrx instructions
+ */
+#define	mm_zero_struct_page(pp) do {					\
+	unsigned long *_pp = (void *)(pp);				\
+									\
+	 /* Check that struct page is either 64, 72, or 80 bytes */	\
+	BUILD_BUG_ON(sizeof(struct page) & 7);				\
+	BUILD_BUG_ON(sizeof(struct page) < 64);				\
+	BUILD_BUG_ON(sizeof(struct page) > 80);				\
+									\
+	switch (sizeof(struct page)) {					\
+	case 80:							\
+		_pp[9] = 0;	/* fallthrough */			\
+	case 72:							\
+		_pp[8] = 0;	/* fallthrough */			\
+	default:							\
+		_pp[7] = 0;						\
+		_pp[6] = 0;						\
+		_pp[5] = 0;						\
+		_pp[4] = 0;						\
+		_pp[3] = 0;						\
+		_pp[2] = 0;						\
+		_pp[1] = 0;						\
+		_pp[0] = 0;						\
+	}								\
+} while (0)
+
 /* PFNs are real physical page numbers.  However, mem_map only begins to record
  * per-page information starting at pfn_base.  This is to handle systems where
  * the first physical page in the machine is at some huge physical address,

arch/sparc/mm/hugetlbpage.c

@@ -397,7 +397,7 @@ static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 
 	pmd_clear(pmd);
 	pte_free_tlb(tlb, token, addr);
-	atomic_long_dec(&tlb->mm->nr_ptes);
+	mm_dec_nr_ptes(tlb->mm);
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -472,6 +472,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	pud = pud_offset(pgd, start);
 	pgd_clear(pgd);
 	pud_free_tlb(tlb, pud, start);
+	mm_dec_nr_puds(tlb->mm);
 }
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb,

arch/sparc/mm/init_64.c

@@ -2540,9 +2540,16 @@ void __init mem_init(void)
 {
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
-	register_page_bootmem_info();
 	free_all_bootmem();
 
+	/*
+	 * Must be done after boot memory is put on freelist, because here we
+	 * might set fields in deferred struct pages that have not yet been
+	 * initialized, and free_all_bootmem() initializes all the reserved
+	 * deferred pages for us.
+	 */
+	register_page_bootmem_info();
+
 	/*
 	 * Set up the zero page, mark it reserved, so that page count
 	 * is not manipulated when freeing the page from user ptes.
@@ -2637,30 +2644,19 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 	vstart = vstart & PMD_MASK;
 	vend = ALIGN(vend, PMD_SIZE);
 	for (; vstart < vend; vstart += PMD_SIZE) {
-		pgd_t *pgd = pgd_offset_k(vstart);
+		pgd_t *pgd = vmemmap_pgd_populate(vstart, node);
 		unsigned long pte;
 		pud_t *pud;
 		pmd_t *pmd;
 
-		if (pgd_none(*pgd)) {
-			pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (!pgd)
+			return -ENOMEM;
 
-			if (!new)
-				return -ENOMEM;
-			pgd_populate(&init_mm, pgd, new);
-		}
-
-		pud = pud_offset(pgd, vstart);
-		if (pud_none(*pud)) {
-			pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
-
-			if (!new)
-				return -ENOMEM;
-			pud_populate(&init_mm, pud, new);
-		}
+		pud = vmemmap_pud_populate(pgd, vstart, node);
+		if (!pud)
+			return -ENOMEM;
 
 		pmd = pmd_offset(pud, vstart);
-
 		pte = pmd_val(*pmd);
 		if (!(pte & _PAGE_VALID)) {
 			void *block = vmemmap_alloc_block(PMD_SIZE, node);
@@ -2927,7 +2923,7 @@ void __flush_tlb_all(void)
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 			    unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	pte_t *pte = NULL;
 
 	if (page)
@@ -2939,11 +2935,11 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 pgtable_t pte_alloc_one(struct mm_struct *mm,
 			unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
-		free_hot_cold_page(page, 0);
+		free_unref_page(page);
 		return NULL;
 	}
 	return (pte_t *) page_address(page);