15 files changed, 281 insertions, 64 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index c070ec0c15b..9ef97417a0b 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -112,18 +112,17 @@ config SPARSEMEM_EXTREME
 	def_bool y
 	depends on SPARSEMEM && !SPARSEMEM_STATIC
 
-#
-# SPARSEMEM_VMEMMAP uses a virtually mapped mem_map to optimise pfn_to_page
-# and page_to_pfn.  The most efficient option where kernel virtual space is
-# not under pressure.
-#
 config SPARSEMEM_VMEMMAP_ENABLE
 	def_bool n
 
 config SPARSEMEM_VMEMMAP
-	bool
-	depends on SPARSEMEM
-	default y if (SPARSEMEM_VMEMMAP_ENABLE)
+	bool "Sparse Memory virtual memmap"
+	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
+	default y
+	help
+	 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
+	 pfn_to_page and page_to_pfn operations.  This is the most
+	 efficient option when sufficient kernel resources are available.
 
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index b0ceb29da4c..e8644b1e552 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -7,7 +7,7 @@
 
 int bdi_init(struct backing_dev_info *bdi)
 {
-	int i, j;
+	int i;
 	int err;
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
@@ -21,7 +21,7 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	if (err) {
 err:
-		for (j = 0; j < i; j++)
+		while (i--)
 			percpu_counter_destroy(&bdi->bdi_stat[i]);
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 188cf5fd3e8..f4d0cded0e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -124,6 +124,18 @@ void __remove_from_page_cache(struct page *page)
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	BUG_ON(page_mapped(page));
+
+	/*
+	 * Some filesystems seem to re-dirty the page even after
+	 * the VM has canceled the dirty bit (eg ext3 journaling).
+	 *
+	 * Fix it up by doing a final dirty accounting check after
+	 * having removed the page entirely.
+	 */
+	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
+		dec_zone_page_state(page, NR_FILE_DIRTY);
+		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+	}
 }
 
 void remove_from_page_cache(struct page *page)
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 32132f3cd64..f874ae818ad 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -25,14 +25,15 @@ static struct page *__xip_sparse_page;
 static struct page *xip_sparse_page(void)
 {
 	if (!__xip_sparse_page) {
-		unsigned long zeroes = get_zeroed_page(GFP_HIGHUSER);
-		if (zeroes) {
+		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+
+		if (page) {
 			static DEFINE_SPINLOCK(xip_alloc_lock);
 			spin_lock(&xip_alloc_lock);
 			if (!__xip_sparse_page)
-				__xip_sparse_page = virt_to_page(zeroes);
+				__xip_sparse_page = page;
 			else
-				free_page(zeroes);
+				__free_page(page);
 			spin_unlock(&xip_alloc_lock);
 		}
 	}
@@ -314,7 +315,7 @@ __xip_file_write(struct file *filp, const char __user *buf,
 		fault_in_pages_readable(buf, bytes);
 		kaddr = kmap_atomic(page, KM_USER0);
 		copied = bytes -
-			__copy_from_user_inatomic_nocache(kaddr, buf, bytes);
+			__copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
 		kunmap_atomic(kaddr, KM_USER0);
 		flush_dcache_page(page);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6121b57bbe9..7224a4f0710 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -31,7 +31,7 @@ static unsigned int free_huge_pages_node[MAX_NUMNODES];
 static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
-int hugetlb_dynamic_pool;
+unsigned long nr_overcommit_huge_pages;
 static int hugetlb_next_nid;
 
 /*
@@ -227,22 +227,58 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 						unsigned long address)
 {
 	struct page *page;
+	unsigned int nid;
 
-	/* Check if the dynamic pool is enabled */
-	if (!hugetlb_dynamic_pool)
+	/*
+	 * Assume we will successfully allocate the surplus page to
+	 * prevent racing processes from causing the surplus to exceed
+	 * overcommit
+	 *
+	 * This however introduces a different race, where a process B
+	 * tries to grow the static hugepage pool while alloc_pages() is
+	 * called by process A. B will only examine the per-node
+	 * counters in determining if surplus huge pages can be
+	 * converted to normal huge pages in adjust_pool_surplus(). A
+	 * won't be able to increment the per-node counter, until the
+	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
+	 * no more huge pages can be converted from surplus to normal
+	 * state (and doesn't try to convert again). Thus, we have a
+	 * case where a surplus huge page exists, the pool is grown, and
+	 * the surplus huge page still exists after, even though it
+	 * should just have been converted to a normal huge page. This
+	 * does not leak memory, though, as the hugepage will be freed
+	 * once it is out of use. It also does not allow the counters to
+	 * go out of whack in adjust_pool_surplus() as we don't modify
+	 * the node values until we've gotten the hugepage and only the
+	 * per-node value is checked there.
+	 */
+	spin_lock(&hugetlb_lock);
+	if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+		spin_unlock(&hugetlb_lock);
 		return NULL;
+	} else {
+		nr_huge_pages++;
+		surplus_huge_pages++;
+	}
+	spin_unlock(&hugetlb_lock);
 
 	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
+
+	spin_lock(&hugetlb_lock);
 	if (page) {
+		nid = page_to_nid(page);
 		set_compound_page_dtor(page, free_huge_page);
-		spin_lock(&hugetlb_lock);
-		nr_huge_pages++;
-		nr_huge_pages_node[page_to_nid(page)]++;
-		surplus_huge_pages++;
-		surplus_huge_pages_node[page_to_nid(page)]++;
-		spin_unlock(&hugetlb_lock);
+		/*
+		 * We incremented the global counters already
+		 */
+		nr_huge_pages_node[nid]++;
+		surplus_huge_pages_node[nid]++;
+	} else {
+		nr_huge_pages--;
+		surplus_huge_pages--;
 	}
+	spin_unlock(&hugetlb_lock);
 
 	return page;
 }
@@ -481,6 +517,12 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	 * Increase the pool size
 	 * First take pages out of surplus state.  Then make up the
 	 * remaining difference by allocating fresh huge pages.
+	 *
+	 * We might race with alloc_buddy_huge_page() here and be unable
+	 * to convert a surplus huge page to a normal huge page. That is
+	 * not critical, though, it just means the overall size of the
+	 * pool might be one hugepage larger than it needs to be, but
+	 * within all the constraints specified by the sysctls.
 	 */
 	spin_lock(&hugetlb_lock);
 	while (surplus_huge_pages && count > persistent_huge_pages) {
@@ -509,6 +551,14 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	 * to keep enough around to satisfy reservations).  Then place
 	 * pages into surplus state as needed so the pool will shrink
 	 * to the desired size as pages become free.
+	 *
+	 * By placing pages into the surplus state independent of the
+	 * overcommit value, we are allowing the surplus pool size to
+	 * exceed overcommit. There are few sane options here. Since
+	 * alloc_buddy_huge_page() is checking the global counter,
+	 * though, we'll note that we're not allowed to exceed surplus
+	 * and won't grow the pool anywhere else. Not until one of the
+	 * sysctls are changed, or the surplus pages go out of use.
 	 */
 	min_count = resv_huge_pages + nr_huge_pages - free_huge_pages;
 	min_count = max(count, min_count);
@@ -907,7 +957,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-		if (!pte || pte_none(*pte)) {
+		if (!pte || pte_none(*pte) || (write && !pte_write(*pte))) {
 			int ret;
 
 			spin_unlock(&mm->page_table_lock);
diff --git a/mm/mmap.c b/mm/mmap.c
index facc1a75bd4..15678aa6ec7 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -912,6 +912,9 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	if (!len)
 		return -EINVAL;
 
+	if (!(flags & MAP_FIXED))
+		addr = round_hint_to_min(addr);
+
 	error = arch_mmap_check(addr, len, flags);
 	if (error)
 		return error;
@@ -1615,6 +1618,12 @@ static inline int expand_downwards(struct vm_area_struct *vma,
 	 */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
+
+	address &= PAGE_MASK;
+	error = security_file_mmap(0, 0, 0, 0, address, 1);
+	if (error)
+		return error;
+
 	anon_vma_lock(vma);
 
 	/*
@@ -1622,8 +1631,6 @@ static inline int expand_downwards(struct vm_area_struct *vma,
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
 	 */
-	address &= PAGE_MASK;
-	error = 0;
 
 	/* Somebody else might have raced and expanded it already */
 	if (address < vma->vm_start) {
@@ -1934,6 +1941,10 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (is_hugepage_only_range(mm, addr, len))
 		return -EINVAL;
 
+	error = security_file_mmap(0, 0, 0, 0, addr, 1);
+	if (error)
+		return error;
+
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = arch_mmap_check(addr, len, flags);
diff --git a/mm/nommu.c b/mm/nommu.c
index 35622c59092..b989cb928a7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -829,6 +829,9 @@ unsigned long do_mmap_pgoff(struct file *file,
 	void *result;
 	int ret;
 
+	if (!(flags & MAP_FIXED))
+		addr = round_hint_to_min(addr);
+
 	/* decide whether we should attempt the mapping, and if so what sort of
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 12376ae3f73..e1028fae3eb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -305,7 +305,6 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	int i;
 
-	VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
 	/*
 	 * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
 	 * and __GFP_HIGHMEM from hard or soft interrupt context.
@@ -848,8 +847,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		struct page *page = __rmqueue(zone, order, migratetype);
 		if (unlikely(page == NULL))
 			break;
+
+		/*
+		 * Split buddy pages returned by expand() are received here
+		 * in physical page order. The page is added to the callers and
+		 * list and the list head then moves forward. From the callers
+		 * perspective, the linked list is ordered by page number in
+		 * some conditions. This is useful for IO devices that can
+		 * merge IO requests if the physical pages are ordered
+		 * properly.
+		 */
 		list_add(&page->lru, list);
 		set_page_private(page, migratetype);
+		list = &page->lru;
 	}
 	spin_unlock(&zone->lock);
 	return i;
@@ -3266,6 +3276,16 @@ static void inline setup_usemap(struct pglist_data *pgdat,
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
+
+/* Return a sensible default order for the pageblock size. */
+static inline int pageblock_default_order(void)
+{
+	if (HPAGE_SHIFT > PAGE_SHIFT)
+		return HUGETLB_PAGE_ORDER;
+
+	return MAX_ORDER-1;
+}
+
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
 static inline void __init set_pageblock_order(unsigned int order)
 {
@@ -3281,7 +3301,16 @@ static inline void __init set_pageblock_order(unsigned int order)
 }
 #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-/* Defined this way to avoid accidently referencing HUGETLB_PAGE_ORDER */
+/*
+ * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
+ * and pageblock_default_order() are unused as pageblock_order is set
+ * at compile-time. See include/linux/pageblock-flags.h for the values of
+ * pageblock_order based on the kernel config
+ */
+static inline int pageblock_default_order(unsigned int order)
+{
+	return MAX_ORDER-1;
+}
 #define set_pageblock_order(x)	do {} while (0)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
@@ -3366,7 +3395,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		if (!size)
 			continue;
 
-		set_pageblock_order(HUGETLB_PAGE_ORDER);
+		set_pageblock_order(pageblock_default_order());
 		setup_usemap(pgdat, zone, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);
@@ -3409,7 +3438,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		mem_map = NODE_DATA(0)->node_mem_map;
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
-			mem_map -= pgdat->node_start_pfn;
+			mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 	}
 #endif
diff --git a/mm/rmap.c b/mm/rmap.c
index dc3be5f5b0d..dbc2ca2057a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -471,11 +471,12 @@ int page_mkclean(struct page *page)
 
 	if (page_mapped(page)) {
 		struct address_space *mapping = page_mapping(page);
-		if (mapping)
+		if (mapping) {
 			ret = page_mkclean_file(mapping, page);
-		if (page_test_dirty(page)) {
-			page_clear_dirty(page);
-			ret = 1;
+			if (page_test_dirty(page)) {
+				page_clear_dirty(page);
+				ret = 1;
+			}
 		}
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 253d205914b..51b3d6ccdda 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1072,7 +1072,7 @@ shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
 	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
 	pvma.vm_pgoff = idx;
 	pvma.vm_end = PAGE_SIZE;
-	page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
+	page = alloc_page_vma(gfp, &pvma, 0);
 	mpol_free(pvma.vm_policy);
 	return page;
 }
@@ -1093,7 +1093,7 @@ shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx)
 static inline struct page *
 shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx)
 {
-	return alloc_page(gfp | __GFP_ZERO);
+	return alloc_page(gfp);
 }
 #endif
 
@@ -1306,6 +1306,7 @@ repeat:
 
 		info->alloced++;
 		spin_unlock(&info->lock);
+		clear_highpage(filepage);
 		flush_dcache_page(filepage);
 		SetPageUptodate(filepage);
 	}
diff --git a/mm/slab.c b/mm/slab.c
index c31cd3682a0..aebb9f68557 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2881,6 +2881,8 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	unsigned int objnr;
 	struct slab *slabp;
 
+	BUG_ON(virt_to_cache(objp) != cachep);
+
 	objp -= obj_offset(cachep);
 	kfree_debugcheck(objp);
 	page = virt_to_head_page(objp);
@@ -3759,8 +3761,6 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
 	unsigned long flags;
 
-	BUG_ON(virt_to_cache(objp) != cachep);
-
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, obj_size(cachep));
 	__cache_free(cachep, objp);
@@ -4105,7 +4105,7 @@ out:
 	schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
 }
 
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_SLABINFO
 
 static void print_slabinfo_header(struct seq_file *m)
 {
@@ -4475,3 +4475,4 @@ size_t ksize(const void *objp)
 
 	return obj_size(virt_to_cache(objp));
 }
+EXPORT_SYMBOL(ksize);
diff --git a/mm/slob.c b/mm/slob.c
index 08a9bd91a1a..773a7aa80ab 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -330,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 
 	/* Not enough space: must allocate a new page */
 	if (!b) {
-		b = slob_new_page(gfp, 0, node);
+		b = slob_new_page(gfp & ~__GFP_ZERO, 0, node);
 		if (!b)
 			return 0;
 		sp = (struct slob_page *)virt_to_page(b);
@@ -495,6 +495,7 @@ size_t ksize(const void *block)
 	else
 		return sp->page.private;
 }
+EXPORT_SYMBOL(ksize);
 
 struct kmem_cache {
 	unsigned int size, align;
diff --git a/mm/slub.c b/mm/slub.c
index 9acb413858a..474945ecd89 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -172,7 +172,7 @@ static inline void ClearSlabDebug(struct page *page)
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
  */
-#define MIN_PARTIAL 2
+#define MIN_PARTIAL 5
 
 /*
  * Maximum number of desirable partial slabs.
@@ -1613,7 +1613,7 @@ checks_ok:
 	 * then add it.
 	 */
 	if (unlikely(!prior))
-		add_partial(get_node(s, page_to_nid(page)), page);
+		add_partial_tail(get_node(s, page_to_nid(page)), page);
 
 out_unlock:
 	slab_unlock(page);
@@ -2558,8 +2558,12 @@ size_t ksize(const void *object)
 	if (unlikely(object == ZERO_SIZE_PTR))
 		return 0;
 
-	page = get_object_page(object);
+	page = virt_to_head_page(object);
 	BUG_ON(!page);
+
+	if (unlikely(!PageSlab(page)))
+		return PAGE_SIZE << compound_order(page);
+
 	s = page->slab;
 	BUG_ON(!s);
 
@@ -3072,6 +3076,19 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	return slab_alloc(s, gfpflags, node, caller);
 }
 
+static unsigned long count_partial(struct kmem_cache_node *n)
+{
+	unsigned long flags;
+	unsigned long x = 0;
+	struct page *page;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	list_for_each_entry(page, &n->partial, lru)
+		x += page->inuse;
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	return x;
+}
+
 #if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
@@ -3454,19 +3471,6 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	return n;
 }
 
-static unsigned long count_partial(struct kmem_cache_node *n)
-{
-	unsigned long flags;
-	unsigned long x = 0;
-	struct page *page;
-
-	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(page, &n->partial, lru)
-		x += page->inuse;
-	spin_unlock_irqrestore(&n->list_lock, flags);
-	return x;
-}
-
 enum slab_stat_type {
 	SL_FULL,
 	SL_PARTIAL,
@@ -4119,3 +4123,89 @@ static int __init slab_sysfs_init(void)
 
 __initcall(slab_sysfs_init);
 #endif
+
+/*
+ * The /proc/slabinfo ABI
+ */
+#ifdef CONFIG_SLABINFO
+
+ssize_t slabinfo_write(struct file *file, const char __user * buffer,
+                       size_t count, loff_t *ppos)
+{
+	return -EINVAL;
+}
+
+
+static void print_slabinfo_header(struct seq_file *m)
+{
+	seq_puts(m, "slabinfo - version: 2.1\n");
+	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> "
+		 "<objperslab> <pagesperslab>");
+	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
+	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
+	seq_putc(m, '\n');
+}
+
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t n = *pos;
+
+	down_read(&slub_lock);
+	if (!n)
+		print_slabinfo_header(m);
+
+	return seq_list_start(&slab_caches, *pos);
+}
+
+static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &slab_caches, pos);
+}
+
+static void s_stop(struct seq_file *m, void *p)
+{
+	up_read(&slub_lock);
+}
+
+static int s_show(struct seq_file *m, void *p)
+{
+	unsigned long nr_partials = 0;
+	unsigned long nr_slabs = 0;
+	unsigned long nr_inuse = 0;
+	unsigned long nr_objs;
+	struct kmem_cache *s;
+	int node;
+
+	s = list_entry(p, struct kmem_cache, list);
+
+	for_each_online_node(node) {
+		struct kmem_cache_node *n = get_node(s, node);
+
+		if (!n)
+			continue;
+
+		nr_partials += n->nr_partial;
+		nr_slabs += atomic_long_read(&n->nr_slabs);
+		nr_inuse += count_partial(n);
+	}
+
+	nr_objs = nr_slabs * s->objects;
+	nr_inuse += (nr_slabs - nr_partials) * s->objects;
+
+	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
+		   nr_objs, s->size, s->objects, (1 << s->order));
+	seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
+	seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
+		   0UL);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+const struct seq_operations slabinfo_op = {
+	.start = s_start,
+	.next = s_next,
+	.stop = s_stop,
+	.show = s_show,
+};
+
+#endif /* CONFIG_SLABINFO */
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 22620f6a976..cd75b21dd4c 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -34,6 +34,16 @@
  * or to back the page tables that are used to create the mapping.
  * Uses the main allocators if they are available, else bootmem.
  */
+
+static void * __init_refok __earlyonly_bootmem_alloc(int node,
+				unsigned long size,
+				unsigned long align,
+				unsigned long goal)
+{
+	return __alloc_bootmem_node(NODE_DATA(node), size, align, goal);
+}
+
+
 void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 {
 	/* If the main allocator is up use that, fallback to bootmem. */
@@ -44,7 +54,7 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 			return page_address(page);
 		return NULL;
 	} else
-		return __alloc_bootmem_node(NODE_DATA(node), size, size,
+		return __earlyonly_bootmem_alloc(node, size, size,
 				__pa(MAX_DMA_ADDRESS));
 }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index e06f514fe04..a2183cb5d52 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -83,6 +83,8 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 		return -EEXIST;
 
 	section = sparse_index_alloc(nid);
+	if (!section)
+		return -ENOMEM;
 	/*
 	 * This lock keeps two different sections from
 	 * reallocating for the same index
@@ -389,9 +391,17 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	 * no locking for this, because it does its own
 	 * plus, it does a kmalloc
 	 */
-	sparse_index_init(section_nr, pgdat->node_id);
+	ret = sparse_index_init(section_nr, pgdat->node_id);
+	if (ret < 0 && ret != -EEXIST)
+		return ret;
 	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+	if (!memmap)
+		return -ENOMEM;
 	usemap = __kmalloc_section_usemap();
+	if (!usemap) {
+		__kfree_section_memmap(memmap, nr_pages);
+		return -ENOMEM;
+	}
 
 	pgdat_resize_lock(pgdat, &flags);
 
@@ -401,18 +411,16 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
-	if (!usemap) {
-		ret = -ENOMEM;
-		goto out;
-	}
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
 	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
 
 out:
 	pgdat_resize_unlock(pgdat, &flags);
-	if (ret <= 0)
+	if (ret <= 0) {
+		kfree(usemap);
 		__kfree_section_memmap(memmap, nr_pages);
+	}
 	return ret;
 }
 #endif