Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify updates

 - ocfs2 updates

 - all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (127 commits)
  console: don't prefer first registered if DT specifies stdout-path
  cred: simpler, 1D supplementary groups
  CREDITS: update Pavel's information, add GPG key, remove snail mail address
  mailmap: add Johan Hovold
  .gitattributes: set git diff driver for C source code files
  uprobes: remove function declarations from arch/{mips,s390}
  spelling.txt: "modeled" is spelt correctly
  nmi_backtrace: generate one-line reports for idle cpus
  arch/tile: adopt the new nmi_backtrace framework
  nmi_backtrace: do a local dump_stack() instead of a self-NMI
  nmi_backtrace: add more trigger_*_cpu_backtrace() methods
  min/max: remove sparse warnings when they're nested
  Documentation/filesystems/proc.txt: add more description for maps/smaps
  mm, proc: fix region lost in /proc/self/smaps
  proc: fix timerslack_ns CAP_SYS_NICE check when adjusting self
  proc: add LSM hook checks to /proc/<tid>/timerslack_ns
  proc: relax /proc/<tid>/timerslack_ns capability requirements
  meminfo: break apart a very long seq_printf with #ifdefs
  seq/proc: modify seq_put_decimal_[u]ll to take a const char *, not char
  proc: faster /proc/*/status
  ...

1 files changed, 33 insertions, 12 deletions

diff --git a/mm/page_ext.c b/mm/page_ext.c
index 44a4c029c8e79..121dcffc4ec17 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -42,6 +42,11 @@
  * and page extension core can skip to allocate memory. As result,
  * none of memory is wasted.
  *
+ * When need callback returns true, page_ext checks if there is a request for
+ * extra memory through size in struct page_ext_operations. If it is non-zero,
+ * extra space is allocated for each page_ext entry and offset is returned to
+ * user through offset in struct page_ext_operations.
+ *
  * The init callback is used to do proper initialization after page extension
  * is completely initialized. In sparse memory system, extra memory is
  * allocated some time later than memmap is allocated. In other words, lifetime
@@ -66,18 +71,24 @@ static struct page_ext_operations *page_ext_ops[] = {
 };
 
 static unsigned long total_usage;
+static unsigned long extra_mem;
 
 static bool __init invoke_need_callbacks(void)
 {
 	int i;
 	int entries = ARRAY_SIZE(page_ext_ops);
+	bool need = false;
 
 	for (i = 0; i < entries; i++) {
-		if (page_ext_ops[i]->need && page_ext_ops[i]->need())
-			return true;
+		if (page_ext_ops[i]->need && page_ext_ops[i]->need()) {
+			page_ext_ops[i]->offset = sizeof(struct page_ext) +
+						extra_mem;
+			extra_mem += page_ext_ops[i]->size;
+			need = true;
+		}
 	}
 
-	return false;
+	return need;
 }
 
 static void __init invoke_init_callbacks(void)
@@ -91,6 +102,16 @@ static void __init invoke_init_callbacks(void)
 	}
 }
 
+static unsigned long get_entry_size(void)
+{
+	return sizeof(struct page_ext) + extra_mem;
+}
+
+static inline struct page_ext *get_entry(void *base, unsigned long index)
+{
+	return base + get_entry_size() * index;
+}
+
 #if !defined(CONFIG_SPARSEMEM)
 
 
@@ -102,7 +123,7 @@ void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
 struct page_ext *lookup_page_ext(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset;
+	unsigned long index;
 	struct page_ext *base;
 
 	base = NODE_DATA(page_to_nid(page))->node_page_ext;
@@ -119,9 +140,9 @@ struct page_ext *lookup_page_ext(struct page *page)
 	if (unlikely(!base))
 		return NULL;
 #endif
-	offset = pfn - round_down(node_start_pfn(page_to_nid(page)),
+	index = pfn - round_down(node_start_pfn(page_to_nid(page)),
 					MAX_ORDER_NR_PAGES);
-	return base + offset;
+	return get_entry(base, index);
 }
 
 static int __init alloc_node_page_ext(int nid)
@@ -143,7 +164,7 @@ static int __init alloc_node_page_ext(int nid)
 		!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
 		nr_pages += MAX_ORDER_NR_PAGES;
 
-	table_size = sizeof(struct page_ext) * nr_pages;
+	table_size = get_entry_size() * nr_pages;
 
 	base = memblock_virt_alloc_try_nid_nopanic(
 			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -196,7 +217,7 @@ struct page_ext *lookup_page_ext(struct page *page)
 	if (!section->page_ext)
 		return NULL;
 #endif
-	return section->page_ext + pfn;
+	return get_entry(section->page_ext, pfn);
 }
 
 static void *__meminit alloc_page_ext(size_t size, int nid)
@@ -229,7 +250,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	if (section->page_ext)
 		return 0;
 
-	table_size = sizeof(struct page_ext) * PAGES_PER_SECTION;
+	table_size = get_entry_size() * PAGES_PER_SECTION;
 	base = alloc_page_ext(table_size, nid);
 
 	/*
@@ -249,7 +270,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	 * we need to apply a mask.
 	 */
 	pfn &= PAGE_SECTION_MASK;
-	section->page_ext = base - pfn;
+	section->page_ext = (void *)base - get_entry_size() * pfn;
 	total_usage += table_size;
 	return 0;
 }
@@ -262,7 +283,7 @@ static void free_page_ext(void *addr)
 		struct page *page = virt_to_page(addr);
 		size_t table_size;
 
-		table_size = sizeof(struct page_ext) * PAGES_PER_SECTION;
+		table_size = get_entry_size() * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
 		free_pages_exact(addr, table_size);
@@ -277,7 +298,7 @@ static void __free_page_ext(unsigned long pfn)
 	ms = __pfn_to_section(pfn);
 	if (!ms || !ms->page_ext)
 		return;
-	base = ms->page_ext + pfn;
+	base = get_entry(ms->page_ext, pfn);
 	free_page_ext(base);
 	ms->page_ext = NULL;
 }