Merge branch 'akpm' (Andrew's incoming - part two)

Says Andrew:

 "60 patches.  That's good enough for -rc1 I guess.  I have quite a lot
  of detritus to be rechecked, work through maintainers, etc.

 - most of the remains of MM
 - rtc
 - various misc
 - cgroups
 - memcg
 - cpusets
 - procfs
 - ipc
 - rapidio
 - sysctl
 - pps
 - w1
 - drivers/misc
 - aio"

* akpm: (60 commits)
  memcg: replace ss->id_lock with a rwlock
  aio: allocate kiocbs in batches
  drivers/misc/vmw_balloon.c: fix typo in code comment
  drivers/misc/vmw_balloon.c: determine page allocation flag can_sleep outside loop
  w1: disable irqs in critical section
  drivers/w1/w1_int.c: multiple masters used same init_name
  drivers/power/ds2780_battery.c: fix deadlock upon insertion and removal
  drivers/power/ds2780_battery.c: add a nolock function to w1 interface
  drivers/power/ds2780_battery.c: create central point for calling w1 interface
  w1: ds2760 and ds2780, use ida for id and ida_simple_get() to get it
  pps gpio client: add missing dependency
  pps: new client driver using GPIO
  pps: default echo function
  include/linux/dma-mapping.h: add dma_zalloc_coherent()
  sysctl: make CONFIG_SYSCTL_SYSCALL default to n
  sysctl: add support for poll()
  RapidIO: documentation update
  drivers/net/rionet.c: fix ethernet address macros for LE platforms
  RapidIO: fix potential null deref in rio_setup_device()
  RapidIO: add mport driver for Tsi721 bridge
  ...

1 files changed, 53 insertions, 30 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 3a442f1..87627f1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,39 +78,22 @@ static void put_compound_page(struct page *page)
 {
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
-		struct page *page_head = page->first_page;
-		smp_rmb();
-		/*
-		 * If PageTail is still set after smp_rmb() we can be sure
-		 * that the page->first_page we read wasn't a dangling pointer.
-		 * See __split_huge_page_refcount() smp_wmb().
-		 */
-		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+		struct page *page_head = compound_trans_head(page);
+
+		if (likely(page != page_head &&
+			   get_page_unless_zero(page_head))) {
 			unsigned long flags;
 			/*
-			 * Verify that our page_head wasn't converted
-			 * to a a regular page before we got a
-			 * reference on it.
+			 * page_head wasn't a dangling pointer but it
+			 * may not be a head page anymore by the time
+			 * we obtain the lock. That is ok as long as it
+			 * can't be freed from under us.
 			 */
-			if (unlikely(!PageHead(page_head))) {
-				/* PageHead is cleared after PageTail */
-				smp_rmb();
-				VM_BUG_ON(PageTail(page));
-				goto out_put_head;
-			}
-			/*
-			 * Only run compound_lock on a valid PageHead,
-			 * after having it pinned with
-			 * get_page_unless_zero() above.
-			 */
-			smp_mb();
-			/* page_head wasn't a dangling pointer */
 			flags = compound_lock_irqsave(page_head);
 			if (unlikely(!PageTail(page))) {
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 				VM_BUG_ON(PageHead(page_head));
-			out_put_head:
 				if (put_page_testzero(page_head))
 					__put_single_page(page_head);
 			out_put_single:
@@ -121,16 +104,17 @@ static void put_compound_page(struct page *page)
 			VM_BUG_ON(page_head != page->first_page);
 			/*
 			 * We can release the refcount taken by
-			 * get_page_unless_zero now that
-			 * split_huge_page_refcount is blocked on the
-			 * compound_lock.
+			 * get_page_unless_zero() now that
+			 * __split_huge_page_refcount() is blocked on
+			 * the compound_lock.
 			 */
 			if (put_page_testzero(page_head))
 				VM_BUG_ON(1);
 			/* __split_huge_page_refcount will wait now */
-			VM_BUG_ON(atomic_read(&page->_count) <= 0);
-			atomic_dec(&page->_count);
+			VM_BUG_ON(page_mapcount(page) <= 0);
+			atomic_dec(&page->_mapcount);
 			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
@@ -160,6 +144,45 @@ void put_page(struct page *page)
 }
 EXPORT_SYMBOL(put_page);
 
+/*
+ * This function is exported but must not be called by anything other
+ * than get_page(). It implements the slow path of get_page().
+ */
+bool __get_page_tail(struct page *page)
+{
+	/*
+	 * This takes care of get_page() if run on a tail page
+	 * returned by one of the get_user_pages/follow_page variants.
+	 * get_user_pages/follow_page itself doesn't need the compound
+	 * lock because it runs __get_page_tail_foll() under the
+	 * proper PT lock that already serializes against
+	 * split_huge_page().
+	 */
+	unsigned long flags;
+	bool got = false;
+	struct page *page_head = compound_trans_head(page);
+
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		/*
+		 * page_head wasn't a dangling pointer but it
+		 * may not be a head page anymore by the time
+		 * we obtain the lock. That is ok as long as it
+		 * can't be freed from under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		/* here __split_huge_page_refcount won't run anymore */
+		if (likely(PageTail(page))) {
+			__get_page_tail_foll(page, false);
+			got = true;
+		}
+		compound_unlock_irqrestore(page_head, flags);
+		if (unlikely(!got))
+			put_page(page_head);
+	}
+	return got;
+}
+EXPORT_SYMBOL(__get_page_tail);
+
 /**
  * put_pages_list() - release a list of pages
  * @pages: list of pages threaded on page->lru