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
  ...

mm/huge_memory.c

@@ -990,7 +990,7 @@ struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON(!PageCompound(page));
 	if (flags & FOLL_GET)
-		get_page(page);
+		get_page_foll(page);
 
 out:
 	return page;
@@ -1202,6 +1202,7 @@ static void __split_huge_page_refcount(struct page *page)
 	unsigned long head_index = page->index;
 	struct zone *zone = page_zone(page);
 	int zonestat;
+	int tail_count = 0;
 
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
 	spin_lock_irq(&zone->lru_lock);
@@ -1210,11 +1211,27 @@ static void __split_huge_page_refcount(struct page *page)
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		struct page *page_tail = page + i;
 
-		/* tail_page->_count cannot change */
-		atomic_sub(atomic_read(&page_tail->_count), &page->_count);
-		BUG_ON(page_count(page) <= 0);
-		atomic_add(page_mapcount(page) + 1, &page_tail->_count);
-		BUG_ON(atomic_read(&page_tail->_count) <= 0);
+		/* tail_page->_mapcount cannot change */
+		BUG_ON(page_mapcount(page_tail) < 0);
+		tail_count += page_mapcount(page_tail);
+		/* check for overflow */
+		BUG_ON(tail_count < 0);
+		BUG_ON(atomic_read(&page_tail->_count) != 0);
+		/*
+		 * tail_page->_count is zero and not changing from
+		 * under us. But get_page_unless_zero() may be running
+		 * from under us on the tail_page. If we used
+		 * atomic_set() below instead of atomic_add(), we
+		 * would then run atomic_set() concurrently with
+		 * get_page_unless_zero(), and atomic_set() is
+		 * implemented in C not using locked ops. spin_unlock
+		 * on x86 sometime uses locked ops because of PPro
+		 * errata 66, 92, so unless somebody can guarantee
+		 * atomic_set() here would be safe on all archs (and
+		 * not only on x86), it's safer to use atomic_add().
+		 */
+		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
+			   &page_tail->_count);
 
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb();
@@ -1232,10 +1249,7 @@ static void __split_huge_page_refcount(struct page *page)
 				      (1L << PG_uptodate)));
 		page_tail->flags |= (1L << PG_dirty);
 
-		/*
-		 * 1) clear PageTail before overwriting first_page
-		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
-		 */
+		/* clear PageTail before overwriting first_page */
 		smp_wmb();
 
 		/*
@@ -1252,7 +1266,6 @@ static void __split_huge_page_refcount(struct page *page)
 		 * status is achieved setting a reserved bit in the
 		 * pmd, not by clearing the present bit.
 		*/
-		BUG_ON(page_mapcount(page_tail));
 		page_tail->_mapcount = page->_mapcount;
 
 		BUG_ON(page_tail->mapping);
@@ -1269,6 +1282,8 @@ static void __split_huge_page_refcount(struct page *page)
 
 		lru_add_page_tail(zone, page, page_tail);
 	}
+	atomic_sub(tail_count, &page->_count);
+	BUG_ON(atomic_read(&page->_count) <= 0);
 
 	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
 	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);

mm/internal.h

@@ -37,6 +37,52 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+static inline void __get_page_tail_foll(struct page *page,
+					bool get_page_head)
+{
+	/*
+	 * If we're getting a tail page, the elevated page->_count is
+	 * required only in the head page and we will elevate the head
+	 * page->_count and tail page->_mapcount.
+	 *
+	 * We elevate page_tail->_mapcount for tail pages to force
+	 * page_tail->_count to be zero at all times to avoid getting
+	 * false positives from get_page_unless_zero() with
+	 * speculative page access (like in
+	 * page_cache_get_speculative()) on tail pages.
+	 */
+	VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+	VM_BUG_ON(atomic_read(&page->_count) != 0);
+	VM_BUG_ON(page_mapcount(page) < 0);
+	if (get_page_head)
+		atomic_inc(&page->first_page->_count);
+	atomic_inc(&page->_mapcount);
+}
+
+/*
+ * This is meant to be called as the FOLL_GET operation of
+ * follow_page() and it must be called while holding the proper PT
+ * lock while the pte (or pmd_trans_huge) is still mapping the page.
+ */
+static inline void get_page_foll(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		/*
+		 * This is safe only because
+		 * __split_huge_page_refcount() can't run under
+		 * get_page_foll() because we hold the proper PT lock.
+		 */
+		__get_page_tail_foll(page, true);
+	else {
+		/*
+		 * Getting a normal page or the head of a compound page
+		 * requires to already have an elevated page->_count.
+		 */
+		VM_BUG_ON(atomic_read(&page->_count) <= 0);
+		atomic_inc(&page->_count);
+	}
+}
+
 extern unsigned long highest_memmap_pfn;
 
 /*

mm/memory.c

@@ -1503,7 +1503,7 @@ split_fallthrough:
 	}
 
 	if (flags & FOLL_GET)
-		get_page(page);
+		get_page_foll(page);
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))

mm/page_cgroup.c

@@ -133,10 +133,13 @@ struct page *lookup_cgroup_page(struct page_cgroup *pc)
 static void *__meminit alloc_page_cgroup(size_t size, int nid)
 {
 	void *addr = NULL;
+	gfp_t flags = GFP_KERNEL | __GFP_NOWARN;
 
-	addr = alloc_pages_exact_nid(nid, size, GFP_KERNEL | __GFP_NOWARN);
-	if (addr)
+	addr = alloc_pages_exact_nid(nid, size, flags);
+	if (addr) {
+		kmemleak_alloc(addr, size, 1, flags);
 		return addr;
+	}
 
 	if (node_state(nid, N_HIGH_MEMORY))
 		addr = vmalloc_node(size, nid);
@@ -357,7 +360,7 @@ struct swap_cgroup_ctrl {
 	spinlock_t	lock;
 };
 
-struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
 struct swap_cgroup {
 	unsigned short		id;

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

mm/vmscan.c

@@ -1767,7 +1767,7 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
 	if (scanning_global_lru(sc))
 		low = inactive_anon_is_low_global(zone);
 	else
-		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup, zone);
 	return low;
 }
 #else
@@ -1810,7 +1810,7 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
 	if (scanning_global_lru(sc))
 		low = inactive_file_is_low_global(zone);
 	else
-		low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+		low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup, zone);
 	return low;
 }