Merge branch 'akpm' (Andrew's fixes)

Merge misc fixes from Andrew Morton:
 "18 total.  15 fixes and some updates to a device_cgroup patchset which
  bring it up to date with the version which I should have merged in the
  first place."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (18 patches)
  fs/compat_ioctl.c: VIDEO_SET_SPU_PALETTE missing error check
  gen_init_cpio: avoid stack overflow when expanding
  drivers/rtc/rtc-imxdi.c: add missing spin lock initialization
  mm, numa: avoid setting zone_reclaim_mode unless a node is sufficiently distant
  pidns: limit the nesting depth of pid namespaces
  drivers/dma/dw_dmac: make driver's endianness configurable
  mm/mmu_notifier: allocate mmu_notifier in advance
  tools/testing/selftests/epoll/test_epoll.c: fix build
  UAPI: fix tools/vm/page-types.c
  mm/page_alloc.c:alloc_contig_range(): return early for err path
  rbtree: include linux/compiler.h for definition of __always_inline
  genalloc: stop crashing the system when destroying a pool
  backlight: ili9320: add missing SPI dependency
  device_cgroup: add proper checking when changing default behavior
  device_cgroup: stop using simple_strtoul()
  device_cgroup: rename deny_all to behavior
  cgroup: fix invalid rcu dereference
  mm: fix XFS oops due to dirty pages without buffers on s390

3 files changed, 30 insertions, 20 deletions

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 479a1e7..8a5ac8c 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -196,28 +196,28 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 
 	/*
-	* Verify that mmu_notifier_init() already run and the global srcu is
-	* initialized.
-	*/
+	 * Verify that mmu_notifier_init() already run and the global srcu is
+	 * initialized.
+	 */
 	BUG_ON(!srcu.per_cpu_ref);
 
+	ret = -ENOMEM;
+	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
+	if (unlikely(!mmu_notifier_mm))
+		goto out;
+
 	if (take_mmap_sem)
 		down_write(&mm->mmap_sem);
 	ret = mm_take_all_locks(mm);
 	if (unlikely(ret))
-		goto out;
+		goto out_clean;
 
 	if (!mm_has_notifiers(mm)) {
-		mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm),
-					GFP_KERNEL);
-		if (unlikely(!mmu_notifier_mm)) {
-			ret = -ENOMEM;
-			goto out_of_mem;
-		}
 		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
 		spin_lock_init(&mmu_notifier_mm->lock);
 
 		mm->mmu_notifier_mm = mmu_notifier_mm;
+		mmu_notifier_mm = NULL;
 	}
 	atomic_inc(&mm->mm_count);
 
@@ -233,12 +233,12 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 	hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
-out_of_mem:
 	mm_drop_all_locks(mm);
-out:
+out_clean:
 	if (take_mmap_sem)
 		up_write(&mm->mmap_sem);
-
+	kfree(mmu_notifier_mm);
+out:
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 	return ret;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b0012ab..5b74de6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1809,10 +1809,10 @@ static void __paginginit init_zone_allows_reclaim(int nid)
 	int i;
 
 	for_each_online_node(i)
-		if (node_distance(nid, i) <= RECLAIM_DISTANCE) {
+		if (node_distance(nid, i) <= RECLAIM_DISTANCE)
 			node_set(i, NODE_DATA(nid)->reclaim_nodes);
+		else
 			zone_reclaim_mode = 1;
-		}
 }
 
 #else	/* CONFIG_NUMA */
diff --git a/mm/rmap.c b/mm/rmap.c
index 7df7984..2ee1ef0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -56,6 +56,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
+#include <linux/backing-dev.h>
 
 #include <asm/tlbflush.h>
 
@@ -926,11 +927,8 @@ 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_and_clear_dirty(page_to_pfn(page), 1))
-				ret = 1;
-		}
 	}
 
 	return ret;
@@ -1116,6 +1114,7 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
+	struct address_space *mapping = page_mapping(page);
 	bool anon = PageAnon(page);
 	bool locked;
 	unsigned long flags;
@@ -1138,8 +1137,19 @@ void page_remove_rmap(struct page *page)
 	 * this if the page is anon, so about to be freed; but perhaps
 	 * not if it's in swapcache - there might be another pte slot
 	 * containing the swap entry, but page not yet written to swap.
+	 *
+	 * And we can skip it on file pages, so long as the filesystem
+	 * participates in dirty tracking; but need to catch shm and tmpfs
+	 * and ramfs pages which have been modified since creation by read
+	 * fault.
+	 *
+	 * Note that mapping must be decided above, before decrementing
+	 * mapcount (which luckily provides a barrier): once page is unmapped,
+	 * it could be truncated and page->mapping reset to NULL at any moment.
+	 * Note also that we are relying on page_mapping(page) to set mapping
+	 * to &swapper_space when PageSwapCache(page).
 	 */
-	if ((!anon || PageSwapCache(page)) &&
+	if (mapping && !mapping_cap_account_dirty(mapping) &&
 	    page_test_and_clear_dirty(page_to_pfn(page), 1))
 		set_page_dirty(page);
 	/*