Merge branch 'akpm' (aka "Andrew's patch-bomb")

Andrew elucidates:
 - First installmeant of MM.  We have a HUGE number of MM patches this
   time.  It's crazy.
 - MAINTAINERS updates
 - backlight updates
 - leds
 - checkpatch updates
 - misc ELF stuff
 - rtc updates
 - reiserfs
 - procfs
 - some misc other bits

* akpm: (124 commits)
  user namespace: make signal.c respect user namespaces
  workqueue: make alloc_workqueue() take printf fmt and args for name
  procfs: add hidepid= and gid= mount options
  procfs: parse mount options
  procfs: introduce the /proc/<pid>/map_files/ directory
  procfs: make proc_get_link to use dentry instead of inode
  signal: add block_sigmask() for adding sigmask to current->blocked
  sparc: make SA_NOMASK a synonym of SA_NODEFER
  reiserfs: don't lock root inode searching
  reiserfs: don't lock journal_init()
  reiserfs: delay reiserfs lock until journal initialization
  reiserfs: delete comments referring to the BKL
  drivers/rtc/interface.c: fix alarm rollover when day or month is out-of-range
  drivers/rtc/rtc-twl.c: add DT support for RTC inside twl4030/twl6030
  drivers/rtc/: remove redundant spi driver bus initialization
  drivers/rtc/rtc-jz4740.c: make jz4740_rtc_driver static
  drivers/rtc/rtc-mc13xxx.c: make mc13xxx_rtc_idtable static
  rtc: convert drivers/rtc/* to use module_platform_driver()
  drivers/rtc/rtc-wm831x.c: convert to devm_kzalloc()
  drivers/rtc/rtc-wm831x.c: remove unused period IRQ handler
  ...

20 files changed, 615 insertions, 313 deletions

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 8b1a477162dc..4b2443254de2 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -4,6 +4,7 @@ config DEBUG_PAGEALLOC
 	depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC
 	depends on !KMEMCHECK
 	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
 	  This results in a large slowdown, but helps to find certain types
@@ -22,3 +23,7 @@ config WANT_PAGE_DEBUG_FLAGS
 config PAGE_POISONING
 	bool
 	select WANT_PAGE_DEBUG_FLAGS
+
+config PAGE_GUARD
+	bool
+	select WANT_PAGE_DEBUG_FLAGS
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 1a77012ecdb3..668e94df8cf2 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -56,7 +56,7 @@ early_param("bootmem_debug", bootmem_debug_setup);
 
 static unsigned long __init bootmap_bytes(unsigned long pages)
 {
-	unsigned long bytes = (pages + 7) / 8;
+	unsigned long bytes = DIV_ROUND_UP(pages, 8);
 
 	return ALIGN(bytes, sizeof(long));
 }
@@ -171,7 +171,6 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
-	int aligned;
 	struct page *page;
 	unsigned long start, end, pages, count = 0;
 
@@ -181,14 +180,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	start = bdata->node_min_pfn;
 	end = bdata->node_low_pfn;
 
-	/*
-	 * If the start is aligned to the machines wordsize, we might
-	 * be able to free pages in bulks of that order.
-	 */
-	aligned = !(start & (BITS_PER_LONG - 1));
-
-	bdebug("nid=%td start=%lx end=%lx aligned=%d\n",
-		bdata - bootmem_node_data, start, end, aligned);
+	bdebug("nid=%td start=%lx end=%lx\n",
+		bdata - bootmem_node_data, start, end);
 
 	while (start < end) {
 		unsigned long *map, idx, vec;
@@ -196,12 +189,17 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
 		vec = ~map[idx / BITS_PER_LONG];
-
-		if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
+		/*
+		 * If we have a properly aligned and fully unreserved
+		 * BITS_PER_LONG block of pages in front of us, free
+		 * it in one go.
+		 */
+		if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
 			int order = ilog2(BITS_PER_LONG);
 
 			__free_pages_bootmem(pfn_to_page(start), order);
 			count += BITS_PER_LONG;
+			start += BITS_PER_LONG;
 		} else {
 			unsigned long off = 0;
 
@@ -214,8 +212,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 				vec >>= 1;
 				off++;
 			}
+			start = ALIGN(start + 1, BITS_PER_LONG);
 		}
-		start += BITS_PER_LONG;
 	}
 
 	page = virt_to_page(bdata->node_bootmem_map);
diff --git a/mm/compaction.c b/mm/compaction.c
index 1253d7ac332b..e6670c34eb49 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -365,8 +365,10 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		nr_isolated++;
 
 		/* Avoid isolating too much */
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
+			++low_pfn;
 			break;
+		}
 	}
 
 	acct_isolated(zone, cc);
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 8d723c9e8b75..469491e0af79 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -117,7 +117,8 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		break;
 	case POSIX_FADV_DONTNEED:
 		if (!bdi_write_congested(mapping->backing_dev_info))
-			filemap_flush(mapping);
+			__filemap_fdatawrite_range(mapping, offset, endbyte,
+						   WB_SYNC_NONE);
 
 		/* First and last FULL page! */
 		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
diff --git a/mm/filemap.c b/mm/filemap.c
index a0701e6eec10..c4ee2e918bea 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2351,8 +2351,11 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 					pgoff_t index, unsigned flags)
 {
 	int status;
+	gfp_t gfp_mask;
 	struct page *page;
 	gfp_t gfp_notmask = 0;
+
+	gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE;
 	if (flags & AOP_FLAG_NOFS)
 		gfp_notmask = __GFP_FS;
 repeat:
@@ -2360,7 +2363,7 @@ repeat:
 	if (page)
 		goto found;
 
-	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
+	page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
 	if (!page)
 		return NULL;
 	status = add_to_page_cache_lru(page, mapping, index,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7acd12503f73..ea8c3a4cd2ae 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -800,7 +800,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 
 	if (page && arch_prepare_hugepage(page)) {
 		__free_pages(page, huge_page_order(h));
-		return NULL;
+		page = NULL;
 	}
 
 	spin_lock(&hugetlb_lock);
@@ -2315,8 +2315,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * from page cache lookup which is in HPAGE_SIZE units.
 	 */
 	address = address & huge_page_mask(h);
-	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
-		+ (vma->vm_pgoff >> PAGE_SHIFT);
+	pgoff = vma_hugecache_offset(h, vma, address);
 	mapping = (struct address_space *)page_private(page);
 
 	/*
@@ -2349,6 +2348,9 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 
 /*
  * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ * Called with hugetlb_instantiation_mutex held and pte_page locked so we
+ * cannot race with other handlers or page migration.
+ * Keep the pte_same checks anyway to make transition from the mutex easier.
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
@@ -2408,7 +2410,14 @@ retry_avoidcopy:
 				BUG_ON(page_count(old_page) != 1);
 				BUG_ON(huge_pte_none(pte));
 				spin_lock(&mm->page_table_lock);
-				goto retry_avoidcopy;
+				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
+				if (likely(pte_same(huge_ptep_get(ptep), pte)))
+					goto retry_avoidcopy;
+				/*
+				 * race occurs while re-acquiring page_table_lock, and
+				 * our job is done.
+				 */
+				return 0;
 			}
 			WARN_ON_ONCE(1);
 		}
@@ -2630,6 +2639,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
 
+	address &= huge_page_mask(h);
+
 	ptep = huge_pte_offset(mm, address);
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c3fdbcb17658..e3d58f088466 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1983,28 +1983,28 @@ struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
 }
 
 /* Slow path of a mempolicy comparison */
-int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
+bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
 	if (!a || !b)
-		return 0;
+		return false;
 	if (a->mode != b->mode)
-		return 0;
+		return false;
 	if (a->flags != b->flags)
-		return 0;
+		return false;
 	if (mpol_store_user_nodemask(a))
 		if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
-			return 0;
+			return false;
 
 	switch (a->mode) {
 	case MPOL_BIND:
 		/* Fall through */
 	case MPOL_INTERLEAVE:
-		return nodes_equal(a->v.nodes, b->v.nodes);
+		return !!nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
 		return a->v.preferred_node == b->v.preferred_node;
 	default:
 		BUG();
-		return 0;
+		return false;
 	}
 }
 
diff --git a/mm/mempool.c b/mm/mempool.c
index e73641b79bb5..d9049811f352 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -27,7 +27,15 @@ static void *remove_element(mempool_t *pool)
 	return pool->elements[--pool->curr_nr];
 }
 
-static void free_pool(mempool_t *pool)
+/**
+ * mempool_destroy - deallocate a memory pool
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ *
+ * Free all reserved elements in @pool and @pool itself.  This function
+ * only sleeps if the free_fn() function sleeps.
+ */
+void mempool_destroy(mempool_t *pool)
 {
 	while (pool->curr_nr) {
 		void *element = remove_element(pool);
@@ -36,6 +44,7 @@ static void free_pool(mempool_t *pool)
 	kfree(pool->elements);
 	kfree(pool);
 }
+EXPORT_SYMBOL(mempool_destroy);
 
 /**
  * mempool_create - create a memory pool
@@ -86,7 +95,7 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
 
 		element = pool->alloc(GFP_KERNEL, pool->pool_data);
 		if (unlikely(!element)) {
-			free_pool(pool);
+			mempool_destroy(pool);
 			return NULL;
 		}
 		add_element(pool, element);
@@ -172,23 +181,6 @@ out:
 EXPORT_SYMBOL(mempool_resize);
 
 /**
- * mempool_destroy - deallocate a memory pool
- * @pool:      pointer to the memory pool which was allocated via
- *             mempool_create().
- *
- * this function only sleeps if the free_fn() function sleeps. The caller
- * has to guarantee that all elements have been returned to the pool (ie:
- * freed) prior to calling mempool_destroy().
- */
-void mempool_destroy(mempool_t *pool)
-{
-	/* Check for outstanding elements */
-	BUG_ON(pool->curr_nr != pool->min_nr);
-	free_pool(pool);
-}
-EXPORT_SYMBOL(mempool_destroy);
-
-/**
  * mempool_alloc - allocate an element from a specific memory pool
  * @pool:      pointer to the memory pool which was allocated via
  *             mempool_create().
@@ -224,28 +216,40 @@ repeat_alloc:
 	if (likely(pool->curr_nr)) {
 		element = remove_element(pool);
 		spin_unlock_irqrestore(&pool->lock, flags);
+		/* paired with rmb in mempool_free(), read comment there */
+		smp_wmb();
 		return element;
 	}
-	spin_unlock_irqrestore(&pool->lock, flags);
 
-	/* We must not sleep in the GFP_ATOMIC case */
-	if (!(gfp_mask & __GFP_WAIT))
+	/*
+	 * We use gfp mask w/o __GFP_WAIT or IO for the first round.  If
+	 * alloc failed with that and @pool was empty, retry immediately.
+	 */
+	if (gfp_temp != gfp_mask) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		gfp_temp = gfp_mask;
+		goto repeat_alloc;
+	}
+
+	/* We must not sleep if !__GFP_WAIT */
+	if (!(gfp_mask & __GFP_WAIT)) {
+		spin_unlock_irqrestore(&pool->lock, flags);
 		return NULL;
+	}
 
-	/* Now start performing page reclaim */
-	gfp_temp = gfp_mask;
+	/* Let's wait for someone else to return an element to @pool */
 	init_wait(&wait);
 	prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
-	smp_mb();
-	if (!pool->curr_nr) {
-		/*
-		 * FIXME: this should be io_schedule().  The timeout is there
-		 * as a workaround for some DM problems in 2.6.18.
-		 */
-		io_schedule_timeout(5*HZ);
-	}
-	finish_wait(&pool->wait, &wait);
 
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	/*
+	 * FIXME: this should be io_schedule().  The timeout is there as a
+	 * workaround for some DM problems in 2.6.18.
+	 */
+	io_schedule_timeout(5*HZ);
+
+	finish_wait(&pool->wait, &wait);
 	goto repeat_alloc;
 }
 EXPORT_SYMBOL(mempool_alloc);
@@ -265,7 +269,39 @@ void mempool_free(void *element, mempool_t *pool)
 	if (unlikely(element == NULL))
 		return;
 
-	smp_mb();
+	/*
+	 * Paired with the wmb in mempool_alloc().  The preceding read is
+	 * for @element and the following @pool->curr_nr.  This ensures
+	 * that the visible value of @pool->curr_nr is from after the
+	 * allocation of @element.  This is necessary for fringe cases
+	 * where @element was passed to this task without going through
+	 * barriers.
+	 *
+	 * For example, assume @p is %NULL at the beginning and one task
+	 * performs "p = mempool_alloc(...);" while another task is doing
+	 * "while (!p) cpu_relax(); mempool_free(p, ...);".  This function
+	 * may end up using curr_nr value which is from before allocation
+	 * of @p without the following rmb.
+	 */
+	smp_rmb();
+
+	/*
+	 * For correctness, we need a test which is guaranteed to trigger
+	 * if curr_nr + #allocated == min_nr.  Testing curr_nr < min_nr
+	 * without locking achieves that and refilling as soon as possible
+	 * is desirable.
+	 *
+	 * Because curr_nr visible here is always a value after the
+	 * allocation of @element, any task which decremented curr_nr below
+	 * min_nr is guaranteed to see curr_nr < min_nr unless curr_nr gets
+	 * incremented to min_nr afterwards.  If curr_nr gets incremented
+	 * to min_nr after the allocation of @element, the elements
+	 * allocated after that are subject to the same guarantee.
+	 *
+	 * Waiters happen iff curr_nr is 0 and the above guarantee also
+	 * ensures that there will be frees which return elements to the
+	 * pool waking up the waiters.
+	 */
 	if (pool->curr_nr < pool->min_nr) {
 		spin_lock_irqsave(&pool->lock, flags);
 		if (pool->curr_nr < pool->min_nr) {
diff --git a/mm/migrate.c b/mm/migrate.c
index 177aca424a06..89ea0854332e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -39,8 +39,6 @@
 
 #include "internal.h"
 
-#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
-
 /*
  * migrate_prep() needs to be called before we start compiling a list of pages
  * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
@@ -181,8 +179,6 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * Something used the pte of a page under migration. We need to
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
- *
- * This function is called from do_swap_page().
  */
 void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 				unsigned long address)
@@ -269,12 +265,12 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 
 	radix_tree_replace_slot(pslot, newpage);
 
-	page_unfreeze_refs(page, expected_count);
 	/*
-	 * Drop cache reference from old page.
+	 * Drop cache reference from old page by unfreezing
+	 * to one less reference.
 	 * We know this isn't the last reference.
 	 */
-	__put_page(page);
+	page_unfreeze_refs(page, expected_count - 1);
 
 	/*
 	 * If moved to a different zone then also account
@@ -334,9 +330,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 	radix_tree_replace_slot(pslot, newpage);
 
-	page_unfreeze_refs(page, expected_count);
-
-	__put_page(page);
+	page_unfreeze_refs(page, expected_count - 1);
 
 	spin_unlock_irq(&mapping->tree_lock);
 	return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index eae90af60ea6..3f758c7f4c81 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1603,39 +1603,19 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 
 EXPORT_SYMBOL(find_vma);
 
-/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */
+/*
+ * Same as find_vma, but also return a pointer to the previous VMA in *pprev.
+ * Note: pprev is set to NULL when return value is NULL.
+ */
 struct vm_area_struct *
 find_vma_prev(struct mm_struct *mm, unsigned long addr,
 			struct vm_area_struct **pprev)
 {
-	struct vm_area_struct *vma = NULL, *prev = NULL;
-	struct rb_node *rb_node;
-	if (!mm)
-		goto out;
-
-	/* Guard against addr being lower than the first VMA */
-	vma = mm->mmap;
-
-	/* Go through the RB tree quickly. */
-	rb_node = mm->mm_rb.rb_node;
-
-	while (rb_node) {
-		struct vm_area_struct *vma_tmp;
-		vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
-
-		if (addr < vma_tmp->vm_end) {
-			rb_node = rb_node->rb_left;
-		} else {
-			prev = vma_tmp;
-			if (!prev->vm_next || (addr < prev->vm_next->vm_end))
-				break;
-			rb_node = rb_node->rb_right;
-		}
-	}
+	struct vm_area_struct *vma;
 
-out:
-	*pprev = prev;
-	return prev ? prev->vm_next : vma;
+	vma = find_vma(mm, addr);
+	*pprev = vma ? vma->vm_prev : NULL;
+	return vma;
 }
 
 /*
@@ -2322,13 +2302,16 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	struct vm_area_struct *new_vma, *prev;
 	struct rb_node **rb_link, *rb_parent;
 	struct mempolicy *pol;
+	bool faulted_in_anon_vma = true;
 
 	/*
 	 * If anonymous vma has not yet been faulted, update new pgoff
 	 * to match new location, to increase its chance of merging.
 	 */
-	if (!vma->vm_file && !vma->anon_vma)
+	if (unlikely(!vma->vm_file && !vma->anon_vma)) {
 		pgoff = addr >> PAGE_SHIFT;
+		faulted_in_anon_vma = false;
+	}
 
 	find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
 	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
@@ -2337,9 +2320,24 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		/*
 		 * Source vma may have been merged into new_vma
 		 */
-		if (vma_start >= new_vma->vm_start &&
-		    vma_start < new_vma->vm_end)
+		if (unlikely(vma_start >= new_vma->vm_start &&
+			     vma_start < new_vma->vm_end)) {
+			/*
+			 * The only way we can get a vma_merge with
+			 * self during an mremap is if the vma hasn't
+			 * been faulted in yet and we were allowed to
+			 * reset the dst vma->vm_pgoff to the
+			 * destination address of the mremap to allow
+			 * the merge to happen. mremap must change the
+			 * vm_pgoff linearity between src and dst vmas
+			 * (in turn preventing a vma_merge) to be
+			 * safe. It is only safe to keep the vm_pgoff
+			 * linear if there are no pages mapped yet.
+			 */
+			VM_BUG_ON(faulted_in_anon_vma);
 			*vmap = new_vma;
+		} else
+			anon_vma_moveto_tail(new_vma);
 	} else {
 		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 		if (new_vma) {
diff --git a/mm/mremap.c b/mm/mremap.c
index d6959cb4df58..87bb8393e7d2 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -221,6 +221,15 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
 	if (moved_len < old_len) {
 		/*
+		 * Before moving the page tables from the new vma to
+		 * the old vma, we need to be sure the old vma is
+		 * queued after new vma in the same_anon_vma list to
+		 * prevent SMP races with rmap_walk (that could lead
+		 * rmap_walk to miss some page table).
+		 */
+		anon_vma_moveto_tail(vma);
+
+		/*
 		 * On error, move entries back from new area to old,
 		 * which will succeed since page tables still there,
 		 * and then proceed to unmap new area instead of old.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index eeb27e27dce3..7c122faa05c5 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -33,6 +33,10 @@
 #include <linux/security.h>
 #include <linux/ptrace.h>
 #include <linux/freezer.h>
+#include <linux/ftrace.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/oom.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
@@ -55,6 +59,7 @@ void compare_swap_oom_score_adj(int old_val, int new_val)
 	spin_lock_irq(&sighand->siglock);
 	if (current->signal->oom_score_adj == old_val)
 		current->signal->oom_score_adj = new_val;
+	trace_oom_score_adj_update(current);
 	spin_unlock_irq(&sighand->siglock);
 }
 
@@ -74,6 +79,7 @@ int test_set_oom_score_adj(int new_val)
 	spin_lock_irq(&sighand->siglock);
 	old_val = current->signal->oom_score_adj;
 	current->signal->oom_score_adj = new_val;
+	trace_oom_score_adj_update(current);
 	spin_unlock_irq(&sighand->siglock);
 
 	return old_val;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8616ef3025a4..5cdd4f2b0c9d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -130,6 +130,191 @@ unsigned long global_dirty_limit;
 static struct prop_descriptor vm_completions;
 
 /*
+ * Work out the current dirty-memory clamping and background writeout
+ * thresholds.
+ *
+ * The main aim here is to lower them aggressively if there is a lot of mapped
+ * memory around.  To avoid stressing page reclaim with lots of unreclaimable
+ * pages.  It is better to clamp down on writers than to start swapping, and
+ * performing lots of scanning.
+ *
+ * We only allow 1/2 of the currently-unmapped memory to be dirtied.
+ *
+ * We don't permit the clamping level to fall below 5% - that is getting rather
+ * excessive.
+ *
+ * We make sure that the background writeout level is below the adjusted
+ * clamping level.
+ */
+
+/*
+ * In a memory zone, there is a certain amount of pages we consider
+ * available for the page cache, which is essentially the number of
+ * free and reclaimable pages, minus some zone reserves to protect
+ * lowmem and the ability to uphold the zone's watermarks without
+ * requiring writeback.
+ *
+ * This number of dirtyable pages is the base value of which the
+ * user-configurable dirty ratio is the effictive number of pages that
+ * are allowed to be actually dirtied.  Per individual zone, or
+ * globally by using the sum of dirtyable pages over all zones.
+ *
+ * Because the user is allowed to specify the dirty limit globally as
+ * absolute number of bytes, calculating the per-zone dirty limit can
+ * require translating the configured limit into a percentage of
+ * global dirtyable memory first.
+ */
+
+static unsigned long highmem_dirtyable_memory(unsigned long total)
+{
+#ifdef CONFIG_HIGHMEM
+	int node;
+	unsigned long x = 0;
+
+	for_each_node_state(node, N_HIGH_MEMORY) {
+		struct zone *z =
+			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+
+		x += zone_page_state(z, NR_FREE_PAGES) +
+		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+	}
+	/*
+	 * Make sure that the number of highmem pages is never larger
+	 * than the number of the total dirtyable memory. This can only
+	 * occur in very strange VM situations but we want to make sure
+	 * that this does not occur.
+	 */
+	return min(x, total);
+#else
+	return 0;
+#endif
+}
+
+/**
+ * global_dirtyable_memory - number of globally dirtyable pages
+ *
+ * Returns the global number of pages potentially available for dirty
+ * page cache.  This is the base value for the global dirty limits.
+ */
+unsigned long global_dirtyable_memory(void)
+{
+	unsigned long x;
+
+	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
+	    dirty_balance_reserve;
+
+	if (!vm_highmem_is_dirtyable)
+		x -= highmem_dirtyable_memory(x);
+
+	return x + 1;	/* Ensure that we never return 0 */
+}
+
+/*
+ * global_dirty_limits - background-writeback and dirty-throttling thresholds
+ *
+ * Calculate the dirty thresholds based on sysctl parameters
+ * - vm.dirty_background_ratio  or  vm.dirty_background_bytes
+ * - vm.dirty_ratio             or  vm.dirty_bytes
+ * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
+ * real-time tasks.
+ */
+void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
+{
+	unsigned long background;
+	unsigned long dirty;
+	unsigned long uninitialized_var(available_memory);
+	struct task_struct *tsk;
+
+	if (!vm_dirty_bytes || !dirty_background_bytes)
+		available_memory = global_dirtyable_memory();
+
+	if (vm_dirty_bytes)
+		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+	else
+		dirty = (vm_dirty_ratio * available_memory) / 100;
+
+	if (dirty_background_bytes)
+		background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+	else
+		background = (dirty_background_ratio * available_memory) / 100;
+
+	if (background >= dirty)
+		background = dirty / 2;
+	tsk = current;
+	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
+		background += background / 4;
+		dirty += dirty / 4;
+	}
+	*pbackground = background;
+	*pdirty = dirty;
+	trace_global_dirty_state(background, dirty);
+}
+
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+	/*
+	 * The effective global number of dirtyable pages may exclude
+	 * highmem as a big-picture measure to keep the ratio between
+	 * dirty memory and lowmem reasonable.
+	 *
+	 * But this function is purely about the individual zone and a
+	 * highmem zone can hold its share of dirty pages, so we don't
+	 * care about vm_highmem_is_dirtyable here.
+	 */
+	return zone_page_state(zone, NR_FREE_PAGES) +
+	       zone_reclaimable_pages(zone) -
+	       zone->dirty_balance_reserve;
+}
+
+/**
+ * zone_dirty_limit - maximum number of dirty pages allowed in a zone
+ * @zone: the zone
+ *
+ * Returns the maximum number of dirty pages allowed in a zone, based
+ * on the zone's dirtyable memory.
+ */
+static unsigned long zone_dirty_limit(struct zone *zone)
+{
+	unsigned long zone_memory = zone_dirtyable_memory(zone);
+	struct task_struct *tsk = current;
+	unsigned long dirty;
+
+	if (vm_dirty_bytes)
+		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
+			zone_memory / global_dirtyable_memory();
+	else
+		dirty = vm_dirty_ratio * zone_memory / 100;
+
+	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
+		dirty += dirty / 4;
+
+	return dirty;
+}
+
+/**
+ * zone_dirty_ok - tells whether a zone is within its dirty limits
+ * @zone: the zone to check
+ *
+ * Returns %true when the dirty pages in @zone are within the zone's
+ * dirty limit, %false if the limit is exceeded.
+ */
+bool zone_dirty_ok(struct zone *zone)
+{
+	unsigned long limit = zone_dirty_limit(zone);
+
+	return zone_page_state(zone, NR_FILE_DIRTY) +
+	       zone_page_state(zone, NR_UNSTABLE_NFS) +
+	       zone_page_state(zone, NR_WRITEBACK) <= limit;
+}
+
+/*
  * couple the period to the dirty_ratio:
  *
  *   period/2 ~ roundup_pow_of_two(dirty limit)
@@ -141,7 +326,7 @@ static int calc_period_shift(void)
 	if (vm_dirty_bytes)
 		dirty_total = vm_dirty_bytes / PAGE_SIZE;
 	else
-		dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
+		dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) /
 				100;
 	return 2 + ilog2(dirty_total - 1);
 }
@@ -196,7 +381,6 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-
 int dirty_bytes_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -291,67 +475,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
 }
 EXPORT_SYMBOL(bdi_set_max_ratio);
 
-/*
- * Work out the current dirty-memory clamping and background writeout
- * thresholds.
- *
- * The main aim here is to lower them aggressively if there is a lot of mapped
- * memory around.  To avoid stressing page reclaim with lots of unreclaimable
- * pages.  It is better to clamp down on writers than to start swapping, and
- * performing lots of scanning.
- *
- * We only allow 1/2 of the currently-unmapped memory to be dirtied.
- *
- * We don't permit the clamping level to fall below 5% - that is getting rather
- * excessive.
- *
- * We make sure that the background writeout level is below the adjusted
- * clamping level.
- */
-
-static unsigned long highmem_dirtyable_memory(unsigned long total)
-{
-#ifdef CONFIG_HIGHMEM
-	int node;
-	unsigned long x = 0;
-
-	for_each_node_state(node, N_HIGH_MEMORY) {
-		struct zone *z =
-			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
-
-		x += zone_page_state(z, NR_FREE_PAGES) +
-		     zone_reclaimable_pages(z);
-	}
-	/*
-	 * Make sure that the number of highmem pages is never larger
-	 * than the number of the total dirtyable memory. This can only
-	 * occur in very strange VM situations but we want to make sure
-	 * that this does not occur.
-	 */
-	return min(x, total);
-#else
-	return 0;
-#endif
-}
-
-/**
- * determine_dirtyable_memory - amount of memory that may be used
- *
- * Returns the numebr of pages that can currently be freed and used
- * by the kernel for direct mappings.
- */
-unsigned long determine_dirtyable_memory(void)
-{
-	unsigned long x;
-
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
-
-	if (!vm_highmem_is_dirtyable)
-		x -= highmem_dirtyable_memory(x);
-
-	return x + 1;	/* Ensure that we never return 0 */
-}
-
 static unsigned long dirty_freerun_ceiling(unsigned long thresh,
 					   unsigned long bg_thresh)
 {
@@ -363,47 +486,6 @@ static unsigned long hard_dirty_limit(unsigned long thresh)
 	return max(thresh, global_dirty_limit);
 }
 
-/*
- * global_dirty_limits - background-writeback and dirty-throttling thresholds
- *
- * Calculate the dirty thresholds based on sysctl parameters
- * - vm.dirty_background_ratio  or  vm.dirty_background_bytes
- * - vm.dirty_ratio             or  vm.dirty_bytes
- * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
- * real-time tasks.
- */
-void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
-{
-	unsigned long background;
-	unsigned long dirty;
-	unsigned long uninitialized_var(available_memory);
-	struct task_struct *tsk;
-
-	if (!vm_dirty_bytes || !dirty_background_bytes)