Merge branch 'linus' into x86/xsave

14 files changed, 110 insertions, 38 deletions

diff --git a/mm/bounce.c b/mm/bounce.c
index b6d2d0f1019..06722c40305 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -267,7 +267,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	/*
 	 * Data-less bio, nothing to bounce
 	 */
-	if (bio_empty_barrier(*bio_orig))
+	if (!bio_has_data(*bio_orig))
 		return;
 
 	/*
diff --git a/mm/filemap.c b/mm/filemap.c
index 54e96865085..876bc595d0f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2129,13 +2129,20 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	 * After a write we want buffered reads to be sure to go to disk to get
 	 * the new data.  We invalidate clean cached page from the region we're
 	 * about to write.  We do this *before* the write so that we can return
-	 * -EIO without clobbering -EIOCBQUEUED from ->direct_IO().
+	 * without clobbering -EIOCBQUEUED from ->direct_IO().
 	 */
 	if (mapping->nrpages) {
 		written = invalidate_inode_pages2_range(mapping,
 					pos >> PAGE_CACHE_SHIFT, end);
-		if (written)
+		/*
+		 * If a page can not be invalidated, return 0 to fall back
+		 * to buffered write.
+		 */
+		if (written) {
+			if (written == -EBUSY)
+				return 0;
 			goto out;
+		}
 	}
 
 	written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
diff --git a/mm/highmem.c b/mm/highmem.c
index e16e1523b68..b36b83b920f 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -70,6 +70,7 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
 static void flush_all_zero_pkmaps(void)
 {
 	int i;
+	int need_flush = 0;
 
 	flush_cache_kmaps();
 
@@ -101,8 +102,10 @@ static void flush_all_zero_pkmaps(void)
 			  &pkmap_page_table[i]);
 
 		set_page_address(page, NULL);
+		need_flush = 1;
 	}
-	flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
+	if (need_flush)
+		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1f7a7374b..36896f3eb7f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -250,6 +250,14 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
+	/*
+	 * mm_update_next_owner() may clear mm->owner to NULL
+	 * if it races with swapoff, page migration, etc.
+	 * So this can be called with p == NULL.
+	 */
+	if (unlikely(!p))
+		return NULL;
+
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
@@ -549,6 +557,11 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	if (likely(!memcg)) {
 		rcu_read_lock();
 		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+		if (unlikely(!mem)) {
+			rcu_read_unlock();
+			kmem_cache_free(page_cgroup_cache, pc);
+			return 0;
+		}
 		/*
 		 * For every charge from the cgroup, increment reference count
 		 */
@@ -801,11 +814,16 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 
 	rcu_read_lock();
 	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!mem)) {
+		rcu_read_unlock();
+		return 0;
+	}
 	css_get(&mem->css);
 	rcu_read_unlock();
 
 	do {
 		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
+		progress += res_counter_check_under_limit(&mem->res);
 	} while (!progress && --retry);
 
 	css_put(&mem->css);
diff --git a/mm/mmap.c b/mm/mmap.c
index 339cf5c4d5d..e7a5a68a9c2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1030,6 +1030,10 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
+			/*
+			 * Ignore pgoff.
+			 */
+			pgoff = 0;
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
 			break;
 		case MAP_PRIVATE:
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 486ed595ee6..16ce8b955dc 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -69,6 +69,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z,
 				(z->zone && !zref_in_nodemask(z, nodes)))
 			z++;
 
-	*zone = zonelist_zone(z++);
+	*zone = zonelist_zone(z);
 	return z;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index af982f7cdb2..27b8681139f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -268,13 +268,14 @@ void prep_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	set_compound_page_dtor(page, free_compound_page);
 	set_compound_order(page, order);
 	__SetPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
-
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 		__SetPageTail(p);
 		p->first_page = page;
 	}
@@ -284,6 +285,7 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
+	struct page *p = page + 1;
 
 	if (unlikely(compound_order(page) != order))
 		bad_page(page);
@@ -291,8 +293,9 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 	if (unlikely(!PageHead(page)))
 			bad_page(page);
 	__ClearPageHead(page);
-	for (i = 1; i < nr_pages; i++) {
-		struct page *p = page + i;
+	for (i = 1; i < nr_pages; i++, p++) {
+		if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
+			p = pfn_to_page(page_to_pfn(page) + i);
 
 		if (unlikely(!PageTail(p) |
 				(p->first_page != page)))
@@ -694,6 +697,9 @@ static int move_freepages(struct zone *zone,
 #endif
 
 	for (page = start_page; page <= end_page;) {
+		/* Make sure we are not inadvertently changing nodes */
+		VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone));
+
 		if (!pfn_valid_within(page_to_pfn(page))) {
 			page++;
 			continue;
@@ -2516,6 +2522,10 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 			continue;
 		page = pfn_to_page(pfn);
 
+		/* Watch out for overlapping nodes */
+		if (page_to_nid(page) != zone_to_nid(zone))
+			continue;
+
 		/* Blocks with reserved pages will never free, skip them. */
 		if (PageReserved(page))
 			continue;
@@ -4064,7 +4074,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
 EXPORT_SYMBOL(contig_page_data);
 #endif
 
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 3444b58033c..b70a7fec1ff 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -2,7 +2,6 @@
  * linux/mm/page_isolation.c
  */
 
-#include <stddef.h>
 #include <linux/mm.h>
 #include <linux/page-isolation.h>
 #include <linux/pageblock-flags.h>
@@ -115,8 +114,10 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, flags;
 	struct page *page;
+	struct zone *zone;
+	int ret;
 
 	pfn = start_pfn;
 	/*
@@ -132,7 +133,9 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	if (pfn < end_pfn)
 		return -EBUSY;
 	/* Check all pages are free or Marked as ISOLATED */
-	if (__test_page_isolated_in_pageblock(start_pfn, end_pfn))
-		return 0;
-	return -EBUSY;
+	zone = page_zone(pfn_to_page(pfn));
+	spin_lock_irqsave(&zone->lock, flags);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret ? 0 : -EBUSY;
 }
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 3f703f7cb39..8dbb6805ef3 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -26,7 +26,10 @@ DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
 static unsigned long max_pages(unsigned long min_pages)
 {
 	unsigned long node_free_pages, max;
-	struct zone *zones = NODE_DATA(numa_node_id())->node_zones;
+	int node = numa_node_id();
+	struct zone *zones = NODE_DATA(node)->node_zones;
+	int num_cpus_on_node;
+	node_to_cpumask_ptr(cpumask_on_node, node);
 
 	node_free_pages =
 #ifdef CONFIG_ZONE_DMA
@@ -38,6 +41,10 @@ static unsigned long max_pages(unsigned long min_pages)
 		zone_page_state(&zones[ZONE_NORMAL], NR_FREE_PAGES);
 
 	max = node_free_pages / FRACTION_OF_NODE_MEM;
+
+	num_cpus_on_node = cpus_weight_nr(*cpumask_on_node);
+	max /= num_cpus_on_node;
+
 	return max(max, min_pages);
 }
 
diff --git a/mm/slob.c b/mm/slob.c
index 4c82dd41f32..cb675d12679 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -514,9 +514,11 @@ size_t ksize(const void *block)
 		return 0;
 
 	sp = (struct slob_page *)virt_to_page(block);
-	if (slob_page(sp))
-		return ((slob_t *)block - 1)->units + SLOB_UNIT;
-	else
+	if (slob_page(sp)) {
+		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		unsigned int *m = (unsigned int *)(block - align);
+		return SLOB_UNITS(*m) * SLOB_UNIT;
+	} else
 		return sp->page.private;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 4f5b9614945..0c83e6afe7b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1932,6 +1932,7 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 	INIT_LIST_HEAD(&n->partial);
 #ifdef CONFIG_SLUB_DEBUG
 	atomic_long_set(&n->nr_slabs, 0);
+	atomic_long_set(&n->total_objects, 0);
 	INIT_LIST_HEAD(&n->full);
 #endif
 }
@@ -2312,7 +2313,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 
 	s->refcount = 1;
 #ifdef CONFIG_NUMA
-	s->remote_node_defrag_ratio = 100;
+	s->remote_node_defrag_ratio = 1000;
 #endif
 	if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
 		goto error;
@@ -4058,7 +4059,7 @@ static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
 	if (err)
 		return err;
 
-	if (ratio < 100)
+	if (ratio <= 100)
 		s->remote_node_defrag_ratio = ratio * 10;
 
 	return length;
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
index ae532f50194..8d7a27a6335 100644
--- a/mm/tiny-shmem.c
+++ b/mm/tiny-shmem.c
@@ -65,31 +65,31 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	if (!dentry)
 		goto put_memory;
 
+	error = -ENFILE;
+	file = get_empty_filp();
+	if (!file)
+		goto put_dentry;
+
 	error = -ENOSPC;
 	inode = ramfs_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto put_dentry;
+		goto close_file;
 
 	d_instantiate(dentry, inode);
-	error = -ENFILE;
-	file = alloc_file(shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
-			&ramfs_file_operations);
-	if (!file)
-		goto put_dentry;
-
+	inode->i_size = size;
 	inode->i_nlink = 0;	/* It is unlinked */
+	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
+			&ramfs_file_operations);
 
-	/* notify everyone as to the change of file size */
-	error = do_truncate(dentry, size, 0, file);
-	if (error < 0)
+#ifndef CONFIG_MMU
+	error = ramfs_nommu_expand_for_mapping(inode, size);
+	if (error)
 		goto close_file;
-
+#endif
 	return file;
 
 close_file:
 	put_filp(file);
-	return ERR_PTR(error);
-
 put_dentry:
 	dput(dentry);
 put_memory:
diff --git a/mm/truncate.c b/mm/truncate.c
index 250505091d3..6650c1d878b 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -380,7 +380,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
  * Any pages which are found to be mapped into pagetables are unmapped prior to
  * invalidation.
  *
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
  */
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
@@ -440,7 +440,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			ret2 = do_launder_page(mapping, page);
 			if (ret2 == 0) {
 				if (!invalidate_complete_page2(mapping, page))
-					ret2 = -EIO;
+					ret2 = -EBUSY;
 			}
 			if (ret2 < 0)
 				ret = ret2;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b0d08e667ec..d7826af2fb0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -516,9 +516,26 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
 			continue;
 
 		page = pfn_to_page(pfn);
+#ifdef CONFIG_ARCH_FLATMEM_HAS_HOLES
+		/*
+		 * Ordinarily, memory holes in flatmem still have a valid
+		 * memmap for the PFN range. However, an architecture for
+		 * embedded systems (e.g. ARM) can free up the memmap backing
+		 * holes to save memory on the assumption the memmap is
+		 * never used. The page_zone linkages are then broken even
+		 * though pfn_valid() returns true. Skip the page if the
+		 * linkages are broken. Even if this test passed, the impact
+		 * is that the counters for the movable type are off but
+		 * fragmentation monitoring is likely meaningless on small
+		 * systems.
+		 */
+		if (page_zone(page) != zone)
+			continue;
+#endif
 		mtype = get_pageblock_migratetype(page);
 
-		count[mtype]++;
+		if (mtype < MIGRATE_TYPES)
+			count[mtype]++;
 	}
 
 	/* Print counts */