Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

63 files changed, 5101 insertions, 3349 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 7c5697116fc..e338407f122 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -137,6 +137,9 @@ config HAVE_MEMBLOCK_NODE_MAP
 config ARCH_DISCARD_MEMBLOCK
 	boolean
 
+config NO_BOOTMEM
+	boolean
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
@@ -362,7 +365,7 @@ config CLEANCACHE
 	  for clean pages that the kernel's pageframe replacement algorithm
 	  (PFRA) would like to keep around, but can't since there isn't enough
 	  memory.  So when the PFRA "evicts" a page, it first attempts to use
-	  cleancacne code to put the data contained in that page into
+	  cleancache code to put the data contained in that page into
 	  "transcendent memory", memory that is not directly accessible or
 	  addressable by the kernel and is of unknown and possibly
 	  time-varying size.  And when a cleancache-enabled
diff --git a/mm/Makefile b/mm/Makefile
index 836e4163c1b..50ec00ef2a0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,7 +5,8 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o
+			   vmalloc.o pagewalk.o pgtable-generic.o \
+			   process_vm_access.o
 
 obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f032e6e1e09..71034f41a2b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -45,6 +45,17 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
+
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -67,34 +78,44 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	struct inode *inode;
 
 	nr_dirty = nr_io = nr_more_io = 0;
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
-		   "BdiWriteback:     %8lu kB\n"
-		   "BdiReclaimable:   %8lu kB\n"
-		   "BdiDirtyThresh:   %8lu kB\n"
-		   "DirtyThresh:      %8lu kB\n"
-		   "BackgroundThresh: %8lu kB\n"
-		   "b_dirty:          %8lu\n"
-		   "b_io:             %8lu\n"
-		   "b_more_io:        %8lu\n"
-		   "bdi_list:         %8u\n"
-		   "state:            %8lx\n",
+		   "BdiWriteback:       %10lu kB\n"
+		   "BdiReclaimable:     %10lu kB\n"
+		   "BdiDirtyThresh:     %10lu kB\n"
+		   "DirtyThresh:        %10lu kB\n"
+		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiDirtied:         %10lu kB\n"
+		   "BdiWritten:         %10lu kB\n"
+		   "BdiWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:            %10lu\n"
+		   "b_io:               %10lu\n"
+		   "b_more_io:          %10lu\n"
+		   "bdi_list:           %10u\n"
+		   "state:              %10lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
-		   K(bdi_thresh), K(dirty_thresh),
-		   K(background_thresh), nr_dirty, nr_io, nr_more_io,
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(bdi->write_bandwidth),
+		   nr_dirty,
+		   nr_io,
+		   nr_more_io,
 		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
@@ -249,18 +270,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return wb_has_dirty_io(&bdi->wb);
 }
 
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
-	struct writeback_control wbc = {
-		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
-		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
-	};
-
-	writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
 /*
  * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
@@ -352,6 +361,17 @@ static unsigned long bdi_longest_inactive(void)
 	return max(5UL * 60 * HZ, interval);
 }
 
+/*
+ * Clear pending bit and wakeup anybody waiting for flusher thread creation or
+ * shutdown
+ */
+static void bdi_clear_pending(struct backing_dev_info *bdi)
+{
+	clear_bit(BDI_pending, &bdi->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&bdi->state, BDI_pending);
+}
+
 static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
@@ -383,6 +403,12 @@ static int bdi_forker_thread(void *ptr)
 		}
 
 		spin_lock_bh(&bdi_lock);
+		/*
+		 * In the following loop we are going to check whether we have
+		 * some work to do without any synchronization with tasks
+		 * waking us up to do work for them. Set the task state here
+		 * so that we don't miss wakeups after verifying conditions.
+		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		list_for_each_entry(bdi, &bdi_list, bdi_list) {
@@ -446,9 +472,11 @@ static int bdi_forker_thread(void *ptr)
 			if (IS_ERR(task)) {
 				/*
 				 * If thread creation fails, force writeout of
-				 * the bdi from the thread.
+				 * the bdi from the thread. Hopefully 1024 is
+				 * large enough for efficient IO.
 				 */
-				bdi_flush_io(bdi);
+				writeback_inodes_wb(&bdi->wb, 1024,
+						    WB_REASON_FORKER_THREAD);
 			} else {
 				/*
 				 * The spinlock makes sure we do not lose
@@ -461,11 +489,13 @@ static int bdi_forker_thread(void *ptr)
 				spin_unlock_bh(&bdi->wb_lock);
 				wake_up_process(task);
 			}
+			bdi_clear_pending(bdi);
 			break;
 
 		case KILL_THREAD:
 			__set_current_state(TASK_RUNNING);
 			kthread_stop(task);
+			bdi_clear_pending(bdi);
 			break;
 
 		case NO_ACTION:
@@ -481,16 +511,8 @@ static int bdi_forker_thread(void *ptr)
 			else
 				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
 			try_to_freeze();
-			/* Back to the main loop */
-			continue;
+			break;
 		}
-
-		/*
-		 * Clear pending bit and wakeup anybody waiting to tear us down.
-		 */
-		clear_bit(BDI_pending, &bdi->state);
-		smp_mb__after_clear_bit();
-		wake_up_bit(&bdi->state, BDI_pending);
 	}
 
 	return 0;
@@ -505,7 +527,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	list_del_rcu(&bdi->bdi_list);
 	spin_unlock_bh(&bdi_lock);
 
-	synchronize_rcu();
+	synchronize_rcu_expedited();
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -606,6 +628,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 		del_timer_sync(&bdi->wb.wakeup_timer);
@@ -628,9 +651,15 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	spin_lock_init(&wb->list_lock);
 	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
 }
 
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -653,6 +682,15 @@ int bdi_init(struct backing_dev_info *bdi)
 	}
 
 	bdi->dirty_exceeded = 0;
+
+	bdi->bw_time_stamp = jiffies;
+	bdi->written_stamp = 0;
+
+	bdi->balanced_dirty_ratelimit = INIT_BW;
+	bdi->dirty_ratelimit = INIT_BW;
+	bdi->write_bandwidth = INIT_BW;
+	bdi->avg_write_bandwidth = INIT_BW;
+
 	err = prop_local_init_percpu(&bdi->completions);
 
 	if (err) {
@@ -676,15 +714,24 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_wb_list_lock);
+		bdi_lock_two(&bdi->wb, dst);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
 	}
 
 	bdi_unregister(bdi);
 
+	/*
+	 * If bdi_unregister() had already been called earlier, the
+	 * wakeup_timer could still be armed because bdi_prune_sb()
+	 * can race with the bdi_wakeup_thread_delayed() calls from
+	 * __mark_inode_dirty().
+	 */
+	del_timer_sync(&bdi->wb.wakeup_timer);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 01d5a4b3dd0..1a77012ecdb 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -12,7 +12,7 @@
 #include <linux/pfn.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
 #include <linux/memblock.h>
diff --git a/mm/bounce.c b/mm/bounce.c
index 1481de68184..4e9ae722af8 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/swap.h>
 #include <linux/gfp.h>
 #include <linux/bio.h>
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
+#include <linux/bootmem.h>
 #include <asm/tlbflush.h>
 
 #include <trace/events/block.h>
@@ -26,12 +27,10 @@ static mempool_t *page_pool, *isa_page_pool;
 #ifdef CONFIG_HIGHMEM
 static __init int init_emergency_pool(void)
 {
-	struct sysinfo i;
-	si_meminfo(&i);
-	si_swapinfo(&i);
-
-	if (!i.totalhigh)
+#ifndef CONFIG_MEMORY_HOTPLUG
+	if (max_pfn <= max_low_pfn)
 		return 0;
+#endif
 
 	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
 	BUG_ON(!page_pool);
diff --git a/mm/compaction.c b/mm/compaction.c
index 6cc604bd564..899d9563858 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -35,10 +35,6 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
 
-	/* Account for isolated anon and file pages */
-	unsigned long nr_anon;
-	unsigned long nr_file;
-
 	unsigned int order;		/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
@@ -223,17 +219,13 @@ static void isolate_freepages(struct zone *zone,
 static void acct_isolated(struct zone *zone, struct compact_control *cc)
 {
 	struct page *page;
-	unsigned int count[NR_LRU_LISTS] = { 0, };
+	unsigned int count[2] = { 0, };
 
-	list_for_each_entry(page, &cc->migratepages, lru) {
-		int lru = page_lru_base_type(page);
-		count[lru]++;
-	}
+	list_for_each_entry(page, &cc->migratepages, lru)
+		count[!!page_is_file_cache(page)]++;
 
-	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
-	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -269,6 +261,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
+	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
 
 	/* Do not scan outside zone boundaries */
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
@@ -356,8 +349,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 		}
 
+		if (!cc->sync)
+			mode |= ISOLATE_CLEAN;
+
 		/* Try isolate the page */
-		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
+		if (__isolate_lru_page(page, mode, 0) != 0)
 			continue;
 
 		VM_BUG_ON(PageTransCompound(page));
@@ -586,7 +582,7 @@ out:
 	return ret;
 }
 
-unsigned long compact_zone_order(struct zone *zone,
+static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
 				 bool sync)
 {
diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c
index a1e3324de2b..7cea557407f 100644
--- a/mm/debug-pagealloc.c
+++ b/mm/debug-pagealloc.c
@@ -1,7 +1,10 @@
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/page-debug-flags.h>
 #include <linux/poison.h>
+#include <linux/ratelimit.h>
 
 static inline void set_page_poison(struct page *page)
 {
@@ -18,28 +21,13 @@ static inline bool page_poison(struct page *page)
 	return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
 }
 
-static void poison_highpage(struct page *page)
-{
-	/*
-	 * Page poisoning for highmem pages is not implemented.
-	 *
-	 * This can be called from interrupt contexts.
-	 * So we need to create a new kmap_atomic slot for this
-	 * application and it will need interrupt protection.
-	 */
-}
-
 static void poison_page(struct page *page)
 {
-	void *addr;
+	void *addr = kmap_atomic(page);
 
-	if (PageHighMem(page)) {
-		poison_highpage(page);
-		return;
-	}
 	set_page_poison(page);
-	addr = page_address(page);
 	memset(addr, PAGE_POISON, PAGE_SIZE);
+	kunmap_atomic(addr);
 }
 
 static void poison_pages(struct page *page, int n)
@@ -59,14 +47,12 @@ static bool single_bit_flip(unsigned char a, unsigned char b)
 
 static void check_poison_mem(unsigned char *mem, size_t bytes)
 {
+	static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10);
 	unsigned char *start;
 	unsigned char *end;
 
-	for (start = mem; start < mem + bytes; start++) {
-		if (*start != PAGE_POISON)
-			break;
-	}
-	if (start == mem + bytes)
+	start = memchr_inv(mem, PAGE_POISON, bytes);
+	if (!start)
 		return;
 
 	for (end = mem + bytes - 1; end > start; end--) {
@@ -74,7 +60,7 @@ static void check_poison_mem(unsigned char *mem, size_t bytes)
 			break;
 	}
 
-	if (!printk_ratelimit())
+	if (!__ratelimit(&ratelimit))
 		return;
 	else if (start == end && single_bit_flip(*start, PAGE_POISON))
 		printk(KERN_ERR "pagealloc: single bit error\n");
@@ -86,27 +72,17 @@ static void check_poison_mem(unsigned char *mem, size_t bytes)
 	dump_stack();
 }
 
-static void unpoison_highpage(struct page *page)
-{
-	/*
-	 * See comment in poison_highpage().
-	 * Highmem pages should not be poisoned for now
-	 */
-	BUG_ON(page_poison(page));
-}
-
 static void unpoison_page(struct page *page)
 {
-	if (PageHighMem(page)) {
-		unpoison_highpage(page);
+	void *addr;
+
+	if (!page_poison(page))
 		return;
-	}
-	if (page_poison(page)) {
-		void *addr = page_address(page);
 
-		check_poison_mem(addr, PAGE_SIZE);
-		clear_page_poison(page);
-	}
+	addr = kmap_atomic(page);
+	check_poison_mem(addr, PAGE_SIZE);
+	clear_page_poison(page);
+	kunmap_atomic(addr);
 }
 
 static void unpoison_pages(struct page *page, int n)
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 03bf3bb4519..c5ab33bca0a 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -27,11 +27,12 @@
 #include <linux/dmapool.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/poison.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/stat.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -500,7 +501,7 @@ void dmam_pool_destroy(struct dma_pool *pool)
 {
 	struct device *dev = pool->dev;
 
-	dma_pool_destroy(pool);
 	WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool));
+	dma_pool_destroy(pool);
 }
 EXPORT_SYMBOL(dmam_pool_destroy);
diff --git a/mm/failslab.c b/mm/failslab.c
index c5f88f240dd..0dd7b8fec71 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -5,10 +5,6 @@ static struct {
 	struct fault_attr attr;
 	u32 ignore_gfp_wait;
 	int cache_filter;
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-	struct dentry *ignore_gfp_wait_file;
-	struct dentry *cache_filter_file;
-#endif
 } failslab = {
 	.attr = FAULT_ATTR_INITIALIZER,
 	.ignore_gfp_wait = 1,
@@ -38,32 +34,25 @@ __setup("failslab=", setup_failslab);
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 static int __init failslab_debugfs_init(void)
 {
-	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
 	struct dentry *dir;
-	int err;
-
-	err = init_fault_attr_dentries(&failslab.attr, "failslab");
-	if (err)
-		return err;
-	dir = failslab.attr.dentries.dir;
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
 
-	failslab.ignore_gfp_wait_file =
-		debugfs_create_bool("ignore-gfp-wait", mode, dir,
-				      &failslab.ignore_gfp_wait);
+	dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
 
-	failslab.cache_filter_file =
-		debugfs_create_bool("cache-filter", mode, dir,
-				      &failslab.cache_filter);
+	if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				&failslab.ignore_gfp_wait))
+		goto fail;
+	if (!debugfs_create_bool("cache-filter", mode, dir,
+				&failslab.cache_filter))
+		goto fail;
 
-	if (!failslab.ignore_gfp_wait_file ||
-	    !failslab.cache_filter_file) {
-		err = -ENOMEM;
-		debugfs_remove(failslab.cache_filter_file);
-		debugfs_remove(failslab.ignore_gfp_wait_file);
-		cleanup_fault_attr_dentries(&failslab.attr);
-	}
+	return 0;
+fail:
+	debugfs_remove_recursive(dir);
 
-	return err;
+	return -ENOMEM;
 }
 
 late_initcall(failslab_debugfs_init);
diff --git a/mm/filemap.c b/mm/filemap.c
index a8251a8d345..c0018f2d50e