Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - various misc bits

 - DAX updates

 - OCFS2

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (119 commits)
  mm,fork: introduce MADV_WIPEONFORK
  x86,mpx: make mpx depend on x86-64 to free up VMA flag
  mm: add /proc/pid/smaps_rollup
  mm: hugetlb: clear target sub-page last when clearing huge page
  mm: oom: let oom_reap_task and exit_mmap run concurrently
  swap: choose swap device according to numa node
  mm: replace TIF_MEMDIE checks by tsk_is_oom_victim
  mm, oom: do not rely on TIF_MEMDIE for memory reserves access
  z3fold: use per-cpu unbuddied lists
  mm, swap: don't use VMA based swap readahead if HDD is used as swap
  mm, swap: add sysfs interface for VMA based swap readahead
  mm, swap: VMA based swap readahead
  mm, swap: fix swap readahead marking
  mm, swap: add swap readahead hit statistics
  mm/vmalloc.c: don't reinvent the wheel but use existing llist API
  mm/vmstat.c: fix wrong comment
  selftests/memfd: add memfd_create hugetlbfs selftest
  mm/shmem: add hugetlbfs support to memfd_create()
  mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups
  mm/vmalloc.c: halve the number of comparisons performed in pcpu_get_vm_areas()
  ...

35 files changed, 365 insertions, 670 deletions

diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 103ca5e1267b..64c58eb26159 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -151,34 +151,6 @@ fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data,
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data)
-{
-	struct v9fs_inode *v9inode = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	for (;;) {
-		nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping,
-					  first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 const struct fscache_cookie_def v9fs_cache_inode_index_def = {
 	.name		= "9p.inode",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -186,7 +158,6 @@ const struct fscache_cookie_def v9fs_cache_inode_index_def = {
 	.get_attr	= v9fs_cache_inode_get_attr,
 	.get_aux	= v9fs_cache_inode_get_aux,
 	.check_aux	= v9fs_cache_inode_check_aux,
-	.now_uncached	= v9fs_cache_inode_now_uncached,
 };
 
 void v9fs_cache_inode_get_cookie(struct inode *inode)
diff --git a/fs/afs/cache.c b/fs/afs/cache.c
index 577763c3d88b..1fe855191261 100644
--- a/fs/afs/cache.c
+++ b/fs/afs/cache.c
@@ -39,7 +39,6 @@ static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
 static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 						       const void *buffer,
 						       uint16_t buflen);
-static void afs_vnode_cache_now_uncached(void *cookie_netfs_data);
 
 struct fscache_netfs afs_cache_netfs = {
 	.name			= "afs",
@@ -75,7 +74,6 @@ struct fscache_cookie_def afs_vnode_cache_index_def = {
 	.get_attr		= afs_vnode_cache_get_attr,
 	.get_aux		= afs_vnode_cache_get_aux,
 	.check_aux		= afs_vnode_cache_check_aux,
-	.now_uncached		= afs_vnode_cache_now_uncached,
 };
 
 /*
@@ -359,44 +357,3 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 	_leave(" = SUCCESS");
 	return FSCACHE_CHECKAUX_OKAY;
 }
-
-/*
- * indication the cookie is no longer uncached
- * - this function is called when the backing store currently caching a cookie
- *   is removed
- * - the netfs should use this to clean up any markers indicating cached pages
- * - this is mandatory for any object that may have data
- */
-static void afs_vnode_cache_now_uncached(void *cookie_netfs_data)
-{
-	struct afs_vnode *vnode = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	_enter("{%x,%x,%Lx}",
-	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version);
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	for (;;) {
-		/* grab a bunch of pages to clean */
-		nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping,
-					  first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-
-	_leave("");
-}
diff --git a/fs/buffer.c b/fs/buffer.c
index 5715dac7821f..50da0e102ca0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1627,20 +1627,17 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 	struct pagevec pvec;
 	pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	pgoff_t end;
-	int i;
+	int i, count;
 	struct buffer_head *bh;
 	struct buffer_head *head;
 
 	end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, bd_mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
-		for (i = 0; i < pagevec_count(&pvec); i++) {
+	while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) {
+		count = pagevec_count(&pvec);
+		for (i = 0; i < count; i++) {
 			struct page *page = pvec.pages[i];
 
-			index = page->index;
-			if (index > end)
-				break;
 			if (!page_has_buffers(page))
 				continue;
 			/*
@@ -1670,7 +1667,9 @@ unlock_page:
 		}
 		pagevec_release(&pvec);
 		cond_resched();
-		index++;
+		/* End of range already reached? */
+		if (index > end || !index)
+			break;
 	}
 }
 EXPORT_SYMBOL(clean_bdev_aliases);
@@ -3549,10 +3548,10 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 	pagevec_init(&pvec, 0);
 
 	do {
-		unsigned want, nr_pages, i;
+		unsigned nr_pages, i;
 
-		want = min_t(unsigned, end - index, PAGEVEC_SIZE);
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
+						end - 1);
 		if (nr_pages == 0)
 			break;
 
@@ -3573,10 +3572,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 			    lastoff < page_offset(page))
 				goto check_range;
 
-			/* Searching done if the page index is out of range. */
-			if (page->index >= end)
-				goto not_found;
-
 			lock_page(page);
 			if (likely(page->mapping == inode->i_mapping) &&
 			    page_has_buffers(page)) {
@@ -3589,12 +3584,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 			unlock_page(page);
 			lastoff = page_offset(page) + PAGE_SIZE;
 		}
-
-		/* Searching done if fewer pages returned than wanted. */
-		if (nr_pages < want)
-			break;
-
-		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index < end);
 
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 337f88673ed9..174d6e6569a8 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -194,36 +194,6 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data)
-{
-	struct ceph_inode_info* ci = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	dout("ceph inode 0x%p now uncached", ci);
-
-	while (1) {
-		nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
 	.name		= "CEPH.inode",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -231,7 +201,6 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
 	.get_attr	= ceph_fscache_inode_get_attr,
 	.get_aux	= ceph_fscache_inode_get_aux,
 	.check_aux	= ceph_fscache_inode_check_aux,
-	.now_uncached	= ceph_fscache_inode_now_uncached,
 };
 
 void ceph_fscache_register_inode_cookie(struct inode *inode)
diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index 6c665bf4a27c..2c14020e5e1d 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -292,36 +292,6 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data,
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data)
-{
-	struct cifsInodeInfo *cifsi = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	cifs_dbg(FYI, "%s: cifs inode 0x%p now uncached\n", __func__, cifsi);
-
-	for (;;) {
-		nr_pages = pagevec_lookup(&pvec,
-					  cifsi->vfs_inode.i_mapping, first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 const struct fscache_cookie_def cifs_fscache_inode_object_def = {
 	.name		= "CIFS.uniqueid",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -329,5 +299,4 @@ const struct fscache_cookie_def cifs_fscache_inode_object_def = {
 	.get_attr	= cifs_fscache_inode_get_attr,
 	.get_aux	= cifs_fscache_inode_get_aux,
 	.check_aux	= cifs_fscache_inode_check_aux,
-	.now_uncached	= cifs_fscache_inode_now_uncached,
 };
diff --git a/fs/dax.c b/fs/dax.c
index ab925dc6647a..6afcacb3a87b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -42,6 +42,9 @@
 #define DAX_WAIT_TABLE_BITS 12
 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
 
+/* The 'colour' (ie low bits) within a PMD of a page offset.  */
+#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
+
 static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
 
 static int __init init_dax_wait_table(void)
@@ -54,6 +57,40 @@ static int __init init_dax_wait_table(void)
 }
 fs_initcall(init_dax_wait_table);
 
+/*
+ * We use lowest available bit in exceptional entry for locking, one bit for
+ * the entry size (PMD) and two more to tell us if the entry is a zero page or
+ * an empty entry that is just used for locking.  In total four special bits.
+ *
+ * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
+ * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
+ * block allocation.
+ */
+#define RADIX_DAX_SHIFT		(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
+#define RADIX_DAX_ENTRY_LOCK	(1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+#define RADIX_DAX_PMD		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
+#define RADIX_DAX_ZERO_PAGE	(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_EMPTY		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+
+static unsigned long dax_radix_sector(void *entry)
+{
+	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+}
+
+static void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+{
+	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
+			((unsigned long)sector << RADIX_DAX_SHIFT) |
+			RADIX_DAX_ENTRY_LOCK);
+}
+
+static unsigned int dax_radix_order(void *entry)
+{
+	if ((unsigned long)entry & RADIX_DAX_PMD)
+		return PMD_SHIFT - PAGE_SHIFT;
+	return 0;
+}
+
 static int dax_is_pmd_entry(void *entry)
 {
 	return (unsigned long)entry & RADIX_DAX_PMD;
@@ -66,7 +103,7 @@ static int dax_is_pte_entry(void *entry)
 
 static int dax_is_zero_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_HZP;
+	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
 }
 
 static int dax_is_empty_entry(void *entry)
@@ -98,7 +135,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
 	 * the range covered by the PMD map to the same bit lock.
 	 */
 	if (dax_is_pmd_entry(entry))
-		index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1);
+		index &= ~PG_PMD_COLOUR;
 
 	key->mapping = mapping;
 	key->entry_start = index;
@@ -121,6 +158,31 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mo
 }
 
 /*
+ * We do not necessarily hold the mapping->tree_lock when we call this
+ * function so it is possible that 'entry' is no longer a valid item in the
+ * radix tree.  This is okay because all we really need to do is to find the
+ * correct waitqueue where tasks might be waiting for that old 'entry' and
+ * wake them.
+ */
+static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+		pgoff_t index, void *entry, bool wake_all)
+{
+	struct exceptional_entry_key key;
+	wait_queue_head_t *wq;
+
+	wq = dax_entry_waitqueue(mapping, index, entry, &key);
+
+	/*
+	 * Checking for locked entry and prepare_to_wait_exclusive() happens
+	 * under mapping->tree_lock, ditto for entry handling in our callers.
+	 * So at this point all tasks that could have seen our entry locked
+	 * must be in the waitqueue and the following check will see them.
+	 */
+	if (waitqueue_active(wq))
+		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+}
+
+/*
  * Check whether the given slot is locked. The function must be called with
  * mapping->tree_lock held
  */
@@ -181,7 +243,8 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 	for (;;) {
 		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
 					  &slot);
-		if (!entry || !radix_tree_exceptional_entry(entry) ||
+		if (!entry ||
+		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
@@ -216,14 +279,9 @@ static void dax_unlock_mapping_entry(struct address_space *mapping,
 }
 
 static void put_locked_mapping_entry(struct address_space *mapping,
-				     pgoff_t index, void *entry)
+		pgoff_t index)
 {
-	if (!radix_tree_exceptional_entry(entry)) {
-		unlock_page(entry);
-		put_page(entry);
-	} else {
-		dax_unlock_mapping_entry(mapping, index);
-	}
+	dax_unlock_mapping_entry(mapping, index);
 }
 
 /*
@@ -233,7 +291,7 @@ static void put_locked_mapping_entry(struct address_space *mapping,
 static void put_unlocked_mapping_entry(struct address_space *mapping,
 				       pgoff_t index, void *entry)
 {
-	if (!radix_tree_exceptional_entry(entry))
+	if (!entry)
 		return;
 
 	/* We have to wake up next waiter for the radix tree entry lock */
@@ -241,15 +299,15 @@ static void put_unlocked_mapping_entry(struct address_space *mapping,
 }
 
 /*
- * Find radix tree entry at given index. If it points to a page, return with
- * the page locked. If it points to the exceptional entry, return with the
- * radix tree entry locked. If the radix tree doesn't contain given index,
- * create empty exceptional entry for the index and return with it locked.
+ * Find radix tree entry at given index. If it points to an exceptional entry,
+ * return it with the radix tree entry locked. If the radix tree doesn't
+ * contain given index, create an empty exceptional entry for the index and
+ * return with it locked.
  *
  * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
  * either return that locked entry or will return an error.  This error will
- * happen if there are any 4k entries (either zero pages or DAX entries)
- * within the 2MiB range that we are requesting.
+ * happen if there are any 4k entries within the 2MiB range that we are
+ * requesting.
  *
  * We always favor 4k entries over 2MiB entries. There isn't a flow where we
  * evict 4k entries in order to 'upgrade' them to a 2MiB entry.  A 2MiB
@@ -276,18 +334,21 @@ restart:
 	spin_lock_irq(&mapping->tree_lock);
 	entry = get_unlocked_mapping_entry(mapping, index, &slot);
 
+	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
+		entry = ERR_PTR(-EIO);
+		goto out_unlock;
+	}
+
 	if (entry) {
 		if (size_flag & RADIX_DAX_PMD) {
-			if (!radix_tree_exceptional_entry(entry) ||
-			    dax_is_pte_entry(entry)) {
+			if (dax_is_pte_entry(entry)) {
 				put_unlocked_mapping_entry(mapping, index,
 						entry);
 				entry = ERR_PTR(-EEXIST);
 				goto out_unlock;
 			}
 		} else { /* trying to grab a PTE entry */
-			if (radix_tree_exceptional_entry(entry) &&
-			    dax_is_pmd_entry(entry) &&
+			if (dax_is_pmd_entry(entry) &&
 			    (dax_is_zero_entry(entry) ||
 			     dax_is_empty_entry(entry))) {
 				pmd_downgrade = true;
@@ -321,7 +382,7 @@ restart:
 				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
 		if (err) {
 			if (pmd_downgrade)
-				put_locked_mapping_entry(mapping, index, entry);
+				put_locked_mapping_entry(mapping, index);
 			return ERR_PTR(err);
 		}
 		spin_lock_irq(&mapping->tree_lock);
@@ -371,52 +432,12 @@ restart:
 		spin_unlock_irq(&mapping->tree_lock);
 		return entry;
 	}
-	/* Normal page in radix tree? */
-	if (!radix_tree_exceptional_entry(entry)) {
-		struct page *page = entry;
-
-		get_page(page);
-		spin_unlock_irq(&mapping->tree_lock);
-		lock_page(page);
-		/* Page got truncated? Retry... */
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
-			goto restart;
-		}
-		return page;
-	}
 	entry = lock_slot(mapping, slot);
  out_unlock:
 	spin_unlock_irq(&mapping->tree_lock);
 	return entry;
 }
 
-/*
- * We do not necessarily hold the mapping->tree_lock when we call this
- * function so it is possible that 'entry' is no longer a valid item in the
- * radix tree.  This is okay because all we really need to do is to find the
- * correct waitqueue where tasks might be waiting for that old 'entry' and
- * wake them.
- */
-void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-		pgoff_t index, void *entry, bool wake_all)
-{
-	struct exceptional_entry_key key;
-	wait_queue_head_t *wq;
-
-	wq = dax_entry_waitqueue(mapping, index, entry, &key);
-
-	/*
-	 * Checking for locked entry and prepare_to_wait_exclusive() happens
-	 * under mapping->tree_lock, ditto for entry handling in our callers.
-	 * So at this point all tasks that could have seen our entry locked
-	 * must be in the waitqueue and the following check will see them.
-	 */
-	if (waitqueue_active(wq))
-		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
-}
-
 static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 					  pgoff_t index, bool trunc)
 {
@@ -426,7 +447,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 
 	spin_lock_irq(&mapping->tree_lock);
 	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || !radix_tree_exceptional_entry(entry))
+	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
 		goto out;
 	if (!trunc &&
 	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
@@ -468,50 +489,6 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
-/*
- * The user has performed a load from a hole in the file.  Allocating
- * a new page in the file would cause excessive storage usage for
- * workloads with sparse files.  We allocate a page cache page instead.
- * We'll kick it out of the page cache if it's ever written to,
- * otherwise it will simply fall out of the page cache under memory
- * pressure without ever having been dirtied.
- */
-static int dax_load_hole(struct address_space *mapping, void **entry,
-			 struct vm_fault *vmf)
-{
-	struct inode *inode = mapping->host;
-	struct page *page;
-	int ret;
-
-	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(*entry)) {
-		page = *entry;
-		goto finish_fault;
-	}
-
-	/* This will replace locked radix tree entry with a hole page */
-	page = find_or_create_page(mapping, vmf->pgoff,
-				   vmf->gfp_mask | __GFP_ZERO);
-	if (!page) {
-		ret = VM_FAULT_OOM;
-		goto out;
-	}
-
-finish_fault:
-	vmf->page = page;
-	ret = finish_fault(vmf);
-	vmf->page = NULL;
-	*entry = page;
-	if (!ret) {
-		/* Grab reference for PTE that is now referencing the page */
-		get_page(page);
-		ret = VM_FAULT_NOPAGE;
-	}
-out:
-	trace_dax_load_hole(inode, vmf, ret);
-	return ret;
-}
-
 static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
 		sector_t sector, size_t size, struct page *to,
 		unsigned long vaddr)
@@ -552,47 +529,27 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 				      unsigned long flags)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	int error = 0;
-	bool hole_fill = false;
 	void *new_entry;
 	pgoff_t index = vmf->pgoff;
 
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	/* Replacing hole page with block mapping? */
-	if (!radix_tree_exceptional_entry(entry)) {
-		hole_fill = true;
-		/*
-		 * Unmap the page now before we remove it from page cache below.
-		 * The page is locked so it cannot be faulted in again.
-		 */
-		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
-				    PAGE_SIZE, 0);
-		error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM);
-		if (error)
-			return ERR_PTR(error);
-	} else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) {
-		/* replacing huge zero page with PMD block mapping */
-		unmap_mapping_range(mapping,
-			(vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
+	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+		/* we are replacing a zero page with block mapping */
+		if (dax_is_pmd_entry(entry))
+			unmap_mapping_range(mapping,
+					(vmf->pgoff << PAGE_SHIFT) & PMD_MASK,
+					PMD_SIZE, 0);
+		else /* pte entry */
+			unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+					PAGE_SIZE, 0);
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
 	new_entry = dax_radix_locked_entry(sector, flags);
 
-	if (hole_fill) {
-		__delete_from_page_cache(entry, NULL);
-		/* Drop pagecache reference */
-		put_page(entry);
-		error = __radix_tree_insert(page_tree, index,
-				dax_radix_order(new_entry), new_entry);
-		if (error) {
-			new_entry = ERR_PTR(error);
-			goto unlock;
-		}
-		mapping->nrexceptional++;
-	} else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
+	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
 		/*
 		 * Only swap our new entry into the radix tree if the current
 		 * entry is a zero page or an empty entry.  If a normal PTE or
@@ -609,23 +566,14 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 		WARN_ON_ONCE(ret != entry);
 		__radix_tree_replace(page_tree, node, slot,
 				     new_entry, NULL, NULL);
+		entry = new_entry;
 	}
+
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
- unlock:
+
 	spin_unlock_irq(&mapping->tree_lock);
-	if (hole_fill) {
-		radix_tree_preload_end();
-		/*
-		 * We don't need hole page anymore, it has been replaced with
-		 * locked radix tree entry now.
-		 */
-		if (mapping->a_ops->freepage)
-			mapping->a_ops->freepage(entry);
-		unlock_page(entry);
-		put_page(entry);
-	}
-	return new_entry;
+	return entry;
 }
 
 static inline unsigned long
@@ -727,7 +675,7 @@ static int dax_writeback_one(struct block_device *bdev,
 	spin_lock_irq(&mapping->tree_lock);
 	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
 	/* Entry got punched out / reallocated? */
-	if (!entry2 || !radix_tree_exceptional_entry(entry2))
+	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
@@ -799,7 +747,7 @@ static int dax_writeback_one(struct block_device *bdev,
 	trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
  dax_unlock:
 	dax_read_unlock(id);
-	put_locked_mapping_entry(mapping, index, entry);
+	put_locked_mapping_entry(mapping, index);
 	return ret;
 
  put_unlocked:
@@ -874,11 +822,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
 static int dax_insert_mapping(struct address_space *mapping,
 		struct block_device *bdev, struct dax_device *dax_dev,
-		sector_t sector, size_t size, void **entryp,
+		sector_t sector, size_t size, void *entry,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	unsigned long vaddr = vmf->address;
-	void *entry = *entryp;
 	void *ret, *kaddr;
 	pgoff_t pgoff;
 	int id, rc;
@@ -899,47 +846,48 @@ static int dax_insert_mapping(struct address_space *mapping,
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0);
 	if (IS_ERR(ret))
 		return PTR_ERR(ret);
-	*entryp = ret;
 
 	trace_dax_insert_mapping(mapping->host, vmf, ret);
-	return vm_insert_mixed(vma, vaddr, pfn);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		return vm_insert_mixed_mkwrite(vma, vaddr, pfn);
+	else
+		return vm_insert_mixed(vma, vaddr, pfn);
 }
 
-/**
- * dax_pfn_mkwrite - handle first write to DAX page
- * @vmf: The description of the fault
+/*
+ * The user has performed a load from a hole in the file.  Allocating a new
+ * page in the file would cause excessive storage usage for workloads with
+ * sparse files.  Instead we insert a read-only mapping of the 4k zero page.
+ * If this page is ever written to we will re-fault and change the mapping to
+ * point to real DAX storage instead.
  */
-int dax_pfn_mkwrite(struct vm_fault *vmf)
+static int dax_load_hole(struct address_space *mapping, void *entry,
+			 struct vm_fault *vmf)
 {
-	struct file *file = vmf->vma->vm_file;
-	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	void *entry, **slot;
-	pgoff_t index = vmf->pgoff;
+	unsigned long vaddr = vmf->address;
+	int ret = VM_FAULT_NOPAGE;
+	struct page *zero_page;
+	void *entry2;
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, &slot);
-	if (!entry || !radix_tree_exceptional_entry(entry)) {
-		if (entry)
-			put_unlocked_mapping_entry(mapping, index, entry);
-		spin_unlock_irq(&mapping->tree_lock);
-		trace_dax_pfn_mkwrite_no_entry(inode, vmf, VM_FAULT_NOPAGE);
-		return VM_FAULT_NOPAGE;
+	zero_page = ZERO_PAGE(0);
+	if (unlikely(!zero_page)) {
+		ret = VM_FAULT_OOM;
+		goto out;
 	}
-	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
-	entry = lock_slot(mapping, slot);
-	spin_unlock_irq(&mapping->tree_lock);
-	/*
-	 * If we race with somebody updating the PTE and finish_mkwrite_fault()
-	 * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry
-	 * the fault in either case.
-	 */
-	finish_mkwrite_fault(vmf);
-	put_locked_mapping_entry(mapping, index, entry);
-	trace_dax_pfn_mkwrite(inode, vmf, VM_FAULT_NOPAGE);
-	return VM_FAULT_NOPAGE;
+
+	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+			RADIX_DAX_ZERO_PAGE);
+	if (IS_ERR(entry2)) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
+
+	vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page));
+out:
+	trace_dax_load_hole(inode, vmf, ret);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
 
 static bool dax_range_is_aligned(struct block_device *bdev,
 				 unsigned int offset, unsigned int length)