Merge branch 'dax-4.10-iomap-pmd' into origin

fs/Kconfig

@@ -55,7 +55,6 @@ config FS_DAX_PMD
 	depends on FS_DAX
 	depends on ZONE_DEVICE
 	depends on TRANSPARENT_HUGEPAGE
-	depends on BROKEN
 
 endif # BLOCK
 

fs/dax.c

@@ -34,25 +34,11 @@
 #include <linux/iomap.h>
 #include "internal.h"
 
-/*
- * We use lowest available bit in exceptional entry for locking, other two
- * bits to determine entry type. In total 3 special bits.
- */
-#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 3)
-#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD)
-#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK)
-#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
-#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
-		RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \
-		RADIX_TREE_EXCEPTIONAL_ENTRY))
-
 /* We choose 4096 entries - same as per-zone page wait tables */
 #define DAX_WAIT_TABLE_BITS 12
 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
 
-wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
+static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
 
 static int __init init_dax_wait_table(void)
 {
@@ -64,14 +50,6 @@ static int __init init_dax_wait_table(void)
 }
 fs_initcall(init_dax_wait_table);
 
-static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
-					      pgoff_t index)
-{
-	unsigned long hash = hash_long((unsigned long)mapping ^ index,
-				       DAX_WAIT_TABLE_BITS);
-	return wait_table + hash;
-}
-
 static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
 {
 	struct request_queue *q = bdev->bd_queue;
@@ -98,6 +76,26 @@ static void dax_unmap_atomic(struct block_device *bdev,
 	blk_queue_exit(bdev->bd_queue);
 }
 
+static int dax_is_pmd_entry(void *entry)
+{
+	return (unsigned long)entry & RADIX_DAX_PMD;
+}
+
+static int dax_is_pte_entry(void *entry)
+{
+	return !((unsigned long)entry & RADIX_DAX_PMD);
+}
+
+static int dax_is_zero_entry(void *entry)
+{
+	return (unsigned long)entry & RADIX_DAX_HZP;
+}
+
+static int dax_is_empty_entry(void *entry)
+{
+	return (unsigned long)entry & RADIX_DAX_EMPTY;
+}
+
 struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 {
 	struct page *page = alloc_pages(GFP_KERNEL, 0);
@@ -123,19 +121,6 @@ static bool buffer_written(struct buffer_head *bh)
 	return buffer_mapped(bh) && !buffer_unwritten(bh);
 }
 
-/*
- * When ext4 encounters a hole, it returns without modifying the buffer_head
- * which means that we can't trust b_size.  To cope with this, we set b_state
- * to 0 before calling get_block and, if any bit is set, we know we can trust
- * b_size.  Unfortunate, really, since ext4 knows precisely how long a hole is
- * and would save us time calling get_block repeatedly.
- */
-static bool buffer_size_valid(struct buffer_head *bh)
-{
-	return bh->b_state != 0;
-}
-
-
 static sector_t to_sector(const struct buffer_head *bh,
 		const struct inode *inode)
 {
@@ -177,8 +162,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 				rc = get_block(inode, block, bh, rw == WRITE);
 				if (rc)
 					break;
-				if (!buffer_size_valid(bh))
-					bh->b_size = 1 << blkbits;
 				bh_max = pos - first + bh->b_size;
 				bdev = bh->b_bdev;
 				/*
@@ -300,7 +283,7 @@ EXPORT_SYMBOL_GPL(dax_do_io);
  */
 struct exceptional_entry_key {
 	struct address_space *mapping;
-	unsigned long index;
+	pgoff_t entry_start;
 };
 
 struct wait_exceptional_entry_queue {
@@ -308,6 +291,26 @@ struct wait_exceptional_entry_queue {
 	struct exceptional_entry_key key;
 };
 
+static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
+		pgoff_t index, void *entry, struct exceptional_entry_key *key)
+{
+	unsigned long hash;
+
+	/*
+	 * If 'entry' is a PMD, align the 'index' that we use for the wait
+	 * queue to the start of that PMD.  This ensures that all offsets in
+	 * 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);
+
+	key->mapping = mapping;
+	key->entry_start = index;
+
+	hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS);
+	return wait_table + hash;
+}
+
 static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
 				       int sync, void *keyp)
 {
@@ -316,7 +319,7 @@ static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
 		container_of(wait, struct wait_exceptional_entry_queue, wait);
 
 	if (key->mapping != ewait->key.mapping ||
-	    key->index != ewait->key.index)
+	    key->entry_start != ewait->key.entry_start)
 		return 0;
 	return autoremove_wake_function(wait, mode, sync, NULL);
 }
@@ -372,24 +375,24 @@ static inline void *unlock_slot(struct address_space *mapping, void **slot)
 static void *get_unlocked_mapping_entry(struct address_space *mapping,
 					pgoff_t index, void ***slotp)
 {
-	void *ret, **slot;
+	void *entry, **slot;
 	struct wait_exceptional_entry_queue ewait;
-	wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+	wait_queue_head_t *wq;
 
 	init_wait(&ewait.wait);
 	ewait.wait.func = wake_exceptional_entry_func;
-	ewait.key.mapping = mapping;
-	ewait.key.index = index;
 
 	for (;;) {
-		ret = __radix_tree_lookup(&mapping->page_tree, index, NULL,
+		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
 					  &slot);
-		if (!ret || !radix_tree_exceptional_entry(ret) ||
+		if (!entry || !radix_tree_exceptional_entry(entry) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
-			return ret;
+			return entry;
 		}
+
+		wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
 		prepare_to_wait_exclusive(wq, &ewait.wait,
 					  TASK_UNINTERRUPTIBLE);
 		spin_unlock_irq(&mapping->tree_lock);
@@ -399,52 +402,157 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 	}
 }
 
+static void put_locked_mapping_entry(struct address_space *mapping,
+				     pgoff_t index, void *entry)
+{
+	if (!radix_tree_exceptional_entry(entry)) {
+		unlock_page(entry);
+		put_page(entry);
+	} else {
+		dax_unlock_mapping_entry(mapping, index);
+	}
+}
+
+/*
+ * Called when we are done with radix tree entry we looked up via
+ * get_unlocked_mapping_entry() and which we didn't lock in the end.
+ */
+static void put_unlocked_mapping_entry(struct address_space *mapping,
+				       pgoff_t index, void *entry)
+{
+	if (!radix_tree_exceptional_entry(entry))
+		return;
+
+	/* We have to wake up next waiter for the radix tree entry lock */
+	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
+}
+
 /*
  * 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.
  *
+ * 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.
+ *
+ * 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
+ * insertion will fail if it finds any 4k entries already in the tree, and a
+ * 4k insertion will cause an existing 2MiB entry to be unmapped and
+ * downgraded to 4k entries.  This happens for both 2MiB huge zero pages as
+ * well as 2MiB empty entries.
+ *
+ * The exception to this downgrade path is for 2MiB DAX PMD entries that have
+ * real storage backing them.  We will leave these real 2MiB DAX entries in
+ * the tree, and PTE writes will simply dirty the entire 2MiB DAX entry.
+ *
  * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
  * persistent memory the benefit is doubtful. We can add that later if we can
  * show it helps.
  */
-static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index)
+static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
+		unsigned long size_flag)
 {
-	void *ret, **slot;
+	bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
+	void *entry, **slot;
 
 restart:
 	spin_lock_irq(&mapping->tree_lock);
-	ret = get_unlocked_mapping_entry(mapping, index, &slot);
+	entry = get_unlocked_mapping_entry(mapping, index, &slot);
+
+	if (entry) {
+		if (size_flag & RADIX_DAX_PMD) {
+			if (!radix_tree_exceptional_entry(entry) ||
+			    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) &&
+			    (dax_is_zero_entry(entry) ||
+			     dax_is_empty_entry(entry))) {
+				pmd_downgrade = true;
+			}
+		}
+	}
+
 	/* No entry for given index? Make sure radix tree is big enough. */
-	if (!ret) {
+	if (!entry || pmd_downgrade) {
 		int err;
 
+		if (pmd_downgrade) {
+			/*
+			 * Make sure 'entry' remains valid while we drop
+			 * mapping->tree_lock.
+			 */
+			entry = lock_slot(mapping, slot);
+		}
+
 		spin_unlock_irq(&mapping->tree_lock);
 		err = radix_tree_preload(
 				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
-		if (err)
+		if (err) {
+			if (pmd_downgrade)
+				put_locked_mapping_entry(mapping, index, entry);
 			return ERR_PTR(err);
-		ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
-			       RADIX_DAX_ENTRY_LOCK);
+		}
+
+		/*
+		 * Besides huge zero pages the only other thing that gets
+		 * downgraded are empty entries which don't need to be
+		 * unmapped.
+		 */
+		if (pmd_downgrade && dax_is_zero_entry(entry))
+			unmap_mapping_range(mapping,
+				(index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
+
 		spin_lock_irq(&mapping->tree_lock);
-		err = radix_tree_insert(&mapping->page_tree, index, ret);
+
+		if (pmd_downgrade) {
+			radix_tree_delete(&mapping->page_tree, index);
+			mapping->nrexceptional--;
+			dax_wake_mapping_entry_waiter(mapping, index, entry,
+					true);
+		}
+
+		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
+
+		err = __radix_tree_insert(&mapping->page_tree, index,
+				dax_radix_order(entry), entry);
 		radix_tree_preload_end();
 		if (err) {
 			spin_unlock_irq(&mapping->tree_lock);
-			/* Someone already created the entry? */
-			if (err == -EEXIST)
+			/*
+			 * Someone already created the entry?  This is a
+			 * normal failure when inserting PMDs in a range
+			 * that already contains PTEs.  In that case we want
+			 * to return -EEXIST immediately.
+			 */
+			if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
 				goto restart;
+			/*
+			 * Our insertion of a DAX PMD entry failed, most
+			 * likely because it collided with a PTE sized entry
+			 * at a different index in the PMD range.  We haven't
+			 * inserted anything into the radix tree and have no
+			 * waiters to wake.
+			 */
 			return ERR_PTR(err);
 		}
 		/* Good, we have inserted empty locked entry into the tree. */
 		mapping->nrexceptional++;
 		spin_unlock_irq(&mapping->tree_lock);
-		return ret;
+		return entry;
 	}
 	/* Normal page in radix tree? */
-	if (!radix_tree_exceptional_entry(ret)) {
-		struct page *page = ret;
+	if (!radix_tree_exceptional_entry(entry)) {
+		struct page *page = entry;
 
 		get_page(page);
 		spin_unlock_irq(&mapping->tree_lock);
@@ -457,15 +565,26 @@ restart:
 		}
 		return page;
 	}
-	ret = lock_slot(mapping, slot);
+	entry = lock_slot(mapping, slot);
+ out_unlock:
 	spin_unlock_irq(&mapping->tree_lock);
-	return ret;
+	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, bool wake_all)
+		pgoff_t index, void *entry, bool wake_all)
 {
-	wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+	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
@@ -473,54 +592,24 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 	 * 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)) {
-		struct exceptional_entry_key key;
-
-		key.mapping = mapping;
-		key.index = index;
+	if (waitqueue_active(wq))
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
-	}
 }
 
 void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *ret, **slot;
+	void *entry, **slot;
 
 	spin_lock_irq(&mapping->tree_lock);
-	ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
-	if (WARN_ON_ONCE(!ret || !radix_tree_exceptional_entry(ret) ||
+	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
+	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
 			 !slot_locked(mapping, slot))) {
 		spin_unlock_irq(&mapping->tree_lock);
 		return;
 	}
 	unlock_slot(mapping, slot);
 	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, false);
-}
-
-static void put_locked_mapping_entry(struct address_space *mapping,
-				     pgoff_t index, void *entry)
-{
-	if (!radix_tree_exceptional_entry(entry)) {
-		unlock_page(entry);
-		put_page(entry);
-	} else {
-		dax_unlock_mapping_entry(mapping, index);
-	}
-}
-
-/*
- * Called when we are done with radix tree entry we looked up via
- * get_unlocked_mapping_entry() and which we didn't lock in the end.
- */
-static void put_unlocked_mapping_entry(struct address_space *mapping,
-				       pgoff_t index, void *entry)
-{
-	if (!radix_tree_exceptional_entry(entry))
-		return;
-
-	/* We have to wake up next waiter for the radix tree entry lock */
-	dax_wake_mapping_entry_waiter(mapping, index, false);
+	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
 }
 
 /*
@@ -547,7 +636,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	radix_tree_delete(&mapping->page_tree, index);
 	mapping->nrexceptional--;
 	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, true);
+	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
 
 	return 1;
 }
@@ -600,11 +689,17 @@ static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size
 	return 0;
 }
 
-#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
-
+/*
+ * By this point grab_mapping_entry() has ensured that we have a locked entry
+ * of the appropriate size so we don't have to worry about downgrading PMDs to
+ * PTEs.  If we happen to be trying to insert a PTE and there is a PMD
+ * already in the tree, we will skip the insertion and just dirty the PMD as
+ * appropriate.
+ */
 static void *dax_insert_mapping_entry(struct address_space *mapping,
 				      struct vm_fault *vmf,
-				      void *entry, sector_t sector)
+				      void *entry, sector_t sector,
+				      unsigned long flags)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
 	int error = 0;
@@ -627,22 +722,35 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 		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);
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
-	new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) |
-		       RADIX_DAX_ENTRY_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, new_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 {
+	} else 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
+		 * PMD entry is already in the tree, we leave it alone.  This
+		 * means that if we are trying to insert a PTE and the
+		 * existing entry is a PMD, we will just leave the PMD in the
+		 * tree and dirty it if necessary.
+		 */
 		void **slot;
 		void *ret;
 
@@ -672,7 +780,6 @@ static int dax_writeback_one(struct block_device *bdev,
 		struct address_space *mapping, pgoff_t index, void *entry)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	int type = RADIX_DAX_TYPE(entry);
 	struct radix_tree_node *node;
 	struct blk_dax_ctl dax;
 	void **slot;
@@ -693,13 +800,21 @@ static int dax_writeback_one(struct block_device *bdev,
 	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
 		goto unlock;
 
-	if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
+	if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
+				dax_is_zero_entry(entry))) {
 		ret = -EIO;
 		goto unlock;
 	}
 
-	dax.sector = RADIX_DAX_SECTOR(entry);
-	dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
+	/*
+	 * Even if dax_writeback_mapping_range() was given a wbc->range_start
+	 * in the middle of a PMD, the 'index' we are given will be aligned to
+	 * the start index of the PMD, as will the sector we pull from
+	 * 'entry'.  This allows us to flush for PMD_SIZE and not have to
+	 * worry about partial PMD writebacks.
+	 */
+	dax.sector = dax_radix_sector(entry);
+	dax.size = PAGE_SIZE << dax_radix_order(entry);
 	spin_unlock_irq(&mapping->tree_lock);
 
 	/*
@@ -738,12 +853,11 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	pgoff_t start_index, end_index, pmd_index;
+	pgoff_t start_index, end_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	bool done = false;
 	int i, ret = 0;
-	void *entry;
 
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
@@ -753,15 +867,6 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 
 	start_index = wbc->range_start >> PAGE_SHIFT;
 	end_index = wbc->range_end >> PAGE_SHIFT;
-	pmd_index = DAX_PMD_INDEX(start_index);
-
-	rcu_read_lock();
-	entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
-	rcu_read_unlock();
-
-	/* see if the start of our range is covered by a PMD entry */
-	if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
-		start_index = pmd_index;
 
 	tag_pages_for_writeback(mapping, start_index, end_index);
 
@@ -806,7 +911,7 @@ static int dax_insert_mapping(struct address_space *mapping,
 		return PTR_ERR(dax.addr);
 	dax_unmap_atomic(bdev, &dax);
 
-	ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector);
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector, 0);
 	if (IS_ERR(ret))
 		return PTR_ERR(ret);
 	*entryp = ret;
@@ -853,7 +958,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	bh.b_bdev = inode->i_sb->s_bdev;
 	bh.b_size = PAGE_SIZE;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff);
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
 	if (IS_ERR(entry)) {
 		error = PTR_ERR(entry);
 		goto out;
@@ -913,224 +1018,6 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 }
 EXPORT_SYMBOL_GPL(dax_fault);
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
-/*
- * The 'colour' (ie low bits) within a PMD of a page offset.  This comes up
- * more often than one might expect in the below function.
- */
-#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
-
-static void __dax_dbg(struct buffer_head *bh, unsigned long address,
-		const char *reason, const char *fn)
-{
-	if (bh) {
-		char bname[BDEVNAME_SIZE];
-		bdevname(bh->b_bdev, bname);
-		pr_debug("%s: %s addr: %lx dev %s state %lx start %lld "
-			"length %zd fallback: %s\n", fn, current->comm,
-			address, bname, bh->b_state, (u64)bh->b_blocknr,
-			bh->b_size, reason);
-	} else {
-		pr_debug("%s: %s addr: %lx fallback: %s\n", fn,
-			current->comm, address, reason);
-	}
-}
-
-#define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
-
-/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
- */
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, get_block_t get_block)
-{
-	struct file *file = vma->vm_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	struct buffer_head bh;
-	unsigned blkbits = inode->i_blkbits;
-	unsigned long pmd_addr = address & PMD_MASK;
-	bool write = flags & FAULT_FLAG_WRITE;
-	struct block_device *bdev;
-	pgoff_t size, pgoff;
-	sector_t block;
-	int result = 0;
-	bool alloc = false;
-
-	/* dax pmd mappings require pfn_t_devmap() */
-	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
-		return VM_FAULT_FALLBACK;
-
-	/* Fall back to PTEs if we're going to COW */
-	if (write && !(vma->vm_flags & VM_SHARED)) {
-		split_huge_pmd(vma, pmd, address);
-		dax_pmd_dbg(NULL, address, "cow write");
-		return VM_FAULT_FALLBACK;
-	}
-	/* If the PMD would extend outside the VMA */
-	if (pmd_addr < vma->vm_start) {
-		dax_pmd_dbg(NULL, address, "vma start unaligned");
-		return VM_FAULT_FALLBACK;
-	}
-	if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
-		dax_pmd_dbg(NULL, address, "vma end unaligned");
-		return VM_FAULT_FALLBACK;
-	}
-
-	pgoff = linear_page_index(vma, pmd_addr);
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (pgoff >= size)
-		return VM_FAULT_SIGBUS;
-	/* If the PMD would cover blocks out of the file */
-	if ((pgoff | PG_PMD_COLOUR) >= size) {
-		dax_pmd_dbg(NULL, address,
-				"offset + huge page size > file size");
-		return VM_FAULT_FALLBACK;
-	}
-
-	memset(&bh, 0, sizeof(bh));
-	bh.b_bdev = inode->i_sb->s_bdev;
-	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
-
-	bh.b_size = PMD_SIZE;
-
-	if (get_block(inode, block, &bh, 0) != 0)
-		return VM_FAULT_SIGBUS;
-
-	if (!buffer_mapped(&bh) && write) {
-		if (get_block(inode, block, &bh, 1) != 0)
-			return VM_FAULT_SIGBUS;
-		alloc = true;
-		WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
-	}
-
-	bdev = bh.b_bdev;
-
-	/*
-	 * If the filesystem isn't willing to tell us the length of a hole,
-	 * just fall back to PTEs.  Calling get_block 512 times in a loop
-	 * would be silly.
-	 */
-	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
-		dax_pmd_dbg(&bh, address, "allocated block too small");
-		return VM_FAULT_FALLBACK;
-	}
-
-	/*
-	 * If we allocated new storage, make sure no process has any
-	 * zero pages covering this hole
-	 */
-	if (alloc) {
-		loff_t lstart = pgoff << PAGE_SHIFT;
-		loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */
-
-		truncate_pagecache_range(inode, lstart, lend);
-	}
-
-	if (!write && !buffer_mapped(&bh)) {
-		spinlock_t *ptl;
-		pmd_t entry;
-		struct page *zero_page = mm_get_huge_zero_page(vma->vm_mm);
-
-		if (unlikely(!zero_page)) {
-			dax_pmd_dbg(&bh, address, "no zero page");
-			goto fallback;
-		}
-
-		ptl = pmd_lock(vma->vm_mm, pmd);
-		if (!pmd_none(*pmd)) {
-			spin_unlock(ptl);
-			dax_pmd_dbg(&bh, address, "pmd already present");
-			goto fallback;
-		}
-
-		dev_dbg(part_to_dev(bdev->bd_part),
-				"%s: %s addr: %lx pfn: <zero> sect: %llx\n",
-				__func__, current->comm, address,
-				(unsigned long long) to_sector(&bh, inode));
-
-		entry = mk_pmd(zero_page, vma->vm_page_prot);
-		entry = pmd_mkhuge(entry);
-		set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
-		result = VM_FAULT_NOPAGE;
-		spin_unlock(ptl);
-	} else {
-		struct blk_dax_ctl dax = {
-			.sector = to_sector(&bh, inode),
-			.size = PMD_SIZE,
-		};
-		long length = dax_map_atomic(bdev, &dax);
-
-		if (length < 0) {
-			dax_pmd_dbg(&bh, address, "dax-error fallback");
-			goto fallback;
-		}
-		if (length < PMD_SIZE) {
-			dax_pmd_dbg(&bh, address, "dax-length too small");
-			dax_unmap_atomic(bdev, &dax);
-			goto fallback;
-		}
-		if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
-			dax_pmd_dbg(&bh, address, "pfn unaligned");
-			dax_unmap_atomic(bdev, &dax);
-			goto fallback;
-		}
-
-		if (!pfn_t_devmap(dax.pfn)) {
-			dax_unmap_atomic(bdev, &dax);
-			dax_pmd_dbg(&bh, address, "pfn not in memmap");
-			goto fallback;
-		}
-		dax_unmap_atomic(bdev, &dax);
-
-		/*
-		 * For PTE faults we insert a radix tree entry for reads, and
-		 * leave it clean.  Then on the first write we dirty the radix
-		 * tree entry via the dax_pfn_mkwrite() path.  This sequence
-		 * allows the dax_pfn_mkwrite() call to be simpler and avoid a
-		 * call into get_block() to translate the pgoff to a sector in
-		 * order to be able to create a new radix tree entry.
-		 *
-		 * The PMD path doesn't have an equivalent to
-		 * dax_pfn_mkwrite(), though, so for a read followed by a
-		 * write we traverse all the way through dax_pmd_fault()
-		 * twice.  This means we can just skip inserting a radix tree
-		 * entry completely on the initial read and just wait until
-		 * the write to insert a dirty entry.
-		 */
-		if (write) {
-			/*
-			 * We should insert radix-tree entry and dirty it here.
-			 * For now this is broken...
-			 */
-		}
-
-		dev_dbg(part_to_dev(bdev->bd_part),
-				"%s: %s addr: %lx pfn: %lx sect: %llx\n",
-				__func__, current->comm, address,
-				pfn_t_to_pfn(dax.pfn),
-				(unsigned long long) dax.sector);
-		result |= vmf_insert_pfn_pmd(vma, address, pmd,
-				dax.pfn, write);
-	}
-
- out:
-	return result;
-
- fallback:
-	count_vm_event(THP_FAULT_FALLBACK);
-	result = VM_FAULT_FALLBACK;
-	goto out;
-}
-EXPORT_SYMBOL_GPL(dax_pmd_fault);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 /**
  * dax_pfn_mkwrite - handle first write to DAX page
  * @vma: The virtual memory area where the fault occurred
@@ -1214,7 +1101,8 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 	/* Block boundary? Nothing to do */
 	if (!length)
 		return 0;
-	BUG_ON((offset + length) > PAGE_SIZE);
+	if (WARN_ON_ONCE((offset + length) > PAGE_SIZE))
+		return -EINVAL;
 
 	memset(&bh, 0, sizeof(bh));
 	bh.b_bdev = inode->i_sb->s_bdev;
@@ -1245,8 +1133,13 @@ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
 EXPORT_SYMBOL_GPL(dax_truncate_page);
 
 #ifdef CONFIG_FS_IOMAP
+static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
+{
+	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
+}
+
 static loff_t
-iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct iomap *iomap)
 {
 	struct iov_iter *iter = data;
@@ -1270,8 +1163,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct blk_dax_ctl dax = { 0 };
 		ssize_t map_len;
 
-		dax.sector = iomap->blkno +
-			(((pos & PAGE_MASK) - iomap->offset) >> 9);
+		dax.sector = dax_iomap_sector(iomap, pos);
 		dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK;
 		map_len = dax_map_atomic(iomap->bdev, &dax);
 		if (map_len < 0) {
@@ -1303,7 +1195,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 }
 
 /**
- * iomap_dax_rw - Perform I/O to a DAX file
+ * dax_iomap_rw - Perform I/O to a DAX file
  * @iocb:	The control block for this I/O
  * @iter:	The addresses to do I/O from or to
  * @ops:	iomap ops passed from the file system
@@ -1313,7 +1205,7 @@ iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
  * and evicting any page cache pages in the region under I/O.
  */
 ssize_t
-iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
+dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		struct iomap_ops *ops)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
@@ -1343,7 +1235,7 @@ iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
-				iter, iomap_dax_actor);
+				iter, dax_iomap_actor);
 		if (ret <= 0)
 			break;
 		pos += ret;
@@ -1353,10 +1245,10 @@ iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
 	iocb->ki_pos += done;
 	return done ? done : ret;
 }
-EXPORT_SYMBOL_GPL(iomap_dax_rw);
+EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
 /**
- * iomap_dax_fault - handle a page fault on a DAX file
+ * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @ops: iomap ops passed from the file system
@@ -1365,7 +1257,7 @@ EXPORT_SYMBOL_GPL(iomap_dax_rw);
  * or mkwrite handler for DAX files. Assumes the caller has done all the
  * necessary locking for the page fault to proceed successfully.
  */
-int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops)
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -1374,8 +1266,9 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	sector_t sector;
 	struct iomap iomap = { 0 };
-	unsigned flags = 0;
+	unsigned flags = IOMAP_FAULT;
 	int error, major = 0;
+	int locked_status = 0;
 	void *entry;
 
 	/*
@@ -1386,7 +1279,7 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff);
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
 	if (IS_ERR(entry)) {
 		error = PTR_ERR(entry);
 		goto out;
@@ -1405,10 +1298,10 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		goto unlock_entry;
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
 		error = -EIO;		/* fs corruption? */
-		goto unlock_entry;
+		goto finish_iomap;
 	}
 
-	sector = iomap.blkno + (((pos & PAGE_MASK) - iomap.offset) >> 9);
+	sector = dax_iomap_sector(&iomap, pos);
 
 	if (vmf->cow_page) {
 		switch (iomap.type) {
@@ -1427,13 +1320,15 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto unlock_entry;
+			goto finish_iomap;
 		if (!radix_tree_exceptional_entry(entry)) {
 			vmf->page = entry;
-			return VM_FAULT_LOCKED;
+			locked_status = VM_FAULT_LOCKED;
+		} else {
+			vmf->entry = entry;
+			locked_status = VM_FAULT_DAX_LOCKED;
 		}
-		vmf->entry = entry;
-		return VM_FAULT_DAX_LOCKED;
+		goto finish_iomap;
 	}
 
 	switch (iomap.type) {
@@ -1448,8 +1343,10 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
-		if (!(vmf->flags & FAULT_FLAG_WRITE))
-			return dax_load_hole(mapping, entry, vmf);
+		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
+			locked_status = dax_load_hole(mapping, entry, vmf);
+			break;
+		}
 		/*FALLTHRU*/
 	default:
 		WARN_ON_ONCE(1);
@@ -1457,15 +1354,218 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
+ finish_iomap:
+	if (ops->iomap_end) {
+		if (error) {
+			/* keep previous error */
+			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
+					&iomap);
+		} else {
+			error = ops->iomap_end(inode, pos, PAGE_SIZE,
+					PAGE_SIZE, flags, &iomap);
+		}
+	}
  unlock_entry:
-	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+	if (!locked_status || error)
+		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  out:
 	if (error == -ENOMEM)
 		return VM_FAULT_OOM | major;
 	/* -EBUSY is fine, somebody else faulted on the same PTE */
 	if (error < 0 && error != -EBUSY)
 		return VM_FAULT_SIGBUS | major;
+	if (locked_status) {
+		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
+		return locked_status;
+	}
 	return VM_FAULT_NOPAGE | major;
 }
-EXPORT_SYMBOL_GPL(iomap_dax_fault);
+EXPORT_SYMBOL_GPL(dax_iomap_fault);
+
+#ifdef CONFIG_FS_DAX_PMD
+/*
+ * The 'colour' (ie low bits) within a PMD of a page offset.  This comes up
+ * more often than one might expect in the below functions.
+ */
+#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
+
+static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
+		struct vm_fault *vmf, unsigned long address,
+		struct iomap *iomap, loff_t pos, bool write, void **entryp)
+{
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct block_device *bdev = iomap->bdev;
+	struct blk_dax_ctl dax = {
+		.sector = dax_iomap_sector(iomap, pos),
+		.size = PMD_SIZE,
+	};
+	long length = dax_map_atomic(bdev, &dax);
+	void *ret;
+
+	if (length < 0) /* dax_map_atomic() failed */
+		return VM_FAULT_FALLBACK;
+	if (length < PMD_SIZE)
+		goto unmap_fallback;
+	if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)
+		goto unmap_fallback;
+	if (!pfn_t_devmap(dax.pfn))
+		goto unmap_fallback;
+
+	dax_unmap_atomic(bdev, &dax);
+
+	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector,
+			RADIX_DAX_PMD);
+	if (IS_ERR(ret))
+		return VM_FAULT_FALLBACK;
+	*entryp = ret;
+
+	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
+
+ unmap_fallback:
+	dax_unmap_atomic(bdev, &dax);
+	return VM_FAULT_FALLBACK;
+}
+
+static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
+		struct vm_fault *vmf, unsigned long address,
+		struct iomap *iomap, void **entryp)
+{
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	unsigned long pmd_addr = address & PMD_MASK;
+	struct page *zero_page;
+	spinlock_t *ptl;
+	pmd_t pmd_entry;
+	void *ret;
+
+	zero_page = mm_get_huge_zero_page(vma->vm_mm);
+
+	if (unlikely(!zero_page))
+		return VM_FAULT_FALLBACK;
+
+	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0,
+			RADIX_DAX_PMD | RADIX_DAX_HZP);
+	if (IS_ERR(ret))
+		return VM_FAULT_FALLBACK;
+	*entryp = ret;
+
+	ptl = pmd_lock(vma->vm_mm, pmd);
+	if (!pmd_none(*pmd)) {
+		spin_unlock(ptl);
+		return VM_FAULT_FALLBACK;
+	}
+
+	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
+	pmd_entry = pmd_mkhuge(pmd_entry);
+	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
+	spin_unlock(ptl);
+	return VM_FAULT_NOPAGE;
+}
+
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops)
+{
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	unsigned long pmd_addr = address & PMD_MASK;
+	bool write = flags & FAULT_FLAG_WRITE;
+	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
+	struct inode *inode = mapping->host;
+	int result = VM_FAULT_FALLBACK;
+	struct iomap iomap = { 0 };
+	pgoff_t max_pgoff, pgoff;
+	struct vm_fault vmf;
+	void *entry;
+	loff_t pos;
+	int error;
+
+	/* Fall back to PTEs if we're going to COW */
+	if (write && !(vma->vm_flags & VM_SHARED))
+		goto fallback;
+
+	/* If the PMD would extend outside the VMA */
+	if (pmd_addr < vma->vm_start)
+		goto fallback;
+	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
+		goto fallback;
+
+	/*
+	 * Check whether offset isn't beyond end of file now. Caller is
+	 * supposed to hold locks serializing us with truncate / punch hole so
+	 * this is a reliable test.
+	 */
+	pgoff = linear_page_index(vma, pmd_addr);
+	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+
+	if (pgoff > max_pgoff)
+		return VM_FAULT_SIGBUS;
+
+	/* If the PMD would extend beyond the file size */
+	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
+		goto fallback;
+
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto fallback;
+
+	/*
+	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
+	 * setting up a mapping, so really we're using iomap_begin() as a way
+	 * to look up our filesystem block.
+	 */
+	pos = (loff_t)pgoff << PAGE_SHIFT;
+	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
+	if (error)
+		goto unlock_entry;
+	if (iomap.offset + iomap.length < pos + PMD_SIZE)
+		goto finish_iomap;
+
+	vmf.pgoff = pgoff;
+	vmf.flags = flags;
+	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		result = dax_pmd_insert_mapping(vma, pmd, &vmf, address,
+				&iomap, pos, write, &entry);
+		break;
+	case IOMAP_UNWRITTEN:
+	case IOMAP_HOLE:
+		if (WARN_ON_ONCE(write))
+			goto finish_iomap;
+		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
+				&entry);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+ finish_iomap:
+	if (ops->iomap_end) {
+		if (result == VM_FAULT_FALLBACK) {
+			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
+					&iomap);
+		} else {
+			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
+					iomap_flags, &iomap);
+			if (error)
+				result = VM_FAULT_FALLBACK;
+		}
+	}
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
+ fallback:
+	if (result == VM_FAULT_FALLBACK) {
+		split_huge_pmd(vma, pmd, address);
+		count_vm_event(THP_FAULT_FALLBACK);
+	}
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
+#endif /* CONFIG_FS_DAX_PMD */
 #endif /* CONFIG_FS_IOMAP */

fs/ext2/file.c

@@ -38,7 +38,7 @@ static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return 0; /* skip atime */
 
 	inode_lock_shared(inode);
-	ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -62,7 +62,7 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out_unlock;
 
-	ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		mark_inode_dirty(inode);
@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops);
+	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -107,27 +107,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&ei->dax_sem);
-
-	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
-
-	up_read(&ei->dax_sem);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -154,7 +133,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
-	.pmd_fault	= ext2_dax_pmd_fault,
+	/*
+	 * .pmd_fault is not supported for DAX because allocation in ext2
+	 * cannot be reliably aligned to huge page sizes and so pmd faults
+	 * will always fail and fail back to regular faults.
+	 */
 	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
@@ -166,7 +149,7 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &ext2_dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	vma->vm_flags |= VM_MIXEDMAP;
 	return 0;
 }
 #else

fs/ext4/inode.c

@@ -767,6 +767,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_update_bh_state(bh, map.m_flags);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
+	} else if (ret == 0) {
+		/* hole case, need to fill in bh->b_size */
+		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 	}
 	return ret;
 }

fs/iomap.c

@@ -467,8 +467,9 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	offset = page_offset(page);
 	while (length > 0) {
-		ret = iomap_apply(inode, offset, length, IOMAP_WRITE,
-				ops, page, iomap_page_mkwrite_actor);
+		ret = iomap_apply(inode, offset, length,
+				IOMAP_WRITE | IOMAP_FAULT, ops, page,
+				iomap_page_mkwrite_actor);
 		if (unlikely(ret <= 0))
 			goto out_unlock;
 		offset += ret;

fs/xfs/xfs_aops.c

@@ -1298,8 +1298,7 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct,
-	bool			dax_fault)
+	bool			direct)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1420,13 +1419,8 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create) {
-			if (dax_fault)
-				ASSERT(!ISUNWRITTEN(&imap));
-			else
-				xfs_map_direct(inode, bh_result, &imap, offset,
-						is_cow);
-		}
+		if (create)
+			xfs_map_direct(inode, bh_result, &imap, offset, is_cow);
 	}
 
 	/*
@@ -1466,7 +1460,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
 }
 
 int
@@ -1476,17 +1470,7 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
-}
-
-int
-xfs_get_blocks_dax_fault(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
 }
 
 /*

fs/xfs/xfs_aops.h

@@ -59,9 +59,6 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
-int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
-			         struct buffer_head *map_bh, int create);
-
 int	xfs_end_io_direct_write(struct kiocb *iocb, loff_t offset,
 		ssize_t size, void *private);
 int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);

fs/xfs/xfs_file.c

@@ -318,7 +318,7 @@ xfs_file_dax_read(
 		return 0; /* skip atime */
 
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	file_accessed(iocb->ki_filp);
@@ -653,7 +653,7 @@ xfs_file_dax_write(
 
 	trace_xfs_file_dax_write(ip, count, pos);
 
-	ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
@@ -1474,7 +1474,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else {
 		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
@@ -1508,7 +1508,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1545,7 +1545,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)

include/linux/dax.h

@@ -8,21 +8,46 @@
 
 struct iomap_ops;
 
-/* We use lowest available exceptional entry bit for locking */
+/*
+ * 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 huge zero
+ * page (HZP) 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 HZP 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_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
 
-ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
+static inline unsigned long dax_radix_sector(void *entry)
+{
+	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+}
+
+static inline 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);
+}
+
+ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		struct iomap_ops *ops);
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
 		  get_block_t, dio_iodone_t, int flags);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-				   pgoff_t index, bool wake_all);
+		pgoff_t index, void *entry, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
@@ -48,15 +73,32 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
 }
 #endif
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t);
-#else
 static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t *pmd, unsigned int flags, get_block_t gb)
 {
 	return VM_FAULT_FALLBACK;
 }
+
+#ifdef CONFIG_FS_DAX_PMD
+static inline unsigned int dax_radix_order(void *entry)
+{
+	if ((unsigned long)entry & RADIX_DAX_PMD)
+		return PMD_SHIFT - PAGE_SHIFT;
+	return 0;
+}
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
+#else
+static inline unsigned int dax_radix_order(void *entry)
+{
+	return 0;
+}
+static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd, unsigned int flags,
+		struct iomap_ops *ops)
+{
+	return VM_FAULT_FALLBACK;
+}
 #endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
 #define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)

include/linux/iomap.h

@@ -49,6 +49,7 @@ struct iomap {
 #define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
 #define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
+#define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 
 struct iomap_ops {
 	/*

mm/filemap.c

@@ -137,13 +137,12 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		} else {
 			/* DAX can replace empty locked entry with a hole */
 			WARN_ON_ONCE(p !=
-				(void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
-					 RADIX_DAX_ENTRY_LOCK));
+				dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
 			/* DAX accounts exceptional entries as normal pages */
 			if (node)
 				workingset_node_pages_dec(node);
 			/* Wakeup waiters for exceptional entry lock */
-			dax_wake_mapping_entry_waiter(mapping, page->index,
+			dax_wake_mapping_entry_waiter(mapping, page->index, p,
 						      false);
 		}
 	}