Merge tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This cycle was was not something I ever want to repeat as there were
  several late changes that have only now just settled.

  Half of the branch up to commit d2c997c0f145 ("fs, dax: use
  page->mapping to warn...") have been in -next for several releases.
  The of_pmem driver and the address range scrub rework were late
  arrivals, and the dax work was scaled back at the last moment.

  The of_pmem driver missed a previous merge window due to an oversight.
  A sense of obligation to rectify that miss is why it is included for
  4.17. It has acks from PowerPC folks. Stephen reported a build failure
  that only occurs when merging it with your latest tree, for now I have
  fixed that up by disabling modular builds of of_pmem. A test merge
  with your tree has received a build success report from the 0day robot
  over 156 configs.

  An initial version of the ARS rework was submitted before the merge
  window. It is self contained to libnvdimm, a net code reduction, and
  passing all unit tests.

  The filesystem-dax changes are based on the wait_var_event()
  functionality from tip/sched/core. However, late review feedback
  showed that those changes regressed truncate performance to a large
  degree. The branch was rewound to drop the truncate behavior change
  and now only includes preparation patches and cleanups (with full acks
  and reviews). The finalization of this dax-dma-vs-trnucate work will
  need to wait for 4.18.

  Summary:

   - A rework of the filesytem-dax implementation provides for detection
     of unmap operations (truncate / hole punch) colliding with
     in-progress device-DMA. A fix for these collisions remains a
     work-in-progress pending resolution of truncate latency and
     starvation regressions.

   - The of_pmem driver expands the users of libnvdimm outside of x86
     and ACPI to describe an implementation of persistent memory on
     PowerPC with Open Firmware / Device tree.

   - Address Range Scrub (ARS) handling is completely rewritten to
     account for the fact that ARS may run for 100s of seconds and there
     is no platform defined way to cancel it. ARS will now no longer
     block namespace initialization.

   - The NVDIMM Namespace Label implementation is updated to handle
     label areas as small as 1K, down from 128K.

   - Miscellaneous cleanups and updates to unit test infrastructure"

* tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (39 commits)
  libnvdimm, of_pmem: workaround OF_NUMA=n build error
  nfit, address-range-scrub: add module option to skip initial ars
  nfit, address-range-scrub: rework and simplify ARS state machine
  nfit, address-range-scrub: determine one platform max_ars value
  powerpc/powernv: Create platform devs for nvdimm buses
  doc/devicetree: Persistent memory region bindings
  libnvdimm: Add device-tree based driver
  libnvdimm: Add of_node to region and bus descriptors
  libnvdimm, region: quiet region probe
  libnvdimm, namespace: use a safe lookup for dimm device name
  libnvdimm, dimm: fix dpa reservation vs uninitialized label area
  libnvdimm, testing: update the default smart ctrl_temperature
  libnvdimm, testing: Add emulation for smart injection commands
  nfit, address-range-scrub: introduce nfit_spa->ars_state
  libnvdimm: add an api to cast a 'struct nd_region' to its 'struct device'
  nfit, address-range-scrub: fix scrub in-progress reporting
  dax, dm: allow device-mapper to operate without dax support
  dax: introduce CONFIG_DAX_DRIVER
  fs, dax: use page->mapping to warn if truncate collides with a busy page
  ext2, dax: introduce ext2_dax_aops
  ...

10 files changed, 217 insertions, 120 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7a506c55a993..7ec920e27065 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1948,11 +1948,6 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 static int blkdev_writepages(struct address_space *mapping,
 			     struct writeback_control *wbc)
 {
-	if (dax_mapping(mapping)) {
-		struct block_device *bdev = I_BDEV(mapping->host);
-
-		return dax_writeback_mapping_range(mapping, bdev, wbc);
-	}
 	return generic_writepages(mapping, wbc);
 }
 
diff --git a/fs/dax.c b/fs/dax.c
index 0276df90e86c..a77394fe586e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -73,16 +73,15 @@ fs_initcall(init_dax_wait_table);
 #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)
+static unsigned long dax_radix_pfn(void *entry)
 {
 	return (unsigned long)entry >> RADIX_DAX_SHIFT;
 }
 
-static void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
 {
 	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
-			((unsigned long)sector << RADIX_DAX_SHIFT) |
-			RADIX_DAX_ENTRY_LOCK);
+			(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
 }
 
 static unsigned int dax_radix_order(void *entry)
@@ -299,6 +298,63 @@ static void put_unlocked_mapping_entry(struct address_space *mapping,
 	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
 }
 
+static unsigned long dax_entry_size(void *entry)
+{
+	if (dax_is_zero_entry(entry))
+		return 0;
+	else if (dax_is_empty_entry(entry))
+		return 0;
+	else if (dax_is_pmd_entry(entry))
+		return PMD_SIZE;
+	else
+		return PAGE_SIZE;
+}
+
+static unsigned long dax_radix_end_pfn(void *entry)
+{
+	return dax_radix_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
+}
+
+/*
+ * Iterate through all mapped pfns represented by an entry, i.e. skip
+ * 'empty' and 'zero' entries.
+ */
+#define for_each_mapped_pfn(entry, pfn) \
+	for (pfn = dax_radix_pfn(entry); \
+			pfn < dax_radix_end_pfn(entry); pfn++)
+
+static void dax_associate_entry(void *entry, struct address_space *mapping)
+{
+	unsigned long pfn;
+
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+		return;
+
+	for_each_mapped_pfn(entry, pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		WARN_ON_ONCE(page->mapping);
+		page->mapping = mapping;
+	}
+}
+
+static void dax_disassociate_entry(void *entry, struct address_space *mapping,
+		bool trunc)
+{
+	unsigned long pfn;
+
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+		return;
+
+	for_each_mapped_pfn(entry, pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
+		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
+		page->mapping = NULL;
+	}
+}
+
 /*
  * 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
@@ -405,6 +461,7 @@ restart:
 		}
 
 		if (pmd_downgrade) {
+			dax_disassociate_entry(entry, mapping, false);
 			radix_tree_delete(&mapping->page_tree, index);
 			mapping->nrexceptional--;
 			dax_wake_mapping_entry_waiter(mapping, index, entry,
@@ -454,6 +511,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
 	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
 		goto out;
+	dax_disassociate_entry(entry, mapping, trunc);
 	radix_tree_delete(page_tree, index);
 	mapping->nrexceptional--;
 	ret = 1;
@@ -526,12 +584,13 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
  */
 static void *dax_insert_mapping_entry(struct address_space *mapping,
 				      struct vm_fault *vmf,
-				      void *entry, sector_t sector,
+				      void *entry, pfn_t pfn_t,
 				      unsigned long flags, bool dirty)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	void *new_entry;
+	unsigned long pfn = pfn_t_to_pfn(pfn_t);
 	pgoff_t index = vmf->pgoff;
+	void *new_entry;
 
 	if (dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -546,7 +605,11 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
-	new_entry = dax_radix_locked_entry(sector, flags);
+	new_entry = dax_radix_locked_entry(pfn, flags);
+	if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
+		dax_disassociate_entry(entry, mapping, false);
+		dax_associate_entry(new_entry, mapping);
+	}
 
 	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
 		/*
@@ -657,17 +720,14 @@ unlock_pte:
 	i_mmap_unlock_read(mapping);
 }
 
-static int dax_writeback_one(struct block_device *bdev,
-		struct dax_device *dax_dev, struct address_space *mapping,
-		pgoff_t index, void *entry)
+static int dax_writeback_one(struct dax_device *dax_dev,
+		struct address_space *mapping, pgoff_t index, void *entry)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	void *entry2, **slot, *kaddr;
-	long ret = 0, id;
-	sector_t sector;
-	pgoff_t pgoff;
+	void *entry2, **slot;
+	unsigned long pfn;
+	long ret = 0;
 	size_t size;
-	pfn_t pfn;
 
 	/*
 	 * A page got tagged dirty in DAX mapping? Something is seriously
@@ -683,10 +743,10 @@ static int dax_writeback_one(struct block_device *bdev,
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
-	 * compare sectors as we must not bail out due to difference in lockbit
+	 * compare pfns as we must not bail out due to difference in lockbit
 	 * or entry type.
 	 */
-	if (dax_radix_sector(entry2) != dax_radix_sector(entry))
+	if (dax_radix_pfn(entry2) != dax_radix_pfn(entry))
 		goto put_unlocked;
 	if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
 				dax_is_zero_entry(entry))) {
@@ -712,33 +772,15 @@ static int dax_writeback_one(struct block_device *bdev,
 	/*
 	 * 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.
+	 * the start index of the PMD, as will the pfn we pull from 'entry'.
+	 * This allows us to flush for PMD_SIZE and not have to worry about
+	 * partial PMD writebacks.
 	 */
-	sector = dax_radix_sector(entry);
+	pfn = dax_radix_pfn(entry);
 	size = PAGE_SIZE << dax_radix_order(entry);
 
-	id = dax_read_lock();
-	ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
-	if (ret)
-		goto dax_unlock;
-
-	/*
-	 * dax_direct_access() may sleep, so cannot hold tree_lock over
-	 * its invocation.
-	 */
-	ret = dax_direct_access(dax_dev, pgoff, size / PAGE_SIZE, &kaddr, &pfn);
-	if (ret < 0)
-		goto dax_unlock;
-
-	if (WARN_ON_ONCE(ret < size / PAGE_SIZE)) {
-		ret = -EIO;
-		goto dax_unlock;
-	}
-
-	dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(pfn));
-	dax_flush(dax_dev, kaddr, size);
+	dax_mapping_entry_mkclean(mapping, index, pfn);
+	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), size);
 	/*
 	 * After we have flushed the cache, we can clear the dirty tag. There
 	 * cannot be new dirty data in the pfn after the flush has completed as
@@ -749,8 +791,6 @@ static int dax_writeback_one(struct block_device *bdev,
 	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
 	spin_unlock_irq(&mapping->tree_lock);
 	trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
- dax_unlock:
-	dax_read_unlock(id);
 	put_locked_mapping_entry(mapping, index);
 	return ret;
 
@@ -808,8 +848,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 				break;
 			}
 
-			ret = dax_writeback_one(bdev, dax_dev, mapping,
-					indices[i], pvec.pages[i]);
+			ret = dax_writeback_one(dax_dev, mapping, indices[i],
+					pvec.pages[i]);
 			if (ret < 0) {
 				mapping_set_error(mapping, ret);
 				goto out;
@@ -877,6 +917,7 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 	int ret = VM_FAULT_NOPAGE;
 	struct page *zero_page;
 	void *entry2;
+	pfn_t pfn;
 
 	zero_page = ZERO_PAGE(0);
 	if (unlikely(!zero_page)) {
@@ -884,14 +925,15 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 		goto out;
 	}
 
-	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+	pfn = page_to_pfn_t(zero_page);
+	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 			RADIX_DAX_ZERO_PAGE, false);
 	if (IS_ERR(entry2)) {
 		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
-	vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page));
+	vm_insert_mixed(vmf->vma, vaddr, pfn);
 out:
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
@@ -1200,8 +1242,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		if (error < 0)
 			goto error_finish_iomap;
 
-		entry = dax_insert_mapping_entry(mapping, vmf, entry,
-						 dax_iomap_sector(&iomap, pos),
+		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						 0, write && !sync);
 		if (IS_ERR(entry)) {
 			error = PTR_ERR(entry);
@@ -1280,13 +1321,15 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	void *ret = NULL;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
+	pfn_t pfn;
 
 	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
 
 	if (unlikely(!zero_page))
 		goto fallback;
 
-	ret = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+	pfn = page_to_pfn_t(zero_page);
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
 	if (IS_ERR(ret))
 		goto fallback;
@@ -1409,8 +1452,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		if (error < 0)
 			goto finish_iomap;
 
-		entry = dax_insert_mapping_entry(mapping, vmf, entry,
-						dax_iomap_sector(&iomap, pos),
+		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						RADIX_DAX_PMD, write && !sync);
 		if (IS_ERR(entry))
 			goto finish_iomap;
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 032295e1d386..cc40802ddfa8 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -814,6 +814,7 @@ extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
 
 /* inode.c */
+extern void ext2_set_file_ops(struct inode *inode);
 extern const struct address_space_operations ext2_aops;
 extern const struct address_space_operations ext2_nobh_aops;
 extern const struct iomap_ops ext2_iomap_ops;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 9b2ac55ac34f..1e01fabef130 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -940,9 +940,6 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
-	if (WARN_ON_ONCE(IS_DAX(inode)))
-		return -EIO;
-
 	ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
 	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		ext2_write_failed(mapping, offset + count);
@@ -952,17 +949,16 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
-#ifdef CONFIG_FS_DAX
-	if (dax_mapping(mapping)) {
-		return dax_writeback_mapping_range(mapping,
-						   mapping->host->i_sb->s_bdev,
-						   wbc);
-	}
-#endif
-
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
+static int
+ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc)
+{
+	return dax_writeback_mapping_range(mapping,
+			mapping->host->i_sb->s_bdev, wbc);
+}
+
 const struct address_space_operations ext2_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
@@ -990,6 +986,13 @@ const struct address_space_operations ext2_nobh_aops = {
 	.error_remove_page	= generic_error_remove_page,
 };
 
+static const struct address_space_operations ext2_dax_aops = {
+	.writepages		= ext2_dax_writepages,
+	.direct_IO		= noop_direct_IO,
+	.set_page_dirty		= noop_set_page_dirty,
+	.invalidatepage		= noop_invalidatepage,
+};
+
 /*
  * Probably it should be a library function... search for first non-zero word
  * or memcmp with zero_page, whatever is better for particular architecture.
@@ -1388,6 +1391,18 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_DAX;
 }
 
+void ext2_set_file_ops(struct inode *inode)
+{
+	inode->i_op = &ext2_file_inode_operations;
+	inode->i_fop = &ext2_file_operations;
+	if (IS_DAX(inode))
+		inode->i_mapping->a_ops = &ext2_dax_aops;
+	else if (test_opt(inode->i_sb, NOBH))
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+	else
+		inode->i_mapping->a_ops = &ext2_aops;
+}
+
 struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 {
 	struct ext2_inode_info *ei;
@@ -1480,14 +1495,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 		ei->i_data[n] = raw_inode->i_block[n];
 
 	if (S_ISREG(inode->i_mode)) {
-		inode->i_op = &ext2_file_inode_operations;
-		if (test_opt(inode->i_sb, NOBH)) {
-			inode->i_mapping->a_ops = &ext2_nobh_aops;
-			inode->i_fop = &ext2_file_operations;
-		} else {
-			inode->i_mapping->a_ops = &ext2_aops;
-			inode->i_fop = &ext2_file_operations;
-		}
+		ext2_set_file_ops(inode);
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &ext2_dir_inode_operations;
 		inode->i_fop = &ext2_dir_operations;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index e078075dc66f..55f7caadb093 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -107,14 +107,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	inode->i_op = &ext2_file_inode_operations;
-	if (test_opt(inode->i_sb, NOBH)) {
-		inode->i_mapping->a_ops = &ext2_nobh_aops;
-		inode->i_fop = &ext2_file_operations;
-	} else {
-		inode->i_mapping->a_ops = &ext2_aops;
-		inode->i_fop = &ext2_file_operations;
-	}
+	ext2_set_file_ops(inode);
 	mark_inode_dirty(inode);
 	return ext2_add_nondir(dentry, inode);
 }
@@ -125,14 +118,7 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	inode->i_op = &ext2_file_inode_operations;
-	if (test_opt(inode->i_sb, NOBH)) {
-		inode->i_mapping->a_ops = &ext2_nobh_aops;
-		inode->i_fop = &ext2_file_operations;
-	} else {
-		inode->i_mapping->a_ops = &ext2_aops;
-		inode->i_fop = &ext2_file_operations;
-	}
+	ext2_set_file_ops(inode);
 	mark_inode_dirty(inode);
 	d_tmpfile(dentry, inode);
 	unlock_new_inode(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 129205028300..1e50c5efae67 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2716,12 +2716,6 @@ static int ext4_writepages(struct address_space *mapping,
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
-	if (dax_mapping(mapping)) {
-		ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
-						  wbc);
-		goto out_writepages;
-	}
-
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -2942,6 +2936,27 @@ out_writepages:
 	return ret;
 }
 
+static int ext4_dax_writepages(struct address_space *mapping,
+			       struct writeback_control *wbc)
+{
+	int ret;
+	long nr_to_write = wbc->nr_to_write;
+	struct inode *inode = mapping->host;
+	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
+	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	trace_ext4_writepages(inode, wbc);
+
+	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+	trace_ext4_writepages_result(inode, wbc, ret,
+				     nr_to_write - wbc->nr_to_write);
+	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	return ret;
+}
+
 static int ext4_nonda_switch(struct super_block *sb)
 {
 	s64 free_clusters, dirty_clusters;
@@ -3845,10 +3860,6 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (ext4_has_inline_data(inode))
 		return 0;
 
-	/* DAX uses iomap path now */
-	if (WARN_ON_ONCE(IS_DAX(inode)))
-		return 0;
-
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 	if (iov_iter_rw(iter) == READ)
 		ret = ext4_direct_IO_read(iocb, iter);
@@ -3934,6 +3945,13 @@ static const struct address_space_operations ext4_da_aops = {
 	.error_remove_page	= generic_error_remove_page,
 };
 
+static const struct address_space_operations ext4_dax_aops = {
+	.writepages		= ext4_dax_writepages,
+	.direct_IO		= noop_direct_IO,
+	.set_page_dirty		= noop_set_page_dirty,
+	.invalidatepage		= noop_invalidatepage,
+};
+
 void ext4_set_aops(struct inode *inode)
 {
 	switch (ext4_inode_journal_mode(inode)) {
@@ -3946,7 +3964,9 @@ void ext4_set_aops(struct inode *inode)
 	default:
 		BUG();
 	}
-	if (test_opt(inode->i_sb, DELALLOC))
+	if (IS_DAX(inode))
+		inode->i_mapping->a_ops = &ext4_dax_aops;
+	else if (test_opt(inode->i_sb, DELALLOC))
 		inode->i_mapping->a_ops = &ext4_da_aops;
 	else
 		inode->i_mapping->a_ops = &ext4_aops;
diff --git a/fs/libfs.c b/fs/libfs.c
index 7ff3cb904acd..0fb590d79f30 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1060,6 +1060,45 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL(noop_fsync);
 
+int noop_set_page_dirty(struct page *page)
+{
+	/*
+	 * Unlike __set_page_dirty_no_writeback that handles dirty page
+	 * tracking in the page object, dax does all dirty tracking in
+	 * the inode address_space in response to mkwrite faults. In the
+	 * dax case we only need to worry about potentially dirty CPU
+	 * caches, not dirty page cache pages to write back.
+	 *
+	 * This callback is defined to prevent fallback to
+	 * __set_page_dirty_buffers() in set_page_dirty().
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(noop_set_page_dirty);
+
+void noop_invalidatepage(struct page *page, unsigned int offset,
+		unsigned int length)
+{
+	/*
+	 * There is no page cache to invalidate in the dax case, however
+	 * we need this callback defined to prevent falling back to
+	 * block_invalidatepage() in do_invalidatepage().
+	 */
+}
+EXPORT_SYMBOL_GPL(noop_invalidatepage);
+
+ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+	/*
+	 * iomap based filesystems support direct I/O without need for
+	 * this callback. However, it still needs to be set in
+	 * inode->a_ops so that open/fcntl know that direct I/O is
+	 * generally supported.
+	 */
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(noop_direct_IO);
+
 /* Because kfree isn't assignment-compatible with void(void*) ;-/ */
 void kfree_link(void *p)
 {
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 31f1f10eecd1..436a1de3fcdf 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1195,16 +1195,22 @@ xfs_vm_writepages(
 	int			ret;
 
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	if (dax_mapping(mapping))
-		return dax_writeback_mapping_range(mapping,
-				xfs_find_bdev_for_inode(mapping->host), wbc);
-
 	ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc);
 	if (wpc.ioend)
 		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
 	return ret;
 }
 
+STATIC int
+xfs_dax_writepages(
+	struct address_space	*mapping,
+	struct writeback_control *wbc)
+{
+	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	return dax_writeback_mapping_range(mapping,
+			xfs_find_bdev_for_inode(mapping->host), wbc);
+}
+
 /*
  * Called to move a page into cleanable state - and from there
  * to be released. The page should already be clean. We always
@@ -1367,17 +1373,6 @@ out_unlock:
 	return error;
 }
 
-STATIC ssize_t
-xfs_vm_direct_IO(
-	struct kiocb		*iocb,
-	struct iov_iter		*iter)
-{
-	/*
-	 * We just need the method present so that open/fcntl allow direct I/O.
-	 */
-	return -EINVAL;
-}
-
 STATIC sector_t
 xfs_vm_bmap(
 	struct address_space	*mapping,
@@ -1500,8 +1495,15 @@ const struct address_space_operations xfs_address_space_operations = {
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.bmap			= xfs_vm_bmap,
-	.direct_IO		= xfs_vm_direct_IO,
+	.direct_IO		= noop_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 };
+
+const struct address_space_operations xfs_dax_aops = {
+	.writepages		= xfs_dax_writepages,
+	.direct_IO		= noop_direct_IO,
+	.set_page_dirty		= noop_set_page_dirty,
+	.invalidatepage		= noop_invalidatepage,
+};
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 88c85ea63da0..69346d460dfa 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -54,6 +54,7 @@ struct xfs_ioend {
 };
 
 extern const struct address_space_operations xfs_address_space_operations;
+extern const struct address_space_operations xfs_dax_aops;
 
 int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index e0307fbff911..154725b1b813 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1285,7 +1285,10 @@ xfs_setup_iops(
 	case S_IFREG:
 		inode->i_op = &xfs_inode_operations;
 		inode->i_fop = &xfs_file_operations;
-		inode->i_mapping->a_ops = &xfs_address_space_operations;
+		if (IS_DAX(inode))
+			inode->i_mapping->a_ops = &xfs_dax_aops;
+		else
+			inode->i_mapping->a_ops = &xfs_address_space_operations;
 		break;
 	case S_IFDIR:
 		if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))