dax: New fault locking

Currently DAX page fault locking is racy.

CPU0 (write fault)		CPU1 (read fault)

__dax_fault()			__dax_fault()
  get_block(inode, block, &bh, 0) -> not mapped
				  get_block(inode, block, &bh, 0)
				    -> not mapped
  if (!buffer_mapped(&bh))
    if (vmf->flags & FAULT_FLAG_WRITE)
      get_block(inode, block, &bh, 1) -> allocates blocks
  if (page) -> no
				  if (!buffer_mapped(&bh))
				    if (vmf->flags & FAULT_FLAG_WRITE) {
				    } else {
				      dax_load_hole();
				    }
  dax_insert_mapping()

And we are in a situation where we fail in dax_radix_entry() with -EIO.

Another problem with the current DAX page fault locking is that there is
no race-free way to clear dirty tag in the radix tree. We can always
end up with clean radix tree and dirty data in CPU cache.

We fix the first problem by introducing locking of exceptional radix
tree entries in DAX mappings acting very similarly to page lock and thus
synchronizing properly faults against the same mapping index. The same
lock can later be used to avoid races when clearing radix tree dirty
tag.
Reviewed-by: NeilBrown <neilb@suse.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>

fs/dax.c

@@ -46,6 +46,30 @@
 		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 int __init init_dax_wait_table(void)
+{
+	int i;
+
+	for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
+		init_waitqueue_head(wait_table + i);
+	return 0;
+}
+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;
@@ -267,6 +291,263 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(dax_do_io);
 
+/*
+ * DAX radix tree locking
+ */
+struct exceptional_entry_key {
+	struct address_space *mapping;
+	unsigned long index;
+};
+
+struct wait_exceptional_entry_queue {
+	wait_queue_t wait;
+	struct exceptional_entry_key key;
+};
+
+static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
+				       int sync, void *keyp)
+{
+	struct exceptional_entry_key *key = keyp;
+	struct wait_exceptional_entry_queue *ewait =
+		container_of(wait, struct wait_exceptional_entry_queue, wait);
+
+	if (key->mapping != ewait->key.mapping ||
+	    key->index != ewait->key.index)
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, NULL);
+}
+
+/*
+ * Check whether the given slot is locked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline int slot_locked(struct address_space *mapping, void **slot)
+{
+	unsigned long entry = (unsigned long)
+		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+	return entry & RADIX_DAX_ENTRY_LOCK;
+}
+
+/*
+ * Mark the given slot is locked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline void *lock_slot(struct address_space *mapping, void **slot)
+{
+	unsigned long entry = (unsigned long)
+		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+
+	entry |= RADIX_DAX_ENTRY_LOCK;
+	radix_tree_replace_slot(slot, (void *)entry);
+	return (void *)entry;
+}
+
+/*
+ * Mark the given slot is unlocked. The function must be called with
+ * mapping->tree_lock held
+ */
+static inline void *unlock_slot(struct address_space *mapping, void **slot)
+{
+	unsigned long entry = (unsigned long)
+		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+
+	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
+	radix_tree_replace_slot(slot, (void *)entry);
+	return (void *)entry;
+}
+
+/*
+ * Lookup entry in radix tree, wait for it to become unlocked if it is
+ * exceptional entry and return it. The caller must call
+ * put_unlocked_mapping_entry() when he decided not to lock the entry or
+ * put_locked_mapping_entry() when he locked the entry and now wants to
+ * unlock it.
+ *
+ * The function must be called with mapping->tree_lock held.
+ */
+static void *get_unlocked_mapping_entry(struct address_space *mapping,
+					pgoff_t index, void ***slotp)
+{
+	void *ret, **slot;
+	struct wait_exceptional_entry_queue ewait;
+	wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+
+	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,
+					  &slot);
+		if (!ret || !radix_tree_exceptional_entry(ret) ||
+		    !slot_locked(mapping, slot)) {
+			if (slotp)
+				*slotp = slot;
+			return ret;
+		}
+		prepare_to_wait_exclusive(wq, &ewait.wait,
+					  TASK_UNINTERRUPTIBLE);
+		spin_unlock_irq(&mapping->tree_lock);
+		schedule();
+		finish_wait(wq, &ewait.wait);
+		spin_lock_irq(&mapping->tree_lock);
+	}
+}
+
+/*
+ * 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.
+ *
+ * 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)
+{
+	void *ret, **slot;
+
+restart:
+	spin_lock_irq(&mapping->tree_lock);
+	ret = get_unlocked_mapping_entry(mapping, index, &slot);
+	/* No entry for given index? Make sure radix tree is big enough. */
+	if (!ret) {
+		int err;
+
+		spin_unlock_irq(&mapping->tree_lock);
+		err = radix_tree_preload(
+				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
+		if (err)
+			return ERR_PTR(err);
+		ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+			       RADIX_DAX_ENTRY_LOCK);
+		spin_lock_irq(&mapping->tree_lock);
+		err = radix_tree_insert(&mapping->page_tree, index, ret);
+		radix_tree_preload_end();
+		if (err) {
+			spin_unlock_irq(&mapping->tree_lock);
+			/* Someone already created the entry? */
+			if (err == -EEXIST)
+				goto restart;
+			return ERR_PTR(err);
+		}
+		/* Good, we have inserted empty locked entry into the tree. */
+		mapping->nrexceptional++;
+		spin_unlock_irq(&mapping->tree_lock);
+		return ret;
+	}
+	/* Normal page in radix tree? */
+	if (!radix_tree_exceptional_entry(ret)) {
+		struct page *page = ret;
+
+		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;
+	}
+	ret = lock_slot(mapping, slot);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
+
+void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+				   pgoff_t index, bool wake_all)
+{
+	wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
+
+	/*
+	 * 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)) {
+		struct exceptional_entry_key key;
+
+		key.mapping = mapping;
+		key.index = index;
+		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+	}
+}
+
+static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	void *ret, **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) ||
+			 !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 {
+		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);
+}
+
+/*
+ * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
+ * entry to get unlocked before deleting it.
+ */
+int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	void *entry;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	/*
+	 * This gets called from truncate / punch_hole path. As such, the caller
+	 * must hold locks protecting against concurrent modifications of the
+	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
+	 * caller has seen exceptional entry for this index, we better find it
+	 * at that index as well...
+	 */
+	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return 0;
+	}
+	radix_tree_delete(&mapping->page_tree, index);
+	mapping->nrexceptional--;
+	spin_unlock_irq(&mapping->tree_lock);
+	dax_wake_mapping_entry_waiter(mapping, index, true);
+
+	return 1;
+}
+
 /*
  * 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
@@ -275,15 +556,24 @@ EXPORT_SYMBOL_GPL(dax_do_io);
  * 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, struct page *page,
-							struct vm_fault *vmf)
+static int dax_load_hole(struct address_space *mapping, void *entry,
+			 struct vm_fault *vmf)
 {
-	if (!page)
-		page = find_or_create_page(mapping, vmf->pgoff,
-						GFP_KERNEL | __GFP_ZERO);
-	if (!page)
-		return VM_FAULT_OOM;
+	struct page *page;
+
+	/* Hole page already exists? Return it...  */
+	if (!radix_tree_exceptional_entry(entry)) {
+		vmf->page = entry;
+		return VM_FAULT_LOCKED;
+	}
 
+	/* 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) {
+		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+		return VM_FAULT_OOM;
+	}
 	vmf->page = page;
 	return VM_FAULT_LOCKED;
 }
@@ -307,77 +597,72 @@ static int copy_user_bh(struct page *to, struct inode *inode,
 	return 0;
 }
 
-#define NO_SECTOR -1
 #define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
 
-static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
-		sector_t sector, bool pmd_entry, bool dirty)
+static void *dax_insert_mapping_entry(struct address_space *mapping,
+				      struct vm_fault *vmf,
+				      void *entry, sector_t sector)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	pgoff_t pmd_index = DAX_PMD_INDEX(index);
-	int type, error = 0;
-	void *entry;
+	int error = 0;
+	bool hole_fill = false;
+	void *new_entry;
+	pgoff_t index = vmf->pgoff;
 
-	WARN_ON_ONCE(pmd_entry && !dirty);
-	if (dirty)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	spin_lock_irq(&mapping->tree_lock);
-
-	entry = radix_tree_lookup(page_tree, pmd_index);
-	if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
-		index = pmd_index;
-		goto dirty;
+	/* 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);
 	}
 
-	entry = radix_tree_lookup(page_tree, index);
-	if (entry) {
-		type = RADIX_DAX_TYPE(entry);
-		if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
-					type != RADIX_DAX_PMD)) {
-			error = -EIO;
+	spin_lock_irq(&mapping->tree_lock);
+	new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) |
+		       RADIX_DAX_ENTRY_LOCK);
+	if (hole_fill) {
+		__delete_from_page_cache(entry, NULL);
+		/* Drop pagecache reference */
+		put_page(entry);
+		error = radix_tree_insert(page_tree, index, new_entry);
+		if (error) {
+			new_entry = ERR_PTR(error);
 			goto unlock;
 		}
+		mapping->nrexceptional++;
+	} else {
+		void **slot;
+		void *ret;
 
-		if (!pmd_entry || type == RADIX_DAX_PMD)
-			goto dirty;
-
-		/*
-		 * We only insert dirty PMD entries into the radix tree.  This
-		 * means we don't need to worry about removing a dirty PTE
-		 * entry and inserting a clean PMD entry, thus reducing the
-		 * range we would flush with a follow-up fsync/msync call.
-		 */
-		radix_tree_delete(&mapping->page_tree, index);
-		mapping->nrexceptional--;
-	}
-
-	if (sector == NO_SECTOR) {
-		/*
-		 * This can happen during correct operation if our pfn_mkwrite
-		 * fault raced against a hole punch operation.  If this
-		 * happens the pte that was hole punched will have been
-		 * unmapped and the radix tree entry will have been removed by
-		 * the time we are called, but the call will still happen.  We
-		 * will return all the way up to wp_pfn_shared(), where the
-		 * pte_same() check will fail, eventually causing page fault
-		 * to be retried by the CPU.
-		 */
-		goto unlock;
+		ret = __radix_tree_lookup(page_tree, index, NULL, &slot);
+		WARN_ON_ONCE(ret != entry);
+		radix_tree_replace_slot(slot, new_entry);
 	}
-
-	error = radix_tree_insert(page_tree, index,
-			RADIX_DAX_ENTRY(sector, pmd_entry));
-	if (error)
-		goto unlock;
-
-	mapping->nrexceptional++;
- dirty:
-	if (dirty)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
  unlock:
 	spin_unlock_irq(&mapping->tree_lock);
-	return error;
+	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;
 }
 
 static int dax_writeback_one(struct block_device *bdev,
@@ -503,17 +788,19 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
-static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
+static int dax_insert_mapping(struct address_space *mapping,
+			struct buffer_head *bh, void **entryp,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
-	struct address_space *mapping = inode->i_mapping;
 	struct block_device *bdev = bh->b_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = to_sector(bh, inode),
+		.sector = to_sector(bh, mapping->host),
 		.size = bh->b_size,
 	};
 	int error;
+	void *ret;
+	void *entry = *entryp;
 
 	i_mmap_lock_read(mapping);
 
@@ -523,16 +810,16 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	}
 	dax_unmap_atomic(bdev, &dax);
 
-	error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
-			vmf->flags & FAULT_FLAG_WRITE);
-	if (error)
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector);
+	if (IS_ERR(ret)) {
+		error = PTR_ERR(ret);
 		goto out;
+	}
+	*entryp = ret;
 
 	error = vm_insert_mixed(vma, vaddr, dax.pfn);
-
  out:
 	i_mmap_unlock_read(mapping);
-
 	return error;
 }
 
@@ -552,7 +839,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	struct page *page;
+	void *entry;
 	struct buffer_head bh;
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
 	unsigned blkbits = inode->i_blkbits;
@@ -561,6 +848,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	int error;
 	int major = 0;
 
+	/*
+	 * 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.
+	 */
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		return VM_FAULT_SIGBUS;
@@ -570,40 +862,17 @@ 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;
 
- repeat:
-	page = find_get_page(mapping, vmf->pgoff);
-	if (page) {
-		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
-			put_page(page);
-			return VM_FAULT_RETRY;
-		}
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
-			goto repeat;
-		}
+	entry = grab_mapping_entry(mapping, vmf->pgoff);
+	if (IS_ERR(entry)) {
+		error = PTR_ERR(entry);
+		goto out;
 	}
 
 	error = get_block(inode, block, &bh, 0);
 	if (!error && (bh.b_size < PAGE_SIZE))
 		error = -EIO;		/* fs corruption? */
 	if (error)
-		goto unlock_page;
-
-	if (!buffer_mapped(&bh) && !vmf->cow_page) {
-		if (vmf->flags & FAULT_FLAG_WRITE) {
-			error = get_block(inode, block, &bh, 1);
-			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
-			major = VM_FAULT_MAJOR;
-			if (!error && (bh.b_size < PAGE_SIZE))
-				error = -EIO;
-			if (error)
-				goto unlock_page;
-		} else {
-			return dax_load_hole(mapping, page, vmf);
-		}
-	}
+		goto unlock_entry;
 
 	if (vmf->cow_page) {
 		struct page *new_page = vmf->cow_page;
@@ -612,30 +881,37 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		else
 			clear_user_highpage(new_page, vaddr);
 		if (error)
-			goto unlock_page;
-		vmf->page = page;
-		if (!page)
+			goto unlock_entry;
+		if (!radix_tree_exceptional_entry(entry)) {
+			vmf->page = entry;
+		} else {
+			unlock_mapping_entry(mapping, vmf->pgoff);
 			i_mmap_lock_read(mapping);
+			vmf->page = NULL;
+		}
 		return VM_FAULT_LOCKED;
 	}
 
-	/* Check we didn't race with a read fault installing a new page */
-	if (!page && major)
-		page = find_lock_page(mapping, vmf->pgoff);
-
-	if (page) {
-		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
-							PAGE_SIZE, 0);
-		delete_from_page_cache(page);
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
+	if (!buffer_mapped(&bh)) {
+		if (vmf->flags & FAULT_FLAG_WRITE) {
+			error = get_block(inode, block, &bh, 1);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			major = VM_FAULT_MAJOR;
+			if (!error && (bh.b_size < PAGE_SIZE))
+				error = -EIO;
+			if (error)
+				goto unlock_entry;
+		} else {
+			return dax_load_hole(mapping, entry, vmf);
+		}
 	}
 
 	/* Filesystem should not return unwritten buffers to us! */
 	WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
-	error = dax_insert_mapping(inode, &bh, vma, vmf);
-
+	error = dax_insert_mapping(mapping, &bh, &entry, vma, vmf);
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  out:
 	if (error == -ENOMEM)
 		return VM_FAULT_OOM | major;
@@ -643,13 +919,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if ((error < 0) && (error != -EBUSY))
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
-
- unlock_page:
-	if (page) {
-		unlock_page(page);
-		put_page(page);
-	}
-	goto out;
 }
 EXPORT_SYMBOL(__dax_fault);
 
@@ -718,7 +987,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	struct block_device *bdev;
 	pgoff_t size, pgoff;
 	sector_t block;
-	int error, result = 0;
+	int result = 0;
 	bool alloc = false;
 
 	/* dax pmd mappings require pfn_t_devmap() */
@@ -865,13 +1134,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		 * the write to insert a dirty entry.
 		 */
 		if (write) {
-			error = dax_radix_entry(mapping, pgoff, dax.sector,
-					true, true);
-			if (error) {
-				dax_pmd_dbg(&bh, address,
-						"PMD radix insertion failed");
-				goto fallback;
-			}
+			/*
+			 * We should insert radix-tree entry and dirty it here.
+			 * For now this is broken...
+			 */
 		}
 
 		dev_dbg(part_to_dev(bdev->bd_part),
@@ -931,23 +1197,18 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
 int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct file *file = vma->vm_file;
-	int error;
-
-	/*
-	 * We pass NO_SECTOR to dax_radix_entry() because we expect that a
-	 * RADIX_DAX_PTE entry already exists in the radix tree from a
-	 * previous call to __dax_fault().  We just want to look up that PTE
-	 * entry using vmf->pgoff and make sure the dirty tag is set.  This
-	 * saves us from having to make a call to get_block() here to look
-	 * up the sector.
-	 */
-	error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false,
-			true);
+	struct address_space *mapping = file->f_mapping;
+	void *entry;
+	pgoff_t index = vmf->pgoff;
 
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM;
-	if (error)
-		return VM_FAULT_SIGBUS;
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
+	put_unlocked_mapping_entry(mapping, index, entry);
+out:
+	spin_unlock_irq(&mapping->tree_lock);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);

include/linux/dax.h

@@ -15,6 +15,9 @@ 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 dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 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);
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);

mm/filemap.c

@@ -160,13 +160,15 @@ static void page_cache_tree_delete(struct address_space *mapping,
 			return;
 
 	/*
-	 * Track node that only contains shadow entries.
+	 * Track node that only contains shadow entries. DAX mappings contain
+	 * no shadow entries and may contain other exceptional entries so skip
+	 * those.
 	 *
 	 * Avoid acquiring the list_lru lock if already tracked.  The
 	 * list_empty() test is safe as node->private_list is
 	 * protected by mapping->tree_lock.
 	 */
-	if (!workingset_node_pages(node) &&
+	if (!dax_mapping(mapping) && !workingset_node_pages(node) &&
 	    list_empty(&node->private_list)) {
 		node->private_data = mapping;
 		list_lru_add(&workingset_shadow_nodes, &node->private_list);
@@ -611,6 +613,9 @@ static int page_cache_tree_insert(struct address_space *mapping,
 			/* 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,
+						      false);
 		}
 	}
 	radix_tree_replace_slot(slot, page);

mm/truncate.c

@@ -34,40 +34,38 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	if (shmem_mapping(mapping))
 		return;
 
-	spin_lock_irq(&mapping->tree_lock);
-
 	if (dax_mapping(mapping)) {
-		if (radix_tree_delete_item(&mapping->page_tree, index, entry))
-			mapping->nrexceptional--;
-	} else {
-		/*
-		 * Regular page slots are stabilized by the page lock even
-		 * without the tree itself locked.  These unlocked entries
-		 * need verification under the tree lock.
-		 */
-		if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
-					&slot))
-			goto unlock;
-		if (*slot != entry)
-			goto unlock;
-		radix_tree_replace_slot(slot, NULL);
-		mapping->nrexceptional--;
-		if (!node)
-			goto unlock;
-		workingset_node_shadows_dec(node);
-		/*
-		 * Don't track node without shadow entries.
-		 *
-		 * Avoid acquiring the list_lru lock if already untracked.
-		 * The list_empty() test is safe as node->private_list is
-		 * protected by mapping->tree_lock.
-		 */
-		if (!workingset_node_shadows(node) &&
-		    !list_empty(&node->private_list))
-			list_lru_del(&workingset_shadow_nodes,
-					&node->private_list);
-		__radix_tree_delete_node(&mapping->page_tree, node);
+		dax_delete_mapping_entry(mapping, index);
+		return;
 	}
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
+				&slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrexceptional--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes,
+				&node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
 unlock:
 	spin_unlock_irq(&mapping->tree_lock);
 }