ext4: handle layout changes to pinned DAX mappings

Follow the lead of xfs_break_dax_layouts() and add synchronization between
operations in ext4 which remove blocks from an inode (hole punch, truncate
down, etc.) and pages which are pinned due to DAX DMA operations.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>

fs/ext4/ext4.h

@@ -2459,6 +2459,7 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
+extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);

fs/ext4/extents.c

@@ -4826,6 +4826,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * released from page cache.
 		 */
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		ret = ext4_break_layouts(inode);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_mutex;
+		}
+
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
@@ -5499,6 +5506,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down offset to be aligned with page size boundary
 	 * for page size > block size.
@@ -5647,6 +5659,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down to align start offset to page size boundary
 	 * for page size > block size.

fs/ext4/inode.c

@@ -4191,6 +4191,39 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return 0;
 }
 
+static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+{
+	*did_unlock = true;
+	up_write(&ei->i_mmap_sem);
+	schedule();
+	down_write(&ei->i_mmap_sem);
+}
+
+int ext4_break_layouts(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct page *page;
+	bool retry;
+	int error;
+
+	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+		return -EINVAL;
+
+	do {
+		retry = false;
+		page = dax_layout_busy_page(inode->i_mapping);
+		if (!page)
+			return 0;
+
+		error = ___wait_var_event(&page->_refcount,
+				atomic_read(&page->_refcount) == 1,
+				TASK_INTERRUPTIBLE, 0, 0,
+				ext4_wait_dax_page(ei, &retry));
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 /*
  * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
@@ -4264,6 +4297,11 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_dio;
+
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -5553,6 +5591,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_wait_for_tail_page_commit(inode);
 		}
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			error = rc;
+			goto err_out;
+		}
+
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.

fs/ext4/truncate.h

@@ -11,6 +11,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	/*
+	 * We don't need to call ext4_break_layouts() because the blocks we
+	 * are truncating were never visible to userspace.
+	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);