1 files changed, 367 insertions, 419 deletions

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 4b091c21908f..0550fd30fd10 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -13,28 +13,14 @@
 #include "ext4.h"
 #include "ext4_extents.h"
 
-/**
- * get_ext_path() - Find an extent path for designated logical block number.
- * @inode:	inode to be searched
- * @lblock:	logical block number to find an extent path
- * @path:	pointer to an extent path
- *
- * ext4_find_extent wrapper. Return an extent path pointer on success,
- * or an error pointer on failure.
- */
-static inline struct ext4_ext_path *
-get_ext_path(struct inode *inode, ext4_lblk_t lblock,
-	     struct ext4_ext_path *path)
-{
-	path = ext4_find_extent(inode, lblock, path, EXT4_EX_NOCACHE);
-	if (IS_ERR(path))
-		return path;
-	if (path[ext_depth(inode)].p_ext == NULL) {
-		ext4_free_ext_path(path);
-		return ERR_PTR(-ENODATA);
-	}
-	return path;
-}
+#include <trace/events/ext4.h>
+
+struct mext_data {
+	struct inode *orig_inode;	/* Origin file inode */
+	struct inode *donor_inode;	/* Donor file inode */
+	struct ext4_map_blocks orig_map;/* Origin file's move mapping */
+	ext4_lblk_t donor_lblk;		/* Start block of the donor file */
+};
 
 /**
  * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem
@@ -52,7 +38,6 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
 	} else {
 		down_write(&EXT4_I(second)->i_data_sem);
 		down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
-
 	}
 }
 
@@ -71,59 +56,14 @@ ext4_double_up_write_data_sem(struct inode *orig_inode,
 	up_write(&EXT4_I(donor_inode)->i_data_sem);
 }
 
-/**
- * mext_check_coverage - Check that all extents in range has the same type
- *
- * @inode:		inode in question
- * @from:		block offset of inode
- * @count:		block count to be checked
- * @unwritten:		extents expected to be unwritten
- * @err:		pointer to save error value
- *
- * Return 1 if all extents in range has expected type, and zero otherwise.
- */
-static int
-mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
-		    int unwritten, int *err)
-{
-	struct ext4_ext_path *path = NULL;
-	struct ext4_extent *ext;
-	int ret = 0;
-	ext4_lblk_t last = from + count;
-	while (from < last) {
-		path = get_ext_path(inode, from, path);
-		if (IS_ERR(path)) {
-			*err = PTR_ERR(path);
-			return ret;
-		}
-		ext = path[ext_depth(inode)].p_ext;
-		if (unwritten != ext4_ext_is_unwritten(ext))
-			goto out;
-		from += ext4_ext_get_actual_len(ext);
-	}
-	ret = 1;
-out:
-	ext4_free_ext_path(path);
-	return ret;
-}
-
-/**
- * mext_folio_double_lock - Grab and lock folio on both @inode1 and @inode2
- *
- * @inode1:	the inode structure
- * @inode2:	the inode structure
- * @index1:	folio index
- * @index2:	folio index
- * @folio:	result folio vector
- *
- * Grab two locked folio for inode's by inode order
- */
-static int
-mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
-		      pgoff_t index1, pgoff_t index2, struct folio *folio[2])
+/* Grab and lock folio on both @inode1 and @inode2 by inode order. */
+static int mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
+				  pgoff_t index1, pgoff_t index2, size_t len,
+				  struct folio *folio[2])
 {
 	struct address_space *mapping[2];
 	unsigned int flags;
+	fgf_t fgp_flags = FGP_WRITEBEGIN;
 
 	BUG_ON(!inode1 || !inode2);
 	if (inode1 < inode2) {
@@ -136,14 +76,15 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 	}
 
 	flags = memalloc_nofs_save();
-	folio[0] = __filemap_get_folio(mapping[0], index1, FGP_WRITEBEGIN,
+	fgp_flags |= fgf_set_order(len);
+	folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags,
 			mapping_gfp_mask(mapping[0]));
 	if (IS_ERR(folio[0])) {
 		memalloc_nofs_restore(flags);
 		return PTR_ERR(folio[0]);
 	}
 
-	folio[1] = __filemap_get_folio(mapping[1], index2, FGP_WRITEBEGIN,
+	folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags,
 			mapping_gfp_mask(mapping[1]));
 	memalloc_nofs_restore(flags);
 	if (IS_ERR(folio[1])) {
@@ -164,8 +105,16 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 	return 0;
 }
 
+static void mext_folio_double_unlock(struct folio *folio[2])
+{
+	folio_unlock(folio[0]);
+	folio_put(folio[0]);
+	folio_unlock(folio[1]);
+	folio_put(folio[1]);
+}
+
 /* Force folio buffers uptodate w/o dropping folio's lock */
-static int mext_page_mkuptodate(struct folio *folio, size_t from, size_t to)
+static int mext_folio_mkuptodate(struct folio *folio, size_t from, size_t to)
 {
 	struct inode *inode = folio->mapping->host;
 	sector_t block;
@@ -238,267 +187,313 @@ out:
 	return 0;
 }
 
-/**
- * move_extent_per_page - Move extent data per page
- *
- * @o_filp:			file structure of original file
- * @donor_inode:		donor inode
- * @orig_page_offset:		page index on original file
- * @donor_page_offset:		page index on donor file
- * @data_offset_in_page:	block index where data swapping starts
- * @block_len_in_page:		the number of blocks to be swapped
- * @unwritten:			orig extent is unwritten or not
- * @err:			pointer to save return value
- *
- * Save the data in original inode blocks and replace original inode extents
- * with donor inode extents by calling ext4_swap_extents().
- * Finally, write out the saved data in new original inode blocks. Return
- * replaced block count.
+enum mext_move_type {MEXT_SKIP_EXTENT, MEXT_MOVE_EXTENT, MEXT_COPY_DATA};
+
+/*
+ * Start to move extent between the origin inode and the donor inode,
+ * hold one folio for each inode and check the candidate moving extent
+ * mapping status again.
  */
-static int
-move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
-		     pgoff_t orig_page_offset, pgoff_t donor_page_offset,
-		     int data_offset_in_page,
-		     int block_len_in_page, int unwritten, int *err)
+static int mext_move_begin(struct mext_data *mext, struct folio *folio[2],
+			   enum mext_move_type *move_type)
 {
-	struct inode *orig_inode = file_inode(o_filp);
-	struct folio *folio[2] = {NULL, NULL};
-	handle_t *handle;
-	ext4_lblk_t orig_blk_offset, donor_blk_offset;
-	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
-	unsigned int tmp_data_size, data_size, replaced_size;
-	int i, err2, jblocks, retries = 0;
-	int replaced_count = 0;
-	int from;
-	int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
-	struct super_block *sb = orig_inode->i_sb;
-	struct buffer_head *bh = NULL;
+	struct inode *orig_inode = mext->orig_inode;
+	struct inode *donor_inode = mext->donor_inode;
+	unsigned int blkbits = orig_inode->i_blkbits;
+	struct ext4_map_blocks donor_map = {0};
+	loff_t orig_pos, donor_pos;
+	size_t move_len;
+	int ret;
+
+	orig_pos = ((loff_t)mext->orig_map.m_lblk) << blkbits;
+	donor_pos = ((loff_t)mext->donor_lblk) << blkbits;
+	ret = mext_folio_double_lock(orig_inode, donor_inode,
+			orig_pos >> PAGE_SHIFT, donor_pos >> PAGE_SHIFT,
+			((size_t)mext->orig_map.m_len) << blkbits, folio);
+	if (ret)
+		return ret;
 
 	/*
-	 * It needs twice the amount of ordinary journal buffers because
-	 * inode and donor_inode may change each different metadata blocks.
+	 * Check the origin inode's mapping information again under the
+	 * folio lock, as we do not hold the i_data_sem at all times, and
+	 * it may change during the concurrent write-back operation.
 	 */
-again:
-	*err = 0;
-	jblocks = ext4_meta_trans_blocks(orig_inode, block_len_in_page,
-					 block_len_in_page) * 2;
-	handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks);
+	if (mext->orig_map.m_seq != READ_ONCE(EXT4_I(orig_inode)->i_es_seq)) {
+		ret = -ESTALE;
+		goto error;
+	}
+
+	/* Adjust the moving length according to the length of shorter folio. */
+	move_len = umin(folio_pos(folio[0]) + folio_size(folio[0]) - orig_pos,
+			folio_pos(folio[1]) + folio_size(folio[1]) - donor_pos);
+	move_len >>= blkbits;
+	if (move_len < mext->orig_map.m_len)
+		mext->orig_map.m_len = move_len;
+
+	donor_map.m_lblk = mext->donor_lblk;
+	donor_map.m_len = mext->orig_map.m_len;
+	donor_map.m_flags = 0;
+	ret = ext4_map_blocks(NULL, donor_inode, &donor_map, 0);
+	if (ret < 0)
+		goto error;
+
+	/* Adjust the moving length according to the donor mapping length. */
+	mext->orig_map.m_len = donor_map.m_len;
+
+	/* Skip moving if the donor range is a hole or a delalloc extent. */
+	if (!(donor_map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN)))
+		*move_type = MEXT_SKIP_EXTENT;
+	/* If both mapping ranges are unwritten, no need to copy data. */
+	else if ((mext->orig_map.m_flags & EXT4_MAP_UNWRITTEN) &&
+		 (donor_map.m_flags & EXT4_MAP_UNWRITTEN))
+		*move_type = MEXT_MOVE_EXTENT;
+	else
+		*move_type = MEXT_COPY_DATA;
+
+	return 0;
+error:
+	mext_folio_double_unlock(folio);
+	return ret;
+}
+
+/*
+ * Re-create the new moved mapping buffers of the original inode and commit
+ * the entire written range.
+ */
+static int mext_folio_mkwrite(struct inode *inode, struct folio *folio,
+			      size_t from, size_t to)
+{
+	unsigned int blocksize = i_blocksize(inode);
+	struct buffer_head *bh, *head;
+	size_t block_start, block_end;
+	sector_t block;
+	int ret;
+
+	head = folio_buffers(folio);
+	if (!head)
+		head = create_empty_buffers(folio, blocksize, 0);
+
+	block = folio_pos(folio) >> inode->i_blkbits;
+	block_end = 0;
+	bh = head;
+	do {
+		block_start = block_end;
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to)
+			continue;
+
+		ret = ext4_get_block(inode, block, bh, 0);
+		if (ret)
+			return ret;
+	} while (block++, (bh = bh->b_this_page) != head);
+
+	block_commit_write(folio, from, to);
+	return 0;
+}
+
+/*
+ * Save the data in original inode extent blocks and replace one folio size
+ * aligned original inode extent with one or one partial donor inode extent,
+ * and then write out the saved data in new original inode blocks. Pass out
+ * the replaced block count through m_len. Return 0 on success, and an error
+ * code otherwise.
+ */
+static int mext_move_extent(struct mext_data *mext, u64 *m_len)
+{
+	struct inode *orig_inode = mext->orig_inode;
+	struct inode *donor_inode = mext->donor_inode;
+	struct ext4_map_blocks *orig_map = &mext->orig_map;
+	unsigned int blkbits = orig_inode->i_blkbits;
+	struct folio *folio[2] = {NULL, NULL};
+	loff_t from, length;
+	enum mext_move_type move_type = 0;
+	handle_t *handle;
+	u64 r_len = 0;
+	unsigned int credits;
+	int ret, ret2;
+
+	*m_len = 0;
+	trace_ext4_move_extent_enter(orig_inode, orig_map, donor_inode,
+				     mext->donor_lblk);
+	credits = ext4_chunk_trans_extent(orig_inode, 0) * 2;
+	handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, credits);
 	if (IS_ERR(handle)) {
-		*err = PTR_ERR(handle);
-		return 0;
+		ret = PTR_ERR(handle);
+		goto out;
 	}
 
-	orig_blk_offset = orig_page_offset * blocks_per_page +
-		data_offset_in_page;
-
-	donor_blk_offset = donor_page_offset * blocks_per_page +
-		data_offset_in_page;
-
-	/* Calculate data_size */
-	if ((orig_blk_offset + block_len_in_page - 1) ==
-	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
-		/* Replace the last block */
-		tmp_data_size = orig_inode->i_size & (blocksize - 1);
-		/*
-		 * If data_size equal zero, it shows data_size is multiples of
-		 * blocksize. So we set appropriate value.
-		 */
-		if (tmp_data_size == 0)
-			tmp_data_size = blocksize;
-
-		data_size = tmp_data_size +
-			((block_len_in_page - 1) << orig_inode->i_blkbits);
-	} else
-		data_size = block_len_in_page << orig_inode->i_blkbits;
-
-	replaced_size = data_size;
-
-	*err = mext_folio_double_lock(orig_inode, donor_inode, orig_page_offset,
-				     donor_page_offset, folio);
-	if (unlikely(*err < 0))
-		goto stop_journal;
+	ret = mext_move_begin(mext, folio, &move_type);
+	if (ret)
+		goto stop_handle;
+
+	if (move_type == MEXT_SKIP_EXTENT)
+		goto unlock;
+
 	/*
-	 * If orig extent was unwritten it can become initialized
-	 * at any time after i_data_sem was dropped, in order to
-	 * serialize with delalloc we have recheck extent while we
-	 * hold page's lock, if it is still the case data copy is not
-	 * necessary, just swap data blocks between orig and donor.
+	 * Copy the data. First, read the original inode data into the page
+	 * cache. Then, release the existing mapping relationships and swap
+	 * the extent. Finally, re-establish the new mapping relationships
+	 * and dirty the page cache.
 	 */
-	if (unwritten) {
-		ext4_double_down_write_data_sem(orig_inode, donor_inode);
-		/* If any of extents in range became initialized we have to
-		 * fallback to data copying */
-		unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
-						block_len_in_page, 1, err);
-		if (*err)
-			goto drop_data_sem;
-
-		unwritten &= mext_check_coverage(donor_inode, donor_blk_offset,
-						 block_len_in_page, 1, err);
-		if (*err)
-			goto drop_data_sem;
-
-		if (!unwritten) {
-			ext4_double_up_write_data_sem(orig_inode, donor_inode);
-			goto data_copy;
-		}
-		if (!filemap_release_folio(folio[0], 0) ||
-		    !filemap_release_folio(folio[1], 0)) {
-			*err = -EBUSY;
-			goto drop_data_sem;
-		}
-		replaced_count = ext4_swap_extents(handle, orig_inode,
-						   donor_inode, orig_blk_offset,
-						   donor_blk_offset,
-						   block_len_in_page, 1, err);
-	drop_data_sem:
-		ext4_double_up_write_data_sem(orig_inode, donor_inode);
-		goto unlock_folios;
+	if (move_type == MEXT_COPY_DATA) {
+		from = offset_in_folio(folio[0],
+				((loff_t)orig_map->m_lblk) << blkbits);
+		length = ((loff_t)orig_map->m_len) << blkbits;
+
+		ret = mext_folio_mkuptodate(folio[0], from, from + length);
+		if (ret)
+			goto unlock;
 	}
-data_copy:
-	from = offset_in_folio(folio[0],
-			       orig_blk_offset << orig_inode->i_blkbits);
-	*err = mext_page_mkuptodate(folio[0], from, from + replaced_size);
-	if (*err)
-		goto unlock_folios;
-
-	/* At this point all buffers in range are uptodate, old mapping layout
-	 * is no longer required, try to drop it now. */
+
 	if (!filemap_release_folio(folio[0], 0) ||
 	    !filemap_release_folio(folio[1], 0)) {
-		*err = -EBUSY;
-		goto unlock_folios;
+		ret = -EBUSY;
+		goto unlock;
 	}
+
+	/* Move extent */
 	ext4_double_down_write_data_sem(orig_inode, donor_inode);
-	replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode,
-					       orig_blk_offset, donor_blk_offset,
-					   block_len_in_page, 1, err);
+	*m_len = ext4_swap_extents(handle, orig_inode, donor_inode,
+				   orig_map->m_lblk, mext->donor_lblk,
+				   orig_map->m_len, 1, &ret);
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
-	if (*err) {
-		if (replaced_count) {
-			block_len_in_page = replaced_count;
-			replaced_size =
-				block_len_in_page << orig_inode->i_blkbits;
-		} else
-			goto unlock_folios;
-	}
-	/* Perform all necessary steps similar write_begin()/write_end()
-	 * but keeping in mind that i_size will not change */
-	bh = folio_buffers(folio[0]);
-	if (!bh)
-		bh = create_empty_buffers(folio[0],
-				1 << orig_inode->i_blkbits, 0);
-	for (i = 0; i < from >> orig_inode->i_blkbits; i++)
-		bh = bh->b_this_page;
-	for (i = 0; i < block_len_in_page; i++) {
-		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
-		if (*err < 0)
-			goto repair_branches;
-		bh = bh->b_this_page;
-	}
 
-	block_commit_write(folio[0], from, from + replaced_size);
+	/* A short-length swap cannot occur after a successful swap extent. */
+	if (WARN_ON_ONCE(!ret && (*m_len != orig_map->m_len)))
+		ret = -EIO;
 
-	/* Even in case of data=writeback it is reasonable to pin
-	 * inode to transaction, to prevent unexpected data loss */
-	*err = ext4_jbd2_inode_add_write(handle, orig_inode,
-			(loff_t)orig_page_offset << PAGE_SHIFT, replaced_size);
+	if (!(*m_len) || (move_type == MEXT_MOVE_EXTENT))
+		goto unlock;
 
-unlock_folios:
-	folio_unlock(folio[0]);
-	folio_put(folio[0]);
-	folio_unlock(folio[1]);
-	folio_put(folio[1]);
-stop_journal:
+	/* Copy data */
+	length = (*m_len) << blkbits;
+	ret2 = mext_folio_mkwrite(orig_inode, folio[0], from, from + length);
+	if (ret2) {
+		if (!ret)
+			ret = ret2;
+		goto repair_branches;
+	}
+	/*
+	 * Even in case of data=writeback it is reasonable to pin
+	 * inode to transaction, to prevent unexpected data loss.
+	 */
+	ret2 = ext4_jbd2_inode_add_write(handle, orig_inode,
+			((loff_t)orig_map->m_lblk) << blkbits, length);
+	if (!ret)
+		ret = ret2;
+unlock:
+	mext_folio_double_unlock(folio);
+stop_handle:
 	ext4_journal_stop(handle);
-	if (*err == -ENOSPC &&
-	    ext4_should_retry_alloc(sb, &retries))
-		goto again;
-	/* Buffer was busy because probably is pinned to journal transaction,
-	 * force transaction commit may help to free it. */
-	if (*err == -EBUSY && retries++ < 4 && EXT4_SB(sb)->s_journal &&
-	    jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal))
-		goto again;
-	return replaced_count;
+out:
+	trace_ext4_move_extent_exit(orig_inode, orig_map->m_lblk, donor_inode,
+				    mext->donor_lblk, orig_map->m_len, *m_len,
+				    move_type, ret);
+	return ret;
 
 repair_branches:
-	/*
-	 * This should never ever happen!
-	 * Extents are swapped already, but we are not able to copy data.
-	 * Try to swap extents to it's original places
-	 */
-	ext4_double_down_write_data_sem(orig_inode, donor_inode);
-	replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode,
-					       orig_blk_offset, donor_blk_offset,
-					   block_len_in_page, 0, &err2);
-	ext4_double_up_write_data_sem(orig_inode, donor_inode);
-	if (replaced_count != block_len_in_page) {
-		ext4_error_inode_block(orig_inode, (sector_t)(orig_blk_offset),
-				       EIO, "Unable to copy data block,"
-				       " data will be lost.");
-		*err = -EIO;
+	ret2 = 0;
+	r_len = ext4_swap_extents(handle, donor_inode, orig_inode,
+				  mext->donor_lblk, orig_map->m_lblk,
+				  *m_len, 0, &ret2);
+	if (ret2 || r_len != *m_len) {
+		ext4_error_inode_block(orig_inode, (sector_t)(orig_map->m_lblk),
+				       EIO, "Unable to copy data block, data will be lost!");
+		ret = -EIO;
 	}
-	replaced_count = 0;
-	goto unlock_folios;
+	*m_len = 0;
+	goto unlock;
 }
 
-/**
- * mext_check_arguments - Check whether move extent can be done
- *
- * @orig_inode:		original inode
- * @donor_inode:	donor inode
- * @orig_start:		logical start offset in block for orig
- * @donor_start:	logical start offset in block for donor
- * @len:		the number of blocks to be moved
- *
- * Check the arguments of ext4_move_extents() whether the files can be
- * exchanged with each other.
- * Return 0 on success, or a negative error value on failure.
+/*
+ * Check the validity of the basic filesystem environment and the
+ * inodes' support status.
  */
-static int
-mext_check_arguments(struct inode *orig_inode,
-		     struct inode *donor_inode, __u64 orig_start,
-		     __u64 donor_start, __u64 *len)
+static int mext_check_validity(struct inode *orig_inode,
+			       struct inode *donor_inode)
 {
-	__u64 orig_eof, donor_eof;
-	unsigned int blkbits = orig_inode->i_blkbits;
-	unsigned int blocksize = 1 << blkbits;
+	struct super_block *sb = orig_inode->i_sb;
+
+	/* origin and donor should be different inodes */
+	if (orig_inode == donor_inode) {
+		ext4_debug("ext4 move extent: The argument files should not be same inode [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* origin and donor should belone to the same filesystem */
+	if (orig_inode->i_sb != donor_inode->i_sb) {
+		ext4_debug("ext4 move extent: The argument files should be in same FS [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Regular file check */
+	if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+		ext4_debug("ext4 move extent: The argument files should be regular file [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
 
-	orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits;
-	donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits;
+	if (ext4_has_feature_bigalloc(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with bigalloc");
+		return -EOPNOTSUPP;
+	}
 
+	if (IS_DAX(orig_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with DAX");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * TODO: it's not obvious how to swap blocks for inodes with full
+	 * journaling enabled.
+	 */
+	if (ext4_should_journal_data(orig_inode) ||
+	    ext4_should_journal_data(donor_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with data journaling");
+		return -EOPNOTSUPP;
+	}
+
+	if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported for encrypted files");
+		return -EOPNOTSUPP;
+	}
+
+	/* Ext4 move extent supports only extent based file */
+	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS)) ||
+	    !(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported for non-extent files");
+		return -EOPNOTSUPP;
+	}
 
 	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
-		ext4_debug("ext4 move extent: suid or sgid is set"
-			   " to donor file [ino:orig %lu, donor %lu]\n",
+		ext4_debug("ext4 move extent: suid or sgid is set to donor file [ino:orig %lu, donor %lu]\n",
 			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
 
-	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
+	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode)) {
+		ext4_debug("ext4 move extent: donor should not be immutable or append file [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EPERM;
+	}
 
 	/* Ext4 move extent does not support swap files */
 	if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
 		ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -ETXTBSY;
 	}
 
-	if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) {
+	if (ext4_is_quota_file(orig_inode) || ext4_is_quota_file(donor_inode)) {
 		ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EOPNOTSUPP;
-	}
-
-	/* Ext4 move extent supports only extent based file */
-	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
-		ext4_debug("ext4 move extent: orig file is not extents "
-			"based file [ino:orig %lu]\n", orig_inode->i_ino);
-		return -EOPNOTSUPP;
-	} else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
-		ext4_debug("ext4 move extent: donor file is not extents "
-			"based file [ino:donor %lu]\n", donor_inode->i_ino);
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EOPNOTSUPP;
 	}
 
@@ -507,12 +502,25 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+/*
+ * Check the moving range of ext4_move_extents() whether the files can be
+ * exchanged with each other, and adjust the length to fit within the file
+ * size. Return 0 on success, or a negative error value on failure.
+ */
+static int mext_check_adjust_range(struct inode *orig_inode,
+				   struct inode *donor_inode, __u64 orig_start,
+				   __u64 donor_start, __u64 *len)
+{
+	__u64 orig_eof, donor_eof;
+
 	/* Start offset should be same */
 	if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
 	    (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
-		ext4_debug("ext4 move extent: orig and donor's start "
-			"offsets are not aligned [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
+		ext4_debug("ext4 move extent: orig and donor's start offsets are not aligned [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
 
@@ -521,11 +529,14 @@ mext_check_arguments(struct inode *orig_inode,
 	    (*len > EXT_MAX_BLOCKS) ||
 	    (donor_start + *len >= EXT_MAX_BLOCKS) ||
 	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
-		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
-			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
-			orig_inode->i_ino, donor_inode->i_ino);
+		ext4_debug("ext4 move extent: Can't handle over [%u] blocks [ino:orig %lu, donor %lu]\n",
+			   EXT_MAX_BLOCKS,
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
+
+	orig_eof = EXT4_B_TO_LBLK(orig_inode, i_size_read(orig_inode));
+	donor_eof = EXT4_B_TO_LBLK(donor_inode, i_size_read(donor_inode));
 	if (orig_eof <= orig_start)
 		*len = 0;
 	else if (orig_eof < orig_start + *len - 1)
@@ -535,9 +546,8 @@ mext_check_arguments(struct inode *orig_inode,
 	else if (donor_eof < donor_start + *len - 1)
 		*len = donor_eof - donor_start;
 	if (!*len) {
-		ext4_debug("ext4 move extent: len should not be 0 "
-			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
-			donor_inode->i_ino);
+		ext4_debug("ext4 move extent: len should not be 0 [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
 
@@ -556,140 +566,81 @@ mext_check_arguments(struct inode *orig_inode,
  *
  * This function returns 0 and moved block length is set in moved_len
  * if succeed, otherwise returns error value.
- *
  */
-int
-ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
-		  __u64 donor_blk, __u64 len, __u64 *moved_len)
+int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
+		      __u64 donor_blk, __u64 len, __u64 *moved_len)
 {
 	struct inode *orig_inode = file_inode(o_filp);
 	struct inode *donor_inode = file_inode(d_filp);
-	struct ext4_ext_path *path = NULL;
-	int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
-	ext4_lblk_t o_end, o_start = orig_blk;
-	ext4_lblk_t d_start = donor_blk;
+	struct mext_data mext;
+	struct super_block *sb = orig_inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int retries = 0;
+	u64 m_len;
 	int ret;
 
-	if (orig_inode->i_sb != donor_inode->i_sb) {
-		ext4_debug("ext4 move extent: The argument files "
-			"should be in same FS [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
-	/* orig and donor should be different inodes */
-	if (orig_inode == donor_inode) {
-		ext4_debug("ext4 move extent: The argument files should not "
-			"be same inode [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
-	/* Regular file check */
-	if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
-		ext4_debug("ext4 move extent: The argument files should be "
-			"regular file [ino:orig %lu, donor %lu]\n",
-			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
-	/* TODO: it's not obvious how to swap blocks for inodes with full
-	   journaling enabled */
-	if (ext4_should_journal_data(orig_inode) ||
-	    ext4_should_journal_data(donor_inode)) {
-		ext4_msg(orig_inode->i_sb, KERN_ERR,
-			 "Online defrag not supported with data journaling");
-		return -EOPNOTSUPP;
-	}
-
-	if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) {
-		ext4_msg(orig_inode->i_sb, KERN_ERR,
-			 "Online defrag not supported for encrypted files");
-		return -EOPNOTSUPP;
-	}
+	*moved_len = 0;
 
 	/* Protect orig and donor inodes against a truncate */
 	lock_two_nondirectories(orig_inode, donor_inode);
 
+	ret = mext_check_validity(orig_inode, donor_inode);
+	if (ret)
+		goto out;
+
 	/* Wait for all existing dio workers */
 	inode_dio_wait(orig_inode);
 	inode_dio_wait(donor_inode);
 
-	/* Protect extent tree against block allocations via delalloc */
-	ext4_double_down_write_data_sem(orig_inode, donor_inode);
-	/* Check the filesystem environment whether move_extent can be done */
-	ret = mext_check_arguments(orig_inode, donor_inode, orig_blk,
-				    donor_blk, &len);
+	/* Check and adjust the specified move_extent range. */
+	ret = mext_check_adjust_range(orig_inode, donor_inode, orig_blk,
+				      donor_blk, &len);
 	if (ret)
 		goto out;
-	o_end = o_start + len;
 
-	*moved_len = 0;
-	while (o_start < o_end) {
-		struct ext4_extent *ex;
-		ext4_lblk_t cur_blk, next_blk;
-		pgoff_t orig_page_index, donor_page_index;
-		int offset_in_page;
-		int unwritten, cur_len;
-
-		path = get_ext_path(orig_inode, o_start, path);
-		if (IS_ERR(path)) {
-			ret = PTR_ERR(path);
+	mext.orig_inode = orig_inode;
+	mext.donor_inode = donor_inode;
+	while (len) {
+		mext.orig_map.m_lblk = orig_blk;
+		mext.orig_map.m_len = len;
+		mext.orig_map.m_flags = 0;
+		mext.donor_lblk = donor_blk;
+
+		ret = ext4_map_blocks(NULL, orig_inode, &mext.orig_map, 0);
+		if (ret < 0)
 			goto out;
-		}
-		ex = path[path->p_depth].p_ext;
-		cur_blk = le32_to_cpu(ex->ee_block);
-		cur_len = ext4_ext_get_actual_len(ex);
-		/* Check hole before the start pos */
-		if (cur_blk + cur_len - 1 < o_start) {
-			next_blk = ext4_ext_next_allocated_block(path);
-			if (next_blk == EXT_MAX_BLOCKS) {
-				ret = -ENODATA;
-				goto out;
+
+		/* Skip moving if it is a hole or a delalloc extent. */
+		if (mext.orig_map.m_flags &
+		    (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN)) {
+			ret = mext_move_extent(&mext, &m_len);
+			*moved_len += m_len;
+			if (!ret)
+				goto next;
+
+			/* Move failed or partially failed. */
+			if (m_len) {
+				orig_blk += m_len;
+				donor_blk += m_len;
+				len -= m_len;
 			}
-			d_start += next_blk - o_start;
-			o_start = next_blk;
-			continue;
-		/* Check hole after the start pos */
-		} else if (cur_blk > o_start) {
-			/* Skip hole */
-			d_start += cur_blk - o_start;
-			o_start = cur_blk;
-			/* Extent inside requested range ?*/
-			if (cur_blk >= o_end)
-				goto out;
-		} else { /* in_range(o_start, o_blk, o_len) */
-			cur_len += cur_blk - o_start;
+			if (ret == -ESTALE)
+				continue;
+			if (ret == -ENOSPC &&
+			    ext4_should_retry_alloc(sb, &retries))
+				continue;
+			if (ret == -EBUSY &&
+			    sbi->s_journal && retries++ < 4 &&
+			    jbd2_journal_force_commit_nested(sbi->s_journal))
+				continue;
+
+			goto out;
 		}
-		unwritten = ext4_ext_is_unwritten(ex);
-		if (o_end - o_start < cur_len)
-			cur_len = o_end - o_start;
-
-		orig_page_index = o_start >> (PAGE_SHIFT -
-					       orig_inode->i_blkbits);
-		donor_page_index = d_start >> (PAGE_SHIFT -
-					       donor_inode->i_blkbits);
-		offset_in_page = o_start % blocks_per_page;
-		if (cur_len > blocks_per_page - offset_in_page)
-			cur_len = blocks_per_page - offset_in_page;
-		/*
-		 * Up semaphore to avoid following problems:
-		 * a. transaction deadlock among ext4_journal_start,
-		 *    ->write_begin via pagefault, and jbd2_journal_commit
-		 * b. racing with ->read_folio, ->write_begin, and
-		 *    ext4_get_block in move_extent_per_page
-		 */
-		ext4_double_up_write_data_sem(orig_inode, donor_inode);
-		/* Swap original branches with new branches */
-		*moved_len += move_extent_per_page(o_filp, donor_inode,
-				     orig_page_index, donor_page_index,
-				     offset_in_page, cur_len,
-				     unwritten, &ret);
-		ext4_double_down_write_data_sem(orig_inode, donor_inode);
-		if (ret < 0)
-			break;
-		o_start += cur_len;
-		d_start += cur_len;
+next:
+		orig_blk += mext.orig_map.m_len;
+		donor_blk += mext.orig_map.m_len;
+		len -= mext.orig_map.m_len;
+		retries = 0;
 	}
 
 out:
@@ -698,9 +649,6 @@ out:
 		ext4_discard_preallocations(donor_inode);
 	}
 
-	ext4_free_ext_path(path);
-	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	unlock_two_nondirectories(orig_inode, donor_inode);
-
 	return ret;
 }