1 files changed, 120 insertions, 82 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 107936db244e..7097b0f680e6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2125,7 +2125,8 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 		next_del = ext4_find_delayed_extent(inode, &es);
 		if (!exists && next_del) {
 			exists = 1;
-			flags |= FIEMAP_EXTENT_DELALLOC;
+			flags |= (FIEMAP_EXTENT_DELALLOC |
+				  FIEMAP_EXTENT_UNKNOWN);
 		}
 		up_read(&EXT4_I(inode)->i_data_sem);
 
@@ -2328,17 +2329,15 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
 }
 
 /*
- * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ * How many index/leaf blocks need to change/allocate to add @extents extents?
  *
- * if nrblocks are fit in a single extent (chunk flag is 1), then
- * in the worse case, each tree level index/leaf need to be changed
- * if the tree split due to insert a new extent, then the old tree
- * index/leaf need to be updated too
+ * If we add a single extent, then in the worse case, each tree level
+ * index/leaf need to be changed in case of the tree split.
  *
- * If the nrblocks are discontiguous, they could cause
- * the whole tree split more than once, but this is really rare.
+ * If more extents are inserted, they could cause the whole tree split more
+ * than once, but this is really rare.
  */
-int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+int ext4_ext_index_trans_blocks(struct inode *inode, int extents)
 {
 	int index;
 	int depth;
@@ -2349,7 +2348,7 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 
 	depth = ext_depth(inode);
 
-	if (chunk)
+	if (extents <= 1)
 		index = depth * 2;
 	else
 		index = depth * 3;
@@ -2357,20 +2356,24 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 	return index;
 }
 
+static inline int get_default_free_blocks_flags(struct inode *inode)
+{
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
+	else if (ext4_should_journal_data(inode))
+		return EXT4_FREE_BLOCKS_FORGET;
+	return 0;
+}
+
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 			      struct ext4_extent *ex,
-			      ext4_fsblk_t *partial_cluster,
+			      long long *partial_cluster,
 			      ext4_lblk_t from, ext4_lblk_t to)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
 	ext4_fsblk_t pblk;
-	int flags = 0;
-
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
-	else if (ext4_should_journal_data(inode))
-		flags |= EXT4_FREE_BLOCKS_FORGET;
+	int flags = get_default_free_blocks_flags(inode);
 
 	/*
 	 * For bigalloc file systems, we never free a partial cluster
@@ -2388,7 +2391,8 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 	 * partial cluster here.
 	 */
 	pblk = ext4_ext_pblock(ex) + ee_len - 1;
-	if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+	if ((*partial_cluster > 0) &&
+	    (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
 		ext4_free_blocks(handle, inode, NULL,
 				 EXT4_C2B(sbi, *partial_cluster),
 				 sbi->s_cluster_ratio, flags);
@@ -2414,41 +2418,46 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 	    && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		/* tail removal */
 		ext4_lblk_t num;
+		unsigned int unaligned;
 
 		num = le32_to_cpu(ex->ee_block) + ee_len - from;
 		pblk = ext4_ext_pblock(ex) + ee_len - num;
-		ext_debug("free last %u blocks starting %llu\n", num, pblk);
+		/*
+		 * Usually we want to free partial cluster at the end of the
+		 * extent, except for the situation when the cluster is still
+		 * used by any other extent (partial_cluster is negative).
+		 */
+		if (*partial_cluster < 0 &&
+		    -(*partial_cluster) == EXT4_B2C(sbi, pblk + num - 1))
+			flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER;
+
+		ext_debug("free last %u blocks starting %llu partial %lld\n",
+			  num, pblk, *partial_cluster);
 		ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
 		/*
 		 * If the block range to be freed didn't start at the
 		 * beginning of a cluster, and we removed the entire
-		 * extent, save the partial cluster here, since we
-		 * might need to delete if we determine that the
-		 * truncate operation has removed all of the blocks in
-		 * the cluster.
+		 * extent and the cluster is not used by any other extent,
+		 * save the partial cluster here, since we might need to
+		 * delete if we determine that the truncate operation has
+		 * removed all of the blocks in the cluster.
+		 *
+		 * On the other hand, if we did not manage to free the whole
+		 * extent, we have to mark the cluster as used (store negative
+		 * cluster number in partial_cluster).
 		 */
-		if (pblk & (sbi->s_cluster_ratio - 1) &&
-		    (ee_len == num))
+		unaligned = pblk & (sbi->s_cluster_ratio - 1);
+		if (unaligned && (ee_len == num) &&
+		    (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
 			*partial_cluster = EXT4_B2C(sbi, pblk);
-		else
+		else if (unaligned)
+			*partial_cluster = -((long long)EXT4_B2C(sbi, pblk));
+		else if (*partial_cluster > 0)
 			*partial_cluster = 0;
-	} else if (from == le32_to_cpu(ex->ee_block)
-		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
-		/* head removal */
-		ext4_lblk_t num;
-		ext4_fsblk_t start;
-
-		num = to - from;
-		start = ext4_ext_pblock(ex);
-
-		ext_debug("free first %u blocks starting %llu\n", num, start);
-		ext4_free_blocks(handle, inode, NULL, start, num, flags);
-
-	} else {
-		printk(KERN_INFO "strange request: removal(2) "
-				"%u-%u from %u:%u\n",
-				from, to, le32_to_cpu(ex->ee_block), ee_len);
-	}
+	} else
+		ext4_error(sbi->s_sb, "strange request: removal(2) "
+			   "%u-%u from %u:%u\n",
+			   from, to, le32_to_cpu(ex->ee_block), ee_len);
 	return 0;
 }
 
@@ -2461,12 +2470,16 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
  * @handle: The journal handle
  * @inode:  The files inode
  * @path:   The path to the leaf
+ * @partial_cluster: The cluster which we'll have to free if all extents
+ *                   has been released from it. It gets negative in case
+ *                   that the cluster is still used.
  * @start:  The first block to remove
  * @end:   The last block to remove
  */
 static int
 ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
-		 struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+		 struct ext4_ext_path *path,
+		 long long *partial_cluster,
 		 ext4_lblk_t start, ext4_lblk_t end)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2479,6 +2492,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	unsigned short ex_ee_len;
 	unsigned uninitialized = 0;
 	struct ext4_extent *ex;
+	ext4_fsblk_t pblk;
 
 	/* the header must be checked already in ext4_ext_remove_space() */
 	ext_debug("truncate since %u in leaf to %u\n", start, end);
@@ -2490,7 +2504,9 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		return -EIO;
 	}
 	/* find where to start removing */
-	ex = EXT_LAST_EXTENT(eh);
+	ex = path[depth].p_ext;
+	if (!ex)
+		ex = EXT_LAST_EXTENT(eh);
 
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2517,6 +2533,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 
 		/* If this extent is beyond the end of the hole, skip it */
 		if (end < ex_ee_block) {
+			/*
+			 * We're going to skip this extent and move to another,
+			 * so if this extent is not cluster aligned we have
+			 * to mark the current cluster as used to avoid
+			 * accidentally freeing it later on
+			 */
+			pblk = ext4_ext_pblock(ex);
+			if (pblk & (sbi->s_cluster_ratio - 1))
+				*partial_cluster =
+					-((long long)EXT4_B2C(sbi, pblk));
 			ex--;
 			ex_ee_block = le32_to_cpu(ex->ee_block);
 			ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2592,7 +2618,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 					sizeof(struct ext4_extent));
 			}
 			le16_add_cpu(&eh->eh_entries, -1);
-		} else
+		} else if (*partial_cluster > 0)
 			*partial_cluster = 0;
 
 		err = ext4_ext_dirty(handle, inode, path + depth);
@@ -2610,17 +2636,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		err = ext4_ext_correct_indexes(handle, inode, path);
 
 	/*
-	 * If there is still a entry in the leaf node, check to see if
-	 * it references the partial cluster.  This is the only place
-	 * where it could; if it doesn't, we can free the cluster.
+	 * Free the partial cluster only if the current extent does not
+	 * reference it. Otherwise we might free used cluster.
 	 */
-	if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+	if (*partial_cluster > 0 &&
 	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
 	     *partial_cluster)) {
-		int flags = EXT4_FREE_BLOCKS_FORGET;
-
-		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-			flags |= EXT4_FREE_BLOCKS_METADATA;
+		int flags = get_default_free_blocks_flags(inode);
 
 		ext4_free_blocks(handle, inode, NULL,
 				 EXT4_C2B(sbi, *partial_cluster),
@@ -2664,7 +2686,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
 	struct ext4_ext_path *path = NULL;
-	ext4_fsblk_t partial_cluster = 0;
+	long long partial_cluster = 0;
 	handle_t *handle;
 	int i = 0, err = 0;
 
@@ -2676,7 +2698,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 		return PTR_ERR(handle);
 
 again:
-	trace_ext4_ext_remove_space(inode, start, depth);
+	trace_ext4_ext_remove_space(inode, start, end, depth);
 
 	/*
 	 * Check if we are removing extents inside the extent tree. If that
@@ -2844,17 +2866,14 @@ again:
 		}
 	}
 
-	trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
-			path->p_hdr->eh_entries);
+	trace_ext4_ext_remove_space_done(inode, start, end, depth,
+			partial_cluster, path->p_hdr->eh_entries);
 
 	/* If we still have something in the partial cluster and we have removed
 	 * even the first extent, then we should free the blocks in the partial
 	 * cluster as well. */
-	if (partial_cluster && path->p_hdr->eh_entries == 0) {
-		int flags = EXT4_FREE_BLOCKS_FORGET;
-
-		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-			flags |= EXT4_FREE_BLOCKS_METADATA;
+	if (partial_cluster > 0 && path->p_hdr->eh_entries == 0) {
+		int flags = get_default_free_blocks_flags(inode);
 
 		ext4_free_blocks(handle, inode, NULL,
 				 EXT4_C2B(EXT4_SB(sb), partial_cluster),
@@ -3642,7 +3661,7 @@ int ext4_find_delalloc_range(struct inode *inode,
 {
 	struct extent_status es;
 
-	ext4_es_find_delayed_extent(inode, lblk_start, &es);
+	ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es);
 	if (es.es_len == 0)
 		return 0; /* there is no delay extent in this tree */
 	else if (es.es_lblk <= lblk_start &&
@@ -4363,7 +4382,7 @@ out2:
 	}
 
 out3:
-	trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated);
+	trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated);
 
 	return err ? err : allocated;
 }
@@ -4446,7 +4465,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		return -EOPNOTSUPP;
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return ext4_punch_hole(file, offset, len);
+		return ext4_punch_hole(inode, offset, len);
 
 	ret = ext4_convert_inline_data(inode);
 	if (ret)
@@ -4548,10 +4567,9 @@ retry:
  * function, to convert the fallocated extents after IO is completed.
  * Returns 0 on success.
  */
-int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
-				    ssize_t len)
+int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
+				   loff_t offset, ssize_t len)
 {
-	handle_t *handle;
 	unsigned int max_blocks;
 	int ret = 0;
 	int ret2 = 0;
@@ -4566,16 +4584,32 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 	max_blocks = ((EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) -
 		      map.m_lblk);
 	/*
-	 * credits to insert 1 extent into extent tree
+	 * This is somewhat ugly but the idea is clear: When transaction is
+	 * reserved, everything goes into it. Otherwise we rather start several
+	 * smaller transactions for conversion of each extent separately.
 	 */
-	credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	if (handle) {
+		handle = ext4_journal_start_reserved(handle,
+						     EXT4_HT_EXT_CONVERT);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+		credits = 0;
+	} else {
+		/*
+		 * credits to insert 1 extent into extent tree
+		 */
+		credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	}
 	while (ret >= 0 && ret < max_blocks) {
 		map.m_lblk += ret;
 		map.m_len = (max_blocks -= ret);
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			break;
+		if (credits) {
+			handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+						    credits);
+			if (IS_ERR(handle)) {
+				ret = PTR_ERR(handle);
+				break;
+			}
 		}
 		ret = ext4_map_blocks(handle, inode, &map,
 				      EXT4_GET_BLOCKS_IO_CONVERT_EXT);
@@ -4586,10 +4620,13 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 				     inode->i_ino, map.m_lblk,
 				     map.m_len, ret);
 		ext4_mark_inode_dirty(handle, inode);
-		ret2 = ext4_journal_stop(handle);
-		if (ret <= 0 || ret2 )
+		if (credits)
+			ret2 = ext4_journal_stop(handle);
+		if (ret <= 0 || ret2)
 			break;
 	}
+	if (!credits)
+		ret2 = ext4_journal_stop(handle);
 	return ret > 0 ? ret2 : ret;
 }
 
@@ -4608,9 +4645,10 @@ static int ext4_find_delayed_extent(struct inode *inode,
 	struct extent_status es;
 	ext4_lblk_t block, next_del;
 
-	ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
-
 	if (newes->es_pblk == 0) {
+		ext4_es_find_delayed_extent_range(inode, newes->es_lblk,
+				newes->es_lblk + newes->es_len - 1, &es);
+
 		/*
 		 * No extent in extent-tree contains block @newes->es_pblk,
 		 * then the block may stay in 1)a hole or 2)delayed-extent.
@@ -4630,7 +4668,7 @@ static int ext4_find_delayed_extent(struct inode *inode,
 	}
 
 	block = newes->es_lblk + newes->es_len;
-	ext4_es_find_delayed_extent(inode, block, &es);
+	ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
 	if (es.es_len == 0)
 		next_del = EXT_MAX_BLOCKS;
 	else
@@ -4658,7 +4696,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		error = ext4_get_inode_loc(inode, &iloc);
 		if (error)
 			return error;
-		physical = iloc.bh->b_blocknr << blockbits;
+		physical = (__u64)iloc.bh->b_blocknr << blockbits;
 		offset = EXT4_GOOD_OLD_INODE_SIZE +
 				EXT4_I(inode)->i_extra_isize;
 		physical += offset;
@@ -4666,7 +4704,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		flags |= FIEMAP_EXTENT_DATA_INLINE;
 		brelse(iloc.bh);
 	} else { /* external block */
-		physical = EXT4_I(inode)->i_file_acl << blockbits;
+		physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
 		length = inode->i_sb->s_blocksize;
 	}