ext4: lookup block mapping in extent status tree

After tracking all extent status, we already have a extent cache in
memory. Every time we want to lookup a block mapping, we can first
try to lookup it in extent status tree to avoid a potential disk I/O.

A new function called ext4_es_lookup_extent is defined to finish this
work. When we try to lookup a block mapping, we always call
ext4_map_blocks and/or ext4_da_map_blocks. So in these functions we
first try to lookup a block mapping in extent status tree.

A new flag EXT4_GET_BLOCKS_NO_PUT_HOLE is used in ext4_da_map_blocks
in order not to put a hole into extent status tree because this hole
will be converted to delayed extent in the tree immediately.

Signed-off-by: Zheng Liu <[e-mail]>
Signed-off-by: "Theodore Ts'o" <[e-mail]>
Cc: Jan kara <[e-mail]>

fs/ext4/ext4.h

···
 #define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
 	/* Do not take i_data_sem locking in ext4_map_blocks */
 #define EXT4_GET_BLOCKS_NO_LOCK			0x0100
+	/* Do not put hole in extent cache */
+#define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
 
 /*
  * Flags used by ext4_free_blocks

fs/ext4/extents.c

···
 				block,
 				le32_to_cpu(ex->ee_block),
 				 ext4_ext_get_actual_len(ex));
+		if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
+			ext4_es_insert_extent(inode, lblock, len, ~0,
+					      EXTENT_STATUS_HOLE);
 	} else if (block >= le32_to_cpu(ex->ee_block)
 			+ ext4_ext_get_actual_len(ex)) {
 		ext4_lblk_t next;
···
 				block);
 		BUG_ON(next == lblock);
 		len = next - lblock;
+		if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
+			ext4_es_insert_extent(inode, lblock, len, ~0,
+					      EXTENT_STATUS_HOLE);
 	} else {
 		lblock = len = 0;
 		BUG();
···
 		 * put just found gap into cache to speed up
 		 * subsequent requests
 		 */
-		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+		if ((flags & EXT4_GET_BLOCKS_NO_PUT_HOLE) == 0)
+			ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
 		goto out2;
 	}
 

fs/ext4/extents_status.c

···
 	return err;
 }
 
+/*
+ * ext4_es_lookup_extent() looks up an extent in extent status tree.
+ *
+ * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
+ *
+ * Return: 1 on found, 0 on not
+ */
+int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+			  struct extent_status *es)
+{
+	struct ext4_es_tree *tree;
+	struct extent_status *es1 = NULL;
+	struct rb_node *node;
+	int found = 0;
+
+	trace_ext4_es_lookup_extent_enter(inode, lblk);
+	es_debug("lookup extent in block %u\n", lblk);
+
+	tree = &EXT4_I(inode)->i_es_tree;
+	read_lock(&EXT4_I(inode)->i_es_lock);
+
+	/* find extent in cache firstly */
+	es->es_lblk = es->es_len = es->es_pblk = 0;
+	if (tree->cache_es) {
+		es1 = tree->cache_es;
+		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
+			es_debug("%u cached by [%u/%u)\n",
+				 lblk, es1->es_lblk, es1->es_len);
+			found = 1;
+			goto out;
+		}
+	}
+
+	node = tree->root.rb_node;
+	while (node) {
+		es1 = rb_entry(node, struct extent_status, rb_node);
+		if (lblk < es1->es_lblk)
+			node = node->rb_left;
+		else if (lblk > ext4_es_end(es1))
+			node = node->rb_right;
+		else {
+			found = 1;
+			break;
+		}
+	}
+
+out:
+	if (found) {
+		BUG_ON(!es1);
+		es->es_lblk = es1->es_lblk;
+		es->es_len = es1->es_len;
+		es->es_pblk = es1->es_pblk;
+	}
+
+	read_unlock(&EXT4_I(inode)->i_es_lock);
+
+	trace_ext4_es_lookup_extent_exit(inode, es, found);
+	return found;
+}
+
 static int __es_remove_extent(struct ext4_es_tree *tree, ext4_lblk_t lblk,
 				 ext4_lblk_t end)
 {

fs/ext4/extents_status.h

···
 				 ext4_lblk_t len);
 extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 					struct extent_status *es);
+extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+				 struct extent_status *es);
 
 static inline int ext4_es_is_written(struct extent_status *es)
 {

fs/ext4/inode.c

···
 int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		    struct ext4_map_blocks *map, int flags)
 {
+	struct extent_status es;
 	int retval;
 
 	map->m_flags = 0;
 	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
 		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
 		  (unsigned long) map->m_lblk);
+
+	/* Lookup extent status tree firstly */
+	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
+			map->m_pblk = ext4_es_pblock(&es) +
+					map->m_lblk - es.es_lblk;
+			map->m_flags |= ext4_es_is_written(&es) ?
+					EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
+			retval = es.es_len - (map->m_lblk - es.es_lblk);
+			if (retval > map->m_len)
+				retval = map->m_len;
+			map->m_len = retval;
+		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+			retval = 0;
+		} else {
+			BUG_ON(1);
+		}
+		goto found;
+	}
+
 	/*
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
···
 	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
 		up_read((&EXT4_I(inode)->i_data_sem));
 
+found:
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		int ret = check_block_validity(inode, map);
 		if (ret != 0)
···
 			      struct ext4_map_blocks *map,
 			      struct buffer_head *bh)
 {
+	struct extent_status es;
 	int retval;
 	sector_t invalid_block = ~((sector_t) 0xffff);
 
···
 	ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
 		  "logical block %lu\n", inode->i_ino, map->m_len,
 		  (unsigned long) map->m_lblk);
+
+	/* Lookup extent status tree firstly */
+	if (ext4_es_lookup_extent(inode, iblock, &es)) {
+
+		if (ext4_es_is_hole(&es)) {
+			retval = 0;
+			down_read((&EXT4_I(inode)->i_data_sem));
+			goto add_delayed;
+		}
+
+		/*
+		 * Delayed extent could be allocated by fallocate.
+		 * So we need to check it.
+		 */
+		if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
+			map_bh(bh, inode->i_sb, invalid_block);
+			set_buffer_new(bh);
+			set_buffer_delay(bh);
+			return 0;
+		}
+
+		map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
+		retval = es.es_len - (iblock - es.es_lblk);
+		if (retval > map->m_len)
+			retval = map->m_len;
+		map->m_len = retval;
+		if (ext4_es_is_written(&es))
+			map->m_flags |= EXT4_MAP_MAPPED;
+		else if (ext4_es_is_unwritten(&es))
+			map->m_flags |= EXT4_MAP_UNWRITTEN;
+		else
+			BUG_ON(1);
+
+		return retval;
+	}
+
 	/*
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
···
 			map->m_flags |= EXT4_MAP_FROM_CLUSTER;
 		retval = 0;
 	} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+		retval = ext4_ext_map_blocks(NULL, inode, map,
+					     EXT4_GET_BLOCKS_NO_PUT_HOLE);
 	else
-		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+		retval = ext4_ind_map_blocks(NULL, inode, map,
+					     EXT4_GET_BLOCKS_NO_PUT_HOLE);
 
+add_delayed:
 	if (retval == 0) {
 		int ret;
 		/*

include/trace/events/ext4.h

···
 		  __entry->pblk, __entry->status)
 );
 
+TRACE_EVENT(ext4_es_lookup_extent_enter,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
+
+	TP_ARGS(inode, lblk),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->lblk	= lblk;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->lblk)
+);
+
+TRACE_EVENT(ext4_es_lookup_extent_exit,
+	TP_PROTO(struct inode *inode, struct extent_status *es,
+		 int found),
+
+	TP_ARGS(inode, es, found),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+		__field(	ext4_lblk_t,	len		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	unsigned long long,	status	)
+		__field(	int,		found		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->lblk	= es->es_lblk;
+		__entry->len	= es->es_len;
+		__entry->pblk	= ext4_es_pblock(es);
+		__entry->status	= ext4_es_status(es);
+		__entry->found	= found;
+	),
+
+	TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->found,
+		  __entry->lblk, __entry->len,
+		  __entry->found ? __entry->pblk : 0,
+		  __entry->found ? __entry->status : 0)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */