ext4: Add support for EXT4_GET_BLOCKS_QUERY_LEAF_BLOCKS

There can be a case where there are contiguous extents on the adjacent
leaf nodes of on-disk extent trees. So when someone tries to write to
this contiguous range, ext4_map_blocks() call will split by returning
1 extent at a time if this is not already cached in extent_status tree
cache (where if these extents when cached can get merged since they are
contiguous).

This is fine for a normal write however in case of atomic writes, it
can't afford to break the write into two. Now this is also something
that will only happen in the slow write case where we call
ext4_map_blocks() for each of these extents spread across different leaf
nodes. However, there is no guarantee that these extent status cache
cannot be reclaimed before the last call to ext4_map_blocks() in
ext4_map_blocks_atomic_write_slow().

Hence this patch adds support of EXT4_GET_BLOCKS_QUERY_LEAF_BLOCKS.
This flag checks if the requested range can be fully found in extent
status cache and return. If not, it looks up in on-disk extent
tree via ext4_map_query_blocks(). If the found extent is the last entry
in the leaf node, then it goes and queries the next lblk to see if there
is an adjacent contiguous extent in the adjacent leaf node of the
on-disk extent tree.

Even though there can be a case where there are multiple adjacent extent
entries spread across multiple leaf nodes. But we only read an adjacent
leaf block i.e. in total of 2 extent entries spread across 2 leaf nodes.
The reason for this is that we are mostly only going to support atomic
writes with upto 64KB or maybe max upto 1MB of atomic write support.

Acked-by: Darrick J. Wong <djwong@kernel.org>
Co-developed-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://patch.msgid.link/6bb563e661f5fbd80e266a9e6ce6e29178f555f6.1747337952.git.ritesh.list@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 83 insertions, 7 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 72dc1314925f..14c19a38cd4f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -483,15 +483,73 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 }
 #endif /* ES_AGGRESSIVE_TEST */
 
+static int ext4_map_query_blocks_next_in_leaf(handle_t *handle,
+			struct inode *inode, struct ext4_map_blocks *map,
+			unsigned int orig_mlen)
+{
+	struct ext4_map_blocks map2;
+	unsigned int status, status2;
+	int retval;
+
+	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+		EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+
+	WARN_ON_ONCE(!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF));
+	WARN_ON_ONCE(orig_mlen <= map->m_len);
+
+	/* Prepare map2 for lookup in next leaf block */
+	map2.m_lblk = map->m_lblk + map->m_len;
+	map2.m_len = orig_mlen - map->m_len;
+	map2.m_flags = 0;
+	retval = ext4_ext_map_blocks(handle, inode, &map2, 0);
+
+	if (retval <= 0) {
+		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+				      map->m_pblk, status, false);
+		return map->m_len;
+	}
+
+	if (unlikely(retval != map2.m_len)) {
+		ext4_warning(inode->i_sb,
+			     "ES len assertion failed for inode "
+			     "%lu: retval %d != map->m_len %d",
+			     inode->i_ino, retval, map2.m_len);
+		WARN_ON(1);
+	}
+
+	status2 = map2.m_flags & EXT4_MAP_UNWRITTEN ?
+		EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+
+	/*
+	 * If map2 is contiguous with map, then let's insert it as a single
+	 * extent in es cache and return the combined length of both the maps.
+	 */
+	if (map->m_pblk + map->m_len == map2.m_pblk &&
+			status == status2) {
+		ext4_es_insert_extent(inode, map->m_lblk,
+				      map->m_len + map2.m_len, map->m_pblk,
+				      status, false);
+		map->m_len += map2.m_len;
+	} else {
+		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+				      map->m_pblk, status, false);
+	}
+
+	return map->m_len;
+}
+
 static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 				 struct ext4_map_blocks *map, int flags)
 {
 	unsigned int status;
 	int retval;
+	unsigned int orig_mlen = map->m_len;
+	unsigned int query_flags = flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF;
 
 	flags &= EXT4_EX_FILTER;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		retval = ext4_ext_map_blocks(handle, inode, map, flags);
+		retval = ext4_ext_map_blocks(handle, inode, map,
+					     flags | query_flags);
 	else
 		retval = ext4_ind_map_blocks(handle, inode, map, flags);
 
@@ -506,11 +564,23 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 		WARN_ON(1);
 	}
 
-	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
-			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-			      map->m_pblk, status, false);
-	return retval;
+	/*
+	 * No need to query next in leaf:
+	 * - if returned extent is not last in leaf or
+	 * - if the last in leaf is the full requested range
+	 */
+	if (!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF) ||
+			((map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF) &&
+			 (map->m_len == orig_mlen))) {
+		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+				      map->m_pblk, status, false);
+		return retval;
+	}
+
+	return ext4_map_query_blocks_next_in_leaf(handle, inode, map,
+						  orig_mlen);
 }
 
 static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
@@ -624,6 +694,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	struct extent_status es;
 	int retval;
 	int ret = 0;
+	unsigned int orig_mlen = map->m_len;
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
@@ -685,7 +756,12 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		ext4_map_blocks_es_recheck(handle, inode, map,
 					   &orig_map, flags);
 #endif
-		goto found;
+		if (!(flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) ||
+				orig_mlen == map->m_len)
+			goto found;
+
+		if (flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF)
+			map->m_len = orig_mlen;
 	}
 	/*
 	 * In the query cache no-wait mode, nothing we can do more if we