ext4fs: Add ext4 extent tree cache

In ext4, the file inode can store up to 4 extents. If a file requires
more (due to size or fragmentation), an extent index tree is used.

Currently, u-boot reads a node from each level of the extent tree
for every block read, which is very inefficient when extent tree
depth is > 0.

This patch adds a cache for the extent tree. We cache the 1
most-recently-seen node at each extent tree level. The typical workload
is sequential block access, so once we leave a given tree node, it will
not be revisited. Therefore, it makes sense to just cache one node
per tree level.

Cached blocks are lazily allocated. The typical case is extent tree
depth = 0, in which case no caching is needed and no allocations will
occur.

For files with extent tree depth = 1, this patch produces a ~10x
improvement in read speed. For deeper extent trees, the improvement is
larger. On my test device, a 3MB file which previously took 9s to read
now takes 150ms.

Cache size is configurable with CONFIG_EXT4_EXTENT_CACHE_SIZE. However
the default of 5 (the maximum depth of well-formed extent trees) is
recommended.

Signed-off-by: Evan Thompson <evan.thompson@flukenetworks.com>
Reviewed-by: Tom Rini <trini@konsulko.com>
Cherry-picked-by: Alexandre Bard <alexandre.bard@netmodule.com>

BugzID: 57904

doc/README.ext4

@@ -33,6 +33,13 @@ In addition, to get the write access command "ext4write", enable:
 which automatically selects CONFIG_EXT4_WRITE if it wasn't defined
 already.
 
+For files with extents, an ext4 extent tree cache improves performance:
+
+  CONFIG_EXT4_EXTENT_CACHE_SIZE <#>
+
+The above cache size defaults to 5 if not defined. This default is
+strongly recommended. 0 will turn off extent caching.
+
 Also relevant are the generic filesystem commands, selected by:
 
   CONFIG_CMD_FS_GENERIC

fs/ext4/Kconfig

@@ -11,3 +11,11 @@ config EXT4_WRITE
 	help
 	  This provides support for creating and writing new files to an
 	  existing ext4 filesystem partition.
+
+config EXT4_EXTENT_CACHE_SIZE
+	int "Set ext4 extent tree cache depth"
+	default 5
+	depends on FS_EXT4
+	help
+	  This sets the depth of extent nodes cached. Sane ext4 files
+	  go no deeper than 5. Set to 0 to disable caching.

fs/ext4/ext4_common.c

@@ -1523,6 +1523,43 @@ void ext4fs_allocate_blocks(struct ext2_inode *file_inode,
 
 #endif
 
+/* Extent tree cache caches one entry per tree level
+ * eg, ext_block->eh_depth is used as the index into the cache
+ *
+ * If the tree is deeper than CONFIG_EXT4_EXTENT_CACHE_SIZE (very unlikely),
+ * file read performance will be impacted by repeated re-reads
+ * of those index nodes.
+ */
+
+struct extent_cache_entry {
+	unsigned long long block;
+	struct ext4_extent_header *ext_block;
+};
+
+static struct extent_cache_entry
+	extent_cache[CONFIG_EXT4_EXTENT_CACHE_SIZE];
+
+static void ext4fs_init_extent_block_cache(void)
+{
+	int i;
+
+	for (i = 0; i < CONFIG_EXT4_EXTENT_CACHE_SIZE; i++) {
+		extent_cache[i].block = 0;
+		extent_cache[i].ext_block = NULL;
+	}
+}
+
+static void ext4fs_free_extent_block_cache(void)
+{
+	int i;
+
+	for (i = 0; i < CONFIG_EXT4_EXTENT_CACHE_SIZE; i++) {
+		extent_cache[i].block = 0;
+		free(extent_cache[i].ext_block);
+		extent_cache[i].ext_block = NULL;
+	}
+}
+
 static struct ext4_extent_header *ext4fs_get_extent_block
 	(struct ext2_data *data, char *buf,
 		struct ext4_extent_header *ext_block,
@@ -1532,6 +1569,7 @@ static struct ext4_extent_header *ext4fs_get_extent_block
 	unsigned long long block;
 	int blksz = EXT2_BLOCK_SIZE(data);
 	int i;
+	unsigned int cache_item;
 
 	while (1) {
 		index = (struct ext4_extent_idx *)(ext_block + 1);
@@ -1554,11 +1592,31 @@ static struct ext4_extent_header *ext4fs_get_extent_block
 		block = le16_to_cpu(index[i].ei_leaf_hi);
 		block = (block << 32) + le32_to_cpu(index[i].ei_leaf_lo);
 
-		if (ext4fs_devread((lbaint_t)block << log2_blksz, 0, blksz,
-				   buf))
-			ext_block = (struct ext4_extent_header *)buf;
-		else
-			return NULL;
+		// check cache, read block from device if not found
+		cache_item = le16_to_cpu(ext_block->eh_depth) - 1;
+		if (cache_item < CONFIG_EXT4_EXTENT_CACHE_SIZE &&
+		    extent_cache[cache_item].block == block) {
+			ext_block = extent_cache[cache_item].ext_block;
+		} else {
+			if (ext4fs_devread((lbaint_t)block << log2_blksz, 0,
+					   blksz, buf))
+				ext_block = (struct ext4_extent_header *)buf;
+			else
+				return NULL;
+			// put in cache
+			if (cache_item < CONFIG_EXT4_EXTENT_CACHE_SIZE) {
+				struct extent_cache_entry *cache_entry =
+				   &extent_cache[cache_item];
+				if (!cache_entry->ext_block)
+					cache_entry->ext_block = zalloc(blksz);
+				if (!cache_entry->ext_block) {
+					printf("ext4 cache alloc failed\n");
+					return NULL;
+				}
+				memcpy(cache_entry->ext_block, buf, blksz);
+				cache_entry->block = block;
+			}
+		}
 	}
 }
 
@@ -2000,6 +2058,7 @@ void ext4fs_close(void)
 	if (ext4fs_root != NULL) {
 		free(ext4fs_root);
 		ext4fs_root = NULL;
+		ext4fs_free_extent_block_cache();
 	}
 
 	ext4fs_reinit_global();
@@ -2376,6 +2435,7 @@ int ext4fs_mount(unsigned part_length)
 
 	ext4fs_root = data;
 
+	ext4fs_init_extent_block_cache();
 	return 1;
 fail:
 	printf("Failed to mount ext2 filesystem...\n");