staging: erofs: introduce VLE decompression support

This patch introduces the basic in-place VLE decompression
implementation for the erofs file system.

Compared with fixed-sized input compression, it implements
what we call 'the variable-length extent compression' which
specifies the same output size for each compression block
to make the full use of IO bandwidth (which means almost
all data from block device can be directly used for decomp-
ression), improve the real (rather than just via data caching,
which costs more memory) random read and keep the relatively
lower compression ratios (it saves more storage space than
fixed-sized input compression which is also configured with
the same input block size), as illustrated below:

        |---  variable-length extent ---|------ VLE ------|---  VLE ---|
         /> clusterofs                  /> clusterofs     /> clusterofs /> clusterofs
   ++---|-------++-----------++---------|-++-----------++-|---------++-|
...||   |       ||           ||         | ||           || |         || | ... original data
   ++---|-------++-----------++---------|-++-----------++-|---------++-|
   ++->cluster<-++->cluster<-++->cluster<-++->cluster<-++->cluster<-++
        size         size         size         size         size
         \                             /                 /            /
          \                      /              /            /
           \               /            /            /
            ++-----------++-----------++-----------++
        ... ||           ||           ||           || ... compressed clusters
            ++-----------++-----------++-----------++
            ++->cluster<-++->cluster<-++->cluster<-++
                 size         size         size

The main point of 'in-place' refers to the decompression mode:
Instead of allocating independent compressed pages and data
structures, it reuses the allocated file cache pages at most
to store its compressed data and the corresponding pagevec in
a time-sharing approach by default, which will be useful for
low memory scenario.

In the end, unlike the other filesystems with (de)compression
support using a relatively large compression block size, which
reads and decompresses >= 128KB at once, and gains a more
good-looking random read (In fact it collects small random reads
into large sequential reads and caches all decompressed data
in memory, but it is unacceptable especially for embedded devices
with limited memory, and it is not the real random read), we
select a universal small-sized 4KB compressed cluster, which is
the smallest page size for most architectures, and all compressed
clusters can be read and decompressed independently, which ensures
random read number for all use cases.

Signed-off-by: Gao Xiang <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

drivers/staging/erofs/inode.c

@@ -210,7 +210,12 @@ static int fill_inode(struct inode *inode, int isdir)
 		}
 
 		if (is_inode_layout_compression(inode)) {
+#ifdef CONFIG_EROFS_FS_ZIP
+			inode->i_mapping->a_ops =
+				&z_erofs_vle_normalaccess_aops;
+#else
 			err = -ENOTSUPP;
+#endif
 			goto out_unlock;
 		}
 

drivers/staging/erofs/internal.h

@@ -262,6 +262,9 @@ static inline void erofs_workstation_cleanup_all(struct super_block *sb)
 #ifdef CONFIG_EROFS_FS_ZIP
 /* hard limit of pages per compressed cluster */
 #define Z_EROFS_CLUSTER_MAX_PAGES       (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
+
+/* page count of a compressed cluster */
+#define erofs_clusterpages(sbi)         ((1 << (sbi)->clusterbits) / PAGE_SIZE)
 #endif
 
 typedef u64 erofs_off_t;
@@ -340,6 +343,9 @@ extern const struct inode_operations erofs_dir_iops;
 extern const struct file_operations erofs_dir_fops;
 
 extern const struct address_space_operations erofs_raw_access_aops;
+#ifdef CONFIG_EROFS_FS_ZIP
+extern const struct address_space_operations z_erofs_vle_normalaccess_aops;
+#endif
 
 /*
  * Logical to physical block mapping, used by erofs_map_blocks()

drivers/staging/erofs/super.c

@@ -115,6 +115,13 @@ static int superblock_read(struct super_block *sb)
 	sbi->xattr_blkaddr = le32_to_cpu(layout->xattr_blkaddr);
 #endif
 	sbi->islotbits = ffs(sizeof(struct erofs_inode_v1)) - 1;
+#ifdef CONFIG_EROFS_FS_ZIP
+	sbi->clusterbits = 12;
+
+	if (1 << (sbi->clusterbits - 12) > Z_EROFS_CLUSTER_MAX_PAGES)
+		errln("clusterbits %u is not supported on this kernel",
+			sbi->clusterbits);
+#endif
 
 	sbi->root_nid = le16_to_cpu(layout->root_nid);
 	sbi->inos = le64_to_cpu(layout->inos);
@@ -441,6 +448,11 @@ static struct file_system_type erofs_fs_type = {
 };
 MODULE_ALIAS_FS("erofs");
 
+#ifdef CONFIG_EROFS_FS_ZIP
+extern int z_erofs_init_zip_subsystem(void);
+extern void z_erofs_exit_zip_subsystem(void);
+#endif
+
 static int __init erofs_module_init(void)
 {
 	int err;
@@ -456,6 +468,12 @@ static int __init erofs_module_init(void)
 	if (err)
 		goto shrinker_err;
 
+#ifdef CONFIG_EROFS_FS_ZIP
+	err = z_erofs_init_zip_subsystem();
+	if (err)
+		goto zip_err;
+#endif
+
 	err = register_filesystem(&erofs_fs_type);
 	if (err)
 		goto fs_err;
@@ -464,6 +482,10 @@ static int __init erofs_module_init(void)
 	return 0;
 
 fs_err:
+#ifdef CONFIG_EROFS_FS_ZIP
+	z_erofs_exit_zip_subsystem();
+zip_err:
+#endif
 	unregister_shrinker(&erofs_shrinker_info);
 shrinker_err:
 	erofs_exit_inode_cache();
@@ -474,6 +496,9 @@ static int __init erofs_module_init(void)
 static void __exit erofs_module_exit(void)
 {
 	unregister_filesystem(&erofs_fs_type);
+#ifdef CONFIG_EROFS_FS_ZIP
+	z_erofs_exit_zip_subsystem();
+#endif
 	unregister_shrinker(&erofs_shrinker_info);
 	erofs_exit_inode_cache();
 	infoln("successfully finalize erofs");