@@ -98,3 +98,13 @@ config EROFS_FS_ZIP_LZMA
systems will be readable without selecting this option.
If unsure, say N.
+
+config EROFS_FS_ONDEMAND
+ bool "EROFS fscache-based ondeand-read"
+ depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE && CACHEFILES || EROFS_FS=y && FSCACHE=y && CACHEFILES=y)
+ default n
+ help
+ EROFS is mounted from data blob files and implement on-demand read
+ semantics through fscache.
+
+ If unsure, say N.
@@ -5,3 +5,4 @@ erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o
erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o
erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o
erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o
+erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o
new file mode 100644
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022, Alibaba Cloud
+ */
+#include <linux/fscache.h>
+#include "internal.h"
+
+static struct fscache_volume *volume;
+
+int __init erofs_init_fscache(void)
+{
+ volume = fscache_acquire_volume("erofs", NULL, NULL, 0);
+ if (!volume)
+ return -EINVAL;
+
+ return 0;
+}
+
+void erofs_exit_fscache(void)
+{
+ fscache_relinquish_volume(volume, NULL, false);
+}
@@ -616,6 +616,15 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb,
}
#endif /* !CONFIG_EROFS_FS_ZIP */
+/* fscache.c */
+#ifdef CONFIG_EROFS_FS_ONDEMAND
+int erofs_init_fscache(void);
+void erofs_exit_fscache(void);
+#else
+static inline int erofs_init_fscache(void) { return 0; }
+static inline void erofs_exit_fscache(void) {}
+#endif
+
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
#endif /* __EROFS_INTERNAL_H */
@@ -814,6 +814,10 @@ static int __init erofs_module_init(void)
if (err)
goto sysfs_err;
+ err = erofs_init_fscache();
+ if (err)
+ goto fscache_err;
+
err = register_filesystem(&erofs_fs_type);
if (err)
goto fs_err;
@@ -821,6 +825,8 @@ static int __init erofs_module_init(void)
return 0;
fs_err:
+ erofs_exit_fscache();
+fscache_err:
erofs_exit_sysfs();
sysfs_err:
z_erofs_exit_zip_subsystem();
@@ -841,6 +847,7 @@ static void __exit erofs_module_exit(void)
/* Ensure all RCU free inodes / pclusters are safe to be destroyed. */
rcu_barrier();
+ erofs_exit_fscache();
erofs_exit_sysfs();
z_erofs_exit_zip_subsystem();
z_erofs_lzma_exit();
All erofs instances will share one global fscache volume. In this using scenario, one erofs instance could be mounted from one (or multiple) blob files instead of blkdev. The number of blob files that each erofs instance could correspond to is limited. For example, when used for container image distribution, one erofs instance used for container image for node.js will correspond to ~20 blob files in total. Thus in densely employed environment, there could be as many as hundreds of containers and thus thousands of fscache cookies under one fscache volume. Then as for cachefiles backend, the hash table managing all cookies under one volume contains 32K slots. Thus the hashing functionality shall scale well in this case. Besides, cachefiles backend will scatter backing files under 256 fan sub-directoris, and thus the scalability of looking up backing files shall also not be an issue. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> --- fs/erofs/Kconfig | 10 ++++++++++ fs/erofs/Makefile | 1 + fs/erofs/fscache.c | 22 ++++++++++++++++++++++ fs/erofs/internal.h | 9 +++++++++ fs/erofs/super.c | 7 +++++++ 5 files changed, 49 insertions(+) create mode 100644 fs/erofs/fscache.c