@@ -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 ondemand-read"
+ depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y)
+ default n
+ help
+ EROFS is mounted from data blobs and on-demand read semantics is
+ implemented 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 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022, Alibaba Cloud
+ */
+#include <linux/fscache.h>
+#include "internal.h"
+
+int erofs_fscache_register_fs(struct super_block *sb)
+{
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+ struct fscache_volume *volume;
+ char *name;
+ int ret = 0;
+
+ name = kasprintf(GFP_KERNEL, "erofs,%s", sbi->opt.fsid);
+ if (!name)
+ return -ENOMEM;
+
+ volume = fscache_acquire_volume(name, NULL, NULL, 0);
+ if (IS_ERR_OR_NULL(volume)) {
+ erofs_err(sb, "failed to register volume for %s", name);
+ ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP;
+ volume = NULL;
+ }
+
+ sbi->volume = volume;
+ kfree(name);
+ return ret;
+}
+
+void erofs_fscache_unregister_fs(struct super_block *sb)
+{
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+ fscache_relinquish_volume(sbi->volume, NULL, false);
+ sbi->volume = NULL;
+}
@@ -74,6 +74,7 @@ struct erofs_mount_opts {
unsigned int max_sync_decompress_pages;
#endif
unsigned int mount_opt;
+ char *fsid;
};
struct erofs_dev_context {
@@ -146,6 +147,9 @@ struct erofs_sb_info {
/* sysfs support */
struct kobject s_kobj; /* /sys/fs/erofs/<devname> */
struct completion s_kobj_unregister;
+
+ /* fscache support */
+ struct fscache_volume *volume;
};
#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
@@ -618,6 +622,15 @@ 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_fscache_register_fs(struct super_block *sb);
+void erofs_fscache_unregister_fs(struct super_block *sb);
+#else
+static inline int erofs_fscache_register_fs(struct super_block *sb) { return 0; }
+static inline void erofs_fscache_unregister_fs(struct super_block *sb) {}
+#endif
+
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
#endif /* __EROFS_INTERNAL_H */
@@ -601,6 +601,12 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
sbi->devs = ctx->devs;
ctx->devs = NULL;
+ if (erofs_is_fscache_mode(sb)) {
+ err = erofs_fscache_register_fs(sb);
+ if (err)
+ return err;
+ }
+
err = erofs_read_superblock(sb);
if (err)
return err;
@@ -757,6 +763,7 @@ static void erofs_kill_sb(struct super_block *sb)
erofs_free_dev_context(sbi->devs);
fs_put_dax(sbi->dax_dev);
+ erofs_fscache_unregister_fs(sb);
kfree(sbi);
sb->s_fs_info = NULL;
}
A new fscache based mode is going to be introduced for erofs, in which case on-demand read semantics is implemented through fscache. As the first step, register fscache volume for each erofs filesystem. That means, data blobs can not be shared among erofs filesystems. In the following iteration, we are going to introduce the domain semantics, in which case several erofs filesystems can belong to one domain, and data blobs can be shared among these erofs filesystems of one domain. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> --- fs/erofs/Kconfig | 10 ++++++++++ fs/erofs/Makefile | 1 + fs/erofs/fscache.c | 37 +++++++++++++++++++++++++++++++++++++ fs/erofs/internal.h | 13 +++++++++++++ fs/erofs/super.c | 7 +++++++ 5 files changed, 68 insertions(+) create mode 100644 fs/erofs/fscache.c