[PATCH V1 2/5] erofs: introduce fscache-based domain

From: Jia Zhu
Date: Thu Sep 01 2022 - 23:48:54 EST


A new fscache-based shared domain mode is going to be introduced for
erofs. In which case, same data blobs in same domain will be shared
and reused to reduce on-disk space usage.

As the first step, we use pseudo mnt to manage and maintain domain's
lifecycle.

The implementation of sharing blobs will be introduced in subsequent
patches.

Signed-off-by: Jia Zhu <zhujia.zj@xxxxxxxxxxxxx>
---
fs/erofs/fscache.c | 103 +++++++++++++++++++++++++++++++++++++++++++-
fs/erofs/internal.h | 19 +++++++-
fs/erofs/super.c | 52 ++++++++++++++++------
3 files changed, 159 insertions(+), 15 deletions(-)

diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 8e01d89c3319..3238813ed520 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -1,10 +1,17 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2022, Alibaba Cloud
+ * Copyright (C) 2022, Bytedance Inc. All rights reserved.
*/
+#include <linux/pseudo_fs.h>
+#include <linux/fs_context.h>
+#include <linux/magic.h>
#include <linux/fscache.h>
#include "internal.h"

+static DEFINE_MUTEX(erofs_domain_list_lock);
+static LIST_HEAD(erofs_domain_list);
+
static struct netfs_io_request *erofs_fscache_alloc_request(struct address_space *mapping,
loff_t start, size_t len)
{
@@ -417,6 +424,92 @@ const struct address_space_operations erofs_fscache_access_aops = {
.readahead = erofs_fscache_readahead,
};

+static void erofs_fscache_domain_get(struct erofs_domain *domain)
+{
+ if (!domain)
+ return;
+ refcount_inc(&domain->ref);
+}
+
+static void erofs_fscache_domain_put(struct erofs_domain *domain)
+{
+ if (!domain)
+ return;
+ if (refcount_dec_and_test(&domain->ref)) {
+ fscache_relinquish_volume(domain->volume, NULL, false);
+ mutex_lock(&erofs_domain_list_lock);
+ list_del(&domain->list);
+ mutex_unlock(&erofs_domain_list_lock);
+ kern_unmount(domain->mnt);
+ kfree(domain->domain_id);
+ kfree(domain);
+ }
+}
+
+static int erofs_fscache_init_domain(struct super_block *sb)
+{
+ int err;
+ struct erofs_domain *domain;
+ struct vfsmount *pseudo_mnt;
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+ domain = kzalloc(sizeof(struct erofs_domain), GFP_KERNEL);
+ if (!domain)
+ return -ENOMEM;
+
+ domain->domain_id = kstrdup(sbi->opt.domain_id, GFP_KERNEL);
+ if (!domain->domain_id) {
+ kfree(domain);
+ return -ENOMEM;
+ }
+ sbi->domain = domain;
+ pseudo_mnt = kern_mount(&erofs_fs_type);
+ if (IS_ERR(pseudo_mnt)) {
+ err = PTR_ERR(pseudo_mnt);
+ goto out;
+ }
+ err = erofs_fscache_register_fs(sb);
+ if (err) {
+ kern_unmount(pseudo_mnt);
+ goto out;
+ }
+
+ domain->mnt = pseudo_mnt;
+ domain->volume = sbi->volume;
+ refcount_set(&domain->ref, 1);
+ mutex_init(&domain->mutex);
+ pseudo_mnt->mnt_sb->s_fs_info = domain;
+ list_add(&domain->list, &erofs_domain_list);
+ return 0;
+out:
+ kfree(domain->domain_id);
+ kfree(domain);
+ sbi->domain = NULL;
+ return err;
+}
+
+int erofs_fscache_register_domain(struct super_block *sb)
+{
+ int err;
+ struct erofs_domain *domain;
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+ mutex_lock(&erofs_domain_list_lock);
+ list_for_each_entry(domain, &erofs_domain_list, list) {
+ if (!strcmp(domain->domain_id, sbi->opt.domain_id)) {
+ erofs_fscache_domain_get(domain);
+ sbi->domain = domain;
+ sbi->volume = domain->volume;
+ mutex_unlock(&erofs_domain_list_lock);
+ return 0;
+ }
+ }
+ err = erofs_fscache_init_domain(sb);
+ mutex_unlock(&erofs_domain_list_lock);
+
+ return err;
+}
+
int erofs_fscache_register_cookie(struct super_block *sb,
struct erofs_fscache **fscache,
char *name, bool need_inode)
@@ -495,7 +588,8 @@ int erofs_fscache_register_fs(struct super_block *sb)
char *name;
int ret = 0;

- name = kasprintf(GFP_KERNEL, "erofs,%s", sbi->opt.fsid);
+ name = kasprintf(GFP_KERNEL, "erofs,%s",
+ sbi->domain ? sbi->domain->domain_id : sbi->opt.fsid);
if (!name)
return -ENOMEM;

@@ -515,6 +609,11 @@ void erofs_fscache_unregister_fs(struct super_block *sb)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);

- fscache_relinquish_volume(sbi->volume, NULL, false);
+ if (sbi->domain)
+ erofs_fscache_domain_put(sbi->domain);
+ else
+ fscache_relinquish_volume(sbi->volume, NULL, false);
+
sbi->volume = NULL;
+ sbi->domain = NULL;
}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index fe435d077f1a..7240a2acaa5c 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -99,6 +99,15 @@ struct erofs_sb_lz4_info {
u16 max_pclusterblks;
};

+struct erofs_domain {
+ refcount_t ref;
+ struct mutex mutex;
+ struct vfsmount *mnt;
+ struct list_head list;
+ struct fscache_volume *volume;
+ char *domain_id;
+};
+
struct erofs_fscache {
struct fscache_cookie *cookie;
struct inode *inode;
@@ -158,6 +167,7 @@ struct erofs_sb_info {
/* fscache support */
struct fscache_volume *volume;
struct erofs_fscache *s_fscache;
+ struct erofs_domain *domain;
};

#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
@@ -394,6 +404,7 @@ struct page *erofs_grab_cache_page_nowait(struct address_space *mapping,
}

extern const struct super_operations erofs_sops;
+extern struct file_system_type erofs_fs_type;

extern const struct address_space_operations erofs_raw_access_aops;
extern const struct address_space_operations z_erofs_aops;
@@ -610,6 +621,7 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb,
#ifdef CONFIG_EROFS_FS_ONDEMAND
int erofs_fscache_register_fs(struct super_block *sb);
void erofs_fscache_unregister_fs(struct super_block *sb);
+int erofs_fscache_register_domain(struct super_block *sb);

int erofs_fscache_register_cookie(struct super_block *sb,
struct erofs_fscache **fscache,
@@ -620,10 +632,15 @@ extern const struct address_space_operations erofs_fscache_access_aops;
#else
static inline int erofs_fscache_register_fs(struct super_block *sb)
{
- return 0;
+ return -EOPNOTSUPP;
}
static inline void erofs_fscache_unregister_fs(struct super_block *sb) {}

+static inline int erofs_fscache_register_domain(const struct super_block *sb)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int erofs_fscache_register_cookie(struct super_block *sb,
struct erofs_fscache **fscache,
char *name, bool need_inode)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index d01109069c6b..a3ff87e45f2c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -688,6 +688,13 @@ static const struct export_operations erofs_export_ops = {
.get_parent = erofs_get_parent,
};

+static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc)
+{
+ static const struct tree_descr empty_descr = {""};
+
+ return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr);
+}
+
static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
@@ -715,12 +722,17 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_blocksize = EROFS_BLKSIZ;
sb->s_blocksize_bits = LOG_BLOCK_SIZE;

- err = erofs_fscache_register_fs(sb);
- if (err)
- return err;
-
- err = erofs_fscache_register_cookie(sb, &sbi->s_fscache,
- sbi->opt.fsid, true);
+ if (sbi->opt.domain_id) {
+ err = erofs_fscache_register_domain(sb);
+ if (err)
+ return err;
+ } else {
+ err = erofs_fscache_register_fs(sb);
+ if (err)
+ return err;
+ err = erofs_fscache_register_cookie(sb, &sbi->s_fscache,
+ sbi->opt.fsid, true);
+ }
if (err)
return err;

@@ -798,8 +810,12 @@ static int erofs_fc_get_tree(struct fs_context *fc)
{
struct erofs_fs_context *ctx = fc->fs_private;

- if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->opt.fsid)
- return get_tree_nodev(fc, erofs_fc_fill_super);
+ if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND)) {
+ if (!ctx && fc->sb_flags & SB_KERNMOUNT)
+ return get_tree_nodev(fc, erofs_fc_fill_pseudo_super);
+ if (ctx->opt.fsid)
+ return get_tree_nodev(fc, erofs_fc_fill_super);
+ }

return get_tree_bdev(fc, erofs_fc_fill_super);
}
@@ -849,6 +865,9 @@ static void erofs_fc_free(struct fs_context *fc)
{
struct erofs_fs_context *ctx = fc->fs_private;

+ if (!ctx)
+ return;
+
erofs_free_dev_context(ctx->devs);
kfree(ctx->opt.fsid);
kfree(ctx->opt.domain_id);
@@ -864,8 +883,12 @@ static const struct fs_context_operations erofs_context_ops = {

static int erofs_init_fs_context(struct fs_context *fc)
{
- struct erofs_fs_context *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ struct erofs_fs_context *ctx;

+ if (fc->sb_flags & SB_KERNMOUNT)
+ goto out;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
@@ -878,6 +901,7 @@ static int erofs_init_fs_context(struct fs_context *fc)
idr_init(&ctx->devs->tree);
init_rwsem(&ctx->devs->rwsem);
erofs_default_options(ctx);
+out:
fc->ops = &erofs_context_ops;
return 0;
}
@@ -892,6 +916,10 @@ static void erofs_kill_sb(struct super_block *sb)

WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);

+ if (sb->s_flags & SB_KERNMOUNT) {
+ kill_litter_super(sb);
+ return;
+ }
if (erofs_is_fscache_mode(sb))
generic_shutdown_super(sb);
else
@@ -916,8 +944,8 @@ static void erofs_put_super(struct super_block *sb)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);

- DBG_BUGON(!sbi);
-
+ if (!sbi)
+ return;
erofs_unregister_sysfs(sb);
erofs_shrinker_unregister(sb);
#ifdef CONFIG_EROFS_FS_ZIP
@@ -927,7 +955,7 @@ static void erofs_put_super(struct super_block *sb)
erofs_fscache_unregister_cookie(&sbi->s_fscache);
}

-static struct file_system_type erofs_fs_type = {
+struct file_system_type erofs_fs_type = {
.owner = THIS_MODULE,
.name = "erofs",
.init_fs_context = erofs_init_fs_context,
--
2.20.1