mirror of
https://github.com/torvalds/linux.git
synced 2026-05-12 16:18:45 +02:00
Commit7d6899fb69("ovl: fsync after metadata copy-up") was done to fix durability of overlayfs copy up on an upper filesystem which does not enforce ordering on storing of metadata changes (e.g. ubifs). In an earlier revision of the regressing commit by Lei Lv, the metadata fsync behavior was opt-in via a new "fsync=strict" mount option. We were hoping that the opt-in mount option could be avoided, so the change was only made to depend on metacopy=off, in the hope of not hurting performance of metadata heavy workloads, which are more likely to be using metacopy=on. This hope was proven wrong by a performance regression report from Google COS workload after upgrade to kernel 6.12. This is an adaptation of Lei's original "fsync=strict" mount option to the existing upstream code. The new mount option is mutually exclusive with the "volatile" mount option, so the latter is now an alias to the "fsync=volatile" mount option. Reported-by: Chenglong Tang <chenglongtang@google.com> Closes: https://lore.kernel.org/linux-unionfs/CAOdxtTadAFH01Vui1FvWfcmQ8jH1O45owTzUcpYbNvBxnLeM7Q@mail.gmail.com/ Link: https://lore.kernel.org/linux-unionfs/CAOQ4uxgKC1SgjMWre=fUb00v8rxtd6sQi-S+dxR8oDzAuiGu8g@mail.gmail.com/ Fixes:7d6899fb69("ovl: fsync after metadata copy-up") Depends:50e638beb6("ovl: Use str_on_off() helper in ovl_show_options()") Cc: stable@vger.kernel.org # v6.12+ Signed-off-by: Fei Lv <feilv@asrmicro.com> Signed-off-by: Amir Goldstein <amir73il@gmail.com>
194 lines
4.6 KiB
C
194 lines
4.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
*
|
|
* Copyright (C) 2011 Novell Inc.
|
|
* Copyright (C) 2016 Red Hat, Inc.
|
|
*/
|
|
|
|
struct ovl_config {
|
|
char *upperdir;
|
|
char *workdir;
|
|
char **lowerdirs;
|
|
bool default_permissions;
|
|
int redirect_mode;
|
|
int verity_mode;
|
|
bool index;
|
|
int uuid;
|
|
bool nfs_export;
|
|
int xino;
|
|
bool metacopy;
|
|
bool userxattr;
|
|
int fsync_mode;
|
|
};
|
|
|
|
struct ovl_sb {
|
|
struct super_block *sb;
|
|
dev_t pseudo_dev;
|
|
/* Unusable (conflicting) uuid */
|
|
bool bad_uuid;
|
|
/* Used as a lower layer (but maybe also as upper) */
|
|
bool is_lower;
|
|
};
|
|
|
|
struct ovl_layer {
|
|
/* ovl_free_fs() relies on @mnt being the first member! */
|
|
struct vfsmount *mnt;
|
|
/* Trap in ovl inode cache */
|
|
struct inode *trap;
|
|
struct ovl_sb *fs;
|
|
/* Index of this layer in fs root (upper idx == 0) */
|
|
int idx;
|
|
/* One fsid per unique underlying sb (upper fsid == 0) */
|
|
int fsid;
|
|
/* xwhiteouts were found on this layer */
|
|
bool has_xwhiteouts;
|
|
};
|
|
|
|
struct ovl_path {
|
|
const struct ovl_layer *layer;
|
|
struct dentry *dentry;
|
|
};
|
|
|
|
struct ovl_entry {
|
|
unsigned int __numlower;
|
|
struct ovl_path __lowerstack[] __counted_by(__numlower);
|
|
};
|
|
|
|
/* private information held for overlayfs's superblock */
|
|
struct ovl_fs {
|
|
unsigned int numlayer;
|
|
/* Number of unique fs among layers including upper fs */
|
|
unsigned int numfs;
|
|
/* Number of data-only lower layers */
|
|
unsigned int numdatalayer;
|
|
struct ovl_layer *layers;
|
|
struct ovl_sb *fs;
|
|
/* workbasedir is the path at workdir= mount option */
|
|
struct dentry *workbasedir;
|
|
/* workdir is the 'work' or 'index' directory under workbasedir */
|
|
struct dentry *workdir;
|
|
long namelen;
|
|
/* pathnames of lower and upper dirs, for show_options */
|
|
struct ovl_config config;
|
|
/* creds of process who forced instantiation of super block */
|
|
const struct cred *creator_cred;
|
|
bool tmpfile;
|
|
bool noxattr;
|
|
bool nofh;
|
|
/* Did we take the inuse lock? */
|
|
bool upperdir_locked;
|
|
bool workdir_locked;
|
|
/* Traps in ovl inode cache */
|
|
struct inode *workbasedir_trap;
|
|
struct inode *workdir_trap;
|
|
/* -1: disabled, 0: same fs, 1..32: number of unused ino bits */
|
|
int xino_mode;
|
|
/* For allocation of non-persistent inode numbers */
|
|
atomic_long_t last_ino;
|
|
/* Shared whiteout cache */
|
|
struct dentry *whiteout;
|
|
bool no_shared_whiteout;
|
|
struct mutex whiteout_lock;
|
|
/* r/o snapshot of upperdir sb's only taken on volatile mounts */
|
|
errseq_t errseq;
|
|
bool casefold;
|
|
};
|
|
|
|
/* Number of lower layers, not including data-only layers */
|
|
static inline unsigned int ovl_numlowerlayer(struct ovl_fs *ofs)
|
|
{
|
|
return ofs->numlayer - ofs->numdatalayer - 1;
|
|
}
|
|
|
|
static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs)
|
|
{
|
|
return ofs->layers[0].mnt;
|
|
}
|
|
|
|
static inline struct mnt_idmap *ovl_upper_mnt_idmap(struct ovl_fs *ofs)
|
|
{
|
|
return mnt_idmap(ovl_upper_mnt(ofs));
|
|
}
|
|
|
|
extern struct file_system_type ovl_fs_type;
|
|
|
|
static inline struct ovl_fs *OVL_FS(struct super_block *sb)
|
|
{
|
|
if (IS_ENABLED(CONFIG_OVERLAY_FS_DEBUG))
|
|
WARN_ON_ONCE(sb->s_type != &ovl_fs_type);
|
|
|
|
return (struct ovl_fs *)sb->s_fs_info;
|
|
}
|
|
|
|
static inline unsigned int ovl_numlower(struct ovl_entry *oe)
|
|
{
|
|
return oe ? oe->__numlower : 0;
|
|
}
|
|
|
|
static inline struct ovl_path *ovl_lowerstack(struct ovl_entry *oe)
|
|
{
|
|
return ovl_numlower(oe) ? oe->__lowerstack : NULL;
|
|
}
|
|
|
|
static inline struct ovl_path *ovl_lowerpath(struct ovl_entry *oe)
|
|
{
|
|
return ovl_lowerstack(oe);
|
|
}
|
|
|
|
static inline struct ovl_path *ovl_lowerdata(struct ovl_entry *oe)
|
|
{
|
|
struct ovl_path *lowerstack = ovl_lowerstack(oe);
|
|
|
|
return lowerstack ? &lowerstack[oe->__numlower - 1] : NULL;
|
|
}
|
|
|
|
/* May return NULL if lazy lookup of lowerdata is needed */
|
|
static inline struct dentry *ovl_lowerdata_dentry(struct ovl_entry *oe)
|
|
{
|
|
struct ovl_path *lowerdata = ovl_lowerdata(oe);
|
|
|
|
return lowerdata ? READ_ONCE(lowerdata->dentry) : NULL;
|
|
}
|
|
|
|
/* private information held for every overlayfs dentry */
|
|
static inline unsigned long *OVL_E_FLAGS(struct dentry *dentry)
|
|
{
|
|
return (unsigned long *) &dentry->d_fsdata;
|
|
}
|
|
|
|
struct ovl_inode {
|
|
union {
|
|
struct ovl_dir_cache *cache; /* directory */
|
|
const char *lowerdata_redirect; /* regular file */
|
|
};
|
|
const char *redirect;
|
|
u64 version;
|
|
unsigned long flags;
|
|
struct inode vfs_inode;
|
|
struct dentry *__upperdentry;
|
|
struct ovl_entry *oe;
|
|
|
|
/* synchronize copy up and more */
|
|
struct mutex lock;
|
|
};
|
|
|
|
static inline struct ovl_inode *OVL_I(struct inode *inode)
|
|
{
|
|
return container_of(inode, struct ovl_inode, vfs_inode);
|
|
}
|
|
|
|
static inline struct ovl_entry *OVL_I_E(struct inode *inode)
|
|
{
|
|
return inode ? OVL_I(inode)->oe : NULL;
|
|
}
|
|
|
|
static inline struct ovl_entry *OVL_E(struct dentry *dentry)
|
|
{
|
|
return OVL_I_E(d_inode(dentry));
|
|
}
|
|
|
|
static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
|
|
{
|
|
return READ_ONCE(oi->__upperdentry);
|
|
}
|