original_kernel/fs/overlayfs/ovl_entry.h

197 lines
4.6 KiB
C
Raw Normal View History

/* 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;
ovl: add support for "xino" mount and config options With mount option "xino=on", mounter declares that there are enough free high bits in underlying fs to hold the layer fsid. If overlayfs does encounter underlying inodes using the high xino bits reserved for layer fsid, a warning will be emitted and the original inode number will be used. The mount option name "xino" goes after a similar meaning mount option of aufs, but in overlayfs case, the mapping is stateless. An example for a use case of "xino=on" is when upper/lower is on an xfs filesystem. xfs uses 64bit inode numbers, but it currently never uses the upper 8bit for inode numbers exposed via stat(2) and that is not likely to change in the future without user opting-in for a new xfs feature. The actual number of unused upper bit is much larger and determined by the xfs filesystem geometry (64 - agno_log - agblklog - inopblog). That means that for all practical purpose, there are enough unused bits in xfs inode numbers for more than OVL_MAX_STACK unique fsid's. Another use case of "xino=on" is when upper/lower is on tmpfs. tmpfs inode numbers are allocated sequentially since boot, so they will practially never use the high inode number bits. For compatibility with applications that expect 32bit inodes, the feature can be disabled with "xino=off". The option "xino=auto" automatically detects underlying filesystem that use 32bit inodes and enables the feature. The Kconfig option OVERLAY_FS_XINO_AUTO and module parameter of the same name, determine if the default mode for overlayfs mount is "xino=auto" or "xino=off". Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2018-03-29 14:08:18 +08:00
int xino;
bool metacopy;
bool userxattr;
ovl: provide a mount option "volatile" Container folks are complaining that dnf/yum issues too many sync while installing packages and this slows down the image build. Build requirement is such that they don't care if a node goes down while build was still going on. In that case, they will simply throw away unfinished layer and start new build. So they don't care about syncing intermediate state to the disk and hence don't want to pay the price associated with sync. So they are asking for mount options where they can disable sync on overlay mount point. They primarily seem to have two use cases. - For building images, they will mount overlay with nosync and then sync upper layer after unmounting overlay and reuse upper as lower for next layer. - For running containers, they don't seem to care about syncing upper layer because if node goes down, they will simply throw away upper layer and create a fresh one. So this patch provides a mount option "volatile" which disables all forms of sync. Now it is caller's responsibility to throw away upper if system crashes or shuts down and start fresh. With "volatile", I am seeing roughly 20% speed up in my VM where I am just installing emacs in an image. Installation time drops from 31 seconds to 25 seconds when nosync option is used. This is for the case of building on top of an image where all packages are already cached. That way I take out the network operations latency out of the measurement. Giuseppe is also looking to cut down on number of iops done on the disk. He is complaining that often in cloud their VMs are throttled if they cross the limit. This option can help them where they reduce number of iops (by cutting down on frequent sync and writebacks). Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2020-09-01 02:15:29 +08:00
bool ovl_volatile;
};
struct ovl_sb {
struct super_block *sb;
dev_t pseudo_dev;
ovl: fix lookup failure on multi lower squashfs In the past, overlayfs required that lower fs have non null uuid in order to support nfs export and decode copy up origin file handles. Commit 9df085f3c9a2 ("ovl: relax requirement for non null uuid of lower fs") relaxed this requirement for nfs export support, as long as uuid (even if null) is unique among all lower fs. However, said commit unintentionally also relaxed the non null uuid requirement for decoding copy up origin file handles, regardless of the unique uuid requirement. Amend this mistake by disabling decoding of copy up origin file handle from lower fs with a conflicting uuid. We still encode copy up origin file handles from those fs, because file handles like those already exist in the wild and because they might provide useful information in the future. There is an unhandled corner case described by Miklos this way: - two filesystems, A and B, both have null uuid - upper layer is on A - lower layer 1 is also on A - lower layer 2 is on B In this case bad_uuid won't be set for B, because the check only involves the list of lower fs. Hence we'll try to decode a layer 2 origin on layer 1 and fail. We will deal with this corner case later. Reported-by: Colin Ian King <colin.king@canonical.com> Tested-by: Colin Ian King <colin.king@canonical.com> Link: https://lore.kernel.org/lkml/20191106234301.283006-1-colin.king@canonical.com/ Fixes: 9df085f3c9a2 ("ovl: relax requirement for non null uuid ...") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-11-15 04:28:41 +08:00
/* 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;
ovl: detect overlapping layers Overlapping overlay layers are not supported and can cause unexpected behavior, but overlayfs does not currently check or warn about these configurations. User is not supposed to specify the same directory for upper and lower dirs or for different lower layers and user is not supposed to specify directories that are descendants of each other for overlay layers, but that is exactly what this zysbot repro did: https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000 Moving layer root directories into other layers while overlayfs is mounted could also result in unexpected behavior. This commit places "traps" in the overlay inode hash table. Those traps are dummy overlay inodes that are hashed by the layers root inodes. On mount, the hash table trap entries are used to verify that overlay layers are not overlapping. While at it, we also verify that overlay layers are not overlapping with directories "in-use" by other overlay instances as upperdir/workdir. On lookup, the trap entries are used to verify that overlay layers root inodes have not been moved into other layers after mount. Some examples: $ ./run --ov --samefs -s ... ( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt mount -o bind base/lower lower mount -o bind base/upper upper mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w) $ umount mnt $ mount -t overlay none mnt ... -o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w [ 94.434900] overlayfs: overlapping upperdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w [ 151.350132] overlayfs: conflicting lowerdir path mount: none is already mounted or mnt busy $ mount -t overlay none mnt ... -o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w [ 201.205045] overlayfs: overlapping lowerdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w $ mv base/upper/0/ base/lower/ $ find mnt/0 mnt/0 mnt/0/w find: 'mnt/0/w/work': Too many levels of symbolic links find: 'mnt/0/u': Too many levels of symbolic links Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 22:42:08 +08:00
/* 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[];
};
/* 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;
ovl: detect overlapping layers Overlapping overlay layers are not supported and can cause unexpected behavior, but overlayfs does not currently check or warn about these configurations. User is not supposed to specify the same directory for upper and lower dirs or for different lower layers and user is not supposed to specify directories that are descendants of each other for overlay layers, but that is exactly what this zysbot repro did: https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000 Moving layer root directories into other layers while overlayfs is mounted could also result in unexpected behavior. This commit places "traps" in the overlay inode hash table. Those traps are dummy overlay inodes that are hashed by the layers root inodes. On mount, the hash table trap entries are used to verify that overlay layers are not overlapping. While at it, we also verify that overlay layers are not overlapping with directories "in-use" by other overlay instances as upperdir/workdir. On lookup, the trap entries are used to verify that overlay layers root inodes have not been moved into other layers after mount. Some examples: $ ./run --ov --samefs -s ... ( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt mount -o bind base/lower lower mount -o bind base/upper upper mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w) $ umount mnt $ mount -t overlay none mnt ... -o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w [ 94.434900] overlayfs: overlapping upperdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w [ 151.350132] overlayfs: conflicting lowerdir path mount: none is already mounted or mnt busy $ mount -t overlay none mnt ... -o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w [ 201.205045] overlayfs: overlapping lowerdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w $ mv base/upper/0/ base/lower/ $ find mnt/0 mnt/0 mnt/0/w find: 'mnt/0/w/work': Too many levels of symbolic links find: 'mnt/0/u': Too many levels of symbolic links Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 22:42:08 +08:00
/* Traps in ovl inode cache */
ovl: fix regression caused by overlapping layers detection Once upon a time, commit 2cac0c00a6cd ("ovl: get exclusive ownership on upper/work dirs") in v4.13 added some sanity checks on overlayfs layers. This change caused a docker regression. The root cause was mount leaks by docker, which as far as I know, still exist. To mitigate the regression, commit 85fdee1eef1a ("ovl: fix regression caused by exclusive upper/work dir protection") in v4.14 turned the mount errors into warnings for the default index=off configuration. Recently, commit 146d62e5a586 ("ovl: detect overlapping layers") in v5.2, re-introduced exclusive upper/work dir checks regardless of index=off configuration. This changes the status quo and mount leak related bug reports have started to re-surface. Restore the status quo to fix the regressions. To clarify, index=off does NOT relax overlapping layers check for this ovelayfs mount. index=off only relaxes exclusive upper/work dir checks with another overlayfs mount. To cover the part of overlapping layers detection that used the exclusive upper/work dir checks to detect overlap with self upper/work dir, add a trap also on the work base dir. Link: https://github.com/moby/moby/issues/34672 Link: https://lore.kernel.org/linux-fsdevel/20171006121405.GA32700@veci.piliscsaba.szeredi.hu/ Link: https://github.com/containers/libpod/issues/3540 Fixes: 146d62e5a586 ("ovl: detect overlapping layers") Cc: <stable@vger.kernel.org> # v4.19+ Signed-off-by: Amir Goldstein <amir73il@gmail.com> Tested-by: Colin Walters <walters@verbum.org> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-07-12 20:24:34 +08:00
struct inode *workbasedir_trap;
ovl: detect overlapping layers Overlapping overlay layers are not supported and can cause unexpected behavior, but overlayfs does not currently check or warn about these configurations. User is not supposed to specify the same directory for upper and lower dirs or for different lower layers and user is not supposed to specify directories that are descendants of each other for overlay layers, but that is exactly what this zysbot repro did: https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000 Moving layer root directories into other layers while overlayfs is mounted could also result in unexpected behavior. This commit places "traps" in the overlay inode hash table. Those traps are dummy overlay inodes that are hashed by the layers root inodes. On mount, the hash table trap entries are used to verify that overlay layers are not overlapping. While at it, we also verify that overlay layers are not overlapping with directories "in-use" by other overlay instances as upperdir/workdir. On lookup, the trap entries are used to verify that overlay layers root inodes have not been moved into other layers after mount. Some examples: $ ./run --ov --samefs -s ... ( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt mount -o bind base/lower lower mount -o bind base/upper upper mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w) $ umount mnt $ mount -t overlay none mnt ... -o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w [ 94.434900] overlayfs: overlapping upperdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w [ 151.350132] overlayfs: conflicting lowerdir path mount: none is already mounted or mnt busy $ mount -t overlay none mnt ... -o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w [ 201.205045] overlayfs: overlapping lowerdir path mount: mount overlay on mnt failed: Too many levels of symbolic links $ mount -t overlay none mnt ... -o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w $ mv base/upper/0/ base/lower/ $ find mnt/0 mnt/0 mnt/0/w find: 'mnt/0/w/work': Too many levels of symbolic links find: 'mnt/0/u': Too many levels of symbolic links Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 22:42:08 +08:00
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;
ovl: implement volatile-specific fsync error behaviour Overlayfs's volatile option allows the user to bypass all forced sync calls to the upperdir filesystem. This comes at the cost of safety. We can never ensure that the user's data is intact, but we can make a best effort to expose whether or not the data is likely to be in a bad state. The best way to handle this in the time being is that if an overlayfs's upperdir experiences an error after a volatile mount occurs, that error will be returned on fsync, fdatasync, sync, and syncfs. This is contradictory to the traditional behaviour of VFS which fails the call once, and only raises an error if a subsequent fsync error has occurred, and been raised by the filesystem. One awkward aspect of the patch is that we have to manually set the superblock's errseq_t after the sync_fs callback as opposed to just returning an error from syncfs. This is because the call chain looks something like this: sys_syncfs -> sync_filesystem -> __sync_filesystem -> /* The return value is ignored here sb->s_op->sync_fs(sb) _sync_blockdev /* Where the VFS fetches the error to raise to userspace */ errseq_check_and_advance Because of this we call errseq_set every time the sync_fs callback occurs. Due to the nature of this seen / unseen dichotomy, if the upperdir is an inconsistent state at the initial mount time, overlayfs will refuse to mount, as overlayfs cannot get a snapshot of the upperdir's errseq that will increment on error until the user calls syncfs. Signed-off-by: Sargun Dhillon <sargun@sargun.me> Suggested-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Fixes: c86243b090bc ("ovl: provide a mount option "volatile"") Cc: stable@vger.kernel.org Reviewed-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2021-01-08 08:10:43 +08:00
/* r/o snapshot of upperdir sb's only taken on volatile mounts */
errseq_t errseq;
};
/* 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;
}
ovl: provide a mount option "volatile" Container folks are complaining that dnf/yum issues too many sync while installing packages and this slows down the image build. Build requirement is such that they don't care if a node goes down while build was still going on. In that case, they will simply throw away unfinished layer and start new build. So they don't care about syncing intermediate state to the disk and hence don't want to pay the price associated with sync. So they are asking for mount options where they can disable sync on overlay mount point. They primarily seem to have two use cases. - For building images, they will mount overlay with nosync and then sync upper layer after unmounting overlay and reuse upper as lower for next layer. - For running containers, they don't seem to care about syncing upper layer because if node goes down, they will simply throw away upper layer and create a fresh one. So this patch provides a mount option "volatile" which disables all forms of sync. Now it is caller's responsibility to throw away upper if system crashes or shuts down and start fresh. With "volatile", I am seeing roughly 20% speed up in my VM where I am just installing emacs in an image. Installation time drops from 31 seconds to 25 seconds when nosync option is used. This is for the case of building on top of an image where all packages are already cached. That way I take out the network operations latency out of the measurement. Giuseppe is also looking to cut down on number of iops done on the disk. He is complaining that often in cloud their VMs are throttled if they cross the limit. This option can help them where they reduce number of iops (by cutting down on frequent sync and writebacks). Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2020-09-01 02:15:29 +08:00
static inline bool ovl_should_sync(struct ovl_fs *ofs)
{
return !ofs->config.ovl_volatile;
}
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);
}