From 4aa7c6346be395bdf776f82bbb2e3e2bc60bdd2b Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:35 +0200 Subject: [PATCH 01/14] vfs: add i_op->dentry_open() Add a new inode operation i_op->dentry_open(). This is for stacked filesystems that want to return a struct file from a different filesystem. Signed-off-by: Miklos Szeredi --- Documentation/filesystems/Locking | 2 ++ Documentation/filesystems/vfs.txt | 7 +++++++ fs/namei.c | 9 ++++++--- fs/open.c | 23 +++++++++++++++++++++-- include/linux/fs.h | 4 ++++ 5 files changed, 40 insertions(+), 5 deletions(-) diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 94d93b1f8b53..b30753cbf431 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -67,6 +67,7 @@ prototypes: struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); locking rules: all may block @@ -96,6 +97,7 @@ fiemap: no update_time: no atomic_open: yes tmpfile: no +dentry_open: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index fceff7c00a3c..20bf204426ca 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -364,6 +364,7 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); }; Again, all methods are called without any locks being held, unless @@ -696,6 +697,12 @@ struct address_space_operations { but instead uses bmap to find out where the blocks in the file are and uses those addresses directly. + dentry_open: *WARNING: probably going away soon, do not use!* This is an + alternative to f_op->open(), the difference is that this method may open + a file not necessarily originating from the same filesystem as the one + i_op->open() was called on. It may be useful for stacking filesystems + which want to allow native I/O directly on underlying files. + invalidatepage: If a page has PagePrivate set, then invalidatepage will be called when part or all of the page is to be removed diff --git a/fs/namei.c b/fs/namei.c index 43927d14db67..75306b3c9526 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3064,9 +3064,12 @@ static int do_last(struct nameidata *nd, struct path *path, error = may_open(&nd->path, acc_mode, open_flag); if (error) goto out; - file->f_path.mnt = nd->path.mnt; - error = finish_open(file, nd->path.dentry, NULL, opened); - if (error) { + + BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ + error = vfs_open(&nd->path, file, current_cred()); + if (!error) { + *opened |= FILE_OPENED; + } else { if (error == -EOPENSTALE) goto stale_open; goto out; diff --git a/fs/open.c b/fs/open.c index d6fd3acde134..de92c13b58be 100644 --- a/fs/open.c +++ b/fs/open.c @@ -823,8 +823,7 @@ struct file *dentry_open(const struct path *path, int flags, f = get_empty_filp(); if (!IS_ERR(f)) { f->f_flags = flags; - f->f_path = *path; - error = do_dentry_open(f, NULL, cred); + error = vfs_open(path, f, cred); if (!error) { /* from now on we need fput() to dispose of f */ error = open_check_o_direct(f); @@ -841,6 +840,26 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +/** + * vfs_open - open the file at the given path + * @path: path to open + * @filp: newly allocated file with f_flag initialized + * @cred: credentials to use + */ +int vfs_open(const struct path *path, struct file *filp, + const struct cred *cred) +{ + struct inode *inode = path->dentry->d_inode; + + if (inode->i_op->dentry_open) + return inode->i_op->dentry_open(path->dentry, filp, cred); + else { + filp->f_path = *path; + return do_dentry_open(filp, NULL, cred); + } +} +EXPORT_SYMBOL(vfs_open); + static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index a957d4366c24..5cf7f6759679 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1528,6 +1528,9 @@ struct inode_operations { umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); + + /* WARNING: probably going away soon, do not use! */ + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); } ____cacheline_aligned; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, @@ -2040,6 +2043,7 @@ extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); +extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); From 1c118596a7682912106c80007102ce0184c77780 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:35 +0200 Subject: [PATCH 02/14] vfs: export do_splice_direct() to modules Export do_splice_direct() to modules. Needed by overlay filesystem. Signed-off-by: Miklos Szeredi --- fs/internal.h | 6 ------ fs/splice.c | 1 + include/linux/fs.h | 3 +++ 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/fs/internal.h b/fs/internal.h index 9477f8f6aefc..0f0626a6997c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -138,12 +138,6 @@ extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan, */ extern int rw_verify_area(int, struct file *, const loff_t *, size_t); -/* - * splice.c - */ -extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, size_t len, unsigned int flags); - /* * pipe.c */ diff --git a/fs/splice.c b/fs/splice.c index f5cb9ba84510..75c6058eabf2 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1330,6 +1330,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, return ret; } +EXPORT_SYMBOL(do_splice_direct); static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, diff --git a/include/linux/fs.h b/include/linux/fs.h index 5cf7f6759679..10ed65b2c31d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2456,6 +2456,9 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags); + extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); From bd5d08569cc379f8366663a61558a9ce17c2e460 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:35 +0200 Subject: [PATCH 03/14] vfs: export __inode_permission() to modules We need to be able to check inode permissions (but not filesystem implied permissions) for stackable filesystems. Expose this interface for overlayfs. Signed-off-by: Miklos Szeredi --- fs/internal.h | 1 - fs/namei.c | 1 + include/linux/fs.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/internal.h b/fs/internal.h index 0f0626a6997c..757ba2abf21e 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -47,7 +47,6 @@ extern void __init chrdev_init(void); /* * namei.c */ -extern int __inode_permission(struct inode *, int); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); diff --git a/fs/namei.c b/fs/namei.c index 75306b3c9526..d944f6db9b07 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -416,6 +416,7 @@ int __inode_permission(struct inode *inode, int mask) return security_inode_permission(inode, mask); } +EXPORT_SYMBOL(__inode_permission); /** * sb_permission - Check superblock-level permissions diff --git a/include/linux/fs.h b/include/linux/fs.h index 10ed65b2c31d..5419df70a835 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2257,6 +2257,7 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); +extern int __inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); static inline bool execute_ok(struct inode *inode) From c771d683a62e5d36bc46036f5c07f4f5bb7dda61 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:36 +0200 Subject: [PATCH 04/14] vfs: introduce clone_private_mount() Overlayfs needs a private clone of the mount, so create a function for this and export to modules. Signed-off-by: Miklos Szeredi --- fs/namespace.c | 27 +++++++++++++++++++++++++++ include/linux/mount.h | 3 +++ 2 files changed, 30 insertions(+) diff --git a/fs/namespace.c b/fs/namespace.c index fbba8b17330d..5b66b2b3624d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1686,6 +1686,33 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +/** + * clone_private_mount - create a private clone of a path + * + * This creates a new vfsmount, which will be the clone of @path. The new will + * not be attached anywhere in the namespace and will be private (i.e. changes + * to the originating mount won't be propagated into this). + * + * Release with mntput(). + */ +struct vfsmount *clone_private_mount(struct path *path) +{ + struct mount *old_mnt = real_mount(path->mnt); + struct mount *new_mnt; + + if (IS_MNT_UNBINDABLE(old_mnt)) + return ERR_PTR(-EINVAL); + + down_read(&namespace_sem); + new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) + return ERR_CAST(new_mnt); + + return &new_mnt->mnt; +} +EXPORT_SYMBOL_GPL(clone_private_mount); + int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { diff --git a/include/linux/mount.h b/include/linux/mount.h index 9262e4bf0cc3..c2c561dc0114 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -81,6 +81,9 @@ extern struct vfsmount *mntget(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(struct path *path); extern int __mnt_is_readonly(struct vfsmount *mnt); +struct path; +extern struct vfsmount *clone_private_mount(struct path *path); + struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, From cbdf35bcb833bfd00f0925d7a9a33a21f41ea582 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:36 +0200 Subject: [PATCH 05/14] vfs: export check_sticky() It's already duplicated in btrfs and about to be used in overlayfs too. Move the sticky bit check to an inline helper and call the out-of-line helper only in the unlikly case of the sticky bit being set. Signed-off-by: Miklos Szeredi --- fs/btrfs/ioctl.c | 20 +------------------- fs/namei.c | 9 ++------- include/linux/fs.h | 9 +++++++++ 3 files changed, 12 insertions(+), 26 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8d2b76e29d3b..4399f0c3a4ce 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -765,23 +765,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, return ret; } -/* copy of check_sticky in fs/namei.c() -* It's inline, so penalty for filesystems that don't use sticky bit is -* minimal. -*/ -static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode) -{ - kuid_t fsuid = current_fsuid(); - - if (!(dir->i_mode & S_ISVTX)) - return 0; - if (uid_eq(inode->i_uid, fsuid)) - return 0; - if (uid_eq(dir->i_uid, fsuid)) - return 0; - return !capable(CAP_FOWNER); -} - /* copy of may_delete in fs/namei.c() * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. @@ -817,8 +800,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) return error; if (IS_APPEND(dir)) return -EPERM; - if (btrfs_check_sticky(dir, victim->d_inode)|| - IS_APPEND(victim->d_inode)|| + if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) || IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode)) return -EPERM; if (isdir) { diff --git a/fs/namei.c b/fs/namei.c index d944f6db9b07..77fd536106cb 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2384,22 +2384,17 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path, } EXPORT_SYMBOL(kern_path_mountpoint); -/* - * It's inline, so penalty for filesystems that don't use sticky bit is - * minimal. - */ -static inline int check_sticky(struct inode *dir, struct inode *inode) +int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (!(dir->i_mode & S_ISVTX)) - return 0; if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } +EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check diff --git a/include/linux/fs.h b/include/linux/fs.h index 5419df70a835..55cc0a319baa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2259,6 +2259,7 @@ extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int __inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); +extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { @@ -2745,6 +2746,14 @@ static inline int is_sxid(umode_t mode) return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } +static inline int check_sticky(struct inode *dir, struct inode *inode) +{ + if (!(dir->i_mode & S_ISVTX)) + return 0; + + return __check_sticky(dir, inode); +} + static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) From 787fb6bc9682ec7c05fb5d9561b57100fbc1cc41 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:36 +0200 Subject: [PATCH 06/14] vfs: add whiteout support Whiteout isn't actually a new file type, but is represented as a char device (Linus's idea) with 0/0 device number. This has several advantages compared to introducing a new whiteout file type: - no userspace API changes (e.g. trivial to make backups of upper layer filesystem, without losing whiteouts) - no fs image format changes (you can boot an old kernel/fsck without whiteout support and things won't break) - implementation is trivial Signed-off-by: Miklos Szeredi --- fs/namei.c | 14 ++++++++++++++ include/linux/fs.h | 11 +++++++++++ 2 files changed, 25 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index 77fd536106cb..d20191c0ebf5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4346,6 +4346,20 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } +int vfs_whiteout(struct inode *dir, struct dentry *dentry) +{ + int error = may_create(dir, dentry); + if (error) + return error; + + if (!dir->i_op->mknod) + return -EPERM; + + return dir->i_op->mknod(dir, dentry, + S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); +} +EXPORT_SYMBOL(vfs_whiteout); + int readlink_copy(char __user *buffer, int buflen, const char *link) { int len = PTR_ERR(link); diff --git a/include/linux/fs.h b/include/linux/fs.h index 55cc0a319baa..69118b3cb917 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -222,6 +222,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) +/* + * Whiteout is represented by a char device. The following constants define the + * mode and device number to use. + */ +#define WHITEOUT_MODE 0 +#define WHITEOUT_DEV 0 + /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. @@ -1398,6 +1405,7 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); +extern int vfs_whiteout(struct inode *, struct dentry *); /* * VFS dentry helper functions. @@ -1628,6 +1636,9 @@ struct super_operations { #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) +#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ + (inode)->i_rdev == WHITEOUT_DEV) + /* * Inode state bits. Protected by inode->i_lock * From 0d7a855526dd672e114aff2ac22b60fc6f155b08 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:37 +0200 Subject: [PATCH 07/14] vfs: add RENAME_WHITEOUT This adds a new RENAME_WHITEOUT flag. This flag makes rename() create a whiteout of source. The whiteout creation is atomic relative to the rename. Signed-off-by: Miklos Szeredi --- fs/namei.c | 8 ++++++-- include/uapi/linux/fs.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index d20191c0ebf5..42df664e95e5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4209,12 +4209,16 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, bool should_retry = false; int error; - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; - if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE)) + if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && + (flags & RENAME_EXCHANGE)) return -EINVAL; + if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD)) + return -EPERM; + retry: from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags); if (IS_ERR(from)) { diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index ca1a11bb4443..3735fa0a6784 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -37,6 +37,7 @@ #define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */ #define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ +#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ struct fstrim_range { __u64 start; From cd808deced431b66b5fa4e5c193cb7ec0059eaff Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:37 +0200 Subject: [PATCH 08/14] ext4: support RENAME_WHITEOUT Add whiteout support to ext4_rename(). A whiteout inode (chrdev/0,0) is created before the rename takes place. The whiteout inode is added to the old entry instead of deleting it. Signed-off-by: Miklos Szeredi --- fs/ext4/namei.c | 95 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 78 insertions(+), 17 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 603e4ebbd0ac..aba86e8ef1ef 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3190,6 +3190,39 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent) } } +static struct inode *ext4_whiteout_for_rename(struct ext4_renament *ent, + int credits, handle_t **h) +{ + struct inode *wh; + handle_t *handle; + int retries = 0; + + /* + * for inode block, sb block, group summaries, + * and inode bitmap + */ + credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) + + EXT4_XATTR_TRANS_BLOCKS + 4); +retry: + wh = ext4_new_inode_start_handle(ent->dir, S_IFCHR | WHITEOUT_MODE, + &ent->dentry->d_name, 0, NULL, + EXT4_HT_DIR, credits); + + handle = ext4_journal_current_handle(); + if (IS_ERR(wh)) { + if (handle) + ext4_journal_stop(handle); + if (PTR_ERR(wh) == -ENOSPC && + ext4_should_retry_alloc(ent->dir->i_sb, &retries)) + goto retry; + } else { + *h = handle; + init_special_inode(wh, wh->i_mode, WHITEOUT_DEV); + wh->i_op = &ext4_special_inode_operations; + } + return wh; +} + /* * Anybody can rename anything with this: the permission checks are left to the * higher-level routines. @@ -3199,7 +3232,8 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent) * This comes from rename(const char *oldpath, const char *newpath) */ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { handle_t *handle = NULL; struct ext4_renament old = { @@ -3214,6 +3248,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, }; int force_reread; int retval; + struct inode *whiteout = NULL; + int credits; + u8 old_file_type; dquot_initialize(old.dir); dquot_initialize(new.dir); @@ -3252,11 +3289,17 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC)) ext4_alloc_da_blocks(old.inode); - handle = ext4_journal_start(old.dir, EXT4_HT_DIR, - (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + credits = (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2); + if (!(flags & RENAME_WHITEOUT)) { + handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + } else { + whiteout = ext4_whiteout_for_rename(&old, credits, &handle); + if (IS_ERR(whiteout)) + return PTR_ERR(whiteout); + } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); @@ -3284,13 +3327,26 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, */ force_reread = (new.dir->i_ino == old.dir->i_ino && ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA)); + + old_file_type = old.de->file_type; + if (whiteout) { + /* + * Do this before adding a new entry, so the old entry is sure + * to be still pointing to the valid old entry. + */ + retval = ext4_setent(handle, &old, whiteout->i_ino, + EXT4_FT_CHRDEV); + if (retval) + goto end_rename; + ext4_mark_inode_dirty(handle, whiteout); + } if (!new.bh) { retval = ext4_add_entry(handle, new.dentry, old.inode); if (retval) goto end_rename; } else { retval = ext4_setent(handle, &new, - old.inode->i_ino, old.de->file_type); + old.inode->i_ino, old_file_type); if (retval) goto end_rename; } @@ -3305,10 +3361,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, old.inode->i_ctime = ext4_current_time(old.inode); ext4_mark_inode_dirty(handle, old.inode); - /* - * ok, that's it - */ - ext4_rename_delete(handle, &old, force_reread); + if (!whiteout) { + /* + * ok, that's it + */ + ext4_rename_delete(handle, &old, force_reread); + } if (new.inode) { ext4_dec_count(handle, new.inode); @@ -3344,6 +3402,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(old.dir_bh); brelse(old.bh); brelse(new.bh); + if (whiteout) { + if (retval) + drop_nlink(whiteout); + unlock_new_inode(whiteout); + iput(whiteout); + } if (handle) ext4_journal_stop(handle); return retval; @@ -3476,18 +3540,15 @@ static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) { return ext4_cross_rename(old_dir, old_dentry, new_dir, new_dentry); } - /* - * Existence checking was done by the VFS, otherwise "RENAME_NOREPLACE" - * is equivalent to regular rename. - */ - return ext4_rename(old_dir, old_dentry, new_dir, new_dentry); + + return ext4_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } /* From 46fdb794e3f52ef18b859ebc92f0a9d7db21c5df Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:37 +0200 Subject: [PATCH 09/14] shmem: support RENAME_WHITEOUT Allocate a dentry, initialize it with a whiteout and hash it in the place of the old dentry. Later the old dentry will be moved away and the whiteout will remain. i_mutex protects agains concurrent readdir. Signed-off-by: Miklos Szeredi Cc: Hugh Dickins --- mm/shmem.c | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) diff --git a/mm/shmem.c b/mm/shmem.c index cd6fc7590e54..185836ba53ef 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2345,6 +2345,32 @@ static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, stru return 0; } +static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) +{ + struct dentry *whiteout; + int error; + + whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name); + if (!whiteout) + return -ENOMEM; + + error = shmem_mknod(old_dir, whiteout, + S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + dput(whiteout); + if (error) + return error; + + /* + * Cheat and hash the whiteout while the old dentry is still in + * place, instead of playing games with FS_RENAME_DOES_D_MOVE. + * + * d_lookup() will consistently find one of them at this point, + * not sure which one, but that isn't even important. + */ + d_rehash(whiteout); + return 0; +} + /* * The VFS layer already does all the dentry stuff for rename, * we just have to decrement the usage count for the target if @@ -2356,7 +2382,7 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc struct inode *inode = old_dentry->d_inode; int they_are_dirs = S_ISDIR(inode->i_mode); - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) @@ -2365,6 +2391,14 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc if (!simple_empty(new_dentry)) return -ENOTEMPTY; + if (flags & RENAME_WHITEOUT) { + int error; + + error = shmem_whiteout(old_dir, old_dentry); + if (error) + return error; + } + if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { From e9be9d5e76e34872f0c37d72e25bc27fe9e2c54c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:38 +0200 Subject: [PATCH 10/14] overlay filesystem Overlayfs allows one, usually read-write, directory tree to be overlaid onto another, read-only directory tree. All modifications go to the upper, writable layer. This type of mechanism is most often used for live CDs but there's a wide variety of other uses. The implementation differs from other "union filesystem" implementations in that after a file is opened all operations go directly to the underlying, lower or upper, filesystems. This simplifies the implementation and allows native performance in these cases. The dentry tree is duplicated from the underlying filesystems, this enables fast cached lookups without adding special support into the VFS. This uses slightly more memory than union mounts, but dentries are relatively small. Currently inodes are duplicated as well, but it is a possible optimization to share inodes for non-directories. Opening non directories results in the open forwarded to the underlying filesystem. This makes the behavior very similar to union mounts (with the same limitations vs. fchmod/fchown on O_RDONLY file descriptors). Usage: mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper/upper,workdir=/upper/work /overlay The following cotributions have been folded into this patch: Neil Brown : - minimal remount support - use correct seek function for directories - initialise is_real before use - rename ovl_fill_cache to ovl_dir_read Felix Fietkau : - fix a deadlock in ovl_dir_read_merged - fix a deadlock in ovl_remove_whiteouts Erez Zadok - fix cleanup after WARN_ON Sedat Dilek - fix up permission to confirm to new API Robin Dong - fix possible leak in ovl_new_inode - create new inode in ovl_link Andy Whitcroft - switch to __inode_permission() - copy up i_uid/i_gid from the underlying inode AV: - ovl_copy_up_locked() - dput(ERR_PTR(...)) on two failure exits - ovl_clear_empty() - one failure exit forgetting to do unlock_rename(), lack of check for udir being the parent of upper, dropping and regaining the lock on udir (which would require _another_ check for parent being right). - bogus d_drop() in copyup and rename [fix from your mail] - copyup/remove and copyup/rename races [fix from your mail] - ovl_dir_fsync() leaving ERR_PTR() in ->realfile - ovl_entry_free() is pointless - it's just a kfree_rcu() - fold ovl_do_lookup() into ovl_lookup() - manually assigning ->d_op is wrong. Just use ->s_d_op. [patches picked from Miklos]: * copyup/remove and copyup/rename races * bogus d_drop() in copyup and rename Also thanks to the following people for testing and reporting bugs: Jordi Pujol Andy Whitcroft Michal Suchanek Felix Fietkau Erez Zadok Randy Dunlap Signed-off-by: Miklos Szeredi --- fs/Kconfig | 1 + fs/Makefile | 1 + fs/overlayfs/Kconfig | 10 + fs/overlayfs/Makefile | 7 + fs/overlayfs/copy_up.c | 414 ++++++++++++++++++ fs/overlayfs/dir.c | 921 +++++++++++++++++++++++++++++++++++++++ fs/overlayfs/inode.c | 425 ++++++++++++++++++ fs/overlayfs/overlayfs.h | 191 ++++++++ fs/overlayfs/readdir.c | 587 +++++++++++++++++++++++++ fs/overlayfs/super.c | 727 ++++++++++++++++++++++++++++++ 10 files changed, 3284 insertions(+) create mode 100644 fs/overlayfs/Kconfig create mode 100644 fs/overlayfs/Makefile create mode 100644 fs/overlayfs/copy_up.c create mode 100644 fs/overlayfs/dir.c create mode 100644 fs/overlayfs/inode.c create mode 100644 fs/overlayfs/overlayfs.h create mode 100644 fs/overlayfs/readdir.c create mode 100644 fs/overlayfs/super.c diff --git a/fs/Kconfig b/fs/Kconfig index db5dc1598716..664991afe0c0 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -67,6 +67,7 @@ source "fs/quota/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" +source "fs/overlayfs/Kconfig" menu "Caches" diff --git a/fs/Makefile b/fs/Makefile index 90c88529892b..34a1b9dea6dd 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ +obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/ obj-$(CONFIG_UDF_FS) += udf/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_OMFS_FS) += omfs/ diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig new file mode 100644 index 000000000000..e60125976873 --- /dev/null +++ b/fs/overlayfs/Kconfig @@ -0,0 +1,10 @@ +config OVERLAYFS_FS + tristate "Overlay filesystem support" + help + An overlay filesystem combines two filesystems - an 'upper' filesystem + and a 'lower' filesystem. When a name exists in both filesystems, the + object in the 'upper' filesystem is visible while the object in the + 'lower' filesystem is either hidden or, in the case of directories, + merged with the 'upper' object. + + For more information see Documentation/filesystems/overlayfs.txt diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile new file mode 100644 index 000000000000..8f91889480d0 --- /dev/null +++ b/fs/overlayfs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the overlay filesystem. +# + +obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o + +overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c new file mode 100644 index 000000000000..ea10a8719107 --- /dev/null +++ b/fs/overlayfs/copy_up.c @@ -0,0 +1,414 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "overlayfs.h" + +#define OVL_COPY_UP_CHUNK_SIZE (1 << 20) + +int ovl_copy_xattr(struct dentry *old, struct dentry *new) +{ + ssize_t list_size, size; + char *buf, *name, *value; + int error; + + if (!old->d_inode->i_op->getxattr || + !new->d_inode->i_op->getxattr) + return 0; + + list_size = vfs_listxattr(old, NULL, 0); + if (list_size <= 0) { + if (list_size == -EOPNOTSUPP) + return 0; + return list_size; + } + + buf = kzalloc(list_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + error = -ENOMEM; + value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); + if (!value) + goto out; + + list_size = vfs_listxattr(old, buf, list_size); + if (list_size <= 0) { + error = list_size; + goto out_free_value; + } + + for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); + if (size <= 0) { + error = size; + goto out_free_value; + } + error = vfs_setxattr(new, name, value, size, 0); + if (error) + goto out_free_value; + } + +out_free_value: + kfree(value); +out: + kfree(buf); + return error; +} + +static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) +{ + struct file *old_file; + struct file *new_file; + loff_t old_pos = 0; + loff_t new_pos = 0; + int error = 0; + + if (len == 0) + return 0; + + old_file = ovl_path_open(old, O_RDONLY); + if (IS_ERR(old_file)) + return PTR_ERR(old_file); + + new_file = ovl_path_open(new, O_WRONLY); + if (IS_ERR(new_file)) { + error = PTR_ERR(new_file); + goto out_fput; + } + + /* FIXME: copy up sparse files efficiently */ + while (len) { + size_t this_len = OVL_COPY_UP_CHUNK_SIZE; + long bytes; + + if (len < this_len) + this_len = len; + + if (signal_pending_state(TASK_KILLABLE, current)) { + error = -EINTR; + break; + } + + bytes = do_splice_direct(old_file, &old_pos, + new_file, &new_pos, + this_len, SPLICE_F_MOVE); + if (bytes <= 0) { + error = bytes; + break; + } + WARN_ON(old_pos != new_pos); + + len -= bytes; + } + + fput(new_file); +out_fput: + fput(old_file); + return error; +} + +static char *ovl_read_symlink(struct dentry *realdentry) +{ + int res; + char *buf; + struct inode *inode = realdentry->d_inode; + mm_segment_t old_fs; + + res = -EINVAL; + if (!inode->i_op->readlink) + goto err; + + res = -ENOMEM; + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + goto err; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = inode->i_op->readlink(realdentry, + (char __user *)buf, PAGE_SIZE - 1); + set_fs(old_fs); + if (res < 0) { + free_page((unsigned long) buf); + goto err; + } + buf[res] = '\0'; + + return buf; + +err: + return ERR_PTR(res); +} + +static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) +{ + struct iattr attr = { + .ia_valid = + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + .ia_atime = stat->atime, + .ia_mtime = stat->mtime, + }; + + return notify_change(upperdentry, &attr, NULL); +} + +int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) +{ + int err = 0; + + if (!S_ISLNK(stat->mode)) { + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = stat->mode, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) { + struct iattr attr = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = stat->uid, + .ia_gid = stat->gid, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) + ovl_set_timestamps(upperdentry, stat); + + return err; + +} + +static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, + struct dentry *dentry, struct path *lowerpath, + struct kstat *stat, struct iattr *attr, + const char *link) +{ + struct inode *wdir = workdir->d_inode; + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry = NULL; + struct dentry *upper = NULL; + umode_t mode = stat->mode; + int err; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out1; + + /* Can't properly set mode on creation because of the umask */ + stat->mode &= S_IFMT; + err = ovl_create_real(wdir, newdentry, stat, link, NULL, true); + stat->mode = mode; + if (err) + goto out2; + + if (S_ISREG(stat->mode)) { + struct path upperpath; + ovl_path_upper(dentry, &upperpath); + BUG_ON(upperpath.dentry != NULL); + upperpath.dentry = newdentry; + + err = ovl_copy_up_data(lowerpath, &upperpath, stat->size); + if (err) + goto out_cleanup; + } + + err = ovl_copy_xattr(lowerpath->dentry, newdentry); + if (err) + goto out_cleanup; + + mutex_lock(&newdentry->d_inode->i_mutex); + err = ovl_set_attr(newdentry, stat); + if (!err && attr) + err = notify_change(newdentry, attr, NULL); + mutex_unlock(&newdentry->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + + ovl_dentry_update(dentry, newdentry); + newdentry = NULL; + + /* + * Non-directores become opaque when copied up. + */ + if (!S_ISDIR(stat->mode)) + ovl_dentry_set_opaque(dentry, true); +out2: + dput(upper); +out1: + dput(newdentry); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out; +} + +/* + * Copy up a single dentry + * + * Directory renames only allowed on "pure upper" (already created on + * upper filesystem, never copied up). Directories which are on lower or + * are merged may not be renamed. For these -EXDEV is returned and + * userspace has to deal with it. This means, when copying up a + * directory we can rely on it and ancestors being stable. + * + * Non-directory renames start with copy up of source if necessary. The + * actual rename will only proceed once the copy up was successful. Copy + * up uses upper parent i_mutex for exclusion. Since rename can change + * d_parent it is possible that the copy up will lock the old parent. At + * that point the file will have already been copied up anyway. + */ +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr) +{ + struct dentry *workdir = ovl_workdir(dentry); + int err; + struct kstat pstat; + struct path parentpath; + struct dentry *upperdir; + struct dentry *upperdentry; + const struct cred *old_cred; + struct cred *override_cred; + char *link = NULL; + + ovl_path_upper(parent, &parentpath); + upperdir = parentpath.dentry; + + err = vfs_getattr(&parentpath, &pstat); + if (err) + return err; + + if (S_ISLNK(stat->mode)) { + link = ovl_read_symlink(lowerpath->dentry); + if (IS_ERR(link)) + return PTR_ERR(link); + } + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_free_link; + + override_cred->fsuid = stat->uid; + override_cred->fsgid = stat->gid; + /* + * CAP_SYS_ADMIN for copying up extended attributes + * CAP_DAC_OVERRIDE for create + * CAP_FOWNER for chmod, timestamp update + * CAP_FSETID for chmod + * CAP_CHOWN for chown + * CAP_MKNOD for mknod + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + cap_raise(override_cred->cap_effective, CAP_MKNOD); + old_cred = override_creds(override_cred); + + err = -EIO; + if (lock_rename(workdir, upperdir) != NULL) { + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + goto out_unlock; + } + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + unlock_rename(workdir, upperdir); + err = 0; + /* Raced with another copy-up? Do the setattr here */ + if (attr) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } + goto out_put_cred; + } + + err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, + stat, attr, link); + if (!err) { + /* Restore timestamps on parent (best effort) */ + ovl_set_timestamps(upperdir, &pstat); + } +out_unlock: + unlock_rename(workdir, upperdir); +out_put_cred: + revert_creds(old_cred); + put_cred(override_cred); + +out_free_link: + if (link) + free_page((unsigned long) link); + + return err; +} + +int ovl_copy_up(struct dentry *dentry) +{ + int err; + + err = 0; + while (!err) { + struct dentry *next; + struct dentry *parent; + struct path lowerpath; + struct kstat stat; + enum ovl_path_type type = ovl_path_type(dentry); + + if (type != OVL_PATH_LOWER) + break; + + next = dget(dentry); + /* find the topmost dentry not yet copied up */ + for (;;) { + parent = dget_parent(next); + + type = ovl_path_type(parent); + if (type != OVL_PATH_LOWER) + break; + + dput(next); + next = parent; + } + + ovl_path_lower(next, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (!err) + err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL); + + dput(parent); + dput(next); + } + + return err; +} diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c new file mode 100644 index 000000000000..15cd91ad9940 --- /dev/null +++ b/fs/overlayfs/dir.c @@ -0,0 +1,921 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include "overlayfs.h" + +void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) +{ + int err; + + dget(wdentry); + if (S_ISDIR(wdentry->d_inode->i_mode)) + err = ovl_do_rmdir(wdir, wdentry); + else + err = ovl_do_unlink(wdir, wdentry); + dput(wdentry); + + if (err) { + pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n", + wdentry, err); + } +} + +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry) +{ + struct dentry *temp; + char name[20]; + + snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry); + + temp = lookup_one_len(name, workdir, strlen(name)); + if (!IS_ERR(temp) && temp->d_inode) { + pr_err("overlayfs: workdir/%s already exists\n", name); + dput(temp); + temp = ERR_PTR(-EIO); + } + + return temp; +} + +/* caller holds i_mutex on workdir */ +static struct dentry *ovl_whiteout(struct dentry *workdir, + struct dentry *dentry) +{ + int err; + struct dentry *whiteout; + struct inode *wdir = workdir->d_inode; + + whiteout = ovl_lookup_temp(workdir, dentry); + if (IS_ERR(whiteout)) + return whiteout; + + err = ovl_do_whiteout(wdir, whiteout); + if (err) { + dput(whiteout); + whiteout = ERR_PTR(err); + } + + return whiteout; +} + +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug) +{ + int err; + + if (newdentry->d_inode) + return -ESTALE; + + if (hardlink) { + err = ovl_do_link(hardlink, dir, newdentry, debug); + } else { + switch (stat->mode & S_IFMT) { + case S_IFREG: + err = ovl_do_create(dir, newdentry, stat->mode, debug); + break; + + case S_IFDIR: + err = ovl_do_mkdir(dir, newdentry, stat->mode, debug); + break; + + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + err = ovl_do_mknod(dir, newdentry, + stat->mode, stat->rdev, debug); + break; + + case S_IFLNK: + err = ovl_do_symlink(dir, newdentry, link, debug); + break; + + default: + err = -EPERM; + } + } + if (!err && WARN_ON(!newdentry->d_inode)) { + /* + * Not quite sure if non-instantiated dentry is legal or not. + * VFS doesn't seem to care so check and warn here. + */ + err = -ENOENT; + } + return err; +} + +static int ovl_set_opaque(struct dentry *upperdentry) +{ + return ovl_do_setxattr(upperdentry, ovl_opaque_xattr, "y", 1, 0); +} + +static void ovl_remove_opaque(struct dentry *upperdentry) +{ + int err; + + err = ovl_do_removexattr(upperdentry, ovl_opaque_xattr); + if (err) { + pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n", + upperdentry->d_name.name, err); + } +} + +static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + int err; + enum ovl_path_type type; + struct path realpath; + + type = ovl_path_real(dentry, &realpath); + err = vfs_getattr(&realpath, stat); + if (err) + return err; + + stat->dev = dentry->d_sb->s_dev; + stat->ino = dentry->d_inode->i_ino; + + /* + * It's probably not worth it to count subdirs to get the + * correct link count. nlink=1 seems to pacify 'find' and + * other utilities. + */ + if (type == OVL_PATH_MERGE) + stat->nlink = 1; + + return 0; +} + +static int ovl_create_upper(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry; + int err; + + mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT); + newdentry = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + err = ovl_create_real(udir, newdentry, stat, link, hardlink, false); + if (err) + goto out_dput; + + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput: + dput(newdentry); +out_unlock: + mutex_unlock(&udir->i_mutex); + return err; +} + +static int ovl_lock_rename_workdir(struct dentry *workdir, + struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} + +static struct dentry *ovl_clear_empty(struct dentry *dentry, + struct list_head *list) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct path upperpath; + struct dentry *upper; + struct dentry *opaquedir; + struct kstat stat; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + ovl_path_upper(dentry, &upperpath); + err = vfs_getattr(&upperpath, &stat); + if (err) + goto out_unlock; + + err = -ESTALE; + if (!S_ISDIR(stat.mode)) + goto out_unlock; + upper = upperpath.dentry; + if (upper->d_parent->d_inode != udir) + goto out_unlock; + + opaquedir = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out_unlock; + + err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true); + if (err) + goto out_dput; + + err = ovl_copy_xattr(upper, opaquedir); + if (err) + goto out_cleanup; + + err = ovl_set_opaque(opaquedir); + if (err) + goto out_cleanup; + + mutex_lock(&opaquedir->d_inode->i_mutex); + err = ovl_set_attr(opaquedir, &stat); + mutex_unlock(&opaquedir->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup_whiteouts(upper, list); + ovl_cleanup(wdir, upper); + unlock_rename(workdir, upperdir); + + /* dentry's upper doesn't match now, get rid of it */ + d_drop(dentry); + + return opaquedir; + +out_cleanup: + ovl_cleanup(wdir, opaquedir); +out_dput: + dput(opaquedir); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return ERR_PTR(err); +} + +static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry, + enum ovl_path_type type) +{ + int err; + struct dentry *ret = NULL; + LIST_HEAD(list); + + err = ovl_check_empty_dir(dentry, &list); + if (err) + ret = ERR_PTR(err); + else if (type == OVL_PATH_MERGE) + ret = ovl_clear_empty(dentry, &list); + + ovl_cache_free(&list); + + return ret; +} + +static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *upper; + struct dentry *newdentry; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out_dput; + + err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true); + if (err) + goto out_dput2; + + if (S_ISDIR(stat->mode)) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, + RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup(wdir, upper); + } else { + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + } + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput2: + dput(upper); +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out_dput2; +} + +static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev, + const char *link, struct dentry *hardlink) +{ + int err; + struct inode *inode; + struct kstat stat = { + .mode = mode, + .rdev = rdev, + }; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata); + if (!inode) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_iput; + + if (!ovl_dentry_is_opaque(dentry)) { + err = ovl_create_upper(dentry, inode, &stat, link, hardlink); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_iput; + + /* + * CAP_SYS_ADMIN for setting opaque xattr + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + old_cred = override_creds(override_cred); + + err = ovl_create_over_whiteout(dentry, inode, &stat, link, + hardlink); + + revert_creds(old_cred); + put_cred(override_cred); + } + + if (!err) + inode = NULL; +out_iput: + iput(inode); +out: + return err; +} + +static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, + const char *link) +{ + int err; + + err = ovl_want_write(dentry); + if (!err) { + err = ovl_create_or_link(dentry, mode, rdev, link, NULL); + ovl_drop_write(dentry); + } + + return err; +} + +static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); +} + +static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); +} + +static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t rdev) +{ + /* Don't allow creation of "whiteout" on overlay */ + if (S_ISCHR(mode) && rdev == WHITEOUT_DEV) + return -EPERM; + + return ovl_create_object(dentry, mode, rdev, NULL); +} + +static int ovl_symlink(struct inode *dir, struct dentry *dentry, + const char *link) +{ + return ovl_create_object(dentry, S_IFLNK, 0, link); +} + +static int ovl_link(struct dentry *old, struct inode *newdir, + struct dentry *new) +{ + int err; + struct dentry *upper; + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + upper = ovl_dentry_upper(old); + err = ovl_create_or_link(new, upper->d_inode->i_mode, 0, NULL, upper); + +out_drop_write: + ovl_drop_write(old); +out: + return err; +} + +static int ovl_remove_and_whiteout(struct dentry *dentry, + enum ovl_path_type type, bool is_dir) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *whiteout; + struct dentry *upper; + struct dentry *opaquedir = NULL; + int err; + + if (is_dir) { + opaquedir = ovl_check_empty_and_clear(dentry, type); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out; + } + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out_dput; + + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto out_unlock; + + if (type == OVL_PATH_LOWER) { + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto kill_whiteout; + + err = ovl_do_rename(wdir, whiteout, udir, upper, 0); + dput(upper); + if (err) + goto kill_whiteout; + } else { + int flags = 0; + + upper = ovl_dentry_upper(dentry); + if (opaquedir) + upper = opaquedir; + err = -ESTALE; + if (upper->d_parent != upperdir) + goto kill_whiteout; + + if (is_dir) + flags |= RENAME_EXCHANGE; + + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + + if (is_dir) + ovl_cleanup(wdir, upper); + } + ovl_dentry_version_inc(dentry->d_parent); +out_d_drop: + d_drop(dentry); + dput(whiteout); +out_unlock: + unlock_rename(workdir, upperdir); +out_dput: + dput(opaquedir); +out: + return err; + +kill_whiteout: + ovl_cleanup(wdir, whiteout); + goto out_d_drop; +} + +static int ovl_remove_upper(struct dentry *dentry, bool is_dir) +{ + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *dir = upperdir->d_inode; + struct dentry *upper = ovl_dentry_upper(dentry); + int err; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + err = -ESTALE; + if (upper->d_parent == upperdir) { + /* Don't let d_delete() think it can reset d_inode */ + dget(upper); + if (is_dir) + err = vfs_rmdir(dir, upper); + else + err = vfs_unlink(dir, upper, NULL); + dput(upper); + ovl_dentry_version_inc(dentry->d_parent); + } + + /* + * Keeping this dentry hashed would mean having to release + * upperpath/lowerpath, which could only be done if we are the + * sole user of this dentry. Too tricky... Just unhash for + * now. + */ + d_drop(dentry); + mutex_unlock(&dir->i_mutex); + + return err; +} + +static inline int ovl_check_sticky(struct dentry *dentry) +{ + struct inode *dir = ovl_dentry_real(dentry->d_parent)->d_inode; + struct inode *inode = ovl_dentry_real(dentry)->d_inode; + + if (check_sticky(dir, inode)) + return -EPERM; + + return 0; +} + +static int ovl_do_remove(struct dentry *dentry, bool is_dir) +{ + enum ovl_path_type type; + int err; + + err = ovl_check_sticky(dentry); + if (err) + goto out; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_drop_write; + + type = ovl_path_type(dentry); + if (type == OVL_PATH_PURE_UPPER) { + err = ovl_remove_upper(dentry, is_dir); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + + err = ovl_remove_and_whiteout(dentry, type, is_dir); + + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_unlink(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, false); +} + +static int ovl_rmdir(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, true); +} + +static int ovl_rename2(struct inode *olddir, struct dentry *old, + struct inode *newdir, struct dentry *new, + unsigned int flags) +{ + int err; + enum ovl_path_type old_type; + enum ovl_path_type new_type; + struct dentry *old_upperdir; + struct dentry *new_upperdir; + struct dentry *olddentry; + struct dentry *newdentry; + struct dentry *trap; + bool old_opaque; + bool new_opaque; + bool new_create = false; + bool cleanup_whiteout = false; + bool overwrite = !(flags & RENAME_EXCHANGE); + bool is_dir = S_ISDIR(old->d_inode->i_mode); + bool new_is_dir = false; + struct dentry *opaquedir = NULL; + const struct cred *old_cred = NULL; + struct cred *override_cred = NULL; + + err = -EINVAL; + if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) + goto out; + + flags &= ~RENAME_NOREPLACE; + + err = ovl_check_sticky(old); + if (err) + goto out; + + /* Don't copy up directory trees */ + old_type = ovl_path_type(old); + err = -EXDEV; + if ((old_type == OVL_PATH_LOWER || old_type == OVL_PATH_MERGE) && is_dir) + goto out; + + if (new->d_inode) { + err = ovl_check_sticky(new); + if (err) + goto out; + + if (S_ISDIR(new->d_inode->i_mode)) + new_is_dir = true; + + new_type = ovl_path_type(new); + err = -EXDEV; + if (!overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) + goto out; + + err = 0; + if (new_type == OVL_PATH_LOWER && old_type == OVL_PATH_LOWER) { + if (ovl_dentry_lower(old)->d_inode == + ovl_dentry_lower(new)->d_inode) + goto out; + } + if (new_type != OVL_PATH_LOWER && old_type != OVL_PATH_LOWER) { + if (ovl_dentry_upper(old)->d_inode == + ovl_dentry_upper(new)->d_inode) + goto out; + } + } else { + if (ovl_dentry_is_opaque(new)) + new_type = OVL_PATH_UPPER; + else + new_type = OVL_PATH_PURE_UPPER; + } + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + err = ovl_copy_up(new->d_parent); + if (err) + goto out_drop_write; + if (!overwrite) { + err = ovl_copy_up(new); + if (err) + goto out_drop_write; + } + + old_opaque = old_type != OVL_PATH_PURE_UPPER; + new_opaque = new_type != OVL_PATH_PURE_UPPER; + + if (old_opaque || new_opaque) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + } + + if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) { + opaquedir = ovl_check_empty_and_clear(new, new_type); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) { + opaquedir = NULL; + goto out_revert_creds; + } + } + + if (overwrite) { + if (old_opaque) { + if (new->d_inode || !new_opaque) { + /* Whiteout source */ + flags |= RENAME_WHITEOUT; + } else { + /* Switch whiteouts */ + flags |= RENAME_EXCHANGE; + } + } else if (is_dir && !new->d_inode && new_opaque) { + flags |= RENAME_EXCHANGE; + cleanup_whiteout = true; + } + } + + old_upperdir = ovl_dentry_upper(old->d_parent); + new_upperdir = ovl_dentry_upper(new->d_parent); + + trap = lock_rename(new_upperdir, old_upperdir); + + olddentry = ovl_dentry_upper(old); + newdentry = ovl_dentry_upper(new); + if (newdentry) { + if (opaquedir) { + newdentry = opaquedir; + opaquedir = NULL; + } else { + dget(newdentry); + } + } else { + new_create = true; + newdentry = lookup_one_len(new->d_name.name, new_upperdir, + new->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + } + + err = -ESTALE; + if (olddentry->d_parent != old_upperdir) + goto out_dput; + if (newdentry->d_parent != new_upperdir) + goto out_dput; + if (olddentry == trap) + goto out_dput; + if (newdentry == trap) + goto out_dput; + + if (is_dir && !old_opaque && new_opaque) { + err = ovl_set_opaque(olddentry); + if (err) + goto out_dput; + } + if (!overwrite && new_is_dir && old_opaque && !new_opaque) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_dput; + } + + if (old_opaque || new_opaque) { + err = ovl_do_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + flags); + } else { + /* No debug for the plain case */ + BUG_ON(flags & ~RENAME_EXCHANGE); + err = vfs_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + NULL, flags); + } + + if (err) { + if (is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(newdentry); + goto out_dput; + } + + if (is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(newdentry); + + if (old_opaque != new_opaque) { + ovl_dentry_set_opaque(old, new_opaque); + if (!overwrite) + ovl_dentry_set_opaque(new, old_opaque); + } + + if (cleanup_whiteout) + ovl_cleanup(old_upperdir->d_inode, newdentry); + + ovl_dentry_version_inc(old->d_parent); + ovl_dentry_version_inc(new->d_parent); + +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(new_upperdir, old_upperdir); +out_revert_creds: + if (old_opaque || new_opaque) { + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(old); +out: + dput(opaquedir); + return err; +} + +const struct inode_operations ovl_dir_inode_operations = { + .lookup = ovl_lookup, + .mkdir = ovl_mkdir, + .symlink = ovl_symlink, + .unlink = ovl_unlink, + .rmdir = ovl_rmdir, + .rename2 = ovl_rename2, + .link = ovl_link, + .setattr = ovl_setattr, + .create = ovl_create, + .mknod = ovl_mknod, + .permission = ovl_permission, + .getattr = ovl_dir_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c new file mode 100644 index 000000000000..af2d18c9fcee --- /dev/null +++ b/fs/overlayfs/inode.c @@ -0,0 +1,425 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include "overlayfs.h" + +static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, + bool no_data) +{ + int err; + struct dentry *parent; + struct kstat stat; + struct path lowerpath; + + parent = dget_parent(dentry); + err = ovl_copy_up(parent); + if (err) + goto out_dput_parent; + + ovl_path_lower(dentry, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (err) + goto out_dput_parent; + + if (no_data) + stat.size = 0; + + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr); + +out_dput_parent: + dput(parent); + return err; +} + +int ovl_setattr(struct dentry *dentry, struct iattr *attr) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } else { + err = ovl_copy_up_last(dentry, attr, false); + } + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct path realpath; + + ovl_path_real(dentry, &realpath); + return vfs_getattr(&realpath, stat); +} + +int ovl_permission(struct inode *inode, int mask) +{ + struct ovl_entry *oe; + struct dentry *alias = NULL; + struct inode *realinode; + struct dentry *realdentry; + bool is_upper; + int err; + + if (S_ISDIR(inode->i_mode)) { + oe = inode->i_private; + } else if (mask & MAY_NOT_BLOCK) { + return -ECHILD; + } else { + /* + * For non-directories find an alias and get the info + * from there. + */ + alias = d_find_any_alias(inode); + if (WARN_ON(!alias)) + return -ENOENT; + + oe = alias->d_fsdata; + } + + realdentry = ovl_entry_real(oe, &is_upper); + + /* Careful in RCU walk mode */ + realinode = ACCESS_ONCE(realdentry->d_inode); + if (!realinode) { + WARN_ON(!(mask & MAY_NOT_BLOCK)); + err = -ENOENT; + goto out_dput; + } + + if (mask & MAY_WRITE) { + umode_t mode = realinode->i_mode; + + /* + * Writes will always be redirected to upper layer, so + * ignore lower layer being read-only. + * + * If the overlay itself is read-only then proceed + * with the permission check, don't return EROFS. + * This will only happen if this is the lower layer of + * another overlayfs. + * + * If upper fs becomes read-only after the overlay was + * constructed return EROFS to prevent modification of + * upper layer. + */ + err = -EROFS; + if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + goto out_dput; + } + + err = __inode_permission(realinode, mask); +out_dput: + dput(alias); + return err; +} + + +struct ovl_link_data { + struct dentry *realdentry; + void *cookie; +}; + +static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + void *ret; + struct dentry *realdentry; + struct inode *realinode; + + realdentry = ovl_dentry_real(dentry); + realinode = realdentry->d_inode; + + if (WARN_ON(!realinode->i_op->follow_link)) + return ERR_PTR(-EPERM); + + ret = realinode->i_op->follow_link(realdentry, nd); + if (IS_ERR(ret)) + return ret; + + if (realinode->i_op->put_link) { + struct ovl_link_data *data; + + data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); + if (!data) { + realinode->i_op->put_link(realdentry, nd, ret); + return ERR_PTR(-ENOMEM); + } + data->realdentry = realdentry; + data->cookie = ret; + + return data; + } else { + return NULL; + } +} + +static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c) +{ + struct inode *realinode; + struct ovl_link_data *data = c; + + if (!data) + return; + + realinode = data->realdentry->d_inode; + realinode->i_op->put_link(data->realdentry, nd, data->cookie); + kfree(data); +} + +static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + struct path realpath; + struct inode *realinode; + + ovl_path_real(dentry, &realpath); + realinode = realpath.dentry->d_inode; + + if (!realinode->i_op->readlink) + return -EINVAL; + + touch_atime(&realpath); + + return realinode->i_op->readlink(realpath.dentry, buf, bufsiz); +} + + +static bool ovl_is_private_xattr(const char *name) +{ + return strncmp(name, "trusted.overlay.", 14) == 0; +} + +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = -EPERM; + if (ovl_is_private_xattr(name)) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + upperdentry = ovl_dentry_upper(dentry); + err = vfs_setxattr(upperdentry, name, value, size, flags); + +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && + ovl_is_private_xattr(name)) + return -ENODATA; + + return vfs_getxattr(ovl_dentry_real(dentry), name, value, size); +} + +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) +{ + ssize_t res; + int off; + + res = vfs_listxattr(ovl_dentry_real(dentry), list, size); + if (res <= 0 || size == 0) + return res; + + if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE) + return res; + + /* filter out private xattrs */ + for (off = 0; off < res;) { + char *s = list + off; + size_t slen = strlen(s) + 1; + + BUG_ON(off + slen > res); + + if (ovl_is_private_xattr(s)) { + res -= slen; + memmove(s, s + slen, res - off); + } else { + off += slen; + } + } + + return res; +} + +int ovl_removexattr(struct dentry *dentry, const char *name) +{ + int err; + struct path realpath; + enum ovl_path_type type; + + err = ovl_want_write(dentry); + if (err) + goto out; + + if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && + ovl_is_private_xattr(name)) + goto out_drop_write; + + type = ovl_path_real(dentry, &realpath); + if (type == OVL_PATH_LOWER) { + err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (err < 0) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_removexattr(realpath.dentry, name); +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, + struct dentry *realdentry) +{ + if (type != OVL_PATH_LOWER) + return false; + + if (special_file(realdentry->d_inode->i_mode)) + return false; + + if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC)) + return false; + + return true; +} + +static int ovl_dentry_open(struct dentry *dentry, struct file *file, + const struct cred *cred) +{ + int err; + struct path realpath; + enum ovl_path_type type; + bool want_write = false; + + type = ovl_path_real(dentry, &realpath); + if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) { + want_write = true; + err = ovl_want_write(dentry); + if (err) + goto out; + + if (file->f_flags & O_TRUNC) + err = ovl_copy_up_last(dentry, NULL, true); + else + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_open(&realpath, file, cred); +out_drop_write: + if (want_write) + ovl_drop_write(dentry); +out: + return err; +} + +static const struct inode_operations ovl_file_inode_operations = { + .setattr = ovl_setattr, + .permission = ovl_permission, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, + .dentry_open = ovl_dentry_open, +}; + +static const struct inode_operations ovl_symlink_inode_operations = { + .setattr = ovl_setattr, + .follow_link = ovl_follow_link, + .put_link = ovl_put_link, + .readlink = ovl_readlink, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe) +{ + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return NULL; + + mode &= S_IFMT; + + inode->i_ino = get_next_ino(); + inode->i_mode = mode; + inode->i_flags |= S_NOATIME | S_NOCMTIME; + + switch (mode) { + case S_IFDIR: + inode->i_private = oe; + inode->i_op = &ovl_dir_inode_operations; + inode->i_fop = &ovl_dir_operations; + break; + + case S_IFLNK: + inode->i_op = &ovl_symlink_inode_operations; + break; + + case S_IFREG: + case S_IFSOCK: + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + inode->i_op = &ovl_file_inode_operations; + break; + + default: + WARN(1, "illegal file type: %i\n", mode); + iput(inode); + inode = NULL; + } + + return inode; + +} diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h new file mode 100644 index 000000000000..814bed33dd07 --- /dev/null +++ b/fs/overlayfs/overlayfs.h @@ -0,0 +1,191 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include + +struct ovl_entry; + +enum ovl_path_type { + OVL_PATH_PURE_UPPER, + OVL_PATH_UPPER, + OVL_PATH_MERGE, + OVL_PATH_LOWER, +}; + +extern const char *ovl_opaque_xattr; + +static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_rmdir(dir, dentry); + pr_debug("rmdir(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_unlink(dir, dentry, NULL); + pr_debug("unlink(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry, bool debug) +{ + int err = vfs_link(old_dentry, dir, new_dentry, NULL); + if (debug) { + pr_debug("link(%pd2, %pd2) = %i\n", + old_dentry, new_dentry, err); + } + return err; +} + +static inline int ovl_do_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_create(dir, dentry, mode, true); + if (debug) + pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_mkdir(dir, dentry, mode); + if (debug) + pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev, bool debug) +{ + int err = vfs_mknod(dir, dentry, mode, dev); + if (debug) { + pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", + dentry, mode, dev, err); + } + return err; +} + +static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry, + const char *oldname, bool debug) +{ + int err = vfs_symlink(dir, dentry, oldname); + if (debug) + pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); + return err; +} + +static inline int ovl_do_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err = vfs_setxattr(dentry, name, value, size, flags); + pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n", + dentry, name, (int) size, (char *) value, flags, err); + return err; +} + +static inline int ovl_do_removexattr(struct dentry *dentry, const char *name) +{ + int err = vfs_removexattr(dentry, name); + pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); + return err; +} + +static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, + struct inode *newdir, struct dentry *newdentry, + unsigned int flags) +{ + int err; + + pr_debug("rename2(%pd2, %pd2, 0x%x)\n", + olddentry, newdentry, flags); + + err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags); + + if (err) { + pr_debug("...rename2(%pd2, %pd2, ...) = %i\n", + olddentry, newdentry, err); + } + return err; +} + +static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_whiteout(dir, dentry); + pr_debug("whiteout(%pd2) = %i\n", dentry, err); + return err; +} + +enum ovl_path_type ovl_path_type(struct dentry *dentry); +u64 ovl_dentry_version_get(struct dentry *dentry); +void ovl_dentry_version_inc(struct dentry *dentry); +void ovl_path_upper(struct dentry *dentry, struct path *path); +void ovl_path_lower(struct dentry *dentry, struct path *path); +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); +struct dentry *ovl_dentry_upper(struct dentry *dentry); +struct dentry *ovl_dentry_lower(struct dentry *dentry); +struct dentry *ovl_dentry_real(struct dentry *dentry); +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper); +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry); +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache); +struct dentry *ovl_workdir(struct dentry *dentry); +int ovl_want_write(struct dentry *dentry); +void ovl_drop_write(struct dentry *dentry); +bool ovl_dentry_is_opaque(struct dentry *dentry); +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque); +bool ovl_is_whiteout(struct dentry *dentry); +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +struct file *ovl_path_open(struct path *path, int flags); + +struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry, + struct kstat *stat, const char *link); + +/* readdir.c */ +extern const struct file_operations ovl_dir_operations; +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list); +void ovl_cache_free(struct list_head *list); + +/* inode.c */ +int ovl_setattr(struct dentry *dentry, struct iattr *attr); +int ovl_permission(struct inode *inode, int mask); +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); +int ovl_removexattr(struct dentry *dentry, const char *name); + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe); +static inline void ovl_copyattr(struct inode *from, struct inode *to) +{ + to->i_uid = from->i_uid; + to->i_gid = from->i_gid; +} + +/* dir.c */ +extern const struct inode_operations ovl_dir_inode_operations; +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry); +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug); +void ovl_cleanup(struct inode *dir, struct dentry *dentry); + +/* copy_up.c */ +int ovl_copy_up(struct dentry *dentry); +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr); +int ovl_copy_xattr(struct dentry *old, struct dentry *new); +int ovl_set_attr(struct dentry *upper, struct kstat *stat); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c new file mode 100644 index 000000000000..c6787f84ece9 --- /dev/null +++ b/fs/overlayfs/readdir.c @@ -0,0 +1,587 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "overlayfs.h" + +struct ovl_cache_entry { + const char *name; + unsigned int len; + unsigned int type; + u64 ino; + bool is_whiteout; + struct list_head l_node; + struct rb_node node; +}; + +struct ovl_dir_cache { + long refcount; + u64 version; + struct list_head entries; +}; + +struct ovl_readdir_data { + struct dir_context ctx; + bool is_merge; + struct rb_root *root; + struct list_head *list; + struct list_head *middle; + int count; + int err; +}; + +struct ovl_dir_file { + bool is_real; + bool is_upper; + struct ovl_dir_cache *cache; + struct ovl_cache_entry cursor; + struct file *realfile; + struct file *upperfile; +}; + +static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) +{ + return container_of(n, struct ovl_cache_entry, node); +} + +static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, + const char *name, int len) +{ + struct rb_node *node = root->rb_node; + int cmp; + + while (node) { + struct ovl_cache_entry *p = ovl_cache_entry_from_node(node); + + cmp = strncmp(name, p->name, len); + if (cmp > 0) + node = p->node.rb_right; + else if (cmp < 0 || len < p->len) + node = p->node.rb_left; + else + return p; + } + + return NULL; +} + +static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len, + u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + + p = kmalloc(sizeof(*p) + len + 1, GFP_KERNEL); + if (p) { + char *name_copy = (char *) (p + 1); + memcpy(name_copy, name, len); + name_copy[len] = '\0'; + p->name = name_copy; + p->len = len; + p->type = d_type; + p->ino = ino; + p->is_whiteout = false; + } + + return p; +} + +static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, + const char *name, int len, u64 ino, + unsigned int d_type) +{ + struct rb_node **newp = &rdd->root->rb_node; + struct rb_node *parent = NULL; + struct ovl_cache_entry *p; + + while (*newp) { + int cmp; + struct ovl_cache_entry *tmp; + + parent = *newp; + tmp = ovl_cache_entry_from_node(*newp); + cmp = strncmp(name, tmp->name, len); + if (cmp > 0) + newp = &tmp->node.rb_right; + else if (cmp < 0 || len < tmp->len) + newp = &tmp->node.rb_left; + else + return 0; + } + + p = ovl_cache_entry_new(name, len, ino, d_type); + if (p == NULL) + return -ENOMEM; + + list_add_tail(&p->l_node, rdd->list); + rb_link_node(&p->node, parent, newp); + rb_insert_color(&p->node, rdd->root); + + return 0; +} + +static int ovl_fill_lower(struct ovl_readdir_data *rdd, + const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + + p = ovl_cache_entry_find(rdd->root, name, namelen); + if (p) { + list_move_tail(&p->l_node, rdd->middle); + } else { + p = ovl_cache_entry_new(name, namelen, ino, d_type); + if (p == NULL) + rdd->err = -ENOMEM; + else + list_add_tail(&p->l_node, rdd->middle); + } + + return rdd->err; +} + +void ovl_cache_free(struct list_head *list) +{ + struct ovl_cache_entry *p; + struct ovl_cache_entry *n; + + list_for_each_entry_safe(p, n, list, l_node) + kfree(p); + + INIT_LIST_HEAD(list); +} + +static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) +{ + struct ovl_dir_cache *cache = od->cache; + + list_del(&od->cursor.l_node); + WARN_ON(cache->refcount <= 0); + cache->refcount--; + if (!cache->refcount) { + if (ovl_dir_cache(dentry) == cache) + ovl_set_dir_cache(dentry, NULL); + + ovl_cache_free(&cache->entries); + kfree(cache); + } +} + +static int ovl_fill_merge(void *buf, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_readdir_data *rdd = buf; + + rdd->count++; + if (!rdd->is_merge) + return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type); + else + return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type); +} + +static inline int ovl_dir_read(struct path *realpath, + struct ovl_readdir_data *rdd) +{ + struct file *realfile; + int err; + + realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY); + if (IS_ERR(realfile)) + return PTR_ERR(realfile); + + rdd->ctx.pos = 0; + do { + rdd->count = 0; + rdd->err = 0; + err = iterate_dir(realfile, &rdd->ctx); + if (err >= 0) + err = rdd->err; + } while (!err && rdd->count); + fput(realfile); + + return err; +} + +static void ovl_dir_reset(struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + struct ovl_dir_cache *cache = od->cache; + struct dentry *dentry = file->f_path.dentry; + enum ovl_path_type type = ovl_path_type(dentry); + + if (cache && ovl_dentry_version_get(dentry) != cache->version) { + ovl_cache_put(od, dentry); + od->cache = NULL; + } + WARN_ON(!od->is_real && type != OVL_PATH_MERGE); + if (od->is_real && type == OVL_PATH_MERGE) + od->is_real = false; +} + +static int ovl_dir_mark_whiteouts(struct dentry *dir, + struct ovl_readdir_data *rdd) +{ + struct ovl_cache_entry *p; + struct dentry *dentry; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) { + ovl_cache_free(rdd->list); + return -ENOMEM; + } + + /* + * CAP_DAC_OVERRIDE for lookup + */ + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + old_cred = override_creds(override_cred); + + mutex_lock(&dir->d_inode->i_mutex); + list_for_each_entry(p, rdd->list, l_node) { + if (!p->name) + continue; + + if (p->type != DT_CHR) + continue; + + dentry = lookup_one_len(p->name, dir, p->len); + if (IS_ERR(dentry)) + continue; + + p->is_whiteout = ovl_is_whiteout(dentry); + dput(dentry); + } + mutex_unlock(&dir->d_inode->i_mutex); + + revert_creds(old_cred); + put_cred(override_cred); + + return 0; +} + +static inline int ovl_dir_read_merged(struct path *upperpath, + struct path *lowerpath, + struct list_head *list) +{ + int err; + struct rb_root root = RB_ROOT; + struct list_head middle; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_merge, + .list = list, + .root = &root, + .is_merge = false, + }; + + if (upperpath->dentry) { + err = ovl_dir_read(upperpath, &rdd); + if (err) + goto out; + + if (lowerpath->dentry) { + err = ovl_dir_mark_whiteouts(upperpath->dentry, &rdd); + if (err) + goto out; + } + } + if (lowerpath->dentry) { + /* + * Insert lowerpath entries before upperpath ones, this allows + * offsets to be reasonably constant + */ + list_add(&middle, rdd.list); + rdd.middle = &middle; + rdd.is_merge = true; + err = ovl_dir_read(lowerpath, &rdd); + list_del(&middle); + } +out: + return err; + +} + +static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) +{ + struct ovl_cache_entry *p; + loff_t off = 0; + + list_for_each_entry(p, &od->cache->entries, l_node) { + if (!p->name) + continue; + if (off >= pos) + break; + off++; + } + list_move_tail(&od->cursor.l_node, &p->l_node); +} + +static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) +{ + int res; + struct path lowerpath; + struct path upperpath; + struct ovl_dir_cache *cache; + + cache = ovl_dir_cache(dentry); + if (cache && ovl_dentry_version_get(dentry) == cache->version) { + cache->refcount++; + return cache; + } + ovl_set_dir_cache(dentry, NULL); + + cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); + if (!cache) + return ERR_PTR(-ENOMEM); + + cache->refcount = 1; + INIT_LIST_HEAD(&cache->entries); + + ovl_path_lower(dentry, &lowerpath); + ovl_path_upper(dentry, &upperpath); + + res = ovl_dir_read_merged(&upperpath, &lowerpath, &cache->entries); + if (res) { + ovl_cache_free(&cache->entries); + kfree(cache); + return ERR_PTR(res); + } + + cache->version = ovl_dentry_version_get(dentry); + ovl_set_dir_cache(dentry, cache); + + return cache; +} + +static int ovl_iterate(struct file *file, struct dir_context *ctx) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + + if (!ctx->pos) + ovl_dir_reset(file); + + if (od->is_real) + return iterate_dir(od->realfile, ctx); + + if (!od->cache) { + struct ovl_dir_cache *cache; + + cache = ovl_cache_get(dentry); + if (IS_ERR(cache)) + return PTR_ERR(cache); + + od->cache = cache; + ovl_seek_cursor(od, ctx->pos); + } + + while (od->cursor.l_node.next != &od->cache->entries) { + struct ovl_cache_entry *p; + + p = list_entry(od->cursor.l_node.next, struct ovl_cache_entry, l_node); + /* Skip cursors */ + if (p->name) { + if (!p->is_whiteout) { + if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) + break; + } + ctx->pos++; + } + list_move(&od->cursor.l_node, &p->l_node); + } + return 0; +} + +static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t res; + struct ovl_dir_file *od = file->private_data; + + mutex_lock(&file_inode(file)->i_mutex); + if (!file->f_pos) + ovl_dir_reset(file); + + if (od->is_real) { + res = vfs_llseek(od->realfile, offset, origin); + file->f_pos = od->realfile->f_pos; + } else { + res = -EINVAL; + + switch (origin) { + case SEEK_CUR: + offset += file->f_pos; + break; + case SEEK_SET: + break; + default: + goto out_unlock; + } + if (offset < 0) + goto out_unlock; + + if (offset != file->f_pos) { + file->f_pos = offset; + if (od->cache) + ovl_seek_cursor(od, offset); + } + res = offset; + } +out_unlock: + mutex_unlock(&file_inode(file)->i_mutex); + + return res; +} + +static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct file *realfile = od->realfile; + + /* + * Need to check if we started out being a lower dir, but got copied up + */ + if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) { + struct inode *inode = file_inode(file); + + mutex_lock(&inode->i_mutex); + realfile = od->upperfile; + if (!realfile) { + struct path upperpath; + + ovl_path_upper(dentry, &upperpath); + realfile = ovl_path_open(&upperpath, O_RDONLY); + if (IS_ERR(realfile)) { + mutex_unlock(&inode->i_mutex); + return PTR_ERR(realfile); + } + od->upperfile = realfile; + } + mutex_unlock(&inode->i_mutex); + } + + return vfs_fsync_range(realfile, start, end, datasync); +} + +static int ovl_dir_release(struct inode *inode, struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + + if (od->cache) { + mutex_lock(&inode->i_mutex); + ovl_cache_put(od, file->f_path.dentry); + mutex_unlock(&inode->i_mutex); + } + fput(od->realfile); + if (od->upperfile) + fput(od->upperfile); + kfree(od); + + return 0; +} + +static int ovl_dir_open(struct inode *inode, struct file *file) +{ + struct path realpath; + struct file *realfile; + struct ovl_dir_file *od; + enum ovl_path_type type; + + od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + if (!od) + return -ENOMEM; + + type = ovl_path_real(file->f_path.dentry, &realpath); + realfile = ovl_path_open(&realpath, file->f_flags); + if (IS_ERR(realfile)) { + kfree(od); + return PTR_ERR(realfile); + } + INIT_LIST_HEAD(&od->cursor.l_node); + od->realfile = realfile; + od->is_real = (type != OVL_PATH_MERGE); + od->is_upper = (type != OVL_PATH_LOWER); + file->private_data = od; + + return 0; +} + +const struct file_operations ovl_dir_operations = { + .read = generic_read_dir, + .open = ovl_dir_open, + .iterate = ovl_iterate, + .llseek = ovl_dir_llseek, + .fsync = ovl_dir_fsync, + .release = ovl_dir_release, +}; + +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) +{ + int err; + struct path lowerpath; + struct path upperpath; + struct ovl_cache_entry *p; + + ovl_path_upper(dentry, &upperpath); + ovl_path_lower(dentry, &lowerpath); + + err = ovl_dir_read_merged(&upperpath, &lowerpath, list); + if (err) + return err; + + err = 0; + + list_for_each_entry(p, list, l_node) { + if (p->is_whiteout) + continue; + + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + err = -ENOTEMPTY; + break; + } + + return err; +} + +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) +{ + struct ovl_cache_entry *p; + + mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_PARENT); + list_for_each_entry(p, list, l_node) { + struct dentry *dentry; + + if (!p->is_whiteout) + continue; + + dentry = lookup_one_len(p->name, upper, p->len); + if (IS_ERR(dentry)) { + pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n", + upper->d_name.name, p->len, p->name, + (int) PTR_ERR(dentry)); + continue; + } + ovl_cleanup(upper->d_inode, dentry); + dput(dentry); + } + mutex_unlock(&upper->d_inode->i_mutex); +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c new file mode 100644 index 000000000000..227710aad781 --- /dev/null +++ b/fs/overlayfs/super.c @@ -0,0 +1,727 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "overlayfs.h" + +MODULE_AUTHOR("Miklos Szeredi "); +MODULE_DESCRIPTION("Overlay filesystem"); +MODULE_LICENSE("GPL"); + +/* private information held for overlayfs's superblock */ +struct ovl_fs { + struct vfsmount *upper_mnt; + struct vfsmount *lower_mnt; + struct dentry *workdir; +}; + +struct ovl_dir_cache; + +/* private information held for every overlayfs dentry */ +struct ovl_entry { + struct dentry *__upperdentry; + struct dentry *lowerdentry; + struct ovl_dir_cache *cache; + union { + struct { + u64 version; + bool opaque; + }; + struct rcu_head rcu; + }; +}; + +const char *ovl_opaque_xattr = "trusted.overlay.opaque"; + + +enum ovl_path_type ovl_path_type(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe->__upperdentry) { + if (oe->lowerdentry) { + if (S_ISDIR(dentry->d_inode->i_mode)) + return OVL_PATH_MERGE; + else + return OVL_PATH_UPPER; + } else { + if (oe->opaque) + return OVL_PATH_UPPER; + else + return OVL_PATH_PURE_UPPER; + } + } else { + return OVL_PATH_LOWER; + } +} + +static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) +{ + struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry); + /* + * Make sure to order reads to upperdentry wrt ovl_dentry_update() + */ + smp_read_barrier_depends(); + return upperdentry; +} + +void ovl_path_upper(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->upper_mnt; + path->dentry = ovl_upperdentry_dereference(oe); +} + +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) +{ + + enum ovl_path_type type = ovl_path_type(dentry); + + if (type == OVL_PATH_LOWER) + ovl_path_lower(dentry, path); + else + ovl_path_upper(dentry, path); + + return type; +} + +struct dentry *ovl_dentry_upper(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return ovl_upperdentry_dereference(oe); +} + +struct dentry *ovl_dentry_lower(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->lowerdentry; +} + +struct dentry *ovl_dentry_real(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (!realdentry) + realdentry = oe->lowerdentry; + + return realdentry; +} + +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper) +{ + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (realdentry) { + *is_upper = true; + } else { + realdentry = oe->lowerdentry; + *is_upper = false; + } + return realdentry; +} + +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->cache; +} + +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + oe->cache = cache; +} + +void ovl_path_lower(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->lower_mnt; + path->dentry = oe->lowerdentry; +} + +int ovl_want_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return mnt_want_write(ofs->upper_mnt); +} + +void ovl_drop_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + mnt_drop_write(ofs->upper_mnt); +} + +struct dentry *ovl_workdir(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return ofs->workdir; +} + +bool ovl_dentry_is_opaque(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + return oe->opaque; +} + +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque) +{ + struct ovl_entry *oe = dentry->d_fsdata; + oe->opaque = opaque; +} + +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex)); + WARN_ON(oe->__upperdentry); + BUG_ON(!upperdentry->d_inode); + /* + * Make sure upperdentry is consistent before making it visible to + * ovl_upperdentry_dereference(). + */ + smp_wmb(); + oe->__upperdentry = upperdentry; +} + +void ovl_dentry_version_inc(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + oe->version++; +} + +u64 ovl_dentry_version_get(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + return oe->version; +} + +bool ovl_is_whiteout(struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + + return inode && IS_WHITEOUT(inode); +} + +static bool ovl_is_opaquedir(struct dentry *dentry) +{ + int res; + char val; + struct inode *inode = dentry->d_inode; + + if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr) + return false; + + res = inode->i_op->getxattr(dentry, ovl_opaque_xattr, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +static void ovl_dentry_release(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe) { + dput(oe->__upperdentry); + dput(oe->lowerdentry); + kfree_rcu(oe, rcu); + } +} + +static const struct dentry_operations ovl_dentry_operations = { + .d_release = ovl_dentry_release, +}; + +static struct ovl_entry *ovl_alloc_entry(void) +{ + return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL); +} + +static inline struct dentry *ovl_lookup_real(struct dentry *dir, + struct qstr *name) +{ + struct dentry *dentry; + + mutex_lock(&dir->d_inode->i_mutex); + dentry = lookup_one_len(name->name, dir, name->len); + mutex_unlock(&dir->d_inode->i_mutex); + + if (IS_ERR(dentry)) { + if (PTR_ERR(dentry) == -ENOENT) + dentry = NULL; + } else if (!dentry->d_inode) { + dput(dentry); + dentry = NULL; + } + return dentry; +} + +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct ovl_entry *oe; + struct dentry *upperdir; + struct dentry *lowerdir; + struct dentry *upperdentry = NULL; + struct dentry *lowerdentry = NULL; + struct inode *inode = NULL; + int err; + + err = -ENOMEM; + oe = ovl_alloc_entry(); + if (!oe) + goto out; + + upperdir = ovl_dentry_upper(dentry->d_parent); + lowerdir = ovl_dentry_lower(dentry->d_parent); + + if (upperdir) { + upperdentry = ovl_lookup_real(upperdir, &dentry->d_name); + err = PTR_ERR(upperdentry); + if (IS_ERR(upperdentry)) + goto out_put_dir; + + if (lowerdir && upperdentry) { + if (ovl_is_whiteout(upperdentry)) { + dput(upperdentry); + upperdentry = NULL; + oe->opaque = true; + } else if (ovl_is_opaquedir(upperdentry)) { + oe->opaque = true; + } + } + } + if (lowerdir && !oe->opaque) { + lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name); + err = PTR_ERR(lowerdentry); + if (IS_ERR(lowerdentry)) + goto out_dput_upper; + } + + if (lowerdentry && upperdentry && + (!S_ISDIR(upperdentry->d_inode->i_mode) || + !S_ISDIR(lowerdentry->d_inode->i_mode))) { + dput(lowerdentry); + lowerdentry = NULL; + oe->opaque = true; + } + + if (lowerdentry || upperdentry) { + struct dentry *realdentry; + + realdentry = upperdentry ? upperdentry : lowerdentry; + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode, + oe); + if (!inode) + goto out_dput; + ovl_copyattr(realdentry->d_inode, inode); + } + + oe->__upperdentry = upperdentry; + oe->lowerdentry = lowerdentry; + + dentry->d_fsdata = oe; + d_add(dentry, inode); + + return NULL; + +out_dput: + dput(lowerdentry); +out_dput_upper: + dput(upperdentry); +out_put_dir: + kfree(oe); +out: + return ERR_PTR(err); +} + +struct file *ovl_path_open(struct path *path, int flags) +{ + return dentry_open(path, flags, current_cred()); +} + +static void ovl_put_super(struct super_block *sb) +{ + struct ovl_fs *ufs = sb->s_fs_info; + + dput(ufs->workdir); + mntput(ufs->upper_mnt); + mntput(ufs->lower_mnt); + + kfree(ufs); +} + +static const struct super_operations ovl_super_operations = { + .put_super = ovl_put_super, +}; + +struct ovl_config { + char *lowerdir; + char *upperdir; + char *workdir; +}; + +enum { + OPT_LOWERDIR, + OPT_UPPERDIR, + OPT_WORKDIR, + OPT_ERR, +}; + +static const match_table_t ovl_tokens = { + {OPT_LOWERDIR, "lowerdir=%s"}, + {OPT_UPPERDIR, "upperdir=%s"}, + {OPT_WORKDIR, "workdir=%s"}, + {OPT_ERR, NULL} +}; + +static int ovl_parse_opt(char *opt, struct ovl_config *config) +{ + char *p; + + config->upperdir = NULL; + config->lowerdir = NULL; + config->workdir = NULL; + + while ((p = strsep(&opt, ",")) != NULL) { + int token; + substring_t args[MAX_OPT_ARGS]; + + if (!*p) + continue; + + token = match_token(p, ovl_tokens, args); + switch (token) { + case OPT_UPPERDIR: + kfree(config->upperdir); + config->upperdir = match_strdup(&args[0]); + if (!config->upperdir) + return -ENOMEM; + break; + + case OPT_LOWERDIR: + kfree(config->lowerdir); + config->lowerdir = match_strdup(&args[0]); + if (!config->lowerdir) + return -ENOMEM; + break; + + case OPT_WORKDIR: + kfree(config->workdir); + config->workdir = match_strdup(&args[0]); + if (!config->workdir) + return -ENOMEM; + break; + + default: + return -EINVAL; + } + } + return 0; +} + +#define OVL_WORKDIR_NAME "work" + +static struct dentry *ovl_workdir_create(struct vfsmount *mnt, + struct dentry *dentry) +{ + struct inode *dir = dentry->d_inode; + struct dentry *work; + int err; + bool retried = false; + + err = mnt_want_write(mnt); + if (err) + return ERR_PTR(err); + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); +retry: + work = lookup_one_len(OVL_WORKDIR_NAME, dentry, + strlen(OVL_WORKDIR_NAME)); + + if (!IS_ERR(work)) { + struct kstat stat = { + .mode = S_IFDIR | 0, + }; + + if (work->d_inode) { + err = -EEXIST; + if (retried) + goto out_dput; + + retried = true; + ovl_cleanup(dir, work); + dput(work); + goto retry; + } + + err = ovl_create_real(dir, work, &stat, NULL, NULL, true); + if (err) + goto out_dput; + } +out_unlock: + mutex_unlock(&dir->i_mutex); + mnt_drop_write(mnt); + + return work; + +out_dput: + dput(work); + work = ERR_PTR(err); + goto out_unlock; +} + +static int ovl_mount_dir(const char *name, struct path *path) +{ + int err; + + err = kern_path(name, LOOKUP_FOLLOW, path); + if (err) { + pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + err = -EINVAL; + } + return err; +} + +static bool ovl_is_allowed_fs_type(struct dentry *root) +{ + const struct dentry_operations *dop = root->d_op; + + /* + * We don't support: + * - automount filesystems + * - filesystems with revalidate (FIXME for lower layer) + * - filesystems with case insensitive names + */ + if (dop && + (dop->d_manage || dop->d_automount || + dop->d_revalidate || dop->d_weak_revalidate || + dop->d_compare || dop->d_hash)) { + return false; + } + return true; +} + +/* Workdir should not be subdir of upperdir and vice versa */ +static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) +{ + bool ok = false; + + if (workdir != upperdir) { + ok = (lock_rename(workdir, upperdir) == NULL); + unlock_rename(workdir, upperdir); + } + return ok; +} + +static int ovl_fill_super(struct super_block *sb, void *data, int silent) +{ + struct path lowerpath; + struct path upperpath; + struct path workpath; + struct inode *root_inode; + struct dentry *root_dentry; + struct ovl_entry *oe; + struct ovl_fs *ufs; + struct ovl_config config; + int err; + + err = ovl_parse_opt((char *) data, &config); + if (err) + goto out; + + /* FIXME: workdir is not needed for a R/O mount */ + err = -EINVAL; + if (!config.upperdir || !config.lowerdir || !config.workdir) { + pr_err("overlayfs: missing upperdir or lowerdir or workdir\n"); + goto out_free_config; + } + + err = -ENOMEM; + ufs = kmalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ufs) + goto out_free_config; + + oe = ovl_alloc_entry(); + if (oe == NULL) + goto out_free_ufs; + + err = ovl_mount_dir(config.upperdir, &upperpath); + if (err) + goto out_free_oe; + + err = ovl_mount_dir(config.lowerdir, &lowerpath); + if (err) + goto out_put_upperpath; + + err = ovl_mount_dir(config.workdir, &workpath); + if (err) + goto out_put_lowerpath; + + err = -EINVAL; + if (!S_ISDIR(upperpath.dentry->d_inode->i_mode) || + !S_ISDIR(lowerpath.dentry->d_inode->i_mode) || + !S_ISDIR(workpath.dentry->d_inode->i_mode)) { + pr_err("overlayfs: upperdir or lowerdir or workdir not a directory\n"); + goto out_put_workpath; + } + + if (upperpath.mnt != workpath.mnt) { + pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); + goto out_put_workpath; + } + if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) { + pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); + goto out_put_workpath; + } + + if (!ovl_is_allowed_fs_type(upperpath.dentry)) { + pr_err("overlayfs: filesystem of upperdir is not supported\n"); + goto out_put_workpath; + } + + if (!ovl_is_allowed_fs_type(lowerpath.dentry)) { + pr_err("overlayfs: filesystem of lowerdir is not supported\n"); + goto out_put_workpath; + } + + ufs->upper_mnt = clone_private_mount(&upperpath); + err = PTR_ERR(ufs->upper_mnt); + if (IS_ERR(ufs->upper_mnt)) { + pr_err("overlayfs: failed to clone upperpath\n"); + goto out_put_workpath; + } + + ufs->lower_mnt = clone_private_mount(&lowerpath); + err = PTR_ERR(ufs->lower_mnt); + if (IS_ERR(ufs->lower_mnt)) { + pr_err("overlayfs: failed to clone lowerpath\n"); + goto out_put_upper_mnt; + } + + ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); + err = PTR_ERR(ufs->workdir); + if (IS_ERR(ufs->workdir)) { + pr_err("overlayfs: failed to create directory %s/%s\n", + config.workdir, OVL_WORKDIR_NAME); + goto out_put_lower_mnt; + } + + /* + * Make lower_mnt R/O. That way fchmod/fchown on lower file + * will fail instead of modifying lower fs. + */ + ufs->lower_mnt->mnt_flags |= MNT_READONLY; + + /* If the upper fs is r/o, we mark overlayfs r/o too */ + if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY) + sb->s_flags |= MS_RDONLY; + + sb->s_d_op = &ovl_dentry_operations; + + err = -ENOMEM; + root_inode = ovl_new_inode(sb, S_IFDIR, oe); + if (!root_inode) + goto out_put_workdir; + + root_dentry = d_make_root(root_inode); + if (!root_dentry) + goto out_put_workdir; + + mntput(upperpath.mnt); + mntput(lowerpath.mnt); + path_put(&workpath); + + oe->__upperdentry = upperpath.dentry; + oe->lowerdentry = lowerpath.dentry; + + root_dentry->d_fsdata = oe; + + sb->s_op = &ovl_super_operations; + sb->s_root = root_dentry; + sb->s_fs_info = ufs; + + return 0; + +out_put_workdir: + dput(ufs->workdir); +out_put_lower_mnt: + mntput(ufs->lower_mnt); +out_put_upper_mnt: + mntput(ufs->upper_mnt); +out_put_workpath: + path_put(&workpath); +out_put_lowerpath: + path_put(&lowerpath); +out_put_upperpath: + path_put(&upperpath); +out_free_oe: + kfree(oe); +out_free_ufs: + kfree(ufs); +out_free_config: + kfree(config.lowerdir); + kfree(config.upperdir); + kfree(config.workdir); +out: + return err; +} + +static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + return mount_nodev(fs_type, flags, raw_data, ovl_fill_super); +} + +static struct file_system_type ovl_fs_type = { + .owner = THIS_MODULE, + .name = "overlayfs", + .mount = ovl_mount, + .kill_sb = kill_anon_super, +}; +MODULE_ALIAS_FS("overlayfs"); + +static int __init ovl_init(void) +{ + return register_filesystem(&ovl_fs_type); +} + +static void __exit ovl_exit(void) +{ + unregister_filesystem(&ovl_fs_type); +} + +module_init(ovl_init); +module_exit(ovl_exit); From cc2596392af3b1404421aaef828a255303c46f93 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Fri, 24 Oct 2014 00:14:38 +0200 Subject: [PATCH 11/14] overlayfs: add statfs support Add support for statfs to the overlayfs filesystem. As the upper layer is the target of all write operations assume that the space in that filesystem is the space in the overlayfs. There will be some inaccuracy as overwriting a file will copy it up and consume space we were not expecting, but it is better than nothing. Use the upper layer dentry and mount from the overlayfs root inode, passing the statfs call to that filesystem. Signed-off-by: Andy Whitcroft Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 227710aad781..aaf562b9f937 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -16,17 +16,21 @@ #include #include #include +#include #include "overlayfs.h" MODULE_AUTHOR("Miklos Szeredi "); MODULE_DESCRIPTION("Overlay filesystem"); MODULE_LICENSE("GPL"); +#define OVERLAYFS_SUPER_MAGIC 0x794c764f + /* private information held for overlayfs's superblock */ struct ovl_fs { struct vfsmount *upper_mnt; struct vfsmount *lower_mnt; struct dentry *workdir; + long lower_namelen; }; struct ovl_dir_cache; @@ -383,8 +387,35 @@ static void ovl_put_super(struct super_block *sb) kfree(ufs); } +/** + * ovl_statfs + * @sb: The overlayfs super block + * @buf: The struct kstatfs to fill in with stats + * + * Get the filesystem statistics. As writes always target the upper layer + * filesystem pass the statfs to the same filesystem. + */ +static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct dentry *root_dentry = dentry->d_sb->s_root; + struct path path; + int err; + + ovl_path_upper(root_dentry, &path); + + err = vfs_statfs(&path, buf); + if (!err) { + buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen); + buf->f_type = OVERLAYFS_SUPER_MAGIC; + } + + return err; +} + static const struct super_operations ovl_super_operations = { .put_super = ovl_put_super, + .statfs = ovl_statfs, }; struct ovl_config { @@ -556,6 +587,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) struct ovl_entry *oe; struct ovl_fs *ufs; struct ovl_config config; + struct kstatfs statfs; int err; err = ovl_parse_opt((char *) data, &config); @@ -617,6 +649,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_put_workpath; } + err = vfs_statfs(&lowerpath, &statfs); + if (err) { + pr_err("overlayfs: statfs failed on lowerpath\n"); + goto out_put_workpath; + } + ufs->lower_namelen = statfs.f_namelen; + ufs->upper_mnt = clone_private_mount(&upperpath); err = PTR_ERR(ufs->upper_mnt); if (IS_ERR(ufs->upper_mnt)) { @@ -669,6 +708,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; + sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; sb->s_root = root_dentry; sb->s_fs_info = ufs; From f45827e84186af152492c6d0dcf4105b4a605f9b Mon Sep 17 00:00:00 2001 From: Erez Zadok Date: Fri, 24 Oct 2014 00:14:38 +0200 Subject: [PATCH 12/14] overlayfs: implement show_options This is useful because of the stacking nature of overlayfs. Users like to find out (via /proc/mounts) which lower/upper directory were used at mount time. AV: even failing ovl_parse_opt() could've done some kstrdup() AV: failure of ovl_alloc_entry() should end up with ENOMEM, not EINVAL Signed-off-by: Erez Zadok Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 76 ++++++++++++++++++++++++++++---------------- 1 file changed, 48 insertions(+), 28 deletions(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index aaf562b9f937..7dcc24e84417 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "overlayfs.h" MODULE_AUTHOR("Miklos Szeredi "); @@ -25,12 +26,20 @@ MODULE_LICENSE("GPL"); #define OVERLAYFS_SUPER_MAGIC 0x794c764f +struct ovl_config { + char *lowerdir; + char *upperdir; + char *workdir; +}; + /* private information held for overlayfs's superblock */ struct ovl_fs { struct vfsmount *upper_mnt; struct vfsmount *lower_mnt; struct dentry *workdir; long lower_namelen; + /* pathnames of lower and upper dirs, for show_options */ + struct ovl_config config; }; struct ovl_dir_cache; @@ -384,6 +393,9 @@ static void ovl_put_super(struct super_block *sb) mntput(ufs->upper_mnt); mntput(ufs->lower_mnt); + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); kfree(ufs); } @@ -413,15 +425,27 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) return err; } +/** + * ovl_show_options + * + * Prints the mount options for a given superblock. + * Returns zero; does not fail. + */ +static int ovl_show_options(struct seq_file *m, struct dentry *dentry) +{ + struct super_block *sb = dentry->d_sb; + struct ovl_fs *ufs = sb->s_fs_info; + + seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir); + seq_printf(m, ",upperdir=%s", ufs->config.upperdir); + seq_printf(m, ",workdir=%s", ufs->config.workdir); + return 0; +} + static const struct super_operations ovl_super_operations = { .put_super = ovl_put_super, .statfs = ovl_statfs, -}; - -struct ovl_config { - char *lowerdir; - char *upperdir; - char *workdir; + .show_options = ovl_show_options, }; enum { @@ -442,10 +466,6 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; - config->upperdir = NULL; - config->lowerdir = NULL; - config->workdir = NULL; - while ((p = strsep(&opt, ",")) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -586,39 +606,40 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) struct dentry *root_dentry; struct ovl_entry *oe; struct ovl_fs *ufs; - struct ovl_config config; struct kstatfs statfs; int err; - err = ovl_parse_opt((char *) data, &config); - if (err) + err = -ENOMEM; + ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ufs) goto out; + err = ovl_parse_opt((char *) data, &ufs->config); + if (err) + goto out_free_config; + /* FIXME: workdir is not needed for a R/O mount */ err = -EINVAL; - if (!config.upperdir || !config.lowerdir || !config.workdir) { + if (!ufs->config.upperdir || !ufs->config.lowerdir || + !ufs->config.workdir) { pr_err("overlayfs: missing upperdir or lowerdir or workdir\n"); goto out_free_config; } err = -ENOMEM; - ufs = kmalloc(sizeof(struct ovl_fs), GFP_KERNEL); - if (!ufs) - goto out_free_config; - oe = ovl_alloc_entry(); if (oe == NULL) - goto out_free_ufs; + goto out_free_config; - err = ovl_mount_dir(config.upperdir, &upperpath); + err = ovl_mount_dir(ufs->config.upperdir, &upperpath); if (err) goto out_free_oe; - err = ovl_mount_dir(config.lowerdir, &lowerpath); + err = ovl_mount_dir(ufs->config.lowerdir, &lowerpath); if (err) goto out_put_upperpath; - err = ovl_mount_dir(config.workdir, &workpath); + err = ovl_mount_dir(ufs->config.workdir, &workpath); if (err) goto out_put_lowerpath; @@ -674,7 +695,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) err = PTR_ERR(ufs->workdir); if (IS_ERR(ufs->workdir)) { pr_err("overlayfs: failed to create directory %s/%s\n", - config.workdir, OVL_WORKDIR_NAME); + ufs->config.workdir, OVL_WORKDIR_NAME); goto out_put_lower_mnt; } @@ -729,12 +750,11 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) path_put(&upperpath); out_free_oe: kfree(oe); -out_free_ufs: - kfree(ufs); out_free_config: - kfree(config.lowerdir); - kfree(config.upperdir); - kfree(config.workdir); + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); + kfree(ufs); out: return err; } From 7c37fbda85ceb9be7bdb9d5f53e702efc40cf783 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Fri, 24 Oct 2014 00:14:39 +0200 Subject: [PATCH 13/14] overlay: overlay filesystem documentation Document the overlay filesystem. Signed-off-by: Miklos Szeredi --- Documentation/filesystems/overlayfs.txt | 198 ++++++++++++++++++++++++ MAINTAINERS | 7 + 2 files changed, 205 insertions(+) create mode 100644 Documentation/filesystems/overlayfs.txt diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt new file mode 100644 index 000000000000..530850a72735 --- /dev/null +++ b/Documentation/filesystems/overlayfs.txt @@ -0,0 +1,198 @@ +Written by: Neil Brown + +Overlay Filesystem +================== + +This document describes a prototype for a new approach to providing +overlay-filesystem functionality in Linux (sometimes referred to as +union-filesystems). An overlay-filesystem tries to present a +filesystem which is the result over overlaying one filesystem on top +of the other. + +The result will inevitably fail to look exactly like a normal +filesystem for various technical reasons. The expectation is that +many use cases will be able to ignore these differences. + +This approach is 'hybrid' because the objects that appear in the +filesystem do not all appear to belong to that filesystem. In many +cases an object accessed in the union will be indistinguishable +from accessing the corresponding object from the original filesystem. +This is most obvious from the 'st_dev' field returned by stat(2). + +While directories will report an st_dev from the overlay-filesystem, +all non-directory objects will report an st_dev from the lower or +upper filesystem that is providing the object. Similarly st_ino will +only be unique when combined with st_dev, and both of these can change +over the lifetime of a non-directory object. Many applications and +tools ignore these values and will not be affected. + +Upper and Lower +--------------- + +An overlay filesystem combines two filesystems - an 'upper' filesystem +and a 'lower' filesystem. When a name exists in both filesystems, the +object in the 'upper' filesystem is visible while the object in the +'lower' filesystem is either hidden or, in the case of directories, +merged with the 'upper' object. + +It would be more correct to refer to an upper and lower 'directory +tree' rather than 'filesystem' as it is quite possible for both +directory trees to be in the same filesystem and there is no +requirement that the root of a filesystem be given for either upper or +lower. + +The lower filesystem can be any filesystem supported by Linux and does +not need to be writable. The lower filesystem can even be another +overlayfs. The upper filesystem will normally be writable and if it +is it must support the creation of trusted.* extended attributes, and +must provide valid d_type in readdir responses, so NFS is not suitable. + +A read-only overlay of two read-only filesystems may use any +filesystem type. + +Directories +----------- + +Overlaying mainly involves directories. If a given name appears in both +upper and lower filesystems and refers to a non-directory in either, +then the lower object is hidden - the name refers only to the upper +object. + +Where both upper and lower objects are directories, a merged directory +is formed. + +At mount time, the two directories given as mount options "lowerdir" and +"upperdir" are combined into a merged directory: + + mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper,\ +workdir=/work /merged + +The "workdir" needs to be an empty directory on the same filesystem +as upperdir. + +Then whenever a lookup is requested in such a merged directory, the +lookup is performed in each actual directory and the combined result +is cached in the dentry belonging to the overlay filesystem. If both +actual lookups find directories, both are stored and a merged +directory is created, otherwise only one is stored: the upper if it +exists, else the lower. + +Only the lists of names from directories are merged. Other content +such as metadata and extended attributes are reported for the upper +directory only. These attributes of the lower directory are hidden. + +whiteouts and opaque directories +-------------------------------- + +In order to support rm and rmdir without changing the lower +filesystem, an overlay filesystem needs to record in the upper filesystem +that files have been removed. This is done using whiteouts and opaque +directories (non-directories are always opaque). + +A whiteout is created as a character device with 0/0 device number. +When a whiteout is found in the upper level of a merged directory, any +matching name in the lower level is ignored, and the whiteout itself +is also hidden. + +A directory is made opaque by setting the xattr "trusted.overlay.opaque" +to "y". Where the upper filesystem contains an opaque directory, any +directory in the lower filesystem with the same name is ignored. + +readdir +------- + +When a 'readdir' request is made on a merged directory, the upper and +lower directories are each read and the name lists merged in the +obvious way (upper is read first, then lower - entries that already +exist are not re-added). This merged name list is cached in the +'struct file' and so remains as long as the file is kept open. If the +directory is opened and read by two processes at the same time, they +will each have separate caches. A seekdir to the start of the +directory (offset 0) followed by a readdir will cause the cache to be +discarded and rebuilt. + +This means that changes to the merged directory do not appear while a +directory is being read. This is unlikely to be noticed by many +programs. + +seek offsets are assigned sequentially when the directories are read. +Thus if + - read part of a directory + - remember an offset, and close the directory + - re-open the directory some time later + - seek to the remembered offset + +there may be little correlation between the old and new locations in +the list of filenames, particularly if anything has changed in the +directory. + +Readdir on directories that are not merged is simply handled by the +underlying directory (upper or lower). + + +Non-directories +--------------- + +Objects that are not directories (files, symlinks, device-special +files etc.) are presented either from the upper or lower filesystem as +appropriate. When a file in the lower filesystem is accessed in a way +the requires write-access, such as opening for write access, changing +some metadata etc., the file is first copied from the lower filesystem +to the upper filesystem (copy_up). Note that creating a hard-link +also requires copy_up, though of course creation of a symlink does +not. + +The copy_up may turn out to be unnecessary, for example if the file is +opened for read-write but the data is not modified. + +The copy_up process first makes sure that the containing directory +exists in the upper filesystem - creating it and any parents as +necessary. It then creates the object with the same metadata (owner, +mode, mtime, symlink-target etc.) and then if the object is a file, the +data is copied from the lower to the upper filesystem. Finally any +extended attributes are copied up. + +Once the copy_up is complete, the overlay filesystem simply +provides direct access to the newly created file in the upper +filesystem - future operations on the file are barely noticed by the +overlay filesystem (though an operation on the name of the file such as +rename or unlink will of course be noticed and handled). + + +Non-standard behavior +--------------------- + +The copy_up operation essentially creates a new, identical file and +moves it over to the old name. The new file may be on a different +filesystem, so both st_dev and st_ino of the file may change. + +Any open files referring to this inode will access the old data and +metadata. Similarly any file locks obtained before copy_up will not +apply to the copied up file. + +On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and +fsetxattr(2) will fail with EROFS. + +If a file with multiple hard links is copied up, then this will +"break" the link. Changes will not be propagated to other names +referring to the same inode. + +Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory +object in overlayfs will not contain valid absolute paths, only +relative paths leading up to the filesystem's root. This will be +fixed in the future. + +Some operations are not atomic, for example a crash during copy_up or +rename will leave the filesystem in an inconsistent state. This will +be addressed in the future. + +Changes to underlying filesystems +--------------------------------- + +Offline changes, when the overlay is not mounted, are allowed to either +the upper or the lower trees. + +Changes to the underlying filesystems while part of a mounted overlay +filesystem are not allowed. If the underlying filesystem is changed, +the behavior of the overlay is undefined, though it will not result in +a crash or deadlock. diff --git a/MAINTAINERS b/MAINTAINERS index a20df9bf8ab0..aa974d445bfd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6832,6 +6832,13 @@ F: drivers/scsi/osd/ F: include/scsi/osd_* F: fs/exofs/ +OVERLAYFS FILESYSTEM +M: Miklos Szeredi +L: linux-fsdevel@vger.kernel.org +S: Supported +F: fs/overlayfs/* +F: Documentation/filesystems/overlayfs.txt + P54 WIRELESS DRIVER M: Christian Lamparter L: linux-wireless@vger.kernel.org From 69c433ed2ecd2d3264efd7afec4439524b319121 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 24 Oct 2014 00:14:39 +0200 Subject: [PATCH 14/14] fs: limit filesystem stacking depth Add a simple read-only counter to super_block that indicates how deep this is in the stack of filesystems. Previously ecryptfs was the only stackable filesystem and it explicitly disallowed multiple layers of itself. Overlayfs, however, can be stacked recursively and also may be stacked on top of ecryptfs or vice versa. To limit the kernel stack usage we must limit the depth of the filesystem stack. Initially the limit is set to 2. Signed-off-by: Miklos Szeredi --- fs/ecryptfs/main.c | 7 +++++++ fs/overlayfs/super.c | 9 +++++++++ include/linux/fs.h | 11 +++++++++++ 3 files changed, 27 insertions(+) diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1b119d3bf924..c4cd1fd86cc2 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -566,6 +566,13 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; s->s_magic = ECRYPTFS_SUPER_MAGIC; + s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1; + + rc = -EINVAL; + if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("eCryptfs: maximum fs stacking depth exceeded\n"); + goto out_free; + } inode = ecryptfs_get_inode(path.dentry->d_inode, s); rc = PTR_ERR(inode); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 7dcc24e84417..08b704cebfc4 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -677,6 +677,15 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } ufs->lower_namelen = statfs.f_namelen; + sb->s_stack_depth = max(upperpath.mnt->mnt_sb->s_stack_depth, + lowerpath.mnt->mnt_sb->s_stack_depth) + 1; + + err = -EINVAL; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("overlayfs: maximum fs stacking depth exceeded\n"); + goto out_put_workpath; + } + ufs->upper_mnt = clone_private_mount(&upperpath); err = PTR_ERR(ufs->upper_mnt); if (IS_ERR(ufs->upper_mnt)) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 69118b3cb917..4e41a4a331bb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -261,6 +261,12 @@ struct iattr { */ #include +/* + * Maximum number of layers of fs stack. Needs to be limited to + * prevent kernel stack overflow + */ +#define FILESYSTEM_MAX_STACK_DEPTH 2 + /** * enum positive_aop_returns - aop return codes with specific semantics * @@ -1273,6 +1279,11 @@ struct super_block { struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; struct list_lru s_inode_lru ____cacheline_aligned_in_smp; struct rcu_head rcu; + + /* + * Indicates how deep in a filesystem stack this SB is + */ + int s_stack_depth; }; extern struct timespec current_fs_time(struct super_block *sb);