diff options
Diffstat (limited to 'fs/overlayfs')
| -rw-r--r-- | fs/overlayfs/file.c | 170 | ||||
| -rw-r--r-- | fs/overlayfs/inode.c | 60 | ||||
| -rw-r--r-- | fs/overlayfs/namei.c | 8 | ||||
| -rw-r--r-- | fs/overlayfs/overlayfs.h | 3 | ||||
| -rw-r--r-- | fs/overlayfs/ovl_entry.h | 6 | ||||
| -rw-r--r-- | fs/overlayfs/super.c | 161 | ||||
| -rw-r--r-- | fs/overlayfs/util.c | 12 |
7 files changed, 373 insertions, 47 deletions
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 0c810f20f778..0bd276e4ccbe 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -11,6 +11,7 @@ #include <linux/mount.h> #include <linux/xattr.h> #include <linux/uio.h> +#include <linux/uaccess.h> #include "overlayfs.h" static char ovl_whatisit(struct inode *inode, struct inode *realinode) @@ -29,10 +30,11 @@ static struct file *ovl_open_realfile(const struct file *file, struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; + int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY; old_cred = ovl_override_creds(inode->i_sb); - realfile = open_with_fake_path(&file->f_path, file->f_flags | O_NOATIME, - realinode, current_cred()); + realfile = open_with_fake_path(&file->f_path, flags, realinode, + current_cred()); revert_creds(old_cred); pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n", @@ -50,7 +52,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags) int err; /* No atime modificaton on underlying */ - flags |= O_NOATIME; + flags |= O_NOATIME | FMODE_NONOTIFY; /* If some flag changed that cannot be changed then something's amiss */ if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK)) @@ -144,11 +146,47 @@ static int ovl_release(struct inode *inode, struct file *file) static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) { - struct inode *realinode = ovl_inode_real(file_inode(file)); + struct inode *inode = file_inode(file); + struct fd real; + const struct cred *old_cred; + ssize_t ret; + + /* + * The two special cases below do not need to involve real fs, + * so we can optimizing concurrent callers. + */ + if (offset == 0) { + if (whence == SEEK_CUR) + return file->f_pos; + + if (whence == SEEK_SET) + return vfs_setpos(file, 0, 0); + } + + ret = ovl_real_fdget(file, &real); + if (ret) + return ret; + + /* + * Overlay file f_pos is the master copy that is preserved + * through copy up and modified on read/write, but only real + * fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose + * limitations that are more strict than ->s_maxbytes for specific + * files, so we use the real file to perform seeks. + */ + inode_lock(inode); + real.file->f_pos = file->f_pos; - return generic_file_llseek_size(file, offset, whence, - realinode->i_sb->s_maxbytes, - i_size_read(realinode)); + old_cred = ovl_override_creds(inode->i_sb); + ret = vfs_llseek(real.file, offset, whence); + revert_creds(old_cred); + + file->f_pos = real.file->f_pos; + inode_unlock(inode); + + fdput(real); + + return ret; } static void ovl_file_accessed(struct file *file) @@ -371,34 +409,118 @@ static long ovl_real_ioctl(struct file *file, unsigned int cmd, return ret; } -static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long ovl_ioctl_set_flags(struct file *file, unsigned int cmd, + unsigned long arg, unsigned int iflags) { long ret; struct inode *inode = file_inode(file); + unsigned int old_iflags; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + ret = mnt_want_write_file(file); + if (ret) + return ret; + + inode_lock(inode); + + /* Check the capability before cred override */ + ret = -EPERM; + old_iflags = READ_ONCE(inode->i_flags); + if (((iflags ^ old_iflags) & (S_APPEND | S_IMMUTABLE)) && + !capable(CAP_LINUX_IMMUTABLE)) + goto unlock; + + ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY); + if (ret) + goto unlock; + + ret = ovl_real_ioctl(file, cmd, arg); + + ovl_copyflags(ovl_inode_real(inode), inode); +unlock: + inode_unlock(inode); + + mnt_drop_write_file(file); + + return ret; + +} + +static unsigned int ovl_fsflags_to_iflags(unsigned int flags) +{ + unsigned int iflags = 0; + + if (flags & FS_SYNC_FL) + iflags |= S_SYNC; + if (flags & FS_APPEND_FL) + iflags |= S_APPEND; + if (flags & FS_IMMUTABLE_FL) + iflags |= S_IMMUTABLE; + if (flags & FS_NOATIME_FL) + iflags |= S_NOATIME; + + return iflags; +} + +static long ovl_ioctl_set_fsflags(struct file *file, unsigned int cmd, + unsigned long arg) +{ + unsigned int flags; + + if (get_user(flags, (int __user *) arg)) + return -EFAULT; + + return ovl_ioctl_set_flags(file, cmd, arg, + ovl_fsflags_to_iflags(flags)); +} + +static unsigned int ovl_fsxflags_to_iflags(unsigned int xflags) +{ + unsigned int iflags = 0; + + if (xflags & FS_XFLAG_SYNC) + iflags |= S_SYNC; + if (xflags & FS_XFLAG_APPEND) + iflags |= S_APPEND; + if (xflags & FS_XFLAG_IMMUTABLE) + iflags |= S_IMMUTABLE; + if (xflags & FS_XFLAG_NOATIME) + iflags |= S_NOATIME; + + return iflags; +} + +static long ovl_ioctl_set_fsxflags(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct fsxattr fa; + + memset(&fa, 0, sizeof(fa)); + if (copy_from_user(&fa, (void __user *) arg, sizeof(fa))) + return -EFAULT; + + return ovl_ioctl_set_flags(file, cmd, arg, + ovl_fsxflags_to_iflags(fa.fsx_xflags)); +} + +static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long ret; switch (cmd) { case FS_IOC_GETFLAGS: + case FS_IOC_FSGETXATTR: ret = ovl_real_ioctl(file, cmd, arg); break; case FS_IOC_SETFLAGS: - if (!inode_owner_or_capable(inode)) - return -EACCES; - - ret = mnt_want_write_file(file); - if (ret) - return ret; - - ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY); - if (!ret) { - ret = ovl_real_ioctl(file, cmd, arg); - - inode_lock(inode); - ovl_copyflags(ovl_inode_real(inode), inode); - inode_unlock(inode); - } + ret = ovl_ioctl_set_fsflags(file, cmd, arg); + break; - mnt_drop_write_file(file); + case FS_IOC_FSSETXATTR: + ret = ovl_ioctl_set_fsxflags(file, cmd, arg); break; default: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b48273e846ad..f0389849fd80 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -553,15 +553,15 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, int xinobits = ovl_xino_bits(inode->i_sb); /* - * When NFS export is enabled and d_ino is consistent with st_ino - * (samefs or i_ino has enough bits to encode layer), set the same - * value used for d_ino to i_ino, because nfsd readdirplus compares - * d_ino values to i_ino values of child entries. When called from + * When d_ino is consistent with st_ino (samefs or i_ino has enough + * bits to encode layer), set the same value used for st_ino to i_ino, + * so inode number exposed via /proc/locks and a like will be + * consistent with d_ino and st_ino values. An i_ino value inconsistent + * with d_ino also causes nfsd readdirplus to fail. When called from * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). */ - if (inode->i_sb->s_export_op && - (ovl_same_sb(inode->i_sb) || xinobits)) { + if (ovl_same_sb(inode->i_sb) || xinobits) { inode->i_ino = ino; if (xinobits && fsid && !(ino >> (64 - xinobits))) inode->i_ino |= (unsigned long)fsid << (64 - xinobits); @@ -777,6 +777,54 @@ struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, return inode; } +bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir) +{ + struct inode *key = d_inode(dir); + struct inode *trap; + bool res; + + trap = ilookup5(sb, (unsigned long) key, ovl_inode_test, key); + if (!trap) + return false; + + res = IS_DEADDIR(trap) && !ovl_inode_upper(trap) && + !ovl_inode_lower(trap); + + iput(trap); + return res; +} + +/* + * Create an inode cache entry for layer root dir, that will intentionally + * fail ovl_verify_inode(), so any lookup that will find some layer root + * will fail. + */ +struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir) +{ + struct inode *key = d_inode(dir); + struct inode *trap; + + if (!d_is_dir(dir)) + return ERR_PTR(-ENOTDIR); + + trap = iget5_locked(sb, (unsigned long) key, ovl_inode_test, + ovl_inode_set, key); + if (!trap) + return ERR_PTR(-ENOMEM); + + if (!(trap->i_state & I_NEW)) { + /* Conflicting layer roots? */ + iput(trap); + return ERR_PTR(-ELOOP); + } + + trap->i_mode = S_IFDIR; + trap->i_flags = S_DEAD; + unlock_new_inode(trap); + + return trap; +} + /* * Does overlay inode need to be hashed by lower inode? */ diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index efd372312ef1..badf039267a2 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -18,6 +18,7 @@ #include "overlayfs.h" struct ovl_lookup_data { + struct super_block *sb; struct qstr name; bool is_dir; bool opaque; @@ -244,6 +245,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, if (!d->metacopy || d->last) goto out; } else { + if (ovl_lookup_trap_inode(d->sb, this)) { + /* Caught in a trap of overlapping layers */ + err = -ELOOP; + goto out_err; + } + if (last_element) d->is_dir = true; if (d->last) @@ -819,6 +826,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, int err; bool metacopy = false; struct ovl_lookup_data d = { + .sb = dentry->d_sb, .name = dentry->d_name, .is_dir = false, .opaque = false, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 80fb66426760..265bf9cfde08 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -270,6 +270,7 @@ void ovl_clear_flag(unsigned long flag, struct inode *inode); bool ovl_test_flag(unsigned long flag, struct inode *inode); bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); +bool ovl_is_inuse(struct dentry *dentry); bool ovl_need_index(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry, bool *locked); void ovl_nlink_end(struct dentry *dentry, bool locked); @@ -366,6 +367,8 @@ struct ovl_inode_params { struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, bool is_upper); +bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir); +struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir); struct inode *ovl_get_inode(struct super_block *sb, struct ovl_inode_params *oip); static inline void ovl_copyattr(struct inode *from, struct inode *to) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index ec237035333a..6ed1ace8f8b3 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -29,6 +29,8 @@ struct ovl_sb { struct ovl_layer { struct vfsmount *mnt; + /* Trap in ovl inode cache */ + struct inode *trap; struct ovl_sb *fs; /* Index of this layer in fs root (upper idx == 0) */ int idx; @@ -65,6 +67,10 @@ struct ovl_fs { /* Did we take the inuse lock? */ bool upperdir_locked; bool workdir_locked; + /* Traps in ovl inode cache */ + struct inode *upperdir_trap; + struct inode *workdir_trap; + struct inode *indexdir_trap; /* Inode numbers in all layers do not use the high xino_bits */ unsigned int xino_bits; }; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 0fb0a59a5e5c..2d028c02621f 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -217,6 +217,9 @@ static void ovl_free_fs(struct ovl_fs *ofs) { unsigned i; + iput(ofs->indexdir_trap); + iput(ofs->workdir_trap); + iput(ofs->upperdir_trap); dput(ofs->indexdir); dput(ofs->workdir); if (ofs->workdir_locked) @@ -225,8 +228,10 @@ static void ovl_free_fs(struct ovl_fs *ofs) if (ofs->upperdir_locked) ovl_inuse_unlock(ofs->upper_mnt->mnt_root); mntput(ofs->upper_mnt); - for (i = 0; i < ofs->numlower; i++) + for (i = 0; i < ofs->numlower; i++) { + iput(ofs->lower_layers[i].trap); mntput(ofs->lower_layers[i].mnt); + } for (i = 0; i < ofs->numlowerfs; i++) free_anon_bdev(ofs->lower_fs[i].pseudo_dev); kfree(ofs->lower_layers); @@ -984,7 +989,26 @@ static const struct xattr_handler *ovl_xattr_handlers[] = { NULL }; -static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) +static int ovl_setup_trap(struct super_block *sb, struct dentry *dir, + struct inode **ptrap, const char *name) +{ + struct inode *trap; + int err; + + trap = ovl_get_trap_inode(sb, dir); + err = PTR_ERR_OR_ZERO(trap); + if (err) { + if (err == -ELOOP) + pr_err("overlayfs: conflicting %s path\n", name); + return err; + } + + *ptrap = trap; + return 0; +} + +static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, + struct path *upperpath) { struct vfsmount *upper_mnt; int err; @@ -1004,6 +1028,11 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) if (err) goto out; + err = ovl_setup_trap(sb, upperpath->dentry, &ofs->upperdir_trap, + "upperdir"); + if (err) + goto out; + upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { @@ -1030,7 +1059,8 @@ out: return err; } -static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath) +static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, + struct path *workpath) { struct vfsmount *mnt = ofs->upper_mnt; struct dentry *temp; @@ -1045,6 +1075,10 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath) if (!ofs->workdir) goto out; + err = ovl_setup_trap(sb, ofs->workdir, &ofs->workdir_trap, "workdir"); + if (err) + goto out; + /* * Upper should support d_type, else whiteouts are visible. Given * workdir and upper are on same fs, we can do iterate_dir() on @@ -1105,7 +1139,8 @@ out: return err; } -static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) +static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs, + struct path *upperpath) { int err; struct path workpath = { }; @@ -1136,19 +1171,16 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } - err = ovl_make_workdir(ofs, &workpath); - if (err) - goto out; + err = ovl_make_workdir(sb, ofs, &workpath); - err = 0; out: path_put(&workpath); return err; } -static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe, - struct path *upperpath) +static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, + struct ovl_entry *oe, struct path *upperpath) { struct vfsmount *mnt = ofs->upper_mnt; int err; @@ -1167,6 +1199,11 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe, ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true); if (ofs->indexdir) { + err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap, + "indexdir"); + if (err) + goto out; + /* * Verify upper root is exclusively associated with index dir. * Older kernels stored upper fh in "trusted.overlay.origin" @@ -1226,8 +1263,8 @@ static int ovl_get_fsid(struct ovl_fs *ofs, struct super_block *sb) return ofs->numlowerfs; } -static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, - unsigned int numlower) +static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, + struct path *stack, unsigned int numlower) { int err; unsigned int i; @@ -1245,16 +1282,28 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, for (i = 0; i < numlower; i++) { struct vfsmount *mnt; + struct inode *trap; int fsid; err = fsid = ovl_get_fsid(ofs, stack[i].mnt->mnt_sb); if (err < 0) goto out; + err = -EBUSY; + if (ovl_is_inuse(stack[i].dentry)) { + pr_err("overlayfs: lowerdir is in-use as upperdir/workdir\n"); + goto out; + } + + err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir"); + if (err) + goto out; + mnt = clone_private_mount(&stack[i]); err = PTR_ERR(mnt); if (IS_ERR(mnt)) { pr_err("overlayfs: failed to clone lowerpath\n"); + iput(trap); goto out; } @@ -1264,6 +1313,7 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, */ mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME; + ofs->lower_layers[ofs->numlower].trap = trap; ofs->lower_layers[ofs->numlower].mnt = mnt; ofs->lower_layers[ofs->numlower].idx = i + 1; ofs->lower_layers[ofs->numlower].fsid = fsid; @@ -1358,7 +1408,7 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, goto out_err; } - err = ovl_get_lower_layers(ofs, stack, numlower); + err = ovl_get_lower_layers(sb, ofs, stack, numlower); if (err) goto out_err; @@ -1390,6 +1440,77 @@ out_err: goto out; } +/* + * Check if this layer root is a descendant of: + * - another layer of this overlayfs instance + * - upper/work dir of any overlayfs instance + */ +static int ovl_check_layer(struct super_block *sb, struct dentry *dentry, + const char *name) +{ + struct dentry *next = dentry, *parent; + int err = 0; + + if (!dentry) + return 0; + + parent = dget_parent(next); + + /* Walk back ancestors to root (inclusive) looking for traps */ + while (!err && parent != next) { + if (ovl_is_inuse(parent)) { + err = -EBUSY; + pr_err("overlayfs: %s path overlapping in-use upperdir/workdir\n", + name); + } else if (ovl_lookup_trap_inode(sb, parent)) { + err = -ELOOP; + pr_err("overlayfs: overlapping %s path\n", name); + } + next = parent; + parent = dget_parent(next); + dput(next); + } + + dput(parent); + + return err; +} + +/* + * Check if any of the layers or work dirs overlap. + */ +static int ovl_check_overlapping_layers(struct super_block *sb, + struct ovl_fs *ofs) +{ + int i, err; + + if (ofs->upper_mnt) { + err = ovl_check_layer(sb, ofs->upper_mnt->mnt_root, "upperdir"); + if (err) + return err; + + /* + * Checking workbasedir avoids hitting ovl_is_inuse(parent) of + * this instance and covers overlapping work and index dirs, + * unless work or index dir have been moved since created inside + * workbasedir. In that case, we already have their traps in + * inode cache and we will catch that case on lookup. + */ + err = ovl_check_layer(sb, ofs->workbasedir, "workdir"); + if (err) + return err; + } + + for (i = 0; i < ofs->numlower; i++) { + err = ovl_check_layer(sb, ofs->lower_layers[i].mnt->mnt_root, + "lowerdir"); + if (err) + return err; + } + + return 0; +} + static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { }; @@ -1429,17 +1550,20 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (ofs->config.xino != OVL_XINO_OFF) ofs->xino_bits = BITS_PER_LONG - 32; + /* alloc/destroy_inode needed for setting up traps in inode cache */ + sb->s_op = &ovl_super_operations; + if (ofs->config.upperdir) { if (!ofs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); goto out_err; } - err = ovl_get_upper(ofs, &upperpath); + err = ovl_get_upper(sb, ofs, &upperpath); if (err) goto out_err; - err = ovl_get_workdir(ofs, &upperpath); + err = ovl_get_workdir(sb, ofs, &upperpath); if (err) goto out_err; @@ -1460,7 +1584,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= SB_RDONLY; if (!(ovl_force_readonly(ofs)) && ofs->config.index) { - err = ovl_get_indexdir(ofs, oe, &upperpath); + err = ovl_get_indexdir(sb, ofs, oe, &upperpath); if (err) goto out_free_oe; @@ -1473,6 +1597,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } + err = ovl_check_overlapping_layers(sb, ofs); + if (err) + goto out_free_oe; + /* Show index=off in /proc/mounts for forced r/o mount */ if (!ofs->indexdir) { ofs->config.index = false; @@ -1494,7 +1622,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); sb->s_magic = OVERLAYFS_SUPER_MAGIC; - sb->s_op = &ovl_super_operations; sb->s_xattr = ovl_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index c9a2e3c6d537..db8bdb29b320 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -653,6 +653,18 @@ void ovl_inuse_unlock(struct dentry *dentry) } } +bool ovl_is_inuse(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + bool inuse; + + spin_lock(&inode->i_lock); + inuse = (inode->i_state & I_OVL_INUSE); + spin_unlock(&inode->i_lock); + + return inuse; +} + /* * Does this overlay dentry need to be indexed on copy up? */ |