diff options
Diffstat (limited to 'fs/namespace.c')
| -rw-r--r-- | fs/namespace.c | 537 |
1 files changed, 464 insertions, 73 deletions
diff --git a/fs/namespace.c b/fs/namespace.c index 9d33909d0f9e..56bb5a5fdc0d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,6 +25,7 @@ #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> +#include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> @@ -73,6 +74,15 @@ static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ +struct mount_kattr { + unsigned int attr_set; + unsigned int attr_clr; + unsigned int propagation; + unsigned int lookup_flags; + bool recurse; + struct user_namespace *mnt_userns; +}; + /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); @@ -87,6 +97,16 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); +static inline void lock_mount_hash(void) +{ + write_seqlock(&mount_lock); +} + +static inline void unlock_mount_hash(void) +{ + write_sequnlock(&mount_lock); +} + static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); @@ -210,6 +230,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + mnt->mnt.mnt_userns = &init_user_ns; } return mnt; @@ -360,50 +381,36 @@ int mnt_want_write(struct vfsmount *m) EXPORT_SYMBOL_GPL(mnt_want_write); /** - * mnt_clone_write - get write access to a mount - * @mnt: the mount on which to take a write - * - * This is effectively like mnt_want_write, except - * it must only be used to take an extra write reference - * on a mountpoint that we already know has a write reference - * on it. This allows some optimisation. - * - * After finished, mnt_drop_write must be called as usual to - * drop the reference. - */ -int mnt_clone_write(struct vfsmount *mnt) -{ - /* superblock may be r/o */ - if (__mnt_is_readonly(mnt)) - return -EROFS; - preempt_disable(); - mnt_inc_writers(real_mount(mnt)); - preempt_enable(); - return 0; -} -EXPORT_SYMBOL_GPL(mnt_clone_write); - -/** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like __mnt_want_write, but it takes a file and can - * do some optimisations if the file is open for write already + * This is like __mnt_want_write, but if the file is already open for writing it + * skips incrementing mnt_writers (since the open file already has a reference) + * and instead only does the check for emergency r/o remounts. This must be + * paired with __mnt_drop_write_file. */ int __mnt_want_write_file(struct file *file) { - if (!(file->f_mode & FMODE_WRITER)) - return __mnt_want_write(file->f_path.mnt); - else - return mnt_clone_write(file->f_path.mnt); + if (file->f_mode & FMODE_WRITER) { + /* + * Superblock may have become readonly while there are still + * writable fd's, e.g. due to a fs error with errors=remount-ro + */ + if (__mnt_is_readonly(file->f_path.mnt)) + return -EROFS; + return 0; + } + return __mnt_want_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like mnt_want_write, but it takes a file and can - * do some optimisations if the file is open for write already + * This is like mnt_want_write, but if the file is already open for writing it + * skips incrementing mnt_writers (since the open file already has a reference) + * and instead only does the freeze protection and the check for emergency r/o + * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { @@ -449,7 +456,8 @@ EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { - __mnt_drop_write(file->f_path.mnt); + if (!(file->f_mode & FMODE_WRITER)) + __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) @@ -459,11 +467,8 @@ void mnt_drop_write_file(struct file *file) } EXPORT_SYMBOL(mnt_drop_write_file); -static int mnt_make_readonly(struct mount *mnt) +static inline int mnt_hold_writers(struct mount *mnt) { - int ret = 0; - - lock_mount_hash(); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store @@ -488,25 +493,30 @@ static int mnt_make_readonly(struct mount *mnt) * we're counting up here. */ if (mnt_get_writers(mnt) > 0) - ret = -EBUSY; - else - mnt->mnt.mnt_flags |= MNT_READONLY; + return -EBUSY; + + return 0; +} + +static inline void mnt_unhold_writers(struct mount *mnt) +{ /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; - unlock_mount_hash(); - return ret; } -static int __mnt_unmake_readonly(struct mount *mnt) +static int mnt_make_readonly(struct mount *mnt) { - lock_mount_hash(); - mnt->mnt.mnt_flags &= ~MNT_READONLY; - unlock_mount_hash(); - return 0; + int ret; + + ret = mnt_hold_writers(mnt); + if (!ret) + mnt->mnt.mnt_flags |= MNT_READONLY; + mnt_unhold_writers(mnt); + return ret; } int sb_prepare_remount_readonly(struct super_block *sb) @@ -547,6 +557,11 @@ int sb_prepare_remount_readonly(struct super_block *sb) static void free_vfsmnt(struct mount *mnt) { + struct user_namespace *mnt_userns; + + mnt_userns = mnt_user_ns(&mnt->mnt); + if (mnt_userns != &init_user_ns) + put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); @@ -1055,6 +1070,9 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); + mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); + if (mnt->mnt.mnt_userns != &init_user_ns) + mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; @@ -2514,20 +2532,15 @@ static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) if (readonly_request) return mnt_make_readonly(mnt); - return __mnt_unmake_readonly(mnt); + mnt->mnt.mnt_flags &= ~MNT_READONLY; + return 0; } -/* - * Update the user-settable attributes on a mount. The caller must hold - * sb->s_umount for writing. - */ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { - lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); - unlock_mount_hash(); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) @@ -2572,11 +2585,17 @@ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; - down_write(&sb->s_umount); + /* + * We're only checking whether the superblock is read-only not + * changing it, so only take down_read(&sb->s_umount). + */ + down_read(&sb->s_umount); + lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); - up_write(&sb->s_umount); + unlock_mount_hash(); + up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); @@ -2616,8 +2635,11 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); - if (!err) + if (!err) { + lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); + unlock_mount_hash(); + } } up_write(&sb->s_umount); } @@ -3440,6 +3462,33 @@ out_type: return ret; } +#define FSMOUNT_VALID_FLAGS \ + (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ + MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) + +#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) + +#define MOUNT_SETATTR_PROPAGATION_FLAGS \ + (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) + +static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) +{ + unsigned int mnt_flags = 0; + + if (attr_flags & MOUNT_ATTR_RDONLY) + mnt_flags |= MNT_READONLY; + if (attr_flags & MOUNT_ATTR_NOSUID) + mnt_flags |= MNT_NOSUID; + if (attr_flags & MOUNT_ATTR_NODEV) + mnt_flags |= MNT_NODEV; + if (attr_flags & MOUNT_ATTR_NOEXEC) + mnt_flags |= MNT_NOEXEC; + if (attr_flags & MOUNT_ATTR_NODIRATIME) + mnt_flags |= MNT_NODIRATIME; + + return mnt_flags; +} + /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. @@ -3462,24 +3511,10 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; - if (attr_flags & ~(MOUNT_ATTR_RDONLY | - MOUNT_ATTR_NOSUID | - MOUNT_ATTR_NODEV | - MOUNT_ATTR_NOEXEC | - MOUNT_ATTR__ATIME | - MOUNT_ATTR_NODIRATIME)) + if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; - if (attr_flags & MOUNT_ATTR_RDONLY) - mnt_flags |= MNT_READONLY; - if (attr_flags & MOUNT_ATTR_NOSUID) - mnt_flags |= MNT_NOSUID; - if (attr_flags & MOUNT_ATTR_NODEV) - mnt_flags |= MNT_NODEV; - if (attr_flags & MOUNT_ATTR_NOEXEC) - mnt_flags |= MNT_NOEXEC; - if (attr_flags & MOUNT_ATTR_NODIRATIME) - mnt_flags |= MNT_NODIRATIME; + mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: @@ -3787,6 +3822,362 @@ out0: return error; } +static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) +{ + unsigned int flags = mnt->mnt.mnt_flags; + + /* flags to clear */ + flags &= ~kattr->attr_clr; + /* flags to raise */ + flags |= kattr->attr_set; + + return flags; +} + +static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct vfsmount *m = &mnt->mnt; + + if (!kattr->mnt_userns) + return 0; + + /* + * Once a mount has been idmapped we don't allow it to change its + * mapping. It makes things simpler and callers can just create + * another bind-mount they can idmap if they want to. + */ + if (mnt_user_ns(m) != &init_user_ns) + return -EPERM; + + /* The underlying filesystem doesn't support idmapped mounts yet. */ + if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) + return -EINVAL; + + /* We're not controlling the superblock. */ + if (!ns_capable(m->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Mount has already been visible in the filesystem hierarchy. */ + if (!is_anon_ns(mnt->mnt_ns)) + return -EINVAL; + + return 0; +} + +static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, + struct mount *mnt, int *err) +{ + struct mount *m = mnt, *last = NULL; + + if (!is_mounted(&m->mnt)) { + *err = -EINVAL; + goto out; + } + + if (!(mnt_has_parent(m) ? check_mnt(m) : is_anon_ns(m->mnt_ns))) { + *err = -EINVAL; + goto out; + } + + do { + unsigned int flags; + + flags = recalc_flags(kattr, m); + if (!can_change_locked_flags(m, flags)) { + *err = -EPERM; + goto out; + } + + *err = can_idmap_mount(kattr, m); + if (*err) + goto out; + + last = m; + + if ((kattr->attr_set & MNT_READONLY) && + !(m->mnt.mnt_flags & MNT_READONLY)) { + *err = mnt_hold_writers(m); + if (*err) + goto out; + } + } while (kattr->recurse && (m = next_mnt(m, mnt))); + +out: + return last; +} + +static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct user_namespace *mnt_userns; + + if (!kattr->mnt_userns) + return; + + mnt_userns = get_user_ns(kattr->mnt_userns); + /* Pairs with smp_load_acquire() in mnt_user_ns(). */ + smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); +} + +static void mount_setattr_commit(struct mount_kattr *kattr, + struct mount *mnt, struct mount *last, + int err) +{ + struct mount *m = mnt; + + do { + if (!err) { + unsigned int flags; + + do_idmap_mount(kattr, m); + flags = recalc_flags(kattr, m); + WRITE_ONCE(m->mnt.mnt_flags, flags); + } + + /* + * We either set MNT_READONLY above so make it visible + * before ~MNT_WRITE_HOLD or we failed to recursively + * apply mount options. + */ + if ((kattr->attr_set & MNT_READONLY) && + (m->mnt.mnt_flags & MNT_WRITE_HOLD)) + mnt_unhold_writers(m); + + if (!err && kattr->propagation) + change_mnt_propagation(m, kattr->propagation); + + /* + * On failure, only cleanup until we found the first mount + * we failed to handle. + */ + if (err && m == last) + break; + } while (kattr->recurse && (m = next_mnt(m, mnt))); + + if (!err) + touch_mnt_namespace(mnt->mnt_ns); +} + +static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) +{ + struct mount *mnt = real_mount(path->mnt), *last = NULL; + int err = 0; + + if (path->dentry != mnt->mnt.mnt_root) + return -EINVAL; + + if (kattr->propagation) { + /* + * Only take namespace_lock() if we're actually changing + * propagation. + */ + namespace_lock(); + if (kattr->propagation == MS_SHARED) { + err = invent_group_ids(mnt, kattr->recurse); + if (err) { + namespace_unlock(); + return err; + } + } + } + + lock_mount_hash(); + + /* + * Get the mount tree in a shape where we can change mount + * properties without failure. + */ + last = mount_setattr_prepare(kattr, mnt, &err); + if (last) /* Commit all changes or revert to the old state. */ + mount_setattr_commit(kattr, mnt, last, err); + + unlock_mount_hash(); + + if (kattr->propagation) { + namespace_unlock(); + if (err) + cleanup_group_ids(mnt, NULL); + } + + return err; +} + +static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, + struct mount_kattr *kattr, unsigned int flags) +{ + int err = 0; + struct ns_common *ns; + struct user_namespace *mnt_userns; + struct file *file; + + if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) + return 0; + + /* + * We currently do not support clearing an idmapped mount. If this ever + * is a use-case we can revisit this but for now let's keep it simple + * and not allow it. + */ + if (attr->attr_clr & MOUNT_ATTR_IDMAP) + return -EINVAL; + + if (attr->userns_fd > INT_MAX) + return -EINVAL; + + file = fget(attr->userns_fd); + if (!file) + return -EBADF; + + if (!proc_ns_file(file)) { + err = -EINVAL; + goto out_fput; + } + + ns = get_proc_ns(file_inode(file)); + if (ns->ops->type != CLONE_NEWUSER) { + err = -EINVAL; + goto out_fput; + } + + /* + * The init_user_ns is used to indicate that a vfsmount is not idmapped. + * This is simpler than just having to treat NULL as unmapped. Users + * wanting to idmap a mount to init_user_ns can just use a namespace + * with an identity mapping. + */ + mnt_userns = container_of(ns, struct user_namespace, ns); + if (mnt_userns == &init_user_ns) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); + +out_fput: + fput(file); + return err; +} + +static int build_mount_kattr(const struct mount_attr *attr, size_t usize, + struct mount_kattr *kattr, unsigned int flags) +{ + unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; + + if (flags & AT_NO_AUTOMOUNT) + lookup_flags &= ~LOOKUP_AUTOMOUNT; + if (flags & AT_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + + *kattr = (struct mount_kattr) { + .lookup_flags = lookup_flags, + .recurse = !!(flags & AT_RECURSIVE), + }; + + if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) + return -EINVAL; + if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) + return -EINVAL; + kattr->propagation = attr->propagation; + + if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) + return -EINVAL; + + kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); + kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); + + /* + * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, + * users wanting to transition to a different atime setting cannot + * simply specify the atime setting in @attr_set, but must also + * specify MOUNT_ATTR__ATIME in the @attr_clr field. + * So ensure that MOUNT_ATTR__ATIME can't be partially set in + * @attr_clr and that @attr_set can't have any atime bits set if + * MOUNT_ATTR__ATIME isn't set in @attr_clr. + */ + if (attr->attr_clr & MOUNT_ATTR__ATIME) { + if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) + return -EINVAL; + + /* + * Clear all previous time settings as they are mutually + * exclusive. + */ + kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; + switch (attr->attr_set & MOUNT_ATTR__ATIME) { + case MOUNT_ATTR_RELATIME: + kattr->attr_set |= MNT_RELATIME; + break; + case MOUNT_ATTR_NOATIME: + kattr->attr_set |= MNT_NOATIME; + break; + case MOUNT_ATTR_STRICTATIME: + break; + default: + return -EINVAL; + } + } else { + if (attr->attr_set & MOUNT_ATTR__ATIME) + return -EINVAL; + } + + return build_mount_idmapped(attr, usize, kattr, flags); +} + +static void finish_mount_kattr(struct mount_kattr *kattr) +{ + put_user_ns(kattr->mnt_userns); + kattr->mnt_userns = NULL; +} + +SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, + unsigned int, flags, struct mount_attr __user *, uattr, + size_t, usize) +{ + int err; + struct path target; + struct mount_attr attr; + struct mount_kattr kattr; + + BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); + + if (flags & ~(AT_EMPTY_PATH | + AT_RECURSIVE | + AT_SYMLINK_NOFOLLOW | + AT_NO_AUTOMOUNT)) + return -EINVAL; + + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; + if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) + return -EINVAL; + + if (!may_mount()) + return -EPERM; + + err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); + if (err) + return err; + + /* Don't bother walking through the mounts if this is a nop. */ + if (attr.attr_set == 0 && + attr.attr_clr == 0 && + attr.propagation == 0) + return 0; + + err = build_mount_kattr(&attr, usize, &kattr, flags); + if (err) + return err; + + err = user_path_at(dfd, path, kattr.lookup_flags, &target); + if (err) + return err; + + err = do_mount_setattr(&target, &kattr); + finish_mount_kattr(&kattr); + path_put(&target); + return err; +} + static void __init init_mount_tree(void) { struct vfsmount *mnt; |