diff options
-rw-r--r-- | fs/ceph/file.c | 4 | ||||
-rw-r--r-- | fs/inode.c | 34 | ||||
-rw-r--r-- | fs/namei.c | 80 | ||||
-rw-r--r-- | fs/ocfs2/namei.c | 1 | ||||
-rw-r--r-- | include/linux/fs.h | 2 |
5 files changed, 102 insertions, 19 deletions
diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 8fab5db16c73..284d2fda663d 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -656,10 +656,6 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, /* Directories always inherit the setgid bit. */ if (S_ISDIR(mode)) mode |= S_ISGID; - else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(dir->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID)) - mode &= ~S_ISGID; } else { in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid())); } diff --git a/fs/inode.c b/fs/inode.c index 524ee91f74a6..9c3cd540c665 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2326,10 +2326,6 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; - else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(i_gid_into_mnt(mnt_userns, dir)) && - !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID)) - mode &= ~S_ISGID; } else inode_fsgid_set(inode, mnt_userns); inode->i_mode = mode; @@ -2485,3 +2481,33 @@ struct timespec64 current_time(struct inode *inode) return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); + +/** + * mode_strip_sgid - handle the sgid bit for non-directories + * @mnt_userns: User namespace of the mount the inode was created from + * @dir: parent directory inode + * @mode: mode of the file to be created in @dir + * + * If the @mode of the new file has both the S_ISGID and S_IXGRP bit + * raised and @dir has the S_ISGID bit raised ensure that the caller is + * either in the group of the parent directory or they have CAP_FSETID + * in their user namespace and are privileged over the parent directory. + * In all other cases, strip the S_ISGID bit from @mode. + * + * Return: the new mode to use for the file + */ +umode_t mode_strip_sgid(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode) +{ + if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) + return mode; + if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) + return mode; + if (in_group_p(i_gid_into_mnt(mnt_userns, dir))) + return mode; + if (capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID)) + return mode; + + return mode & ~S_ISGID; +} +EXPORT_SYMBOL(mode_strip_sgid); diff --git a/fs/namei.c b/fs/namei.c index ed3ffd9b22a3..53b4bc094db2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3024,6 +3024,65 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) EXPORT_SYMBOL(unlock_rename); /** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * Umask stripping depends on whether or not the filesystem supports POSIX + * ACLs. If the filesystem doesn't support it umask stripping is done directly + * in here. If the filesystem does support POSIX ACLs umask stripping is + * deferred until the filesystem calls posix_acl_create(). + * + * Returns: mode + */ +static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); + return mode; +} + +/** + * vfs_prepare_mode - prepare the mode to be used for a new inode + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: parent directory of the new inode + * @mode: mode of the new inode + * @mask_perms: allowed permission by the vfs + * @type: type of file to be created + * + * This helper consolidates and enforces vfs restrictions on the @mode of a new + * object to be created. + * + * Umask stripping depends on whether the filesystem supports POSIX ACLs (see + * the kernel documentation for mode_strip_umask()). Moving umask stripping + * after setgid stripping allows the same ordering for both non-POSIX ACL and + * POSIX ACL supporting filesystems. + * + * Note that it's currently valid for @type to be 0 if a directory is created. + * Filesystems raise that flag individually and we need to check whether each + * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a + * non-zero type. + * + * Returns: mode to be passed to the filesystem + */ +static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode, + umode_t mask_perms, umode_t type) +{ + mode = mode_strip_sgid(mnt_userns, dir, mode); + mode = mode_strip_umask(dir, mode); + + /* + * Apply the vfs mandated allowed permission mask and set the type of + * file to be created before we call into the filesystem. + */ + mode &= (mask_perms & ~S_IFMT); + mode |= (type & S_IFMT); + + return mode; +} + +/** * vfs_create - create new file * @mnt_userns: user namespace of the mount the inode was found from * @dir: inode of @dentry @@ -3048,8 +3107,8 @@ int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode &= S_IALLUGO; - mode |= S_IFREG; + + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; @@ -3312,8 +3371,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(mnt_userns, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(mnt_userns, &nd->path, dentry, mode); @@ -3544,6 +3602,7 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = dir->i_op->tmpfile(mnt_userns, dir, child, mode); if (error) goto out_err; @@ -3821,6 +3880,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mknod) return -EPERM; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3871,9 +3931,8 @@ retry: if (IS_ERR(dentry)) goto out1; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&path, dentry, mode, dev); + error = security_path_mknod(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2; @@ -3943,7 +4002,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mkdir) return -EPERM; - mode &= (S_IRWXUGO|S_ISVTX); + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -3971,9 +4030,8 @@ retry: if (IS_ERR(dentry)) goto out_putname; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); + error = security_path_mkdir(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(path.mnt); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c75fd54b9185..961d1cf54388 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -197,6 +197,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); + mode = mode_strip_sgid(&init_user_ns, dir, mode); inode_init_owner(&init_user_ns, inode, dir, mode); status = dquot_initialize(inode); if (status) diff --git a/include/linux/fs.h b/include/linux/fs.h index 8c127ffa6563..5113f65c786f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2035,6 +2035,8 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); +umode_t mode_strip_sgid(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let |