{
int size, ret;
kuid_t kroot;
+ u32 nsmagic, magic;
uid_t root, mappedroot;
char *tmpbuf = NULL;
struct vfs_cap_data *cap;
- struct vfs_ns_cap_data *nscap;
+ struct vfs_ns_cap_data *nscap = NULL;
struct dentry *dentry;
struct user_namespace *fs_ns;
fs_ns = inode->i_sb->s_user_ns;
cap = (struct vfs_cap_data *) tmpbuf;
if (is_v2header((size_t) ret, cap)) {
- /* If this is sizeof(vfs_cap_data) then we're ok with the
- * on-disk value, so return that. */
- if (alloc)
- *buffer = tmpbuf;
- else
- kfree(tmpbuf);
- return ret;
- } else if (!is_v3header((size_t) ret, cap)) {
- kfree(tmpbuf);
- return -EINVAL;
+ root = 0;
+ } else if (is_v3header((size_t) ret, cap)) {
+ nscap = (struct vfs_ns_cap_data *) tmpbuf;
+ root = le32_to_cpu(nscap->rootid);
+ } else {
+ size = -EINVAL;
+ goto out_free;
}
- nscap = (struct vfs_ns_cap_data *) tmpbuf;
- root = le32_to_cpu(nscap->rootid);
kroot = make_kuid(fs_ns, root);
/* If the root kuid maps to a valid uid in current ns, then return
* this as a nscap. */
mappedroot = from_kuid(current_user_ns(), kroot);
if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
+ size = sizeof(struct vfs_ns_cap_data);
if (alloc) {
- *buffer = tmpbuf;
+ if (!nscap) {
+ /* v2 -> v3 conversion */
+ nscap = kzalloc(size, GFP_ATOMIC);
+ if (!nscap) {
+ size = -ENOMEM;
+ goto out_free;
+ }
+ nsmagic = VFS_CAP_REVISION_3;
+ magic = le32_to_cpu(cap->magic_etc);
+ if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+ nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+ memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+ nscap->magic_etc = cpu_to_le32(nsmagic);
+ } else {
+ /* use allocated v3 buffer */
+ tmpbuf = NULL;
+ }
nscap->rootid = cpu_to_le32(mappedroot);
- } else
- kfree(tmpbuf);
- return size;
+ *buffer = nscap;
+ }
+ goto out_free;
}
if (!rootid_owns_currentns(kroot)) {
- kfree(tmpbuf);
- return -EOPNOTSUPP;
+ size = -EOVERFLOW;
+ goto out_free;
}
/* This comes from a parent namespace. Return as a v2 capability */
size = sizeof(struct vfs_cap_data);
if (alloc) {
- *buffer = kmalloc(size, GFP_ATOMIC);
- if (*buffer) {
- struct vfs_cap_data *cap = *buffer;
- __le32 nsmagic, magic;
+ if (nscap) {
+ /* v3 -> v2 conversion */
+ cap = kzalloc(size, GFP_ATOMIC);
+ if (!cap) {
+ size = -ENOMEM;
+ goto out_free;
+ }
magic = VFS_CAP_REVISION_2;
nsmagic = le32_to_cpu(nscap->magic_etc);
if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
cap->magic_etc = cpu_to_le32(magic);
} else {
- size = -ENOMEM;
+ /* use unconverted v2 */
+ tmpbuf = NULL;
}
+ *buffer = cap;
}
+out_free:
kfree(tmpbuf);
return size;
}
__u32 magic, nsmagic;
struct inode *inode = d_backing_inode(dentry);
struct user_namespace *task_ns = current_user_ns(),
- *fs_ns = inode->i_sb->s_user_ns;
+ *fs_ns = inode->i_sb->s_user_ns,
+ *ancestor;
kuid_t rootid;
size_t newsize;
if (nsrootid == -1)
return -EINVAL;
+ /*
+ * Do not allow allow adding a v3 filesystem capability xattr
+ * if the rootid field is ambiguous.
+ */
+ for (ancestor = task_ns->parent; ancestor; ancestor = ancestor->parent) {
+ if (from_kuid(ancestor, rootid) == 0)
+ return -EINVAL;
+ }
+
newsize = sizeof(struct vfs_ns_cap_data);
nscap = kmalloc(newsize, GFP_ATOMIC);
if (!nscap)
* its xattrs and, if present, apply them to the proposed credentials being
* constructed by execve().
*/
-static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_fcap)
+static int get_file_caps(struct linux_binprm *bprm, struct file *file,
+ bool *effective, bool *has_fcap)
{
int rc = 0;
struct cpu_vfs_cap_data vcaps;
if (!file_caps_enabled)
return 0;
- if (!mnt_may_suid(bprm->file->f_path.mnt))
+ if (!mnt_may_suid(file->f_path.mnt))
return 0;
/*
* explicit that capability bits are limited to s_user_ns and its
* descendants.
*/
- if (!current_in_userns(bprm->file->f_path.mnt->mnt_sb->s_user_ns))
+ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns))
return 0;
- rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps);
+ rc = get_vfs_caps_from_disk(file->f_path.dentry, &vcaps);
if (rc < 0) {
if (rc == -EINVAL)
printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
}
/**
- * cap_bprm_set_creds - Set up the proposed credentials for execve().
+ * cap_bprm_creds_from_file - Set up the proposed credentials for execve().
* @bprm: The execution parameters, including the proposed creds
+ * @file: The file to pull the credentials from
*
* Set up the proposed credentials for a new execution context being
* constructed by execve(). The proposed creds in @bprm->cred is altered,
* which won't take effect immediately. Returns 0 if successful, -ve on error.
*/
-int cap_bprm_set_creds(struct linux_binprm *bprm)
+int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file)
{
+ /* Process setpcap binaries and capabilities for uid 0 */
const struct cred *old = current_cred();
struct cred *new = bprm->cred;
bool effective = false, has_fcap = false, is_setid;
int ret;
kuid_t root_uid;
- new->cap_ambient = old->cap_ambient;
if (WARN_ON(!cap_ambient_invariant_ok(old)))
return -EPERM;
- ret = get_file_caps(bprm, &effective, &has_fcap);
+ ret = get_file_caps(bprm, file, &effective, &has_fcap);
if (ret < 0)
return ret;
return -EPERM;
/* Check for privilege-elevated exec. */
- bprm->cap_elevated = 0;
if (is_setid ||
(!__is_real(root_uid, new) &&
(effective ||
__cap_grew(permitted, ambient, new))))
- bprm->cap_elevated = 1;
+ bprm->secureexec = 1;
return 0;
}
LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme),
LSM_HOOK_INIT(capget, cap_capget),
LSM_HOOK_INIT(capset, cap_capset),
- LSM_HOOK_INIT(bprm_set_creds, cap_bprm_set_creds),
+ LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file),
LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv),
LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv),
LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity),