提交 fc832ad3 编写于 作者: S Serge E. Hallyn 提交者: Linus Torvalds

userns: user namespaces: convert all capable checks in kernel/sys.c

This allows setuid/setgid in containers.  It also fixes some corner cases
where kernel logic foregoes capability checks when uids are equivalent.
The latter will need to be done throughout the whole kernel.

Changelog:
	Jan 11: Use nsown_capable() as suggested by Bastian Blank.
	Jan 11: Fix logic errors in uid checks pointed out by Bastian.
	Feb 15: allow prlimit to current (was regression in previous version)
	Feb 23: remove debugging printks, uninline set_one_prio_perm and
		make it bool, and document its return value.
Signed-off-by: NSerge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: NDaniel Lezcano <daniel.lezcano@free.fr>
Acked-by: NDavid Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 3263245d
......@@ -119,17 +119,34 @@ EXPORT_SYMBOL(cad_pid);
void (*pm_power_off_prepare)(void);
/*
* Returns true if current's euid is same as p's uid or euid,
* or has CAP_SYS_NICE to p's user_ns.
*
* Called with rcu_read_lock, creds are safe
*/
static bool set_one_prio_perm(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
if (pcred->user->user_ns == cred->user->user_ns &&
(pcred->uid == cred->euid ||
pcred->euid == cred->euid))
return true;
if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE))
return true;
return false;
}
/*
* set the priority of a task
* - the caller must hold the RCU read lock
*/
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
int no_nice;
if (pcred->uid != cred->euid &&
pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
if (!set_one_prio_perm(p)) {
error = -EPERM;
goto out;
}
......@@ -506,7 +523,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
if (rgid != (gid_t) -1) {
if (old->gid == rgid ||
old->egid == rgid ||
capable(CAP_SETGID))
nsown_capable(CAP_SETGID))
new->gid = rgid;
else
goto error;
......@@ -515,7 +532,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
if (old->gid == egid ||
old->egid == egid ||
old->sgid == egid ||
capable(CAP_SETGID))
nsown_capable(CAP_SETGID))
new->egid = egid;
else
goto error;
......@@ -550,7 +567,7 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
old = current_cred();
retval = -EPERM;
if (capable(CAP_SETGID))
if (nsown_capable(CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = gid;
else if (gid == old->gid || gid == old->sgid)
new->egid = new->fsgid = gid;
......@@ -617,7 +634,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
new->uid = ruid;
if (old->uid != ruid &&
old->euid != ruid &&
!capable(CAP_SETUID))
!nsown_capable(CAP_SETUID))
goto error;
}
......@@ -626,7 +643,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
if (old->uid != euid &&
old->euid != euid &&
old->suid != euid &&
!capable(CAP_SETUID))
!nsown_capable(CAP_SETUID))
goto error;
}
......@@ -674,7 +691,7 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
old = current_cred();
retval = -EPERM;
if (capable(CAP_SETUID)) {
if (nsown_capable(CAP_SETUID)) {
new->suid = new->uid = uid;
if (uid != old->uid) {
retval = set_user(new);
......@@ -716,7 +733,7 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
old = current_cred();
retval = -EPERM;
if (!capable(CAP_SETUID)) {
if (!nsown_capable(CAP_SETUID)) {
if (ruid != (uid_t) -1 && ruid != old->uid &&
ruid != old->euid && ruid != old->suid)
goto error;
......@@ -780,7 +797,7 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
old = current_cred();
retval = -EPERM;
if (!capable(CAP_SETGID)) {
if (!nsown_capable(CAP_SETGID)) {
if (rgid != (gid_t) -1 && rgid != old->gid &&
rgid != old->egid && rgid != old->sgid)
goto error;
......@@ -840,7 +857,7 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
if (uid == old->uid || uid == old->euid ||
uid == old->suid || uid == old->fsuid ||
capable(CAP_SETUID)) {
nsown_capable(CAP_SETUID)) {
if (uid != old_fsuid) {
new->fsuid = uid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
......@@ -873,7 +890,7 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
if (gid == old->gid || gid == old->egid ||
gid == old->sgid || gid == old->fsgid ||
capable(CAP_SETGID)) {
nsown_capable(CAP_SETGID)) {
if (gid != old_fsgid) {
new->fsgid = gid;
goto change_okay;
......@@ -1183,6 +1200,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
......@@ -1230,7 +1248,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
int errno;
char tmp[__NEW_UTS_LEN];
if (!capable(CAP_SYS_ADMIN))
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
......@@ -1345,6 +1363,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource,
rlim = tsk->signal->rlim + resource;
task_lock(tsk->group_leader);
if (new_rlim) {
/* Keep the capable check against init_user_ns until
cgroups can contain all limits */
if (new_rlim->rlim_max > rlim->rlim_max &&
!capable(CAP_SYS_RESOURCE))
retval = -EPERM;
......@@ -1388,19 +1408,22 @@ static int check_prlimit_permission(struct task_struct *task)
{
const struct cred *cred = current_cred(), *tcred;
tcred = __task_cred(task);
if (current != task &&
(cred->uid != tcred->euid ||
cred->uid != tcred->suid ||
cred->uid != tcred->uid ||
cred->gid != tcred->egid ||
cred->gid != tcred->sgid ||
cred->gid != tcred->gid) &&
!capable(CAP_SYS_RESOURCE)) {
return -EPERM;
}
if (current == task)
return 0;
return 0;
tcred = __task_cred(task);
if (cred->user->user_ns == tcred->user->user_ns &&
(cred->uid == tcred->euid &&
cred->uid == tcred->suid &&
cred->uid == tcred->uid &&
cred->gid == tcred->egid &&
cred->gid == tcred->sgid &&
cred->gid == tcred->gid))
return 0;
if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE))
return 0;
return -EPERM;
}
SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册