cgroup: Add generic cgroup subsystem permission checks.
Rather than using explicit euid == 0 checks when trying to move
tasks into a cgroup via CFS, move permission checks into each
specific cgroup subsystem. If a subsystem does not specify a
'can_attach' handler, then we fall back to doing our checks the old way.
This way non-root processes can add arbitrary processes to
a cgroup if all the registered subsystems on that cgroup agree.
Also change explicit euid == 0 check to CAP_SYS_ADMIN
Signed-off-by: San Mehat <san@google.com>
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2731d11..129b47f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_proc */
+#include <linux/capability.h>
#include <asm/atomic.h>
@@ -1839,6 +1840,15 @@
failed_ss = ss;
goto out;
}
+ } else if (!capable(CAP_SYS_ADMIN)) {
+ const struct cred *cred = current_cred(), *tcred;
+
+ /* No can_attach() - check perms generically */
+ tcred = __task_cred(tsk);
+ if (cred->euid != tcred->uid &&
+ cred->euid != tcred->suid) {
+ return -EACCES;
+ }
}
if (ss->can_attach_task) {
retval = ss->can_attach_task(cgrp, tsk);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e691818..6ebda1d 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -164,6 +164,14 @@
{
struct freezer *freezer;
+ if ((current != task) && (!capable(CAP_SYS_ADMIN))) {
+ const struct cred *cred = current_cred(), *tcred;
+
+ tcred = __task_cred(task);
+ if (cred->euid != tcred->uid && cred->euid != tcred->suid)
+ return -EPERM;
+ }
+
/*
* Anything frozen can't move or be moved to/from.
*/
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9c9b754..a1df487 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1373,6 +1373,13 @@
{
struct cpuset *cs = cgroup_cs(cont);
+ if ((current != task) && (!capable(CAP_SYS_ADMIN))) {
+ const struct cred *cred = current_cred(), *tcred;
+
+ if (cred->euid != tcred->uid && cred->euid != tcred->suid)
+ return -EPERM;
+ }
+
if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
return -ENOSPC;
diff --git a/kernel/sched.c b/kernel/sched.c
index ea7a385..13f13af 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8803,6 +8803,15 @@
static int
cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
+ if ((current != tsk) && (!capable(CAP_SYS_NICE))) {
+ const struct cred *cred = current_cred(), *tcred;
+
+ tcred = __task_cred(tsk);
+
+ if (cred->euid != tcred->uid && cred->euid != tcred->suid)
+ return -EPERM;
+ }
+
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
return -EINVAL;