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>

4 files changed, 33 insertions, 9 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 25c7eb52de1a..aab77936c064 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,6 +57,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/eventfd.h>
 #include <linux/poll.h>
+#include <linux/capability.h>
 
 #include <asm/atomic.h>
 
@@ -1782,6 +1783,14 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 				 */
 				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;
 			}
 		}
 	}
@@ -1879,7 +1888,6 @@ EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
 {
 	struct task_struct *tsk;
-	const struct cred *cred = current_cred(), *tcred;
 	int ret;
 
 	if (pid) {
@@ -1889,14 +1897,6 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
 			rcu_read_unlock();
 			return -ESRCH;
 		}
-
-		tcred = __task_cred(tsk);
-		if (cred->euid &&
-		    cred->euid != tcred->uid &&
-		    cred->euid != tcred->suid) {
-			rcu_read_unlock();
-			return -EACCES;
-		}
 		get_task_struct(tsk);
 		rcu_read_unlock();
 	} else {
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e7bebb7c6c38..12a4881dffae 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -164,6 +164,14 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 {
 	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 33eee16addb8..121c37da5ac2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1377,6 +1377,13 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
 	int ret;
 	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 3809ab027c6c..4672238977fd 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9073,6 +9073,15 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 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;