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
'allow_attach' handler, then we fall back to doing our checks
the old way.

Use the 'allow_attach' handler for the 'cpu' cgroup to allow
non-root processes to add arbitrary processes to a 'cpu' cgroup
if it has the CAP_SYS_NICE capability set.

This version of the patch adds a 'allow_attach' handler instead
of reusing the 'can_attach' handler.  If the 'can_attach' handler
is reused, a new cgroup that implements 'can_attach' but not
the permission checks could end up with no permission checks
at all.

Change-Id: Icfa950aa9321d1ceba362061d32dc7dfa2c64f0c
Original-Author: San Mehat <san@google.com>
Signed-off-by: Colin Cross <ccross@android.com>

4 files changed, 61 insertions, 3 deletions

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 821de56d1580..91bd5e0d34e4 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -578,6 +578,15 @@ is completely unused; @cgrp->parent is still valid. (Note - can also
 be called for a newly-created cgroup if an error occurs after this
 subsystem's create() method has been called for the new cgroup).
 
+int allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+(cgroup_mutex held by caller)
+
+Called prior to moving a task into a cgroup; if the subsystem
+returns an error, this will abort the attach operation.  Used
+to extend the permission checks - if all subsystems in a cgroup
+return 0, the attach will be allowed to proceed, even if the
+default permission check (root or same user) fails.
+
 int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 (cgroup_mutex held by caller)
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 9450f025fe0c..bbda8c015591 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -579,6 +579,8 @@ struct cgroup_subsys {
 	void (*css_offline)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 
+	int (*allow_attach)(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset);
 	int (*can_attach)(struct cgroup_subsys_state *css,
 			  struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_subsys_state *css,
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 105f273b6f86..81523efd585b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2110,6 +2110,25 @@ out_free_group_list:
 	return retval;
 }
 
+static int cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+	struct cgroup_subsys_state *css;
+	int i;
+	int ret;
+
+	for_each_css(css, i, cgrp) {
+		if (css->ss->allow_attach) {
+			ret = css->ss->allow_attach(css, tset);
+			if (ret)
+				return ret;
+		} else {
+			return -EACCES;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Find the task_struct of the task to attach by vpid and pass it along to the
  * function to attach either it or all tasks in its threadgroup. Will lock
@@ -2141,9 +2160,18 @@ retry_find_task:
 		if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
 		    !uid_eq(cred->euid, tcred->uid) &&
 		    !uid_eq(cred->euid, tcred->suid)) {
-			rcu_read_unlock();
-			ret = -EACCES;
-			goto out_unlock_cgroup;
+			/*
+			 * if the default permission check fails, give each
+			 * cgroup a chance to extend the permission check
+			 */
+			struct cgroup_taskset tset = { };
+			tset.single.task = tsk;
+			tset.single.cgrp = cgrp;
+			ret = cgroup_allow_attach(cgrp, &tset);
+			if (ret) {
+				rcu_read_unlock();
+				goto out_unlock_cgroup;
+			}
 		}
 	} else
 		tsk = current;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4bf263e8040a..a55b70c98302 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7619,6 +7619,24 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
 	sched_offline_group(tg);
 }
 
+static int cpu_cgroup_allow_attach(struct cgroup_subsys_state *css,
+				   struct cgroup_taskset *tset)
+{
+	const struct cred *cred = current_cred(), *tcred;
+	struct task_struct *task;
+
+	cgroup_taskset_for_each(task, css, tset) {
+		tcred = __task_cred(task);
+
+		if ((current != task) && !capable(CAP_SYS_NICE) &&
+		    !uid_eq(cred->euid, tcred->uid) &&
+		    !uid_eq(cred->euid, tcred->suid))
+			return -EACCES;
+	}
+
+	return 0;
+}
+
 static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 				 struct cgroup_taskset *tset)
 {
@@ -7989,6 +8007,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.css_offline	= cpu_cgroup_css_offline,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
+	.allow_attach	= cpu_cgroup_allow_attach,
 	.exit		= cpu_cgroup_exit,
 	.subsys_id	= cpu_cgroup_subsys_id,
 	.base_cftypes	= cpu_files,