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>

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)
 

include/linux/cgroup-defs.h

@@ -422,6 +422,8 @@ struct cgroup_subsys {
 	void (*css_reset)(struct cgroup_subsys_state *css);
 	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
+	int (*allow_attach)(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset);
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);

kernel/cgroup.c

@@ -2682,6 +2682,25 @@ int subsys_cgroup_allow_attach(struct cgroup_subsys_state *css, struct cgroup_ta
 	return 0;
 }
 
+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;
+}
+
 static int cgroup_procs_write_permission(struct task_struct *task,
 					 struct cgroup *dst_cgrp,
 					 struct kernfs_open_file *of)
@@ -2696,8 +2715,23 @@ static int cgroup_procs_write_permission(struct task_struct *task,
 	 */
 	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
 	    !uid_eq(cred->euid, tcred->uid) &&
-	    !uid_eq(cred->euid, tcred->suid))
-		ret = -EACCES;
+	    !uid_eq(cred->euid, tcred->suid)) {
+		/*
+		 * if the default permission check fails, give each
+		 * cgroup a chance to extend the permission check
+		 */
+		struct cgroup_taskset tset = {
+			.src_csets = LIST_HEAD_INIT(tset.src_csets),
+			.dst_csets = LIST_HEAD_INIT(tset.dst_csets),
+			.csets = &tset.src_csets,
+		};
+		struct css_set *cset;
+		cset = task_css_set(task);
+		list_add(&cset->mg_node, &tset.src_csets);
+		ret = cgroup_allow_attach(dst_cgrp, &tset);
+		if (ret)
+			ret = -EACCES;
+	}
 
 	if (!ret && cgroup_on_dfl(dst_cgrp)) {
 		struct super_block *sb = of->file->f_path.dentry->d_sb;