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>

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 638bf17ff86965a561b5cc258451ea53bd752f1a..61dc0ec5c9a9b11986f625cdc1e891e272cd5f06 100644 (file)
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -598,6 +598,15 @@ 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 8bda1294c035b24912a3da178ebc2c8e1cd5f827..8f73d835d4d57053052570edd7f5ed2d451b831a 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -578,6 +578,7 @@ struct cgroup_subsys {
        void (*css_offline)(struct cgroup *cgrp);
        void (*css_free)(struct cgroup *cgrp);
 
+       int (*allow_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
        int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
        void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
        void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a7c9e6ddb9797a886e96bbff7c75fb8ed9670c68..1f5338773862e5aef43fe47e8cc5715f5e432d34 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2098,6 +2098,24 @@ out_free_group_list:
        return retval;
 }
 
+static int cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+       struct cgroup_subsys *ss;
+       int ret;
+
+       for_each_subsys(cgrp->root, ss) {
+               if (ss->allow_attach) {
+                       ret = ss->allow_attach(cgrp, 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
@@ -2129,9 +2147,18 @@ 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 5b582cabd31674e1ed33fdcc6186c21f43e4f0c5..014040fa3d2176af53f20db84f0e9a97615418c8 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7716,6 +7716,23 @@ static void cpu_cgroup_css_offline(struct cgroup *cgrp)
        sched_offline_group(tg);
 }
 
+static int
+cpu_cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+       const struct cred *cred = current_cred(), *tcred;
+       struct task_struct *task;
+
+       cgroup_taskset_for_each(task, cgrp, tset) {
+               tcred = __task_cred(task);
+
+               if ((current != task) && !capable(CAP_SYS_NICE) &&
+                   cred->euid != tcred->uid && cred->euid != tcred->suid)
+                       return -EACCES;
+       }
+
+       return 0;
+}
+
 static int cpu_cgroup_can_attach(struct cgroup *cgrp,
                                 struct cgroup_taskset *tset)
 {
@@ -8075,6 +8092,7 @@ 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,