cgroup: disallow debug controller on the default hierarchy

The debug controller, as its name suggests, exposes cgroup core
internals to userland to aid debugging.  Unfortunately, except for the
name, there's no provision to prevent its usage in production
configurations and the controller is widely enabled and mounted
leaking internal details to userland.  Like most other debug
information, the information exposed by debug isn't interesting even
for debugging itself once the related parts are working reliably.

This controller has no reason for existing.  This patch implements
cgrp_dfl_root_inhibit_ss_mask which can suppress specific subsystems
on the default hierarchy and adds the debug subsystem to it so that it
can be gradually deprecated as usages move towards the unified
hierarchy.

Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4afe544d35479329d42d83ab757d6869eedf4693..8a111dd42d7aea1764f55abd385ab149fcd196f1 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -305,6 +305,8 @@ enum {
         *   the flag is not created.
         *
         * - blkcg: blk-throttle becomes properly hierarchical.
+        *
+        * - debug: disallowed on the default hierarchy.
         */
        CGRP_ROOT_SANE_BEHAVIOR = (1 << 0),
 

diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 768fe44e19f0da66b9dbac8054e151a2e4b6a9d3..98c4f9b12b03742aae05101b3f6cbebc99ff28a0 100644 (file)
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -7,10 +7,6 @@
 SUBSYS(cpuset)
 #endif
 
-#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
-SUBSYS(debug)
-#endif
-
 #if IS_ENABLED(CONFIG_CGROUP_SCHED)
 SUBSYS(cpu)
 #endif
@@ -50,6 +46,13 @@ SUBSYS(net_prio)
 #if IS_ENABLED(CONFIG_CGROUP_HUGETLB)
 SUBSYS(hugetlb)
 #endif
+
+/*
+ * The following subsystems are not supported on the default hierarchy.
+ */
+#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
+SUBSYS(debug)
+#endif
 /*
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 082bb842b11a94a6163f38cf52ecbd56e9d1f881..a5f75ac4e793ac84eb5069473684c5c0edcd3699 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -148,6 +148,13 @@ struct cgroup_root cgrp_dfl_root;
  */
 static bool cgrp_dfl_root_visible;
 
+/* some controllers are not supported in the default hierarchy */
+static const unsigned int cgrp_dfl_root_inhibit_ss_mask = 0
+#ifdef CONFIG_CGROUP_DEBUG
+       | (1 << debug_cgrp_id)
+#endif
+       ;
+
 /* The list of hierarchy roots */
 
 static LIST_HEAD(cgroup_roots);
@@ -1126,6 +1133,7 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned int subsys_mask)
 static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask)
 {
        struct cgroup_subsys *ss;
+       unsigned int tmp_ss_mask;
        int ssid, i, ret;
 
        lockdep_assert_held(&cgroup_mutex);
@@ -1143,7 +1151,12 @@ static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask)
                        return -EBUSY;
        }
 
-       ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+       /* skip creating root files on dfl_root for inhibited subsystems */
+       tmp_ss_mask = ss_mask;
+       if (dst_root == &cgrp_dfl_root)
+               tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask;
+
+       ret = cgroup_populate_dir(&dst_root->cgrp, tmp_ss_mask);
        if (ret) {
                if (dst_root != &cgrp_dfl_root)
                        return ret;
@@ -2426,7 +2439,8 @@ static int cgroup_root_controllers_show(struct seq_file *seq, void *v)
 {
        struct cgroup *cgrp = seq_css(seq)->cgroup;
 
-       cgroup_print_ss_mask(seq, cgrp->root->subsys_mask);
+       cgroup_print_ss_mask(seq, cgrp->root->subsys_mask &
+                            ~cgrp_dfl_root_inhibit_ss_mask);
        return 0;
 }
 
@@ -2564,7 +2578,8 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
                if (tok[0] == '\0')
                        continue;
                for_each_subsys(ss, ssid) {
-                       if (ss->disabled || strcmp(tok + 1, ss->name))
+                       if (ss->disabled || strcmp(tok + 1, ss->name) ||
+                           ((1 << ss->id) & cgrp_dfl_root_inhibit_ss_mask))
                                continue;
 
                        if (*tok == '+') {