[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1456351975-1899-2-git-send-email-tj@kernel.org>
Date: Wed, 24 Feb 2016 17:12:54 -0500
From: Tejun Heo <tj@...nel.org>
To: lizefan@...wei.com, hannes@...xchg.org, a.p.zijlstra@...llo.nl,
mingo@...hat.com, acme@...nel.org
Cc: linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
kernel-team@...com, Tejun Heo <tj@...nel.org>
Subject: [PATCH 1/2] cgroup: implement cgroup_subsys->implicit_on_dfl
Some controllers, perf_event for now and possibly freezer in the
future, don't really make sense to control explicitly through
"cgroup.subtree_control". For example, the primary role of perf_event
is identifying the cgroups of tasks; however, because the controller
also keeps a small amount of state per cgroup, it can't be replaced
with simple cgroup membership tests.
This patch implements cgroup_subsys->implicit_on_dfl flag. When set,
the controller is implicitly enabled on all cgroups on the v2
hierarchy so that utility type controllers such as perf_event can be
enabled and function transparently.
An implicit controller doesn't show up in "cgroup.controllers" or
"cgroup.subtree_control", is exempt from no internal process rule and
can be stolen from the default hierarchy even if there are non-root
csses.
v2: Reimplemented on top of the recent updates to css handling and
subsystem rebinding. Rebinding implicit subsystems is now a
simple matter of exempting it from the busy subsystem check.
Signed-off-by: Tejun Heo <tj@...nel.org>
---
include/linux/cgroup-defs.h | 13 +++++++++++++
kernel/cgroup.c | 38 +++++++++++++++++++++++++++++++-------
2 files changed, 44 insertions(+), 7 deletions(-)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index aae8c94..0af8dc4 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -450,6 +450,19 @@ struct cgroup_subsys {
bool early_init:1;
/*
+ * If %true, the controller, on the default hierarchy, doesn't show
+ * up in "cgroup.controllers" or "cgroup.subtree_control", is
+ * implicitly enabled on all cgroups on the default hierarchy, and
+ * bypasses the "no internal process" constraint. This is for
+ * utility type controllers which is transparent to userland.
+ *
+ * An implicit controller can be stolen from the default hierarchy
+ * anytime and thus must be okay with offline csses from previous
+ * hierarchies coexisting with csses for the current one.
+ */
+ bool implicit_on_dfl:1;
+
+ /*
* If %false, this subsystem is properly hierarchical -
* configuration, resource accounting and restriction on a parent
* cgroup cover those of its children. If %true, hierarchy support
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a44c123..0f17c65 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -186,6 +186,9 @@ static u16 cgroup_no_v1_mask;
/* some controllers are not supported in the default hierarchy */
static u16 cgrp_dfl_inhibit_ss_mask;
+/* some controllers are implicitly enabled on the default hierarchy */
+static unsigned long cgrp_dfl_implicit_ss_mask;
+
/* The list of hierarchy roots */
static LIST_HEAD(cgroup_roots);
@@ -359,8 +362,8 @@ static u16 cgroup_control(struct cgroup *cgrp)
return parent->subtree_control;
if (cgroup_on_dfl(cgrp))
- root_ss_mask &= ~cgrp_dfl_inhibit_ss_mask;
-
+ root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask |
+ cgrp_dfl_implicit_ss_mask);
return root_ss_mask;
}
@@ -1326,6 +1329,8 @@ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask)
lockdep_assert_held(&cgroup_mutex);
+ cur_ss_mask |= cgrp_dfl_implicit_ss_mask;
+
while (true) {
u16 new_ss_mask = cur_ss_mask;
@@ -1511,8 +1516,13 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
lockdep_assert_held(&cgroup_mutex);
do_each_subsys_mask(ss, ssid, ss_mask) {
- /* if @ss has non-root csses attached to it, can't move */
- if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)))
+ /*
+ * If @ss has non-root csses attached to it, can't move.
+ * If @ss is an implicit controller, it is exempt from this
+ * rule and can be stolen.
+ */
+ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) &&
+ !ss->implicit_on_dfl)
return -EBUSY;
/* can't move between two non-dummy roots either */
@@ -3032,6 +3042,18 @@ static void cgroup_restore_control(struct cgroup *cgrp)
}
}
+static bool css_visible(struct cgroup_subsys_state *css)
+{
+ struct cgroup_subsys *ss = css->ss;
+ struct cgroup *cgrp = css->cgroup;
+
+ if (cgroup_control(cgrp) & (1 << ss->id))
+ return true;
+ if (!(cgroup_ss_mask(cgrp) & (1 << ss->id)))
+ return false;
+ return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl;
+}
+
/**
* cgroup_apply_control_enable - enable or show csses according to control
* @cgrp: root of the target subtree
@@ -3067,7 +3089,7 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp)
return PTR_ERR(css);
}
- if (cgroup_control(dsct) & (1 << ss->id)) {
+ if (css_visible(css)) {
ret = css_populate_dir(css);
if (ret)
return ret;
@@ -3110,7 +3132,7 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp)
if (css->parent &&
!(cgroup_ss_mask(dsct) & (1 << ss->id))) {
kill_css(css);
- } else if (!(cgroup_control(dsct) & (1 << ss->id))) {
+ } else if (!css_visible(css)) {
css_clear_dir(css);
if (ss->css_reset)
ss->css_reset(css);
@@ -5440,7 +5462,9 @@ int __init cgroup_init(void)
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
- if (!ss->dfl_cftypes)
+ if (ss->implicit_on_dfl)
+ cgrp_dfl_implicit_ss_mask |= 1 << ss->id;
+ else if (!ss->dfl_cftypes)
cgrp_dfl_inhibit_ss_mask |= 1 << ss->id;
if (ss->dfl_cftypes == ss->legacy_cftypes) {
--
2.5.0
Powered by blists - more mailing lists