cgroup: replace cgroup_on_dfl() tests in controllers with cgroup_subsys_on_dfl()

cgroup_on_dfl() tests whether the cgroup's root is the default
hierarchy; however, an individual controller is only interested in
whether the controller is attached to the default hierarchy and never
tests a cgroup which doesn't belong to the hierarchy that the
controller is attached to.

This patch replaces cgroup_on_dfl() tests in controllers with faster
static_key based cgroup_subsys_on_dfl().  This leaves cgroup core as
the only user of cgroup_on_dfl() and the function is moved from the
header file to cgroup.c.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Zefan Li <lizefan@huawei.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index c75a2636dd404840ea13000ea5747e0d44ddd7be..2149a1ddbacf21a02a164b042c76e06bf6734c77 100644 (file)
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -369,7 +369,7 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
         * regardless of the position of the group in the hierarchy.
         */
        sq->parent_sq = &td->service_queue;
-       if (cgroup_on_dfl(blkg->blkcg->css.cgroup) && blkg->parent)
+       if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
                sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
        tg->td = td;
 }

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 04de88463a986384b54fa57593d2c89e7189e95c..1f9093e901daed7849a54633be5d80ce96b010f4 100644 (file)
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1581,7 +1581,7 @@ static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp)
 static void cfq_cpd_init(struct blkcg_policy_data *cpd)
 {
        struct cfq_group_data *cgd = cpd_to_cfqgd(cpd);
-       unsigned int weight = cgroup_on_dfl(blkcg_root.css.cgroup) ?
+       unsigned int weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
                              CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL;
 
        if (cpd_to_blkcg(cpd) == &blkcg_root)
@@ -1599,7 +1599,7 @@ static void cfq_cpd_free(struct blkcg_policy_data *cpd)
 static void cfq_cpd_bind(struct blkcg_policy_data *cpd)
 {
        struct blkcg *blkcg = cpd_to_blkcg(cpd);
-       bool on_dfl = cgroup_on_dfl(blkcg_root.css.cgroup);
+       bool on_dfl = cgroup_subsys_on_dfl(io_cgrp_subsys);
        unsigned int weight = on_dfl ? CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL;
 
        if (blkcg == &blkcg_root)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c3a9f1eb409739e12453073bee03081cf17fa99e..355bf2ed886730be83611711339d587b4e41c85a 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -433,64 +433,6 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
        return task_css(task, subsys_id)->cgroup;
 }
 
-/**
- * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
- * @cgrp: the cgroup of interest
- *
- * The default hierarchy is the v2 interface of cgroup and this function
- * can be used to test whether a cgroup is on the default hierarchy for
- * cases where a subsystem should behave differnetly depending on the
- * interface version.
- *
- * The set of behaviors which change on the default hierarchy are still
- * being determined and the mount option is prefixed with __DEVEL__.
- *
- * List of changed behaviors:
- *
- * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
- *   and "name" are disallowed.
- *
- * - When mounting an existing superblock, mount options should match.
- *
- * - Remount is disallowed.
- *
- * - rename(2) is disallowed.
- *
- * - "tasks" is removed.  Everything should be at process granularity.  Use
- *   "cgroup.procs" instead.
- *
- * - "cgroup.procs" is not sorted.  pids will be unique unless they got
- *   recycled inbetween reads.
- *
- * - "release_agent" and "notify_on_release" are removed.  Replacement
- *   notification mechanism will be implemented.
- *
- * - "cgroup.clone_children" is removed.
- *
- * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
- *   and its descendants contain no task; otherwise, 1.  The file also
- *   generates kernfs notification which can be monitored through poll and
- *   [di]notify when the value of the file changes.
- *
- * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
- *   take masks of ancestors with non-empty cpus/mems, instead of being
- *   moved to an ancestor.
- *
- * - cpuset: a task can be moved into an empty cpuset, and again it takes
- *   masks of ancestors.
- *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
- * - blkcg: blk-throttle becomes properly hierarchical.
- *
- * - debug: disallowed on the default hierarchy.
- */
-static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
-{
-       return cgrp->root == &cgrp_dfl_root;
-}
-
 /* no synchronization, the result can only be used as a hint */
 static inline bool cgroup_has_tasks(struct cgroup *cgrp)
 {

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5703ba791b3d1e79d02d6b8fe854a3bab233aaae..c24f929fdeb70433714660711ce4076c4f9041b4 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -237,6 +237,64 @@ static bool cgroup_ssid_enabled(int ssid)
        return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
 }
 
+/**
+ * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
+ * @cgrp: the cgroup of interest
+ *
+ * The default hierarchy is the v2 interface of cgroup and this function
+ * can be used to test whether a cgroup is on the default hierarchy for
+ * cases where a subsystem should behave differnetly depending on the
+ * interface version.
+ *
+ * The set of behaviors which change on the default hierarchy are still
+ * being determined and the mount option is prefixed with __DEVEL__.
+ *
+ * List of changed behaviors:
+ *
+ * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
+ *   and "name" are disallowed.
+ *
+ * - When mounting an existing superblock, mount options should match.
+ *
+ * - Remount is disallowed.
+ *
+ * - rename(2) is disallowed.
+ *
+ * - "tasks" is removed.  Everything should be at process granularity.  Use
+ *   "cgroup.procs" instead.
+ *
+ * - "cgroup.procs" is not sorted.  pids will be unique unless they got
+ *   recycled inbetween reads.
+ *
+ * - "release_agent" and "notify_on_release" are removed.  Replacement
+ *   notification mechanism will be implemented.
+ *
+ * - "cgroup.clone_children" is removed.
+ *
+ * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
+ *   and its descendants contain no task; otherwise, 1.  The file also
+ *   generates kernfs notification which can be monitored through poll and
+ *   [di]notify when the value of the file changes.
+ *
+ * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
+ *   take masks of ancestors with non-empty cpus/mems, instead of being
+ *   moved to an ancestor.
+ *
+ * - cpuset: a task can be moved into an empty cpuset, and again it takes
+ *   masks of ancestors.
+ *
+ * - memcg: use_hierarchy is on by default and the cgroup file for the flag
+ *   is not created.
+ *
+ * - blkcg: blk-throttle becomes properly hierarchical.
+ *
+ * - debug: disallowed on the default hierarchy.
+ */
+static bool cgroup_on_dfl(const struct cgroup *cgrp)
+{
+       return cgrp->root == &cgrp_dfl_root;
+}
+
 /* IDR wrappers which synchronize using cgroup_idr_lock */
 static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
                            gfp_t gfp_mask)

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f0acff0f66c91380412dcbc1c899c94b1d3236b0..20eedd8098c063ae648ee5d522efe913b052572a 100644 (file)
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -473,7 +473,8 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
        /* On legacy hiearchy, we must be a subset of our parent cpuset. */
        ret = -EACCES;
-       if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
+       if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+           !is_cpuset_subset(trial, par))
                goto out;
 
        /*
@@ -879,7 +880,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
                 * If it becomes empty, inherit the effective mask of the
                 * parent, which is guaranteed to have some CPUs.
                 */
-               if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))
+               if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+                   cpumask_empty(new_cpus))
                        cpumask_copy(new_cpus, parent->effective_cpus);
 
                /* Skip the whole subtree if the cpumask remains the same. */
@@ -896,7 +898,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
                cpumask_copy(cp->effective_cpus, new_cpus);
                spin_unlock_irq(&callback_lock);
 
-               WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+               WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
                        !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
                update_tasks_cpumask(cp);
@@ -1135,7 +1137,8 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
                 * If it becomes empty, inherit the effective mask of the
                 * parent, which is guaranteed to have some MEMs.
                 */
-               if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))
+               if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+                   nodes_empty(*new_mems))
                        *new_mems = parent->effective_mems;
 
                /* Skip the whole subtree if the nodemask remains the same. */
@@ -1152,7 +1155,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
                cp->effective_mems = *new_mems;
                spin_unlock_irq(&callback_lock);
 
-               WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+               WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
                        !nodes_equal(cp->mems_allowed, cp->effective_mems));
 
                update_tasks_nodemask(cp);
@@ -1440,7 +1443,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 
        /* allow moving tasks into an empty cpuset if on default hierarchy */
        ret = -ENOSPC;
-       if (!cgroup_on_dfl(css->cgroup) &&
+       if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
            (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
                goto out_unlock;
 
@@ -1952,7 +1955,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
        cpuset_inc();
 
        spin_lock_irq(&callback_lock);
-       if (cgroup_on_dfl(cs->css.cgroup)) {
+       if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
                cpumask_copy(cs->effective_cpus, parent->effective_cpus);
                cs->effective_mems = parent->effective_mems;
        }
@@ -2029,7 +2032,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
        mutex_lock(&cpuset_mutex);
        spin_lock_irq(&callback_lock);
 
-       if (cgroup_on_dfl(root_css->cgroup)) {
+       if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
                cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
                top_cpuset.mems_allowed = node_possible_map;
        } else {
@@ -2210,7 +2213,7 @@ retry:
        cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
        mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-       if (cgroup_on_dfl(cs->css.cgroup))
+       if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
                hotplug_update_tasks(cs, &new_cpus, &new_mems,
                                     cpus_updated, mems_updated);
        else
@@ -2241,7 +2244,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
        static cpumask_t new_cpus;
        static nodemask_t new_mems;
        bool cpus_updated, mems_updated;
-       bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup);
+       bool on_dfl = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
 
        mutex_lock(&cpuset_mutex);
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ddaeba34e097a7553d33b8add26e26a27d3c81a..b35c4cc47a30ae1e33c59d31b9bb2c54fb84d41a 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -434,7 +434,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 
        memcg = page->mem_cgroup;
 
-       if (!memcg || !cgroup_on_dfl(memcg->css.cgroup))
+       if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
                memcg = root_mem_cgroup;
 
        rcu_read_unlock();
@@ -5059,7 +5059,7 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
         * guarantees that @root doesn't have any children, so turning it
         * on for the root memcg is enough.
         */
-       if (cgroup_on_dfl(root_css->cgroup))
+       if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
                root_mem_cgroup->use_hierarchy = true;
        else
                root_mem_cgroup->use_hierarchy = false;