cpuset: make cs->{cpus, mems}_allowed as user-configured masks

Now we've used effective cpumasks to enforce hierarchical manner,
we can use cs->{cpus,mems}_allowed as configured masks.

Configured masks can be changed by writing cpuset.cpus and cpuset.mems
only. The new behaviors are:

- They won't be changed by hotplug anymore.
- They won't be limited by its parent's masks.

This ia a behavior change, but won't take effect unless mount with
sane_behavior.

v2:
- Add comments to explain the differences between configured masks and
effective masks.

Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 29 insertions, 6 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 820870a715f8..4b409d2ecbb9 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -77,6 +77,26 @@ struct cpuset {
 
         unsigned long flags;            /* "unsigned long" so bitops work */
 
+        /*
+         * On default hierarchy:
+         *
+         * The user-configured masks can only be changed by writing to
+         * cpuset.cpus and cpuset.mems, and won't be limited by the
+         * parent masks.
+         *
+         * The effective masks is the real masks that apply to the tasks
+         * in the cpuset. They may be changed if the configured masks are
+         * changed or hotplug happens.
+         *
+         * effective_mask == configured_mask & parent's effective_mask,
+         * and if it ends up empty, it will inherit the parent's mask.
+         *
+         *
+         * On legacy hierachy:
+         *
+         * The user-configured masks are always the same with effective masks.
+         */
+
         /* user-configured CPUs and Memory Nodes allow to tasks */
         cpumask_var_t cpus_allowed;
         nodemask_t mems_allowed;
@@ -450,9 +470,9 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
         par = parent_cs(cur);
 
-        /* We must be a subset of our parent cpuset */
+        /* On legacy hiearchy, we must be a subset of our parent cpuset. */
         ret = -EACCES;
-        if (!is_cpuset_subset(trial, par))
+        if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
                 goto out;
 
         /*
@@ -2167,6 +2187,7 @@ 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);
 
         mutex_lock(&cpuset_mutex);
 
@@ -2174,13 +2195,14 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
         cpumask_copy(&new_cpus, cpu_active_mask);
         new_mems = node_states[N_MEMORY];
 
-        cpus_updated = !cpumask_equal(top_cpuset.cpus_allowed, &new_cpus);
-        mems_updated = !nodes_equal(top_cpuset.mems_allowed, new_mems);
+        cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus);
+        mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
 
         /* synchronize cpus_allowed to cpu_active_mask */
         if (cpus_updated) {
                 mutex_lock(&callback_mutex);
-                cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+                if (!on_dfl)
+                        cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
                 cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
                 mutex_unlock(&callback_mutex);
                 /* we don't mess with cpumasks of tasks in top_cpuset */
@@ -2189,7 +2211,8 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
         /* synchronize mems_allowed to N_MEMORY */
         if (mems_updated) {
                 mutex_lock(&callback_mutex);
-                top_cpuset.mems_allowed = new_mems;
+                if (!on_dfl)
+                        top_cpuset.mems_allowed = new_mems;
                 top_cpuset.effective_mems = new_mems;
                 mutex_unlock(&callback_mutex);
                 update_tasks_nodemask(&top_cpuset);