cgroup/cpuset: Always use cpu_active_mask

The current cpuset code uses both cpu_active_mask and cpu_online_mask
and it can be confusing which one should be used if we need to update
the code.

The top_cpuset is always synchronized to cpu_active_mask and we should
avoid using cpu_online_mask as much as possible. An active CPU is always
an online CPU, but not vice versa. cpu_active_mask and cpu_online_mask
can differ during hotplug operations.

A CPU is marked active at the last stage of CPU bringup (CPUHP_AP_ACTIVE).
It is also the stage where cpuset hotplug code will be called to update
the sched domains so that the scheduler can move a normal task to a
newly active CPU or remove tasks away from a newly inactivated CPU. The
online bit is set much earlier in the CPU bringup process and cleared
much later in CPU teardown.

If cpu_online_mask is used while a hotunplug operation is happening in
parallel, we may leave an offline CPU in cpu_allowed or have a higher
chance of leaving an offline CPU in some other masks.  Avoid this
problem by always using cpu_active_mask in the cpuset code and leave
a comment as to why the use of cpu_online_mask is discouraged.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 306b60430091452e4ddd263a5aed9aee79ab3417..583f20942802e98eb0f63e45bbd4ce39baf56150 100644 (file)
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -192,6 +192,20 @@ static inline void notify_partition_change(struct cpuset *cs, int old_prs)
                WRITE_ONCE(cs->prs_err, PERR_NONE);
 }
 
+/*
+ * The top_cpuset is always synchronized to cpu_active_mask and we should avoid
+ * using cpu_online_mask as much as possible. An active CPU is always an online
+ * CPU, but not vice versa. cpu_active_mask and cpu_online_mask can differ
+ * during hotplug operations. A CPU is marked active at the last stage of CPU
+ * bringup (CPUHP_AP_ACTIVE). It is also the stage where cpuset hotplug code
+ * will be called to update the sched domains so that the scheduler can move
+ * a normal task to a newly active CPU or remove tasks away from a newly
+ * inactivated CPU. The online bit is set much earlier in the CPU bringup
+ * process and cleared much later in CPU teardown.
+ *
+ * If cpu_online_mask is used while a hotunplug operation is happening in
+ * parallel, we may leave an offline CPU in cpu_allowed or some other masks.
+ */
 static struct cpuset top_cpuset = {
        .flags = BIT(CS_ONLINE) | BIT(CS_CPU_EXCLUSIVE) |
                 BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE),
@@ -355,18 +369,18 @@ static inline bool partition_is_populated(struct cpuset *cs,
  * appropriate cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
- * of cpu_online_mask.
+ * of cpu_active_mask.
  *
  * Call with callback_lock or cpuset_mutex held.
  */
-static void guarantee_online_cpus(struct task_struct *tsk,
+static void guarantee_active_cpus(struct task_struct *tsk,
                                  struct cpumask *pmask)
 {
        const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
        struct cpuset *cs;
 
-       if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
-               cpumask_copy(pmask, cpu_online_mask);
+       if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_active_mask)))
+               cpumask_copy(pmask, cpu_active_mask);
 
        rcu_read_lock();
        cs = task_cs(tsk);
@@ -2263,7 +2277,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
        bool force = false;
        int old_prs = cs->partition_root_state;
 
-       /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
+       /* top_cpuset.cpus_allowed tracks cpu_active_mask; it's read-only */
        if (cs == &top_cpuset)
                return -EACCES;
 
@@ -3082,7 +3096,7 @@ static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
        lockdep_assert_held(&cpuset_mutex);
 
        if (cs != &top_cpuset)
-               guarantee_online_cpus(task, cpus_attach);
+               guarantee_active_cpus(task, cpus_attach);
        else
                cpumask_andnot(cpus_attach, task_cpu_possible_mask(task),
                               subpartitions_cpus);
@@ -4026,7 +4040,7 @@ void __init cpuset_init_smp(void)
  *
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of cpu_online_mask, even if this means going outside the
+ * subset of cpu_active_mask, even if this means going outside the
  * tasks cpuset, except when the task is in the top cpuset.
  **/
 
@@ -4040,7 +4054,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 
        cs = task_cs(tsk);
        if (cs != &top_cpuset)
-               guarantee_online_cpus(tsk, pmask);
+               guarantee_active_cpus(tsk, pmask);
        /*
         * Tasks in the top cpuset won't get update to their cpumasks
         * when a hotplug online/offline event happens. So we include all
@@ -4054,7 +4068,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
                 * allowable online cpu left, we fall back to all possible cpus.
                 */
                cpumask_andnot(pmask, possible_mask, subpartitions_cpus);
-               if (!cpumask_intersects(pmask, cpu_online_mask))
+               if (!cpumask_intersects(pmask, cpu_active_mask))
                        cpumask_copy(pmask, possible_mask);
        }