2 files changed, 39 insertions, 4 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8c8bd652dd12..746d1eeb5dbe 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2054,6 +2054,9 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * (of no affect) on systems that are actively using CPU hotplug
  * but making no active use of cpusets.
  *
+ * The only exception to this is suspend/resume, where we don't
+ * modify cpusets at all.
+ *
  * This routine ensures that top_cpuset.cpus_allowed tracks
  * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 468bdd44c1ba..4c1d80c6b318 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7097,34 +7097,66 @@ match2:
         mutex_unlock(&sched_domains_mutex);
 }
 
+static int num_cpus_frozen;     /* used to mark begin/end of suspend/resume */
+
 /*
  * Update cpusets according to cpu_active mask.  If cpusets are
  * disabled, cpuset_update_active_cpus() becomes a simple wrapper
  * around partition_sched_domains().
+ *
+ * If we come here as part of a suspend/resume, don't touch cpusets because we
+ * want to restore it back to its original state upon resume anyway.
  */
 static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
                              void *hcpu)
 {
-        switch (action & ~CPU_TASKS_FROZEN) {
+        switch (action) {
+        case CPU_ONLINE_FROZEN:
+        case CPU_DOWN_FAILED_FROZEN:
+
+                /*
+                 * num_cpus_frozen tracks how many CPUs are involved in suspend
+                 * resume sequence. As long as this is not the last online
+                 * operation in the resume sequence, just build a single sched
+                 * domain, ignoring cpusets.
+                 */
+                num_cpus_frozen--;
+                if (likely(num_cpus_frozen)) {
+                        partition_sched_domains(1, NULL, NULL);
+                        break;
+                }
+
+                /*
+                 * This is the last CPU online operation. So fall through and
+                 * restore the original sched domains by considering the
+                 * cpuset configurations.
+                 */
+
         case CPU_ONLINE:
         case CPU_DOWN_FAILED:
                 cpuset_update_active_cpus();
-                return NOTIFY_OK;
+                break;
         default:
                 return NOTIFY_DONE;
         }
+        return NOTIFY_OK;
 }
 
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
                                void *hcpu)
 {
-        switch (action & ~CPU_TASKS_FROZEN) {
+        switch (action) {
         case CPU_DOWN_PREPARE:
                 cpuset_update_active_cpus();
-                return NOTIFY_OK;
+                break;
+        case CPU_DOWN_PREPARE_FROZEN:
+                num_cpus_frozen++;
+                partition_sched_domains(1, NULL, NULL);
+                break;
         default:
                 return NOTIFY_DONE;
         }
+        return NOTIFY_OK;
 }
 
 void __init sched_init_smp(void)