Fix missing cpuset code from suspend/resume sequences.

-ck

Index: linux-3.12-ck1/kernel/sched/bfs.c
===================================================================
--- linux-3.12-ck1.orig/kernel/sched/bfs.c	2013-12-02 09:56:58.000000000 +1100
+++ linux-3.12-ck1/kernel/sched/bfs.c	2013-12-02 10:39:35.133023202 +1100
@@ -5390,24 +5390,21 @@ extern struct task_struct *cpu_stopper_t
 static void break_sole_affinity(int src_cpu, struct task_struct *idle)
 {
 	struct task_struct *p, *t, *stopper;
+	int unbound = 0;
 
 	stopper = per_cpu(cpu_stopper_task, src_cpu);
 	do_each_thread(t, p) {
-		if (p != stopper && p != idle && !online_cpus(p)) {
-			cpumask_copy(tsk_cpus_allowed(p), cpu_possible_mask);
-			/*
-			 * Don't tell them about moving exiting tasks or
-			 * kernel threads (both mm NULL), since they never
-			 * leave kernel.
-			 */
-			if (p->mm && printk_ratelimit()) {
-				printk(KERN_INFO "process %d (%s) no "
-				       "longer affine to cpu %d\n",
-				       task_pid_nr(p), p->comm, src_cpu);
-			}
+		if (p != stopper && !online_cpus(p)) {
+			cpuset_cpus_allowed_fallback(p);
+			unbound++;
 		}
 		clear_sticky(p);
 	} while_each_thread(t, p);
+
+	if (unbound) {
+		printk(KERN_INFO "Broke affinity for %d processes to cpu %d\n",
+		       unbound, src_cpu);
+	}
 }
 
 /*
@@ -6822,34 +6819,66 @@ 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(true);
-		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(false);
-		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;
 }
 
 #if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)