sched/numa: Modify migrate_swap() to accept additional parameters

There are checks in migrate_swap_stop() that check if the task/CPU
combination is as per migrate_swap_arg before migrating.

However atleast one of the two tasks to be swapped by migrate_swap() could
have migrated to a completely different CPU before updating the
migrate_swap_arg. The new CPU where the task is currently running could
be a different node too. If the task has migrated, numa balancer might
end up placing a task in a wrong node.  Instead of achieving node
consolidation, it may end up spreading the load across nodes.

To avoid that pass the CPUs as additional parameters.

While here, place migrate_swap under CONFIG_NUMA_BALANCING.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25377.3     25226.6     -0.59
1     72287       73326       1.437

Signed-off-by: Srikar Dronamraju <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: srikard

kernel/sched/core.c

@@ -1176,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
@@ -1257,16 +1258,17 @@ static int migrate_swap_stop(void *data)
 /*
  * Cross migrate two tasks
  */
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+		int target_cpu, int curr_cpu)
 {
 	struct migration_swap_arg arg;
 	int ret = -EINVAL;
 
 	arg = (struct migration_swap_arg){
 		.src_task = cur,
-		.src_cpu = task_cpu(cur),
+		.src_cpu = curr_cpu,
 		.dst_task = p,
-		.dst_cpu = task_cpu(p),
+		.dst_cpu = target_cpu,
 	};
 
 	if (arg.src_cpu == arg.dst_cpu)
@@ -1291,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 out:
 	return ret;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * wait_task_inactive - wait for a thread to unschedule.

kernel/sched/fair.c

@@ -1848,7 +1848,8 @@ static int task_numa_migrate(struct task_struct *p)
 		return ret;
 	}
 
-	ret = migrate_swap(p, env.best_task);
+	ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
 	if (ret != 0)
 		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
 	put_task_struct(env.best_task);

kernel/sched/sched.h

@@ -1099,7 +1099,8 @@ enum numa_faults_stats {
 };
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+			int cpu, int scpu);
 extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
 #else
 static inline void