lockdep: change scheduler annotation

While thinking about David's graph walk lockdep patch it _finally_
dawned on me that there is no reason we have a lock class per cpu ...

Sorry for being dense :-/

The below changes the annotation from a lock class per cpu, to a single
nested lock, as the scheduler never holds more that 2 rq locks at a time
anyway.

If there was code requiring holding all rq locks this would not work and
the original annotation would be the only option, but that not being the
case, this is a much lighter one.

Compiles and boots on a 2-way x86_64.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index 0236958..655f1db 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -600,7 +600,6 @@
 	/* BKL stats */
 	unsigned int bkl_count;
 #endif
-	struct lock_class_key rq_lock_key;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -2759,10 +2758,10 @@
 	} else {
 		if (rq1 < rq2) {
 			spin_lock(&rq1->lock);
-			spin_lock(&rq2->lock);
+			spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
 		} else {
 			spin_lock(&rq2->lock);
-			spin_lock(&rq1->lock);
+			spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
 		}
 	}
 	update_rq_clock(rq1);
@@ -2805,10 +2804,10 @@
 		if (busiest < this_rq) {
 			spin_unlock(&this_rq->lock);
 			spin_lock(&busiest->lock);
-			spin_lock(&this_rq->lock);
+			spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
 			ret = 1;
 		} else
-			spin_lock(&busiest->lock);
+			spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
 	}
 	return ret;
 }
@@ -7998,7 +7997,6 @@
 
 		rq = cpu_rq(i);
 		spin_lock_init(&rq->lock);
-		lockdep_set_class(&rq->lock, &rq->rq_lock_key);
 		rq->nr_running = 0;
 		init_cfs_rq(&rq->cfs, rq);
 		init_rt_rq(&rq->rt, rq);