locking/pvqspinlock: Move lock stealing count tracking code into pv_queued_spin_steal_lock()

This patch moves the lock stealing count tracking code into
pv_queued_spin_steal_lock() instead of via a jacket function simplifying
the code.

Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1449778666-13593-3-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 87bb235..78f04a2 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -55,6 +55,11 @@
 };
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * By replacing the regular queued_spin_trylock() with the function below,
  * it will be called once when a lock waiter enter the PV slowpath before
  * being queued. By allowing one lock stealing attempt here when the pending
@@ -65,9 +70,11 @@
 static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
+	int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
+		   (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
 
-	return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
-		(cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
+	qstat_inc(qstat_pv_lock_stealing, ret);
+	return ret;
 }
 
 /*
@@ -138,11 +145,6 @@
 #endif /* _Q_PENDING_BITS == 8 */
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Lock and MCS node addresses hash table for fast lookup
  *
  * Hashing is done on a per-cacheline basis to minimize the need to access