The current cmpxchg() loop in setting the _QW_WAITING flag for writers
in queue_write_lock_slowpath() will contend with incoming readers
causing possibly extra cmpxchg() operations that are wasteful. This
patch changes the code to do a byte cmpxchg() to eliminate contention
with new readers.

A multithreaded microbenchmark running 5M read_lock/write_lock loop
on a 8-socket 80-core Westmere-EX machine running 4.0 based kernel
with the qspinlock patch have the following execution times (in ms)
with and without the patch:

With R:W ratio = 5:1

	Threads	   w/o patch	with patch	% change
	-------	   ---------	----------	--------
	   2	     990 	    895		  -9.6%
	   3	    2136 	   1912		 -10.5%
	   4	    3166	   2830		 -10.6%
	   5	    3953	   3629		  -8.2%
	   6	    4628	   4405		  -4.8%
	   7	    5344	   5197		  -2.8%
	   8	    6065	   6004		  -1.0%
	   9	    6826	   6811		  -0.2%
	  10	    7599	   7599		   0.0%
	  15	    9757	   9766		  +0.1%
	  20	   13767	  13817		  +0.4%

With small number of contending threads, this patch can improve
locking performance by up to 10%. With more contending threads,
however, the gain diminishes.

Signed-off-by: Waiman Long <redacted>
---
 kernel/locking/qrwlock.c |   28 ++++++++++++++++++++++++----
 1 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index d7d7557..559198a 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c

@@ -22,6 +22,26 @@
 #include <linux/hardirq.h>
 #include <asm/qrwlock.h>
 
+/*
+ * This internal data structure is used for optimizing access to some of
+ * the subfields within the atomic_t cnts.
+ */
+struct __qrwlock {
+	union {
+		atomic_t cnts;
+		struct {
+#ifdef __LITTLE_ENDIAN
+			u8 wmode;	/* Writer mode   */
+			u8 rcnts[3];	/* Reader counts */
+#else
+			u8 rcnts[3];	/* Reader counts */
+			u8 wmode;	/* Writer mode   */
+#endif
+		};
+	};
+	arch_spinlock_t	lock;
+};
+
 /**
  * rspin_until_writer_unlock - inc reader count & spin until writer is gone
  * @lock  : Pointer to queue rwlock structure

@@ -109,10 +129,10 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
 	 * or wait for a previous writer to go away.
 	 */
 	for (;;) {
-		cnts = atomic_read(&lock->cnts);
-		if (!(cnts & _QW_WMASK) &&
-		    (atomic_cmpxchg(&lock->cnts, cnts,
-				    cnts | _QW_WAITING) == cnts))
+		struct __qrwlock *l = (struct __qrwlock *)lock;
+
+		if (!READ_ONCE(l->wmode) &&
+		   (cmpxchg(&l->wmode, 0, _QW_WAITING) == 0))
 			break;