locking/qrwlock: Prevent slowpath writers getting held up by fastpath

When a prospective writer takes the qrwlock locking slowpath due to the
lock being held, it attempts to cmpxchg the wmode field from 0 to
_QW_WAITING so that concurrent lockers also take the slowpath and queue
on the spinlock accordingly, allowing the lockers to drain.

Unfortunately, this isn't fair, because a fastpath writer that comes in
after the lock is made available but before the _QW_WAITING flag is set
can effectively jump the queue. If there is a steady stream of prospective
writers, then the waiter will be held off indefinitely.

This patch restores fairness by separating _QW_WAITING and _QW_LOCKED
into two distinct fields: _QW_LOCKED continues to occupy the bottom byte
of the lockword so that it can be cleared unconditionally when unlocking,
but _QW_WAITING now occupies what used to be the bottom bit of the reader
count. This then forces the slow-path for concurrent lockers.

Tested-by: Waiman Long <longman@redhat.com>
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Tested-by: Adam Wallis <awallis@codeaurora.org>
Tested-by: Jan Glauber <jglauber@cavium.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Jeremy.Linton@arm.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1507810851-306-6-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index c716b02..0f7062b 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -26,24 +26,11 @@
 
 /*
  * Writer states & reader shift and bias.
- *
- *       | +0 | +1 | +2 | +3 |
- *   ----+----+----+----+----+
- *    LE | 78 | 56 | 34 | 12 | 0x12345678
- *   ----+----+----+----+----+
- *       | wr |      rd      |
- *       +----+----+----+----+
- *
- *   ----+----+----+----+----+
- *    BE | 12 | 34 | 56 | 78 | 0x12345678
- *   ----+----+----+----+----+
- *       |      rd      | wr |
- *       +----+----+----+----+
  */
-#define	_QW_WAITING	1		/* A writer is waiting	   */
-#define	_QW_LOCKED	0xff		/* A writer holds the lock */
-#define	_QW_WMASK	0xff		/* Writer mask		   */
-#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define	_QW_WAITING	0x100		/* A writer is waiting	   */
+#define	_QW_LOCKED	0x0ff		/* A writer holds the lock */
+#define	_QW_WMASK	0x1ff		/* Writer mask		   */
+#define	_QR_SHIFT	9		/* Reader count shift	   */
 #define _QR_BIAS	(1U << _QR_SHIFT)
 
 /*
@@ -134,7 +121,7 @@
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	smp_store_release(&lock->wmode, 0);
+	smp_store_release(&lock->wlocked, 0);
 }
 
 /*
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
index 507f2dc..8af752a 100644
--- a/include/asm-generic/qrwlock_types.h
+++ b/include/asm-generic/qrwlock_types.h
@@ -13,11 +13,11 @@
 		atomic_t cnts;
 		struct {
 #ifdef __LITTLE_ENDIAN
-			u8 wmode;	/* Writer mode   */
-			u8 rcnts[3];	/* Reader counts */
+			u8 wlocked;	/* Locked for write? */
+			u8 __lstate[3];
 #else
-			u8 rcnts[3];	/* Reader counts */
-			u8 wmode;	/* Writer mode   */
+			u8 __lstate[3];
+			u8 wlocked;	/* Locked for write? */
 #endif
 		};
 	};