locking/rwsem: Reduce the size of struct rw_semaphore

Recent optimistic spinning additions to rwsem provide significant performance
benefits on many workloads on large machines. The cost of it was increasing
the size of the rwsem structure by up to 128 bits.

However, now that the previous patches in this series bring the overhead of
struct optimistic_spin_queue to 32 bits, this patch reorders some fields in
struct rw_semaphore such that we can reduce the overhead of the rwsem structure
by 64 bits (on 64 bit systems).

The extra overhead required for rwsem optimistic spinning would now be up
to 8 additional bytes instead of up to 16 bytes. Additionally, the size of
rwsem would now be more in line with mutexes.

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Waiman Long <waiman.long@hp.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Link: http://lkml.kernel.org/r/1405358872-3732-6-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/rwsem.h

@@ -24,15 +24,15 @@ struct rw_semaphore;
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
 	long count;
-	raw_spinlock_t wait_lock;
 	struct list_head wait_list;
+	raw_spinlock_t wait_lock;
 #ifdef CONFIG_SMP
+	struct optimistic_spin_queue osq; /* spinner MCS lock */
 	/*
 	 * Write owner. Used as a speculative check to see
 	 * if the owner is running on the cpu.
 	 */
 	struct task_struct *owner;
-	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
@@ -64,21 +64,18 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
-#define __RWSEM_INITIALIZER(name)			\
-	{ RWSEM_UNLOCKED_VALUE,				\
-	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list),		\
-	  NULL, /* owner */				\
-	  OSQ_LOCK_UNLOCKED /* osq */			\
-	  __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
 #else
-#define __RWSEM_INITIALIZER(name)			\
-	{ RWSEM_UNLOCKED_VALUE,				\
-	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list)		\
-	  __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_OPT_INIT(lockname)
 #endif
 
+#define __RWSEM_INITIALIZER(name)				\
+	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
+	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
+	  __RWSEM_OPT_INIT(name)				\
+	  __RWSEM_DEP_MAP_INIT(name) }
+
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)