libgfortran: Replace mutex with rwlock

This patch try to introduce the rwlock and split the read/write to
unit_root tree and unit_cache with rwlock instead of the mutex to
increase CPU efficiency. In the get_gfc_unit function, the percentage
to step into the insert_unit function is around 30%, in most instances,
we can get the unit in the phase of reading the unit_cache or unit_root
tree. So split the read/write phase by rwlock would be an approach to
make it more parallel.

BTW, the IPC metrics can gain around 9x in our test
server with 220 cores. The benchmark we used is
https://github.com/rwesson/NEAT

libgcc/ChangeLog:

	* gthr-posix.h (__GTHREAD_RWLOCK_INIT): New macro.
	(__gthrw): New function.
	(__gthread_rwlock_rdlock): New function.
	(__gthread_rwlock_tryrdlock): New function.
	(__gthread_rwlock_wrlock): New function.
	(__gthread_rwlock_trywrlock): New function.
	(__gthread_rwlock_unlock): New function.

libgfortran/ChangeLog:

	* io/async.c (DEBUG_LINE): New macro.
	* io/async.h (RWLOCK_DEBUG_ADD): New macro.
	(CHECK_RDLOCK): New macro.
	(CHECK_WRLOCK): New macro.
	(TAIL_RWLOCK_DEBUG_QUEUE): New macro.
	(IN_RWLOCK_DEBUG_QUEUE): New macro.
	(RDLOCK): New macro.
	(WRLOCK): New macro.
	(RWUNLOCK): New macro.
	(RD_TO_WRLOCK): New macro.
	(INTERN_RDLOCK): New macro.
	(INTERN_WRLOCK): New macro.
	(INTERN_RWUNLOCK): New macro.
	* io/io.h (struct gfc_unit): Change UNIT_LOCK to UNIT_RWLOCK in
	a comment.
	(unit_lock): Remove including associated internal_proto.
	(unit_rwlock): New declarations including associated internal_proto.
	(dec_waiting_unlocked): Use WRLOCK and RWUNLOCK on unit_rwlock
	instead of __gthread_mutex_lock and __gthread_mutex_unlock on
	unit_lock.
	* io/transfer.c (st_read_done_worker): Use WRLOCK and RWUNLOCK on
	unit_rwlock instead of LOCK and UNLOCK on unit_lock.
	(st_write_done_worker): Likewise.
	* io/unit.c: Change UNIT_LOCK to UNIT_RWLOCK in 'IO locking rules'
	comment. Use unit_rwlock variable instead of unit_lock variable.
	(get_gfc_unit_from_unit_root): New function.
	(get_gfc_unit): Use RDLOCK, WRLOCK and RWUNLOCK on unit_rwlock
	instead of LOCK and UNLOCK on unit_lock.
	(close_unit_1): Use WRLOCK and RWUNLOCK on unit_rwlock instead of
	LOCK and UNLOCK on unit_lock.
	(close_units): Likewise.
	(newunit_alloc): Use RWUNLOCK on unit_rwlock instead of UNLOCK on
	unit_lock.
	* io/unix.c (find_file): Use RDLOCK and RWUNLOCK on unit_rwlock
	instead of LOCK and UNLOCK on unit_lock.
	(flush_all_units): Use WRLOCK and RWUNLOCK on unit_rwlock instead
	of LOCK and UNLOCK on unit_lock.

1 files changed, 60 insertions, 0 deletions

diff --git a/libgcc/gthr-posix.h b/libgcc/gthr-posix.h
index aebcfdd..7328308 100644
--- a/libgcc/gthr-posix.h
+++ b/libgcc/gthr-posix.h
@@ -48,6 +48,9 @@ typedef pthread_t __gthread_t;
 typedef pthread_key_t __gthread_key_t;
 typedef pthread_once_t __gthread_once_t;
 typedef pthread_mutex_t __gthread_mutex_t;
+#ifndef __cplusplus
+typedef pthread_rwlock_t __gthread_rwlock_t;
+#endif
 typedef pthread_mutex_t __gthread_recursive_mutex_t;
 typedef pthread_cond_t __gthread_cond_t;
 typedef struct timespec __gthread_time_t;
@@ -58,6 +61,9 @@ typedef struct timespec __gthread_time_t;
 
 #define __GTHREAD_MUTEX_INIT PTHREAD_MUTEX_INITIALIZER
 #define __GTHREAD_MUTEX_INIT_FUNCTION __gthread_mutex_init_function
+#ifndef __cplusplus
+#define __GTHREAD_RWLOCK_INIT PTHREAD_RWLOCK_INITIALIZER
+#endif
 #define __GTHREAD_ONCE_INIT PTHREAD_ONCE_INIT
 #if defined(PTHREAD_RECURSIVE_MUTEX_INITIALIZER)
 #define __GTHREAD_RECURSIVE_MUTEX_INIT PTHREAD_RECURSIVE_MUTEX_INITIALIZER
@@ -135,6 +141,13 @@ __gthrw(pthread_mutexattr_init)
 __gthrw(pthread_mutexattr_settype)
 __gthrw(pthread_mutexattr_destroy)
 
+#ifndef __cplusplus
+__gthrw(pthread_rwlock_rdlock)
+__gthrw(pthread_rwlock_tryrdlock)
+__gthrw(pthread_rwlock_wrlock)
+__gthrw(pthread_rwlock_trywrlock)
+__gthrw(pthread_rwlock_unlock)
+#endif
 
 #if defined(_LIBOBJC) || defined(_LIBOBJC_WEAK)
 /* Objective-C.  */
@@ -885,6 +898,53 @@ __gthread_cond_destroy (__gthread_cond_t* __cond)
   return __gthrw_(pthread_cond_destroy) (__cond);
 }
 
+#ifndef __cplusplus
+static inline int
+__gthread_rwlock_rdlock (__gthread_rwlock_t *__rwlock)
+{
+  if (__gthread_active_p ())
+    return __gthrw_(pthread_rwlock_rdlock) (__rwlock);
+  else
+    return 0;
+}
+
+static inline int
+__gthread_rwlock_tryrdlock (__gthread_rwlock_t *__rwlock)
+{
+  if (__gthread_active_p ())
+    return __gthrw_(pthread_rwlock_tryrdlock) (__rwlock);
+  else
+    return 0;
+}
+
+static inline int
+__gthread_rwlock_wrlock (__gthread_rwlock_t *__rwlock)
+{
+  if (__gthread_active_p ())
+    return __gthrw_(pthread_rwlock_wrlock) (__rwlock);
+  else
+    return 0;
+}
+
+static inline int
+__gthread_rwlock_trywrlock (__gthread_rwlock_t *__rwlock)
+{
+  if (__gthread_active_p ())
+    return __gthrw_(pthread_rwlock_trywrlock) (__rwlock);
+  else
+    return 0;
+}
+
+static inline int
+__gthread_rwlock_unlock (__gthread_rwlock_t *__rwlock)
+{
+  if (__gthread_active_p ())
+    return __gthrw_(pthread_rwlock_unlock) (__rwlock);
+  else
+    return 0;
+}
+#endif
+
 #endif /* _LIBOBJC */
 
 #endif /* ! GCC_GTHR_POSIX_H */