New pthread rwlock that is more scalable.

This replaces the pthread rwlock with a new implementation that uses a
more scalable algorithm (primarily through not using a critical section
anymore to make state changes).  The fast path for rdlock acquisition and
release is now basically a single atomic read-modify write or CAS and a few
branches.  See nptl/pthread_rwlock_common.c for details.

	* nptl/DESIGN-rwlock.txt: Remove.
	* nptl/lowlevelrwlock.sym: Remove.
	* nptl/Makefile: Add new tests.
	* nptl/pthread_rwlock_common.c: New file.  Contains the new rwlock.
	* nptl/pthreadP.h (PTHREAD_RWLOCK_PREFER_READER_P): Remove.
	(PTHREAD_RWLOCK_WRPHASE, PTHREAD_RWLOCK_WRLOCKED,
	PTHREAD_RWLOCK_RWAITING, PTHREAD_RWLOCK_READER_SHIFT,
	PTHREAD_RWLOCK_READER_OVERFLOW, PTHREAD_RWLOCK_WRHANDOVER,
	PTHREAD_RWLOCK_FUTEX_USED): New.
	* nptl/pthread_rwlock_init.c (__pthread_rwlock_init): Adapt to new
	implementation.
	* nptl/pthread_rwlock_rdlock.c (__pthread_rwlock_rdlock_slow): Remove.
	(__pthread_rwlock_rdlock): Adapt.
	* nptl/pthread_rwlock_timedrdlock.c
	(pthread_rwlock_timedrdlock): Adapt.
	* nptl/pthread_rwlock_timedwrlock.c
	(pthread_rwlock_timedwrlock): Adapt.
	* nptl/pthread_rwlock_trywrlock.c (pthread_rwlock_trywrlock): Adapt.
	* nptl/pthread_rwlock_tryrdlock.c (pthread_rwlock_tryrdlock): Adapt.
	* nptl/pthread_rwlock_unlock.c (pthread_rwlock_unlock): Adapt.
	* nptl/pthread_rwlock_wrlock.c (__pthread_rwlock_wrlock_slow): Remove.
	(__pthread_rwlock_wrlock): Adapt.
	* nptl/tst-rwlock10.c: Adapt.
	* nptl/tst-rwlock11.c: Adapt.
	* nptl/tst-rwlock17.c: New file.
	* nptl/tst-rwlock18.c: New file.
	* nptl/tst-rwlock19.c: New file.
	* nptl/tst-rwlock2b.c: New file.
	* nptl/tst-rwlock8.c: Adapt.
	* nptl/tst-rwlock9.c: Adapt.
	* sysdeps/aarch64/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/arm/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/hppa/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/ia64/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/m68k/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/microblaze/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/mips/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/nios2/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/s390/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/sh/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/sparc/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/tile/nptl/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* sysdeps/unix/sysv/linux/alpha/bits/pthreadtypes.h
	(pthread_rwlock_t): Adapt.
	* sysdeps/unix/sysv/linux/powerpc/bits/pthreadtypes.h
	(pthread_rwlock_t): Adapt.
	* sysdeps/x86/bits/pthreadtypes.h (pthread_rwlock_t): Adapt.
	* nptl/nptl-printers.py (): Adapt.
	* nptl/nptl_lock_constants.pysym: Adapt.
	* nptl/test-rwlock-printers.py: Adapt.
	* nptl/test-rwlockattr-printers.c: Adapt.
	* nptl/test-rwlockattr-printers.py: Adapt.

1 files changed, 14 insertions, 14 deletions

diff --git a/sysdeps/x86/bits/pthreadtypes.h b/sysdeps/x86/bits/pthreadtypes.h
index bc7f68bfdf..c3055cac7f 100644
--- a/sysdeps/x86/bits/pthreadtypes.h
+++ b/sysdeps/x86/bits/pthreadtypes.h
@@ -189,13 +189,13 @@ typedef union
 # ifdef __x86_64__
   struct
   {
-    int __lock;
-    unsigned int __nr_readers;
-    unsigned int __readers_wakeup;
-    unsigned int __writer_wakeup;
-    unsigned int __nr_readers_queued;
-    unsigned int __nr_writers_queued;
-    int __writer;
+    unsigned int __readers;
+    unsigned int __writers;
+    unsigned int __wrphase_futex;
+    unsigned int __writers_futex;
+    unsigned int __pad3;
+    unsigned int __pad4;
+    int __cur_writer;
     int __shared;
     signed char __rwelision;
 #  ifdef  __ILP32__
@@ -214,12 +214,12 @@ typedef union
 # else
   struct
   {
-    int __lock;
-    unsigned int __nr_readers;
-    unsigned int __readers_wakeup;
-    unsigned int __writer_wakeup;
-    unsigned int __nr_readers_queued;
-    unsigned int __nr_writers_queued;
+    unsigned int __readers;
+    unsigned int __writers;
+    unsigned int __wrphase_futex;
+    unsigned int __writers_futex;
+    unsigned int __pad3;
+    unsigned int __pad4;
     /* FLAGS must stay at this position in the structure to maintain
        binary compatibility.  */
     unsigned char __flags;
@@ -227,7 +227,7 @@ typedef union
     signed char __rwelision;
 # define __PTHREAD_RWLOCK_ELISION_EXTRA 0
     unsigned char __pad2;
-    int __writer;
+    int __cur_writer;
   } __data;
 # endif
   char __size[__SIZEOF_PTHREAD_RWLOCK_T];