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, 5 insertions, 153 deletions

diff --git a/nptl/pthread_rwlock_rdlock.c b/nptl/pthread_rwlock_rdlock.c
index 8adefc32c0..e07581bbf5 100644
--- a/nptl/pthread_rwlock_rdlock.c
+++ b/nptl/pthread_rwlock_rdlock.c
@@ -16,165 +16,17 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#include <errno.h>
-#include <sysdep.h>
-#include <lowlevellock.h>
-#include <futex-internal.h>
-#include <pthread.h>
-#include <pthreadP.h>
-#include <stap-probe.h>
-#include <elide.h>
-#include <stdbool.h>
-
-
-/* Acquire read lock for RWLOCK.  Slow path.  */
-static int __attribute__((noinline))
-__pthread_rwlock_rdlock_slow (pthread_rwlock_t *rwlock)
-{
-  int result = 0;
-  bool wake = false;
-  int futex_shared =
-      rwlock->__data.__shared == LLL_PRIVATE ? FUTEX_PRIVATE : FUTEX_SHARED;
-
-  /* Lock is taken in caller.  */
-
-  while (1)
-    {
-      /* Make sure we are not holding the rwlock as a writer.  This is
-	 a deadlock situation we recognize and report.  */
-      if (__builtin_expect (rwlock->__data.__writer
-			    == THREAD_GETMEM (THREAD_SELF, tid), 0))
-	{
-	  result = EDEADLK;
-	  break;
-	}
-
-      /* Remember that we are a reader.  */
-      if (__glibc_unlikely (++rwlock->__data.__nr_readers_queued == 0))
-	{
-	  /* Overflow on number of queued readers.  */
-	  --rwlock->__data.__nr_readers_queued;
-	  result = EAGAIN;
-	  break;
-	}
-
-      int waitval = rwlock->__data.__readers_wakeup;
-
-      /* Free the lock.  */
-      lll_unlock (rwlock->__data.__lock, rwlock->__data.__shared);
-
-      /* Wait for the writer to finish.  We do not check the return value
-	 because we decide how to continue based on the state of the rwlock.  */
-      futex_wait_simple (&rwlock->__data.__readers_wakeup, waitval,
-			 futex_shared);
-
-      /* Get the lock.  */
-      lll_lock (rwlock->__data.__lock, rwlock->__data.__shared);
-
-      --rwlock->__data.__nr_readers_queued;
-
-      /* Get the rwlock if there is no writer...  */
-      if (rwlock->__data.__writer == 0
-	  /* ...and if either no writer is waiting or we prefer readers.  */
-	  && (!rwlock->__data.__nr_writers_queued
-	      || PTHREAD_RWLOCK_PREFER_READER_P (rwlock)))
-	{
-	  /* Increment the reader counter.  Avoid overflow.  */
-	  if (__glibc_unlikely (++rwlock->__data.__nr_readers == 0))
-	    {
-	      /* Overflow on number of readers.	 */
-	      --rwlock->__data.__nr_readers;
-	      result = EAGAIN;
-	    }
-	  else
-	    {
-	      LIBC_PROBE (rdlock_acquire_read, 1, rwlock);
-	      /* See pthread_rwlock_rdlock.  */
-	      if (rwlock->__data.__nr_readers == 1
-		  && rwlock->__data.__nr_readers_queued > 0
-		  && rwlock->__data.__nr_writers_queued > 0)
-		{
-		  ++rwlock->__data.__readers_wakeup;
-		  wake = true;
-		}
-	    }
-
-	  break;
-	}
-    }
-
-  /* We are done, free the lock.  */
-  lll_unlock (rwlock->__data.__lock, rwlock->__data.__shared);
-
-  if (wake)
-    futex_wake (&rwlock->__data.__readers_wakeup, INT_MAX, futex_shared);
-
-  return result;
-}
-
-
-/* Fast path of acquiring read lock on RWLOCK.  */
+#include "pthread_rwlock_common.c"
 
+/* See pthread_rwlock_common.c.  */
 int
 __pthread_rwlock_rdlock (pthread_rwlock_t *rwlock)
 {
-  int result = 0;
-  bool wake = false;
-  int futex_shared =
-      rwlock->__data.__shared == LLL_PRIVATE ? FUTEX_PRIVATE : FUTEX_SHARED;
-
   LIBC_PROBE (rdlock_entry, 1, rwlock);
 
-  if (ELIDE_LOCK (rwlock->__data.__rwelision,
-		  rwlock->__data.__lock == 0
-		  && rwlock->__data.__writer == 0
-		  && rwlock->__data.__nr_readers == 0))
-    return 0;
-
-  /* Make sure we are alone.  */
-  lll_lock (rwlock->__data.__lock, rwlock->__data.__shared);
-
-  /* Get the rwlock if there is no writer...  */
-  if (rwlock->__data.__writer == 0
-      /* ...and if either no writer is waiting or we prefer readers.  */
-      && (!rwlock->__data.__nr_writers_queued
-	  || PTHREAD_RWLOCK_PREFER_READER_P (rwlock)))
-    {
-      /* Increment the reader counter.  Avoid overflow.  */
-      if (__glibc_unlikely (++rwlock->__data.__nr_readers == 0))
-	{
-	  /* Overflow on number of readers.	 */
-	  --rwlock->__data.__nr_readers;
-	  result = EAGAIN;
-	}
-      else
-	{
-	  LIBC_PROBE (rdlock_acquire_read, 1, rwlock);
-	  /* If we are the first reader, and there are blocked readers and
-	     writers (which we don't prefer, see above), then it can be the
-	     case that we stole the lock from a writer that was already woken
-	     to acquire it.  That means that we need to take over the writer's
-	     responsibility to wake all readers (see pthread_rwlock_unlock).
-	     Thus, wake all readers in this case.  */
-	  if (rwlock->__data.__nr_readers == 1
-	      && rwlock->__data.__nr_readers_queued > 0
-	      && rwlock->__data.__nr_writers_queued > 0)
-	    {
-	      ++rwlock->__data.__readers_wakeup;
-	      wake = true;
-	    }
-	}
-
-      /* We are done, free the lock.  */
-      lll_unlock (rwlock->__data.__lock, rwlock->__data.__shared);
-
-      if (wake)
-	futex_wake (&rwlock->__data.__readers_wakeup, INT_MAX, futex_shared);
-
-      return result;
-    }
-
-  return __pthread_rwlock_rdlock_slow (rwlock);
+  int result = __pthread_rwlock_rdlock_full (rwlock, NULL);
+  LIBC_PROBE (rdlock_acquire_read, 1, rwlock);
+  return result;
 }
 
 weak_alias (__pthread_rwlock_rdlock, pthread_rwlock_rdlock)