Optimize __libc_lock_lock and __libc_lock_trylock for MIPS.

4 files changed, 57 insertions, 4 deletions

diff --git a/nptl/ChangeLog b/nptl/ChangeLog
index 0f31b4dbe4..545b2c2152 100644
--- a/nptl/ChangeLog
+++ b/nptl/ChangeLog
@@ -1,3 +1,9 @@
+2012-08-15  Tom de Vries  <vries@codesourcery.com>
+	    Maxim Kuvyrkov  <maxim@codesourcery.com>
+
+	* sysdeps/pthread/bits/libc-lockP.h (__libc_lock_lock)
+	(__libc_lock_trylock): Allow pre-existing definitions.
+
 2012-08-15  Maxim Kuvyrkov  <maxim@codesourcery.com>
 
 	* pthread_spin_lock.c: New file.
diff --git a/nptl/sysdeps/pthread/bits/libc-lockP.h b/nptl/sysdeps/pthread/bits/libc-lockP.h
index 0ebac917d7..7adaeb4398 100644
--- a/nptl/sysdeps/pthread/bits/libc-lockP.h
+++ b/nptl/sysdeps/pthread/bits/libc-lockP.h
@@ -176,9 +176,12 @@ typedef pthread_key_t __libc_key_t;
 
 /* Lock the named lock variable.  */
 #if !defined NOT_IN_libc || defined IS_IN_libpthread
-# define __libc_lock_lock(NAME) \
+# ifndef __libc_lock_lock
+#  define __libc_lock_lock(NAME) \
   ({ lll_lock (NAME, LLL_PRIVATE); 0; })
+# endif
 #else
+# undef __libc_lock_lock
 # define __libc_lock_lock(NAME) \
   __libc_maybe_call (__pthread_mutex_lock, (&(NAME)), 0)
 #endif
@@ -189,9 +192,12 @@ typedef pthread_key_t __libc_key_t;
 
 /* Try to lock the named lock variable.  */
 #if !defined NOT_IN_libc || defined IS_IN_libpthread
-# define __libc_lock_trylock(NAME) \
+# ifndef __libc_lock_trylock
+#  define __libc_lock_trylock(NAME) \
   lll_trylock (NAME)
+# endif
 #else
+# undef __libc_lock_trylock
 # define __libc_lock_trylock(NAME) \
   __libc_maybe_call (__pthread_mutex_trylock, (&(NAME)), 0)
 #endif
diff --git a/ports/ChangeLog.mips b/ports/ChangeLog.mips
index 518777223c..f8c18b3275 100644
--- a/ports/ChangeLog.mips
+++ b/ports/ChangeLog.mips
@@ -1,3 +1,9 @@
+2012-08-15  Tom de Vries  <vries@codesourcery.com>
+	    Maxim Kuvyrkov  <maxim@codesourcery.com>
+
+	* sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h (__libc_lock_lock)
+	(__libc_lock_trylock): Define versions optimized for MIPS.
+
 2012-08-15  Maxim Kuvyrkov  <maxim@codesourcery.com>
 
 	* sysdeps/mips/nptl/pthread_spin_lock.S: Remove, use generic version.
diff --git a/ports/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h b/ports/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
index 88b601eadd..d368ae1b66 100644
--- a/ports/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
+++ b/ports/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
@@ -1,5 +1,4 @@
-/* Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008,
-   2009 Free Software Foundation, Inc.
+/* Copyright (C) 2003-2012 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -291,4 +290,40 @@ extern int __lll_timedwait_tid (int *, const struct timespec *)
     __res;						\
   })
 
+/* Implement __libc_lock_lock using exchange_and_add, which expands into
+   a single instruction on XLP processors.  We enable this for all MIPS
+   processors as atomic_exchange_and_add_acq and
+   atomic_compare_and_exchange_acq take the same time to execute.
+   This is a simplified expansion of ({ lll_lock (NAME, LLL_PRIVATE); 0; }).
+
+   Note: __lll_lock_wait_private() resets lock value to '2', which prevents
+   unbounded increase of the lock value and [with billions of threads]
+   overflow.  */
+#define __libc_lock_lock(NAME)						\
+  ({									\
+    int *__futex = &(NAME);						\
+    if (__builtin_expect (atomic_exchange_and_add_acq (__futex, 1), 0))	\
+      __lll_lock_wait_private (__futex);				\
+    0;									\
+  })
+
+#ifdef _MIPS_ARCH_XLP
+/* The generic version using a single atomic_compare_and_exchange_acq takes
+   less time for non-XLP processors, so we use below for XLP only.  */
+# define __libc_lock_trylock(NAME)					\
+  ({									\
+  int *__futex = &(NAME);						\
+  int __result = atomic_exchange_and_add_acq (__futex, 1);		\
+  /* If __result == 0, we succeeded in acquiring the lock.		\
+     If __result == 1, we switched the lock to 'contended' state, which	\
+     will cause a [possibly unnecessary] call to lll_futex_wait.  This is \
+     unlikely, so we accept the possible inefficiency.			\
+     If __result >= 2, we need to set the lock to 'contended' state to avoid \
+     unbounded increase from subsequent trylocks.  */			\
+  if (__result >= 2)							\
+    __result = atomic_exchange_acq (__futex, 2);			\
+  __result;								\
+  })
+#endif
+
 #endif	/* lowlevellock.h */