powerpc: Optimize lock elision for pthread_mutex_t

With TLE enabled, the adapt count variable update incurs
an 8% overhead before entering the critical section of an
elided mutex.

Instead, if it is done right after leaving the critical
section, this serialization can be avoided.

This alters the existing behavior of __lll_trylock_elision
as it will only decrement the adapt_count if it successfully
acquires the lock.

	* sysdeps/unix/sysv/linux/powerpc/elision-lock.c
	(__lll_lock_elision): Remove adapt_count decrement...
	* sysdeps/unix/sysv/linux/powerpc/elision-trylock.c
	(__lll_trylock_elision): Likewise.
	* sysdeps/unix/sysv/linux/powerpc/elision-unlock.c
	(__lll_unlock_elision): ... to here. And utilize
	new adapt_count parameter.
	* sysdeps/unix/sysv/linux/powerpc/lowlevellock.h
	(__lll_unlock_elision): Update to include adapt_count
	parameter.
	(lll_unlock_elision): Pass pointer to adapt_count
	variable.

4 files changed, 12 insertions, 6 deletions

diff --git a/sysdeps/unix/sysv/linux/powerpc/elision-lock.c b/sysdeps/unix/sysv/linux/powerpc/elision-lock.c
index 26d272e..3762732 100644
--- a/sysdeps/unix/sysv/linux/powerpc/elision-lock.c
+++ b/sysdeps/unix/sysv/linux/powerpc/elision-lock.c
@@ -47,7 +47,6 @@ __lll_lock_elision (int *lock, short *adapt_count, EXTRAARG int pshared)
 {
   if (*adapt_count > 0)
     {
-      (*adapt_count)--;
       goto use_lock;
     }
 
diff --git a/sysdeps/unix/sysv/linux/powerpc/elision-trylock.c b/sysdeps/unix/sysv/linux/powerpc/elision-trylock.c
index 7b6d1b9..440939c 100644
--- a/sysdeps/unix/sysv/linux/powerpc/elision-trylock.c
+++ b/sysdeps/unix/sysv/linux/powerpc/elision-trylock.c
@@ -36,7 +36,6 @@ __lll_trylock_elision (int *futex, short *adapt_count)
   /* Only try a transaction if it's worth it.  */
   if (*adapt_count > 0)
     {
-      (*adapt_count)--;
       goto use_lock;
     }
 
diff --git a/sysdeps/unix/sysv/linux/powerpc/elision-unlock.c b/sysdeps/unix/sysv/linux/powerpc/elision-unlock.c
index f04c339..72b893d 100644
--- a/sysdeps/unix/sysv/linux/powerpc/elision-unlock.c
+++ b/sysdeps/unix/sysv/linux/powerpc/elision-unlock.c
@@ -21,12 +21,20 @@
 #include "htm.h"
 
 int
-__lll_unlock_elision(int *lock, int pshared)
+__lll_unlock_elision (int *lock, short *adapt_count, int pshared)
 {
   /* When the lock was free we're in a transaction.  */
   if (*lock == 0)
     __builtin_tend (0);
   else
-    lll_unlock ((*lock), pshared);
+    {
+      lll_unlock ((*lock), pshared);
+
+      /* Update the adapt count AFTER completing the critical section.
+         Doing this here prevents unneeded stalling when entering
+         a critical section.  Saving about 8% runtime on P8.  */
+      if (*adapt_count > 0)
+	(*adapt_count)--;
+    }
   return 0;
 }
diff --git a/sysdeps/unix/sysv/linux/powerpc/lowlevellock.h b/sysdeps/unix/sysv/linux/powerpc/lowlevellock.h
index 16479e7..6769c25 100644
--- a/sysdeps/unix/sysv/linux/powerpc/lowlevellock.h
+++ b/sysdeps/unix/sysv/linux/powerpc/lowlevellock.h
@@ -32,7 +32,7 @@ extern int __lll_timedlock_elision
 extern int __lll_lock_elision (int *futex, short *adapt_count, int private)
   attribute_hidden;
 
-extern int __lll_unlock_elision(int *lock, int private)
+extern int __lll_unlock_elision (int *lock, short *adapt_count, int private)
   attribute_hidden;
 
 extern int __lll_trylock_elision(int *lock, short *adapt_count)
@@ -41,7 +41,7 @@ extern int __lll_trylock_elision(int *lock, short *adapt_count)
 #define lll_lock_elision(futex, adapt_count, private) \
   __lll_lock_elision (&(futex), &(adapt_count), private)
 #define lll_unlock_elision(futex, adapt_count, private) \
-  __lll_unlock_elision (&(futex), private)
+  __lll_unlock_elision (&(futex), &(adapt_count), private)
 #define lll_trylock_elision(futex, adapt_count) \
   __lll_trylock_elision (&(futex), &(adapt_count))