[PATCH] Improve performance of libc locks

[Wilco Dijkstra <Wilco.Dijkstra@arm.com>]

Improve performance of libc locks by adding a fast path for the
single-threaded case.

On Neoverse V1, a loop using rand() improved 3.6 times. Multithreaded
performance is unchanged.

Passes regress on AArch64, OK for commit?

---

diff --git a/sysdeps/nptl/libc-lockP.h b/sysdeps/nptl/libc-lockP.h
index d3a6837fd212f3f5dfd80f46d0e9ce365042ae0c..ccdb11fee6f14069d0b936be93d0f0fa6d8bc30b 100644
--- a/sysdeps/nptl/libc-lockP.h
+++ b/sysdeps/nptl/libc-lockP.h
@@ -108,7 +108,14 @@ _Static_assert (LLL_LOCK_INITIALIZER == 0, "LLL_LOCK_INITIALIZER != 0");
 #define __libc_rwlock_fini(NAME) ((void) 0)
 
 /* Lock the named lock variable.  */
-#define __libc_lock_lock(NAME) ({ lll_lock (NAME, LLL_PRIVATE); 0; })
+#define __libc_lock_lock(NAME)						\
+ ({									\
+    if (SINGLE_THREAD_P)						\
+      (NAME) = LLL_LOCK_INITIALIZER_LOCKED;				\
+    else								\
+      lll_lock (NAME, LLL_PRIVATE);					\
+    0;									\
+  })
 #define __libc_rwlock_rdlock(NAME) __pthread_rwlock_rdlock (&(NAME))
 #define __libc_rwlock_wrlock(NAME) __pthread_rwlock_wrlock (&(NAME))
 
@@ -116,7 +123,14 @@ _Static_assert (LLL_LOCK_INITIALIZER == 0, "LLL_LOCK_INITIALIZER != 0");
 #define __libc_lock_trylock(NAME) lll_trylock (NAME)
 
 /* Unlock the named lock variable.  */
-#define __libc_lock_unlock(NAME) lll_unlock (NAME, LLL_PRIVATE)
+#define __libc_lock_unlock(NAME)					\
+ ({									\
+    if (SINGLE_THREAD_P)						\
+      (NAME) = LLL_LOCK_INITIALIZER;					\
+    else								\
+      lll_unlock (NAME, LLL_PRIVATE);					\
+    0;									\
+ })
 #define __libc_rwlock_unlock(NAME) __pthread_rwlock_unlock (&(NAME))
 
 #if IS_IN (rtld)