[PATCH v3] Add single-threaded fast path to rand()

[Wilco Dijkstra]

ping
 
Improve performance of rand() and __random() by adding a single-threaded fast
path.  Bench-random-lock shows about 5x speedup on Neoverse V1.

---

diff --git a/stdlib/random.c b/stdlib/random.c
index 62f22fac8d58c7977f09c134bf80a797750da645..174603a8915fd8aa4b3ae64d023003c9e2c038f2 100644
--- a/stdlib/random.c
+++ b/stdlib/random.c
@@ -51,6 +51,7 @@
    SUCH DAMAGE.*/
 
 #include <libc-lock.h>
+#include <sys/single_threaded.h>
 #include <limits.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -288,6 +289,12 @@ __random (void)
 {
   int32_t retval;
 
+  if (SINGLE_THREAD_P)
+    {
+      (void) __random_r (&unsafe_state, &retval);
+      return retval;
+    }
+
   __libc_lock_lock (lock);
 
   (void) __random_r (&unsafe_state, &retval);