commit a6b81f605dfba8650ea1f80122f41eb8e6c73dc7

Author: H.J. Lu <hjl.tools@gmail.com>

Date:   Tue Nov 2 18:33:07 2021 -0700

    Add LLL_MUTEX_READ_LOCK [BZ #28537]

    CAS instruction is expensive.  From the x86 CPU's point of view, getting

    a cache line for writing is more expensive than reading.  See Appendix

    A.2 Spinlock in:

    https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/xeon-lock-scaling-analysis-paper.pdf

    The full compare and swap will grab the cache line exclusive and cause

    excessive cache line bouncing.

    Add LLL_MUTEX_READ_LOCK to do an atomic load and skip CAS in spinlock

    loop if compare may fail to reduce cache line bouncing on contended locks.

    Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>

    (cherry picked from commit d672a98a1af106bd68deb15576710cd61363f7a6)

diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c

index a04e0158451c8fff..9f40928cc6b9a067 100644

--- a/nptl/pthread_mutex_lock.c

+++ b/nptl/pthread_mutex_lock.c

@@ -65,6 +65,11 @@ lll_mutex_lock_optimized (pthread_mutex_t *mutex)

 # define PTHREAD_MUTEX_VERSIONS 1

 #endif

+#ifndef LLL_MUTEX_READ_LOCK

+# define LLL_MUTEX_READ_LOCK(mutex) \

+  atomic_load_relaxed (&(mutex)->__data.__lock)

+#endif

+

 static int __pthread_mutex_lock_full (pthread_mutex_t *mutex)

      __attribute_noinline__;

@@ -142,6 +147,8 @@ PTHREAD_MUTEX_LOCK (pthread_mutex_t *mutex)

 		  break;

 		}

 	      atomic_spin_nop ();

+	      if (LLL_MUTEX_READ_LOCK (mutex) != 0)

+		continue;

 	    }

 	  while (LLL_MUTEX_TRYLOCK (mutex) != 0);