1 files changed, 53 insertions, 1 deletions
diff --git a/nptl/pthread_spin_trylock.c b/nptl/pthread_spin_trylock.c
index 593bba3ed8..83921b06b8 100644
--- a/nptl/pthread_spin_trylock.c
+++ b/nptl/pthread_spin_trylock.c
@@ -23,5 +23,57 @@
 int
 pthread_spin_trylock (pthread_spinlock_t *lock)
 {
-  return atomic_exchange_acq (lock, 1) ? EBUSY : 0;
+  /* For the spin try lock, we have the following possibilities:
+
+     1) If we assume that trylock will most likely succeed in practice:
+     * We just do an exchange.
+
+     2) If we want to bias towards cases where trylock succeeds, but don't
+     rule out contention:
+     * If exchange is not implemented by a CAS loop, and exchange is faster
+     than CAS, do an exchange.
+     * If exchange is implemented by a CAS loop, use a weak CAS and not an
+     exchange so we bail out after the first failed attempt to change the state.
+
+     3) If we expect contention to be likely:
+     * If CAS always brings the cache line into an exclusive state even if the
+     spinlock is already acquired, then load the value first with
+     atomic_load_relaxed and test if lock is not acquired. Then do 2).
+
+     We assume that 2) is the common case, and that this won't be slower than
+     1) in the common case.
+
+     We use acquire MO to synchronize-with the release MO store in
+     pthread_spin_unlock, and thus ensure that prior critical sections
+     happen-before this critical section.  */
+#if ! ATOMIC_EXCHANGE_USES_CAS
+  /* Try to acquire the lock with an exchange instruction as this architecture
+     has such an instruction and we assume it is faster than a CAS.
+     The acquisition succeeds if the lock is not in an acquired state.  */
+  if (atomic_exchange_acquire (lock, 1) == 0)
+    return 0;
+#else
+  /* Try to acquire the lock with a CAS instruction as this architecture
+     has no exchange instruction.  The acquisition succeeds if the lock is not
+     acquired.  */
+  do
+    {
+      int val = 0;
+      if (atomic_compare_exchange_weak_acquire (lock, &val, 1))
+	return 0;
+    }
+  /* atomic_compare_exchange_weak_acquire can fail spuriously.  Whereas
+     C++11 and C11 make it clear that trylock operations can fail spuriously,
+     POSIX does not explicitly specify this; it only specifies that failing
+     synchronization operations do not need to have synchronization effects
+     themselves, but a spurious failure is something that could contradict a
+     happens-before established earlier (e.g., that we need to observe that
+     the lock is acquired).  Therefore, we emulate a strong CAS by simply
+     checking with a relaxed MO load that the lock is really acquired before
+     returning EBUSY; the additional overhead this may cause is on the slow
+     path.  */
+  while (atomic_load_relaxed (lock) == 0);
+#endif
+
+  return EBUSY;
 }