nptl: Cleanup cancellation macros

This patch wraps all uses of *_{enable,disable}_asynccancel and
and *_CANCEL_{ASYNC,RESET} in either already provided macros
(lll_futex_timed_wait_cancel) or creates new ones if the
functionality is not provided (SYSCALL_CANCEL_NCS, lll_futex_wait_cancel,
and lll_futex_timed_wait_cancel).

Also for some generic implementations, the direct call of the macros
are removed since the underlying symbols are suppose to provide
cancellation support.

This is a priliminary patch intended to simplify the work required
for BZ#12683 fix.  It is a refactor change, no semantic changes are
expected.

Checked on x86_64-linux-gnu and i686-linux-gnu.

	* nptl/pthread_join_common.c (__pthread_timedjoin_ex): Use
	lll_wait_tid with timeout.
	* nptl/sem_wait.c (__old_sem_wait): Use lll_futex_wait_cancel.
	* sysdeps/nptl/aio_misc.h (AIO_MISC_WAIT): Use
	futex_reltimed_wait_cancelable for cancelabla mode.
	* sysdeps/nptl/gai_misc.h (GAI_MISC_WAIT): Likewise.
	* sysdeps/posix/open64.c (__libc_open64): Do not call cancelation
	macros.
	* sysdeps/posix/sigwait.c (__sigwait): Likewise.
	* sysdeps/posix/waitid.c (__sigwait): Likewise.
	* sysdeps/unix/sysdep.h (__SYSCALL_CANCEL_CALL,
	SYSCALL_CANCEL_NCS): New macro.
	* sysdeps/nptl/lowlevellock.h (lll_wait_tid): Add timeout argument.
	(lll_timedwait_tid): Remove macro.
	* sysdeps/unix/sysv/linux/i386/lowlevellock.h (lll_wait_tid):
	Likewise.
	(lll_timedwait_tid): Likewise.
	* sysdeps/unix/sysv/linux/sparc/lowlevellock.h (lll_wait_tid):
	Likewise.
	(lll_timedwait_tid): Likewise.
	* sysdeps/unix/sysv/linux/x86_64/lowlevellock.h (lll_wait_tid):
	Likewise.
	(lll_timedwait_tid): Likewise.
	* sysdeps/unix/sysv/linux/clock_nanosleep.c (__clock_nanosleep):
	Use INTERNAL_SYSCALL_CANCEL.
	* sysdeps/unix/sysv/linux/futex-internal.h
	(futex_reltimed_wait_cancelable): Use LIBC_CANCEL_{ASYNC,RESET}
	instead of __pthread_{enable,disable}_asynccancel.
	* sysdeps/unix/sysv/linux/lowlevellock-futex.h
	(lll_futex_wait_cancel): New macro.

sysdeps/unix/sysv/linux/sparc/lowlevellock.h

@@ -108,28 +108,29 @@ __lll_timedlock (int *futex, const struct timespec *abstime, int private)
 #define LLL_LOCK_INITIALIZER		(0)
 #define LLL_LOCK_INITIALIZER_LOCKED	(1)
 
-/* The kernel notifies a process which uses CLONE_CHILD_CLEARTID via futex
-   wakeup when the clone terminates.  The memory location contains the
-   thread ID while the clone is running and is reset to zero
-   afterwards.	*/
-#define lll_wait_tid(tid) \
-  do							\
-    {							\
-      __typeof (tid) __tid;				\
-      while ((__tid = (tid)) != 0)			\
-	lll_futex_wait (&(tid), __tid, LLL_SHARED);	\
-    }							\
-  while (0)
-
 extern int __lll_timedwait_tid (int *, const struct timespec *)
      attribute_hidden;
 
-#define lll_timedwait_tid(tid, abstime) \
-  ({							\
-    int __res = 0;					\
-    if ((tid) != 0)					\
-      __res = __lll_timedwait_tid (&(tid), (abstime));	\
-    __res;						\
+/* The kernel notifies a process which uses CLONE_CHILD_CLEARTID via futex
+   wake-up when the clone terminates.  The memory location contains the
+   thread ID while the clone is running and is reset to zero by the kernel
+   afterwards.  The kernel up to version 3.16.3 does not use the private futex
+   operations for futex wake-up when the clone terminates.
+   If ABSTIME is not NULL, is used a timeout for futex call.  If the timeout
+   occurs then return ETIMEOUT, if ABSTIME is invalid, return EINVAL.
+   The futex operation are issues with cancellable versions.  */
+#define lll_wait_tid(tid, abstime)					\
+  ({									\
+    int __res = 0;							\
+    __typeof (tid) __tid;						\
+    if (abstime != NULL)						\
+      __res = __lll_timedwait_tid (&(tid), (abstime));			\
+    else								\
+      /* We need acquire MO here so that we synchronize with the 	\
+	 kernel's store to 0 when the clone terminates. (see above)  */	\
+      while ((__tid = atomic_load_acquire (&(tid))) != 0)		\
+        lll_futex_wait_cancel (&(tid), __tid, LLL_SHARED);		\
+    __res;								\
   })
 
 #endif	/* lowlevellock.h */