New condvar implementation that provides stronger ordering guarantees.

This is a new implementation for condition variables, required
after http://austingroupbugs.net/view.php?id=609 to fix bug 13165.  In
essence, we need to be stricter in which waiters a signal or broadcast
is required to wake up; this couldn't be solved using the old algorithm.
ISO C++ made a similar clarification, so this also fixes a bug in
current libstdc++, for example.

We can't use the old algorithm anymore because futexes do not guarantee
to wake in FIFO order.  Thus, when we wake, we can't simply let any
waiter grab a signal, but we need to ensure that one of the waiters
happening before the signal is woken up.  This is something the previous
algorithm violated (see bug 13165).

There's another issue specific to condvars: ABA issues on the underlying
futexes.  Unlike mutexes that have just three states, or semaphores that
have no tokens or a limited number of them, the state of a condvar is
the *order* of the waiters.  A waiter on a semaphore can grab a token
whenever one is available; a condvar waiter must only consume a signal
if it is eligible to do so as determined by the relative order of the
waiter and the signal.
Therefore, this new algorithm maintains two groups of waiters: Those
eligible to consume signals (G1), and those that have to wait until
previous waiters have consumed signals (G2).  Once G1 is empty, G2
becomes the new G1.  64b counters are used to avoid ABA issues.

This condvar doesn't yet use a requeue optimization (ie, on a broadcast,
waking just one thread and requeueing all others on the futex of the
mutex supplied by the program).  I don't think doing the requeue is
necessarily the right approach (but I haven't done real measurements
yet):
* If a program expects to wake many threads at the same time and make
that scalable, a condvar isn't great anyway because of how it requires
waiters to operate mutually exclusive (due to the mutex usage).  Thus, a
thundering herd problem is a scalability problem with or without the
optimization.  Using something like a semaphore might be more
appropriate in such a case.
* The scalability problem is actually at the mutex side; the condvar
could help (and it tries to with the requeue optimization), but it
should be the mutex who decides how that is done, and whether it is done
at all.
* Forcing all but one waiter into the kernel-side wait queue of the
mutex prevents/avoids the use of lock elision on the mutex.  Thus, it
prevents the only cure against the underlying scalability problem
inherent to condvars.
* If condvars use short critical sections (ie, hold the mutex just to
check a binary flag or such), which they should do ideally, then forcing
all those waiter to proceed serially with kernel-based hand-off (ie,
futex ops in the mutex' contended state, via the futex wait queues) will
be less efficient than just letting a scalable mutex implementation take
care of it.  Our current mutex impl doesn't employ spinning at all, but
if critical sections are short, spinning can be much better.
* Doing the requeue stuff requires all waiters to always drive the mutex
into the contended state.  This leads to each waiter having to call
futex_wake after lock release, even if this wouldn't be necessary.

	[BZ #13165]
	* nptl/pthread_cond_broadcast.c (__pthread_cond_broadcast): Rewrite to
	use new algorithm.
	* nptl/pthread_cond_destroy.c (__pthread_cond_destroy): Likewise.
	* nptl/pthread_cond_init.c (__pthread_cond_init): Likewise.
	* nptl/pthread_cond_signal.c (__pthread_cond_signal): Likewise.
	* nptl/pthread_cond_wait.c (__pthread_cond_wait): Likewise.
	(__pthread_cond_timedwait): Move here from pthread_cond_timedwait.c.
	(__condvar_confirm_wakeup, __condvar_cancel_waiting,
	__condvar_cleanup_waiting, __condvar_dec_grefs,
	__pthread_cond_wait_common): New.
	(__condvar_cleanup): Remove.
	* npt/pthread_condattr_getclock.c (pthread_condattr_getclock): Adapt.
	* npt/pthread_condattr_setclock.c (pthread_condattr_setclock):
	Likewise.
	* npt/pthread_condattr_getpshared.c (pthread_condattr_getpshared):
	Likewise.
	* npt/pthread_condattr_init.c (pthread_condattr_init): Likewise.
	* nptl/tst-cond1.c: Add comment.
	* nptl/tst-cond20.c (do_test): Adapt.
	* nptl/tst-cond22.c (do_test): Likewise.
	* sysdeps/aarch64/nptl/bits/pthreadtypes.h (pthread_cond_t): Adapt
	structure.
	* sysdeps/arm/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/ia64/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/m68k/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/microblaze/nptl/bits/pthreadtypes.h (pthread_cond_t):
	Likewise.
	* sysdeps/mips/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/nios2/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/s390/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/sh/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/tile/nptl/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/unix/sysv/linux/alpha/bits/pthreadtypes.h (pthread_cond_t):
	Likewise.
	* sysdeps/unix/sysv/linux/powerpc/bits/pthreadtypes.h (pthread_cond_t):
	Likewise.
	* sysdeps/x86/bits/pthreadtypes.h (pthread_cond_t): Likewise.
	* sysdeps/nptl/internaltypes.h (COND_NWAITERS_SHIFT): Remove.
	(COND_CLOCK_BITS): Adapt.
	* sysdeps/nptl/pthread.h (PTHREAD_COND_INITIALIZER): Adapt.
	* nptl/pthreadP.h (__PTHREAD_COND_CLOCK_MONOTONIC_MASK,
	__PTHREAD_COND_SHARED_MASK): New.
	* nptl/nptl-printers.py (CLOCK_IDS): Remove.
	(ConditionVariablePrinter, ConditionVariableAttributesPrinter): Adapt.
	* nptl/nptl_lock_constants.pysym: Adapt.
	* nptl/test-cond-printers.py: Adapt.
	* sysdeps/unix/sysv/linux/hppa/internaltypes.h (cond_compat_clear,
	cond_compat_check_and_clear): Adapt.
	* sysdeps/unix/sysv/linux/hppa/pthread_cond_timedwait.c: Remove file ...
	* sysdeps/unix/sysv/linux/hppa/pthread_cond_wait.c
	(__pthread_cond_timedwait): ... and move here.
	* nptl/DESIGN-condvar.txt: Remove file.
	* nptl/lowlevelcond.sym: Likewise.
	* nptl/pthread_cond_timedwait.c: Likewise.
	* sysdeps/unix/sysv/linux/i386/i486/pthread_cond_broadcast.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i486/pthread_cond_signal.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i486/pthread_cond_timedwait.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i486/pthread_cond_wait.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i586/pthread_cond_broadcast.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i586/pthread_cond_signal.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i586/pthread_cond_timedwait.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i586/pthread_cond_wait.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i686/pthread_cond_broadcast.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i686/pthread_cond_signal.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i686/pthread_cond_timedwait.S: Likewise.
	* sysdeps/unix/sysv/linux/i386/i686/pthread_cond_wait.S: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/pthread_cond_broadcast.S: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/pthread_cond_signal.S: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S: Likewise.
	* sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S: Likewise.

1 files changed, 29 insertions, 53 deletions

diff --git a/nptl/pthread_cond_destroy.c b/nptl/pthread_cond_destroy.c
index 1acd8042d8..5845c6a7ad 100644
--- a/nptl/pthread_cond_destroy.c
+++ b/nptl/pthread_cond_destroy.c
@@ -20,66 +20,42 @@
 #include <shlib-compat.h>
 #include "pthreadP.h"
 #include <stap-probe.h>
-
-
+#include <atomic.h>
+#include <futex-internal.h>
+
+#include "pthread_cond_common.c"
+
+/* See __pthread_cond_wait for a high-level description of the algorithm.
+
+   A correct program must make sure that no waiters are blocked on the condvar
+   when it is destroyed, and that there are no concurrent signals or
+   broadcasts.  To wake waiters reliably, the program must signal or
+   broadcast while holding the mutex or after having held the mutex.  It must
+   also ensure that no signal or broadcast are still pending to unblock
+   waiters; IOW, because waiters can wake up spuriously, the program must
+   effectively ensure that destruction happens after the execution of those
+   signal or broadcast calls.
+   Thus, we can assume that all waiters that are still accessing the condvar
+   have been woken.  We wait until they have confirmed to have woken up by
+   decrementing __wrefs.  */
 int
 __pthread_cond_destroy (pthread_cond_t *cond)
 {
-  int pshared = (cond->__data.__mutex == (void *) ~0l)
-		? LLL_SHARED : LLL_PRIVATE;
-
   LIBC_PROBE (cond_destroy, 1, cond);
 
-  /* Make sure we are alone.  */
-  lll_lock (cond->__data.__lock, pshared);
-
-  if (cond->__data.__total_seq > cond->__data.__wakeup_seq)
-    {
-      /* If there are still some waiters which have not been
-	 woken up, this is an application bug.  */
-      lll_unlock (cond->__data.__lock, pshared);
-      return EBUSY;
-    }
-
-  /* Tell pthread_cond_*wait that this condvar is being destroyed.  */
-  cond->__data.__total_seq = -1ULL;
-
-  /* If there are waiters which have been already signalled or
-     broadcasted, but still are using the pthread_cond_t structure,
-     pthread_cond_destroy needs to wait for them.  */
-  unsigned int nwaiters = cond->__data.__nwaiters;
-
-  if (nwaiters >= (1 << COND_NWAITERS_SHIFT))
+  /* Set the wake request flag.  We could also spin, but destruction that is
+     concurrent with still-active waiters is probably neither common nor
+     performance critical.  Acquire MO to synchronize with waiters confirming
+     that they finished.  */
+  unsigned int wrefs = atomic_fetch_or_acquire (&cond->__data.__wrefs, 4);
+  int private = __condvar_get_private (wrefs);
+  while (wrefs >> 3 != 0)
     {
-      /* Wake everybody on the associated mutex in case there are
-	 threads that have been requeued to it.
-	 Without this, pthread_cond_destroy could block potentially
-	 for a long time or forever, as it would depend on other
-	 thread's using the mutex.
-	 When all threads waiting on the mutex are woken up, pthread_cond_wait
-	 only waits for threads to acquire and release the internal
-	 condvar lock.  */
-      if (cond->__data.__mutex != NULL
-	  && cond->__data.__mutex != (void *) ~0l)
-	{
-	  pthread_mutex_t *mut = (pthread_mutex_t *) cond->__data.__mutex;
-	  lll_futex_wake (&mut->__data.__lock, INT_MAX,
-			  PTHREAD_MUTEX_PSHARED (mut));
-	}
-
-      do
-	{
-	  lll_unlock (cond->__data.__lock, pshared);
-
-	  lll_futex_wait (&cond->__data.__nwaiters, nwaiters, pshared);
-
-	  lll_lock (cond->__data.__lock, pshared);
-
-	  nwaiters = cond->__data.__nwaiters;
-	}
-      while (nwaiters >= (1 << COND_NWAITERS_SHIFT));
+      futex_wait_simple (&cond->__data.__wrefs, wrefs, private);
+      /* See above.  */
+      wrefs = atomic_load_acquire (&cond->__data.__wrefs);
     }
-
+  /* The memory the condvar occupies can now be reused.  */
   return 0;
 }
 versioned_symbol (libpthread, __pthread_cond_destroy,