Commit 2496afbf authored Sep 09, 2009 by Yang Xiaowei Committed by Jeremy Fitzhardinge Sep 09, 2009

xen: use stronger barrier after unlocking lock



We need to have a stronger barrier between releasing the lock and
checking for any waiting spinners.  A compiler barrier is not sufficient
because the CPU's ordering rules do not prevent the read xl->spinners
from happening before the unlock assignment, as they are different
memory locations.

We need to have an explicit barrier to enforce the write-read ordering
to different memory locations.

Because of it, I can't bring up > 4 HVM guests on one SMP machine.

[ Code and commit comments expanded -J ]

[ Impact: avoid deadlock when using Xen PV spinlocks ]

Signed-off-by: Yang Xiaowei <xiaowei.yang@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

parent 4d576b57

arch/x86/xen/spinlock.c

+7 −2

Original line number	Diff line number	Diff line
		@@ -326,8 +326,13 @@ static void xen_spin_unlock(struct raw_spinlock *lock)
		smp_wmb(); /* make sure no writes get moved after unlock */
		xl->lock = 0; /* release lock */

		/* make sure unlock happens before kick */
		barrier();
		/*
		* Make sure unlock happens before checking for waiting
		* spinners. We need a strong barrier to enforce the
		* write-read ordering to different memory locations, as the
		* CPU makes no implied guarantees about their ordering.
		*/
		mb();

		if (unlikely(xl->spinners))
		xen_spin_unlock_slow(xl);

Admin message