ia64: Based on patch by Jerome Marchand: Add ia64-optimized

	atomic_dec_and_lock().  Actually, this could be the generic
	version for any platform that has cmpxchg().

arch/ia64/Kconfig

@@ -375,6 +375,11 @@ config COMPAT
 	depends on IA32_SUPPORT
 	default y
 
+config HAVE_DEC_LOCK
+	bool
+	depends on (SMP || PREEMPT)
+	default y
+
 config PERFMON
 	bool "Performance monitor support"
 	help

arch/ia64/lib/Makefile

@@ -13,6 +13,7 @@ lib-$(CONFIG_ITANIUM)	+= copy_page.o copy_user.o memcpy.o
 lib-$(CONFIG_MCKINLEY)	+= copy_page_mck.o memcpy_mck.o
 lib-$(CONFIG_PERFMON)	+= carta_random.o
 lib-$(CONFIG_MD_RAID5)	+= xor.o
+lib-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
 
 AFLAGS___divdi3.o	=
 AFLAGS___udivdi3.o	= -DUNSIGNED

arch/ia64/lib/dec_and_lock.c

+/*
+ * Copyright (C) 2003 Jerome Marchand, Bull S.A.
+ *	Cleaned up by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * This file is released under the GPLv2, or at your option any later version.
+ *
+ * ia64 version of "atomic_dec_and_lock()" using the atomic "cmpxchg" instruction.  This
+ * code is an adaptation of the x86 version of "atomic_dec_and_lock()".
+ */
+
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+
+/*
+ * Decrement REFCOUNT and if the count reaches zero, acquire the spinlock.  Both of these
+ * operations have to be done atomically, so that the count doesn't drop to zero without
+ * acquiring the spinlock first.
+ */
+int
+atomic_dec_and_lock (atomic_t *refcount, spinlock_t *lock)
+{
+	int old, new;
+
+	do {
+		old = atomic_read(refcount);
+		new = old - 1;
+
+		if (unlikely (old == 1)) {
+			/* oops, we may be decrementing to zero, do it the slow way... */
+			spin_lock(lock);
+			if (atomic_dec_and_test(refcount))
+				return 1;
+			spin_unlock(lock);
+			return 0;
+		}
+	} while (cmpxchg(&refcount->counter, old, new) != old);
+	return 0;
+}
+
+EXPORT_SYMBOL(atomic_dec_and_lock);