diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 5b7e736f3b4924beb5e779a92b3c93a7f2a606f2..028a2b95936c1fa48ca316921c65b1023b9e1585 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -249,3 +249,32 @@ time_init (void)
 	 */
 	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
 }
+
+#define SMALLUSECS 100
+
+void
+udelay (unsigned long usecs)
+{
+	unsigned long start;
+	unsigned long cycles;
+	unsigned long smallusecs;
+
+	/*
+	 * Execute the non-preemptible delay loop (because the ITC might
+	 * not be synchronized between CPUS) in relatively short time
+	 * chunks, allowing preemption between the chunks.
+	 */
+	while (usecs > 0) {
+		smallusecs = (usecs > SMALLUSECS) ? SMALLUSECS : usecs;
+		preempt_disable();
+		cycles = smallusecs*local_cpu_data->cyc_per_usec;
+		start = ia64_get_itc();
+
+		while (ia64_get_itc() - start < cycles)
+			cpu_relax();
+
+		preempt_enable();
+		usecs -= smallusecs;
+	}
+}
+EXPORT_SYMBOL(udelay);
diff --git a/include/asm-ia64/delay.h b/include/asm-ia64/delay.h
index 57182d6f2b9a10c3f3f9f288d1e6f4613a9121bd..bba70207639103caaa05d0a0815b90d6eb4d3fa2 100644
--- a/include/asm-ia64/delay.h
+++ b/include/asm-ia64/delay.h
@@ -84,14 +84,6 @@ __delay (unsigned long loops)
 	ia64_delay_loop (loops - 1);
 }
 
-static __inline__ void
-udelay (unsigned long usecs)
-{
-	unsigned long start = ia64_get_itc();
-	unsigned long cycles = usecs*local_cpu_data->cyc_per_usec;
-
-	while (ia64_get_itc() - start < cycles)
-		cpu_relax();
-}
+extern void udelay (unsigned long usecs);
 
 #endif /* _ASM_IA64_DELAY_H */