diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index bc683b8219b5bf3715345742b0d41d4746e4746b..c5767b5a4318090d68d6047420acc8b11df18c3b 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
+#include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/signal.h>
@@ -432,7 +433,10 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 
 static void vfp_enable(void *unused)
 {
-	u32 access = get_copro_access();
+	u32 access;
+
+	BUG_ON(preemptible());
+	access = get_copro_access();
 
 	/*
 	 * Enable full access to VFP (cp10 and cp11)
@@ -657,7 +661,7 @@ static int __init vfp_init(void)
 	unsigned int cpu_arch = cpu_architecture();
 
 	if (cpu_arch >= CPU_ARCH_ARMv6)
-		vfp_enable(NULL);
+		on_each_cpu(vfp_enable, NULL, 1);
 
 	/*
 	 * First check that there is a VFP that we can use.
@@ -678,8 +682,6 @@ static int __init vfp_init(void)
 	} else {
 		hotcpu_notifier(vfp_hotplug, 0);
 
-		smp_call_function(vfp_enable, NULL, 1);
-
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;  /* Extract the architecture version */
 		printk("implementor %02x architecture %d part %02x variant %x rev %x\n",
 			(vfpsid & FPSID_IMPLEMENTER_MASK) >> FPSID_IMPLEMENTER_BIT,