diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 59bd93ac7fef..509ddabeae25 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -31,7 +31,6 @@ extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
 extern asmlinkage void math_state_restore(void);
 extern void __math_state_restore(void);
-extern void init_thread_xstate(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 94d5f84d89f2..4d3b5d1fc028 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -28,7 +28,6 @@ extern u64 pcntxt_mask;
 extern struct xsave_struct *init_xstate_buf;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
-extern void xsave_cntxt_init(void);
 extern void xsave_init(void);
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 40561085d4f3..94c36c7ac183 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1210,6 +1210,7 @@ void __cpuinit cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu_init();
+	xsave_init();
 
 	raw_local_save_flags(kernel_eflags);
 
@@ -1270,6 +1271,7 @@ void __cpuinit cpu_init(void)
 	clear_used_math();
 	mxcsr_feature_mask_init();
 
+	fpu_init();
 	xsave_init();
 }
 #endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 2f32ef05f10e..e73c54ebafce 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -59,18 +59,18 @@ void __cpuinit mxcsr_feature_mask_init(void)
 	stts();
 }
 
-void __cpuinit init_thread_xstate(void)
+static void __cpuinit init_thread_xstate(void)
 {
+	/*
+	 * Note that xstate_size might be overwriten later during
+	 * xsave_init().
+	 */
+
 	if (!HAVE_HWFP) {
 		xstate_size = sizeof(struct i387_soft_struct);
 		return;
 	}
 
-	if (cpu_has_xsave) {
-		xsave_cntxt_init();
-		return;
-	}
-
 	if (cpu_has_fxsr)
 		xstate_size = sizeof(struct i387_fxsave_struct);
 #ifdef CONFIG_X86_32
@@ -84,6 +84,7 @@ void __cpuinit init_thread_xstate(void)
  * Called at bootup to set up the initial FPU state that is later cloned
  * into all processes.
  */
+
 void __cpuinit fpu_init(void)
 {
 	unsigned long oldcr0 = read_cr0();
@@ -93,14 +94,24 @@ void __cpuinit fpu_init(void)
 
 	write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */
 
-	xsave_init();
+	if (!smp_processor_id())
+		init_thread_xstate();
 
 	mxcsr_feature_mask_init();
 	/* clean state in init */
 	current_thread_info()->status = 0;
 	clear_used_math();
 }
-#endif	/* CONFIG_X86_64 */
+
+#else	/* CONFIG_X86_64 */
+
+void __cpuinit fpu_init(void)
+{
+	if (!smp_processor_id())
+		init_thread_xstate();
+}
+
+#endif	/* CONFIG_X86_32 */
 
 static void fpu_finit(struct fpu *fpu)
 {
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index ab9ad48b6530..550bf45236f4 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -362,9 +362,6 @@ unsigned int sig_xstate_size = sizeof(struct _fpstate);
  */
 static void __cpuinit __xsave_init(void)
 {
-	if (!cpu_has_xsave)
-		return;
-
 	set_in_cr4(X86_CR4_OSXSAVE);
 
 	/*
@@ -429,7 +426,7 @@ static void __init setup_xstate_init(void)
 /*
  * Enable and initialize the xsave feature.
  */
-void __ref xsave_cntxt_init(void)
+static void __cpuinit xsave_cntxt_init(void)
 {
 	unsigned int eax, ebx, ecx, edx;
 
@@ -466,10 +463,13 @@ void __ref xsave_cntxt_init(void)
 
 void __cpuinit xsave_init(void)
 {
+	if (!cpu_has_xsave)
+		return;
+
 	/*
 	 * Boot processor to setup the FP and extended state context info.
 	 */
 	if (!smp_processor_id())
-		init_thread_xstate();
+		xsave_cntxt_init();
 	__xsave_init();
 }