diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index fdee23e..16bf4d4 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -204,6 +204,14 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
 }
 
+static inline void fxsave(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+	else
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
 /* These macros all use (%edi)/(%rdi) as the single memory argument. */
 #define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
 #define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
@@ -272,28 +280,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  * This function is called only during boot time when x86 caps are not set
  * up and alternative can not be used yet.
  */
-static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
-{
-	u64 mask = xfeatures_mask_all;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
-	else
-		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
-
-	/* We should never fault when copying to a kernel buffer: */
-	WARN_ON_FPU(err);
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
 static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 {
 	u64 mask = -1;
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d0eef96..1cadb2f 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -441,12 +441,35 @@ static void __init print_xstate_offset_size(void)
 }
 
 /*
+ * All supported features have either init state all zeros or are
+ * handled in setup_init_fpu() individually. This is an explicit
+ * feature list and does not use XFEATURE_MASK*SUPPORTED to catch
+ * newly added supported features at build time and make people
+ * actually look at the init state for the new feature.
+ */
+#define XFEATURES_INIT_FPSTATE_HANDLED		\
+	(XFEATURE_MASK_FP |			\
+	 XFEATURE_MASK_SSE |			\
+	 XFEATURE_MASK_YMM |			\
+	 XFEATURE_MASK_OPMASK |			\
+	 XFEATURE_MASK_ZMM_Hi256 |		\
+	 XFEATURE_MASK_Hi16_ZMM	 |		\
+	 XFEATURE_MASK_PKRU |			\
+	 XFEATURE_MASK_BNDREGS |		\
+	 XFEATURE_MASK_BNDCSR |			\
+	 XFEATURE_MASK_PASID)
+
+/*
  * setup the xstate image representing the init state
  */
 static void __init setup_init_fpu_buf(void)
 {
 	static int on_boot_cpu __initdata = 1;
 
+	BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED |
+		      XFEATURE_MASK_SUPERVISOR_SUPPORTED) !=
+		     XFEATURES_INIT_FPSTATE_HANDLED);
+
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
@@ -466,10 +489,22 @@ static void __init setup_init_fpu_buf(void)
 	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
 
 	/*
-	 * Dump the init state again. This is to identify the init state
-	 * of any feature which is not represented by all zero's.
+	 * All components are now in init state. Read the state back so
+	 * that init_fpstate contains all non-zero init state. This only
+	 * works with XSAVE, but not with XSAVEOPT and XSAVES because
+	 * those use the init optimization which skips writing data for
+	 * components in init state.
+	 *
+	 * XSAVE could be used, but that would require to reshuffle the
+	 * data when XSAVES is available because XSAVES uses xstate
+	 * compaction. But doing so is a pointless exercise because most
+	 * components have an all zeros init state except for the legacy
+	 * ones (FP and SSE). Those can be saved with FXSAVE into the
+	 * legacy area. Adding new features requires to ensure that init
+	 * state is all zeroes or if not to add the necessary handling
+	 * here.
 	 */
-	copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+	fxsave(&init_fpstate.fxsave);
 }
 
 static int xfeature_uncompacted_offset(int xfeature_nr)