diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 4b69be9bea5535127b6e1e83e354fb602652ae6a..aa7e808b9d1e15a0d12c8bdcb74a20bb1101072a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -259,19 +259,6 @@ int fpu_clone(struct task_struct *dst)
 	return 0;
 }
 
-/*
- * Activate the current task's in-memory FPU context,
- * if it has not been used before:
- */
-static void fpu__initialize(struct fpu *fpu)
-{
-	WARN_ON_FPU(fpu != &current->thread.fpu);
-
-	set_thread_flag(TIF_NEED_FPU_LOAD);
-	fpstate_init(&fpu->state);
-	trace_x86_fpu_init_state(fpu);
-}
-
 /*
  * Drops current FPU state: deactivates the fpregs and
  * the fpstate. NOTE: it still leaves previous contents
@@ -314,47 +301,99 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
 	pkru_write_default();
 }
 
+static inline unsigned int init_fpstate_copy_size(void)
+{
+	if (!use_xsave())
+		return fpu_kernel_xstate_size;
+
+	/* XSAVE(S) just needs the legacy and the xstate header part */
+	return sizeof(init_fpstate.xsave);
+}
+
+/* Temporary workaround. Will be removed once PKRU and XSTATE are untangled. */
+static inline void pkru_set_default_in_xstate(struct xregs_state *xsave)
+{
+	struct pkru_state *pk;
+
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+	/*
+	 * Force XFEATURE_PKRU to be set in the header otherwise
+	 * get_xsave_addr() does not work and it also needs to be set to
+	 * make XRSTOR(S) load it.
+	 */
+	xsave->header.xfeatures |= XFEATURE_MASK_PKRU;
+	pk = get_xsave_addr(xsave, XFEATURE_PKRU);
+	pk->pkru = pkru_get_init_value();
+}
+
 /*
- * Clear the FPU state back to init state.
- *
- * Called by sys_execve(), by the signal handler code and by various
- * error paths.
+ * Reset current->fpu memory state to the init values.
+ */
+static void fpu_reset_fpstate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	fpregs_lock();
+	fpu__drop(fpu);
+	/*
+	 * This does not change the actual hardware registers. It just
+	 * resets the memory image and sets TIF_NEED_FPU_LOAD so a
+	 * subsequent return to usermode will reload the registers from the
+	 * task's memory image.
+	 *
+	 * Do not use fpstate_init() here. Just copy init_fpstate which has
+	 * the correct content already except for PKRU.
+	 */
+	memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size());
+	pkru_set_default_in_xstate(&fpu->state.xsave);
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	fpregs_unlock();
+}
+
+/*
+ * Reset current's user FPU states to the init states.  current's
+ * supervisor states, if any, are not modified by this function.  The
+ * caller guarantees that the XSTATE header in memory is intact.
  */
-static void fpu__clear(struct fpu *fpu, bool user_only)
+void fpu__clear_user_states(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!static_cpu_has(X86_FEATURE_FPU)) {
-		fpu__drop(fpu);
-		fpu__initialize(fpu);
+	fpregs_lock();
+	if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+		fpu_reset_fpstate();
+		fpregs_unlock();
 		return;
 	}
 
-	fpregs_lock();
-
-	if (user_only) {
-		if (!fpregs_state_valid(fpu, smp_processor_id()) &&
-		    xfeatures_mask_supervisor())
-			os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
-		restore_fpregs_from_init_fpstate(xfeatures_mask_user());
-	} else {
-		restore_fpregs_from_init_fpstate(xfeatures_mask_all);
+	/*
+	 * Ensure that current's supervisor states are loaded into their
+	 * corresponding registers.
+	 */
+	if (xfeatures_mask_supervisor() &&
+	    !fpregs_state_valid(fpu, smp_processor_id())) {
+		os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
 	}
 
+	/* Reset user states in registers. */
+	restore_fpregs_from_init_fpstate(xfeatures_mask_user());
+
+	/*
+	 * Now all FPU registers have their desired values.  Inform the FPU
+	 * state machine that current's FPU registers are in the hardware
+	 * registers. The memory image does not need to be updated because
+	 * any operation relying on it has to save the registers first when
+	 * current's FPU is marked active.
+	 */
 	fpregs_mark_activate();
 	fpregs_unlock();
 }
 
-void fpu__clear_user_states(struct fpu *fpu)
-{
-	fpu__clear(fpu, true);
-}
-
 void fpu_flush_thread(void)
 {
-	fpu__clear(&current->thread.fpu, false);
+	fpu_reset_fpstate();
 }
-
 /*
  * Load FPU context before returning to userspace.
  */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b9b0ddcc2b62144d08fae2bda092425e4a21b796..d20963c3bb6d015f2f1a8bb70b9c478e3dc56280 100755
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -188,6 +188,15 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	return ret;
 }
 
+static void pkru_flush_thread(void)
+{
+	/*
+	 * If PKRU is enabled the default PKRU value has to be loaded into
+	 * the hardware right here (similar to context switch).
+	 */
+	pkru_write_default();
+}
+
 void flush_thread(void)
 {
 	struct task_struct *tsk = current;
@@ -196,6 +205,7 @@ void flush_thread(void)
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
 	fpu_flush_thread();
+	pkru_flush_thread();
 }
 
 void disable_TSC(void)