diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 6184fe70a9e1..9393a445d73c 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -347,6 +347,23 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		ret = copy_user_to_fpregs_zeroing(buf_fx, user_xfeatures, fx_only);
 		pagefault_enable();
 		if (!ret) {
+
+			/*
+			 * Restore supervisor states: previous context switch
+			 * etc has done XSAVES and saved the supervisor states
+			 * in the kernel buffer from which they can be restored
+			 * now.
+			 *
+			 * We cannot do a single XRSTORS here - which would
+			 * be nice - because the rest of the FPU registers are
+			 * being restored from a user buffer directly. The
+			 * single XRSTORS happens below, when the user buffer
+			 * has been copied to the kernel one.
+			 */
+			if (test_thread_flag(TIF_NEED_FPU_LOAD) &&
+			    xfeatures_mask_supervisor())
+				copy_kernel_to_xregs(&fpu->state.xsave,
+						     xfeatures_mask_supervisor());
 			fpregs_mark_activate();
 			fpregs_unlock();
 			return 0;
@@ -364,14 +381,25 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	}
 
 	/*
-	 * The current state of the FPU registers does not matter. By setting
-	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
-	 * is not modified on context switch and that the xstate is considered
+	 * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is
+	 * not modified on context switch and that the xstate is considered
 	 * to be loaded again on return to userland (overriding last_cpu avoids
 	 * the optimisation).
 	 */
-	set_thread_flag(TIF_NEED_FPU_LOAD);
+	fpregs_lock();
+
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+
+		/*
+		 * Supervisor states are not modified by user space input.  Save
+		 * current supervisor states first and invalidate the FPU regs.
+		 */
+		if (xfeatures_mask_supervisor())
+			copy_supervisor_to_kernel(&fpu->state.xsave);
+		set_thread_flag(TIF_NEED_FPU_LOAD);
+	}
 	__fpu_invalidate_fpregs_state(fpu);
+	fpregs_unlock();
 
 	if (use_xsave() && !fx_only) {
 		u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;
@@ -393,7 +421,13 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		fpregs_lock();
 		if (unlikely(init_bv))
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, user_xfeatures);
+
+		/*
+		 * Restore previously saved supervisor xstates along with
+		 * copied-in user xstates.
+		 */
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave,
+					       user_xfeatures | xfeatures_mask_supervisor());
 
 	} else if (use_fxsr()) {
 		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);