diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6dd2a2988c2d9d68cacc7030554424ad70..d5dd808144190ffd1d443229b4dbbd56740fface 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4b8995e532f5422a03a7fb65c716cbf35d..ff898bbf579d7f34ce7b8c98a5482f72e4d338bf 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
 		return;
 
 	pci_read_config_dword(nb_ht, 0x60, &val);
-	node = val & 7;
+	node = pcibus_to_node(dev->bus) | (val & 7);
 	/*
 	 * Some hardware may return an invalid node ID,
 	 * so check it first: