diff --git a/lld/test/wasm/pie.ll b/lld/test/wasm/pie.ll
--- a/lld/test/wasm/pie.ll
+++ b/lld/test/wasm/pie.ll
@@ -88,8 +88,8 @@
 
 ; DISASSEM:       <__wasm_start>:
 ; DISASSEM-EMPTY:
-; DISASSEM-NEXT:   call 2
 ; DISASSEM-NEXT:   call 3
+; DISASSEM-NEXT:   call 2
 ; DISASSEM-NEXT:   end
 
 ; Run the same test with threading support.  In this mode
@@ -107,8 +107,8 @@
 
 ; DISASSEM-SHMEM:       <__wasm_start>:
 ; DISASSEM-SHMEM-EMPTY:
-; DISASSEM-SHMEM-NEXT:   call 3
 ; DISASSEM-SHMEM-NEXT:   call 5
+; DISASSEM-SHMEM-NEXT:   call 3
 ; DISASSEM-SHMEM-NEXT:   end
 
 ; SHMEM:         FunctionNames:
diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp
--- a/lld/wasm/Writer.cpp
+++ b/lld/wasm/Writer.cpp
@@ -1253,6 +1253,11 @@
     {
       raw_string_ostream os(bodyContent);
       writeUleb128(os, 0, "num locals");
+      if (WasmSym::applyGlobalRelocs) {
+        writeU8(os, WASM_OPCODE_CALL, "CALL");
+        writeUleb128(os, WasmSym::applyGlobalRelocs->getFunctionIndex(),
+                     "function index");
+      }
       if (WasmSym::initMemory) {
         writeU8(os, WASM_OPCODE_CALL, "CALL");
         writeUleb128(os, WasmSym::initMemory->getFunctionIndex(),
@@ -1264,11 +1269,6 @@
         writeUleb128(os, WasmSym::applyDataRelocs->getFunctionIndex(),
                      "function index");
       }
-      if (WasmSym::applyGlobalRelocs) {
-        writeU8(os, WASM_OPCODE_CALL, "CALL");
-        writeUleb128(os, WasmSym::applyGlobalRelocs->getFunctionIndex(),
-                     "function index");
-      }
       writeU8(os, WASM_OPCODE_END, "END");
     }
     createFunction(WasmSym::startFunction, bodyContent);