[lld][WebAssembly] Apply global relocs before data relocs

[sbc100]

Summary

Since the code for apply data relocations can sometimes use
the values stored in he globals, they need to be relocated
before the data relocations can be run.

Fixes: https://github.com/emscripten-core/emscripten/issues/13398

lld/test/wasm/pie.ll

 ; CHECK-NEXT:         Name:            __wasm_apply_data_relocs
 ; CHECK-NEXT:       - Index:           3
 ; CHECK-NEXT:         Name:            __wasm_apply_global_relocs
 ; CHECK-NEXT:       - Index:           4
 ; CHECK-NEXT:         Name:            __wasm_start
 
 ; 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
 ; we expect __wasm_init_memory and __wasm_apply_data_relocs
 ; to be generated along with __wasm_start as the start
 ; function.
 
 ; RUN: llc -relocation-model=pic -mattr=+mutable-globals,+atomics,+bulk-memory -filetype=obj %s -o %t.shmem.o
 ; RUN: wasm-ld --no-gc-sections --shared-memory --allow-undefined --experimental-pic -pie -o %t.shmem.wasm %t.shmem.o
 ; RUN: obj2yaml %t.shmem.wasm | FileCheck %s --check-prefix=SHMEM
 ; RUN: llvm-objdump --disassemble-symbols=__wasm_start --no-show-raw-insn --no-leading-addr %t.shmem.wasm | FileCheck %s --check-prefixes DISASSEM-SHMEM
 
 ; SHMEM:         - Type:            START
 ; SHMEM-NEXT:      StartFunction:   6
 
 ; 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:
 ; SHMEM-NEXT:      - Index:           0
 ; SHMEM-NEXT:        Name:            external_func
 ; SHMEM-NEXT:      - Index:           1
 ; SHMEM-NEXT:        Name:            __wasm_call_ctors
 ; SHMEM-NEXT:      - Index:           2

lld/wasm/Writer.cpp

 
 void Writer::createStartFunction() {
   // If the start function exists when we have more than one function to call.
   if (WasmSym::startFunction) {
     std::string bodyContent;
     {
       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(),
                      "function index");
       } else if (WasmSym::applyDataRelocs) {
         // When initMemory is present it calls applyDataRelocs.  If not,
         // we must call it directly.
         writeU8(os, WASM_OPCODE_CALL, "CALL");
         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);
   } else if (WasmSym::initMemory) {
     WasmSym::startFunction = WasmSym::initMemory;
   } else if (WasmSym::applyGlobalRelocs) {
     WasmSym::startFunction = WasmSym::applyGlobalRelocs;
   } else if (WasmSym::applyDataRelocs) {