3 files changed, 135 insertions, 9 deletions
diff --git a/src/wasm/wasm-stack.cpp b/src/wasm/wasm-stack.cpp
index dda47ffa6..1ed60abed 100644
--- a/src/wasm/wasm-stack.cpp
+++ b/src/wasm/wasm-stack.cpp
@@ -2568,25 +2568,45 @@ void BinaryInstWriter::mapLocalsAndEmitHeader() {
   for (Index i = 0; i < func->getNumParams(); i++) {
     mappedLocals[std::make_pair(i, 0)] = i;
   }
+
   // Normally we map all locals of the same type into a range of adjacent
   // addresses, which is more compact. However, if we need to keep DWARF valid,
   // do not do any reordering at all - instead, do a trivial mapping that
   // keeps everything unmoved.
+  //
+  // Unless we have run DWARF-invalidating passes, all locals added during the
+  // process that are not in DWARF info (tuple locals, tuple scratch locals,
+  // locals to resolve stacky format, ..) have been all tacked on to the
+  // existing locals and happen at the end, so as long as we print the local
+  // types in order, we don't invalidate original local DWARF info here.
   if (DWARF) {
-    FindAll<TupleExtract> extracts(func->body);
-    if (!extracts.list.empty()) {
-      Fatal() << "DWARF + multivalue is not yet complete";
+    Index mappedIndex = func->getVarIndexBase();
+    for (Index i = func->getVarIndexBase(); i < func->getNumLocals(); i++) {
+      size_t size = func->getLocalType(i).size();
+      for (Index j = 0; j < size; j++) {
+        mappedLocals[std::make_pair(i, j)] = mappedIndex + j;
+      }
+      mappedIndex += size;
     }
-    Index varStart = func->getVarIndexBase();
-    Index varEnd = varStart + func->getNumVars();
-    o << U32LEB(func->getNumVars());
-    for (Index i = varStart; i < varEnd; i++) {
-      mappedLocals[std::make_pair(i, 0)] = i;
+    countScratchLocals();
+
+    size_t numBinaryLocals =
+      mappedIndex - func->getVarIndexBase() + scratchLocals.size();
+    o << U32LEB(numBinaryLocals);
+    for (Index i = func->getVarIndexBase(); i < func->getNumLocals(); i++) {
+      for (const auto& type : func->getLocalType(i)) {
+        o << U32LEB(1);
+        parent.writeType(type);
+      }
+    }
+    for (auto& [type, _] : scratchLocals) {
       o << U32LEB(1);
-      parent.writeType(func->getLocalType(i));
+      parent.writeType(type);
+      scratchLocals[type] = mappedIndex++;
     }
     return;
   }
+
   for (auto type : func->vars) {
     for (const auto& t : type) {
       noteLocalType(t);
diff --git a/test/lit/binary/dwarf-multivalue.test b/test/lit/binary/dwarf-multivalue.test
new file mode 100644
index 000000000..435aebe25
--- /dev/null
+++ b/test/lit/binary/dwarf-multivalue.test
@@ -0,0 +1,106 @@
+;; Test that we handle multivalue + DWARF correctly. When we need to preserve
+;; DWARF info, we don't do any local reordering and all newly added locals
+;; during parsing/writing are added at the end of the local list.
+
+;; Generated from this c file with the following command:
+;; $ emcc -g -Xclang -target-abi -Xclang experimental-mv dwarf-multivalue.c -o dwarf-multivalue.wasm
+;;
+;; struct MyStruct {
+;;   int a;
+;;   float b;
+;; };
+;;
+;; struct MyStruct foo() {
+;;   struct MyStruct ret = {.a = 3, .b = 3.5};
+;;   return ret;
+;; }
+;;
+;; void test() {
+;;   struct MyStruct s = foo();
+;; }
+;;
+;; int main() {
+;;   test();
+;;   return 0;
+;; }
+
+;; The original wasm file's $test function's locals are as follows:
+;; (func $test
+;;  (local $0 i32)
+;;  (local $1 i32)
+;;  (local $2 i32)
+;;  (local $3 i32)
+;;  (local $4 f32)
+;;  (local $5 i32)
+;;  (local $6 i32)
+;;  (local $7 i32)
+;;  (local $8 f32)
+;;  (local $9 i32)
+;;  (local $10 f32)
+
+;; If we parse this wasm file into Binaryen IR, two locals are added in the
+;; process. Here $11 is added for tuple parsing and $12 is added for stacky IR
+;; resolving during binary reading process.
+;; RUN: wasm-dis %s.wasm -o - | filecheck %s --check-prefix=ORIG
+;; ORIG:      (func $test
+;; ORIG-NEXT:  (local $0 i32)
+;; ORIG-NEXT:  (local $1 i32)
+;; ORIG-NEXT:  (local $2 i32)
+;; ORIG-NEXT:  (local $3 i32)
+;; ORIG-NEXT:  (local $4 f32)
+;; ORIG-NEXT:  (local $5 i32)
+;; ORIG-NEXT:  (local $6 i32)
+;; ORIG-NEXT:  (local $7 i32)
+;; ORIG-NEXT:  (local $8 f32)
+;; ORIG-NEXT:  (local $9 i32)
+;; ORIG-NEXT:  (local $10 f32)
+;; ORIG-NEXT:  (local $11 (tuple i32 f32))
+;; ORIG-NEXT:  (local $12 i32)
+
+;; If we write this IR into binary, even if this cannot be displayed in the wast
+;; format, the local order of $test will look like this, because we don't
+;; reorder locals:
+;; (func $test
+;;  (local $0 i32)
+;;  (local $1 i32)
+;;  (local $2 i32)
+;;  (local $3 i32)
+;;  (local $4 f32)
+;;  (local $5 i32)
+;;  (local $6 i32)
+;;  (local $7 i32)
+;;  (local $8 f32)
+;;  (local $9 i32)
+;;  (local $10 f32)
+;;  (local $11 i32) ;; Previous (local $11 (tuple i32 f32))'s first element
+;;  (local $12 f32) ;; Previous (local $11 (tuple i32 f32))'s second element
+;;  (local $13 i32) ;; Previous (local $12 i32)
+;;  (local $14 f32) ;; scratch local for f32
+
+;; We parse this binary again into Binaryen IR, roundtripping the original
+;; binary. Here until (local $14) is the same with the previous list, and $15 is
+;; is added for tuple parsing and $16 is added for stacky IR resolving during
+;; binary reading process.
+;; RUN: wasm-opt -all -g --roundtrip %s.wasm -S -o - | filecheck %s --check-prefix=ROUNDTRIP
+;; ROUNDTRIP:      (func $test
+;; ROUNDTRIP-NEXT:  (local $0 i32)
+;; ROUNDTRIP-NEXT:  (local $1 i32)
+;; ROUNDTRIP-NEXT:  (local $2 i32)
+;; ROUNDTRIP-NEXT:  (local $3 i32)
+;; ROUNDTRIP-NEXT:  (local $4 f32)
+;; ROUNDTRIP-NEXT:  (local $5 i32)
+;; ROUNDTRIP-NEXT:  (local $6 i32)
+;; ROUNDTRIP-NEXT:  (local $7 i32)
+;; ROUNDTRIP-NEXT:  (local $8 f32)
+;; ROUNDTRIP-NEXT:  (local $9 i32)
+;; ROUNDTRIP-NEXT:  (local $10 f32)
+;; ROUNDTRIP-NEXT:  (local $11 i32)
+;; ROUNDTRIP-NEXT:  (local $12 f32)
+;; ROUNDTRIP-NEXT:  (local $13 i32)
+;; ROUNDTRIP-NEXT:  (local $14 f32)
+;; ROUNDTRIP-NEXT:  (local $15 (tuple i32 f32))
+;; ROUNDTRIP-NEXT:  (local $16 i32)
+
+;; We can see that we don't reorder the locals during the process and the
+;; original list of locals, local $0~$10, is untouched, to NOT invalidate DWARF
+;; info.
diff --git a/test/lit/binary/dwarf-multivalue.test.wasm b/test/lit/binary/dwarf-multivalue.test.wasm
new file mode 100755
index 000000000..14d7dc60e
--- /dev/null
+++ b/test/lit/binary/dwarf-multivalue.test.wasm