Add a string lowering mode disallowing non-UTF-8 strings

src/passes/StringLowering.cpp

@@ -194,8 +194,16 @@ struct StringLowering : public StringGathering {
   // instead of emitting them into the JSON custom section.
   bool useMagicImports;
 
-  StringLowering(bool useMagicImports = false)
-    : useMagicImports(useMagicImports) {}
+  // Whether to throw a fatal error on non-UTF8 strings that would not be able
+  // to use the "magic import" mechanism. Only usable in conjunction with magic
+  // imports.
+  bool assertUTF8;
+
+  StringLowering(bool useMagicImports = false, bool assertUTF8 = false)
+    : useMagicImports(useMagicImports), assertUTF8(assertUTF8) {
+    // If we are asserting valid UTF-8, we must be using magic imports.
+    assert(!assertUTF8 || useMagicImports);
+  }
 
   void run(Module* module) override {
     if (!module->features.has(FeatureSet::Strings)) {
@@ -238,6 +246,12 @@ struct StringLowering : public StringGathering {
             global->module = "'";
             global->base = Name(utf8.str());
           } else {
+            if (assertUTF8) {
+              std::stringstream escaped;
+              String::printEscaped(escaped, utf8.str());
+              Fatal() << "Cannot lower non-UTF-16 string " << escaped.str()
+                      << '\n';
+            }
             global->module = "string.const";
             global->base = std::to_string(jsonImportIndex);
             if (first) {
@@ -534,5 +548,8 @@ struct StringLowering : public StringGathering {
 Pass* createStringGatheringPass() { return new StringGathering(); }
 Pass* createStringLoweringPass() { return new StringLowering(); }
 Pass* createStringLoweringMagicImportPass() { return new StringLowering(true); }
+Pass* createStringLoweringMagicImportAssertPass() {
+  return new StringLowering(true, true);
+}
 
 } // namespace wasm

src/passes/pass.cpp

@@ -503,6 +503,10 @@ void PassRegistry::registerPasses() {
     "string-lowering-magic-imports",
     "same as string-lowering, but encodes well-formed strings as magic imports",
     createStringLoweringMagicImportPass);
+  registerPass("string-lowering-magic-imports-assert",
+               "same as string-lowering-magic-imports, but raise a fatal error "
+               "if there are invalid strings",
+               createStringLoweringMagicImportAssertPass);
   registerPass(
     "strip", "deprecated; same as strip-debug", createStripDebugPass);
   registerPass("stack-check",

src/passes/passes.h

@@ -158,6 +158,7 @@ Pass* createStackCheckPass();
 Pass* createStringGatheringPass();
 Pass* createStringLoweringPass();
 Pass* createStringLoweringMagicImportPass();
+Pass* createStringLoweringMagicImportAssertPass();
 Pass* createStripDebugPass();
 Pass* createStripDWARFPass();
 Pass* createStripProducersPass();

test/lit/help/wasm-metadce.test

@@ -478,6 +478,11 @@
 ;; CHECK-NEXT:                                                 encodes well-formed strings as
 ;; CHECK-NEXT:                                                 magic imports
 ;; CHECK-NEXT:
+;; CHECK-NEXT:   --string-lowering-magic-imports-assert        same as
+;; CHECK-NEXT:                                                 string-lowering-magic-imports,
+;; CHECK-NEXT:                                                 but raise a fatal error if there
+;; CHECK-NEXT:                                                 are invalid strings
+;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip                                       deprecated; same as strip-debug
 ;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip-debug                                 strip debug info (including the

test/lit/help/wasm-opt.test

@@ -487,6 +487,11 @@
 ;; CHECK-NEXT:                                                 encodes well-formed strings as
 ;; CHECK-NEXT:                                                 magic imports
 ;; CHECK-NEXT:
+;; CHECK-NEXT:   --string-lowering-magic-imports-assert        same as
+;; CHECK-NEXT:                                                 string-lowering-magic-imports,
+;; CHECK-NEXT:                                                 but raise a fatal error if there
+;; CHECK-NEXT:                                                 are invalid strings
+;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip                                       deprecated; same as strip-debug
 ;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip-debug                                 strip debug info (including the

test/lit/help/wasm2js.test

@@ -441,6 +441,11 @@
 ;; CHECK-NEXT:                                                 encodes well-formed strings as
 ;; CHECK-NEXT:                                                 magic imports
 ;; CHECK-NEXT:
+;; CHECK-NEXT:   --string-lowering-magic-imports-assert        same as
+;; CHECK-NEXT:                                                 string-lowering-magic-imports,
+;; CHECK-NEXT:                                                 but raise a fatal error if there
+;; CHECK-NEXT:                                                 are invalid strings
+;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip                                       deprecated; same as strip-debug
 ;; CHECK-NEXT:
 ;; CHECK-NEXT:   --strip-debug                                 strip debug info (including the

test/lit/passes/string-lowering.wast

@@ -35,9 +35,16 @@
 ;; RUN: wasm-opt %s --string-lowering-magic-imports -all -S -o - \
 ;; RUN:     | filecheck %s --check-prefix=MAGIC
 ;;
+;; If we use magic imports with asserts, we should get an error.
+;;
+;; RUN: not wasm-opt %s --string-lowering-magic-imports-assert -all -S -o - \
+;; RUN:     2>&1 | filecheck %s --check-prefix=ASSERT
+;;
 ;; CHECK: custom section "string.consts", size 136, contents: "[\"bar\",\"foo\",\"needs\\tescaping\\u0000.'#%\\\"- .\\r\\n\\\\08\\f\\n\\r\\t.\\ua66e\",\"unpaired high surrogate \\ud800 \",\"unpaired low surrogate \\udf48 \"]"
 ;;
 ;; MAGIC: custom section "string.consts", size 68, contents: "[\"unpaired high surrogate \\ud800 \",\"unpaired low surrogate \\udf48 \"]"
+;;
+;; ASSERT: Fatal: Cannot lower non-UTF-16 string "unpaired high surrogate \ef\bf\bd "
 
 ;; The custom section should parse OK using JSON.parse from node.
 ;; (Note we run --remove-unused-module-elements to remove externref-using