Add a string lowering mode disallowing non-UTF-8 strings (#6861)

The best way to lower strings is via the "magic imports" API that uses
the names of imported string globals as their values. This approach only
works for valid UTF-8 strings, though. The existing
string-lowering-magic-imports pass falls back to putting non-UTF-8
strings in a JSON custom section, but this requires the runtime to
support that custom section for correctness. To help catch errors early
when runtimes do not support the strings custom section, add a new pass
that uses magic imports and raises an error if there are any invalid
strings.

3 files changed, 24 insertions, 2 deletions

diff --git a/src/passes/StringLowering.cpp b/src/passes/StringLowering.cpp
index fa5c1c9a8..92e3268dc 100644
--- a/src/passes/StringLowering.cpp
+++ b/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
diff --git a/src/passes/pass.cpp b/src/passes/pass.cpp
index ccfc7b728..35d2f6779 100644
--- a/src/passes/pass.cpp
+++ b/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",
diff --git a/src/passes/passes.h b/src/passes/passes.h
index 9fcb5f95f..a95365676 100644
--- a/src/passes/passes.h
+++ b/src/passes/passes.h
@@ -158,6 +158,7 @@ Pass* createStackCheckPass();
 Pass* createStringGatheringPass();
 Pass* createStringLoweringPass();
 Pass* createStringLoweringMagicImportPass();
+Pass* createStringLoweringMagicImportAssertPass();
 Pass* createStripDebugPass();
 Pass* createStripDWARFPass();
 Pass* createStripProducersPass();