[WebAssembly] Emit clangast in custom section aligned by 4 bytes

Emit __clangast in custom section instead of named data segment
to find it while iterating sections.
This could be avoided if all data segements (the wasm sense) were
represented as their own sections (in the llvm sense).
This can be resolved by WebAssembly/tool-conventions#138

And the on-disk hashtable in clangast needs to be aligned by 4 bytes,
so add paddings in name length field in custom section header.

The length of clangast section name can be represented in 1 byte
by leb128, and possible maximum pads are 3 bytes, so the section
name length won't be invalid in theory.

Fixes https://bugs.llvm.org/show_bug.cgi?id=35928

Differential Revision: https://reviews.llvm.org/D74531

Author: kateinoigakukun

clang/lib/CodeGen/ObjectFilePCHContainerOperations.cpp

@@ -270,25 +270,42 @@ class PCHContainerGenerator : public ASTConsumer {
     assert(Buffer->IsComplete && "serialization did not complete");
     auto &SerializedAST = Buffer->Data;
     auto Size = SerializedAST.size();
-    auto Int8Ty = llvm::Type::getInt8Ty(*VMContext);
-    auto *Ty = llvm::ArrayType::get(Int8Ty, Size);
-    auto *Data = llvm::ConstantDataArray::getString(
-        *VMContext, StringRef(SerializedAST.data(), Size),
-        /*AddNull=*/false);
-    auto *ASTSym = new llvm::GlobalVariable(
-        *M, Ty, /*constant*/ true, llvm::GlobalVariable::InternalLinkage, Data,
-        "__clang_ast");
-    // The on-disk hashtable needs to be aligned.
-    ASTSym->setAlignment(llvm::Align(8));
-
-    // Mach-O also needs a segment name.
-    if (Triple.isOSBinFormatMachO())
-      ASTSym->setSection("__CLANG,__clangast");
-    // COFF has an eight character length limit.
-    else if (Triple.isOSBinFormatCOFF())
-      ASTSym->setSection("clangast");
-    else
-      ASTSym->setSection("__clangast");
+
+    if (Triple.isOSBinFormatWasm()) {
+      // Emit __clangast in custom section instead of named data segment
+      // to find it while iterating sections.
+      // This could be avoided if all data segements (the wasm sense) were
+      // represented as their own sections (in the llvm sense).
+      // TODO: https://github.com/WebAssembly/tool-conventions/issues/138
+      llvm::NamedMDNode *MD =
+          M->getOrInsertNamedMetadata("wasm.custom_sections");
+      llvm::Metadata *Ops[2] = {
+          llvm::MDString::get(*VMContext, "__clangast"),
+          llvm::MDString::get(*VMContext,
+                              StringRef(SerializedAST.data(), Size))};
+      auto *NameAndContent = llvm::MDTuple::get(*VMContext, Ops);
+      MD->addOperand(NameAndContent);
+    } else {
+      auto Int8Ty = llvm::Type::getInt8Ty(*VMContext);
+      auto *Ty = llvm::ArrayType::get(Int8Ty, Size);
+      auto *Data = llvm::ConstantDataArray::getString(
+          *VMContext, StringRef(SerializedAST.data(), Size),
+          /*AddNull=*/false);
+      auto *ASTSym = new llvm::GlobalVariable(
+          *M, Ty, /*constant*/ true, llvm::GlobalVariable::InternalLinkage,
+          Data, "__clang_ast");
+      // The on-disk hashtable needs to be aligned.
+      ASTSym->setAlignment(llvm::Align(8));
+
+      // Mach-O also needs a segment name.
+      if (Triple.isOSBinFormatMachO())
+        ASTSym->setSection("__CLANG,__clangast");
+      // COFF has an eight character length limit.
+      else if (Triple.isOSBinFormatCOFF())
+        ASTSym->setSection("clangast");
+      else
+        ASTSym->setSection("__clangast");
+    }
 
     LLVM_DEBUG({
       // Print the IR for the PCH container to the debug output.

clang/test/PCH/pch-wasm.c

@@ -0,0 +1,7 @@
+// REQUIRES: webassembly-registered-target
+// RUN: %clang_cc1 -triple wasm32-unknown-unknown-wasm -emit-pch -fmodule-format=obj %S/pchpch1.h -o - | llvm-objdump --section-headers - | FileCheck %s
+
+// Ensure that clangast section should be emitted in a section for wasm object file
+
+// CHECK: file format wasm
+// CHECK: __clangast   {{[0-9a-f]+}} {{[0-9a-f]+}}

llvm/lib/MC/WasmObjectWriter.cpp

@@ -292,6 +292,8 @@ class WasmObjectWriter : public MCObjectWriter {
     W->OS << Str;
   }
 
+  void writeStringWithAlignment(const StringRef Str, unsigned Alignment);
+
   void writeI32(int32_t val) {
     char Buffer[4];
     support::endian::write32le(Buffer, val);
@@ -362,6 +364,28 @@ void WasmObjectWriter::startSection(SectionBookkeeping &Section,
   Section.Index = SectionCount++;
 }
 
+// Write a string with extra paddings for trailing alignment
+// TODO: support alignment at asm and llvm level?
+void WasmObjectWriter::writeStringWithAlignment(const StringRef Str,
+                                                unsigned Alignment) {
+
+  // Calculate the encoded size of str length and add pads based on it and
+  // alignment.
+  raw_null_ostream NullOS;
+  uint64_t StrSizeLength = encodeULEB128(Str.size(), NullOS);
+  uint64_t Offset = W->OS.tell() + StrSizeLength + Str.size();
+  uint64_t Paddings = offsetToAlignment(Offset, Align(Alignment));
+  Offset += Paddings;
+
+  // LEB128 greater than 5 bytes is invalid
+  assert((StrSizeLength + Paddings) <= 5 && "too long string to align");
+
+  encodeSLEB128(Str.size(), W->OS, StrSizeLength + Paddings);
+  W->OS << Str;
+
+  assert(W->OS.tell() == Offset && "invalid padding");
+}
+
 void WasmObjectWriter::startCustomSection(SectionBookkeeping &Section,
                                           StringRef Name) {
   LLVM_DEBUG(dbgs() << "startCustomSection " << Name << "\n");
@@ -371,7 +395,12 @@ void WasmObjectWriter::startCustomSection(SectionBookkeeping &Section,
   Section.PayloadOffset = W->OS.tell();
 
   // Custom sections in wasm also have a string identifier.
-  writeString(Name);
+  if (Name != "__clangast") {
+    writeString(Name);
+  } else {
+    // The on-disk hashtable in clangast needs to be aligned by 4 bytes.
+    writeStringWithAlignment(Name, 4);
+  }
 
   // The position where the custom section starts.
   Section.ContentsOffset = W->OS.tell();

llvm/test/MC/WebAssembly/custom-section-alignment.ll

@@ -0,0 +1,10 @@
+; RUN: llc -filetype=obj %s -o - | od -t x1 -v | FileCheck %s
+
+target triple = "wasm32-unknown-unknown"
+
+!0 = !{ !"before", !"\de\ad\be\ef" }
+!1 = !{ !"__clangast", !"\fe\ed\fa\ce" }
+!wasm.custom_sections = !{ !0, !1 }
+
+; Ensure that __clangast content is aligned by 4 bytes
+; CHECK: {{(([0-9a-f]{2} ){4})*}}fe ed fa ce