-fms-extensions: Implement half of #pragma init_seg

Summary:
This pragma is very rare.  We could *hypothetically* lower some uses of
it down to @llvm.global_ctors, but given that GlobalOpt isn't able to
optimize prioritized global ctors today, there's really no point.

If we wanted to do this in the future, I would check if the section used
in the pragma started with ".CRT$XC" and had up to two characters after
it.  Those two characters could form the 16-bit initialization priority
that we support in @llvm.global_ctors.  We would have to teach LLVM to
lower prioritized global ctors on COFF as well.

This should let us compile some silly uses of this pragma in WebKit /
Blink.

Reviewers: rsmith, majnemer

Subscribers: cfe-commits

Differential Revision: http://reviews.llvm.org/D4549

llvm-svn: 213593
diff --git a/clang/lib/CodeGen/CGDeclCXX.cpp b/clang/lib/CodeGen/CGDeclCXX.cpp
index 6a03e9a..94cfe21 100644
--- a/clang/lib/CodeGen/CGDeclCXX.cpp
+++ b/clang/lib/CodeGen/CGDeclCXX.cpp
@@ -257,6 +257,32 @@
   return Fn;
 }
 
+/// Create a global pointer to a function that will initialize a global
+/// variable.  The user has requested that this pointer be emitted in a specific
+/// section.
+void CodeGenModule::EmitPointerToInitFunc(const VarDecl *D,
+                                          llvm::GlobalVariable *GV,
+                                          llvm::Function *InitFunc,
+                                          InitSegAttr *ISA) {
+  llvm::GlobalVariable *PtrArray = new llvm::GlobalVariable(
+      TheModule, InitFunc->getType(), /*isConstant=*/true,
+      llvm::GlobalValue::PrivateLinkage, InitFunc, "__cxx_init_fn_ptr");
+  PtrArray->setSection(ISA->getSection());
+  addUsedGlobal(PtrArray);
+
+  // If the GV is already in a comdat group, then we have to join it.
+  llvm::Comdat *C = GV->getComdat();
+
+  // LinkOnce and Weak linkage are lowered down to a single-member comdat group.
+  // Make an explicit group so we can join it.
+  if (!C && (GV->hasWeakLinkage() || GV->hasLinkOnceLinkage())) {
+    C = TheModule.getOrInsertComdat(GV->getName());
+    GV->setComdat(C);
+  }
+  if (C)
+    PtrArray->setComdat(C);
+}
+
 void
 CodeGenModule::EmitCXXGlobalVarDeclInitFunc(const VarDecl *D,
                                             llvm::GlobalVariable *Addr,
@@ -272,9 +298,9 @@
   llvm::Function *Fn =
       CreateGlobalInitOrDestructFunction(*this, FTy, FnName.str());
 
+  auto *ISA = D->getAttr<InitSegAttr>();
   CodeGenFunction(*this).GenerateCXXGlobalVarDeclInitFunc(Fn, D, Addr,
                                                           PerformInit);
-
   if (D->getTLSKind()) {
     // FIXME: Should we support init_priority for thread_local?
     // FIXME: Ideally, initialization of instantiated thread_local static data
@@ -283,7 +309,10 @@
     // FIXME: We only need to register one __cxa_thread_atexit function for the
     // entire TU.
     CXXThreadLocalInits.push_back(Fn);
-  } else if (const InitPriorityAttr *IPA = D->getAttr<InitPriorityAttr>()) {
+  } else if (PerformInit && ISA) {
+    EmitPointerToInitFunc(D, Addr, Fn, ISA);
+    DelayedCXXInitPosition.erase(D);
+  } else if (auto *IPA = D->getAttr<InitPriorityAttr>()) {
     OrderGlobalInits Key(IPA->getPriority(), PrioritizedCXXGlobalInits.size());
     PrioritizedCXXGlobalInits.push_back(std::make_pair(Key, Fn));
     DelayedCXXInitPosition.erase(D);
diff --git a/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
index c65598e..44597bf 100644
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -1103,6 +1103,9 @@
                                     llvm::GlobalVariable *Addr,
                                     bool PerformInit);
 
+  void EmitPointerToInitFunc(const VarDecl *VD, llvm::GlobalVariable *Addr,
+                             llvm::Function *InitFunc, InitSegAttr *ISA);
+
   // FIXME: Hardcoding priority here is gross.
   void AddGlobalCtor(llvm::Function *Ctor, int Priority = 65535,
                      llvm::Constant *AssociatedData = 0);
diff --git a/clang/lib/Parse/ParsePragma.cpp b/clang/lib/Parse/ParsePragma.cpp
index a7b5f6e..b94c4bc 100644
--- a/clang/lib/Parse/ParsePragma.cpp
+++ b/clang/lib/Parse/ParsePragma.cpp
@@ -652,12 +652,61 @@
   return true;
 }
 
+// #pragma init_seg({ compiler | lib | user | "section-name" [, func-name]} )
 bool Parser::HandlePragmaMSInitSeg(StringRef PragmaName,
                                    SourceLocation PragmaLocation) {
-  PP.Diag(PragmaLocation,
-          PP.getDiagnostics().getCustomDiagID(
-              DiagnosticsEngine::Error, "'#pragma init_seg' not implemented."));
-  return false;
+  if (ExpectAndConsume(tok::l_paren, diag::warn_pragma_expected_lparen,
+                       PragmaName))
+    return false;
+
+  // Parse either the known section names or the string section name.
+  StringLiteral *SegmentName = nullptr;
+  if (Tok.isAnyIdentifier()) {
+    auto *II = Tok.getIdentifierInfo();
+    StringRef Section = llvm::StringSwitch<StringRef>(II->getName())
+                            .Case("compiler", "\".CRT$XCC\"")
+                            .Case("lib", "\".CRT$XCL\"")
+                            .Case("user", "\".CRT$XCU\"")
+                            .Default("");
+
+    if (!Section.empty()) {
+      // Pretend the user wrote the appropriate string literal here.
+      Token Toks[1];
+      Toks[0].startToken();
+      Toks[0].setKind(tok::string_literal);
+      Toks[0].setLocation(Tok.getLocation());
+      Toks[0].setLiteralData(Section.data());
+      Toks[0].setLength(Section.size());
+      SegmentName =
+          cast<StringLiteral>(Actions.ActOnStringLiteral(Toks, nullptr).get());
+      PP.Lex(Tok);
+    }
+  } else if (Tok.is(tok::string_literal)) {
+    ExprResult StringResult = ParseStringLiteralExpression();
+    if (StringResult.isInvalid())
+      return false;
+    SegmentName = cast<StringLiteral>(StringResult.get());
+    if (SegmentName->getCharByteWidth() != 1) {
+      PP.Diag(PragmaLocation, diag::warn_pragma_expected_non_wide_string)
+          << PragmaName;
+      return false;
+    }
+    // FIXME: Add support for the '[, func-name]' part of the pragma.
+  }
+
+  if (!SegmentName) {
+    PP.Diag(PragmaLocation, diag::warn_pragma_expected_init_seg) << PragmaName;
+    return false;
+  }
+
+  if (ExpectAndConsume(tok::r_paren, diag::warn_pragma_expected_rparen,
+                       PragmaName) ||
+      ExpectAndConsume(tok::eof, diag::warn_pragma_extra_tokens_at_eol,
+                       PragmaName))
+    return false;
+
+  Actions.ActOnPragmaMSInitSeg(PragmaLocation, SegmentName);
+  return true;
 }
 
 struct PragmaLoopHintInfo {
diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp
index d28e046..37ce157 100644
--- a/clang/lib/Parse/Parser.cpp
+++ b/clang/lib/Parse/Parser.cpp
@@ -109,7 +109,7 @@
 }
 
 bool Parser::ExpectAndConsume(tok::TokenKind ExpectedTok, unsigned DiagID,
-                              const char *Msg) {
+                              StringRef Msg) {
   if (Tok.is(ExpectedTok) || Tok.is(tok::code_completion)) {
     ConsumeAnyToken();
     return false;
diff --git a/clang/lib/Sema/Sema.cpp b/clang/lib/Sema/Sema.cpp
index 478c34f..2c65332 100644
--- a/clang/lib/Sema/Sema.cpp
+++ b/clang/lib/Sema/Sema.cpp
@@ -87,7 +87,7 @@
         LangOpts.getMSPointerToMemberRepresentationMethod()),
     VtorDispModeStack(1, MSVtorDispAttr::Mode(LangOpts.VtorDispMode)),
     DataSegStack(nullptr), BSSSegStack(nullptr), ConstSegStack(nullptr),
-    CodeSegStack(nullptr), VisContext(nullptr),
+    CodeSegStack(nullptr), CurInitSeg(nullptr), VisContext(nullptr),
     IsBuildingRecoveryCallExpr(false),
     ExprNeedsCleanups(false), LateTemplateParser(nullptr),
     OpaqueParser(nullptr), IdResolver(pp), StdInitializerList(nullptr),
diff --git a/clang/lib/Sema/SemaAttr.cpp b/clang/lib/Sema/SemaAttr.cpp
index 7c182a1..a7d606d 100644
--- a/clang/lib/Sema/SemaAttr.cpp
+++ b/clang/lib/Sema/SemaAttr.cpp
@@ -431,6 +431,15 @@
   UnifySection(SegmentName->getString(), SectionFlags, PragmaLocation);
 }
 
+void Sema::ActOnPragmaMSInitSeg(SourceLocation PragmaLocation,
+                                StringLiteral *SegmentName) {
+  // There's no stack to maintain, so we just have a current section.  When we
+  // see the default section, reset our current section back to null so we stop
+  // tacking on unnecessary attributes.
+  CurInitSeg = SegmentName->getString() == ".CRT$XCU" ? nullptr : SegmentName;
+  CurInitSegLoc = PragmaLocation;
+}
+
 void Sema::ActOnPragmaUnused(const Token &IdTok, Scope *curScope,
                              SourceLocation PragmaLoc) {
 
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index 3e930f4..bbe6930 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -9125,6 +9125,13 @@
     if (const SectionAttr *SA = var->getAttr<SectionAttr>())
       if (UnifySection(SA->getName(), SectionFlags, var))
         var->dropAttr<SectionAttr>();
+
+    // Apply the init_seg attribute if this has an initializer.  If the
+    // initializer turns out to not be dynamic, we'll end up ignoring this
+    // attribute.
+    if (CurInitSeg && var->getInit())
+      var->addAttr(InitSegAttr::CreateImplicit(Context, CurInitSeg->getString(),
+                                               CurInitSegLoc));
   }
 
   // All the following checks are C++ only.