CodeGenModule: Always output wchar_size, check LLVM assumptions.

llvm::TargetLibraryInfo needs to know the size of wchar_t to work on
functions like `wcslen`. This patch changes clang to always emit the
wchar_size module flag (it would only do so for ARM previously).
This also adds an `assert()` to ensure the LLVM defaults based on the
target triple are in sync with clang.

Differential Revision: https://reviews.llvm.org/D32982

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@303463 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CodeGenModule.cpp b/lib/CodeGen/CodeGenModule.cpp
index dee4351a51e3097bb10f20a70b60b9c91dd45771..9d0f802ece075cb5a8da2ed928d28402b3c35cfb 100644 (file)
--- a/lib/CodeGen/CodeGenModule.cpp
+++ b/lib/CodeGen/CodeGenModule.cpp
@@ -45,6 +45,7 @@
 #include "clang/Frontend/CodeGenOptions.h"
 #include "clang/Sema/SemaDiagnostic.h"
 #include "llvm/ADT/Triple.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/DataLayout.h"
@@ -465,18 +466,24 @@ void CodeGenModule::Release() {
     getModule().addModuleFlag(llvm::Module::Warning, "Debug Info Version",
                               llvm::DEBUG_METADATA_VERSION);
 
+  // Width of wchar_t in bytes
+  uint64_t WCharWidth =
+      Context.getTypeSizeInChars(Context.getWideCharType()).getQuantity();
+  assert(LangOpts.ShortWChar ||
+         llvm::TargetLibraryInfoImpl::getTargetWCharSize(Target.getTriple()) ==
+                 Target.getWCharWidth() / 8 &&
+             "LLVM wchar_t size out of sync");
+
   // We need to record the widths of enums and wchar_t, so that we can generate
-  // the correct build attributes in the ARM backend.
+  // the correct build attributes in the ARM backend. wchar_size is also used by
+  // TargetLibraryInfo.
+  getModule().addModuleFlag(llvm::Module::Error, "wchar_size", WCharWidth);
+
   llvm::Triple::ArchType Arch = Context.getTargetInfo().getTriple().getArch();
   if (   Arch == llvm::Triple::arm
       || Arch == llvm::Triple::armeb
       || Arch == llvm::Triple::thumb
       || Arch == llvm::Triple::thumbeb) {
-    // Width of wchar_t in bytes
-    uint64_t WCharWidth =
-        Context.getTypeSizeInChars(Context.getWideCharType()).getQuantity();
-    getModule().addModuleFlag(llvm::Module::Error, "wchar_size", WCharWidth);
-
     // The minimum width of an enum in bytes
     uint64_t EnumWidth = Context.getLangOpts().ShortEnums ? 1 : 4;
     getModule().addModuleFlag(llvm::Module::Error, "min_enum_size", EnumWidth);

diff --git a/test/CodeGen/wchar-size.c b/test/CodeGen/wchar-size.c
new file mode 100644 (file)
index 0000000..38da462
--- /dev/null
+++ b/test/CodeGen/wchar-size.c
@@ -0,0 +1,8 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -o - %s | FileCheck %s -check-prefix=LONG-WCHAR
+// RUN: %clang_cc1 -triple x86_64-unknown-windows-msvc -emit-llvm -o - %s | FileCheck %s -check-prefix=SHORT-WCHAR
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -o - -fshort-wchar %s | FileCheck %s -check-prefix=SHORT-WCHAR
+// Note: -fno-short-wchar implies the target default is used; so there is no
+// need to test this separately here.
+
+// LONG-WCHAR: !{{[0-9]+}} = !{i32 {{[0-9]+}}, !"wchar_size", i32 4}
+// SHORT-WCHAR: !{{[0-9]+}} = !{i32 {{[0-9]+}}, !"wchar_size", i32 2}