PNaCl wire format: Remove the top-level DATALAYOUT record

PNaCl only supports a fixed data layout, so treat this as implicit in
the pexe file.

Add the data layout field back at read time, to prevent accidentally
using any architecture-specific backend data layout when translating,
and to ensure that any IR passes that use the data layout work
correctly.

BUG=https://code.google.com/p/nativeclient/issues/detail?id=3505
TEST=*.ll tests + PNaCl toolchain trybots

Review URL: https://codereview.chromium.org/17591014

4 files changed, 20 insertions, 11 deletions

diff --git a/include/llvm/Bitcode/NaCl/NaClLLVMBitCodes.h b/include/llvm/Bitcode/NaCl/NaClLLVMBitCodes.h
index 1c4d80efba..0f3755abba 100644
--- a/include/llvm/Bitcode/NaCl/NaClLLVMBitCodes.h
+++ b/include/llvm/Bitcode/NaCl/NaClLLVMBitCodes.h
@@ -51,7 +51,7 @@ namespace naclbitc {
   enum NaClModuleCodes {
     MODULE_CODE_VERSION     = 1,    // VERSION:     [version#]
     MODULE_CODE_TRIPLE      = 2,    // Not used in PNaCl
-    MODULE_CODE_DATALAYOUT  = 3,    // DATALAYOUT:  [strchr x N]
+    MODULE_CODE_DATALAYOUT  = 3,    // Not used in PNaCl
     MODULE_CODE_ASM         = 4,    // ASM:         [strchr x N]
     MODULE_CODE_SECTIONNAME = 5,    // SECTIONNAME: [strchr x N]
 
diff --git a/lib/Bitcode/NaCl/Reader/NaClBitcodeReader.cpp b/lib/Bitcode/NaCl/Reader/NaClBitcodeReader.cpp
index 8fe6274a15..bd6ddcb020 100644
--- a/lib/Bitcode/NaCl/Reader/NaClBitcodeReader.cpp
+++ b/lib/Bitcode/NaCl/Reader/NaClBitcodeReader.cpp
@@ -1477,13 +1477,6 @@ bool NaClBitcodeReader::ParseModule(bool Resume) {
       }
       break;
     }
-    case naclbitc::MODULE_CODE_DATALAYOUT: {  // DATALAYOUT: [strchr x N]
-      std::string S;
-      if (ConvertToString(Record, 0, S))
-        return Error("Invalid MODULE_CODE_DATALAYOUT record");
-      TheModule->setDataLayout(S);
-      break;
-    }
     case naclbitc::MODULE_CODE_ASM: {  // ASM: [strchr x N]
       std::string S;
       if (ConvertToString(Record, 0, S))
@@ -1630,6 +1623,16 @@ bool NaClBitcodeReader::ParseModule(bool Resume) {
 bool NaClBitcodeReader::ParseBitcodeInto(Module *M) {
   TheModule = 0;
 
+  // PNaCl does not support different DataLayouts in pexes, so we
+  // implicitly set the DataLayout to the following default.
+  //
+  // This is not usually needed by the backend, but it might be used
+  // by IR passes that the PNaCl translator runs.  We set this in the
+  // reader rather than in pnacl-llc so that 'opt' will also use the
+  // correct DataLayout if it is run on a pexe.
+  M->setDataLayout("e-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-"
+                   "f32:32:32-f64:64:64-p:32:32:32-v128:32:32");
+
   if (InitStream()) return true;
 
   // We expect a number of well-defined blocks, though we don't necessarily
diff --git a/lib/Bitcode/NaCl/Writer/NaClBitcodeWriter.cpp b/lib/Bitcode/NaCl/Writer/NaClBitcodeWriter.cpp
index bf1faa463d..7afcf666dc 100644
--- a/lib/Bitcode/NaCl/Writer/NaClBitcodeWriter.cpp
+++ b/lib/Bitcode/NaCl/Writer/NaClBitcodeWriter.cpp
@@ -431,9 +431,6 @@ static void WriteModuleInfo(const Module *M, const NaClValueEnumerator &VE,
                             NaClBitstreamWriter &Stream) {
   DEBUG(dbgs() << "-> WriteModuleInfo\n");
   // Emit various pieces of data attached to a module.
-  if (!M->getDataLayout().empty())
-    WriteStringRecord(naclbitc::MODULE_CODE_DATALAYOUT, M->getDataLayout(),
-                      0/*TODO*/, Stream);
   if (!M->getModuleInlineAsm().empty())
     WriteStringRecord(naclbitc::MODULE_CODE_ASM, M->getModuleInlineAsm(),
                       0/*TODO*/, Stream);
diff --git a/test/NaCl/Bitcode/implicit-datalayout.ll b/test/NaCl/Bitcode/implicit-datalayout.ll
new file mode 100644
index 0000000000..5a957dffec
--- /dev/null
+++ b/test/NaCl/Bitcode/implicit-datalayout.ll
@@ -0,0 +1,9 @@
+; RUN: llvm-as < %s | pnacl-freeze | pnacl-thaw - | llvm-dis - | FileCheck %s
+
+; The "datalayout" field is considered to be implicit in the pexe.  It
+; is not stored in the pexe; the reader adds it implicitly.
+;
+; The most important parts of the datalayout for PNaCl are the pointer
+; size and the endianness ("e" for little endian).
+
+; CHECK: target datalayout = "e{{.*}}p:32:32:32{{.*}}"