ABI verifier: Add standalone tool pnacl-abicheck

This CL adds a standalone tool pnacl-abicheck for checking the ABI validity of a bitcode file.
It also adds a flag pnaclabi-verify to llc to enable the same checking in llc.
It also improves the mechanism for handling and reporting validation errors and uses it in both tools.

R=jvoung@chromium.org,mseaborn@chromium.org
BUG= https://code.google.com/p/nativeclient/issues/detail?id=2309

Review URL: https://codereview.chromium.org/12449014

8 files changed, 147 insertions, 2 deletions

diff --git a/tools/CMakeLists.txt b/tools/CMakeLists.txt
index 144e8ec3ea..145645e3c0 100644
--- a/tools/CMakeLists.txt
+++ b/tools/CMakeLists.txt
@@ -42,6 +42,7 @@ add_subdirectory(llvm-stress)
 add_subdirectory(llvm-mcmarkup)
 
 add_subdirectory(llvm-symbolizer)
+add_subdirectory(pnacl-abicheck)
 
 if( NOT WIN32 )
   add_subdirectory(lto)
diff --git a/tools/LLVMBuild.txt b/tools/LLVMBuild.txt
index 25aa177b35..c887a4d9ad 100644
--- a/tools/LLVMBuild.txt
+++ b/tools/LLVMBuild.txt
@@ -16,7 +16,7 @@
 ;===------------------------------------------------------------------------===;
 
 [common]
-subdirectories = bugpoint llc lli llvm-ar llvm-as llvm-bcanalyzer llvm-cov llvm-diff llvm-dis llvm-dwarfdump llvm-extract llvm-jitlistener llvm-link llvm-mc llvm-nm llvm-objdump llvm-prof llvm-ranlib llvm-rtdyld llvm-size macho-dump opt llvm-mcmarkup
+subdirectories = bugpoint llc lli llvm-ar llvm-as llvm-bcanalyzer llvm-cov llvm-diff llvm-dis llvm-dwarfdump llvm-extract llvm-jitlistener llvm-link llvm-mc llvm-nm llvm-objdump llvm-prof llvm-ranlib llvm-rtdyld llvm-size macho-dump opt llvm-mcmarkup pnacl-abicheck
 
 [component_0]
 type = Group
diff --git a/tools/Makefile b/tools/Makefile
index cc1eea144f..38e79ab306 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -35,7 +35,7 @@ PARALLEL_DIRS := opt llvm-as llvm-dis \
                  llvm-diff macho-dump llvm-objdump llvm-readobj \
 	         llvm-rtdyld llvm-dwarfdump llvm-cov \
 	         llvm-size llvm-stress llvm-mcmarkup bc-wrap pso-stub \
-	         llvm-symbolizer
+	         llvm-symbolizer pnacl-abicheck
 
 # If Intel JIT Events support is configured, build an extra tool to test it.
 ifeq ($(USE_INTEL_JITEVENTS), 1)
diff --git a/tools/llc/llc.cpp b/tools/llc/llc.cpp
index bdc14fc554..7294b3d347 100644
--- a/tools/llc/llc.cpp
+++ b/tools/llc/llc.cpp
@@ -15,6 +15,7 @@
 
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/ADT/Triple.h"
+#include "llvm/Analysis/NaCl.h"
 #include "llvm/Assembly/PrintModulePass.h"
 #include "llvm/Support/DataStream.h"  // @LOCALMOD
 #include "llvm/CodeGen/CommandFlags.h"
@@ -107,6 +108,14 @@ ReduceMemoryFootprint("reduce-memory-footprint",
   cl::desc("Aggressively reduce memory used by llc"),
   cl::init(false));
 
+static cl::opt<bool>
+PNaClABIVerify("pnaclabi-verify",
+  cl::desc("Verify PNaCl bitcode ABI before translating"),
+  cl::init(false));
+static cl::opt<bool>
+PNaClABIVerifyFatalErrors("pnaclabi-verify-fatal-errors",
+  cl::desc("PNaCl ABI verification errors are fatal"),
+  cl::init(false));
 // @LOCALMOD-END
 
 // Determine optimization level.
@@ -307,6 +316,20 @@ int llc_main(int argc, char **argv) {
   return 0;
 }
 
+// @LOCALMOD-BEGIN
+static void CheckABIVerifyErrors(PNaClABIErrorReporter &Reporter,
+                                 const Twine &Name) {
+  if (PNaClABIVerify && Reporter.getErrorCount() > 0) {
+    errs() << (PNaClABIVerifyFatalErrors ? "ERROR:" : "WARNING:");
+    errs() << Name << " is not valid PNaCl bitcode:\n";
+    Reporter.printErrors(errs());
+    if (PNaClABIVerifyFatalErrors)
+      exit(1);
+  }
+  Reporter.reset();
+}
+// @LOCALMOD-END
+
 static int compileModule(char **argv, LLVMContext &Context) {
   // Load the module to be compiled...
   SMDiagnostic Err;
@@ -317,6 +340,8 @@ static int compileModule(char **argv, LLVMContext &Context) {
   bool SkipModule = MCPU == "help" ||
                     (!MAttrs.empty() && MAttrs.front() == "help");
 
+  PNaClABIErrorReporter ABIErrorReporter; // @LOCALMOD
+
   // If user just wants to list available options, skip module loading
   if (!SkipModule) {
     // @LOCALMOD-BEGIN
@@ -346,6 +371,12 @@ static int compileModule(char **argv, LLVMContext &Context) {
     }
 
     // @LOCALMOD-BEGIN
+    if (PNaClABIVerify) {
+      // Verify the module (but not the functions yet)
+      ModulePass *VerifyPass = createPNaClABIVerifyModulePass(&ABIErrorReporter);
+      VerifyPass->runOnModule(*mod);
+      CheckABIVerifyErrors(ABIErrorReporter, "Module");
+    }
 #if defined(__native_client__) && defined(NACL_SRPC)
     RecordMetadataForSrpc(*mod);
 
@@ -472,6 +503,13 @@ static int compileModule(char **argv, LLVMContext &Context) {
     PM.reset(new FunctionPassManager(mod));
   else
     PM.reset(new PassManager());
+
+  // Add the ABI verifier pass before the analysis and code emission passes.
+  FunctionPass *FunctionVerifyPass = NULL;
+  if (PNaClABIVerify) {
+    FunctionVerifyPass = createPNaClABIVerifyFunctionsPass(&ABIErrorReporter);
+    PM->add(FunctionVerifyPass);
+  }
   // @LOCALMOD-END
 
   // Add an appropriate TargetLibraryInfo pass for the module's triple.
@@ -506,6 +544,7 @@ static int compileModule(char **argv, LLVMContext &Context) {
     raw_fd_ostream ROS(GetObjectFileFD(), true);
     ROS.SetBufferSize(1 << 20);
     formatted_raw_ostream FOS(ROS);
+
     // Ask the target to add backend passes as necessary.
     if (Target.addPassesToEmitFile(*PM, FOS, FileType, NoVerify)) {
       errs() << argv[0] << ": target does not support generation of this"
@@ -518,6 +557,7 @@ static int compileModule(char **argv, LLVMContext &Context) {
       P->doInitialization();
       for (Module::iterator I = mod->begin(), E = mod->end(); I != E; ++I) {
         P->run(*I);
+        CheckABIVerifyErrors(ABIErrorReporter, "Function " + I->getName());
         if (ReduceMemoryFootprint) {
           I->Dematerialize();
         }
@@ -570,6 +610,7 @@ static int compileModule(char **argv, LLVMContext &Context) {
       P->doInitialization();
       for (Module::iterator I = mod->begin(), E = mod->end(); I != E; ++I) {
         P->run(*I);
+        CheckABIVerifyErrors(ABIErrorReporter, "Function " + I->getName());
         if (ReduceMemoryFootprint) {
           I->Dematerialize();
         }
diff --git a/tools/pnacl-abicheck/CMakeLists.txt b/tools/pnacl-abicheck/CMakeLists.txt
new file mode 100644
index 0000000000..d3296fa5a5
--- /dev/null
+++ b/tools/pnacl-abicheck/CMakeLists.txt
@@ -0,0 +1,5 @@
+set(LLVM_LINK_COMPONENTS bitreader asmparser)
+
+add_llvm_tool(pnacl-abicheck
+  pnacl-abicheck.cc
+  )
diff --git a/tools/pnacl-abicheck/LLVMBuild.txt b/tools/pnacl-abicheck/LLVMBuild.txt
new file mode 100644
index 0000000000..0af322769c
--- /dev/null
+++ b/tools/pnacl-abicheck/LLVMBuild.txt
@@ -0,0 +1,22 @@
+;===- ./tools/pnacl-abicheck/LLVMBuild.txt ---------------------*- Conf -*--===;
+;
+;                     The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+;   http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+
+[component_0]
+type = Tool
+name = pnacl-abicheck
+parent = Tools
+required_libraries = AsmParser BitReader
diff --git a/tools/pnacl-abicheck/Makefile b/tools/pnacl-abicheck/Makefile
new file mode 100644
index 0000000000..bd98690dd1
--- /dev/null
+++ b/tools/pnacl-abicheck/Makefile
@@ -0,0 +1,16 @@
+#===- tools/pnacl-abicheck/Makefile ------------------------*- Makefile -*-===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+# 
+##===----------------------------------------------------------------------===##
+
+LEVEL := ../..
+TOOLNAME := pnacl-abicheck
+LINK_COMPONENTS := bitreader asmparser
+
+include $(LEVEL)/Makefile.common
+
+
diff --git a/tools/pnacl-abicheck/pnacl-abicheck.cpp b/tools/pnacl-abicheck/pnacl-abicheck.cpp
new file mode 100644
index 0000000000..2bee788872
--- /dev/null
+++ b/tools/pnacl-abicheck/pnacl-abicheck.cpp
@@ -0,0 +1,60 @@
+//===-- pnacl-abicheck.cpp - Check PNaCl bitcode ABI ----------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This tool checks files for compliance with the PNaCl bitcode ABI
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/Analysis/NaCl.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/FormattedStream.h"
+#include "llvm/Support/IRReader.h"
+#include <string>
+
+using namespace llvm;
+
+static cl::opt<std::string>
+InputFilename(cl::Positional, cl::desc("<input bitcode>"), cl::init("-"));
+
+static void CheckABIVerifyErrors(PNaClABIErrorReporter &Reporter,
+                                 const Twine &Name) {
+  if (Reporter.getErrorCount() > 0) {
+    errs() << "ERROR: " << Name << " is not valid PNaCl bitcode:\n";
+    Reporter.printErrors(errs());
+  }
+  Reporter.reset();
+}
+
+int main(int argc, char **argv) {
+  LLVMContext &Context = getGlobalContext();
+  SMDiagnostic Err;
+  OwningPtr<Module> Mod(ParseIRFile(InputFilename, Err, Context));
+  if (Mod.get() == 0) {
+    Err.print(argv[0], errs());
+    return 1;
+  }
+  PNaClABIErrorReporter ABIErrorReporter;
+  // Manually run the passes so we can tell the user which function had the
+  // error. No need for a pass manager since it's just one pass.
+  ModulePass *ModuleChecker = createPNaClABIVerifyModulePass(&ABIErrorReporter);
+  ModuleChecker->runOnModule(*Mod);
+  CheckABIVerifyErrors(ABIErrorReporter, "Module");
+  FunctionPass *FunctionChecker =
+      createPNaClABIVerifyFunctionsPass(&ABIErrorReporter);
+  for (Module::iterator MI = Mod->begin(), ME = Mod->end(); MI != ME; ++MI) {
+    FunctionChecker->runOnFunction(*MI);
+    CheckABIVerifyErrors(ABIErrorReporter, "Function " + MI->getName());
+  }
+
+  return 0;
+}