Create one-off tool pnacl-hack-memset

tools/pnacl-hack-memset/pnacl-hack-memset.cpp

Index: tools/pnacl-hack-memset/pnacl-hack-memset.cpp
diff --git a/tools/pnacl-thaw/pnacl-thaw.cpp b/tools/pnacl-hack-memset/pnacl-hack-memset.cpp
similarity index 53%
copy from tools/pnacl-thaw/pnacl-thaw.cpp
copy to tools/pnacl-hack-memset/pnacl-hack-memset.cpp
index 5adebdebea0cbd21d3b55afd287e3d4ee2a50e25..caf77ef2689193a3de932db1d0392e73a6732e0b 100644
--- a/tools/pnacl-thaw/pnacl-thaw.cpp
+++ b/tools/pnacl-hack-memset/pnacl-hack-memset.cpp
@@ -1,4 +1,4 @@
-/* Copyright 2013 The Native Client Authors. All rights reserved.
+/* Copyright 2016 The Native Client Authors. All rights reserved.
  * Use of this source code is governed by a BSD-style license that can
  * be found in the LICENSE file.
  */
@@ -12,7 +12,9 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Bitcode/NaCl/NaClReaderWriter.h"
-#include "llvm/Bitcode/ReaderWriter.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Instructions.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/CommandLine.h"
@@ -29,11 +31,14 @@ using namespace llvm;
 namespace {
 
 static cl::opt<std::string>
-OutputFilename("o", cl::desc("Specify thawed pexe filename"),
-	       cl::value_desc("filename"), cl::init("-"));
+OutputFilename("o", cl::desc("Specify fixed pexe filename"),
+               cl::value_desc("fixed pexe file"), cl::init("-"));
 
 static cl::opt<std::string>
-InputFilename(cl::Positional, cl::desc("<frozen file>"), cl::init("-"));
+InputFilename(cl::Positional, cl::desc("<pexe file>"), cl::init("-"));
+
+static cl::opt<bool>
+ShowFixes("show-fixes", cl::desc("Show fixes to memset"), cl::init(false));
 
 static void WriteOutputFile(const Module *M) {
 
@@ -45,7 +50,7 @@ static void WriteOutputFile(const Module *M) {
     exit(1);
   }
 
-  WriteBitcodeToFile(M, Out->os());
+  NaClWriteBitcodeToFile(M, Out->os(), /* AcceptSupportedOnly = */ false);
 
   // Declare success.
   Out->keep();
@@ -78,6 +83,82 @@ static Module *readBitcode(std::string &Filename, LLVMContext &Context,
   return M;
 }
 
+size_t fixCallToMemset(CallInst &Call) {

[Jim Stichnoth, 2016/08/22 21:55:43]

Document return value

[Jim Stichnoth, 2016/08/22 21:55:44]

Can this be CallInst *Call?  Makes it clearer at the call site that the arg may
be modified.

[Karl, 2016/08/23 15:17:31]

Done.

+  if (Call.getNumArgOperands() != 5)
+    return 0;
+  Value* Val = Call.getArgOperand(1);

[Jim Stichnoth, 2016/08/22 21:55:43]

"Value *Val" rather than "Value* Val", right?
here and below

[Karl, 2016/08/23 15:17:31]

Correct. Fixing. I was getting too used to the Chrome style, which does "Value*
Val".

+  auto* CVal = dyn_cast<ConstantInt>(Val);
+  if (CVal == nullptr)
+    return 0;
+  if (!CVal->getType()->isIntegerTy(8))
+    return 0;
+  const APInt & IVal = CVal->getUniqueInteger();
+  if (!IVal.isNegative())
+    return 0;
+  Value* Count = Call.getArgOperand(2);
+  auto* CCount = dyn_cast<ConstantInt>(Count);
+  if (CCount == nullptr)
+    return 0;
+  if (!CCount->getType()->isIntegerTy(32))
+    return 0;
+  if (ShowFixes) {
+    Call.print(errs());
+    errs() << "\n-->\n";
+  }
+  auto* Zero = ConstantInt::getSigned(CCount->getType(), 0);
+  Value* Add = BinaryOperator::Create(Instruction::BinaryOps::Add,
+                                      CCount, Zero);
+  auto *IAdd = dyn_cast<Instruction>(Add);
+  if (IAdd == nullptr)
+    return 0;
+  Call.setArgOperand(2, Add);
+  IAdd->insertBefore(&Call);
+  if (ShowFixes) {
+    IAdd->print(errs());
+    errs() << "\n";
+    Call.print(errs());
+    errs() << "\n\n";
+  }
+  return 1;
+}
+
+size_t fixCallsToMemset(Instruction &I) {
+  size_t Count = 0;
+  if (auto *Call = dyn_cast<CallInst>(&I)) {
+    if (Function *F = Call->getCalledFunction()) {
+      if ("llvm.memset.p0i8.i32" == F->getName()) {
+        Count += fixCallToMemset(*Call);
+      }
+    }
+  }
+  return Count;
+}
+
+size_t fixCallsToMemset(BasicBlock &B) {
+  size_t Count = 0;
+  for (auto &I : B) {
+    Count += fixCallsToMemset(I);
+  }
+  return Count;
+}
+
+size_t fixCallsToMemset(Function &F) {
+  size_t Count = 0;
+  for (auto &B : F) {
+    Count += fixCallsToMemset(B);
+  }
+  return Count;
+}
+
+size_t fixCallsToMemset(Module *M) {
+  size_t ErrorCount = 0;
+  for (auto &F : *M) {
+    if (!F.isDeclaration())
+      ErrorCount += fixCallsToMemset(F);
+  }
+  return ErrorCount;
+}
+
 } // end of anonymous namespace
 
 int main(int argc, char **argv) {
@@ -103,6 +184,11 @@ int main(int argc, char **argv) {
     return 1;
   }
 
+  size_t ErrorCount = fixCallsToMemset(M.get());
+  if (ErrorCount > 0) {
+    errs() << argv[0] << ": " << "Fixed " << ErrorCount << " calls to memset.\n";

[Jim Stichnoth, 2016/08/22 21:55:43]

80-col

[Jim Stichnoth, 2016/08/22 21:55:43]

... << ": Fixed " << ...
i.e. concatenate strings here

[Karl, 2016/08/23 15:17:31]

Done.

+  }
+
   WriteOutputFile(M.get());
   return 0;
 }