Prologue support

Patch by Ben Gamari!

This redefines the `prefix` attribute introduced previously and
introduces a `prologue` attribute.  There are a two primary usecases
that these attributes aim to serve,

  1. Function prologue sigils

  2. Function hot-patching: Enable the user to insert `nop` operations
     at the beginning of the function which can later be safely replaced
     with a call to some instrumentation facility

  3. Runtime metadata: Allow a compiler to insert data for use by the
     runtime during execution. GHC is one example of a compiler that
     needs this functionality for its tables-next-to-code functionality.

Previously `prefix` served cases (1) and (2) quite well by allowing the user
to introduce arbitrary data at the entrypoint but before the function
body. Case (3), however, was poorly handled by this approach as it
required that prefix data was valid executable code.

Here we redefine the notion of prefix data to instead be data which
occurs immediately before the function entrypoint (i.e. the symbol
address). Since prefix data now occurs before the function entrypoint,
there is no need for the data to be valid code.

The previous notion of prefix data now goes under the name "prologue
data" to emphasize its duality with the function epilogue.

The intention here is to handle cases (1) and (2) with prologue data and
case (3) with prefix data.

References
----------

This idea arose out of discussions[1] with Reid Kleckner in response to a
proposal to introduce the notion of symbol offsets to enable handling of
case (3).

[1] http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-May/073235.html

Test Plan: testsuite

Differential Revision: http://reviews.llvm.org/D6454

llvm-svn: 223189

4 files changed, 57 insertions, 4 deletions

diff --git a/llvm/lib/IR/AsmWriter.cpp b/llvm/lib/IR/AsmWriter.cpp
index e461187a0c6..4af03465f41 100644
--- a/llvm/lib/IR/AsmWriter.cpp
+++ b/llvm/lib/IR/AsmWriter.cpp
@@ -101,6 +101,11 @@ static OrderMap orderModule(const Module *M) {
     if (F.hasPrefixData())
       if (!isa<GlobalValue>(F.getPrefixData()))
         orderValue(F.getPrefixData(), OM);
+
+    if (F.hasPrologueData())
+      if (!isa<GlobalValue>(F.getPrologueData()))
+        orderValue(F.getPrologueData(), OM);
+
     orderValue(&F, OM);
 
     if (F.isDeclaration())
@@ -1902,6 +1907,11 @@ void AssemblyWriter::printFunction(const Function *F) {
     Out << " prefix ";
     writeOperand(F->getPrefixData(), true);
   }
+  if (F->hasPrologueData()) {
+    Out << " prologue ";
+    writeOperand(F->getPrologueData(), true);
+  }
+
   if (F->isDeclaration()) {
     Out << '\n';
   } else {
diff --git a/llvm/lib/IR/Function.cpp b/llvm/lib/IR/Function.cpp
index b53f6f314ee..c7d3d149e0c 100644
--- a/llvm/lib/IR/Function.cpp
+++ b/llvm/lib/IR/Function.cpp
@@ -298,7 +298,7 @@ void Function::BuildLazyArguments() const {
 
   // Clear the lazy arguments bit.
   unsigned SDC = getSubclassDataFromValue();
-  const_cast<Function*>(this)->setValueSubclassData(SDC &= ~1);
+  const_cast<Function*>(this)->setValueSubclassData(SDC &= ~(1<<0));
 }
 
 size_t Function::arg_size() const {
@@ -335,8 +335,9 @@ void Function::dropAllReferences() {
   while (!BasicBlocks.empty())
     BasicBlocks.begin()->eraseFromParent();
 
-  // Prefix data is stored in a side table.
+  // Prefix and prologue data are stored in a side table.
   setPrefixData(nullptr);
+  setPrologueData(nullptr);
 }
 
 void Function::addAttribute(unsigned i, Attribute::AttrKind attr) {
@@ -416,6 +417,10 @@ void Function::copyAttributesFrom(const GlobalValue *Src) {
     setPrefixData(SrcF->getPrefixData());
   else
     setPrefixData(nullptr);
+  if (SrcF->hasPrologueData())
+    setPrologueData(SrcF->getPrologueData());
+  else
+    setPrologueData(nullptr);
 }
 
 /// getIntrinsicID - This method returns the ID number of the specified
@@ -880,11 +885,40 @@ void Function::setPrefixData(Constant *PrefixData) {
       PDHolder->setOperand(0, PrefixData);
     else
       PDHolder = ReturnInst::Create(getContext(), PrefixData);
-    SCData |= 2;
+    SCData |= (1<<1);
   } else {
     delete PDHolder;
     PDMap.erase(this);
-    SCData &= ~2;
+    SCData &= ~(1<<1);
   }
   setValueSubclassData(SCData);
 }
+
+Constant *Function::getPrologueData() const {
+  assert(hasPrologueData());
+  const LLVMContextImpl::PrologueDataMapTy &SOMap =
+      getContext().pImpl->PrologueDataMap;
+  assert(SOMap.find(this) != SOMap.end());
+  return cast<Constant>(SOMap.find(this)->second->getReturnValue());
+}
+
+void Function::setPrologueData(Constant *PrologueData) {
+  if (!PrologueData && !hasPrologueData())
+    return;
+
+  unsigned PDData = getSubclassDataFromValue();
+  LLVMContextImpl::PrologueDataMapTy &PDMap = getContext().pImpl->PrologueDataMap;
+  ReturnInst *&PDHolder = PDMap[this];
+  if (PrologueData) {
+    if (PDHolder)
+      PDHolder->setOperand(0, PrologueData);
+    else
+      PDHolder = ReturnInst::Create(getContext(), PrologueData);
+    PDData |= (1<<2);
+  } else {
+    delete PDHolder;
+    PDMap.erase(this);
+    PDData &= ~(1<<2);
+  }
+  setValueSubclassData(PDData);
+}
diff --git a/llvm/lib/IR/LLVMContextImpl.h b/llvm/lib/IR/LLVMContextImpl.h
index 7a298cfecf3..5fd8683ccaf 100644
--- a/llvm/lib/IR/LLVMContextImpl.h
+++ b/llvm/lib/IR/LLVMContextImpl.h
@@ -401,6 +401,12 @@ public:
   typedef DenseMap<const Function *, ReturnInst *> PrefixDataMapTy;
   PrefixDataMapTy PrefixDataMap;
 
+  /// \brief Mapping from a function to its prologue data, which is stored as
+  /// the operand of an unparented ReturnInst so that the prologue data has a
+  /// Use.
+  typedef DenseMap<const Function *, ReturnInst *> PrologueDataMapTy;
+  PrologueDataMapTy PrologueDataMap;
+
   int getOrAddScopeRecordIdxEntry(MDNode *N, int ExistingIdx);
   int getOrAddScopeInlinedAtIdxEntry(MDNode *Scope, MDNode *IA,int ExistingIdx);
   
diff --git a/llvm/lib/IR/TypeFinder.cpp b/llvm/lib/IR/TypeFinder.cpp
index 6796075bfc2..7e92818db5e 100644
--- a/llvm/lib/IR/TypeFinder.cpp
+++ b/llvm/lib/IR/TypeFinder.cpp
@@ -47,6 +47,9 @@ void TypeFinder::run(const Module &M, bool onlyNamed) {
     if (FI->hasPrefixData())
       incorporateValue(FI->getPrefixData());
 
+    if (FI->hasPrologueData())
+      incorporateValue(FI->getPrologueData());
+
     // First incorporate the arguments.
     for (Function::const_arg_iterator AI = FI->arg_begin(),
            AE = FI->arg_end(); AI != AE; ++AI)