IR: New representation for CFI and virtual call optimization pass metadata.

The bitset metadata currently used in LLVM has a few problems:

1. It has the wrong name. The name "bitset" refers to an implementation
   detail of one use of the metadata (i.e. its original use case, CFI).
   This makes it harder to understand, as the name makes no sense in the
   context of virtual call optimization.

2. It is represented using a global named metadata node, rather than
   being directly associated with a global. This makes it harder to
   manipulate the metadata when rebuilding global variables, summarise it
   as part of ThinLTO and drop unused metadata when associated globals are
   dropped. For this reason, CFI does not currently work correctly when
   both CFI and vcall opt are enabled, as vcall opt needs to rebuild vtable
   globals, and fails to associate metadata with the rebuilt globals. As I
   understand it, the same problem could also affect ASan, which rebuilds
   globals with a red zone.

This patch solves both of those problems in the following way:

1. Rename the metadata to "type metadata". This new name reflects how
   the metadata is currently being used (i.e. to represent type information
   for CFI and vtable opt). The new name is reflected in the name for the
   associated intrinsic (llvm.type.test) and pass (LowerTypeTests).

2. Attach metadata directly to the globals that it pertains to, rather
   than using the "llvm.bitsets" global metadata node as we are doing now.
   This is done using the newly introduced capability to attach
   metadata to global variables (r271348 and r271358).

See also: http://lists.llvm.org/pipermail/llvm-dev/2016-June/100462.html

Differential Revision: http://reviews.llvm.org/D21053

llvm-svn: 273729

1 files changed, 24 insertions, 27 deletions

diff --git a/llvm/lib/Transforms/IPO/CrossDSOCFI.cpp b/llvm/lib/Transforms/IPO/CrossDSOCFI.cpp
index 4c62cbe2da5..99d58333954 100644
--- a/llvm/lib/Transforms/IPO/CrossDSOCFI.cpp
+++ b/llvm/lib/Transforms/IPO/CrossDSOCFI.cpp
@@ -36,7 +36,7 @@ using namespace llvm;
 
 #define DEBUG_TYPE "cross-dso-cfi"
 
-STATISTIC(TypeIds, "Number of unique type identifiers");
+STATISTIC(NumTypeIds, "Number of unique type identifiers");
 
 namespace {
 
@@ -49,7 +49,7 @@ struct CrossDSOCFI : public ModulePass {
   Module *M;
   MDNode *VeryLikelyWeights;
 
-  ConstantInt *extractBitSetTypeId(MDNode *MD);
+  ConstantInt *extractNumericTypeId(MDNode *MD);
   void buildCFICheck();
 
   bool doInitialization(Module &M) override;
@@ -73,10 +73,10 @@ bool CrossDSOCFI::doInitialization(Module &Mod) {
   return false;
 }
 
-/// extractBitSetTypeId - Extracts TypeId from a hash-based bitset MDNode.
-ConstantInt *CrossDSOCFI::extractBitSetTypeId(MDNode *MD) {
+/// Extracts a numeric type identifier from an MDNode containing type metadata.
+ConstantInt *CrossDSOCFI::extractNumericTypeId(MDNode *MD) {
   // This check excludes vtables for classes inside anonymous namespaces.
-  auto TM = dyn_cast<ValueAsMetadata>(MD->getOperand(0));
+  auto TM = dyn_cast<ValueAsMetadata>(MD->getOperand(1));
   if (!TM)
     return nullptr;
   auto C = dyn_cast_or_null<ConstantInt>(TM->getValue());
@@ -84,29 +84,27 @@ ConstantInt *CrossDSOCFI::extractBitSetTypeId(MDNode *MD) {
   // We are looking for i64 constants.
   if (C->getBitWidth() != 64) return nullptr;
 
-  // Sanity check.
-  auto FM = dyn_cast_or_null<ValueAsMetadata>(MD->getOperand(1));
-  // Can be null if a function was removed by an optimization.
-  if (FM) {
-    auto F = dyn_cast<Function>(FM->getValue());
-    // But can never be a function declaration.
-    assert(!F || !F->isDeclaration());
-    (void)F; // Suppress unused variable warning in the no-asserts build.
-  }
   return C;
 }
 
 /// buildCFICheck - emits __cfi_check for the current module.
 void CrossDSOCFI::buildCFICheck() {
   // FIXME: verify that __cfi_check ends up near the end of the code section,
-  // but before the jump slots created in LowerBitSets.
-  llvm::DenseSet<uint64_t> BitSetIds;
-  NamedMDNode *BitSetNM = M->getNamedMetadata("llvm.bitsets");
-
-  if (BitSetNM)
-    for (unsigned I = 0, E = BitSetNM->getNumOperands(); I != E; ++I)
-      if (ConstantInt *TypeId = extractBitSetTypeId(BitSetNM->getOperand(I)))
-        BitSetIds.insert(TypeId->getZExtValue());
+  // but before the jump slots created in LowerTypeTests.
+  llvm::DenseSet<uint64_t> TypeIds;
+  SmallVector<MDNode *, 2> Types;
+  for (GlobalObject &GO : M->global_objects()) {
+    Types.clear();
+    GO.getMetadata(LLVMContext::MD_type, Types);
+    for (MDNode *Type : Types) {
+      // Sanity check. GO must not be a function declaration.
+      auto F = dyn_cast<Function>(&GO);
+      assert(!F || !F->isDeclaration());
+
+      if (ConstantInt *TypeId = extractNumericTypeId(Type))
+        TypeIds.insert(TypeId->getZExtValue());
+    }
+  }
 
   LLVMContext &Ctx = M->getContext();
   Constant *C = M->getOrInsertFunction(
@@ -138,13 +136,12 @@ void CrossDSOCFI::buildCFICheck() {
   IRBExit.CreateRetVoid();
 
   IRBuilder<> IRB(BB);
-  SwitchInst *SI = IRB.CreateSwitch(&CallSiteTypeId, TrapBB, BitSetIds.size());
-  for (uint64_t TypeId : BitSetIds) {
+  SwitchInst *SI = IRB.CreateSwitch(&CallSiteTypeId, TrapBB, TypeIds.size());
+  for (uint64_t TypeId : TypeIds) {
     ConstantInt *CaseTypeId = ConstantInt::get(Type::getInt64Ty(Ctx), TypeId);
     BasicBlock *TestBB = BasicBlock::Create(Ctx, "test", F);
     IRBuilder<> IRBTest(TestBB);
-    Function *BitsetTestFn =
-        Intrinsic::getDeclaration(M, Intrinsic::bitset_test);
+    Function *BitsetTestFn = Intrinsic::getDeclaration(M, Intrinsic::type_test);
 
     Value *Test = IRBTest.CreateCall(
         BitsetTestFn, {&Addr, MetadataAsValue::get(
@@ -153,7 +150,7 @@ void CrossDSOCFI::buildCFICheck() {
     BI->setMetadata(LLVMContext::MD_prof, VeryLikelyWeights);
 
     SI->addCase(CaseTypeId, TestBB);
-    ++TypeIds;
+    ++NumTypeIds;
   }
 }