Add helper functions in Statepoint.h to handle invoke statepoints.

[igor-laevsky]

Summary

This patch adds invoke related functionality into StatepointSite classes. Uses of it will follow up in the next few patches shortly.

[reames]

Some style cleanup needed. Comments inline.

include/llvm/IR/Statepoint.h

32

If we have the versions that take Value's, why do we need versions which take Instructions? Shouldn't the later match the former?

202

Doxygen comment please

218

Add a comment here. This combines both call statepoints and the normal path of invokes right?

272

Make this an early return to reduce indentation.

273

LandingPad please

[igor-laevsky]

Ping?

include/llvm/IR/Statepoint.h

32

Because in case if we will pass Instruction* it will be converted into ImmutableCallSite instead of the Value*. Anyway on a second thought I figured out nicer way to express this in the code - check updated diff.

[reames]

LGTM, I assume you'd like me to commit on your behalf? If so, I'll do so in the morning.

[igor-laevsky]

Yes, please commit on my behalf.

include/llvm/IR/Statepoint.h

 #include "llvm/ADT/iterator_range.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/Support/Compiler.h"
 
 namespace llvm {
 
+class GCRelocateOperands;
+class ImmutableStatepoint;
+
 bool isStatepoint(const ImmutableCallSite &CS);
 bool isStatepoint(const Instruction *inst);
 bool isStatepoint(const Instruction &inst);
+bool isStatepoint(const Value *inst);
+bool isStatepoint(const Value &inst);
 
+bool isGCRelocate(const Value *inst);
 bool isGCRelocate(const Instruction *inst);
 bool isGCRelocate(const ImmutableCallSite &CS);
 
+bool isGCResult(const Value *inst);
 bool isGCResult(const Instruction *inst);
 bool isGCResult(const ImmutableCallSite &CS);
 
 /// Analogous to CallSiteBase, this provides most of the actual
 /// functionality for Statepoint and ImmutableStatepoint.  It is
 /// templatized to allow easily specializing of const and non-const
 /// concrete subtypes.  This is structured analogous to CallSite
 /// rather than the IntrinsicInst.h helpers since we want to support
typename CallSiteTy::arg_iterator gc_args_end() {
     return StatepointCS.arg_end();
   }
 
   /// range adapter for gc arguments
   iterator_range<arg_iterator> gc_args() {
     return iterator_range<arg_iterator>(gc_args_begin(), gc_args_end());
   }
 
+  /// Get list of all gc reloactes linked to this statepoint
+  /// May contain several relocations for the same base/derived pair.
+  /// For example this could happen due to relocations on exceptional
+  /// path of invoke.
+  std::vector<GCRelocateOperands> getRelocates(ImmutableStatepoint &IS);
 
 #ifndef NDEBUG
   /// Asserts if this statepoint is malformed.  Common cases for failure
   /// include incorrect length prefixes for variable length sections or
   /// illegal values for parameters.
   void verify() {
     assert(numCallArgs() >= 0 &&
            "number of arguments to actually callee can't be negative");
public:
   }
   GCRelocateOperands(const Instruction *inst) : RelocateCS(inst) {
     assert(isGCRelocate(inst));
   }
   GCRelocateOperands(CallSite CS) : RelocateCS(CS) {
     assert(isGCRelocate(CS));
   }
 
+  bool isTiedToInvoke() const {
+    const Value *Token = RelocateCS.getArgument(0);
+
+    return isa<ExtractValueInst>(Token) ||
+      isa<InvokeInst>(Token);
+  }
+
+  /// Get enclosed relocate intrinsic
+  ImmutableCallSite getUnderlyingCallSite() {
+    return RelocateCS;
+  }
+
   /// The statepoint with which this gc.relocate is associated.
   const Instruction *statepoint() {
-    return cast<Instruction>(RelocateCS.getArgument(0));
+    const Value *token = RelocateCS.getArgument(0);
+
+    if (!isa<ExtractValueInst>(token)) {
+      return cast<Instruction>(token);
+    }
+
+    // This relocate is on exceptional path of an invoke statepoint
+    const BasicBlock *invokeBB =
+      cast<Instruction>(token)->getParent()->getUniquePredecessor();
+
+    assert(invokeBB && "safepoints should have unique landingpads");
+    assert(invokeBB->getTerminator() && "safepoint block should be well formed");
+    assert(isStatepoint(invokeBB->getTerminator()));
+
+    return invokeBB->getTerminator();
   }
   /// The index into the associate statepoint's argument list
   /// which contains the base pointer of the pointer whose
   /// relocation this gc.relocate describes.
   unsigned basePtrIndex() {
     return cast<ConstantInt>(RelocateCS.getArgument(1))->getZExtValue();
   }
   /// The index into the associate statepoint's argument list which
   /// contains the pointer whose relocation this gc.relocate describes.
   unsigned derivedPtrIndex() {
     return cast<ConstantInt>(RelocateCS.getArgument(2))->getZExtValue();
   }
   Value *basePtr() {
     ImmutableCallSite CS(statepoint());
     return *(CS.arg_begin() + basePtrIndex());
   }
   Value *derivedPtr() {
     ImmutableCallSite CS(statepoint());
     return *(CS.arg_begin() + derivedPtrIndex());
   }
 };
+
+template <typename InstructionTy, typename ValueTy, typename CallSiteTy>
+std::vector<GCRelocateOperands>
+  StatepointBase<InstructionTy, ValueTy, CallSiteTy>::
+    getRelocates(ImmutableStatepoint &IS) {
+
+  std::vector<GCRelocateOperands> res;
+
+  ImmutableCallSite StatepointCS = IS.getCallSite();
+
+  // Search for relocated pointers.  Note that working backwards from the
+  // gc_relocates ensures that we only get pairs which are actually relocated
+  // and used after the statepoint.
+  for (const User *U : StatepointCS.getInstruction()->users()) {
+    if (isGCRelocate(U)) {
+      res.push_back(GCRelocateOperands(U));
+    }
+  }
+
+  // Scan thorough exceptional relocations if it is invoke statepoint
+  if (StatepointCS.isInvoke()) {
+    LandingPadInst *landingpad =
+      cast<InvokeInst>(StatepointCS.getInstruction())->getLandingPadInst();
+
+    // Search for extract value from landingpad instruction to which
+    // gc relocates will be attached
+    for (const User *landingpadUser : landingpad->users()) {
+      if (!isa<ExtractValueInst>(landingpadUser)) {
+        continue;
+      }
+
+      // gc relocates should be attached to this extract value
+      for (const User *U : landingpadUser->users()) {
+        if (isGCRelocate(U)) {
+          res.push_back(GCRelocateOperands(U));
+        }
+      }
+    }
+  }
+  return res;
+}
+
 }
 #endif

lib/IR/Statepoint.cpp

 
 using namespace std;
 using namespace llvm;
 
 bool llvm::isStatepoint(const ImmutableCallSite &CS) {
   const Function *F = CS.getCalledFunction();
   return (F && F->getIntrinsicID() == Intrinsic::experimental_gc_statepoint);
 }
-bool llvm::isStatepoint(const Instruction *inst) {
+bool llvm::isStatepoint(const Value *inst) {
   if (isa<InvokeInst>(inst) || isa<CallInst>(inst)) {
     ImmutableCallSite CS(inst);
     return isStatepoint(CS);
   }
   return false;
 }
-bool llvm::isStatepoint(const Instruction &inst) {
+bool llvm::isStatepoint(const Value &inst) {
   return isStatepoint(&inst);
 }
+bool llvm::isStatepoint(const Instruction *inst) {
+  return isStatepoint(static_cast<const Value*>(inst));
+}
+bool llvm::isStatepoint(const Instruction &inst) {
+  return isStatepoint(static_cast<const Value*>(&inst));
+}
 
 bool llvm::isGCRelocate(const ImmutableCallSite &CS) {
   return isGCRelocate(CS.getInstruction());
 }
-bool llvm::isGCRelocate(const Instruction *inst) {
+bool llvm::isGCRelocate(const Value *inst) {
   if (const CallInst *call = dyn_cast<CallInst>(inst)) {
     if (const Function *F = call->getCalledFunction()) {
       return F->getIntrinsicID() == Intrinsic::experimental_gc_relocate;
     }
   }
   return false;
 }
+bool llvm::isGCRelocate(const Instruction *inst) {
+  return isGCRelocate(static_cast<const Value*>(inst));
+}
 
 bool llvm::isGCResult(const ImmutableCallSite &CS) {
   return isGCResult(CS.getInstruction());
 }
-bool llvm::isGCResult(const Instruction *inst) {
+bool llvm::isGCResult(const Value *inst) {
   if (const CallInst *call = dyn_cast<CallInst>(inst)) {
     if (Function *F = call->getCalledFunction()) {
       return (F->getIntrinsicID() == Intrinsic::experimental_gc_result_int ||
               F->getIntrinsicID() == Intrinsic::experimental_gc_result_float ||
               F->getIntrinsicID() == Intrinsic::experimental_gc_result_ptr ||
               F->getIntrinsicID() == Intrinsic::experimental_gc_result);
     }
   }
   return false;
 }
+bool llvm::isGCResult(const Instruction *inst) {
+  return isGCResult(static_cast<const Value*>(inst));
+}