[IR] Reformulate LLVM's EH funclet IR

While we have successfully implemented a funclet-oriented EH scheme on
top of LLVM IR, our scheme has some notable deficiencies:
- catchendpad and cleanupendpad are necessary in the current design
  but they are difficult to explain to others, even to seasoned LLVM
  experts.
- catchendpad and cleanupendpad are optimization barriers.  They cannot
  be split and force all potentially throwing call-sites to be invokes.
  This has a noticable effect on the quality of our code generation.
- catchpad, while similar in some aspects to invoke, is fairly awkward.
  It is unsplittable, starts a funclet, and has control flow to other
  funclets.
- The nesting relationship between funclets is currently a property of
  control flow edges.  Because of this, we are forced to carefully
  analyze the flow graph to see if there might potentially exist illegal
  nesting among funclets.  While we have logic to clone funclets when
  they are illegally nested, it would be nicer if we had a
  representation which forbade them upfront.

Let's clean this up a bit by doing the following:
- Instead, make catchpad more like cleanuppad and landingpad: no control
  flow, just a bunch of simple operands;  catchpad would be splittable.
- Introduce catchswitch, a control flow instruction designed to model
  the constraints of funclet oriented EH.
- Make funclet scoping explicit by having funclet instructions consume
  the token produced by the funclet which contains them.
- Remove catchendpad and cleanupendpad.  Their presence can be inferred
  implicitly using coloring information.

N.B.  The state numbering code for the CLR has been updated but the
veracity of it's output cannot be spoken for.  An expert should take a
look to make sure the results are reasonable.

Reviewers: rnk, JosephTremoulet, andrew.w.kaylor

Differential Revision: http://reviews.llvm.org/D15139

llvm-svn: 255422

6 files changed, 80 insertions, 17 deletions

diff --git a/llvm/lib/Analysis/CaptureTracking.cpp b/llvm/lib/Analysis/CaptureTracking.cpp
index c717a8ee2e6..1add2fa7756 100644
--- a/llvm/lib/Analysis/CaptureTracking.cpp
+++ b/llvm/lib/Analysis/CaptureTracking.cpp
@@ -80,12 +80,11 @@ namespace {
       if (BB == BeforeHere->getParent()) {
         // 'I' dominates 'BeforeHere' => not safe to prune.
         //
-        // The value defined by an invoke/catchpad dominates an instruction only
+        // The value defined by an invoke dominates an instruction only
         // if it dominates every instruction in UseBB. A PHI is dominated only
         // if the instruction dominates every possible use in the UseBB. Since
         // UseBB == BB, avoid pruning.
-        if (isa<InvokeInst>(BeforeHere) || isa<CatchPadInst>(BeforeHere) ||
-            isa<PHINode>(I) || I == BeforeHere)
+        if (isa<InvokeInst>(BeforeHere) || isa<PHINode>(I) || I == BeforeHere)
           return false;
         if (!OrderedBB->dominates(BeforeHere, I))
           return false;
diff --git a/llvm/lib/Analysis/EHPersonalities.cpp b/llvm/lib/Analysis/EHPersonalities.cpp
index 1d1b5fe11f6..c95fcee13b8 100644
--- a/llvm/lib/Analysis/EHPersonalities.cpp
+++ b/llvm/lib/Analysis/EHPersonalities.cpp
@@ -9,7 +9,11 @@
 
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/ADT/StringSwitch.h"
+#include "llvm/IR/CFG.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/Support/Debug.h"
 using namespace llvm;
 
 /// See if the given exception handling personality function is one that we
@@ -39,3 +43,64 @@ bool llvm::canSimplifyInvokeNoUnwind(const Function *F) {
   // implies that the function does not throw synchronous exceptions.
   return !isAsynchronousEHPersonality(Personality);
 }
+
+DenseMap<BasicBlock *, ColorVector> llvm::colorEHFunclets(Function &F) {
+  SmallVector<std::pair<BasicBlock *, BasicBlock *>, 16> Worklist;
+  BasicBlock *EntryBlock = &F.getEntryBlock();
+  DenseMap<BasicBlock *, ColorVector> BlockColors;
+
+  // Build up the color map, which maps each block to its set of 'colors'.
+  // For any block B the "colors" of B are the set of funclets F (possibly
+  // including a root "funclet" representing the main function) such that
+  // F will need to directly contain B or a copy of B (where the term "directly
+  // contain" is used to distinguish from being "transitively contained" in
+  // a nested funclet).
+  //
+  // Note: Despite not being funclets in the truest sense, terminatepad and
+  // catchswitch are considered to belong to their own funclet for the purposes
+  // of coloring.
+
+  DEBUG_WITH_TYPE("winehprepare-coloring", dbgs() << "\nColoring funclets for "
+                                                  << F.getName() << "\n");
+
+  Worklist.push_back({EntryBlock, EntryBlock});
+
+  while (!Worklist.empty()) {
+    BasicBlock *Visiting;
+    BasicBlock *Color;
+    std::tie(Visiting, Color) = Worklist.pop_back_val();
+    DEBUG_WITH_TYPE("winehprepare-coloring",
+                    dbgs() << "Visiting " << Visiting->getName() << ", "
+                           << Color->getName() << "\n");
+    Instruction *VisitingHead = Visiting->getFirstNonPHI();
+    if (VisitingHead->isEHPad()) {
+      // Mark this funclet head as a member of itself.
+      Color = Visiting;
+    }
+    // Note that this is a member of the given color.
+    ColorVector &Colors = BlockColors[Visiting];
+    if (std::find(Colors.begin(), Colors.end(), Color) == Colors.end())
+      Colors.push_back(Color);
+    else
+      continue;
+
+    DEBUG_WITH_TYPE("winehprepare-coloring",
+                    dbgs() << "  Assigned color \'" << Color->getName()
+                           << "\' to block \'" << Visiting->getName()
+                           << "\'.\n");
+
+    BasicBlock *SuccColor = Color;
+    TerminatorInst *Terminator = Visiting->getTerminator();
+    if (auto *CatchRet = dyn_cast<CatchReturnInst>(Terminator)) {
+      Value *ParentPad = CatchRet->getParentPad();
+      if (isa<ConstantTokenNone>(ParentPad))
+        SuccColor = EntryBlock;
+      else
+        SuccColor = cast<Instruction>(ParentPad)->getParent();
+    }
+
+    for (BasicBlock *Succ : successors(Visiting))
+      Worklist.push_back({Succ, SuccColor});
+  }
+  return BlockColors;
+}
diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index 0bd18c1a35c..db17d886e4b 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -122,10 +122,10 @@ static bool ValueDominatesPHI(Value *V, PHINode *P, const DominatorTree *DT) {
     return DT->dominates(I, P);
   }
 
-  // Otherwise, if the instruction is in the entry block, and is not an invoke,
-  // and is not a catchpad, then it obviously dominates all phi nodes.
+  // Otherwise, if the instruction is in the entry block and is not an invoke,
+  // then it obviously dominates all phi nodes.
   if (I->getParent() == &I->getParent()->getParent()->getEntryBlock() &&
-      !isa<InvokeInst>(I) && !isa<CatchPadInst>(I))
+      !isa<InvokeInst>(I))
     return true;
 
   return false;
diff --git a/llvm/lib/Analysis/LoopInfo.cpp b/llvm/lib/Analysis/LoopInfo.cpp
index 67a82b192e5..07fd6a2ae70 100644
--- a/llvm/lib/Analysis/LoopInfo.cpp
+++ b/llvm/lib/Analysis/LoopInfo.cpp
@@ -227,9 +227,15 @@ bool Loop::isSafeToClone() const {
     if (isa<IndirectBrInst>((*I)->getTerminator()))
       return false;
 
-    if (const InvokeInst *II = dyn_cast<InvokeInst>((*I)->getTerminator()))
+    if (const InvokeInst *II = dyn_cast<InvokeInst>((*I)->getTerminator())) {
       if (II->cannotDuplicate())
         return false;
+      // Return false if any loop blocks contain invokes to EH-pads other than
+      // landingpads;  we don't know how to split those edges yet.
+      auto *FirstNonPHI = II->getUnwindDest()->getFirstNonPHI();
+      if (FirstNonPHI->isEHPad() && !isa<LandingPadInst>(FirstNonPHI))
+        return false;
+    }
 
     for (BasicBlock::iterator BI = (*I)->begin(), BE = (*I)->end(); BI != BE; ++BI) {
       if (const CallInst *CI = dyn_cast<CallInst>(BI)) {
diff --git a/llvm/lib/Analysis/ScalarEvolutionExpander.cpp b/llvm/lib/Analysis/ScalarEvolutionExpander.cpp
index abfcfbafb32..bcbf35b046b 100644
--- a/llvm/lib/Analysis/ScalarEvolutionExpander.cpp
+++ b/llvm/lib/Analysis/ScalarEvolutionExpander.cpp
@@ -91,22 +91,16 @@ static BasicBlock::iterator findInsertPointAfter(Instruction *I,
   BasicBlock::iterator IP = ++I->getIterator();
   if (auto *II = dyn_cast<InvokeInst>(I))
     IP = II->getNormalDest()->begin();
-  if (auto *CPI = dyn_cast<CatchPadInst>(I))
-    IP = CPI->getNormalDest()->begin();
 
   while (isa<PHINode>(IP))
     ++IP;
 
   while (IP->isEHPad()) {
-    if (isa<LandingPadInst>(IP) || isa<CleanupPadInst>(IP)) {
+    if (isa<FuncletPadInst>(IP) || isa<LandingPadInst>(IP)) {
       ++IP;
     } else if (auto *TPI = dyn_cast<TerminatePadInst>(IP)) {
       IP = TPI->getUnwindDest()->getFirstNonPHI()->getIterator();
-    } else if (auto *CEPI = dyn_cast<CatchEndPadInst>(IP)) {
-      IP = CEPI->getUnwindDest()->getFirstNonPHI()->getIterator();
-    } else if (auto *CEPI = dyn_cast<CleanupEndPadInst>(IP)) {
-      IP = CEPI->getUnwindDest()->getFirstNonPHI()->getIterator();
-    } else if (isa<CatchPadInst>(IP)) {
+    } else if (isa<CatchSwitchInst>(IP)) {
       IP = MustDominate->getFirstInsertionPt();
     } else {
       llvm_unreachable("unexpected eh pad!");
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index b2a1034eeaa..4a228c30a93 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -3431,11 +3431,10 @@ bool llvm::isSafeToSpeculativelyExecute(const Value *V,
   case Instruction::AtomicCmpXchg:
   case Instruction::LandingPad:
   case Instruction::Resume:
+  case Instruction::CatchSwitch:
   case Instruction::CatchPad:
-  case Instruction::CatchEndPad:
   case Instruction::CatchRet:
   case Instruction::CleanupPad:
-  case Instruction::CleanupEndPad:
   case Instruction::CleanupRet:
   case Instruction::TerminatePad:
     return false; // Misc instructions which have effects