Merge llvm trunk r238337 from ^/vendor/llvm/dist, resolve conflicts, and

preserve our customizations, where necessary.

1 files changed, 158 insertions, 49 deletions

diff --git a/contrib/llvm/lib/CodeGen/PrologEpilogInserter.cpp b/contrib/llvm/lib/CodeGen/PrologEpilogInserter.cpp
index 61407fa..76583f0 100644
--- a/contrib/llvm/lib/CodeGen/PrologEpilogInserter.cpp
+++ b/contrib/llvm/lib/CodeGen/PrologEpilogInserter.cpp
@@ -16,7 +16,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "PrologEpilogInserter.h"
 #include "llvm/ADT/IndexedMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
@@ -28,8 +27,10 @@
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
 #include "llvm/CodeGen/StackProtector.h"
+#include "llvm/CodeGen/WinEHFuncInfo.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/InlineAsm.h"
 #include "llvm/IR/LLVMContext.h"
@@ -48,6 +49,53 @@ using namespace llvm;
 
 #define DEBUG_TYPE "pei"
 
+namespace {
+class PEI : public MachineFunctionPass {
+public:
+  static char ID;
+  PEI() : MachineFunctionPass(ID) {
+    initializePEIPass(*PassRegistry::getPassRegistry());
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+
+  /// runOnMachineFunction - Insert prolog/epilog code and replace abstract
+  /// frame indexes with appropriate references.
+  ///
+  bool runOnMachineFunction(MachineFunction &Fn) override;
+
+private:
+  RegScavenger *RS;
+
+  // MinCSFrameIndex, MaxCSFrameIndex - Keeps the range of callee saved
+  // stack frame indexes.
+  unsigned MinCSFrameIndex, MaxCSFrameIndex;
+
+  // Save and Restore blocks of the current function.
+  MachineBasicBlock *SaveBlock;
+  SmallVector<MachineBasicBlock *, 4> RestoreBlocks;
+
+  // Flag to control whether to use the register scavenger to resolve
+  // frame index materialization registers. Set according to
+  // TRI->requiresFrameIndexScavenging() for the current function.
+  bool FrameIndexVirtualScavenging;
+
+  void calculateSets(MachineFunction &Fn);
+  void calculateCallsInformation(MachineFunction &Fn);
+  void calculateCalleeSavedRegisters(MachineFunction &Fn);
+  void insertCSRSpillsAndRestores(MachineFunction &Fn);
+  void calculateFrameObjectOffsets(MachineFunction &Fn);
+  void replaceFrameIndices(MachineFunction &Fn);
+  void replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn,
+                           int &SPAdj);
+  void scavengeFrameVirtualRegs(MachineFunction &Fn);
+  void insertPrologEpilogCode(MachineFunction &Fn);
+
+  // Convenience for recognizing return blocks.
+  bool isReturnBlock(MachineBasicBlock *MBB);
+};
+} // namespace
+
 char PEI::ID = 0;
 char &llvm::PrologEpilogCodeInserterID = PEI::ID;
 
@@ -85,20 +133,26 @@ bool PEI::isReturnBlock(MachineBasicBlock* MBB) {
 
 /// Compute the set of return blocks
 void PEI::calculateSets(MachineFunction &Fn) {
-  // Sets used to compute spill, restore placement sets.
-  const std::vector<CalleeSavedInfo> &CSI =
-    Fn.getFrameInfo()->getCalleeSavedInfo();
+  const MachineFrameInfo *MFI = Fn.getFrameInfo();
 
-  // If no CSRs used, we are done.
-  if (CSI.empty())
+  // Even when we do not change any CSR, we still want to insert the
+  // prologue and epilogue of the function.
+  // So set the save points for those.
+
+  // Use the points found by shrink-wrapping, if any.
+  if (MFI->getSavePoint()) {
+    SaveBlock = MFI->getSavePoint();
+    assert(MFI->getRestorePoint() && "Both restore and save must be set");
+    RestoreBlocks.push_back(MFI->getRestorePoint());
     return;
+  }
 
   // Save refs to entry and return blocks.
-  EntryBlock = Fn.begin();
+  SaveBlock = Fn.begin();
   for (MachineFunction::iterator MBB = Fn.begin(), E = Fn.end();
        MBB != E; ++MBB)
     if (isReturnBlock(MBB))
-      ReturnBlocks.push_back(MBB);
+      RestoreBlocks.push_back(MBB);
 
   return;
 }
@@ -178,7 +232,7 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) {
   }
 
   delete RS;
-  ReturnBlocks.clear();
+  RestoreBlocks.clear();
   return true;
 }
 
@@ -194,12 +248,12 @@ void PEI::calculateCallsInformation(MachineFunction &Fn) {
   bool AdjustsStack = MFI->adjustsStack();
 
   // Get the function call frame set-up and tear-down instruction opcode
-  int FrameSetupOpcode   = TII.getCallFrameSetupOpcode();
-  int FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();
+  unsigned FrameSetupOpcode = TII.getCallFrameSetupOpcode();
+  unsigned FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();
 
   // Early exit for targets which have no call frame setup/destroy pseudo
   // instructions.
-  if (FrameSetupOpcode == -1 && FrameDestroyOpcode == -1)
+  if (FrameSetupOpcode == ~0u && FrameDestroyOpcode == ~0u)
     return;
 
   std::vector<MachineBasicBlock::iterator> FrameSDOps;
@@ -324,6 +378,61 @@ void PEI::calculateCalleeSavedRegisters(MachineFunction &F) {
   MFI->setCalleeSavedInfo(CSI);
 }
 
+/// Helper function to update the liveness information for the callee-saved
+/// registers.
+static void updateLiveness(MachineFunction &MF) {
+  MachineFrameInfo *MFI = MF.getFrameInfo();
+  // Visited will contain all the basic blocks that are in the region
+  // where the callee saved registers are alive:
+  // - Anything that is not Save or Restore -> LiveThrough.
+  // - Save -> LiveIn.
+  // - Restore -> LiveOut.
+  // The live-out is not attached to the block, so no need to keep
+  // Restore in this set.
+  SmallPtrSet<MachineBasicBlock *, 8> Visited;
+  SmallVector<MachineBasicBlock *, 8> WorkList;
+  MachineBasicBlock *Entry = &MF.front();
+  MachineBasicBlock *Save = MFI->getSavePoint();
+
+  if (!Save)
+    Save = Entry;
+
+  if (Entry != Save) {
+    WorkList.push_back(Entry);
+    Visited.insert(Entry);
+  }
+  Visited.insert(Save);
+
+  MachineBasicBlock *Restore = MFI->getRestorePoint();
+  if (Restore)
+    // By construction Restore cannot be visited, otherwise it
+    // means there exists a path to Restore that does not go
+    // through Save.
+    WorkList.push_back(Restore);
+
+  while (!WorkList.empty()) {
+    const MachineBasicBlock *CurBB = WorkList.pop_back_val();
+    // By construction, the region that is after the save point is
+    // dominated by the Save and post-dominated by the Restore.
+    if (CurBB == Save)
+      continue;
+    // Enqueue all the successors not already visited.
+    // Those are by construction either before Save or after Restore.
+    for (MachineBasicBlock *SuccBB : CurBB->successors())
+      if (Visited.insert(SuccBB).second)
+        WorkList.push_back(SuccBB);
+  }
+
+  const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
+
+  for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
+    for (MachineBasicBlock *MBB : Visited)
+      // Add the callee-saved register as live-in.
+      // It's killed at the spill.
+      MBB->addLiveIn(CSI[i].getReg());
+  }
+}
+
 /// insertCSRSpillsAndRestores - Insert spill and restore code for
 /// callee saved registers used in the function.
 ///
@@ -344,26 +453,22 @@ void PEI::insertCSRSpillsAndRestores(MachineFunction &Fn) {
   MachineBasicBlock::iterator I;
 
   // Spill using target interface.
-  I = EntryBlock->begin();
-  if (!TFI->spillCalleeSavedRegisters(*EntryBlock, I, CSI, TRI)) {
+  I = SaveBlock->begin();
+  if (!TFI->spillCalleeSavedRegisters(*SaveBlock, I, CSI, TRI)) {
     for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
-      // Add the callee-saved register as live-in.
-      // It's killed at the spill.
-      EntryBlock->addLiveIn(CSI[i].getReg());
-
       // Insert the spill to the stack frame.
       unsigned Reg = CSI[i].getReg();
       const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
-      TII.storeRegToStackSlot(*EntryBlock, I, Reg, true, CSI[i].getFrameIdx(),
+      TII.storeRegToStackSlot(*SaveBlock, I, Reg, true, CSI[i].getFrameIdx(),
                               RC, TRI);
     }
   }
+  // Update the live-in information of all the blocks up to the save point.
+  updateLiveness(Fn);
 
   // Restore using target interface.
-  for (unsigned ri = 0, re = ReturnBlocks.size(); ri != re; ++ri) {
-    MachineBasicBlock *MBB = ReturnBlocks[ri];
+  for (MachineBasicBlock *MBB : RestoreBlocks) {
     I = MBB->end();
-    --I;
 
     // Skip over all terminator instructions, which are part of the return
     // sequence.
@@ -495,7 +600,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
 
       unsigned Align = MFI->getObjectAlignment(i);
       // Adjust to alignment boundary
-      Offset = (Offset+Align-1)/Align*Align;
+      Offset = RoundUpToAlignment(Offset, Align);
 
       MFI->setObjectOffset(i, -Offset);        // Set the computed offset
     }
@@ -504,7 +609,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
     for (int i = MaxCSFI; i >= MinCSFI ; --i) {
       unsigned Align = MFI->getObjectAlignment(i);
       // Adjust to alignment boundary
-      Offset = (Offset+Align-1)/Align*Align;
+      Offset = RoundUpToAlignment(Offset, Align);
 
       MFI->setObjectOffset(i, Offset);
       Offset += MFI->getObjectSize(i);
@@ -537,7 +642,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
     unsigned Align = MFI->getLocalFrameMaxAlign();
 
     // Adjust to alignment boundary.
-    Offset = (Offset + Align - 1) / Align * Align;
+    Offset = RoundUpToAlignment(Offset, Align);
 
     DEBUG(dbgs() << "Local frame base offset: " << Offset << "\n");
 
@@ -656,8 +761,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) {
     // If the frame pointer is eliminated, all frame offsets will be relative to
     // SP not FP. Align to MaxAlign so this works.
     StackAlign = std::max(StackAlign, MaxAlign);
-    unsigned AlignMask = StackAlign - 1;
-    Offset = (Offset + AlignMask) & ~uint64_t(AlignMask);
+    Offset = RoundUpToAlignment(Offset, StackAlign);
   }
 
   // Update frame info to pretend that this is part of the stack...
@@ -674,21 +778,18 @@ void PEI::insertPrologEpilogCode(MachineFunction &Fn) {
   const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering();
 
   // Add prologue to the function...
-  TFI.emitPrologue(Fn);
+  TFI.emitPrologue(Fn, *SaveBlock);
 
-  // Add epilogue to restore the callee-save registers in each exiting block
-  for (MachineFunction::iterator I = Fn.begin(), E = Fn.end(); I != E; ++I) {
-    // If last instruction is a return instruction, add an epilogue
-    if (!I->empty() && I->back().isReturn())
-      TFI.emitEpilogue(Fn, *I);
-  }
+  // Add epilogue to restore the callee-save registers in each exiting block.
+  for (MachineBasicBlock *RestoreBlock : RestoreBlocks)
+    TFI.emitEpilogue(Fn, *RestoreBlock);
 
   // Emit additional code that is required to support segmented stacks, if
   // we've been asked for it.  This, when linked with a runtime with support
   // for segmented stacks (libgcc is one), will result in allocating stack
   // space in small chunks instead of one large contiguous block.
   if (Fn.shouldSplitStack())
-    TFI.adjustForSegmentedStacks(Fn);
+    TFI.adjustForSegmentedStacks(Fn, *SaveBlock);
 
   // Emit additional code that is required to explicitly handle the stack in
   // HiPE native code (if needed) when loaded in the Erlang/OTP runtime. The
@@ -696,7 +797,7 @@ void PEI::insertPrologEpilogCode(MachineFunction &Fn) {
   // different conditional check and another BIF for allocating more stack
   // space.
   if (Fn.getFunction()->getCallingConv() == CallingConv::HiPE)
-    TFI.adjustForHiPEPrologue(Fn);
+    TFI.adjustForHiPEPrologue(Fn, *SaveBlock);
 }
 
 /// replaceFrameIndices - Replace all MO_FrameIndex operands with physical
@@ -706,6 +807,25 @@ void PEI::replaceFrameIndices(MachineFunction &Fn) {
   const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering();
   if (!TFI.needsFrameIndexResolution(Fn)) return;
 
+  MachineModuleInfo &MMI = Fn.getMMI();
+  const Function *F = Fn.getFunction();
+  const Function *ParentF = MMI.getWinEHParent(F);
+  unsigned FrameReg;
+  if (F == ParentF) {
+    WinEHFuncInfo &FuncInfo = MMI.getWinEHFuncInfo(Fn.getFunction());
+    // FIXME: This should be unconditional but we have bugs in the preparation
+    // pass.
+    if (FuncInfo.UnwindHelpFrameIdx != INT_MAX)
+      FuncInfo.UnwindHelpFrameOffset = TFI.getFrameIndexReferenceFromSP(
+          Fn, FuncInfo.UnwindHelpFrameIdx, FrameReg);
+  } else if (MMI.hasWinEHFuncInfo(F)) {
+    WinEHFuncInfo &FuncInfo = MMI.getWinEHFuncInfo(Fn.getFunction());
+    auto I = FuncInfo.CatchHandlerParentFrameObjIdx.find(F);
+    if (I != FuncInfo.CatchHandlerParentFrameObjIdx.end())
+      FuncInfo.CatchHandlerParentFrameObjOffset[F] =
+          TFI.getFrameIndexReferenceFromSP(Fn, I->second, FrameReg);
+  }
+
   // Store SPAdj at exit of a basic block.
   SmallVector<int, 8> SPState;
   SPState.resize(Fn.getNumBlockIDs());
@@ -744,8 +864,8 @@ void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn,
   const TargetInstrInfo &TII = *Fn.getSubtarget().getInstrInfo();
   const TargetRegisterInfo &TRI = *Fn.getSubtarget().getRegisterInfo();
   const TargetFrameLowering *TFI = Fn.getSubtarget().getFrameLowering();
-  int FrameSetupOpcode   = TII.getCallFrameSetupOpcode();
-  int FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();
+  unsigned FrameSetupOpcode = TII.getCallFrameSetupOpcode();
+  unsigned FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();
 
   if (RS && !FrameIndexVirtualScavenging) RS->enterBasicBlock(BB);
 
@@ -811,17 +931,6 @@ void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn,
         continue;
       }
 
-      // Frame allocations are target independent. Simply swap the index with
-      // the offset.
-      if (MI->getOpcode() == TargetOpcode::FRAME_ALLOC) {
-        assert(TFI->hasFP(Fn) && "frame alloc requires FP");
-        MachineOperand &FI = MI->getOperand(i);
-        unsigned Reg;
-        int FrameOffset = TFI->getFrameIndexReference(Fn, FI.getIndex(), Reg);
-        FI.ChangeToImmediate(FrameOffset);
-        continue;
-      }
-
       // Some instructions (e.g. inline asm instructions) can have
       // multiple frame indices and/or cause eliminateFrameIndex
       // to insert more than one instruction. We need the register