Revert (52748 and friends):

Move GetConstantStringInfo to lib/Analysis. Remove
string output routine from Constant. Update all
callers. Change debug intrinsic api slightly to
accomodate move of routine, these now return values
instead of strings.

This unbreaks llvm-gcc bootstrap.

llvm-svn: 52884

llvm/include/llvm/Analysis/ValueTracking.h

@@ -72,16 +72,7 @@ namespace llvm {
                                  Instruction *InsertBefore = 0) {
     const unsigned Idxs[1] = { Idx };
     return FindInsertedValue(V, &Idxs[0], &Idxs[1], InsertBefore);
-  }
+  }  
-  
-  /// GetConstantStringInfo - This function computes the length of a
-  /// null-terminated C string pointed to by V.  If successful, it returns true
-  /// and returns the string in Str.  If unsuccessful, it returns false.  If
-  /// StopAtNul is set to true (the default), the returned string is truncated
-  /// by a nul character in the global.  If StopAtNul is false, the nul
-  /// character is included in the result string.
-  bool GetConstantStringInfo(Value *V, std::string &Str, uint64_t Offset = 0,
-                             bool StopAtNul = true);
 } // end namespace llvm
 
 #endif

llvm/include/llvm/Constant.h

@@ -115,6 +115,13 @@ public:
            "implemented for all constants that have operands!");
     assert(0 && "Constants that do not have operands cannot be using 'From'!");
   }
+
+  /// getStringValue - Turn an LLVM constant pointer that eventually points to a
+  /// global into a string value.  Return an empty string if we can't do it.
+  /// Parameter Chop determines if the result is chopped at the first null
+  /// terminator.
+  ///
+  std::string getStringValue(bool Chop = true, unsigned Offset = 0);
 };
 
 } // End llvm namespace

llvm/include/llvm/IntrinsicInst.h

@@ -96,8 +96,8 @@ namespace llvm {
       return unsigned(cast<ConstantInt>(getOperand(2))->getZExtValue());
     }
     
-    Value* getFileName() const;
+    std::string getFileName() const;
-    Value* getDirectory() const;
+    std::string getDirectory() const;
 
     // Methods for support type inquiry through isa, cast, and dyn_cast:
     static inline bool classof(const DbgStopPointInst *) { return true; }

llvm/lib/Analysis/ValueTracking.cpp

@@ -15,7 +15,6 @@
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Constants.h"
 #include "llvm/Instructions.h"
-#include "llvm/GlobalVariable.h"
 #include "llvm/IntrinsicInst.h"
 #include "llvm/Target/TargetData.h"
 #include "llvm/Support/GetElementPtrTypeIterator.h"
@@ -931,102 +930,3 @@ Value *llvm::FindInsertedValue(Value *V, const unsigned *idx_begin,
   // or load instruction)
   return 0;
 }
-
-/// GetConstantStringInfo - This function computes the length of a
-/// null-terminated C string pointed to by V.  If successful, it returns true
-/// and returns the string in Str.  If unsuccessful, it returns false.
-bool llvm::GetConstantStringInfo(Value *V, std::string &Str, uint64_t Offset,
-                                 bool StopAtNul) {
-  // If V is NULL then return false;
-  if (V == NULL) return false;
-
-  // Look through bitcast instructions.
-  if (BitCastInst *BCI = dyn_cast<BitCastInst>(V))
-    return GetConstantStringInfo(BCI->getOperand(0), Str, Offset, StopAtNul);
-  
-  // If the value is not a GEP instruction nor a constant expression with a
-  // GEP instruction, then return false because ConstantArray can't occur
-  // any other way
-  User *GEP = 0;
-  if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(V)) {
-    GEP = GEPI;
-  } else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(V)) {
-    if (CE->getOpcode() == Instruction::BitCast)
-      return GetConstantStringInfo(CE->getOperand(0), Str, Offset, StopAtNul);
-    if (CE->getOpcode() != Instruction::GetElementPtr)
-      return false;
-    GEP = CE;
-  }
-  
-  if (GEP) {
-    // Make sure the GEP has exactly three arguments.
-    if (GEP->getNumOperands() != 3)
-      return false;
-    
-    // Make sure the index-ee is a pointer to array of i8.
-    const PointerType *PT = cast<PointerType>(GEP->getOperand(0)->getType());
-    const ArrayType *AT = dyn_cast<ArrayType>(PT->getElementType());
-    if (AT == 0 || AT->getElementType() != Type::Int8Ty)
-      return false;
-    
-    // Check to make sure that the first operand of the GEP is an integer and
-    // has value 0 so that we are sure we're indexing into the initializer.
-    ConstantInt *FirstIdx = dyn_cast<ConstantInt>(GEP->getOperand(1));
-    if (FirstIdx == 0 || !FirstIdx->isZero())
-      return false;
-    
-    // If the second index isn't a ConstantInt, then this is a variable index
-    // into the array.  If this occurs, we can't say anything meaningful about
-    // the string.
-    uint64_t StartIdx = 0;
-    if (ConstantInt *CI = dyn_cast<ConstantInt>(GEP->getOperand(2)))
-      StartIdx = CI->getZExtValue();
-    else
-      return false;
-    return GetConstantStringInfo(GEP->getOperand(0), Str, StartIdx+Offset,
-                                 StopAtNul);
-  }
-  
-  // The GEP instruction, constant or instruction, must reference a global
-  // variable that is a constant and is initialized. The referenced constant
-  // initializer is the array that we'll use for optimization.
-  GlobalVariable* GV = dyn_cast<GlobalVariable>(V);
-  if (!GV || !GV->isConstant() || !GV->hasInitializer())
-    return false;
-  Constant *GlobalInit = GV->getInitializer();
-  
-  // Handle the ConstantAggregateZero case
-  if (isa<ConstantAggregateZero>(GlobalInit)) {
-    // This is a degenerate case. The initializer is constant zero so the
-    // length of the string must be zero.
-    Str.clear();
-    return true;
-  }
-  
-  // Must be a Constant Array
-  ConstantArray *Array = dyn_cast<ConstantArray>(GlobalInit);
-  if (Array == 0 || Array->getType()->getElementType() != Type::Int8Ty)
-    return false;
-  
-  // Get the number of elements in the array
-  uint64_t NumElts = Array->getType()->getNumElements();
-  
-  if (Offset > NumElts)
-    return false;
-  
-  // Traverse the constant array from 'Offset' which is the place the GEP refers
-  // to in the array.
-  Str.reserve(NumElts-Offset);
-  for (unsigned i = Offset; i != NumElts; ++i) {
-    Constant *Elt = Array->getOperand(i);
-    ConstantInt *CI = dyn_cast<ConstantInt>(Elt);
-    if (!CI) // This array isn't suitable, non-int initializer.
-      return false;
-    if (StopAtNul && CI->isZero())
-      return true; // we found end of string, success!
-    Str += (char)CI->getZExtValue();
-  }
-  
-  // The array isn't null terminated, but maybe this is a memcpy, not a strcpy.
-  return true;
-}

llvm/lib/CodeGen/MachineModuleInfo.cpp

@@ -10,7 +10,6 @@
 #include "llvm/CodeGen/MachineModuleInfo.h"
 
 #include "llvm/Constants.h"
-#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineLocation.h"
@@ -207,9 +206,7 @@ public:
   }
   virtual void Apply(std::string &Field) {
     Constant *C = CI->getOperand(I++);
-    // Fills in the string if it succeeds
+    Field = C->getStringValue();
-    if (!GetConstantStringInfo(C, Field))
-      Field.clear();
   }
   virtual void Apply(DebugInfoDesc *&Field) {
     Constant *C = CI->getOperand(I++);

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

@@ -12,7 +12,6 @@
 //===----------------------------------------------------------------------===//
 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/Constants.h"
-#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/GlobalAlias.h"
 #include "llvm/GlobalVariable.h"
 #include "llvm/Intrinsics.h"
@@ -2578,7 +2577,8 @@ static SDOperand getMemBasePlusOffset(SDOperand Base, unsigned Offset,
 
 /// isMemSrcFromString - Returns true if memcpy source is a string constant.
 ///
-static bool isMemSrcFromString(SDOperand Src, std::string &Str) {
+static bool isMemSrcFromString(SDOperand Src, std::string &Str,
+                               uint64_t &SrcOff) {
   unsigned SrcDelta = 0;
   GlobalAddressSDNode *G = NULL;
   if (Src.getOpcode() == ISD::GlobalAddress)
@@ -2593,8 +2593,13 @@ static bool isMemSrcFromString(SDOperand Src, std::string &Str) {
     return false;
 
   GlobalVariable *GV = dyn_cast<GlobalVariable>(G->getGlobal());
-  if (GV && GetConstantStringInfo(GV, Str, SrcDelta, false))
+  if (GV && GV->isConstant()) {
-    return true;
+    Str = GV->getStringValue(false);
+    if (!Str.empty()) {
+      SrcOff += SrcDelta;
+      return true;
+    }
+  }
 
   return false;
 }
@@ -2611,7 +2616,8 @@ bool MeetsMaxMemopRequirement(std::vector<MVT> &MemOps,
   bool AllowUnalign = TLI.allowsUnalignedMemoryAccesses();
 
   std::string Str;
-  bool isSrcStr = isMemSrcFromString(Src, Str);
+  uint64_t SrcOff = 0;
+  bool isSrcStr = isMemSrcFromString(Src, Str, SrcOff);
   bool isSrcConst = isa<ConstantSDNode>(Src);
   MVT VT= TLI.getOptimalMemOpType(Size, Align, isSrcConst, isSrcStr);
   if (VT != MVT::iAny) {
@@ -2706,11 +2712,11 @@ static SDOperand getMemcpyLoadsAndStores(SelectionDAG &DAG,
     return SDOperand();
 
   std::string Str;
-  bool CopyFromStr = isMemSrcFromString(Src, Str);
+  uint64_t SrcOff = 0, DstOff = 0;
+  bool CopyFromStr = isMemSrcFromString(Src, Str, SrcOff);
 
   SmallVector<SDOperand, 8> OutChains;
   unsigned NumMemOps = MemOps.size();
-  uint64_t SrcOff = 0, DstOff = 0;
   for (unsigned i = 0; i < NumMemOps; i++) {
     MVT VT = MemOps[i];
     unsigned VTSize = VT.getSizeInBits() / 8;

llvm/lib/Debugger/ProgramInfo.cpp

@@ -14,7 +14,6 @@
 
 #include "llvm/Debugger/ProgramInfo.h"
 #include "llvm/Constants.h"
-#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/DerivedTypes.h"
 #include "llvm/Intrinsics.h"
 #include "llvm/IntrinsicInst.h"
@@ -116,10 +115,8 @@ SourceFileInfo::SourceFileInfo(const GlobalVariable *Desc,
         if (ConstantInt *CUI = dyn_cast<ConstantInt>(CS->getOperand(1)))
           Version = CUI->getZExtValue();
 
-        if (!GetConstantStringInfo(CS->getOperand(3), BaseName))
+        BaseName  = CS->getOperand(3)->getStringValue();
-          BaseName = "";
+        Directory = CS->getOperand(4)->getStringValue();
-        if (!GetConstantStringInfo(CS->getOperand(4), Directory))
-          Directory = "";
       }
 }
 
@@ -159,8 +156,7 @@ SourceFunctionInfo::SourceFunctionInfo(ProgramInfo &PI,
           SourceFile = &PI.getSourceFile(GV);
 
         // Entry #2 is the function name.
-        if (!GetConstantStringInfo(CS->getOperand(2), Name))
+        Name = CS->getOperand(2)->getStringValue();
-          Name = "";
       }
 }
 

llvm/lib/Transforms/Scalar/InstructionCombining.cpp

@@ -9973,8 +9973,8 @@ static Instruction *InstCombineLoadCast(InstCombiner &IC, LoadInst &LI,
   if (ConstantExpr *CE = dyn_cast<ConstantExpr>(CI)) {
     // Instead of loading constant c string, use corresponding integer value
     // directly if string length is small enough.
-    std::string Str;
+    const std::string &Str = CE->getOperand(0)->getStringValue();
-    if (GetConstantStringInfo(CE->getOperand(0), Str) && !Str.empty()) {
+    if (!Str.empty()) {
       unsigned len = Str.length();
       const Type *Ty = cast<PointerType>(CE->getType())->getElementType();
       unsigned numBits = Ty->getPrimitiveSizeInBits();

llvm/lib/Transforms/Scalar/SimplifyLibCalls.cpp

@@ -23,7 +23,6 @@
 #include "llvm/Module.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/IRBuilder.h"
-#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Target/TargetData.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/StringMap.h"
@@ -230,6 +229,88 @@ void LibCallOptimization::EmitFWrite(Value *Ptr, Value *Size, Value *File,
 // Helper Functions
 //===----------------------------------------------------------------------===//
 
+/// GetConstantStringInfo - This function computes the length of a
+/// null-terminated C string pointed to by V.  If successful, it returns true
+/// and returns the string in Str.  If unsuccessful, it returns false.
+static bool GetConstantStringInfo(Value *V, std::string &Str) {
+  // Look bitcast instructions.
+  if (BitCastInst *BCI = dyn_cast<BitCastInst>(V))
+    return GetConstantStringInfo(BCI->getOperand(0), Str);
+  
+  // If the value is not a GEP instruction nor a constant expression with a
+  // GEP instruction, then return false because ConstantArray can't occur
+  // any other way
+  User *GEP = 0;
+  if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(V)) {
+    GEP = GEPI;
+  } else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(V)) {
+    if (CE->getOpcode() != Instruction::GetElementPtr)
+      return false;
+    GEP = CE;
+  } else {
+    return false;
+  }
+  
+  // Make sure the GEP has exactly three arguments.
+  if (GEP->getNumOperands() != 3)
+    return false;
+  
+  // Check to make sure that the first operand of the GEP is an integer and
+  // has value 0 so that we are sure we're indexing into the initializer.
+  if (ConstantInt *Idx = dyn_cast<ConstantInt>(GEP->getOperand(1))) {
+    if (!Idx->isZero())
+      return false;
+  } else
+    return false;
+  
+  // If the second index isn't a ConstantInt, then this is a variable index
+  // into the array.  If this occurs, we can't say anything meaningful about
+  // the string.
+  uint64_t StartIdx = 0;
+  if (ConstantInt *CI = dyn_cast<ConstantInt>(GEP->getOperand(2)))
+    StartIdx = CI->getZExtValue();
+  else
+    return false;
+  
+  // The GEP instruction, constant or instruction, must reference a global
+  // variable that is a constant and is initialized. The referenced constant
+  // initializer is the array that we'll use for optimization.
+  GlobalVariable* GV = dyn_cast<GlobalVariable>(GEP->getOperand(0));
+  if (!GV || !GV->isConstant() || !GV->hasInitializer())
+    return false;
+  Constant *GlobalInit = GV->getInitializer();
+  
+  // Handle the ConstantAggregateZero case
+  if (isa<ConstantAggregateZero>(GlobalInit)) {
+    // This is a degenerate case. The initializer is constant zero so the
+    // length of the string must be zero.
+    Str.clear();
+    return true;
+  }
+  
+  // Must be a Constant Array
+  ConstantArray *Array = dyn_cast<ConstantArray>(GlobalInit);
+  if (Array == 0 || Array->getType()->getElementType() != Type::Int8Ty)
+    return false;
+  
+  // Get the number of elements in the array
+  uint64_t NumElts = Array->getType()->getNumElements();
+  
+  // Traverse the constant array from StartIdx (derived above) which is
+  // the place the GEP refers to in the array.
+  for (unsigned i = StartIdx; i < NumElts; ++i) {
+    Constant *Elt = Array->getOperand(i);
+    ConstantInt *CI = dyn_cast<ConstantInt>(Elt);
+    if (!CI) // This array isn't suitable, non-int initializer.
+      return false;
+    if (CI->isZero())
+      return true; // we found end of string, success!
+    Str += (char)CI->getZExtValue();
+  }
+  
+  return false; // The array isn't null terminated.
+}
+
 /// GetStringLengthH - If we can compute the length of the string pointed to by
 /// the specified pointer, return 'len+1'.  If we can't, return 0.
 static uint64_t GetStringLengthH(Value *V, SmallPtrSet<PHINode*, 32> &PHIs) {

llvm/lib/VMCore/Constants.cpp

@@ -2658,4 +2658,44 @@ void ConstantExpr::replaceUsesOfWithOnConstant(Value *From, Value *ToV,
   
   // Delete the old constant!
   destroyConstant();
-}
+}
+
+
+/// getStringValue - Turn an LLVM constant pointer that eventually points to a
+/// global into a string value.  Return an empty string if we can't do it.
+/// Parameter Chop determines if the result is chopped at the first null
+/// terminator.
+///
+std::string Constant::getStringValue(bool Chop, unsigned Offset) {
+  if (GlobalVariable *GV = dyn_cast<GlobalVariable>(this)) {
+    if (GV->hasInitializer() && isa<ConstantArray>(GV->getInitializer())) {
+      ConstantArray *Init = cast<ConstantArray>(GV->getInitializer());
+      if (Init->isString()) {
+        std::string Result = Init->getAsString();
+        if (Offset < Result.size()) {
+          // If we are pointing INTO The string, erase the beginning...
+          Result.erase(Result.begin(), Result.begin()+Offset);
+
+          // Take off the null terminator, and any string fragments after it.
+          if (Chop) {
+            std::string::size_type NullPos = Result.find_first_of((char)0);
+            if (NullPos != std::string::npos)
+              Result.erase(Result.begin()+NullPos, Result.end());
+          }
+          return Result;
+        }
+      }
+    }
+  } else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(this)) {
+    if (CE->getOpcode() == Instruction::GetElementPtr) {
+      // Turn a gep into the specified offset.
+      if (CE->getNumOperands() == 3 &&
+          cast<Constant>(CE->getOperand(1))->isNullValue() &&
+          isa<ConstantInt>(CE->getOperand(2))) {
+        Offset += cast<ConstantInt>(CE->getOperand(2))->getZExtValue();
+        return CE->getOperand(0)->getStringValue(Chop, Offset);
+      }
+    }
+  }
+  return "";
+}

llvm/lib/VMCore/IntrinsicInst.cpp

@@ -28,7 +28,6 @@
 #include "llvm/IntrinsicInst.h"
 #include "llvm/Constants.h"
 #include "llvm/GlobalVariable.h"
-#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/MachineDebugInfoDesc.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 using namespace llvm;
@@ -59,20 +58,20 @@ Value *DbgInfoIntrinsic::StripCast(Value *C) {
 /// DbgStopPointInst - This represents the llvm.dbg.stoppoint instruction.
 ///
 
-Value *DbgStopPointInst::getFileName() const {
+std::string DbgStopPointInst::getFileName() const {
   // Once the operand indices are verified, update this assert
   assert(LLVMDebugVersion == (6 << 16) && "Verify operand indices");
   GlobalVariable *GV = cast<GlobalVariable>(getContext());
-  if (!GV->hasInitializer()) return NULL;
+  if (!GV->hasInitializer()) return "";
   ConstantStruct *CS = cast<ConstantStruct>(GV->getInitializer());
-  return CS->getOperand(4);
+  return CS->getOperand(3)->getStringValue();
 }
 
-Value *DbgStopPointInst::getDirectory() const {
+std::string DbgStopPointInst::getDirectory() const {
   // Once the operand indices are verified, update this assert
   assert(LLVMDebugVersion == (6 << 16) && "Verify operand indices");
   GlobalVariable *GV = cast<GlobalVariable>(getContext());
-  if (!GV->hasInitializer()) return NULL;
+  if (!GV->hasInitializer()) return "";
   ConstantStruct *CS = cast<ConstantStruct>(GV->getInitializer());
-  return CS->getOperand(4);
+  return CS->getOperand(4)->getStringValue();
 }