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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@52748 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Analysis/ValueTracking.h

@@ -15,6 +15,8 @@
 #ifndef LLVM_ANALYSIS_VALUETRACKING_H
 #define LLVM_ANALYSIS_VALUETRACKING_H
 
+#include <string>
+
 namespace llvm {
   class Value;
   class Instruction;
@@ -70,6 +72,11 @@ namespace llvm {
     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.
+  bool GetConstantStringInfo(Value *V, std::string &Str);
 } // end namespace llvm
 
 #endif

include/llvm/Constant.h

@@ -115,13 +115,6 @@ 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

include/llvm/IntrinsicInst.h

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

lib/Analysis/ValueTracking.cpp

@@ -15,6 +15,7 @@
 #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"
@@ -930,3 +931,88 @@ 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) {
+  // 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);
+  
+  // 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.
+}

lib/CodeGen/MachineModuleInfo.cpp

@@ -10,6 +10,7 @@
 #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"
@@ -230,7 +231,11 @@ public:
   }
   virtual void Apply(std::string &Field) {
     Constant *C = CI->getOperand(I++);
-    Field = C->getStringValue();
+    std::string S;
+    if (GetConstantStringInfo(C, S))
+      Field = S;
+    else
+      Field = "";
   }
   virtual void Apply(DebugInfoDesc *&Field) {
     Constant *C = CI->getOperand(I++);

lib/CodeGen/SelectionDAG/SelectionDAG.cpp

@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 #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"
@@ -2594,8 +2595,7 @@ static bool isMemSrcFromString(SDOperand Src, std::string &Str,
 
   GlobalVariable *GV = dyn_cast<GlobalVariable>(G->getGlobal());
   if (GV && GV->isConstant()) {
-    Str = GV->getStringValue(false);
+    if (GetConstantStringInfo(GV, Str)) {
-    if (!Str.empty()) {
       SrcOff += SrcDelta;
       return true;
     }

lib/Debugger/ProgramInfo.cpp

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

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.
-    const std::string &Str = CE->getOperand(0)->getStringValue();
+    std::string Str;
-    if (!Str.empty()) {
+    if (GetConstantStringInfo(CE->getOperand(0), Str) && !Str.empty()) {
       unsigned len = Str.length();
       const Type *Ty = cast<PointerType>(CE->getType())->getElementType();
       unsigned numBits = Ty->getPrimitiveSizeInBits();

lib/VMCore/Constants.cpp

@@ -2658,44 +2658,4 @@ 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 "";
-}

lib/VMCore/IntrinsicInst.cpp

@@ -28,6 +28,7 @@
 #include "llvm/IntrinsicInst.h"
 #include "llvm/Constants.h"
 #include "llvm/GlobalVariable.h"
+#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 using namespace llvm;
 
@@ -57,20 +58,20 @@ Value *DbgInfoIntrinsic::StripCast(Value *C) {
 /// DbgStopPointInst - This represents the llvm.dbg.stoppoint instruction.
 ///
 
-std::string DbgStopPointInst::getFileName() const {
+Value *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 "";
+  if (!GV->hasInitializer()) return NULL;
   ConstantStruct *CS = cast<ConstantStruct>(GV->getInitializer());
-  return CS->getOperand(3)->getStringValue();
+  return CS->getOperand(4);
 }
 
-std::string DbgStopPointInst::getDirectory() const {
+Value *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 "";
+  if (!GV->hasInitializer()) return NULL;
   ConstantStruct *CS = cast<ConstantStruct>(GV->getInitializer());
-  return CS->getOperand(4)->getStringValue();
+  return CS->getOperand(4);
 }