Make it possible to use the linker without destroying the source module. This is so the source module can be linked to multiple other destination modules. For all that used LinkModules() before, they will continue to destroy the source module as before.

This line, and those below, will be ignored--

M    include/llvm/Linker.h
M    tools/bugpoint/Miscompilation.cpp
M    tools/bugpoint/BugDriver.cpp
M    tools/llvm-link/llvm-link.cpp
M    lib/Linker/LinkModules.cpp


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@141606 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Linker.h

@@ -57,7 +57,12 @@ class Linker {
       QuietWarnings = 2, ///< Don't print warnings to stderr.
       QuietErrors   = 4  ///< Don't print errors to stderr.
     };
-
+  
+    enum LinkerMode {
+      DestroySource = 0, // Allow source module to be destroyed.
+      PreserveSource = 1 // Preserve the source module.
+    };
+  
   /// @}
   /// @name Constructors
   /// @{
@@ -245,7 +250,7 @@ class Linker {
       Module* Src,              ///< Module linked into \p Dest
       std::string* ErrorMsg = 0 /// Error/diagnostic string
     ) { 
-      return LinkModules(Composite, Src, ErrorMsg ); 
+      return LinkModules(Composite, Src, Linker::DestroySource, ErrorMsg ); 
     }
 
     /// This is the heart of the linker. This method will take unconditional
@@ -259,7 +264,8 @@ class Linker {
     /// error.
     /// @returns True if an error occurs, false otherwise.
     /// @brief Generically link two modules together.
-    static bool LinkModules(Module* Dest, Module* Src, std::string* ErrorMsg);
+    static bool LinkModules(Module* Dest, Module* Src, unsigned Mode,
+                            std::string* ErrorMsg);
 
     /// This function looks through the Linker's LibPaths to find a library with
     /// the name \p Filename. If the library cannot be found, the returned path

lib/Linker/LinkModules.cpp

@@ -14,9 +14,12 @@
 #include "llvm/Linker.h"
 #include "llvm/Constants.h"
 #include "llvm/DerivedTypes.h"
+#include "llvm/Instructions.h"
 #include "llvm/Module.h"
+#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Support/Path.h"
+#include "llvm/Transforms/Utils/Cloning.h"
 #include "llvm/Transforms/Utils/ValueMapper.h"
 using namespace llvm;
 
@@ -333,10 +336,16 @@ namespace {
     
     std::vector<AppendingVarInfo> AppendingVars;
     
+    unsigned Mode; // Mode to treat source module.
+    
+    // Set of items not to link in from source.
+    SmallPtrSet<const Value*, 16> DoNotLinkFromSource;
+    
   public:
     std::string ErrorMsg;
     
-    ModuleLinker(Module *dstM, Module *srcM) : DstM(dstM), SrcM(srcM) { }
+    ModuleLinker(Module *dstM, Module *srcM, unsigned mode)
+      : DstM(dstM), SrcM(srcM), Mode(mode) { }
     
     bool run();
     
@@ -596,9 +605,9 @@ bool ModuleLinker::linkAppendingVarProto(GlobalVariable *DstGV,
   DstGV->replaceAllUsesWith(ConstantExpr::getBitCast(NG, DstGV->getType()));
   DstGV->eraseFromParent();
   
-  // Zap the initializer in the source variable so we don't try to link it.
-  SrcGV->setInitializer(0);
-  SrcGV->setLinkage(GlobalValue::ExternalLinkage);
+  // Track the source variable so we don't try to link it.
+  DoNotLinkFromSource.insert(SrcGV);
+  
   return false;
 }
 
@@ -633,11 +642,10 @@ bool ModuleLinker::linkGlobalProto(GlobalVariable *SGV) {
       // Make sure to remember this mapping.
       ValueMap[SGV] = ConstantExpr::getBitCast(DGV,TypeMap.get(SGV->getType()));
       
-      // Destroy the source global's initializer (and convert it to a prototype)
-      // so that we don't attempt to copy it over when processing global
-      // initializers.
-      SGV->setInitializer(0);
-      SGV->setLinkage(GlobalValue::ExternalLinkage);
+      // Track the source global so that we don't attempt to copy it over when 
+      // processing global initializers.
+      DoNotLinkFromSource.insert(SGV);
+      
       return false;
     }
   }
@@ -682,8 +690,10 @@ bool ModuleLinker::linkFunctionProto(Function *SF) {
       // Make sure to remember this mapping.
       ValueMap[SF] = ConstantExpr::getBitCast(DGV, TypeMap.get(SF->getType()));
       
-      // Remove the body from the source module so we don't attempt to remap it.
-      SF->deleteBody();
+      // Track the function from the source module so we don't attempt to remap 
+      // it.
+      DoNotLinkFromSource.insert(SF);
+      
       return false;
     }
   }
@@ -722,8 +732,9 @@ bool ModuleLinker::linkAliasProto(GlobalAlias *SGA) {
       // Make sure to remember this mapping.
       ValueMap[SGA] = ConstantExpr::getBitCast(DGV,TypeMap.get(SGA->getType()));
       
-      // Remove the body from the source module so we don't attempt to remap it.
-      SGA->setAliasee(0);
+      // Track the alias from the source module so we don't attempt to remap it.
+      DoNotLinkFromSource.insert(SGA);
+      
       return false;
     }
   }
@@ -779,7 +790,9 @@ void ModuleLinker::linkGlobalInits() {
   // Loop over all of the globals in the src module, mapping them over as we go
   for (Module::const_global_iterator I = SrcM->global_begin(),
        E = SrcM->global_end(); I != E; ++I) {
-    if (!I->hasInitializer()) continue;      // Only process initialized GV's.
+    
+    // Only process initialized GV's or ones not already in dest.
+    if (!I->hasInitializer() || DoNotLinkFromSource.count(I)) continue;          
     
     // Grab destination global variable.
     GlobalVariable *DGV = cast<GlobalVariable>(ValueMap[I]);
@@ -805,31 +818,42 @@ void ModuleLinker::linkFunctionBody(Function *Dst, Function *Src) {
     ValueMap[I] = DI;
   }
 
-  // Splice the body of the source function into the dest function.
-  Dst->getBasicBlockList().splice(Dst->end(), Src->getBasicBlockList());
-
-  // At this point, all of the instructions and values of the function are now
-  // copied over.  The only problem is that they are still referencing values in
-  // the Source function as operands.  Loop through all of the operands of the
-  // functions and patch them up to point to the local versions.
-  for (Function::iterator BB = Dst->begin(), BE = Dst->end(); BB != BE; ++BB)
-    for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I)
-      RemapInstruction(I, ValueMap, RF_IgnoreMissingEntries, &TypeMap);
-
+  if (Mode == Linker::DestroySource) {
+    // Splice the body of the source function into the dest function.
+    Dst->getBasicBlockList().splice(Dst->end(), Src->getBasicBlockList());
+    
+    // At this point, all of the instructions and values of the function are now
+    // copied over.  The only problem is that they are still referencing values in
+    // the Source function as operands.  Loop through all of the operands of the
+    // functions and patch them up to point to the local versions.
+    for (Function::iterator BB = Dst->begin(), BE = Dst->end(); BB != BE; ++BB)
+      for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I)
+        RemapInstruction(I, ValueMap, RF_IgnoreMissingEntries, &TypeMap);
+    
+  } else {
+    // Clone the body of the function into the dest function.
+    SmallVector<ReturnInst*, 8> Returns; // Ignore returns.
+    CloneFunctionInto(Dst, Src, ValueMap, false, Returns);
+  }
+  
   // There is no need to map the arguments anymore.
   for (Function::arg_iterator I = Src->arg_begin(), E = Src->arg_end();
        I != E; ++I)
     ValueMap.erase(I);
+  
 }
 
 
 void ModuleLinker::linkAliasBodies() {
   for (Module::alias_iterator I = SrcM->alias_begin(), E = SrcM->alias_end();
-       I != E; ++I)
+       I != E; ++I) {
+    if (DoNotLinkFromSource.count(I))
+      continue;
     if (Constant *Aliasee = I->getAliasee()) {
       GlobalAlias *DA = cast<GlobalAlias>(ValueMap[I]);
       DA->setAliasee(MapValue(Aliasee, ValueMap, RF_None, &TypeMap));
     }
+  }
 }
 
 /// linkNamedMDNodes - Insert all of the named mdnodes in Src into the Dest
@@ -891,7 +915,6 @@ bool ModuleLinker::run() {
   StringRef ModuleId = SrcM->getModuleIdentifier();
   if (!ModuleId.empty())
     DstM->removeLibrary(sys::path::stem(ModuleId));
-
   
   // Loop over all of the linked values to compute type mappings.
   computeTypeMapping();
@@ -928,7 +951,8 @@ bool ModuleLinker::run() {
   // Link in the function bodies that are defined in the source module into
   // DstM.
   for (Module::iterator SF = SrcM->begin(), E = SrcM->end(); SF != E; ++SF) {
-    if (SF->isDeclaration()) continue;      // No body if function is external.
+    // Skip if no body (function is external) or marked to skip.
+    if (SF->isDeclaration() || DoNotLinkFromSource.count(SF)) continue;
     
     linkFunctionBody(cast<Function>(ValueMap[SF]), SF);
   }
@@ -957,8 +981,9 @@ bool ModuleLinker::run() {
 // error occurs, true is returned and ErrorMsg (if not null) is set to indicate
 // the problem.  Upon failure, the Dest module could be in a modified state, and
 // shouldn't be relied on to be consistent.
-bool Linker::LinkModules(Module *Dest, Module *Src, std::string *ErrorMsg) {
-  ModuleLinker TheLinker(Dest, Src);
+bool Linker::LinkModules(Module *Dest, Module *Src, unsigned Mode, 
+                         std::string *ErrorMsg) {
+  ModuleLinker TheLinker(Dest, Src, Mode);
   if (TheLinker.run()) {
     if (ErrorMsg) *ErrorMsg = TheLinker.ErrorMsg;
     return true;

tools/bugpoint/BugDriver.cpp

@@ -127,7 +127,8 @@ bool BugDriver::addSources(const std::vector<std::string> &Filenames) {
 
     outs() << "Linking in input file: '" << Filenames[i] << "'\n";
     std::string ErrorMessage;
-    if (Linker::LinkModules(Program, M.get(), &ErrorMessage)) {
+    if (Linker::LinkModules(Program, M.get(), Linker::DestroySource,
+                            &ErrorMessage)) {
       errs() << ToolName << ": error linking in '" << Filenames[i] << "': "
              << ErrorMessage << '\n';
       return true;

tools/bugpoint/Miscompilation.cpp

@@ -222,7 +222,7 @@ static Module *TestMergedProgram(const BugDriver &BD, Module *M1, Module *M2,
     M1 = CloneModule(M1);
     M2 = CloneModule(M2);
   }
-  if (Linker::LinkModules(M1, M2, &ErrorMsg)) {
+  if (Linker::LinkModules(M1, M2, Linker::DestroySource, &ErrorMsg)) {
     errs() << BD.getToolName() << ": Error linking modules together:"
            << ErrorMsg << '\n';
     exit(1);
@@ -396,7 +396,8 @@ static bool ExtractLoops(BugDriver &BD,
     // Replace the current program with the loop extracted version, and try to
     // extract another loop.
     std::string ErrorMsg;
-    if (Linker::LinkModules(ToNotOptimize, ToOptimizeLoopExtracted, &ErrorMsg)){
+    if (Linker::LinkModules(ToNotOptimize, ToOptimizeLoopExtracted, 
+                            Linker::DestroySource, &ErrorMsg)){
       errs() << BD.getToolName() << ": Error linking modules together:"
              << ErrorMsg << '\n';
       exit(1);
@@ -575,7 +576,8 @@ static bool ExtractBlocks(BugDriver &BD,
                                                 I->getFunctionType()));
 
   std::string ErrorMsg;
-  if (Linker::LinkModules(ProgClone, Extracted, &ErrorMsg)) {
+  if (Linker::LinkModules(ProgClone, Extracted, Linker::DestroySource, 
+                          &ErrorMsg)) {
     errs() << BD.getToolName() << ": Error linking modules together:"
            << ErrorMsg << '\n';
     exit(1);

tools/llvm-link/llvm-link.cpp

@@ -103,7 +103,8 @@ int main(int argc, char **argv) {
 
     if (Verbose) errs() << "Linking in '" << InputFilenames[i] << "'\n";
 
-    if (Linker::LinkModules(Composite.get(), M.get(), &ErrorMessage)) {
+    if (Linker::LinkModules(Composite.get(), M.get(), Linker::DestroySource,
+                            &ErrorMessage)) {
       errs() << argv[0] << ": link error in '" << InputFilenames[i]
              << "': " << ErrorMessage << "\n";
       return 1;