[ArgPromotion] Set debug location at updated callsites

[vsk]

Summary

Set the correct debug location on instructions which load arguments in
preparation for a call to an arg-promoted function.

This prevents location cascade from misattributing the line/scope of one
of these loads to the location of the instruction preceding the call.

[davide]

Thanks.

llvm/trunk/lib/Transforms/IPO/ArgumentPromotion.cpp

 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Metadata.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/NoFolder.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Use.h"
 #include "llvm/IR/User.h"
 #include "llvm/IR/Value.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Debug.h"
doPromotion(Function *F, SmallPtrSetImpl<Argument *> &ArgsToPromote,
   // to pass in the loaded pointers.
   //
   SmallVector<Value *, 16> Args;
   while (!F->use_empty()) {
     CallSite CS(F->user_back());
     assert(CS.getCalledFunction() == F);
     Instruction *Call = CS.getInstruction();
     const AttributeList &CallPAL = CS.getAttributes();
+    IRBuilder<NoFolder> IRB(Call);
 
     // Loop over the operands, inserting GEP and loads in the caller as
     // appropriate.
     CallSite::arg_iterator AI = CS.arg_begin();
     ArgNo = 0;
     for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(); I != E;
          ++I, ++AI, ++ArgNo)
       if (!ArgsToPromote.count(&*I) && !ByValArgsToTransform.count(&*I)) {
         Args.push_back(*AI); // Unmodified argument
         ArgAttrVec.push_back(CallPAL.getParamAttributes(ArgNo));
       } else if (ByValArgsToTransform.count(&*I)) {
         // Emit a GEP and load for each element of the struct.
         Type *AgTy = cast<PointerType>(I->getType())->getElementType();
         StructType *STy = cast<StructType>(AgTy);
         Value *Idxs[2] = {
             ConstantInt::get(Type::getInt32Ty(F->getContext()), 0), nullptr};
         for (unsigned i = 0, e = STy->getNumElements(); i != e; ++i) {
           Idxs[1] = ConstantInt::get(Type::getInt32Ty(F->getContext()), i);
-          Value *Idx = GetElementPtrInst::Create(
-              STy, *AI, Idxs, (*AI)->getName() + "." + Twine(i), Call);
+          auto *Idx =
+              IRB.CreateGEP(STy, *AI, Idxs, (*AI)->getName() + "." + Twine(i));
           // TODO: Tell AA about the new values?
-          Args.push_back(new LoadInst(STy->getElementType(i), Idx,
-                                      Idx->getName() + ".val", Call));
+          Args.push_back(IRB.CreateLoad(STy->getElementType(i), Idx,
+                                        Idx->getName() + ".val"));
           ArgAttrVec.push_back(AttributeSet());
         }
       } else if (!I->use_empty()) {
         // Non-dead argument: insert GEPs and loads as appropriate.
         ScalarizeTable &ArgIndices = ScalarizedElements[&*I];
         // Store the Value* version of the indices in here, but declare it now
         // for reuse.
         std::vector<Value *> Ops;
for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(); I != E;
               Ops.push_back(ConstantInt::get(IdxTy, II));
               // Keep track of the type we're currently indexing.
               if (auto *ElPTy = dyn_cast<PointerType>(ElTy))
                 ElTy = ElPTy->getElementType();
               else
                 ElTy = cast<CompositeType>(ElTy)->getTypeAtIndex(II);
             }
             // And create a GEP to extract those indices.
-            V = GetElementPtrInst::Create(ArgIndex.first, V, Ops,
-                                          V->getName() + ".idx", Call);
+            V = IRB.CreateGEP(ArgIndex.first, V, Ops, V->getName() + ".idx");
             Ops.clear();
           }
           // Since we're replacing a load make sure we take the alignment
           // of the previous load.
           LoadInst *newLoad =
-              new LoadInst(OrigLoad->getType(), V, V->getName() + ".val", Call);
+              IRB.CreateLoad(OrigLoad->getType(), V, V->getName() + ".val");
           newLoad->setAlignment(OrigLoad->getAlignment());
           // Transfer the AA info too.
           AAMDNodes AAInfo;
           OrigLoad->getAAMetadata(AAInfo);
           newLoad->setAAMetadata(AAInfo);
 
           Args.push_back(newLoad);
           ArgAttrVec.push_back(AttributeSet());

llvm/trunk/test/Transforms/ArgumentPromotion/dbg.ll

 ; RUN: opt < %s -argpromotion -S | FileCheck %s
 ; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
 
 declare void @sink(i32)
 
 ; CHECK: define internal void @test({{.*}} !dbg [[SP:![0-9]+]]
 define internal void @test(i32** %X) !dbg !2 {
   %1 = load i32*, i32** %X, align 8
   %2 = load i32, i32* %1, align 8
   call void @sink(i32 %2)
   ret void
 }
 
-define void @caller(i32** %Y) {
-; CHECK: call void @test(i32 %
-  call void @test(i32** %Y)
+%struct.pair = type { i32, i32 }
+
+; CHECK: define internal void @test_byval(i32 %{{.*}}, i32 %{{.*}})
+define internal void @test_byval(%struct.pair* byval %P) {
+  ret void
+}
+
+; CHECK-LABEL: define {{.*}} @caller(
+define void @caller(i32** %Y, %struct.pair* %P) {
+; CHECK:  load i32*, {{.*}} !dbg [[LOC_1:![0-9]+]]
+; CHECK-NEXT:  load i32, {{.*}} !dbg [[LOC_1]]
+; CHECK-NEXT: call void @test(i32 %{{.*}}), !dbg [[LOC_1]]
+  call void @test(i32** %Y), !dbg !1
+
+; CHECK: getelementptr %struct.pair, {{.*}} !dbg [[LOC_2:![0-9]+]]
+; CHECK-NEXT: load i32, i32* {{.*}} !dbg [[LOC_2]]
+; CHECK-NEXT: getelementptr %struct.pair, {{.*}} !dbg [[LOC_2]]
+; CHECK-NEXT: load i32, i32* {{.*}} !dbg [[LOC_2]]
+; CHECK-NEXT: call void @test_byval(i32 %{{.*}}, i32 %{{.*}}), !dbg [[LOC_2]]
+  call void @test_byval(%struct.pair* %P), !dbg !6
   ret void
 }
 
 ; CHECK: [[SP]] = distinct !DISubprogram(name: "test",
+; CHECK: [[LOC_1]] = !DILocation(line: 8
+; CHECK: [[LOC_2]] = !DILocation(line: 9
 
 !llvm.module.flags = !{!0}
 !llvm.dbg.cu = !{!3}
 
 !0 = !{i32 2, !"Debug Info Version", i32 3}
 !1 = !DILocation(line: 8, scope: !2)
 !2 = distinct !DISubprogram(name: "test", file: !5, line: 3, isLocal: true, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !3, scopeLine: 3, scope: null)
 !3 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5.0 ", isOptimized: false, emissionKind: LineTablesOnly, file: !5)
 !5 = !DIFile(filename: "test.c", directory: "")
+!6 = !DILocation(line: 9, scope: !2)