[DebugInfo] Update loop metadata for inlined loops

[Orlando]

Summary

Currently, when a loop is cloned while inlining function (A) into function (B) the loop metadata is copied and then not modified at all. The loop metadata can encode the loop's start and end DILocations. Therefore, the new inlined loop in function (B) may have loop metadata which shows start and end locations residing in function (A).

This patch ensures loop metadata is updated while inlining so that the start and end DILocations are given the "inlinedAt" operand. I've also added a regression test for this.

This fix is required for D60831 because that patch uses loop metadata to determine the DILocation for the branches of new loop preheaders.

[aprantl]

Seems reasonable, nitpicks inside.

llvm/lib/Transforms/Utils/InlineFunction.cpp

1378

what can this be except an MDNode?

1380

what can this be except a DILocation?

1381

this is reusing the same code used for inlining instructions — looks good

1388

referential

1420

this is just factored out — LGTM

1432

this is weird, why no move the loop metadata update *above* the DILocation update?

[Orlando]

llvm/lib/Transforms/Utils/InlineFunction.cpp

1380

It can be some other loop metadata.

The test inlined-loop-metadata.ll provides an example:

...
br i1 %13, label %middle.block, label %vector.body, !llvm.loop !15
...
!10 = !DILocation(line: 4, scope: !8)
!15 = distinct !{!15, !10, !16, !17}
!16 = !DILocation(line: 6, scope: !8)
!17 = !{!"llvm.loop.isvectorized", i32 1}

[Orlando]

Address suggestions and add some const correctness.

[Orlando]

llvm/lib/Transforms/Utils/InlineFunction.cpp

1432

Ah, that was left over from some experimental code. I've fixed this now.

[Orlando]

Reverted with commit 95805bc425b because armv8 build bots are failing.

[Orlando]

Resubmitted in rL361149.

llvm/lib/Transforms/Utils/InlineFunction.cpp

 
 /// Return the result of AI->isStaticAlloca() if AI were moved to the entry
 /// block. Allocas used in inalloca calls and allocas of dynamic array size
 /// cannot be static.
 static bool allocaWouldBeStaticInEntry(const AllocaInst *AI ) {
   return isa<Constant>(AI->getArraySize()) && !AI->isUsedWithInAlloca();
 }
 
+/// Returns a DebugLoc for a new DILocation which is a clone of \p OrigDL
+/// inlined at \p InlinedAt. \p IANodes is an inlined-at cache.
+static DebugLoc inlineDebugLoc(DebugLoc OrigDL, DILocation *InlinedAt,
+                               LLVMContext &Ctx,
+                               DenseMap<const MDNode *, MDNode *> &IANodes) {
+  auto IA = DebugLoc::appendInlinedAt(OrigDL, InlinedAt, Ctx, IANodes);
+  return DebugLoc::get(OrigDL.getLine(), OrigDL.getCol(), OrigDL.getScope(),
+                       IA);
+}
+
+/// Returns the LoopID for a loop which has has been cloned from another
+/// function for inlining with the new inlined-at start and end locs.
+static MDNode *inlineLoopID(MDNode *OrigLoopId, DILocation *InlinedAt,
+                            LLVMContext &Ctx,
+                            DenseMap<const MDNode *, MDNode *> &IANodes) {
+  assert(OrigLoopId && OrigLoopId->getNumOperands() > 0 &&
+         "Loop ID needs at least one operand");
+  assert(OrigLoopId && OrigLoopId->getOperand(0) == OrigLoopId &&
+         "Loop ID should refer to itself");
+
+  // Save space for the self-referencial LoopID.
+  SmallVector<Metadata *, 4> MDs = {nullptr};
+
+  for (unsigned i = 1; i < OrigLoopId->getNumOperands(); ++i) {
+    if (MDNode *MD = dyn_cast<MDNode>(OrigLoopId->getOperand(i))) {
+      // Update the DILocations to encode the inlined-at metadata.
+      if (DILocation *DL = dyn_cast<DILocation>(MD))
+        MDs.push_back(inlineDebugLoc(DL, InlinedAt, Ctx, IANodes));
+      else
+        MDs.push_back(MD);
+    }
+  }
+
+  MDNode *NewLoopID = MDNode::getDistinct(Ctx, MDs);
+  // Insert the self-referencial LoopID.
+  NewLoopID->replaceOperandWith(0, NewLoopID);
+  return NewLoopID;
+}
+
 /// Update inlined instructions' line numbers to
 /// to encode location where these instructions are inlined.
 static void fixupLineNumbers(Function *Fn, Function::iterator FI,
                              Instruction *TheCall, bool CalleeHasDebugInfo) {
   const DebugLoc &TheCallDL = TheCall->getDebugLoc();
   if (!TheCallDL)
     return;
 
static void fixupLineNumbers(Function *Fn, Function::iterator FI,
   // Cache the inlined-at nodes as they're built so they are reused, without
   // this every instruction's inlined-at chain would become distinct from each
   // other.
   DenseMap<const MDNode *, MDNode *> IANodes;
 
   for (; FI != Fn->end(); ++FI) {
     for (BasicBlock::iterator BI = FI->begin(), BE = FI->end();
          BI != BE; ++BI) {
+      DebugLoc IDL = nullptr;
       if (DebugLoc DL = BI->getDebugLoc()) {
-        auto IA = DebugLoc::appendInlinedAt(DL, InlinedAtNode, BI->getContext(),
-                                            IANodes);
-        auto IDL = DebugLoc::get(DL.getLine(), DL.getCol(), DL.getScope(), IA);
+        IDL = inlineDebugLoc(DL, InlinedAtNode, BI->getContext(), IANodes);
         BI->setDebugLoc(IDL);
-        continue;
       }
 
+      // Loop metadata needs to be updated so that the start and end locs
+      // reference inlined-at locations.
+      if (MDNode *LoopID = BI->getMetadata(LLVMContext::MD_loop)) {
+        MDNode *NewLoopID = inlineLoopID(LoopID, InlinedAtNode, BI->getContext(), IANodes);
+        BI->setMetadata(LLVMContext::MD_loop, NewLoopID);
+      }
+      // Check if we have now updated an existing DL.
+      if (IDL)
+        continue;
+
       if (CalleeHasDebugInfo)
         continue;
 
       // If the inlined instruction has no line number, make it look as if it
       // originates from the call location. This is important for
       // ((__always_inline__, __nodebug__)) functions which must use caller
       // location for all instructions in their function body.
 

llvm/test/Transforms/Inline/inlined-loop-metadata.ll

+; This test checks that the !llvm.loop metadata has been updated after inlining
+; so that the start and end locations refer to the inlined DILocations.
+
+; RUN: opt -loop-vectorize -inline %s -S 2>&1 | FileCheck %s
+; CHECK: br i1 %{{.*}}, label %middle.block.i, label %vector.body.i, !dbg !{{[0-9]+}}, !llvm.loop [[VECTOR:![0-9]+]]
+; CHECK: br i1 %{{.*}}, label %for.cond.cleanup.loopexit.i, label %for.body.i, !dbg !{{[0-9]+}}, !llvm.loop [[SCALAR:![0-9]+]]
+; CHECK-DAG: [[VECTOR]] = distinct !{[[VECTOR]], [[START:![0-9]+]], [[END:![0-9]+]], [[IS_VECTORIZED:![0-9]+]]}
+; CHECK-DAG: [[SCALAR]] = distinct !{[[SCALAR]], [[START]], [[END]], [[NO_UNROLL:![0-9]+]], [[IS_VECTORIZED]]}
+; CHECK-DAG: [[IS_VECTORIZED]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK-DAG: [[NO_UNROLL]] = !{!"llvm.loop.unroll.runtime.disable"}
+
+; This IR can be generated by running:
+;   clang -emit-llvm -S -gmlt -O2 inlined.cpp -o before.ll -mllvm -opt-bisect-limit=53
+;
+; Where inlined.cpp contains:
+; extern int *Array;
+; static int bar(unsigned x)
+; {
+;   int Ret = 0;
+;   for (unsigned i = 0; i < x; ++i)
+;   {
+;     Ret += Array[i] * i;
+;   }
+;   return Ret;
+; }
+;
+; int foo(unsigned x)
+; {
+;   int Bar = bar(x);
+;   return Bar;
+; }
+
+; ModuleID = 'inlined.cpp'
+source_filename = "inlined.cpp"
+target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-windows-msvc19.16.27030"
+
+@"?Array@@3PEAHEA" = external dso_local local_unnamed_addr global i32*, align 8
+
+; Function Attrs: nounwind uwtable
+define dso_local i32 @"?foo@@YAHI@Z"(i32 %x) local_unnamed_addr !dbg !8 {
+entry:
+  %call = call fastcc i32 @"?bar@@YAHI@Z"(i32 %x), !dbg !10
+  ret i32 %call, !dbg !11
+}
+
+; Function Attrs: norecurse nounwind readonly uwtable
+define internal fastcc i32 @"?bar@@YAHI@Z"(i32 %x) unnamed_addr !dbg !12 {
+entry:
+  %cmp7 = icmp eq i32 %x, 0, !dbg !13
+  br i1 %cmp7, label %for.cond.cleanup, label %for.body.lr.ph, !dbg !13
+
+for.body.lr.ph:                                   ; preds = %entry
+  %0 = load i32*, i32** @"?Array@@3PEAHEA", align 8, !dbg !14, !tbaa !15
+  %wide.trip.count = zext i32 %x to i64, !dbg !14
+  br label %for.body, !dbg !13
+
+for.cond.cleanup.loopexit:                        ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ], !dbg !19
+  br label %for.cond.cleanup, !dbg !20
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  %Ret.0.lcssa = phi i32 [ 0, %entry ], [ %add.lcssa, %for.cond.cleanup.loopexit ], !dbg !14
+  ret i32 %Ret.0.lcssa, !dbg !20
+
+for.body:                                         ; preds = %for.body, %for.body.lr.ph
+  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %Ret.08 = phi i32 [ 0, %for.body.lr.ph ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %0, i64 %indvars.iv, !dbg !19
+  %1 = load i32, i32* %arrayidx, align 4, !dbg !19, !tbaa !21
+  %2 = trunc i64 %indvars.iv to i32, !dbg !19
+  %mul = mul i32 %1, %2, !dbg !19
+  %add = add i32 %mul, %Ret.08, !dbg !19
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !13
+  %exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count, !dbg !13
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body, !dbg !13, !llvm.loop !23
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6}
+!llvm.ident = !{!7}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 9.0.0 (https://github.com/llvm/llvm-project.git b1e28d9b6a16380ccf1456fe0695f639364407a9)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "inlined.cpp", directory: "")
+!2 = !{}
+!3 = !{i32 2, !"CodeView", i32 1}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 2}
+!6 = !{i32 7, !"PIC Level", i32 2}
+!7 = !{!"clang version 9.0.0 (https://github.com/llvm/llvm-project.git b1e28d9b6a16380ccf1456fe0695f639364407a9)"}
+!8 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 13, type: !9, scopeLine: 14, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!9 = !DISubroutineType(types: !2)
+!10 = !DILocation(line: 15, scope: !8)
+!11 = !DILocation(line: 16, scope: !8)
+!12 = distinct !DISubprogram(name: "bar", scope: !1, file: !1, line: 3, type: !9, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagLocalToUnit | DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!13 = !DILocation(line: 6, scope: !12)
+!14 = !DILocation(line: 0, scope: !12)
+!15 = !{!16, !16, i64 0}
+!16 = !{!"any pointer", !17, i64 0}
+!17 = !{!"omnipotent char", !18, i64 0}
+!18 = !{!"Simple C++ TBAA"}
+!19 = !DILocation(line: 8, scope: !12)
+!20 = !DILocation(line: 10, scope: !12)
+!21 = !{!22, !22, i64 0}
+!22 = !{!"int", !17, i64 0}
+!23 = distinct !{!23, !13, !24}
+!24 = !DILocation(line: 9, scope: !12)
+