[DebugInfo] getMergedLocation: match scopes based on their location (#132286)

dzhidzhoev · web-flow · commit 6462fad3d04d · 2025-04-18T13:57:28.000+02:00
getMergedLocation uses a common parent scope of the two input locations for an output location. It doesn't consider the case when the common parent scope is from a file other than L1's and L2's files. In that case, it produces a merged location with an erroneous scope (#122846). In some cases, such as #125780 (comment), L1, L2 having a common parent scope from another file indicate that the code at L1 and L2 is included from the same source location. With this commit, getMergedLocation detects that L1, L2, or their common parent scope files are different. If so, it assumes that L1 and L2 were included from some source location, and tries to attach the output location to a scope with the nearest common source location with regard to L1 and L2. If the nearest common location is also from another file, getMergedLocation returns it as a merged location, assuming that L1 and L2 belong to files that were both included in the nearest common location. Fixes #122846.
diff --git a/llvm/lib/IR/DebugInfoMetadata.cpp b/llvm/lib/IR/DebugInfoMetadata.cpp
@@ -13,7 +13,7 @@
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "LLVMContextImpl.h"
 #include "MetadataImpl.h"
-#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/IR/DebugProgramInstruction.h"
@@ -125,6 +125,98 @@ DILocation *DILocation::getMergedLocations(ArrayRef<DILocation *> Locs) {
   return Merged;
 }
 
+static DILexicalBlockBase *cloneAndReplaceParentScope(DILexicalBlockBase *LBB,
+                                                      DIScope *NewParent) {
+  TempMDNode ClonedScope = LBB->clone();
+  cast<DILexicalBlockBase>(*ClonedScope).replaceScope(NewParent);
+  return cast<DILexicalBlockBase>(
+      MDNode::replaceWithUniqued(std::move(ClonedScope)));
+}
+
+using LineColumn = std::pair<unsigned /* Line */, unsigned /* Column */>;
+
+/// Returns the location of DILocalScope, if present, or a default value.
+static LineColumn getLocalScopeLocationOr(DIScope *S, LineColumn Default) {
+  assert(isa<DILocalScope>(S) && "Expected DILocalScope.");
+
+  if (isa<DILexicalBlockFile>(S))
+    return Default;
+  if (auto *LB = dyn_cast<DILexicalBlock>(S))
+    return {LB->getLine(), LB->getColumn()};
+  if (auto *SP = dyn_cast<DISubprogram>(S))
+    return {SP->getLine(), 0u};
+
+  llvm_unreachable("Unhandled type of DILocalScope.");
+}
+
+// Returns the nearest matching scope inside a subprogram.
+template <typename MatcherT>
+static std::pair<DIScope *, LineColumn>
+getNearestMatchingScope(const DILocation *L1, const DILocation *L2) {
+  MatcherT Matcher;
+
+  DIScope *S1 = L1->getScope();
+  DIScope *S2 = L2->getScope();
+
+  LineColumn Loc1(L1->getLine(), L1->getColumn());
+  for (; S1; S1 = S1->getScope()) {
+    Loc1 = getLocalScopeLocationOr(S1, Loc1);
+    Matcher.insert(S1, Loc1);
+    if (isa<DISubprogram>(S1))
+      break;
+  }
+
+  LineColumn Loc2(L2->getLine(), L2->getColumn());
+  for (; S2; S2 = S2->getScope()) {
+    Loc2 = getLocalScopeLocationOr(S2, Loc2);
+
+    if (DIScope *S = Matcher.match(S2, Loc2))
+      return std::make_pair(S, Loc2);
+
+    if (isa<DISubprogram>(S2))
+      break;
+  }
+  return std::make_pair(nullptr, LineColumn(L2->getLine(), L2->getColumn()));
+}
+
+// Matches equal scopes.
+struct EqualScopesMatcher {
+  SmallPtrSet<DIScope *, 8> Scopes;
+
+  void insert(DIScope *S, LineColumn Loc) { Scopes.insert(S); }
+
+  DIScope *match(DIScope *S, LineColumn Loc) {
+    return Scopes.contains(S) ? S : nullptr;
+  }
+};
+
+// Matches scopes with the same location.
+struct ScopeLocationsMatcher {
+  SmallMapVector<std::pair<DIFile *, LineColumn>, SmallSetVector<DIScope *, 8>,
+                 8>
+      Scopes;
+
+  void insert(DIScope *S, LineColumn Loc) {
+    Scopes[{S->getFile(), Loc}].insert(S);
+  }
+
+  DIScope *match(DIScope *S, LineColumn Loc) {
+    auto ScopesAtLoc = Scopes.find({S->getFile(), Loc});
+    // No scope found with the given location.
+    if (ScopesAtLoc == Scopes.end())
+      return nullptr;
+
+    // Prefer S over other scopes with the same location.
+    if (ScopesAtLoc->second.contains(S))
+      return S;
+
+    if (!ScopesAtLoc->second.empty())
+      return *ScopesAtLoc->second.begin();
+
+    llvm_unreachable("Scopes must not have empty entries.");
+  }
+};
+
 DILocation *DILocation::getMergedLocation(DILocation *LocA, DILocation *LocB) {
   if (!LocA || !LocB)
     return nullptr;
@@ -208,28 +300,31 @@ DILocation *DILocation::getMergedLocation(DILocation *LocA, DILocation *LocB) {
     if (L1->getScope()->getSubprogram() != L2->getScope()->getSubprogram())
       return nullptr;
 
-    // Return the nearest common scope inside a subprogram.
-    auto GetNearestCommonScope = [](DIScope *S1, DIScope *S2) -> DIScope * {
-      SmallPtrSet<DIScope *, 8> Scopes;
-      for (; S1; S1 = S1->getScope()) {
-        Scopes.insert(S1);
-        if (isa<DISubprogram>(S1))
-          break;
-      }
-
-      for (; S2; S2 = S2->getScope()) {
-        if (Scopes.count(S2))
-          return S2;
-        if (isa<DISubprogram>(S2))
-          break;
-      }
-
-      return nullptr;
-    };
-
-    auto Scope = GetNearestCommonScope(L1->getScope(), L2->getScope());
+    // Find nearest common scope inside subprogram.
+    DIScope *Scope = getNearestMatchingScope<EqualScopesMatcher>(L1, L2).first;
     assert(Scope && "No common scope in the same subprogram?");
 
+    // Try using the nearest scope with common location if files are different.
+    if (Scope->getFile() != L1->getFile() || L1->getFile() != L2->getFile()) {
+      auto [CommonLocScope, CommonLoc] =
+          getNearestMatchingScope<ScopeLocationsMatcher>(L1, L2);
+
+      // If CommonLocScope is a DILexicalBlockBase, clone it and locate
+      // a new scope inside the nearest common scope to preserve
+      // lexical blocks structure.
+      if (auto *LBB = dyn_cast<DILexicalBlockBase>(CommonLocScope);
+          LBB && LBB != Scope)
+        CommonLocScope = cloneAndReplaceParentScope(LBB, Scope);
+
+      Scope = CommonLocScope;
+
+      // If files are still different, assume that L1 and L2 were "included"
+      // from CommonLoc. Use it as merged location.
+      if (Scope->getFile() != L1->getFile() || L1->getFile() != L2->getFile())
+        return DILocation::get(C, CommonLoc.first, CommonLoc.second,
+                               CommonLocScope, InlinedAt);
+    }
+
     bool SameLine = L1->getLine() == L2->getLine();
     bool SameCol = L1->getColumn() == L2->getColumn();
     unsigned Line = SameLine ? L1->getLine() : 0;
@@ -1187,10 +1282,8 @@ DILocalScope *DILocalScope::cloneScopeForSubprogram(
   // cached result).
   DIScope *UpdatedScope = CachedResult ? CachedResult : &NewSP;
   for (DIScope *ScopeToUpdate : reverse(ScopeChain)) {
-    TempMDNode ClonedScope = ScopeToUpdate->clone();
-    cast<DILexicalBlockBase>(*ClonedScope).replaceScope(UpdatedScope);
-    UpdatedScope =
-        cast<DIScope>(MDNode::replaceWithUniqued(std::move(ClonedScope)));
+    UpdatedScope = cloneAndReplaceParentScope(
+        cast<DILexicalBlockBase>(ScopeToUpdate), UpdatedScope);
     Cache[ScopeToUpdate] = UpdatedScope;
   }
 
diff --git a/llvm/test/DebugInfo/AArch64/merge-nested-block-loc.ll b/llvm/test/DebugInfo/AArch64/merge-nested-block-loc.ll
@@ -0,0 +1,79 @@
+; RUN: opt -mtriple=aarch64-unknown-linux-gnu -S %s -passes=sroa -o - | FileCheck %s
+
+; In this test we want to ensure that the merged location of phi instruction
+; belongs to the correct scope (DILexicalBlockFile), so that line number
+; of that location belongs to the corresponding file.
+
+; Generated with clang from
+; # 1 "1.c" 1
+; # 1 "1.c" 2
+; int foo(int a) {
+;   int i = 0;
+;   if ((a & 1) == 1) {
+;     a -= 1;
+; # 1 "m.c" 1
+; # 40 "m.c"
+; i += a;
+; i -= 10*a;
+; i *= a*a;
+; # 6 "1.c" 2
+;  } else {
+;     a += 3;
+; # 1 "m.c" 1
+; # 40 "m.c"
+; i += a;
+; i -= 10*a;
+; i *= a*a;
+; # 9 "1.c" 2
+;  }
+;   return i;
+; }
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128-Fn32"
+target triple = "aarch64-unknown-linux-gnu"
+
+define i32 @foo() !dbg !3 {
+; CHECK:    phi i32 {{.*}}, !dbg [[PHILOC:![0-9]+]]
+;
+entry:
+  %i = alloca i32, align 4
+  br i1 false, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i32 1, ptr %i, align 4, !dbg !7
+  br label %if.end
+
+if.else:                                          ; preds = %entry
+  store i32 0, ptr %i, align 4, !dbg !12
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  %0 = load i32, ptr %i, align 4
+  ret i32 0
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "clang version 21.0.0git", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
+!1 = !DIFile(filename: "repro.c", directory: "")
+!2 = !{i32 2, !"Debug Info Version", i32 3}
+!3 = distinct !DISubprogram(name: "foo", scope: !4, file: !4, line: 1, type: !5, scopeLine: 1, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !6)
+!4 = !DIFile(filename: "1.c", directory: "")
+!5 = !DISubroutineType(types: !6)
+!6 = !{}
+!7 = !DILocation(line: 42, column: 3, scope: !8)
+!8 = !DILexicalBlockFile(scope: !10, file: !9, discriminator: 0)
+!9 = !DIFile(filename: "m.c", directory: "")
+!10 = distinct !DILexicalBlock(scope: !11, file: !4, line: 3, column: 21)
+!11 = distinct !DILexicalBlock(scope: !3, file: !4, line: 3, column: 7)
+!12 = !DILocation(line: 42, column: 3, scope: !13)
+!13 = !DILexicalBlockFile(scope: !14, file: !9, discriminator: 0)
+!14 = distinct !DILexicalBlock(scope: !11, file: !4, line: 6, column: 9)
+
+; CHECK: [[SP:![0-9]+]] = distinct !DISubprogram(name: "foo", scope: [[FILE1:![0-9]+]], file: [[FILE1]], line: 1
+; CHECK: [[FILE1]] = !DIFile(filename: "1.c", directory: "")
+; CHECK: [[PHILOC]] = !DILocation(line: 42, column: 3, scope: [[LBF:![0-9]+]])
+; CHECK: [[LBF]] = !DILexicalBlockFile(scope: [[LB:![0-9]+]], file: [[FILE2:![0-9]+]], discriminator: 0)
+; CHECK: [[FILE2]] = !DIFile(filename: "m.c", directory: "")
+; CHECK: [[LB]] = distinct !DILexicalBlock(scope: [[SP]], file: [[FILE1]], line: 3, column: 7)
diff --git a/llvm/test/DebugInfo/AArch64/merge-nested-block-loc2.ll b/llvm/test/DebugInfo/AArch64/merge-nested-block-loc2.ll
@@ -0,0 +1,130 @@
+; RUN: opt -mtriple=aarch64-unknown-linux-gnu -S %s -passes=sroa -o - | FileCheck %s
+
+; In this test we want to ensure that getMergedLocations uses common include
+; location if incoming locations belong to different files.
+; The location of phi instruction merged from locations of %mul3 and %mul10
+; should be the location of do-loop lexical block from y.c.
+
+; Generated with clang from
+;
+; main.c:
+;   int foo(int a) {
+;     int i = 0;
+;     if ((a & 1) == 1) {
+;       a -= 1;
+;   #define A
+;   #include "y.c"
+;    } else {
+;       a += 3;
+;   #undef A
+;   #include "y.c"
+;    }
+;     return i;
+;   }
+;
+; y.c:
+;   # 300 "y.c" 1
+;   do {
+;   #ifdef A
+;   #include "z1.c"
+;   #else
+;   #include "z2.c"
+;   #endif
+;   } while (0);
+;
+; z1.c:
+;   # 100 "z1.c" 1
+;   i += a;
+;   i -= 10*a;
+;   i *= a*a;
+;
+; z2.c:
+;   # 200 "z1.c" 1
+;   i += a;
+;   i -= 10*a;
+;   i *= a*a;
+;
+; Preprocessed source:
+;
+; # 1 "main.c"
+; int foo(int a) {
+;   int i = 0;
+;   if ((a & 1) == 1) {
+;     a -= 1;
+; # 300 "y.c" 1
+; do {
+; # 100 "z1.c" 1
+; i += a;
+; i -= 10*a;
+; i *= a*a;
+; # 303 "y.c" 2
+; } while (0);
+; # 7 "main.c" 2
+;  } else {
+;     a += 3;
+; # 300 "y.c" 1
+; do {
+; # 200 "z2.c" 1
+; i += a;
+; i -= 10*a;
+; i *= a*a;
+; # 305 "y.c" 2
+; } while (0);
+; # 11 "main.c" 2
+;  }
+;   return i;
+; }
+
+target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-n32:64-S128-Fn32"
+target triple = "arm64-apple-macosx15.0.0"
+
+define i32 @foo() !dbg !3 {
+; CHECK:    phi i32 {{.*}}, !dbg [[PHILOC:![0-9]+]]
+;
+entry:
+  %i = alloca i32, align 4
+  br i1 false, label %do.body, label %if.else
+
+do.body:                                          ; preds = %entry
+  store i32 1, ptr %i, align 4, !dbg !6
+  br label %if.end
+
+if.else:                                          ; preds = %entry
+  store i32 0, ptr %i, align 4, !dbg !14
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %do.body
+  %0 = load i32, ptr %i, align 4
+  ret i32 0
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "clang version 21.0.0git", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: Apple, sysroot: "/")
+!1 = !DIFile(filename: "main.c", directory: "")
+!2 = !{i32 2, !"Debug Info Version", i32 3}
+!3 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 1, type: !4, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !5)
+!4 = !DISubroutineType(types: !5)
+!5 = !{}
+!6 = !DILocation(line: 102, column: 3, scope: !7)
+!7 = !DILexicalBlockFile(scope: !9, file: !8, discriminator: 0)
+!8 = !DIFile(filename: "z1.c", directory: "")
+!9 = distinct !DILexicalBlock(scope: !11, file: !10, line: 300, column: 4)
+!10 = !DIFile(filename: "y.c", directory: "")
+!11 = !DILexicalBlockFile(scope: !12, file: !10, discriminator: 0)
+!12 = distinct !DILexicalBlock(scope: !13, file: !1, line: 3, column: 21)
+!13 = distinct !DILexicalBlock(scope: !3, file: !1, line: 3, column: 7)
+!14 = !DILocation(line: 202, column: 3, scope: !15)
+!15 = !DILexicalBlockFile(scope: !17, file: !16, discriminator: 0)
+!16 = !DIFile(filename: "z2.c", directory: "")
+!17 = distinct !DILexicalBlock(scope: !18, file: !10, line: 300, column: 4)
+!18 = !DILexicalBlockFile(scope: !19, file: !10, discriminator: 0)
+!19 = distinct !DILexicalBlock(scope: !13, file: !1, line: 7, column: 9)
+
+; CHECK: [[FILE_MAIN:![0-9]+]] = !DIFile(filename: "main.c"
+; CHECK: [[SP:![0-9]+]] = distinct !DISubprogram(name: "foo", scope: [[FILE_MAIN]], file: [[FILE_MAIN]], line: 1
+; CHECK: [[PHILOC]] = !DILocation(line: 300, column: 4, scope: [[BLOCK_Y:![0-9]+]])
+; CHECK-NEXT: [[BLOCK_Y]] = !DILexicalBlock(scope: [[BLOCK_MAIN:![0-9]+]], file: [[FILE_Y:![0-9]+]], line: 300, column: 4)
+; CHECK-NEXT: [[FILE_Y]] = !DIFile(filename: "y.c"
+; CHECK: [[BLOCK_MAIN]] = distinct !DILexicalBlock(scope: [[SP]], file: [[FILE_MAIN]], line: 3, column: 7)
diff --git a/llvm/unittests/IR/MetadataTest.cpp b/llvm/unittests/IR/MetadataTest.cpp
