llvm-dwarfdump][Statistics] Make calculations of vars in global scope more accurate

[krisb]

Summary

It isn't known how many times we've seen the same variable or member in
the global scope (unlike in functions), but there still can be some duplicates
among different CUs.
So, this patch proposes to count variables in the global scope just as a sum of
the number of vars, constant members and artificial entities.

[aprantl]

llvm/tools/llvm-dwarfdump/Statistics.cpp

329–330

How does this condition ensure that this is a constant member now?

[krisb]

Refactor checks for constant members a bit.

llvm/tools/llvm-dwarfdump/Statistics.cpp

329–330

The function returns on lines 259-262 (of original code) if Die is a member, but not a constant one, so it's not possible to reach this 'if' for a non-constant member.
But, yeah, it's a bit unclear. I moved the check for constantness to the top of the function, to be clear we do not consider non-constant members at all. This looks better to me.

[aprantl]

Nice.

llvm/test/tools/llvm-dwarfdump/X86/stats-multiple-cu-members.ll

+; RUN: llc -O0 %s -o - -filetype=obj \
+; RUN:   | llvm-dwarfdump -statistics - | FileCheck %s
+
+; This checks that if DW_TAG_structure_type duplicates in multiple CU,
+; the number of total vars ("source variables") will include every copy,
+; so the number of "variables with location" doesn't exceed the number of total vars.
+
+; $ cat test.h
+; struct s { static const int ss = 42; };
+;
+; $ cat test1.cpp
+; #include "test.h"
+; s S1;
+;
+; $ cat test2.cpp
+; #include "test.h"
+; s S2;
+
+; CHECK:      "source variables":4
+; CHECK-SAME: "variables with location":4
+
+source_filename = "llvm-link"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.s = type { i8 }
+%struct.s.1 = type { i8 }
+
+@S1 = dso_local global %struct.s zeroinitializer, align 1, !dbg !0
+@S2 = dso_local global %struct.s.1 zeroinitializer, align 1, !dbg !13
+
+!llvm.dbg.cu = !{!2, !15}
+!llvm.ident = !{!18, !18}
+!llvm.module.flags = !{!19, !20, !21}
+
+!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+!1 = distinct !DIGlobalVariable(name: "S1", scope: !2, file: !3, line: 2, type: !6, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !3, producer: "clang version 10.0.0", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, retainedTypes: !5, globals: !12, splitDebugInlining: false, nameTableKind: None)
+!3 = !DIFile(filename: "test1.cpp", directory: "/")
+!4 = !{}
+!5 = !{!6}
+!6 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s", file: !7, line: 1, size: 8, flags: DIFlagTypePassByValue, elements: !8, identifier: "_ZTS1s")
+!7 = !DIFile(filename: "./test.h", directory: "/")
+!8 = !{!9}
+!9 = !DIDerivedType(tag: DW_TAG_member, name: "ss", scope: !6, file: !7, line: 1, baseType: !10, flags: DIFlagStaticMember, extraData: i32 42)
+!10 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !11)
+!11 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!12 = !{!0}
+!13 = !DIGlobalVariableExpression(var: !14, expr: !DIExpression())
+!14 = distinct !DIGlobalVariable(name: "S2", scope: !15, file: !16, line: 2, type: !6, isLocal: false, isDefinition: true)
+!15 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !16, producer: "clang version 10.0.0", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, retainedTypes: !22, globals: !17, splitDebugInlining: false, nameTableKind: None)
+!16 = !DIFile(filename: "test2.cpp", directory: "/")
+!17 = !{!13}
+!18 = !{!"clang version 10.0.0"}
+!19 = !{i32 7, !"Dwarf Version", i32 4}
+!20 = !{i32 2, !"Debug Info Version", i32 3}
+!21 = !{i32 1, !"wchar_size", i32 4}
+!22 = !{!23}
+!23 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s", file: !7, line: 1, size: 8, flags: DIFlagTypePassByValue, elements: !24, identifier: "_ZTS1s")
+!24 = !{!25}
+!25 = !DIDerivedType(tag: DW_TAG_member, name: "ss", scope: !23, file: !7, line: 1, baseType: !10, flags: DIFlagStaticMember, extraData: i32 42)

llvm/tools/llvm-dwarfdump/Statistics.cpp

struct PerFunctionStats {
   unsigned NumFnOutOfLine = 0;
   /// Number of inlined instances that have abstract origins.
   unsigned NumAbstractOrigins = 0;
   /// Number of variables and parameters with location across all inlined
   /// instances.
   unsigned TotalVarWithLoc = 0;
   /// Number of constants with location across all inlined instances.
   unsigned ConstantMembers = 0;
+  /// Number of arificial variables, parameters or members across all instances.
+  unsigned NumArtificial = 0;
   /// List of all Variables and parameters in this function.
   StringSet<> VarsInFunction;
   /// Compile units also cover a PC range, but have this flag set to false.
   bool IsFunction = false;
   /// Function has source location information.
   bool HasSourceLocation = false;
   /// Number of function parameters.
   unsigned NumParams = 0;
static void collectStatsForDie(DWARFDie Die, std::string FnPrefix,
                                std::string VarPrefix, uint64_t BytesInScope,
                                uint32_t InlineDepth,
                                StringMap<PerFunctionStats> &FnStatMap,
                                GlobalStats &GlobalStats,
                                LocationStats &LocStats) {
   bool HasLoc = false;
   bool HasSrcLoc = false;
   bool HasType = false;
-  bool IsArtificial = false;
   uint64_t BytesCovered = 0;
   uint64_t BytesEntryValuesCovered = 0;
   auto &FnStats = FnStatMap[FnPrefix];
   bool IsParam = Die.getTag() == dwarf::DW_TAG_formal_parameter;
   bool IsVariable = Die.getTag() == dwarf::DW_TAG_variable;
+  bool IsConstantMember = Die.getTag() == dwarf::DW_TAG_member &&
+                          Die.find(dwarf::DW_AT_const_value);
 
   if (Die.getTag() == dwarf::DW_TAG_call_site ||
       Die.getTag() == dwarf::DW_TAG_GNU_call_site) {
     GlobalStats.CallSiteDIEs++;
     return;
   }
 
   if (Die.getTag() == dwarf::DW_TAG_call_site_parameter ||
       Die.getTag() == dwarf::DW_TAG_GNU_call_site_parameter) {
     GlobalStats.CallSiteParamDIEs++;
     return;
   }
 
-  if (!IsParam && !IsVariable && Die.getTag() != dwarf::DW_TAG_member) {
+  if (!IsParam && !IsVariable && !IsConstantMember) {
     // Not a variable or constant member.
     return;
   }
 
   // Ignore declarations of global variables.
   if (IsVariable && Die.find(dwarf::DW_AT_declaration))
     return;
 
   if (Die.findRecursively(dwarf::DW_AT_decl_file) &&
       Die.findRecursively(dwarf::DW_AT_decl_line))
     HasSrcLoc = true;
 
   if (Die.findRecursively(dwarf::DW_AT_type))
     HasType = true;
 
-  if (Die.find(dwarf::DW_AT_artificial))
-    IsArtificial = true;
-
   auto IsEntryValue = [&](ArrayRef<uint8_t> D) -> bool {
     DWARFUnit *U = Die.getDwarfUnit();
     DataExtractor Data(toStringRef(D),
                        Die.getDwarfUnit()->getContext().isLittleEndian(), 0);
     DWARFExpression Expression(Data, U->getVersion(), U->getAddressByteSize());
     // Consider the expression containing the DW_OP_entry_value as
     // an entry value.
     return llvm::any_of(Expression, [](DWARFExpression::Operation &Op) {
       return Op.getCode() == dwarf::DW_OP_entry_value ||
              Op.getCode() == dwarf::DW_OP_GNU_entry_value;
     });
   };
 
   if (Die.find(dwarf::DW_AT_const_value)) {
     // This catches constant members *and* variables.
     HasLoc = true;
     BytesCovered = BytesInScope;
   } else {
-    if (Die.getTag() == dwarf::DW_TAG_member) {
-      // Non-const member.
-      return;
-    }
     // Handle variables and function arguments.
     Expected<std::vector<DWARFLocationExpression>> Loc =
         Die.getLocations(dwarf::DW_AT_location);
     if (!Loc) {
       consumeError(Loc.takeError());
     } else {
       HasLoc = true;
       // Get PC coverage.
static void collectStatsForDie(DWARFDie Die, std::string FnPrefix,
   if (DWARFDie D =
           Die.getAttributeValueAsReferencedDie(dwarf::DW_AT_abstract_origin))
     Die = D;
 
   std::string VarID = constructDieID(Die, VarPrefix);
   FnStats.VarsInFunction.insert(VarID);
 
   if (BytesInScope) {
-    FnStats.TotalVarWithLoc += (unsigned)HasLoc;
     // Turns out we have a lot of ranges that extend past the lexical scope.
     GlobalStats.ScopeBytesCovered += std::min(BytesInScope, BytesCovered);
     GlobalStats.ScopeBytes += BytesInScope;
     GlobalStats.ScopeEntryValueBytesCovered += BytesEntryValuesCovered;
     if (IsParam) {
       GlobalStats.ParamScopeBytesCovered +=
           std::min(BytesInScope, BytesCovered);
       GlobalStats.ParamScopeBytes += BytesInScope;
       GlobalStats.ParamScopeEntryValueBytesCovered += BytesEntryValuesCovered;
     } else if (IsVariable) {
       GlobalStats.VarScopeBytesCovered += std::min(BytesInScope, BytesCovered);
       GlobalStats.VarScopeBytes += BytesInScope;
       GlobalStats.VarScopeEntryValueBytesCovered += BytesEntryValuesCovered;
     }
     assert(GlobalStats.ScopeBytesCovered <= GlobalStats.ScopeBytes);
-  } else if (Die.getTag() == dwarf::DW_TAG_member) {
+  }
+
+  if (IsConstantMember) {
     FnStats.ConstantMembers++;
-  } else {
-    FnStats.TotalVarWithLoc += (unsigned)HasLoc;
+    return;
+  }
+
+
+  if (Die.find(dwarf::DW_AT_artificial)) {
+    FnStats.NumArtificial++;
+    return;
   }
-  if (!IsArtificial) {
-    if (IsParam) {
-      FnStats.NumParams++;
-      if (HasType)
-        FnStats.NumParamTypes++;
-      if (HasSrcLoc)
-        FnStats.NumParamSourceLocations++;
-      if (HasLoc)
-        FnStats.NumParamLocations++;
-    } else if (IsVariable) {
-      FnStats.NumVars++;
-      if (HasType)
-        FnStats.NumVarTypes++;
-      if (HasSrcLoc)
-        FnStats.NumVarSourceLocations++;
-      if (HasLoc)
-        FnStats.NumVarLocations++;
-    }
-  }
-}
+
 
 /// Recursively collect debug info quality metrics.
 static void collectStatsRecursive(DWARFDie Die, std::string FnPrefix,
                                   std::string VarPrefix, uint64_t BytesInScope,
                                   uint32_t InlineDepth,
                                   StringMap<PerFunctionStats> &FnStatMap,
                                   GlobalStats &GlobalStats,
                                   LocationStats &LocStats) {
bool collectStatsForObjectFile(ObjectFile &Obj, DWARFContext &DICtx,
   unsigned VarWithSrcLoc = 0;
   unsigned VarWithLoc = 0;
   for (auto &Entry : Statistics) {
     PerFunctionStats &Stats = Entry.getValue();
     unsigned TotalVars = Stats.VarsInFunction.size() *
                          (Stats.NumFnInlined + Stats.NumFnOutOfLine);
     // Count variables in global scope.
     if (!Stats.IsFunction)
-      TotalVars += Stats.VarsInFunction.size();
+      TotalVars = Stats.NumVars + Stats.ConstantMembers + Stats.NumArtificial;
     unsigned Constants = Stats.ConstantMembers;
     VarParamWithLoc += Stats.TotalVarWithLoc + Constants;
     VarParamTotal += TotalVars;
     VarParamUnique += Stats.VarsInFunction.size();
     LLVM_DEBUG(for (auto &V
                     : Stats.VarsInFunction) llvm::dbgs()
                << Entry.getKey() << ": " << V.getKey() << "\n");
     NumFunctions += Stats.IsFunction;