[llvm] r364736 - [DebugInfo] Avoid adding too much indirection to pointer-valued variables

Jeremy Morse via llvm-commits llvm-commits at lists.llvm.org
Mon Jul 1 02:38:23 PDT 2019


Author: jmorse
Date: Mon Jul  1 02:38:23 2019
New Revision: 364736

URL: http://llvm.org/viewvc/llvm-project?rev=364736&view=rev
Log:
[DebugInfo] Avoid adding too much indirection to pointer-valued variables

This patch addresses PR41675, where a stack-pointer variable is dereferenced
too many times by its location expression, presenting a value on the stack as
the pointer to the stack.

The difference between a stack *pointer* DBG_VALUE and one that refers to a
value on the stack, is currently the indirect flag. However the DWARF backend
will also try to guess whether something is a memory location or not, based
on whether there is any computation in the location expression. By simply
prepending the stack offset to existing expressions, we can accidentally
convert a register location into a memory location, which introduces a
suprise (and unintended) dereference.

The solution is to add DW_OP_stack_value whenever we add a DIExpression
computation to a stack *pointer*. It's an implicit location computed on the
expression stack, thus needs to be flagged as a stack_value.

For the edge case where the offset is zero and the location could be a register
location, DIExpression::prepend will still generate opcodes, and thus
DW_OP_stack_value must still be added.

Differential Revision: https://reviews.llvm.org/D63429

Added:
    llvm/trunk/test/DebugInfo/MIR/X86/prolog-epilog-indirection.mir
Modified:
    llvm/trunk/include/llvm/IR/DebugInfoMetadata.h
    llvm/trunk/lib/CodeGen/PrologEpilogInserter.cpp
    llvm/trunk/lib/IR/DebugInfoMetadata.cpp

Modified: llvm/trunk/include/llvm/IR/DebugInfoMetadata.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IR/DebugInfoMetadata.h?rev=364736&r1=364735&r2=364736&view=diff
==============================================================================
--- llvm/trunk/include/llvm/IR/DebugInfoMetadata.h (original)
+++ llvm/trunk/include/llvm/IR/DebugInfoMetadata.h Mon Jul  1 02:38:23 2019
@@ -2464,6 +2464,10 @@ public:
   /// Return whether this is an implicit location description.
   bool isImplicit() const;
 
+  /// Return whether the location is computed on the expression stack, meaning
+  /// it cannot be a simple register location.
+  bool isComplex() const;
+
   /// Append \p Ops with operations to apply the \p Offset.
   static void appendOffset(SmallVectorImpl<uint64_t> &Ops, int64_t Offset);
 

Modified: llvm/trunk/lib/CodeGen/PrologEpilogInserter.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/PrologEpilogInserter.cpp?rev=364736&r1=364735&r2=364736&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/PrologEpilogInserter.cpp (original)
+++ llvm/trunk/lib/CodeGen/PrologEpilogInserter.cpp Mon Jul  1 02:38:23 2019
@@ -1200,6 +1200,16 @@ void PEI::replaceFrameIndices(MachineBas
         MI.getOperand(0).setIsDebug();
 
         const DIExpression *DIExpr = MI.getDebugExpression();
+
+        // If we have a direct DBG_VALUE, and its location expression isn't
+        // currently complex, then adding an offset will morph it into a
+        // complex location that is interpreted as being a memory address.
+        // This changes a pointer-valued variable to dereference that pointer,
+        // which is incorrect. Fix by adding DW_OP_stack_value.
+        unsigned PrependFlags = DIExpression::ApplyOffset;
+        if (!MI.isIndirectDebugValue() && !DIExpr->isComplex())
+          PrependFlags |= DIExpression::StackValue;
+
         // If we have DBG_VALUE that is indirect and has a Implicit location
         // expression need to insert a deref before prepending a Memory
         // location expression. Also after doing this we change the DBG_VALUE
@@ -1211,8 +1221,7 @@ void PEI::replaceFrameIndices(MachineBas
           // Make the DBG_VALUE direct.
           MI.getOperand(1).ChangeToRegister(0, false);
         }
-        DIExpr =
-            DIExpression::prepend(DIExpr, DIExpression::ApplyOffset, Offset);
+        DIExpr = DIExpression::prepend(DIExpr, PrependFlags, Offset);
         MI.getOperand(3).setMetadata(DIExpr);
         continue;
       }

Modified: llvm/trunk/lib/IR/DebugInfoMetadata.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/IR/DebugInfoMetadata.cpp?rev=364736&r1=364735&r2=364736&view=diff
==============================================================================
--- llvm/trunk/lib/IR/DebugInfoMetadata.cpp (original)
+++ llvm/trunk/lib/IR/DebugInfoMetadata.cpp Mon Jul  1 02:38:23 2019
@@ -926,6 +926,27 @@ bool DIExpression::isImplicit() const {
   return false;
 }
 
+bool DIExpression::isComplex() const {
+  if (!isValid())
+    return false;
+
+  if (getNumElements() == 0)
+    return false;
+
+  // If there are any elements other than fragment or tag_offset, then some
+  // kind of complex computation occurs.
+  for (const auto &It : expr_ops()) {
+    switch (It.getOp()) {
+      case dwarf::DW_OP_LLVM_tag_offset:
+      case dwarf::DW_OP_LLVM_fragment:
+        continue;
+      default: return true;
+    }
+  }
+
+  return false;
+}
+
 Optional<DIExpression::FragmentInfo>
 DIExpression::getFragmentInfo(expr_op_iterator Start, expr_op_iterator End) {
   for (auto I = Start; I != End; ++I)

Added: llvm/trunk/test/DebugInfo/MIR/X86/prolog-epilog-indirection.mir
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/DebugInfo/MIR/X86/prolog-epilog-indirection.mir?rev=364736&view=auto
==============================================================================
--- llvm/trunk/test/DebugInfo/MIR/X86/prolog-epilog-indirection.mir (added)
+++ llvm/trunk/test/DebugInfo/MIR/X86/prolog-epilog-indirection.mir Mon Jul  1 02:38:23 2019
@@ -0,0 +1,130 @@
+# RUN: llc %s -x mir -o - -mtriple=x86_64-unknown-unknown -run-pass=prologepilog | FileCheck %s
+#
+# Check when the DBG_VALUE on a stack slot below (for var "c") has its  stack
+# slot replaced with $rsp and a complex expression, it has DW_OP_stack_value
+# added. A direct reference to the stack slot is considered to be the _address_
+# of that stack slot, wheras its contents would be an indirect DBG_VALUE.
+#
+# Check too that for the same DBG_VALUE inst, with an indirect reference to
+# the stack slot, we do _not_ get DW_OP_plus_uconst added. This expression
+# should remain indirect, referring to the contents of the stack slot.
+#
+# CHECK:      ![[VAR:[0-9]+]] = !DILocalVariable(name: "c"
+# CHECK:      ![[VAR2:[0-9]+]] = !DILocalVariable(name: "asdf"
+# CHECK:      ![[VAR3:[0-9]+]] = !DILocalVariable(name: "bees"
+#
+# CHECK:      LEA64r $rsp
+# CHECK-NEXT: DBG_VALUE $rsp, $noreg, ![[VAR]], !DIExpression(DW_OP_plus_uconst, {{[0-9]+}}, DW_OP_stack_value)
+# CHECK-NEXT: DBG_VALUE $rsp, $noreg, ![[VAR2]], !DIExpression(DW_OP_plus_uconst, {{[0-9]+}}, DW_OP_stack_value, DW_OP_LLVM_fragment, 1, 2)
+# CHECK-NEXT: DBG_VALUE $rsp, $noreg, ![[VAR3]], !DIExpression(DW_OP_plus_uconst, {{[0-9]+}}, DW_OP_LLVM_tag_offset, 0, DW_OP_stack_value)
+# CHECK-NEXT: DBG_VALUE 1834104526
+# CHECK-NEXT: MOV64mr
+# CHECK-NEXT: DBG_VALUE $rsp, 0, ![[VAR]], !DIExpression(DW_OP_plus_uconst, {{[0-9]+}})
+
+--- |
+  ; ModuleID = 'out.ll'
+  source_filename = "abc.c"
+  target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-unknown-linux-gnu"
+  
+  @b = common dso_local local_unnamed_addr global i32* null, align 8, !dbg !0
+  @a = common dso_local local_unnamed_addr global i32 0, align 4, !dbg !6
+  
+  ; Function Attrs: nounwind uwtable
+  define dso_local i32 @main() local_unnamed_addr !dbg !14 {
+  entry:
+    %l_1081 = alloca i32, align 4
+    %0 = bitcast i32* %l_1081 to i8*, !dbg !20
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0), !dbg !20
+    call void @llvm.dbg.value(metadata i32 1834104526, metadata !18, metadata !DIExpression()), !dbg !21
+    call void @llvm.dbg.value(metadata i32* %l_1081, metadata !19, metadata !DIExpression()), !dbg !21
+    store i32* %l_1081, i32** @b, align 8, !dbg !22, !tbaa !23
+    store i32 9, i32* @a, align 4, !dbg !27, !tbaa !28
+    store i32 9, i32* %l_1081, align 4, !dbg !30, !tbaa !28
+    %call = call i32 (...) @optimize_me_not(), !dbg !31
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0), !dbg !32
+    ret i32 0, !dbg !32
+  }
+  
+  ; Function Attrs: argmemonly nounwind
+  declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)
+  
+  declare dso_local i32 @optimize_me_not(...) local_unnamed_addr
+  
+  ; Function Attrs: argmemonly nounwind
+  declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
+  
+  ; Function Attrs: nounwind readnone speculatable
+  declare void @llvm.dbg.value(metadata, metadata, metadata)
+  
+  !llvm.dbg.cu = !{!2}
+  !llvm.module.flags = !{!10, !11, !12}
+  !llvm.ident = !{!13}
+  
+  !0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+  !1 = distinct !DIGlobalVariable(name: "b", scope: !2, file: !3, line: 2, type: !9, isLocal: false, isDefinition: true)
+  !2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5, nameTableKind: None)
+  !3 = !DIFile(filename: "abc.c", directory: ".")
+  !4 = !{}
+  !5 = !{!6, !0}
+  !6 = !DIGlobalVariableExpression(var: !7, expr: !DIExpression())
+  !7 = distinct !DIGlobalVariable(name: "a", scope: !2, file: !3, line: 1, type: !8, isLocal: false, isDefinition: true)
+  !8 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+  !9 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !8, size: 64)
+  !10 = !{i32 2, !"Dwarf Version", i32 4}
+  !11 = !{i32 2, !"Debug Info Version", i32 3}
+  !12 = !{i32 1, !"wchar_size", i32 4}
+  !13 = !{!"clang"}
+  !14 = distinct !DISubprogram(name: "main", scope: !3, file: !3, line: 3, type: !15, scopeLine: 3, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !17)
+  !15 = !DISubroutineType(types: !16)
+  !16 = !{!8}
+  !17 = !{!18, !19, !33, !34}
+  !18 = !DILocalVariable(name: "l_1081", scope: !14, file: !3, line: 4, type: !8)
+  !19 = !DILocalVariable(name: "c", scope: !14, file: !3, line: 5, type: !9)
+  !20 = !DILocation(line: 4, column: 3, scope: !14)
+  !21 = !DILocation(line: 0, scope: !14)
+  !22 = !DILocation(line: 6, column: 5, scope: !14)
+  !23 = !{!24, !24, i64 0}
+  !24 = !{!"any pointer", !25, i64 0}
+  !25 = !{!"omnipotent char", !26, i64 0}
+  !26 = !{!"Simple C/C++ TBAA"}
+  !27 = !DILocation(line: 7, column: 10, scope: !14)
+  !28 = !{!29, !29, i64 0}
+  !29 = !{!"int", !25, i64 0}
+  !30 = !DILocation(line: 7, column: 6, scope: !14)
+  !31 = !DILocation(line: 8, column: 3, scope: !14)
+  !32 = !DILocation(line: 9, column: 1, scope: !14)
+  !33 = !DILocalVariable(name: "asdf", scope: !14, file: !3, line: 4, type: !8)
+  !34 = !DILocalVariable(name: "bees", scope: !14, file: !3, line: 4, type: !8)
+
+...
+---
+name:            main
+alignment:       4
+tracksRegLiveness: true
+frameInfo:       
+  maxAlignment:    4
+  hasCalls:        true
+stack:           
+  - { id: 0, name: l_1081, type: default, offset: 0, size: 4, alignment: 4, 
+      callee-saved-register: '', callee-saved-restored: true, 
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+body:             |
+  bb.0.entry:
+    renamable $rax = LEA64r %stack.0.l_1081, 1, $noreg, 0, $noreg
+    DBG_VALUE %stack.0.l_1081, $noreg, !19, !DIExpression(), debug-location !21
+    DBG_VALUE %stack.0.l_1081, $noreg, !33, !DIExpression(DW_OP_LLVM_fragment, 1, 2), debug-location !21
+    DBG_VALUE %stack.0.l_1081, $noreg, !34, !DIExpression(DW_OP_LLVM_tag_offset, 0), debug-location !21
+    DBG_VALUE 1834104526, $noreg, !18, !DIExpression(), debug-location !21
+    MOV64mr $rip, 1, $noreg, @b, $noreg, killed renamable $rax, debug-location !22 :: (store 8 into @b, !tbaa !23)
+    DBG_VALUE %stack.0.l_1081, 0, !19, !DIExpression(), debug-location !21
+    MOV32mi $rip, 1, $noreg, @a, $noreg, 9, debug-location !27 :: (store 4 into @a, !tbaa !28)
+    MOV32mi %stack.0.l_1081, 1, $noreg, 0, $noreg, 9, debug-location !30 :: (store 4 into %ir.l_1081, !tbaa !28)
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp, debug-location !31
+    dead $eax = MOV32r0 implicit-def dead $eflags, implicit-def $al, debug-location !31
+    CALL64pcrel32 @optimize_me_not, csr_64, implicit $rsp, implicit $ssp, implicit $al, implicit-def $rsp, implicit-def $ssp, implicit-def dead $eax, debug-location !31
+    ADJCALLSTACKUP64 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp, debug-location !31
+    $eax = MOV32r0 implicit-def dead $eflags, debug-location !32
+    RET 0, $eax, debug-location !32
+
+...




More information about the llvm-commits mailing list