Tighten up DIFile verifier checks on checksum

[aprantl]

Awesome, thanks!

[davide]

lgtm

llvm/lib/IR/Verifier.cpp

 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/ADT/ilist.h"
 #include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/IR/Argument.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
if (auto *Types = N.getRawTypeArray()) {
     }
   }
   AssertDI(!hasConflictingReferenceFlags(N.getFlags()),
            "invalid reference flags", &N);
 }
 
 void Verifier::visitDIFile(const DIFile &N) {
   AssertDI(N.getTag() == dwarf::DW_TAG_file_type, "invalid tag", &N);
-  AssertDI((N.getChecksumKind() != DIFile::CSK_None ||
-            N.getChecksum().empty()), "invalid checksum kind", &N);
+  AssertDI(N.getChecksumKind() <= DIFile::CSK_Last, "invalid checksum kind",
+           &N);
+  size_t Size;
+  switch (N.getChecksumKind()) {
+  case DIFile::CSK_None:
+    Size = 0;
+    break;
+  case DIFile::CSK_MD5:
+    Size = 32;
+    break;
+  case DIFile::CSK_SHA1:
+    Size = 40;
+    break;
+  }
+  AssertDI(N.getChecksum().size() == Size, "invalid checksum length", &N);
+  AssertDI(N.getChecksum().find_if_not(llvm::isHexDigit) == StringRef::npos,
+           "invalid checksum", &N);
 }
 
 void Verifier::visitDICompileUnit(const DICompileUnit &N) {
   AssertDI(N.isDistinct(), "compile units must be distinct", &N);
   AssertDI(N.getTag() == dwarf::DW_TAG_compile_unit, "invalid tag", &N);
 
   // Don't bother verifying the compilation directory or producer string
   // as those could be empty.

llvm/test/MC/AArch64/coff-debug.ll

 
 attributes #0 = { noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
 
 !llvm.dbg.cu = !{!0}
 !llvm.module.flags = !{!3, !4, !5}
 !llvm.ident = !{!6}
 
 !0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
-!1 = !DIFile(filename: "a.c", directory: "/", checksumkind: CSK_MD5, checksum: "")
+!1 = !DIFile(filename: "a.c", directory: "/", checksumkind: CSK_MD5, checksum: "12345678901234567890123456789012")
 !2 = !{}
 !3 = !{i32 2, !"CodeView", i32 1}
 !4 = !{i32 2, !"Debug Info Version", i32 3}
 !5 = !{i32 1, !"wchar_size", i32 2}
 !6 = !{!"clang"}
 !7 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, isOptimized: false, unit: !0, variables: !2)
 !8 = !DISubroutineType(types: !9)
 !9 = !{!10}

 ; CHECK:   ]
 ; CHECK:   Subsection [
 ; CHECK:     SubSectionType: Lines (0xF2)
 ; CHECK:     LinkageName: main
 ; CHECK:   ]
 ; CHECK:   Subsection [
 ; CHECK:     SubSectionType: FileChecksums (0xF4)
 ; CHECK:     FileChecksum {
-; CHECK:       ChecksumSize: 0x0
+; CHECK:       ChecksumSize: 0x10
 ; CHECK:       ChecksumKind: MD5 (0x1)
-; CHECK:       ChecksumBytes: ()
+; CHECK:       ChecksumBytes: (12 34 56 78 90 12 34 56 78 90 12 34 56 78 90 12)
 ; CHECK:     }
 ; CHECK:   ]
 ; CHECK:   Subsection [
 ; CHECK:     SubSectionType: StringTable (0xF3)
 ; CHECK:   ]
 ; CHECK:   FunctionLineTable [
 ; CHECK:     LinkageName: main
 ; CHECK:     Flags: 0x1

llvm/test/Verifier/DIFile.ll

+; RUN: llvm-as -disable-output < %s 2>&1 | FileCheck %s
+
+; The lengths for None and MD5 are wrong; SHA1 has a non-hex digit.
+; CHECK: invalid checksum length
+; CHECK: invalid checksum{{$}}
+; CHECK: invalid checksum length
+; CHECK: warning: ignoring invalid debug info in <stdin>
+
+@t1 = global i32 1, align 4, !dbg !0
+@t2 = global i32 0, align 4, !dbg !6
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!11, !12, !13}
+!llvm.ident = !{!14}
+
+!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+!1 = distinct !DIGlobalVariable(name: "t1", scope: !2, file: !10, line: 1, type: !9, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang version 7.0.0 (trunk 322159)", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
+!3 = !DIFile(filename: "t.c", directory: "/scratch", checksumkind: CSK_None, checksum: "00")
+!4 = !{}
+!5 = !{!0, !6}
+!6 = !DIGlobalVariableExpression(var: !7, expr: !DIExpression())
+!7 = distinct !DIGlobalVariable(name: "t2", scope: !2, file: !8, line: 1, type: !9, isLocal: false, isDefinition: true)
+!8 = !DIFile(filename: "./t2.h", directory: "/scratch", checksumkind: CSK_MD5, checksum: "2222")
+!9 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!10 = !DIFile(filename: "./t1.h", directory: "/scratch", checksumkind: CSK_SHA1, checksum: "123456789012345678901234567890123456789.")
+!11 = !{i32 2, !"Dwarf Version", i32 4}
+!12 = !{i32 2, !"Debug Info Version", i32 3}
+!13 = !{i32 1, !"wchar_size", i32 4}
+!14 = !{!"clang version 7.0.0 (trunk 322159)"}