[codeview] Include record prefix in global type hashing

The prefix includes type kind, which is important to preserve. Two
different type leafs can easily have the same interior record contents
as another type.

We ran into this issue in PR37492 where a bitfield type record collided
with a const modifier record. Their contents were bitwise identical, but
their kinds were different.

llvm-svn: 332664

4 files changed, 102 insertions, 39 deletions

diff --git a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
index f5b28b2a207..c2f8cd5466a 100644
--- a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
+++ b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
@@ -39,6 +39,7 @@ GloballyHashedType::hashType(ArrayRef<uint8_t> RecordData,
   SHA1 S;
   S.init();
   uint32_t Off = 0;
+  S.update(RecordData.take_front(sizeof(RecordPrefix)));
   RecordData = RecordData.drop_front(sizeof(RecordPrefix));
   for (const auto &Ref : Refs) {
     // Hash any data that comes before this TiRef.
diff --git a/llvm/test/DebugInfo/COFF/global-type-hashes.ll b/llvm/test/DebugInfo/COFF/global-type-hashes.ll
index 2595c387fc9..99006a34543 100644
--- a/llvm/test/DebugInfo/COFF/global-type-hashes.ll
+++ b/llvm/test/DebugInfo/COFF/global-type-hashes.ll
@@ -275,23 +275,22 @@ attributes #2 = { noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-ma
 ; YAML:       Version:         0
 ; YAML:       HashAlgorithm:   0
 ; YAML:       HashValues:
-; YAML:         - 9E56666824DC4B12E25261D4E09E6E9DA0F4EE31
-; YAML:         - FDEC3D2D96287486127C66070B248ED52E421F55
-; YAML:         - 074AE5CC2D68AF9F0A3BEF23993968F7FD82CA84
-; YAML:         - BF0439C1A64C9070C6A6ADB0A34D21DAD0FFC3E9
-; YAML:         - CF1B3AD4A96BA628E6556FD28A222FBBEBBE140E
-; YAML:         - EC50195BFE148C0DC6A87A59D49CA1D9B146DB86
-; YAML:         - 123C8BA63AD23386897AB6D814A9932F03846156
-; YAML:         - 0F135243878289B83835BC2DB9EE25A1D4D0DA2B
-; YAML:         - 9069CA78E7450A285173431B3E52C5C25299E473
-; YAML:         - ADA6E11350E9F2069D4689E3646C90D67B28DA62
-; YAML:         - BD535FA9877A4DD123840AF849F3B0110EEB1D7A
-; YAML:         - 8044F70193FE40B71867158C5E50F0467485FA99
-; YAML:         - 558606D57A76D125B705FC6DD18EEE3C1C0C4C09
-; YAML:         - A64A018D9EB1EB8015917925662C8508D81CDA68
-; YAML:         - 51E89AD9992AC6F11F9E3F1665F41C53BDA8AFC4
-; YAML:         - 4F1C3BCA73099EF3466AAC99CC4951767DF890F5
-; ...
+; YAML:         - 624A7FEE7323656B7F1C5A63800309EE1ED8BB5B
+; YAML:         - 0EB2C87AD629AA9E5C98B7A3ED69DB1355707DF1
+; YAML:         - 624E463ACE08649D0FC35F163E20CC43089ADCA6
+; YAML:         - 4B712C03EDA4CB88537EBAE4005A09006A9FB389
+; YAML:         - 59EC21C3D8D594FF77854ABAC324F82D24D22283
+; YAML:         - DA76AFB7C767EC00BAA171FEFAA2801D95716C22
+; YAML:         - 4927143F1D91A64983DDA6B6DDE23757322DB7C3
+; YAML:         - DFDF871AD3841199ACD961EA57243C7A1305B4DD
+; YAML:         - 20015FA1AD3D0FF3546B4428D341E2F9BE57A1C7
+; YAML:         - 8DC9D77BACDD53AAE3A5AC8F41C43D3C3122DCBC
+; YAML:         - 77A85205D34B9C26802849355086C2937E3F45D8
+; YAML:         - 4AEF9C1D1509C0FFA2A02F86B3C28FB0F254096C
+; YAML:         - 83B03F51A4BABAE1E8B560B40634944401BCC520
+; YAML:         - A82772A0D760F3EB5FC7A3022A6D376F5D7A92E2
+; YAML:         - 235B46C1A3E3FB71D89ED6085E8B8D38632AACD6
+; YAML:         - D52F03DB055DE93F19066E93FB3BA86C5A652429
 
 
 ; ASM:      .section        .debug$H,"dr"
@@ -299,14 +298,14 @@ attributes #2 = { noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-ma
 ; ASM-NEXT: .long   20171205                # Magic
 ; ASM-NEXT: .short  0                       # Section Version
 ; ASM-NEXT: .short  0                       # Hash Algorithm
-; ASM-NEXT: .byte   0x9e, 0x56, 0x66, 0x68  # 0x1000 [9E56666824DC4B12E25261D4E09E6E9DA0F4EE31]
-; ASM-NEXT: .byte   0x24, 0xdc, 0x4b, 0x12
-; ASM-NEXT: .byte   0xe2, 0x52, 0x61, 0xd4
-; ASM-NEXT: .byte   0xe0, 0x9e, 0x6e, 0x9d
-; ASM-NEXT: .byte   0xa0, 0xf4, 0xee, 0x31
-; ASM-NEXT: .byte   0xfd, 0xec, 0x3d, 0x2d  # 0x1001 [FDEC3D2D96287486127C66070B248ED52E421F55]
-; ASM-NEXT: .byte   0x96, 0x28, 0x74, 0x86
-; ASM-NEXT: .byte   0x12, 0x7c, 0x66, 0x07
-; ASM-NEXT: .byte   0x0b, 0x24, 0x8e, 0xd5
-; ASM-NEXT: .byte   0x2e, 0x42, 0x1f, 0x55
-; ASM-NEXT: .byte   0x07, 0x4a, 0xe5, 0xcc  # 0x1002 [074AE5CC2D68AF9F0A3BEF23993968F7FD82CA84]
+; ASM-NEXT: .byte   0x62, 0x4a, 0x7f, 0xee  # 0x1000 [624A7FEE7323656B7F1C5A63800309EE1ED8BB5B]
+; ASM-NEXT: .byte   0x73, 0x23, 0x65, 0x6b
+; ASM-NEXT: .byte   0x7f, 0x1c, 0x5a, 0x63
+; ASM-NEXT: .byte   0x80, 0x03, 0x09, 0xee
+; ASM-NEXT: .byte   0x1e, 0xd8, 0xbb, 0x5b
+; ASM-NEXT: .byte   0x0e, 0xb2, 0xc8, 0x7a  # 0x1001 [0EB2C87AD629AA9E5C98B7A3ED69DB1355707DF1]
+; ASM-NEXT: .byte   0xd6, 0x29, 0xaa, 0x9e
+; ASM-NEXT: .byte   0x5c, 0x98, 0xb7, 0xa3
+; ASM-NEXT: .byte   0xed, 0x69, 0xdb, 0x13
+; ASM-NEXT: .byte   0x55, 0x70, 0x7d, 0xf1
+; ASM-NEXT: .byte   0x62, 0x4e, 0x46, 0x3a  # 0x1002 [624E463ACE08649D0FC35F163E20CC43089ADCA6]
diff --git a/llvm/test/DebugInfo/COFF/pr37492.ll b/llvm/test/DebugInfo/COFF/pr37492.ll
new file mode 100644
index 00000000000..7edff440b67
--- /dev/null
+++ b/llvm/test/DebugInfo/COFF/pr37492.ll
@@ -0,0 +1,63 @@
+; RUN: llc < %s | FileCheck %s
+
+; Original C++ source:
+; struct Bits {
+;   unsigned char b0 : 1;
+;   unsigned char b1 : 1;
+; } bits;
+; const unsigned char *p_const;
+
+; In PR37492, there was an issue in global type hashing where we forgot to
+; consider the prefix portion of a type record when hashing it. This lead to a
+; collision between this LF_BITFIELD and LF_MODIFIER record, so we only emitted
+; one under the assumption that the other was redundant. Check that we emit both.
+
+; CHECK-LABEL: # BitField ({{.*}}) {
+; CHECK-NEXT: #   TypeLeafKind: LF_BITFIELD (0x1205)
+; CHECK-NEXT: #   Type: unsigned char (0x20)
+; CHECK-NEXT: #   BitSize: 1
+; CHECK-NEXT: #   BitOffset: 0
+; CHECK-NEXT: # }
+
+; CHECK-LABEL: # Modifier ({{.*}}) {
+; CHECK-NEXT: #   TypeLeafKind: LF_MODIFIER (0x1001)
+; CHECK-NEXT: #   ModifiedType: unsigned char (0x20)
+; CHECK-NEXT: #   Modifiers [ (0x1)
+; CHECK-NEXT: #     Const (0x1)
+; CHECK-NEXT: #   ]
+; CHECK-NEXT: # }
+
+; ModuleID = 't.cpp'
+source_filename = "t.cpp"
+target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-windows-msvc19.13.26131"
+
+%struct.Bits = type { i8 }
+
+@"?bits@@3UBits@@A" = dso_local global %struct.Bits zeroinitializer, align 1, !dbg !0
+@"?p_const@@3PEBEEB" = dso_local global i8* null, align 8, !dbg !6
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!15, !16, !17, !18}
+!llvm.ident = !{!19}
+
+!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+!1 = distinct !DIGlobalVariable(name: "bits", linkageName: "?bits@@3UBits@@A", scope: !2, file: !3, line: 4, type: !11, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !3, producer: "clang version 7.0.0 ", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
+!3 = !DIFile(filename: "t.cpp", directory: "C:\5Csrc\5Cllvm-project\5Cbuild", checksumkind: CSK_MD5, checksum: "8910833bbe8b669a3787c8f44dff1313")
+!4 = !{}
+!5 = !{!0, !6}
+!6 = !DIGlobalVariableExpression(var: !7, expr: !DIExpression())
+!7 = distinct !DIGlobalVariable(name: "p_const", linkageName: "?p_const@@3PEBEEB", scope: !2, file: !3, line: 5, type: !8, isLocal: false, isDefinition: true)
+!8 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !9, size: 64)
+!9 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !10)
+!10 = !DIBasicType(name: "unsigned char", size: 8, encoding: DW_ATE_unsigned_char)
+!11 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "Bits", file: !3, line: 1, size: 8, flags: DIFlagTypePassByValue, elements: !12, identifier: ".?AUBits@@")
+!12 = !{!13, !14}
+!13 = !DIDerivedType(tag: DW_TAG_member, name: "b0", scope: !11, file: !3, line: 2, baseType: !10, size: 1, flags: DIFlagBitField, extraData: i64 0)
+!14 = !DIDerivedType(tag: DW_TAG_member, name: "b1", scope: !11, file: !3, line: 3, baseType: !10, size: 1, offset: 1, flags: DIFlagBitField, extraData: i64 0)
+!15 = !{i32 2, !"CodeView", i32 1}
+!16 = !{i32 2, !"Debug Info Version", i32 3}
+!17 = !{i32 1, !"wchar_size", i32 2}
+!18 = !{i32 7, !"PIC Level", i32 2}
+!19 = !{!"clang version 7.0.0 "}
diff --git a/llvm/test/DebugInfo/PDB/obj-globalhash.test b/llvm/test/DebugInfo/PDB/obj-globalhash.test
index 9bb6946050a..770eae2704a 100644
--- a/llvm/test/DebugInfo/PDB/obj-globalhash.test
+++ b/llvm/test/DebugInfo/PDB/obj-globalhash.test
@@ -14,41 +14,41 @@ RUN: cat %T/hashes-combined.out | FileCheck --check-prefix=CHECK-SIX %s
 ; char**.  Both the local and global hashes should be the same, since the only
 ; back-references are for simple types which have fixed indices.
 CHECK-ONE:   obj-hashes-1
-CHECK-ONE:   TI: 0x1001, LocalHash: {{.*}}, GlobalHash: 8B2BA87CC27BF9D290A31A6070FA296AAA577E53
+CHECK-ONE:   TI: 0x1001, LocalHash: {{.*}}, GlobalHash: 414E8FCAB16EC28AB86498D1A7F8CF106F39A384
 CHECK-ONE:   obj-hashes-2
-CHECK-ONE:   TI: 0x1000, LocalHash: {{.*}}, GlobalHash: 8B2BA87CC27BF9D290A31A6070FA296AAA577E53
+CHECK-ONE:   TI: 0x1000, LocalHash: {{.*}}, GlobalHash: 414E8FCAB16EC28AB86498D1A7F8CF106F39A384
 
 ; int**.  Same as char**, both the local and global hashes should be the same.
 CHECK-TWO:   obj-hashes-1
-CHECK-TWO:   TI: 0x1000, LocalHash: {{.*}}, GlobalHash: 1522A98D88FAF71B618D97BCAC2B89A424EC4805
+CHECK-TWO:   TI: 0x1000, LocalHash: {{.*}}, GlobalHash: 91D2E2AD5D0F20EC1A24BE2E95D0616C5962F4B1
 CHECK-TWO:   obj-hashes-2
-CHECK-TWO:   TI: 0x1002, LocalHash: {{.*}}, GlobalHash: 1522A98D88FAF71B618D97BCAC2B89A424EC4805
+CHECK-TWO:   TI: 0x1002, LocalHash: {{.*}}, GlobalHash: 91D2E2AD5D0F20EC1A24BE2E95D0616C5962F4B1
 
 ; int***. Different local hashes, since the referent type (int**) is not at the
 ; same TypeIndex in both streams.  Same global hash, since they represent the
 ; same record.
 CHECK-THREE: obj-hashes-1
-CHECK-THREE: TI: 0x1002, LocalHash: {{.*}}, GlobalHash: EC11CE9F78D6BF61F8D913A9E2C98293782A7EB4
+CHECK-THREE: TI: 0x1002, LocalHash: {{.*}}, GlobalHash: 68A6DDB5C538D379E72E6425591A2B16352DF93D
 CHECK-THREE: obj-hashes-2
-CHECK-THREE: TI: 0x1001, LocalHash: {{.*}}, GlobalHash: EC11CE9F78D6BF61F8D913A9E2C98293782A7EB4
+CHECK-THREE: TI: 0x1001, LocalHash: {{.*}}, GlobalHash: 68A6DDB5C538D379E72E6425591A2B16352DF93D
 
 ; arg list (char**, int***).  Different local hashes, since the parameter types
 ; both occur at different TypeIndices in their respective input streams.  Same
 ; global hash, since the global hash of all referenced types is the same in
 ; both streams.
 CHECK-FOUR:  obj-hashes-1
-CHECK-FOUR:  TI: 0x1003, LocalHash: {{.*}}, GlobalHash: 1088AD64CEBC88D9E015058A159516AF20B79286
+CHECK-FOUR:  TI: 0x1003, LocalHash: {{.*}}, GlobalHash: FD539365C0A8DEC0A1567C3E2F4C82E7AADB0E51
 CHECK-FOUR:  obj-hashes-2
-CHECK-FOUR:  TI: 0x1004, LocalHash: {{.*}}, GlobalHash: 1088AD64CEBC88D9E015058A159516AF20B79286
+CHECK-FOUR:  TI: 0x1004, LocalHash: {{.*}}, GlobalHash: FD539365C0A8DEC0A1567C3E2F4C82E7AADB0E51
 
 ; double**.  This is only in stream 2, as a means to throw off the indexing.
 CHECK-FIVE:  obj-hashes-1
 CHECK-FIVE:  obj-hashes-2
-CHECK-FIVE:  TI: 0x1003, LocalHash: {{.*}}, GlobalHash: 7803BBDB2947EF46BEA2310D102BD08F68315506
+CHECK-FIVE:  TI: 0x1003, LocalHash: {{.*}}, GlobalHash: 5BB6926CA7924D06908872FA20691EA9B88584CC
 
 ; int** (char**, int***).  For the same logic as described in previous records,
 ; these two records have the same global hash but different local hashes.
 CHECK-SIX:   obj-hashes-1
-CHECK-SIX:   TI: 0x1004, LocalHash: {{.*}}, GlobalHash: 457ABCB8AB70407594B5D72BF471B6BDECC99BC9
+CHECK-SIX:   TI: 0x1004, LocalHash: {{.*}}, GlobalHash: 7A8576BA937B2E87BBF94A9CBFA8F993EE746065
 CHECK-SIX:   obj-hashes-2
-CHECK-SIX:   TI: 0x1005, LocalHash: {{.*}}, GlobalHash: 457ABCB8AB70407594B5D72BF471B6BDECC99BC9
+CHECK-SIX:   TI: 0x1005, LocalHash: {{.*}}, GlobalHash: 7A8576BA937B2E87BBF94A9CBFA8F993EE746065