[BPF] add unit tests for preserve_{array,union,struct}_access_index intrinsics

[yonghong-song]

Summary

This is a followup patch for https://reviews.llvm.org/D61810/new/,
which adds new intrinsics preserve_{array,union,struct}_access_index.

Currently, only BPF backend utilizes preserve_{array,union,struct}_access_index
intrinsics, so all tests are compiled with BPF target.

https://reviews.llvm.org/D61524 already added some tests for these
intrinsics, but some of them pretty complex.
This patch added a few unit test cases focusing on individual intrinsic
functions.

Also made a few clarification on language reference for these intrinsics.

[jdoerfert]

Thank you for adding test and clarification as requested. Given that I am not working in this area, I will not do the actual review.

[yonghong-song]

@jdoerfert Thanks for commenting on my diff. Will find the appropriate person to review.

llvm/trunk/docs/LangRef.rst

 
 '``llvm.preserve.array.access.index``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
 """""""
 ::
 
-      declare <type2>
+      declare <ret_type>
       @llvm.preserve.array.access.index.p0s_union.anons.p0a10s_union.anons(<type> base,
                                                                            i32 dim,
                                                                            i32 index)
 
 Overview:
 """""""""
 
 The '``llvm.preserve.array.access.index``' intrinsic returns the getelementptr address
 based on array base ``base``, array dimension ``dim`` and the last access index ``index``
-into the array.
+into the array. The return type ``ret_type`` is a pointer type to the array element.
+The array ``dim`` and ``index`` are preserved which is more robust than
+getelementptr instruction which may be subject to compiler transformation.
 
 Arguments:
 """"""""""
 
 The ``base`` is the array base address.  The ``dim`` is the array dimension.
 The ``base`` is a pointer if ``dim`` equals 0.
 The ``index`` is the last access index into the array or pointer.
 

 
 Overview:
 """""""""
 
 The '``llvm.preserve.union.access.index``' intrinsic carries the debuginfo field index
 ``di_index`` and returns the ``base`` address.
 The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
 to provide union debuginfo type.
+The metadata is a ``DICompositeType`` representing the debuginfo version of ``type``.
+The return type ``type`` is the same as the ``base`` type.
 
 Arguments:
 """"""""""
 
 The ``base`` is the union base address. The ``di_index`` is the field index in debuginfo.
 
 Semantics:
 """"""""""
 
 The '``llvm.preserve.union.access.index``' intrinsic returns the ``base`` address.
 
 '``llvm.preserve.struct.access.index``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
 """""""
 ::
 
-      declare <type2>
+      declare <ret_type>
       @llvm.preserve.struct.access.index.p0i8.p0s_struct.anon.0s(<type> base,
                                                                  i32 gep_index,
                                                                  i32 di_index)
 
 Overview:
 """""""""
 
 The '``llvm.preserve.struct.access.index``' intrinsic returns the getelementptr address
 based on struct base ``base`` and IR struct member index ``gep_index``.
 The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
 to provide struct debuginfo type.
+The metadata is a ``DICompositeType`` representing the debuginfo version of ``type``.
+The return type ``ret_type`` is a pointer type to the structure member.
 
 Arguments:
 """"""""""
 
 The ``base`` is the structure base address. The ``gep_index`` is the struct member index
 based on IR structures. The ``di_index`` is the struct member index based on debuginfo.
 
 Semantics:
 """"""""""
 
 The '``llvm.preserve.struct.access.index``' intrinsic produces the same result
 as a getelementptr with base ``base`` and access operands ``{0, gep_index}``.

llvm/trunk/test/CodeGen/BPF/CORE/intrinsic-array.ll

+; RUN: llc -march=bpfel -filetype=asm -o - %s | FileCheck %s
+;
+; Source code:
+;   #define _(x) (__builtin_preserve_access_index(x))
+;   struct s { int a; int b; };
+;   int get_value(const void *addr);
+;   int test(struct s *arg) { return get_value(_(&arg[2].b)); }
+; Compiler flag to generate IR:
+;   clang -target bpf -S -O2 -g -emit-llvm test.c
+
+%struct.s = type { i32, i32 }
+
+; Function Attrs: nounwind
+define dso_local i32 @test(%struct.s* %arg) local_unnamed_addr #0 !dbg !7 {
+entry:
+  call void @llvm.dbg.value(metadata %struct.s* %arg, metadata !17, metadata !DIExpression()), !dbg !18
+  %0 = tail call %struct.s* @llvm.preserve.array.access.index.p0s_struct.ss.p0s_struct.ss(%struct.s* %arg, i32 0, i32 2), !dbg !19
+  %1 = tail call i32* @llvm.preserve.struct.access.index.p0i32.p0s_struct.ss(%struct.s* %0, i32 1, i32 1), !dbg !19, !llvm.preserve.access.index !12
+  %2 = bitcast i32* %1 to i8*, !dbg !19
+  %call = tail call i32 @get_value(i8* %2) #4, !dbg !20
+  ret i32 %call, !dbg !21
+}
+; CHECK-LABEL: test
+; CHECK:       [[RELOC:.Ltmp[0-9]+]]
+; CHECK:       r2 = 20
+; CHECK:       r1 += r2
+; CHECK:       call get_value
+; CHECK:       exit
+;
+; CHECK:      .section        .BTF.ext,"",@progbits
+; CHECK:      .long   12                      # OffsetReloc
+; CHECK-NEXT: .long   20                      # Offset reloc section string offset=20
+; CHECK-NEXT: .long   1
+; CHECK-NEXT: .long   [[RELOC]]
+; CHECK-NEXT: .long   2
+; CHECK-NEXT: .long   26
+
+declare dso_local i32 @get_value(i8*) local_unnamed_addr #1
+
+; Function Attrs: nounwind readnone
+declare %struct.s* @llvm.preserve.array.access.index.p0s_struct.ss.p0s_struct.ss(%struct.s*, i32 immarg, i32 immarg) #2
+
+; Function Attrs: nounwind readnone
+declare i32* @llvm.preserve.struct.access.index.p0i32.p0s_struct.ss(%struct.s*, i32 immarg, i32 immarg) #2
+
+; Function Attrs: nounwind readnone speculatable
+declare void @llvm.dbg.value(metadata, metadata, metadata) #3
+
+attributes #0 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "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" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind readnone }
+attributes #3 = { nounwind readnone speculatable }
+attributes #4 = { nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 9.0.0 (trunk 365789)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "test.c", directory: "/tmp/home/yhs/work/tests/core")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 9.0.0 (trunk 365789)"}
+!7 = distinct !DISubprogram(name: "test", scope: !1, file: !1, line: 4, type: !8, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !16)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10, !11}
+!10 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64)
+!12 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s", file: !1, line: 2, size: 64, elements: !13)
+!13 = !{!14, !15}
+!14 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !12, file: !1, line: 2, baseType: !10, size: 32)
+!15 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !12, file: !1, line: 2, baseType: !10, size: 32, offset: 32)
+!16 = !{!17}
+!17 = !DILocalVariable(name: "arg", arg: 1, scope: !7, file: !1, line: 4, type: !11)
+!18 = !DILocation(line: 0, scope: !7)
+!19 = !DILocation(line: 4, column: 44, scope: !7)
+!20 = !DILocation(line: 4, column: 34, scope: !7)
+!21 = !DILocation(line: 4, column: 27, scope: !7)

llvm/trunk/test/CodeGen/BPF/CORE/intrinsic-struct.ll

+; RUN: llc -march=bpfel -filetype=asm -o - %s | FileCheck %s
+;
+; Source code:
+;   struct s { int a; int b; };
+;   #define _(x) (__builtin_preserve_access_index(x))
+;   int get_value(const void *addr);
+;   int test(struct s *arg) { return get_value(_(&arg->b)); }
+; Compiler flag to generate IR:
+;   clang -target bpf -S -O2 -g -emit-llvm test.c
+
+%struct.s = type { i32, i32 }
+
+; Function Attrs: nounwind
+define dso_local i32 @test(%struct.s* %arg) local_unnamed_addr #0 !dbg !7 {
+entry:
+  call void @llvm.dbg.value(metadata %struct.s* %arg, metadata !17, metadata !DIExpression()), !dbg !18
+  %0 = tail call i32* @llvm.preserve.struct.access.index.p0i32.p0s_struct.ss(%struct.s* %arg, i32 1, i32 1), !dbg !19, !llvm.preserve.access.index !12
+  %1 = bitcast i32* %0 to i8*, !dbg !19
+  %call = tail call i32 @get_value(i8* %1) #4, !dbg !20
+  ret i32 %call, !dbg !21
+}
+
+; CHECK-LABEL: test
+; CHECK:       [[RELOC:.Ltmp[0-9]+]]
+; CHECK:       r2 = 4
+; CHECK:       r1 += r2
+; CHECK:       call get_value
+; CHECK:       exit
+;
+; CHECK:      .section        .BTF.ext,"",@progbits
+; CHECK:      .long   12                      # OffsetReloc
+; CHECK-NEXT: .long   20                      # Offset reloc section string offset=20
+; CHECK-NEXT: .long   1
+; CHECK-NEXT: .long   [[RELOC]]
+; CHECK-NEXT: .long   2
+; CHECK-NEXT: .long   26
+
+declare dso_local i32 @get_value(i8*) local_unnamed_addr #1
+
+; Function Attrs: nounwind readnone
+declare i32* @llvm.preserve.struct.access.index.p0i32.p0s_struct.ss(%struct.s*, i32 immarg, i32 immarg) #2
+
+; Function Attrs: nounwind readnone speculatable
+declare void @llvm.dbg.value(metadata, metadata, metadata) #3
+
+attributes #0 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "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" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind readnone }
+attributes #3 = { nounwind readnone speculatable }
+attributes #4 = { nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 9.0.0 (trunk 365789)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "test.c", directory: "/tmp/home/yhs/work/tests/core")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 9.0.0 (trunk 365789)"}
+!7 = distinct !DISubprogram(name: "test", scope: !1, file: !1, line: 4, type: !8, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !16)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10, !11}
+!10 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64)
+!12 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s", file: !1, line: 1, size: 64, elements: !13)
+!13 = !{!14, !15}
+!14 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !12, file: !1, line: 1, baseType: !10, size: 32)
+!15 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !12, file: !1, line: 1, baseType: !10, size: 32, offset: 32)
+!16 = !{!17}
+!17 = !DILocalVariable(name: "arg", arg: 1, scope: !7, file: !1, line: 4, type: !11)
+!18 = !DILocation(line: 0, scope: !7)
+!19 = !DILocation(line: 4, column: 44, scope: !7)
+!20 = !DILocation(line: 4, column: 34, scope: !7)
+!21 = !DILocation(line: 4, column: 27, scope: !7)

llvm/trunk/test/CodeGen/BPF/CORE/intrinsic-union.ll

+; RUN: llc -march=bpfel -filetype=asm -o - %s | FileCheck %s
+;
+; Source code:
+;   union u { int a; int b; };
+;   #define _(x) (__builtin_preserve_access_index(x))
+;   int get_value(const void *addr);
+;   int test(union u *arg) { return get_value(_(&arg->b)); }
+; Compiler flag to generate IR:
+;   clang -target bpf -S -O2 -g -emit-llvm test.c
+
+%union.u = type { i32 }
+
+; Function Attrs: nounwind
+define dso_local i32 @test(%union.u* %arg) local_unnamed_addr #0 !dbg !7 {
+entry:
+  call void @llvm.dbg.value(metadata %union.u* %arg, metadata !17, metadata !DIExpression()), !dbg !18
+  %0 = tail call %union.u* @llvm.preserve.union.access.index.p0s_union.us.p0s_union.us(%union.u* %arg, i32 1), !dbg !19, !llvm.preserve.access.index !12
+  %1 = bitcast %union.u* %0 to i8*, !dbg !19
+  %call = tail call i32 @get_value(i8* %1) #4, !dbg !20
+  ret i32 %call, !dbg !21
+}
+; CHECK-LABEL: test
+; CHECK:       [[RELOC:.Ltmp[0-9]+]]
+; CHECK:       r2 = 0
+; CHECK:       r1 += r2
+; CHECK:       call get_value
+; CHECK:       exit
+
+; CHECK:      .section        .BTF.ext,"",@progbits
+; CHECK:      .long   12                      # OffsetReloc
+; CHECK-NEXT: .long   20                      # Offset reloc section string offset=20
+; CHECK-NEXT: .long   1
+; CHECK-NEXT: .long   [[RELOC]]
+; CHECK-NEXT: .long   2
+; CHECK-NEXT: .long   26
+
+declare dso_local i32 @get_value(i8*) local_unnamed_addr #1
+
+; Function Attrs: nounwind readnone
+declare %union.u* @llvm.preserve.union.access.index.p0s_union.us.p0s_union.us(%union.u*, i32 immarg) #2
+
+; Function Attrs: nounwind readnone speculatable
+declare void @llvm.dbg.value(metadata, metadata, metadata) #3
+
+attributes #0 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "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" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind readnone }
+attributes #3 = { nounwind readnone speculatable }
+attributes #4 = { nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 9.0.0 (trunk 365789)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "test.c", directory: "/tmp/home/yhs/work/tests/core")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 9.0.0 (trunk 365789)"}
+!7 = distinct !DISubprogram(name: "test", scope: !1, file: !1, line: 4, type: !8, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !16)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10, !11}
+!10 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64)
+!12 = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u", file: !1, line: 1, size: 32, elements: !13)
+!13 = !{!14, !15}
+!14 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !12, file: !1, line: 1, baseType: !10, size: 32)
+!15 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !12, file: !1, line: 1, baseType: !10, size: 32)
+!16 = !{!17}
+!17 = !DILocalVariable(name: "arg", arg: 1, scope: !7, file: !1, line: 4, type: !11)
+!18 = !DILocation(line: 0, scope: !7)
+!19 = !DILocation(line: 4, column: 43, scope: !7)
+!20 = !DILocation(line: 4, column: 33, scope: !7)
+!21 = !DILocation(line: 4, column: 26, scope: !7)