[yaml2obj/obj2yaml] - Make RawContentSection::Content and RawContentS…

…ection::Size optional

This is a follow-up for D62809.

Content and Size fields should be optional as was discussed in comments
of the D62809's thread. With that, we can describe a specific string table and
symbol table sections in a more correct way and also show appropriate errors.

The patch adds lots of test cases where the behavior is described in details.

Differential revision: https://reviews.llvm.org/D62957

llvm-svn: 362931

llvm/include/llvm/ObjectYAML/ELFYAML.h

@@ -151,8 +151,8 @@ struct DynamicSection : Section {
 };
 
 struct RawContentSection : Section {
-  yaml::BinaryRef Content;
-  llvm::yaml::Hex64 Size;
+  Optional<yaml::BinaryRef> Content;
+  Optional<llvm::yaml::Hex64> Size;
   llvm::yaml::Hex64 Info;
 
   RawContentSection() : Section(SectionKind::RawContent) {}

llvm/lib/ObjectYAML/ELFYAML.cpp

@@ -914,7 +914,7 @@ static void sectionMapping(IO &IO, ELFYAML::DynamicSection &Section) {
 static void sectionMapping(IO &IO, ELFYAML::RawContentSection &Section) {
   commonSectionMapping(IO, Section);
   IO.mapOptional("Content", Section.Content);
-  IO.mapOptional("Size", Section.Size, Hex64(Section.Content.binary_size()));
+  IO.mapOptional("Size", Section.Size);
   IO.mapOptional("Info", Section.Info, Hex64(0));
 }
 
@@ -1042,9 +1042,12 @@ void MappingTraits<std::unique_ptr<ELFYAML::Section>>::mapping(
 StringRef MappingTraits<std::unique_ptr<ELFYAML::Section>>::validate(
     IO &io, std::unique_ptr<ELFYAML::Section> &Section) {
   const auto *RawSection = dyn_cast<ELFYAML::RawContentSection>(Section.get());
-  if (!RawSection || RawSection->Size >= RawSection->Content.binary_size())
-    return StringRef();
-  return "Section size must be greater or equal to the content size";
+  if (!RawSection)
+    return {};
+  if (RawSection->Size && RawSection->Content &&
+      (uint64_t)(*RawSection->Size) < RawSection->Content->binary_size())
+    return "Section size must be greater than or equal to the content size";
+  return {};
 }
 
 namespace {

llvm/test/Object/obj2yaml.test

@@ -389,7 +389,6 @@ ELF-MIPSEL-NEXT:   - Name:            .data
 ELF-MIPSEL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPSEL-NEXT:     Flags:           [ SHF_WRITE, SHF_ALLOC ]
 ELF-MIPSEL-NEXT:     AddressAlign:    0x0000000000000004
-ELF-MIPSEL-NEXT:     Content:         ''
 ELF-MIPSEL-NEXT:   - Name:            .bss
 ELF-MIPSEL-NEXT:     Type:            SHT_NOBITS
 ELF-MIPSEL-NEXT:     Flags:           [ SHF_WRITE, SHF_ALLOC ]
@@ -398,7 +397,6 @@ ELF-MIPSEL-NEXT:     Size:            0x0000000000000004
 ELF-MIPSEL-NEXT:   - Name:            .mdebug.abi32
 ELF-MIPSEL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPSEL-NEXT:     AddressAlign:    0x0000000000000001
-ELF-MIPSEL-NEXT:     Content:         ''
 ELF-MIPSEL-NEXT:   - Name:            .rodata.str1.1
 ELF-MIPSEL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPSEL-NEXT:     Flags:           [ SHF_ALLOC, SHF_MERGE, SHF_STRINGS ]
@@ -477,7 +475,6 @@ ELF-MIPS64EL-NEXT:   - Name:            .text
 ELF-MIPS64EL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPS64EL-NEXT:     Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
 ELF-MIPS64EL-NEXT:     AddressAlign:    0x0000000000000010
-ELF-MIPS64EL-NEXT:     Content:         ''
 ELF-MIPS64EL-NEXT:   - Name:            .data
 ELF-MIPS64EL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPS64EL-NEXT:     Flags:           [ SHF_WRITE, SHF_ALLOC ]
@@ -506,7 +503,6 @@ ELF-MIPS64EL-NEXT:     Content:         '012800000000000000000000000000000000000
 ELF-MIPS64EL-NEXT:   - Name:            .pdr
 ELF-MIPS64EL-NEXT:     Type:            SHT_PROGBITS
 ELF-MIPS64EL-NEXT:     AddressAlign:    0x0000000000000004
-ELF-MIPS64EL-NEXT:     Content:         ''
 ELF-MIPS64EL-NEXT: Symbols:
 ELF-MIPS64EL-NEXT:     - Name:            .text
 ELF-MIPS64EL-NEXT:       Type:            STT_SECTION
@@ -550,7 +546,6 @@ ELF-X86-64-NEXT:   - Name:            .note.GNU-stack
 ELF-X86-64-NEXT:     Type:            SHT_PROGBITS
 ELF-X86-64-NEXT:     Address:         0x0000000000000033
 ELF-X86-64-NEXT:     AddressAlign:    0x0000000000000001
-ELF-X86-64-NEXT:     Content:         ''
 ELF-X86-64-NEXT:   - Name:            .rela.text
 ELF-X86-64-NEXT:     Type:            SHT_RELA
 ELF-X86-64-NEXT:     Address:         0x0000000000000038
@@ -610,7 +605,6 @@ ELF-AVR-NEXT:     Type:            SHT_PROGBITS
 ELF-AVR-NEXT:     Flags:           [ SHF_WRITE, SHF_ALLOC ]
 ELF-AVR-NEXT:     Address:         0x0000000000800060
 ELF-AVR-NEXT:     AddressAlign:    0x0000000000000001
-ELF-AVR-NEXT:     Content:         ''
 ELF-AVR-NEXT: Symbols:
 ELF-AVR-NEXT:     - Name:           .text
 ELF-AVR-NEXT:       Type:            STT_SECTION
@@ -706,7 +700,6 @@ ELF-X86-64-UNWIND:      - Name:            .eh_frame
 ELF-X86-64-UNWIND-NEXT:   Type:            SHT_X86_64_UNWIND
 ELF-X86-64-UNWIND-NEXT:   Flags:           [ SHF_ALLOC ]
 ELF-X86-64-UNWIND-NEXT:   AddressAlign:    0x0000000000000001
-ELF-X86-64-UNWIND-NEXT:   Content:         ''
 
 RUN: not obj2yaml %t.blah 2>&1 | FileCheck --check-prefix=ENOENT %s
 ENOENT: Error reading file: {{.*}}.blah: {{[Nn]}}o such file or directory

llvm/test/Object/yaml2obj-elf-section-invalid-size.yaml

@@ -20,7 +20,7 @@ Sections:
     Content: 0000000000000000
     Size: 2
 
-# CHECK: YAML:17:5: error: Section size must be greater or equal to the content size
+# CHECK: YAML:17:5: error: Section size must be greater than or equal to the content size
 # CHECK-NEXT: - Name: .data
 # CHECK-NEXT:   ^
 # CHECK-NEXT: yaml2obj: Failed to parse YAML file!

llvm/test/tools/obj2yaml/elf-shinfo.yaml

@@ -5,7 +5,6 @@
 
 # CHECK:      - Name:            .test
 # CHECK-NEXT:   Type:            SHT_PROGBITS
-# CHECK-NEXT:   Content:         ''
 # CHECK-NEXT:   Info:            0x000000000000002A
 
 --- !ELF

llvm/test/tools/yaml2obj/dynsymtab-implicit-sections-size-content.yaml

@@ -0,0 +1,222 @@
+## For implicit dynamic symbol table sections, `Size` and/or `Content`
+## fields can also be specified in YAML. Here we test the behavior in
+## different cases.
+
+## When no `Size` or `Content` is specified for a dynamic symbol table section,
+## yaml2obj writes the default content.
+
+# RUN: yaml2obj --docnum=1 %s -o %t1
+# RUN: llvm-readelf %t1 --dyn-symbols | FileCheck %s --check-prefix=CASE1
+
+# CASE1:      Symbol table '.dynsym' contains 2 entries:
+# CASE1-NEXT:    Num:    Value          Size Type    Bind   Vis      Ndx Name
+# CASE1-NEXT:      0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND
+# CASE1-NEXT:      1: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT  UND foo
+# CASE1-EMPTY:
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+DynamicSymbols:
+  - Name:    foo
+    Binding: STB_GLOBAL
+
+## Specifying both `Size` and symbols at the same time is not allowed.
+# RUN: not yaml2obj --docnum=2 %s -o %t2 2>&1 | FileCheck %s --check-prefix=CASE2
+
+# CASE2: error: Cannot specify both `Size` and `DynamicSymbols` for symbol table section '.dynsym'.
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Size: 0x100
+DynamicSymbols:
+  - Name:    foo
+    Binding: STB_GLOBAL
+
+## Specifying both `Content` and symbols at the same time is not allowed.
+# RUN: not yaml2obj --docnum=3 %s -o %t3 2>&1 | FileCheck %s --check-prefix=CASE3
+
+# CASE3: error: Cannot specify both `Content` and `DynamicSymbols` for symbol table section '.dynsym'.
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Content: "00"
+DynamicSymbols:
+  - Name:    foo
+    Binding: STB_GLOBAL
+
+## Check we can use just `Content` to emit custom data in the symbol table section.
+# RUN: yaml2obj --docnum=4 %s -o %t4
+# RUN: llvm-readobj --section-data -S %t4 | FileCheck %s --check-prefix=CASE4
+
+# CASE4:      Name: .dynsym
+# CASE4-NEXT: Type: SHT_DYNSYM
+# CASE4-NEXT: Flags [
+# CASE4-NEXT:   SHF_ALLOC
+# CASE4-NEXT: ]
+# CASE4-NEXT: Address: 0x0
+# CASE4-NEXT: Offset: 0x1C0
+# CASE4-NEXT: Size: 2
+# CASE4-NEXT: Link: 2
+# CASE4-NEXT: Info: 0
+# CASE4-NEXT: AddressAlignment: 0
+# CASE4-NEXT: EntrySize: 24
+# CASE4-NEXT: SectionData (
+# CASE4-NEXT:   0000: 0123
+# CASE4-NEXT: )
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Content: "0123"
+## TODO: .dynstr here is needed to set a proper Link for .dynsym.
+## Without this, llvm-readobj reports an error.
+## See https://bugs.llvm.org/show_bug.cgi?id=42215.
+  - Name: .dynstr
+    Type: SHT_STRTAB
+    Content: "00"
+
+## Check we can use just `Size` to emit custom data filled with zeroes
+## in the symbol table section.
+# RUN: yaml2obj --docnum=5 %s -o %t5
+# RUN: llvm-readobj --section-data -S %t5 | FileCheck %s --check-prefix=CASE5
+
+# CASE5:      Name: .dynsym
+# CASE5-NEXT: Type: SHT_DYNSYM
+# CASE5-NEXT: Flags [
+# CASE5-NEXT:   SHF_ALLOC
+# CASE5-NEXT: ]
+# CASE5-NEXT: Address: 0x0
+# CASE5-NEXT: Offset: 0x1C0
+# CASE5-NEXT: Size: 5
+# CASE5-NEXT: Link: 2
+# CASE5-NEXT: Info: 0
+# CASE5-NEXT: AddressAlignment: 0
+# CASE5-NEXT: EntrySize: 24
+# CASE5-NEXT: SectionData (
+# CASE5-NEXT:   0000: 00000000 00
+# CASE5-NEXT: )
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Size: 5
+## TODO: .dynstr here is needed to set a proper Link for .dynsym.
+## Without this, llvm-readobj reports an error.
+## See https://bugs.llvm.org/show_bug.cgi?id=42215.
+  - Name: .dynstr
+    Type: SHT_STRTAB
+    Content: "00"
+
+## Check we can specify both `Size` and `Content` when size is greater
+## than content size. In this case zeroes are added as padding
+## after after the specified content.
+
+# RUN: yaml2obj --docnum=6 %s -o %t6
+# RUN: llvm-readobj %t6 --section-data -S | FileCheck %s --check-prefix=CASE6
+
+# CASE6:      Name: .dynsym
+# CASE6-NEXT: Type: SHT_DYNSYM
+# CASE6-NEXT: Flags [
+# CASE6-NEXT:   SHF_ALLOC
+# CASE6-NEXT: ]
+# CASE6-NEXT: Address: 0x0
+# CASE6-NEXT: Offset: 0x1C0
+# CASE6-NEXT: Size: 4
+# CASE6-NEXT: Link: 2
+# CASE6-NEXT: Info: 0
+# CASE6-NEXT: AddressAlignment: 0
+# CASE6-NEXT: EntrySize: 24
+# CASE6-NEXT: SectionData (
+# CASE6-NEXT:   0000: 01230000
+# CASE6-NEXT: )
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Content: "0123"
+    Size: 4
+## TODO: .dynstr here is needed to set a proper Link for .dynsym.
+## Without this, llvm-readobj reports an error.
+## See https://bugs.llvm.org/show_bug.cgi?id=42215.
+  - Name: .dynstr
+    Type: SHT_STRTAB
+    Content: "00"
+
+## Check we can specify both `Size` and `Content` when size is
+## equal to content size.
+
+# RUN: yaml2obj --docnum=7 %s -o %t7
+# RUN: llvm-readobj --section-data -S %t7 | FileCheck %s --check-prefix=CASE7
+
+# CASE7:       Name: .dynsym
+# CASE7-NEXT:  Type: SHT_DYNSYM
+# CASE7-NEXT:  Flags [
+# CASE7-NEXT:    SHF_ALLOC
+# CASE7-NEXT:  ]
+# CASE7-NEXT:  Address: 0x0
+# CASE7-NEXT:  Offset: 0x1C0
+# CASE7-NEXT:  Size: 2
+# CASE7-NEXT:  Link: 2
+# CASE7-NEXT:  Info: 0
+# CASE7-NEXT:  AddressAlignment: 0
+# CASE7-NEXT:  EntrySize: 24
+# CASE7-NEXT:  SectionData (
+# CASE7-NEXT:    0000: 0123
+# CASE7-NEXT:  )
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_DYN
+  Machine: EM_X86_64
+Sections:
+  - Name: .dynsym
+    Type: SHT_DYNSYM
+    Content: "0123"
+    Size: 2
+## TODO: .dynstr here is needed to set a proper Link for .dynsym.
+## Without this, llvm-readobj reports an error.
+## See https://bugs.llvm.org/show_bug.cgi?id=42215.
+  - Name: .dynstr
+    Type: SHT_STRTAB
+    Content: "00"