[yaml2obj] Write the section header table after section contents

Linkers (ld.bfd/gold/lld) place the section header table at the very
end. This allows tools to strip it, which is optional in executable/shared objects.
In addition, if we add or section, the size of the section header table
will change. Placing the section header table in the end keeps section
offsets unchanged.

yaml2obj currently places the section header table immediately after the
program header. Follow what linkers do to make offset updating easier.

Reviewed By: grimar

Differential Revision: https://reviews.llvm.org/D67221

llvm-svn: 371074

llvm/lib/ObjectYAML/ELFEmitter.cpp

@@ -116,7 +116,6 @@ template <class ELFT> class ELFState {
 
   bool buildSectionIndex();
   bool buildSymbolIndexes();
-  void initELFHeader(Elf_Ehdr &Header);
   void initProgramHeaders(std::vector<Elf_Phdr> &PHeaders);
   bool initImplicitHeader(ContiguousBlobAccumulator &CBA, Elf_Shdr &Header,
                           StringRef SecName, ELFYAML::Section *YAMLSec);
@@ -132,6 +131,7 @@ template <class ELFT> class ELFState {
   void setProgramHeaderLayout(std::vector<Elf_Phdr> &PHeaders,
                               std::vector<Elf_Shdr> &SHeaders);
   void finalizeStrings();
+  void writeELFHeader(ContiguousBlobAccumulator &CBA, raw_ostream &OS);
   bool writeSectionContent(Elf_Shdr &SHeader,
                            const ELFYAML::RawContentSection &Section,
                            ContiguousBlobAccumulator &CBA);
@@ -205,8 +205,11 @@ template <class ELFT> ELFState<ELFT>::ELFState(ELFYAML::Object &D) : Doc(D) {
   }
 }
 
-template <class ELFT> void ELFState<ELFT>::initELFHeader(Elf_Ehdr &Header) {
+template <class ELFT>
+void ELFState<ELFT>::writeELFHeader(ContiguousBlobAccumulator &CBA, raw_ostream &OS) {
   using namespace llvm::ELF;
+
+  Elf_Ehdr Header;
   zero(Header);
   Header.e_ident[EI_MAG0] = 0x7f;
   Header.e_ident[EI_MAG1] = 'E';
@@ -230,14 +233,18 @@ template <class ELFT> void ELFState<ELFT>::initELFHeader(Elf_Ehdr &Header) {
   Header.e_shentsize =
       Doc.Header.SHEntSize ? (uint16_t)*Doc.Header.SHEntSize : sizeof(Elf_Shdr);
   // Immediately following the ELF header and program headers.
-  Header.e_shoff =
-      Doc.Header.SHOffset
-          ? (typename ELFT::uint)(*Doc.Header.SHOffset)
-          : sizeof(Header) + sizeof(Elf_Phdr) * Doc.ProgramHeaders.size();
+  // Align the start of the section header and write the ELF header.
+  uint64_t ShOffset;
+  CBA.getOSAndAlignedOffset(ShOffset, sizeof(typename ELFT::uint));
+  Header.e_shoff = Doc.Header.SHOffset
+                       ? typename ELFT::uint(*Doc.Header.SHOffset)
+                       : ShOffset;
   Header.e_shnum =
       Doc.Header.SHNum ? (uint16_t)*Doc.Header.SHNum : Doc.Sections.size();
   Header.e_shstrndx = Doc.Header.SHStrNdx ? (uint16_t)*Doc.Header.SHStrNdx
                                           : SN2I.get(".shstrtab");
+
+  OS.write((const char *)&Header, sizeof(Header));
 }
 
 template <class ELFT>
@@ -1040,19 +1047,13 @@ int ELFState<ELFT>::writeELF(raw_ostream &OS, ELFYAML::Object &Doc) {
   if (!State.buildSectionIndex() || !State.buildSymbolIndexes())
     return 1;
 
-  Elf_Ehdr Header;
-  State.initELFHeader(Header);
-
-  // TODO: Flesh out section header support.
-
   std::vector<Elf_Phdr> PHeaders;
   State.initProgramHeaders(PHeaders);
 
   // XXX: This offset is tightly coupled with the order that we write
   // things to `OS`.
-  const size_t SectionContentBeginOffset = Header.e_ehsize +
-                                           Header.e_phentsize * Header.e_phnum +
-                                           Header.e_shentsize * Header.e_shnum;
+  const size_t SectionContentBeginOffset =
+      sizeof(Elf_Ehdr) + sizeof(Elf_Phdr) * Doc.ProgramHeaders.size();
   ContiguousBlobAccumulator CBA(SectionContentBeginOffset);
 
   std::vector<Elf_Shdr> SHeaders;
@@ -1062,10 +1063,10 @@ int ELFState<ELFT>::writeELF(raw_ostream &OS, ELFYAML::Object &Doc) {
   // Now we can decide segment offsets
   State.setProgramHeaderLayout(PHeaders, SHeaders);
 
-  OS.write((const char *)&Header, sizeof(Header));
+  State.writeELFHeader(CBA, OS);
   writeArrayData(OS, makeArrayRef(PHeaders));
-  writeArrayData(OS, makeArrayRef(SHeaders));
   CBA.writeBlobToStream(OS);
+  writeArrayData(OS, makeArrayRef(SHeaders));
   return 0;
 }
 

llvm/test/Object/invalid.test

@@ -315,7 +315,7 @@ FileHeader:
 # RUN: yaml2obj %s --docnum=16 -o %t16
 # RUN: not llvm-readobj -r %t16 2>&1 | FileCheck -DFILE=%t16 --check-prefix=INVALID-REL-SYM %s
 
-# INVALID-REL-SYM: error: '[[FILE]]': unable to access section [index 2] data at 0x18000180: offset goes past the end of file
+# INVALID-REL-SYM: error: '[[FILE]]': unable to access section [index 2] data at 0x18000040: offset goes past the end of file
 
 --- !ELF
 FileHeader:
@@ -565,7 +565,7 @@ Sections:
 # RUN: yaml2obj --docnum=26 %s -o %t26
 # RUN: not llvm-readobj -h %t26 2>&1 | FileCheck -DFILE=%t26 --check-prefix=INVALID-SEC-NUM1 %s
 
-# INVALID-SEC-NUM1: error: '[[FILE]]': invalid section header table offset (e_shoff = 0x40) or invalid number of sections specified in the first section header's sh_size field (0x3ffffffffffffff)
+# INVALID-SEC-NUM1: error: '[[FILE]]': invalid section header table offset (e_shoff = 0x78) or invalid number of sections specified in the first section header's sh_size field (0x3ffffffffffffff)
 
 --- !ELF
 FileHeader:

llvm/test/tools/llvm-objcopy/ELF/group-reorder.test

@@ -8,12 +8,12 @@
 # aren't purely sorting based on offsets (it gets moved to the beginning
 # despite having a larger offset).
 
-# IN:      There are 7 section headers, starting at offset 0x40:
+# IN:      There are 7 section headers, starting at offset 0x160:
 # IN:        [Nr] Name              Type            Address          Off    Size
 # IN-NEXT:   [ 0]                   NULL            0000000000000000 000000 000000
-# IN-NEXT:   [ 1] .foo              PROGBITS        0000000000000000 000200 000040
-# IN-NEXT:   [ 2] .group            GROUP           0000000000000000 000240 000008
-# IN-NEXT:   [ 3] .bar              PROGBITS        0000000000000000 000248 000040
+# IN-NEXT:   [ 1] .foo              PROGBITS        0000000000000000 000040 000040
+# IN-NEXT:   [ 2] .group            GROUP           0000000000000000 000080 000008
+# IN-NEXT:   [ 3] .bar              PROGBITS        0000000000000000 000088 000040
 
 # IN:      COMDAT group section [    2] `.group' [bar] contains 1 sections:
 # IN-NEXT:    [Index]    Name

llvm/test/tools/llvm-objcopy/ELF/invalid-e_shoff.test

@@ -7,13 +7,13 @@
 
 ## Sanity check that the section header table is at offset 64:
 # RUN: llvm-readobj --file-headers %t.o | FileCheck %s --check-prefix=VALIDATE
-# VALIDATE: SectionHeaderOffset: 0x40{{$}}
+# VALIDATE: SectionHeaderOffset: 0x80{{$}}
 
 ## Truncate the file to end before the section header table ends.
-# RUN: %python -c "with open('%/t.o', 'r+b') as input: input.truncate(65)"
+# RUN: %python -c "with open('%/t.o', 'r+b') as input: input.truncate(0x7f)"
 # RUN: not llvm-objcopy %t.o 2>&1 | FileCheck %s -DINPUT=%t.o --check-prefix=CASE1
 
-# CASE1: error: '[[INPUT]]': section header table goes past the end of the file: e_shoff = 0x40
+# CASE1: error: '[[INPUT]]': section header table goes past the end of the file: e_shoff = 0x80
 
 ## Set the e_shoff field to a value much larger than the object file size.
 # RUN: %python -c "with open('%/t2.o', 'r+b') as input: import struct; bytes = struct.pack('<Q', 0x40000000); input.seek(40); input.write(bytes)"

llvm/test/tools/llvm-objcopy/ELF/invalid-p_filesz-p_offset.test

@@ -4,7 +4,7 @@
 
 # RUN: yaml2obj --docnum=1 %s -o %t1.o
 # RUN: not llvm-objcopy %t1.o 2>&1 | FileCheck %s --check-prefix=ERR1
-# ERR1: error: program header with offset 0x1b8 and file size 0x100000 goes past the end of the file
+# ERR1: error: program header with offset 0x78 and file size 0x100000 goes past the end of the file
 
 --- !ELF
 FileHeader:

llvm/test/tools/llvm-objcopy/ELF/overlapping-sections-in-segments.test

@@ -4,14 +4,13 @@
 ## inputs somehow.
 # RUN: yaml2obj %s -o %t.o
 
-## First, check that the section header table appears immediately after the program
-## header table.
+## First, check the address of the section header table.
 # RUN: llvm-readobj --file-headers %t.o | FileCheck %s --check-prefix=SHDRS-OFFSET
-# SHDRS-OFFSET: SectionHeaderOffset: 0x78{{$}}
+# SHDRS-OFFSET: SectionHeaderOffset: 0x1050{{$}}
 
 ## Binary edit the section header sh_offset field of the second section to
-## overlap the first one.
-# RUN: %python -c "with open('%/t.o', 'r+b') as input: import struct; bytes = struct.pack('<Q', 0x1001); input.seek(272); input.write(bytes)"
+## (e_shoff+64*2+24 = 0x10e8) overlap the first one.
+# RUN: %python -c "with open('%/t.o', 'r+b') as input: import struct; bytes = struct.pack('<Q', 0x1001); input.seek(0x10e8); input.write(bytes)"
 
 ## Sanity check that the binary editing modified the correct field.
 # RUN: llvm-readobj --section-headers %t.o | FileCheck %s

llvm/test/tools/llvm-objcopy/ELF/overlapping-sections.test

@@ -3,14 +3,13 @@
 ## inputs somehow.
 # RUN: yaml2obj %s -o %t.o
 
-## First, check that the section header table appears immediately after the ELF
-## header.
+## First, check the address of the section header table.
 # RUN: llvm-readobj --file-headers %t.o | FileCheck %s --check-prefix=SHDRS-OFFSET
-# SHDRS-OFFSET: SectionHeaderOffset: 0x40{{$}}
+# SHDRS-OFFSET: SectionHeaderOffset: 0x1050{{$}}
 
 ## Binary edit the section header sh_offset field of the second section to
-## overlap the first one.
-# RUN: %python -c "with open('%/t.o', 'r+b') as input: import struct; bytes = struct.pack('<Q', 0x1001); input.seek(216); input.write(bytes)"
+## (e_shoff+64*2+24 = 0x10e8) overlap the first one.
+# RUN: %python -c "with open('%/t.o', 'r+b') as input: import struct; bytes = struct.pack('<Q', 0x1001); input.seek(0x10e8); input.write(bytes)"
 
 ## Sanity check that the binary editing modified the correct field.
 # RUN: llvm-readobj --section-headers %t.o | FileCheck %s --check-prefix=VALIDATE

llvm/test/tools/llvm-objcopy/ELF/preserve-segment-contents-ehdr-phdrs.test

@@ -11,7 +11,7 @@
 # BEFORE:      Type: PT_LOAD
 # BEFORE-NEXT: Offset: 0x0
 # BEFORE:      Type: PT_LOAD
-# BEFORE-NEXT: Offset: 0x240
+# BEFORE-NEXT: Offset: 0xC0
 
 # AFTER:      SectionHeaderCount: 3
 # AFTER:      Type: PT_LOAD

llvm/test/tools/llvm-readobj/elf-broken-dynsym-link.test

@@ -14,14 +14,14 @@
 # LLVM-NEXT:    SHF_ALLOC
 # LLVM-NEXT:  ]
 # LLVM-NEXT:  Address: 0x0
-# LLVM-NEXT:  Offset: 0x180
+# LLVM-NEXT:  Offset: 0x40
 # LLVM-NEXT:  Size: 24
 # LLVM-NEXT:  Link: 0
 
 # GNU:      Section Headers:
 # GNU-NEXT:  [Nr] Name    Type   Address          Off    Size   ES Flg Lk
 # GNU-NEXT:  [ 0]         NULL   0000000000000000 000000 000000 00 0   0
-# GNU-NEXT:  [ 1] .dynsym DYNSYM 0000000000000000 000180 000018 18 A   0
+# GNU-NEXT:  [ 1] .dynsym DYNSYM 0000000000000000 000040 000018 18 A   0
 
 --- !ELF
 FileHeader:
@@ -58,11 +58,11 @@ Sections:
 # LLVM2-NEXT:    SHF_ALLOC
 # LLVM2-NEXT:  ]
 # LLVM2-NEXT:  Address: 0x0
-# LLVM2-NEXT:  Offset: 0x180
+# LLVM2-NEXT:  Offset: 0x40
 # LLVM2-NEXT:  Size: 24
 # LLVM2-NEXT:  Link: 255
 
 # GNU2:      Section Headers:
 # GNU2-NEXT:  [Nr] Name    Type   Address          Off    Size   ES Flg Lk
 # GNU2-NEXT:  [ 0]         NULL   0000000000000000 000000 000000 00 0   0
-# GNU2-NEXT:  [ 1] .dynsym DYNSYM 0000000000000000 000180 000018 18 A   255
+# GNU2-NEXT:  [ 1] .dynsym DYNSYM 0000000000000000 000040 000018 18 A   255

llvm/test/tools/llvm-readobj/elf-dynamic-malformed.test

@@ -216,7 +216,7 @@ ProgramHeaders:
 # BAD-RELA-NEXT:   0x0000000000000007 RELA 0x1000000
 # BAD-RELA-NEXT:   0x0000000000000000 NULL 0x0
 # BAD-RELA-NEXT: ]
-# BAD-RELA-GNU:      Dynamic section at offset 0x1f0 contains 2 entries:
+# BAD-RELA-GNU:      Dynamic section at offset 0xb0 contains 2 entries:
 # BAD-RELA-GNU-NEXT: Tag                Type   Name/Value
 # BAD-RELA-GNU-NEXT: 0x0000000000000007 (RELA) 0x1000000
 # BAD-RELA-GNU-NEXT: 0x0000000000000000 (NULL) 0x0

llvm/test/tools/llvm-readobj/elf-dynamic-no-pt-dynamic.test

@@ -14,7 +14,7 @@
 # LLVM-NEXT:   0x0000000000000000 NULL 0x0
 # LLVM-NEXT: ]
 
-# GNU:      Dynamic section at offset 0x1b8 contains 1 entries:
+# GNU:      Dynamic section at offset 0x78 contains 1 entries:
 # GNU-NEXT: Tag                Type   Name/Value
 # GNU-NEXT: 0x0000000000000000 (NULL) 0x0
 

llvm/test/tools/llvm-readobj/elf-file-headers.test

@@ -21,7 +21,7 @@
 # I386-NEXT:  Version: 1
 # I386-NEXT:  Entry: 0x0
 # I386-NEXT:  ProgramHeaderOffset: 0x34
-# I386-NEXT:  SectionHeaderOffset: 0x34
+# I386-NEXT:  SectionHeaderOffset: 0x64
 # I386-NEXT:  Flags [ (0x0)
 # I386-NEXT:  ]
 # I386-NEXT:  HeaderSize: 52
@@ -65,7 +65,7 @@ FileHeader:
 # X86-64-NEXT:  Version: 1
 # X86-64-NEXT:  Entry: 0x0
 # X86-64-NEXT:  ProgramHeaderOffset: 0x40
-# X86-64-NEXT:  SectionHeaderOffset: 0x40
+# X86-64-NEXT:  SectionHeaderOffset: 0x78
 # X86-64-NEXT:  Flags [ (0x0)
 # X86-64-NEXT:  ]
 # X86-64-NEXT:  HeaderSize: 64
@@ -116,7 +116,7 @@ FileHeader:
 # LANAI-NEXT:  Version: 1
 # LANAI-NEXT:  Entry: 0x0
 # LANAI-NEXT:  ProgramHeaderOffset: 0x34
-# LANAI-NEXT:  SectionHeaderOffset: 0x34
+# LANAI-NEXT:  SectionHeaderOffset: 0x64
 # LANAI-NEXT:  Flags [ (0x0)
 # LANAI-NEXT:  ]
 # LANAI-NEXT:  HeaderSize: 52

llvm/test/tools/llvm-readobj/elf-hidden-versym.test

@@ -2,7 +2,7 @@
 # RUN: llvm-readelf -V %t | FileCheck %s --check-prefix=HIDDEN
 
 # HIDDEN:      Version symbols section '.gnu.version' contains 2 entries:
-# HIDDEN-NEXT:  Addr: 0000000000200210  Offset: 0x000240  Link: 6 (.dynsym)
+# HIDDEN-NEXT:  Addr: 0000000000200210  Offset: 0x000040  Link: 6 (.dynsym)
 # HIDDEN-NEXT:   000:   0 (*local*)       3h(hiddensym)
 
 --- !ELF

llvm/test/tools/llvm-readobj/elf-invalid-shstrndx.test

@@ -4,7 +4,7 @@
 
 # GNU:      ELF Header:
 # GNU:        Section header string table index: 255
-# GNU-NEXT:   There are 4 section headers, starting at offset 0x40:
+# GNU-NEXT:   There are 4 section headers, starting at offset 0x78:
 # GNU:      Section Headers:
 # GNU-NEXT:  [Nr] Name
 # GNU-EMPTY:

llvm/test/tools/llvm-readobj/elf-invalid-versioning.test

@@ -2,7 +2,7 @@
 # RUN: llvm-readelf -V %t | FileCheck %s --check-prefix=INVALID
 
 # INVALID:      Version symbols section '.gnu.version' contains 2 entries:
-# INVALID-NEXT:  Addr: 0000000000200210  Offset: 0x000240  Link: 6 (.dynsym)
+# INVALID-NEXT:  Addr: 0000000000200210  Offset: 0x000040  Link: 6 (.dynsym)
 # INVALID-NEXT:   000:   0 (*local*)       3 (*invalid*)
 
 --- !ELF

llvm/test/tools/llvm-readobj/elf-loadname.test

@@ -9,7 +9,7 @@
 # LLVM-NEXT: AddressSize: 64bit
 # LLVM-NEXT: LoadName: test.so
 
-# GNU:       Dynamic section at offset 0x200 contains 4 entries:
+# GNU:       Dynamic section at offset 0x80 contains 4 entries:
 # GNU-NEXT:   Tag                Type     Name/Value
 # GNU-NEXT:   0x0000000000000005 (STRTAB) 0x0
 # GNU-NEXT:   0x000000000000000a (STRSZ)  7 (bytes)

llvm/test/tools/llvm-readobj/elf-packed-relocs.test

@@ -14,7 +14,7 @@
 # LLVM1-NEXT: }
 
 # RUN: yaml2obj -docnum 1 %s | llvm-readelf -relocations - | FileCheck --check-prefix=GNU1 %s
-# GNU1:      Relocation section '.rela.dyn' at offset 0x180 contains 8 entries:
+# GNU1:      Relocation section '.rela.dyn' at offset 0x40 contains 8 entries:
 # GNU1:      0000000000001100  0000000000000008 R_X86_64_RELATIVE                 0
 # GNU1-NEXT: 0000000000001180  0000000000000008 R_X86_64_RELATIVE                 0
 # GNU1-NEXT: 0000000000001188  0000000100000001 R_X86_64_64            0000000000000000 sym1 + 0
@@ -62,7 +62,7 @@ Symbols:
 # LLVM2-NEXT: }
 
 # RUN: yaml2obj -docnum 2 %s | llvm-readelf -relocations - | FileCheck --check-prefix=GNU2 %s
-# GNU2:      Relocation section '.rel.dyn' at offset 0xfc contains 10 entries:
+# GNU2:      Relocation section '.rel.dyn' at offset 0x34 contains 10 entries:
 # GNU2:      00001008  00000101 R_386_32               00000000   sym1
 # GNU2-NEXT: 00001010  00000203 R_386_GOT32            00000000   sym2
 # GNU2-NEXT: 0000100c  00000008 R_386_RELATIVE
@@ -109,7 +109,7 @@ Symbols:
 # LLVM3-NEXT: }
 
 # RUN: yaml2obj -docnum 3 %s | llvm-readelf -relocations - | FileCheck --check-prefix=GNU3 %s
-# GNU3:      Relocation section '.rela.dyn' at offset 0x180 contains 6 entries:
+# GNU3:      Relocation section '.rela.dyn' at offset 0x40 contains 6 entries:
 # GNU3: 0000000000001100  0000000000000008 R_X86_64_RELATIVE                 0
 # GNU3-NEXT: 0000000000001180  0000000000000008 R_X86_64_RELATIVE                 8
 # GNU3-NEXT: 0000000000001200  0000000100000001 R_X86_64_64            0000000000000000 sym1 + 0

llvm/test/tools/llvm-readobj/elf-relr-relocs.test

@@ -42,7 +42,7 @@
 # RUN: yaml2obj -docnum 1 %s \
 # RUN:   | llvm-readelf -relocations -raw-relr - \
 # RUN:   | FileCheck --check-prefix=RAW-GNU1 %s
-# RAW-GNU1:      Relocation section '.relr.dyn' at offset 0x180 contains 5 entries:
+# RAW-GNU1:      Relocation section '.relr.dyn' at offset 0x40 contains 5 entries:
 # RAW-GNU1:      0000000000010d60
 # RAW-GNU1-NEXT: 0000000000000103
 # RAW-GNU1-NEXT: 0000000000020000
@@ -52,7 +52,7 @@
 # RUN: yaml2obj -docnum 1 %s \
 # RUN:   | llvm-readelf -relocations - \
 # RUN:   | FileCheck --check-prefix=GNU1 %s
-# GNU1:      Relocation section '.relr.dyn' at offset 0x180 contains 21 entries:
+# GNU1:      Relocation section '.relr.dyn' at offset 0x40 contains 21 entries:
 # GNU1:      0000000000010d60  0000000000000008 R_X86_64_RELATIVE
 # GNU1-NEXT: 0000000000010d68  0000000000000008 R_X86_64_RELATIVE
 # GNU1-NEXT: 0000000000010da0  0000000000000008 R_X86_64_RELATIVE
@@ -127,7 +127,7 @@ Sections:
 # RUN: yaml2obj -docnum 2 %s \
 # RUN:   | llvm-readelf -relocations -raw-relr - \
 # RUN:   | FileCheck --check-prefix=RAW-GNU2 %s
-# RAW-GNU2:      Relocation section '.relr.dyn' at offset 0xfc contains 5 entries:
+# RAW-GNU2:      Relocation section '.relr.dyn' at offset 0x34 contains 5 entries:
 # RAW-GNU2:      00010d60
 # RAW-GNU2-NEXT: 00000103
 # RAW-GNU2-NEXT: 00020000
@@ -137,7 +137,7 @@ Sections:
 # RUN: yaml2obj -docnum 2 %s \
 # RUN:   | llvm-readelf -relocations - \
 # RUN:   | FileCheck --check-prefix=GNU2 %s
-# GNU2:      Relocation section '.relr.dyn' at offset 0xfc contains 14 entries:
+# GNU2:      Relocation section '.relr.dyn' at offset 0x34 contains 14 entries:
 # GNU2:      00010d60  00000008 R_386_RELATIVE
 # GNU2-NEXT: 00010d64  00000008 R_386_RELATIVE
 # GNU2-NEXT: 00010d80  00000008 R_386_RELATIVE