[llvm-objcopy] Handle -O <format> flag.

Summary:
The -O flag is currently being mostly ignored; it's only checked whether or not the output format is "binary". This adds support for a few formats (e.g. elf64-x86-64), so that when specified, the output can change between 32/64 bit and sizes/alignments are updated accordingly.

This fixes PR39135

Reviewers: jakehehrlich, jhenderson, alexshap, espindola

Reviewed By: jhenderson

Subscribers: emaste, arichardson, llvm-commits

Differential Revision: https://reviews.llvm.org/D53667

llvm-svn: 350541

diff --git a/llvm/test/tools/llvm-objcopy/ELF/bad-output-format.test b/llvm/test/tools/llvm-objcopy/ELF/bad-output-format.test
new file mode 100644 (file)
index 0000000..e01d955
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/ELF/bad-output-format.test
@@ -0,0 +1,13 @@
+# RUN: yaml2obj %s > %t.o
+
+# RUN: not llvm-objcopy -O xyz %t.o %t.2.o 2>&1 \
+# RUN:   | FileCheck %s --check-prefix=BAD-OUTPUT-FORMAT
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS32
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_386
+
+# BAD-OUTPUT-FORMAT: Invalid output format: 'xyz'.

diff --git a/llvm/test/tools/llvm-objcopy/ELF/binary-input-with-arch.test b/llvm/test/tools/llvm-objcopy/ELF/binary-input-with-arch.test
new file mode 100644 (file)
index 0000000..e8ae841
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/ELF/binary-input-with-arch.test
@@ -0,0 +1,20 @@
+# RUN: echo -n abcd > %t.x-txt
+# Preserve input to verify it is not modified.
+# RUN: cp %t.x-txt %t-copy.txt
+# RUN: llvm-objcopy -I binary -B i386 -O elf64-x86-64 %t.x-txt %t.o
+# RUN: llvm-readobj --file-headers %t.o | FileCheck %s
+# RUN: cmp %t.x-txt %t-copy.txt
+
+# Many uses of objcopy use no spaces in the flags, make sure that also works.
+# RUN: llvm-objcopy -Ibinary -Bi386 -Oelf64-x86-64 %t.x-txt %t-no-spaces.o
+# RUN: cmp %t.o %t-no-spaces.o
+
+# CHECK:      Format: ELF64-x86-64
+# CHECK-NEXT: Arch: x86_64
+# CHECK-NEXT: AddressSize: 64bit
+
+# CHECK: Class: 64-bit
+# CHECK: DataEncoding: LittleEndian
+# CHECK: Machine: EM_X86_64
+# CHECK: HeaderSize: 64
+# CHECK: SectionHeaderEntrySize: 64

diff --git a/llvm/test/tools/llvm-objcopy/ELF/cross-arch-headers.test b/llvm/test/tools/llvm-objcopy/ELF/cross-arch-headers.test
new file mode 100644 (file)
index 0000000..ec76fa6
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/ELF/cross-arch-headers.test
@@ -0,0 +1,71 @@
+# RUN: yaml2obj %s > %t.o
+
+# RUN: llvm-objcopy %t.o -O elf32-i386 %t.elf32_i386.o
+# RUN: llvm-readobj --file-headers %t.elf32_i386.o | FileCheck %s --check-prefixes=CHECK,I386,32
+
+# RUN: llvm-objcopy %t.o -O elf32-powerpcle %t.elf32_ppcle.o
+# RUN: llvm-readobj --file-headers %t.elf32_ppcle.o | FileCheck %s --check-prefixes=CHECK,PPC,32
+
+# RUN: llvm-objcopy %t.o -O elf32-x86-64 %t.elf32_x86_64.o
+# RUN: llvm-readobj --file-headers %t.elf32_x86_64.o | FileCheck %s --check-prefixes=CHECK,X86-64,32
+
+# RUN: llvm-objcopy %t.o -O elf64-powerpcle %t.elf64_ppcle.o
+# RUN: llvm-readobj --file-headers %t.elf64_ppcle.o | FileCheck %s --check-prefixes=CHECK,PPC64,64
+
+# RUN: llvm-objcopy %t.o -O elf64-x86-64 %t.elf64_x86_64.o
+# RUN: llvm-readobj --file-headers %t.elf64_x86_64.o | FileCheck %s --check-prefixes=CHECK,X86-64,64
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS32
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_386
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+  - Name:            .data
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+Symbols:
+  Global:
+    - Name:     foo
+      Type:     STT_FUNC
+      Section:  .text
+      Value:    0x1234
+    - Name:     bar
+      Type:     STT_OBJECT
+      Section:  .data
+      Value:    0xabcd
+
+# CHECK: Format:
+# 32-SAME:      ELF32-
+# 64-SAME:      ELF64-
+# I386-SAME:    i386
+# PPC-SAME:     ppc
+# PPC64-SAME:   ppc64
+# X86-64-SAME:  x86-64
+
+# I386-NEXT:    Arch: i386
+# PPC-NEXT:     Arch: powerpc
+# PPC64-NEXT:   Arch: powerpc64le
+# X86-64-NEXT:  Arch: x86_64
+
+# 32-NEXT:      AddressSize: 32bit
+# 64-NEXT:      AddressSize: 64bit
+
+# 32:     Class: 32-bit
+# 64:     Class: 64-bit
+# CHECK:  DataEncoding: LittleEndian
+
+# I386:   Machine: EM_386
+# PPC:    Machine: EM_PPC
+# PPC64:  Machine: EM_PPC64
+# X86-64: Machine: EM_X86_64
+
+# 32: HeaderSize: 52
+# 64: HeaderSize: 64
+
+# 32: SectionHeaderEntrySize: 40
+# 64: SectionHeaderEntrySize: 64

diff --git a/llvm/test/tools/llvm-objcopy/ELF/cross-arch-sections-symbols.test b/llvm/test/tools/llvm-objcopy/ELF/cross-arch-sections-symbols.test
new file mode 100644 (file)
index 0000000..1d959a9
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/ELF/cross-arch-sections-symbols.test
@@ -0,0 +1,153 @@
+# RUN: yaml2obj %s > %t.o
+# Preserve input to verify it is not modified.
+# RUN: cp %t.o %t-copy.o
+# RUN: llvm-objcopy %t.o -O elf64-x86-64 %t.2.o
+# RUN: llvm-readobj --sections --symbols %t.2.o | FileCheck %s
+# RUN: cmp %t.o %t-copy.o
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS32
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_386
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Size:            32
+  - Name:            .data
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+    Content:         DEADBEEF
+    Size:            16
+Symbols:
+  Global:
+    - Name:     foo
+      Type:     STT_FUNC
+      Section:  .text
+      Value:    16
+      Size:     8
+    - Name:     bar
+      Type:     STT_OBJECT
+      Section:  .data
+      Size:     16
+
+# CHECK:      Sections [
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 0
+# CHECK-NEXT:     Name:  (0)
+# CHECK-NEXT:     Type: SHT_NULL (0x0)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 0
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 0
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 1
+# CHECK-NEXT:     Name: .text
+# CHECK-NEXT:     Type: SHT_PROGBITS (0x1)
+# CHECK-NEXT:     Flags [ (0x6)
+# CHECK-NEXT:       SHF_ALLOC (0x2)
+# CHECK-NEXT:       SHF_EXECINSTR (0x4)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 32
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 0
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 2
+# CHECK-NEXT:     Name: .data
+# CHECK-NEXT:     Type: SHT_PROGBITS (0x1)
+# CHECK-NEXT:     Flags [ (0x2)
+# CHECK-NEXT:       SHF_ALLOC (0x2)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 16
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 0
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 3
+# CHECK-NEXT:     Name: .symtab
+# CHECK-NEXT:     Type: SHT_SYMTAB (0x2)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 72
+# CHECK-NEXT:     Link: 4
+# CHECK-NEXT:     Info: 1
+# CHECK-NEXT:     AddressAlignment: 8
+# CHECK-NEXT:     EntrySize: 24
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 4
+# CHECK-NEXT:     Name: .strtab
+# CHECK-NEXT:     Type: SHT_STRTAB (0x3)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 10
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 1
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 5
+# CHECK-NEXT:     Name: .shstrtab
+# CHECK-NEXT:     Type: SHT_STRTAB (0x3)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address:
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 39
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 1
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT: ]
+# CHECK-NEXT: Symbols [
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name:
+# CHECK-NEXT:     Value: 0x0
+# CHECK-NEXT:     Size: 0
+# CHECK-NEXT:     Binding: Local (0x0)
+# CHECK-NEXT:     Type: None (0x0)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: Undefined
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name: foo
+# CHECK-NEXT:     Value: 0x10
+# CHECK-NEXT:     Size: 8
+# CHECK-NEXT:     Binding: Global (0x1)
+# CHECK-NEXT:     Type: Function (0x2)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: .text
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name: bar
+# CHECK-NEXT:     Value: 0x0
+# CHECK-NEXT:     Size: 16
+# CHECK-NEXT:     Binding: Global (0x1)
+# CHECK-NEXT:     Type: Object (0x1)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: .data
+# CHECK-NEXT:   }
+# CHECK-NEXT: ]

diff --git a/llvm/tools/llvm-objcopy/CopyConfig.cpp b/llvm/tools/llvm-objcopy/CopyConfig.cpp
index 24f0e29..3737f57 100644 (file)
--- a/llvm/tools/llvm-objcopy/CopyConfig.cpp
+++ b/llvm/tools/llvm-objcopy/CopyConfig.cpp
@@ -189,6 +189,22 @@ static const MachineInfo &getMachineInfo(StringRef Arch) {
   return Iter->getValue();
 }
 
+static const StringMap<MachineInfo> OutputFormatMap{
+    // Name, {EMachine, 64bit, LittleEndian}
+    {"elf32-i386", {ELF::EM_386, false, true}},
+    {"elf32-powerpcle", {ELF::EM_PPC, false, true}},
+    {"elf32-x86-64", {ELF::EM_X86_64, false, true}},
+    {"elf64-powerpcle", {ELF::EM_PPC64, true, true}},
+    {"elf64-x86-64", {ELF::EM_X86_64, true, true}},
+};
+
+static const MachineInfo &getOutputFormatMachineInfo(StringRef Format) {
+  auto Iter = OutputFormatMap.find(Format);
+  if (Iter == std::end(OutputFormatMap))
+    error("Invalid output format: '" + Format + "'");
+  return Iter->getValue();
+}
+
 static void addGlobalSymbolsFromFile(std::vector<std::string> &Symbols,
                                      StringRef Filename) {
   SmallVector<StringRef, 16> Lines;
@@ -266,6 +282,8 @@ DriverConfig parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
       error("Specified binary input without specifiying an architecture");
     Config.BinaryArch = getMachineInfo(BinaryArch);
   }
+  if (!Config.OutputFormat.empty() && Config.OutputFormat != "binary")
+    Config.OutputArch = getOutputFormatMachineInfo(Config.OutputFormat);
 
   if (auto Arg = InputArgs.getLastArg(OBJCOPY_compress_debug_sections,
                                       OBJCOPY_compress_debug_sections_eq)) {

diff --git a/llvm/tools/llvm-objcopy/CopyConfig.h b/llvm/tools/llvm-objcopy/CopyConfig.h
index ce6ead8..71a2423 100644 (file)
--- a/llvm/tools/llvm-objcopy/CopyConfig.h
+++ b/llvm/tools/llvm-objcopy/CopyConfig.h
@@ -46,8 +46,10 @@ struct CopyConfig {
   StringRef OutputFilename;
   StringRef OutputFormat;
 
-  // Only applicable for --input-format=Binary
+  // Only applicable for --input-format=binary
   MachineInfo BinaryArch;
+  // Only applicable when --output-format!=binary (e.g. elf64-x86-64).
+  Optional<MachineInfo> OutputArch;
 
   // Advanced options
   StringRef AddGnuDebugLink;

diff --git a/llvm/tools/llvm-objcopy/ELF/ELFObjcopy.cpp b/llvm/tools/llvm-objcopy/ELF/ELFObjcopy.cpp
index 7008bcd..08e37d1 100644 (file)
--- a/llvm/tools/llvm-objcopy/ELF/ELFObjcopy.cpp
+++ b/llvm/tools/llvm-objcopy/ELF/ELFObjcopy.cpp
@@ -173,6 +173,8 @@ static void splitDWOToFile(const CopyConfig &Config, const Reader &Reader,
   auto DWOFile = Reader.create();
   DWOFile->removeSections(
       [&](const SectionBase &Sec) { return onlyKeepDWOPred(*DWOFile, Sec); });
+  if (Config.OutputArch)
+    DWOFile->Machine = Config.OutputArch.getValue().EMachine;
   FileBuffer FB(File);
   auto Writer = createWriter(Config, *DWOFile, FB, OutputElfType);
   Writer->finalize();
@@ -261,6 +263,8 @@ static void handleArgs(const CopyConfig &Config, Object &Obj,
   if (!Config.SplitDWO.empty()) {
     splitDWOToFile(Config, Reader, Config.SplitDWO, OutputElfType);
   }
+  if (Config.OutputArch)
+    Obj.Machine = Config.OutputArch.getValue().EMachine;
 
   // TODO: update or remove symbols only if there is an option that affects
   // them.
@@ -528,7 +532,10 @@ void executeObjcopyOnRawBinary(const CopyConfig &Config, MemoryBuffer &In,
   BinaryReader Reader(Config.BinaryArch, &In);
   std::unique_ptr<Object> Obj = Reader.create();
 
-  const ElfType OutputElfType = getOutputElfType(Config.BinaryArch);
+  // Prefer OutputArch (-O<format>) if set, otherwise fallback to BinaryArch
+  // (-B<arch>).
+  const ElfType OutputElfType = getOutputElfType(
+      Config.OutputArch ? Config.OutputArch.getValue() : Config.BinaryArch);
   handleArgs(Config, *Obj, Reader, OutputElfType);
   std::unique_ptr<Writer> Writer =
       createWriter(Config, *Obj, Out, OutputElfType);
@@ -540,7 +547,10 @@ void executeObjcopyOnBinary(const CopyConfig &Config,
                             object::ELFObjectFileBase &In, Buffer &Out) {
   ELFReader Reader(&In);
   std::unique_ptr<Object> Obj = Reader.create();
-  const ElfType OutputElfType = getOutputElfType(In);
+  // Prefer OutputArch (-O<format>) if set, otherwise infer it from the input.
+  const ElfType OutputElfType =
+      Config.OutputArch ? getOutputElfType(Config.OutputArch.getValue())
+                        : getOutputElfType(In);
   ArrayRef<uint8_t> BuildIdBytes;
 
   if (!Config.BuildIdLinkDir.empty()) {