[llvm-objcopy] Add RISC-V support for -B/-O

[rupprecht]

Summary

This fixes PR41544

[jakehehrlich]

I recall @ruiu telling me that mips had a really odd endianness that wasn't accounted for by the standard ELFT types. Is that still true?

[rupprecht]

In D61272#1482825, @jakehehrlich wrote:

I recall @ruiu telling me that mips had a really odd endianness that wasn't accounted for by the standard ELFT types. Is that still true?

The mips changes here are just rearranging the map a bit -- the only thing added to the map is risc-v.

[ruiu]

Some field in the MIPS ELF file is not neither little nor big endian but a middle-endian (i.e. its byte order is not ABCD nor DCBA but CDAB). That's still true. But that doesn't seem to be relevant to this patch.

llvm/trunk/test/tools/llvm-objcopy/ELF/binary-input-arch.test

 # RUN: llvm-readobj --file-headers %t.i386_x86-64.o | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64
 
 # RUN: llvm-objcopy -I binary -B mips %t.txt %t.mips.o
 # RUN: llvm-readobj --file-headers %t.mips.o | FileCheck %s --check-prefixes=CHECK,BE,MIPS,32
 
 # RUN: llvm-objcopy -I binary -B powerpc:common64 %t.txt %t.powerpc_common64.o
 # RUN: llvm-readobj --file-headers %t.powerpc_common64.o | FileCheck %s --check-prefixes=CHECK,LE,PPC,64
 
+# RUN: llvm-objcopy -I binary -B riscv:rv32 %t.txt %t.rv32.o
+# RUN: llvm-readobj --file-headers %t.rv32.o | FileCheck %s --check-prefixes=CHECK,LE,RISCV32,32
+
+# RUN: llvm-objcopy -I binary -B riscv:rv64 %t.txt %t.rv64.o
+# RUN: llvm-readobj --file-headers %t.rv64.o | FileCheck %s --check-prefixes=CHECK,LE,RISCV64,64
+
 # RUN: llvm-objcopy -I binary -B sparc %t.txt %t.sparc.o
 # RUN: llvm-readobj --file-headers %t.sparc.o | FileCheck %s --check-prefixes=CHECK,LE,SPARC,32
 
 # RUN: llvm-objcopy -I binary -B x86-64 %t.txt %t.x86-64.o
 # RUN: llvm-readobj --file-headers %t.x86-64.o | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64
 
 # CHECK: Format:
-# AARCH64-SAME: ELF64-aarch64-little
-# ARM-SAME:     ELF32-arm-little
-# I386-SAME:    ELF32-i386
-# MIPS-SAME:    ELF32-mips{{$}}
-# PPC-SAME:     ELF64-ppc64
-# SPARC-SAME:   ELF32-sparc
-# X86-64-SAME:  ELF64-x86-64
+# 32-SAME:      ELF32-
+# 64-SAME:      ELF64-
+# AARCH64-SAME: aarch64-little
+# ARM-SAME:     arm-little
+# I386-SAME:    i386
+# MIPS-SAME:    mips{{$}}
+# RISCV32-SAME: riscv{{$}}
+# RISCV64-SAME: riscv{{$}}
+# PPC-SAME:     ppc64
+# SPARC-SAME:   sparc
+# X86-64-SAME:  x86-64
 
 # AARCH64-NEXT: Arch: aarch64
 # ARM-NEXT:     Arch: arm
 # I386-NEXT:    Arch: i386
 # MIPS-NEXT:    Arch: mips{{$$}}
 # PPC-NEXT:     Arch: powerpc64le
+# RISCV32-NEXT: Arch: riscv32
+# RISCV64-NEXT: Arch: riscv64
 # SPARC-NEXT:   Arch: sparcel
 # X86-64-NEXT:  Arch: x86_64
 
 # 32-NEXT:      AddressSize: 32bit
 # 64-NEXT:      AddressSize: 64bit
 
 # CHECK:        ElfHeader {
 # CHECK-NEXT:     Ident {
 # CHECK-NEXT:       Magic: (7F 45 4C 46)
 # 32-NEXT:          Class: 32-bit (0x1)
 # 64-NEXT:          Class: 64-bit (0x2)
 # LE-NEXT:          DataEncoding: LittleEndian (0x1)
 # BE-NEXT:          DataEncoding: BigEndian (0x2)
 # CHECK-NEXT:       FileVersion: 1
 # CHECK-NEXT:       OS/ABI: SystemV (0x0)
 # CHECK-NEXT:       ABIVersion: 0
 # CHECK-NEXT:       Unused: (00 00 00 00 00 00 00)
 # CHECK-NEXT:     }
 # CHECK-NEXT:     Type: Relocatable (0x1)
 # AARCH64-NEXT:   Machine: EM_AARCH64 (0xB7)
 # ARM-NEXT:       Machine: EM_ARM (0x28)
 # I386-NEXT:      Machine: EM_386 (0x3)
 # MIPS-NEXT:      Machine: EM_MIPS (0x8)
 # PPC-NEXT:       Machine: EM_PPC64 (0x15)
+# RISCV32-NEXT:   Machine: EM_RISCV (0xF3)
+# RISCV64-NEXT:   Machine: EM_RISCV (0xF3)
 # SPARC-NEXT:     Machine: EM_SPARC (0x2)
 # X86-64-NEXT:    Machine: EM_X86_64 (0x3E)
 # CHECK-NEXT:     Version: 1
 # CHECK-NEXT:     Entry: 0x0
 # CHECK-NEXT:     ProgramHeaderOffset:
 # CHECK-NEXT:     SectionHeaderOffset:
 # CHECK-NEXT:     Flags [ (0x0)
 # CHECK-NEXT:     ]

llvm/trunk/test/tools/llvm-objcopy/ELF/cross-arch-headers.test

 # RUN: llvm-objcopy %t.o -O elf32-x86-64 %t.elf32_x86_64.o --split-dwo=%t.elf32_x86_64.dwo
 # RUN: llvm-readobj --file-headers %t.elf32_x86_64.o | FileCheck %s --check-prefixes=CHECK,LE,X86-64,32,SYSV
 # RUN: llvm-readobj --file-headers %t.elf32_x86_64.dwo | FileCheck %s --check-prefixes=CHECK,LE,X86-64,32,SYSV
 
 # RUN: llvm-objcopy %t.o -O elf64-powerpcle %t.elf64_ppcle.o --split-dwo=%t.elf64_ppcle.dwo
 # RUN: llvm-readobj --file-headers %t.elf64_ppcle.o | FileCheck %s --check-prefixes=CHECK,LE,PPC64LE,64,SYSV
 # RUN: llvm-readobj --file-headers %t.elf64_ppcle.dwo | FileCheck %s --check-prefixes=CHECK,LE,PPC64LE,64,SYSV
 
+# RUN: llvm-objcopy %t.o -O elf32-littleriscv %t.elf32_littleriscv.o --split-dwo=%t.elf32_littleriscv.dwo
+# RUN: llvm-readobj --file-headers %t.elf32_littleriscv.o | FileCheck %s --check-prefixes=CHECK,LE,RISCV32,32,SYSV
+# RUN: llvm-readobj --file-headers %t.elf32_littleriscv.dwo | FileCheck %s --check-prefixes=CHECK,LE,RISCV32,32,SYSV
+
+# RUN: llvm-objcopy %t.o -O elf64-littleriscv %t.elf64_littleriscv.o --split-dwo=%t.elf64_littleriscv.dwo
+# RUN: llvm-readobj --file-headers %t.elf64_littleriscv.o | FileCheck %s --check-prefixes=CHECK,LE,RISCV64,64,SYSV
+# RUN: llvm-readobj --file-headers %t.elf64_littleriscv.dwo | FileCheck %s --check-prefixes=CHECK,LE,RISCV64,64,SYSV
+
 # RUN: llvm-objcopy %t.o -O elf64-x86-64 %t.elf64_x86_64.o --split-dwo=%t.elf64_x86_64.dwo
 # RUN: llvm-readobj --file-headers %t.elf64_x86_64.o | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64,SYSV
 # RUN: llvm-readobj --file-headers %t.elf64_x86_64.dwo | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64,SYSV
 
 # RUN: llvm-objcopy %t.o -O elf64-x86-64-freebsd %t.elf64_x86_64_freebsd.o --split-dwo=%t.elf64_x86_64_freebsd.dwo
 # RUN: llvm-readobj --file-headers %t.elf64_x86_64_freebsd.o | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64,FREEBSD
 # RUN: llvm-readobj --file-headers %t.elf64_x86_64_freebsd.dwo | FileCheck %s --check-prefixes=CHECK,LE,X86-64,64,FREEBSD
 

 # I386-SAME:    i386
 # IAMCU-SAME:   iamcu
 # AARCH-SAME:   aarch64
 # ARM-SAME:     arm-little
 # MIPS-SAME:    mips
 # PPC-SAME:     ppc{{$}}
 # PPC64BE-SAME: ppc64{{$}}
 # PPC64LE-SAME: ppc64{{$}}
+# RISCV32-SAME: riscv{{$}}
+# RISCV64-SAME: riscv{{$}}
 # X86-64-SAME:  x86-64
 # DEFAULT-SAME: unknown
 
 # I386-NEXT:     Arch: i386
 # IAMCU-NEXT:    Arch: i386
 # AARCH-NEXT:    Arch: aarch64
 # ARM-NEXT:      Arch: arm
 # MIPSBE-NEXT:   Arch: mips{{$}}
 # MIPSLE-NEXT:   Arch: mipsel{{$}}
 # MIPS64BE-NEXT: Arch: mips64{{$}}
 # MIPS64LE-NEXT: Arch: mips64el{{$}}
 # PPC-NEXT:      Arch: powerpc{{$}}
 # PPC64BE-NEXT:  Arch: powerpc64{{$}}
 # PPC64LE-NEXT:  Arch: powerpc64le
+# RISCV32-NEXT:  Arch: riscv32
+# RISCV64-NEXT:  Arch: riscv64
 # X86-64-NEXT:   Arch: x86_64
 # DEFAULT-NEXT:  Arch: unknown
 
 # 32-NEXT:      AddressSize: 32bit
 # 64-NEXT:      AddressSize: 64bit
 
 # 32: Class: 32-bit
 # 64: Class: 64-bit
 # LE: DataEncoding: LittleEndian
 # BE: DataEncoding: BigEndian
 
 # SYSV:    OS/ABI: SystemV (0x0)
 # FREEBSD: OS/ABI: FreeBSD (0x9)
 # DEFAULT: OS/ABI: Standalone (0xFF)
 
-# AARCH:  Machine: EM_AARCH64 (0xB7)
-# ARM:    Machine: EM_ARM (0x28)
-# I386:   Machine: EM_386 (0x3)
-# IAMCU:  Machine: EM_IAMCU (0x6)
-# MIPS:   Machine: EM_MIPS (0x8)
-# PPC:    Machine: EM_PPC (0x14)
-# PPC64:  Machine: EM_PPC64 (0x15)
-# X86-64: Machine: EM_X86_64 (0x3E)
+# AARCH:   Machine: EM_AARCH64 (0xB7)
+# ARM:     Machine: EM_ARM (0x28)
+# I386:    Machine: EM_386 (0x3)
+# IAMCU:   Machine: EM_IAMCU (0x6)
+# MIPS:    Machine: EM_MIPS (0x8)
+# PPC:     Machine: EM_PPC (0x14)
+# PPC64:   Machine: EM_PPC64 (0x15)
+# RISCV32: Machine: EM_RISCV (0xF3)
+# RISCV64: Machine: EM_RISCV (0xF3)
+# X86-64:  Machine: EM_X86_64 (0x3E)
 
 # 32: HeaderSize: 52
 # 64: HeaderSize: 64
 
 # 32: SectionHeaderEntrySize: 40
 # 64: SectionHeaderEntrySize: 64

llvm/trunk/tools/llvm-objcopy/CopyConfig.cpp

 static const StringMap<MachineInfo> ArchMap{
     // Name, {EMachine, 64bit, LittleEndian}
     {"aarch64", {ELF::EM_AARCH64, true, true}},
     {"arm", {ELF::EM_ARM, false, true}},
     {"i386", {ELF::EM_386, false, true}},
     {"i386:x86-64", {ELF::EM_X86_64, true, true}},
     {"mips", {ELF::EM_MIPS, false, false}},
     {"powerpc:common64", {ELF::EM_PPC64, true, true}},
+    {"riscv:rv32", {ELF::EM_RISCV, false, true}},
+    {"riscv:rv64", {ELF::EM_RISCV, true, true}},
     {"sparc", {ELF::EM_SPARC, false, true}},
     {"x86-64", {ELF::EM_X86_64, true, true}},
 };
 
 static Expected<const MachineInfo &> getMachineInfo(StringRef Arch) {
   auto Iter = ArchMap.find(Arch);
   if (Iter == std::end(ArchMap))
     return createStringError(errc::invalid_argument,
                              "Invalid architecture: '%s'", Arch.str().c_str());
   return Iter->getValue();
 }
 
 // FIXME: consolidate with the bfd parsing used by lld.
 static const StringMap<MachineInfo> OutputFormatMap{
     // Name, {EMachine, 64bit, LittleEndian}
+    // x86
     {"elf32-i386", {ELF::EM_386, false, true}},
+    {"elf32-x86-64", {ELF::EM_X86_64, false, true}},
+    {"elf64-x86-64", {ELF::EM_X86_64, true, true}},
+    // Intel MCU
     {"elf32-iamcu", {ELF::EM_IAMCU, false, true}},
+    // ARM
     {"elf32-littlearm", {ELF::EM_ARM, false, true}},
-    {"elf32-x86-64", {ELF::EM_X86_64, false, true}},
+    // ARM AArch64
     {"elf64-aarch64", {ELF::EM_AARCH64, true, true}},
     {"elf64-littleaarch64", {ELF::EM_AARCH64, true, true}},
+    // RISC-V
+    {"elf32-littleriscv", {ELF::EM_RISCV, false, true}},
+    {"elf64-littleriscv", {ELF::EM_RISCV, true, true}},
+    // PowerPC
     {"elf32-powerpc", {ELF::EM_PPC, false, false}},
     {"elf32-powerpcle", {ELF::EM_PPC, false, true}},
     {"elf64-powerpc", {ELF::EM_PPC64, true, false}},
     {"elf64-powerpcle", {ELF::EM_PPC64, true, true}},
-    {"elf64-x86-64", {ELF::EM_X86_64, true, true}},
-    {"elf32-tradbigmips", {ELF::EM_MIPS, false, false}},
+    // MIPS
     {"elf32-bigmips", {ELF::EM_MIPS, false, false}},
     {"elf32-ntradbigmips", {ELF::EM_MIPS, false, false}},
-    {"elf32-tradlittlemips", {ELF::EM_MIPS, false, true}},
     {"elf32-ntradlittlemips", {ELF::EM_MIPS, false, true}},
+    {"elf32-tradbigmips", {ELF::EM_MIPS, false, false}},
+    {"elf32-tradlittlemips", {ELF::EM_MIPS, false, true}},
     {"elf64-tradbigmips", {ELF::EM_MIPS, true, false}},
     {"elf64-tradlittlemips", {ELF::EM_MIPS, true, true}},
 };
 
 static Expected<MachineInfo> getOutputFormatMachineInfo(StringRef Format) {
   StringRef OriginalFormat = Format;
   bool IsFreeBSD = Format.consume_back("-freebsd");
   auto Iter = OutputFormatMap.find(Format);