[llvm-objcopy] Add support for -I binary -B <arch>.

Summary:
The -I (--input-target) and -B (--binary-architecture) flags exist but are currently silently ignored. This adds support for -I binary for architectures i386, x86-64 (and alias i386:x86-64), arm, aarch64, sparc, and ppc (powerpc:common64). This is largely based on D41687.

This is done by implementing an additional subclass of Reader, BinaryReader, which works by interpreting the input file as contents for .data field, sets up a synthetic header, and adds additional sections/symbols (e.g. _binary__tmp_data_txt_start).

Reviewers: jakehehrlich, alexshap, jhenderson, javed.absar

Reviewed By: jhenderson

Subscribers: jyknight, nemanjai, kbarton, fedor.sergeev, jrtc27, kristof.beyls, paulsemel, llvm-commits

Differential Revision: https://reviews.llvm.org/D50343

llvm-svn: 340070

4 files changed, 212 insertions, 0 deletions

diff --git a/llvm/test/tools/llvm-objcopy/binary-input-and-output.test b/llvm/test/tools/llvm-objcopy/binary-input-and-output.test
new file mode 100644
index 00000000000..0fc2a4bc3c1
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/binary-input-and-output.test
@@ -0,0 +1,15 @@
+# RUN: echo abcd > %t.txt
+
+# Preserve input to verify it is not modified
+# RUN: cp %t.txt %t-copy.txt
+
+# -I binary -O binary preserves payload through in-memory representation
+# RUN: llvm-objcopy -I binary -B i386:x86-64 -O binary %t.txt %t.2.txt
+# RUN: cmp %t.txt %t.2.txt
+# RUN: cmp %t.txt %t-copy.txt
+
+# -I binary -O binary preserves payload through an intermediate object file
+# RUN: llvm-objcopy -I binary -B i386:x86-64 %t.txt %t.o
+# RUN: llvm-objcopy -O binary %t.o %t.3.txt
+# RUN: cmp %t.txt %t.3.txt
+# RUN: cmp %t.txt %t-copy.txt
diff --git a/llvm/test/tools/llvm-objcopy/binary-input-arch.test b/llvm/test/tools/llvm-objcopy/binary-input-arch.test
new file mode 100644
index 00000000000..0273b640bd1
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/binary-input-arch.test
@@ -0,0 +1,75 @@
+# RUN: echo abcd > %t.txt
+
+# RUN: llvm-objcopy -I binary -B aarch64 %t.txt %t.aarch64.o
+# RUN: llvm-readobj -file-headers %t.aarch64.o | FileCheck %s --check-prefixes=CHECK,AARCH64,64
+
+# RUN: llvm-objcopy -I binary -B arm %t.txt %t.arm.o
+# RUN: llvm-readobj -file-headers %t.arm.o | FileCheck %s --check-prefixes=CHECK,ARM,32
+
+# RUN: llvm-objcopy -I binary -B i386 %t.txt %t.i386.o
+# RUN: llvm-readobj -file-headers %t.i386.o | FileCheck %s --check-prefixes=CHECK,I386,32
+
+# RUN: llvm-objcopy -I binary -B i386:x86-64 %t.txt %t.i386:x86-64.o
+# RUN: llvm-readobj -file-headers %t.i386:x86-64.o | FileCheck %s --check-prefixes=CHECK,X86-64,64
+
+# 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,PPC,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,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,X86-64,64
+
+# CHECK: Format:
+# AARCH64-SAME: ELF64-aarch64-little
+# ARM-SAME:     ELF32-arm-little
+# I386-SAME:    ELF32-i386
+# PPC-SAME:     ELF64-ppc64
+# SPARC-SAME:   ELF32-sparc
+# X86-64-SAME:  ELF64-x86-64
+
+# AARCH64-NEXT: Arch: aarch64
+# ARM-NEXT:     Arch: arm
+# I386-NEXT:    Arch: i386
+# PPC-NEXT:     Arch: powerpc64le
+# 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)
+# CHECK-NEXT:       DataEncoding: LittleEndian (0x1)
+# 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)
+# PPC-NEXT:       Machine: EM_PPC64 (0x15)
+# 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:     ]
+# 32-NEXT:        HeaderSize: 52
+# 64-NEXT:        HeaderSize: 64
+# 32-NEXT:        ProgramHeaderEntrySize: 32
+# 64-NEXT:        ProgramHeaderEntrySize: 56
+# CHECK-NEXT:     ProgramHeaderCount: 0
+# 32-NEXT:        SectionHeaderEntrySize: 40
+# 64-NEXT:        SectionHeaderEntrySize: 64
+# CHECK-NEXT:     SectionHeaderCount: 4
+# CHECK-NEXT:     StringTableSectionIndex:
+# CHECK-NEXT:   }
diff --git a/llvm/test/tools/llvm-objcopy/binary-input-error.test b/llvm/test/tools/llvm-objcopy/binary-input-error.test
new file mode 100644
index 00000000000..820e569ad7b
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/binary-input-error.test
@@ -0,0 +1,10 @@
+# RUN: echo abcd > %t.txt
+
+# RUN: not llvm-objcopy -I binary %t.txt %t.o 2>&1 \
+# RUN:   | FileCheck %s --check-prefix=MISSING-BINARY-ARCH
+
+# RUN: not llvm-objcopy -I binary -B xyz %t.txt %t.o 2>&1 \
+# RUN:   | FileCheck %s --check-prefix=BAD-BINARY-ARCH
+
+# MISSING-BINARY-ARCH: Specified binary input without specifiying an architecture.
+# BAD-BINARY-ARCH: Invalid architecture: 'xyz'.
diff --git a/llvm/test/tools/llvm-objcopy/binary-input.test b/llvm/test/tools/llvm-objcopy/binary-input.test
new file mode 100644
index 00000000000..ff1d381c3fa
--- /dev/null
+++ b/llvm/test/tools/llvm-objcopy/binary-input.test
@@ -0,0 +1,112 @@
+# 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:x86-64 %t.x-txt %t.o
+# RUN: llvm-readobj -sections -symbols %t.o | FileCheck %s
+# RUN: cmp %t.x-txt %t-copy.txt
+
+# 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: 0x0
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size:
+# 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: .strtab
+# CHECK-NEXT:     Type: SHT_STRTAB (0x3)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address: 0x0
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size:
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 1
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 2
+# CHECK-NEXT:     Name: .symtab
+# CHECK-NEXT:     Type: SHT_SYMTAB (0x2)
+# CHECK-NEXT:     Flags [ (0x0)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address: 0x0
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size:
+# CHECK-NEXT:     Link: 1
+# CHECK-NEXT:     Info: 1
+# CHECK-NEXT:     AddressAlignment: 1
+# CHECK-NEXT:     EntrySize: 24
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Section {
+# CHECK-NEXT:     Index: 3
+# CHECK-NEXT:     Name: .data
+# CHECK-NEXT:     Type: SHT_PROGBITS (0x1)
+# CHECK-NEXT:     Flags [ (0x3)
+# CHECK-NEXT:       SHF_ALLOC (0x2)
+# CHECK-NEXT:       SHF_WRITE (0x1)
+# CHECK-NEXT:     ]
+# CHECK-NEXT:     Address: 0x0
+# CHECK-NEXT:     Offset:
+# CHECK-NEXT:     Size: 4
+# CHECK-NEXT:     Link: 0
+# CHECK-NEXT:     Info: 0
+# CHECK-NEXT:     AddressAlignment: 1
+# CHECK-NEXT:     EntrySize: 0
+# CHECK-NEXT:   }
+# CHECK-NEXT: ]
+
+# Note: the symbol names are derived from the full path (with non-alnum values
+# replaced with "_"), e.g. "/tmp/a-b.c" should yield
+# _binary__tmp_a_b_c_{start,end,size}.
+# Just check for _binary_{{[_a-zA-Z0-9]*}}_x_txt_{start,end,size} to avoid
+# making assumptions about how this test is run.
+
+# CHECK:      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 (0x0)
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name: _binary_{{[_a-zA-Z0-9]*}}_x_txt_start
+# CHECK-NEXT:     Value: 0x0
+# CHECK-NEXT:     Size: 0
+# CHECK-NEXT:     Binding: Global (0x1)
+# CHECK-NEXT:     Type: None (0x0)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: .data
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name: _binary_{{[_a-zA-Z0-9]*}}_x_txt_end
+# CHECK-NEXT:     Value: 0x4
+# CHECK-NEXT:     Size: 0
+# CHECK-NEXT:     Binding: Global (0x1)
+# CHECK-NEXT:     Type: None (0x0)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: .data
+# CHECK-NEXT:   }
+# CHECK-NEXT:   Symbol {
+# CHECK-NEXT:     Name: _binary_{{[_a-zA-Z0-9]*}}_x_txt_size
+# CHECK-NEXT:     Value: 0x4
+# CHECK-NEXT:     Size: 0
+# CHECK-NEXT:     Binding: Global (0x1)
+# CHECK-NEXT:     Type: None (0x0)
+# CHECK-NEXT:     Other: 0
+# CHECK-NEXT:     Section: Absolute
+# CHECK-NEXT:   }
+# CHECK-NEXT: ]