llvm-objdump -m -D should disassemble all text segments

Summary:
When running llvm-objdump with the -macho option objdump will by default
disassemble only the __TEXT,__text section (or __TEXT_EXEC,__text when
disassembling MH_KEXT_BUNDLE files). The -disassemble-all option is
treated no diferently than -disassemble.

This change upates llvm-objdump's MachO parsing code to disassemble all
__text sections found in a file when -disassemble-all is specified. This
is useful for disassembling files with more than one __text section, or
when disassembling files whose __text section is not present in __TEXT.

I added a lit test case that verifies "llvm-objdump -m -d" and 
"llvm-objdump -m -D" produce the expected results on a reference binary. 
I also updated the CommandGuide documentation for llvm-objdump.rst and
verified it renders correctly as man and html.

rdar://42899338

Reviewers: ab, pete, lhames

Reviewed By: lhames

Subscribers: rupprecht, llvm-commits

Differential Revision: https://reviews.llvm.org/D56649

llvm-svn: 351238

llvm/docs/CommandGuide/llvm-objdump.rst

@@ -16,11 +16,18 @@ stream.
 
 COMMANDS
 --------
-At least one of the following commands are required, and some commands can be combined with other commands:
+At least one of the following commands are required, and some commands can be
+combined with other commands:
 
-.. option:: -disassemble
+.. option:: -d, -disassemble
 
-  Display assembler mnemonics for the machine instructions
+  Display assembler mnemonics for the machine instructions. Disassembles all
+  text sections found in the input file(s).
+
+.. option:: -D, -disassemble-all
+
+  Display assembler mnemonics for the machine instructions. Disassembles all
+  sections found in the input file(s).
 
 .. option:: -help
 
@@ -52,7 +59,7 @@ OPTIONS
 
 .. option:: -arch=<architecture>
 
-  Specify the architecture to disassemble. see -version for available
+  Specify the architecture to disassemble. see ``-version`` for available
   architectures.
 
 .. option:: -cfg
@@ -68,9 +75,10 @@ OPTIONS
 
   Print line information from debug info if available.
 
-.. option:: -macho
+.. option:: -m, -macho
 
-  Use Mach-O specific object file parser.
+  Use Mach-O specific object file parser. Commands and other options may behave
+  differently when used with ``-macho``.
 
 .. option:: -mattr=<a1,+a2,-a3,...>
 
@@ -86,7 +94,7 @@ OPTIONS
 
 .. option:: -triple=<string>
 
-  Target triple to disassemble for, see -version for available targets.
+  Target triple to disassemble for, see ``-version`` for available targets.
 
 .. option:: -x86-asm-syntax=<style>
 

llvm/test/tools/llvm-objdump/X86/macho-disassemble-all.test

@@ -0,0 +1,39 @@
+// RUN: llvm-objdump -m -d -full-leading-addr -print-imm-hex -no-show-raw-insn %p/Inputs/macho-multiple-text | FileCheck %s -check-prefix=TEXT
+
+TEXT:      (__TEXT,__text) section
+TEXT_NEXT: _main:
+TEXT_NEXT: 0000000100000f60	pushq	%rbp
+TEXT_NEXT: 0000000100000f61	movq	%rsp, %rbp
+TEXT_NEXT: 0000000100000f64	subq	$0x10, %rsp
+TEXT_NEXT: 0000000100000f68	movl	$0x0, -0x4(%rbp)
+TEXT_NEXT: 0000000100000f6f	callq	_hello
+TEXT_NEXT: 0000000100000f74	xorl	%eax, %eax
+TEXT_NEXT: 0000000100000f76	addq	$0x10, %rsp
+TEXT_NEXT: 0000000100000f7a	popq	%rbp
+TEXT_NEXT: 0000000100000f7b	retq
+
+// RUN: llvm-objdump -m -D -full-leading-addr -print-imm-hex -no-show-raw-insn %p/Inputs/macho-multiple-text | FileCheck %s -check-prefix=ALL
+
+ALL:      (__TEXT,__text) section
+ALL_NEXT: _main:
+ALL_NEXT: 0000000100000f60	pushq	%rbp
+ALL_NEXT: 0000000100000f61	movq	%rsp, %rbp
+ALL_NEXT: 0000000100000f64	subq	$0x10, %rsp
+ALL_NEXT: 0000000100000f68	movl	$0x0, -0x4(%rbp)
+ALL_NEXT: 0000000100000f6f	callq	_hello
+ALL_NEXT: 0000000100000f74	xorl	%eax, %eax
+ALL_NEXT: 0000000100000f76	addq	$0x10, %rsp
+ALL_NEXT: 0000000100000f7a	popq	%rbp
+ALL_NEXT: 0000000100000f7b	retq
+ALL:      (__TEXT_EXEC,__text) section
+ALL_NEXT: _hello:
+ALL_NEXT: 0000000100001000	pushq	%rbp
+ALL_NEXT: 0000000100001001	movq	%rsp, %rbp
+ALL_NEXT: 0000000100001004	subq	$0x10, %rsp
+ALL_NEXT: 0000000100001008	leaq	-0x71(%rip), %rdi ## literal pool for: "hello, world!\n"
+ALL_NEXT: 000000010000100f	movb	$0x0, %al
+ALL_NEXT: 0000000100001011	callq	0x100000f7c ## symbol stub for: _printf
+ALL_NEXT: 0000000100001016	movl	%eax, -0x4(%rbp)
+ALL_NEXT: 0000000100001019	addq	$0x10, %rsp
+ALL_NEXT: 000000010000101d	popq	%rbp
+ALL_NEXT: 000000010000101e	retq

llvm/tools/llvm-objdump/MachODump.cpp

@@ -1611,7 +1611,18 @@ static void ProcessMachO(StringRef Name, MachOObjectFile *MachOOF,
     if (Error Err = MachOOF->checkSymbolTable())
       report_error(ArchiveName, FileName, std::move(Err), ArchitectureName);
   
-  if (Disassemble) {
+  if (DisassembleAll) {
+    for (const SectionRef &Section : MachOOF->sections()) {
+      StringRef SectName;
+      Section.getName(SectName);
+      if (SectName.equals("__text")) {
+        DataRefImpl Ref = Section.getRawDataRefImpl();
+        StringRef SegName = MachOOF->getSectionFinalSegmentName(Ref);
+        DisassembleMachO(FileName, MachOOF, SegName, SectName);
+      }
+    }
+  }
+  else if (Disassemble) {
     if (MachOOF->getHeader().filetype == MachO::MH_KEXT_BUNDLE &&
         MachOOF->getHeader().cputype == MachO::CPU_TYPE_ARM64)
       DisassembleMachO(FileName, MachOOF, "__TEXT_EXEC", "__text");