[llvm-lipo] Implement -thin

Creates thin output file of specified arch_type from the fat input file.

Patch by Anusha Basana <anushabasana@fb.com>

Differential Revision: https://reviews.llvm.org/D63341

llvm-svn: 364107

test/tools/llvm-lipo/Inputs/i386-slice.yaml

@@ -0,0 +1,88 @@
+--- !mach-o
+FileHeader:      
+  magic:           0xFEEDFACE
+  cputype:         0x00000007
+  cpusubtype:      0x00000003
+  filetype:        0x00000001
+  ncmds:           4
+  sizeofcmds:      312
+  flags:           0x00002000
+LoadCommands:    
+  - cmd:             LC_SEGMENT
+    cmdsize:         192
+    segname:         ''
+    vmaddr:          0
+    vmsize:          72
+    fileoff:         340
+    filesize:        72
+    maxprot:         7
+    initprot:        7
+    nsects:          2
+    flags:           0
+    Sections:        
+      - sectname:        __text
+        segname:         __TEXT
+        addr:            0x0000000000000000
+        size:            18
+        offset:          0x00000154
+        align:           4
+        reloff:          0x00000000
+        nreloc:          0
+        flags:           0x80000400
+        reserved1:       0x00000000
+        reserved2:       0x00000000
+        reserved3:       0x00000000
+      - sectname:        __eh_frame
+        segname:         __TEXT
+        addr:            0x0000000000000014
+        size:            52
+        offset:          0x00000168
+        align:           2
+        reloff:          0x00000000
+        nreloc:          0
+        flags:           0x6800000B
+        reserved1:       0x00000000
+        reserved2:       0x00000000
+        reserved3:       0x00000000
+  - cmd:             LC_VERSION_MIN_MACOSX
+    cmdsize:         16
+    version:         656384
+    sdk:             0
+  - cmd:             LC_SYMTAB
+    cmdsize:         24
+    symoff:          412
+    nsyms:           1
+    stroff:          424
+    strsize:         8
+  - cmd:             LC_DYSYMTAB
+    cmdsize:         80
+    ilocalsym:       0
+    nlocalsym:       0
+    iextdefsym:      0
+    nextdefsym:      1
+    iundefsym:       1
+    nundefsym:       0
+    tocoff:          0
+    ntoc:            0
+    modtaboff:       0
+    nmodtab:         0
+    extrefsymoff:    0
+    nextrefsyms:     0
+    indirectsymoff:  0
+    nindirectsyms:   0
+    extreloff:       0
+    nextrel:         0
+    locreloff:       0
+    nlocrel:         0
+LinkEditData:    
+  NameList:        
+    - n_strx:          1
+      n_type:          0x0F
+      n_sect:          1
+      n_desc:          0
+      n_value:         0
+  StringTable:     
+    - ''
+    - _main
+    - ''
+...

test/tools/llvm-lipo/Inputs/i386-x86_64-universal.yaml

@@ -0,0 +1,192 @@
+--- !fat-mach-o
+FatHeader:       
+  magic:           0xCAFEBABE
+  nfat_arch:       2
+FatArchs:        
+  - cputype:         0x00000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000001000
+    size:            432
+    align:           12
+  - cputype:         0x01000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000002000
+    size:            488
+    align:           12
+Slices:          
+  - !mach-o
+    FileHeader:      
+      magic:           0xFEEDFACE
+      cputype:         0x00000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           4
+      sizeofcmds:      312
+      flags:           0x00002000
+    LoadCommands:    
+      - cmd:             LC_SEGMENT
+        cmdsize:         192
+        segname:         ''
+        vmaddr:          0
+        vmsize:          72
+        fileoff:         340
+        filesize:        72
+        maxprot:         7
+        initprot:        7
+        nsects:          2
+        flags:           0
+        Sections:        
+          - sectname:        __text
+            segname:         __TEXT
+            addr:            0x0000000000000000
+            size:            18
+            offset:          0x00000154
+            align:           4
+            reloff:          0x00000000
+            nreloc:          0
+            flags:           0x80000400
+            reserved1:       0x00000000
+            reserved2:       0x00000000
+            reserved3:       0x00000000
+          - sectname:        __eh_frame
+            segname:         __TEXT
+            addr:            0x0000000000000014
+            size:            52
+            offset:          0x00000168
+            align:           2
+            reloff:          0x00000000
+            nreloc:          0
+            flags:           0x6800000B
+            reserved1:       0x00000000
+            reserved2:       0x00000000
+            reserved3:       0x00000000
+      - cmd:             LC_VERSION_MIN_MACOSX
+        cmdsize:         16
+        version:         656384
+        sdk:             0
+      - cmd:             LC_SYMTAB
+        cmdsize:         24
+        symoff:          412
+        nsyms:           1
+        stroff:          424
+        strsize:         8
+      - cmd:             LC_DYSYMTAB
+        cmdsize:         80
+        ilocalsym:       0
+        nlocalsym:       0
+        iextdefsym:      0
+        nextdefsym:      1
+        iundefsym:       1
+        nundefsym:       0
+        tocoff:          0
+        ntoc:            0
+        modtaboff:       0
+        nmodtab:         0
+        extrefsymoff:    0
+        nextrefsyms:     0
+        indirectsymoff:  0
+        nindirectsyms:   0
+        extreloff:       0
+        nextrel:         0
+        locreloff:       0
+        nlocrel:         0
+    LinkEditData:    
+      NameList:        
+        - n_strx:          1
+          n_type:          0x0F
+          n_sect:          1
+          n_desc:          0
+          n_value:         0
+      StringTable:     
+        - ''
+        - _main
+        - ''
+  - !mach-o
+    FileHeader:      
+      magic:           0xFEEDFACF
+      cputype:         0x01000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           4
+      sizeofcmds:      352
+      flags:           0x00002000
+      reserved:        0x00000000
+    LoadCommands:    
+      - cmd:             LC_SEGMENT_64
+        cmdsize:         232
+        segname:         ''
+        vmaddr:          0
+        vmsize:          80
+        fileoff:         384
+        filesize:        80
+        maxprot:         7
+        initprot:        7
+        nsects:          2
+        flags:           0
+        Sections:        
+          - sectname:        __text
+            segname:         __TEXT
+            addr:            0x0000000000000000
+            size:            15
+            offset:          0x00000180
+            align:           4
+            reloff:          0x00000000
+            nreloc:          0
+            flags:           0x80000400
+            reserved1:       0x00000000
+            reserved2:       0x00000000
+            reserved3:       0x00000000
+          - sectname:        __eh_frame
+            segname:         __TEXT
+            addr:            0x0000000000000010
+            size:            64
+            offset:          0x00000190
+            align:           3
+            reloff:          0x00000000
+            nreloc:          0
+            flags:           0x6800000B
+            reserved1:       0x00000000
+            reserved2:       0x00000000
+            reserved3:       0x00000000
+      - cmd:             LC_VERSION_MIN_MACOSX
+        cmdsize:         16
+        version:         656384
+        sdk:             0
+      - cmd:             LC_SYMTAB
+        cmdsize:         24
+        symoff:          464
+        nsyms:           1
+        stroff:          480
+        strsize:         8
+      - cmd:             LC_DYSYMTAB
+        cmdsize:         80
+        ilocalsym:       0
+        nlocalsym:       0
+        iextdefsym:      0
+        nextdefsym:      1
+        iundefsym:       1
+        nundefsym:       0
+        tocoff:          0
+        ntoc:            0
+        modtaboff:       0
+        nmodtab:         0
+        extrefsymoff:    0
+        nextrefsyms:     0
+        indirectsymoff:  0
+        nindirectsyms:   0
+        extreloff:       0
+        nextrel:         0
+        locreloff:       0
+        nlocrel:         0
+    LinkEditData:    
+      NameList:        
+        - n_strx:          1
+          n_type:          0x0F
+          n_sect:          1
+          n_desc:          0
+          n_value:         0
+      StringTable:     
+        - ''
+        - _main
+        - ''
+...

test/tools/llvm-lipo/help-error-messages.test

@@ -9,7 +9,10 @@
 # RUN: not llvm-lipo --abcabc 2>&1 | FileCheck --check-prefix=LIPO-UNKNOWN-ARG %s
 
 # RUN: not llvm-lipo %t -archs -verify_arch i386 2>&1 | FileCheck --check-prefix=MULTIPLE_FLAGS %s
-# MULTIPLE_FLAGS: only one of the following actions can be specified: -archs -verify_arch
+# RUN: not llvm-lipo %t -archs -thin i386 2>&1 | FileCheck --check-prefix=MULTIPLE_FLAGS %s
+# RUN: not llvm-lipo %t -thin i386 -verify_arch i386 2>&1 | FileCheck --check-prefix=MULTIPLE_FLAGS %s
+# RUN: not llvm-lipo %t -archs -thin i386 -verify_arch i386 2>&1 | FileCheck --check-prefix=MULTIPLE_FLAGS %s
+# MULTIPLE_FLAGS: only one of the following actions can be specified:
 
 # LIPO-USAGE:    USAGE: llvm-lipo
 # LIPO-UNKNOWN-ARG:    unknown argument '{{-+}}abcabc'

test/tools/llvm-lipo/thin-executable-universal-binary.test

@@ -0,0 +1,50 @@
+# Executable testing is not supported on Windows, since all files are considered executable
+# UNSUPPORTED: windows
+# RUN: yaml2obj %s > %t-universal.o
+
+# RUN: chmod -x %t-universal.o
+# RUN: llvm-lipo %t-universal.o -thin i386 -output %t32.o
+# RUN: test ! -x %t32.o
+
+# RUN: chmod +x %t-universal.o
+# RUN: llvm-lipo %t-universal.o -thin i386 -output %t32-ex.o
+# RUN: test -x %t32-ex.o
+
+
+
+--- !fat-mach-o
+FatHeader:
+  magic:           0xCAFEBABE
+  nfat_arch:       2
+FatArchs:
+  - cputype:         0x00000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000001000
+    size:            28
+    align:           12
+  - cputype:         0x01000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000002000
+    size:            32
+    align:           12
+Slices:
+  - !mach-o
+    FileHeader:
+      magic:           0xFEEDFACE
+      cputype:         0x00000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           0
+      sizeofcmds:      0
+      flags:           0x00002000
+  - !mach-o
+    FileHeader:
+      magic:           0xFEEDFACF
+      cputype:         0x01000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           0
+      sizeofcmds:      0
+      flags:           0x00002000
+      reserved:        0x00000000
+...

test/tools/llvm-lipo/thin-macho-binary.test

@@ -0,0 +1,21 @@
+# RUN: yaml2obj %s > %t
+
+# RUN: not llvm-lipo %t -thin i386 2>&1 | FileCheck --check-prefix=NO_OUTPUT %s
+# NO_OUTPUT: error: thin expects a single output file
+
+# RUN: not llvm-lipo %t %t -thin i386 2>&1 | FileCheck --check-prefix=MULTIPLE_INPUT_OBJ %s
+# MULTIPLE_INPUT_OBJ: thin expects a single input file
+
+# RUN: not llvm-lipo %t -thin i386 -output %t.out 2>&1 | FileCheck --check-prefix=INPUT_FILE_THIN %s
+# INPUT_FILE_THIN: must be a fat file when the -thin option is specified
+
+--- !mach-o
+FileHeader:
+  magic:           0xFEEDFACE
+  cputype:         0x00000097
+  cpusubtype:      0x00000003
+  filetype:        0x00000001
+  ncmds:           0
+  sizeofcmds:      0
+  flags:           0x00002000
+...

test/tools/llvm-lipo/thin-universal-binary.test

@@ -0,0 +1,49 @@
+# RUN: yaml2obj %s > %t
+
+# RUN: not llvm-lipo %t -thin arc -output %t.out 2>&1 | FileCheck --check-prefix=ARCH_NOT_IN_FILE %s
+# ARCH_NOT_IN_FILE: does not contain the specified architecture arc to thin it to
+
+# RUN: not llvm-lipo %t -thin aarch101 -output %t.out 2>&1 | FileCheck --check-prefix=INVALID_ARCH %s
+# INVALID_ARCH: Invalid architecture: aarch101
+
+# RUN: yaml2obj %p/Inputs/i386-x86_64-universal.yaml > %t-universal.o
+# RUN: llvm-lipo %t-universal.o -thin i386 -output %t32.o
+# RUN: yaml2obj %p/Inputs/i386-slice.yaml > %t-basic32.o
+# RUN: cmp %t32.o %t-basic32.o
+
+--- !fat-mach-o
+FatHeader:
+  magic:           0xCAFEBABE
+  nfat_arch:       2
+FatArchs:
+  - cputype:         0x00000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000001000
+    size:            28
+    align:           12
+  - cputype:         0x01000007
+    cpusubtype:      0x00000003
+    offset:          0x0000000000002000
+    size:            32
+    align:           12
+Slices:
+  - !mach-o
+    FileHeader:
+      magic:           0xFEEDFACE
+      cputype:         0x00000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           0
+      sizeofcmds:      0
+      flags:           0x00002000
+  - !mach-o
+    FileHeader:
+      magic:           0xFEEDFACF
+      cputype:         0x01000007
+      cpusubtype:      0x00000003
+      filetype:        0x00000001
+      ncmds:           0
+      sizeofcmds:      0
+      flags:           0x00002000
+      reserved:        0x00000000
+...

tools/llvm-lipo/LipoOpts.td

@@ -17,3 +17,12 @@ def verify_arch
 def archs : Option<["-", "--"], "archs", KIND_FLAG>,
             Group<action_group>,
             HelpText<"Display the arch_types present in the input file">;
+
+def thin : Option<["-", "--"], "thin", KIND_SEPARATE>,
+           Group<action_group>,
+           HelpText<"Create a thin output file of specified arch_type from the "
+                    "fat input file. Requires -output option">;
+
+def output : Option<["-", "--"], "output", KIND_SEPARATE>,
+             HelpText<"Create output file with specified name">;
+def o : JoinedOrSeparate<["-"], "o">, Alias<output>;

tools/llvm-lipo/llvm-lipo.cpp

@@ -19,6 +19,7 @@
 #include "llvm/Option/ArgList.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Error.h"
+#include "llvm/Support/FileOutputBuffer.h"
 #include "llvm/Support/InitLLVM.h"
 #include "llvm/Support/WithColor.h"
 
@@ -78,16 +79,24 @@ public:
 enum class LipoAction {
   PrintArchs,
   VerifyArch,
+  ThinArch,
 };
 
 struct Config {
   SmallVector<std::string, 1> InputFiles;
   SmallVector<std::string, 1> VerifyArchList;
+  std::string ThinArchType;
+  std::string OutputFile;
   LipoAction ActionToPerform;
 };
 
 } // end namespace
 
+static void validateArchitectureName(StringRef ArchitectureName) {
+  if (Triple(ArchitectureName).getArch() == Triple::ArchType::UnknownArch)
+    reportError("Invalid architecture: " + ArchitectureName);
+}
+
 static Config parseLipoOptions(ArrayRef<const char *> ArgsArr) {
   Config C;
   LipoOptTable T;
@@ -95,6 +104,11 @@ static Config parseLipoOptions(ArrayRef<const char *> ArgsArr) {
   llvm::opt::InputArgList InputArgs =
       T.ParseArgs(ArgsArr, MissingArgumentIndex, MissingArgumentCount);
 
+  if (MissingArgumentCount)
+    reportError("missing argument to " +
+                StringRef(InputArgs.getArgString(MissingArgumentIndex)) +
+                " option");
+
   if (InputArgs.size() == 0) {
     // PrintHelp does not accept Twine.
     T.PrintHelp(errs(), "llvm-lipo input[s] option[s]", "llvm-lipo");
@@ -121,6 +135,9 @@ static Config parseLipoOptions(ArrayRef<const char *> ArgsArr) {
   if (C.InputFiles.empty())
     reportError("at least one input file should be specified");
 
+  if (InputArgs.hasArg(LIPO_output))
+    C.OutputFile = InputArgs.getLastArgValue(LIPO_output);
+
   SmallVector<opt::Arg *, 1> ActionArgs(InputArgs.filtered(LIPO_action_group));
   if (ActionArgs.empty())
     reportError("at least one action should be specified");
@@ -151,6 +168,17 @@ static Config parseLipoOptions(ArrayRef<const char *> ArgsArr) {
     C.ActionToPerform = LipoAction::PrintArchs;
     return C;
 
+  case LIPO_thin:
+    if (C.InputFiles.size() > 1)
+      reportError("thin expects a single input file");
+    C.ThinArchType = ActionArgs[0]->getValue();
+    validateArchitectureName(C.ThinArchType);
+    if (C.OutputFile.empty())
+      reportError("thin expects a single output file");
+
+    C.ActionToPerform = LipoAction::ThinArch;
+    return C;
+
   default:
     reportError("llvm-lipo action unspecified");
   }
@@ -164,8 +192,12 @@ readInputBinaries(ArrayRef<std::string> InputFiles) {
         createBinary(InputFile);
     if (!BinaryOrErr)
       reportError(InputFile, BinaryOrErr.takeError());
-    if (!isa<MachOObjectFile>(BinaryOrErr->getBinary()) &&
-        !isa<MachOUniversalBinary>(BinaryOrErr->getBinary()))
+    // TODO: Add compatibility for archive files
+    if (BinaryOrErr->getBinary()->isArchive())
+      reportError("File " + InputFile +
+                  " is an archive file and is not yet supported.");
+    if (!BinaryOrErr->getBinary()->isMachO() &&
+        !BinaryOrErr->getBinary()->isMachOUniversalBinary())
       reportError("File " + InputFile + " has unsupported binary format");
     InputBinaries.push_back(std::move(*BinaryOrErr));
   }
@@ -180,8 +212,7 @@ static void verifyArch(ArrayRef<OwningBinary<Binary>> InputBinaries,
   assert(InputBinaries.size() == 1 && "Incorrect number of input binaries");
 
   for (StringRef Arch : VerifyArchList)
-    if (Triple(Arch).getArch() == Triple::ArchType::UnknownArch)
-      reportError("Invalid architecture: " + Arch);
+    validateArchitectureName(Arch);
 
   if (auto UO =
           dyn_cast<MachOUniversalBinary>(InputBinaries.front().getBinary())) {
@@ -238,6 +269,44 @@ static void printArchs(ArrayRef<OwningBinary<Binary>> InputBinaries) {
   exit(EXIT_SUCCESS);
 }
 
+LLVM_ATTRIBUTE_NORETURN
+static void extractSlice(ArrayRef<OwningBinary<Binary>> InputBinaries,
+                         StringRef ThinArchType, StringRef OutputFileName) {
+  assert(!ThinArchType.empty() && "The architecture type should be non-empty");
+  assert(InputBinaries.size() == 1 && "Incorrect number of input binaries");
+  assert(!OutputFileName.empty() && "Thin expects a single output file");
+
+  if (InputBinaries.front().getBinary()->isMachO()) {
+    reportError("input file " +
+                InputBinaries.front().getBinary()->getFileName() +
+                " must be a fat file when the -thin option is specified");
+    exit(EXIT_FAILURE);
+  }
+
+  auto *UO = cast<MachOUniversalBinary>(InputBinaries.front().getBinary());
+  Expected<std::unique_ptr<MachOObjectFile>> Obj =
+      UO->getObjectForArch(ThinArchType);
+  if (!Obj)
+    reportError("fat input file " + UO->getFileName() +
+                " does not contain the specified architecture " + ThinArchType +
+                " to thin it to");
+
+  Expected<std::unique_ptr<FileOutputBuffer>> OutFileOrError =
+      FileOutputBuffer::create(OutputFileName,
+                               Obj.get()->getMemoryBufferRef().getBufferSize(),
+                               sys::fs::can_execute(UO->getFileName())
+                                   ? FileOutputBuffer::F_executable
+                                   : 0);
+  if (!OutFileOrError)
+    reportError(OutputFileName, OutFileOrError.takeError());
+  std::copy(Obj.get()->getMemoryBufferRef().getBufferStart(),
+            Obj.get()->getMemoryBufferRef().getBufferEnd(),
+            OutFileOrError.get()->getBufferStart());
+  if (Error E = OutFileOrError.get()->commit())
+    reportError(OutputFileName, std::move(E));
+  exit(EXIT_SUCCESS);
+}
+
 int main(int argc, char **argv) {
   InitLLVM X(argc, argv);
   Config C = parseLipoOptions(makeArrayRef(argv + 1, argc));
@@ -251,6 +320,9 @@ int main(int argc, char **argv) {
   case LipoAction::PrintArchs:
     printArchs(InputBinaries);
     break;
+  case LipoAction::ThinArch:
+    extractSlice(InputBinaries, C.ThinArchType, C.OutputFile);
+    break;
   }
   return EXIT_SUCCESS;
 }