Add a libLTO API to query a memory buffer and check if it contains Ob…

…jC categories

The linker supports a feature to force load an object from a static
archive if it defines an Objective-C category.
This API supports this feature by looking at every section in the
module to find if a category is defined in the module.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275125 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm-c/lto.h

@@ -44,7 +44,7 @@ typedef bool lto_bool_t;
  * @{
  */
 
-#define LTO_API_VERSION 19
+#define LTO_API_VERSION 20
 
 /**
  * \since prior to LTO_API_VERSION=3
@@ -136,12 +136,20 @@ lto_module_is_object_file_for_target(const char* path,
                                      const char* target_triple_prefix);
 
 /**
- * Checks if a buffer is a loadable object file.
+ * Return true if \p Buffer contains a bitcode file with ObjC code (category
+ * or class) in it.
  *
- * \since prior to LTO_API_VERSION=3
+ * \since LTO_API_VERSION=20
  */
-extern lto_bool_t
-lto_module_is_object_file_in_memory(const void* mem, size_t length);
+bool lto_module_has_objc_category(const void *mem, size_t length);
+
+/**
+* Checks if a buffer is a loadable object file.
+*
+* \since prior to LTO_API_VERSION=3
+*/
+extern lto_bool_t lto_module_is_object_file_in_memory(const void *mem,
+                                                      size_t length);
 
 /**
  * Checks if a buffer is a loadable object compiled for requested target.

include/llvm/Bitcode/ReaderWriter.h

@@ -60,6 +60,11 @@ namespace llvm {
   std::string getBitcodeTargetTriple(MemoryBufferRef Buffer,
                                      LLVMContext &Context);
 
+  /// Return true if \p Buffer contains a bitcode file with ObjC code (category
+  /// or class) in it.
+  bool isBitcodeContainingObjCCategory(MemoryBufferRef Buffer,
+                                       LLVMContext &Context);
+
   /// Read the header of the specified bitcode buffer and extract just the
   /// producer string information. If successful, this returns a string. On
   /// error, this returns "".

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -313,6 +313,10 @@ class BitcodeReader : public GVMaterializer {
   /// Cheap mechanism to just extract the identification block out of bitcode.
   ErrorOr<std::string> parseIdentificationBlock();
 
+  /// Peak at the module content and return true if any ObjC category or class
+  /// is found.
+  ErrorOr<bool> hasObjCCategory();
+
   static uint64_t decodeSignRotatedValue(uint64_t V);
 
   /// Materialize any deferred Metadata block.
@@ -450,6 +454,7 @@ class BitcodeReader : public GVMaterializer {
                               ArrayRef<uint64_t> Record);
   std::error_code parseMetadataAttachment(Function &F);
   ErrorOr<std::string> parseModuleTriple();
+  ErrorOr<bool> hasObjCCategoryInModule();
   std::error_code parseUseLists();
   std::error_code initStream(std::unique_ptr<DataStreamer> Streamer);
   std::error_code initStreamFromBuffer();
@@ -4195,6 +4200,81 @@ std::error_code BitcodeReader::parseGlobalObjectAttachment(
   return std::error_code();
 }
 
+ErrorOr<bool> BitcodeReader::hasObjCCategory() {
+  if (std::error_code EC = initStream(nullptr))
+    return EC;
+
+  // Sniff for the signature.
+  if (!hasValidBitcodeHeader(Stream))
+    return error("Invalid bitcode signature");
+
+  // We expect a number of well-defined blocks, though we don't necessarily
+  // need to understand them all.
+  while (1) {
+    BitstreamEntry Entry = Stream.advance();
+
+    switch (Entry.Kind) {
+    case BitstreamEntry::Error:
+      return error("Malformed block");
+    case BitstreamEntry::EndBlock:
+      return std::error_code();
+
+    case BitstreamEntry::SubBlock:
+      if (Entry.ID == bitc::MODULE_BLOCK_ID)
+        return hasObjCCategoryInModule();
+
+      // Ignore other sub-blocks.
+      if (Stream.SkipBlock())
+        return error("Malformed block");
+      continue;
+
+    case BitstreamEntry::Record:
+      Stream.skipRecord(Entry.ID);
+      continue;
+    }
+  }
+}
+
+ErrorOr<bool> BitcodeReader::hasObjCCategoryInModule() {
+  if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID))
+    return error("Invalid record");
+
+  SmallVector<uint64_t, 64> Record;
+  // Read all the records for this module.
+  while (1) {
+    BitstreamEntry Entry = Stream.advanceSkippingSubblocks();
+
+    switch (Entry.Kind) {
+    case BitstreamEntry::SubBlock: // Handled for us already.
+    case BitstreamEntry::Error:
+      return error("Malformed block");
+    case BitstreamEntry::EndBlock:
+      return false;
+    case BitstreamEntry::Record:
+      // The interesting case.
+      break;
+    }
+
+    // Read a record.
+    switch (Stream.readRecord(Entry.ID, Record)) {
+    default:
+      break; // Default behavior, ignore unknown content.
+    case bitc::MODULE_CODE_SECTIONNAME: { // SECTIONNAME: [strchr x N]
+      std::string S;
+      if (convertToString(Record, 0, S))
+        return error("Invalid record");
+      // Check for the i386 and other (x86_64, ARM) conventions
+      if (S.find("__DATA, __objc_catlist") != std::string::npos ||
+          S.find("__OBJC,__category") != std::string::npos)
+        return true;
+      break;
+    }
+    }
+    Record.clear();
+  }
+  llvm_unreachable("Exit infinite loop");
+}
+
 /// Parse metadata attachments.
 std::error_code BitcodeReader::parseMetadataAttachment(Function &F) {
   if (Stream.EnterSubBlock(bitc::METADATA_ATTACHMENT_ID))
@@ -6548,6 +6628,16 @@ std::string llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer,
   return Triple.get();
 }
 
+bool llvm::isBitcodeContainingObjCCategory(MemoryBufferRef Buffer,
+                                           LLVMContext &Context) {
+  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
+  auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context);
+  ErrorOr<bool> hasObjCCategory = R->hasObjCCategory();
+  if (hasObjCCategory.getError())
+    return false;
+  return hasObjCCategory.get();
+}
+
 std::string llvm::getBitcodeProducerString(MemoryBufferRef Buffer,
                                            LLVMContext &Context) {
   std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);

test/LTO/X86/objc-detection-i386.ll

@@ -0,0 +1,59 @@
+; RUN: llvm-as < %s -o %t
+; RUN: llvm-lto -check-for-objc %t | FileCheck %s
+
+; CHECK: contains ObjC
+
+
+target datalayout = "e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128"
+target triple = "i386-apple-macosx10.12.0"
+
+module asm "\09.lazy_reference .objc_class_name_A"
+module asm "\09.objc_category_name_A_foo=0"
+module asm "\09.globl .objc_category_name_A_foo"
+
+%0 = type opaque
+%struct._objc_method = type { i8*, i8*, i8* }
+%struct._objc_category = type { i8*, i8*, %struct._objc_method_list*, %struct._objc_method_list*, %struct._objc_protocol_list*, i32, %struct._prop_list_t*, %struct._prop_list_t* }
+%struct._objc_method_list = type opaque
+%struct._objc_protocol_list = type { %struct._objc_protocol_list*, i32, [0 x %struct._objc_protocol] }
+%struct._objc_protocol = type { %struct._objc_protocol_extension*, i8*, %struct._objc_protocol_list*, %struct._objc_method_description_list*, %struct._objc_method_description_list* }
+%struct._objc_protocol_extension = type { i32, %struct._objc_method_description_list*, %struct._objc_method_description_list*, %struct._prop_list_t*, i8**, %struct._prop_list_t* }
+%struct._objc_method_description_list = type { i32, [0 x %struct._objc_method_description] }
+%struct._objc_method_description = type { i8*, i8* }
+%struct._prop_list_t = type { i32, i32, [0 x %struct._prop_t] }
+%struct._prop_t = type { i8*, i8* }
+%struct._objc_module = type { i32, i32, i8*, %struct._objc_symtab* }
+%struct._objc_symtab = type { i32, i8*, i16, i16, [0 x i8*] }
+
+@OBJC_METH_VAR_NAME_ = private global [12 x i8] c"foo_myStuff\00", section "__TEXT,__cstring,cstring_literals", align 1
+@OBJC_METH_VAR_TYPE_ = private global [7 x i8] c"v8@0:4\00", section "__TEXT,__cstring,cstring_literals", align 1
+@OBJC_CLASS_NAME_ = private global [4 x i8] c"foo\00", section "__TEXT,__cstring,cstring_literals", align 1
+@OBJC_CLASS_NAME_.1 = private global [2 x i8] c"A\00", section "__TEXT,__cstring,cstring_literals", align 1
+@OBJC_CATEGORY_INSTANCE_METHODS_A_foo = private global { i8*, i32, [1 x %struct._objc_method] } { i8* null, i32 1, [1 x %struct._objc_method] [%struct._objc_method { i8* getelementptr inbounds ([12 x i8], [12 x i8]* @OBJC_METH_VAR_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([7 x i8], [7 x i8]* @OBJC_METH_VAR_TYPE_, i32 0, i32 0), i8* bitcast (void (%0*, i8*)* @"\01-[A(foo) foo_myStuff]" to i8*) }] }, section "__OBJC,__cat_inst_meth,regular,no_dead_strip", align 4
+@OBJC_CATEGORY_A_foo = private global %struct._objc_category { i8* getelementptr inbounds ([4 x i8], [4 x i8]* @OBJC_CLASS_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([2 x i8], [2 x i8]* @OBJC_CLASS_NAME_.1, i32 0, i32 0), %struct._objc_method_list* bitcast ({ i8*, i32, [1 x %struct._objc_method] }* @OBJC_CATEGORY_INSTANCE_METHODS_A_foo to %struct._objc_method_list*), %struct._objc_method_list* null, %struct._objc_protocol_list* null, i32 32, %struct._prop_list_t* null, %struct._prop_list_t* null }, section "__OBJC,__category,regular,no_dead_strip", align 4
+@OBJC_CLASS_NAME_.2 = private global [1 x i8] zeroinitializer, section "__TEXT,__cstring,cstring_literals", align 1
+@OBJC_SYMBOLS = private global { i32, i8*, i16, i16, [1 x i8*] } { i32 0, i8* null, i16 0, i16 1, [1 x i8*] [i8* bitcast (%struct._objc_category* @OBJC_CATEGORY_A_foo to i8*)] }, section "__OBJC,__symbols,regular,no_dead_strip", align 4
+@OBJC_MODULES = private global %struct._objc_module { i32 7, i32 16, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @OBJC_CLASS_NAME_.2, i32 0, i32 0), %struct._objc_symtab* bitcast ({ i32, i8*, i16, i16, [1 x i8*] }* @OBJC_SYMBOLS to %struct._objc_symtab*) }, section "__OBJC,__module_info,regular,no_dead_strip", align 4
+@llvm.compiler.used = appending global [9 x i8*] [i8* getelementptr inbounds ([12 x i8], [12 x i8]* @OBJC_METH_VAR_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([7 x i8], [7 x i8]* @OBJC_METH_VAR_TYPE_, i32 0, i32 0), i8* getelementptr inbounds ([4 x i8], [4 x i8]* @OBJC_CLASS_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([2 x i8], [2 x i8]* @OBJC_CLASS_NAME_.1, i32 0, i32 0), i8* bitcast ({ i8*, i32, [1 x %struct._objc_method] }* @OBJC_CATEGORY_INSTANCE_METHODS_A_foo to i8*), i8* bitcast (%struct._objc_category* @OBJC_CATEGORY_A_foo to i8*), i8* getelementptr inbounds ([1 x i8], [1 x i8]* @OBJC_CLASS_NAME_.2, i32 0, i32 0), i8* bitcast ({ i32, i8*, i16, i16, [1 x i8*] }* @OBJC_SYMBOLS to i8*), i8* bitcast (%struct._objc_module* @OBJC_MODULES to i8*)], section "llvm.metadata"
+
+; Function Attrs: nounwind ssp
+define internal void @"\01-[A(foo) foo_myStuff]"(%0*, i8*) #0 {
+  %3 = alloca %0*, align 4
+  %4 = alloca i8*, align 4
+  store %0* %0, %0** %3, align 4
+  store i8* %1, i8** %4, align 4
+  ret void
+}
+
+attributes #0 = { nounwind ssp "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+sse4.1,+ssse3" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0, !1, !2, !3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = !{i32 1, !"Objective-C Version", i32 1}
+!1 = !{i32 1, !"Objective-C Image Info Version", i32 0}
+!2 = !{i32 1, !"Objective-C Image Info Section", !"__OBJC, __image_info,regular"}
+!3 = !{i32 4, !"Objective-C Garbage Collection", i32 0}
+!4 = !{i32 1, !"Objective-C Class Properties", i32 64}
+!5 = !{i32 1, !"PIC Level", i32 2}
+!6 = !{!"Apple LLVM version 8.0.0 (clang-800.0.24.1)"}

test/LTO/X86/objc-detection.ll

@@ -0,0 +1,52 @@
+; RUN: llvm-as < %s -o %t
+; RUN: llvm-lto -check-for-objc %t | FileCheck %s
+
+; CHECK: contains ObjC
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.12.0"
+
+%0 = type opaque
+%struct._class_t = type { %struct._class_t*, %struct._class_t*, %struct._objc_cache*, i8* (i8*, i8*)**, %struct._class_ro_t* }
+%struct._objc_cache = type opaque
+%struct._class_ro_t = type { i32, i32, i32, i8*, i8*, %struct.__method_list_t*, %struct._objc_protocol_list*, %struct._ivar_list_t*, i8*, %struct._prop_list_t* }
+%struct.__method_list_t = type { i32, i32, [0 x %struct._objc_method] }
+%struct._objc_method = type { i8*, i8*, i8* }
+%struct._objc_protocol_list = type { i64, [0 x %struct._protocol_t*] }
+%struct._protocol_t = type { i8*, i8*, %struct._objc_protocol_list*, %struct.__method_list_t*, %struct.__method_list_t*, %struct.__method_list_t*, %struct.__method_list_t*, %struct._prop_list_t*, i32, i32, i8**, i8*, %struct._prop_list_t* }
+%struct._ivar_list_t = type { i32, i32, [0 x %struct._ivar_t] }
+%struct._ivar_t = type { i64*, i8*, i8*, i32, i32 }
+%struct._prop_list_t = type { i32, i32, [0 x %struct._prop_t] }
+%struct._prop_t = type { i8*, i8* }
+%struct._category_t = type { i8*, %struct._class_t*, %struct.__method_list_t*, %struct.__method_list_t*, %struct._objc_protocol_list*, %struct._prop_list_t*, %struct._prop_list_t*, i32 }
+
+@OBJC_CLASS_NAME_ = private global [4 x i8] c"foo\00", section "__TEXT,__objc_classname,cstring_literals", align 1
+@"OBJC_CLASS_$_A" = external global %struct._class_t
+@OBJC_METH_VAR_NAME_ = private global [12 x i8] c"foo_myStuff\00", section "__TEXT,__objc_methname,cstring_literals", align 1
+@OBJC_METH_VAR_TYPE_ = private global [8 x i8] c"v16@0:8\00", section "__TEXT,__objc_methtype,cstring_literals", align 1
+@"\01l_OBJC_$_CATEGORY_INSTANCE_METHODS_A_$_foo" = private global { i32, i32, [1 x %struct._objc_method] } { i32 24, i32 1, [1 x %struct._objc_method] [%struct._objc_method { i8* getelementptr inbounds ([12 x i8], [12 x i8]* @OBJC_METH_VAR_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([8 x i8], [8 x i8]* @OBJC_METH_VAR_TYPE_, i32 0, i32 0), i8* bitcast (void (%0*, i8*)* @"\01-[A(foo) foo_myStuff]" to i8*) }] }, section "__DATA, __objc_const", align 8
+@"\01l_OBJC_$_CATEGORY_A_$_foo" = private global %struct._category_t { i8* getelementptr inbounds ([4 x i8], [4 x i8]* @OBJC_CLASS_NAME_, i32 0, i32 0), %struct._class_t* @"OBJC_CLASS_$_A", %struct.__method_list_t* bitcast ({ i32, i32, [1 x %struct._objc_method] }* @"\01l_OBJC_$_CATEGORY_INSTANCE_METHODS_A_$_foo" to %struct.__method_list_t*), %struct.__method_list_t* null, %struct._objc_protocol_list* null, %struct._prop_list_t* null, %struct._prop_list_t* null, i32 64 }, section "__DATA, __objc_const", align 8
+@"OBJC_LABEL_CATEGORY_$" = private global [1 x i8*] [i8* bitcast (%struct._category_t* @"\01l_OBJC_$_CATEGORY_A_$_foo" to i8*)], section "__DATA, __objc_catlist, regular, no_dead_strip", align 8
+@llvm.compiler.used = appending global [6 x i8*] [i8* getelementptr inbounds ([4 x i8], [4 x i8]* @OBJC_CLASS_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @OBJC_METH_VAR_NAME_, i32 0, i32 0), i8* getelementptr inbounds ([8 x i8], [8 x i8]* @OBJC_METH_VAR_TYPE_, i32 0, i32 0), i8* bitcast ({ i32, i32, [1 x %struct._objc_method] }* @"\01l_OBJC_$_CATEGORY_INSTANCE_METHODS_A_$_foo" to i8*), i8* bitcast (%struct._category_t* @"\01l_OBJC_$_CATEGORY_A_$_foo" to i8*), i8* bitcast ([1 x i8*]* @"OBJC_LABEL_CATEGORY_$" to i8*)], section "llvm.metadata"
+
+; Function Attrs: ssp uwtable
+define internal void @"\01-[A(foo) foo_myStuff]"(%0*, i8*) #0 {
+  %3 = alloca %0*, align 8
+  %4 = alloca i8*, align 8
+  store %0* %0, %0** %3, align 8
+  store i8* %1, i8** %4, align 8
+  ret void
+}
+
+attributes #0 = { ssp uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+sse4.1,+ssse3" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0, !1, !2, !3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = !{i32 1, !"Objective-C Version", i32 2}
+!1 = !{i32 1, !"Objective-C Image Info Version", i32 0}
+!2 = !{i32 1, !"Objective-C Image Info Section", !"__DATA, __objc_imageinfo, regular, no_dead_strip"}
+!3 = !{i32 4, !"Objective-C Garbage Collection", i32 0}
+!4 = !{i32 1, !"Objective-C Class Properties", i32 64}
+!5 = !{i32 1, !"PIC Level", i32 2}
+!6 = !{!"Apple LLVM version 8.0.0 (clang-800.0.24.1)"}

tools/llvm-lto/llvm-lto.cpp

@@ -156,6 +156,10 @@ static cl::opt<bool> RestoreGlobalsLinkage(
     "restore-linkage", cl::init(false),
     cl::desc("Restore original linkage of globals prior to CodeGen"));
 
+static cl::opt<bool> CheckHasObjC(
+    "check-for-objc", cl::init(false),
+    cl::desc("Only check if the module has objective-C defined in it"));
+
 namespace {
 struct ModuleInfo {
   std::vector<bool> CanBeHidden;
@@ -714,6 +718,21 @@ int main(int argc, char **argv) {
     return 0;
   }
 
+  if (CheckHasObjC) {
+    for (auto &Filename : InputFilenames) {
+      ErrorOr<std::unique_ptr<MemoryBuffer>> BufferOrErr =
+          MemoryBuffer::getFile(Filename);
+      error(BufferOrErr, "error loading file '" + Filename + "'");
+      auto Buffer = std::move(BufferOrErr.get());
+      LLVMContext Ctx;
+      if (llvm::isBitcodeContainingObjCCategory(*Buffer, Ctx))
+        outs() << "Bitcode " << Filename << " contains ObjC\n";
+      else
+        outs() << "Bitcode " << Filename << " does not contain ObjC\n";
+    }
+    return 0;
+  }
+
   if (ThinLTOMode.getNumOccurrences()) {
     if (ThinLTOMode.getNumOccurrences() > 1)
       report_fatal_error("You can't specify more than one -thinlto-action");

tools/lto/lto.cpp

@@ -14,6 +14,7 @@
 
 #include "llvm-c/lto.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Bitcode/ReaderWriter.h"
 #include "llvm/CodeGen/CommandFlags.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/DiagnosticPrinter.h"
@@ -180,6 +181,14 @@ bool lto_module_is_object_file_for_target(const char* path,
   return LTOModule::isBitcodeForTarget(Buffer->get(), target_triplet_prefix);
 }
 
+bool lto_module_has_objc_category(const void *mem, size_t length) {
+  std::unique_ptr<MemoryBuffer> Buffer(LTOModule::makeBuffer(mem, length));
+  if (!Buffer)
+    return false;
+  LLVMContext Ctx;
+  return llvm::isBitcodeContainingObjCCategory(*Buffer, Ctx);
+}
+
 bool lto_module_is_object_file_in_memory(const void* mem, size_t length) {
   return LTOModule::isBitcodeFile(mem, length);
 }

tools/lto/lto.exports

@@ -18,6 +18,7 @@ lto_module_is_object_file
 lto_module_is_object_file_for_target
 lto_module_is_object_file_in_memory
 lto_module_is_object_file_in_memory_for_target
+lto_module_has_objc_category
 lto_module_dispose
 lto_api_version
 lto_codegen_set_diagnostic_handler