[Clang][Bundler] Reduce fat object size

Summary:
Fat object size has significantly increased after D65819 which changed bundler tool to add host object as a normal bundle to the fat output which almost doubled its size. That patch was fixing the following issues

1. Problems associated with the partial linking - global constructors were not called for partially linking objects which clearly resulted in incorrect behavior.
2. Eliminating "junk" target object sections from the linked binary on the host side.

The first problem is no longer relevant because we do not use partial linking for creating fat objects anymore. Target objects sections are now inserted into the resulting fat object with a help of llvm-objcopy tool.

The second issue, "junk" sections in the linked host binary, has been fixed in D73408 by adding "exclude" flag to the fat object's sections which contain target objects. This flag tells linker to drop section from the inputs when linking executable or shared library, therefore these sections will not be propagated in the linked binary.

Since both problems have been solved, we can revert D65819 changes to reduce fat object size and this patch essentially is doing that.

Reviewers: ABataev, alexshap, jdoerfert

Reviewed By: ABataev

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D73642

Author: sndmitriev

clang/test/Driver/clang-offload-bundler.c

@@ -253,16 +253,16 @@
 
 // RUN: clang-offload-bundler -type=o -targets=host-%itanium_abi_triple,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu -inputs=%t.o,%t.tgt1,%t.tgt2 -outputs=%t.bundle3.o -### 2>&1 \
 // RUN: | FileCheck %s -DHOST=%itanium_abi_triple -DINOBJ1=%t.o -DINOBJ2=%t.tgt1 -DINOBJ3=%t.tgt2 -DOUTOBJ=%t.bundle3.o --check-prefix CK-OBJ-CMD
-// CK-OBJ-CMD: llvm-objcopy{{(.exe)?}}" "--add-section=__CLANG_OFFLOAD_BUNDLE__host-[[HOST]]=[[INOBJ1]]" "--add-section=__CLANG_OFFLOAD_BUNDLE__openmp-powerpc64le-ibm-linux-gnu=[[INOBJ2]]" "--add-section=__CLANG_OFFLOAD_BUNDLE__openmp-x86_64-pc-linux-gnu=[[INOBJ3]]" "[[INOBJ1]]" "[[TEMPOBJ:.*]]"
+// CK-OBJ-CMD: llvm-objcopy{{(.exe)?}}" "--add-section=__CLANG_OFFLOAD_BUNDLE__host-[[HOST]]={{.*}}" "--add-section=__CLANG_OFFLOAD_BUNDLE__openmp-powerpc64le-ibm-linux-gnu=[[INOBJ2]]" "--add-section=__CLANG_OFFLOAD_BUNDLE__openmp-x86_64-pc-linux-gnu=[[INOBJ3]]" "[[INOBJ1]]" "[[TEMPOBJ:.*]]"
 // CK-OBJ-CMD: llvm-objcopy{{(.exe)?}}" "--set-section-flags=__CLANG_OFFLOAD_BUNDLE__host-[[HOST]]=readonly,exclude" "--set-section-flags=__CLANG_OFFLOAD_BUNDLE__openmp-powerpc64le-ibm-linux-gnu=readonly,exclude" "--set-section-flags=__CLANG_OFFLOAD_BUNDLE__openmp-x86_64-pc-linux-gnu=readonly,exclude" "[[TEMPOBJ]]" "[[OUTOBJ]]"
 
 // RUN: clang-offload-bundler -type=o -targets=host-%itanium_abi_triple,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu -inputs=%t.o,%t.tgt1,%t.tgt2 -outputs=%t.bundle3.o
 // RUN: clang-offload-bundler -type=o -targets=host-%itanium_abi_triple,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu -outputs=%t.res.o,%t.res.tgt1,%t.res.tgt2 -inputs=%t.bundle3.o -unbundle
-// RUN: diff %t.o %t.res.o
+// RUN: diff %t.bundle3.o %t.res.o
 // RUN: diff %t.tgt1 %t.res.tgt1
 // RUN: diff %t.tgt2 %t.res.tgt2
 // RUN: clang-offload-bundler -type=o -targets=openmp-powerpc64le-ibm-linux-gnu,host-%itanium_abi_triple,openmp-x86_64-pc-linux-gnu -outputs=%t.res.tgt1,%t.res.o,%t.res.tgt2 -inputs=%t.bundle3.o -unbundle
-// RUN: diff %t.o %t.res.o
+// RUN: diff %t.bundle3.o %t.res.o
 // RUN: diff %t.tgt1 %t.res.tgt1
 // RUN: diff %t.tgt2 %t.res.tgt2
 // RUN: clang-offload-bundler -type=o -targets=openmp-powerpc64le-ibm-linux-gnu -outputs=%t.res.tgt1 -inputs=%t.bundle3.o -unbundle

clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp

@@ -30,7 +30,6 @@
 #include "llvm/Support/Error.h"
 #include "llvm/Support/ErrorOr.h"
 #include "llvm/Support/FileSystem.h"
-#include "llvm/Support/FileUtilities.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Program.h"
@@ -365,6 +364,41 @@ class BinaryFileHandler final : public FileHandler {
   }
 };
 
+namespace {
+
+// This class implements a list of temporary files that are removed upon
+// object destruction.
+class TempFileHandlerRAII {
+public:
+  ~TempFileHandlerRAII() {
+    for (const auto &File : Files)
+      sys::fs::remove(File);
+  }
+
+  // Creates temporary file with given contents.
+  Expected<StringRef> Create(Optional<ArrayRef<char>> Contents) {
+    SmallString<128u> File;
+    if (std::error_code EC =
+            sys::fs::createTemporaryFile("clang-offload-bundler", "tmp", File))
+      return createFileError(File, EC);
+    Files.push_back(File);
+
+    if (Contents) {
+      std::error_code EC;
+      raw_fd_ostream OS(File, EC);
+      if (EC)
+        return createFileError(File, EC);
+      OS.write(Contents->data(), Contents->size());
+    }
+    return Files.back();
+  }
+
+private:
+  SmallVector<SmallString<128u>, 4u> Files;
+};
+
+} // end anonymous namespace
+
 /// Handler for object files. The bundles are organized by sections with a
 /// designated name.
 ///
@@ -433,11 +467,16 @@ class ObjectFileHandler final : public FileHandler {
   Error ReadBundleEnd(MemoryBuffer &Input) final { return Error::success(); }
 
   Error ReadBundle(raw_fd_ostream &OS, MemoryBuffer &Input) final {
-    Expected<StringRef> Content = CurrentSection->getContents();
-    if (!Content)
-      return Content.takeError();
+    Expected<StringRef> ContentOrErr = CurrentSection->getContents();
+    if (!ContentOrErr)
+      return ContentOrErr.takeError();
+    StringRef Content = *ContentOrErr;
+
+    // Copy fat object contents to the output when extracting host bundle.
+    if (Content.size() == 1u && Content.front() == 0)
+      Content = StringRef(Input.getBufferStart(), Input.getBufferSize());
 
-    OS.write(Content->data(), Content->size());
+    OS.write(Content.data(), Content.size());
     return Error::success();
   }
 
@@ -486,22 +525,37 @@ class ObjectFileHandler final : public FileHandler {
     // to pass down to llvm-objcopy.
     OS.close();
 
+    // Temporary files that need to be removed.
+    TempFileHandlerRAII TempFiles;
+
     // Create an intermediate temporary file to save object after the first
     // llvm-objcopy run.
-    SmallString<128u> IntermediateObj;
-    if (std::error_code EC = sys::fs::createTemporaryFile(
-            "clang-offload-bundler", "tmp", IntermediateObj))
-      return createFileError(IntermediateObj, EC);
-    FileRemover IntermediateObjRemover(IntermediateObj);
+    Expected<SmallString<128u>> IntermediateObjOrErr = TempFiles.Create(None);
+    if (!IntermediateObjOrErr)
+      return IntermediateObjOrErr.takeError();
+    const SmallString<128u> &IntermediateObj = *IntermediateObjOrErr;
 
     // Compose llvm-objcopy command line for add target objects' sections.
     BumpPtrAllocator Alloc;
     StringSaver SS{Alloc};
     SmallVector<StringRef, 8u> ObjcopyArgs{"llvm-objcopy"};
-    for (unsigned I = 0; I < NumberOfInputs; ++I)
+    for (unsigned I = 0; I < NumberOfInputs; ++I) {
+      StringRef InputFile = InputFileNames[I];
+      if (I == HostInputIndex) {
+        // Special handling for the host bundle. We do not need to add a
+        // standard bundle for the host object since we are going to use fat
+        // object as a host object. Therefore use dummy contents (one zero byte)
+        // when creating section for the host bundle.
+        Expected<StringRef> TempFileOrErr = TempFiles.Create(ArrayRef<char>(0));
+        if (!TempFileOrErr)
+          return TempFileOrErr.takeError();
+        InputFile = *TempFileOrErr;
+      }
+
       ObjcopyArgs.push_back(SS.save(Twine("--add-section=") +
                                     OFFLOAD_BUNDLER_MAGIC_STR + TargetNames[I] +
-                                    "=" + InputFileNames[I]));
+                                    "=" + InputFile));
+    }
     ObjcopyArgs.push_back(InputFileNames[HostInputIndex]);
     ObjcopyArgs.push_back(IntermediateObj);