[dsymutil] Add support for mergeable libraries

This adds support in dsymutil for mergeable libraries [1]. dsymutil reads a new stab emitted by ld, allowing it to operate on dynamic libraries instead of object files. It also now loads the DWARF files associated to the libraries, and build the debug map for each binary from the list of symbols exported by the library. For each Debug Map Object, there is a new associated Relocation Map which is serialized from the information retrieved in the original debug_info (or debug_addr) section of the .o file. The final DWARF file has multiple compile units, so the offsets information of the relocations are adjusted relatively to the compile unit they will end up belonging to, inside the final linked DWARF file. [1] https://developer.apple.com/documentation/xcode/configuring-your-project-to-use-mergeable-libraries Differential revision: https://reviews.llvm.org/D158124
llvm · Oct 24, 2023 · 122c89b · 122c89b
1 parent 4c28e66
commit 122c89b
Show file tree

Hide file tree

Showing 34 changed files with 1,217 additions and 198 deletions.
diff --git a/llvm/docs/CommandGuide/dsymutil.rst b/llvm/docs/CommandGuide/dsymutil.rst
@@ -32,11 +32,26 @@ OPTIONS
  architectures will be linked by default and any architectures that can't be
  properly linked will cause :program:`dsymutil` to return an error.
 
+.. option:: --build-variant-suffix <suffix=buildvariant>
+
+ Specify the build variant suffix used to build the executabe file.
+ There can be multiple variants for the binary of a product, each built
+ slightly differently. The most common build variants are 'debug' and
+ 'profile'. Setting the DYLD_IMAGE_SUFFIX environment variable will
+ cause dyld to load the specified variant at runtime.
+
 .. option:: --dump-debug-map
 
  Dump the *executable*'s debug-map (the list of the object files containing the
  debug information) in YAML format and exit. No DWARF link will take place.
 
+ .. option:: -D <path>
+
+ Specify a directory that contain dSYM files to search for.
+ This is used for mergeable libraries, so dsymutil knows where to look
+ for dSYM files with  debug information about symbols present in those
+ libraries.
+
 .. option:: --fat64
 
  Use a 64-bit header when emitting universal binaries.

diff --git a/llvm/include/llvm/BinaryFormat/Dwarf.def b/llvm/include/llvm/BinaryFormat/Dwarf.def
@@ -629,6 +629,7 @@ HANDLE_DW_AT(0x3fec, APPLE_objc_complete_type, 0, APPLE)
 HANDLE_DW_AT(0x3fed, APPLE_property, 0, APPLE)
 HANDLE_DW_AT(0x3fee, APPLE_objc_direct, 0, APPLE)
 HANDLE_DW_AT(0x3fef, APPLE_sdk, 0, APPLE)
+HANDLE_DW_AT(0x3ff0, APPLE_origin, 0, APPLE)
 
 // Attribute form encodings.
 HANDLE_DW_FORM(0x01, addr, 2, DWARF)

diff --git a/llvm/include/llvm/BinaryFormat/MachO.h b/llvm/include/llvm/BinaryFormat/MachO.h
@@ -373,6 +373,7 @@ enum StabType {
   N_SSYM = 0x60u,
   N_SO = 0x64u,
   N_OSO = 0x66u,
+  N_LIB = 0x68u,
   N_LSYM = 0x80u,
   N_BINCL = 0x82u,
   N_SOL = 0x84u,

diff --git a/llvm/include/llvm/DWARFLinker/DWARFLinker.h b/llvm/include/llvm/DWARFLinker/DWARFLinker.h
@@ -62,13 +62,33 @@ class AddressesMap {
   virtual std::optional<int64_t>
   getSubprogramRelocAdjustment(const DWARFDie &DIE) = 0;
 
+  /// Returns the file name associated to the AddessesMap
+  virtual std::optional<StringRef> getLibraryInstallName() = 0;
+
   /// Apply the valid relocations to the buffer \p Data, taking into
   /// account that Data is at \p BaseOffset in the .debug_info section.
   ///
   /// \returns true whether any reloc has been applied.
   virtual bool applyValidRelocs(MutableArrayRef<char> Data, uint64_t BaseOffset,
                                 bool IsLittleEndian) = 0;
 
+  /// Check if the linker needs to gather and save relocation info.
+  virtual bool needToSaveValidRelocs() = 0;
+
+  /// Update and save original relocations located in between StartOffset and
+  /// EndOffset. LinkedOffset is the value which should be added to the original
+  /// relocation offset to get new relocation offset in linked binary.
+  virtual void updateAndSaveValidRelocs(bool IsDWARF5,
+                                        uint64_t OriginalUnitOffset,
+                                        int64_t LinkedOffset,
+                                        uint64_t StartOffset,
+                                        uint64_t EndOffset) = 0;
+
+  /// Update the valid relocations that used OriginalUnitOffset as the compile
+  /// unit offset, and update their values to reflect OutputUnitOffset.
+  virtual void updateRelocationsWithUnitOffset(uint64_t OriginalUnitOffset,
+                                               uint64_t OutputUnitOffset) = 0;
+
   /// Erases all data.
   virtual void clear() = 0;
 };
@@ -752,6 +772,9 @@ class DWARFLinker {
       /// Is there a DW_AT_str_offsets_base in the CU?
       bool AttrStrOffsetBaseSeen = false;
 
+      /// Is there a DW_AT_APPLE_origin in the CU?
+      bool HasAppleOrigin = false;
+
       AttributesInfo() = default;
     };
 

diff --git a/llvm/include/llvm/DWARFLinkerParallel/AddressesMap.h b/llvm/include/llvm/DWARFLinkerParallel/AddressesMap.h
@@ -55,13 +55,31 @@ class AddressesMap {
   virtual std::optional<int64_t>
   getSubprogramRelocAdjustment(const DWARFDie &DIE) = 0;
 
+  // Returns the library install name associated to the AddessesMap.
+  virtual std::optional<StringRef> getLibraryInstallName() = 0;
+
   /// Apply the valid relocations to the buffer \p Data, taking into
   /// account that Data is at \p BaseOffset in the .debug_info section.
   ///
   /// \returns true whether any reloc has been applied.
   virtual bool applyValidRelocs(MutableArrayRef<char> Data, uint64_t BaseOffset,
                                 bool IsLittleEndian) = 0;
 
+  /// Check if the linker needs to gather and save relocation info.
+  virtual bool needToSaveValidRelocs() = 0;
+
+  /// Update and save relocation values to be serialized
+  virtual void updateAndSaveValidRelocs(bool IsDWARF5,
+                                        uint64_t OriginalUnitOffset,
+                                        int64_t LinkedOffset,
+                                        uint64_t StartOffset,
+                                        uint64_t EndOffset) = 0;
+
+  /// Update the valid relocations that used OriginalUnitOffset as the compile
+  /// unit offset, and update their values to reflect OutputUnitOffset.
+  virtual void updateRelocationsWithUnitOffset(uint64_t OriginalUnitOffset,
+                                               uint64_t OutputUnitOffset) = 0;
+
   /// Erases all data.
   virtual void clear() = 0;
 

diff --git a/llvm/include/llvm/TargetParser/Triple.h b/llvm/include/llvm/TargetParser/Triple.h
@@ -418,9 +418,6 @@ class Triple {
   /// Get the architecture (first) component of the triple.
   StringRef getArchName() const;
 
-  /// Get the architecture name based on Kind and SubArch.
-  StringRef getArchName(ArchType Kind, SubArchType SubArch = NoSubArch) const;
-
   /// Get the vendor (second) component of the triple.
   StringRef getVendorName() const;
 
@@ -1118,6 +1115,9 @@ class Triple {
   /// Get the canonical name for the \p Kind architecture.
   static StringRef getArchTypeName(ArchType Kind);
 
+  /// Get the architecture name based on \p Kind and \p SubArch.
+  static StringRef getArchName(ArchType Kind, SubArchType SubArch = NoSubArch);
+
   /// Get the "prefix" canonical name for the \p Kind architecture. This is the
   /// prefix used by the architecture specific builtins, and is suitable for
   /// passing to \see Intrinsic::getIntrinsicForClangBuiltin().

diff --git a/llvm/lib/DWARFLinker/DWARFLinker.cpp b/llvm/lib/DWARFLinker/DWARFLinker.cpp
@@ -1026,6 +1026,15 @@ unsigned DWARFLinker::DIECloner::cloneStringAttribute(DIE &Die,
     StringEntry = DebugLineStrPool.getEntry(*String);
   } else {
     StringEntry = DebugStrPool.getEntry(*String);
+
+    if (AttrSpec.Attr == dwarf::DW_AT_APPLE_origin) {
+      Info.HasAppleOrigin = true;
+      if (std::optional<StringRef> FileName =
+              ObjFile.Addresses->getLibraryInstallName()) {
+        StringEntry = DebugStrPool.getEntry(*FileName);
+      }
+    }
+
     // Update attributes info.
     if (AttrSpec.Attr == dwarf::DW_AT_name)
       Info.Name = StringEntry;
@@ -1637,6 +1646,12 @@ shouldSkipAttribute(bool Update,
   }
 }
 
+struct AttributeLinkedOffsetFixup {
+  int64_t LinkedOffsetFixupVal;
+  uint64_t InputAttrStartOffset;
+  uint64_t InputAttrEndOffset;
+};
+
 DIE *DWARFLinker::DIECloner::cloneDIE(const DWARFDie &InputDIE,
                                       const DWARFFile &File, CompileUnit &Unit,
                                       int64_t PCOffset, uint32_t OutOffset,
@@ -1720,24 +1735,51 @@ DIE *DWARFLinker::DIECloner::cloneDIE(const DWARFDie &InputDIE,
       Flags |= TF_SkipPC;
   }
 
+  std::optional<StringRef> LibraryInstallName =
+      ObjFile.Addresses->getLibraryInstallName();
+  SmallVector<AttributeLinkedOffsetFixup> AttributesFixups;
   for (const auto &AttrSpec : Abbrev->attributes()) {
     if (shouldSkipAttribute(Update, AttrSpec, Flags & TF_SkipPC)) {
       DWARFFormValue::skipValue(AttrSpec.Form, Data, &Offset,
                                 U.getFormParams());
       continue;
     }
 
+    AttributeLinkedOffsetFixup CurAttrFixup;
+    CurAttrFixup.InputAttrStartOffset = InputDIE.getOffset() + Offset;
+    CurAttrFixup.LinkedOffsetFixupVal =
+        Unit.getStartOffset() + OutOffset - CurAttrFixup.InputAttrStartOffset;
+
     DWARFFormValue Val = AttrSpec.getFormValue();
     uint64_t AttrSize = Offset;
     Val.extractValue(Data, &Offset, U.getFormParams(), &U);
+    CurAttrFixup.InputAttrEndOffset = InputDIE.getOffset() + Offset;
     AttrSize = Offset - AttrSize;
 
-    OutOffset += cloneAttribute(*Die, InputDIE, File, Unit, Val, AttrSpec,
-                                AttrSize, AttrInfo, IsLittleEndian);
+    uint64_t FinalAttrSize =
+        cloneAttribute(*Die, InputDIE, File, Unit, Val, AttrSpec, AttrSize,
+                       AttrInfo, IsLittleEndian);
+    if (FinalAttrSize != 0 && ObjFile.Addresses->needToSaveValidRelocs())
+      AttributesFixups.push_back(CurAttrFixup);
+
+    OutOffset += FinalAttrSize;
   }
 
-  // Look for accelerator entries.
   uint16_t Tag = InputDIE.getTag();
+  // Add the DW_AT_APPLE_origin attribute to Compile Unit die if we have
+  // an install name and the DWARF doesn't have the attribute yet.
+  const bool NeedsAppleOrigin = (Tag == dwarf::DW_TAG_compile_unit) &&
+                                LibraryInstallName.has_value() &&
+                                !AttrInfo.HasAppleOrigin;
+  if (NeedsAppleOrigin) {
+    auto StringEntry = DebugStrPool.getEntry(LibraryInstallName.value());
+    Die->addValue(DIEAlloc, dwarf::Attribute(dwarf::DW_AT_APPLE_origin),
+                  dwarf::DW_FORM_strp, DIEInteger(StringEntry.getOffset()));
+    AttrInfo.Name = StringEntry;
+    OutOffset += 4;
+  }
+
+  // Look for accelerator entries.
   // FIXME: This is slightly wrong. An inline_subroutine without a
   // low_pc, but with AT_ranges might be interesting to get into the
   // accelerator tables too. For now stick with dsymutil's behavior.
@@ -1806,8 +1848,19 @@ DIE *DWARFLinker::DIECloner::cloneDIE(const DWARFDie &InputDIE,
   Linker.assignAbbrev(NewAbbrev);
   Die->setAbbrevNumber(NewAbbrev.getNumber());
 
+  uint64_t AbbrevNumberSize = getULEB128Size(Die->getAbbrevNumber());
+
   // Add the size of the abbreviation number to the output offset.
-  OutOffset += getULEB128Size(Die->getAbbrevNumber());
+  OutOffset += AbbrevNumberSize;
+
+  // Update fixups with the size of the abbreviation number
+  for (AttributeLinkedOffsetFixup &F : AttributesFixups)
+    F.LinkedOffsetFixupVal += AbbrevNumberSize;
+
+  for (AttributeLinkedOffsetFixup &F : AttributesFixups)
+    ObjFile.Addresses->updateAndSaveValidRelocs(
+        Unit.getOrigUnit().getVersion() >= 5, Unit.getOrigUnit().getOffset(),
+        F.LinkedOffsetFixupVal, F.InputAttrStartOffset, F.InputAttrEndOffset);
 
   if (!HasChildren) {
     // Update our size.

diff --git a/llvm/lib/TargetParser/Triple.cpp b/llvm/lib/TargetParser/Triple.cpp
@@ -90,6 +90,36 @@ StringRef Triple::getArchTypeName(ArchType Kind) {
   llvm_unreachable("Invalid ArchType!");
 }
 
+StringRef Triple::getArchName(ArchType Kind, SubArchType SubArch) {
+  switch (Kind) {
+  case Triple::mips:
+    if (SubArch == MipsSubArch_r6)
+      return "mipsisa32r6";
+    break;
+  case Triple::mipsel:
+    if (SubArch == MipsSubArch_r6)
+      return "mipsisa32r6el";
+    break;
+  case Triple::mips64:
+    if (SubArch == MipsSubArch_r6)
+      return "mipsisa64r6";
+    break;
+  case Triple::mips64el:
+    if (SubArch == MipsSubArch_r6)
+      return "mipsisa64r6el";
+    break;
+  case Triple::aarch64:
+    if (SubArch == AArch64SubArch_arm64ec)
+      return "arm64ec";
+    if (SubArch == AArch64SubArch_arm64e)
+      return "arm64e";
+    break;
+  default:
+    break;
+  }
+  return getArchTypeName(Kind);
+}
+
 StringRef Triple::getArchTypePrefix(ArchType Kind) {
   switch (Kind) {
   default:
@@ -1143,34 +1173,6 @@ StringRef Triple::getArchName() const {
   return StringRef(Data).split('-').first;           // Isolate first component
 }
 
-StringRef Triple::getArchName(ArchType Kind, SubArchType SubArch) const {
-  switch (Kind) {
-  case Triple::mips:
-    if (SubArch == MipsSubArch_r6)
-      return "mipsisa32r6";
-    break;
-  case Triple::mipsel:
-    if (SubArch == MipsSubArch_r6)
-      return "mipsisa32r6el";
-    break;
-  case Triple::mips64:
-    if (SubArch == MipsSubArch_r6)
-      return "mipsisa64r6";
-    break;
-  case Triple::mips64el:
-    if (SubArch == MipsSubArch_r6)
-      return "mipsisa64r6el";
-    break;
-  case Triple::aarch64:
-    if (SubArch == AArch64SubArch_arm64ec)
-      return "arm64ec";
-    break;
-  default:
-    break;
-  }
-  return getArchTypeName(Kind);
-}
-
 StringRef Triple::getVendorName() const {
   StringRef Tmp = StringRef(Data).split('-').second; // Strip first component
   return Tmp.split('-').first;                       // Isolate second component

diff --git a/llvm/test/tools/dsymutil/Inputs/bar-relink-variant.dylib.dSYM/Contents/Info.plist b/llvm/test/tools/dsymutil/Inputs/bar-relink-variant.dylib.dSYM/Contents/Info.plist
@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+	<dict>
+		<key>CFBundleDevelopmentRegion</key>
+		<string>English</string>
+		<key>CFBundleIdentifier</key>
+		<string>com.apple.xcode.dsym.bar-relink-variant.dylib</string>
+		<key>CFBundleInfoDictionaryVersion</key>
+		<string>6.0</string>
+		<key>CFBundlePackageType</key>
+		<string>dSYM</string>
+		<key>CFBundleSignature</key>
+		<string>????</string>
+		<key>CFBundleShortVersionString</key>
+		<string>1.0</string>
+		<key>CFBundleVersion</key>
+		<string>1</string>
+	</dict>
+</plist>
diff --git a/...nk-variant.dylib.dSYM/Contents/Resources/Relocations/aarch64/bar-relink-variant.dylib.yml b/...nk-variant.dylib.dSYM/Contents/Resources/Relocations/aarch64/bar-relink-variant.dylib.yml
@@ -0,0 +1,8 @@
+---
+triple:          'arm64-apple-darwin'
+binary-path:     bar-relink-variant.dylib
+relocations:
+  - { offset: 0x26, size: 0x8, addend: 0x0, symName: _bar, symObjAddr: 0x0, symBinAddr: 0x3FA0, symSize: 0x8 }
+  - { offset: 0x3F, size: 0x8, addend: 0x0, symName: _baz, symObjAddr: 0x8, symBinAddr: 0x4000, symSize: 0x0 }
+  - { offset: 0x4F, size: 0x8, addend: 0x0, symName: _bar, symObjAddr: 0x0, symBinAddr: 0x3FA0, symSize: 0x8 }
+...
diff --git a/llvm/test/tools/dsymutil/Inputs/bar-relink.dylib.dSYM/Contents/Info.plist b/llvm/test/tools/dsymutil/Inputs/bar-relink.dylib.dSYM/Contents/Info.plist
@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+	<dict>
+		<key>CFBundleDevelopmentRegion</key>
+		<string>English</string>
+		<key>CFBundleIdentifier</key>
+		<string>com.apple.xcode.dsym.bar-relink.dylib</string>
+		<key>CFBundleInfoDictionaryVersion</key>
+		<string>6.0</string>
+		<key>CFBundlePackageType</key>
+		<string>dSYM</string>
+		<key>CFBundleSignature</key>
+		<string>????</string>
+		<key>CFBundleShortVersionString</key>
+		<string>1.0</string>
+		<key>CFBundleVersion</key>
+		<string>1</string>
+	</dict>
+</plist>
diff --git a/.../Inputs/bar-relink.dylib.dSYM/Contents/Resources/Relocations/aarch64/bar-relink.dylib.yml b/.../Inputs/bar-relink.dylib.dSYM/Contents/Resources/Relocations/aarch64/bar-relink.dylib.yml
@@ -0,0 +1,8 @@
+---
+triple:          'arm64-apple-darwin'
+binary-path:     bar-relink.dylib
+relocations:
+  - { offset: 0x26, size: 0x8, addend: 0x0, symName: _bar, symObjAddr: 0x0, symBinAddr: 0x3FA0, symSize: 0x8 }
+  - { offset: 0x3F, size: 0x8, addend: 0x0, symName: _baz, symObjAddr: 0x8, symBinAddr: 0x4000, symSize: 0x0 }
+  - { offset: 0x4F, size: 0x8, addend: 0x0, symName: _bar, symObjAddr: 0x0, symBinAddr: 0x3FA0, symSize: 0x8 }
+...
diff --git a/llvm/test/tools/dsymutil/Inputs/foo-relink-variant.dylib.dSYM/Contents/Info.plist b/llvm/test/tools/dsymutil/Inputs/foo-relink-variant.dylib.dSYM/Contents/Info.plist
@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+	<dict>
+		<key>CFBundleDevelopmentRegion</key>
+		<string>English</string>
+		<key>CFBundleIdentifier</key>
+		<string>com.apple.xcode.dsym.foo-relink-variant.dylib</string>
+		<key>CFBundleInfoDictionaryVersion</key>
+		<string>6.0</string>
+		<key>CFBundlePackageType</key>
+		<string>dSYM</string>
+		<key>CFBundleSignature</key>
+		<string>????</string>
+		<key>CFBundleShortVersionString</key>
+		<string>1.0</string>
+		<key>CFBundleVersion</key>
+		<string>1</string>
+	</dict>
+</plist>