[llvm-objcopy] Add --strip-unneeded option

Differential Revision: https://reviews.llvm.org/D46896

llvm-svn: 333267

llvm/test/tools/llvm-objcopy/strip-unneeded.test

@@ -0,0 +1,136 @@
+# RUN: yaml2obj %s > %t
+# RUN: llvm-objcopy --strip-unneeded %t %t2
+# RUN: llvm-readobj -symbols %t2 | FileCheck %s
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_REL
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address:         0x1000
+    AddressAlign:    0x0000000000000010
+    Size:            64
+  - Name:            .group
+    Type:            SHT_GROUP
+    Link:            .symtab
+    AddressAlign:    0x0000000000000004
+    Info:            barfoo
+    Members:
+      - SectionOrType:   GRP_COMDAT
+      - SectionOrType:   .text
+  - Name:            .rel.text
+    Type:            SHT_REL
+    Link:            .symtab
+    Info:            .text
+    Relocations:
+      - Offset: 0x1000
+        Symbol: foo
+        Type:   R_X86_64_PC32
+Symbols:
+  Local:
+    - Name:     foo
+      Type:     STT_FUNC
+      Section:  .text
+      Value:    0x1000
+      Size:     8
+    - Name:     bar
+      Type:     STT_FUNC
+      Size:     8
+      Section:  .text
+      Value:    0x1008
+    - Name:     barfoo
+      Type:     STT_FUNC
+      Size:     8
+      Section:  .text
+      Value:    0x1010
+    - Name:     fileSymbol
+      Type:     STT_FILE
+    - Name:     sectionSymbol
+      Type:     STT_SECTION
+  Weak:
+    - Name:     baz
+      Type:     STT_FUNC
+      Size:     8
+      Section:  .text
+      Value:    0x1018
+    - Name:     foobaz
+      Type:     STT_FUNC
+  Global:
+    - Name:     foobar
+      Type:     STT_FUNC
+    - Name:     barbaz
+      Type:     STT_FUNC
+      Size:     8
+      Section:  .text
+      Value:    0x1020
+
+#CHECK: Symbols [
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name:
+#CHECK-NEXT:    Value: 0x0
+#CHECK-NEXT:    Size: 0
+#CHECK-NEXT:    Binding: Local
+#CHECK-NEXT:    Type: None
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: Undefined
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: foo
+#CHECK-NEXT:    Value: 0x1000
+#CHECK-NEXT:    Size: 8
+#CHECK-NEXT:    Binding: Local
+#CHECK-NEXT:    Type: Function
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: .text
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: barfoo
+#CHECK-NEXT:    Value: 0x1010
+#CHECK-NEXT:    Size: 8
+#CHECK-NEXT:    Binding: Local
+#CHECK-NEXT:    Type: Function
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: .text
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: fileSymbol
+#CHECK-NEXT:    Value: 0x0
+#CHECK-NEXT:    Size: 0
+#CHECK-NEXT:    Binding: Local
+#CHECK-NEXT:    Type: File
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: Undefined
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: sectionSymbol
+#CHECK-NEXT:    Value: 0x0
+#CHECK-NEXT:    Size: 0
+#CHECK-NEXT:    Binding: Local
+#CHECK-NEXT:    Type: Section
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: Undefined
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: barbaz
+#CHECK-NEXT:    Value: 0x1020
+#CHECK-NEXT:    Size: 8
+#CHECK-NEXT:    Binding: Global
+#CHECK-NEXT:    Type: Function
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: .text
+#CHECK-NEXT:  }
+#CHECK-NEXT:  Symbol {
+#CHECK-NEXT:    Name: baz
+#CHECK-NEXT:    Value: 0x1018
+#CHECK-NEXT:    Size: 8
+#CHECK-NEXT:    Binding: Weak
+#CHECK-NEXT:    Type: Function
+#CHECK-NEXT:    Other: 0
+#CHECK-NEXT:    Section: .text
+#CHECK-NEXT:  }
+#CHECK-NEXT:]

llvm/tools/llvm-objcopy/ObjcopyOpts.td

@@ -90,3 +90,5 @@ def K : JoinedOrSeparate<["-"], "K">,
         Alias<keep_symbol>;
 def only_keep_debug : Flag<["-", "--"], "only-keep-debug">,
                           HelpText<"Currently ignored. Only for compaitability with GNU objcopy.">;
+def strip_unneeded : Flag<["-", "--"], "strip-unneeded">,
+                      HelpText<"Remove all symbols not needed by relocations">;

llvm/tools/llvm-objcopy/Object.cpp

@@ -50,6 +50,7 @@ void SectionBase::removeSectionReferences(const SectionBase *Sec) {}
 void SectionBase::removeSymbols(function_ref<bool(const Symbol &)> ToRemove) {}
 void SectionBase::initialize(SectionTableRef SecTable) {}
 void SectionBase::finalize() {}
+void SectionBase::markSymbols() {}
 
 template <class ELFT> void ELFWriter<ELFT>::writeShdr(const SectionBase &Sec) {
   uint8_t *Buf = BufPtr->getBufferStart();
@@ -255,6 +256,11 @@ const Symbol *SymbolTableSection::getSymbolByIndex(uint32_t Index) const {
   return Symbols[Index].get();
 }
 
+Symbol *SymbolTableSection::getSymbolByIndex(uint32_t Index) {
+  return const_cast<Symbol *>(
+      static_cast<const SymbolTableSection *>(this)->getSymbolByIndex(Index));
+}
+
 template <class ELFT>
 void ELFSectionWriter<ELFT>::visit(const SymbolTableSection &Sec) {
   uint8_t *Buf = Out.getBufferStart();
@@ -352,6 +358,11 @@ void RelocationSection::removeSymbols(
             "' because it is named in a relocation");
 }
 
+void RelocationSection::markSymbols() {
+  for (const Relocation &Reloc : Relocations)
+    Reloc.RelocSymbol->Referenced = true;
+}
+
 void SectionWriter::visit(const DynamicRelocationSection &Sec) {
   std::copy(std::begin(Sec.Contents), std::end(Sec.Contents),
             Out.getBufferStart() + Sec.Offset);
@@ -384,6 +395,11 @@ void GroupSection::removeSymbols(function_ref<bool(const Symbol &)> ToRemove) {
   }
 }
 
+void GroupSection::markSymbols() {
+  if (Sym)
+    Sym->Referenced = true;
+}
+
 void Section::initialize(SectionTableRef SecTable) {
   if (Link != ELF::SHN_UNDEF)
     LinkSection =

llvm/tools/llvm-objcopy/Object.h

@@ -212,6 +212,7 @@ class SectionBase {
   virtual void removeSectionReferences(const SectionBase *Sec);
   virtual void removeSymbols(function_ref<bool(const Symbol &)> ToRemove);
   virtual void accept(SectionVisitor &Visitor) const = 0;
+  virtual void markSymbols();
 };
 
 class Segment {
@@ -344,6 +345,7 @@ struct Symbol {
   uint8_t Type;
   uint64_t Value;
   uint8_t Visibility;
+  bool Referenced = false;
 
   uint16_t getShndx() const;
 };
@@ -368,6 +370,7 @@ class SymbolTableSection : public SectionBase {
   bool empty() const { return Symbols.empty(); }
   const SectionBase *getStrTab() const { return SymbolNames; }
   const Symbol *getSymbolByIndex(uint32_t Index) const;
+  Symbol *getSymbolByIndex(uint32_t Index);
   void updateSymbols(function_ref<void(Symbol &)> Callable);
 
   void removeSectionReferences(const SectionBase *Sec) override;
@@ -382,7 +385,7 @@ class SymbolTableSection : public SectionBase {
 };
 
 struct Relocation {
-  const Symbol *RelocSymbol = nullptr;
+  Symbol *RelocSymbol = nullptr;
   uint64_t Offset;
   uint64_t Addend;
   uint32_t Type;
@@ -436,6 +439,7 @@ class RelocationSection
   void addRelocation(Relocation Rel) { Relocations.push_back(Rel); }
   void accept(SectionVisitor &Visitor) const override;
   void removeSymbols(function_ref<bool(const Symbol &)> ToRemove) override;
+  void markSymbols() override;
 
   static bool classof(const SectionBase *S) {
     if (S->Flags & ELF::SHF_ALLOC)
@@ -450,7 +454,7 @@ class RelocationSection
 class GroupSection : public SectionBase {
   MAKE_SEC_WRITER_FRIEND
   const SymbolTableSection *SymTab = nullptr;
-  const Symbol *Sym = nullptr;
+  Symbol *Sym = nullptr;
   ELF::Elf32_Word FlagWord;
   SmallVector<SectionBase *, 3> GroupMembers;
 
@@ -462,14 +466,15 @@ class GroupSection : public SectionBase {
   explicit GroupSection(ArrayRef<uint8_t> Data) : Contents(Data) {}
 
   void setSymTab(const SymbolTableSection *SymTabSec) { SymTab = SymTabSec; }
-  void setSymbol(const Symbol *S) { Sym = S; }
+  void setSymbol(Symbol *S) { Sym = S; }
   void setFlagWord(ELF::Elf32_Word W) { FlagWord = W; }
   void addMember(SectionBase *Sec) { GroupMembers.push_back(Sec); }
 
   void initialize(SectionTableRef SecTable) override{};
   void accept(SectionVisitor &) const override;
   void finalize() override;
   void removeSymbols(function_ref<bool(const Symbol &)> ToRemove) override;
+  void markSymbols() override;
 
   static bool classof(const SectionBase *S) {
     return S->Type == ELF::SHT_GROUP;

llvm/tools/llvm-objcopy/llvm-objcopy.cpp

@@ -168,6 +168,7 @@ struct CopyConfig {
   bool StripSections = false;
   bool StripNonAlloc = false;
   bool StripDWO = false;
+  bool StripUnneeded = false;
   bool ExtractDWO = false;
   bool LocalizeHidden = false;
   bool Weaken = false;
@@ -263,6 +264,14 @@ void HandleArgs(const CopyConfig &Config, Object &Obj, const Reader &Reader,
         Sym.Name = I->getValue();
     });
 
+    // The purpose of this loop is to mark symbols referenced by sections
+    // (like GroupSection or RelocationSection). This way, we know which
+    // symbols are still 'needed' and wich are not.
+    if (Config.StripUnneeded) {
+      for (auto &Section : Obj.sections())
+        Section.markSymbols();
+    }
+
     Obj.removeSymbols([&](const Symbol &Sym) {
       if (!Config.SymbolsToKeep.empty() &&
           is_contained(Config.SymbolsToKeep, Sym.Name))
@@ -281,6 +290,13 @@ void HandleArgs(const CopyConfig &Config, Object &Obj, const Reader &Reader,
         return true;
       }
 
+      // TODO: We might handle the 'null symbol' in a different way
+      // by probably handling it the same way as we handle 'null section' ?
+      if (Config.StripUnneeded && !Sym.Referenced && Sym.Index != 0 &&
+          (Sym.Binding == STB_LOCAL || Sym.getShndx() == SHN_UNDEF) &&
+          Sym.Type != STT_FILE && Sym.Type != STT_SECTION)
+        return true;
+
       return false;
     });
   }
@@ -509,6 +525,7 @@ CopyConfig ParseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
   Config.StripDWO = InputArgs.hasArg(OBJCOPY_strip_dwo);
   Config.StripSections = InputArgs.hasArg(OBJCOPY_strip_sections);
   Config.StripNonAlloc = InputArgs.hasArg(OBJCOPY_strip_non_alloc);
+  Config.StripUnneeded = InputArgs.hasArg(OBJCOPY_strip_unneeded);
   Config.ExtractDWO = InputArgs.hasArg(OBJCOPY_extract_dwo);
   Config.LocalizeHidden = InputArgs.hasArg(OBJCOPY_localize_hidden);
   Config.Weaken = InputArgs.hasArg(OBJCOPY_weaken);