Make __start_sec __end_sec handling more precise

[• rafael]

Summary

With this we only ask LTO to keep a C named section if there is a start_ or end symbol.

This is not as strict as lld's --gc-sections, but is as good as we can get without having a far more detailed ir summary.

[pcc]

ELF/LTO.cpp

134

Probably better to move this loop to the BitcodeCompiler ctor to avoid quadratic complexity.

136

Should this be __stop_ instead of __end_?

[• rafael]

Address review comments

[pcc]

LGTM

ELF/LTO.h

43

Nit: I'd move this to where the other fields are.

[davide]

LGTM

[• espindola]

309232

ELF/LTO.h

 // functionality.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLD_ELF_LTO_H
 #define LLD_ELF_LTO_H
 
 #include "lld/Core/LLVM.h"
+#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/SmallString.h"
 #include <memory>
 #include <vector>
 
 namespace llvm {
 namespace lto {
 class LTO;
 }
 } // namespace llvm
 
 namespace lld {
 namespace elf {
 
 class BitcodeFile;
 class InputFile;
 
 class BitcodeCompiler {
+  llvm::DenseSet<StringRef> UsedStartStop;
+
 public:
   BitcodeCompiler();
   ~BitcodeCompiler();
 
   void add(BitcodeFile &F);
   std::vector<InputFile *> compile();
 
 private:
   std::unique_ptr<llvm::lto::LTO> LTOObj;
   std::vector<SmallString<0>> Buff;
   std::vector<std::unique_ptr<MemoryBuffer>> Files;
 };
 } // namespace elf
 } // namespace lld
 
 #endif

ELF/LTO.cpp

 //===- LTO.cpp ------------------------------------------------------------===//
 //
 //                             The LLVM Linker
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 
 #include "LTO.h"
 #include "Config.h"
 #include "Error.h"
 #include "InputFiles.h"
+#include "SymbolTable.h"
 #include "Symbols.h"
 #include "lld/Core/TargetOptionsCommandFlags.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/IR/DiagnosticPrinter.h"
static std::unique_ptr<lto::LTO> createLTO() {
 
   lto::ThinBackend Backend;
   if (Config->ThinLTOJobs != -1u)
     Backend = lto::createInProcessThinBackend(Config->ThinLTOJobs);
   return llvm::make_unique<lto::LTO>(std::move(Conf), Backend,
                                      Config->LTOPartitions);
 }
 
-BitcodeCompiler::BitcodeCompiler() : LTOObj(createLTO()) {}
+BitcodeCompiler::BitcodeCompiler() : LTOObj(createLTO()) {
+  for (Symbol *Sym : Symtab->getSymbols()) {
+    StringRef Name = Sym->body()->getName();
+    for (StringRef Prefix : {"__start_", "__stop_"})
+      if (Name.startswith(Prefix))
+        UsedStartStop.insert(Name.substr(Prefix.size()));
+  }
+}
 
 BitcodeCompiler::~BitcodeCompiler() = default;
 
 static void undefine(Symbol *S) {
   replaceBody<Undefined>(S, S->body()->getName(), /*IsLocal=*/false,
                          STV_DEFAULT, S->body()->Type, nullptr);
 }
 
 void BitcodeCompiler::add(BitcodeFile &F) {
   lto::InputFile &Obj = *F.Obj;
   unsigned SymNum = 0;
   std::vector<Symbol *> Syms = F.getSymbols();
   std::vector<lto::SymbolResolution> Resols(Syms.size());
 
   // Provide a resolution to the LTO API for each symbol.
   for (const lto::InputFile::Symbol &ObjSym : Obj.symbols()) {
     Symbol *Sym = Syms[SymNum];
     lto::SymbolResolution &R = Resols[SymNum];
     ++SymNum;
     SymbolBody *B = Sym->body();
 
     // Ideally we shouldn't check for SF_Undefined but currently IRObjectFile
     // reports two symbols for module ASM defined. Without this check, lld
     // flags an undefined in IR with a definition in ASM as prevailing.
     // Once IRObjectFile is fixed to report only one symbol this hack can
     // be removed.
     R.Prevailing = !ObjSym.isUndefined() && B->File == &F;
 
     R.VisibleToRegularObj = Sym->IsUsedInRegularObj ||
                             (R.Prevailing && Sym->includeInDynsym()) ||
-                            isValidCIdentifier(ObjSym.getSectionName());
+                            UsedStartStop.count(ObjSym.getSectionName());
     if (R.Prevailing)
       undefine(Sym);
     R.LinkerRedefined = Config->RenamedSymbols.count(Sym);
   }
   checkError(LTOObj->add(std::move(F.Obj), Resols));
 }
 
 // Merge all the bitcode files we have seen, codegen the result

test/ELF/lto/section-name.ll

 ; REQUIRES: x86
 ; RUN: llvm-as %s -o %t.o
 ; RUN: ld.lld %t.o -o %t.so -shared
 ; RUN: llvm-readelf -s %t.so | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @foo = hidden global i32 42, section "foo_section"
+@bar = hidden global i32 42, section "bar_section"
+@zed = hidden global i32 42, section "zed_section"
 
-; CHECK: foo_section PROGBITS
+@__start_foo_section = external global i32
+@__stop_bar_section = external global i32
+
+define i32* @use1() {
+  ret i32* @__start_foo_section
+}
+
+define i32* @use2() {
+  ret i32* @__stop_bar_section
+}
+
+; CHECK-NOT: zed_section
+; CHECK:     foo_section PROGBITS
+; CHECK-NEXT:     bar_section PROGBITS
+; CHECK-NOT: zed_section