[ELF] Implement --force-group-allocation

lld/ELF/Config.h

@@ -286,6 +286,7 @@ struct Config {
   bool relax;
   bool relaxGP;
   bool relocatable;
+  bool resolveGroups;
   bool relrGlibc = false;
   bool relrPackDynRelocs = false;
   llvm::DenseSet<llvm::StringRef> saveTempsArgs;

lld/ELF/Driver.cpp

@@ -1384,6 +1384,8 @@ static void readConfigs(opt::InputArgList &args) {
   config->relaxGP = args.hasFlag(OPT_relax_gp, OPT_no_relax_gp, false);
   config->rpath = getRpath(args);
   config->relocatable = args.hasArg(OPT_relocatable);
+  config->resolveGroups =
+      !args.hasArg(OPT_relocatable) || args.hasArg(OPT_force_group_allocation);
 
   if (args.hasArg(OPT_save_temps)) {
     // --save-temps implies saving all temps.

lld/ELF/InputFiles.cpp

@@ -676,7 +676,7 @@ template <class ELFT> void ObjFile<ELFT>::parse(bool ignoreComdats) {
         symtab.comdatGroups.try_emplace(CachedHashStringRef(signature), this)
             .second;
     if (keepGroup) {
-      if (config->relocatable)
+      if (!config->resolveGroups)
         this->sections[i] = createInputSection(
             i, sec, check(obj.getSectionName(sec, shstrtab)));
       continue;

lld/ELF/InputSection.cpp

@@ -76,12 +76,12 @@ InputSectionBase::InputSectionBase(InputFile *file, uint64_t flags,
     invokeELFT(parseCompressedHeader,);
 }
 
-// Drop SHF_GROUP bit unless we are producing a re-linkable object file.
-// SHF_GROUP is a marker that a section belongs to some comdat group.
-// That flag doesn't make sense in an executable.
+// SHF_INFO_LINK and SHF_GROUP are normally resolved and not copied to the
+// output section. However, for relocatable linking without
+// --force-group-allocation, the SHF_GROUP flag and section groups are retained.
 static uint64_t getFlags(uint64_t flags) {
   flags &= ~(uint64_t)SHF_INFO_LINK;
-  if (!config->relocatable)
+  if (config->resolveGroups)
     flags &= ~(uint64_t)SHF_GROUP;
   return flags;
 }

lld/ELF/Options.td

@@ -254,6 +254,9 @@ def fix_cortex_a53_843419: F<"fix-cortex-a53-843419">,
 def fix_cortex_a8: F<"fix-cortex-a8">,
   HelpText<"Apply fixes for ARM Cortex-A8 erratum 657417">;
 
+def force_group_allocation: FF<"force-group-allocation">,
+  HelpText<"Only meaningful for -r. Section groups are discarded. If two section group members are placed to the same output section, combine their relocations as well">;
+
 defm format: Eq<"format", "Change the input format of the inputs following this option">,
   MetaVarName<"[default,elf,binary]">;
 

lld/docs/ReleaseNotes.rst

@@ -44,6 +44,10 @@ ELF Improvements
   (typical for embedded). It also makes full LTO feasible in such cases, since
   IR merging currently prevents the linker script from referring to input
   files. (`#90007 <https://github.com/llvm/llvm-project/pull/90007>`_)
+* ``--force-group-allocation`` is implemented to discard ``SHT_GROUP`` sections
+  and combine relocation sections if their relocated section group members are
+  placed to the same output section.
+  (`#94704 <https://github.com/llvm/llvm-project/pull/94704>`_)
 
 Breaking changes
 ----------------

lld/docs/ld.lld.1

@@ -278,6 +278,8 @@ Set the
 field to the specified value.
 .It Fl -fini Ns = Ns Ar symbol
 Specify a finalizer function.
+.It Fl -force-group-allocation
+Only meaningful for -r. Section groups are discarded. If two section group members are placed to the same output section, combine their relocations as well.
 .It Fl -format Ns = Ns Ar input-format , Fl b Ar input-format
 Specify the format of the inputs following this option.
 .Ar input-format

lld/test/ELF/comdat.s

@@ -4,6 +4,7 @@
 // RUN: ld.lld -shared %t.o %t2.o -o %t
 // RUN: llvm-objdump -d %t | FileCheck %s
 // RUN: llvm-readelf -S -s %t | FileCheck --check-prefix=READ %s
+// RUN: ld.lld -shared --force-group-allocation %t.o %t2.o -o - | cmp - %t
 
 // Check that we don't crash with --gc-section and that we print a list of
 // reclaimed sections on stderr.

lld/test/ELF/relocatable-comdat.s

@@ -47,6 +47,16 @@
 # COMBINE-NEXT: .rela.text
 # COMBINE-NEXT: .rela.text
 
+## If --force-group-allocation is specified, discard .group and combine .rela.* if their relocated sections are combined.
+# RUN: ld.lld -r -T combine.lds a.o a.o --force-group-allocation -o combine-a.ro
+# RUN: llvm-readelf -g -S combine-a.ro | FileCheck %s --check-prefix=COMBINE-A
+
+# COMBINE-A:      Name            Type     Address          Off    Size   ES Flg Lk    Inf   Al
+# COMBINE-A:      .rodata         PROGBITS 0000000000000000 {{.*}} 000002 00   A  0      0    1
+# COMBINE-A-NEXT: .text           PROGBITS 0000000000000000 {{.*}} 000010 00  AX  0      0    4
+# COMBINE-A-NEXT: .rela.text      RELA     0000000000000000 {{.*}} 000030 18   I [[#]] [[#]]  8
+# COMBINE-A-NEXT: .note.GNU-stack
+
 # RUN: echo 'SECTIONS { /DISCARD/ : {*(.rodata.*)} }' > discard-rodata.lds
 # RUN: ld.lld -r -T discard-rodata.lds a.o a.o -o discard-rodata.ro
 # RUN: llvm-readelf -g -S discard-rodata.ro | FileCheck %s --check-prefix=NO-RODATA