[ELF] Change --call-graph-profile-sort to accept an argument

[MaskRay]

Summary

Change the FF form --call-graph-profile-sort to --call-graph-profile-sort={none,hfsort}.
This will be extended to support llvm/lib/Transforms/Utils/CodeLayout.cpp.

--call-graph-profile-sort is not used in the wild but
--no-call-graph-profile-sort is (Chromium). Make --no-call-graph-profile-sort an
alias for --call-graph-profile-sort=none.

[MaskRay]

.

lld/ELF/Config.h

 
 // For -Bno-symbolic, -Bsymbolic-non-weak-functions, -Bsymbolic-functions,
 // -Bsymbolic-non-weak, -Bsymbolic.
 enum class BsymbolicKind { None, NonWeakFunctions, Functions, NonWeak, All };
 
 // For --build-id.
 enum class BuildIdKind { None, Fast, Md5, Sha1, Hexstring, Uuid };
 
+// For --call-graph-profile-sort={none,hfsort}.
+enum class CGProfileSortKind { None, Hfsort };
+
 // For --discard-{all,locals,none}.
 enum class DiscardPolicy { Default, All, Locals, None };
 
 // For --icf={none,safe,all}.
 enum class ICFLevel { None, Safe, All };
 
 // For --strip-{all,debug}.
 enum class StripPolicy { None, All, Debug };
struct Config {
   bool androidPackDynRelocs = false;
   bool armHasBlx = false;
   bool armHasMovtMovw = false;
   bool armJ1J2BranchEncoding = false;
   bool armCMSESupport = false;
   bool asNeeded = false;
   bool armBe8 = false;
   BsymbolicKind bsymbolic = BsymbolicKind::None;
-  bool callGraphProfileSort;
+  CGProfileSortKind callGraphProfileSort;
   bool checkSections;
   bool checkDynamicRelocs;
   llvm::DebugCompressionType compressDebugSections;
   bool cref;
   llvm::SmallVector<std::pair<llvm::GlobPattern, uint64_t>, 0>
       deadRelocInNonAlloc;
   bool demangle = true;
   bool dependentLibraries;

lld/ELF/Driver.cpp

static void ltoValidateAllVtablesHaveTypeInfos(opt::InputArgList &args) {
   for (StringRef s : vtableSymbolsWithNoRTTI) {
     message(
         "--lto-validate-all-vtables-have-type-infos: RTTI missing for vtable "
         "_ZTV" +
         s + ", --lto-whole-program-visibility disabled");
   }
 }
 
+static CGProfileSortKind getCGProfileSortKind(opt::InputArgList &args) {
+  StringRef s = args.getLastArgValue(OPT_call_graph_profile_sort, "hfsort");
+  if (s == "hfsort")
+    return CGProfileSortKind::Hfsort;
+  if (s != "none")
+    error("unknown --call-graph-profile-sort= value: " + s);
+  return CGProfileSortKind::None;
+}
+
 static DebugCompressionType getCompressionType(StringRef s, StringRef option) {
   DebugCompressionType type = StringSwitch<DebugCompressionType>(s)
                                   .Case("zlib", DebugCompressionType::Zlib)
                                   .Case("zstd", DebugCompressionType::Zstd)
                                   .Default(DebugCompressionType::None);
   if (type == DebugCompressionType::None) {
     if (s != "none")
       error("unknown " + option + " value: " + s);
if (arg->getOption().matches(OPT_Bsymbolic_non_weak_functions))
       config->bsymbolic = BsymbolicKind::NonWeakFunctions;
     else if (arg->getOption().matches(OPT_Bsymbolic_functions))
       config->bsymbolic = BsymbolicKind::Functions;
     else if (arg->getOption().matches(OPT_Bsymbolic_non_weak))
       config->bsymbolic = BsymbolicKind::NonWeak;
     else if (arg->getOption().matches(OPT_Bsymbolic))
       config->bsymbolic = BsymbolicKind::All;
   }
+  config->callGraphProfileSort = getCGProfileSortKind(args);
   config->checkSections =
       args.hasFlag(OPT_check_sections, OPT_no_check_sections, true);
   config->chroot = args.getLastArgValue(OPT_chroot);
   config->compressDebugSections = getCompressionType(
       args.getLastArgValue(OPT_compress_debug_sections, "none"),
       "--compress-debug-sections");
   config->cref = args.hasArg(OPT_cref);
   config->optimizeBBJumps =
       args.hasFlag(OPT_optimize_bb_jumps, OPT_no_optimize_bb_jumps, false);
   config->demangle = args.hasFlag(OPT_demangle, OPT_no_demangle, true);
   config->dependencyFile = args.getLastArgValue(OPT_dependency_file);
   config->dependentLibraries = args.hasFlag(OPT_dependent_libraries, OPT_no_dependent_libraries, true);
   config->disableVerify = args.hasArg(OPT_disable_verify);
   config->discard = getDiscard(args);
   config->dwoDir = args.getLastArgValue(OPT_plugin_opt_dwo_dir_eq);
   config->dynamicLinker = getDynamicLinker(args);
   config->ehFrameHdr =
       args.hasFlag(OPT_eh_frame_hdr, OPT_no_eh_frame_hdr, false);
   config->emitLLVM = args.hasArg(OPT_plugin_opt_emit_llvm, false);
   config->emitRelocs = args.hasArg(OPT_emit_relocs);
-  config->callGraphProfileSort = args.hasFlag(
-      OPT_call_graph_profile_sort, OPT_no_call_graph_profile_sort, true);
   config->enableNewDtags =
       args.hasFlag(OPT_enable_new_dtags, OPT_disable_new_dtags, true);
   config->entry = args.getLastArgValue(OPT_entry);
 
   errorHandler().errorHandlingScript =
       args.getLastArgValue(OPT_error_handling_script);
 
   config->executeOnly =
static void readConfigs(opt::InputArgList &args) {
   if (auto *arg = args.getLastArg(OPT_symbol_ordering_file)){
     if (args.hasArg(OPT_call_graph_ordering_file))
       error("--symbol-ordering-file and --call-graph-order-file "
             "may not be used together");
     if (std::optional<MemoryBufferRef> buffer = readFile(arg->getValue())) {
       config->symbolOrderingFile = getSymbolOrderingFile(*buffer);
       // Also need to disable CallGraphProfileSort to prevent
       // LLD order symbols with CGProfile
-      config->callGraphProfileSort = false;
+      config->callGraphProfileSort = CGProfileSortKind::None;
     }
   }
 
   assert(config->versionDefinitions.empty());
   config->versionDefinitions.push_back(
       {"local", (uint16_t)VER_NDX_LOCAL, {}, {}});
   config->versionDefinitions.push_back(
       {"global", (uint16_t)VER_NDX_GLOBAL, {}, {}});
void LinkerDriver::link(opt::InputArgList &args) {
   // Two input sections with different output sections should not be folded.
   // ICF runs after processSectionCommands() so that we know the output sections.
   if (config->icf != ICFLevel::None) {
     invokeELFT(findKeepUniqueSections, args);
     invokeELFT(doIcf,);
   }
 
   // Read the callgraph now that we know what was gced or icfed
-  if (config->callGraphProfileSort) {
+  if (config->callGraphProfileSort != CGProfileSortKind::None) {
     if (auto *arg = args.getLastArg(OPT_call_graph_ordering_file))
       if (std::optional<MemoryBufferRef> buffer = readFile(arg->getValue()))
         readCallGraph(*buffer);
     invokeELFT(readCallGraphsFromObjectFiles,);
   }
 
   // Write the result to the file.
   invokeELFT(writeResult,);
 }

lld/ELF/Options.td

 
 defm as_needed: B<"as-needed",
     "Only set DT_NEEDED for shared libraries if used",
     "Always set DT_NEEDED for shared libraries (default)">;
 
 defm call_graph_ordering_file:
   Eq<"call-graph-ordering-file", "Layout sections to optimize the given callgraph">;
 
-defm call_graph_profile_sort: BB<"call-graph-profile-sort",
-    "Reorder sections with call graph profile (default)",
-    "Do not reorder sections with call graph profile">;
+def call_graph_profile_sort: JJ<"call-graph-profile-sort=">,
+  HelpText<"Reorder input sections with call graph profile using the specified algorithm (default: hfsort)">,
+  MetaVarName<"[none,hfsort]">,
+  Values<"none,hfsort">;
+def : FF<"no-call-graph-profile-sort">, Alias<call_graph_profile_sort>, AliasArgs<["none"]>,
+  Flags<[HelpHidden]>;
 
 // --chroot doesn't have a help text because it is an internal option.
 def chroot: Separate<["--"], "chroot">;
 
 def color_diagnostics: JJ<"color-diagnostics=">,
   HelpText<"Use colors in diagnostics (default: auto)">,
   MetaVarName<"[auto,always,never]">;
 def : Flag<["--"], "color-diagnostics">, Alias<color_diagnostics>, AliasArgs<["always"]>,

lld/docs/ld.lld.1

 and
 .Cm tree
 are calculated from the object contents.
 .Cm fast
 is not intended to be cryptographically secure.
 .It Fl -build-id
 Synonym for
 .Fl -build-id Ns = Ns Cm fast .
+.It Fl -call-graph-profile-sort Ns = Ns Ar algorithm
+.Ar algorithm
+may be:
+.Pp
+.Bl -tag -width 2n -compact
+.It Cm none
+Ignore call graph profile.
+.It Cm hfsort
+Use hfsort (default).
+.El
+.Pp
 .It Fl -color-diagnostics Ns = Ns Ar value
 Use colors in diagnostics.
 .Ar value
 may be one of
 .Cm always ,
 .Cm auto ,
 and
 .Cm never .

lld/test/ELF/cgprofile-obj.s

 # REQUIRES: x86
 
 # RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
 # RUN: ld.lld -e A %t.o -o %t
 # RUN: llvm-nm --no-sort %t | FileCheck %s
-# RUN: ld.lld --no-call-graph-profile-sort -e A %t.o -o %t
+# RUN: ld.lld --call-graph-profile-sort=none -e A %t.o -o %t
 # RUN: llvm-nm --no-sort %t | FileCheck %s --check-prefix=NO-CG
+## --no-call-graph-profile-sort is an alias for --call-graph-profile-sort=none.
+# RUN: ld.lld --no-call-graph-profile-sort -e A %t.o -o %t1
+# RUN: cmp %t %t1
 
     .section    .text.D,"ax",@progbits
 D:
     retq
 
     .section    .text.C,"ax",@progbits
     .globl  C
 C:

lld/test/ELF/cgprofile-txt.s

 # RUN: echo "TooManyPreds3 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds4 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds5 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds6 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds7 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds8 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds9 TooManyPreds 10" >> %t.call_graph
 # RUN: echo "TooManyPreds10 TooManyPreds 11" >> %t.call_graph
-# RUN: ld.lld -e A %t --call-graph-ordering-file %t.call_graph -o %t2
+# RUN: ld.lld -e A %t --call-graph-ordering-file %t.call_graph --call-graph-profile-sort=hfsort -o %t2
 # RUN: llvm-readobj --symbols %t2 | FileCheck %s
+## --call-graph-profile-sort=hfsort is the default.
+# RUN: ld.lld -e A %t --call-graph-ordering-file %t.call_graph -o %t2b
+# RUN: cmp %t2 %t2b
+
+# RUN: not ld.lld -e A %t --call-graph-ordering-file %t.call_graph --call-graph-profile-sort=sort \
+# RUN:   -o /dev/null 2>&1 | FileCheck %s --check-prefix=UNKNOWN
+
+# UNKNOWN: error: unknown --call-graph-profile-sort= value: sort
 
     .section    .text.D,"ax",@progbits
 D:
     retq
 
     .section    .text.C,"ax",@progbits
     .globl  C
 C: