[ELF] Add BPSectionOrderer options

lld/ELF/BPSectionOrderer.cpp

@@ -0,0 +1,95 @@
+//===- BPSectionOrderer.cpp -----------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "BPSectionOrderer.h"
+#include "InputFiles.h"
+#include "InputSection.h"
+#include "SymbolTable.h"
+#include "Symbols.h"
+#include "lld/Common/BPSectionOrdererBase.inc"
+#include "llvm/Support/Endian.h"
+
+using namespace llvm;
+using namespace lld::elf;
+
+namespace {
+struct BPOrdererELF;
+}
+template <> struct lld::BPOrdererTraits<struct BPOrdererELF> {
+  using Section = elf::InputSectionBase;
+  using Defined = elf::Defined;
+};
+namespace {
+struct BPOrdererELF : lld::BPOrderer<BPOrdererELF> {
+  DenseMap<const InputSectionBase *, Defined *> secToSym;
+
+  static uint64_t getSize(const Section &sec) { return sec.getSize(); }
+  static bool isCodeSection(const Section &sec) {
+    return sec.flags & llvm::ELF::SHF_EXECINSTR;
+  }
+  ArrayRef<Defined *> getSymbols(const Section &sec) {
+    auto it = secToSym.find(&sec);
+    if (it == secToSym.end())
+      return {};
+    return ArrayRef(it->second);
+  }
+
+  static void
+  getSectionHashes(const Section &sec, llvm::SmallVectorImpl<uint64_t> &hashes,
+                   const llvm::DenseMap<const void *, uint64_t> &sectionToIdx) {
+    constexpr unsigned windowSize = 4;
+
+    // Calculate content hashes: k-mers and the last k-1 bytes.
+    ArrayRef<uint8_t> data = sec.content();
+    if (data.size() >= windowSize)
+      for (size_t i = 0; i <= data.size() - windowSize; ++i)
+        hashes.push_back(llvm::support::endian::read32le(data.data() + i));
+    for (uint8_t byte : data.take_back(windowSize - 1))
+      hashes.push_back(byte);
+
+    llvm::sort(hashes);
+    hashes.erase(std::unique(hashes.begin(), hashes.end()), hashes.end());
+  }
+
+  static StringRef getSymName(const Defined &sym) { return sym.getName(); }
+  static uint64_t getSymValue(const Defined &sym) { return sym.value; }
+  static uint64_t getSymSize(const Defined &sym) { return sym.size; }
+};
+} // namespace
+
+DenseMap<const InputSectionBase *, int> elf::runBalancedPartitioning(
+    Ctx &ctx, StringRef profilePath, bool forFunctionCompression,
+    bool forDataCompression, bool compressionSortStartupFunctions,
+    bool verbose) {
+  // Collect candidate sections and associated symbols.
+  SmallVector<InputSectionBase *> sections;
+  DenseMap<CachedHashStringRef, DenseSet<unsigned>> rootSymbolToSectionIdxs;
+  BPOrdererELF orderer;
+
+  auto addSection = [&](Symbol &sym) {
+    auto *d = dyn_cast<Defined>(&sym);
+    if (!d)
+      return;
+    auto *sec = dyn_cast_or_null<InputSectionBase>(d->section);
+    if (!sec || sec->size == 0 || !orderer.secToSym.try_emplace(sec, d).second)
+      return;
+    rootSymbolToSectionIdxs[CachedHashStringRef(getRootSymbol(sym.getName()))]
+        .insert(sections.size());
+    sections.emplace_back(sec);
+  };
+
+  for (Symbol *sym : ctx.symtab->getSymbols())
+    addSection(*sym);
+  for (ELFFileBase *file : ctx.objectFiles)
+    for (Symbol *sym : file->getLocalSymbols())
+      addSection(*sym);
+  return orderer.computeOrder(profilePath, forFunctionCompression,
+                              forDataCompression,
+                              compressionSortStartupFunctions, verbose,
+                              sections, rootSymbolToSectionIdxs);
+}

lld/ELF/BPSectionOrderer.h

@@ -0,0 +1,37 @@
+//===- BPSectionOrderer.h -------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// This file uses Balanced Partitioning to order sections to improve startup
+/// time and compressed size.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLD_ELF_BPSECTION_ORDERER_H
+#define LLD_ELF_BPSECTION_ORDERER_H
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/StringRef.h"
+
+namespace lld::elf {
+struct Ctx;
+class InputSectionBase;
+
+/// Run Balanced Partitioning to find the optimal function and data order to
+/// improve startup time and compressed size.
+///
+/// It is important that -ffunction-sections and -fdata-sections compiler flags
+/// are used to ensure functions and data are in their own sections and thus
+/// can be reordered.
+llvm::DenseMap<const InputSectionBase *, int>
+runBalancedPartitioning(Ctx &ctx, llvm::StringRef profilePath,
+                        bool forFunctionCompression, bool forDataCompression,
+                        bool compressionSortStartupFunctions, bool verbose);
+
+} // namespace lld::elf
+
+#endif

lld/ELF/CMakeLists.txt

@@ -37,6 +37,7 @@ add_lld_library(lldELF
   Arch/X86.cpp
   Arch/X86_64.cpp
   ARMErrataFix.cpp
+  BPSectionOrderer.cpp
   CallGraphSort.cpp
   DWARF.cpp
   Driver.cpp
@@ -72,6 +73,7 @@ add_lld_library(lldELF
   Object
   Option
   Passes
+  ProfileData
   Support
   TargetParser
   TransformUtils

lld/ELF/Config.h

@@ -264,6 +264,12 @@ struct Config {
   bool armBe8 = false;
   BsymbolicKind bsymbolic = BsymbolicKind::None;
   CGProfileSortKind callGraphProfileSort;
+  llvm::StringRef irpgoProfilePath;
+  bool bpStartupFunctionSort = false;
+  bool bpCompressionSortStartupFunctions = false;
+  bool bpFunctionOrderForCompression = false;
+  bool bpDataOrderForCompression = false;
+  bool bpVerboseSectionOrderer = false;
   bool checkSections;
   bool checkDynamicRelocs;
   std::optional<llvm::DebugCompressionType> compressDebugSections;

lld/ELF/Driver.cpp

@@ -1118,6 +1118,53 @@ static CGProfileSortKind getCGProfileSortKind(Ctx &ctx,
   return CGProfileSortKind::None;
 }
 
+static void parseBPOrdererOptions(Ctx &ctx, opt::InputArgList &args) {
+  if (auto *arg = args.getLastArg(OPT_bp_compression_sort)) {
+    StringRef s = arg->getValue();
+    if (s == "function") {
+      ctx.arg.bpFunctionOrderForCompression = true;
+    } else if (s == "data") {
+      ctx.arg.bpDataOrderForCompression = true;
+    } else if (s == "both") {
+      ctx.arg.bpFunctionOrderForCompression = true;
+      ctx.arg.bpDataOrderForCompression = true;
+    } else if (s != "none") {
+      ErrAlways(ctx) << arg->getSpelling()
+                     << ": expected [none|function|data|both]";
+    }
+    if (s != "none" && args.hasArg(OPT_call_graph_ordering_file))
+      ErrAlways(ctx) << "--bp-compression-sort is incompatible with "
+                        "--call-graph-ordering-file";
+  }
+  if (auto *arg = args.getLastArg(OPT_bp_startup_sort)) {
+    StringRef s = arg->getValue();
+    if (s == "function") {
+      ctx.arg.bpStartupFunctionSort = true;
+    } else if (s != "none") {
+      ErrAlways(ctx) << arg->getSpelling() << ": expected [none|function]";
+    }
+    if (s != "none" && args.hasArg(OPT_call_graph_ordering_file))
+      ErrAlways(ctx) << "--bp-startup-sort=function is incompatible with "
+                        "--call-graph-ordering-file";
+  }
+
+  ctx.arg.bpCompressionSortStartupFunctions =
+      args.hasFlag(OPT_bp_compression_sort_startup_functions,
+                   OPT_no_bp_compression_sort_startup_functions, false);
+  ctx.arg.bpVerboseSectionOrderer = args.hasArg(OPT_verbose_bp_section_orderer);
+
+  ctx.arg.irpgoProfilePath = args.getLastArgValue(OPT_irpgo_profile);
+  if (ctx.arg.irpgoProfilePath.empty()) {
+    if (ctx.arg.bpStartupFunctionSort)
+      ErrAlways(ctx) << "--bp-startup-sort=function must be used with "
+                        "--irpgo-profile";
+    if (ctx.arg.bpCompressionSortStartupFunctions)
+      ErrAlways(ctx)
+          << "--bp-compression-sort-startup-functions must be used with "
+             "--irpgo-profile";
+  }
+}
+
 static DebugCompressionType getCompressionType(Ctx &ctx, StringRef s,
                                                StringRef option) {
   DebugCompressionType type = StringSwitch<DebugCompressionType>(s)
@@ -1259,6 +1306,7 @@ static void readConfigs(Ctx &ctx, opt::InputArgList &args) {
       ctx.arg.bsymbolic = BsymbolicKind::All;
   }
   ctx.arg.callGraphProfileSort = getCGProfileSortKind(ctx, args);
+  parseBPOrdererOptions(ctx, args);
   ctx.arg.checkSections =
       args.hasFlag(OPT_check_sections, OPT_no_check_sections, true);
   ctx.arg.chroot = args.getLastArgValue(OPT_chroot);

lld/ELF/Options.td

@@ -141,6 +141,19 @@ def call_graph_profile_sort: JJ<"call-graph-profile-sort=">,
 def : FF<"no-call-graph-profile-sort">, Alias<call_graph_profile_sort>, AliasArgs<["none"]>,
   Flags<[HelpHidden]>;
 
+defm irpgo_profile: EEq<"irpgo-profile",
+  "Read a temporary profile file for use with --bp-startup-sort=">;
+def bp_compression_sort: JJ<"bp-compression-sort=">, MetaVarName<"[none,function,data,both]">,
+  HelpText<"Improve Lempel-Ziv compression by grouping similar sections together, resulting in a smaller compressed app size">;
+def bp_startup_sort: JJ<"bp-startup-sort=">, MetaVarName<"[none,function]">,
+  HelpText<"Utilize a temporal profile file to reduce page faults during program startup">;
+
+// Auxiliary options related to balanced partition
+defm bp_compression_sort_startup_functions: BB<"bp-compression-sort-startup-functions",
+  "When --irpgo-profile is pecified, prioritize function similarity for compression in addition to startup time", "">;
+def verbose_bp_section_orderer: FF<"verbose-bp-section-orderer">,
+  HelpText<"Print information on balanced partitioning">;
+
 // --chroot doesn't have a help text because it is an internal option.
 def chroot: Separate<["--"], "chroot">;
 

lld/ELF/Writer.cpp

@@ -9,6 +9,7 @@
 #include "Writer.h"
 #include "AArch64ErrataFix.h"
 #include "ARMErrataFix.h"
+#include "BPSectionOrderer.h"
 #include "CallGraphSort.h"
 #include "Config.h"
 #include "InputFiles.h"
@@ -1082,8 +1083,18 @@ static void maybeShuffle(Ctx &ctx,
 // that don't appear in the order file.
 static DenseMap<const InputSectionBase *, int> buildSectionOrder(Ctx &ctx) {
   DenseMap<const InputSectionBase *, int> sectionOrder;
-  if (!ctx.arg.callGraphProfile.empty())
+  if (ctx.arg.bpStartupFunctionSort || ctx.arg.bpFunctionOrderForCompression ||
+      ctx.arg.bpDataOrderForCompression) {
+    TimeTraceScope timeScope("Balanced Partitioning Section Orderer");
+    sectionOrder = runBalancedPartitioning(
+        ctx, ctx.arg.bpStartupFunctionSort ? ctx.arg.irpgoProfilePath : "",
+        ctx.arg.bpFunctionOrderForCompression,
+        ctx.arg.bpDataOrderForCompression,
+        ctx.arg.bpCompressionSortStartupFunctions,
+        ctx.arg.bpVerboseSectionOrderer);
+  } else if (!ctx.arg.callGraphProfile.empty()) {
     sectionOrder = computeCallGraphProfileOrder(ctx);
+  }
 
   if (ctx.arg.symbolOrderingFile.empty())
     return sectionOrder;

lld/include/lld/Common/BPSectionOrdererBase.inc

@@ -63,6 +63,10 @@ template <class D> struct BPOrderer {
                     const DenseMap<CachedHashStringRef, DenseSet<unsigned>>
                         &rootSymbolToSectionIdxs)
       -> llvm::DenseMap<const Section *, int>;
+
+  std::optional<StringRef> static getResolvedLinkageName(llvm::StringRef name) {
+    return {};
+  }
 };
 } // namespace lld
 
@@ -97,10 +101,11 @@ static SmallVector<std::pair<unsigned, UtilityNodes>> getUnsForCompression(
     // Merge sections that are nearly identical
     SmallVector<std::pair<unsigned, SmallVector<uint64_t>>> newSectionHashes;
     DenseMap<uint64_t, unsigned> wholeHashToSectionIdx;
+    unsigned threshold = sectionHashes.size() > 10000 ? 5 : 0;
     for (auto &[sectionIdx, hashes] : sectionHashes) {
       uint64_t wholeHash = 0;
       for (auto hash : hashes)
-        if (hashFrequency[hash] > 5)
+        if (hashFrequency[hash] > threshold)
           wholeHash ^= hash;
       auto [it, wasInserted] =
           wholeHashToSectionIdx.insert(std::make_pair(wholeHash, sectionIdx));