[lld] [lld][ELF] Extend profile guided function ordering to ELF binaries (PR #117514)

[Ellis Hoag via llvm-commits]

================
@@ -0,0 +1,383 @@
+//===- BPSectionOrdererBase.cpp---------------------------------------*- C++
+//-*-===//
+//
+// 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 "lld/Common/BPSectionOrdererBase.h"
+#include "lld/Common/ErrorHandler.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/ProfileData/InstrProfReader.h"
+#include "llvm/Support/BalancedPartitioning.h"
+#include "llvm/Support/TimeProfiler.h"
+#include "llvm/Support/VirtualFileSystem.h"
+#include "llvm/Support/xxhash.h"
+
+#define DEBUG_TYPE "bp-section-orderer"
+using namespace llvm;
+using UtilityNodes = SmallVector<BPFunctionNode::UtilityNodeT>;
+
+namespace lld {
+
+static SmallVector<std::pair<unsigned, UtilityNodes>> getUnsForCompression(
+    ArrayRef<const BPSectionBase *> sections,
+    const DenseMap<const BPSectionBase *, uint64_t> &sectionToIdx,
+    ArrayRef<unsigned> sectionIdxs,
+    DenseMap<unsigned, SmallVector<unsigned>> *duplicateSectionIdxs,
+    BPFunctionNode::UtilityNodeT &maxUN) {
+  TimeTraceScope timeScope("Build nodes for compression");
+
+  SmallVector<std::pair<unsigned, SmallVector<uint64_t>>> sectionHashes;
+  sectionHashes.reserve(sectionIdxs.size());
+  SmallVector<uint64_t> hashes;
+
+  for (unsigned sectionIdx : sectionIdxs) {
+    const auto *isec = sections[sectionIdx];
+    isec->getSectionHash(hashes, sectionToIdx);
+    sectionHashes.emplace_back(sectionIdx, std::move(hashes));
+    hashes.clear();
+  }
+
+  DenseMap<uint64_t, unsigned> hashFrequency;
+  for (auto &[sectionIdx, hashes] : sectionHashes)
+    for (auto hash : hashes)
+      ++hashFrequency[hash];
+
+  if (duplicateSectionIdxs) {
+    // Merge section that are nearly identical
+    SmallVector<std::pair<unsigned, SmallVector<uint64_t>>> newSectionHashes;
+    DenseMap<uint64_t, unsigned> wholeHashToSectionIdx;
+    for (auto &[sectionIdx, hashes] : sectionHashes) {
+      uint64_t wholeHash = 0;
+      for (auto hash : hashes)
+        if (hashFrequency[hash] > 5)
+          wholeHash ^= hash;
+      auto [it, wasInserted] =
+          wholeHashToSectionIdx.insert(std::make_pair(wholeHash, sectionIdx));
+      if (wasInserted) {
+        newSectionHashes.emplace_back(sectionIdx, hashes);
+      } else {
+        (*duplicateSectionIdxs)[it->getSecond()].push_back(sectionIdx);
+      }
+    }
+    sectionHashes = newSectionHashes;
+
+    // Recompute hash frequencies
+    hashFrequency.clear();
+    for (auto &[sectionIdx, hashes] : sectionHashes)
+      for (auto hash : hashes)
+        ++hashFrequency[hash];
+  }
+
+  // Filter rare and common hashes and assign each a unique utility node that
+  // doesn't conflict with the trace utility nodes
+  DenseMap<uint64_t, BPFunctionNode::UtilityNodeT> hashToUN;
+  for (auto &[hash, frequency] : hashFrequency) {
+    if (frequency <= 1 || frequency * 2 > sectionHashes.size())
+      continue;
+    hashToUN[hash] = ++maxUN;
+  }
+
+  SmallVector<std::pair<unsigned, UtilityNodes>> sectionUns;
+  for (auto &[sectionIdx, hashes] : sectionHashes) {
+    UtilityNodes uns;
+    for (auto &hash : hashes) {
+      auto it = hashToUN.find(hash);
+      if (it != hashToUN.end())
+        uns.push_back(it->second);
+    }
+    sectionUns.emplace_back(sectionIdx, uns);
+  }
+  return sectionUns;
+}
+
+llvm::DenseMap<const BPSectionBase *, size_t>
+BPSectionOrdererBase::reorderSectionsByBalancedPartitioning(
+    size_t &highestAvailablePriority, llvm::StringRef profilePath,
+    bool forFunctionCompression, bool forDataCompression,
+    bool compressionSortStartupFunctions, bool verbose,
+    SmallVector<BPSectionBase *> inputSections) {
+  TimeTraceScope timeScope("Balanced Partitioning");
+  SmallVector<const BPSectionBase *> sections;
+  DenseMap<const BPSectionBase *, uint64_t> sectionToIdx;
+  StringMap<DenseSet<unsigned>> symbolToSectionIdxs;
+
+  // Process input sections
+  for (const auto *isec : inputSections) {
+    if (!isec->hasValidData())
+      continue;
+
+    unsigned sectionIdx = sections.size();
+    sectionToIdx.try_emplace(isec, sectionIdx);
+    sections.push_back(isec);
+
+    for (auto *sym : isec->getSymbols())
+      if (auto *d = sym->asDefinedSymbol())
+        symbolToSectionIdxs[d->getName()].insert(sectionIdx);
+  }
+  StringMap<DenseSet<unsigned>> rootSymbolToSectionIdxs;
+  for (auto &entry : symbolToSectionIdxs) {
+    StringRef name = entry.getKey();
+    auto &sectionIdxs = entry.getValue();
+    name = BPSectionBase::getRootSymbol(name);
+    rootSymbolToSectionIdxs[name].insert(sectionIdxs.begin(),
+                                         sectionIdxs.end());
+    // Linkage names can be prefixed with "_" or "l_" on Mach-O. See
+    // Mangler::getNameWithPrefix() for details.
+    if (name.consume_front("_") || name.consume_front("l_"))
+      rootSymbolToSectionIdxs[name].insert(sectionIdxs.begin(),
+                                           sectionIdxs.end());
----------------
ellishg wrote:

This code is Mach-O specific and probably shouldn't be in `lld/Common`. Unless there is a way to detect the target in this file?

https://github.com/llvm/llvm-project/pull/117514