BOLT fails to read correctly the size of multi-segment mmaps.

Author: paschalis-mpeis

bolt/include/bolt/Profile/DataAggregator.h

@@ -492,6 +492,11 @@ class DataAggregator : public DataReader {
   /// and return a file name matching a given \p FileBuildID.
   std::optional<StringRef> getFileNameForBuildID(StringRef FileBuildID);
 
+  /// Get a constant reference to the parsed binary mmap entries.
+  const std::unordered_map<uint64_t, MMapInfo> &getBinaryMMapInfo() {
+    return BinaryMMapInfo;
+  }
+
   friend class YAMLProfileWriter;
 };
 } // namespace bolt

bolt/lib/Profile/DataAggregator.cpp

@@ -95,6 +95,12 @@ cl::opt<bool> ReadPreAggregated(
     "pa", cl::desc("skip perf and read data from a pre-aggregated file format"),
     cl::cat(AggregatorCategory));
 
+cl::opt<std::string>
+    ReadPerfEvents("perf-script-events",
+                   cl::desc("skip perf event collection by supplying a "
+                            "perf-script output in a textual format"),
+                   cl::cat(AggregatorCategory));
+
 static cl::opt<bool>
 TimeAggregator("time-aggr",
   cl::desc("time BOLT aggregator"),
@@ -464,6 +470,13 @@ void DataAggregator::filterBinaryMMapInfo() {
 
 int DataAggregator::prepareToParse(StringRef Name, PerfProcessInfo &Process,
                                    PerfProcessErrorCallbackTy Callback) {
+  if (!opts::ReadPerfEvents.empty()) {
+    dbgs() << "PERF2BOLT: using pre-processed perf events for '" << Name
+           << "' (perf-script-events)\n";
+    ParsingBuf = opts::ReadPerfEvents;
+    return 0;
+  }
+
   std::string Error;
   outs() << "PERF2BOLT: waiting for perf " << Name
          << " collection to finish...\n";

bolt/unittests/Core/CMakeLists.txt

@@ -8,6 +8,7 @@ set(LLVM_LINK_COMPONENTS
 add_bolt_unittest(CoreTests
   BinaryContext.cpp
   MCPlusBuilder.cpp
+  MemoryMaps.cpp
   DynoStats.cpp
 
   DISABLE_LLVM_LINK_LLVM_DYLIB
@@ -17,6 +18,8 @@ target_link_libraries(CoreTests
   PRIVATE
   LLVMBOLTCore
   LLVMBOLTRewrite
+  LLVMBOLTProfile
+  LLVMTestingSupport
   )
 
 foreach (tgt ${BOLT_TARGETS_TO_BUILD})

bolt/unittests/Core/MemoryMaps.cpp

@@ -0,0 +1,113 @@
+//===- bolt/unittest/Core/MemoryMaps.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 "bolt/Core/BinaryContext.h"
+#include "bolt/Profile/DataAggregator.h"
+#include "llvm/BinaryFormat/ELF.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Testing/Support/Error.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+using namespace llvm::object;
+using namespace llvm::ELF;
+using namespace bolt;
+
+namespace opts {
+extern cl::opt<std::string> ReadPerfEvents;
+} // namespace opts
+
+namespace {
+struct MemoryMapsTester : public testing::TestWithParam<Triple::ArchType> {
+  void SetUp() override {
+    initalizeLLVM();
+    prepareElf();
+    initializeBOLT();
+  }
+
+protected:
+  void initalizeLLVM() {
+    llvm::InitializeAllTargetInfos();
+    llvm::InitializeAllTargetMCs();
+    llvm::InitializeAllAsmParsers();
+    llvm::InitializeAllDisassemblers();
+    llvm::InitializeAllTargets();
+    llvm::InitializeAllAsmPrinters();
+  }
+
+  void prepareElf() {
+    memcpy(ElfBuf, "\177ELF", 4);
+    ELF64LE::Ehdr *EHdr = reinterpret_cast<typename ELF64LE::Ehdr *>(ElfBuf);
+    EHdr->e_ident[llvm::ELF::EI_CLASS] = llvm::ELF::ELFCLASS64;
+    EHdr->e_ident[llvm::ELF::EI_DATA] = llvm::ELF::ELFDATA2LSB;
+    EHdr->e_machine = GetParam() == Triple::aarch64 ? EM_AARCH64 : EM_X86_64;
+    MemoryBufferRef Source(StringRef(ElfBuf, sizeof(ElfBuf)), "ELF");
+    ObjFile = cantFail(ObjectFile::createObjectFile(Source));
+  }
+
+  void initializeBOLT() {
+    Relocation::Arch = ObjFile->makeTriple().getArch();
+    BC = cantFail(BinaryContext::createBinaryContext(
+        ObjFile->makeTriple(), ObjFile->getFileName(), nullptr, true,
+        DWARFContext::create(*ObjFile.get()), {llvm::outs(), llvm::errs()}));
+    ASSERT_FALSE(!BC);
+  }
+
+  char ElfBuf[sizeof(typename ELF64LE::Ehdr)] = {};
+  std::unique_ptr<ObjectFile> ObjFile;
+  std::unique_ptr<BinaryContext> BC;
+};
+} // namespace
+
+#ifdef X86_AVAILABLE
+
+INSTANTIATE_TEST_SUITE_P(X86, MemoryMapsTester,
+                         ::testing::Values(Triple::x86_64));
+
+#endif
+
+#ifdef AARCH64_AVAILABLE
+
+INSTANTIATE_TEST_SUITE_P(AArch64, MemoryMapsTester,
+                         ::testing::Values(Triple::aarch64));
+
+#endif
+
+/// Check that the correct mmap size is computed when we have multiple text
+/// segment mappings. Uses 'opts::ReadPerfEvents' flag to pass a custom 'perf
+/// script' output, along with two text segments (SegmentInfo).
+TEST_P(MemoryMapsTester, ParseMultipleSegments) {
+  const int Pid = 1234;
+  StringRef Filename = "BINARY";
+  opts::ReadPerfEvents = formatv(
+      "name       0 [000]     0.000000: PERF_RECORD_MMAP2 {0}/{0}: "
+      "[0xabc0000000(0x1000000) @ 0x11c0000 103:01 1573523 0]: r-xp {1}\n"
+      "name       0 [000]     0.000000: PERF_RECORD_MMAP2 {0}/{0}: "
+      "[0xabc2000000(0x8000000) @ 0x31d0000 103:01 1573523 0]: r-xp {1}\n",
+      Pid, Filename);
+
+  BC->SegmentMapInfo[0x11da000] =
+      SegmentInfo{0x11da000, 0x10da000, 0x11ca000, 0x10da000, 0x10000};
+  BC->SegmentMapInfo[0x31d0000] =
+      SegmentInfo{0x31d0000, 0x51ac82c, 0x31d0000, 0x3000000, 0x200000};
+
+  DataAggregator DA("");
+  BC->setFilename(Filename);
+  Error Err = DA.preprocessProfile(*BC);
+
+  // Ignore errors from perf2bolt when parsing memory events later on.
+  ASSERT_THAT_ERROR(std::move(Err), Succeeded());
+
+  auto &BinaryMMapInfo = DA.getBinaryMMapInfo();
+  auto El = BinaryMMapInfo.find(Pid);
+  // Check that memory mapping is present and has the expected size.
+  ASSERT_NE(El, BinaryMMapInfo.end());
+  ASSERT_EQ(El->second.Size, static_cast<uint64_t>(0xb1d0000));
+}