Merge branch 'main' of https://github.com/llvm/llvm-project

* 'main' of https://github.com/llvm/llvm-project: (700 commits)
  [SandboxIR][NFC] SingleLLVMInstructionImpl class (llvm#102687)
  [ThinLTO]Clean up 'import-assume-unique-local' flag. (llvm#102424)
  [nsan] Make #include more conventional
  [SandboxIR][NFC] Use Tracker.emplaceIfTracking()
  [libc]  Moved range_reduction_double ifdef statement (llvm#102659)
  [libc] Fix CFP long double and add tests (llvm#102660)
  [TargetLowering] Handle vector types in expandFixedPointMul (llvm#102635)
  [compiler-rt][NFC] Replace environment variable with %t (llvm#102197)
  [UnitTests] Convert a test to use opaque pointers (llvm#102668)
  [CodeGen][NFCI] Don't re-implement parts of ASTContext::getIntWidth (llvm#101765)
  [SandboxIR] Clean up tracking code with the help of emplaceIfTracking() (llvm#102406)
  [mlir][bazel] remove extra blanks in mlir-tblgen test
  [NVPTX][NFC] Update tests to use bfloat type (llvm#101493)
  [mlir] Add support for parsing nested PassPipelineOptions (llvm#101118)
  [mlir][bazel] add missing td dependency in mlir-tblgen test
  [flang][cuda] Fix lib dependency
  [libc] Clean up remaining use of *_WIDTH macros in printf (llvm#102679)
  [flang][cuda] Convert cuf.alloc for box to fir.alloca in device context (llvm#102662)
  [SandboxIR] Implement the InsertElementInst class (llvm#102404)
  [libc] Fix use of cpp::numeric_limits<...>::digits (llvm#102674)
  [mlir][ODS] Verify type constraints in Types and Attributes (llvm#102326)
  [LTO] enable `ObjCARCContractPass` only on optimized build  (llvm#101114)
  [mlir][ODS] Consistent `cppType` / `cppClassName` usage (llvm#102657)
  [lldb] Move definition of SBSaveCoreOptions dtor out of header (llvm#102539)
  [libc] Use cpp::numeric_limits in preference to C23 <limits.h> macros (llvm#102665)
  [clang] Implement -fptrauth-auth-traps. (llvm#102417)
  [LLVM][rtsan] rtsan transform to preserve CFGAnalyses (llvm#102651)
  Revert "[AMDGPU] Move `AMDGPUAttributorPass` to full LTO post link stage (llvm#102086)"
  [RISCV][GISel] Add missing tests for G_CTLZ/CTTZ instruction selection. NFC
  Return available function types for BindingDecls. (llvm#102196)
  [clang] Wire -fptrauth-returns to "ptrauth-returns" fn attribute. (llvm#102416)
  [RISCV] Remove riscv-experimental-rv64-legal-i32. (llvm#102509)
  [RISCV] Move PseudoVSET(I)VLI expansion to use PseudoInstExpansion. (llvm#102496)
  [NVPTX] support switch statement with brx.idx (reland) (llvm#102550)
  [libc][newhdrgen]sorted function names in yaml (llvm#102544)
  [GlobalIsel] Combine G_ADD and G_SUB with constants (llvm#97771)
  Suppress spurious warnings due to R_RISCV_SET_ULEB128
  [scudo] Separated committed and decommitted entries. (llvm#101409)
  [MIPS] Fix missing ANDI optimization (llvm#97689)
  [Clang] Add env var for nvptx-arch/amdgpu-arch timeout (llvm#102521)
  [asan] Switch allocator to dynamic base address (llvm#98511)
  [AMDGPU] Move `AMDGPUAttributorPass` to full LTO post link stage (llvm#102086)
  [libc][math][c23] Add fadd{l,f128} C23 math functions (llvm#102531)
  [mlir][bazel] revert bazel rule change for DLTITransformOps
  [msan] Support vst{2,3,4}_lane instructions (llvm#101215)
  Revert "[MLIR][DLTI][Transform] Introduce transform.dlti.query (llvm#101561)"
  [X86] pr57673.ll - generate MIR test checks
  [mlir][vector][test] Split tests from vector-transfer-flatten.mlir (llvm#102584)
  [mlir][bazel] add bazel rule for DLTITransformOps
  OpenMPOpt: Remove dead include
  [IR] Add method to GlobalVariable to change type of initializer. (llvm#102553)
  [flang][cuda] Force default allocator in device code (llvm#102238)
  [llvm] Construct SmallVector<SDValue> with ArrayRef (NFC) (llvm#102578)
  [MLIR][DLTI][Transform] Introduce transform.dlti.query (llvm#101561)
  [AMDGPU][AsmParser][NFC] Remove a misleading comment. (llvm#102604)
  [Arm][AArch64][Clang] Respect function's branch protection attributes. (llvm#101978)
  [mlir] Verifier: steal bit to track seen instead of set. (llvm#102626)
  [Clang] Fix Handling of Init Capture with Parameter Packs in LambdaScopeForCallOperatorInstantiationRAII (llvm#100766)
  [X86] Convert truncsat clamping patterns to use SDPatternMatch. NFC.
  [gn] Give two scripts argparse.RawDescriptionHelpFormatter
  [bazel] Add missing dep for the SPIRVToLLVM target
  [Clang] Simplify specifying passes via -Xoffload-linker (llvm#102483)
  [bazel] Port for d45de80
  [SelectionDAG] Use unaligned store/load to move AVX registers onto stack for `insertelement` (llvm#82130)
  [Clang][OMPX] Add the code generation for multi-dim `num_teams` (llvm#101407)
  [ARM] Regenerate big-endian-vmov.ll. NFC
  [AMDGPU][AsmParser][NFCI] All NamedIntOperands to be of the i32 type. (llvm#102616)
  [libc][math][c23] Add totalorderl function. (llvm#102564)
  [mlir][spirv] Support `memref` in `convert-to-spirv` pass (llvm#102534)
  [MLIR][GPU-LLVM] Convert `gpu.func` to `llvm.func` (llvm#101664)
  Fix a unit test input file (llvm#102567)
  [llvm-readobj][COFF] Dump hybrid objects for ARM64X files. (llvm#102245)
  AMDGPU/NewPM: Port SIFixSGPRCopies to new pass manager (llvm#102614)
  [MemoryBuiltins] Simplify getCalledFunction() helper (NFC)
  [AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (llvm#102105)
  [MemoryBuiltins] Handle allocator attributes on call-site
  LSV/test/AArch64: add missing lit.local.cfg; fix build (llvm#102607)
  Revert "Enable logf128 constant folding for hosts with 128bit floats (llvm#96287)"
  [RISCV] Add Syntacore SCR5 RV32/64 processors definition (llvm#102285)
  [InstCombine] Remove unnecessary RUN line from test (NFC)
  [flang][OpenMP] Handle multiple ranges in `num_teams` clause (llvm#102535)
  [mlir][vector] Add tests for scalable vectors in one-shot-bufferize.mlir (llvm#102361)
  [mlir][vector] Disable `vector.matrix_multiply` for scalable vectors (llvm#102573)
  [clang] Implement CWG2627 Bit-fields and narrowing conversions (llvm#78112)
  [NFC] Use references to avoid copying (llvm#99863)
  Revert "[mlir][ArmSME] Pattern to swap shape_cast(tranpose) with transpose(shape_cast) (llvm#100731)" (llvm#102457)
  [IRBuilder] Generate nuw GEPs for struct member accesses (llvm#99538)
  [bazel] Port for 9b06e25
  [CodeGen][NewPM] Improve start/stop pass error message CodeGenPassBuilder (llvm#102591)
  [AArch64] Implement TRBMPAM_EL1 system register (llvm#102485)
  [InstCombine] Fixing wrong select folding in vectors with undef elements (llvm#102244)
  [AArch64] Sink operands to fmuladd. (llvm#102297)
  LSV: document hang reported in llvm#37865 (llvm#102479)
  Enable logf128 constant folding for hosts with 128bit floats (llvm#96287)
  [RISCV][clang] Remove bfloat base type in non-zvfbfmin vcreate (llvm#102146)
  [RISCV][clang] Add missing `zvfbfmin` to `vget_v` intrinsic (llvm#102149)
  [mlir][vector] Add mask elimination transform (llvm#99314)
  [Clang][Interp] Fix display of syntactically-invalid note for member function calls (llvm#102170)
  [bazel] Port for 3fffa6d
  [DebugInfo][RemoveDIs] Use iterator-inserters in clang (llvm#102006)
  ...

Signed-off-by: Edwiin Kusuma Jaya <[email protected]>

Author: kutemeikito

.github/CODEOWNERS

@@ -33,9 +33,6 @@
 /clang/www/cxx_dr_status.html @Endilll
 /clang/www/make_cxx_dr_status @Endilll
 
-clang/lib/AST/Interp/ @tbaederr
-clang/test/AST/Interp/ @tbaederr
-
 /clang/include/clang/CIR @lanza @bcardosolopes
 /clang/lib/CIR @lanza @bcardosolopes
 /clang/tools/cir-* @lanza @bcardosolopes

.github/workflows/libclang-python-tests.yml

@@ -22,12 +22,6 @@ on:
       - '.github/workflows/libclang-python-tests.yml'
       - '.github/workflows/llvm-project-tests.yml'
 
-concurrency:
-  # Skip intermediate builds: always.
-  # Cancel intermediate builds: only if it is a pull request build.
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
-
 jobs:
   check-clang-python:
     # Build libclang and then run the libclang Python binding's unit tests.

.github/workflows/llvm-project-tests.yml

@@ -51,7 +51,7 @@ concurrency:
   # Cancel intermediate builds: only if it is a pull request build.
   # If the group name here is the same as the group name in the workflow that includes
   # this one, then the action will try to wait on itself and get stuck.
-  group: llvm-project-${{ github.workflow }}-${{ inputs.projects }}${{ github.ref }}
+  group: llvm-project-${{ github.workflow }}-${{ inputs.projects }}-${{ inputs.python_version }}${{ github.ref }}
   cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
 
 jobs:

.github/workflows/release-binaries-all.yml

@@ -91,4 +91,8 @@ jobs:
       release-version: "${{ needs.setup-variables.outputs.release-version }}"
       upload: ${{ needs.setup-variables.outputs.upload == 'true'}}
       runs-on: "${{ matrix.runs-on }}"
-
+    secrets:
+      # This will be empty for pull_request events, but that's fine, because
+      # the release-binaries workflow does not use this secret for the
+      # pull_request event.
+      RELEASE_TASKS_USER_TOKEN: ${{ secrets.RELEASE_TASKS_USER_TOKEN }}

.github/workflows/release-binaries.yml

@@ -37,6 +37,11 @@ on:
         description: "Runner to use for the build"
         required: true
         type: string
+    secrets:
+      RELEASE_TASKS_USER_TOKEN:
+        description: "Secret used to check user permissions."
+        required: false
+
 
 permissions:
   contents: read # Default everything to read-only
@@ -442,7 +447,7 @@ jobs:
     - name: Upload Build Provenance
       uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 #v4.3.3
       with:
-        name: ${{ runner.os }}-${{ runner.arch }}-release-binary-attestation
+        name: ${{ needs.prepare.outputs.release-binary-filename }}-attestation
         path: ${{ needs.prepare.outputs.release-binary-filename }}.jsonl
 
     - name: Upload Release

.github/workflows/release-tasks.yml

@@ -78,6 +78,8 @@ jobs:
     name: Build Release Binaries
     permissions:
       contents: write
+      id-token: write
+      attestations: write
     needs:
       - validate-tag
       - release-create
@@ -99,6 +101,7 @@ jobs:
   release-sources:
     name: Package Release Sources
     permissions:
+      contents: read
       id-token: write
       attestations: write
     needs:

bolt/CMakeLists.txt

@@ -82,7 +82,7 @@ endforeach()
 
 set(BOLT_ENABLE_RUNTIME_default OFF)
 if ((CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64"
-    OR CMAKE_SYSTEM_PROCESSOR STREQUAL "aarch64")
+    OR CMAKE_SYSTEM_PROCESSOR MATCHES "^(arm64|aarch64)$")
     AND (CMAKE_SYSTEM_NAME STREQUAL "Linux"
       OR CMAKE_SYSTEM_NAME STREQUAL "Darwin")
     AND (NOT CMAKE_CROSSCOMPILING))

bolt/docs/CommandLineArgumentReference.md

@@ -113,6 +113,10 @@
 
   Prints out offsets for abbrev and debug_info of Skeleton CUs that get patched.
 
+- `--debug-thread-count=<uint>`
+
+  Specifies the number of threads to be used when processing DWO debug information.
+
 - `--dot-tooltip-code`
 
   Add basic block instructions as tool tips on nodes

bolt/docs/OptimizingLinux.md

@@ -37,7 +37,7 @@ Convert `perf` profile into a format suitable for BOLT passing the `vmlinux` bin
 
 
 ```bash
-$ sudo chwon $USER perf.data
+$ sudo chown $USER perf.data
 $ perf2bolt -p perf.data -o perf.fdata vmlinux
 ```
 

bolt/include/bolt/Core/ParallelUtilities.h

@@ -50,7 +50,8 @@ enum SchedulingPolicy {
 };
 
 /// Return the managed thread pool and initialize it if not initialized.
-ThreadPoolInterface &getThreadPool();
+ThreadPoolInterface &
+getThreadPool(const unsigned ThreadsCount = opts::ThreadCount);
 
 /// Perform the work on each BinaryFunction except those that are accepted
 /// by SkipPredicate, scheduling heuristic is based on SchedPolicy.

bolt/include/bolt/Rewrite/DWARFRewriter.h

@@ -184,7 +184,8 @@ class DWARFRewriter {
   /// Output .dwo files.
   void writeDWOFiles(DWARFUnit &, const OverriddenSectionsMap &,
                      const std::string &, DebugLocWriter &,
-                     DebugStrOffsetsWriter &, DebugStrWriter &);
+                     DebugStrOffsetsWriter &, DebugStrWriter &,
+                     DebugRangesSectionWriter &);
   using KnownSectionsEntry = std::pair<MCSection *, DWARFSectionKind>;
 };
 

bolt/lib/Core/BinaryContext.cpp

@@ -142,7 +142,6 @@ BinaryContext::BinaryContext(std::unique_ptr<MCContext> Ctx,
       InstPrinter(std::move(InstPrinter)), MIA(std::move(MIA)),
       MIB(std::move(MIB)), MRI(std::move(MRI)), DisAsm(std::move(DisAsm)),
       Logger(Logger), InitialDynoStats(isAArch64()) {
-  Relocation::Arch = this->TheTriple->getArch();
   RegularPageSize = isAArch64() ? RegularPageSizeAArch64 : RegularPageSizeX86;
   PageAlign = opts::NoHugePages ? RegularPageSize : HugePageSize;
 }

bolt/lib/Core/BinaryFunction.cpp

@@ -2502,7 +2502,10 @@ void BinaryFunction::annotateCFIState() {
     }
   }
 
-  assert(StateStack.empty() && "corrupt CFI stack");
+  if (!StateStack.empty()) {
+    BC.errs() << "BOLT-WARNING: non-empty CFI stack at the end of " << *this
+              << '\n';
+  }
 }
 
 namespace {

bolt/lib/Core/ParallelUtilities.cpp

@@ -49,7 +49,7 @@ namespace ParallelUtilities {
 
 namespace {
 /// A single thread pool that is used to run parallel tasks
-std::unique_ptr<DefaultThreadPool> ThreadPoolPtr;
+std::unique_ptr<ThreadPoolInterface> ThreadPoolPtr;
 
 unsigned computeCostFor(const BinaryFunction &BF,
                         const PredicateTy &SkipPredicate,
@@ -102,12 +102,15 @@ inline unsigned estimateTotalCost(const BinaryContext &BC,
 
 } // namespace
 
-ThreadPoolInterface &getThreadPool() {
+ThreadPoolInterface &getThreadPool(const unsigned ThreadsCount) {
   if (ThreadPoolPtr.get())
     return *ThreadPoolPtr;
 
-  ThreadPoolPtr = std::make_unique<DefaultThreadPool>(
-      llvm::hardware_concurrency(opts::ThreadCount));
+  if (ThreadsCount > 1)
+    ThreadPoolPtr = std::make_unique<DefaultThreadPool>(
+        llvm::hardware_concurrency(ThreadsCount));
+  else
+    ThreadPoolPtr = std::make_unique<SingleThreadExecutor>();
   return *ThreadPoolPtr;
 }
 

bolt/lib/Rewrite/DWARFRewriter.cpp

@@ -329,6 +329,12 @@ static cl::opt<bool> KeepARanges(
         "keep or generate .debug_aranges section if .gdb_index is written"),
     cl::Hidden, cl::cat(BoltCategory));
 
+static cl::opt<unsigned>
+    DebugThreadCount("debug-thread-count",
+                     cl::desc("specifies thread count for the multithreading "
+                              "for updating DWO debug info"),
+                     cl::init(1), cl::cat(BoltCategory));
+
 static cl::opt<std::string> DwarfOutputPath(
     "dwarf-output-path",
     cl::desc("Path to where .dwo files will be written out to."), cl::init(""),
@@ -475,8 +481,8 @@ static void emitDWOBuilder(const std::string &DWOName,
                            DWARFUnit &SplitCU, DWARFUnit &CU,
                            DebugLocWriter &LocWriter,
                            DebugStrOffsetsWriter &StrOffstsWriter,
-                           DebugStrWriter &StrWriter,
-                           GDBIndex &GDBIndexSection) {
+                           DebugStrWriter &StrWriter, GDBIndex &GDBIndexSection,
+                           DebugRangesSectionWriter &TempRangesSectionWriter) {
   // Populate debug_info and debug_abbrev for current dwo into StringRef.
   DWODIEBuilder.generateAbbrevs();
   DWODIEBuilder.finish();
@@ -532,7 +538,7 @@ static void emitDWOBuilder(const std::string &DWOName,
     OverriddenSections[Kind] = Contents;
   }
   Rewriter.writeDWOFiles(CU, OverriddenSections, DWOName, LocWriter,
-                         StrOffstsWriter, StrWriter);
+                         StrOffstsWriter, StrWriter, TempRangesSectionWriter);
 }
 
 using DWARFUnitVec = std::vector<DWARFUnit *>;
@@ -646,7 +652,6 @@ void DWARFRewriter::updateDebugInfo() {
                                          *StrWriter);
   GDBIndex GDBIndexSection(BC);
   auto processSplitCU = [&](DWARFUnit &Unit, DWARFUnit &SplitCU,
-                            DIEBuilder &DIEBlder,
                             DebugRangesSectionWriter &TempRangesSectionWriter,
                             DebugAddrWriter &AddressWriter,
                             const std::string &DWOName,
@@ -669,7 +674,7 @@ void DWARFRewriter::updateDebugInfo() {
 
     emitDWOBuilder(DWOName, DWODIEBuilder, *this, SplitCU, Unit,
                    DebugLocDWoWriter, DWOStrOffstsWriter, DWOStrWriter,
-                   GDBIndexSection);
+                   GDBIndexSection, TempRangesSectionWriter);
   };
   auto processMainBinaryCU = [&](DWARFUnit &Unit, DIEBuilder &DIEBlder) {
     std::optional<DWARFUnit *> SplitCU;
@@ -716,9 +721,13 @@ void DWARFRewriter::updateDebugInfo() {
       finalizeTypeSections(DIEBlder, *Streamer, GDBIndexSection);
 
   CUPartitionVector PartVec = partitionCUs(*BC.DwCtx);
+  const unsigned int ThreadCount =
+      std::min(opts::DebugThreadCount, opts::ThreadCount);
   for (std::vector<DWARFUnit *> &Vec : PartVec) {
     DIEBlder.buildCompileUnits(Vec);
     llvm::SmallVector<std::unique_ptr<DIEBuilder>, 72> DWODIEBuildersByCU;
+    ThreadPoolInterface &ThreadPool =
+        ParallelUtilities::getThreadPool(ThreadCount);
     for (DWARFUnit *CU : DIEBlder.getProcessedCUs()) {
       createRangeLocListAddressWriters(*CU);
       std::optional<DWARFUnit *> SplitCU;
@@ -729,9 +738,9 @@ void DWARFRewriter::updateDebugInfo() {
         continue;
       DebugAddrWriter &AddressWriter =
           *AddressWritersByCU[CU->getOffset()].get();
-      DebugRangesSectionWriter *TempRangesSectionWriter =
-          CU->getVersion() >= 5 ? RangeListsWritersByCU[*DWOId].get()
-                                : LegacyRangesWritersByCU[*DWOId].get();
+      DebugRangesSectionWriter &TempRangesSectionWriter =
+          CU->getVersion() >= 5 ? *RangeListsWritersByCU[*DWOId].get()
+                                : *LegacyRangesWritersByCU[*DWOId].get();
       std::optional<std::string> DwarfOutputPath =
           opts::DwarfOutputPath.empty()
               ? std::nullopt
@@ -744,9 +753,17 @@ void DWARFRewriter::updateDebugInfo() {
           *DWODIEBuildersByCU.emplace_back(std::move(DWODIEBuilderPtr)).get();
       if (CU->getVersion() >= 5)
         StrOffstsWriter->finalizeSection(*CU, DIEBlder);
-      processSplitCU(*CU, **SplitCU, DIEBlder, *TempRangesSectionWriter,
-                     AddressWriter, DWOName, DwarfOutputPath, DWODIEBuilder);
+      // Important to capture CU and SplitCU by value here, otherwise when the
+      // thread is executed at some point after the current iteration of the
+      // loop, dereferencing CU/SplitCU in the call to processSplitCU means it
+      // will dereference a different variable than the one intended, causing a
+      // seg fault.
+      ThreadPool.async([&, DwarfOutputPath, DWOName, CU, SplitCU] {
+        processSplitCU(*CU, **SplitCU, TempRangesSectionWriter, AddressWriter,
+                       DWOName, DwarfOutputPath, DWODIEBuilder);
+      });
     }
+    ThreadPool.wait();
     for (std::unique_ptr<DIEBuilder> &DWODIEBuilderPtr : DWODIEBuildersByCU)
       DWODIEBuilderPtr->updateDebugNamesTable();
     for (DWARFUnit *CU : DIEBlder.getProcessedCUs())
@@ -1807,7 +1824,8 @@ std::optional<StringRef> updateDebugData(
 void DWARFRewriter::writeDWOFiles(
     DWARFUnit &CU, const OverriddenSectionsMap &OverridenSections,
     const std::string &DWOName, DebugLocWriter &LocWriter,
-    DebugStrOffsetsWriter &StrOffstsWriter, DebugStrWriter &StrWriter) {
+    DebugStrOffsetsWriter &StrOffstsWriter, DebugStrWriter &StrWriter,
+    DebugRangesSectionWriter &TempRangesSectionWriter) {
   // Setup DWP code once.
   DWARFContext *DWOCtx = BC.getDWOContext();
   const uint64_t DWOId = *CU.getDWOId();
@@ -1854,9 +1872,8 @@ void DWARFRewriter::writeDWOFiles(
 
   DebugRangeListsSectionWriter *RangeListssWriter = nullptr;
   if (CU.getVersion() == 5) {
-    assert(RangeListsWritersByCU.count(DWOId) != 0 &&
-           "No RangeListsWriter for DWO ID.");
-    RangeListssWriter = RangeListsWritersByCU[DWOId].get();
+    RangeListssWriter =
+        llvm::dyn_cast<DebugRangeListsSectionWriter>(&TempRangesSectionWriter);
 
     // Handling .debug_rnglists.dwo separately. The original .o/.dwo might not
     // have .debug_rnglists so won't be part of the loop below.

bolt/lib/Rewrite/MachORewriteInstance.cpp

@@ -72,6 +72,7 @@ MachORewriteInstance::MachORewriteInstance(object::MachOObjectFile *InputFile,
                                            StringRef ToolPath, Error &Err)
     : InputFile(InputFile), ToolPath(ToolPath) {
   ErrorAsOutParameter EAO(&Err);
+  Relocation::Arch = InputFile->makeTriple().getArch();
   auto BCOrErr = BinaryContext::createBinaryContext(
       InputFile->makeTriple(), InputFile->getFileName(), nullptr,
       /* IsPIC */ true, DWARFContext::create(*InputFile),

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -354,6 +354,7 @@ RewriteInstance::RewriteInstance(ELFObjectFileBase *File, const int Argc,
     }
   }
 
+  Relocation::Arch = TheTriple.getArch();
   auto BCOrErr = BinaryContext::createBinaryContext(
       TheTriple, File->getFileName(), Features.get(), IsPIC,
       DWARFContext::create(*File, DWARFContext::ProcessDebugRelocations::Ignore,
@@ -2143,6 +2144,14 @@ bool RewriteInstance::analyzeRelocation(
   if (!Relocation::isSupported(RType))
     return false;
 
+  auto IsWeakReference = [](const SymbolRef &Symbol) {
+    Expected<uint32_t> SymFlagsOrErr = Symbol.getFlags();
+    if (!SymFlagsOrErr)
+      return false;
+    return (*SymFlagsOrErr & SymbolRef::SF_Undefined) &&
+           (*SymFlagsOrErr & SymbolRef::SF_Weak);
+  };
+
   const bool IsAArch64 = BC->isAArch64();
 
   const size_t RelSize = Relocation::getSizeForType(RType);
@@ -2174,7 +2183,8 @@ bool RewriteInstance::analyzeRelocation(
     // Section symbols are marked as ST_Debug.
     IsSectionRelocation = (cantFail(Symbol.getType()) == SymbolRef::ST_Debug);
     // Check for PLT entry registered with symbol name
-    if (!SymbolAddress && (IsAArch64 || BC->isRISCV())) {
+    if (!SymbolAddress && !IsWeakReference(Symbol) &&
+        (IsAArch64 || BC->isRISCV())) {
       const BinaryData *BD = BC->getPLTBinaryDataByName(SymbolName);
       SymbolAddress = BD ? BD->getAddress() : 0;
     }
@@ -2603,7 +2613,7 @@ void RewriteInstance::handleRelocation(const SectionRef &RelocatedSection,
       Expected<StringRef> SectionName = Section->getName();
       if (SectionName && !SectionName->empty())
         ReferencedSection = BC->getUniqueSectionByName(*SectionName);
-    } else if (ReferencedSymbol && ContainingBF &&
+    } else if (BC->isRISCV() && ReferencedSymbol && ContainingBF &&
                (cantFail(Symbol.getFlags()) & SymbolRef::SF_Absolute)) {
       // This might be a relocation for an ABS symbols like __global_pointer$ on
       // RISC-V
@@ -5509,6 +5519,14 @@ uint64_t RewriteInstance::getNewFunctionOrDataAddress(uint64_t OldAddress) {
   if (const BinaryFunction *BF =
           BC->getBinaryFunctionContainingAddress(OldAddress)) {
     if (BF->isEmitted()) {
+      // If OldAddress is the another entry point of
+      // the function, then BOLT could get the new address.
+      if (BF->isMultiEntry()) {
+        for (const BinaryBasicBlock &BB : *BF)
+          if (BB.isEntryPoint() &&
+              (BF->getAddress() + BB.getOffset()) == OldAddress)
+            return BF->getOutputAddress() + BB.getOffset();
+      }
       BC->errs() << "BOLT-ERROR: unable to get new address corresponding to "
                     "input address 0x"
                  << Twine::utohexstr(OldAddress) << " in function " << *BF

bolt/test/AArch64/Inputs/build_id.ldscript

@@ -0,0 +1,9 @@
+SECTIONS
+{
+  PROVIDE (__executable_start = SEGMENT_START("text-segment", 0x400000)); . = SEGMENT_START("text-segment", 0x400000) + SIZEOF_HEADERS;
+  .note.gnu.build-id (0x400400):
+   {
+    build_id_note = ABSOLUTE(.);
+    *(.note.gnu.build-id)
+   }
+}

bolt/test/AArch64/build_id.c

@@ -0,0 +1,25 @@
+// This test checks that referencing build_id through GOT table
+// would result in GOT access after disassembly, not directly
+// to build_id address.
+
+// RUN: %clang %cflags -fuse-ld=lld -Wl,-T,%S/Inputs/build_id.ldscript -Wl,-q \
+// RUN:   -Wl,--no-relax -Wl,--build-id=sha1 %s -o %t.exe
+// RUN: llvm-bolt -print-disasm --print-only=get_build_id %t.exe -o %t.bolt | \
+// RUN:   FileCheck %s
+
+// CHECK: adrp	[[REG:x[0-28]+]], __BOLT_got_zero
+// CHECK: ldr x{{.*}}, [[[REG]], :lo12:__BOLT_got_zero{{.*}}]
+
+struct build_id_note {
+  char pad[16];
+  char hash[20];
+};
+
+extern const struct build_id_note build_id_note;
+
+__attribute__((noinline)) char get_build_id() { return build_id_note.hash[0]; }
+
+int main() {
+  get_build_id();
+  return 0;
+}