Merge branch 'main' into fix_for_revert_of_dea5aa73f

Author: alex-t

.ci/compute_projects.py

@@ -200,6 +200,11 @@ def _get_modified_projects(modified_files: list[str]) -> Set[str]:
         # documentation builds.
         if len(path_parts) > 2 and path_parts[1] == "docs":
             continue
+        # Exclude files for the gn build. We do not test it within premerge
+        # and changes occur often enough that they otherwise take up
+        # capacity.
+        if len(path_parts) > 3 and path_parts[:3] == ("llvm", "utils", "gn"):
+            continue
         modified_projects.add(pathlib.Path(modified_file).parts[0])
     return modified_projects
 

.ci/compute_projects_test.py

@@ -179,6 +179,15 @@ def test_exclude_docs(self):
         self.assertEqual(env_variables["runtimes_to_build"], "")
         self.assertEqual(env_variables["runtimes_check_targets"], "")
 
+    def test_exclude_gn(self):
+        env_variables = compute_projects.get_env_variables(
+            ["llvm/utils/gn/build/BUILD.gn"], "Linux"
+        )
+        self.assertEqual(env_variables["projects_to_build"], "")
+        self.assertEqual(env_variables["project_check_targets"], "")
+        self.assertEqual(env_variables["runtimes_to_build"], "")
+        self.assertEqual(env_variables["runtimes_check_targets"], "")
+
 
 if __name__ == "__main__":
     unittest.main()

.ci/monolithic-linux.sh

@@ -53,6 +53,7 @@ targets="${2}"
 lit_args="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --use-unique-output-file-name --timeout=1200 --time-tests"
 
 echo "--- cmake"
+export PIP_BREAK_SYSTEM_PACKAGES=1
 pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
 pip install -q -r "${MONOREPO_ROOT}"/lldb/test/requirements.txt
 pip install -q -r "${MONOREPO_ROOT}"/.ci/requirements.txt

.github/workflows/containers/github-action-ci-windows/Dockerfile

@@ -108,7 +108,7 @@ RUN choco install -y handle
 
 RUN pip3 install pywin32 buildbot-worker==2.8.4
 
-ARG RUNNER_VERSION=2.322.0
+ARG RUNNER_VERSION=2.323.0
 ENV RUNNER_VERSION=$RUNNER_VERSION
 
 RUN powershell -Command \

.github/workflows/containers/github-action-ci/Dockerfile

@@ -95,7 +95,7 @@ WORKDIR /home/gha
 
 FROM ci-container as ci-container-agent
 
-ENV GITHUB_RUNNER_VERSION=2.322.0
+ENV GITHUB_RUNNER_VERSION=2.323.0
 
 RUN mkdir actions-runner && \
     cd actions-runner && \

.github/workflows/libcxx-build-and-test.yaml

@@ -197,10 +197,20 @@ jobs:
           os: macos-15
         - config: apple-configuration
           os: macos-15
+        # TODO: These jobs are intended to test back-deployment (building against ToT libc++ but running against an
+        #       older system-provided libc++.dylib). Doing this properly would require building the test suite on a
+        #       recent macOS using a recent Clang (hence recent Xcode), and then running the actual test suite on an
+        #       older mac. We could do that by e.g. sharing artifacts between the two jobs.
+        #
+        #       However, our Lit configuration currently doesn't provide a good way to do that in a batch, so our only
+        #       alternative is to actually build on the same host that we're going to run on. Sadly, that doesn't work
+        #       since older macOSes don't support newer Xcodes. For now, we run the "backdeployment" jobs on recent
+        #       macOS versions as a way to avoid rotting that configuration, but it doesn't provide a lot of additional
+        #       coverage.
         - config: apple-system
-          os: macos-13
+          os: macos-15
         - config: apple-system-hardened
-          os: macos-13
+          os: macos-15
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2

bolt/include/bolt/Core/MCPlusBuilder.h

@@ -577,6 +577,51 @@ class MCPlusBuilder {
     return getNoRegister();
   }
 
+  /// Returns the register used as call destination, or no-register, if not
+  /// an indirect call. Sets IsAuthenticatedInternally if the instruction
+  /// accepts a signed pointer as its operand and authenticates it internally.
+  virtual MCPhysReg
+  getRegUsedAsCallDest(const MCInst &Inst,
+                       bool &IsAuthenticatedInternally) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
+  /// Returns the register containing an address safely materialized by `Inst`
+  /// under the Pointer Authentication threat model.
+  ///
+  /// Returns the register `Inst` writes to if:
+  /// 1. the register is a materialized address, and
+  /// 2. the register has been materialized safely, i.e. cannot be attacker-
+  ///    controlled, under the Pointer Authentication threat model.
+  ///
+  /// If the instruction does not write to any register satisfying the above
+  /// two conditions, NoRegister is returned.
+  ///
+  /// The Pointer Authentication threat model assumes an attacker is able to
+  /// modify any writable memory, but not executable code (due to W^X).
+  virtual MCPhysReg
+  getMaterializedAddressRegForPtrAuth(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
+  /// Analyzes if this instruction can safely perform address arithmetics
+  /// under Pointer Authentication threat model.
+  ///
+  /// If an (OutReg, InReg) pair is returned, then after Inst is executed,
+  /// OutReg is as trusted as InReg is.
+  ///
+  /// The arithmetic instruction is considered safe if OutReg is not attacker-
+  /// controlled, provided InReg and executable code are not. Please note that
+  /// registers other than InReg as well as the contents of memory which is
+  /// writable by the process should be considered attacker-controlled.
+  virtual std::optional<std::pair<MCPhysReg, MCPhysReg>>
+  analyzeAddressArithmeticsForPtrAuth(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return std::make_pair(getNoRegister(), getNoRegister());
+  }
+
   virtual bool isTerminator(const MCInst &Inst) const;
 
   virtual bool isNoop(const MCInst &Inst) const {
@@ -1741,6 +1786,15 @@ class MCPlusBuilder {
     return {};
   }
 
+  /// Create a sequence of instructions to compare contents of a register
+  /// \p RegNo to immediate \Imm and jump to \p Target if they are different.
+  virtual InstructionListType createCmpJNE(MCPhysReg RegNo, int64_t Imm,
+                                           const MCSymbol *Target,
+                                           MCContext *Ctx) const {
+    llvm_unreachable("not implemented");
+    return {};
+  }
+
   /// Creates inline memcpy instruction. If \p ReturnEnd is true, then return
   /// (dest + n) instead of dest.
   virtual InstructionListType createInlineMemcpy(bool ReturnEnd) const {

bolt/include/bolt/Core/Relocation.h

@@ -86,6 +86,9 @@ class Relocation {
   /// Adjust value depending on relocation type (make it PC relative or not).
   static uint64_t encodeValue(uint32_t Type, uint64_t Value, uint64_t PC);
 
+  /// Return true if there are enough bits to encode the relocation value.
+  static bool canEncodeValue(uint32_t Type, uint64_t Value, uint64_t PC);
+
   /// Extract current relocated value from binary contents. This is used for
   /// RISC architectures where values are encoded in specific bits depending
   /// on the relocation value. For X86, we limit to sign extending the value

bolt/include/bolt/Passes/DataflowAnalysis.h

@@ -292,14 +292,17 @@ class DataflowAnalysis {
   /// Relies on a ptr map to fetch the previous instruction and then retrieve
   /// state. WARNING: Watch out for invalidated pointers. Do not use this
   /// function if you invalidated pointers after the analysis has been completed
-  ErrorOr<const StateTy &> getStateBefore(const MCInst &Point) {
-    return getStateAt(PrevPoint[&Point]);
+  ErrorOr<const StateTy &> getStateBefore(const MCInst &Point) const {
+    auto It = PrevPoint.find(&Point);
+    if (It == PrevPoint.end())
+      return make_error_code(std::errc::result_out_of_range);
+    return getStateAt(It->getSecond());
   }
 
-  ErrorOr<const StateTy &> getStateBefore(ProgramPoint Point) {
+  ErrorOr<const StateTy &> getStateBefore(ProgramPoint Point) const {
     if (Point.isBB())
       return getStateAt(*Point.getBB());
-    return getStateAt(PrevPoint[Point.getInst()]);
+    return getStateBefore(*Point.getInst());
   }
 
   /// Remove any state annotations left by this analysis

bolt/include/bolt/Passes/PAuthGadgetScanner.h

@@ -248,6 +248,9 @@ struct FunctionAnalysisResult {
 };
 
 class Analysis : public BinaryFunctionPass {
+  /// Only search for pac-ret violations.
+  bool PacRetGadgetsOnly;
+
   void runOnFunction(BinaryFunction &Function,
                      MCPlusBuilder::AllocatorIdTy AllocatorId);
   FunctionAnalysisResult findGadgets(BinaryFunction &BF,
@@ -261,7 +264,8 @@ class Analysis : public BinaryFunctionPass {
   std::mutex AnalysisResultsMutex;
 
 public:
-  explicit Analysis() : BinaryFunctionPass(false) {}
+  explicit Analysis(bool PacRetGadgetsOnly)
+      : BinaryFunctionPass(false), PacRetGadgetsOnly(PacRetGadgetsOnly) {}
 
   const char *getName() const override { return "pauth-gadget-scanner"; }
 

bolt/include/bolt/Utils/CommandLineOpts.h

@@ -81,9 +81,9 @@ extern llvm::cl::opt<unsigned> Verbosity;
 /// Return true if we should process all functions in the binary.
 bool processAllFunctions();
 
-enum GadgetScannerKind { GS_PACRET, GS_ALL };
+enum GadgetScannerKind { GS_PACRET, GS_PAUTH, GS_ALL };
 
-extern llvm::cl::list<GadgetScannerKind> GadgetScannersToRun;
+extern llvm::cl::bits<GadgetScannerKind> GadgetScannersToRun;
 
 } // namespace opts
 

bolt/lib/Core/BinaryFunction.cpp

@@ -1795,6 +1795,8 @@ bool BinaryFunction::scanExternalRefs() {
     // Create relocation for every fixup.
     for (const MCFixup &Fixup : Fixups) {
       std::optional<Relocation> Rel = BC.MIB->createRelocation(Fixup, *BC.MAB);
+      // Can be skipped in case of overlow during relocation value encoding.
+      Rel->setOptional();
       if (!Rel) {
         Success = false;
         continue;

bolt/lib/Core/BinarySection.cpp

@@ -12,6 +12,7 @@
 
 #include "bolt/Core/BinarySection.h"
 #include "bolt/Core/BinaryContext.h"
+#include "bolt/Utils/CommandLineOpts.h"
 #include "bolt/Utils/Utils.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/Support/CommandLine.h"
@@ -22,8 +23,8 @@ using namespace llvm;
 using namespace bolt;
 
 namespace opts {
-extern cl::opt<bool> PrintRelocations;
 extern cl::opt<bool> HotData;
+extern cl::opt<bool> PrintRelocations;
 } // namespace opts
 
 uint64_t BinarySection::Count = 0;
@@ -174,11 +175,30 @@ void BinarySection::flushPendingRelocations(raw_pwrite_stream &OS,
     OS.pwrite(Patch.Bytes.data(), Patch.Bytes.size(),
               SectionFileOffset + Patch.Offset);
 
+  uint64_t SkippedPendingRelocations = 0;
   for (Relocation &Reloc : PendingRelocations) {
     uint64_t Value = Reloc.Addend;
     if (Reloc.Symbol)
       Value += Resolver(Reloc.Symbol);
 
+    // Safely skip any optional pending relocation that cannot be encoded.
+    if (Reloc.isOptional() &&
+        !Relocation::canEncodeValue(Reloc.Type, Value,
+                                    SectionAddress + Reloc.Offset)) {
+
+      // A successful run of 'scanExternalRefs' means that all pending
+      // relocations are flushed. Otherwise, PatchEntries should run.
+      if (!opts::ForcePatch) {
+        BC.errs()
+            << "BOLT-ERROR: cannot encode relocation for symbol "
+            << Reloc.Symbol->getName()
+            << " as it is out-of-range. To proceed must use -force-patch\n";
+        exit(1);
+      }
+
+      ++SkippedPendingRelocations;
+      continue;
+    }
     Value = Relocation::encodeValue(Reloc.Type, Value,
                                     SectionAddress + Reloc.Offset);
 
@@ -197,6 +217,11 @@ void BinarySection::flushPendingRelocations(raw_pwrite_stream &OS,
   }
 
   clearList(PendingRelocations);
+
+  if (SkippedPendingRelocations > 0 && opts::Verbosity >= 1) {
+    BC.outs() << "BOLT-INFO: skipped " << SkippedPendingRelocations
+              << " out-of-range optional relocations\n";
+  }
 }
 
 BinarySection::~BinarySection() { updateContents(nullptr, 0); }

bolt/lib/Core/Relocation.cpp

@@ -271,6 +271,16 @@ static uint64_t encodeValueX86(uint32_t Type, uint64_t Value, uint64_t PC) {
   return Value;
 }
 
+static bool canEncodeValueAArch64(uint32_t Type, uint64_t Value, uint64_t PC) {
+  switch (Type) {
+  default:
+    llvm_unreachable("unsupported relocation");
+  case ELF::R_AARCH64_CALL26:
+  case ELF::R_AARCH64_JUMP26:
+    return isInt<28>(Value - PC);
+  }
+}
+
 static uint64_t encodeValueAArch64(uint32_t Type, uint64_t Value, uint64_t PC) {
   switch (Type) {
   default:
@@ -303,6 +313,16 @@ static uint64_t encodeValueAArch64(uint32_t Type, uint64_t Value, uint64_t PC) {
   return Value;
 }
 
+static uint64_t canEncodeValueRISCV(uint32_t Type, uint64_t Value,
+                                    uint64_t PC) {
+  switch (Type) {
+  default:
+    llvm_unreachable("unsupported relocation");
+  case ELF::R_RISCV_64:
+    return true;
+  }
+}
+
 static uint64_t encodeValueRISCV(uint32_t Type, uint64_t Value, uint64_t PC) {
   switch (Type) {
   default:
@@ -739,6 +759,19 @@ uint64_t Relocation::encodeValue(uint32_t Type, uint64_t Value, uint64_t PC) {
   }
 }
 
+bool Relocation::canEncodeValue(uint32_t Type, uint64_t Value, uint64_t PC) {
+  switch (Arch) {
+  default:
+    llvm_unreachable("Unsupported architecture");
+  case Triple::aarch64:
+    return canEncodeValueAArch64(Type, Value, PC);
+  case Triple::riscv64:
+    return canEncodeValueRISCV(Type, Value, PC);
+  case Triple::x86_64:
+    return true;
+  }
+}
+
 uint64_t Relocation::extractValue(uint32_t Type, uint64_t Contents,
                                   uint64_t PC) {
   switch (Arch) {