Merge branch 'main' into main

Author: svkeerthy

.ci/generate_test_report_lib.py

@@ -92,7 +92,9 @@ def plural(num_tests):
             ]
         )
     elif failures:
-        report.extend(["", "## Failed Tests", "(click on a test name to see its output)"])
+        report.extend(
+            ["", "## Failed Tests", "(click on a test name to see its output)"]
+        )
 
         for testsuite_name, failures in failures.items():
             report.extend(["", f"### {testsuite_name}"])

.ci/metrics/metrics.py

@@ -67,6 +67,7 @@
 # remain small.
 BUILDKITE_GRAPHQL_BUILDS_PER_PAGE = 50
 
+
 @dataclass
 class JobMetrics:
     job_name: str
@@ -77,6 +78,7 @@ class JobMetrics:
     workflow_id: int
     workflow_name: str
 
+
 @dataclass
 class GaugeMetric:
     name: str
@@ -258,6 +260,7 @@ def buildkite_get_metrics(
 
     return output, incomplete_now
 
+
 def github_get_metrics(
     github_repo: github.Repository, last_workflows_seen_as_completed: set[int]
 ) -> tuple[list[JobMetrics], int]:

.github/new-prs-labeler.yml

@@ -702,6 +702,7 @@ mlgo:
   - llvm/unittests/CodeGen/ML*
   - llvm/test/CodeGen/MLRegAlloc/**
   - llvm/utils/mlgo-utils/**
+  - llvm/docs/MLGO.rst
 
 tools:llvm-exegesis:
   - llvm/tools/llvm-exegesis/**

.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=2.323.0
+ARG RUNNER_VERSION=2.324.0
 ENV RUNNER_VERSION=$RUNNER_VERSION
 
 RUN powershell -Command \

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

@@ -2,7 +2,7 @@ FROM docker.io/library/ubuntu:24.04 as base
 ENV LLVM_SYSROOT=/opt/llvm
 
 FROM base as stage1-toolchain
-ENV LLVM_VERSION=20.1.1
+ENV LLVM_VERSION=20.1.4
 
 RUN apt-get update && \
     apt-get install -y \
@@ -86,7 +86,7 @@ WORKDIR /home/gha
 
 FROM ci-container as ci-container-agent
 
-ENV GITHUB_RUNNER_VERSION=2.323.0
+ENV GITHUB_RUNNER_VERSION=2.324.0
 
 RUN mkdir actions-runner && \
     cd actions-runner && \

bolt/include/bolt/Core/BinaryFunction.h

@@ -142,8 +142,8 @@ class BinaryFunction {
   /// Types of profile the function can use. Could be a combination.
   enum {
     PF_NONE = 0,     /// No profile.
-    PF_LBR = 1,      /// Profile is based on last branch records.
-    PF_SAMPLE = 2,   /// Non-LBR sample-based profile.
+    PF_BRANCH = 1,   /// Profile is based on branches or branch stacks.
+    PF_BASIC = 2,    /// Non-branch IP sample-based profile.
     PF_MEMEVENT = 4, /// Profile has mem events.
   };
 
@@ -392,7 +392,7 @@ class BinaryFunction {
   float ProfileMatchRatio{0.0f};
 
   /// Raw branch count for this function in the profile.
-  uint64_t RawBranchCount{0};
+  uint64_t RawSampleCount{0};
 
   /// Dynamically executed function bytes, used for density computation.
   uint64_t SampleCountInBytes{0};
@@ -804,6 +804,19 @@ class BinaryFunction {
     return iterator_range<const_cfi_iterator>(cie_begin(), cie_end());
   }
 
+  /// Iterate over instructions (only if CFG is unavailable or not built yet).
+  iterator_range<InstrMapType::iterator> instrs() {
+    assert(!hasCFG() && "Iterate over basic blocks instead");
+    return make_range(Instructions.begin(), Instructions.end());
+  }
+  iterator_range<InstrMapType::const_iterator> instrs() const {
+    assert(!hasCFG() && "Iterate over basic blocks instead");
+    return make_range(Instructions.begin(), Instructions.end());
+  }
+
+  /// Returns whether there are any labels at Offset.
+  bool hasLabelAt(unsigned Offset) const { return Labels.count(Offset) != 0; }
+
   /// Iterate over all jump tables associated with this function.
   iterator_range<std::map<uint64_t, JumpTable *>::const_iterator>
   jumpTables() const {
@@ -1893,11 +1906,11 @@ class BinaryFunction {
 
   /// Return the raw profile information about the number of branch
   /// executions corresponding to this function.
-  uint64_t getRawBranchCount() const { return RawBranchCount; }
+  uint64_t getRawSampleCount() const { return RawSampleCount; }
 
   /// Set the profile data about the number of branch executions corresponding
   /// to this function.
-  void setRawBranchCount(uint64_t Count) { RawBranchCount = Count; }
+  void setRawSampleCount(uint64_t Count) { RawSampleCount = Count; }
 
   /// Return the number of dynamically executed bytes, from raw perf data.
   uint64_t getSampleCountInBytes() const { return SampleCountInBytes; }

bolt/include/bolt/Core/MCPlusBuilder.h

@@ -49,6 +49,7 @@ class MCSymbol;
 class raw_ostream;
 
 namespace bolt {
+class BinaryBasicBlock;
 class BinaryFunction;
 
 /// Different types of indirect branches encountered during disassembly.
@@ -572,6 +573,11 @@ class MCPlusBuilder {
     return false;
   }
 
+  virtual MCPhysReg getSignedReg(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
   virtual ErrorOr<MCPhysReg> getRegUsedAsRetDest(const MCInst &Inst) const {
     llvm_unreachable("not implemented");
     return getNoRegister();
@@ -622,6 +628,54 @@ class MCPlusBuilder {
     return std::make_pair(getNoRegister(), getNoRegister());
   }
 
+  /// Analyzes if a pointer is checked to be authenticated successfully
+  /// by the end of the basic block.
+  ///
+  /// It is possible for pointer authentication instructions not to terminate
+  /// the program abnormally on authentication failure and return some invalid
+  /// pointer instead (like it is done on AArch64 when FEAT_FPAC is not
+  /// implemented). This might be enough to crash on invalid memory access when
+  /// the pointer is later used as the destination of a load, store, or branch
+  /// instruction. On the other hand, when the pointer is not used right away,
+  /// it may be important for the compiler to check the address explicitly not
+  /// to introduce a signing or authentication oracle.
+  ///
+  /// This function is intended to detect a complex, multi-instruction pointer-
+  /// checking sequence spanning a contiguous range of instructions at the end
+  /// of the basic block (as these sequences are expected to end with a
+  /// conditional branch - this is how they are implemented on AArch64 by LLVM).
+  /// If a (Reg, FirstInst) pair is returned and before execution of FirstInst
+  /// Reg was last written to by an authentication instruction, then it is known
+  /// that in any successor of BB either
+  /// * the authentication instruction that last wrote to Reg succeeded, or
+  /// * the program is terminated abnormally without introducing any signing
+  ///   or authentication oracles
+  ///
+  /// Note that this function is not expected to repeat the results returned
+  /// by getAuthCheckedReg(Inst, MayOverwrite) function below.
+  virtual std::optional<std::pair<MCPhysReg, MCInst *>>
+  getAuthCheckedReg(BinaryBasicBlock &BB) const {
+    llvm_unreachable("not implemented");
+    return std::nullopt;
+  }
+
+  /// Returns the register that is checked to be authenticated successfully.
+  ///
+  /// If the returned register was last written to by an authentication
+  /// instruction and that authentication failed, then the program is known
+  /// to be terminated abnormally as a result of execution of Inst.
+  ///
+  /// Additionally, if MayOverwrite is false, it is known that the authenticated
+  /// pointer is not clobbered by Inst itself.
+  ///
+  /// Use this function for simple, single-instruction patterns instead of
+  /// its getAuthCheckedReg(BB) counterpart.
+  virtual MCPhysReg getAuthCheckedReg(const MCInst &Inst,
+                                      bool MayOverwrite) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
   virtual bool isTerminator(const MCInst &Inst) const;
 
   virtual bool isNoop(const MCInst &Inst) const {

bolt/include/bolt/Passes/PAuthGadgetScanner.h

@@ -12,7 +12,6 @@
 #include "bolt/Core/BinaryContext.h"
 #include "bolt/Core/BinaryFunction.h"
 #include "bolt/Passes/BinaryPasses.h"
-#include "llvm/ADT/SmallSet.h"
 #include "llvm/Support/raw_ostream.h"
 #include <memory>
 
@@ -65,6 +64,14 @@ struct MCInstInBFReference {
   uint64_t Offset;
   MCInstInBFReference(BinaryFunction *BF, uint64_t Offset)
       : BF(BF), Offset(Offset) {}
+
+  static MCInstInBFReference get(const MCInst *Inst, BinaryFunction &BF) {
+    for (auto &I : BF.instrs())
+      if (Inst == &I.second)
+        return MCInstInBFReference(&BF, I.first);
+    return {};
+  }
+
   MCInstInBFReference() : BF(nullptr), Offset(0) {}
   bool operator==(const MCInstInBFReference &RHS) const {
     return BF == RHS.BF && Offset == RHS.Offset;
@@ -104,6 +111,12 @@ struct MCInstReference {
   MCInstReference(BinaryFunction *BF, uint32_t Offset)
       : MCInstReference(MCInstInBFReference(BF, Offset)) {}
 
+  static MCInstReference get(const MCInst *Inst, BinaryFunction &BF) {
+    if (BF.hasCFG())
+      return MCInstInBBReference::get(Inst, BF);
+    return MCInstInBFReference::get(Inst, BF);
+  }
+
   bool operator<(const MCInstReference &RHS) const {
     if (ParentKind != RHS.ParentKind)
       return ParentKind < RHS.ParentKind;
@@ -138,6 +151,16 @@ struct MCInstReference {
     llvm_unreachable("");
   }
 
+  operator bool() const {
+    switch (ParentKind) {
+    case BasicBlockParent:
+      return U.BBRef.BB != nullptr;
+    case FunctionParent:
+      return U.BFRef.BF != nullptr;
+    }
+    llvm_unreachable("");
+  }
+
   uint64_t getAddress() const {
     switch (ParentKind) {
     case BasicBlockParent:
@@ -173,9 +196,6 @@ raw_ostream &operator<<(raw_ostream &OS, const MCInstReference &);
 
 namespace PAuthGadgetScanner {
 
-class SrcSafetyAnalysis;
-struct SrcState;
-
 /// Description of a gadget kind that can be detected. Intended to be
 /// statically allocated to be attached to reports by reference.
 class GadgetKind {
@@ -184,7 +204,7 @@ class GadgetKind {
 public:
   GadgetKind(const char *Description) : Description(Description) {}
 
-  const StringRef getDescription() const { return Description; }
+  StringRef getDescription() const { return Description; }
 };
 
 /// Base report located at some instruction, without any additional information.
@@ -199,8 +219,8 @@ struct Report {
 
   // The two methods below are called by Analysis::computeDetailedInfo when
   // iterating over the reports.
-  virtual const ArrayRef<MCPhysReg> getAffectedRegisters() const { return {}; }
-  virtual void setOverwritingInstrs(const ArrayRef<MCInstReference> Instrs) {}
+  virtual ArrayRef<MCPhysReg> getAffectedRegisters() const { return {}; }
+  virtual void setOverwritingInstrs(ArrayRef<MCInstReference> Instrs) {}
 
   void printBasicInfo(raw_ostream &OS, const BinaryContext &BC,
                       StringRef IssueKind) const;
@@ -223,19 +243,19 @@ struct GadgetReport : public Report {
 
   void generateReport(raw_ostream &OS, const BinaryContext &BC) const override;
 
-  const ArrayRef<MCPhysReg> getAffectedRegisters() const override {
+  ArrayRef<MCPhysReg> getAffectedRegisters() const override {
     return AffectedRegisters;
   }
 
-  void setOverwritingInstrs(const ArrayRef<MCInstReference> Instrs) override {
+  void setOverwritingInstrs(ArrayRef<MCInstReference> Instrs) override {
     OverwritingInstrs.assign(Instrs.begin(), Instrs.end());
   }
 };
 
 /// Report with a free-form message attached.
 struct GenericReport : public Report {
   std::string Text;
-  GenericReport(MCInstReference Location, const std::string &Text)
+  GenericReport(MCInstReference Location, StringRef Text)
       : Report(Location), Text(Text) {}
   virtual void generateReport(raw_ostream &OS,
                               const BinaryContext &BC) const override;

bolt/include/bolt/Profile/DataAggregator.h

@@ -92,16 +92,6 @@ class DataAggregator : public DataReader {
     uint64_t Addr;
   };
 
-  /// Used for parsing specific pre-aggregated input files.
-  struct AggregatedLBREntry {
-    enum Type : char { BRANCH = 0, FT, FT_EXTERNAL_ORIGIN, TRACE };
-    Location From;
-    Location To;
-    uint64_t Count;
-    uint64_t Mispreds;
-    Type EntryType;
-  };
-
   struct Trace {
     uint64_t From;
     uint64_t To;
@@ -131,7 +121,6 @@ class DataAggregator : public DataReader {
   /// and use them later for processing and assigning profile.
   std::unordered_map<Trace, TakenBranchInfo, TraceHash> BranchLBRs;
   std::unordered_map<Trace, FTInfo, TraceHash> FallthroughLBRs;
-  std::vector<AggregatedLBREntry> AggregatedLBRs;
   std::unordered_map<uint64_t, uint64_t> BasicSamples;
   std::vector<PerfMemSample> MemSamples;
 
@@ -223,11 +212,6 @@ class DataAggregator : public DataReader {
   uint64_t NumTraces{0};
   uint64_t NumInvalidTraces{0};
   uint64_t NumLongRangeTraces{0};
-  /// Specifies how many samples were recorded in cold areas if we are dealing
-  /// with profiling data collected in a bolted binary. For LBRs, incremented
-  /// for the source of the branch to avoid counting cold activity twice (one
-  /// for source and another for destination).
-  uint64_t NumColdSamples{0};
   uint64_t NumTotalSamples{0};
 
   /// Looks into system PATH for Linux Perf and set up the aggregator to use it
@@ -257,7 +241,8 @@ class DataAggregator : public DataReader {
 
   /// Semantic actions - parser hooks to interpret parsed perf samples
   /// Register a sample (non-LBR mode), i.e. a new hit at \p Address
-  bool doSample(BinaryFunction &Func, const uint64_t Address, uint64_t Count);
+  bool doBasicSample(BinaryFunction &Func, const uint64_t Address,
+                     uint64_t Count);
 
   /// Register an intraprocedural branch \p Branch.
   bool doIntraBranch(BinaryFunction &Func, uint64_t From, uint64_t To,
@@ -422,9 +407,6 @@ class DataAggregator : public DataReader {
   /// an external tool.
   std::error_code parsePreAggregatedLBRSamples();
 
-  /// Process parsed pre-aggregated data.
-  void processPreAggregated();
-
   /// If \p Address falls into the binary address space based on memory
   /// mapping info \p MMI, then adjust it for further processing by subtracting
   /// the base load address. External addresses, i.e. addresses that do not
@@ -486,7 +468,6 @@ class DataAggregator : public DataReader {
   void dump(const PerfMemSample &Sample) const;
 
   /// Profile diagnostics print methods
-  void printColdSamplesDiagnostic() const;
   void printLongRangeTracesDiagnostic() const;
   void printBranchSamplesDiagnostics() const;
   void printBasicSamplesDiagnostics(uint64_t OutOfRangeSamples) const;