Merge branch 'main' into users/kparzysz/spr/a04-atomic-one

Author: kparzysz

.github/new-prs-labeler.yml

@@ -791,6 +791,12 @@ lld:wasm:
   - lld/**/wasm/**
   - lld/Common/**
 
+backend:ARC:
+  - llvm/lib/Target/ARC/**
+  - clang/lib/Basic/Targets/ARC.h
+  - clang/lib/Basic/Targets/ARC.cpp
+  - clang/lib/CodeGen/Targets/ARC.cpp
+
 backend:ARM:
   - llvm/include/llvm/IR/IntrinsicsARM.td
   - llvm/test/MC/ARM/**
@@ -817,6 +823,19 @@ backend:AArch64:
   - clang/include/clang/Sema/SemaARM.h
   - clang/lib/Sema/SemaARM.cpp
 
+backend:CSKY:
+  - llvm/lib/Target/CSKY/**
+  - llvm/include/llvm/TargetParser/CSKYTargetParser.def
+  - llvm/include/llvm/TargetParser/CSKYTargetParser.h
+  - llvm/include/llvm/BinaryFormat/ELFRelocs/CSKY.def
+  - llvm/lib/TargetParser/CSKYTargetParser.cpp
+  - llvm/lib/Support/CSKYAttributes.cpp
+  - llvm/lib/Support/CSKYAttributeParser.cpp
+  - clang/lib/Basic/Targets/CSKY.h
+  - clang/lib/Basic/Targets/CSKY.cpp
+  - clang/lib/CodeGen/Targets/CSKY.cpp
+  - clang/lib/Driver/ToolChains/CSKY*
+
 backend:Hexagon:
   - clang/include/clang/Basic/BuiltinsHexagon*.def
   - clang/include/clang/Sema/SemaHexagon.h
@@ -840,6 +859,13 @@ backend:Hexagon:
   - llvm/test/MC/Hexagon/**
   - llvm/test/tools/llvm-objdump/ELF/Hexagon/**
 
+backend:Lanai:
+  - llvm/lib/Target/Lanai/**
+  - clang/lib/Basic/Targets/Lanai.h
+  - clang/lib/Basic/Targets/Lanai.cpp
+  - clang/lib/CodeGen/Targets/Lanai.cpp
+  - clang/lib/Driver/ToolChains/Lanai*
+
 backend:loongarch:
   - llvm/include/llvm/IR/IntrinsicsLoongArch.td
   - llvm/test/MC/LoongArch/**

.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 && \

CONTRIBUTING.md

@@ -9,9 +9,8 @@ describes how to get involved, raise issues and submit patches.
 
 ## Getting in touch
 
-Join the [LLVM Discourse forums](https://discourse.llvm.org/), [Discord
-chat](https://discord.gg/xS7Z362), or #llvm IRC channel on
-[OFTC](https://oftc.net/).
+Join the [LLVM Discourse forums](https://discourse.llvm.org/) or [Discord
+chat](https://discord.gg/xS7Z362).
 
 The LLVM project has adopted a [code of conduct](https://llvm.org/docs/CodeOfConduct.html) for
 participants to all modes of communication within the project.

bolt/Maintainers.txt

@@ -5,9 +5,8 @@ what goes in or not.
 
 The list is sorted by surname and formatted to allow easy grepping and
 beautification by scripts. The fields are: name (N), email (E), web-address
-(W), PGP key ID and fingerprint (P), description (D), snail-mail address
-(S) and (I) IRC handle. Each entry should contain at least the (N), (E) and
-(D) fields.
+(W), PGP key ID and fingerprint (P), and description (D). Each entry should
+contain at least the (N), (E) and (D) fields.
 
 N: Maksim Panchenko, Rafael Auler
 E: [email protected], [email protected]

bolt/include/bolt/Core/BinaryContext.h

@@ -1499,7 +1499,7 @@ class BinaryContext {
     MCEInstance.LocalCtx.reset(
         new MCContext(*TheTriple, AsmInfo.get(), MRI.get(), STI.get()));
     MCEInstance.LocalMOFI.reset(
-        TheTarget->createMCObjectFileInfo(*MCEInstance.LocalCtx.get(),
+        TheTarget->createMCObjectFileInfo(*MCEInstance.LocalCtx,
                                           /*PIC=*/!HasFixedLoadAddress));
     MCEInstance.LocalCtx->setObjectFileInfo(MCEInstance.LocalMOFI.get());
     MCEInstance.MCE.reset(

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.
   };
 
@@ -360,6 +360,11 @@ class BinaryFunction {
   /// True if the function is used for patching code at a fixed address.
   bool IsPatch{false};
 
+  /// True if the original entry point of the function may get called, but the
+  /// original body cannot be executed and needs to be patched with code that
+  /// redirects execution to the new function body.
+  bool NeedsPatch{false};
+
   /// True if the function should not have an associated symbol table entry.
   bool IsAnonymous{false};
 
@@ -387,7 +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};
@@ -862,15 +867,15 @@ class BinaryFunction {
   /// Returns if BinaryDominatorTree has been constructed for this function.
   bool hasDomTree() const { return BDT != nullptr; }
 
-  BinaryDominatorTree &getDomTree() { return *BDT.get(); }
+  BinaryDominatorTree &getDomTree() { return *BDT; }
 
   /// Constructs DomTree for this function.
   void constructDomTree();
 
   /// Returns if loop detection has been run for this function.
   bool hasLoopInfo() const { return BLI != nullptr; }
 
-  const BinaryLoopInfo &getLoopInfo() { return *BLI.get(); }
+  const BinaryLoopInfo &getLoopInfo() { return *BLI; }
 
   bool isLoopFree() {
     if (!hasLoopInfo())
@@ -1372,6 +1377,9 @@ class BinaryFunction {
   /// Return true if this function is used for patching existing code.
   bool isPatch() const { return IsPatch; }
 
+  /// Return true if the function requires a patch.
+  bool needsPatch() const { return NeedsPatch; }
+
   /// Return true if the function should not have associated symbol table entry.
   bool isAnonymous() const { return IsAnonymous; }
 
@@ -1757,6 +1765,9 @@ class BinaryFunction {
     IsPatch = V;
   }
 
+  /// Mark the function for patching.
+  void setNeedsPatch(bool V) { NeedsPatch = V; }
+
   /// Indicate if the function should have a name in the symbol table.
   void setAnonymous(bool V) {
     assert(isInjected() && "Only injected functions could be anonymous");
@@ -1882,11 +1893,11 @@ 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/DIEBuilder.h

@@ -137,7 +137,7 @@ class DIEBuilder {
   std::unordered_map<std::string, uint32_t> NameToIndexMap;
 
   /// Returns current state of the DIEBuilder
-  State &getState() { return *BuilderState.get(); }
+  State &getState() { return *BuilderState; }
 
   /// Resolve the reference in DIE, if target is not loaded into IR,
   /// pre-allocate it. \p RefCU will be updated to the Unit specific by \p

bolt/include/bolt/Passes/FrameAnalysis.h

@@ -10,6 +10,7 @@
 #define BOLT_PASSES_FRAMEANALYSIS_H
 
 #include "bolt/Passes/StackPointerTracking.h"
+#include <tuple>
 
 namespace llvm {
 namespace bolt {
@@ -53,9 +54,7 @@ struct ArgInStackAccess {
   uint8_t Size;
 
   bool operator<(const ArgInStackAccess &RHS) const {
-    if (StackOffset != RHS.StackOffset)
-      return StackOffset < RHS.StackOffset;
-    return Size < RHS.Size;
+    return std::tie(StackOffset, Size) < std::tie(RHS.StackOffset, RHS.Size);
   }
 };
 

bolt/include/bolt/Passes/PAuthGadgetScanner.h

@@ -43,9 +43,7 @@ struct MCInstInBBReference {
     return BB == RHS.BB && BBIndex == RHS.BBIndex;
   }
   bool operator<(const MCInstInBBReference &RHS) const {
-    if (BB != RHS.BB)
-      return BB < RHS.BB;
-    return BBIndex < RHS.BBIndex;
+    return std::tie(BB, BBIndex) < std::tie(RHS.BB, RHS.BBIndex);
   }
   operator MCInst &() const {
     assert(BB != nullptr);

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;