Merge branch 'main' into remove_is_nullptr

Author: philnik777

.git-blame-ignore-revs

@@ -84,3 +84,6 @@ b9079baaddfed5e604fbfaa1d81a7a1c38e78c26
 
 # [libc++][NFC] Run clang-format on libcxx/include again (#95874)
 e2c2ffbe7a1b5d9e32a2ce64279475b50c4cba5b
+
+# [lldb][nfc] Deindent ProcessGDBRemote::SetThreadStopInfo by two levels
+b32931c5b32eb0d2cf37d688b34f8548c9674c19

.github/CODEOWNERS

@@ -67,11 +67,11 @@ clang/test/AST/Interp/ @tbaederr
 /mlir/include/mlir/Dialect/Linalg @dcaballe @nicolasvasilache @rengolin
 /mlir/lib/Dialect/Linalg @dcaballe @nicolasvasilache @rengolin
 /mlir/lib/Dialect/Linalg/Transforms/DecomposeLinalgOps.cpp @MaheshRavishankar @nicolasvasilache
-/mlir/lib/Dialect/Linalg/Transforms/DropUnitDims.cpp @MaheshRavishankar @nicolasvasilache
+/mlir/lib/Dialect/Linalg/Transforms/DropUnitDims.cpp @dcaballe @MaheshRavishankar @nicolasvasilache
 /mlir/lib/Dialect/Linalg/Transforms/ElementwiseOpFusion.cpp @MaheshRavishankar @nicolasvasilache
 /mlir/lib/Dialect/Linalg/Transforms/DataLayoutPropagation.cpp @hanhanW @nicolasvasilache
-/mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp @hanhanW @nicolasvasilache
-/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp @hanhanW @nicolasvasilache
+/mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp @dcaballe @hanhanW @nicolasvasilache
+/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp @banach-space @dcaballe @hanhanW @nicolasvasilache
 
 # MemRef Dialect in MLIR.
 /mlir/lib/Dialect/MemRef/Transforms/EmulateNarrowType.cpp @MaheshRavishankar @nicolasvasilache
@@ -85,10 +85,11 @@ clang/test/AST/Interp/ @tbaederr
 /mlir/**/*VectorToSCF* @banach-space @dcaballe @matthias-springer @nicolasvasilache
 /mlir/**/*VectorToLLVM* @banach-space @dcaballe @nicolasvasilache
 /mlir/**/*X86Vector* @aartbik @dcaballe @nicolasvasilache
-/mlir/include/mlir/Dialect/Vector @dcaballe @nicolasvasilache
-/mlir/lib/Dialect/Vector @dcaballe @nicolasvasilache
-/mlir/lib/Dialect/Vector/Transforms/* @hanhanW @nicolasvasilache
-/mlir/lib/Dialect/Vector/Transforms/VectorEmulateNarrowType.cpp @MaheshRavishankar @nicolasvasilache
+/mlir/include/mlir/Dialect/Vector @banach-space @dcaballe @nicolasvasilache
+/mlir/include/mlir/Dialect/Vector/IR @kuhar
+/mlir/lib/Dialect/Vector @banach-space @dcaballe @nicolasvasilache
+/mlir/lib/Dialect/Vector/Transforms/* @banach-space @dcaballe @hanhanW @nicolasvasilache
+/mlir/lib/Dialect/Vector/Transforms/VectorEmulateNarrowType.cpp @banach-space @dcaballe @MaheshRavishankar @nicolasvasilache
 /mlir/**/*EmulateNarrowType* @dcaballe @hanhanW
 
 # Presburger library in MLIR

.github/workflows/issue-write.yml

@@ -24,14 +24,21 @@ jobs:
         github.event.workflow_run.conclusion == 'failure'
       )
     steps:
+      - name: Fetch Sources
+        uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            .github/workflows/unprivileged-download-artifact/action.yml
+          sparse-checkout-cone-mode: false
       - name: 'Download artifact'
-        uses: actions/download-artifact@6b208ae046db98c579e8a3aa621ab581ff575935 # v4.1.1
+        uses: ./.github/workflows/unprivileged-download-artifact
+        id: download-artifact
         with:
-          github-token: ${{ secrets.ISSUE_WRITE_DOWNLOAD_ARTIFACT }}
           run-id: ${{ github.event.workflow_run.id }}
-          name: workflow-args
+          artifact-name: workflow-args
 
       - name: 'Comment on PR'
+        if: steps.download-artifact.outputs.artifact-id != ''
         uses: actions/github-script@v3
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -144,5 +151,7 @@ jobs:
             });
 
       - name: Dump comments file
-        if: always()
+        if: >-
+          always() &&
+          steps.download-artifact.outputs.artifact-id != ''
         run: cat comments

.github/workflows/unprivileged-download-artifact/action.yml

@@ -0,0 +1,81 @@
+name: Unprivileged Download Artifact
+description: >-
+  Download artifacts from another workflow run without using an access token.
+inputs:
+  run-id:
+    description: >-
+      The run-id for the workflow run that you want to download the artifact
+      from.  If ommitted it will download the most recently created artifact
+      from the repo with the artifact-name.
+    required: false
+  artifact-name:
+    desciption: The name of the artifact to download.
+    required: true
+
+
+outputs:
+  filename:
+    description: >-
+      The filename of the downloaded artifact or the empty string if the
+      artifact was not found.
+    value: ${{ steps.download-artifact.outputs.filename }}
+  artifact-id:
+    description: "The id of the artifact being downloaded."
+    value: ${{ steps.artifact-url.outputs.id }}
+
+
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea #v7.0.1
+      id: artifact-url
+      with:
+        script: |
+          var response;
+          if (!"${{ inputs.run-id }}") {
+            response = await github.rest.actions.listArtifactsForRepo({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              name: "${{ inputs.artifact-name }}"
+            })
+          } else {
+            response = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: "${{ inputs.run-id }}",
+              name: "${{ inputs.artifact-name }}"
+            })
+          }
+
+          console.log(response)
+
+          for (artifact of response.data.artifacts) {
+            console.log(artifact);
+          }
+
+          if (response.data.artifacts.length == 0) {
+            console.log("Could not find artifact ${{ inputs.artifact-name }} for workflow run ${{ inputs.run-id }}")
+            return;
+          }
+
+          const url_response = await github.rest.actions.downloadArtifact({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            artifact_id: response.data.artifacts[0].id,
+            archive_format: "zip"
+          })
+
+          core.setOutput("url", url_response.url);
+          core.setOutput("id", response.data.artifacts[0].id);
+
+    - shell: bash
+      if: steps.artifact-url.outputs.url != ''
+      id: download-artifact
+      run: |
+        curl -L -o ${{ inputs.artifact-name }}.zip "${{ steps.artifact-url.outputs.url }}"
+        echo "filename=${{ inputs.artifact-name }}.zip" >> $GITHUB_OUTPUT
+
+    - shell: bash
+      if: steps.download-artifact.outputs.filename != ''
+      run: |
+        unzip ${{ steps.download-artifact.outputs.filename }}

.github/workflows/version-check.yml

@@ -27,5 +27,5 @@ jobs:
 
       - name: Version Check
         run: |
-          version=$(grep -o 'LLVM_VERSION_\(MAJOR\|MINOR\|PATCH\) [0-9]\+' llvm/CMakeLists.txt  | cut -d ' ' -f 2 | tr "\n" "." | sed 's/.$//g')
+          version=$(grep -o 'LLVM_VERSION_\(MAJOR\|MINOR\|PATCH\) [0-9]\+' cmake/Modules/LLVMVersion.cmake  | cut -d ' ' -f 2 | tr "\n" "." | sed 's/.$//g')
           .github/workflows/version-check.py "$version"

bolt/docs/CommandLineArgumentReference.md

@@ -88,7 +88,7 @@
 
 - `--comp-dir-override=<string>`
 
-  Overrides DW_AT_comp_dir, and provides an alterantive base location, which is
+  Overrides DW_AT_comp_dir, and provides an alternative base location, which is
   used with DW_AT_dwo_name to construct a path to *.dwo files.
 
 - `--create-debug-names-section`
@@ -113,11 +113,6 @@
 
   Prints out offsets for abbrev and debug_info of Skeleton CUs that get patched.
 
-- `--deterministic-debuginfo`
-
-  Disables parallel execution of tasks that may produce nondeterministic debug
-  info
-
 - `--dot-tooltip-code`
 
   Add basic block instructions as tool tips on nodes
@@ -686,6 +681,10 @@
   threshold means fewer functions to process. E.g threshold of 90 means only top
   10 percent of functions with profile will be processed.
 
+- `--match-with-call-graph`
+
+  Match functions with call graph
+
 - `--memcpy1-spec=<func1,func2:cs1:cs2,func3:cs1,...>`
 
   List of functions with call sites for which to specialize memcpy() for size 1

bolt/docs/OptimizingClang.md

@@ -49,6 +49,7 @@ $ cd ${TOPLEV}/stage3
 $ CPATH=${TOPLEV}/stage2-prof-use-lto/install/bin/
 $ cmake -G Ninja ${TOPLEV}/llvm -DLLVM_TARGETS_TO_BUILD=X86 -DCMAKE_BUILD_TYPE=Release \
     -DCMAKE_C_COMPILER=$CPATH/clang -DCMAKE_CXX_COMPILER=$CPATH/clang++ \
+    -DLLVM_ENABLE_PROJECTS="clang" \
     -DLLVM_USE_LINKER=lld -DCMAKE_INSTALL_PREFIX=${TOPLEV}/stage3/install
 $ perf record -e cycles:u -j any,u -- ninja clang
 ```

bolt/docs/generate_doc.py

@@ -45,7 +45,7 @@ def parse_bolt_options(output):
         cleaned_line = line.strip()
 
         if cleaned_line.casefold() in map(str.casefold, section_headers):
-            if prev_section != None:  # Save last option from prev section
+            if prev_section is not None:  # Save last option from prev section
                 add_info(sections, current_section, option, description)
                 option, description = None, []
 
@@ -76,7 +76,7 @@ def parse_bolt_options(output):
                 description = [descr]
                 if option.startswith("--print") or option.startswith("--time"):
                     current_section = "BOLT printing options:"
-                elif prev_section != None:
+                elif prev_section is not None:
                     current_section = prev_section
             continue
 

bolt/include/bolt/Core/BinaryContext.h

@@ -23,6 +23,7 @@
 #include "bolt/RuntimeLibs/RuntimeLibrary.h"
 #include "llvm/ADT/AddressRanges.h"
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/EquivalenceClasses.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/iterator.h"
 #include "llvm/BinaryFormat/Dwarf.h"
@@ -32,6 +33,7 @@
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCObjectFileInfo.h"
 #include "llvm/MC/MCObjectWriter.h"
+#include "llvm/MC/MCPseudoProbe.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCSectionMachO.h"
 #include "llvm/MC/MCStreamer.h"
@@ -240,12 +242,19 @@ class BinaryContext {
   /// Function fragments to skip.
   std::unordered_set<BinaryFunction *> FragmentsToSkip;
 
+  /// Fragment equivalence classes to query belonging to the same "family" in
+  /// presence of multiple fragments/multiple parents.
+  EquivalenceClasses<const BinaryFunction *> FragmentClasses;
+
   /// The runtime library.
   std::unique_ptr<RuntimeLibrary> RtLibrary;
 
   /// DWP Context.
   std::shared_ptr<DWARFContext> DWPContext;
 
+  /// Decoded pseudo probes.
+  std::shared_ptr<MCPseudoProbeDecoder> PseudoProbeDecoder;
+
   /// A map of DWO Ids to CUs.
   using DWOIdToCUMapType = std::unordered_map<uint64_t, DWARFUnit *>;
   DWOIdToCUMapType DWOCUs;
@@ -377,6 +386,15 @@ class BinaryContext {
     RtLibrary = std::move(Lib);
   }
 
+  const MCPseudoProbeDecoder *getPseudoProbeDecoder() const {
+    return PseudoProbeDecoder.get();
+  }
+
+  void setPseudoProbeDecoder(std::shared_ptr<MCPseudoProbeDecoder> Decoder) {
+    assert(!PseudoProbeDecoder && "Cannot set pseudo probe decoder twice.");
+    PseudoProbeDecoder = Decoder;
+  }
+
   /// Return BinaryFunction containing a given \p Address or nullptr if
   /// no registered function contains the \p Address.
   ///
@@ -431,6 +449,9 @@ class BinaryContext {
     return nullptr;
   }
 
+  /// Deregister JumpTable registered at a given \p Address and delete it.
+  void deleteJumpTable(uint64_t Address);
+
   unsigned getDWARFEncodingSize(unsigned Encoding) {
     if (Encoding == dwarf::DW_EH_PE_omit)
       return 0;
@@ -1016,7 +1037,15 @@ class BinaryContext {
   ///   fragment_name == parent_name.cold(.\d+)?
   /// True if the Function is registered, false if the check failed.
   bool registerFragment(BinaryFunction &TargetFunction,
-                        BinaryFunction &Function) const;
+                        BinaryFunction &Function);
+
+  /// Return true if two functions belong to the same "family": are fragments
+  /// of one another, or fragments of the same parent, or transitively fragment-
+  /// related.
+  bool areRelatedFragments(const BinaryFunction *LHS,
+                           const BinaryFunction *RHS) const {
+    return FragmentClasses.isEquivalent(LHS, RHS);
+  }
 
   /// Add interprocedural reference for \p Function to \p Address
   void addInterproceduralReference(BinaryFunction *Function, uint64_t Address) {
@@ -1436,10 +1465,7 @@ class BinaryContext {
     std::unique_ptr<MCObjectWriter> OW = MAB->createObjectWriter(OS);
     std::unique_ptr<MCStreamer> Streamer(TheTarget->createMCObjectStreamer(
         *TheTriple, *Ctx, std::unique_ptr<MCAsmBackend>(MAB), std::move(OW),
-        std::unique_ptr<MCCodeEmitter>(MCE), *STI,
-        /* RelaxAll */ false,
-        /* IncrementalLinkerCompatible */ false,
-        /* DWARFMustBeAtTheEnd */ false));
+        std::unique_ptr<MCCodeEmitter>(MCE), *STI));
     return Streamer;
   }
 

bolt/include/bolt/Core/BinaryFunction.h

@@ -416,6 +416,9 @@ class BinaryFunction {
   /// different parameters by every pass.
   mutable uint64_t Hash{0};
 
+  /// Function GUID assigned externally.
+  uint64_t GUID{0};
+
   /// For PLT functions it contains a symbol associated with a function
   /// reference. It is nullptr for non-PLT functions.
   const MCSymbol *PLTSymbol{nullptr};
@@ -1790,11 +1793,6 @@ class BinaryFunction {
     return ParentFragments.contains(&Other);
   }
 
-  /// Returns if this function is a parent of \p Other function.
-  bool isParentOf(const BinaryFunction &Other) const {
-    return Fragments.contains(&Other);
-  }
-
   /// Return the child fragment form parent function
   iterator_range<FragmentsSetTy::const_iterator> getFragments() const {
     return iterator_range<FragmentsSetTy::const_iterator>(Fragments.begin(),
@@ -1804,11 +1802,6 @@ class BinaryFunction {
   /// Return the parent function for split function fragments.
   FragmentsSetTy *getParentFragments() { return &ParentFragments; }
 
-  /// Returns if this function is a parent or child of \p Other function.
-  bool isParentOrChildOf(const BinaryFunction &Other) const {
-    return isChildOf(Other) || isParentOf(Other);
-  }
-
   /// Set the profile data for the number of times the function was called.
   BinaryFunction &setExecutionCount(uint64_t Count) {
     ExecutionCount = Count;
@@ -2256,6 +2249,11 @@ class BinaryFunction {
   /// Returns the last computed hash value of the function.
   size_t getHash() const { return Hash; }
 
+  /// Returns the function GUID.
+  uint64_t getGUID() const { return GUID; }
+
+  void setGUID(uint64_t Id) { GUID = Id; }
+
   using OperandHashFuncTy =
       function_ref<typename std::string(const MCOperand &)>;
 

bolt/include/bolt/Core/DIEBuilder.h

@@ -135,13 +135,6 @@ class DIEBuilder {
 
   /// Returns current state of the DIEBuilder
   State &getState() { return *BuilderState.get(); }
-  /// 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
-  /// RefValue.
-  DWARFDie resolveDIEReference(
-      const DWARFFormValue &RefValue,
-      const DWARFAbbreviationDeclaration::AttributeSpec AttrSpec,
-      DWARFUnit *&RefCU, DWARFDebugInfoEntry &DwarfDebugInfoEntry);
 
   /// 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
@@ -165,10 +158,9 @@ class DIEBuilder {
       const DWARFFormValue &Val);
 
   /// Clone an attribute in reference format.
-  void cloneDieReferenceAttribute(
+  void cloneDieOffsetReferenceAttribute(
       DIE &Die, const DWARFUnit &U, const DWARFDie &InputDIE,
-      const DWARFAbbreviationDeclaration::AttributeSpec AttrSpec,
-      const DWARFFormValue &Val);
+      const DWARFAbbreviationDeclaration::AttributeSpec AttrSpec, uint64_t Ref);
 
   /// Clone an attribute in block format.
   void cloneBlockAttribute(