LLVM and SPIRV-LLVM-Translator pulldown (WW32)

LLVM: llvm/llvm-project@920c461
SPIRV-LLVM-Translator: KhronosGroup/SPIRV-LLVM-Translator@bb2196b

.ci/generate-buildkite-pipeline-premerge

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+#===----------------------------------------------------------------------===##
+#
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+#
+#===----------------------------------------------------------------------===##
+
+#
+# This file generates a Buildkite pipeline that triggers the various CI jobs for
+# the LLVM project during pre-commit CI (each time a Phabricator diff is uploaded).
+#
+# See https://buildkite.com/docs/agent/v3/cli-pipeline#pipeline-format.
+#
+
+if ! git diff --name-only HEAD~1 | grep -q -E "^libcxx/|^libcxxabi/|^libunwind/|^runtimes/|^cmake/|^clang/"; then
+  # libcxx/, libcxxabi/, libunwind/, runtimes/, cmake/ or clang/ are not affected
+  exit 0
+fi
+
+reviewID="$(git log --format=%B -n 1 | sed -nE 's/^Review-ID:[[:space:]]*(.+)$/\1/p')"
+if [[ "${reviewID}" != "" ]]; then
+  buildMessage="https://llvm.org/${reviewID}"
+else
+  buildMessage="Push to branch ${BUILDKITE_BRANCH}"
+fi
+
+cat <<EOF
+steps:
+EOF
+
+# If libc++ or one of the runtimes directories changed
+if git diff --name-only HEAD~1 | grep -q -E "^libcxx/|^libcxxabi/|^libunwind/|^runtimes/|^cmake/"; then
+  cat <<EOF
+  - trigger: "libcxx-ci"
+    build:
+      message: "${buildMessage}"
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+EOF
+fi
+
+# If clang changed
+if git diff --name-only HEAD~1 | grep -q -E "^clang/"; then
+  cat <<EOF
+  - trigger: "clang-ci"
+    build:
+      message: "${buildMessage}"
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+EOF
+fi

.ci/generate-buildkite-pipeline-scheduled

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+#===----------------------------------------------------------------------===##
+#
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+#
+#===----------------------------------------------------------------------===##
+
+#
+# This file generates a Buildkite pipeline that triggers the various CI jobs for
+# the LLVM project on scheduled builds.
+#
+# See https://buildkite.com/docs/agent/v3/cli-pipeline#pipeline-format.
+#
+
+cat <<EOF
+steps:
+  - trigger: "libcxx-ci"
+    build:
+      message: "${BUILDKITE_MESSAGE}"
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+
+  - trigger: "clang-ci"
+    build:
+      message: "${BUILDKITE_MESSAGE}"
+      commit: "${BUILDKITE_COMMIT}"
+      branch: "${BUILDKITE_BRANCH}"
+EOF

.git-blame-ignore-revs

@@ -58,3 +58,9 @@ f9008e6366c2496b1ca1785b891d5578174ad63e
 
 # [libc++][NFC] Apply clang-format on large parts of the code base
 5aa03b648b827128d439f705cd7d57d59673741d
+
+# [clang][NFC] Remove trailing whitespaces and enforce it in lib, include and docs
+f6d557ee34b6bbdb1dc32f29e34b4a4a8ad35e81
+
+# [libc++][NFC] clang-format <shared_mutex>
+2d7eb9c9ea1a146412a83603d5c0c6339a5d8284

.github/workflows/closed-issues.yml

@@ -1,7 +1,8 @@
 name: Labeling closed issues
 on:
-  issues:
-    types: ['closed']
+  workflow_dispatch
+#  issues:
+#    types: ['closed']
 
 permissions:
   contents: read

.github/workflows/release-tasks.yml

@@ -84,7 +84,7 @@ jobs:
         uses: actions/checkout@v3
 
       - name: Install dependencies
-        run: apt-get install -y python3-setuptools
+        run: sudo apt-get install -y python3-setuptools
 
       - name: Test lit
         run: |

.github/workflows/repo-lockdown.yml

@@ -7,6 +7,13 @@ on:
       - 'libcxxabi/**'
       - 'libunwind/**'
       - 'runtimes/**'
+      - 'lldb/**'
+      - '.github/**'
+      - 'clang/lib/Format/**'
+      - 'clang/include/clang/Format/**'
+      - 'clang/docs/**'
+      - 'clang/unitests/Format/**'
+      - 'clang/tools/clang-format/**'
 
 permissions:
   pull-requests: write

bolt/include/bolt/Core/BinaryBasicBlock.h

@@ -103,7 +103,7 @@ class BinaryBasicBlock {
   /// After output/codegen, map output offsets of instructions in this basic
   /// block to instruction offsets in the original function. Note that the
   /// output basic block could be different from the input basic block.
-  /// We only map instruction of interest, such as calls, and sdt markers.
+  /// We only map instruction of interest, such as calls and markers.
   ///
   /// We store the offset array in a basic block to facilitate BAT tables
   /// generation. Otherwise, the mapping could be done at function level.

bolt/include/bolt/Core/BinaryContext.h

@@ -29,7 +29,6 @@
 #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"
@@ -639,9 +638,22 @@ class BinaryContext {
   /// Total hotness score according to profiling data for this binary.
   uint64_t TotalScore{0};
 
-  /// Binary-wide stats for macro-fusion.
-  uint64_t MissedMacroFusionPairs{0};
-  uint64_t MissedMacroFusionExecCount{0};
+  /// Binary-wide aggregated stats.
+  struct BinaryStats {
+    /// Stats for macro-fusion.
+    uint64_t MissedMacroFusionPairs{0};
+    uint64_t MissedMacroFusionExecCount{0};
+
+    /// Stats for stale profile matching:
+    ///   the total number of basic blocks in the profile
+    uint32_t NumStaleBlocks{0};
+    ///   the number of matched basic blocks
+    uint32_t NumMatchedBlocks{0};
+    ///   the total count of samples in the profile
+    uint64_t StaleSampleCount{0};
+    ///   the count of matched samples
+    uint64_t MatchedSampleCount{0};
+  } Stats;
 
   // Address of the first allocated segment.
   uint64_t FirstAllocAddress{std::numeric_limits<uint64_t>::max()};
@@ -673,20 +685,10 @@ class BinaryContext {
   /// List of functions that always trap.
   std::vector<const BinaryFunction *> TrappedFunctions;
 
-  /// Map SDT locations to SDT markers info
-  std::unordered_map<uint64_t, SDTMarkerInfo> SDTMarkers;
-
-  /// Map linux kernel program locations/instructions to their pointers in
-  /// special linux kernel sections
-  std::unordered_map<uint64_t, std::vector<LKInstructionMarkerInfo>> LKMarkers;
-
   /// List of external addresses in the code that are not a function start
   /// and are referenced from BinaryFunction.
   std::list<std::pair<BinaryFunction *, uint64_t>> InterproceduralReferences;
 
-  /// PseudoProbe decoder
-  MCPseudoProbeDecoder ProbeDecoder;
-
   /// DWARF encoding. Available encoding types defined in BinaryFormat/Dwarf.h
   /// enum Constants, e.g. DW_EH_PE_omit.
   unsigned LSDAEncoding = dwarf::DW_EH_PE_omit;

bolt/include/bolt/Core/BinaryFunction.h

@@ -339,6 +339,9 @@ class BinaryFunction {
   bool HasPseudoProbe{BC.getUniqueSectionByName(".pseudo_probe_desc") &&
                       BC.getUniqueSectionByName(".pseudo_probe")};
 
+  /// True if the function uses ORC format for stack unwinding.
+  bool HasORC{false};
+
   /// True if the original entry point was patched.
   bool IsPatched{false};
 
@@ -378,7 +381,7 @@ class BinaryFunction {
   /// Profile match ratio.
   float ProfileMatchRatio{0.0f};
 
-  /// Raw branch count for this function in the profile
+  /// Raw branch count for this function in the profile.
   uint64_t RawBranchCount{0};
 
   /// Indicates the type of profile the function is using.
@@ -423,21 +426,6 @@ class BinaryFunction {
     return BB->getIndex();
   }
 
-  /// Return basic block that originally contained offset \p Offset
-  /// from the function start.
-  BinaryBasicBlock *getBasicBlockContainingOffset(uint64_t Offset);
-
-  const BinaryBasicBlock *getBasicBlockContainingOffset(uint64_t Offset) const {
-    return const_cast<BinaryFunction *>(this)->getBasicBlockContainingOffset(
-        Offset);
-  }
-
-  /// Return basic block that started at offset \p Offset.
-  BinaryBasicBlock *getBasicBlockAtOffset(uint64_t Offset) {
-    BinaryBasicBlock *BB = getBasicBlockContainingOffset(Offset);
-    return BB && BB->getOffset() == Offset ? BB : nullptr;
-  }
-
   /// Release memory taken by the list.
   template <typename T> BinaryFunction &clearList(T &List) {
     T TempList;
@@ -619,10 +607,6 @@ class BinaryFunction {
     Islands->CodeOffsets.emplace(Offset);
   }
 
-  /// Register secondary entry point at a given \p Offset into the function.
-  /// Return global symbol for use by extern function references.
-  MCSymbol *addEntryPointAtOffset(uint64_t Offset);
-
   /// Register an internal offset in a function referenced from outside.
   void registerReferencedOffset(uint64_t Offset) {
     ExternallyReferencedOffsets.emplace(Offset);
@@ -900,6 +884,21 @@ class BinaryFunction {
     return LabelToBB.lookup(Label);
   }
 
+  /// Return basic block that originally contained offset \p Offset
+  /// from the function start.
+  BinaryBasicBlock *getBasicBlockContainingOffset(uint64_t Offset);
+
+  const BinaryBasicBlock *getBasicBlockContainingOffset(uint64_t Offset) const {
+    return const_cast<BinaryFunction *>(this)->getBasicBlockContainingOffset(
+        Offset);
+  }
+
+  /// Return basic block that started at offset \p Offset.
+  BinaryBasicBlock *getBasicBlockAtOffset(uint64_t Offset) {
+    BinaryBasicBlock *BB = getBasicBlockContainingOffset(Offset);
+    return BB && BB->getOffset() == Offset ? BB : nullptr;
+  }
+
   /// Retrieve the landing pad BB associated with invoke instruction \p Invoke
   /// that is in \p BB. Return nullptr if none exists
   BinaryBasicBlock *getLandingPadBBFor(const BinaryBasicBlock &BB,
@@ -1344,6 +1343,9 @@ class BinaryFunction {
   /// Return true if the function has Pseudo Probe
   bool hasPseudoProbe() const { return HasPseudoProbe; }
 
+  /// Return true if the function uses ORC format for stack unwinding.
+  bool hasORC() const { return HasORC; }
+
   /// Return true if the original entry point was patched.
   bool isPatched() const { return IsPatched; }
 
@@ -1445,6 +1447,10 @@ class BinaryFunction {
   /// symbol associated with the entry.
   MCSymbol *addEntryPoint(const BinaryBasicBlock &BB);
 
+  /// Register secondary entry point at a given \p Offset into the function.
+  /// Return global symbol for use by extern function references.
+  MCSymbol *addEntryPointAtOffset(uint64_t Offset);
+
   /// Mark all blocks that are unreachable from a root (entry point
   /// or landing pad) as invalid.
   void markUnreachableBlocks();
@@ -1702,6 +1708,11 @@ class BinaryFunction {
   /// Indicate that another function body was merged with this function.
   void setHasFunctionsFoldedInto() { HasFunctionsFoldedInto = true; }
 
+  void setHasSDTMarker(bool V) { HasSDTMarker = V; }
+
+  /// Mark the function as using ORC format for stack unwinding.
+  void setHasORC(bool V) { HasORC = V; }
+
   BinaryFunction &setPersonalityFunction(uint64_t Addr) {
     assert(!PersonalityFunction && "can't set personality function twice");
     PersonalityFunction = BC.getOrCreateGlobalSymbol(Addr, "FUNCat");

bolt/include/bolt/Core/BinarySection.h

@@ -509,27 +509,6 @@ inline raw_ostream &operator<<(raw_ostream &OS, const BinarySection &Section) {
   return OS;
 }
 
-struct SDTMarkerInfo {
-  uint64_t PC;
-  uint64_t Base;
-  uint64_t Semaphore;
-  StringRef Provider;
-  StringRef Name;
-  StringRef Args;
-
-  /// The offset of PC within the note section
-  unsigned PCOffset;
-};
-
-/// Linux Kernel special sections point to a specific instruction in many cases.
-/// Unlike SDTMarkerInfo, these markers can come from different sections.
-struct LKInstructionMarkerInfo {
-  uint64_t SectionOffset;
-  int32_t PCRelativeOffset;
-  bool IsPCRelative;
-  StringRef SectionName;
-};
-
 } // namespace bolt
 } // namespace llvm