[AutoBump] Merge with 235d6841 (17)

.ci/monolithic-linux.sh

@@ -18,7 +18,7 @@ set -o pipefail
 
 MONOREPO_ROOT="${MONOREPO_ROOT:="$(git rev-parse --show-toplevel)"}"
 BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
-rm -rf ${BUILD_DIR}
+rm -rf "${BUILD_DIR}"
 
 ccache --zero-stats
 
@@ -37,8 +37,8 @@ projects="${1}"
 targets="${2}"
 
 echo "--- cmake"
-pip install -q -r ${MONOREPO_ROOT}/mlir/python/requirements.txt
-cmake -S ${MONOREPO_ROOT}/llvm -B ${BUILD_DIR} \
+pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
+cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_PROJECTS="${projects}" \
       -G Ninja \
       -D CMAKE_BUILD_TYPE=Release \

.ci/monolithic-windows.sh

@@ -19,7 +19,7 @@ set -o pipefail
 MONOREPO_ROOT="${MONOREPO_ROOT:="$(git rev-parse --show-toplevel)"}"
 BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
 
-rm -rf ${BUILD_DIR}
+rm -rf "${BUILD_DIR}"
 
 if [[ -n "${CLEAR_CACHE:-}" ]]; then
   echo "clearing sccache"
@@ -37,14 +37,14 @@ projects="${1}"
 targets="${2}"
 
 echo "--- cmake"
-pip install -q -r ${MONOREPO_ROOT}/mlir/python/requirements.txt
+pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
 
 # The CMAKE_*_LINKER_FLAGS to disable the manifest come from research
 # on fixing a build reliability issue on the build server, please
 # see https://github.com/llvm/llvm-project/pull/82393 and
 # https://discourse.llvm.org/t/rfc-future-of-windows-pre-commit-ci/76840/40
 # for further information.
-cmake -S ${MONOREPO_ROOT}/llvm -B ${BUILD_DIR} \
+cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_PROJECTS="${projects}" \
       -G Ninja \
       -D CMAKE_BUILD_TYPE=Release \

.github/workflows/scorecard.yml

@@ -36,7 +36,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@e38b1902ae4f44df626f11ba0734b14fb91f8f86 # v2.1.2
+        uses: ossf/scorecard-action@0864cf19026789058feabb7e87baa5f140aac736 # v2.3.1
         with:
           results_file: results.sarif
           results_format: sarif

bolt/lib/Core/BinaryFunction.cpp

@@ -3547,7 +3547,7 @@ MCSymbol *BinaryFunction::getSymbolForEntryID(uint64_t EntryID) {
   if (!isMultiEntry())
     return nullptr;
 
-  uint64_t NumEntries = 0;
+  uint64_t NumEntries = 1;
   if (hasCFG()) {
     for (BinaryBasicBlock *BB : BasicBlocks) {
       MCSymbol *EntrySymbol = getSecondaryEntryPointSymbol(*BB);
@@ -3580,7 +3580,7 @@ uint64_t BinaryFunction::getEntryIDForSymbol(const MCSymbol *Symbol) const {
       return 0;
 
   // Check all secondary entries available as either basic blocks or lables.
-  uint64_t NumEntries = 0;
+  uint64_t NumEntries = 1;
   for (const BinaryBasicBlock *BB : BasicBlocks) {
     MCSymbol *EntrySymbol = getSecondaryEntryPointSymbol(*BB);
     if (!EntrySymbol)
@@ -3589,7 +3589,7 @@ uint64_t BinaryFunction::getEntryIDForSymbol(const MCSymbol *Symbol) const {
       return NumEntries;
     ++NumEntries;
   }
-  NumEntries = 0;
+  NumEntries = 1;
   for (const std::pair<const uint32_t, MCSymbol *> &KV : Labels) {
     MCSymbol *EntrySymbol = getSecondaryEntryPointSymbol(KV.second);
     if (!EntrySymbol)

bolt/lib/Profile/YAMLProfileWriter.cpp

@@ -25,6 +25,25 @@ extern llvm::cl::opt<bool> ProfileUseDFS;
 namespace llvm {
 namespace bolt {
 
+/// Set CallSiteInfo destination fields from \p Symbol and return a target
+/// BinaryFunction for that symbol.
+static const BinaryFunction *setCSIDestination(const BinaryContext &BC,
+                                               yaml::bolt::CallSiteInfo &CSI,
+                                               const MCSymbol *Symbol) {
+  CSI.DestId = 0; // designated for unknown functions
+  CSI.EntryDiscriminator = 0;
+  if (Symbol) {
+    uint64_t EntryID = 0;
+    if (const BinaryFunction *const Callee =
+            BC.getFunctionForSymbol(Symbol, &EntryID)) {
+      CSI.DestId = Callee->getFunctionNumber();
+      CSI.EntryDiscriminator = EntryID;
+      return Callee;
+    }
+  }
+  return nullptr;
+}
+
 yaml::bolt::BinaryFunctionProfile
 YAMLProfileWriter::convert(const BinaryFunction &BF, bool UseDFS) {
   yaml::bolt::BinaryFunctionProfile YamlBF;
@@ -79,31 +98,20 @@ YAMLProfileWriter::convert(const BinaryFunction &BF, bool UseDFS) {
           continue;
         for (const IndirectCallProfile &CSP : ICSP.get()) {
           StringRef TargetName = "";
-          CSI.DestId = 0; // designated for unknown functions
-          CSI.EntryDiscriminator = 0;
-          if (CSP.Symbol) {
-            const BinaryFunction *Callee = BC.getFunctionForSymbol(CSP.Symbol);
-            if (Callee) {
-              CSI.DestId = Callee->getFunctionNumber();
-              TargetName = Callee->getOneName();
-            }
-          }
+          const BinaryFunction *Callee = setCSIDestination(BC, CSI, CSP.Symbol);
+          if (Callee)
+            TargetName = Callee->getOneName();
           CSI.Count = CSP.Count;
           CSI.Mispreds = CSP.Mispreds;
           CSTargets.emplace_back(TargetName, CSI);
         }
       } else { // direct call or a tail call
-        uint64_t EntryID = 0;
-        CSI.DestId = 0;
         StringRef TargetName = "";
         const MCSymbol *CalleeSymbol = BC.MIB->getTargetSymbol(Instr);
         const BinaryFunction *const Callee =
-            BC.getFunctionForSymbol(CalleeSymbol, &EntryID);
-        if (Callee) {
-          CSI.DestId = Callee->getFunctionNumber();
-          CSI.EntryDiscriminator = EntryID;
+            setCSIDestination(BC, CSI, CalleeSymbol);
+        if (Callee)
           TargetName = Callee->getOneName();
-        }
 
         auto getAnnotationWithDefault = [&](const MCInst &Inst, StringRef Ann) {
           return BC.MIB->getAnnotationWithDefault(Instr, Ann, 0ull);

bolt/lib/Rewrite/LinuxKernelRewriter.cpp

@@ -212,6 +212,11 @@ class LinuxKernelRewriter final : public MetadataRewriter {
   /// Size of bug_entry struct.
   static constexpr size_t BUG_TABLE_ENTRY_SIZE = 12;
 
+  /// List of bug entries per function.
+  using FunctionBugListType =
+      DenseMap<BinaryFunction *, SmallVector<uint32_t, 2>>;
+  FunctionBugListType FunctionBugList;
+
   /// .pci_fixup section.
   ErrorOr<BinarySection &> PCIFixupSection = std::errc::bad_address;
   static constexpr size_t PCI_FIXUP_ENTRY_SIZE = 16;
@@ -254,7 +259,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
   Error readParaInstructions();
   Error rewriteParaInstructions();
 
+  /// __bug_table section handling.
   Error readBugTable();
+  Error rewriteBugTable();
 
   /// Do no process functions containing instruction annotated with
   /// \p Annotation.
@@ -339,6 +346,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
     if (Error E = rewriteStaticKeysJumpTable())
       return E;
 
+    if (Error E = rewriteBugTable())
+      return E;
+
     return Error::success();
   }
 
@@ -1164,15 +1174,17 @@ Error LinuxKernelRewriter::rewriteParaInstructions() {
 }
 
 /// Process __bug_table section.
-/// This section contains information useful for kernel debugging.
+/// This section contains information useful for kernel debugging, mostly
+/// utilized by WARN()/WARN_ON() macros and deprecated BUG()/BUG_ON().
+///
 /// Each entry in the section is a struct bug_entry that contains a pointer to
 /// the ud2 instruction corresponding to the bug, corresponding file name (both
 /// pointers use PC relative offset addressing), line number, and flags.
 /// The definition of the struct bug_entry can be found in
-/// `include/asm-generic/bug.h`
-///
-/// NB: find_bug() uses linear search to match an address to an entry in the bug
-///     table. Hence there is no need to sort entries when rewriting the table.
+/// `include/asm-generic/bug.h`. The first entry in the struct is an instruction
+/// address encoded as a PC-relative offset. In theory, it could be an absolute
+/// address if CONFIG_GENERIC_BUG_RELATIVE_POINTERS is not set, but in practice
+/// the kernel code relies on it being a relative offset on x86-64.
 Error LinuxKernelRewriter::readBugTable() {
   BugTableSection = BC.getUniqueSectionByName("__bug_table");
   if (!BugTableSection)
@@ -1215,6 +1227,8 @@ Error LinuxKernelRewriter::readBugTable() {
                                  " referenced by bug table entry %d",
                                  InstAddress, EntryID);
       BC.MIB->addAnnotation(*Inst, "BugEntry", EntryID);
+
+      FunctionBugList[BF].push_back(EntryID);
     }
   }
 
@@ -1223,6 +1237,52 @@ Error LinuxKernelRewriter::readBugTable() {
   return Error::success();
 }
 
+/// find_bug() uses linear search to match an address to an entry in the bug
+/// table. Hence, there is no need to sort entries when rewriting the table.
+/// When we need to erase an entry, we set its instruction address to zero.
+Error LinuxKernelRewriter::rewriteBugTable() {
+  if (!BugTableSection)
+    return Error::success();
+
+  for (BinaryFunction &BF : llvm::make_second_range(BC.getBinaryFunctions())) {
+    if (!BC.shouldEmit(BF))
+      continue;
+
+    if (!FunctionBugList.count(&BF))
+      continue;
+
+    // Bugs that will be emitted for this function.
+    DenseSet<uint32_t> EmittedIDs;
+    for (BinaryBasicBlock &BB : BF) {
+      for (MCInst &Inst : BB) {
+        if (!BC.MIB->hasAnnotation(Inst, "BugEntry"))
+          continue;
+        const uint32_t ID = BC.MIB->getAnnotationAs<uint32_t>(Inst, "BugEntry");
+        EmittedIDs.insert(ID);
+
+        // Create a relocation entry for this bug entry.
+        MCSymbol *Label =
+            BC.MIB->getOrCreateInstLabel(Inst, "__BUG_", BC.Ctx.get());
+        const uint64_t EntryOffset = (ID - 1) * BUG_TABLE_ENTRY_SIZE;
+        BugTableSection->addRelocation(EntryOffset, Label, ELF::R_X86_64_PC32,
+                                       /*Addend*/ 0);
+      }
+    }
+
+    // Clear bug entries that were not emitted for this function, e.g. as a
+    // result of DCE, but setting their instruction address to zero.
+    for (const uint32_t ID : FunctionBugList[&BF]) {
+      if (!EmittedIDs.count(ID)) {
+        const uint64_t EntryOffset = (ID - 1) * BUG_TABLE_ENTRY_SIZE;
+        BugTableSection->addRelocation(EntryOffset, nullptr, ELF::R_X86_64_PC32,
+                                       /*Addend*/ 0);
+      }
+    }
+  }
+
+  return Error::success();
+}
+
 /// The kernel can replace certain instruction sequences depending on hardware
 /// it is running on and features specified during boot time. The information
 /// about alternative instruction sequences is stored in .altinstructions

bolt/test/X86/linux-bug-table.s

@@ -1,14 +1,21 @@
 # REQUIRES: system-linux
 
-## Check that BOLT correctly parses the Linux kernel __bug_table section.
+## Check that BOLT correctly parses and updates the Linux kernel __bug_table
+## section.
 
 # RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s -o %t.o
 # RUN: %clang %cflags -nostdlib %t.o -o %t.exe \
 # RUN:   -Wl,--image-base=0xffffffff80000000,--no-dynamic-linker,--no-eh-frame-hdr,--no-pie
 
 ## Verify bug entry bindings to instructions.
 
-# RUN: llvm-bolt %t.exe --print-normalized -o %t.out | FileCheck %s
+# RUN: llvm-bolt %t.exe --print-normalized --print-only=_start -o %t.out \
+# RUN:   --eliminate-unreachable=1 --bolt-info=0 | FileCheck %s
+
+## Verify bug entry bindings again after unreachable code elimination.
+
+# RUN: llvm-bolt %t.out -o %t.out.1 --print-only=_start --print-normalized \
+# RUN:   |& FileCheck --check-prefix=CHECK-REOPT %s
 
 # CHECK:      BOLT-INFO: Linux kernel binary detected
 # CHECK:      BOLT-INFO: parsed 2 bug table entries
@@ -17,17 +24,21 @@
   .globl _start
   .type _start, %function
 _start:
-# CHECK: Binary Function "_start"
-  nop
+  jmp .L1
 .L0:
   ud2
 # CHECK:      ud2
 # CHECK-SAME: BugEntry: 1
-  nop
 .L1:
   ud2
 # CHECK:      ud2
 # CHECK-SAME: BugEntry: 2
+
+## Only the second entry should remain after the first pass.
+
+# CHECK-REOPT: ud2
+# CHECK-REOPT-SAME: BugEntry: 2
+
   ret
   .size _start, .-_start
 

bolt/test/X86/yaml-secondary-entry-discriminator.s

@@ -0,0 +1,74 @@
+# This reproduces a bug with BOLT setting incorrect discriminator for
+# secondary entry points in YAML profile.
+
+# REQUIRES: system-linux
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s -o %t.o
+# RUN: link_fdata %s %t.o %t.fdata
+# RUN: llvm-strip --strip-unneeded %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN: llvm-bolt %t.exe -o %t.out --data %t.fdata -w %t.yaml --print-profile \
+# RUN:   --print-only=main | FileCheck %s --check-prefix=CHECK-CFG
+# RUN: FileCheck %s -input-file %t.yaml
+# CHECK:      - name:    main
+# CHECK-NEXT:   fid:     2
+# CHECK-NEXT:   hash:    0xADF270D550151185
+# CHECK-NEXT:   exec:    0
+# CHECK-NEXT:   nblocks: 4
+# CHECK-NEXT:   blocks:
+# CHECK:          - bid:   1
+# CHECK-NEXT:       insns: 1
+# CHECK-NEXT:       hash:  0x36A303CBA4360014
+# CHECK-NEXT:       calls: [ { off: 0x0, fid: 1, disc: 1, cnt: 1 } ]
+# CHECK:          - bid:   2
+# CHECK-NEXT:       insns: 5
+# CHECK-NEXT:       hash:  0x8B2F5747CD0019
+# CHECK-NEXT:       calls: [ { off: 0x0, fid: 1, disc: 1, cnt: 1, mis: 1 } ]
+
+# Make sure that the profile is attached correctly
+# RUN: llvm-bolt %t.exe -o %t.out --data %t.yaml --print-profile \
+# RUN:   --print-only=main | FileCheck %s --check-prefix=CHECK-CFG
+
+# CHECK-CFG: Binary Function "main" after attaching profile {
+# CHECK-CFG:      callq secondary_entry # Offset: [[#]] # Count: 1
+# CHECK-CFG:      callq *%rax # Offset: [[#]] # CallProfile: 1 (1 misses) :
+# CHECK-CFG-NEXT:     { secondary_entry: 1 (1 misses) }
+
+.globl func
+.type	func, @function
+func:
+# FDATA: 0 [unknown] 0 1 func 0 1 0
+  .cfi_startproc
+  pushq   %rbp
+  movq    %rsp, %rbp
+.globl secondary_entry
+secondary_entry:
+  popq    %rbp
+  retq
+  nopl    (%rax)
+  .cfi_endproc
+  .size	func, .-func
+
+.globl main
+.type	main, @function
+main:
+  .cfi_startproc
+  pushq   %rbp
+  movq    %rsp, %rbp
+  subq    $16, %rsp
+  movl    $0, -4(%rbp)
+  testq   %rax, %rax
+  jne     Lindcall
+Lcall:
+  call    secondary_entry
+# FDATA: 1 main #Lcall# 1 secondary_entry 0 1 1
+Lindcall:
+  callq   *%rax
+# FDATA: 1 main #Lindcall# 1 secondary_entry 0 1 1
+  xorl    %eax, %eax
+  addq    $16, %rsp
+  popq    %rbp
+  retq
+# For relocations against .text
+  call exit
+  .cfi_endproc
+  .size	main, .-main

clang-tools-extra/clangd/support/Trace.h

@@ -143,8 +143,8 @@ bool enabled();
 class Span {
 public:
   Span(llvm::Twine Name);
-  /// Records span's duration in seconds to \p LatencyMetric with \p Name as the
-  /// label.
+  /// Records span's duration in milliseconds to \p LatencyMetric with \p Name
+  /// as the label.
   Span(llvm::Twine Name, const Metric &LatencyMetric);
   ~Span();