Merge branch 'main' into users/skatrak/spr/clause-operands-01-mlir

Author: skatrak

.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/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();
 

clang/docs/ReleaseNotes.rst

@@ -304,6 +304,9 @@ Improvements to Clang's diagnostics
   annotated with the ``clang::always_destroy`` attribute.
   Fixes #GH68686, #GH86486
 
+- ``-Wmicrosoft``, ``-Wgnu``, or ``-pedantic`` is now required to diagnose C99
+  flexible array members in a union or alone in a struct. Fixes GH#84565.
+
 Improvements to Clang's time-trace
 ----------------------------------
 
@@ -454,6 +457,8 @@ Bug Fixes to C++ Support
 - Fix a crash when instantiating a lambda that captures ``this`` outside of its context. Fixes (#GH85343).
 - Fix an issue where a namespace alias could be defined using a qualified name (all name components
   following the first `::` were ignored).
+- Fix an out-of-bounds crash when checking the validity of template partial specializations. (part of #GH86757).
+- Fix an issue caused by not handling invalid cases when substituting into the parameter mapping of a constraint. Fixes (#GH86757).
 
 Bug Fixes to AST Handling
 ^^^^^^^^^^^^^^^^^^^^^^^^^

clang/docs/analyzer/checkers.rst

@@ -849,10 +849,89 @@ Check for performance anti-patterns when using Grand Central Dispatch.
 
 .. _optin-performance-Padding:
 
-optin.performance.Padding
-"""""""""""""""""""""""""
+optin.performance.Padding (C, C++, ObjC)
+""""""""""""""""""""""""""""""""""""""""
 Check for excessively padded structs.
 
+This checker detects structs with excessive padding, which can lead to wasted
+memory thus decreased performance by reducing the effectiveness of the
+processor cache. Padding bytes are added by compilers to align data accesses
+as some processors require data to be aligned to certain boundaries. On others,
+unaligned data access are possible, but impose significantly larger latencies.
+
+To avoid padding bytes, the fields of a struct should be ordered by decreasing
+by alignment. Usually, its easier to think of the ``sizeof`` of the fields, and
+ordering the fields by ``sizeof`` would usually also lead to the same optimal
+layout.
+
+In rare cases, one can use the ``#pragma pack(1)`` directive to enforce a packed
+layout too, but it can significantly increase the access times, so reordering the
+fields is usually a better solution.
+
+
+.. code-block:: cpp
+
+ // warn: Excessive padding in 'struct NonOptimal' (35 padding bytes, where 3 is optimal)
+ struct NonOptimal {
+   char c1;
+   // 7 bytes of padding
+   std::int64_t big1; // 8 bytes
+   char c2;
+   // 7 bytes of padding
+   std::int64_t big2; // 8 bytes
+   char c3;
+   // 7 bytes of padding
+   std::int64_t big3; // 8 bytes
+   char c4;
+   // 7 bytes of padding
+   std::int64_t big4; // 8 bytes
+   char c5;
+   // 7 bytes of padding
+ };
+ static_assert(sizeof(NonOptimal) == 4*8+5+5*7);
+
+ // no-warning: The fields are nicely aligned to have the minimal amount of padding bytes.
+ struct Optimal {
+   std::int64_t big1; // 8 bytes
+   std::int64_t big2; // 8 bytes
+   std::int64_t big3; // 8 bytes
+   std::int64_t big4; // 8 bytes
+   char c1;
+   char c2;
+   char c3;
+   char c4;
+   char c5;
+   // 3 bytes of padding
+ };
+ static_assert(sizeof(Optimal) == 4*8+5+3);
+
+ // no-warning: Bit packing representation is also accepted by this checker, but
+ // it can significantly increase access times, so prefer reordering the fields.
+ #pragma pack(1)
+ struct BitPacked {
+   char c1;
+   std::int64_t big1; // 8 bytes
+   char c2;
+   std::int64_t big2; // 8 bytes
+   char c3;
+   std::int64_t big3; // 8 bytes
+   char c4;
+   std::int64_t big4; // 8 bytes
+   char c5;
+ };
+ static_assert(sizeof(BitPacked) == 4*8+5);
+
+The ``AllowedPad`` option can be used to specify a threshold for the number
+padding bytes raising the warning. If the number of padding bytes of the struct
+and the optimal number of padding bytes differ by more than the threshold value,
+a warning will be raised.
+
+By default, the ``AllowedPad`` threshold is 24 bytes.
+
+To override this threshold to e.g. 4 bytes, use the
+``-analyzer-config optin.performance.Padding:AllowedPad=4`` option.
+
+
 .. _optin-portability-UnixAPI:
 
 optin.portability.UnixAPI

clang/include/clang-c/Index.h

@@ -2991,6 +2991,7 @@ enum CXCallingConv {
   CXCallingConv_AArch64SVEPCS = 18,
   CXCallingConv_M68kRTD = 19,
   CXCallingConv_PreserveNone = 20,
+  CXCallingConv_RISCVVectorCall = 21,
 
   CXCallingConv_Invalid = 100,
   CXCallingConv_Unexposed = 200

clang/include/clang/AST/TextNodeDumper.h

@@ -352,6 +352,7 @@ class TextNodeDumper
   void VisitEnumConstantDecl(const EnumConstantDecl *D);
   void VisitIndirectFieldDecl(const IndirectFieldDecl *D);
   void VisitFunctionDecl(const FunctionDecl *D);
+  void VisitCXXDeductionGuideDecl(const CXXDeductionGuideDecl *D);
   void VisitFieldDecl(const FieldDecl *D);
   void VisitVarDecl(const VarDecl *D);
   void VisitBindingDecl(const BindingDecl *D);

clang/include/clang/Analysis/FlowSensitive/DataflowEnvironment.h

@@ -744,6 +744,35 @@ RecordStorageLocation *getBaseObjectLocation(const MemberExpr &ME,
 std::vector<const FieldDecl *>
 getFieldsForInitListExpr(const InitListExpr *InitList);
 
+/// Helper class for initialization of a record with an `InitListExpr`.
+/// `InitListExpr::inits()` contains the initializers for both the base classes
+/// and the fields of the record; this helper class separates these out into two
+/// different lists. In addition, it deals with special cases associated with
+/// unions.
+class RecordInitListHelper {
+public:
+  // `InitList` must have record type.
+  RecordInitListHelper(const InitListExpr *InitList);
+
+  // Base classes with their associated initializer expressions.
+  ArrayRef<std::pair<const CXXBaseSpecifier *, Expr *>> base_inits() const {
+    return BaseInits;
+  }
+
+  // Fields with their associated initializer expressions.
+  ArrayRef<std::pair<const FieldDecl *, Expr *>> field_inits() const {
+    return FieldInits;
+  }
+
+private:
+  SmallVector<std::pair<const CXXBaseSpecifier *, Expr *>> BaseInits;
+  SmallVector<std::pair<const FieldDecl *, Expr *>> FieldInits;
+
+  // We potentially synthesize an `ImplicitValueInitExpr` for unions. It's a
+  // member variable because we store a pointer to it in `FieldInits`.
+  std::optional<ImplicitValueInitExpr> ImplicitValueInitForUnion;
+};
+
 /// Associates a new `RecordValue` with `Loc` and returns the new value.
 RecordValue &refreshRecordValue(RecordStorageLocation &Loc, Environment &Env);