Merge branch 'main' into main

Author: jph-13

.github/workflows/release-binaries.yml

@@ -142,7 +142,7 @@ jobs:
             # 2-3 hours to build on macOS, much slower than on Linux.
             # The long build time causes the release build to time out on x86_64,
             # so we need to disable flang there.
-            target_cmake_flags="$target_cmake_flags -DLLVM_RELEASE_ENABLE_PROJECTS='clang;lld;lldb;clang-tools-extra;bolt;polly;mlir'"
+            target_cmake_flags="$target_cmake_flags -DLLVM_RELEASE_ENABLE_PROJECTS='clang;lld;lldb;clang-tools-extra;polly;mlir'"
           fi
           target_cmake_flags="$target_cmake_flags -DBOOTSTRAP_BOOTSTRAP_DARWIN_osx_ARCHS=$arches -DBOOTSTRAP_BOOTSTRAP_DARWIN_osx_BUILTIN_ARCHS=$arches"
         fi

bolt/lib/Core/BinaryFunction.cpp

@@ -15,6 +15,7 @@
 #include "bolt/Core/DynoStats.h"
 #include "bolt/Core/HashUtilities.h"
 #include "bolt/Core/MCPlusBuilder.h"
+#include "bolt/Utils/CommandLineOpts.h"
 #include "bolt/Utils/NameResolver.h"
 #include "bolt/Utils/NameShortener.h"
 #include "bolt/Utils/Utils.h"
@@ -1753,8 +1754,8 @@ void BinaryFunction::postProcessEntryPoints() {
     // In non-relocation mode there's potentially an external undetectable
     // reference to the entry point and hence we cannot move this entry
     // point. Optimizing without moving could be difficult.
-    // In BAT mode, register any known entry points for CFG construction.
-    if (!BC.HasRelocations && !BC.HasBATSection)
+    // In aggregation, register any known entry points for CFG construction.
+    if (!BC.HasRelocations && !opts::AggregateOnly)
       setSimple(false);
 
     const uint32_t Offset = KV.first;

bolt/lib/Profile/DataAggregator.cpp

@@ -831,9 +831,10 @@ bool DataAggregator::doTrace(const LBREntry &First, const LBREntry &Second,
     ParentFunc = FromFunc;
   ParentFunc->SampleCountInBytes += Count * (Second.From - First.To);
 
+  const uint64_t FuncAddress = FromFunc->getAddress();
   std::optional<BoltAddressTranslation::FallthroughListTy> FTs =
-      BAT ? BAT->getFallthroughsInTrace(FromFunc->getAddress(), First.To,
-                                        Second.From)
+      BAT && BAT->isBATFunction(FuncAddress)
+          ? BAT->getFallthroughsInTrace(FuncAddress, First.To, Second.From)
           : getFallthroughsInTrace(*FromFunc, First, Second, Count);
   if (!FTs) {
     LLVM_DEBUG(

bolt/test/X86/bolt-address-translation-yaml.test

@@ -61,6 +61,11 @@ YAML-BAT-CHECK-NEXT:   - bid:   0
 YAML-BAT-CHECK-NEXT:     insns: 26
 YAML-BAT-CHECK-NEXT:     hash:  0xA900AE79CFD40000
 YAML-BAT-CHECK-NEXT:     succ:  [ { bid: 3, cnt: 0 }, { bid: 1, cnt: 0 } ]
+# Check fallthroughs in non-BAT function
+YAML-BAT-CHECK-NEXT:   - bid:   27
+YAML-BAT-CHECK-NEXT:     insns: 3
+YAML-BAT-CHECK-NEXT:     hash:  0x30A1EBA77A903F0
+YAML-BAT-CHECK-NEXT:     succ:  [ { bid: 28, cnt: 1 } ]
 # Calls from no-BAT to BAT function
 YAML-BAT-CHECK:        - bid:   28
 YAML-BAT-CHECK-NEXT:     insns: 13

bolt/test/X86/entry-point-fallthru.s

@@ -0,0 +1,24 @@
+## Checks that fallthroughs spanning entry points are accepted in aggregation
+## mode.
+
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s -o %t.o
+# RUN: ld.lld %t.o -o %t
+# RUN: link_fdata %s %t %t.preagg PREAGG
+# RUN: perf2bolt %t -p %t.preagg --pa -o %t.fdata | FileCheck %s
+# CHECK: traces mismatching disassembled function contents: 0
+
+	.globl main
+main:
+	.cfi_startproc
+	vmovaps %zmm31,%zmm3
+
+next:
+	add    $0x4,%r9
+	add    $0x40,%r10
+	dec    %r14
+Ljmp:
+	jne    main
+# PREAGG: T #Ljmp# #main# #Ljmp# 1
+	ret
+	.cfi_endproc
+.size main,.-main

clang/cmake/caches/Release.cmake

@@ -29,14 +29,21 @@ endfunction()
 # cache file to CMake via -C. e.g.
 #
 # cmake -D LLVM_RELEASE_ENABLE_PGO=ON -C Release.cmake
+
+set (DEFAULT_PROJECTS "clang;lld;lldb;clang-tools-extra;polly;mlir;flang")
+# bolt only supports ELF, so only enable it for Linux.
+if (${CMAKE_HOST_SYSTEM_NAME} MATCHES "Linux")
+  list(APPEND DEFAULT_PROJECTS "bolt")
+endif()
+
 set (DEFAULT_RUNTIMES "compiler-rt;libcxx")
 if (NOT WIN32)
   list(APPEND DEFAULT_RUNTIMES "libcxxabi" "libunwind")
 endif()
 set(LLVM_RELEASE_ENABLE_LTO THIN CACHE STRING "")
 set(LLVM_RELEASE_ENABLE_PGO ON CACHE BOOL "")
 set(LLVM_RELEASE_ENABLE_RUNTIMES ${DEFAULT_RUNTIMES} CACHE STRING "")
-set(LLVM_RELEASE_ENABLE_PROJECTS "clang;lld;lldb;clang-tools-extra;bolt;polly;mlir;flang" CACHE STRING "")
+set(LLVM_RELEASE_ENABLE_PROJECTS ${DEFAULT_PROJECTS} CACHE STRING "")
 # Note we don't need to add install here, since it is one of the pre-defined
 # steps.
 set(LLVM_RELEASE_FINAL_STAGE_TARGETS "clang;package;check-all;check-llvm;check-clang" CACHE STRING "")
@@ -118,13 +125,21 @@ if(NOT ${CMAKE_HOST_SYSTEM_NAME} MATCHES "Darwin")
   set(RELEASE_LINKER_FLAGS "${RELEASE_LINKER_FLAGS} -static-libgcc")
 endif()
 
+# Set flags for bolt
+if (${CMAKE_HOST_SYSTEM_NAME} MATCHES "Linux")
+  set(RELEASE_LINKER_FLAGS "${RELEASE_LINKER_FLAGS} -Wl,--emit-relocs,-znow")
+endif()
+
 set_instrument_and_final_stage_var(CMAKE_EXE_LINKER_FLAGS ${RELEASE_LINKER_FLAGS} STRING)
 set_instrument_and_final_stage_var(CMAKE_SHARED_LINKER_FLAGS ${RELEASE_LINKER_FLAGS} STRING)
 set_instrument_and_final_stage_var(CMAKE_MODULE_LINKER_FLAGS ${RELEASE_LINKER_FLAGS} STRING)
 
 # Final Stage Config (stage2)
 set_final_stage_var(LLVM_ENABLE_RUNTIMES "${LLVM_RELEASE_ENABLE_RUNTIMES}" STRING)
 set_final_stage_var(LLVM_ENABLE_PROJECTS "${LLVM_RELEASE_ENABLE_PROJECTS}" STRING)
+if (${CMAKE_HOST_SYSTEM_NAME} MATCHES "Linux")
+  set_final_stage_var(CLANG_BOLT "INSTRUMENT" STRING)
+endif()
 set_final_stage_var(CPACK_GENERATOR "TXZ" STRING)
 set_final_stage_var(CPACK_ARCHIVE_THREADS "0" STRING)
 

clang/docs/ReleaseNotes.rst

@@ -124,6 +124,8 @@ Removed Compiler Flags
 
 Attribute Changes in Clang
 --------------------------
+Adding [[clang::unsafe_buffer_usage]] attribute to a method definition now turns off all -Wunsafe-buffer-usage
+related warnings within the method body.
 
 - The ``no_sanitize`` attribute now accepts both ``gnu`` and ``clang`` names.
 - Clang now diagnoses use of declaration attributes on void parameters. (#GH108819)

clang/lib/Basic/Targets/SPIR.h

@@ -399,6 +399,8 @@ class LLVM_LIBRARY_VISIBILITY SPIRV64AMDGCNTargetInfo final
     HasLegalHalfType = true;
     HasFloat16 = true;
     HalfArgsAndReturns = true;
+
+    MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64;
   }
 
   bool hasBFloat16Type() const override { return true; }

clang/lib/Sema/AnalysisBasedWarnings.cpp

@@ -2566,6 +2566,9 @@ void clang::sema::AnalysisBasedWarnings::IssueWarnings(
 
   // The Callback function that performs analyses:
   auto CallAnalyzers = [&](const Decl *Node) -> void {
+    if (Node->hasAttr<UnsafeBufferUsageAttr>())
+      return;
+
     // Perform unsafe buffer usage analysis:
     if (!Diags.isIgnored(diag::warn_unsafe_buffer_operation,
                          Node->getBeginLoc()) ||

clang/lib/Sema/SemaChecking.cpp

@@ -7390,10 +7390,11 @@ bool DecomposePrintfHandler::GetSpecifiers(
   const char *Str = Data.data();
   llvm::SmallBitVector BV;
   UncoveredArgHandler UA;
+  const Expr *PrintfArgs[] = {FSL->getFormatString()};
   DecomposePrintfHandler H(S, FSL, FSL->getFormatString(), Type, 0, 0, IsObjC,
-                           Str, Sema::FAPK_Elsewhere, {FSL->getFormatString()},
-                           0, InFunctionCall, Sema::VariadicDoesNotApply, BV,
-                           UA, Args);
+                           Str, Sema::FAPK_Elsewhere, PrintfArgs, 0,
+                           InFunctionCall, Sema::VariadicDoesNotApply, BV, UA,
+                           Args);
 
   if (!analyze_format_string::ParsePrintfString(
           H, Str, Str + Data.size(), S.getLangOpts(), S.Context.getTargetInfo(),
@@ -7402,7 +7403,7 @@ bool DecomposePrintfHandler::GetSpecifiers(
   if (H.HadError)
     return false;
 
-  std::sort(
+  std::stable_sort(
       Args.begin(), Args.end(),
       [](const EquatableFormatArgument &A, const EquatableFormatArgument &B) {
         return A.getPosition() < B.getPosition();