[NFC][Profile] Access profile through VirtualFileSystem

cachemeifyoucan · cachemeifyoucan · commit 9c3ff1296b45 · 2023-02-02T15:06:43.000-08:00
Make the access to profile data going through virtual file system so the inputs can be remapped. In the context of the caching, it can make sure we capture the inputs and provided an immutable input as profile data. Reviewed By: akyrtzi, benlangmuir Differential Revision: https://reviews.llvm.org/D139052
diff --git a/clang/include/clang/CodeGen/BackendUtil.h b/clang/include/clang/CodeGen/BackendUtil.h
@@ -17,8 +17,12 @@
 namespace llvm {
   class BitcodeModule;
   template <typename T> class Expected;
+  template <typename T> class IntrusiveRefCntPtr;
   class Module;
   class MemoryBufferRef;
+  namespace vfs {
+  class FileSystem;
+  } // namespace vfs
 }
 
 namespace clang {
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
@@ -192,7 +192,7 @@ class EmitAssemblyHelper {
                      const LangOptions &LOpts, Module *M,
                      IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS)
       : Diags(_Diags), HSOpts(HeaderSearchOpts), CodeGenOpts(CGOpts),
-        TargetOpts(TOpts), LangOpts(LOpts), TheModule(M), VFS(VFS),
+        TargetOpts(TOpts), LangOpts(LOpts), TheModule(M), VFS(std::move(VFS)),
         CodeGenerationTime("codegen", "Code Generation Time"),
         TargetTriple(TheModule->getTargetTriple()) {}
 
@@ -1201,9 +1201,8 @@ void clang::EmitBackendOutput(DiagnosticsEngine &Diags,
                               const HeaderSearchOptions &HeaderOpts,
                               const CodeGenOptions &CGOpts,
                               const clang::TargetOptions &TOpts,
-                              const LangOptions &LOpts,
-                              StringRef TDesc, Module *M,
-                              BackendAction Action,
+                              const LangOptions &LOpts, StringRef TDesc,
+                              Module *M, BackendAction Action,
                               IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS,
                               std::unique_ptr<raw_pwrite_stream> OS) {
 
diff --git a/clang/lib/CodeGen/CodeGenAction.cpp b/clang/lib/CodeGen/CodeGenAction.cpp
@@ -147,7 +147,7 @@ namespace clang {
 
   public:
     BackendConsumer(BackendAction Action, DiagnosticsEngine &Diags,
-                    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
+                    IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS,
                     const HeaderSearchOptions &HeaderSearchOpts,
                     const PreprocessorOptions &PPOpts,
                     const CodeGenOptions &CodeGenOpts,
@@ -158,10 +158,10 @@ namespace clang {
                     CoverageSourceInfo *CoverageInfo = nullptr)
         : Diags(Diags), Action(Action), HeaderSearchOpts(HeaderSearchOpts),
           CodeGenOpts(CodeGenOpts), TargetOpts(TargetOpts), LangOpts(LangOpts),
-          AsmOutStream(std::move(OS)), Context(nullptr), FS(FS),
+          AsmOutStream(std::move(OS)), Context(nullptr), FS(VFS),
           LLVMIRGeneration("irgen", "LLVM IR Generation Time"),
           LLVMIRGenerationRefCount(0),
-          Gen(CreateLLVMCodeGen(Diags, InFile, FS, HeaderSearchOpts,
+          Gen(CreateLLVMCodeGen(Diags, InFile, std::move(VFS), HeaderSearchOpts,
                                 PPOpts, CodeGenOpts, C, CoverageInfo)),
           LinkModules(std::move(LinkModules)) {
       TimerIsEnabled = CodeGenOpts.TimePasses;
@@ -173,7 +173,7 @@ namespace clang {
     // to use the clang diagnostic handler for IR input files. It avoids
     // initializing the OS field.
     BackendConsumer(BackendAction Action, DiagnosticsEngine &Diags,
-                    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
+                    IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS,
                     const HeaderSearchOptions &HeaderSearchOpts,
                     const PreprocessorOptions &PPOpts,
                     const CodeGenOptions &CodeGenOpts,
@@ -183,10 +183,10 @@ namespace clang {
                     CoverageSourceInfo *CoverageInfo = nullptr)
         : Diags(Diags), Action(Action), HeaderSearchOpts(HeaderSearchOpts),
           CodeGenOpts(CodeGenOpts), TargetOpts(TargetOpts), LangOpts(LangOpts),
-          Context(nullptr), FS(FS),
+          Context(nullptr), FS(VFS),
           LLVMIRGeneration("irgen", "LLVM IR Generation Time"),
           LLVMIRGenerationRefCount(0),
-          Gen(CreateLLVMCodeGen(Diags, "", FS, HeaderSearchOpts,
+          Gen(CreateLLVMCodeGen(Diags, "", std::move(VFS), HeaderSearchOpts,
                                 PPOpts, CodeGenOpts, C, CoverageInfo)),
           LinkModules(std::move(LinkModules)), CurLinkModule(Module) {
       TimerIsEnabled = CodeGenOpts.TimePasses;
@@ -1212,10 +1212,10 @@ void CodeGenAction::ExecuteAction() {
   std::unique_ptr<llvm::ToolOutputFile> OptRecordFile =
       std::move(*OptRecordFileOrErr);
 
-  EmitBackendOutput(Diagnostics, CI.getHeaderSearchOpts(), CodeGenOpts,
-                    TargetOpts, CI.getLangOpts(),
-                    CI.getTarget().getDataLayoutString(), TheModule.get(), BA,
-                    CI.getFileManager().getVirtualFileSystemPtr(), std::move(OS));
+  EmitBackendOutput(
+      Diagnostics, CI.getHeaderSearchOpts(), CodeGenOpts, TargetOpts,
+      CI.getLangOpts(), CI.getTarget().getDataLayoutString(), TheModule.get(),
+      BA, CI.getFileManager().getVirtualFileSystemPtr(), std::move(OS));
   if (OptRecordFile)
     OptRecordFile->keep();
 }
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -106,11 +106,11 @@ CodeGenModule::CodeGenModule(ASTContext &C,
                              const CodeGenOptions &CGO, llvm::Module &M,
                              DiagnosticsEngine &diags,
                              CoverageSourceInfo *CoverageInfo)
-    : Context(C), LangOpts(C.getLangOpts()), FS(FS),
-      HeaderSearchOpts(HSO), PreprocessorOpts(PPO), CodeGenOpts(CGO),
-      TheModule(M), Diags(diags), Target(C.getTargetInfo()),
-      ABI(createCXXABI(*this)), VMContext(M.getContext()), Types(*this),
-      VTables(*this), SanitizerMD(new SanitizerMetadata(*this)) {
+    : Context(C), LangOpts(C.getLangOpts()), FS(FS), HeaderSearchOpts(HSO),
+      PreprocessorOpts(PPO), CodeGenOpts(CGO), TheModule(M), Diags(diags),
+      Target(C.getTargetInfo()), ABI(createCXXABI(*this)),
+      VMContext(M.getContext()), Types(*this), VTables(*this),
+      SanitizerMD(new SanitizerMetadata(*this)) {
 
   // Initialize the type cache.
   llvm::LLVMContext &LLVMContext = M.getContext();
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -2153,8 +2153,8 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
                      Opts.OptimizationRemarkAnalysis.hasValidPattern();
 
   bool UsingSampleProfile = !Opts.SampleProfileFile.empty();
-  bool UsingProfile = UsingSampleProfile ||
-      (Opts.getProfileUse() != CodeGenOptions::ProfileNone);
+  bool UsingProfile =
+      UsingSampleProfile || !Opts.ProfileInstrumentUsePath.empty();
 
   if (Opts.DiagnosticsWithHotness && !UsingProfile &&
       // An IR file will contain PGO as metadata
diff --git a/llvm/include/llvm/CodeGen/MIRSampleProfile.h b/llvm/include/llvm/CodeGen/MIRSampleProfile.h
@@ -14,6 +14,7 @@
 #ifndef LLVM_CODEGEN_MIRSAMPLEPROFILE_H
 #define LLVM_CODEGEN_MIRSAMPLEPROFILE_H
 
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/Support/Discriminator.h"
@@ -27,6 +28,10 @@ class MachineBlockFrequencyInfo;
 class MachineFunction;
 class Module;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 using namespace sampleprof;
 
 class MIRProfileLoader;
diff --git a/llvm/include/llvm/Passes/PassBuilder.h b/llvm/include/llvm/Passes/PassBuilder.h
@@ -34,6 +34,10 @@ class StringRef;
 class AAManager;
 class TargetMachine;
 class ModuleSummaryIndex;
+template <typename T> class IntrusiveRefCntPtr;
+namespace vfs {
+class FileSystem;
+} // namespace vfs
 
 /// Tunable parameters for passes in the default pipelines.
 class PipelineTuningOptions {
diff --git a/llvm/include/llvm/ProfileData/Coverage/CoverageMapping.h b/llvm/include/llvm/ProfileData/Coverage/CoverageMapping.h
@@ -44,6 +44,10 @@ namespace llvm {
 
 class IndexedInstrProfReader;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 namespace coverage {
 
 class CoverageMappingReader;
diff --git a/llvm/include/llvm/ProfileData/InstrProfReader.h b/llvm/include/llvm/ProfileData/InstrProfReader.h
@@ -40,6 +40,10 @@ namespace llvm {
 
 class InstrProfReader;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 /// A file format agnostic iterator over profiling data.
 template <class record_type = NamedInstrProfRecord,
           class reader_type = InstrProfReader>
diff --git a/llvm/include/llvm/ProfileData/SampleProfReader.h b/llvm/include/llvm/ProfileData/SampleProfReader.h
@@ -252,6 +252,10 @@ namespace llvm {
 class raw_ostream;
 class Twine;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 namespace sampleprof {
 
 class SampleProfileReader;
diff --git a/llvm/include/llvm/Support/PGOOptions.h b/llvm/include/llvm/Support/PGOOptions.h
@@ -14,49 +14,29 @@
 #ifndef LLVM_SUPPORT_PGOOPTIONS_H
 #define LLVM_SUPPORT_PGOOPTIONS_H
 
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/Support/Error.h"
-#include "llvm/Support/VirtualFileSystem.h"
 
 namespace llvm {
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 /// A struct capturing PGO tunables.
 struct PGOOptions {
   enum PGOAction { NoAction, IRInstr, IRUse, SampleUse };
   enum CSPGOAction { NoCSAction, CSIRInstr, CSIRUse };
-  PGOOptions(std::string ProfileFile = "", std::string CSProfileGenFile = "",
-             std::string ProfileRemappingFile = "",
-             IntrusiveRefCntPtr<vfs::FileSystem> FS = nullptr,
+  PGOOptions(std::string ProfileFile, std::string CSProfileGenFile,
+             std::string ProfileRemappingFile,
+             IntrusiveRefCntPtr<vfs::FileSystem> FS,
              PGOAction Action = NoAction, CSPGOAction CSAction = NoCSAction,
              bool DebugInfoForProfiling = false,
-             bool PseudoProbeForProfiling = false)
-      : ProfileFile(ProfileFile), CSProfileGenFile(CSProfileGenFile),
-        ProfileRemappingFile(ProfileRemappingFile), Action(Action),
-        CSAction(CSAction), DebugInfoForProfiling(DebugInfoForProfiling ||
-                                                  (Action == SampleUse &&
-                                                   !PseudoProbeForProfiling)),
-        PseudoProbeForProfiling(PseudoProbeForProfiling), FS(FS) {
-    // Note, we do allow ProfileFile.empty() for Action=IRUse LTO can
-    // callback with IRUse action without ProfileFile.
-
-    // If there is a CSAction, PGOAction cannot be IRInstr or SampleUse.
-    assert(this->CSAction == NoCSAction ||
-           (this->Action != IRInstr && this->Action != SampleUse));
-
-    // For CSIRInstr, CSProfileGenFile also needs to be nonempty.
-    assert(this->CSAction != CSIRInstr || !this->CSProfileGenFile.empty());
-
-    // If CSAction is CSIRUse, PGOAction needs to be IRUse as they share
-    // a profile.
-    assert(this->CSAction != CSIRUse || this->Action == IRUse);
-
-    // If neither Action nor CSAction, DebugInfoForProfiling or
-    // PseudoProbeForProfiling needs to be true.
-    assert(this->Action != NoAction || this->CSAction != NoCSAction ||
-           this->DebugInfoForProfiling || this->PseudoProbeForProfiling);
+             bool PseudoProbeForProfiling = false);
+  PGOOptions(const PGOOptions &);
+  ~PGOOptions();
+  PGOOptions &operator=(const PGOOptions &);
 
-    // If we need to use the profile, the VFS cannot be nullptr.
-    assert(this->FS || !(this->Action == IRUse || this->CSAction == CSIRUse));
-  }
   std::string ProfileFile;
   std::string CSProfileGenFile;
   std::string ProfileRemappingFile;
diff --git a/llvm/include/llvm/Transforms/IPO/SampleProfile.h b/llvm/include/llvm/Transforms/IPO/SampleProfile.h
@@ -14,24 +14,26 @@
 #ifndef LLVM_TRANSFORMS_IPO_SAMPLEPROFILE_H
 #define LLVM_TRANSFORMS_IPO_SAMPLEPROFILE_H
 
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/VirtualFileSystem.h"
 #include <string>
 
 namespace llvm {
 
 class Module;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 /// The sample profiler data loader pass.
 class SampleProfileLoaderPass : public PassInfoMixin<SampleProfileLoaderPass> {
 public:
   SampleProfileLoaderPass(
       std::string File = "", std::string RemappingFile = "",
       ThinOrFullLTOPhase LTOPhase = ThinOrFullLTOPhase::None,
-      IntrusiveRefCntPtr<vfs::FileSystem> FS = nullptr)
-      : ProfileFileName(File), ProfileRemappingFileName(RemappingFile),
-        LTOPhase(LTOPhase) {}
+      IntrusiveRefCntPtr<vfs::FileSystem> FS = nullptr);
 
   PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
 
diff --git a/llvm/include/llvm/Transforms/Instrumentation/PGOInstrumentation.h b/llvm/include/llvm/Transforms/Instrumentation/PGOInstrumentation.h
@@ -16,6 +16,7 @@
 #define LLVM_TRANSFORMS_INSTRUMENTATION_PGOINSTRUMENTATION_H
 
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/VirtualFileSystem.h"
 #include <cstdint>
@@ -27,6 +28,10 @@ class Function;
 class Instruction;
 class Module;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 /// The instrumentation (profile-instr-gen) pass for IR based PGO.
 // We use this pass to create COMDAT profile variables for context
 // sensitive PGO (CSPGO). The reason to have a pass for this is CSPGO
diff --git a/llvm/include/llvm/Transforms/Utils/SampleProfileLoaderBaseImpl.h b/llvm/include/llvm/Transforms/Utils/SampleProfileLoaderBaseImpl.h
@@ -18,6 +18,7 @@
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
@@ -47,6 +48,10 @@ using namespace sampleprof;
 using namespace sampleprofutil;
 using ProfileCount = Function::ProfileCount;
 
+namespace vfs {
+class FileSystem;
+} // namespace vfs
+
 #define DEBUG_TYPE "sample-profile-impl"
 
 namespace afdo_detail {
@@ -83,7 +88,7 @@ template <typename BT> class SampleProfileLoaderBaseImpl {
 public:
   SampleProfileLoaderBaseImpl(std::string Name, std::string RemapName,
                               IntrusiveRefCntPtr<vfs::FileSystem> FS)
-      : Filename(Name), RemappingFilename(RemapName), FS(FS) {}
+      : Filename(Name), RemappingFilename(RemapName), FS(std::move(FS)) {}
   void dump() { Reader->dump(); }
 
   using InstructionT = typename afdo_detail::IRTraits<BT>::InstructionT;
diff --git a/llvm/lib/CodeGen/MIRSampleProfile.cpp b/llvm/lib/CodeGen/MIRSampleProfile.cpp
@@ -77,7 +77,7 @@ FunctionPass *
 llvm::createMIRProfileLoaderPass(std::string File, std::string RemappingFile,
                                  FSDiscriminatorPass P,
                                  IntrusiveRefCntPtr<vfs::FileSystem> FS) {
-  return new MIRProfileLoaderPass(File, RemappingFile, P, FS);
+  return new MIRProfileLoaderPass(File, RemappingFile, P, std::move(FS));
 }
 
 namespace llvm {
@@ -141,7 +141,7 @@ class MIRProfileLoader final
   MIRProfileLoader(StringRef Name, StringRef RemapName,
                    IntrusiveRefCntPtr<vfs::FileSystem> FS)
       : SampleProfileLoaderBaseImpl(std::string(Name), std::string(RemapName),
-                                    FS) {}
+                                    std::move(FS)) {}
 
   void setBranchProbs(MachineFunction &F);
   bool runOnFunction(MachineFunction &F);
@@ -301,9 +301,9 @@ MIRProfileLoaderPass::MIRProfileLoaderPass(
   LowBit = getFSPassBitBegin(P);
   HighBit = getFSPassBitEnd(P);
 
-  this->FS = FS ? std::move(FS) : vfs::getRealFileSystem();
-  MIRSampleLoader =
-      std::make_unique<MIRProfileLoader>(FileName, RemappingFileName, this->FS);
+  auto VFS = FS ? std::move(FS) : vfs::getRealFileSystem();
+  MIRSampleLoader = std::make_unique<MIRProfileLoader>(
+      FileName, RemappingFileName, std::move(VFS));
   assert(LowBit < HighBit && "HighBit needs to be greater than Lowbit");
 }
 
diff --git a/llvm/lib/CodeGen/TargetPassConfig.cpp b/llvm/lib/CodeGen/TargetPassConfig.cpp
@@ -1178,9 +1178,9 @@ void TargetPassConfig::addMachinePasses() {
         sampleprof::FSDiscriminatorPass::Pass1));
     const std::string ProfileFile = getFSProfileFile(TM);
     if (!ProfileFile.empty() && !DisableRAFSProfileLoader)
-      addPass(
-          createMIRProfileLoaderPass(ProfileFile, getFSRemappingFile(TM),
-                                     sampleprof::FSDiscriminatorPass::Pass1, nullptr));
+      addPass(createMIRProfileLoaderPass(ProfileFile, getFSRemappingFile(TM),
+                                         sampleprof::FSDiscriminatorPass::Pass1,
+                                         nullptr));
   }
 
   // Run register allocation and passes that are tightly coupled with it,
@@ -1548,9 +1548,9 @@ void TargetPassConfig::addBlockPlacement() {
         sampleprof::FSDiscriminatorPass::Pass2));
     const std::string ProfileFile = getFSProfileFile(TM);
     if (!ProfileFile.empty() && !DisableLayoutFSProfileLoader)
-      addPass(
-          createMIRProfileLoaderPass(ProfileFile, getFSRemappingFile(TM),
-                                     sampleprof::FSDiscriminatorPass::Pass2, nullptr));
+      addPass(createMIRProfileLoaderPass(ProfileFile, getFSRemappingFile(TM),
+                                         sampleprof::FSDiscriminatorPass::Pass2,
+                                         nullptr));
   }
   if (addPass(&MachineBlockPlacementID)) {
     // Run a separate pass to collect block placement statistics.
diff --git a/llvm/lib/ProfileData/InstrProf.cpp b/llvm/lib/ProfileData/InstrProf.cpp
@@ -1224,6 +1224,8 @@ Error OverlapStats::accumulateCounts(const std::string &BaseFilename,
                                      bool IsCS) {
   auto getProfileSum = [IsCS](const std::string &Filename,
                               CountSumOrPercent &Sum) -> Error {
+    // This function is only used from llvm-profdata that doesn't use any kind
+    // of VFS. Just create a default RealFileSystem to read profiles.
     auto FS = vfs::getRealFileSystem();
     auto ReaderOrErr = InstrProfReader::create(Filename, *FS);
     if (Error E = ReaderOrErr.takeError()) {
diff --git a/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
diff --git a/llvm/lib/Support/CMakeLists.txt b/llvm/lib/Support/CMakeLists.txt
diff --git a/llvm/lib/Support/PGOOptions.cpp b/llvm/lib/Support/PGOOptions.cpp
diff --git a/llvm/lib/Target/X86/X86InsertPrefetch.cpp b/llvm/lib/Target/X86/X86InsertPrefetch.cpp
diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
diff --git a/llvm/tools/opt/NewPMDriver.cpp b/llvm/tools/opt/NewPMDriver.cpp
diff --git a/llvm/unittests/ProfileData/SampleProfTest.cpp b/llvm/unittests/ProfileData/SampleProfTest.cpp
