[NFC][Profile] Access profile through VirtualFileSystem

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

5 files changed, 66 insertions, 50 deletions

diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
index 10d6bff..2b43d0e 100644
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -52,6 +52,7 @@
 #include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/Timer.h"
 #include "llvm/Support/ToolOutputFile.h"
+#include "llvm/Support/VirtualFileSystem.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetOptions.h"
@@ -123,6 +124,7 @@ class EmitAssemblyHelper {
   const clang::TargetOptions &TargetOpts;
   const LangOptions &LangOpts;
   Module *TheModule;
+  IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS;
 
   Timer CodeGenerationTime;
 
@@ -187,9 +189,10 @@ public:
                      const HeaderSearchOptions &HeaderSearchOpts,
                      const CodeGenOptions &CGOpts,
                      const clang::TargetOptions &TOpts,
-                     const LangOptions &LOpts, Module *M)
+                     const LangOptions &LOpts, Module *M,
+                     IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS)
       : Diags(_Diags), HSOpts(HeaderSearchOpts), CodeGenOpts(CGOpts),
-        TargetOpts(TOpts), LangOpts(LOpts), TheModule(M),
+        TargetOpts(TOpts), LangOpts(LOpts), TheModule(M), VFS(std::move(VFS)),
         CodeGenerationTime("codegen", "Code Generation Time"),
         TargetTriple(TheModule->getTargetTriple()) {}
 
@@ -767,32 +770,33 @@ void EmitAssemblyHelper::RunOptimizationPipeline(
 
   if (CodeGenOpts.hasProfileIRInstr())
     // -fprofile-generate.
-    PGOOpt = PGOOptions(CodeGenOpts.InstrProfileOutput.empty()
-                            ? getDefaultProfileGenName()
-                            : CodeGenOpts.InstrProfileOutput,
-                        "", "", PGOOptions::IRInstr, PGOOptions::NoCSAction,
-                        CodeGenOpts.DebugInfoForProfiling);
+    PGOOpt = PGOOptions(
+        CodeGenOpts.InstrProfileOutput.empty() ? getDefaultProfileGenName()
+                                               : CodeGenOpts.InstrProfileOutput,
+        "", "", nullptr, PGOOptions::IRInstr, PGOOptions::NoCSAction,
+        CodeGenOpts.DebugInfoForProfiling);
   else if (CodeGenOpts.hasProfileIRUse()) {
     // -fprofile-use.
     auto CSAction = CodeGenOpts.hasProfileCSIRUse() ? PGOOptions::CSIRUse
                                                     : PGOOptions::NoCSAction;
-    PGOOpt = PGOOptions(CodeGenOpts.ProfileInstrumentUsePath, "",
-                        CodeGenOpts.ProfileRemappingFile, PGOOptions::IRUse,
-                        CSAction, CodeGenOpts.DebugInfoForProfiling);
+    PGOOpt =
+        PGOOptions(CodeGenOpts.ProfileInstrumentUsePath, "",
+                   CodeGenOpts.ProfileRemappingFile, VFS, PGOOptions::IRUse,
+                   CSAction, CodeGenOpts.DebugInfoForProfiling);
   } else if (!CodeGenOpts.SampleProfileFile.empty())
     // -fprofile-sample-use
     PGOOpt = PGOOptions(
         CodeGenOpts.SampleProfileFile, "", CodeGenOpts.ProfileRemappingFile,
-        PGOOptions::SampleUse, PGOOptions::NoCSAction,
+        VFS, PGOOptions::SampleUse, PGOOptions::NoCSAction,
         CodeGenOpts.DebugInfoForProfiling, CodeGenOpts.PseudoProbeForProfiling);
   else if (CodeGenOpts.PseudoProbeForProfiling)
     // -fpseudo-probe-for-profiling
-    PGOOpt =
-        PGOOptions("", "", "", PGOOptions::NoAction, PGOOptions::NoCSAction,
-                   CodeGenOpts.DebugInfoForProfiling, true);
+    PGOOpt = PGOOptions("", "", "", nullptr, PGOOptions::NoAction,
+                        PGOOptions::NoCSAction,
+                        CodeGenOpts.DebugInfoForProfiling, true);
   else if (CodeGenOpts.DebugInfoForProfiling)
     // -fdebug-info-for-profiling
-    PGOOpt = PGOOptions("", "", "", PGOOptions::NoAction,
+    PGOOpt = PGOOptions("", "", "", nullptr, PGOOptions::NoAction,
                         PGOOptions::NoCSAction, true);
 
   // Check to see if we want to generate a CS profile.
@@ -810,12 +814,13 @@ void EmitAssemblyHelper::RunOptimizationPipeline(
                                      : CodeGenOpts.InstrProfileOutput;
       PGOOpt->CSAction = PGOOptions::CSIRInstr;
     } else
-      PGOOpt = PGOOptions("",
-                          CodeGenOpts.InstrProfileOutput.empty()
-                              ? getDefaultProfileGenName()
-                              : CodeGenOpts.InstrProfileOutput,
-                          "", PGOOptions::NoAction, PGOOptions::CSIRInstr,
-                          CodeGenOpts.DebugInfoForProfiling);
+      PGOOpt =
+          PGOOptions("",
+                     CodeGenOpts.InstrProfileOutput.empty()
+                         ? getDefaultProfileGenName()
+                         : CodeGenOpts.InstrProfileOutput,
+                     "", nullptr, PGOOptions::NoAction, PGOOptions::CSIRInstr,
+                     CodeGenOpts.DebugInfoForProfiling);
   }
   if (TM)
     TM->setPGOOption(PGOOpt);
@@ -1219,9 +1224,9 @@ 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) {
 
   llvm::TimeTraceScope TimeScope("Backend");
@@ -1264,7 +1269,7 @@ void clang::EmitBackendOutput(DiagnosticsEngine &Diags,
     }
   }
 
-  EmitAssemblyHelper AsmHelper(Diags, HeaderOpts, CGOpts, TOpts, LOpts, M);
+  EmitAssemblyHelper AsmHelper(Diags, HeaderOpts, CGOpts, TOpts, LOpts, M, VFS);
   AsmHelper.EmitAssembly(Action, std::move(OS));
 
   // Verify clang's TargetInfo DataLayout against the LLVM TargetMachine's
diff --git a/clang/lib/CodeGen/CodeGenAction.cpp b/clang/lib/CodeGen/CodeGenAction.cpp
index 2b21926..1d69221 100644
--- a/clang/lib/CodeGen/CodeGenAction.cpp
+++ b/clang/lib/CodeGen/CodeGenAction.cpp
@@ -115,6 +115,7 @@ namespace clang {
     const LangOptions &LangOpts;
     std::unique_ptr<raw_pwrite_stream> AsmOutStream;
     ASTContext *Context;
+    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS;
 
     Timer LLVMIRGeneration;
     unsigned LLVMIRGenerationRefCount;
@@ -147,7 +148,7 @@ 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 +159,10 @@ namespace clang {
                     CoverageSourceInfo *CoverageInfo = nullptr)
         : Diags(Diags), Action(Action), HeaderSearchOpts(HeaderSearchOpts),
           CodeGenOpts(CodeGenOpts), TargetOpts(TargetOpts), LangOpts(LangOpts),
-          AsmOutStream(std::move(OS)), Context(nullptr),
+          AsmOutStream(std::move(OS)), Context(nullptr), FS(VFS),
           LLVMIRGeneration("irgen", "LLVM IR Generation Time"),
           LLVMIRGenerationRefCount(0),
-          Gen(CreateLLVMCodeGen(Diags, InFile, std::move(FS), HeaderSearchOpts,
+          Gen(CreateLLVMCodeGen(Diags, InFile, std::move(VFS), HeaderSearchOpts,
                                 PPOpts, CodeGenOpts, C, CoverageInfo)),
           LinkModules(std::move(LinkModules)) {
       TimerIsEnabled = CodeGenOpts.TimePasses;
@@ -173,7 +174,7 @@ 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 +184,10 @@ namespace clang {
                     CoverageSourceInfo *CoverageInfo = nullptr)
         : Diags(Diags), Action(Action), HeaderSearchOpts(HeaderSearchOpts),
           CodeGenOpts(CodeGenOpts), TargetOpts(TargetOpts), LangOpts(LangOpts),
-          Context(nullptr),
+          Context(nullptr), FS(VFS),
           LLVMIRGeneration("irgen", "LLVM IR Generation Time"),
           LLVMIRGenerationRefCount(0),
-          Gen(CreateLLVMCodeGen(Diags, "", std::move(FS), HeaderSearchOpts,
+          Gen(CreateLLVMCodeGen(Diags, "", std::move(VFS), HeaderSearchOpts,
                                 PPOpts, CodeGenOpts, C, CoverageInfo)),
           LinkModules(std::move(LinkModules)), CurLinkModule(Module) {
       TimerIsEnabled = CodeGenOpts.TimePasses;
@@ -381,7 +382,7 @@ namespace clang {
 
       EmitBackendOutput(Diags, HeaderSearchOpts, CodeGenOpts, TargetOpts,
                         LangOpts, C.getTargetInfo().getDataLayoutString(),
-                        getModule(), Action, std::move(AsmOutStream));
+                        getModule(), Action, FS, std::move(AsmOutStream));
 
       Ctx.setDiagnosticHandler(std::move(OldDiagnosticHandler));
 
@@ -1238,10 +1239,10 @@ 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,
-                    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
index 38e6ec6..24b6337 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -107,11 +107,11 @@ CodeGenModule::CodeGenModule(ASTContext &C,
                              const CodeGenOptions &CGO, llvm::Module &M,
                              DiagnosticsEngine &diags,
                              CoverageSourceInfo *CoverageInfo)
-    : Context(C), LangOpts(C.getLangOpts()), FS(std::move(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();
@@ -185,7 +185,8 @@ CodeGenModule::CodeGenModule(ASTContext &C,
 
   if (CodeGenOpts.hasProfileClangUse()) {
     auto ReaderOrErr = llvm::IndexedInstrProfReader::create(
-        CodeGenOpts.ProfileInstrumentUsePath, CodeGenOpts.ProfileRemappingFile);
+        CodeGenOpts.ProfileInstrumentUsePath, *FS,
+        CodeGenOpts.ProfileRemappingFile);
     // We're checking for profile read errors in CompilerInvocation, so if
     // there was an error it should've already been caught. If it hasn't been
     // somehow, trip an assertion.
diff --git a/clang/lib/CodeGen/ObjectFilePCHContainerOperations.cpp b/clang/lib/CodeGen/ObjectFilePCHContainerOperations.cpp
index 677b66d..2f2126e 100644
--- a/clang/lib/CodeGen/ObjectFilePCHContainerOperations.cpp
+++ b/clang/lib/CodeGen/ObjectFilePCHContainerOperations.cpp
@@ -320,7 +320,7 @@ public:
       clang::EmitBackendOutput(
           Diags, HeaderSearchOpts, CodeGenOpts, TargetOpts, LangOpts,
           Ctx.getTargetInfo().getDataLayoutString(), M.get(),
-          BackendAction::Backend_EmitLL,
+          BackendAction::Backend_EmitLL, FS,
           std::make_unique<llvm::raw_svector_ostream>(Buffer));
       llvm::dbgs() << Buffer;
     });
@@ -329,7 +329,7 @@ public:
     clang::EmitBackendOutput(Diags, HeaderSearchOpts, CodeGenOpts, TargetOpts,
                              LangOpts,
                              Ctx.getTargetInfo().getDataLayoutString(), M.get(),
-                             BackendAction::Backend_EmitObj, std::move(OS));
+                             BackendAction::Backend_EmitObj, FS, std::move(OS));
 
     // Free the memory for the temporary buffer.
     llvm::SmallVector<char, 0> Empty;
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 0bb9c8c..ed483d2 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -1304,8 +1304,9 @@ static std::string serializeXRayInstrumentationBundle(const XRayInstrSet &S) {
 // Set the profile kind using fprofile-instrument-use-path.
 static void setPGOUseInstrumentor(CodeGenOptions &Opts,
                                   const Twine &ProfileName,
+                                  llvm::vfs::FileSystem &FS,
                                   DiagnosticsEngine &Diags) {
-  auto ReaderOrErr = llvm::IndexedInstrProfReader::create(ProfileName);
+  auto ReaderOrErr = llvm::IndexedInstrProfReader::create(ProfileName, FS);
   if (auto E = ReaderOrErr.takeError()) {
     unsigned DiagID = Diags.getCustomDiagID(DiagnosticsEngine::Error,
                                             "Error in reading profile %0: %1");
@@ -1724,9 +1725,6 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
             : codegenoptions::DebugTemplateNamesKind::Mangled);
   }
 
-  if (!Opts.ProfileInstrumentUsePath.empty())
-    setPGOUseInstrumentor(Opts, Opts.ProfileInstrumentUsePath, Diags);
-
   if (const Arg *A = Args.getLastArg(OPT_ftime_report, OPT_ftime_report_EQ)) {
     Opts.TimePasses = true;
 
@@ -1962,8 +1960,8 @@ 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
@@ -4563,6 +4561,17 @@ bool CompilerInvocation::CreateFromArgsImpl(
     append_range(Res.getCodeGenOpts().CommandLineArgs, CommandLineArgs);
   }
 
+  // Set PGOOptions. Need to create a temporary VFS to read the profile
+  // to determine the PGO type.
+  if (!Res.getCodeGenOpts().ProfileInstrumentUsePath.empty()) {
+    auto FS =
+        createVFSFromOverlayFiles(Res.getHeaderSearchOpts().VFSOverlayFiles,
+                                  Diags, llvm::vfs::getRealFileSystem());
+    setPGOUseInstrumentor(Res.getCodeGenOpts(),
+                          Res.getCodeGenOpts().ProfileInstrumentUsePath, *FS,
+                          Diags);
+  }
+
   FixupInvocation(Res, Diags, Args, DashX);
 
   return Diags.getNumErrors() == NumErrorsBefore;