[ExtendLifetimes] Add extend lifetimes to emit fake uses from clang

clang/include/clang/Basic/CodeGenOptions.def

@@ -387,6 +387,12 @@ CODEGENOPT(EnableTLSDESC, 1, 0)
 /// Bit size of immediate TLS offsets (0 == use the default).
 VALUE_CODEGENOPT(TLSSize, 8, 0)
 
+/// Whether to extend the live range of the `this` pointer.
+CODEGENOPT(ExtendThisPtr, 1, 0)
+
+/// Whether to extend the live ranges of all local variables.
+CODEGENOPT(ExtendLifetimes, 1, 0)
+
 /// The default stack protector guard offset to use.
 VALUE_CODEGENOPT(StackProtectorGuardOffset, 32, INT_MAX)
 

clang/include/clang/Driver/Options.td

@@ -4243,6 +4243,15 @@ def stack_usage_file : Separate<["-"], "stack-usage-file">,
   Visibility<[CC1Option]>,
   HelpText<"Filename (or -) to write stack usage output to">,
   MarshallingInfoString<CodeGenOpts<"StackUsageOutput">>;
+def fextend_this_ptr : Flag <["-"], "fextend-this-ptr">, Group<f_Group>,
+  MarshallingInfoFlag<CodeGenOpts<"ExtendThisPtr">>,
+  HelpText<"Extend the lifetime of the 'this' pointer to improve visibility "
+           "in optimized debugging">, Visibility<[ClangOption, CC1Option]>;
+def fextend_lifetimes : Flag <["-"], "fextend-lifetimes">, Group<f_Group>,
+  MarshallingInfoFlag<CodeGenOpts<"ExtendLifetimes">>,
+  HelpText<"Extend the lifetimes of local variables and parameters to improve "
+           "visibility in optimized debugging">,
+           Visibility<[ClangOption, CC1Option]>;
 
 defm unique_basic_block_section_names : BoolFOption<"unique-basic-block-section-names",
   CodeGenOpts<"UniqueBasicBlockSectionNames">, DefaultFalse,

clang/lib/CodeGen/CGCall.cpp

@@ -2543,6 +2543,10 @@ void CodeGenModule::ConstructAttributeList(StringRef Name,
     if (shouldDisableTailCalls())
       FuncAttrs.addAttribute("disable-tail-calls", "true");
 
+    // Suppress the machine instruction scheduler when -fextend-lifetimes is on.
+    if (CodeGenOpts.ExtendLifetimes)
+      FuncAttrs.addAttribute(llvm::Attribute::OptimizeForDebugging);
+
     // CPU/feature overrides.  addDefaultFunctionDefinitionAttributes
     // handles these separately to set them based on the global defaults.
     GetCPUAndFeaturesAttributes(CalleeInfo.getCalleeDecl(), FuncAttrs);
@@ -3558,15 +3562,26 @@ static llvm::StoreInst *findDominatingStoreToReturnValue(CodeGenFunction &CGF) {
     llvm::BasicBlock *IP = CGF.Builder.GetInsertBlock();
     if (IP->empty()) return nullptr;
 
-    // Look at directly preceding instruction, skipping bitcasts and lifetime
-    // markers.
+    // Look at directly preceding instruction, skipping bitcasts, lifetime
+    // markers, and fake uses and their operands.
+    const llvm::Instruction *LoadIntoFakeUse = nullptr;
     for (llvm::Instruction &I : make_range(IP->rbegin(), IP->rend())) {
+      // Ignore instructions are just loads for fake uses; the load should
+      // immediately precede the fake use, so we only need to remember the
+      // operand for the last fake use seen.
+      if (LoadIntoFakeUse == &I)
+        continue;
       if (isa<llvm::BitCastInst>(&I))
         continue;
-      if (auto *II = dyn_cast<llvm::IntrinsicInst>(&I))
+      if (auto *II = dyn_cast<llvm::IntrinsicInst>(&I)) {
         if (II->getIntrinsicID() == llvm::Intrinsic::lifetime_end)
           continue;
 
+        if (II->getIntrinsicID() == llvm::Intrinsic::fake_use) {
+          LoadIntoFakeUse = dyn_cast<llvm::Instruction>(II->getArgOperand(0));
+          continue;
+        }
+      }
       return GetStoreIfValid(&I);
     }
     return nullptr;

clang/lib/CodeGen/CGCleanup.cpp

@@ -112,11 +112,11 @@ void EHScopeStack::deallocate(size_t Size) {
   StartOfData += llvm::alignTo(Size, ScopeStackAlignment);
 }
 
-bool EHScopeStack::containsOnlyLifetimeMarkers(
+bool EHScopeStack::containsOnlyNoopCleanups(
     EHScopeStack::stable_iterator Old) const {
   for (EHScopeStack::iterator it = begin(); stabilize(it) != Old; it++) {
     EHCleanupScope *cleanup = dyn_cast<EHCleanupScope>(&*it);
-    if (!cleanup || !cleanup->isLifetimeMarker())
+    if (!cleanup || !(cleanup->isLifetimeMarker() || cleanup->isFakeUse()))
       return false;
   }
 
@@ -154,6 +154,7 @@ void *EHScopeStack::pushCleanup(CleanupKind Kind, size_t Size) {
   bool IsNormalCleanup = Kind & NormalCleanup;
   bool IsEHCleanup = Kind & EHCleanup;
   bool IsLifetimeMarker = Kind & LifetimeMarker;
+  bool IsFakeUse = Kind & FakeUse;
 
   // Per C++ [except.terminate], it is implementation-defined whether none,
   // some, or all cleanups are called before std::terminate. Thus, when
@@ -176,6 +177,8 @@ void *EHScopeStack::pushCleanup(CleanupKind Kind, size_t Size) {
     InnermostEHScope = stable_begin();
   if (IsLifetimeMarker)
     Scope->setLifetimeMarker();
+  if (IsFakeUse)
+    Scope->setFakeUse();
 
   // With Windows -EHa, Invoke llvm.seh.scope.begin() for EHCleanup
   // If exceptions are disabled/ignored and SEH is not in use, then there is no

clang/lib/CodeGen/CGCleanup.h

@@ -87,6 +87,9 @@ class EHScope {
     LLVM_PREFERRED_TYPE(bool)
     unsigned IsLifetimeMarker : 1;
 
+    /// Whether this cleanup is a fake use
+    unsigned IsFakeUse : 1;
+
     /// Whether the normal cleanup should test the activation flag.
     LLVM_PREFERRED_TYPE(bool)
     unsigned TestFlagInNormalCleanup : 1;
@@ -352,6 +355,7 @@ class alignas(8) EHCleanupScope : public EHScope {
     CleanupBits.IsEHCleanup = isEH;
     CleanupBits.IsActive = true;
     CleanupBits.IsLifetimeMarker = false;
+    CleanupBits.IsFakeUse = false;
     CleanupBits.TestFlagInNormalCleanup = false;
     CleanupBits.TestFlagInEHCleanup = false;
     CleanupBits.CleanupSize = cleanupSize;
@@ -384,6 +388,9 @@ class alignas(8) EHCleanupScope : public EHScope {
   bool isLifetimeMarker() const { return CleanupBits.IsLifetimeMarker; }
   void setLifetimeMarker() { CleanupBits.IsLifetimeMarker = true; }
 
+  bool isFakeUse() const { return CleanupBits.IsFakeUse; }
+  void setFakeUse() { CleanupBits.IsFakeUse = true; }
+
   bool hasActiveFlag() const { return ActiveFlag.isValid(); }
   Address getActiveFlag() const {
     return ActiveFlag;

clang/lib/CodeGen/CGDecl.cpp

@@ -1353,6 +1353,14 @@ void CodeGenFunction::EmitLifetimeEnd(llvm::Value *Size, llvm::Value *Addr) {
   C->setDoesNotThrow();
 }
 
+void CodeGenFunction::EmitFakeUse(Address Addr) {
+  auto NL = ApplyDebugLocation::CreateEmpty(*this);
+  llvm::Value *V = Builder.CreateLoad(Addr, "fake.use");
+  llvm::CallInst *C = Builder.CreateCall(CGM.getLLVMFakeUseFn(), {V});
+  C->setDoesNotThrow();
+  C->setTailCallKind(llvm::CallInst::TCK_NoTail);
+}
+
 void CodeGenFunction::EmitAndRegisterVariableArrayDimensions(
     CGDebugInfo *DI, const VarDecl &D, bool EmitDebugInfo) {
   // For each dimension stores its QualType and corresponding
@@ -1412,6 +1420,39 @@ void CodeGenFunction::EmitAndRegisterVariableArrayDimensions(
   }
 }
 
+/// Return the maximum size of an aggregate for which we generate a fake use
+/// intrinsic when -fextend-lifetimes is in effect.
+static uint64_t maxFakeUseAggregateSize(const ASTContext &C) {
+  return 4 * C.getTypeSize(C.UnsignedIntTy);
+}
+
+// Helper function to determine whether a variable's or parameter's lifetime
+// should be extended.
+static bool extendLifetime(const ASTContext &Context, const Decl *FuncDecl,
+                           const VarDecl &D,
+                           ImplicitParamDecl *CXXABIThisDecl) {
+  // When we're not inside a valid function it is unlikely that any
+  // lifetime extension is useful.
+  if (!FuncDecl)
+    return false;
+  if (FuncDecl->isImplicit())
+    return false;
+  // Do not extend compiler-created variables except for the this pointer.
+  if (D.isImplicit() && &D != CXXABIThisDecl)
+    return false;
+  QualType Ty = D.getType();
+  // No need to extend volatiles, they have a memory location.
+  if (Ty.isVolatileQualified())
+    return false;
+  // Don't extend variables that exceed a certain size.
+  if (Context.getTypeSize(Ty) > maxFakeUseAggregateSize(Context))
+    return false;
+  // Do not extend variables in nodebug functions.
+  if (FuncDecl->hasAttr<NoDebugAttr>())
+    return false;
+  return true;
+}
+
 /// EmitAutoVarAlloca - Emit the alloca and debug information for a
 /// local variable.  Does not emit initialization or destruction.
 CodeGenFunction::AutoVarEmission
@@ -1664,6 +1705,17 @@ CodeGenFunction::EmitAutoVarAlloca(const VarDecl &D) {
                                          emission.getOriginalAllocatedAddress(),
                                          emission.getSizeForLifetimeMarkers());
 
+  // Analogous to lifetime markers, we use a 'cleanup' to emit fake.use
+  // calls for local variables. We are exempting volatile variables and
+  // non-scalars larger than 4 times the size of an unsigned int (32 bytes).
+  // Larger non-scalars are often allocated in memory and may create unnecessary
+  // overhead.
+  if (CGM.getCodeGenOpts().ExtendLifetimes) {
+    if (extendLifetime(getContext(), CurCodeDecl, D, CXXABIThisDecl))
+      EHStack.pushCleanup<FakeUse>(NormalFakeUse,
+                                   emission.getAllocatedAddress());
+  }
+
   return emission;
 }
 
@@ -2523,6 +2575,15 @@ llvm::Function *CodeGenModule::getLLVMLifetimeEndFn() {
   return LifetimeEndFn;
 }
 
+/// Lazily declare the @llvm.fake.use intrinsic.
+llvm::Function *CodeGenModule::getLLVMFakeUseFn() {
+  if (FakeUseFn)
+    return FakeUseFn;
+  FakeUseFn =
+      llvm::Intrinsic::getDeclaration(&getModule(), llvm::Intrinsic::fake_use);
+  return FakeUseFn;
+}
+
 namespace {
   /// A cleanup to perform a release of an object at the end of a
   /// function.  This is used to balance out the incoming +1 of a
@@ -2716,6 +2777,15 @@ void CodeGenFunction::EmitParmDecl(const VarDecl &D, ParamValue Arg,
 
   setAddrOfLocalVar(&D, DeclPtr);
 
+  // Push a FakeUse 'cleanup' object onto the EHStack for the parameter,
+  // which may be the 'this' pointer. This causes the emission of a fake.use
+  // call with the parameter as argument at the end of the function.
+  if (CGM.getCodeGenOpts().ExtendLifetimes ||
+      (CGM.getCodeGenOpts().ExtendThisPtr && &D == CXXABIThisDecl)) {
+    if (extendLifetime(getContext(), CurCodeDecl, D, CXXABIThisDecl))
+      EHStack.pushCleanup<FakeUse>(NormalFakeUse, DeclPtr);
+  }
+
   // Emit debug info for param declarations in non-thunk functions.
   if (CGDebugInfo *DI = getDebugInfo()) {
     if (CGM.getCodeGenOpts().hasReducedDebugInfo() && !CurFuncIsThunk &&

clang/lib/CodeGen/CodeGenFunction.cpp

@@ -403,9 +403,9 @@ void CodeGenFunction::FinishFunction(SourceLocation EndLoc) {
   // important to do this before we enter the return block or return
   // edges will be *really* confused.
   bool HasCleanups = EHStack.stable_begin() != PrologueCleanupDepth;
-  bool HasOnlyLifetimeMarkers =
-      HasCleanups && EHStack.containsOnlyLifetimeMarkers(PrologueCleanupDepth);
-  bool EmitRetDbgLoc = !HasCleanups || HasOnlyLifetimeMarkers;
+  bool HasOnlyNoopCleanups =
+      HasCleanups && EHStack.containsOnlyNoopCleanups(PrologueCleanupDepth);
+  bool EmitRetDbgLoc = !HasCleanups || HasOnlyNoopCleanups;
 
   std::optional<ApplyDebugLocation> OAL;
   if (HasCleanups) {

clang/lib/CodeGen/CodeGenFunction.h

@@ -718,6 +718,20 @@ class CodeGenFunction : public CodeGenTypeCache {
     }
   };
 
+  // We are using objects of this 'cleanup' class to emit fake.use calls
+  // for -fextend-lifetimes and -fextend-this-ptr. They are placed at the end of
+  // a variable's scope analogous to lifetime markers.
+  class FakeUse final : public EHScopeStack::Cleanup {
+    Address Addr;
+
+  public:
+    FakeUse(Address addr) : Addr(addr) {}
+
+    void Emit(CodeGenFunction &CGF, Flags flags) override {
+      CGF.EmitFakeUse(Addr);
+    }
+  };
+
   /// Header for data within LifetimeExtendedCleanupStack.
   struct LifetimeExtendedCleanupHeader {
     /// The size of the following cleanup object.
@@ -4966,6 +4980,8 @@ class CodeGenFunction : public CodeGenTypeCache {
 
   RValue EmitAtomicExpr(AtomicExpr *E);
 
+  void EmitFakeUse(Address Addr);
+
   //===--------------------------------------------------------------------===//
   //                         Annotations Emission
   //===--------------------------------------------------------------------===//

clang/lib/CodeGen/CodeGenModule.h

@@ -601,6 +601,9 @@ class CodeGenModule : public CodeGenTypeCache {
   /// void @llvm.lifetime.end(i64 %size, i8* nocapture <ptr>)
   llvm::Function *LifetimeEndFn = nullptr;
 
+  /// void @llvm.fake.use(i8* nocapture <ptr>)
+  llvm::Function *FakeUseFn = nullptr;
+
   std::unique_ptr<SanitizerMetadata> SanitizerMD;
 
   llvm::MapVector<const Decl *, bool> DeferredEmptyCoverageMappingDecls;
@@ -1268,6 +1271,7 @@ class CodeGenModule : public CodeGenTypeCache {
 
   llvm::Function *getLLVMLifetimeStartFn();
   llvm::Function *getLLVMLifetimeEndFn();
+  llvm::Function *getLLVMFakeUseFn();
 
   // Make sure that this type is translated.
   void UpdateCompletedType(const TagDecl *TD);

clang/lib/CodeGen/EHScopeStack.h

@@ -87,6 +87,11 @@ enum CleanupKind : unsigned {
 
   LifetimeMarker = 0x8,
   NormalEHLifetimeMarker = LifetimeMarker | NormalAndEHCleanup,
+
+  // FakeUse needs to be recognized as a special cleanup similar to lifetime
+  // markers chiefly to be ignored in most contexts.
+  FakeUse = 0x10,
+  NormalFakeUse = FakeUse | NormalCleanup,
 };
 
 /// A stack of scopes which respond to exceptions, including cleanups
@@ -352,8 +357,8 @@ class EHScopeStack {
   void popTerminate();
 
   // Returns true iff the current scope is either empty or contains only
-  // lifetime markers, i.e. no real cleanup code
-  bool containsOnlyLifetimeMarkers(stable_iterator Old) const;
+  // noop cleanups, i.e. lifetime markers and fake uses.
+  bool containsOnlyNoopCleanups(stable_iterator Old) const;
 
   /// Determines whether the exception-scopes stack is empty.
   bool empty() const { return StartOfData == EndOfBuffer; }

clang/lib/Driver/ToolChains/Clang.cpp

@@ -7581,6 +7581,11 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   if (Args.hasArg(options::OPT_fretain_comments_from_system_headers))
     CmdArgs.push_back("-fretain-comments-from-system-headers");
 
+  if (Args.hasArg(options::OPT_fextend_this_ptr))
+    CmdArgs.push_back("-fextend-this-ptr");
+  if (Args.hasArg(options::OPT_fextend_lifetimes))
+    CmdArgs.push_back("-fextend-lifetimes");
+
   // Forward -fcomment-block-commands to -cc1.
   Args.AddAllArgs(CmdArgs, options::OPT_fcomment_block_commands);
   // Forward -fparse-all-comments to -cc1.

clang/lib/Frontend/CompilerInvocation.cpp

@@ -2219,6 +2219,11 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
                       Args.getAllArgValues(OPT_fsanitize_trap_EQ), Diags,
                       Opts.SanitizeTrap);
 
+  Opts.ExtendThisPtr =
+      Opts.OptimizationLevel > 0 && Args.hasArg(OPT_fextend_this_ptr);
+  Opts.ExtendLifetimes =
+      Opts.OptimizationLevel > 0 && Args.hasArg(OPT_fextend_lifetimes);
+
   Opts.EmitVersionIdentMetadata = Args.hasFlag(OPT_Qy, OPT_Qn, true);
 
   if (!LangOpts->CUDAIsDevice)

clang/test/CodeGen/extend-lifetimes-optdebug.c

@@ -0,0 +1,8 @@
+// RUN: %clang_cc1 %s -emit-llvm -O2 -fextend-lifetimes -o - | FileCheck %s
+
+// Emit the function attribute disable-post-ra when
+// -fextend-lifetimes is on.
+
+// CHECK: attributes #0 = {{{.*}}optdebug
+
+void foo() {}

clang/test/CodeGen/extend-liveness1.c

@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 %s -O2 -emit-llvm -fextend-lifetimes -o - | FileCheck %s
+// Check that fake use calls are emitted at the correct locations, i.e.
+// at the end of lexical blocks and at the end of the function.
+
+extern int use(int);
+int glob1;
+int glob2;
+float globf;
+
+int foo(int i) {
+  // CHECK: define{{.*}}foo
+  if (i < 4) {
+    int j = i * 3;
+    if (glob1 > 3) {
+      float f = globf;
+      // CHECK: [[SSAVAL:%[a-z0-9]*]] = load float{{.*}}globf
+      j = f;
+      glob2 = j;
+      // CHECK: store{{.*}}glob2
+      // CHECK-NEXT: call void (...) @llvm.fake.use(float [[SSAVAL]])
+    }
+    glob1 = j;
+    // CHECK: store{{.*}}glob1
+    // CHECK-NEXT: call void (...) @llvm.fake.use(i32 %j.
+  }
+  // CHECK: call void (...) @llvm.fake.use(i32 %i)
+  // CHECK-NEXT: ret
+  return 4;
+}