[MC] Function stack size section.

Re applying after fixing issues in the diff, sorry for any painful conflicts/merges!

Original RFC: http://lists.llvm.org/pipermail/llvm-dev/2017-August/117028.html

This change adds a '.stack-size' section containing metadata on function stack sizes to output ELF files behind the new -stack-size-section flag. The section contains pairs of function symbol references (8 byte) and stack sizes (unsigned LEB128).

The contents of this section can be used to measure changes to stack sizes between different versions of the compiler or a source base. The advantage of having a section is that we can extract this information when examining binaries that we didn't build, and it allows users and tools easy access to that information just by referencing the binary.

There is a follow up change to add an option to clang.

Thanks.

Reviewers: hfinkel, MatzeB

Reviewed By: MatzeB

Subscribers: thegameg, asb, llvm-commits

Differential Revision: https://reviews.llvm.org/D39788

llvm-svn: 319430

llvm/docs/CodeGenerator.rst

@@ -1578,6 +1578,17 @@ which lowers MCInst's into machine code bytes and relocations.  This is
 important if you want to support direct .o file emission, or would like to
 implement an assembler for your target.
 
+Emitting function stack size information
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+A section containing metadata on function stack sizes will be emitted when
+``TargetLoweringObjectFile::StackSizesSection`` is not null, and
+``TargetOptions::EmitStackSizeSection`` is set (-stack-size-section). The
+section will contain an array of pairs of function symbol references (8 byte)
+and stack sizes (unsigned LEB128). The stack size values only include the space
+allocated in the function prologue. Functions with dynamic stack allocations are
+not included.
+
 VLIW Packetizer
 ---------------
 

llvm/docs/CommandGuide/llc.rst

@@ -132,6 +132,14 @@ End-user Options
  Specify which EABI version should conform to.  Valid EABI versions are *gnu*,
  *4* and *5*.  Default value (*default*) depends on the triple.
 
+.. option:: -stack-size-section
+
+ Emit the .stack_sizes section which contains stack size metadata. The section
+ contains an array of pairs of function symbol references (8 byte) and stack
+ sizes (unsigned LEB128). The stack size values only include the space allocated
+ in the function prologue. Functions with dynamic stack allocations are not
+ included.
+
 
 Tuning/Configuration Options
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

llvm/include/llvm/CodeGen/AsmPrinter.h

@@ -295,6 +295,8 @@ class AsmPrinter : public MachineFunctionPass {
 
   void emitFrameAlloc(const MachineInstr &MI);
 
+  void emitStackSizeSection(const MachineFunction &MF);
+
   enum CFIMoveType { CFI_M_None, CFI_M_EH, CFI_M_Debug };
   CFIMoveType needsCFIMoves() const;
 

llvm/include/llvm/CodeGen/CommandFlags.def

@@ -255,6 +255,10 @@ static cl::opt<DebuggerKind> DebuggerTuningOpt(
                clEnumValN(DebuggerKind::LLDB, "lldb", "lldb"),
                clEnumValN(DebuggerKind::SCE, "sce", "SCE targets (e.g. PS4)")));
 
+static cl::opt<bool> EnableStackSizeSection(
+    "stack-size-section",
+    cl::desc("Emit a section containing stack size metadata"), cl::init(false));
+
 // Common utility function tightly tied to the options listed here. Initializes
 // a TargetOptions object with CodeGen flags and returns it.
 static TargetOptions InitTargetOptionsFromCodeGenFlags() {
@@ -281,6 +285,7 @@ static TargetOptions InitTargetOptionsFromCodeGenFlags() {
   Options.UniqueSectionNames = UniqueSectionNames;
   Options.EmulatedTLS = EmulatedTLS;
   Options.ExceptionModel = ExceptionModel;
+  Options.EmitStackSizeSection = EnableStackSizeSection;
 
   Options.MCOptions = InitMCTargetOptionsFromFlags();
 

llvm/include/llvm/MC/MCObjectFileInfo.h

@@ -154,6 +154,9 @@ class MCObjectFileInfo {
   /// It is initialized on demand so it can be overwritten (with uniquing).
   MCSection *EHFrameSection;
 
+  /// Section containing metadata on function stack sizes.
+  MCSection *StackSizesSection;
+
   // ELF specific sections.
   MCSection *DataRelROSection;
   MCSection *MergeableConst4Section;
@@ -287,6 +290,8 @@ class MCObjectFileInfo {
   MCSection *getStackMapSection() const { return StackMapSection; }
   MCSection *getFaultMapSection() const { return FaultMapSection; }
 
+  MCSection *getStackSizesSection() const { return StackSizesSection; }
+
   // ELF specific sections.
   MCSection *getDataRelROSection() const { return DataRelROSection; }
   const MCSection *getMergeableConst4Section() const {

llvm/include/llvm/Target/TargetOptions.h

@@ -108,7 +108,7 @@ namespace llvm {
           DisableIntegratedAS(false), RelaxELFRelocations(false),
           FunctionSections(false), DataSections(false),
           UniqueSectionNames(true), TrapUnreachable(false), EmulatedTLS(false),
-          EnableIPRA(false) {}
+          EnableIPRA(false), EmitStackSizeSection(false) {}
 
     /// PrintMachineCode - This flag is enabled when the -print-machineinstrs
     /// option is specified on the command line, and should enable debugging
@@ -216,6 +216,9 @@ namespace llvm {
     /// This flag enables InterProcedural Register Allocation (IPRA).
     unsigned EnableIPRA : 1;
 
+    /// Emit section containing metadata on function stack sizes.
+    unsigned EmitStackSizeSection : 1;
+
     /// FloatABIType - This setting is set by -float-abi=xxx option is specfied
     /// on the command line. This setting may either be Default, Soft, or Hard.
     /// Default selects the target's default behavior. Soft selects the ABI for

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -964,6 +964,31 @@ void AsmPrinter::emitFrameAlloc(const MachineInstr &MI) {
                              MCConstantExpr::create(FrameOffset, OutContext));
 }
 
+void AsmPrinter::emitStackSizeSection(const MachineFunction &MF) {
+  if (!MF.getTarget().Options.EmitStackSizeSection)
+    return;
+
+  MCSection *StackSizeSection = getObjFileLowering().getStackSizesSection();
+  if (!StackSizeSection)
+    return;
+
+  const MachineFrameInfo &FrameInfo = MF.getFrameInfo();
+  // Don't emit functions with dynamic stack allocations.
+  if (FrameInfo.hasVarSizedObjects())
+    return;
+
+  OutStreamer->PushSection();
+  OutStreamer->SwitchSection(StackSizeSection);
+
+  const MCSymbol *FunctionSymbol = getSymbol(MF.getFunction());
+  uint64_t StackSize = FrameInfo.getStackSize();
+  OutStreamer->EmitValue(MCSymbolRefExpr::create(FunctionSymbol, OutContext),
+                         /* size = */ 8);
+  OutStreamer->EmitULEB128IntValue(StackSize);
+
+  OutStreamer->PopSection();
+}
+
 static bool needFuncLabelsForEHOrDebugInfo(const MachineFunction &MF,
                                            MachineModuleInfo *MMI) {
   if (!MF.getLandingPads().empty() || MF.hasEHFunclets() || MMI->hasDebugInfo())
@@ -1135,6 +1160,9 @@ void AsmPrinter::EmitFunctionBody() {
     HI.Handler->endFunction(MF);
   }
 
+  // Emit section containing stack size metadata.
+  emitStackSizeSection(*MF);
+
   if (isVerbose())
     OutStreamer->GetCommentOS() << "-- End function\n";
 

llvm/lib/MC/MCObjectFileInfo.cpp

@@ -594,6 +594,8 @@ void MCObjectFileInfo::initELFMCObjectFileInfo(const Triple &T, bool Large) {
 
   EHFrameSection =
       Ctx->getELFSection(".eh_frame", EHSectionType, EHSectionFlags);
+
+  StackSizesSection = Ctx->getELFSection(".stack_sizes", ELF::SHT_PROGBITS, 0);
 }
 
 void MCObjectFileInfo::initCOFFMCObjectFileInfo(const Triple &T) {

llvm/test/CodeGen/X86/stack-size-section.ll

@@ -0,0 +1,30 @@
+; RUN: llc < %s -mtriple=x86_64-linux -stack-size-section | FileCheck %s
+
+; CHECK-LABEL: func1:
+; CHECK: .section .stack_sizes,"",@progbits
+; CHECK-NEXT: .quad func1
+; CHECK-NEXT: .byte 8
+define void @func1(i32, i32) #0 {
+  alloca i32, align 4
+  alloca i32, align 4
+  ret void
+}
+
+; CHECK-LABEL: func2:
+; CHECK: .section .stack_sizes,"",@progbits
+; CHECK-NEXT: .quad func2
+; CHECK-NEXT: .byte 24
+define void @func2() #0 {
+  alloca i32, align 4
+  call void @func1(i32 1, i32 2)
+  ret void
+}
+
+; CHECK-LABEL: dynalloc:
+; CHECK-NOT: .section .stack_sizes
+define void @dynalloc(i32 %N) #0 {
+  alloca i32, i32 %N
+  ret void
+}
+
+attributes #0 = { "no-frame-pointer-elim"="true" }