Add support for generating a call graph profile from Branch Frequency Info.

=== Generating the CG Profile ===

The CGProfile module pass simply gets the block profile count for each BB and scans for call instructions.  For each call instruction it adds an edge from the current function to the called function with the current BB block profile count as the weight.

After scanning all the functions, it generates an appending module flag containing the data. The format looks like:
```
!llvm.module.flags = !{!0}

!0 = !{i32 5, !"CG Profile", !1}
!1 = !{!2, !3, !4} ; List of edges
!2 = !{void ()* @a, void ()* @b, i64 32} ; Edge from a to b with a weight of 32
!3 = !{void (i1)* @freq, void ()* @a, i64 11}
!4 = !{void (i1)* @freq, void ()* @b, i64 20}
```

Differential Revision: https://reviews.llvm.org/D48105

llvm-svn: 335794

include/llvm/CodeGen/TargetLoweringObjectFileImpl.h

@@ -36,11 +36,14 @@ class TargetLoweringObjectFileELF : public TargetLoweringObjectFile {
 protected:
   MCSymbolRefExpr::VariantKind PLTRelativeVariantKind =
       MCSymbolRefExpr::VK_None;
+  const TargetMachine *TM;
 
 public:
   TargetLoweringObjectFileELF() = default;
   ~TargetLoweringObjectFileELF() override = default;
 
+  void Initialize(MCContext &Ctx, const TargetMachine &TM) override;
+
   /// Emit Obj-C garbage collection and linker options.
   void emitModuleMetadata(MCStreamer &Streamer, Module &M) const override;
 

include/llvm/Transforms/Instrumentation/CGProfile.h

@@ -0,0 +1,31 @@
+//===- Transforms/Instrumentation/CGProfile.h -------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This file provides the interface for LLVM's Call Graph Profile pass.
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_CGPROFILE_H
+#define LLVM_TRANSFORMS_CGPROFILE_H
+
+#include "llvm/ADT/MapVector.h"
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+class CGProfilePass : public PassInfoMixin<CGProfilePass> {
+public:
+  PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
+
+private:
+  void addModuleFlags(
+      Module &M,
+      MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) const;
+};
+} // end namespace llvm
+
+#endif // LLVM_TRANSFORMS_CGPROFILE_H

lib/CodeGen/TargetLoweringObjectFileImpl.cpp

@@ -91,6 +91,12 @@ static void GetObjCImageInfo(Module &M, unsigned &Version, unsigned &Flags,
 //                                  ELF
 //===----------------------------------------------------------------------===//
 
+void TargetLoweringObjectFileELF::Initialize(MCContext &Ctx,
+                                             const TargetMachine &TgtM) {
+  TargetLoweringObjectFile::Initialize(Ctx, TgtM);
+  TM = &TgtM;
+}
+
 void TargetLoweringObjectFileELF::emitModuleMetadata(MCStreamer &Streamer,
                                                      Module &M) const {
   auto &C = getContext();
@@ -116,15 +122,49 @@ void TargetLoweringObjectFileELF::emitModuleMetadata(MCStreamer &Streamer,
   StringRef Section;
 
   GetObjCImageInfo(M, Version, Flags, Section);
-  if (Section.empty())
+  if (!Section.empty()) {
+    auto *S = C.getELFSection(Section, ELF::SHT_PROGBITS, ELF::SHF_ALLOC);
+    Streamer.SwitchSection(S);
+    Streamer.EmitLabel(C.getOrCreateSymbol(StringRef("OBJC_IMAGE_INFO")));
+    Streamer.EmitIntValue(Version, 4);
+    Streamer.EmitIntValue(Flags, 4);
+    Streamer.AddBlankLine();
+  }
+
+  SmallVector<Module::ModuleFlagEntry, 8> ModuleFlags;
+  M.getModuleFlagsMetadata(ModuleFlags);
+
+  MDNode *CFGProfile = nullptr;
+
+  for (const auto &MFE : ModuleFlags) {
+    StringRef Key = MFE.Key->getString();
+    if (Key == "CG Profile") {
+      CFGProfile = cast<MDNode>(MFE.Val);
+      break;
+    }
+  }
+
+  if (!CFGProfile)
     return;
 
-  auto *S = C.getELFSection(Section, ELF::SHT_PROGBITS, ELF::SHF_ALLOC);
-  Streamer.SwitchSection(S);
-  Streamer.EmitLabel(C.getOrCreateSymbol(StringRef("OBJC_IMAGE_INFO")));
-  Streamer.EmitIntValue(Version, 4);
-  Streamer.EmitIntValue(Flags, 4);
-  Streamer.AddBlankLine();
+  auto GetSym = [this](const MDOperand &MDO) {
+    auto V = cast<ValueAsMetadata>(MDO);
+    const Function *F = cast<Function>(V->getValue());
+    return TM->getSymbol(F);
+  };
+
+  for (const auto &Edge : CFGProfile->operands()) {
+    MDNode *E = cast<MDNode>(Edge);
+    const MCSymbol *From = GetSym(E->getOperand(0));
+    const MCSymbol *To = GetSym(E->getOperand(1));
+    uint64_t Count = cast<ConstantAsMetadata>(E->getOperand(2))
+                         ->getValue()
+                         ->getUniqueInteger()
+                         .getZExtValue();
+    Streamer.emitCGProfileEntry(
+        MCSymbolRefExpr::create(From, MCSymbolRefExpr::VK_None, C),
+        MCSymbolRefExpr::create(To, MCSymbolRefExpr::VK_None, C), Count);
+  }
 }
 
 MCSymbol *TargetLoweringObjectFileELF::getCFIPersonalitySymbol(

lib/IR/Verifier.cpp

@@ -409,6 +409,7 @@ private:
   void visitModuleFlag(const MDNode *Op,
                        DenseMap<const MDString *, const MDNode *> &SeenIDs,
                        SmallVectorImpl<const MDNode *> &Requirements);
+  void visitModuleFlagCGProfileEntry(const MDOperand &MDO);
   void visitFunction(const Function &F);
   void visitBasicBlock(BasicBlock &BB);
   void visitRangeMetadata(Instruction &I, MDNode *Range, Type *Ty);
@@ -1411,6 +1412,25 @@ Verifier::visitModuleFlag(const MDNode *Op,
     Assert(M.getNamedMetadata("llvm.linker.options"),
            "'Linker Options' named metadata no longer supported");
   }
+
+  if (ID->getString() == "CG Profile") {
+    for (const MDOperand &MDO : cast<MDNode>(Op->getOperand(2))->operands())
+      visitModuleFlagCGProfileEntry(MDO);
+  }
+}
+
+void Verifier::visitModuleFlagCGProfileEntry(const MDOperand &MDO) {
+  auto Node = dyn_cast_or_null<MDNode>(MDO);
+  Assert(Node && Node->getNumOperands() == 3, "expected a MDNode triple", MDO);
+  auto From = dyn_cast_or_null<ValueAsMetadata>(Node->getOperand(0));
+  Assert(From && isa<Function>(From->getValue()), "expected a Function",
+         Node->getOperand(0));
+  auto To = dyn_cast_or_null<ValueAsMetadata>(Node->getOperand(1));
+  Assert(To && isa<Function>(To->getValue()), "expected a Function",
+         Node->getOperand(1));
+  auto Count = dyn_cast_or_null<ConstantAsMetadata>(Node->getOperand(2));
+  Assert(Count && Count->getType()->isIntegerTy(),
+         "expected an integer constant", Node->getOperand(2));
 }
 
 /// Return true if this attribute kind only applies to functions.

lib/Passes/PassBuilder.cpp

@@ -61,6 +61,7 @@
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/AggressiveInstCombine/AggressiveInstCombine.h"
 #include "llvm/Transforms/Instrumentation/GCOVProfiler.h"
+#include "llvm/Transforms/Instrumentation/CGProfile.h"
 #include "llvm/Transforms/IPO/AlwaysInliner.h"
 #include "llvm/Transforms/IPO/ArgumentPromotion.h"
 #include "llvm/Transforms/IPO/CalledValuePropagation.h"
@@ -832,6 +833,8 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
   // Add the core optimizing pipeline.
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(OptimizePM)));
 
+  MPM.addPass(CGProfilePass());
+
   // Now we need to do some global optimization transforms.
   // FIXME: It would seem like these should come first in the optimization
   // pipeline and maybe be the bottom of the canonicalization pipeline? Weird

lib/Passes/PassRegistry.def

@@ -40,6 +40,7 @@ MODULE_ALIAS_ANALYSIS("globals-aa", GlobalsAA())
 #endif
 MODULE_PASS("always-inline", AlwaysInlinerPass())
 MODULE_PASS("called-value-propagation", CalledValuePropagationPass())
+MODULE_PASS("cg-profile", CGProfilePass())
 MODULE_PASS("constmerge", ConstantMergePass())
 MODULE_PASS("cross-dso-cfi", CrossDSOCFIPass())
 MODULE_PASS("deadargelim", DeadArgumentEliminationPass())

lib/Transforms/Instrumentation/CGProfile.cpp

@@ -0,0 +1,100 @@
+//===-- CGProfile.cpp -----------------------------------------------------===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Instrumentation/CGProfile.h"
+
+#include "llvm/ADT/MapVector.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/IR/CallSite.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/ProfileData/InstrProf.h"
+#include "llvm/Transforms/Instrumentation.h"
+
+#include <array>
+
+using namespace llvm;
+
+PreservedAnalyses CGProfilePass::run(Module &M, ModuleAnalysisManager &MAM) {
+  MapVector<std::pair<Function *, Function *>, uint64_t> Counts;
+  FunctionAnalysisManager &FAM =
+      MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
+  InstrProfSymtab Symtab;
+  auto UpdateCounts = [&](TargetTransformInfo &TTI, Function *F,
+                          Function *CalledF, uint64_t NewCount) {
+    if (!CalledF || !TTI.isLoweredToCall(CalledF))
+      return;
+    uint64_t &Count = Counts[std::make_pair(F, CalledF)];
+    Count = SaturatingAdd(Count, NewCount);
+  };
+  // Ignore error here.  Indirect calls are ignored if this fails.
+  (bool)Symtab.create(M);
+  for (auto &F : M) {
+    if (F.isDeclaration())
+      continue;
+    auto &BFI = FAM.getResult<BlockFrequencyAnalysis>(F);
+    if (BFI.getEntryFreq() == 0)
+      continue;
+    TargetTransformInfo &TTI = FAM.getResult<TargetIRAnalysis>(F);
+    for (auto &BB : F) {
+      Optional<uint64_t> BBCount = BFI.getBlockProfileCount(&BB);
+      if (!BBCount)
+        continue;
+      for (auto &I : BB) {
+        CallSite CS(&I);
+        if (!CS)
+          continue;
+        if (CS.isIndirectCall()) {
+          InstrProfValueData ValueData[8];
+          uint32_t ActualNumValueData;
+          uint64_t TotalC;
+          if (!getValueProfDataFromInst(*CS.getInstruction(),
+                                        IPVK_IndirectCallTarget, 8, ValueData,
+                                        ActualNumValueData, TotalC))
+            continue;
+          for (const auto &VD :
+               ArrayRef<InstrProfValueData>(ValueData, ActualNumValueData)) {
+            UpdateCounts(TTI, &F, Symtab.getFunction(VD.Value), VD.Count);
+          }
+          continue;
+        }
+        UpdateCounts(TTI, &F, CS.getCalledFunction(), *BBCount);
+      }
+    }
+  }
+
+  addModuleFlags(M, Counts);
+
+  return PreservedAnalyses::all();
+}
+
+void CGProfilePass::addModuleFlags(
+    Module &M,
+    MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) const {
+  if (Counts.empty())
+    return;
+
+  LLVMContext &Context = M.getContext();
+  MDBuilder MDB(Context);
+  std::vector<Metadata *> Nodes;
+
+  for (auto E : Counts) {
+    SmallVector<Metadata *, 3> Vals;
+    Vals.push_back(ValueAsMetadata::get(E.first.first));
+    Vals.push_back(ValueAsMetadata::get(E.first.second));
+    Vals.push_back(MDB.createConstant(
+        ConstantInt::get(Type::getInt64Ty(Context), E.second)));
+    Nodes.push_back(MDNode::get(Context, Vals));
+  }
+
+  M.addModuleFlag(Module::Append, "CG Profile", MDNode::get(Context, Nodes));
+}

lib/Transforms/Instrumentation/CMakeLists.txt

@@ -1,6 +1,7 @@
 add_llvm_library(LLVMInstrumentation
   AddressSanitizer.cpp
   BoundsChecking.cpp
+  CGProfile.cpp
   DataFlowSanitizer.cpp
   GCOVProfiling.cpp
   MemorySanitizer.cpp

test/Instrumentation/cgprofile.ll

@@ -0,0 +1,41 @@
+; RUN: opt < %s -passes cg-profile -S | FileCheck %s
+
+declare void @b()
+
+define void @a() !prof !1 {
+  call void @b()
+  ret void
+}
+
+@foo = common global i32 ()* null, align 8
+declare i32 @func1()
+declare i32 @func2()
+declare i32 @func3()
+declare i32 @func4()
+
+define void @freq(i1 %cond) !prof !1 {
+  %tmp = load i32 ()*, i32 ()** @foo, align 8
+  call i32 %tmp(), !prof !3
+  br i1 %cond, label %A, label %B, !prof !2
+A:
+  call void @a();
+  ret void
+B:
+  call void @b();
+  ret void
+}
+
+!1 = !{!"function_entry_count", i64 32}
+!2 = !{!"branch_weights", i32 5, i32 10}
+!3 = !{!"VP", i32 0, i64 1600, i64 7651369219802541373, i64 1030, i64 -4377547752858689819, i64 410, i64 -6929281286627296573, i64 150, i64 -2545542355363006406, i64 10}
+
+; CHECK: !llvm.module.flags = !{![[cgprof:[0-9]+]]}
+; CHECK: ![[cgprof]] = !{i32 5, !"CG Profile", ![[prof:[0-9]+]]}
+; CHECK: ![[prof]] = !{![[e0:[0-9]+]], ![[e1:[0-9]+]], ![[e2:[0-9]+]], ![[e3:[0-9]+]], ![[e4:[0-9]+]], ![[e5:[0-9]+]], ![[e6:[0-9]+]]}
+; CHECK: ![[e0]] = !{void ()* @a, void ()* @b, i64 32}
+; CHECK: ![[e1]] = !{void (i1)* @freq, i32 ()* @func4, i64 1030}
+; CHECK: ![[e2]] = !{void (i1)* @freq, i32 ()* @func2, i64 410}
+; CHECK: ![[e3]] = !{void (i1)* @freq, i32 ()* @func3, i64 150}
+; CHECK: ![[e4]] = !{void (i1)* @freq, i32 ()* @func1, i64 10}
+; CHECK: ![[e5]] = !{void (i1)* @freq, void ()* @a, i64 11}
+; CHECK: ![[e6]] = !{void (i1)* @freq, void ()* @b, i64 20}

test/MC/ELF/cgprofile.ll

@@ -0,0 +1,50 @@
+; RUN: llc -filetype=asm %s -o - -mtriple x86_64-pc-linux-gnu | FileCheck %s
+; RUN: llc -filetype=obj %s -o %t -mtriple x86_64-pc-linux-gnu
+; RUN: llvm-readobj -elf-cg-profile %t | FileCheck %s --check-prefix=OBJ
+
+declare void @b()
+
+define void @a() {
+  call void @b()
+  ret void
+}
+
+define void @freq(i1 %cond) {
+  br i1 %cond, label %A, label %B
+A:
+  call void @a();
+  ret void
+B:
+  call void @b();
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+
+!0 = !{i32 5, !"CG Profile", !1}
+!1 = !{!2, !3, !4}
+!2 = !{void ()* @a, void ()* @b, i64 32}
+!3 = !{void (i1)* @freq, void ()* @a, i64 11}
+!4 = !{void (i1)* @freq, void ()* @b, i64 20}
+
+; CHECK: .cg_profile a, b, 32
+; CHECK: .cg_profile freq, a, 11
+; CHECK: .cg_profile freq, b, 20
+
+; OBJ: CGProfile [
+; OBJ:  CGProfileEntry {
+; OBJ:    From: a
+; OBJ:    To: b
+; OBJ:    Weight: 32
+; OBJ:  }
+; OBJ:  CGProfileEntry {
+; OBJ:    From: freq
+; OBJ:    To: a
+; OBJ:    Weight: 11
+; OBJ:  }
+; OBJ:  CGProfileEntry {
+; OBJ:    From: freq
+; OBJ:    To: b
+; OBJ:    Weight: 20
+; OBJ:  }
+; OBJ:]

test/Other/new-pm-defaults.ll

@@ -246,6 +246,7 @@
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O-NEXT: Running pass: SpeculateAroundPHIsPass
 ; CHECK-O-NEXT: Finished llvm::Function pass manager run.
+; CHECK-O-NEXT: Running pass: CGProfilePass
 ; CHECK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Running pass: ConstantMergePass
 ; CHECK-O-NEXT: Finished llvm::Module pass manager run.

test/Other/new-pm-thinlto-defaults.ll

@@ -224,6 +224,7 @@
 ; CHECK-POSTLINK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: SpeculateAroundPHIsPass
 ; CHECK-POSTLINK-O-NEXT: Finished llvm::Function pass manager run.
+; CHECK-POSTLINK-O-NEXT: Running pass: CGProfilePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: ConstantMergePass
 ; CHECK-POSTLINK-O-NEXT: Finished llvm::Module pass manager run.

test/Verifier/module-flags-cgprofile.ll

@@ -0,0 +1,30 @@
+; RUN: not llvm-as < %s -o /dev/null 2>&1 | FileCheck %s
+
+declare void @b()
+declare void @a()
+
+!llvm.module.flags = !{!0}
+
+!0 = !{i32 5, !"CG Profile", !1}
+!1 = !{!2, !"", !3, !4, !5, !6, !7, !8}
+!2 = !{void ()* @a, void ()* @b, i64 32}
+!3 = !{void ()* @a, void ()* @b}
+!4 = !{void ()* @a, void ()* @b, i64 32, i64 32}
+!5 = !{!"a", void ()* @b, i64 32}
+!6 = !{void ()* @a, !"b", i64 32}
+!7 = !{void ()* @a, void ()* @b, !""}
+!8 = !{void ()* @a, void ()* @b, null}
+
+; CHECK: expected a MDNode triple
+; CHECK: !""
+; CHECK: expected a MDNode triple
+; CHECK: !3 = !{void ()* @a, void ()* @b}
+; CHECK: expected a MDNode triple
+; CHECK: !4 = !{void ()* @a, void ()* @b, i64 32, i64 32}
+; CHECK: expected a Function
+; CHECK: !"a"
+; CHECK: expected a Function
+; CHECK: !"b"
+; CHECK: expected an integer constant
+; CHECK: !""
+; CHECK: expected an integer constant