[ctxprof] Prepare profile format for flat profiles

compiler-rt/lib/ctx_profile/CtxInstrContextNode.h

@@ -114,9 +114,14 @@ class ContextNode final {
 };
 
 /// Abstraction for the parameter passed to `__llvm_ctx_profile_fetch`.
+/// `startContextSection` is called before any context roots are sent for
+/// writing. Then one or more `writeContextual` calls are made; finally,
+/// `endContextSection` is called.
 class ProfileWriter {
 public:
+  virtual void startContextSection() = 0;
   virtual void writeContextual(const ctx_profile::ContextNode &RootNode) = 0;
+  virtual void endContextSection() = 0;
   virtual ~ProfileWriter() = default;
 };
 } // namespace ctx_profile

compiler-rt/lib/ctx_profile/CtxInstrProfiling.cpp

@@ -298,6 +298,7 @@ bool __llvm_ctx_profile_fetch(ProfileWriter &Writer) {
   __sanitizer::GenericScopedLock<__sanitizer::SpinMutex> Lock(
       &AllContextsMutex);
 
+  Writer.startContextSection();
   for (int I = 0, E = AllContextRoots.Size(); I < E; ++I) {
     auto *Root = AllContextRoots[I];
     __sanitizer::GenericScopedLock<__sanitizer::StaticSpinMutex> TakenLock(
@@ -308,6 +309,7 @@ bool __llvm_ctx_profile_fetch(ProfileWriter &Writer) {
     }
     Writer.writeContextual(*Root->FirstNode);
   }
+  Writer.endContextSection();
   return true;
 }
 

compiler-rt/lib/ctx_profile/tests/CtxInstrProfilingTest.cpp

@@ -183,11 +183,18 @@ TEST_F(ContextTest, Dump) {
   public:
     ContextRoot *const Root;
     const size_t Entries;
+
+    int EnteredSectionCount = 0;
+    int ExitedSectionCount = 0;
+
     bool State = false;
+
     TestProfileWriter(ContextRoot *Root, size_t Entries)
         : Root(Root), Entries(Entries) {}
 
     void writeContextual(const ContextNode &Node) override {
+      EXPECT_EQ(EnteredSectionCount, 1);
+      EXPECT_EQ(ExitedSectionCount, 0);
       EXPECT_FALSE(Root->Taken.TryLock());
       EXPECT_EQ(Node.guid(), 1U);
       EXPECT_EQ(Node.counters()[0], Entries);
@@ -205,7 +212,13 @@ TEST_F(ContextTest, Dump) {
       EXPECT_EQ(SN.subContexts()[0], nullptr);
       State = true;
     }
+    void startContextSection() override { ++EnteredSectionCount; }
+    void endContextSection() override {
+      EXPECT_EQ(EnteredSectionCount, 1);
+      ++ExitedSectionCount;
+    }
   };
+
   TestProfileWriter W(&Root, 1);
   EXPECT_FALSE(W.State);
   __llvm_ctx_profile_fetch(W);
@@ -217,4 +230,6 @@ TEST_F(ContextTest, Dump) {
   EXPECT_FALSE(W2.State);
   __llvm_ctx_profile_fetch(W2);
   EXPECT_TRUE(W2.State);
+  EXPECT_EQ(W2.EnteredSectionCount, 1);
+  EXPECT_EQ(W2.ExitedSectionCount, 1);
 }

compiler-rt/test/ctx_profile/TestCases/generate-context.cpp

@@ -62,7 +62,14 @@ class TestProfileWriter : public ProfileWriter {
       }
   }
 
-public:
+  void startContextSection() override {
+    std::cout << "Entered Context Section" << std::endl;
+  }
+
+  void endContextSection() override {
+    std::cout << "Exited Context Section" << std::endl;
+  }
+
   void writeContextual(const ContextNode &RootNode) override {
     printProfile(RootNode, "", "");
   }
@@ -77,6 +84,7 @@ class TestProfileWriter : public ProfileWriter {
 // path gets instrumented).
 // The second context is in the loop. We expect 2 entries and each of the
 // branches would be taken once, so the second counter is 1.
+// CHECK-NEXT: Entered Context Section
 // CHECK-NEXT: Guid: 8657661246551306189
 // CHECK-NEXT: Entries: 1
 // CHECK-NEXT: 2 counters and 3 callsites
@@ -91,6 +99,7 @@ class TestProfileWriter : public ProfileWriter {
 // CHECK-NEXT:   Entries: 2
 // CHECK-NEXT:   2 counters and 2 callsites
 // CHECK-NEXT:   Counter values: 2 1
+// CHECK-NEXT: Exited Context Section
 
 bool profileWriter() {
   TestProfileWriter W;

llvm/include/llvm/Analysis/CtxProfAnalysis.h

@@ -54,6 +54,8 @@ class PGOContextualProfile {
     return Profiles.Contexts;
   }
 
+  const PGOCtxProfile &profiles() const { return Profiles; }
+
   bool isFunctionKnown(const Function &F) const {
     return getDefinedFunctionGUID(F) != 0;
   }

llvm/include/llvm/ProfileData/CtxInstrContextNode.h

@@ -114,9 +114,14 @@ class ContextNode final {
 };
 
 /// Abstraction for the parameter passed to `__llvm_ctx_profile_fetch`.
+/// `startContextSection` is called before any context roots are sent for
+/// writing. Then one or more `writeContextual` calls are made; finally,
+/// `endContextSection` is called.
 class ProfileWriter {
 public:
+  virtual void startContextSection() = 0;
   virtual void writeContextual(const ctx_profile::ContextNode &RootNode) = 0;
+  virtual void endContextSection() = 0;
   virtual ~ProfileWriter() = default;
 };
 } // namespace ctx_profile

llvm/include/llvm/ProfileData/PGOCtxProfReader.h

@@ -190,8 +190,12 @@ class PGOCtxProfileReader final {
   Error unsupported(const Twine &);
 
   Expected<std::pair<std::optional<uint32_t>, PGOCtxProfContext>>
-  readContext(bool ExpectIndex);
-  bool canReadContext();
+  readProfile(PGOCtxProfileBlockIDs Kind);
+
+  bool canEnterBlockWithID(PGOCtxProfileBlockIDs ID);
+  Error enterBlockWithID(PGOCtxProfileBlockIDs ID);
+
+  Error loadContexts(CtxProfContextualProfiles &);
 
 public:
   PGOCtxProfileReader(StringRef Buffer)
@@ -201,7 +205,6 @@ class PGOCtxProfileReader final {
   Expected<PGOCtxProfile> loadProfiles();
 };
 
-void convertCtxProfToYaml(raw_ostream &OS,
-                          const PGOCtxProfContext::CallTargetMapTy &);
+void convertCtxProfToYaml(raw_ostream &OS, const PGOCtxProfile &);
 } // namespace llvm
 #endif

llvm/include/llvm/ProfileData/PGOCtxProfWriter.h

@@ -23,7 +23,9 @@ enum PGOCtxProfileRecords { Invalid = 0, Version, Guid, CalleeIndex, Counters };
 
 enum PGOCtxProfileBlockIDs {
   ProfileMetadataBlockID = bitc::FIRST_APPLICATION_BLOCKID,
-  ContextNodeBlockID = ProfileMetadataBlockID + 1
+  ContextsSectionBlockID = ProfileMetadataBlockID + 1,
+  ContextRootBlockID = ContextsSectionBlockID + 1,
+  ContextNodeBlockID = ContextRootBlockID + 1,
 };
 
 /// Write one or more ContextNodes to the provided raw_fd_stream.
@@ -60,23 +62,30 @@ enum PGOCtxProfileBlockIDs {
 /// like value profiling - which would appear as additional records. For
 /// example, value profiling would produce a new record with a new record ID,
 /// containing the profiled values (much like the counters)
-class PGOCtxProfileWriter final {
+class PGOCtxProfileWriter : public ctx_profile::ProfileWriter {
+  enum class EmptyContextCriteria { None, EntryIsZero, AllAreZero };
+
   BitstreamWriter Writer;
+  const bool IncludeEmpty;
 
-  void writeCounters(const ctx_profile::ContextNode &Node);
+  void writeGuid(ctx_profile::GUID Guid);
+  void writeCounters(ArrayRef<uint64_t> Counters);
   void writeImpl(std::optional<uint32_t> CallerIndex,
                  const ctx_profile::ContextNode &Node);
 
 public:
   PGOCtxProfileWriter(raw_ostream &Out,
-                      std::optional<unsigned> VersionOverride = std::nullopt);
+                      std::optional<unsigned> VersionOverride = std::nullopt,
+                      bool IncludeEmpty = false);
   ~PGOCtxProfileWriter() { Writer.ExitBlock(); }
 
-  void write(const ctx_profile::ContextNode &);
+  void startContextSection() override;
+  void writeContextual(const ctx_profile::ContextNode &RootNode) override;
+  void endContextSection() override;
 
   // constants used in writing which a reader may find useful.
   static constexpr unsigned CodeLen = 2;
-  static constexpr uint32_t CurrentVersion = 1;
+  static constexpr uint32_t CurrentVersion = 2;
   static constexpr unsigned VBREncodingBits = 6;
   static constexpr StringRef ContainerMagic = "CTXP";
 };

llvm/lib/Analysis/CtxProfAnalysis.cpp

@@ -180,7 +180,7 @@ PreservedAnalyses CtxProfAnalysisPrinterPass::run(Module &M,
 
   if (Mode == PrintMode::Everything)
     OS << "\nCurrent Profile:\n";
-  convertCtxProfToYaml(OS, C.contexts());
+  convertCtxProfToYaml(OS, C.profiles());
   OS << "\n";
   if (Mode == PrintMode::YAML)
     return PreservedAnalyses::all();

llvm/lib/ProfileData/PGOCtxProfReader.cpp

@@ -19,7 +19,6 @@
 #include "llvm/Support/Error.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/YAMLTraits.h"
-#include <iterator>
 #include <utility>
 
 using namespace llvm;
@@ -58,26 +57,34 @@ Error PGOCtxProfileReader::unsupported(const Twine &Msg) {
   return make_error<InstrProfError>(instrprof_error::unsupported_version, Msg);
 }
 
-bool PGOCtxProfileReader::canReadContext() {
+bool PGOCtxProfileReader::canEnterBlockWithID(PGOCtxProfileBlockIDs ID) {
   auto Blk = advance();
   if (!Blk) {
     consumeError(Blk.takeError());
     return false;
   }
-  return Blk->Kind == BitstreamEntry::SubBlock &&
-         Blk->ID == PGOCtxProfileBlockIDs::ContextNodeBlockID;
+  return Blk->Kind == BitstreamEntry::SubBlock && Blk->ID == ID;
+}
+
+Error PGOCtxProfileReader::enterBlockWithID(PGOCtxProfileBlockIDs ID) {
+  RET_ON_ERR(Cursor.EnterSubBlock(ID));
+  return Error::success();
 }
 
 Expected<std::pair<std::optional<uint32_t>, PGOCtxProfContext>>
-PGOCtxProfileReader::readContext(bool ExpectIndex) {
-  RET_ON_ERR(Cursor.EnterSubBlock(PGOCtxProfileBlockIDs::ContextNodeBlockID));
+PGOCtxProfileReader::readProfile(PGOCtxProfileBlockIDs Kind) {
+  assert((Kind == PGOCtxProfileBlockIDs::ContextRootBlockID ||
+          Kind == PGOCtxProfileBlockIDs::ContextNodeBlockID) &&
+         "Unexpected profile kind");
+  RET_ON_ERR(enterBlockWithID(Kind));
 
   std::optional<ctx_profile::GUID> Guid;
   std::optional<SmallVector<uint64_t, 16>> Counters;
   std::optional<uint32_t> CallsiteIndex;
 
   SmallVector<uint64_t, 1> RecordValues;
 
+  const bool ExpectIndex = Kind == PGOCtxProfileBlockIDs::ContextNodeBlockID;
   // We don't prescribe the order in which the records come in, and we are ok
   // if other unsupported records appear. We seek in the current subblock until
   // we get all we know.
@@ -121,8 +128,8 @@ PGOCtxProfileReader::readContext(bool ExpectIndex) {
 
   PGOCtxProfContext Ret(*Guid, std::move(*Counters));
 
-  while (canReadContext()) {
-    EXPECT_OR_RET(SC, readContext(true));
+  while (canEnterBlockWithID(PGOCtxProfileBlockIDs::ContextNodeBlockID)) {
+    EXPECT_OR_RET(SC, readProfile(PGOCtxProfileBlockIDs::ContextNodeBlockID));
     auto &Targets = Ret.callsites()[*SC->first];
     auto [_, Inserted] =
         Targets.insert({SC->second.guid(), std::move(SC->second)});
@@ -168,15 +175,23 @@ Error PGOCtxProfileReader::readMetadata() {
   return Error::success();
 }
 
+Error PGOCtxProfileReader::loadContexts(CtxProfContextualProfiles &P) {
+  if (canEnterBlockWithID(PGOCtxProfileBlockIDs::ContextsSectionBlockID)) {
+    RET_ON_ERR(enterBlockWithID(PGOCtxProfileBlockIDs::ContextsSectionBlockID));
+    while (canEnterBlockWithID(PGOCtxProfileBlockIDs::ContextRootBlockID)) {
+      EXPECT_OR_RET(E, readProfile(PGOCtxProfileBlockIDs::ContextRootBlockID));
+      auto Key = E->second.guid();
+      if (!P.insert({Key, std::move(E->second)}).second)
+        return wrongValue("Duplicate roots");
+    }
+  }
+  return Error::success();
+}
+
 Expected<PGOCtxProfile> PGOCtxProfileReader::loadProfiles() {
-  PGOCtxProfile Ret;
   RET_ON_ERR(readMetadata());
-  while (canReadContext()) {
-    EXPECT_OR_RET(E, readContext(false));
-    auto Key = E->second.guid();
-    if (!Ret.Contexts.insert({Key, std::move(E->second)}).second)
-      return wrongValue("Duplicate roots");
-  }
+  PGOCtxProfile Ret;
+  RET_ON_ERR(loadContexts(Ret.Contexts));
   return std::move(Ret);
 }
 
@@ -224,41 +239,54 @@ void toYaml(yaml::Output &Out,
   Out.endSequence();
 }
 
-void toYaml(yaml::Output &Out, const PGOCtxProfContext &Ctx) {
+void toYaml(yaml::Output &Out, GlobalValue::GUID Guid,
+            const SmallVectorImpl<uint64_t> &Counters,
+            const PGOCtxProfContext::CallsiteMapTy &Callsites) {
   yaml::EmptyContext Empty;
   Out.beginMapping();
   void *SaveInfo = nullptr;
   bool UseDefault = false;
   {
     Out.preflightKey("Guid", /*Required=*/true, /*SameAsDefault=*/false,
                      UseDefault, SaveInfo);
-    auto Guid = Ctx.guid();
     yaml::yamlize(Out, Guid, true, Empty);
     Out.postflightKey(nullptr);
   }
   {
     Out.preflightKey("Counters", true, false, UseDefault, SaveInfo);
     Out.beginFlowSequence();
-    for (size_t I = 0U, E = Ctx.counters().size(); I < E; ++I) {
+    for (size_t I = 0U, E = Counters.size(); I < E; ++I) {
       Out.preflightFlowElement(I, SaveInfo);
-      uint64_t V = Ctx.counters()[I];
+      uint64_t V = Counters[I];
       yaml::yamlize(Out, V, true, Empty);
       Out.postflightFlowElement(SaveInfo);
     }
     Out.endFlowSequence();
     Out.postflightKey(nullptr);
   }
-  if (!Ctx.callsites().empty()) {
+  if (!Callsites.empty()) {
     Out.preflightKey("Callsites", true, false, UseDefault, SaveInfo);
-    toYaml(Out, Ctx.callsites());
+    toYaml(Out, Callsites);
     Out.postflightKey(nullptr);
   }
   Out.endMapping();
 }
+void toYaml(yaml::Output &Out, const PGOCtxProfContext &Ctx) {
+  toYaml(Out, Ctx.guid(), Ctx.counters(), Ctx.callsites());
+}
+
 } // namespace
 
-void llvm::convertCtxProfToYaml(
-    raw_ostream &OS, const PGOCtxProfContext::CallTargetMapTy &Profiles) {
+void llvm::convertCtxProfToYaml(raw_ostream &OS,
+                                const PGOCtxProfile &Profiles) {
   yaml::Output Out(OS);
-  toYaml(Out, Profiles);
-}
+  void *SaveInfo = nullptr;
+  bool UseDefault = false;
+  Out.beginMapping();
+  if (!Profiles.Contexts.empty()) {
+    Out.preflightKey("Contexts", false, false, UseDefault, SaveInfo);
+    toYaml(Out, Profiles.Contexts);
+    Out.postflightKey(nullptr);
+  }
+  Out.endMapping();
+}