Reland "[Propeller] Promote functions with propeller profiles to .text.hot."

[rahmanl]

Summary

This relands commit 4d8d2580c53e130c3c3dd3877384301e3c495554.

The only change here is using 'addUsedIfAvailable<BasicBlockSectionsProfileReader>()` to make sure we don't change the pipeline tests.

[rahmanl]

nit.

[MaskRay]

The convention is to reuse the original differential when relanding a patch (if needed, reopen the original patch with Add Action->Reopen), instead of creating a new differential.

llvm/include/llvm/CodeGen/BasicBlockSectionsProfileReader.h

+//===-- BasicBlockSectionsProfileReader.h - BB sections profile reader pass ==//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass creates the basic block cluster info by reading the basic block
+// sections profile. The cluster info will be used by the basic-block-sections
+// pass to arrange basic blocks in their sections.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H
+#define LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H
+
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/LineIterator.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+using namespace llvm;
+
+namespace llvm {
+
+// The cluster information for a machine basic block.
+struct BBClusterInfo {
+  // MachineBasicBlock ID.
+  unsigned MBBNumber;
+  // Cluster ID this basic block belongs to.
+  unsigned ClusterID;
+  // Position of basic block within the cluster.
+  unsigned PositionInCluster;
+};
+
+using ProgramBBClusterInfoMapTy = StringMap<SmallVector<BBClusterInfo>>;
+
+class BasicBlockSectionsProfileReader : public ImmutablePass {
+public:
+  static char ID;
+
+  BasicBlockSectionsProfileReader(const MemoryBuffer *Buf)
+      : ImmutablePass(ID), MBuf(Buf) {
+    initializeBasicBlockSectionsProfileReaderPass(
+        *PassRegistry::getPassRegistry());
+  };
+
+  BasicBlockSectionsProfileReader() : ImmutablePass(ID) {
+    initializeBasicBlockSectionsProfileReaderPass(
+        *PassRegistry::getPassRegistry());
+  }
+
+  StringRef getPassName() const override {
+    return "Basic Block Sections Profile Reader";
+  }
+
+  // Returns true if basic block sections profile exist for function \p
+  // FuncName.
+  bool isFunctionHot(StringRef FuncName) const;
+
+  // Returns a pair with first element representing whether basic block sections
+  // profile exist for the function \p FuncName, and the second element
+  // representing the basic block sections profile (cluster info) for this
+  // function. If the first element is true and the second element is empty, it
+  // means unique basic block sections are desired for all basic blocks of the
+  // function.
+  std::pair<bool, SmallVector<BBClusterInfo>>
+  getBBClusterInfoForFunction(StringRef FuncName) const;
+
+  /// Read profiles of basic blocks if available here.
+  void initializePass() override;
+
+private:
+  StringRef getAliasName(StringRef FuncName) const {
+    auto R = FuncAliasMap.find(FuncName);
+    return R == FuncAliasMap.end() ? FuncName : R->second;
+  }
+
+  // This contains the basic-block-sections profile.
+  const MemoryBuffer *MBuf = nullptr;
+
+  // This encapsulates the BB cluster information for the whole program.
+  //
+  // For every function name, it contains the cluster information for (all or
+  // some of) its basic blocks. The cluster information for every basic block
+  // includes its cluster ID along with the position of the basic block in that
+  // cluster.
+  ProgramBBClusterInfoMapTy ProgramBBClusterInfo;
+
+  // Some functions have alias names. We use this map to find the main alias
+  // name for which we have mapping in ProgramBBClusterInfo.
+  StringMap<StringRef> FuncAliasMap;
+};
+
+// Creates a BasicBlockSectionsProfileReader pass to parse the basic block
+// sections profile. \p Buf is a memory buffer that contains the list of
+// functions and basic block ids to selectively enable basic block sections.
+ImmutablePass *
+createBasicBlockSectionsProfileReaderPass(const MemoryBuffer *Buf);
+
+} // namespace llvm
+#endif // LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H

llvm/include/llvm/CodeGen/Passes.h

namespace llvm {
   /// work well with unreachable basic blocks (what live ranges make sense for a
   /// block that cannot be reached?).  As such, a code generator should either
   /// not instruction select unreachable blocks, or run this pass as its
   /// last LLVM modifying pass to clean up blocks that are not reachable from
   /// the entry block.
   FunctionPass *createUnreachableBlockEliminationPass();
 
   /// createBasicBlockSections Pass - This pass assigns sections to machine
-  /// basic blocks and is enabled with -fbasic-block-sections. Buf is a memory
-  /// buffer that contains the list of functions and basic block ids to
-  /// selectively enable basic block sections.
-  MachineFunctionPass *createBasicBlockSectionsPass(const MemoryBuffer *Buf);
+  /// basic blocks and is enabled with -fbasic-block-sections.
+  MachineFunctionPass *createBasicBlockSectionsPass();
 
   /// createMachineFunctionSplitterPass - This pass splits machine functions
   /// using profile information.
   MachineFunctionPass *createMachineFunctionSplitterPass();
 
   /// MachineFunctionPrinter pass - This pass prints out the machine function to
   /// the given stream as a debugging tool.
   MachineFunctionPass *

llvm/include/llvm/InitializePasses.h

 void initializeAnnotation2MetadataLegacyPass(PassRegistry &);
 void initializeAnnotationRemarksLegacyPass(PassRegistry &);
 void initializeOpenMPOptCGSCCLegacyPassPass(PassRegistry &);
 void initializeArgPromotionPass(PassRegistry&);
 void initializeAssumptionCacheTrackerPass(PassRegistry&);
 void initializeAtomicExpandPass(PassRegistry&);
 void initializeAttributorLegacyPassPass(PassRegistry&);
 void initializeAttributorCGSCCLegacyPassPass(PassRegistry &);
+void initializeBasicBlockSectionsProfileReaderPass(PassRegistry &);
 void initializeBasicBlockSectionsPass(PassRegistry &);
 void initializeBDCELegacyPassPass(PassRegistry&);
 void initializeBarrierNoopPass(PassRegistry&);
 void initializeBasicAAWrapperPassPass(PassRegistry&);
 void initializeBlockExtractorLegacyPassPass(PassRegistry &);
 void initializeBlockFrequencyInfoWrapperPassPass(PassRegistry&);
 void initializeBoundsCheckingLegacyPassPass(PassRegistry&);
 void initializeBranchFolderPassPass(PassRegistry&);

llvm/lib/CodeGen/BasicBlockSections.cpp

 // every function into the .llvm_bb_addr_map section. Along with the function
 // symbols, this allows for mapping of virtual addresses in PMU profiles back to
 // the corresponding basic blocks. This logic is implemented in AsmPrinter. This
 // pass only assigns the BBSectionType of every function to ``labels``.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/Optional.h"
-#include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
 #include "llvm/CodeGen/BasicBlockSectionUtils.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Error.h"
-#include "llvm/Support/LineIterator.h"
-#include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Target/TargetMachine.h"
 
-using llvm::SmallSet;
-using llvm::SmallVector;
-using llvm::StringMap;
-using llvm::StringRef;
 using namespace llvm;
 
 // Placing the cold clusters in a separate section mitigates against poor
 // profiles and allows optimizations such as hugepage mapping to be applied at a
 // section granularity. Defaults to ".text.split." which is recognized by lld
 // via the `-z keep-text-section-prefix` flag.
 cl::opt<std::string> llvm::BBSectionsColdTextPrefix(
     "bbsections-cold-text-prefix",
     cl::desc("The text prefix to use for cold basic block clusters"),
     cl::init(".text.split."), cl::Hidden);
 
 cl::opt<bool> BBSectionsDetectSourceDrift(
     "bbsections-detect-source-drift",
     cl::desc("This checks if there is a fdo instr. profile hash "
              "mismatch for this function"),
     cl::init(true), cl::Hidden);
 
 namespace {
 
-// This struct represents the cluster information for a machine basic block.
-struct BBClusterInfo {
-  // MachineBasicBlock ID.
-  unsigned MBBNumber;
-  // Cluster ID this basic block belongs to.
-  unsigned ClusterID;
-  // Position of basic block within the cluster.
-  unsigned PositionInCluster;
-};
-
-using ProgramBBClusterInfoMapTy = StringMap<SmallVector<BBClusterInfo, 4>>;
-
 class BasicBlockSections : public MachineFunctionPass {
 public:
   static char ID;
 
-  // This contains the basic-block-sections profile.
-  const MemoryBuffer *MBuf = nullptr;
-
-  // This encapsulates the BB cluster information for the whole program.
-  //
-  // For every function name, it contains the cluster information for (all or
-  // some of) its basic blocks. The cluster information for every basic block
-  // includes its cluster ID along with the position of the basic block in that
-  // cluster.
-  ProgramBBClusterInfoMapTy ProgramBBClusterInfo;
-
-  // Some functions have alias names. We use this map to find the main alias
-  // name for which we have mapping in ProgramBBClusterInfo.
-  StringMap<StringRef> FuncAliasMap;
-
-  BasicBlockSections(const MemoryBuffer *Buf)
-      : MachineFunctionPass(ID), MBuf(Buf) {
-    initializeBasicBlockSectionsPass(*PassRegistry::getPassRegistry());
-  };
+  BasicBlockSectionsProfileReader *BBSectionsProfileReader = nullptr;
 
   BasicBlockSections() : MachineFunctionPass(ID) {
     initializeBasicBlockSectionsPass(*PassRegistry::getPassRegistry());
   }
 
   StringRef getPassName() const override {
     return "Basic Block Sections Analysis";
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override;
 
-  /// Read profiles of basic blocks if available here.
-  bool doInitialization(Module &M) override;
-
   /// Identify basic blocks that need separate sections and prepare to emit them
   /// accordingly.
   bool runOnMachineFunction(MachineFunction &MF) override;
 };
 
 } // end anonymous namespace
 
 char BasicBlockSections::ID = 0;
for (auto &MBB : MF) {
     if (TII->analyzeBranch(MBB, TBB, FBB, Cond))
       continue;
     MBB.updateTerminator(FTMBB);
   }
 }
 
 // This function provides the BBCluster information associated with a function.
 // Returns true if a valid association exists and false otherwise.
-static bool getBBClusterInfoForFunction(
-    const MachineFunction &MF, const StringMap<StringRef> FuncAliasMap,
-    const ProgramBBClusterInfoMapTy &ProgramBBClusterInfo,
+bool getBBClusterInfoForFunction(
+    const MachineFunction &MF,
+    BasicBlockSectionsProfileReader *BBSectionsProfileReader,
     std::vector<Optional<BBClusterInfo>> &V) {
-  // Get the main alias name for the function.
-  auto FuncName = MF.getName();
-  auto R = FuncAliasMap.find(FuncName);
-  StringRef AliasName = R == FuncAliasMap.end() ? FuncName : R->second;
 
   // Find the assoicated cluster information.
-  auto P = ProgramBBClusterInfo.find(AliasName);
-  if (P == ProgramBBClusterInfo.end())
+  std::pair<bool, SmallVector<BBClusterInfo, 4>> P =
+      BBSectionsProfileReader->getBBClusterInfoForFunction(MF.getName());
+  if (!P.first)
     return false;
 
-  if (P->second.empty()) {
+  if (P.second.empty()) {
     // This indicates that sections are desired for all basic blocks of this
     // function. We clear the BBClusterInfo vector to denote this.
     V.clear();
     return true;
   }
 
   V.resize(MF.getNumBlockIDs());
-  for (auto bbClusterInfo : P->second) {
+  for (auto bbClusterInfo : P.second) {
     // Bail out if the cluster information contains invalid MBB numbers.
     if (bbClusterInfo.MBBNumber >= MF.getNumBlockIDs())
       return false;
     V[bbClusterInfo.MBBNumber] = bbClusterInfo;
   }
   return true;
 }
 
bool BasicBlockSections::runOnMachineFunction(MachineFunction &MF) {
   // labels to match the profiles with the correct blocks.
   MF.RenumberBlocks();
 
   if (BBSectionsType == BasicBlockSection::Labels) {
     MF.setBBSectionsType(BBSectionsType);
     return true;
   }
 
+  BBSectionsProfileReader = &getAnalysis<BasicBlockSectionsProfileReader>();
+
   std::vector<Optional<BBClusterInfo>> FuncBBClusterInfo;
   if (BBSectionsType == BasicBlockSection::List &&
-      !getBBClusterInfoForFunction(MF, FuncAliasMap, ProgramBBClusterInfo,
+      !getBBClusterInfoForFunction(MF, BBSectionsProfileReader,
                                    FuncBBClusterInfo))
     return true;
   MF.setBBSectionsType(BBSectionsType);
   assignSections(MF, FuncBBClusterInfo);
 
   // We make sure that the cluster including the entry basic block precedes all
   // other clusters.
   auto EntryBBSectionID = MF.front().getSectionID();
auto Comparator = [&](const MachineBasicBlock &X,
     return X.getNumber() < Y.getNumber();
   };
 
   sortBasicBlocksAndUpdateBranches(MF, Comparator);
   avoidZeroOffsetLandingPad(MF);
   return true;
 }
 
-// Basic Block Sections can be enabled for a subset of machine basic blocks.
-// This is done by passing a file containing names of functions for which basic
-// block sections are desired.  Additionally, machine basic block ids of the
-// functions can also be specified for a finer granularity. Moreover, a cluster
-// of basic blocks could be assigned to the same section.
-// A file with basic block sections for all of function main and three blocks
-// for function foo (of which 1 and 2 are placed in a cluster) looks like this:
-// ----------------------------
-// list.txt:
-// !main
-// !foo
-// !!1 2
-// !!4
-static Error getBBClusterInfo(const MemoryBuffer *MBuf,
-                              ProgramBBClusterInfoMapTy &ProgramBBClusterInfo,
-                              StringMap<StringRef> &FuncAliasMap) {
-  assert(MBuf);
-  line_iterator LineIt(*MBuf, /*SkipBlanks=*/true, /*CommentMarker=*/'#');
-
-  auto invalidProfileError = [&](auto Message) {
-    return make_error<StringError>(
-        Twine("Invalid profile " + MBuf->getBufferIdentifier() + " at line " +
-              Twine(LineIt.line_number()) + ": " + Message),
-        inconvertibleErrorCode());
-  };
-
-  auto FI = ProgramBBClusterInfo.end();
-
-  // Current cluster ID corresponding to this function.
-  unsigned CurrentCluster = 0;
-  // Current position in the current cluster.
-  unsigned CurrentPosition = 0;
-
-  // Temporary set to ensure every basic block ID appears once in the clusters
-  // of a function.
-  SmallSet<unsigned, 4> FuncBBIDs;
-
-  for (; !LineIt.is_at_eof(); ++LineIt) {
-    StringRef S(*LineIt);
-    if (S[0] == '@')
-      continue;
-    // Check for the leading "!"
-    if (!S.consume_front("!") || S.empty())
-      break;
-    // Check for second "!" which indicates a cluster of basic blocks.
-    if (S.consume_front("!")) {
-      if (FI == ProgramBBClusterInfo.end())
-        return invalidProfileError(
-            "Cluster list does not follow a function name specifier.");
-      SmallVector<StringRef, 4> BBIndexes;
-      S.split(BBIndexes, ' ');
-      // Reset current cluster position.
-      CurrentPosition = 0;
-      for (auto BBIndexStr : BBIndexes) {
-        unsigned long long BBIndex;
-        if (getAsUnsignedInteger(BBIndexStr, 10, BBIndex))
-          return invalidProfileError(Twine("Unsigned integer expected: '") +
-                                     BBIndexStr + "'.");
-        if (!FuncBBIDs.insert(BBIndex).second)
-          return invalidProfileError(Twine("Duplicate basic block id found '") +
-                                     BBIndexStr + "'.");
-        if (!BBIndex && CurrentPosition)
-          return invalidProfileError("Entry BB (0) does not begin a cluster.");
-
-        FI->second.emplace_back(BBClusterInfo{
-            ((unsigned)BBIndex), CurrentCluster, CurrentPosition++});
-      }
-      CurrentCluster++;
-    } else { // This is a function name specifier.
-      // Function aliases are separated using '/'. We use the first function
-      // name for the cluster info mapping and delegate all other aliases to
-      // this one.
-      SmallVector<StringRef, 4> Aliases;
-      S.split(Aliases, '/');
-      for (size_t i = 1; i < Aliases.size(); ++i)
-        FuncAliasMap.try_emplace(Aliases[i], Aliases.front());
-
-      // Prepare for parsing clusters of this function name.
-      // Start a new cluster map for this function name.
-      FI = ProgramBBClusterInfo.try_emplace(Aliases.front()).first;
-      CurrentCluster = 0;
-      FuncBBIDs.clear();
-    }
-  }
-  return Error::success();
-}
-
-bool BasicBlockSections::doInitialization(Module &M) {
-  if (!MBuf)
-    return false;
-  if (auto Err = getBBClusterInfo(MBuf, ProgramBBClusterInfo, FuncAliasMap))
-    report_fatal_error(std::move(Err));
-  return false;
-}
-
 void BasicBlockSections::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
+  AU.addRequired<BasicBlockSectionsProfileReader>();
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
-MachineFunctionPass *
-llvm::createBasicBlockSectionsPass(const MemoryBuffer *Buf) {
-  return new BasicBlockSections(Buf);
+MachineFunctionPass *llvm::createBasicBlockSectionsPass() {
+  return new BasicBlockSections();
 }

llvm/lib/CodeGen/BasicBlockSectionsProfileReader.cpp

+//===-- BasicBlockSectionsProfileReader.cpp -------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// Implementation of the basic block sections profile reader pass. It parses
+// and stores the basic block sections profile file (which is specified via the
+// `-basic-block-sections` flag).
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/LineIterator.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+using namespace llvm;
+
+char BasicBlockSectionsProfileReader::ID = 0;
+INITIALIZE_PASS(BasicBlockSectionsProfileReader, "bbsections-profile-reader",
+                "Reads and parses a basic block sections profile.", false,
+                false)
+
+bool BasicBlockSectionsProfileReader::isFunctionHot(StringRef FuncName) const {
+  return getBBClusterInfoForFunction(FuncName).first;
+}
+
+std::pair<bool, SmallVector<BBClusterInfo>>
+BasicBlockSectionsProfileReader::getBBClusterInfoForFunction(
+    StringRef FuncName) const {
+  std::pair<bool, SmallVector<BBClusterInfo>> cluster_info(false, {});
+  auto R = ProgramBBClusterInfo.find(getAliasName(FuncName));
+  if (R != ProgramBBClusterInfo.end()) {
+    cluster_info.second = R->second;
+    cluster_info.first = true;
+  }
+  return cluster_info;
+}
+
+// Basic Block Sections can be enabled for a subset of machine basic blocks.
+// This is done by passing a file containing names of functions for which basic
+// block sections are desired.  Additionally, machine basic block ids of the
+// functions can also be specified for a finer granularity. Moreover, a cluster
+// of basic blocks could be assigned to the same section.
+// A file with basic block sections for all of function main and three blocks
+// for function foo (of which 1 and 2 are placed in a cluster) looks like this:
+// ----------------------------
+// list.txt:
+// !main
+// !foo
+// !!1 2
+// !!4
+static Error getBBClusterInfo(const MemoryBuffer *MBuf,
+                              ProgramBBClusterInfoMapTy &ProgramBBClusterInfo,
+                              StringMap<StringRef> &FuncAliasMap) {
+  assert(MBuf);
+  line_iterator LineIt(*MBuf, /*SkipBlanks=*/true, /*CommentMarker=*/'#');
+
+  auto invalidProfileError = [&](auto Message) {
+    return make_error<StringError>(
+        Twine("Invalid profile " + MBuf->getBufferIdentifier() + " at line " +
+              Twine(LineIt.line_number()) + ": " + Message),
+        inconvertibleErrorCode());
+  };
+
+  auto FI = ProgramBBClusterInfo.end();
+
+  // Current cluster ID corresponding to this function.
+  unsigned CurrentCluster = 0;
+  // Current position in the current cluster.
+  unsigned CurrentPosition = 0;
+
+  // Temporary set to ensure every basic block ID appears once in the clusters
+  // of a function.
+  SmallSet<unsigned, 4> FuncBBIDs;
+
+  for (; !LineIt.is_at_eof(); ++LineIt) {
+    StringRef S(*LineIt);
+    if (S[0] == '@')
+      continue;
+    // Check for the leading "!"
+    if (!S.consume_front("!") || S.empty())
+      break;
+    // Check for second "!" which indicates a cluster of basic blocks.
+    if (S.consume_front("!")) {
+      if (FI == ProgramBBClusterInfo.end())
+        return invalidProfileError(
+            "Cluster list does not follow a function name specifier.");
+      SmallVector<StringRef, 4> BBIndexes;
+      S.split(BBIndexes, ' ');
+      // Reset current cluster position.
+      CurrentPosition = 0;
+      for (auto BBIndexStr : BBIndexes) {
+        unsigned long long BBIndex;
+        if (getAsUnsignedInteger(BBIndexStr, 10, BBIndex))
+          return invalidProfileError(Twine("Unsigned integer expected: '") +
+                                     BBIndexStr + "'.");
+        if (!FuncBBIDs.insert(BBIndex).second)
+          return invalidProfileError(Twine("Duplicate basic block id found '") +
+                                     BBIndexStr + "'.");
+        if (!BBIndex && CurrentPosition)
+          return invalidProfileError("Entry BB (0) does not begin a cluster.");
+
+        FI->second.emplace_back(BBClusterInfo{
+            ((unsigned)BBIndex), CurrentCluster, CurrentPosition++});
+      }
+      CurrentCluster++;
+    } else { // This is a function name specifier.
+      // Function aliases are separated using '/'. We use the first function
+      // name for the cluster info mapping and delegate all other aliases to
+      // this one.
+      SmallVector<StringRef, 4> Aliases;
+      S.split(Aliases, '/');
+      for (size_t i = 1; i < Aliases.size(); ++i)
+        FuncAliasMap.try_emplace(Aliases[i], Aliases.front());
+
+      // Prepare for parsing clusters of this function name.
+      // Start a new cluster map for this function name.
+      FI = ProgramBBClusterInfo.try_emplace(Aliases.front()).first;
+      CurrentCluster = 0;
+      FuncBBIDs.clear();
+    }
+  }
+  return Error::success();
+}
+
+void BasicBlockSectionsProfileReader::initializePass() {
+  if (!MBuf)
+    return;
+  if (auto Err = getBBClusterInfo(MBuf, ProgramBBClusterInfo, FuncAliasMap))
+    report_fatal_error(std::move(Err));
+}
+
+ImmutablePass *
+llvm::createBasicBlockSectionsProfileReaderPass(const MemoryBuffer *Buf) {
+  return new BasicBlockSectionsProfileReader(Buf);
+}

llvm/lib/CodeGen/CMakeLists.txt

add_llvm_component_library(LLVMCodeGen
   AllocationOrder.cpp
   Analysis.cpp
   AtomicExpandPass.cpp
   BasicTargetTransformInfo.cpp
   BranchFolding.cpp
   BranchRelaxation.cpp
   BreakFalseDeps.cpp
   BasicBlockSections.cpp
+  BasicBlockSectionsProfileReader.cpp
   CalcSpillWeights.cpp
   CallingConvLower.cpp
   CFGuardLongjmp.cpp
   CFIFixup.cpp
   CFIInstrInserter.cpp
   CodeGen.cpp
   CodeGenCommonISel.cpp
   CodeGenPassBuilder.cpp

llvm/lib/CodeGen/CodeGenPrepare.cpp

 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Analysis/VectorUtils.h"
 #include "llvm/CodeGen/Analysis.h"
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
 #include "llvm/CodeGen/SelectionDAGNodes.h"
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/CodeGen/ValueTypes.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/IR/Argument.h"
static cl::opt<bool> ProfileUnknownInSpecialSection(
     cl::desc("In profiling mode like sampleFDO, if a function doesn't have "
              "profile, we cannot tell the function is cold for sure because "
              "it may be a function newly added without ever being sampled. "
              "With the flag enabled, compiler can put such profile unknown "
              "functions into a special section, so runtime system can choose "
              "to handle it in a different way than .text section, to save "
              "RAM for example. "));
 
+static cl::opt<bool> BBSectionsGuidedSectionPrefix(
+    "bbsections-guided-section-prefix", cl::Hidden, cl::init(true),
+    cl::desc("Use the basic-block-sections profile to determine the text "
+             "section prefix for hot functions. Functions with "
+             "basic-block-sections profile will be placed in `.text.hot` "
+             "regardless of their FDO profile info. Other functions won't be "
+             "impacted, i.e., their prefixes will be decided by FDO/sampleFDO "
+             "profiles."));
+
 static cl::opt<unsigned> FreqRatioToSkipMerge(
     "cgp-freq-ratio-to-skip-merge", cl::Hidden, cl::init(2),
     cl::desc("Skip merging empty blocks if (frequency of empty block) / "
              "(frequency of destination block) is greater than this ratio"));
 
 static cl::opt<bool> ForceSplitStore(
     "force-split-store", cl::Hidden, cl::init(false),
     cl::desc("Force store splitting no matter what the target query says."));

 class TypePromotionTransaction;
 
   class CodeGenPrepare : public FunctionPass {
     const TargetMachine *TM = nullptr;
     const TargetSubtargetInfo *SubtargetInfo;
     const TargetLowering *TLI = nullptr;
     const TargetRegisterInfo *TRI;
     const TargetTransformInfo *TTI = nullptr;
+    const BasicBlockSectionsProfileReader *BBSectionsProfileReader = nullptr;
     const TargetLibraryInfo *TLInfo;
     const LoopInfo *LI;
     std::unique_ptr<BlockFrequencyInfo> BFI;
     std::unique_ptr<BranchProbabilityInfo> BPI;
     ProfileSummaryInfo *PSI;
 
     /// As we scan instructions optimizing them, this is the next instruction
     /// to optimize. Transforms that can invalidate this should update it.
public:
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       // FIXME: When we can selectively preserve passes, preserve the domtree.
       AU.addRequired<ProfileSummaryInfoWrapperPass>();
       AU.addRequired<TargetLibraryInfoWrapperPass>();
       AU.addRequired<TargetPassConfig>();
       AU.addRequired<TargetTransformInfoWrapperPass>();
       AU.addRequired<LoopInfoWrapperPass>();
+      AU.addUsedIfAvailable<BasicBlockSectionsProfileReader>();
     }
 
   private:
     template <typename F>
     void resetIteratorIfInvalidatedWhileCalling(BasicBlock *BB, F f) {
       // Substituting can cause recursive simplifications, which can invalidate
       // our iterator.  Use a WeakTrackingVH to hold onto it in case this
       // happens.
class TypePromotionTransaction;
   };
 
 } // end anonymous namespace
 
 char CodeGenPrepare::ID = 0;
 
 INITIALIZE_PASS_BEGIN(CodeGenPrepare, DEBUG_TYPE,
                       "Optimize for code generation", false, false)
+INITIALIZE_PASS_DEPENDENCY(BasicBlockSectionsProfileReader)
 INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetPassConfig)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
 INITIALIZE_PASS_END(CodeGenPrepare, DEBUG_TYPE,
                     "Optimize for code generation", false, false)
 
bool CodeGenPrepare::runOnFunction(Function &F) {
   TLI = SubtargetInfo->getTargetLowering();
   TRI = SubtargetInfo->getRegisterInfo();
   TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
   TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
   LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
   BPI.reset(new BranchProbabilityInfo(F, *LI));
   BFI.reset(new BlockFrequencyInfo(F, *BPI, *LI));
   PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  BBSectionsProfileReader =
+      getAnalysisIfAvailable<BasicBlockSectionsProfileReader>();
   OptSize = F.hasOptSize();
-  if (ProfileGuidedSectionPrefix) {
+  // Use the basic-block-sections profile to promote hot functions to .text.hot if requested.
+  if (BBSectionsGuidedSectionPrefix && BBSectionsProfileReader &&
+      BBSectionsProfileReader->isFunctionHot(F.getName())) {
+    F.setSectionPrefix("hot");
+  } else if (ProfileGuidedSectionPrefix) {
     // The hot attribute overwrites profile count based hotness while profile
     // counts based hotness overwrite the cold attribute.
     // This is a conservative behabvior.
     if (F.hasFnAttribute(Attribute::Hot) ||
         PSI->isFunctionHotInCallGraph(&F, *BFI))
       F.setSectionPrefix("hot");
     // If PSI shows this function is not hot, we will placed the function
     // into unlikely section if (1) PSI shows this is a cold function, or

llvm/lib/CodeGen/TargetPassConfig.cpp

 #include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/BasicAliasAnalysis.h"
 #include "llvm/Analysis/CFLAndersAliasAnalysis.h"
 #include "llvm/Analysis/CFLSteensAliasAnalysis.h"
 #include "llvm/Analysis/CallGraphSCCPass.h"
 #include "llvm/Analysis/ScopedNoAliasAA.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/TypeBasedAliasAnalysis.h"
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
 #include "llvm/CodeGen/CSEConfigBase.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachinePassRegistry.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/RegAllocRegistry.h"
 #include "llvm/IR/IRPrintingPasses.h"
 #include "llvm/IR/LegacyPassManager.h"
 #include "llvm/IR/PassInstrumentation.h"
if (AddOutliner)
       addPass(createMachineOutlinerPass(RunOnAllFunctions));
   }
 
   // Machine function splitter uses the basic block sections feature. Both
   // cannot be enabled at the same time. Basic block sections takes precedence.
   // FIXME: In principle, BasicBlockSection::Labels and splitting can used
   // together. Update this check once we have addressed any issues.
   if (TM->getBBSectionsType() != llvm::BasicBlockSection::None) {
-    addPass(llvm::createBasicBlockSectionsPass(TM->getBBSectionsFuncListBuf()));
+    if (TM->getBBSectionsType() == llvm::BasicBlockSection::List) {
+      addPass(llvm::createBasicBlockSectionsProfileReaderPass(
+          TM->getBBSectionsFuncListBuf()));
+    }
+    addPass(llvm::createBasicBlockSectionsPass());
   } else if (TM->Options.EnableMachineFunctionSplitter ||
              EnableMachineFunctionSplitter) {
     addPass(createMachineFunctionSplitterPass());
   }
 
   if (!DisableCFIFixup && TM->Options.EnableCFIFixup)
     addPass(createCFIFixup());
 

llvm/test/CodeGen/X86/basic-block-sections-cold.ll

 6:                                                ; preds = %2, %4
   ret void
 }
 
 declare i32 @_Z3barv() #1
 
 declare i32 @_Z3foov() #1
 
-; LINUX-SECTIONS: .section        .text._Z3bazb,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3bazb,"ax",@progbits
 ; LINUX-SECTIONS: _Z3bazb:
 ; Check that the basic block with id 1 doesn't get a section.
-; LINUX-SECTIONS-NOT: .section        .text._Z3bazb._Z3bazb.1,"ax",@progbits,unique
+; LINUX-SECTIONS-NOT: .section        .text{{.*}}._Z3bazb.1,"ax",@progbits,unique
 ; Check that a single cold section is started here and id 1 and 2 blocks are placed here.
 ; LINUX-SECTIONS: .section  .text.split._Z3bazb,"ax",@progbits
 ; LINUX-SECTIONS: _Z3bazb.cold:
-; LINUX-SECTIONS-NOT: .section        .text._Z3bazb._Z3bazb.2,"ax",@progbits,unique
+; LINUX-SECTIONS-NOT: .section        .text.hot._Z3bazb._Z3bazb.2,"ax",@progbits,unique
 ; LINUX-SECTIONS: .LBB0_2:
 ; LINUX-SECTIONS: .size   _Z3bazb, .Lfunc_end{{[0-9]}}-_Z3bazb
 
 ; LINUX-SPLIT:      .section  .text.unlikely._Z3bazb,"ax",@progbits
 ; LINUX-SPLIT-NEXT: _Z3bazb.cold:
 ; LINUX-SPLIT-NEXT:   callq _Z3barv
 ; LINUX-SPLIT:      .LBB0_2:
 ; LINUX-SPLIT:      .LBB_END0_2:

llvm/test/CodeGen/X86/basic-block-sections-list.ll

 ; Check the basic block sections list option.
 ; RUN: echo '!_Z3foob' > %t
 ; RUN: llc < %s -mtriple=x86_64-pc-linux -function-sections -basic-block-sections=%t -unique-basic-block-section-names | FileCheck %s -check-prefix=LINUX-SECTIONS --check-prefix=LINUX-SECTIONS-FUNCTION-SECTION
-;  llc < %s -mtriple=x86_64-pc-linux -basic-block-sections=%t -unique-basic-block-section-names | FileCheck %s -check-prefix=LINUX-SECTIONS --check-prefix=LINUX-SECTIONS-NO-FUNCTION-SECTION
+; RUN: llc < %s -mtriple=x86_64-pc-linux -basic-block-sections=%t -unique-basic-block-section-names | FileCheck %s -check-prefix=LINUX-SECTIONS --check-prefix=LINUX-SECTIONS-NO-FUNCTION-SECTION
+; RUN: llc < %s -mtriple=x86_64-pc-linux -basic-block-sections=%t -unique-basic-block-section-names --bbsections-guided-section-prefix=false | FileCheck %s -check-prefix=LINUX-SECTIONS-NO-GUIDED-PREFIX
 
 define i32 @_Z3foob(i1 zeroext %0) nounwind {
   %2 = alloca i32, align 4
   %3 = alloca i8, align 1
   %4 = zext i1 %0 to i8
   store i8 %4, i8* %3, align 1
   %5 = load i8, i8* %3, align 1
   %6 = trunc i8 %5 to i1
11:                                               ; preds = %1
   store i32 %12, i32* %2, align 4
   br label %13
 
 13:                                               ; preds = %11, %9
   %14 = load i32, i32* %2, align 4
   ret i32 %14
 }
 
-; LINUX-SECTIONS: .section        .text._Z3foob,"ax",@progbits
+; LINUX-SECTIONS-NO-GUIDED-PREFIX: .section        .text._Z3foob,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3foob,"ax",@progbits
 ; LINUX-SECTIONS: _Z3foob:
-; LINUX-SECTIONS: .section        .text._Z3foob._Z3foob.__part.1,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3foob._Z3foob.__part.1,"ax",@progbits
 ; LINUX-SECTIONS: _Z3foob.__part.1:
-; LINUX-SECTIONS: .section        .text._Z3foob._Z3foob.__part.2,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3foob._Z3foob.__part.2,"ax",@progbits
 ; LINUX-SECTIONS: _Z3foob.__part.2:
-; LINUX-SECTIONS: .section        .text._Z3foob._Z3foob.__part.3,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3foob._Z3foob.__part.3,"ax",@progbits
 ; LINUX-SECTIONS: _Z3foob.__part.3:
 
-; LINUX-SECTIONS-FUNCTION-SECTION: .section        .text._Z3zipb,"ax",@progbits
-; LINUX-SECIONS-NO-FUNCTION-SECTION-NOT: .section        .text._Z3zipb,"ax",@progbits
+; LINUX-SECTIONS-FUNCTION-SECTION: .section     .text._Z3zipb,"ax",@progbits
+; LINUX-SECTIONS-NO-FUNCTION-SECTION-NOT: .section     .text{{.*}}._Z3zipb,"ax",@progbits
 ; LINUX-SECTIONS: _Z3zipb:
-; LINUX-SECTIONS-NOT: .section        .text._Z3zipb._Z3zipb.__part.{{[0-9]+}},"ax",@progbits
+; LINUX-SECTIONS-NOT: .section        .text{{.*}}._Z3zipb.__part.{{[0-9]+}},"ax",@progbits
 ; LINUX-SECTIONS-NOT: _Z3zipb.__part.{{[0-9]+}}:

llvm/test/CodeGen/X86/basic-block-sections-listbb.ll

 }
 
 declare i32 @_Z3barv() #1
 
 declare i32 @_Z3foov() #1
 
 ; Check that the correct block is found using the call insts for foo and bar.
 ;
-; LINUX-SECTIONS: .section        .text._Z3bazb,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3bazb,"ax",@progbits
 ; LINUX-SECTIONS: _Z3bazb:
 ; Check that the basic block with id 1 doesn't get a section.
-; LINUX-SECTIONS-NOT: .section        .text._Z3bazb._Z3bazb.__part.{{[0-9]+}},"ax",@progbits
+; LINUX-SECTIONS-NOT: .section        .text{{.*}}._Z3bazb.__part.{{[0-9]+}},"ax",@progbits
 ; LINUX-SECTIONS-LABEL: # %bb.1:
 ; LINUX-SECTIONS-NEXT:        callq   _Z3barv
-; LINUX-SECTIONS: .section        .text._Z3bazb.[[SECTION_LABEL:_Z3bazb.__part.[0-9]+]],"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3bazb.[[SECTION_LABEL:_Z3bazb.__part.[0-9]+]],"ax",@progbits
 ; LINUX-SECTIONS-NEXT: [[SECTION_LABEL]]:
 ; LINUX-SECTIONS-NEXT:        callq   _Z3foov
 ; LINUX-SECTIONS: .LBB_END0_2:
 ; LINUX-SECTIONS-NEXT: .size   [[SECTION_LABEL]], .LBB_END0_2-[[SECTION_LABEL]]
-; LINUX-SECTIONS: .section        .text._Z3bazb,"ax",@progbits
+; LINUX-SECTIONS: .section        .text.hot._Z3bazb,"ax",@progbits
 ; LINUX-SECTIONS: .Lfunc_end0:
 ; LINUX-SECTIONS-NEXT: .size _Z3bazb, .Lfunc_end0-_Z3bazb

llvm/test/CodeGen/X86/basic-block-sections-source-drift.ll

3:                                                ; preds = %2
   ret i32 %4
 
 5:                                                ; preds = %2
   ret i32 1
 }
 
 !1 = !{!"instr_prof_hash_mismatch"}
 
-; SOURCE-DRIFT-NOT: .section .text
-; HASH-CHECK-DISABLED: .section .text
+; SOURCE-DRIFT-NOT: .section .text{{.*}}.foo
+; HASH-CHECK-DISABLED: .section .text.hot.foo