[llvm-profgen] Allow generating AutoFDO profile from CSSPGO binary

[wenlei]

Summary

Add -use-dwarf-correlation switch to allow llvm-profgen to generate AutoFDO profile for binaries built with CSSPGO (pseudo-probe).

[wlei]

LGTM, thanks!

[wenlei]

linter

[hoy]

lgtm.

llvm/test/tools/llvm-profgen/inline-force-dwarf.test

+; RUN: llvm-profgen --format=text --ignore-stack-samples --use-dwarf-correlation --perfscript=%S/Inputs/inline-cs-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --profile-summary-cold-count=0
+; RUN: FileCheck %s --input-file %t
+
+; CHECK:     main:295:0
+; CHECK-NEXT: 0: 0
+; CHECK-NEXT: 2: 0
+; CHECK-NEXT: 1: foo:295
+; CHECK-NEXT:  2: 14
+; CHECK-NEXT:  3: 15
+; CHECK-NEXT:  4: 0
+; CHECK-NEXT:  3: bar:84
+; CHECK-NEXT:   1: 14
+
+
+; clang -O3 -fexperimental-new-pass-manager -fuse-ld=lld -fpseudo-probe-for-profiling
+; -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -Xclang -mdisable-tail-calls
+; -g test.c  -o a.out
+
+#include <stdio.h>
+
+int bar(int x, int y) {
+  if (x % 3) {
+    return x - y;
+  }
+  return x + y;
+}
+
+void foo() {
+  int s, i = 0;
+  while (i++ < 4000 * 4000)
+    if (i % 91) s = bar(i, s); else s += 30;
+  printf("sum is %d\n", s);
+}
+
+int main() {
+  foo();
+  return 0;
+}

llvm/test/tools/llvm-profgen/inline-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
+; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
+; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
+; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t
+; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
 CHECK: main:669:0
 CHECK:  0: 0
 CHECK:  2: 0
 CHECK:  1: foo:669
 CHECK:   2.1: 42
 CHECK:   3: 62
 CHECK:   3.2: 21

llvm/tools/llvm-profgen/PerfReader.cpp

 //===-- PerfReader.cpp - perfscript reader  ---------------------*- C++ -*-===//
 //
 // 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
 //
 //===----------------------------------------------------------------------===//
 #include "PerfReader.h"
 #include "ProfileGenerator.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Process.h"
 
 #define DEBUG_TYPE "perf-reader"
 
-static cl::opt<bool> ShowMmapEvents("show-mmap-events", cl::ReallyHidden,
-                                    cl::init(false), cl::ZeroOrMore,
-                                    cl::desc("Print binary load events."));
-
-cl::opt<bool> SkipSymbolization("skip-symbolization", cl::ReallyHidden,
-                                cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> SkipSymbolization("skip-symbolization", cl::init(false),
+                                cl::ZeroOrMore,
                                 cl::desc("Dump the unsymbolized profile to the "
                                          "output file. It will show unwinder "
                                          "output for CS profile generation."));
-cl::opt<bool> UseOffset("use-offset", cl::ReallyHidden, cl::init(true),
+
+static cl::opt<bool> ShowMmapEvents("show-mmap-events", cl::init(false),
                                     cl::ZeroOrMore,
-                        cl::desc("Work with `--skip-symbolization` to dump the "
-                                 "offset instead of virtual address."));
-cl::opt<bool>
-    IgnoreStackSamples("ignore-stack-samples", cl::ReallyHidden,
-                       cl::init(false), cl::ZeroOrMore,
+                                    cl::desc("Print binary load events."));
+
+static cl::opt<bool>
+    UseOffset("use-offset", cl::init(true), cl::ZeroOrMore,
+static cl::opt<bool>
+    IgnoreStackSamples("ignore-stack-samples", cl::init(false), cl::ZeroOrMore,
                        cl::desc("Ignore call stack samples for hybrid samples "
                                 "and produce context-insensitive profile."));
 
 extern cl::opt<std::string> PerfTraceFilename;
 extern cl::opt<bool> ShowDisassemblyOnly;
 extern cl::opt<bool> ShowSourceLocations;
 extern cl::opt<std::string> OutputFilename;
 

llvm/tools/llvm-profgen/ProfiledBinary.cpp

 #include "llvm/Support/Format.h"
 #include "llvm/Support/TargetSelect.h"
 
 #define DEBUG_TYPE "load-binary"
 
 using namespace llvm;
 using namespace sampleprof;
 
-cl::opt<bool> ShowDisassemblyOnly("show-disassembly-only", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> ShowDisassemblyOnly("show-disassembly-only", cl::init(false),
+                                  cl::ZeroOrMore,
                                   cl::desc("Print disassembled code."));
 
-cl::opt<bool> ShowSourceLocations("show-source-locations", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> ShowSourceLocations("show-source-locations", cl::init(false),
+                                  cl::ZeroOrMore,
                                   cl::desc("Print source locations."));
 
-cl::opt<bool> ShowCanonicalFnName("show-canonical-fname", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
-                                  cl::desc("Print canonical function name."));
+static cl::opt<bool>
+    ShowCanonicalFnName("show-canonical-fname", cl::init(false), cl::ZeroOrMore,
 
-cl::opt<bool> ShowPseudoProbe(
-    "show-pseudo-probe", cl::ReallyHidden, cl::init(false), cl::ZeroOrMore,
+static cl::opt<bool> ShowPseudoProbe(
+    "show-pseudo-probe", cl::init(false), cl::ZeroOrMore,
     cl::desc("Print pseudo probe section and disassembled info."));
 
+static cl::opt<bool> UseDwarfCorrelation(
+    "use-dwarf-correlation", cl::init(false), cl::ZeroOrMore,
+    cl::desc("Use dwarf for profile correlation even when binary contains "
+             "pseudo probe."));
+
 static cl::list<std::string> DisassembleFunctions(
     "disassemble-functions", cl::CommaSeparated,
     cl::desc("List of functions to print disassembly for. Accept demangled "
              "names only. Only work with show-disassembly-only"));
 
 namespace llvm {
 namespace sampleprof {
 
else if (const auto *ELFObj = dyn_cast<ELF64LEObjectFile>(Obj))
     setPreferredTextSegmentAddresses(ELFObj->getELFFile(), Obj->getFileName());
   else if (const auto *ELFObj = cast<ELF64BEObjectFile>(Obj))
     setPreferredTextSegmentAddresses(ELFObj->getELFFile(), Obj->getFileName());
   else
     llvm_unreachable("invalid ELF object format");
 }
 
 void ProfiledBinary::decodePseudoProbe(const ELFObjectFileBase *Obj) {
+  if (UseDwarfCorrelation)
+    return;
+
   StringRef FileName = Obj->getFileName();
   for (section_iterator SI = Obj->section_begin(), SE = Obj->section_end();
        SI != SE; ++SI) {
     const SectionRef &Section = *SI;
     StringRef SectionName = unwrapOrError(Section.getName(), FileName);
 
     if (SectionName == ".pseudo_probe_desc") {
       StringRef Contents = unwrapOrError(Section.getContents(), FileName);