[llvm-profdata] Handle the cases of overlapping input file and output file

[xur]

Summary

Currently llvm-profdata does not expect the same file name for the input profile
and the output profile.
>llvm-profdata merge A.profraw B.profraw -o B.profraw
The above command runs successfully but the resulted B.profraw is not correct.
This patch fixes the issue by moving the initialization of writer after loading
the profile.

For the show command, the following will report a confusing error of
"Empty raw profile file":
>llvm-profdata show B.profraw -o B.profraw
It's harder to fix as we need to output something before loading the input profile.
I don't think that a fix for this is worth the effort. I just make the error explicit for
the show command.

[davidxl]

llvm/tools/llvm-profdata/llvm-profdata.cpp

1024

Use the same error reporting format:

errs() << ProgName << ": " << ReasonString <<"!\n";

[xur]

Change the error report format suggested by David.

[davidxl]

lgtm

llvm/test/tools/llvm-profdata/Inputs/same-name-1.proftext

+# IR level Instrumentation Flag
+:ir
+main
+# Func Hash:
[phone]
+# Num Counters:
+1
+# Counter Values:
+1
+

llvm/test/tools/llvm-profdata/Inputs/same-name-2.proftext

+# IR level Instrumentation Flag
+:ir
+main
+# Func Hash:
[phone]
+# Num Counters:
+1
+# Counter Values:
+2
+

llvm/test/tools/llvm-profdata/Inputs/same-name-3.proftext

+_Z3bari:20301:1437
+ 1: 1437
+_Z3fooi:7711:610
+ 1: 610
+main:184019:0
+ 4: 534
+ 4.2: 534
+ 5: 1075
+ 5.1: 1075
+ 6: 2080
+ 7: 534
+ 9: 2064 _Z3bari:1471 _Z3fooi:631
+ 10: inline1:1000
+  1: 1000
+ 10: inline2:2000
+  1: 2000

llvm/test/tools/llvm-profdata/Inputs/same-name-4.proftext

+_Z3bari:40602:2874
+ 1: 2874
+_Z3fooi:15422:1220
+ 1: 1220
+main:368038:0
+ 4: 1068
+ 4.2: 1068
+ 5: 2150
+ 5.1: 2150
+ 6: 4160
+ 7: 1068
+ 9: 4128 _Z3bari:2942 _Z3fooi:1262
+ 10: inline1:2000
+  1: 2000
+ 10: inline2:4000
+  1: 4000

llvm/test/tools/llvm-profdata/same-filename.test

+Test the input file names overlap with the output file names.
+
+This is OK for merging instrument profiles.
+RUN: cp %S/Inputs/same-name-1.proftext %t.0.proftext
+RUN: llvm-profdata merge -o %t.0.proftext -text %t.0.proftext %t.0.proftext
+RUN: llvm-profdata show -counts -all-functions %t.0.proftext -o %t_show_0
+RUN: llvm-profdata show -counts -all-functions %S/Inputs/same-name-2.proftext -o %t_show_1
+RUN: diff %t_show_0 %t_show_1
+RUN: llvm-profdata merge -o %t.1.profdata %S/Inputs/same-name-1.proftext
+RUN: llvm-profdata merge -o %t.1.profdata %t.1.profdata %t.1.profdata
+RUN: llvm-profdata show -counts -all-functions %t.1.profdata -o %t_show_2
+RUN: diff %t_show_2 %t_show_1
+
+We report error for the show command.
+RUN: not llvm-profdata show -o %t.1.profdata %t.1.profdata 2>&1 | FileCheck %s
+CHECK: llvm-profdata show: Input file name cannot be the same as the output file name!
+
+This is OK for merging sample fdo profiles.
+RUN: cp %S/Inputs/same-name-3.proftext %t.3.proftext
+RUN: llvm-profdata merge --sample -o %t.3.proftext -text %t.3.proftext %t.3.proftext
+RUN: llvm-profdata show --sample -counts -all-functions %t.3.proftext -o %t_show_3
+RUN: llvm-profdata show --sample -counts -all-functions %S/Inputs/same-name-4.proftext -o %t_show_4
+RUN: diff %t_show_3 %t_show_4
+RUN: llvm-profdata merge --sample -o %t.5.profdata %S/Inputs/same-name-3.proftext
+RUN: llvm-profdata merge --sample -o %t.5.profdata %t.5.profdata %t.5.profdata
+RUN: llvm-profdata show --sample -counts -all-functions %t.5.profdata -o %t_show_6
+RUN: diff %t_show_6 %t_show_4

llvm/tools/llvm-profdata/llvm-profdata.cpp

static void mergeInstrProfile(const WeightedFileVector &Inputs,
                               unsigned NumThreads) {
   if (OutputFilename.compare("-") == 0)
     exitWithError("Cannot write indexed profdata format to stdout.");
 
   if (OutputFormat != PF_Binary && OutputFormat != PF_Compact_Binary &&
       OutputFormat != PF_Text)
     exitWithError("Unknown format is specified.");
 
-  std::error_code EC;
-  raw_fd_ostream Output(OutputFilename.data(), EC, sys::fs::F_None);
-  if (EC)
-    exitWithErrorCode(EC, OutputFilename);
-
   std::mutex ErrorLock;
   SmallSet<instrprof_error, 4> WriterErrorCodes;
 
   // If NumThreads is not specified, auto-detect a good default.
   if (NumThreads == 0)
     NumThreads =
         std::min(hardware_concurrency(), unsigned((Inputs.size() + 1) / 2));
 
for (std::unique_ptr<WriterContext> &WC : Contexts) {
     instrprof_error IPE = InstrProfError::take(std::move(WC->Err));
     if (isFatalError(IPE))
       exitWithError(make_error<InstrProfError>(IPE), WC->ErrWhence);
     else
       warn(toString(make_error<InstrProfError>(IPE)),
            WC->ErrWhence);
   }
 
+  std::error_code EC;
+  raw_fd_ostream Output(OutputFilename.data(), EC, sys::fs::F_None);
+  if (EC)
+    exitWithErrorCode(EC, OutputFilename);
+
   InstrProfWriter &Writer = Contexts[0]->Writer;
   if (OutputFormat == PF_Text) {
     if (Error E = Writer.writeText(Output))
       exitWithError(std::move(E));
   } else {
     Writer.write(Output);
   }
 }
static sampleprof::SampleProfileFormat FormatMap[] = {
     sampleprof::SPF_None, sampleprof::SPF_Text, sampleprof::SPF_Compact_Binary,
     sampleprof::SPF_GCC, sampleprof::SPF_Binary};
 
 static void mergeSampleProfile(const WeightedFileVector &Inputs,
                                SymbolRemapper *Remapper,
                                StringRef OutputFilename,
                                ProfileFormat OutputFormat) {
   using namespace sampleprof;
-  auto WriterOrErr =
-      SampleProfileWriter::create(OutputFilename, FormatMap[OutputFormat]);
-  if (std::error_code EC = WriterOrErr.getError())
-    exitWithErrorCode(EC, OutputFilename);
-
-  auto Writer = std::move(WriterOrErr.get());
   StringMap<FunctionSamples> ProfileMap;
   SmallVector<std::unique_ptr<sampleprof::SampleProfileReader>, 5> Readers;
   LLVMContext Context;
   for (const auto &Input : Inputs) {
     auto ReaderOrErr = SampleProfileReader::create(Input.Filename, Context);
     if (std::error_code EC = ReaderOrErr.getError())
       exitWithErrorCode(EC, Input.Filename);
 
for (StringMap<FunctionSamples>::iterator I = Profiles.begin(),
       StringRef FName = Samples.getName();
       MergeResult(Result, ProfileMap[FName].merge(Samples, Input.Weight));
       if (Result != sampleprof_error::success) {
         std::error_code EC = make_error_code(Result);
         handleMergeWriterError(errorCodeToError(EC), Input.Filename, FName);
       }
     }
   }
+  auto WriterOrErr =
+      SampleProfileWriter::create(OutputFilename, FormatMap[OutputFormat]);
+  if (std::error_code EC = WriterOrErr.getError())
+    exitWithErrorCode(EC, OutputFilename);
+
+  auto Writer = std::move(WriterOrErr.get());
   Writer->write(ProfileMap);
 }
 
 static WeightedFile parseWeightedFile(const StringRef &WeightedFilename) {
   StringRef WeightStr, FileName;
   std::tie(WeightStr, FileName) = WeightedFilename.split(',');
 
   uint64_t Weight;
cl::opt<bool> OnlyListBelow(
       "list-below-cutoff", cl::init(false),
       cl::desc("Only output names of functions whose max count values are "
                "below the cutoff value"));
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data summary\n");
 
   if (OutputFilename.empty())
     OutputFilename = "-";
 
+  if (!Filename.compare(OutputFilename)) {
+    errs() << sys::path::filename(argv[0])
+           << ": Input file name cannot be the same as the output file name!\n";
+    return 1;
+  }
+
   std::error_code EC;
   raw_fd_ostream OS(OutputFilename.data(), EC, sys::fs::F_Text);
   if (EC)
     exitWithErrorCode(EC, OutputFilename);
 
   if (ShowAllFunctions && !ShowFunction.empty())
     WithColor::warning() << "-function argument ignored: showing all functions\n";