[llvm-profdata] Add check for text profile formats and improve error reporting (2nd...

Summary:
This change addresses two possible instances of user error / confusion when
merging sampled profile data.

Previously any input that didn't match the raw or processed instrumented format
would automatically be interpreted as instrumented profile text format data.
No error would be reported during the merge.

Example:
If foo-sampled.profdata and bar-sampled.profdata are binary sampled profiles:

Old behavior:
$ llvm-profdata merge foo-sampled.profdata bar-sampled.profdata -output foobar-sampled.profdata
$ llvm-profdata show -sample foobar-sampled.profdata
error: foobar-sampled.profdata:1: Expected 'mangled_name:NUM:NUM', found  lprofi

This change adds basic checks for valid input data when assuming text input.
It also makes error messages related to file format validity more specific about
the assumbed profile data type.

New behavior:
$ llvm-profdata merge foo-sampled.profdata bar-sampled.profdata -o foobar-sampled.profdata
error: foo.profdata: Unrecognized instrumentation profile encoding format
Perhaps you forgot to use the -sample option?

Reviewers: bogner, davidxl, dnovillo

Subscribers: davidxl, llvm-commits

Differential Revision: http://reviews.llvm.org/D14558

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@253009 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/ProfileData/InstrProf.h b/include/llvm/ProfileData/InstrProf.h
index 607f29de8a23f8523397146de9f3ac3c9c21637b..2339a46f9c5540c55b3cd3a788e07aadf0b34add 100644 (file)
--- a/include/llvm/ProfileData/InstrProf.h
+++ b/include/llvm/ProfileData/InstrProf.h
@@ -149,6 +149,7 @@ const std::error_category &instrprof_category();
 enum class instrprof_error {
   success = 0,
   eof,
+  unrecognized_format,
   bad_magic,
   bad_header,
   unsupported_version,

diff --git a/include/llvm/ProfileData/InstrProfReader.h b/include/llvm/ProfileData/InstrProfReader.h
index d0f5a57b1ae80e89c2100fd05e7d1e809c5628d3..3d4777a853ecf6dec73e3c3b7850fe3163bb8d2c 100644 (file)
--- a/include/llvm/ProfileData/InstrProfReader.h
+++ b/include/llvm/ProfileData/InstrProfReader.h
@@ -111,6 +111,9 @@ public:
   TextInstrProfReader(std::unique_ptr<MemoryBuffer> DataBuffer_)
       : DataBuffer(std::move(DataBuffer_)), Line(*DataBuffer, true, '#') {}
 
+  /// Return true if the given buffer is in text instrprof format.
+  static bool hasFormat(const MemoryBuffer &Buffer);
+
   /// Read the header.
   std::error_code readHeader() override { return success(); }
   /// Read a single record.

diff --git a/include/llvm/ProfileData/SampleProfReader.h b/include/llvm/ProfileData/SampleProfReader.h
index 2f404be50e6ae699ec4a70462ddb2776dfb7042d..1fb2cf6e0ca4b9b3a2f36a6b91180aa0e3b265c6 100644 (file)
--- a/include/llvm/ProfileData/SampleProfReader.h
+++ b/include/llvm/ProfileData/SampleProfReader.h
@@ -292,6 +292,9 @@ public:
 
   /// \brief Read sample profiles from the associated file.
   std::error_code read() override;
+
+  /// \brief Return true if \p Buffer is in the format supported by this class.
+  static bool hasFormat(const MemoryBuffer &Buffer);
 };
 
 class SampleProfileReaderBinary : public SampleProfileReader {

diff --git a/lib/ProfileData/InstrProf.cpp b/lib/ProfileData/InstrProf.cpp
index 92a3c251f6ef806ddf24b6bb05d8caebaa3f5447..762f00b48b6404dfd272508a9b868af045261fa5 100644 (file)
--- a/lib/ProfileData/InstrProf.cpp
+++ b/lib/ProfileData/InstrProf.cpp
@@ -32,20 +32,22 @@ class InstrProfErrorCategoryType : public std::error_category {
       return "Success";
     case instrprof_error::eof:
       return "End of File";
+    case instrprof_error::unrecognized_format:
+      return "Unrecognized instrumentation profile encoding format";
     case instrprof_error::bad_magic:
-      return "Invalid profile data (bad magic)";
+      return "Invalid instrumentation profile data (bad magic)";
     case instrprof_error::bad_header:
-      return "Invalid profile data (file header is corrupt)";
+      return "Invalid instrumentation profile data (file header is corrupt)";
     case instrprof_error::unsupported_version:
-      return "Unsupported profiling format version";
+      return "Unsupported instrumentation profile format version";
     case instrprof_error::unsupported_hash_type:
-      return "Unsupported profiling hash";
+      return "Unsupported instrumentation profile hash type";
     case instrprof_error::too_large:
       return "Too much profile data";
     case instrprof_error::truncated:
       return "Truncated profile data";
     case instrprof_error::malformed:
-      return "Malformed profile data";
+      return "Malformed instrumentation profile data";
     case instrprof_error::unknown_function:
       return "No profile data available for function";
     case instrprof_error::hash_mismatch:

diff --git a/lib/ProfileData/InstrProfReader.cpp b/lib/ProfileData/InstrProfReader.cpp
index bf10b448e4cc7c29729575805df617965018100e..6f201243736d09baecce19d27c1fa7478a70add8 100644 (file)
--- a/lib/ProfileData/InstrProfReader.cpp
+++ b/lib/ProfileData/InstrProfReader.cpp
@@ -54,8 +54,10 @@ InstrProfReader::create(std::unique_ptr<MemoryBuffer> Buffer) {
     Result.reset(new RawInstrProfReader64(std::move(Buffer)));
   else if (RawInstrProfReader32::hasFormat(*Buffer))
     Result.reset(new RawInstrProfReader32(std::move(Buffer)));
-  else
+  else if (TextInstrProfReader::hasFormat(*Buffer))
     Result.reset(new TextInstrProfReader(std::move(Buffer)));
+  else
+    return instrprof_error::unrecognized_format;
 
   // Initialize the reader and return the result.
   if (std::error_code EC = initializeReader(*Result))
@@ -97,6 +99,15 @@ void InstrProfIterator::Increment() {
     *this = InstrProfIterator();
 }
 
+bool TextInstrProfReader::hasFormat(const MemoryBuffer &Buffer) {
+  // Verify that this really looks like plain ASCII text by checking a
+  // 'reasonable' number of characters (up to profile magic size).
+  size_t count = std::min(Buffer.getBufferSize(), sizeof(uint64_t));
+  StringRef buffer = Buffer.getBufferStart();
+  return count == 0 || std::all_of(buffer.begin(), buffer.begin() + count,
+    [](char c) { return ::isprint(c) || ::isspace(c); });
+}
+
 std::error_code TextInstrProfReader::readNextRecord(InstrProfRecord &Record) {
   // Skip empty lines and comments.
   while (!Line.is_at_end() && (Line->empty() || Line->startswith("#")))

diff --git a/lib/ProfileData/SampleProf.cpp b/lib/ProfileData/SampleProf.cpp
index b5d3b2d2e551c9c03d7b10bdd3b34544a5277cc6..856923e164bd72bf3bee44436c12f9311737faea 100644 (file)
--- a/lib/ProfileData/SampleProf.cpp
+++ b/lib/ProfileData/SampleProf.cpp
@@ -28,17 +28,17 @@ class SampleProfErrorCategoryType : public std::error_category {
     case sampleprof_error::success:
       return "Success";
     case sampleprof_error::bad_magic:
-      return "Invalid file format (bad magic)";
+      return "Invalid sample profile data (bad magic)";
     case sampleprof_error::unsupported_version:
-      return "Unsupported format version";
+      return "Unsupported sample profile format version";
     case sampleprof_error::too_large:
       return "Too much profile data";
     case sampleprof_error::truncated:
       return "Truncated profile data";
     case sampleprof_error::malformed:
-      return "Malformed profile data";
+      return "Malformed sample profile data";
     case sampleprof_error::unrecognized_format:
-      return "Unrecognized profile encoding format";
+      return "Unrecognized sample profile encoding format";
     case sampleprof_error::unsupported_writing_format:
       return "Profile encoding format unsupported for writing operations";
     case sampleprof_error::truncated_name_table:

diff --git a/lib/ProfileData/SampleProfReader.cpp b/lib/ProfileData/SampleProfReader.cpp
index a5d00083b53641400f1244890d0be28b05afd41f..0bed4f09f1f1cd0808c208f74c581b980ad6bf15 100644 (file)
--- a/lib/ProfileData/SampleProfReader.cpp
+++ b/lib/ProfileData/SampleProfReader.cpp
@@ -222,6 +222,22 @@ std::error_code SampleProfileReaderText::read() {
   return sampleprof_error::success;
 }
 
+bool SampleProfileReaderText::hasFormat(const MemoryBuffer &Buffer) {
+  bool result = false;
+
+  // Check that the first non-comment line is a valid function header.
+  line_iterator LineIt(Buffer, /*SkipBlanks=*/true, '#');
+  if (!LineIt.is_at_eof()) {
+    if ((*LineIt)[0] != ' ') {
+      uint64_t NumSamples, NumHeadSamples;
+      StringRef FName;
+      result = ParseHead(*LineIt, FName, NumSamples, NumHeadSamples);
+    }
+  }
+
+  return result;
+}
+
 template <typename T> ErrorOr<T> SampleProfileReaderBinary::readNumber() {
   unsigned NumBytesRead = 0;
   std::error_code EC;
@@ -685,8 +701,10 @@ SampleProfileReader::create(StringRef Filename, LLVMContext &C) {
     Reader.reset(new SampleProfileReaderBinary(std::move(Buffer), C));
   else if (SampleProfileReaderGCC::hasFormat(*Buffer))
     Reader.reset(new SampleProfileReaderGCC(std::move(Buffer), C));
-  else
+  else if (SampleProfileReaderText::hasFormat(*Buffer))
     Reader.reset(new SampleProfileReaderText(std::move(Buffer), C));
+  else
+    return sampleprof_error::unrecognized_format;
 
   if (std::error_code EC = Reader->readHeader())
     return EC;

diff --git a/test/Transforms/SampleProfile/syntax.ll b/test/Transforms/SampleProfile/syntax.ll
index ed38a175288a289bfcfda4a58f392911db65fbd0..debbc7c87ddb9feaca07b0fec9e6aa5f7a479030 100644 (file)
--- a/test/Transforms/SampleProfile/syntax.ll
+++ b/test/Transforms/SampleProfile/syntax.ll
@@ -13,7 +13,7 @@ entry:
 }
 ; NO-DEBUG: warning: No debug information found in function empty: Function profile not used
 ; MISSING-FILE: missing.prof: Could not open profile:
-; BAD-FN-HEADER: error: {{.*}}bad_fn_header.prof:1: Expected 'mangled_name:NUM:NUM', found 3empty:100:BAD
+; BAD-FN-HEADER: error: {{.*}}bad_fn_header.prof: Could not open profile: Unrecognized sample profile encoding format
 ; BAD-SAMPLE-LINE: error: {{.*}}bad_sample_line.prof:3: Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found 1: BAD
 ; BAD-LINE-VALUES: error: {{.*}}bad_line_values.prof:2: Expected 'mangled_name:NUM:NUM', found -1: 10
 ; BAD-DISCRIMINATOR-VALUE: error: {{.*}}bad_discriminator_value.prof:2: Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found 1.-3: 10

diff --git a/test/tools/llvm-profdata/raw-magic-but-no-header.test b/test/tools/llvm-profdata/raw-magic-but-no-header.test
index b2a697042b0ab72b4863ec4617d257ab5f200c9c..76894faa183c9dd4e21dfd625790b3981d73e13e 100644 (file)
--- a/test/tools/llvm-profdata/raw-magic-but-no-header.test
+++ b/test/tools/llvm-profdata/raw-magic-but-no-header.test
@@ -3,4 +3,4 @@ RUN: not llvm-profdata show %t 2>&1 | FileCheck %s
 RUN: printf '\377lprofr\201' > %t
 RUN: not llvm-profdata show %t 2>&1 | FileCheck %s
 
-CHECK: error: {{.+}}: Invalid profile data (file header is corrupt)
+CHECK: error: {{.+}}: Invalid instrumentation profile data (file header is corrupt)

diff --git a/test/tools/llvm-profdata/sample-profile-basic.test b/test/tools/llvm-profdata/sample-profile-basic.test
index 0651c513e9655f7606d70f153c37961ab00a7161..9981d4204c430ae4c467619f560f106f049c4814 100644 (file)
--- a/test/tools/llvm-profdata/sample-profile-basic.test
+++ b/test/tools/llvm-profdata/sample-profile-basic.test
@@ -28,3 +28,7 @@ RUN: llvm-profdata merge --sample --text %p/Inputs/sample-profile.proftext %t-bi
 MERGE1: main:368038:0
 MERGE1: 9: 4128 _Z3fooi:1262 _Z3bari:2942
 MERGE1: _Z3fooi:15422:1220
+
+5- Detect invalid text encoding (e.g. instrumentation profile text format).
+RUN: not llvm-profdata show --sample %p/Inputs/foo3bar3-1.proftext 2>&1 | FileCheck %s --check-prefix=BADTEXT
+BADTEXT: error: {{.+}}: Unrecognized sample profile encoding format

diff --git a/test/tools/llvm-profdata/text-format-errors.test b/test/tools/llvm-profdata/text-format-errors.test
index 01513e4fcb9e700360c894f87c3acf2f4a443116..113b10ee4e858d12faa4c3224c076fb28f2b5c38 100644 (file)
--- a/test/tools/llvm-profdata/text-format-errors.test
+++ b/test/tools/llvm-profdata/text-format-errors.test
@@ -1,10 +1,21 @@
+Tests for instrumentation profile bad encoding.
+
+1- Detect invalid count
 RUN: not llvm-profdata show %p/Inputs/invalid-count-later.proftext 2>&1 | FileCheck %s --check-prefix=INVALID-COUNT-LATER
 RUN: not llvm-profdata merge %p/Inputs/invalid-count-later.proftext %p/Inputs/invalid-count-later.profdata -o %t.out 2>&1 | FileCheck %s --check-prefix=INVALID-COUNT-LATER
-INVALID-COUNT-LATER: error: {{.*}}invalid-count-later.proftext: Malformed profile data
+INVALID-COUNT-LATER: error: {{.*}}invalid-count-later.proftext: Malformed instrumentation profile data
 
+2- Detect bad hash
 RUN: not llvm-profdata show %p/Inputs/bad-hash.proftext 2>&1 | FileCheck %s --check-prefix=BAD-HASH
 RUN: not llvm-profdata merge %p/Inputs/bad-hash.proftext %p/Inputs/bad-hash.proftext -o %t.out 2>&1 | FileCheck %s --check-prefix=BAD-HASH
-BAD-HASH: error: {{.*}}bad-hash.proftext: Malformed profile data
+BAD-HASH: error: {{.*}}bad-hash.proftext: Malformed instrumentation profile data
 
+3- Detect no counts
 RUN: not llvm-profdata show %p/Inputs/no-counts.proftext 2>&1 | FileCheck %s --check-prefix=NO-COUNTS
-NO-COUNTS: error: {{.*}}no-counts.proftext: Malformed profile data
+NO-COUNTS: error: {{.*}}no-counts.proftext: Malformed instrumentation profile data
+
+4- Detect binary input
+RUN: echo -n $'\xff\xe5\xd0\xb1\xf4\c9\x94\xa8' > %t.bin
+RUN: not llvm-profdata show %t.bin 2>&1 | FileCheck %s --check-prefix=BINARY
+BINARY: error: {{.+}}: Unrecognized instrumentation profile encoding format
+BINARY: Perhaps you forgot to use the -sample option?

diff --git a/tools/llvm-profdata/llvm-profdata.cpp b/tools/llvm-profdata/llvm-profdata.cpp
index 48fc83c6971ba9196f245004e9c15f664415ada2..1cd47dd5e84c248cb883474f6c7c2866e1fe7d57 100644 (file)
--- a/tools/llvm-profdata/llvm-profdata.cpp
+++ b/tools/llvm-profdata/llvm-profdata.cpp
@@ -29,16 +29,32 @@
 
 using namespace llvm;
 
-static void exitWithError(const Twine &Message, StringRef Whence = "") {
+static void exitWithError(const Twine &Message,
+                          StringRef Whence = "",
+                          StringRef Hint = "") {
   errs() << "error: ";
   if (!Whence.empty())
     errs() << Whence << ": ";
   errs() << Message << "\n";
+  if (!Hint.empty())
+    errs() << Hint << "\n";
   ::exit(1);
 }
 
+static void exitWithErrorCode(const std::error_code &Error, StringRef Whence = "") {
+  if (Error.category() == instrprof_category()) {
+    instrprof_error instrError = static_cast<instrprof_error>(Error.value());
+    if (instrError == instrprof_error::unrecognized_format) {
+      // Hint for common error of forgetting -sample for sample profiles.
+      exitWithError(Error.message(), Whence,
+                    "Perhaps you forgot to use the -sample option?");
+    }
+  }
+  exitWithError(Error.message(), Whence);
+}
+
 namespace {
-enum ProfileKinds { instr, sample };
+    enum ProfileKinds { instr, sample };
 }
 
 static void mergeInstrProfile(const cl::list<std::string> &Inputs,
@@ -49,20 +65,20 @@ static void mergeInstrProfile(const cl::list<std::string> &Inputs,
   std::error_code EC;
   raw_fd_ostream Output(OutputFilename.data(), EC, sys::fs::F_None);
   if (EC)
-    exitWithError(EC.message(), OutputFilename);
+    exitWithErrorCode(EC, OutputFilename);
 
   InstrProfWriter Writer;
   for (const auto &Filename : Inputs) {
     auto ReaderOrErr = InstrProfReader::create(Filename);
     if (std::error_code ec = ReaderOrErr.getError())
-      exitWithError(ec.message(), Filename);
+      exitWithErrorCode(ec, Filename);
 
     auto Reader = std::move(ReaderOrErr.get());
     for (auto &I : *Reader)
       if (std::error_code EC = Writer.addRecord(std::move(I)))
         errs() << Filename << ": " << I.Name << ": " << EC.message() << "\n";
     if (Reader->hasError())
-      exitWithError(Reader->getError().message(), Filename);
+      exitWithErrorCode(Reader->getError(), Filename);
   }
   Writer.write(Output);
 }
@@ -73,7 +89,7 @@ static void mergeSampleProfile(const cl::list<std::string> &Inputs,
   using namespace sampleprof;
   auto WriterOrErr = SampleProfileWriter::create(OutputFilename, OutputFormat);
   if (std::error_code EC = WriterOrErr.getError())
-    exitWithError(EC.message(), OutputFilename);
+    exitWithErrorCode(EC, OutputFilename);
 
   auto Writer = std::move(WriterOrErr.get());
   StringMap<FunctionSamples> ProfileMap;
@@ -82,7 +98,7 @@ static void mergeSampleProfile(const cl::list<std::string> &Inputs,
     auto ReaderOrErr =
         SampleProfileReader::create(Filename, getGlobalContext());
     if (std::error_code EC = ReaderOrErr.getError())
-      exitWithError(EC.message(), Filename);
+      exitWithErrorCode(EC, Filename);
 
     // We need to keep the readers around until after all the files are
     // read so that we do not lose the function names stored in each
@@ -91,7 +107,7 @@ static void mergeSampleProfile(const cl::list<std::string> &Inputs,
     Readers.push_back(std::move(ReaderOrErr.get()));
     const auto Reader = Readers.back().get();
     if (std::error_code EC = Reader->read())
-      exitWithError(EC.message(), Filename);
+      exitWithErrorCode(EC, Filename);
 
     StringMap<FunctionSamples> &Profiles = Reader->getProfiles();
     for (StringMap<FunctionSamples>::iterator I = Profiles.begin(),
@@ -143,7 +159,7 @@ static int showInstrProfile(std::string Filename, bool ShowCounts,
                             std::string ShowFunction, raw_fd_ostream &OS) {
   auto ReaderOrErr = InstrProfReader::create(Filename);
   if (std::error_code EC = ReaderOrErr.getError())
-    exitWithError(EC.message(), Filename);
+    exitWithErrorCode(EC, Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
   uint64_t MaxFunctionCount = 0, MaxBlockCount = 0;
@@ -198,7 +214,7 @@ static int showInstrProfile(std::string Filename, bool ShowCounts,
     }
   }
   if (Reader->hasError())
-    exitWithError(Reader->getError().message(), Filename);
+    exitWithErrorCode(Reader->getError(), Filename);
 
   if (ShowAllFunctions || !ShowFunction.empty())
     OS << "Functions shown: " << ShownFunctions << "\n";
@@ -214,11 +230,11 @@ static int showSampleProfile(std::string Filename, bool ShowCounts,
   using namespace sampleprof;
   auto ReaderOrErr = SampleProfileReader::create(Filename, getGlobalContext());
   if (std::error_code EC = ReaderOrErr.getError())
-    exitWithError(EC.message(), Filename);
+    exitWithErrorCode(EC, Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
   if (std::error_code EC = Reader->read())
-    exitWithError(EC.message(), Filename);
+    exitWithErrorCode(EC, Filename);
 
   if (ShowAllFunctions || ShowFunction.empty())
     Reader->dump(OS);
@@ -259,7 +275,7 @@ static int show_main(int argc, const char *argv[]) {
   std::error_code EC;
   raw_fd_ostream OS(OutputFilename.data(), EC, sys::fs::F_Text);
   if (EC)
-    exitWithError(EC.message(), OutputFilename);
+      exitWithErrorCode(EC, OutputFilename);
 
   if (ShowAllFunctions && !ShowFunction.empty())
     errs() << "warning: -function argument ignored: showing all functions\n";