From: Nathan Slingerland Date: Thu, 12 Nov 2015 18:06:18 +0000 (+0000) Subject: [llvm-profdata] Add check for text profile formats and improve error reporting X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=commitdiff_plain;h=7b81b822ba8418a27225056bff9229b2d6c7dca9 [llvm-profdata] Add check for text profile formats and improve error reporting 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@252916 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/include/llvm/ProfileData/InstrProf.h b/include/llvm/ProfileData/InstrProf.h index 607f29de8a2..2339a46f9c5 100644 --- 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 d0f5a57b1ae..3d4777a853e 100644 --- a/include/llvm/ProfileData/InstrProfReader.h +++ b/include/llvm/ProfileData/InstrProfReader.h @@ -111,6 +111,9 @@ public: TextInstrProfReader(std::unique_ptr 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 2f404be50e6..1fb2cf6e0ca 100644 --- 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 92a3c251f6e..762f00b48b6 100644 --- 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 bf10b448e4c..6f201243736 100644 --- a/lib/ProfileData/InstrProfReader.cpp +++ b/lib/ProfileData/InstrProfReader.cpp @@ -54,8 +54,10 @@ InstrProfReader::create(std::unique_ptr 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 b5d3b2d2e55..856923e164b 100644 --- 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 a5d00083b53..0bed4f09f1f 100644 --- 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 ErrorOr 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/tools/llvm-profdata/raw-magic-but-no-header.test b/test/tools/llvm-profdata/raw-magic-but-no-header.test index b2a697042b0..76894faa183 100644 --- 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 0651c513e96..9981d4204c4 100644 --- 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 01513e4fcb9..113b10ee4e8 100644 --- 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 48fc83c6971..1cd47dd5e84 100644 --- 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(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 &Inputs, @@ -49,20 +65,20 @@ static void mergeInstrProfile(const cl::list &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 &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 ProfileMap; @@ -82,7 +98,7 @@ static void mergeSampleProfile(const cl::list &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 &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 &Profiles = Reader->getProfiles(); for (StringMap::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";