[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

llvm-svn: 252916

4 files changed, 42 insertions, 11 deletions

diff --git a/llvm/lib/ProfileData/InstrProf.cpp b/llvm/lib/ProfileData/InstrProf.cpp
index 92a3c251f6e..762f00b48b6 100644
--- a/llvm/lib/ProfileData/InstrProf.cpp
+++ b/llvm/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/llvm/lib/ProfileData/InstrProfReader.cpp b/llvm/lib/ProfileData/InstrProfReader.cpp
index bf10b448e4c..6f201243736 100644
--- a/llvm/lib/ProfileData/InstrProfReader.cpp
+++ b/llvm/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/llvm/lib/ProfileData/SampleProf.cpp b/llvm/lib/ProfileData/SampleProf.cpp
index b5d3b2d2e55..856923e164b 100644
--- a/llvm/lib/ProfileData/SampleProf.cpp
+++ b/llvm/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/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
index a5d00083b53..0bed4f09f1f 100644
--- a/llvm/lib/ProfileData/SampleProfReader.cpp
+++ b/llvm/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;