Minor Instr PGO code restructuring

1. Key constant values (version, magic) and data structures related to raw and 
   indexed profile format are moved into one centralized file: InstrProf.h.
2. Utility function such as MD5Hash computation is also moved to the common 
   header to allow sharing with other components in the future.
3. A header data structure is introduced for Indexed format so that the reader
   and writer can always be in sync.
4. Added some comments to document different places where multiple definition
   of the data structure must be kept in sync (reader/writer, runtime, lowering 
   etc).  No functional change is intended.

Differential Revision:  http://reviews.llvm.org/D13758

llvm-svn: 250638

2 files changed, 105 insertions, 19 deletions

diff --git a/llvm/include/llvm/ProfileData/InstrProf.h b/llvm/include/llvm/ProfileData/InstrProf.h
index 668e6d3663d..f425c6e13ed 100644
--- a/llvm/include/llvm/ProfileData/InstrProf.h
+++ b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -16,8 +16,11 @@
 #ifndef LLVM_PROFILEDATA_INSTRPROF_H_
 #define LLVM_PROFILEDATA_INSTRPROF_H_
 
+#include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/StringSet.h"
+#include "llvm/Support/Endian.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/MD5.h"
 #include <cstdint>
 #include <list>
 #include <system_error>
@@ -132,6 +135,105 @@ struct InstrProfRecord {
   }
 };
 
+namespace IndexedInstrProf {
+enum class HashT : uint32_t {
+  MD5,
+
+  Last = MD5
+};
+
+static inline uint64_t MD5Hash(StringRef Str) {
+  MD5 Hash;
+  Hash.update(Str);
+  llvm::MD5::MD5Result Result;
+  Hash.final(Result);
+  // Return the least significant 8 bytes. Our MD5 implementation returns the
+  // result in little endian, so we may need to swap bytes.
+  using namespace llvm::support;
+  return endian::read<uint64_t, little, unaligned>(Result);
+}
+
+static inline uint64_t ComputeHash(HashT Type, StringRef K) {
+  switch (Type) {
+    case HashT::MD5:
+      return IndexedInstrProf::MD5Hash(K);
+  }
+  llvm_unreachable("Unhandled hash type");
+}
+
+const uint64_t Magic = 0x8169666f72706cff;  // "\xfflprofi\x81"
+const uint64_t Version = 3;
+const HashT HashType = HashT::MD5;
+
+struct Header {
+  uint64_t Magic;
+  uint64_t Version;
+  uint64_t MaxFunctionCount;
+  uint64_t HashType;
+  uint64_t HashOffset;
+};
+
+}  // end namespace IndexedInstrProf
+
+namespace RawInstrProf {
+
+const uint64_t Version = 1;
+
+// Magic number to detect file format and endianness.
+// Use 255 at one end, since no UTF-8 file can use that character.  Avoid 0,
+// so that utilities, like strings, don't grab it as a string.  129 is also
+// invalid UTF-8, and high enough to be interesting.
+// Use "lprofr" in the centre to stand for "LLVM Profile Raw", or "lprofR"
+// for 32-bit platforms.
+// The magic and version need to be kept in sync with
+// projects/compiler-rt/lib/profile/InstrProfiling.c
+
+template <class IntPtrT>
+inline uint64_t getMagic();
+template <>
+inline uint64_t getMagic<uint64_t>() {
+  return uint64_t(255) << 56 | uint64_t('l') << 48 | uint64_t('p') << 40 |
+         uint64_t('r') << 32 | uint64_t('o') << 24 | uint64_t('f') << 16 |
+         uint64_t('r') << 8 | uint64_t(129);
+}
+
+template <>
+inline uint64_t getMagic<uint32_t>() {
+  return uint64_t(255) << 56 | uint64_t('l') << 48 | uint64_t('p') << 40 |
+         uint64_t('r') << 32 | uint64_t('o') << 24 | uint64_t('f') << 16 |
+         uint64_t('R') << 8 | uint64_t(129);
+}
+
+// The definition should match the structure defined in
+// compiler-rt/lib/profile/InstrProfiling.h.
+// It should also match the synthesized type in
+// Transforms/Instrumentation/InstrProfiling.cpp:getOrCreateRegionCounters.
+
+template <class IntPtrT>
+struct ProfileData {
+  const uint32_t NameSize;
+  const uint32_t NumCounters;
+  const uint64_t FuncHash;
+  const IntPtrT NamePtr;
+  const IntPtrT CounterPtr;
+};
+
+// The definition should match the header referenced in
+// compiler-rt/lib/profile/InstrProfilingFile.c  and
+// InstrProfilingBuffer.c.
+
+struct Header {
+  const uint64_t Magic;
+  const uint64_t Version;
+  const uint64_t DataSize;
+  const uint64_t CountersSize;
+  const uint64_t NamesSize;
+  const uint64_t CountersDelta;
+  const uint64_t NamesDelta;
+};
+
+}  // end namespace RawInstrProf
+
 } // end namespace llvm
 
 namespace std {
diff --git a/llvm/include/llvm/ProfileData/InstrProfReader.h b/llvm/include/llvm/ProfileData/InstrProfReader.h
index c0585d6f6d2..cdead0f112d 100644
--- a/llvm/include/llvm/ProfileData/InstrProfReader.h
+++ b/llvm/include/llvm/ProfileData/InstrProfReader.h
@@ -132,28 +132,12 @@ class RawInstrProfReader : public InstrProfReader {
 private:
   /// The profile data file contents.
   std::unique_ptr<MemoryBuffer> DataBuffer;
-  struct ProfileData {
-    const uint32_t NameSize;
-    const uint32_t NumCounters;
-    const uint64_t FuncHash;
-    const IntPtrT NamePtr;
-    const IntPtrT CounterPtr;
-  };
-  struct RawHeader {
-    const uint64_t Magic;
-    const uint64_t Version;
-    const uint64_t DataSize;
-    const uint64_t CountersSize;
-    const uint64_t NamesSize;
-    const uint64_t CountersDelta;
-    const uint64_t NamesDelta;
-  };
 
   bool ShouldSwapBytes;
   uint64_t CountersDelta;
   uint64_t NamesDelta;
-  const ProfileData *Data;
-  const ProfileData *DataEnd;
+  const RawInstrProf::ProfileData<IntPtrT> *Data;
+  const RawInstrProf::ProfileData<IntPtrT> *DataEnd;
   const uint64_t *CountersStart;
   const char *NamesStart;
   const char *ProfileEnd;
@@ -170,7 +154,7 @@ public:
 
 private:
   std::error_code readNextHeader(const char *CurrentPos);
-  std::error_code readHeader(const RawHeader &Header);
+  std::error_code readHeader(const RawInstrProf::Header &Header);
   template <class IntT>
   IntT swap(IntT Int) const {
     return ShouldSwapBytes ? sys::getSwappedBytes(Int) : Int;