#include "llvm/Analysis/Verifier.h"
#include "llvm/Bitcode/BitstreamReader.h"
#include "llvm/Bitcode/LLVMBitCodes.h"
+#include "llvm/Bitcode/ReaderWriter.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/PrettyStackTrace.h"
#include "llvm/System/Signals.h"
#include <map>
-#include <fstream>
-#include <iostream>
#include <algorithm>
using namespace llvm;
/// GetBlockName - Return a symbolic block name if known, otherwise return
/// null.
-static const char *GetBlockName(unsigned BlockID) {
+static const char *GetBlockName(unsigned BlockID,
+ const BitstreamReader &StreamFile) {
// Standard blocks for all bitcode files.
if (BlockID < bitc::FIRST_APPLICATION_BLOCKID) {
if (BlockID == bitc::BLOCKINFO_BLOCK_ID)
return 0;
}
+ // Check to see if we have a blockinfo record for this block, with a name.
+ if (const BitstreamReader::BlockInfo *Info =
+ StreamFile.getBlockInfo(BlockID)) {
+ if (!Info->Name.empty())
+ return Info->Name.c_str();
+ }
+
+
if (CurStreamType != LLVMIRBitstream) return 0;
switch (BlockID) {
case bitc::FUNCTION_BLOCK_ID: return "FUNCTION_BLOCK";
case bitc::TYPE_SYMTAB_BLOCK_ID: return "TYPE_SYMTAB";
case bitc::VALUE_SYMTAB_BLOCK_ID: return "VALUE_SYMTAB";
+ case bitc::METADATA_BLOCK_ID: return "METADATA_BLOCK";
}
}
/// GetCodeName - Return a symbolic code name if known, otherwise return
/// null.
-static const char *GetCodeName(unsigned CodeID, unsigned BlockID) {
+static const char *GetCodeName(unsigned CodeID, unsigned BlockID,
+ const BitstreamReader &StreamFile) {
// Standard blocks for all bitcode files.
if (BlockID < bitc::FIRST_APPLICATION_BLOCKID) {
if (BlockID == bitc::BLOCKINFO_BLOCK_ID) {
switch (CodeID) {
default: return 0;
- case bitc::MODULE_CODE_VERSION: return "VERSION";
+ case bitc::BLOCKINFO_CODE_SETBID: return "SETBID";
+ case bitc::BLOCKINFO_CODE_BLOCKNAME: return "BLOCKNAME";
+ case bitc::BLOCKINFO_CODE_SETRECORDNAME: return "SETRECORDNAME";
}
}
return 0;
}
+ // Check to see if we have a blockinfo record for this record, with a name.
+ if (const BitstreamReader::BlockInfo *Info =
+ StreamFile.getBlockInfo(BlockID)) {
+ for (unsigned i = 0, e = Info->RecordNames.size(); i != e; ++i)
+ if (Info->RecordNames[i].first == CodeID)
+ return Info->RecordNames[i].second.c_str();
+ }
+
+
if (CurStreamType != LLVMIRBitstream) return 0;
switch (BlockID) {
case bitc::MODULE_CODE_FUNCTION: return "FUNCTION";
case bitc::MODULE_CODE_ALIAS: return "ALIAS";
case bitc::MODULE_CODE_PURGEVALS: return "PURGEVALS";
+ case bitc::MODULE_CODE_GCNAME: return "GCNAME";
}
case bitc::PARAMATTR_BLOCK_ID:
switch (CodeID) {
case bitc::TYPE_BLOCK_ID:
switch (CodeID) {
default: return 0;
- case bitc::TYPE_CODE_NUMENTRY: return "NUMENTRY";
- case bitc::TYPE_CODE_VOID: return "VOID";
- case bitc::TYPE_CODE_FLOAT: return "FLOAT";
- case bitc::TYPE_CODE_DOUBLE: return "DOUBLE";
- case bitc::TYPE_CODE_LABEL: return "LABEL";
- case bitc::TYPE_CODE_OPAQUE: return "OPAQUE";
- case bitc::TYPE_CODE_INTEGER: return "INTEGER";
- case bitc::TYPE_CODE_POINTER: return "POINTER";
- case bitc::TYPE_CODE_FUNCTION: return "FUNCTION";
- case bitc::TYPE_CODE_STRUCT: return "STRUCT";
- case bitc::TYPE_CODE_ARRAY: return "ARRAY";
- case bitc::TYPE_CODE_VECTOR: return "VECTOR";
+ case bitc::TYPE_CODE_NUMENTRY: return "NUMENTRY";
+ case bitc::TYPE_CODE_VOID: return "VOID";
+ case bitc::TYPE_CODE_FLOAT: return "FLOAT";
+ case bitc::TYPE_CODE_DOUBLE: return "DOUBLE";
+ case bitc::TYPE_CODE_LABEL: return "LABEL";
+ case bitc::TYPE_CODE_OPAQUE: return "OPAQUE";
+ case bitc::TYPE_CODE_INTEGER: return "INTEGER";
+ case bitc::TYPE_CODE_POINTER: return "POINTER";
+ case bitc::TYPE_CODE_FUNCTION: return "FUNCTION";
+ case bitc::TYPE_CODE_STRUCT: return "STRUCT";
+ case bitc::TYPE_CODE_ARRAY: return "ARRAY";
+ case bitc::TYPE_CODE_VECTOR: return "VECTOR";
+ case bitc::TYPE_CODE_X86_FP80: return "X86_FP80";
+ case bitc::TYPE_CODE_FP128: return "FP128";
+ case bitc::TYPE_CODE_PPC_FP128: return "PPC_FP128";
+ case bitc::TYPE_CODE_METADATA: return "METADATA";
}
case bitc::CONSTANTS_BLOCK_ID:
case bitc::CST_CODE_CE_SHUFFLEVEC: return "CE_SHUFFLEVEC";
case bitc::CST_CODE_CE_CMP: return "CE_CMP";
case bitc::CST_CODE_INLINEASM: return "INLINEASM";
+ case bitc::CST_CODE_CE_SHUFVEC_EX: return "CE_SHUFVEC_EX";
}
case bitc::FUNCTION_BLOCK_ID:
switch (CodeID) {
default: return 0;
case bitc::FUNC_CODE_DECLAREBLOCKS: return "DECLAREBLOCKS";
- case bitc::FUNC_CODE_INST_BB_UNWINDDEST: return "UNWINDDEST";
case bitc::FUNC_CODE_INST_BINOP: return "INST_BINOP";
case bitc::FUNC_CODE_INST_CAST: return "INST_CAST";
case bitc::FUNC_CODE_INST_VAARG: return "INST_VAARG";
case bitc::FUNC_CODE_INST_STORE2: return "INST_STORE2";
case bitc::FUNC_CODE_INST_GETRESULT: return "INST_GETRESULT";
+ case bitc::FUNC_CODE_INST_EXTRACTVAL: return "INST_EXTRACTVAL";
+ case bitc::FUNC_CODE_INST_INSERTVAL: return "INST_INSERTVAL";
+ case bitc::FUNC_CODE_INST_CMP2: return "INST_CMP2";
+ case bitc::FUNC_CODE_INST_VSELECT: return "INST_VSELECT";
}
case bitc::TYPE_SYMTAB_BLOCK_ID:
switch (CodeID) {
case bitc::VST_CODE_ENTRY: return "ENTRY";
case bitc::VST_CODE_BBENTRY: return "BBENTRY";
}
+ case bitc::METADATA_BLOCK_ID:
+ switch(CodeID) {
+ default:return 0;
+ case bitc::METADATA_STRING: return "MDSTRING";
+ case bitc::METADATA_NODE: return "MDNODE";
+ case bitc::METADATA_NAME: return "METADATA_NAME";
+ case bitc::METADATA_NAMED_NODE: return "NAMEDMDNODE";
+ }
}
}
+struct PerRecordStats {
+ unsigned NumInstances;
+ unsigned NumAbbrev;
+ uint64_t TotalBits;
+
+ PerRecordStats() : NumInstances(0), NumAbbrev(0), TotalBits(0) {}
+};
struct PerBlockIDStats {
/// NumInstances - This the number of times this block ID has been seen.
unsigned NumRecords, NumAbbreviatedRecords;
/// CodeFreq - Keep track of the number of times we see each code.
- std::vector<unsigned> CodeFreq;
+ std::vector<PerRecordStats> CodeFreq;
PerBlockIDStats()
: NumInstances(0), NumBits(0),
/// Error - All bitcode analysis errors go through this function, making this a
/// good place to breakpoint if debugging.
static bool Error(const std::string &Err) {
- std::cerr << Err << "\n";
+ errs() << Err << "\n";
return true;
}
/// ParseBlock - Read a block, updating statistics, etc.
-static bool ParseBlock(BitstreamReader &Stream, unsigned IndentLevel) {
+static bool ParseBlock(BitstreamCursor &Stream, unsigned IndentLevel) {
std::string Indent(IndentLevel*2, ' ');
uint64_t BlockBitStart = Stream.GetCurrentBitNo();
unsigned BlockID = Stream.ReadSubBlockID();
// BLOCKINFO is a special part of the stream.
if (BlockID == bitc::BLOCKINFO_BLOCK_ID) {
- if (Dump) std::cerr << Indent << "<BLOCKINFO_BLOCK/>\n";
+ if (Dump) errs() << Indent << "<BLOCKINFO_BLOCK/>\n";
if (Stream.ReadBlockInfoBlock())
return Error("Malformed BlockInfoBlock");
uint64_t BlockBitEnd = Stream.GetCurrentBitNo();
const char *BlockName = 0;
if (Dump) {
- std::cerr << Indent << "<";
- if ((BlockName = GetBlockName(BlockID)))
- std::cerr << BlockName;
+ errs() << Indent << "<";
+ if ((BlockName = GetBlockName(BlockID, *Stream.getBitStreamReader())))
+ errs() << BlockName;
else
- std::cerr << "UnknownBlock" << BlockID;
+ errs() << "UnknownBlock" << BlockID;
if (NonSymbolic && BlockName)
- std::cerr << " BlockID=" << BlockID;
+ errs() << " BlockID=" << BlockID;
- std::cerr << " NumWords=" << NumWords
- << " BlockCodeSize=" << Stream.GetAbbrevIDWidth() << ">\n";
+ errs() << " NumWords=" << NumWords
+ << " BlockCodeSize=" << Stream.GetAbbrevIDWidth() << ">\n";
}
SmallVector<uint64_t, 64> Record;
if (Stream.AtEndOfStream())
return Error("Premature end of bitstream");
+ uint64_t RecordStartBit = Stream.GetCurrentBitNo();
+
// Read the code for this record.
unsigned AbbrevID = Stream.ReadCode();
switch (AbbrevID) {
uint64_t BlockBitEnd = Stream.GetCurrentBitNo();
BlockStats.NumBits += BlockBitEnd-BlockBitStart;
if (Dump) {
- std::cerr << Indent << "</";
+ errs() << Indent << "</";
if (BlockName)
- std::cerr << BlockName << ">\n";
+ errs() << BlockName << ">\n";
else
- std::cerr << "UnknownBlock" << BlockID << ">\n";
+ errs() << "UnknownBlock" << BlockID << ">\n";
}
return false;
}
++BlockStats.NumAbbrevs;
break;
default:
+ Record.clear();
+
++BlockStats.NumRecords;
if (AbbrevID != bitc::UNABBREV_RECORD)
++BlockStats.NumAbbreviatedRecords;
-
- Record.clear();
- unsigned Code = Stream.ReadRecord(AbbrevID, Record);
+
+ const char *BlobStart = 0;
+ unsigned BlobLen = 0;
+ unsigned Code = Stream.ReadRecord(AbbrevID, Record, BlobStart, BlobLen);
+
+
// Increment the # occurrences of this code.
if (BlockStats.CodeFreq.size() <= Code)
BlockStats.CodeFreq.resize(Code+1);
- BlockStats.CodeFreq[Code]++;
-
+ BlockStats.CodeFreq[Code].NumInstances++;
+ BlockStats.CodeFreq[Code].TotalBits +=
+ Stream.GetCurrentBitNo()-RecordStartBit;
+ if (AbbrevID != bitc::UNABBREV_RECORD)
+ BlockStats.CodeFreq[Code].NumAbbrev++;
+
if (Dump) {
- std::cerr << Indent << " <";
- if (const char *CodeName = GetCodeName(Code, BlockID))
- std::cerr << CodeName;
+ errs() << Indent << " <";
+ if (const char *CodeName =
+ GetCodeName(Code, BlockID, *Stream.getBitStreamReader()))
+ errs() << CodeName;
else
- std::cerr << "UnknownCode" << Code;
- if (NonSymbolic && GetCodeName(Code, BlockID))
- std::cerr << " codeid=" << Code;
+ errs() << "UnknownCode" << Code;
+ if (NonSymbolic &&
+ GetCodeName(Code, BlockID, *Stream.getBitStreamReader()))
+ errs() << " codeid=" << Code;
if (AbbrevID != bitc::UNABBREV_RECORD)
- std::cerr << " abbrevid=" << AbbrevID;
+ errs() << " abbrevid=" << AbbrevID;
for (unsigned i = 0, e = Record.size(); i != e; ++i)
- std::cerr << " op" << i << "=" << (int64_t)Record[i];
+ errs() << " op" << i << "=" << (int64_t)Record[i];
+
+ errs() << "/>";
- std::cerr << "/>\n";
+ if (BlobStart) {
+ errs() << " blob data = ";
+ bool BlobIsPrintable = true;
+ for (unsigned i = 0; i != BlobLen; ++i)
+ if (!isprint(BlobStart[i])) {
+ BlobIsPrintable = false;
+ break;
+ }
+
+ if (BlobIsPrintable)
+ errs() << "'" << std::string(BlobStart, BlobStart+BlobLen) <<"'";
+ else
+ errs() << "unprintable, " << BlobLen << " bytes.";
+ }
+
+ errs() << "\n";
}
break;
}
static void PrintSize(double Bits) {
- std::cerr << Bits << "b/" << Bits/8 << "B/" << Bits/32 << "W";
+ fprintf(stderr, "%.2f/%.2fB/%lluW", Bits, Bits/8,(unsigned long long)Bits/32);
+}
+static void PrintSize(uint64_t Bits) {
+ fprintf(stderr, "%llub/%.2fB/%lluW", (unsigned long long)Bits,
+ (double)Bits/8, (unsigned long long)Bits/32);
}
/// AnalyzeBitcode - Analyze the bitcode file specified by InputFilename.
static int AnalyzeBitcode() {
// Read the input file.
- MemoryBuffer *Buffer;
- if (InputFilename == "-")
- Buffer = MemoryBuffer::getSTDIN();
- else
- Buffer = MemoryBuffer::getFile(&InputFilename[0], InputFilename.size());
+ MemoryBuffer *MemBuf = MemoryBuffer::getFileOrSTDIN(InputFilename.c_str());
- if (Buffer == 0)
+ if (MemBuf == 0)
return Error("Error reading '" + InputFilename + "'.");
- if (Buffer->getBufferSize() & 3)
+ if (MemBuf->getBufferSize() & 3)
return Error("Bitcode stream should be a multiple of 4 bytes in length");
- unsigned char *BufPtr = (unsigned char *)Buffer->getBufferStart();
- BitstreamReader Stream(BufPtr, BufPtr+Buffer->getBufferSize());
-
+ unsigned char *BufPtr = (unsigned char *)MemBuf->getBufferStart();
+ unsigned char *EndBufPtr = BufPtr+MemBuf->getBufferSize();
+
+ // If we have a wrapper header, parse it and ignore the non-bc file contents.
+ // The magic number is 0x0B17C0DE stored in little endian.
+ if (isBitcodeWrapper(BufPtr, EndBufPtr))
+ if (SkipBitcodeWrapperHeader(BufPtr, EndBufPtr))
+ return Error("Invalid bitcode wrapper header");
+
+ BitstreamReader StreamFile(BufPtr, EndBufPtr);
+ BitstreamCursor Stream(StreamFile);
+ StreamFile.CollectBlockInfoNames();
// Read the stream signature.
char Signature[6];
++NumTopBlocks;
}
- if (Dump) std::cerr << "\n\n";
+ if (Dump) errs() << "\n\n";
- uint64_t BufferSizeBits = Buffer->getBufferSize()*8;
+ uint64_t BufferSizeBits = (EndBufPtr-BufPtr)*CHAR_BIT;
// Print a summary of the read file.
- std::cerr << "Summary of " << InputFilename << ":\n";
- std::cerr << " Total size: ";
+ errs() << "Summary of " << InputFilename << ":\n";
+ errs() << " Total size: ";
PrintSize(BufferSizeBits);
- std::cerr << "\n";
- std::cerr << " Stream type: ";
+ errs() << "\n";
+ errs() << " Stream type: ";
switch (CurStreamType) {
default: assert(0 && "Unknown bitstream type");
- case UnknownBitstream: std::cerr << "unknown\n"; break;
- case LLVMIRBitstream: std::cerr << "LLVM IR\n"; break;
+ case UnknownBitstream: errs() << "unknown\n"; break;
+ case LLVMIRBitstream: errs() << "LLVM IR\n"; break;
}
- std::cerr << " # Toplevel Blocks: " << NumTopBlocks << "\n";
- std::cerr << "\n";
+ errs() << " # Toplevel Blocks: " << NumTopBlocks << "\n";
+ errs() << "\n";
// Emit per-block stats.
- std::cerr << "Per-block Summary:\n";
+ errs() << "Per-block Summary:\n";
for (std::map<unsigned, PerBlockIDStats>::iterator I = BlockIDStats.begin(),
E = BlockIDStats.end(); I != E; ++I) {
- std::cerr << " Block ID #" << I->first;
- if (const char *BlockName = GetBlockName(I->first))
- std::cerr << " (" << BlockName << ")";
- std::cerr << ":\n";
+ errs() << " Block ID #" << I->first;
+ if (const char *BlockName = GetBlockName(I->first, StreamFile))
+ errs() << " (" << BlockName << ")";
+ errs() << ":\n";
const PerBlockIDStats &Stats = I->second;
- std::cerr << " Num Instances: " << Stats.NumInstances << "\n";
- std::cerr << " Total Size: ";
+ errs() << " Num Instances: " << Stats.NumInstances << "\n";
+ errs() << " Total Size: ";
PrintSize(Stats.NumBits);
- std::cerr << "\n";
- std::cerr << " % of file: "
- << Stats.NumBits/(double)BufferSizeBits*100 << "\n";
+ errs() << "\n";
+ errs() << " % of file: "
+ << Stats.NumBits/(double)BufferSizeBits*100 << "\n";
if (Stats.NumInstances > 1) {
- std::cerr << " Average Size: ";
+ errs() << " Average Size: ";
PrintSize(Stats.NumBits/(double)Stats.NumInstances);
- std::cerr << "\n";
- std::cerr << " Tot/Avg SubBlocks: " << Stats.NumSubBlocks << "/"
- << Stats.NumSubBlocks/(double)Stats.NumInstances << "\n";
- std::cerr << " Tot/Avg Abbrevs: " << Stats.NumAbbrevs << "/"
- << Stats.NumAbbrevs/(double)Stats.NumInstances << "\n";
- std::cerr << " Tot/Avg Records: " << Stats.NumRecords << "/"
- << Stats.NumRecords/(double)Stats.NumInstances << "\n";
+ errs() << "\n";
+ errs() << " Tot/Avg SubBlocks: " << Stats.NumSubBlocks << "/"
+ << Stats.NumSubBlocks/(double)Stats.NumInstances << "\n";
+ errs() << " Tot/Avg Abbrevs: " << Stats.NumAbbrevs << "/"
+ << Stats.NumAbbrevs/(double)Stats.NumInstances << "\n";
+ errs() << " Tot/Avg Records: " << Stats.NumRecords << "/"
+ << Stats.NumRecords/(double)Stats.NumInstances << "\n";
} else {
- std::cerr << " Num SubBlocks: " << Stats.NumSubBlocks << "\n";
- std::cerr << " Num Abbrevs: " << Stats.NumAbbrevs << "\n";
- std::cerr << " Num Records: " << Stats.NumRecords << "\n";
+ errs() << " Num SubBlocks: " << Stats.NumSubBlocks << "\n";
+ errs() << " Num Abbrevs: " << Stats.NumAbbrevs << "\n";
+ errs() << " Num Records: " << Stats.NumRecords << "\n";
}
if (Stats.NumRecords)
- std::cerr << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/
- (double)Stats.NumRecords)*100 << "\n";
- std::cerr << "\n";
+ errs() << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/
+ (double)Stats.NumRecords)*100 << "\n";
+ errs() << "\n";
// Print a histogram of the codes we see.
if (!NoHistogram && !Stats.CodeFreq.empty()) {
std::vector<std::pair<unsigned, unsigned> > FreqPairs; // <freq,code>
for (unsigned i = 0, e = Stats.CodeFreq.size(); i != e; ++i)
- if (unsigned Freq = Stats.CodeFreq[i])
+ if (unsigned Freq = Stats.CodeFreq[i].NumInstances)
FreqPairs.push_back(std::make_pair(Freq, i));
std::stable_sort(FreqPairs.begin(), FreqPairs.end());
std::reverse(FreqPairs.begin(), FreqPairs.end());
- std::cerr << "\tCode Histogram:\n";
+ errs() << "\tRecord Histogram:\n";
+ fprintf(stderr, "\t\t Count # Bits %% Abv Record Kind\n");
for (unsigned i = 0, e = FreqPairs.size(); i != e; ++i) {
- std::cerr << "\t\t" << FreqPairs[i].first << "\t";
- if (const char *CodeName = GetCodeName(FreqPairs[i].second, I->first))
- std::cerr << CodeName << "\n";
+ const PerRecordStats &RecStats = Stats.CodeFreq[FreqPairs[i].second];
+
+ fprintf(stderr, "\t\t%7d %9llu ", RecStats.NumInstances,
+ (unsigned long long)RecStats.TotalBits);
+
+ if (RecStats.NumAbbrev)
+ fprintf(stderr, "%7.2f ",
+ (double)RecStats.NumAbbrev/RecStats.NumInstances*100);
+ else
+ fprintf(stderr, " ");
+
+ if (const char *CodeName =
+ GetCodeName(FreqPairs[i].second, I->first, StreamFile))
+ fprintf(stderr, "%s\n", CodeName);
else
- std::cerr << "UnknownCode" << FreqPairs[i].second << "\n";
+ fprintf(stderr, "UnknownCode%d\n", FreqPairs[i].second);
}
- std::cerr << "\n";
+ errs() << "\n";
}
}
int main(int argc, char **argv) {
- llvm_shutdown_obj X; // Call llvm_shutdown() on exit.
- cl::ParseCommandLineOptions(argc, argv, "llvm-bcanalyzer file analyzer\n");
-
+ // Print a stack trace if we signal out.
sys::PrintStackTraceOnErrorSignal();
+ PrettyStackTraceProgram X(argc, argv);
+ llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
+ cl::ParseCommandLineOptions(argc, argv, "llvm-bcanalyzer file analyzer\n");
return AnalyzeBitcode();
}