[lld] 4d2eda2 - Revert "[LLD] [COFF] Use StringTableBuilder to optimize the string table"
Martin Storsjö via llvm-commits
llvm-commits at lists.llvm.org
Tue Jun 21 03:25:14 PDT 2022
Author: Martin Storsjö
Date: 2022-06-21T13:25:08+03:00
New Revision: 4d2eda2bb3156cee63ea486be34b01164b178e10
URL: https://github.com/llvm/llvm-project/commit/4d2eda2bb3156cee63ea486be34b01164b178e10
DIFF: https://github.com/llvm/llvm-project/commit/4d2eda2bb3156cee63ea486be34b01164b178e10.diff
LOG: Revert "[LLD] [COFF] Use StringTableBuilder to optimize the string table"
This reverts commit 9ffeaaa0ea54307db309104696a0b6cce6ddda38.
This fixes debugging large executables with lldb and gdb.
When StringTableBuilder is used, the string offsets for any string
can point anywhere in the string table - while previously, all strings
were inserted in order (without deduplication and tail merging).
For symbols, there's no complications in encoding the string offset;
the offset is encoded as a raw 32 bit binary number in half of the
symbol name field.
For sections, the string table offset is written as
"/<decimaloffset>", but if the decimal offset would be larger than
7 digits, it's instead written as "//<base64offset>". Tools that
operate on object files can handle the base64 offset format, but
apparently neither lldb nor gdb expect that syntax when locating the
debug information section. Prior to the reverted commit, all long
section names were located at the start of the string table, so
their offset never exceeded the range for the decimal syntax.
Just reverting this change for now, as the actual benefit from it
was fairly modest.
Longer term, lld could write all long section names unoptimized
at the start of the string table, followed by all the strings for
symbol names, with deduplication and tail merging. And lldb and
gdb could be fixed to handle sections with the base64 offset syntax.
This fixes https://github.com/mstorsjo/llvm-mingw/issues/289.
Added:
Modified:
lld/COFF/Writer.cpp
Removed:
################################################################################
diff --git a/lld/COFF/Writer.cpp b/lld/COFF/Writer.cpp
index 1b9a870d4630..df60c9032b2d 100644
--- a/lld/COFF/Writer.cpp
+++ b/lld/COFF/Writer.cpp
@@ -24,7 +24,6 @@
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/ADT/StringSwitch.h"
-#include "llvm/MC/StringTableBuilder.h"
#include "llvm/Support/BinaryStreamReader.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Endian.h"
@@ -196,9 +195,7 @@ class PartialSectionKey {
// The writer writes a SymbolTable result to a file.
class Writer {
public:
- Writer(COFFLinkerContext &c)
- : buffer(errorHandler().outputBuffer),
- strtab(StringTableBuilder::WinCOFF), ctx(c) {}
+ Writer(COFFLinkerContext &c) : buffer(errorHandler().outputBuffer), ctx(c) {}
void run();
private:
@@ -243,6 +240,7 @@ class Writer {
PartialSection *findPartialSection(StringRef name, uint32_t outChars);
llvm::Optional<coff_symbol16> createSymbol(Defined *d);
+ size_t addEntryToStringTable(StringRef str);
OutputSection *findSection(StringRef name);
void addBaserels();
@@ -252,7 +250,7 @@ class Writer {
std::unique_ptr<FileOutputBuffer> &buffer;
std::map<PartialSectionKey, PartialSection *> partialSections;
- StringTableBuilder strtab;
+ std::vector<char> strtab;
std::vector<llvm::object::coff_symbol16> outputSymtab;
IdataContents idata;
Chunk *importTableStart = nullptr;
@@ -1128,6 +1126,14 @@ void Writer::assignOutputSectionIndices() {
sc->setOutputSectionIdx(mc->getOutputSectionIdx());
}
+size_t Writer::addEntryToStringTable(StringRef str) {
+ assert(str.size() > COFF::NameSize);
+ size_t offsetOfEntry = strtab.size() + 4; // +4 for the size field
+ strtab.insert(strtab.end(), str.begin(), str.end());
+ strtab.push_back('\0');
+ return offsetOfEntry;
+}
+
Optional<coff_symbol16> Writer::createSymbol(Defined *def) {
coff_symbol16 sym;
switch (def->kind()) {
@@ -1164,8 +1170,7 @@ Optional<coff_symbol16> Writer::createSymbol(Defined *def) {
StringRef name = def->getName();
if (name.size() > COFF::NameSize) {
sym.Name.Offset.Zeroes = 0;
- sym.Name.Offset.Offset = 0; // Filled in later
- strtab.add(name);
+ sym.Name.Offset.Offset = addEntryToStringTable(name);
} else {
memset(sym.Name.ShortName, 0, COFF::NameSize);
memcpy(sym.Name.ShortName, name.data(), name.size());
@@ -1192,7 +1197,6 @@ void Writer::createSymbolAndStringTable() {
// solution where discardable sections have long names preserved and
// non-discardable sections have their names truncated, to ensure that any
// section which is mapped at runtime also has its name mapped at runtime.
- std::vector<OutputSection *> longNameSections;
for (OutputSection *sec : ctx.outputSections) {
if (sec->name.size() <= COFF::NameSize)
continue;
@@ -1203,12 +1207,9 @@ void Writer::createSymbolAndStringTable() {
" is longer than 8 characters and will use a non-standard string "
"table");
}
-
- strtab.add(sec->name);
- longNameSections.push_back(sec);
+ sec->setStringTableOff(addEntryToStringTable(sec->name));
}
- std::vector<std::pair<size_t, StringRef>> longNameSymbols;
if (config->debugDwarf || config->debugSymtab) {
for (ObjFile *file : ctx.objFileInstances) {
for (Symbol *b : file->getSymbols()) {
@@ -1223,33 +1224,20 @@ void Writer::createSymbolAndStringTable() {
continue;
}
- if (Optional<coff_symbol16> sym = createSymbol(d)) {
+ if (Optional<coff_symbol16> sym = createSymbol(d))
outputSymtab.push_back(*sym);
- if (d->getName().size() > COFF::NameSize)
- longNameSymbols.push_back({outputSymtab.size() - 1, d->getName()});
- }
}
}
}
- strtab.finalize();
-
- for (OutputSection *sec : longNameSections)
- sec->setStringTableOff(strtab.getOffset(sec->name));
-
- for (auto P : longNameSymbols) {
- coff_symbol16 &sym = outputSymtab[P.first];
- sym.Name.Offset.Offset = strtab.getOffset(P.second);
- }
-
- if (outputSymtab.empty() && strtab.getSize() <= 4)
+ if (outputSymtab.empty() && strtab.empty())
return;
// We position the symbol table to be adjacent to the end of the last section.
uint64_t fileOff = fileSize;
pointerToSymbolTable = fileOff;
fileOff += outputSymtab.size() * sizeof(coff_symbol16);
- fileOff += strtab.getSize();
+ fileOff += 4 + strtab.size();
fileSize = alignTo(fileOff, config->fileAlign);
}
@@ -1524,7 +1512,7 @@ template <typename PEHeaderTy> void Writer::writeHeader() {
sectionTable = ArrayRef<uint8_t>(
buf - ctx.outputSections.size() * sizeof(coff_section), buf);
- if (outputSymtab.empty() && strtab.getSize() <= 4)
+ if (outputSymtab.empty() && strtab.empty())
return;
coff->PointerToSymbolTable = pointerToSymbolTable;
@@ -1537,7 +1525,9 @@ template <typename PEHeaderTy> void Writer::writeHeader() {
// Create the string table, it follows immediately after the symbol table.
// The first 4 bytes is length including itself.
buf = reinterpret_cast<uint8_t *>(&symbolTable[numberOfSymbols]);
- strtab.write(buf);
+ write32le(buf, strtab.size() + 4);
+ if (!strtab.empty())
+ memcpy(buf + 4, strtab.data(), strtab.size());
}
void Writer::openFile(StringRef path) {
More information about the llvm-commits
mailing list