llvm-project/llvm/lib/Analysis/ModuleDebugInfoPrinter.cpp
Michael Buch 6cba572d9e
[llvm][DebugInfo][NFC] Abstract DICompileUnit::SourceLanguage to allow alternate DWARF SourceLanguage encoding (#162255)
This patch sets up `DICompileUnit` to support the DWARFv6
`DW_AT_language_name` and `DW_AT_language_version` attributes (which are
set to replace `DW_AT_language`). This patch changes the
`DICompileUnit::SourceLanguage` field type to a `DISourceLanguageName`
that encapsulates the notion of "versioned vs. unversioned name". A
"versioned" name is one that has an associated version stored separately
in `DISourceLanguageName::Version`.

This patch just changes all the clients of the `getSourceLanguage` API
to the expect a `DISourceLanguageName`. Currently they all just `assert`
(via `DISourceLanguageName::getUnversionedName`) that we're dealing with
"unversioned names" (i.e., the pre-DWARFv6 language codes). In follow-up
patches (e.g., draft is at
https://github.com/llvm/llvm-project/pull/162261), when we start
emitting versioned language codes, the `getUnversionedName` calls can
then be adjusted to `getName`.

**Implementation considerations**

* We could have added a new member to `DICompileUnit` alongside the
existing `SourceLanguage` field. I don't think this would have made the
transition any simpler (clients would still need to be aware of
"versioned" vs. "unversioned" language names). I felt that encapsulating
this inside a `DISourceLanguageName` was easier to reason about for
maintainers.
* Currently DISourceLanguageName is a `12` byte structure. We could
probably pack all the info inside a `uint64_t` (16-bits for the name,
32-bits for the version, 1-bit for answering the `hasVersionedName`).
Just to keep the prototype simple I used a `std::optional`. But since
the guts of the structure are hidden, we can always change the layout to
a more compact representation instead.

**How to review**

* The new `DISourceLanguageName` structure is defined in
`DebugInfoMetadata.h`. All the other changes fall out from changing the
`DICompileUnit::SourceLanguage` from `unsigned` to
`DISourceLanguageName`.
2025-10-08 18:27:22 +01:00

111 lines
3.6 KiB
C++

//===-- ModuleDebugInfoPrinter.cpp - Prints module debug info metadata ----===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This pass decodes the debug info metadata in a module and prints in a
// (sufficiently-prepared-) human-readable form.
//
// For example, run this pass from opt along with the -analyze option, and
// it'll print to standard output.
//
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/ModuleDebugInfoPrinter.h"
#include "llvm/BinaryFormat/Dwarf.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/PassManager.h"
#include "llvm/Pass.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
static void printFile(raw_ostream &O, StringRef Filename, StringRef Directory,
unsigned Line = 0) {
if (Filename.empty())
return;
O << " from ";
if (!Directory.empty())
O << Directory << "/";
O << Filename;
if (Line)
O << ":" << Line;
}
static void printModuleDebugInfo(raw_ostream &O, const Module *M,
const DebugInfoFinder &Finder) {
// Printing the nodes directly isn't particularly helpful (since they
// reference other nodes that won't be printed, particularly for the
// filenames), so just print a few useful things.
for (DICompileUnit *CU : Finder.compile_units()) {
O << "Compile unit: ";
auto Lang =
dwarf::LanguageString(CU->getSourceLanguage().getUnversionedName());
if (!Lang.empty())
O << Lang;
else
O << "unknown-language(" << CU->getSourceLanguage().getUnversionedName()
<< ")";
printFile(O, CU->getFilename(), CU->getDirectory());
O << '\n';
}
for (DISubprogram *S : Finder.subprograms()) {
O << "Subprogram: " << S->getName();
printFile(O, S->getFilename(), S->getDirectory(), S->getLine());
if (!S->getLinkageName().empty())
O << " ('" << S->getLinkageName() << "')";
O << '\n';
}
for (auto *GVU : Finder.global_variables()) {
const auto *GV = GVU->getVariable();
O << "Global variable: " << GV->getName();
printFile(O, GV->getFilename(), GV->getDirectory(), GV->getLine());
if (!GV->getLinkageName().empty())
O << " ('" << GV->getLinkageName() << "')";
O << '\n';
}
for (const DIType *T : Finder.types()) {
O << "Type:";
if (!T->getName().empty())
O << ' ' << T->getName();
printFile(O, T->getFilename(), T->getDirectory(), T->getLine());
if (auto *BT = dyn_cast<DIBasicType>(T)) {
O << " ";
auto Encoding = dwarf::AttributeEncodingString(BT->getEncoding());
if (!Encoding.empty())
O << Encoding;
else
O << "unknown-encoding(" << BT->getEncoding() << ')';
} else {
O << ' ';
auto Tag = dwarf::TagString(T->getTag());
if (!Tag.empty())
O << Tag;
else
O << "unknown-tag(" << T->getTag() << ")";
}
if (auto *CT = dyn_cast<DICompositeType>(T)) {
if (auto *S = CT->getRawIdentifier())
O << " (identifier: '" << S->getString() << "')";
}
O << '\n';
}
}
ModuleDebugInfoPrinterPass::ModuleDebugInfoPrinterPass(raw_ostream &OS)
: OS(OS) {}
PreservedAnalyses ModuleDebugInfoPrinterPass::run(Module &M,
ModuleAnalysisManager &AM) {
Finder.processModule(M);
printModuleDebugInfo(OS, &M, Finder);
return PreservedAnalyses::all();
}