Author: Qiongsi Wu
Date: 2025-02-26T13:21:14-08:00
New Revision: 7f482aa848c5f136d2b32431f91f88492c78c709

URL: 
https://github.com/llvm/llvm-project/commit/7f482aa848c5f136d2b32431f91f88492c78c709
DIFF: 
https://github.com/llvm/llvm-project/commit/7f482aa848c5f136d2b32431f91f88492c78c709.diff

LOG: [clang modules] Setting `DebugCompilationDir` when it is safe to ignore 
current working directory (#128446)

This PR explicitly sets `DebugCompilationDir` to the system's root
directory if it is safe to ignore the current working directory.

This fixes a problem where a PCM file's embedded debug information can
lead to compilation failure. The compiler may have decided it is indeed
safe to ignore the current working directory. In this case, the PCM
file's content is functionally correct regardless of the current working
directory because no inputs use relative paths (see
https://github.com/llvm/llvm-project/pull/124786). However, a PCM may
contain debug info. If debug info is requested, the compiler uses the
current working directory value to set `DW_AT_comp_dir`. This may lead
to the following situation:
1. Two different compilations need the same PCM file. 
2. The PCM file is compiled assuming a working directory, which is
embedded in the debug info, but otherwise has no effect.
3. The second compilation assumes a different working directory, and
expects an identically-sized pcm file. However, it cannot find such a
PCM, because the existing PCM file has been compiled assuming a
different `DW_AT_comp_dir `, which is embedded in the debug info.

This PR resets the `DebugCompilationDir` if it is functionally safe to
ignore the working directory so the above situation is avoided, since
all debug information will share the same working directory.

rdar://145249881

Added: 
    clang/test/ClangScanDeps/modules-debug-dir.c

Modified: 
    clang/include/clang/Tooling/DependencyScanning/ModuleDepCollector.h
    clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp

Removed: 
    


################################################################################
diff  --git 
a/clang/include/clang/Tooling/DependencyScanning/ModuleDepCollector.h 
b/clang/include/clang/Tooling/DependencyScanning/ModuleDepCollector.h
index c2071a6eadedd..b41efa254342e 100644
--- a/clang/include/clang/Tooling/DependencyScanning/ModuleDepCollector.h
+++ b/clang/include/clang/Tooling/DependencyScanning/ModuleDepCollector.h
@@ -317,7 +317,7 @@ class ModuleDepCollector final : public DependencyCollector 
{
 
   /// Compute the context hash for \p Deps, and create the mapping
   /// \c ModuleDepsByID[Deps.ID] = &Deps.
-  void associateWithContextHash(const CowCompilerInvocation &CI,
+  void associateWithContextHash(const CowCompilerInvocation &CI, bool 
IgnoreCWD,
                                 ModuleDeps &Deps);
 };
 

diff  --git a/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp 
b/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
index 1c5f4c4b50ab6..7da3ec71f2da4 100644
--- a/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
+++ b/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
@@ -129,6 +129,34 @@ static void optimizeDiagnosticOpts(DiagnosticOptions &Opts,
   Opts.Remarks.clear();
 }
 
+static void optimizeCWD(CowCompilerInvocation &BuildInvocation, StringRef CWD) 
{
+  BuildInvocation.getMutFileSystemOpts().WorkingDir.clear();
+  if (BuildInvocation.getCodeGenOpts().DwarfVersion) {
+    // It is necessary to explicitly set the DebugCompilationDir
+    // to a common directory (e.g. root) if IgnoreCWD is true.
+    // When IgnoreCWD is true, the module's content should not
+    // depend on the current working directory. However, if dwarf
+    // information is needed (when CGOpts.DwarfVersion is
+    // non-zero), then CGOpts.DebugCompilationDir must be
+    // populated, because otherwise the current working directory
+    // will be automatically embedded in the dwarf information in
+    // the pcm, contradicting the assumption that it is safe to
+    // ignore the CWD. Thus in such cases,
+    // CGOpts.DebugCompilationDir is explicitly set to a common
+    // directory.
+    // FIXME: It is still excessive to create a copy of
+    // CodeGenOpts for each module. Since we do not modify the
+    // CodeGenOpts otherwise per module, the following code
+    // ends up generating identical CodeGenOpts for each module
+    // with DebugCompilationDir pointing to the root directory.
+    // We can optimize this away by creating a _single_ copy of
+    // CodeGenOpts whose DebugCompilationDir points to the root
+    // directory and reuse it across modules.
+    BuildInvocation.getMutCodeGenOpts().DebugCompilationDir =
+        llvm::sys::path::root_path(CWD);
+  }
+}
+
 static std::vector<std::string> splitString(std::string S, char Separator) {
   SmallVector<StringRef> Segments;
   StringRef(S).split(Segments, Separator, /*MaxSplit=*/-1, 
/*KeepEmpty=*/false);
@@ -489,11 +517,8 @@ static std::string getModuleContextHash(const ModuleDeps 
&MD,
   HashBuilder.add(getClangFullRepositoryVersion());
   HashBuilder.add(serialization::VERSION_MAJOR, serialization::VERSION_MINOR);
   llvm::ErrorOr<std::string> CWD = VFS.getCurrentWorkingDirectory();
-  auto &FSOpts = const_cast<FileSystemOptions &>(CI.getFileSystemOpts());
   if (CWD && !IgnoreCWD)
     HashBuilder.add(*CWD);
-  else
-    FSOpts.WorkingDir.clear();
 
   // Hash the BuildInvocation without any input files.
   SmallString<0> ArgVec;
@@ -524,9 +549,7 @@ static std::string getModuleContextHash(const ModuleDeps 
&MD,
 }
 
 void ModuleDepCollector::associateWithContextHash(
-    const CowCompilerInvocation &CI, ModuleDeps &Deps) {
-  bool IgnoreCWD = any(OptimizeArgs & ScanningOptimizations::IgnoreCWD) &&
-                   isSafeToIgnoreCWD(CI);
+    const CowCompilerInvocation &CI, bool IgnoreCWD, ModuleDeps &Deps) {
   Deps.ID.ContextHash =
       getModuleContextHash(Deps, CI, EagerLoadModules, IgnoreCWD,
                            ScanInstance.getVirtualFileSystem());
@@ -726,6 +749,7 @@ ModuleDepCollectorPP::handleTopLevelModule(const Module *M) 
{
         MD.ModuleMapFileDeps.emplace_back(*ResolvedFilenameAsRequested);
       });
 
+  bool IgnoreCWD = false;
   CowCompilerInvocation CI =
       MDC.getInvocationAdjustedForModuleBuildWithoutOutputs(
           MD, [&](CowCompilerInvocation &BuildInvocation) {
@@ -735,13 +759,25 @@ ModuleDepCollectorPP::handleTopLevelModule(const Module 
*M) {
                                        *MDC.ScanInstance.getASTReader(), *MF,
                                        MDC.PrebuiltModuleVFSMap,
                                        MDC.OptimizeArgs);
+
             if (any(MDC.OptimizeArgs & ScanningOptimizations::SystemWarnings))
               optimizeDiagnosticOpts(
                   BuildInvocation.getMutDiagnosticOpts(),
                   BuildInvocation.getFrontendOpts().IsSystemModule);
+
+            IgnoreCWD =
+                any(MDC.OptimizeArgs & ScanningOptimizations::IgnoreCWD) &&
+                isSafeToIgnoreCWD(BuildInvocation);
+            if (IgnoreCWD) {
+              llvm::ErrorOr<std::string> CWD =
+                  MDC.ScanInstance.getVirtualFileSystem()
+                      .getCurrentWorkingDirectory();
+              if (CWD)
+                optimizeCWD(BuildInvocation, *CWD);
+            }
           });
 
-  MDC.associateWithContextHash(CI, MD);
+  MDC.associateWithContextHash(CI, IgnoreCWD, MD);
 
   // Finish the compiler invocation. Requires dependencies and the context 
hash.
   MDC.addOutputPaths(CI, MD);

diff  --git a/clang/test/ClangScanDeps/modules-debug-dir.c 
b/clang/test/ClangScanDeps/modules-debug-dir.c
new file mode 100644
index 0000000000000..fadec1ad52e35
--- /dev/null
+++ b/clang/test/ClangScanDeps/modules-debug-dir.c
@@ -0,0 +1,32 @@
+// REQUIRES: shell
+
+// RUN: rm -rf %t
+// RUN: split-file %s %t
+// RUN: sed -e "s|DIR|%/t|g" %t/cdb.json.in > %t/cdb.json
+// RUN: clang-scan-deps -compilation-database %t/cdb.json -format \
+// RUN:   experimental-full > %t/result.json
+// RUN: cat %t/result.json | sed 's:\\\\\?:/:g' | FileCheck %s
+
+//--- cdb.json.in
+[{
+  "directory": "DIR",
+  "command": "clang -c -g -gmodules DIR/tu.c -fmodules 
-fmodules-cache-path=DIR/cache -IDIR/include/ -fdebug-compilation-dir=DIR -o 
DIR/tu.o",
+  "file": "DIR/tu.c"
+}]
+
+//--- include/module.modulemap
+module mod {
+  header "mod.h"
+}
+
+//--- include/mod.h
+
+//--- tu.c
+#include "mod.h"
+
+// Check the -fdebug-compilation-dir used for the module is the root
+// directory when current working directory optimization is in effect.
+// CHECK:  "modules": [
+// CHECK: "command-line": [
+// CHECK: "-fdebug-compilation-dir={{\/|.*:(\\)?}}",
+// CHECK:  "translation-units": [


        
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to