[lldb] Fix the DWARF index cache when index is partial. (llvm#118390)

The ManualDWARFIndex class can create a index cache if the LLDB index
cache is enabled. This used to save the index to the same file,
regardless of wether the cache was a full index (no .debug_names) or a
partial index (have .debug_names, but not all .o files were had
.debug_names). So we could end up saving an index cache that was
partial, and then later load that partial index as if it were a full
index if the user set the 'settings set
plugin.symbol-file.dwarf.ignore-file-indexes true'. This would cause us
to ignore the .debug_names section, and if the index cache was enabled,
we could end up loading the partial index as if it were a full DWARF
index.

This patch detects when the ManualDWARFIndex is being used with
.debug_names, and saves out a cache file with a suffix of "-full" or
"-partial" to avoid this issue.

Author: clayborg

lldb/source/Plugins/SymbolFile/DWARF/ManualDWARFIndex.cpp

@@ -706,16 +706,38 @@ bool ManualDWARFIndex::Encode(DataEncoder &encoder) const {
   return true;
 }
 
+bool ManualDWARFIndex::IsPartial() const {
+  // If we have units or type units to skip, then this index is partial.
+  return !m_units_to_avoid.empty() || !m_type_sigs_to_avoid.empty();
+}
+
 std::string ManualDWARFIndex::GetCacheKey() {
   std::string key;
   llvm::raw_string_ostream strm(key);
   // DWARF Index can come from different object files for the same module. A
   // module can have one object file as the main executable and might have
   // another object file in a separate symbol file, or we might have a .dwo file
   // that claims its module is the main executable.
+
+  // This class can be used to index all of the DWARF, or part of the DWARF
+  // when there is a .debug_names index where some compile or type units were
+  // built without .debug_names. So we need to know when we have a full manual
+  // DWARF index or a partial manual DWARF index and save them to different
+  // cache files. Before this fix we might end up debugging a binary with
+  // .debug_names where some of the compile or type units weren't indexed, and
+  // find an issue with the .debug_names tables (bugs or being incomplete), and
+  // then we disable loading the .debug_names by setting a setting in LLDB by
+  // running "settings set plugin.symbol-file.dwarf.ignore-file-indexes 0" in
+  // another LLDB instance. The problem arose when there was an index cache from
+  // a previous run where .debug_names was enabled and it had saved a cache file
+  // that only covered the missing compile and type units from the .debug_names,
+  // and with the setting that disables the loading of the cache files we would
+  // load partial cache index cache. So we need to pick a unique cache suffix
+  // name that indicates if the cache is partial or full to avoid this problem.
+  llvm::StringRef dwarf_index_suffix(IsPartial() ? "partial-" : "full-");
   ObjectFile *objfile = m_dwarf->GetObjectFile();
   strm << objfile->GetModule()->GetCacheKey() << "-dwarf-index-"
-      << llvm::format_hex(objfile->GetCacheHash(), 10);
+       << dwarf_index_suffix << llvm::format_hex(objfile->GetCacheHash(), 10);
   return key;
 }
 

lldb/source/Plugins/SymbolFile/DWARF/ManualDWARFIndex.h

@@ -168,6 +168,16 @@ class ManualDWARFIndex : public DWARFIndex {
                             const lldb::LanguageType cu_language,
                             IndexSet &set);
 
+  /// Return true if this manual DWARF index is covering only part of the DWARF.
+  ///
+  /// An instance of this class will be used to index all of the DWARF, but also
+  /// when we have .debug_names we will use one to index any compile or type
+  /// units that are not covered by the .debug_names table.
+  ///
+  /// \return
+  ///   True if this index is a partial index, false otherwise.
+  bool IsPartial() const;
+
   /// The DWARF file which we are indexing.
   SymbolFileDWARF *m_dwarf;
   /// Which dwarf units should we skip while building the index.

lldb/test/Shell/SymbolFile/DWARF/x86/dwp-index-cache.cpp

@@ -0,0 +1,62 @@
+// REQUIRES: lld
+
+// Test if we build a mixed binary where one .o file has a .debug_names and
+// another doesn't have one, that we save a full or partial index cache.
+// Previous versions of LLDB would have ManualDWARFIndex.cpp that would save out
+// an index cache to the same file regardless of wether the index cache was a
+// full DWARF manual index, or just the CUs and TUs that were missing from any
+// .debug_names tables. If the user had a .debug_names table and debugged once
+// with index caching enabled, then debugged again but set the setting to ignore
+// .debug_names ('settings set plugin.symbol-file.dwarf.ignore-file-indexes 1')
+// this could cause LLDB to load the index cache from the previous run which
+// was incomplete and it only contained the manually indexed DWARF from the run
+// where we used .debug_names, but it would now load it as if it were the
+// complete DWARF index.
+
+// Test that if we don't have .debug_names, that we save a full DWARF index.
+// RUN: %clang -target x86_64-pc-linux -gsplit-dwarf -gdwarf-5 -DMAIN=1 -c %s -o %t.main.o
+// RUN: %clang -target x86_64-pc-linux -gsplit-dwarf -gdwarf-5 -DMAIN=0 -c %s -o %t.foo.o
+// RUN: ld.lld %t.main.o %t.foo.o -o %t.nonames
+// RUN: llvm-dwp %t.main.dwo %t.foo.dwo -o %t.nonames.dwp
+// RUN: rm %t.main.dwo %t.foo.dwo
+// Run one time with the index cache enabled to populate the index cache. When
+// we populate the index cache we have to parse all of the DWARF debug info
+// and it is always available.
+// RUN: rm -rf %t.lldb-index-cache
+// RUN: %lldb \
+// RUN:   -O 'settings set symbols.enable-lldb-index-cache true' \
+// RUN:   -O 'settings set symbols.lldb-index-cache-path %t.lldb-index-cache' \
+// RUN:   -O 'settings set target.preload-symbols true' \
+// RUN:   %t.nonames -b
+
+// Make sure there is a file with "dwarf-index-full" in its filename
+// RUN: ls %t.lldb-index-cache | FileCheck %s -check-prefix=FULL
+// FULL: {{dwp-index-cache.cpp.tmp.nonames.*-dwarf-index-full-}}
+
+// Test that if we have one .o file with .debug_names and one without, that we
+// save a partial DWARF index.
+// RUN: %clang -target x86_64-pc-linux -gsplit-dwarf -gdwarf-5 -DMAIN=1 -c %s -o %t.main.o -gpubnames
+// RUN: %clang -target x86_64-pc-linux -gsplit-dwarf -gdwarf-5 -DMAIN=0 -c %s -o %t.foo.o
+// RUN: ld.lld %t.main.o %t.foo.o -o %t.somenames
+// RUN: llvm-dwp %t.main.dwo %t.foo.dwo -o %t.somenames.dwp
+// RUN: rm %t.main.dwo %t.foo.dwo
+// Run one time with the index cache enabled to populate the index cache. When
+// we populate the index cache we have to parse all of the DWARF debug info
+// and it is always available.
+// RUN: rm -rf %t.lldb-index-cache
+// RUN: %lldb \
+// RUN:   -O 'settings set symbols.enable-lldb-index-cache true' \
+// RUN:   -O 'settings set symbols.lldb-index-cache-path %t.lldb-index-cache' \
+// RUN:   -O 'settings set target.preload-symbols true' \
+// RUN:   %t.somenames -b
+
+// Make sure there is a file with "dwarf-index-full" in its filename
+// RUN: ls %t.lldb-index-cache | FileCheck %s -check-prefix=PARTIAL
+// PARTIAL: {{dwp-index-cache.cpp.tmp.somenames.*-dwarf-index-partial-}}
+
+#if MAIN
+extern int foo();
+int main() { return foo(); }
+#else
+int foo() { return 0; }
+#endif