[clang] use string tables for static diagnostic descriptions

Using a pointer for the description string in StaticDiagInfoRec causes
several problems:

1. We don't need to use a whole pointer to represent the string;
2. The use of pointers incurs runtime relocations for those pointers;
   the relocations take up space on disk and represent runtime overhead;
3. The need to relocate data implies that, on some platforms, the entire
   array containing StaticDiagInfoRecs cannot be shared between processes.

This patch changes the storage scheme for the diagnostic descriptions to
avoid these problems.  We instead generate (effectively) one large
string and then StaticDiagInfoRec conceptually holds offsets into the
string.  We elected to also move the storage of those offsets into a
separate array to further reduce the space required.

On x86-64 Linux, this change removes about 120KB of relocations and
moves about 60KB from the non-shareable .data.rel.ro section to
shareable .rodata.  (The array is about 80KB before this, but we
eliminated 4 bytes/entry by using offsets rather than pointers.)  We
actually reap this benefit twice, because these tables show up in both
libclang.so and libclang-cpp.so and we get the reduction in both places.

Differential Revision: https://reviews.llvm.org/D81865

Author: froydnj

clang/lib/Basic/DiagnosticIDs.cpp

@@ -26,6 +26,78 @@ using namespace clang;
 
 namespace {
 
+struct StaticDiagInfoRec;
+
+// Store the descriptions in a separate table to avoid pointers that need to
+// be relocated, and also decrease the amount of data needed on 64-bit
+// platforms. See "How To Write Shared Libraries" by Ulrich Drepper.
+struct StaticDiagInfoDescriptionStringTable {
+#define DIAG(ENUM, CLASS, DEFAULT_SEVERITY, DESC, GROUP, SFINAE, NOWERROR,     \
+             SHOWINSYSHEADER, DEFERRABLE, CATEGORY)                            \
+  char ENUM##_desc[sizeof(DESC)];
+  // clang-format off
+#include "clang/Basic/DiagnosticCommonKinds.inc"
+#include "clang/Basic/DiagnosticDriverKinds.inc"
+#include "clang/Basic/DiagnosticFrontendKinds.inc"
+#include "clang/Basic/DiagnosticSerializationKinds.inc"
+#include "clang/Basic/DiagnosticLexKinds.inc"
+#include "clang/Basic/DiagnosticParseKinds.inc"
+#include "clang/Basic/DiagnosticASTKinds.inc"
+#include "clang/Basic/DiagnosticCommentKinds.inc"
+#include "clang/Basic/DiagnosticCrossTUKinds.inc"
+#include "clang/Basic/DiagnosticSemaKinds.inc"
+#include "clang/Basic/DiagnosticAnalysisKinds.inc"
+#include "clang/Basic/DiagnosticRefactoringKinds.inc"
+  // clang-format on
+#undef DIAG
+};
+
+const StaticDiagInfoDescriptionStringTable StaticDiagInfoDescriptions = {
+#define DIAG(ENUM, CLASS, DEFAULT_SEVERITY, DESC, GROUP, SFINAE, NOWERROR,     \
+             SHOWINSYSHEADER, DEFERRABLE, CATEGORY)                            \
+  DESC,
+  // clang-format off
+#include "clang/Basic/DiagnosticCommonKinds.inc"
+#include "clang/Basic/DiagnosticDriverKinds.inc"
+#include "clang/Basic/DiagnosticFrontendKinds.inc"
+#include "clang/Basic/DiagnosticSerializationKinds.inc"
+#include "clang/Basic/DiagnosticLexKinds.inc"
+#include "clang/Basic/DiagnosticParseKinds.inc"
+#include "clang/Basic/DiagnosticASTKinds.inc"
+#include "clang/Basic/DiagnosticCommentKinds.inc"
+#include "clang/Basic/DiagnosticCrossTUKinds.inc"
+#include "clang/Basic/DiagnosticSemaKinds.inc"
+#include "clang/Basic/DiagnosticAnalysisKinds.inc"
+#include "clang/Basic/DiagnosticRefactoringKinds.inc"
+  // clang-format on
+#undef DIAG
+};
+
+extern const StaticDiagInfoRec StaticDiagInfo[];
+
+// Stored separately from StaticDiagInfoRec to pack better.  Otherwise,
+// StaticDiagInfoRec would have extra padding on 64-bit platforms.
+const uint32_t StaticDiagInfoDescriptionOffsets[] = {
+#define DIAG(ENUM, CLASS, DEFAULT_SEVERITY, DESC, GROUP, SFINAE, NOWERROR,     \
+             SHOWINSYSHEADER, DEFERRABLE, CATEGORY)                            \
+  offsetof(StaticDiagInfoDescriptionStringTable, ENUM##_desc),
+  // clang-format off
+#include "clang/Basic/DiagnosticCommonKinds.inc"
+#include "clang/Basic/DiagnosticDriverKinds.inc"
+#include "clang/Basic/DiagnosticFrontendKinds.inc"
+#include "clang/Basic/DiagnosticSerializationKinds.inc"
+#include "clang/Basic/DiagnosticLexKinds.inc"
+#include "clang/Basic/DiagnosticParseKinds.inc"
+#include "clang/Basic/DiagnosticASTKinds.inc"
+#include "clang/Basic/DiagnosticCommentKinds.inc"
+#include "clang/Basic/DiagnosticCrossTUKinds.inc"
+#include "clang/Basic/DiagnosticSemaKinds.inc"
+#include "clang/Basic/DiagnosticAnalysisKinds.inc"
+#include "clang/Basic/DiagnosticRefactoringKinds.inc"
+  // clang-format on
+#undef DIAG
+};
+
 // Diagnostic classes.
 enum {
   CLASS_NOTE       = 0x01,
@@ -48,14 +120,16 @@ struct StaticDiagInfoRec {
   uint16_t OptionGroupIndex;
 
   uint16_t DescriptionLen;
-  const char *DescriptionStr;
 
   unsigned getOptionGroupIndex() const {
     return OptionGroupIndex;
   }
 
   StringRef getDescription() const {
-    return StringRef(DescriptionStr, DescriptionLen);
+    size_t MyIndex = this - &StaticDiagInfo[0];
+    uint32_t StringOffset = StaticDiagInfoDescriptionOffsets[MyIndex];
+    const char* Table = reinterpret_cast<const char*>(&StaticDiagInfoDescriptions);
+    return StringRef(&Table[StringOffset], DescriptionLen);
   }
 
   diag::Flavor getFlavor() const {
@@ -93,14 +167,21 @@ VALIDATE_DIAG_SIZE(REFACTORING)
 #undef VALIDATE_DIAG_SIZE
 #undef STRINGIFY_NAME
 
-} // namespace anonymous
-
-static const StaticDiagInfoRec StaticDiagInfo[] = {
+const StaticDiagInfoRec StaticDiagInfo[] = {
 #define DIAG(ENUM, CLASS, DEFAULT_SEVERITY, DESC, GROUP, SFINAE, NOWERROR,     \
              SHOWINSYSHEADER, DEFERRABLE, CATEGORY)                            \
-  {diag::ENUM, DEFAULT_SEVERITY,         CLASS,      DiagnosticIDs::SFINAE,    \
-   NOWERROR,   SHOWINSYSHEADER,          DEFERRABLE, CATEGORY,                 \
-   GROUP,      STR_SIZE(DESC, uint16_t), DESC},
+  {                                                                            \
+      diag::ENUM,                                                              \
+      DEFAULT_SEVERITY,                                                        \
+      CLASS,                                                                   \
+      DiagnosticIDs::SFINAE,                                                   \
+      NOWERROR,                                                                \
+      SHOWINSYSHEADER,                                                         \
+      DEFERRABLE,                                                              \
+      CATEGORY,                                                                \
+      GROUP,                                                                   \
+      STR_SIZE(DESC, uint16_t)},
+  // clang-format off
 #include "clang/Basic/DiagnosticCommonKinds.inc"
 #include "clang/Basic/DiagnosticDriverKinds.inc"
 #include "clang/Basic/DiagnosticFrontendKinds.inc"
@@ -113,9 +194,12 @@ static const StaticDiagInfoRec StaticDiagInfo[] = {
 #include "clang/Basic/DiagnosticSemaKinds.inc"
 #include "clang/Basic/DiagnosticAnalysisKinds.inc"
 #include "clang/Basic/DiagnosticRefactoringKinds.inc"
+  // clang-format on
 #undef DIAG
 };
 
+} // namespace
+
 static const unsigned StaticDiagInfoSize = llvm::array_lengthof(StaticDiagInfo);
 
 /// GetDiagInfo - Return the StaticDiagInfoRec entry for the specified DiagID,