[UBSan][BoundsSafety] Cherry-pick Implement support for more expressive trap reasons and dependent patches

clang/docs/ReleaseNotes.rst

@@ -366,9 +366,33 @@ Non-comprehensive list of changes in this release
   correct method to check for these features is to test for the ``__PTRAUTH__``
   macro.
 
+- Trapping UBSan (e.g. ``-fsanitize=undefined -fsanitize-trap=undefined``) now
+  emits a string describing the reason for trapping into the generated debug
+  info. This feature allows debuggers (e.g. LLDB) to display the reason for
+  trapping if the trap is reached. The string is currently encoded in the debug
+  info as an artificial frame that claims to be inlined at the trap location.
+  The function used for the artificial frame is an artificial function whose
+  name encodes the reason for trapping. The encoding used is currently the same
+  as ``__builtin_verbose_trap`` but might change in the future. This feature is
+  enabled by default but can be disabled by compiling with
+  ``-fno-sanitize-debug-trap-reasons``. The feature has a ``basic`` and
+  ``detailed`` mode (the default). The ``basic`` mode emits a hard-coded string
+  per trap kind (e.g. ``Integer addition overflowed``) and the ``detailed`` mode
+  emits a more descriptive string describing each individual trap (e.g. ``signed
+  integer addition overflow in 'a + b'``). The ``detailed`` mode produces larger
+  debug info than ``basic`` but is more helpful for debugging. The
+  ``-fsanitize-debug-trap-reasons=`` flag can be used to switch between the
+  different modes or disable the feature entirely. Note due to trap merging in
+  optimized builds (i.e. in each function all traps of the same kind get merged
+  into the same trap instruction) the trap reasons might be removed. To prevent
+  this build without optimizations (i.e. use `-O0` or use the `optnone` function
+  attribute) or use the `fno-sanitize-merge=` flag in optimized builds.
 
 New Compiler Flags
 ------------------
+- New option ``-fno-sanitize-debug-trap-reasons`` added to disable emitting trap reasons into the debug info when compiling with trapping UBSan (e.g. ``-fsanitize-trap=undefined``).
+- New option ``-fsanitize-debug-trap-reasons=`` added to control emitting trap reasons into the debug info when compiling with trapping UBSan (e.g. ``-fsanitize-trap=undefined``).
+
 
 - New option ``-Wundef-true`` added and enabled by default to warn when `true` is used in the C preprocessor without being defined before C23.
 

clang/include/clang/Basic/AllDiagnosticKinds.inc

@@ -30,5 +30,7 @@
 #include "clang/Basic/DiagnosticAnalysisKinds.inc"
 #include "clang/Basic/DiagnosticRefactoringKinds.inc"
 #include "clang/Basic/DiagnosticInstallAPIKinds.inc"
+#include "clang/Basic/DiagnosticTrapKinds.inc"
 #include "clang/Basic/DiagnosticCASKinds.inc"
+
 // clang-format on

clang/include/clang/Basic/AllDiagnostics.h

@@ -24,20 +24,21 @@
 #include "clang/Basic/DiagnosticInstallAPI.h"
 #include "clang/Basic/DiagnosticLex.h"
 #include "clang/Basic/DiagnosticParse.h"
+#include "clang/Basic/DiagnosticRefactoring.h"
 #include "clang/Basic/DiagnosticSema.h"
 #include "clang/Basic/DiagnosticSerialization.h"
-#include "clang/Basic/DiagnosticRefactoring.h"
+#include "clang/Basic/DiagnosticTrap.h"
 
 namespace clang {
-template <size_t SizeOfStr, typename FieldType>
-class StringSizerHelper {
+template <size_t SizeOfStr, typename FieldType> class StringSizerHelper {
   static_assert(SizeOfStr <= FieldType(~0U), "Field too small!");
+
 public:
   enum { Size = SizeOfStr };
 };
 } // end namespace clang
 
-#define STR_SIZE(str, fieldTy) clang::StringSizerHelper<sizeof(str)-1, \
-                                                        fieldTy>::Size
+#define STR_SIZE(str, fieldTy)                                                 \
+  clang::StringSizerHelper<sizeof(str) - 1, fieldTy>::Size
 
 #endif

clang/include/clang/Basic/CMakeLists.txt

@@ -34,6 +34,7 @@ clang_diag_gen(Parse)
 clang_diag_gen(Refactoring)
 clang_diag_gen(Sema)
 clang_diag_gen(Serialization)
+clang_diag_gen(Trap)
 clang_tablegen(DiagnosticGroups.inc -gen-clang-diag-groups
   SOURCE Diagnostic.td
   TARGET ClangDiagnosticGroups)

clang/include/clang/Basic/CodeGenOptions.def

@@ -306,6 +306,7 @@ CODEGENOPT(SanitizeBinaryMetadataAtomics, 1, 0, Benign) ///< Emit PCs for atomic
 CODEGENOPT(SanitizeBinaryMetadataUAR, 1, 0, Benign) ///< Emit PCs for start of functions
                                                     ///< that are subject for use-after-return checking.
 CODEGENOPT(SanitizeStats     , 1, 0, Benign) ///< Collect statistics for sanitizers.
+ENUM_CODEGENOPT(SanitizeDebugTrapReasons, SanitizeDebugTrapReasonKind, 2, SanitizeDebugTrapReasonKind::Detailed, Benign) ///< Control how "trap reasons" are emitted in debug info
 CODEGENOPT(SimplifyLibCalls  , 1, 1, Benign) ///< Set when -fbuiltin is enabled.
 CODEGENOPT(SoftFloat         , 1, 0, Benign) ///< -soft-float.
 CODEGENOPT(SpeculativeLoadHardening, 1, 0, Benign) ///< Enable speculative load hardening.

clang/include/clang/Basic/CodeGenOptions.h

@@ -178,6 +178,16 @@ class CodeGenOptions : public CodeGenOptionsBase {
   /// The callback for mc result.
   std::optional<llvm::MCTargetOptions::ResultCallBackTy> MCCallBack;
 
+  enum SanitizeDebugTrapReasonKind {
+    None,  ///< Trap Messages are omitted. This offers the smallest debug info
+           ///< size but at the cost of making traps hard to debug.
+    Basic, ///< Trap Message is fixed per SanitizerKind. Produces smaller debug
+           ///< info than `Detailed` but is not as helpful for debugging.
+    Detailed, ///< Trap Message includes more context (e.g. the expression being
+              ///< overflowed). This is more helpful for debugging but produces
+              ///< larger debug info than `Basic`.
+  };
+
   /// The code model to use (-mcmodel).
   std::string CodeModel;
 

clang/include/clang/Basic/Diagnostic.h

@@ -23,6 +23,7 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/FunctionExtras.h"
 #include "llvm/ADT/IntrusiveRefCntPtr.h"
+#include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Support/Compiler.h"
@@ -1269,10 +1270,13 @@ class DiagnosticBuilder : public StreamingDiagnostic {
 
   DiagnosticBuilder() = default;
 
+protected:
   DiagnosticBuilder(DiagnosticsEngine *DiagObj, SourceLocation DiagLoc,
                     unsigned DiagID);
 
-protected:
+  DiagnosticsEngine *getDiagnosticsEngine() const { return DiagObj; }
+  unsigned getDiagID() const { return DiagID; }
+
   /// Clear out the current diagnostic.
   void Clear() const {
     DiagObj = nullptr;

clang/include/clang/Basic/Diagnostic.td

@@ -30,6 +30,7 @@ def CLASS_REMARK    : DiagClass;
 def CLASS_WARNING   : DiagClass;
 def CLASS_EXTENSION : DiagClass;
 def CLASS_ERROR     : DiagClass;
+def CLASS_TRAP      : DiagClass;
 
 // Responses to a diagnostic in a SFINAE context.
 class SFINAEResponse;
@@ -144,7 +145,8 @@ class Extension<string str> : Diagnostic<str, CLASS_EXTENSION, SEV_Ignored>;
 class ExtWarn<string str>   : Diagnostic<str, CLASS_EXTENSION, SEV_Warning>;
 // Notes can provide supplementary information on errors, warnings, and remarks.
 class Note<string str>      : Diagnostic<str, CLASS_NOTE, SEV_Fatal/*ignored*/>;
-
+// Trap messages attached to traps in debug info.
+class Trap<string str>      : Diagnostic<str, CLASS_TRAP, SEV_Fatal/*ignored*/>;
 
 class DefaultIgnore { Severity DefaultSeverity = SEV_Ignored; }
 class DefaultWarn   { Severity DefaultSeverity = SEV_Warning; }
@@ -236,3 +238,4 @@ include "DiagnosticParseKinds.td"
 include "DiagnosticRefactoringKinds.td"
 include "DiagnosticSemaKinds.td"
 include "DiagnosticSerializationKinds.td"
+include "DiagnosticTrapKinds.td"

clang/include/clang/Basic/DiagnosticIDs.h

@@ -23,78 +23,82 @@
 #include <vector>
 
 namespace clang {
-  class DiagnosticsEngine;
-  class DiagnosticBuilder;
-  class LangOptions;
-  class SourceLocation;
-
-  // Import the diagnostic enums themselves.
-  namespace diag {
-    enum class Group;
-
-    // Size of each of the diagnostic categories.
-    enum {
-      DIAG_SIZE_COMMON        =  300,
-      DIAG_SIZE_DRIVER        =  400,
-      DIAG_SIZE_FRONTEND      =  200,
-      DIAG_SIZE_SERIALIZATION =  120,
-      DIAG_SIZE_LEX           =  500,
-      DIAG_SIZE_PARSE         =  800,
-      DIAG_SIZE_AST           =  300,
-      DIAG_SIZE_COMMENT       =  100,
-      DIAG_SIZE_CROSSTU       =  100,
-      DIAG_SIZE_SEMA          = 5000,
-      DIAG_SIZE_ANALYSIS      =  100,
-      DIAG_SIZE_REFACTORING   = 1000,
-      DIAG_SIZE_INSTALLAPI    =  100,
-      DIAG_SIZE_CAS           =  100,
-    };
-    // Start position for diagnostics.
-    enum {
-      DIAG_START_COMMON        =                          0,
-      DIAG_START_DRIVER        = DIAG_START_COMMON        + static_cast<int>(DIAG_SIZE_COMMON),
-      DIAG_START_FRONTEND      = DIAG_START_DRIVER        + static_cast<int>(DIAG_SIZE_DRIVER),
-      DIAG_START_SERIALIZATION = DIAG_START_FRONTEND      + static_cast<int>(DIAG_SIZE_FRONTEND),
-      DIAG_START_LEX           = DIAG_START_SERIALIZATION + static_cast<int>(DIAG_SIZE_SERIALIZATION),
-      DIAG_START_PARSE         = DIAG_START_LEX           + static_cast<int>(DIAG_SIZE_LEX),
-      DIAG_START_AST           = DIAG_START_PARSE         + static_cast<int>(DIAG_SIZE_PARSE),
-      DIAG_START_COMMENT       = DIAG_START_AST           + static_cast<int>(DIAG_SIZE_AST),
-      DIAG_START_CROSSTU       = DIAG_START_COMMENT       + static_cast<int>(DIAG_SIZE_COMMENT),
-      DIAG_START_SEMA          = DIAG_START_CROSSTU       + static_cast<int>(DIAG_SIZE_CROSSTU),
-      DIAG_START_ANALYSIS      = DIAG_START_SEMA          + static_cast<int>(DIAG_SIZE_SEMA),
-      DIAG_START_REFACTORING   = DIAG_START_ANALYSIS      + static_cast<int>(DIAG_SIZE_ANALYSIS),
-      DIAG_START_INSTALLAPI    = DIAG_START_REFACTORING   + static_cast<int>(DIAG_SIZE_REFACTORING),
-      DIAG_START_CAS           = DIAG_START_INSTALLAPI    + static_cast<int>(DIAG_START_INSTALLAPI),
-      DIAG_UPPER_LIMIT         = DIAG_START_CAS           + static_cast<int>(DIAG_SIZE_CAS)
-    };
-
-    class CustomDiagInfo;
-
-    /// All of the diagnostics that can be emitted by the frontend.
-    typedef unsigned kind;
-
-    /// Enum values that allow the client to map NOTEs, WARNINGs, and EXTENSIONs
-    /// to either Ignore (nothing), Remark (emit a remark), Warning
-    /// (emit a warning) or Error (emit as an error).  It allows clients to
-    /// map ERRORs to Error or Fatal (stop emitting diagnostics after this one).
-    enum class Severity : uint8_t {
-      // NOTE: 0 means "uncomputed".
-      Ignored = 1, ///< Do not present this diagnostic, ignore it.
-      Remark = 2,  ///< Present this diagnostic as a remark.
-      Warning = 3, ///< Present this diagnostic as a warning.
-      Error = 4,   ///< Present this diagnostic as an error.
-      Fatal = 5    ///< Present this diagnostic as a fatal error.
-    };
-
-    /// Flavors of diagnostics we can emit. Used to filter for a particular
-    /// kind of diagnostic (for instance, for -W/-R flags).
-    enum class Flavor {
-      WarningOrError, ///< A diagnostic that indicates a problem or potential
-                      ///< problem. Can be made fatal by -Werror.
-      Remark          ///< A diagnostic that indicates normal progress through
-                      ///< compilation.
-    };
-  } // end namespace diag
+class DiagnosticsEngine;
+class DiagnosticBuilder;
+class LangOptions;
+class SourceLocation;
+
+// Import the diagnostic enums themselves.
+namespace diag {
+enum class Group;
+
+// Size of each of the diagnostic categories.
+enum {
+  DIAG_SIZE_COMMON = 300,
+  DIAG_SIZE_DRIVER = 400,
+  DIAG_SIZE_FRONTEND = 200,
+  DIAG_SIZE_SERIALIZATION = 120,
+  DIAG_SIZE_LEX = 500,
+  DIAG_SIZE_PARSE = 800,
+  DIAG_SIZE_AST = 300,
+  DIAG_SIZE_COMMENT = 100,
+  DIAG_SIZE_CROSSTU = 100,
+  DIAG_SIZE_SEMA = 5000,
+  DIAG_SIZE_ANALYSIS = 100,
+  DIAG_SIZE_REFACTORING = 1000,
+  DIAG_SIZE_INSTALLAPI = 100,
+  DIAG_SIZE_TRAP = 100,
+  DIAG_SIZE_CAS = 100,
+};
+// Start position for diagnostics.
+// clang-format off
+enum {
+  DIAG_START_COMMON        =                          0,
+  DIAG_START_DRIVER        = DIAG_START_COMMON        + static_cast<int>(DIAG_SIZE_COMMON),
+  DIAG_START_FRONTEND      = DIAG_START_DRIVER        + static_cast<int>(DIAG_SIZE_DRIVER),
+  DIAG_START_SERIALIZATION = DIAG_START_FRONTEND      + static_cast<int>(DIAG_SIZE_FRONTEND),
+  DIAG_START_LEX           = DIAG_START_SERIALIZATION + static_cast<int>(DIAG_SIZE_SERIALIZATION),
+  DIAG_START_PARSE         = DIAG_START_LEX           + static_cast<int>(DIAG_SIZE_LEX),
+  DIAG_START_AST           = DIAG_START_PARSE         + static_cast<int>(DIAG_SIZE_PARSE),
+  DIAG_START_COMMENT       = DIAG_START_AST           + static_cast<int>(DIAG_SIZE_AST),
+  DIAG_START_CROSSTU       = DIAG_START_COMMENT       + static_cast<int>(DIAG_SIZE_COMMENT),
+  DIAG_START_SEMA          = DIAG_START_CROSSTU       + static_cast<int>(DIAG_SIZE_CROSSTU),
+  DIAG_START_ANALYSIS      = DIAG_START_SEMA          + static_cast<int>(DIAG_SIZE_SEMA),
+  DIAG_START_REFACTORING   = DIAG_START_ANALYSIS      + static_cast<int>(DIAG_SIZE_ANALYSIS),
+  DIAG_START_INSTALLAPI    = DIAG_START_REFACTORING   + static_cast<int>(DIAG_SIZE_REFACTORING),
+  DIAG_START_TRAP          = DIAG_START_INSTALLAPI    + static_cast<int>(DIAG_SIZE_INSTALLAPI),
+  DIAG_START_CAS           = DIAG_START_TRAP          + static_cast<int>(DIAG_SIZE_TRAP),
+  DIAG_UPPER_LIMIT         = DIAG_START_CAS           + static_cast<int>(DIAG_SIZE_CAS)
+};
+// clang-format on
+
+class CustomDiagInfo;
+
+/// All of the diagnostics that can be emitted by the frontend.
+typedef unsigned kind;
+
+/// Enum values that allow the client to map NOTEs, WARNINGs, and EXTENSIONs
+/// to either Ignore (nothing), Remark (emit a remark), Warning
+/// (emit a warning) or Error (emit as an error).  It allows clients to
+/// map ERRORs to Error or Fatal (stop emitting diagnostics after this one).
+enum class Severity : uint8_t {
+  // NOTE: 0 means "uncomputed".
+  Ignored = 1, ///< Do not present this diagnostic, ignore it.
+  Remark = 2,  ///< Present this diagnostic as a remark.
+  Warning = 3, ///< Present this diagnostic as a warning.
+  Error = 4,   ///< Present this diagnostic as an error.
+  Fatal = 5    ///< Present this diagnostic as a fatal error.
+};
+
+/// Flavors of diagnostics we can emit. Used to filter for a particular
+/// kind of diagnostic (for instance, for -W/-R flags).
+enum class Flavor {
+  WarningOrError, ///< A diagnostic that indicates a problem or potential
+                  ///< problem. Can be made fatal by -Werror.
+  Remark          ///< A diagnostic that indicates normal progress through
+                  ///< compilation.
+};
+} // end namespace diag
 } // end namespace clang
 
 // This has to be included *after* the DIAG_START_ enums above are defined.
@@ -175,7 +179,8 @@ class DiagnosticMapping {
 
 /// Used for handling and querying diagnostic IDs.
 ///
-/// Can be used and shared by multiple Diagnostics for multiple translation units.
+/// Can be used and shared by multiple Diagnostics for multiple translation
+/// units.
 class DiagnosticIDs : public RefCountedBase<DiagnosticIDs> {
 public:
   /// The level of the diagnostic, after it has been through mapping.
@@ -188,7 +193,8 @@ class DiagnosticIDs : public RefCountedBase<DiagnosticIDs> {
     CLASS_REMARK = 0x02,
     CLASS_WARNING = 0x03,
     CLASS_EXTENSION = 0x04,
-    CLASS_ERROR = 0x05
+    CLASS_ERROR = 0x05,
+    CLASS_TRAP = 0x06
   };
 
   static bool IsCustomDiag(diag::kind Diag) {
@@ -358,6 +364,10 @@ class DiagnosticIDs : public RefCountedBase<DiagnosticIDs> {
   ///
   bool isExtensionDiag(unsigned DiagID, bool &EnabledByDefault) const;
 
+  bool isTrapDiag(unsigned DiagID) const {
+    return getDiagClass(DiagID) == CLASS_TRAP;
+  }
+
   /// Given a group ID, returns the flag that toggles the group.
   /// For example, for Group::DeprecatedDeclarations, returns
   /// "deprecated-declarations".
@@ -496,6 +506,6 @@ class DiagnosticIDs : public RefCountedBase<DiagnosticIDs> {
   friend class DiagnosticsEngine;
 };
 
-}  // end namespace clang
+} // end namespace clang
 
 #endif

clang/include/clang/Basic/DiagnosticTrap.h

@@ -0,0 +1,14 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_CLANG_BASIC_DIAGNOSTICTRAP_H
+#define LLVM_CLANG_BASIC_DIAGNOSTICTRAP_H
+
+#include "clang/Basic/Diagnostic.h"
+#include "clang/Basic/DiagnosticTrapInterface.inc"
+
+#endif

clang/include/clang/Basic/DiagnosticTrapKinds.td

@@ -0,0 +1,30 @@
+//==--- DiagnosticTrapKinds.td ------------------------ -------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+// Trap Diagnostics
+//
+// These are diagnostics that are emitted into `TrapReason` objects using the
+// `TrapReasonBuilder` class. These `TrapReason` objects are then encoded into
+// debug info during codegen, rather than to the traditional diagnostic
+// consumers like the terminal. Their primary purpose is to make debugging traps
+// (e.g. `-fsanitize-trap=undefined`) easier by attaching a trap category and
+// message to the trap instruction that tools like a debugger can show.
+//
+//===----------------------------------------------------------------------===//
+let Component = "Trap" in {
+let CategoryName = "Undefined Behavior Sanitizer" in {
+
+def trap_ubsan_arith_overflow : Trap<
+  "%select{unsigned|signed}0 integer "
+  "%enum_select<UBSanArithKind>{"
+    "%Add{addition}|"
+    "%Sub{subtraction}|"
+    "%Mul{multiplication}"
+  "}1 overflow in %2">;
+
+}
+}