Merge commit '774ffe5cce73' from llvm.org/main into next

Author: git apple-llvm automerger

clang/docs/AllocToken.rst

@@ -0,0 +1,173 @@
+=================
+Allocation Tokens
+=================
+
+.. contents::
+   :local:
+
+Introduction
+============
+
+Clang provides support for allocation tokens to enable allocator-level heap
+organization strategies. Clang assigns mode-dependent token IDs to allocation
+calls; the runtime behavior depends entirely on the implementation of a
+compatible memory allocator.
+
+Possible allocator strategies include:
+
+* **Security Hardening**: Placing allocations into separate, isolated heap
+  partitions. For example, separating pointer-containing types from raw data
+  can mitigate exploits that rely on overflowing a primitive buffer to corrupt
+  object metadata.
+
+* **Memory Layout Optimization**: Grouping related allocations to improve data
+  locality and cache utilization.
+
+* **Custom Allocation Policies**: Applying different management strategies to
+  different partitions.
+
+Token Assignment Mode
+=====================
+
+The default mode to calculate tokens is:
+
+* ``typehash``: This mode assigns a token ID based on the hash of the allocated
+  type's name.
+
+Other token ID assignment modes are supported, but they may be subject to
+change or removal. These may (experimentally) be selected with ``-mllvm
+-alloc-token-mode=<mode>``:
+
+* ``random``: This mode assigns a statically-determined random token ID to each
+  allocation site.
+
+* ``increment``: This mode assigns a simple, incrementally increasing token ID
+  to each allocation site.
+
+Allocation Token Instrumentation
+================================
+
+To enable instrumentation of allocation functions, code can be compiled with
+the ``-fsanitize=alloc-token`` flag:
+
+.. code-block:: console
+
+    % clang++ -fsanitize=alloc-token example.cc
+
+The instrumentation transforms allocation calls to include a token ID. For
+example:
+
+.. code-block:: c
+
+    // Original:
+    ptr = malloc(size);
+
+    // Instrumented:
+    ptr = __alloc_token_malloc(size, <token id>);
+
+The following command-line options affect generated token IDs:
+
+* ``-falloc-token-max=<N>``
+    Configures the maximum number of tokens. No max by default (tokens bounded
+    by ``SIZE_MAX``).
+
+    .. code-block:: console
+
+        % clang++ -fsanitize=alloc-token -falloc-token-max=512 example.cc
+
+Runtime Interface
+-----------------
+
+A compatible runtime must be provided that implements the token-enabled
+allocation functions. The instrumentation generates calls to functions that
+take a final ``size_t token_id`` argument.
+
+.. code-block:: c
+
+    // C standard library functions
+    void *__alloc_token_malloc(size_t size, size_t token_id);
+    void *__alloc_token_calloc(size_t count, size_t size, size_t token_id);
+    void *__alloc_token_realloc(void *ptr, size_t size, size_t token_id);
+    // ...
+
+    // C++ operators (mangled names)
+    // operator new(size_t, size_t)
+    void *__alloc_token__Znwm(size_t size, size_t token_id);
+    // operator new[](size_t, size_t)
+    void *__alloc_token__Znam(size_t size, size_t token_id);
+    // ... other variants like nothrow, etc., are also instrumented.
+
+Fast ABI
+--------
+
+An alternative ABI can be enabled with ``-fsanitize-alloc-token-fast-abi``,
+which encodes the token ID hint in the allocation function name.
+
+.. code-block:: c
+
+    void *__alloc_token_0_malloc(size_t size);
+    void *__alloc_token_1_malloc(size_t size);
+    void *__alloc_token_2_malloc(size_t size);
+    ...
+    void *__alloc_token_0_Znwm(size_t size);
+    void *__alloc_token_1_Znwm(size_t size);
+    void *__alloc_token_2_Znwm(size_t size);
+    ...
+
+This ABI provides a more efficient alternative where
+``-falloc-token-max`` is small.
+
+Disabling Instrumentation
+-------------------------
+
+To exclude specific functions from instrumentation, you can use the
+``no_sanitize("alloc-token")`` attribute:
+
+.. code-block:: c
+
+    __attribute__((no_sanitize("alloc-token")))
+    void* custom_allocator(size_t size) {
+        return malloc(size);  // Uses original malloc
+    }
+
+Note: Independent of any given allocator support, the instrumentation aims to
+remain performance neutral. As such, ``no_sanitize("alloc-token")``
+functions may be inlined into instrumented functions and vice-versa. If
+correctness is affected, such functions should explicitly be marked
+``noinline``.
+
+The ``__attribute__((disable_sanitizer_instrumentation))`` is also supported to
+disable this and other sanitizer instrumentations.
+
+Suppressions File (Ignorelist)
+------------------------------
+
+AllocToken respects the ``src`` and ``fun`` entity types in the
+:doc:`SanitizerSpecialCaseList`, which can be used to omit specified source
+files or functions from instrumentation.
+
+.. code-block:: bash
+
+    [alloc-token]
+    # Exclude specific source files
+    src:third_party/allocator.c
+    # Exclude function name patterns
+    fun:*custom_malloc*
+    fun:LowLevel::*
+
+.. code-block:: console
+
+    % clang++ -fsanitize=alloc-token -fsanitize-ignorelist=my_ignorelist.txt example.cc
+
+Conditional Compilation with ``__SANITIZE_ALLOC_TOKEN__``
+-----------------------------------------------------------
+
+In some cases, one may need to execute different code depending on whether
+AllocToken instrumentation is enabled. The ``__SANITIZE_ALLOC_TOKEN__`` macro
+can be used for this purpose.
+
+.. code-block:: c
+
+    #ifdef __SANITIZE_ALLOC_TOKEN__
+    // Code specific to -fsanitize=alloc-token builds
+    #endif

clang/docs/ReleaseNotes.rst

@@ -257,10 +257,16 @@ Non-comprehensive list of changes in this release
 
 - Fixed a crash when the second argument to ``__builtin_assume_aligned`` was not constant (#GH161314)
 
+- Introduce support for :doc:`allocation tokens <AllocToken>` to enable
+  allocator-level heap organization strategies. A feature to instrument all
+  allocation functions with a token ID can be enabled via the
+  ``-fsanitize=alloc-token`` flag.
+
 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 options for enabling allocation token instrumentation: ``-fsanitize=alloc-token``, ``-falloc-token-max=``, ``-fsanitize-alloc-token-fast-abi``, ``-fsanitize-alloc-token-extended``.
 
 
 Lanai Support

clang/docs/UsersManual.rst

@@ -2155,13 +2155,11 @@ are listed below.
 
 .. option:: -f[no-]sanitize=check1,check2,...
 
-   Turn on runtime checks for various forms of undefined or suspicious
-   behavior.
+   Turn on runtime checks or mitigations for various forms of undefined or
+   suspicious behavior. These are disabled by default.
 
-   This option controls whether Clang adds runtime checks for various
-   forms of undefined or suspicious behavior, and is disabled by
-   default. If a check fails, a diagnostic message is produced at
-   runtime explaining the problem. The main checks are:
+   The following options enable runtime checks for various forms of undefined
+   or suspicious behavior:
 
    -  .. _opt_fsanitize_address:
 
@@ -2195,6 +2193,14 @@ are listed below.
    -  ``-fsanitize=realtime``: :doc:`RealtimeSanitizer`,
       a real-time safety checker.
 
+   The following options enable runtime mitigations for various forms of
+   undefined or suspicious behavior:
+
+   -  ``-fsanitize=alloc-token``: Enables :doc:`allocation tokens <AllocToken>`
+      for allocator-level heap organization strategies, such as for security
+      hardening. It passes type-derived token IDs to a compatible memory
+      allocator. Requires linking against a token-aware allocator.
+
    There are more fine-grained checks available: see
    the :ref:`list <ubsan-checks>` of specific kinds of
    undefined behavior that can be detected and the :ref:`list <cfi-schemes>`

clang/docs/index.rst

@@ -40,6 +40,7 @@ Using Clang as a Compiler
    SanitizerCoverage
    SanitizerStats
    SanitizerSpecialCaseList
+   AllocToken
    BoundsSafety
    BoundsSafetyAdoptionGuide
    BoundsSafetyImplPlans

clang/include/clang/Basic/CodeGenOptions.def

@@ -307,6 +307,8 @@ CODEGENOPT(SanitizeBinaryMetadataCovered, 1, 0, Benign) ///< Emit PCs for covere
 CODEGENOPT(SanitizeBinaryMetadataAtomics, 1, 0, Benign) ///< Emit PCs for atomic operations.
 CODEGENOPT(SanitizeBinaryMetadataUAR, 1, 0, Benign) ///< Emit PCs for start of functions
                                                     ///< that are subject for use-after-return checking.
+CODEGENOPT(SanitizeAllocTokenFastABI, 1, 0, Benign) ///< Use the AllocToken fast ABI.
+CODEGENOPT(SanitizeAllocTokenExtended, 1, 0, Benign) ///< Extend coverage to custom allocation functions.
 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.

clang/include/clang/Basic/CodeGenOptions.h

@@ -450,6 +450,10 @@ class CodeGenOptions : public CodeGenOptionsBase {
 
   std::optional<double> AllowRuntimeCheckSkipHotCutoff;
 
+  /// Maximum number of allocation tokens (0 = no max), nullopt if none set (use
+  /// pass default).
+  std::optional<uint64_t> AllocTokenMax;
+
   /// List of backend command-line options for -fembed-bitcode.
   std::vector<uint8_t> CmdArgs;
 

clang/include/clang/Driver/Options.td

@@ -2850,8 +2850,25 @@ def fsanitize_skip_hot_cutoff_EQ
           "(0.0 [default] = skip none; 1.0 = skip all). "
           "Argument format: <sanitizer1>=<value1>,<sanitizer2>=<value2>,...">;
 
+defm sanitize_alloc_token_fast_abi : BoolOption<"f", "sanitize-alloc-token-fast-abi",
+  CodeGenOpts<"SanitizeAllocTokenFastABI">, DefaultFalse,
+  PosFlag<SetTrue, [], [ClangOption], "Use the AllocToken fast ABI">,
+  NegFlag<SetFalse, [], [ClangOption], "Use the default AllocToken ABI">>,
+  Group<f_clang_Group>;
+defm sanitize_alloc_token_extended : BoolOption<"f", "sanitize-alloc-token-extended",
+  CodeGenOpts<"SanitizeAllocTokenExtended">, DefaultFalse,
+  PosFlag<SetTrue, [], [ClangOption], "Enable">,
+  NegFlag<SetFalse, [], [ClangOption], "Disable">,
+  BothFlags<[], [ClangOption], " extended coverage to custom allocation functions">>,
+  Group<f_clang_Group>;
+
 } // end -f[no-]sanitize* flags
 
+def falloc_token_max_EQ : Joined<["-"], "falloc-token-max=">,
+  Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
+  MetaVarName<"<N>">,
+  HelpText<"Limit to maximum N allocation tokens (0 = no max)">;
+
 def fallow_runtime_check_skip_hot_cutoff_EQ
     : Joined<["-"], "fallow-runtime-check-skip-hot-cutoff=">,
       Group<f_clang_Group>,

clang/include/clang/Driver/SanitizerArgs.h

@@ -75,6 +75,8 @@ class SanitizerArgs {
       llvm::AsanDetectStackUseAfterReturnMode::Invalid;
 
   std::string MemtagMode;
+  bool AllocTokenFastABI = false;
+  bool AllocTokenExtended = false;
 
 public:
   /// Parses the sanitizer arguments from an argument list.

clang/lib/CodeGen/BackendUtil.cpp

@@ -61,11 +61,13 @@
 #include "llvm/TargetParser/Triple.h"
 #include "llvm/Transforms/HipStdPar/HipStdPar.h"
 #include "llvm/Transforms/IPO/EmbedBitcodePass.h"
+#include "llvm/Transforms/IPO/InferFunctionAttrs.h"
 #include "llvm/Transforms/IPO/LowerTypeTests.h"
 #include "llvm/Transforms/IPO/ThinLTOBitcodeWriter.h"
 #include "llvm/Transforms/InstCombine/InstCombine.h"
 #include "llvm/Transforms/Instrumentation/AddressSanitizer.h"
 #include "llvm/Transforms/Instrumentation/AddressSanitizerOptions.h"
+#include "llvm/Transforms/Instrumentation/AllocToken.h"
 #include "llvm/Transforms/Instrumentation/BoundsChecking.h"
 #include "llvm/Transforms/Instrumentation/DataFlowSanitizer.h"
 #include "llvm/Transforms/Instrumentation/GCOVProfiler.h"
@@ -240,6 +242,14 @@ class EmitAssemblyHelper {
 };
 } // namespace
 
+static AllocTokenOptions getAllocTokenOptions(const CodeGenOptions &CGOpts) {
+  AllocTokenOptions Opts;
+  Opts.MaxTokens = CGOpts.AllocTokenMax;
+  Opts.Extended = CGOpts.SanitizeAllocTokenExtended;
+  Opts.FastABI = CGOpts.SanitizeAllocTokenFastABI;
+  return Opts;
+}
+
 static SanitizerCoverageOptions
 getSancovOptsFromCGOpts(const CodeGenOptions &CGOpts) {
   SanitizerCoverageOptions Opts;
@@ -807,6 +817,16 @@ static void addSanitizers(const Triple &TargetTriple,
       MPM.addPass(DataFlowSanitizerPass(LangOpts.NoSanitizeFiles,
                                         PB.getVirtualFileSystemPtr()));
     }
+
+    if (LangOpts.Sanitize.has(SanitizerKind::AllocToken)) {
+      if (Level == OptimizationLevel::O0) {
+        // The default pass builder only infers libcall function attrs when
+        // optimizing, so we insert it here because we need it for accurate
+        // memory allocation function detection.
+        MPM.addPass(InferFunctionAttrsPass());
+      }
+      MPM.addPass(AllocTokenPass(getAllocTokenOptions(CodeGenOpts)));
+    }
   };
   if (ClSanitizeOnOptimizerEarlyEP) {
     PB.registerOptimizerEarlyEPCallback(