[AllocToken] Refactor stateless token calculation into Support (#163633)

Refactor the stateless (hash-based) token calculation logic out of the
`AllocToken` pass and into `llvm/Support/AllocToken.h`.

This helps with making the token calculation logic available to other
parts of the codebase, which will be necessary for frontend
implementation of `__builtin_infer_alloc_token` to perform constexpr
evaluation.

The `AllocTokenMode` enum and a new `AllocTokenMetadata` struct are
moved into a shared header. The `getAllocTokenHash()` function now
provides the source of truth for calculating token IDs for `TypeHash`
and `TypeHashPointerSplit` modes.

llvm/include/llvm/Support/AllocToken.h

@@ -0,0 +1,58 @@
+//===- llvm/Support/AllocToken.h - Allocation Token Calculation -----*- C++ -*//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Definition of AllocToken modes and shared calculation of stateless token IDs.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_ALLOCTOKEN_H
+#define LLVM_SUPPORT_ALLOCTOKEN_H
+
+#include "llvm/ADT/SmallString.h"
+#include <cstdint>
+#include <optional>
+
+namespace llvm {
+
+/// Modes for generating allocation token IDs.
+enum class AllocTokenMode {
+  /// Incrementally increasing token ID.
+  Increment,
+
+  /// Simple mode that returns a statically-assigned random token ID.
+  Random,
+
+  /// Token ID based on allocated type hash.
+  TypeHash,
+
+  /// Token ID based on allocated type hash, where the top half ID-space is
+  /// reserved for types that contain pointers and the bottom half for types
+  /// that do not contain pointers.
+  TypeHashPointerSplit,
+};
+
+/// Metadata about an allocation used to generate a token ID.
+struct AllocTokenMetadata {
+  SmallString<64> TypeName;
+  bool ContainsPointer;
+};
+
+/// Calculates stable allocation token ID. Returns std::nullopt for stateful
+/// modes that are only available in the AllocToken pass.
+///
+/// \param Mode The token generation mode.
+/// \param Metadata The metadata about the allocation.
+/// \param MaxTokens The maximum number of tokens (must not be 0)
+/// \return The calculated allocation token ID, or std::nullopt.
+LLVM_ABI std::optional<uint64_t>
+getAllocToken(AllocTokenMode Mode, const AllocTokenMetadata &Metadata,
+              uint64_t MaxTokens);
+
+} // end namespace llvm
+
+#endif // LLVM_SUPPORT_ALLOCTOKEN_H

llvm/lib/Support/AllocToken.cpp

@@ -0,0 +1,50 @@
+//===- AllocToken.cpp - Allocation Token Calculation ----------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Definition of AllocToken modes and shared calculation of stateless token IDs.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/AllocToken.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/SipHash.h"
+
+using namespace llvm;
+
+static uint64_t getStableHash(const AllocTokenMetadata &Metadata,
+                              uint64_t MaxTokens) {
+  return getStableSipHash(Metadata.TypeName) % MaxTokens;
+}
+
+std::optional<uint64_t> llvm::getAllocToken(AllocTokenMode Mode,
+                                            const AllocTokenMetadata &Metadata,
+                                            uint64_t MaxTokens) {
+  assert(MaxTokens && "Must provide non-zero max tokens");
+
+  switch (Mode) {
+  case AllocTokenMode::Increment:
+  case AllocTokenMode::Random:
+    // Stateful modes cannot be implemented as a pure function.
+    return std::nullopt;
+
+  case AllocTokenMode::TypeHash:
+    return getStableHash(Metadata, MaxTokens);
+
+  case AllocTokenMode::TypeHashPointerSplit: {
+    if (MaxTokens == 1)
+      return 0;
+    const uint64_t HalfTokens = MaxTokens / 2;
+    uint64_t Hash = getStableHash(Metadata, HalfTokens);
+    if (Metadata.ContainsPointer)
+      Hash += HalfTokens;
+    return Hash;
+  }
+  }
+
+  llvm_unreachable("");
+}

llvm/lib/Support/CMakeLists.txt

@@ -149,6 +149,7 @@ add_llvm_component_library(LLVMSupport
   AArch64BuildAttributes.cpp
   ARMAttributeParser.cpp
   ARMWinEH.cpp
+  AllocToken.cpp
   Allocator.cpp
   AutoConvert.cpp
   Base64.cpp

llvm/lib/Transforms/Instrumentation/AllocToken.cpp

@@ -36,6 +36,7 @@
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Type.h"
+#include "llvm/Support/AllocToken.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compiler.h"
@@ -54,29 +55,12 @@
 #include <variant>
 
 using namespace llvm;
+using TokenMode = AllocTokenMode;
 
 #define DEBUG_TYPE "alloc-token"
 
 namespace {
 
-//===--- Constants --------------------------------------------------------===//
-
-enum class TokenMode : unsigned {
-  /// Incrementally increasing token ID.
-  Increment = 0,
-
-  /// Simple mode that returns a statically-assigned random token ID.
-  Random = 1,
-
-  /// Token ID based on allocated type hash.
-  TypeHash = 2,
-
-  /// Token ID based on allocated type hash, where the top half ID-space is
-  /// reserved for types that contain pointers and the bottom half for types
-  /// that do not contain pointers.
-  TypeHashPointerSplit = 3,
-};
-
 //===--- Command-line options ---------------------------------------------===//
 
 cl::opt<TokenMode> ClMode(
@@ -217,22 +201,19 @@ public:
   using ModeBase::ModeBase;
 
   uint64_t operator()(const CallBase &CB, OptimizationRemarkEmitter &ORE) {
-    const auto [N, H] = getHash(CB, ORE);
-    return N ? boundedToken(H) : H;
-  }
 
-protected:
-  std::pair<MDNode *, uint64_t> getHash(const CallBase &CB,
-                                        OptimizationRemarkEmitter &ORE) {
     if (MDNode *N = getAllocTokenMetadata(CB)) {
       MDString *S = cast<MDString>(N->getOperand(0));
-      return {N, getStableSipHash(S->getString())};
+      AllocTokenMetadata Metadata{S->getString(), containsPointer(N)};
+      if (auto Token = getAllocToken(TokenMode::TypeHash, Metadata, MaxTokens))
+        return *Token;
     }
     // Fallback.
     remarkNoMetadata(CB, ORE);
-    return {nullptr, ClFallbackToken};
+    return ClFallbackToken;
   }
 
+protected:
   /// Remark that there was no precise type information.
   static void remarkNoMetadata(const CallBase &CB,
                                OptimizationRemarkEmitter &ORE) {
@@ -253,20 +234,18 @@ public:
   using TypeHashMode::TypeHashMode;
 
   uint64_t operator()(const CallBase &CB, OptimizationRemarkEmitter &ORE) {
-    if (MaxTokens == 1)
-      return 0;
-    const uint64_t HalfTokens = MaxTokens / 2;
-    const auto [N, H] = getHash(CB, ORE);
-    if (!N) {
-      // Pick the fallback token (ClFallbackToken), which by default is 0,
-      // meaning it'll fall into the pointer-less bucket. Override by setting
-      // -alloc-token-fallback if that is the wrong choice.
-      return H;
+    if (MDNode *N = getAllocTokenMetadata(CB)) {
+      MDString *S = cast<MDString>(N->getOperand(0));
+      AllocTokenMetadata Metadata{S->getString(), containsPointer(N)};
+      if (auto Token = getAllocToken(TokenMode::TypeHashPointerSplit, Metadata,
+                                     MaxTokens))
+        return *Token;
     }
-    uint64_t Hash = H % HalfTokens; // base hash
-    if (containsPointer(N))
-      Hash += HalfTokens;
-    return Hash;
+    // Pick the fallback token (ClFallbackToken), which by default is 0, meaning
+    // it'll fall into the pointer-less bucket. Override by setting
+    // -alloc-token-fallback if that is the wrong choice.
+    remarkNoMetadata(CB, ORE);
+    return ClFallbackToken;
   }
 };
 

llvm/utils/gn/secondary/llvm/lib/Support/BUILD.gn

@@ -45,6 +45,7 @@ static_library("Support") {
     "ARMAttributeParser.cpp",
     "ARMBuildAttributes.cpp",
     "ARMWinEH.cpp",
+    "AllocToken.cpp",
     "Allocator.cpp",
     "AutoConvert.cpp",
     "BalancedPartitioning.cpp",