[llvm] [CAS] Add LLVMCAS library with InMemoryCAS implementation (PR #114096)

[Paul Kirth via llvm-commits]

================
@@ -0,0 +1,320 @@
+//===- InMemoryCAS.cpp ------------------------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "BuiltinCAS.h"
+#include "llvm/ADT/LazyAtomicPointer.h"
+#include "llvm/ADT/PointerIntPair.h"
+#include "llvm/ADT/TrieRawHashMap.h"
+#include "llvm/Support/Allocator.h"
+#include "llvm/Support/Casting.h"
+#include "llvm/Support/ThreadSafeAllocator.h"
+
+using namespace llvm;
+using namespace llvm::cas;
+using namespace llvm::cas::builtin;
+
+namespace {
+
+class InMemoryObject;
+
+/// Index of referenced IDs (map: Hash -> InMemoryObject*). Uses
+/// LazyAtomicPointer to coordinate creation of objects.
+using InMemoryIndexT =
+    ThreadSafeTrieRawHashMap<LazyAtomicPointer<const InMemoryObject>,
+                             sizeof(HashType)>;
+
+/// Values in \a InMemoryIndexT. \a InMemoryObject's point at this to access
+/// their hash.
+using InMemoryIndexValueT = InMemoryIndexT::value_type;
+
+class InMemoryObject {
+public:
+  enum class Kind {
+    /// Node with refs and data.
+    RefNode,
+
+    /// Node with refs and data co-allocated.
+    InlineNode,
+
+    Max = InlineNode,
+  };
+
+  Kind getKind() const { return IndexAndKind.getInt(); }
+  const InMemoryIndexValueT &getIndex() const {
+    assert(IndexAndKind.getPointer());
+    return *IndexAndKind.getPointer();
+  }
+
+  ArrayRef<uint8_t> getHash() const { return getIndex().Hash; }
+
+  InMemoryObject() = delete;
+  InMemoryObject(InMemoryObject &&) = delete;
+  InMemoryObject(const InMemoryObject &) = delete;
+
+protected:
+  InMemoryObject(Kind K, const InMemoryIndexValueT &I) : IndexAndKind(&I, K) {}
+
+private:
+  enum Counts : int {
+    NumKindBits = 2,
+  };
+  PointerIntPair<const InMemoryIndexValueT *, NumKindBits, Kind> IndexAndKind;
+  static_assert((1U << NumKindBits) <= alignof(InMemoryIndexValueT),
+                "Kind will clobber pointer");
+  static_assert(((int)Kind::Max >> NumKindBits) == 0, "Kind will be truncated");
+
+public:
+  inline ArrayRef<char> getData() const;
+
+  inline ArrayRef<const InMemoryObject *> getRefs() const;
+};
+
+class InMemoryRefObject : public InMemoryObject {
+public:
+  static constexpr Kind KindValue = Kind::RefNode;
+  static bool classof(const InMemoryObject *O) {
+    return O->getKind() == KindValue;
+  }
+
+  ArrayRef<const InMemoryObject *> getRefsImpl() const { return Refs; }
+  ArrayRef<const InMemoryObject *> getRefs() const { return Refs; }
+  ArrayRef<char> getDataImpl() const { return Data; }
+  ArrayRef<char> getData() const { return Data; }
+
+  static InMemoryRefObject &create(function_ref<void *(size_t Size)> Allocate,
+                                   const InMemoryIndexValueT &I,
+                                   ArrayRef<const InMemoryObject *> Refs,
+                                   ArrayRef<char> Data) {
+    void *Mem = Allocate(sizeof(InMemoryRefObject));
+    return *new (Mem) InMemoryRefObject(I, Refs, Data);
+  }
+
+private:
+  InMemoryRefObject(const InMemoryIndexValueT &I,
+                    ArrayRef<const InMemoryObject *> Refs, ArrayRef<char> Data)
+      : InMemoryObject(KindValue, I), Refs(Refs), Data(Data) {
+    assert(isAddrAligned(Align(8), this) && "Expected 8-byte alignment");
+    assert(isAddrAligned(Align(8), Data.data()) && "Expected 8-byte alignment");
+    assert(*Data.end() == 0 && "Expected null-termination");
+  }
+
+  ArrayRef<const InMemoryObject *> Refs;
+  ArrayRef<char> Data;
+};
+
+class InMemoryInlineObject : public InMemoryObject {
+public:
+  static constexpr Kind KindValue = Kind::InlineNode;
+  static bool classof(const InMemoryObject *O) {
+    return O->getKind() == KindValue;
+  }
+
+  ArrayRef<const InMemoryObject *> getRefs() const { return getRefsImpl(); }
+  ArrayRef<const InMemoryObject *> getRefsImpl() const {
+    return ArrayRef(reinterpret_cast<const InMemoryObject *const *>(this + 1),
+                    NumRefs);
+  }
+
+  ArrayRef<char> getData() const { return getDataImpl(); }
+  ArrayRef<char> getDataImpl() const {
+    ArrayRef<const InMemoryObject *> Refs = getRefs();
+    return ArrayRef(reinterpret_cast<const char *>(Refs.data() + Refs.size()),
+                    DataSize);
----------------
ilovepi wrote:

What's going on here? why is the data ptr part of the ArrayRef set to just after `Refs.data()`? This seems incorrect, or at least warrants some comment about why this is safe.

https://github.com/llvm/llvm-project/pull/114096