[CAS] Improve MappedFileRegionBumpPtr

clang/test/CAS/daemon-cas-recovery.c

@@ -4,7 +4,7 @@
 
 /// Construct a malformed CAS to recovery from.
 // RUN: echo "abc" | llvm-cas --cas %t/cas --make-blob --data -
-// RUN: rm %t/cas/v1.1/v9.data
+// RUN: rm %t/cas/v1.1/v10.data
 // RUN: not llvm-cas --cas %t/cas --validate --check-hash
 
 // RUN: env LLVM_CACHE_CAS_PATH=%t/cas LLVM_CAS_FORCE_VALIDATION=1 %clang-cache \

clang/test/CAS/depscan-cas-log.c

@@ -10,11 +10,11 @@
 // RUN:   -cc1-args -cc1 -triple x86_64-apple-macosx11.0.0 -emit-obj %s -o %t/t.o -fcas-path %t/cas
 // RUN: FileCheck %s --input-file %t/cas/v1.log
 
-// CHECK: [[PID1:[0-9]*]] {{[0-9]*}}: mmap '{{.*}}v9.index'
+// CHECK: [[PID1:[0-9]*]] {{[0-9]*}}: mmap '{{.*}}v{{[0-9]+}}.index'
 // CHECK: [[PID1]] {{[0-9]*}}: create subtrie
 
 // Even a minimal compilation involves at least 9 records for the cache key.
 // CHECK-COUNT-9: [[PID1]] {{[0-9]*}}: create record
 
-// CHECK: [[PID2:[0-9]*]] {{[0-9]*}}: mmap '{{.*}}v9.index'
-// CHECK: [[PID2]] {{[0-9]*}}: close mmap '{{.*}}v9.index'
+// CHECK: [[PID2:[0-9]*]] {{[0-9]*}}: mmap '{{.*}}v{{[0-9]+}}.index'
+// CHECK: [[PID2]] {{[0-9]*}}: close mmap '{{.*}}v{{[0-9]+}}.index'

clang/test/CAS/validate-once.c

@@ -1,7 +1,7 @@
 // RUN: rm -rf %t
 
 // RUN: llvm-cas --cas %t/cas --ingest %s
-// RUN: mv %t/cas/v1.1/v9.data %t/cas/v1.1/v9.data.bak
+// RUN: mv %t/cas/v1.1/v10.data %t/cas/v1.1/v10.data.bak
 
 // RUN: %clang -cc1depscand -execute %{clang-daemon-dir}/%basename_t -cas-args -fcas-path %t/cas -- \
 // RUN:   %clang -target x86_64-apple-macos11 -I %S/Inputs \

clang/tools/driver/cc1depscanProtocol.cpp

@@ -190,6 +190,7 @@ Expected<ScanDaemon> ScanDaemon::launchDaemon(StringRef BasePath,
   static constexpr const char *PassThroughEnv[] = {
       "LLVM_CAS_LOG",
       "LLVM_CAS_DISABLE_VALIDATION",
+      "LLVM_CAS_MAX_MAPPING_SIZE",
   };
   SmallVector<const char *> EnvP;
   for (const char *Name : PassThroughEnv)

llvm/include/llvm/CAS/MappedFileRegionBumpPtr.h

@@ -5,11 +5,16 @@
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
+//
+/// \file
+/// This file declares interface for MappedFileRegionBumpPtr, a bump pointer
+/// allocator, backed by a memory-mapped file.
+///
+//===----------------------------------------------------------------------===//
 
 #ifndef LLVM_CAS_MAPPEDFILEREGIONBUMPPTR_H
 #define LLVM_CAS_MAPPEDFILEREGIONBUMPPTR_H
 
-#include "llvm/Config/llvm-config.h"
 #include "llvm/Support/Alignment.h"
 #include "llvm/Support/FileSystem.h"
 #include <atomic>
@@ -18,7 +23,7 @@ namespace llvm::cas {
 
 namespace ondisk {
 class OnDiskCASLogger;
-}
+} // namespace ondisk
 
 /// Allocator for an owned mapped file region that supports thread-safe and
 /// process-safe bump pointer allocation.
@@ -31,33 +36,37 @@ class OnDiskCASLogger;
 /// Process-safe. Uses file locks when resizing the file during initialization
 /// and destruction.
 ///
-/// Thread-safe, assuming all threads use the same instance to talk to a given
-/// file/mapping. Unsafe to have multiple instances talking to the same file
-/// in the same process since file locks will misbehave. Clients should
-/// coordinate (somehow).
-///
-/// \note Currently we allocate the whole file without sparseness on Windows.
+/// Thread-safe. Requires OS support thread-safe file lock.
 ///
 /// Provides 8-byte alignment for all allocations.
 class MappedFileRegionBumpPtr {
 public:
   using RegionT = sys::fs::mapped_file_region;
 
+  /// Header for MappedFileRegionBumpPtr. It can be configured to be located
+  /// at any location within the file and the allocation will be appended after
+  /// the header.
+  struct Header {
+    std::atomic<uint64_t> BumpPtr;
+    std::atomic<uint64_t> AllocatedSize;
+  };
+
   /// Create a \c MappedFileRegionBumpPtr.
   ///
   /// \param Path the path to open the mapped region.
   /// \param Capacity the maximum size for the mapped file region.
-  /// \param BumpPtrOffset the offset at which to store the bump pointer.
+  /// \param HeaderOffset the offset at which to store the header. This is so
+  /// that information can be stored before the header, like a file magic.
   /// \param NewFileConstructor is for constructing new files. It has exclusive
   /// access to the file. Must call \c initializeBumpPtr.
   static Expected<MappedFileRegionBumpPtr>
-  create(const Twine &Path, uint64_t Capacity, int64_t BumpPtrOffset,
+  create(const Twine &Path, uint64_t Capacity, uint64_t HeaderOffset,
          std::shared_ptr<ondisk::OnDiskCASLogger> Logger,
          function_ref<Error(MappedFileRegionBumpPtr &)> NewFileConstructor);
 
-  /// Finish initializing the bump pointer. Must be called by
-  /// \c NewFileConstructor.
-  void initializeBumpPtr(int64_t BumpPtrOffset);
+  /// Finish initializing the header. Must be called by \c NewFileConstructor.
+  /// \c HeaderOffset passed should match the value passed to \c create.
+  void initializeHeader(uint64_t HeaderOffset);
 
   /// Minimum alignment for allocations, currently hardcoded to 8B.
   static constexpr Align getAlign() {
@@ -108,14 +117,12 @@ class MappedFileRegionBumpPtr {
   }
 
 private:
-  struct Header {
-    std::atomic<int64_t> BumpPtr;
-    std::atomic<int64_t> AllocatedSize;
-  };
   RegionT Region;
   Header *H = nullptr;
   std::string Path;
+  // File descriptor for the main storage file.
   std::optional<int> FD;
+  // File descriptor for the file used as reader/writer lock.
   std::optional<int> SharedLockFD;
   std::shared_ptr<ondisk::OnDiskCASLogger> Logger = nullptr;
 };