[Support][ThinLTO] Move ThinLTO caching to LLVM Support library

We would like to move ThinLTO’s battle-tested file caching mechanism to
the LLVM Support library so that we can use it elsewhere in LLVM.

Patch By: noajshu

Differential Revision: https://reviews.llvm.org/D111371

Author: noajshu

clang/docs/tools/clang-formatted-files.txt

@@ -4745,7 +4745,6 @@ llvm/include/llvm/IR/ReplaceConstant.h
 llvm/include/llvm/IR/StructuralHash.h
 llvm/include/llvm/IR/TrackingMDRef.h
 llvm/include/llvm/IR/UseListOrder.h
-llvm/include/llvm/LTO/Caching.h
 llvm/include/llvm/LTO/SummaryBasedOptimizations.h
 llvm/include/llvm/MC/MCAsmInfoCOFF.h
 llvm/include/llvm/MC/MCAsmInfoDarwin.h
@@ -4852,6 +4851,7 @@ llvm/include/llvm/Support/BinaryStreamRef.h
 llvm/include/llvm/Support/BinaryStreamWriter.h
 llvm/include/llvm/Support/BuryPointer.h
 llvm/include/llvm/Support/CachePruning.h
+llvm/include/llvm/Support/Caching.h
 llvm/include/llvm/Support/CFGDiff.h
 llvm/include/llvm/Support/CFGUpdate.h
 llvm/include/llvm/Support/CodeGenCoverage.h

clang/lib/CodeGen/BackendUtil.cpp

@@ -1561,7 +1561,7 @@ static void runThinLTOBackend(
     return;
 
   auto AddStream = [&](size_t Task) {
-    return std::make_unique<lto::NativeObjectStream>(std::move(OS));
+    return std::make_unique<NativeObjectStream>(std::move(OS));
   };
   lto::Config Conf;
   if (CGOpts.SaveTempsFilePrefix != "") {

lld/COFF/LTO.cpp

@@ -20,10 +20,10 @@
 #include "llvm/ADT/Twine.h"
 #include "llvm/Bitcode/BitcodeWriter.h"
 #include "llvm/IR/DiagnosticPrinter.h"
-#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/Config.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Object/SymbolicFile.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/FileSystem.h"
@@ -164,16 +164,17 @@ std::vector<InputFile *> BitcodeCompiler::compile(COFFLinkerContext &ctx) {
   // The /lldltocache option specifies the path to a directory in which to cache
   // native object files for ThinLTO incremental builds. If a path was
   // specified, configure LTO to use it as the cache directory.
-  lto::NativeObjectCache cache;
+  NativeObjectCache cache;
   if (!config->ltoCache.empty())
-    cache = check(lto::localCache(
-        config->ltoCache, [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-          files[task] = std::move(mb);
-        }));
+    cache =
+        check(localCache("ThinLTO", "Thin", config->ltoCache,
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                           files[task] = std::move(mb);
+                         }));
 
   checkError(ltoObj->run(
       [&](size_t task) {
-        return std::make_unique<lto::NativeObjectStream>(
+        return std::make_unique<NativeObjectStream>(
             std::make_unique<raw_svector_ostream>(buf[task]));
       },
       cache));

lld/ELF/LTO.cpp

@@ -23,10 +23,10 @@
 #include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/Bitcode/BitcodeWriter.h"
 #include "llvm/IR/DiagnosticPrinter.h"
-#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/Config.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Object/SymbolicFile.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/FileSystem.h"
@@ -304,18 +304,18 @@ std::vector<InputFile *> BitcodeCompiler::compile() {
   // The --thinlto-cache-dir option specifies the path to a directory in which
   // to cache native object files for ThinLTO incremental builds. If a path was
   // specified, configure LTO to use it as the cache directory.
-  lto::NativeObjectCache cache;
+  NativeObjectCache cache;
   if (!config->thinLTOCacheDir.empty())
-    cache = check(
-        lto::localCache(config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(mb);
-                        }));
+    cache =
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                           files[task] = std::move(mb);
+                         }));
 
   if (!bitcodeFiles.empty())
     checkError(ltoObj->run(
         [&](size_t task) {
-          return std::make_unique<lto::NativeObjectStream>(
+          return std::make_unique<NativeObjectStream>(
               std::make_unique<raw_svector_ostream>(buf[task]));
         },
         cache));

lld/MachO/LTO.cpp

@@ -17,9 +17,9 @@
 #include "lld/Common/ErrorHandler.h"
 #include "lld/Common/Strings.h"
 #include "lld/Common/TargetOptionsCommandFlags.h"
-#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/Config.h"
 #include "llvm/LTO/LTO.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/raw_ostream.h"
@@ -105,17 +105,17 @@ std::vector<ObjFile *> BitcodeCompiler::compile() {
   // The -cache_path_lto option specifies the path to a directory in which
   // to cache native object files for ThinLTO incremental builds. If a path was
   // specified, configure LTO to use it as the cache directory.
-  lto::NativeObjectCache cache;
+  NativeObjectCache cache;
   if (!config->thinLTOCacheDir.empty())
-    cache = check(
-        lto::localCache(config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(mb);
-                        }));
+    cache =
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                           files[task] = std::move(mb);
+                         }));
 
   checkError(ltoObj->run(
       [&](size_t task) {
-        return std::make_unique<lto::NativeObjectStream>(
+        return std::make_unique<NativeObjectStream>(
             std::make_unique<raw_svector_ostream>(buf[task]));
       },
       cache));

lld/wasm/LTO.cpp

@@ -19,10 +19,10 @@
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/IR/DiagnosticPrinter.h"
-#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/Config.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Object/SymbolicFile.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/FileSystem.h"
@@ -127,17 +127,17 @@ std::vector<StringRef> BitcodeCompiler::compile() {
   // The --thinlto-cache-dir option specifies the path to a directory in which
   // to cache native object files for ThinLTO incremental builds. If a path was
   // specified, configure LTO to use it as the cache directory.
-  lto::NativeObjectCache cache;
+  NativeObjectCache cache;
   if (!config->thinLTOCacheDir.empty())
-    cache = check(
-        lto::localCache(config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(mb);
-                        }));
+    cache =
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                           files[task] = std::move(mb);
+                         }));
 
   checkError(ltoObj->run(
       [&](size_t task) {
-        return std::make_unique<lto::NativeObjectStream>(
+        return std::make_unique<NativeObjectStream>(
             std::make_unique<raw_svector_ostream>(buf[task]));
       },
       cache));

llvm/include/llvm/LTO/Caching.h

@@ -21,6 +21,7 @@
 #include "llvm/IR/ModuleSummaryIndex.h"
 #include "llvm/LTO/Config.h"
 #include "llvm/Object/IRSymtab.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/thread.h"
 #include "llvm/Transforms/IPO/FunctionAttrs.h"
@@ -187,40 +188,6 @@ class InputFile {
   }
 };
 
-/// This class wraps an output stream for a native object. Most clients should
-/// just be able to return an instance of this base class from the stream
-/// callback, but if a client needs to perform some action after the stream is
-/// written to, that can be done by deriving from this class and overriding the
-/// destructor.
-class NativeObjectStream {
-public:
-  NativeObjectStream(std::unique_ptr<raw_pwrite_stream> OS) : OS(std::move(OS)) {}
-  std::unique_ptr<raw_pwrite_stream> OS;
-  virtual ~NativeObjectStream() = default;
-};
-
-/// This type defines the callback to add a native object that is generated on
-/// the fly.
-///
-/// Stream callbacks must be thread safe.
-using AddStreamFn =
-    std::function<std::unique_ptr<NativeObjectStream>(unsigned Task)>;
-
-/// This is the type of a native object cache. To request an item from the
-/// cache, pass a unique string as the Key. For hits, the cached file will be
-/// added to the link and this function will return AddStreamFn(). For misses,
-/// the cache will return a stream callback which must be called at most once to
-/// produce content for the stream. The native object stream produced by the
-/// stream callback will add the file to the link after the stream is written
-/// to.
-///
-/// Clients generally look like this:
-///
-/// if (AddStreamFn AddStream = Cache(Task, Key))
-///   ProduceContent(AddStream);
-using NativeObjectCache =
-    std::function<AddStreamFn(unsigned Task, StringRef Key)>;
-
 /// A ThinBackend defines what happens after the thin-link phase during ThinLTO.
 /// The details of this type definition aren't important; clients can only
 /// create a ThinBackend using one of the create*ThinBackend() functions below.

llvm/include/llvm/LTO/LTO.h

@@ -176,7 +176,7 @@ struct LTOCodeGenerator {
   /// created using the \p AddStream callback. Returns true on success.
   ///
   /// Calls \a verifyMergedModuleOnce().
-  bool compileOptimized(lto::AddStreamFn AddStream, unsigned ParallelismLevel);
+  bool compileOptimized(AddStreamFn AddStream, unsigned ParallelismLevel);
 
   /// Enable the Freestanding mode: indicate that the optimizer should not
   /// assume builtins are present on the target.

llvm/include/llvm/LTO/legacy/LTOCodeGenerator.h

@@ -0,0 +1,76 @@
+//===- Caching.h - LLVM File Cache Handling Configuration -------*- 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the localCache function, which allows clients to add a
+// filesystem cache. This is used by ThinLTO.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_CACHING_H
+#define LLVM_SUPPORT_CACHING_H
+
+#include "llvm/Support/Error.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/thread.h"
+
+namespace llvm {
+
+/// This class wraps an output stream for a native object. Most clients should
+/// just be able to return an instance of this base class from the stream
+/// callback, but if a client needs to perform some action after the stream is
+/// written to, that can be done by deriving from this class and overriding the
+/// destructor.
+class NativeObjectStream {
+public:
+  NativeObjectStream(std::unique_ptr<raw_pwrite_stream> OS)
+      : OS(std::move(OS)) {}
+  std::unique_ptr<raw_pwrite_stream> OS;
+  virtual ~NativeObjectStream() = default;
+};
+
+/// This type defines the callback to add a native object that is generated on
+/// the fly.
+///
+/// Stream callbacks must be thread safe.
+using AddStreamFn =
+    std::function<std::unique_ptr<NativeObjectStream>(unsigned Task)>;
+
+/// This is the type of a native object cache. To request an item from the
+/// cache, pass a unique string as the Key. For hits, the cached file will be
+/// added to the link and this function will return AddStreamFn(). For misses,
+/// the cache will return a stream callback which must be called at most once to
+/// produce content for the stream. The native object stream produced by the
+/// stream callback will add the file to the link after the stream is written
+/// to.
+///
+/// Clients generally look like this:
+///
+/// if (AddStreamFn AddStream = Cache(Task, Key))
+///   ProduceContent(AddStream);
+using NativeObjectCache =
+    std::function<AddStreamFn(unsigned Task, StringRef Key)>;
+
+/// This type defines the callback to add a pre-existing native object file
+/// (e.g. in a cache).
+///
+/// Buffer callbacks must be thread safe.
+using AddBufferFn =
+    std::function<void(unsigned Task, std::unique_ptr<MemoryBuffer> MB)>;
+
+/// Create a local file system cache which uses the given cache name, temporary
+/// file prefix, cache directory and file callback. This function also creates
+/// the cache directory if it does not already exist. The cache name appears in
+/// error messages for errors during caching. The temporary file prefix is used
+/// in the temporary file naming scheme used when writing files atomically.
+Expected<NativeObjectCache> localCache(Twine CacheNameRef,
+                                       Twine TempFilePrefixRef,
+                                       Twine CacheDirectoryPathRef,
+                                       AddBufferFn AddBuffer);
+} // namespace llvm
+
+#endif