[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

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(
+    cache =
-        config->ltoCache, [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+        check(localCache("ThinLTO", "Thin", config->ltoCache,
-          files[task] = std::move(mb);
+                         [&](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(
+    cache =
-        lto::localCache(config->thinLTOCacheDir,
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(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(
+    cache =
-        lto::localCache(config->thinLTOCacheDir,
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(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(
+    cache =
-        lto::localCache(config->thinLTOCacheDir,
+        check(localCache("ThinLTO", "Thin", config->thinLTOCacheDir,
-                        [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
+                         [&](size_t task, std::unique_ptr<MemoryBuffer> mb) {
-                          files[task] = std::move(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

@@ -1,38 +0,0 @@
-//===- Caching.h - LLVM Link Time Optimizer Configuration -----------------===//
-//
-// 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 to ThinLTO.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef LLVM_LTO_CACHING_H
-#define LLVM_LTO_CACHING_H
-
-#include "llvm/LTO/LTO.h"
-
-namespace llvm {
-namespace lto {
-
-/// 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 directory and
-/// file callback. This function also creates the cache directory if it does not
-/// already exist.
-Expected<NativeObjectCache> localCache(StringRef CacheDirectoryPath,
-                                       AddBufferFn AddBuffer);
-
-} // namespace lto
-} // namespace llvm
-
-#endif

llvm/include/llvm/LTO/LTO.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 @@ private:
   }
 };
 
-/// 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/legacy/LTOCodeGenerator.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/Support/Caching.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

llvm/lib/LTO/CMakeLists.txt

@@ -1,5 +1,4 @@
 add_llvm_component_library(LLVMLTO
-  Caching.cpp
   LTO.cpp
   LTOBackend.cpp
   LTOModule.cpp

llvm/lib/LTO/LTOCodeGenerator.cpp

@@ -245,8 +245,7 @@ bool LTOCodeGenerator::compileOptimizedToFile(const char **Name) {
   // make unique temp output file to put generated code
   SmallString<128> Filename;
 
-  auto AddStream =
+  auto AddStream = [&](size_t Task) -> std::unique_ptr<NativeObjectStream> {
-      [&](size_t Task) -> std::unique_ptr<lto::NativeObjectStream> {
     StringRef Extension(Config.CGFileType == CGFT_AssemblyFile ? "s" : "o");
 
     int FD;
@@ -255,7 +254,7 @@ bool LTOCodeGenerator::compileOptimizedToFile(const char **Name) {
     if (EC)
       emitError(EC.message());
 
-    return std::make_unique<lto::NativeObjectStream>(
+    return std::make_unique<NativeObjectStream>(
         std::make_unique<llvm::raw_fd_ostream>(FD, true));
   };
 
@@ -557,7 +556,7 @@ bool LTOCodeGenerator::optimize() {
   return true;
 }
 
-bool LTOCodeGenerator::compileOptimized(lto::AddStreamFn AddStream,
+bool LTOCodeGenerator::compileOptimized(AddStreamFn AddStream,
                                         unsigned ParallelismLevel) {
   if (!this->determineTarget())
     return false;

llvm/lib/Support/CMakeLists.txt

@@ -123,6 +123,7 @@ add_llvm_component_library(LLVMSupport
   BranchProbability.cpp
   BuryPointer.cpp
   CachePruning.cpp
+  Caching.cpp
   circular_raw_ostream.cpp
   Chrono.cpp
   COM.cpp

llvm/lib/Support/Caching.cpp

@@ -1,4 +1,4 @@
-//===-Caching.cpp - LLVM Link Time Optimizer Cache Handling ---------------===//
+//===-Caching.cpp - LLVM File Cache Handling ------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
@@ -6,11 +6,11 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements the Caching for ThinLTO.
+// This file implements the Caching used by ThinLTO.
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/LTO/Caching.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/FileSystem.h"
@@ -26,13 +26,20 @@
 #endif
 
 using namespace llvm;
-using namespace llvm::lto;
 
-Expected<NativeObjectCache> lto::localCache(StringRef CacheDirectoryPath,
+Expected<NativeObjectCache> llvm::localCache(Twine CacheNameRef,
-                                            AddBufferFn AddBuffer) {
+                                             Twine TempFilePrefixRef,
-  if (std::error_code EC = sys::fs::create_directories(CacheDirectoryPath))
+                                             Twine CacheDirectoryPathRef,
+                                             AddBufferFn AddBuffer) {
+  if (std::error_code EC = sys::fs::create_directories(CacheDirectoryPathRef))
     return errorCodeToError(EC);
 
+  // Create local copies which are safely captured-by-copy in lambdas
+  SmallString<64> CacheName, TempFilePrefix, CacheDirectoryPath;
+  CacheNameRef.toVector(CacheName);
+  TempFilePrefixRef.toVector(TempFilePrefix);
+  CacheDirectoryPathRef.toVector(CacheDirectoryPath);
+
   return [=](unsigned Task, StringRef Key) -> AddStreamFn {
     // This choice of file name allows the cache to be pruned (see pruneCache()
     // in include/llvm/Support/CachePruning.h).
@@ -134,12 +141,13 @@ Expected<NativeObjectCache> lto::localCache(StringRef CacheDirectoryPath,
     return [=](size_t Task) -> std::unique_ptr<NativeObjectStream> {
       // Write to a temporary to avoid race condition
       SmallString<64> TempFilenameModel;
-      sys::path::append(TempFilenameModel, CacheDirectoryPath, "Thin-%%%%%%.tmp.o");
+      sys::path::append(TempFilenameModel, CacheDirectoryPath,
+                        TempFilePrefix + "-%%%%%%.tmp.o");
       Expected<sys::fs::TempFile> Temp = sys::fs::TempFile::create(
           TempFilenameModel, sys::fs::owner_read | sys::fs::owner_write);
       if (!Temp) {
         errs() << "Error: " << toString(Temp.takeError()) << "\n";
-        report_fatal_error("ThinLTO: Can't get a temporary file");
+        report_fatal_error(CacheName + ": Can't get a temporary file");
       }
 
       // This CacheStream will move the temporary file into the cache when done.

llvm/tools/gold/gold-plugin.cpp

@@ -1081,12 +1081,11 @@ static std::vector<std::pair<SmallString<128>, bool>> runLTO() {
   size_t MaxTasks = Lto->getMaxTasks();
   std::vector<std::pair<SmallString<128>, bool>> Files(MaxTasks);
 
-  auto AddStream =
+  auto AddStream = [&](size_t Task) -> std::unique_ptr<NativeObjectStream> {
-      [&](size_t Task) -> std::unique_ptr<lto::NativeObjectStream> {
     Files[Task].second = !SaveTemps;
     int FD = getOutputFileName(Filename, /* TempOutFile */ !SaveTemps,
                                Files[Task].first, Task);
-    return std::make_unique<lto::NativeObjectStream>(
+    return std::make_unique<NativeObjectStream>(
         std::make_unique<llvm::raw_fd_ostream>(FD, true));
   };
 
@@ -1096,7 +1095,7 @@ static std::vector<std::pair<SmallString<128>, bool>> runLTO() {
 
   NativeObjectCache Cache;
   if (!options::cache_dir.empty())
-    Cache = check(localCache(options::cache_dir, AddBuffer));
+    Cache = check(localCache("ThinLTO", "Thin", options::cache_dir, AddBuffer));
 
   check(Lto->run(AddStream, Cache));
 

llvm/tools/llvm-lto/llvm-lto.cpp

@@ -1097,8 +1097,7 @@ int main(int argc, char **argv) {
         error("writing merged module failed.");
     }
 
-    auto AddStream =
+    auto AddStream = [&](size_t Task) -> std::unique_ptr<NativeObjectStream> {
-        [&](size_t Task) -> std::unique_ptr<lto::NativeObjectStream> {
       std::string PartFilename = OutputFilename;
       if (Parallelism != 1)
         PartFilename += "." + utostr(Task);
@@ -1108,7 +1107,7 @@ int main(int argc, char **argv) {
           std::make_unique<raw_fd_ostream>(PartFilename, EC, sys::fs::OF_None);
       if (EC)
         error("error opening the file '" + PartFilename + "': " + EC.message());
-      return std::make_unique<lto::NativeObjectStream>(std::move(S));
+      return std::make_unique<NativeObjectStream>(std::move(S));
     };
 
     if (!CodeGen.compileOptimized(AddStream, Parallelism))

llvm/tools/llvm-lto2/llvm-lto2.cpp

@@ -19,10 +19,10 @@
 #include "llvm/CodeGen/CommandFlags.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/IR/DiagnosticPrinter.h"
-#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Passes/PassPlugin.h"
 #include "llvm/Remarks/HotnessThresholdParser.h"
+#include "llvm/Support/Caching.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/InitLLVM.h"
@@ -362,14 +362,13 @@ static int run(int argc, char **argv) {
   if (HasErrors)
     return 1;
 
-  auto AddStream =
+  auto AddStream = [&](size_t Task) -> std::unique_ptr<NativeObjectStream> {
-      [&](size_t Task) -> std::unique_ptr<lto::NativeObjectStream> {
     std::string Path = OutputFilename + "." + utostr(Task);
 
     std::error_code EC;
     auto S = std::make_unique<raw_fd_ostream>(Path, EC, sys::fs::OF_None);
     check(EC, Path);
-    return std::make_unique<lto::NativeObjectStream>(std::move(S));
+    return std::make_unique<NativeObjectStream>(std::move(S));
   };
 
   auto AddBuffer = [&](size_t Task, std::unique_ptr<MemoryBuffer> MB) {
@@ -378,7 +377,8 @@ static int run(int argc, char **argv) {
 
   NativeObjectCache Cache;
   if (!CacheDir.empty())
-    Cache = check(localCache(CacheDir, AddBuffer), "failed to create cache");
+    Cache = check(localCache("ThinLTO", "Thin", CacheDir, AddBuffer),
+                  "failed to create cache");
 
   check(Lto.run(AddStream, Cache), "LTO::run failed");
   return 0;