Implement sys::fs::copy_file using the macOS copyfile(3) API

to support APFS clones.

This patch adds a Darwin-specific implementation of
llvm::sys::fs::copy_file() that uses the macOS copyfile(3) API to
support APFS copy-on-write clones, which should be faster and much
more space efficient.

https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/APFS_Guide/ToolsandAPIs/ToolsandAPIs.html

Differential Revision: https://reviews.llvm.org/D60802

This reapplies 358628 with an additional bugfix handling the case
where the destination file already exists. (Caught by the clang testsuite).

llvm-svn: 358716

diff --git a/llvm/lib/Support/Path.cpp b/llvm/lib/Support/Path.cpp
index 902df74..9466591 100644 (file)
--- a/llvm/lib/Support/Path.cpp
+++ b/llvm/lib/Support/Path.cpp
@@ -935,6 +935,7 @@ std::error_code create_directories(const Twine &Path, bool IgnoreExisting,
   return create_directory(P, IgnoreExisting, Perms);
 }
 
+#ifndef __APPLE__
 static std::error_code copy_file_internal(int ReadFD, int WriteFD) {
   const size_t BufSize = 4096;
   char *Buf = new char[BufSize];
@@ -988,6 +989,7 @@ std::error_code copy_file(const Twine &From, int ToFD) {
 
   return EC;
 }
+#endif
 
 ErrorOr<MD5::MD5Result> md5_contents(int FD) {
   MD5 Hash;

diff --git a/llvm/lib/Support/Unix/Path.inc b/llvm/lib/Support/Unix/Path.inc
index 05ccc6c..fbe3ed1 100644 (file)
--- a/llvm/lib/Support/Unix/Path.inc
+++ b/llvm/lib/Support/Unix/Path.inc
@@ -37,6 +37,7 @@
 #ifdef __APPLE__
 #include <mach-o/dyld.h>
 #include <sys/attr.h>
+#include <copyfile.h>
 #elif defined(__DragonFly__)
 #include <sys/mount.h>
 #endif
@@ -1113,5 +1114,52 @@ void system_temp_directory(bool ErasedOnReboot, SmallVectorImpl<char> &Result) {
 
 } // end namespace path
 
+namespace fs {
+
+#ifdef __APPLE__
+/// This implementation tries to perform an APFS CoW clone of the file,
+/// which can be much faster and uses less space.
+std::error_code copy_file(const Twine &From, const Twine &To) {
+  uint32_t Flag = COPYFILE_DATA;
+  if (__builtin_available(macos 10.12, *)) {
+    bool IsSymlink;
+    if (std::error_code Error = is_symlink_file(From, IsSymlink))
+      return Error;
+    // COPYFILE_CLONE clones the symlink instead of following it
+    // and returns EEXISTS if the target file already exists.
+    if (!IsSymlink && !exists(To))
+      Flag = COPYFILE_CLONE;
+  }
+
+  int Status =
+      copyfile(From.str().c_str(), To.str().c_str(), /* State */ NULL, Flag);
+
+  if (Status == 0)
+    return std::error_code();
+  return std::error_code(errno, std::generic_category());
+}
+
+/// This implementation tries to perform an APFS CoW clone of the file,
+/// which can be much faster and uses less space.
+std::error_code copy_file(const Twine &From, int ToFD) {
+  int ReadFD;
+  if (std::error_code EC = openFileForRead(From, ReadFD, OF_None))
+    return EC;
+
+  uint32_t Flag = COPYFILE_DATA;
+  if (__builtin_available(macos 10.12, *))
+    Flag = COPYFILE_CLONE;
+
+  int Status = fcopyfile(ReadFD, ToFD, /*State*/ NULL, Flag);
+
+  close(ReadFD);
+  if (Status == 0)
+    return std::error_code();
+  return std::error_code(errno, std::generic_category());
+}
+#endif
+
+} // end namespace fs
+
 } // end namespace sys
 } // end namespace llvm