[gcc r14-1569] libstdc++: Use copy_file_range for filesystem::copy_file

[gcc r14-1569] libstdc++: Use copy_file_range for filesystem::copy_file

[Jonathan Wakely]

https://gcc.gnu.org/g:d87caacf8e2df563afda85f3a5b7b852e08b6b2c

commit r14-1569-gd87caacf8e2df563afda85f3a5b7b852e08b6b2c
Author: Jannik Glückert <jannik.glueckert@gmail.com>
Date:   Wed Mar 8 19:37:43 2023 +0100

    libstdc++: Use copy_file_range for filesystem::copy_file
    
    copy_file_range is a recent-ish syscall for copying files. It is similar
    to sendfile but allows filesystem-specific optimizations. Common are:
    Reflinks: BTRFS, XFS, ZFS (does not implement the syscall yet)
    Server-side copy: NFS, SMB, Ceph
    
    If copy_file_range is not available for the given files, fall back to
    sendfile / userspace copy.
    
    libstdc++-v3/ChangeLog:
    
            * acinclude.m4 (_GLIBCXX_USE_COPY_FILE_RANGE): Define.
            * config.h.in: Regenerate.
            * configure: Regenerate.
            * src/filesystem/ops-common.h (copy_file_copy_file_range):
            Define new function.
            (do_copy_file): Use it.
    
    Signed-off-by: Jannik Glückert <jannik.glueckert@gmail.com>

Diff:
---
 libstdc++-v3/acinclude.m4                | 20 +++++++++++
 libstdc++-v3/config.h.in                 |  3 ++
 libstdc++-v3/configure                   | 62 ++++++++++++++++++++++++++++++++
 libstdc++-v3/src/filesystem/ops-common.h | 56 +++++++++++++++++++++++++++++
 4 files changed, 141 insertions(+)

diff --git a/libstdc++-v3/acinclude.m4 b/libstdc++-v3/acinclude.m4
index 1920444e5cd..13c3966b317 100644
--- a/libstdc++-v3/acinclude.m4
+++ b/libstdc++-v3/acinclude.m4
@@ -4954,6 +4954,7 @@ dnl  _GLIBCXX_USE_UTIMENSAT
 dnl  _GLIBCXX_USE_ST_MTIM
 dnl  _GLIBCXX_USE_FCHMOD
 dnl  _GLIBCXX_USE_FCHMODAT
+dnl  _GLIBCXX_USE_COPY_FILE_RANGE
 dnl  _GLIBCXX_USE_SENDFILE
 dnl  HAVE_LINK
 dnl  HAVE_LSEEK
@@ -5152,6 +5153,25 @@ dnl
   if test $glibcxx_cv_truncate = yes; then
     AC_DEFINE(HAVE_TRUNCATE, 1, [Define if truncate is available in <unistd.h>.])
   fi
+dnl
+  AC_CACHE_CHECK([for copy_file_range that can copy files],
+    glibcxx_cv_copy_file_range, [dnl
+    case "${target_os}" in
+      linux*)
+	GCC_TRY_COMPILE_OR_LINK(
+	  [#include <unistd.h>],
+	  [copy_file_range(1, nullptr, 2, nullptr, 1, 0);],
+	  [glibcxx_cv_copy_file_range=yes],
+	  [glibcxx_cv_copy_file_range=no])
+	;;
+      *)
+	glibcxx_cv_copy_file_range=no
+	;;
+    esac
+  ])
+  if test $glibcxx_cv_copy_file_range = yes; then
+    AC_DEFINE(_GLIBCXX_USE_COPY_FILE_RANGE, 1, [Define if copy_file_range is available in <unistd.h>.])
+  fi
 dnl
   AC_CACHE_CHECK([for sendfile that can copy files],
     glibcxx_cv_sendfile, [dnl
diff --git a/libstdc++-v3/config.h.in b/libstdc++-v3/config.h.in
index 99ce682670e..e156650792e 100644
--- a/libstdc++-v3/config.h.in
+++ b/libstdc++-v3/config.h.in
@@ -971,6 +971,9 @@
 /* Defined if clock_gettime has realtime clock support. */
 #undef _GLIBCXX_USE_CLOCK_REALTIME
 
+/* Define if copy_file_range is available in <unistd.h>. */
+#undef _GLIBCXX_USE_COPY_FILE_RANGE
+
 /* Define if ISO/IEC TR 24733 decimal floating point types are supported on
    this host. */
 #undef _GLIBCXX_USE_DECIMAL_FLOAT
diff --git a/libstdc++-v3/configure b/libstdc++-v3/configure
index 50a7c30665b..47db64ff8fb 100755
--- a/libstdc++-v3/configure
+++ b/libstdc++-v3/configure
@@ -71279,6 +71279,68 @@ $as_echo "$glibcxx_cv_truncate" >&6; }
 
 $as_echo "#define HAVE_TRUNCATE 1" >>confdefs.h
 
+  fi
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for copy_file_range that can copy files" >&5
+$as_echo_n "checking for copy_file_range that can copy files... " >&6; }
+if ${glibcxx_cv_copy_file_range+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+      case "${target_os}" in
+      linux*)
+	if test x$gcc_no_link = xyes; then
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <unistd.h>
+int
+main ()
+{
+copy_file_range(1, nullptr, 2, nullptr, 1, 0);
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_cxx_try_compile "$LINENO"; then :
+  glibcxx_cv_copy_file_range=yes
+else
+  glibcxx_cv_copy_file_range=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+else
+  if test x$gcc_no_link = xyes; then
+  as_fn_error $? "Link tests are not allowed after GCC_NO_EXECUTABLES." "$LINENO" 5
+fi
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <unistd.h>
+int
+main ()
+{
+copy_file_range(1, nullptr, 2, nullptr, 1, 0);
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_cxx_try_link "$LINENO"; then :
+  glibcxx_cv_copy_file_range=yes
+else
+  glibcxx_cv_copy_file_range=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+	;;
+      *)
+	glibcxx_cv_copy_file_range=no
+	;;
+    esac
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $glibcxx_cv_copy_file_range" >&5
+$as_echo "$glibcxx_cv_copy_file_range" >&6; }
+  if test $glibcxx_cv_copy_file_range = yes; then
+
+$as_echo "#define _GLIBCXX_USE_COPY_FILE_RANGE 1" >>confdefs.h
+
   fi
   { $as_echo "$as_me:${as_lineno-$LINENO}: checking for sendfile that can copy files" >&5
 $as_echo_n "checking for sendfile that can copy files... " >&6; }
diff --git a/libstdc++-v3/src/filesystem/ops-common.h b/libstdc++-v3/src/filesystem/ops-common.h
index 36444388208..7c8d3a694e2 100644
--- a/libstdc++-v3/src/filesystem/ops-common.h
+++ b/libstdc++-v3/src/filesystem/ops-common.h
@@ -49,6 +49,9 @@
 #ifdef NEED_DO_COPY_FILE
 # include <filesystem>
 # include <ext/stdio_filebuf.h>
+# ifdef _GLIBCXX_USE_COPY_FILE_RANGE
+#  include <unistd.h> // copy_file_range
+# endif
 # ifdef _GLIBCXX_USE_SENDFILE
 #  include <sys/sendfile.h> // sendfile
 #  include <unistd.h> // lseek
@@ -359,6 +362,32 @@ _GLIBCXX_BEGIN_NAMESPACE_FILESYSTEM
   }
 
 #ifdef NEED_DO_COPY_FILE
+#ifdef _GLIBCXX_USE_COPY_FILE_RANGE
+  bool
+  copy_file_copy_file_range(int fd_in, int fd_out, size_t length) noexcept
+  {
+    // a zero-length file is either empty, or not copyable by this syscall
+    // return early to avoid the syscall cost
+    if (length == 0)
+      {
+	errno = EINVAL;
+	return false;
+      }
+    size_t bytes_left = length;
+    off64_t off_in = 0, off_out = 0;
+    ssize_t bytes_copied;
+    do
+      {
+	bytes_copied = ::copy_file_range(fd_in, &off_in, fd_out, &off_out,
+					 bytes_left, 0);
+	bytes_left -= bytes_copied;
+      }
+    while (bytes_left > 0 && bytes_copied > 0);
+    if (bytes_copied < 0)
+      return false;
+    return true;
+  }
+#endif
 #if defined _GLIBCXX_USE_SENDFILE && ! defined _GLIBCXX_FILESYSTEM_IS_WINDOWS
   bool
   copy_file_sendfile(int fd_in, int fd_out, size_t length) noexcept
@@ -529,6 +558,33 @@ _GLIBCXX_BEGIN_NAMESPACE_FILESYSTEM
 
     bool has_copied = false;
 
+#ifdef _GLIBCXX_USE_COPY_FILE_RANGE
+    if (!has_copied)
+      has_copied = copy_file_copy_file_range(in.fd, out.fd, from_st->st_size);
+    if (!has_copied)
+      {
+	// EINVAL: src and dst are the same file (this is not cheaply
+	// detectable from userspace)
+	// EINVAL: copy_file_range is unsupported for this file type by the
+	// underlying filesystem
+	// ENOTSUP: undocumented, can arise with old kernels and NFS
+	// EOPNOTSUPP: filesystem does not implement copy_file_range
+	// ETXTBSY: src or dst is an active swapfile (nonsensical, but allowed
+	// with normal copying)
+	// EXDEV: src and dst are on different filesystems that do not support
+	// cross-fs copy_file_range
+	// ENOENT: undocumented, can arise with CIFS
+	// ENOSYS: unsupported by kernel or blocked by seccomp
+	if (errno != EINVAL && errno != ENOTSUP && errno != EOPNOTSUPP
+	      && errno != ETXTBSY && errno != EXDEV && errno != ENOENT
+	      && errno != ENOSYS)
+	  {
+	    ec.assign(errno, std::generic_category());
+	    return false;
+	  }
+      }
+#endif
+
 #if defined _GLIBCXX_USE_SENDFILE && ! defined _GLIBCXX_FILESYSTEM_IS_WINDOWS
     if (!has_copied)
       has_copied = copy_file_sendfile(in.fd, out.fd, from_st->st_size);