lseek: avoid SEEK_HOLE bugs in FreeBSD, macOS

This attempts to fix <https://bugs.gnu.org/61386>, a bug in GNU cp
caused by a serious data corruption bug in FreeBSD and macOS.
* doc/posix-functions/lseek.texi: Mention the bug.
* lib/unistd.in.h (SEEK_DATA, SEEK_HOLE): Undef in macOS < 13 and
FreeBSD < 14.  FreeBSD fixed the bug sometime during FreeBSD 13
<https://bugs.freebsd.org/256205>, so the "FreeBSD < 14" is
conservative.  It’s unknown when Apple will fix macOS so use
macOS "9999" as a placeholder.
* m4/lseek.m4 (gl_FUNC_LSEEK): Replace lseek if on one of the
above platforms.

ChangeLog

@@ -1,3 +1,17 @@
+2023-02-23  Paul Eggert  <eggert@cs.ucla.edu>
+
+	lseek: avoid SEEK_HOLE bugs in FreeBSD, macOS
+	This attempts to fix <https://bugs.gnu.org/61386>, a bug in GNU cp
+	caused by a serious data corruption bug in FreeBSD and macOS.
+	* doc/posix-functions/lseek.texi: Mention the bug.
+	* lib/unistd.in.h (SEEK_DATA, SEEK_HOLE): Undef in macOS < 13 and
+	FreeBSD < 14.  FreeBSD fixed the bug sometime during FreeBSD 13
+	<https://bugs.freebsd.org/256205>, so the "FreeBSD < 14" is
+	conservative.  It’s unknown when Apple will fix macOS so use
+	macOS "9999" as a placeholder.
+	* m4/lseek.m4 (gl_FUNC_LSEEK): Replace lseek if on one of the
+	above platforms.
+
 2023-02-18  Bruno Haible  <bruno@clisp.org>
 
 	configmake: Add support for $build_os != $host_os.

doc/posix-functions/lseek.texi

@@ -37,4 +37,9 @@ IRIX 6.5.
 @item
 Some systems do not support @code{SEEK_DATA} and @code{SEEK_HOLE}:
 AIX, HP-UX, Microsoft Windows, NetBSD, OpenBSD.
+@item
+Some systems have a buggy @code{SEEK_DATA} and @code{SEEK_HOLE},
+and Gnulib works around the problem via @code{#undef SEEK_DATA}
+and @code{#undef SEEK_HOLE}:
+FreeBSD 13, macOS 12.
 @end itemize

lib/unistd.in.h

@@ -40,6 +40,24 @@
 # undef _GL_INCLUDING_UNISTD_H
 #endif
 
+/* Avoid lseek bugs in FreeBSD, macOS <https://bugs.gnu.org/61386>.
+   This bug is fixed after FreeBSD 13; see <https://bugs.freebsd.org/256205>.
+   Use macOS "9999" to stand for a future fixed macOS version.  */
+#if defined __FreeBSD__ && __FreeBSD__ < 14
+# undef SEEK_DATA
+# undef SEEK_HOLE
+#elif defined __APPLE__ && defined __MACH__ && defined SEEK_DATA
+# ifdef __ENVIRONMENT_MAC_OS_X_VERSION_MIN_REQUIRED__
+#  include <AvailabilityMacros.h>
+# endif
+# if (!defined MAC_OS_X_VERSION_MIN_REQUIRED \
+      || MAC_OS_X_VERSION_MIN_REQUIRED < 99990000)
+#  include <sys/fcntl.h> /* It also defines the two macros.  */
+#  undef SEEK_DATA
+#  undef SEEK_HOLE
+# endif
+#endif
+
 /* Get all possible declarations of gethostname().  */
 #if @GNULIB_GETHOSTNAME@ && @UNISTD_H_HAVE_WINSOCK2_H@ \
   && !defined _GL_INCLUDING_WINSOCK2_H

m4/lseek.m4

@@ -1,4 +1,4 @@
-# lseek.m4 serial 12
+# lseek.m4 serial 13
 dnl Copyright (C) 2007, 2009-2023 Free Software Foundation, Inc.
 dnl This file is free software; the Free Software Foundation
 dnl gives unlimited permission to copy and/or distribute it,
@@ -70,9 +70,29 @@ AC_DEFUN([gl_FUNC_LSEEK],
     REPLACE_LSEEK=1
   fi
 
-  dnl macOS SEEK_DATA is incompatible with other platforms.
-  case $host_os in
-    darwin*)
-      REPLACE_LSEEK=1;;
-  esac
+  AS_IF([test $REPLACE_LSEEK = 0],
+    [AC_CACHE_CHECK([whether SEEK_DATA works but is incompatible with GNU],
+       [gl_cv_func_lseek_works_but_incompatible],
+       [AC_PREPROC_IFELSE(
+          [AC_LANG_SOURCE(
+             dnl Use macOS "9999" to stand for a future fixed macOS version.
+             dnl See ../lib/unistd.in.h and <https://bugs.gnu.org/61386>.
+             [[#include <unistd.h>
+               #if defined __APPLE__ && defined __MACH__ && defined SEEK_DATA
+               # ifdef __ENVIRONMENT_MAC_OS_X_VERSION_MIN_REQUIRED__
+               #  include <AvailabilityMacros.h>
+               # endif
+               # if 99990000 <= MAC_OS_X_VERSION_MIN_REQUIRED
+               #  define LSEEK_WORKS_BUT_IS_INCOMPATIBLE_WITH_GNU
+               # endif
+               #endif
+               #ifndef LSEEK_WORKS_BUT_IS_INCOMPATIBLE_WITH_GNU
+                #error "No need to work around the bug"
+               #endif
+             ]])],
+          [gl_cv_func_lseek_works_but_incompatible=yes],
+          [gl_cv_func_lseek_works_but_incompatible=no])])
+     if test "$gl_cv_func_lseek_works_but_incompatible" = yes; then
+       REPLACE_LSEEK=1
+     fi])
 ])