posix: Add posix_spawn_file_actions_addclosefrom_np

This patch adds a way to close a range of file descriptors on
posix_spawn as a new file action.  The API is similar to the one
provided by Solaris 11 [1], where the file action causes the all open
file descriptors greater than or equal to input on to be closed when
the new process is spawned.

The function posix_spawn_file_actions_addclosefrom_np is safe to be
implemented by iterating over /proc/self/fd, since the Linux spawni.c
helper process does not use CLONE_FILES, so its has own file descriptor
table and any failure (in /proc operation) aborts the process creation
and returns an error to the caller.

I am aware that this file action might be redundant to the current
approach of POSIX in promoting O_CLOEXEC in more interfaces. However
O_CLOEXEC is still not the default and for some specific usages, the
caller needs to close all possible file descriptors to avoid them
leaking.  Some examples are CPython (discussed in BZ#10353) and OpenJDK
jspawnhelper [2] (where OpenJDK spawns a helper process to exactly
closes all file descriptors).  Most likely any environment which calls
functions that might open file descriptor under the hood and aim to use
posix_spawn might face the same requirement.

Checked on x86_64-linux-gnu and i686-linux-gnu on kernel 5.11 and 4.15.

[1] https://docs.oracle.com/cd/E36784_01/html/E36874/posix-spawn-file-actions-addclosefrom-np-3c.html
[2] https://github.com/openjdk/jdk/blob/master/src/java.base/unix/native/libjava/childproc.c#L82

1 files changed, 19 insertions, 15 deletions

diff --git a/sysdeps/unix/sysv/linux/spawni.c b/sysdeps/unix/sysv/linux/spawni.c
index 3b435e6c86..f7e7353a05 100644
--- a/sysdeps/unix/sysv/linux/spawni.c
+++ b/sysdeps/unix/sysv/linux/spawni.c
@@ -16,22 +16,16 @@
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
-#include <spawn.h>
-#include <fcntl.h>
-#include <paths.h>
-#include <string.h>
-#include <sys/resource.h>
-#include <sys/wait.h>
-#include <sys/param.h>
-#include <sys/mman.h>
-#include <not-cancel.h>
+#include <internal-signals.h>
+#include <ldsodefs.h>
 #include <local-setxid.h>
+#include <not-cancel.h>
+#include <paths.h>
 #include <shlib-compat.h>
-#include <pthreadP.h>
-#include <dl-sysdep.h>
-#include <libc-pointer-arith.h>
-#include <ldsodefs.h>
-#include "spawn_int.h"
+#include <spawn.h>
+#include <spawn_int.h>
+#include <sysdep.h>
+#include <sys/resource.h>
 
 /* The Linux implementation of posix_spawn{p} uses the clone syscall directly
    with CLONE_VM and CLONE_VFORK flags and an allocated stack.  The new stack
@@ -280,6 +274,14 @@ __spawni_child (void *arguments)
 	      if (__fchdir (action->action.fchdir_action.fd) != 0)
 		goto fail;
 	      break;
+
+	    case spawn_do_closefrom:
+	      {
+		int lowfd = action->action.closefrom_action.from;
+	        int r = INLINE_SYSCALL_CALL (close_range, lowfd, ~0U, 0);
+		if (r != 0 && !__closefrom_fallback (lowfd, false))
+		  goto fail;
+	      } break;
 	    }
 	}
     }
@@ -344,7 +346,9 @@ __spawnix (pid_t * pid, const char *file,
   /* We need at least a few pages in case the compiler's stack checking is
      enabled.  In some configs, it is known to use at least 24KiB.  We use
      32KiB to be "safe" from anything the compiler might do.  Besides, the
-     extra pages won't actually be allocated unless they get used.  */
+     extra pages won't actually be allocated unless they get used.
+     It also acts the slack for spawn_closefrom (including MIPS64 getdents64
+     where it might use about 1k extra stack space).  */
   argv_size += (32 * 1024);
   size_t stack_size = ALIGN_UP (argv_size, GLRO(dl_pagesize));
   void *stack = __mmap (NULL, stack_size, prot,