flag parameters: pipe

This patch introduces the new syscall pipe2 which is like pipe but it also
takes an additional parameter which takes a flag value.  This patch implements
the handling of O_CLOEXEC for the flag.  I did not add support for the new
syscall for the architectures which have a special sys_pipe implementation.  I
think the maintainers of those archs have the chance to go with the unified
implementation but that's up to them.

The implementation introduces do_pipe_flags.  I did that instead of changing
all callers of do_pipe because some of the callers are written in assembler.
I would probably screw up changing the assembly code.  To avoid breaking code
do_pipe is now a small wrapper around do_pipe_flags.  Once all callers are
changed over to do_pipe_flags the old do_pipe function can be removed.

The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>

#ifndef __NR_pipe2
# ifdef __x86_64__
#  define __NR_pipe2 293
# elif defined __i386__
#  define __NR_pipe2 331
# else
#  error "need __NR_pipe2"
# endif
#endif

int
main (void)
{
  int fd[2];
  if (syscall (__NR_pipe2, fd, 0) != 0)
    {
      puts ("pipe2(0) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      int coe = fcntl (fd[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if (coe & FD_CLOEXEC)
        {
          printf ("pipe2(0) set close-on-exit for fd[%d]\n", i);
          return 1;
        }
    }
  close (fd[0]);
  close (fd[1]);

  if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0)
    {
      puts ("pipe2(O_CLOEXEC) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      int coe = fcntl (fd[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if ((coe & FD_CLOEXEC) == 0)
        {
          printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i);
          return 1;
        }
    }
  close (fd[0]);
  close (fd[1]);

  puts ("OK");

  return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 4 insertions, 0 deletions

diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h
index a1f6383bf695..748a05c77da4 100644
--- a/include/asm-x86/unistd_32.h
+++ b/include/asm-x86/unistd_32.h
@@ -336,6 +336,7 @@
 #define __NR_eventfd2           328
 #define __NR_epoll_create2      329
 #define __NR_dup3               330
+#define __NR_pipe2              331
 
 #ifdef __KERNEL__
 
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index f0fb2bd40cdb..d2284b43ad58 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -649,6 +649,8 @@ __SYSCALL(__NR_eventfd2, sys_eventfd2)
 __SYSCALL(__NR_epoll_create2, sys_epoll_create2)
 #define __NR_dup3                               292
 __SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2                              293
+__SYSCALL(__NR_pipe2, sys_pipe2)
 
 
 #ifndef __NO_STUBS
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e5e6a244096c..0e80cd717d32 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1777,6 +1777,7 @@ static inline void allow_write_access(struct file *file)
                 atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
 extern int do_pipe(int *);
+extern int do_pipe_flags(int *, int);
 extern struct file *create_read_pipe(struct file *f);
 extern struct file *create_write_pipe(void);
 extern void free_write_pipe(struct file *);