Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...

1 files changed, 1 insertions, 96 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 42f25952edd9..346616c0092c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -457,108 +457,13 @@ void daemonize(const char *name, ...)
         /* Become as one with the init task */
 
         daemonize_fs_struct();
-        exit_files(current);
-        current->files = init_task.files;
-        atomic_inc(&current->files->count);
+        daemonize_descriptors();
 
         reparent_to_kthreadd();
 }
 
 EXPORT_SYMBOL(daemonize);
 
-static void close_files(struct files_struct * files)
-{
-        int i, j;
-        struct fdtable *fdt;
-
-        j = 0;
-
-        /*
-         * It is safe to dereference the fd table without RCU or
-         * ->file_lock because this is the last reference to the
-         * files structure.  But use RCU to shut RCU-lockdep up.
-         */
-        rcu_read_lock();
-        fdt = files_fdtable(files);
-        rcu_read_unlock();
-        for (;;) {
-                unsigned long set;
-                i = j * BITS_PER_LONG;
-                if (i >= fdt->max_fds)
-                        break;
-                set = fdt->open_fds[j++];
-                while (set) {
-                        if (set & 1) {
-                                struct file * file = xchg(&fdt->fd[i], NULL);
-                                if (file) {
-                                        filp_close(file, files);
-                                        cond_resched();
-                                }
-                        }
-                        i++;
-                        set >>= 1;
-                }
-        }
-}
-
-struct files_struct *get_files_struct(struct task_struct *task)
-{
-        struct files_struct *files;
-
-        task_lock(task);
-        files = task->files;
-        if (files)
-                atomic_inc(&files->count);
-        task_unlock(task);
-
-        return files;
-}
-
-void put_files_struct(struct files_struct *files)
-{
-        struct fdtable *fdt;
-
-        if (atomic_dec_and_test(&files->count)) {
-                close_files(files);
-                /*
-                 * Free the fd and fdset arrays if we expanded them.
-                 * If the fdtable was embedded, pass files for freeing
-                 * at the end of the RCU grace period. Otherwise,
-                 * you can free files immediately.
-                 */
-                rcu_read_lock();
-                fdt = files_fdtable(files);
-                if (fdt != &files->fdtab)
-                        kmem_cache_free(files_cachep, files);
-                free_fdtable(fdt);
-                rcu_read_unlock();
-        }
-}
-
-void reset_files_struct(struct files_struct *files)
-{
-        struct task_struct *tsk = current;
-        struct files_struct *old;
-
-        old = tsk->files;
-        task_lock(tsk);
-        tsk->files = files;
-        task_unlock(tsk);
-        put_files_struct(old);
-}
-
-void exit_files(struct task_struct *tsk)
-{
-        struct files_struct * files = tsk->files;
-
-        if (files) {
-                task_lock(tsk);
-                tsk->files = NULL;
-                task_unlock(tsk);
-                put_files_struct(files);
-        }
-}
-
 #ifdef CONFIG_MM_OWNER
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.