Re: [PATCH 3/3] proc: simplify proc_task_readdir/first_tid paths

[Eric W. Biederman]

Oleg Nesterov <oleg@xxxxxxxxxx> writes:

> proc_task_readdir() does not really need "leader", first_tid()
> has to revalidate it anyway. Just pass proc_pid(inode) to
> first_tid() instead, it can do pid_task(PIDTYPE_PID) itself
> and read ->group_leader only if necessary.
>
> Note: I am not sure proc_task_readdir() really needs the initial
> -ENOENT check, but this is what the current code does.

This looks like a nice cleanup.

We would need either -ENOENT or a return of 0 and an empty directory at
the least.  We need the check so that empty directories don't have "."
and ".." entries.

Eric


> Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
> ---
>  fs/proc/base.c |   46 ++++++++++++++++------------------------------
>  1 files changed, 16 insertions(+), 30 deletions(-)
>
> diff --git a/fs/proc/base.c b/fs/proc/base.c
> index bed1096..dbc4dae 100644
> --- a/fs/proc/base.c
> +++ b/fs/proc/base.c
> @@ -3173,34 +3173,35 @@ out_no_task:
>   * In the case of a seek we start with the leader and walk nr
>   * threads past it.
>   */
> -static struct task_struct *first_tid(struct task_struct *leader,
> -		int tid, int nr, struct pid_namespace *ns)
> +static struct task_struct *first_tid(struct pid *pid, int tid,
> +					int nr, struct pid_namespace *ns)
>  {
> -	struct task_struct *pos;
> +	struct task_struct *pos, *task;
>  
>  	rcu_read_lock();
> -	/* Attempt to start with the pid of a thread */
> +	task = pid_task(pid, PIDTYPE_PID);
Elegant.  If we can from the task from the pid the task is hashed
and still alive when we are in the rcu critical section.

> +	if (!task)
> +		goto fail;
> +
> +	/* Attempt to start with the tid of a thread */
>  	if (tid && (nr > 0)) {
>  		pos = find_task_by_pid_ns(tid, ns);
> -		if (pos && (pos->group_leader == leader))
> +		if (pos && same_thread_group(pos, task))

Sigh this reminds me we need to figure out how to kill task->pid and
task->tgid, which I assume means fixing same_thread_group.

>  			goto found;
>  	}
>  
>  	/* If nr exceeds the number of threads there is nothing todo */
> -	if (nr && nr >= get_nr_threads(leader))
> -		goto fail;
> -	/* It could be unhashed before we take rcu lock */
> -	if (!pid_alive(leader))
> +	if (nr && nr >= get_nr_threads(task))
>  		goto fail;

>  	/* If we haven't found our starting place yet start
>  	 * with the leader and walk nr threads forward.
>  	 */
> -	pos = leader;
> +	pos = task = task->group_leader;
>  	do {
>  		if (nr-- <= 0)
>  			goto found;
> -	} while_each_thread(leader, pos);
> +	} while_each_thread(task, pos);
>  fail:
>  	pos = NULL;
>  	goto out;
> @@ -3247,26 +3248,13 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
>  {
>  	struct dentry *dentry = filp->f_path.dentry;
>  	struct inode *inode = dentry->d_inode;
> -	struct task_struct *leader = NULL;
>  	struct task_struct *task;
> -	int retval = -ENOENT;
>  	ino_t ino;
>  	int tid;
>  	struct pid_namespace *ns;
>  
> -	task = get_proc_task(inode);
> -	if (!task)
> -		goto out_no_task;
> -	rcu_read_lock();
> -	if (pid_alive(task)) {
> -		leader = task->group_leader;
> -		get_task_struct(leader);
> -	}
> -	rcu_read_unlock();
> -	put_task_struct(task);
> -	if (!leader)
> -		goto out_no_task;
> -	retval = 0;


> +	if (!pid_task(proc_pid(inode), PIDTYPE_PID))
> +		return -ENOENT;

Strictly speaking this call to pid_task needs to be in a rcu critical
section.

>  	switch ((unsigned long)filp->f_pos) {
>  	case 0:
> @@ -3289,7 +3277,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
>  	ns = filp->f_dentry->d_sb->s_fs_info;
>  	tid = (int)filp->f_version;
>  	filp->f_version = 0;
> -	for (task = first_tid(leader, tid, filp->f_pos - 2, ns);
> +	for (task = first_tid(proc_pid(inode), tid, filp->f_pos - 2, ns);
>  	     task;
>  	     task = next_tid(task), filp->f_pos++) {
>  		tid = task_pid_nr_ns(task, ns);
> @@ -3302,9 +3290,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
>  		}
>  	}
>  out:
> -	put_task_struct(leader);
> -out_no_task:
> -	return retval;
> +	return 0;
>  }
>  
>  static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/