Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754454AbXKSVqQ (ORCPT ); Mon, 19 Nov 2007 16:46:16 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751896AbXKSVqB (ORCPT ); Mon, 19 Nov 2007 16:46:01 -0500 Received: from ebiederm.dsl.xmission.com ([166.70.28.69]:53771 "EHLO ebiederm.dsl.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751424AbXKSVqA (ORCPT ); Mon, 19 Nov 2007 16:46:00 -0500 From: ebiederm@xmission.com (Eric W. Biederman) To: Oleg Nesterov Cc: Andrew Morton , Pavel Emelyanov , linux-kernel@vger.kernel.org Subject: [PATCH] proc: Remove races from proc_id_readdir() References: <20071117181549.GA1415@tv-sign.ru> <20071118142047.GA360@tv-sign.ru> <20071119182937.GA89@tv-sign.ru> Date: Mon, 19 Nov 2007 14:44:52 -0700 In-Reply-To: <20071119182937.GA89@tv-sign.ru> (Oleg Nesterov's message of "Mon, 19 Nov 2007 21:29:37 +0300") Message-ID: User-Agent: Gnus/5.110006 (No Gnus v0.6) Emacs/21.4 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4013 Lines: 128 Oleg noticed that the call of task_pid_nr_ns() in proc_pid_readdir is racy with respect to tasks exiting. After a bit of examination it also appears that the call itself is completely unnecessary. So to fix the problem this patch modifies next_tgid() to return both a tgid and the task struct in question. A structure is introduced to return these values because it is slightly cleaner and easier to optimize, and the resulting code is a little shorter. Signed-off-by: "Eric W. Biederman" --- fs/proc/base.c | 51 ++++++++++++++++++++++++++++----------------------- 1 files changed, 28 insertions(+), 23 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 5b92b79..7e8eca4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2454,19 +2454,23 @@ out: * Find the first task with tgid >= tgid * */ -static struct task_struct *next_tgid(unsigned int tgid, - struct pid_namespace *ns) -{ +struct tgid_iter { + unsigned int tgid; struct task_struct *task; +}; +static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) +{ struct pid *pid; + if (iter.task) + put_task_struct(iter.task); rcu_read_lock(); retry: - task = NULL; - pid = find_ge_pid(tgid, ns); + iter.task = NULL; + pid = find_ge_pid(iter.tgid, ns); if (pid) { - tgid = pid_nr_ns(pid, ns) + 1; - task = pid_task(pid, PIDTYPE_PID); + iter.tgid = pid_nr_ns(pid, ns); + iter.task = pid_task(pid, PIDTYPE_PID); /* What we to know is if the pid we have find is the * pid of a thread_group_leader. Testing for task * being a thread_group_leader is the obvious thing @@ -2479,23 +2483,25 @@ retry: * found doesn't happen to be a thread group leader. * As we don't care in the case of readdir. */ - if (!task || !has_group_leader_pid(task)) + if (!iter.task || !has_group_leader_pid(iter.task)) { + iter.tgid += 1; goto retry; - get_task_struct(task); + } + get_task_struct(iter.task); } rcu_read_unlock(); - return task; + return iter; } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff)) static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir, - struct task_struct *task, int tgid) + struct tgid_iter iter) { char name[PROC_NUMBUF]; - int len = snprintf(name, sizeof(name), "%d", tgid); + int len = snprintf(name, sizeof(name), "%d", iter.tgid); return proc_fill_cache(filp, dirent, filldir, name, len, - proc_pid_instantiate, task, NULL); + proc_pid_instantiate, iter.task, NULL); } /* for the /proc/ directory itself, after non-process stuff has been done */ @@ -2503,8 +2509,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode); - struct task_struct *task; - int tgid; + struct tgid_iter iter; struct pid_namespace *ns; if (!reaper) @@ -2517,14 +2522,14 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) } ns = filp->f_dentry->d_sb->s_fs_info; - tgid = filp->f_pos - TGID_OFFSET; - for (task = next_tgid(tgid, ns); - task; - put_task_struct(task), task = next_tgid(tgid + 1, ns)) { - tgid = task_pid_nr_ns(task, ns); - filp->f_pos = tgid + TGID_OFFSET; - if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) { - put_task_struct(task); + iter.task = NULL; + iter.tgid = filp->f_pos - TGID_OFFSET; + for (iter = next_tgid(ns, iter); + iter.task; + iter.tgid += 1, iter = next_tgid(ns, iter)) { + filp->f_pos = iter.tgid + TGID_OFFSET; + if (proc_pid_fill_cache(filp, dirent, filldir, iter) < 0) { + put_task_struct(iter.task); goto out; } } -- 1.5.3.rc6.17.g1911 - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/