Commit c9e75f04 authored by Oleg Nesterov's avatar Oleg Nesterov Committed by Tejun Heo
Browse files

cgroup: pids: fix race between cgroup_post_fork() and cgroup_migrate() 



If the new child migrates to another cgroup before cgroup_post_fork() calls
subsys->fork(), then both pids_can_attach() and pids_fork() will do the same
pids_uncharge(old_pids) + pids_charge(pids) sequence twice.

Change copy_process() to call threadgroup_change_begin/threadgroup_change_end
unconditionally. percpu_down_read() is cheap and this allows other cleanups,
see the next changes.

Also, this way we can unify cgroup_threadgroup_rwsem and dup_mmap_sem.

Signed-off-by: default avatarOleg Nesterov <oleg@redhat.com>
Acked-by: default avatarZefan Li <lizefan@huawei.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 53254f90

kernel/cgroup_pids.c

+2 −19
Original line number Diff line number Diff line
@@ -243,27 +243,10 @@ static void pids_cancel_fork(struct task_struct *task, void *priv) 


static void pids_fork(struct task_struct *task, void *priv)

{

	struct cgroup_subsys_state *css;

	struct cgroup_subsys_state *old_css = priv;

	struct pids_cgroup *pids;

	struct pids_cgroup *old_pids = css_pids(old_css);



	css = task_get_css(task, pids_cgrp_id);

	pids = css_pids(css);



	/*

	 * If the association has changed, we have to revert and reapply the

	 * charge/uncharge on the wrong hierarchy to the current one. Since

	 * the association can only change due to an organisation event, its

	 * okay for us to ignore the limit in this case.

	 */

	if (pids != old_pids) {

		pids_uncharge(old_pids, 1);

		pids_charge(pids, 1);

	}

	struct cgroup_subsys_state *css = priv;



	WARN_ON(task_css_check(task, pids_cgrp_id, true) != css);

	css_put(css);

	css_put(old_css);

}



static void pids_free(struct task_struct *task)

kernel/fork.c

+3 −6
Original line number Diff line number Diff line
@@ -1368,7 +1368,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, 
	p->real_start_time = ktime_get_boot_ns();

	p->io_context = NULL;

	p->audit_context = NULL;

	if (clone_flags & CLONE_THREAD)

	threadgroup_change_begin(current);

	cgroup_fork(p);

#ifdef CONFIG_NUMA
@@ -1610,7 +1609,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, 


	proc_fork_connector(p);

	cgroup_post_fork(p, cgrp_ss_priv);

	if (clone_flags & CLONE_THREAD)

	threadgroup_change_end(current);

	perf_event_fork(p);
@@ -1652,7 +1650,6 @@ bad_fork_cleanup_policy: 
	mpol_put(p->mempolicy);

bad_fork_cleanup_threadgroup_lock:

#endif

	if (clone_flags & CLONE_THREAD)

	threadgroup_change_end(current);

	delayacct_tsk_free(p);

bad_fork_cleanup_count:

CRA Git | Maintained and supported by SUSTech CRA and CCSE