summaryrefslogtreecommitdiff
path: root/kernel/pid_namespace.c
diff options
context:
space:
mode:
authorEric W. Biederman <ebiederm@xmission.com>2012-08-01 10:33:47 -0700
committerEric W. Biederman <ebiederm@xmission.com>2012-11-19 05:59:10 -0800
commit0a01f2cc390e10633a54f72c608cc3fe19a50c3d (patch)
treee713a1c45b5ce125a5d33b61d528cd45264d47a7 /kernel/pid_namespace.c
parent17cf22c33e1f1b5e435469c84e43872579497653 (diff)
downloadlwn-0a01f2cc390e10633a54f72c608cc3fe19a50c3d.tar.gz
lwn-0a01f2cc390e10633a54f72c608cc3fe19a50c3d.zip
pidns: Make the pidns proc mount/umount logic obvious.
Track the number of pids in the proc hash table. When the number of pids goes to 0 schedule work to unmount the kernel mount of proc. Move the mount of proc into alloc_pid when we allocate the pid for init. Remove the surprising calls of pid_ns_release proc in fork and proc_flush_task. Those code paths really shouldn't know about proc namespace implementation details and people have demonstrated several times that finding and understanding those code paths is difficult and non-obvious. Because of the call path detach pid is alwasy called with the rtnl_lock held free_pid is not allowed to sleep, so the work to unmounting proc is moved to a work queue. This has the side benefit of not blocking the entire world waiting for the unnecessary rcu_barrier in deactivate_locked_super. In the process of making the code clear and obvious this fixes a bug reported by Gao feng <gaofeng@cn.fujitsu.com> where we would leak a mount of proc during clone(CLONE_NEWPID|CLONE_NEWNET) if copy_pid_ns succeeded and copy_net_ns failed. Acked-by: "Serge E. Hallyn" <serge@hallyn.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Diffstat (limited to 'kernel/pid_namespace.c')
-rw-r--r--kernel/pid_namespace.c14
1 files changed, 7 insertions, 7 deletions
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index b2604950aa50..84591cfeefc1 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -72,6 +72,12 @@ err_alloc:
return NULL;
}
+static void proc_cleanup_work(struct work_struct *work)
+{
+ struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
+ pid_ns_release_proc(ns);
+}
+
/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
#define MAX_PID_NS_LEVEL 32
@@ -105,6 +111,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->level = level;
ns->parent = get_pid_ns(parent_pid_ns);
ns->user_ns = get_user_ns(user_ns);
+ INIT_WORK(&ns->proc_work, proc_cleanup_work);
set_bit(0, ns->pidmap[0].page);
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -112,15 +119,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
for (i = 1; i < PIDMAP_ENTRIES; i++)
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
- err = pid_ns_prepare_proc(ns);
- if (err)
- goto out_put_parent_pid_ns;
-
return ns;
-out_put_parent_pid_ns:
- put_pid_ns(parent_pid_ns);
- put_user_ns(user_ns);
out_free_map:
kfree(ns->pidmap[0].page);
out_free: