summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2012-02-08 03:37:27 +0100
committerTejun Heo <tj@kernel.org>2012-02-21 18:46:47 +0100
commit3ce3230a0cff484e5130153f244d4fb8a56b3a8b (patch)
tree6ee374618c9edacefd2e9d0f912c651bd5f12cb7
parentcgroup: Remove wrong comment on cgroup_enable_task_cg_list() (diff)
downloadlinux-3ce3230a0cff484e5130153f244d4fb8a56b3a8b.tar.xz
linux-3ce3230a0cff484e5130153f244d4fb8a56b3a8b.zip
cgroup: Walk task list under tasklist_lock in cgroup_enable_task_cg_list
Walking through the tasklist in cgroup_enable_task_cg_list() inside an RCU read side critical section is not enough because: - RCU is not (yet) safe against while_each_thread() - If we use only RCU, a forking task that has passed cgroup_post_fork() without seeing use_task_css_set_links == 1 is not guaranteed to have its child immediately visible in the tasklist if we walk through it remotely with RCU. In this case it will be missing in its css_set's task list. Thus we need to traverse the list (unfortunately) under the tasklist_lock. It makes us safe against while_each_thread() and also make sure we see all forked task that have been added to the tasklist. As a secondary effect, reading and writing use_task_css_set_links are now well ordered against tasklist traversing and modification. The new layout is: CPU 0 CPU 1 use_task_css_set_links = 1 write_lock(tasklist_lock) read_lock(tasklist_lock) add task to tasklist do_each_thread() { write_unlock(tasklist_lock) add thread to css set links if (use_task_css_set_links) } while_each_thread() add thread to css set links read_unlock(tasklist_lock) If CPU 0 traverse the list after the task has been added to the tasklist then it is correctly added to the css set links. OTOH if CPU 0 traverse the tasklist before the new task had the opportunity to be added to the tasklist because it was too early in the fork process, then CPU 1 catches up and add the task to the css set links after it added the task to the tasklist. The right value of use_task_css_set_links is guaranteed to be visible from CPU 1 due to the LOCK/UNLOCK implicit barrier properties: the read_unlock on CPU 0 makes the write on use_task_css_set_links happening and the write_lock on CPU 1 make the read of use_task_css_set_links that comes afterward to return the correct value. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Mandeep Singh Baines <msb@chromium.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-rw-r--r--kernel/cgroup.c20
1 files changed, 20 insertions, 0 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 6e4eb4312571..c6877fe9a831 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2707,6 +2707,14 @@ static void cgroup_enable_task_cg_lists(void)
struct task_struct *p, *g;
write_lock(&css_set_lock);
use_task_css_set_links = 1;
+ /*
+ * We need tasklist_lock because RCU is not safe against
+ * while_each_thread(). Besides, a forking task that has passed
+ * cgroup_post_fork() without seeing use_task_css_set_links = 1
+ * is not guaranteed to have its child immediately visible in the
+ * tasklist if we walk through it with RCU.
+ */
+ read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
/*
@@ -2718,6 +2726,7 @@ static void cgroup_enable_task_cg_lists(void)
list_add(&p->cg_list, &p->cgroups->tasks);
task_unlock(p);
} while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
write_unlock(&css_set_lock);
}
@@ -4522,6 +4531,17 @@ void cgroup_fork_callbacks(struct task_struct *child)
*/
void cgroup_post_fork(struct task_struct *child)
{
+ /*
+ * use_task_css_set_links is set to 1 before we walk the tasklist
+ * under the tasklist_lock and we read it here after we added the child
+ * to the tasklist under the tasklist_lock as well. If the child wasn't
+ * yet in the tasklist when we walked through it from
+ * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
+ * should be visible now due to the paired locking and barriers implied
+ * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
+ * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
+ * lock on fork.
+ */
if (use_task_css_set_links) {
write_lock(&css_set_lock);
if (list_empty(&child->cg_list)) {