The reference count in the css_set data structure was used as a proxy of the number of tasks attached to that css_set. However, that count is actually not an accurate measure especially with thread mode support. So a new variable task_count is added to the css_set to keep track of the actual task count. This new variable is protected by the css_set_lock. Functions that require the actual task count are updated to use the new variable. Signed-off-by: Waiman Long <longman@xxxxxxxxxx> --- include/linux/cgroup-defs.h | 3 +++ kernel/cgroup/cgroup-v1.c | 6 +----- kernel/cgroup/cgroup.c | 5 +++++ kernel/cgroup/debug.c | 6 +----- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index b123afc..104be73 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -163,6 +163,9 @@ struct css_set { /* reference count */ refcount_t refcount; + /* internal task count, protected by css_set_lock */ + int task_count; + /* * If not threaded, the following points to self. If threaded, to * a cset which belongs to the top cgroup of the threaded subtree. diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 7ad6b17..302b3b8 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -334,10 +334,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question - * - * Return the number of tasks in the cgroup. The returned number can be - * higher than the actual number of tasks due to css_set references from - * namespace roots and temporary usages. */ static int cgroup_task_count(const struct cgroup *cgrp) { @@ -346,7 +342,7 @@ static int cgroup_task_count(const struct cgroup *cgrp) spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) - count += refcount_read(&link->cset->refcount); + count += link->cset->task_count; spin_unlock_irq(&css_set_lock); return count; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7b085d5..7e3ddfb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1676,6 +1676,7 @@ static void cgroup_enable_task_cg_lists(void) css_set_update_populated(cset, true); list_add_tail(&p->cg_list, &cset->tasks); get_css_set(cset); + cset->task_count++; } spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); @@ -2159,8 +2160,10 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); + to_cset->task_count++; css_set_move_task(task, from_cset, to_cset, true); put_css_set_locked(from_cset); + from_cset->task_count--; } } spin_unlock_irq(&css_set_lock); @@ -5160,6 +5163,7 @@ void cgroup_post_fork(struct task_struct *child) cset = task_css_set(current); if (list_empty(&child->cg_list)) { get_css_set(cset); + cset->task_count++; css_set_move_task(child, NULL, cset, false); } spin_unlock_irq(&css_set_lock); @@ -5209,6 +5213,7 @@ void cgroup_exit(struct task_struct *tsk) if (!list_empty(&tsk->cg_list)) { spin_lock_irq(&css_set_lock); css_set_move_task(tsk, cset, NULL, false); + cset->task_count--; spin_unlock_irq(&css_set_lock); } else { get_css_set(cset); diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c index 56e60a2..ada53e6 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -23,10 +23,6 @@ static void debug_css_free(struct cgroup_subsys_state *css) /* * debug_taskcount_read - return the number of tasks in a cgroup. * @cgrp: the cgroup in question - * - * Return the number of tasks in the cgroup. The returned number can be - * higher than the actual number of tasks due to css_set references from - * namespace roots and temporary usages. */ static u64 debug_taskcount_read(struct cgroup_subsys_state *css, struct cftype *cft) @@ -37,7 +33,7 @@ static u64 debug_taskcount_read(struct cgroup_subsys_state *css, spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) - count += refcount_read(&link->cset->refcount); + count += link->cset->task_count; spin_unlock_irq(&css_set_lock); return count; } -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe cgroups" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html