summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLai Jiangshan <laijs@cn.fujitsu.com>2012-09-18 10:40:00 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2012-10-13 05:50:20 +0900
commitd024fea7032bc7c333c967db530b44d59a180d14 (patch)
tree2deb7366049b81f19b2197c09af5d5297251ebc3 /kernel
parentd878ce75405d3fc90b0253d44ce603e5948584fb (diff)
workqueue: fix possible stall on try_to_grab_pending() of a delayed work item
commit 3aa62497594430ea522050b75c033f71f2c60ee6 upstream. Currently, when try_to_grab_pending() grabs a delayed work item, it leaves its linked work items alone on the delayed_works. The linked work items are always NO_COLOR and will cause future cwq_activate_first_delayed() increase cwq->nr_active incorrectly, and may cause the whole cwq to stall. For example, state: cwq->max_active = 1, cwq->nr_active = 1 one work in cwq->pool, many in cwq->delayed_works. step1: try_to_grab_pending() removes a work item from delayed_works but leaves its NO_COLOR linked work items on it. step2: Later on, cwq_activate_first_delayed() activates the linked work item increasing ->nr_active. step3: cwq->nr_active = 1, but all activated work items of the cwq are NO_COLOR. When they finish, cwq->nr_active will not be decreased due to NO_COLOR, and no further work items will be activated from cwq->delayed_works. the cwq stalls. Fix it by ensuring the target work item is activated before stealing PENDING in try_to_grab_pending(). This ensures that all the linked work items are activated without incorrectly bumping cwq->nr_active. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/workqueue.c25
1 files changed, 22 insertions, 3 deletions
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index cb16c8a82a14..872bd6d9be2d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1927,10 +1927,9 @@ static void move_linked_works(struct work_struct *work, struct list_head *head,
*nextp = n;
}
-static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
+static void cwq_activate_delayed_work(struct work_struct *work)
{
- struct work_struct *work = list_first_entry(&cwq->delayed_works,
- struct work_struct, entry);
+ struct cpu_workqueue_struct *cwq = get_work_cwq(work);
trace_workqueue_activate_work(work);
move_linked_works(work, &cwq->pool->worklist, NULL);
@@ -1938,6 +1937,14 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
cwq->nr_active++;
}
+static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
+{
+ struct work_struct *work = list_first_entry(&cwq->delayed_works,
+ struct work_struct, entry);
+
+ cwq_activate_delayed_work(work);
+}
+
/**
* cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
* @cwq: cwq of interest
@@ -2846,6 +2853,18 @@ static int try_to_grab_pending(struct work_struct *work)
smp_rmb();
if (gcwq == get_work_gcwq(work)) {
debug_work_deactivate(work);
+
+ /*
+ * A delayed work item cannot be grabbed directly
+ * because it might have linked NO_COLOR work items
+ * which, if left on the delayed_list, will confuse
+ * cwq->nr_active management later on and cause
+ * stall. Make sure the work item is activated
+ * before grabbing.
+ */
+ if (*work_data_bits(work) & WORK_STRUCT_DELAYED)
+ cwq_activate_delayed_work(work);
+
list_del_init(&work->entry);
cwq_dec_nr_in_flight(get_work_cwq(work),
get_work_color(work),