From: Tejun Heo <tj@xxxxxxxxxx>
3.12-stable review patch. If anyone has any objections, please let me know.
===============
commit e09c2c295468476a239d13324ce9042ec4de05eb upstream.
create_singlethread_workqueue() is a compat interface for single
threaded workqueue which maps to ordered workqueue w/ rescuer in the
current implementation. create_singlethread_workqueue() currently
implemented by invoking alloc_workqueue() w/ appropriate parameters.
8719dceae2f9 ("workqueue: reject adjusting max_active or applying
attrs to ordered workqueues") introduced __WQ_ORDERED to protect
ordered workqueues against dynamic attribute changes which can break
ordering guarantees but forgot to apply it to
create_singlethread_workqueue(). This in itself is okay as nobody
currently uses dynamic attribute change on workqueues created with
create_singlethread_workqueue().
However, 4c16bd327c ("workqueue: implement NUMA affinity for unbound
workqueues") broke singlethreaded guarantee for ordered workqueues
through allocating a separate pool_workqueue on each NUMA node by
default. A later change 8a2b75384444 ("workqueue: fix ordered
workqueues in NUMA setups") fixed it by allocating only one global
pool_workqueue if __WQ_ORDERED is set.
Combined, the __WQ_ORDERED omission in create_singlethread_workqueue()
became critical breaking its single threadedness and ordering
guarantee.
Let's make create_singlethread_workqueue() wrap
alloc_ordered_workqueue() instead so that it inherits __WQ_ORDERED and
can implicitly track future ordered_workqueue changes.
v2: I missed that __WQ_ORDERED now protects against pwq splitting
across NUMA nodes and incorrectly described the patch as a
nice-to-have fix to protect against future dynamic attribute
usages. Oleg pointed out that this is actually a critical
breakage due to 8a2b75384444 ("workqueue: fix ordered workqueues
in NUMA setups").
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-by: Mike Anderson <mike.anderson@xxxxxxxxxx>
Cc: Oleg Nesterov <onestero@xxxxxxxxxx>
Cc: Gustavo Luiz Duarte <gduarte@xxxxxxxxxx>
Cc: Tomas Henzl <thenzl@xxxxxxxxxx>
Fixes: 4c16bd327c ("workqueue: implement NUMA affinity for unbound workqueues")
Signed-off-by: Jiri Slaby <jslaby@xxxxxxx>
---
include/linux/workqueue.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 594521ba0d43..eff358e6945d 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -455,7 +455,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
1, (name))
#define create_singlethread_workqueue(name) \
- alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name))
+ alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
extern void destroy_workqueue(struct workqueue_struct *wq);
--
2.1.1
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html