workqueue: restore WQ_UNBOUND/max_active==1 to be ordered

The combination of WQ_UNBOUND and max_active == 1 used to imply
ordered execution.  After NUMA affinity 4c16bd327c74 ("workqueue:
implement NUMA affinity for unbound workqueues"), this is no longer
true due to per-node worker pools.

While the right way to create an ordered workqueue is
alloc_ordered_workqueue(), the documentation has been misleading for a
long time and people do use WQ_UNBOUND and max_active == 1 for ordered
workqueues which can lead to subtle bugs which are very difficult to
trigger.

It's unlikely that we'd see noticeable performance impact by enforcing
ordering on WQ_UNBOUND / max_active == 1 workqueues.  Let's
automatically set __WQ_ORDERED for those workqueues.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Reported-by: Alexei Potashnik <alexei@purestorage.com>
Fixes: 4c16bd327c74 ("workqueue: implement NUMA affinity for unbound workqueues")
Cc: stable@vger.kernel.org # v3.10+

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a86688fabc55c4a4ec2bad843f6dc1e0e411f2d1..abe4a4971c246ded51a0d81c53b714de97f61be9 100644 (file)
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3929,6 +3929,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
        struct workqueue_struct *wq;
        struct pool_workqueue *pwq;
 
+       /*
+        * Unbound && max_active == 1 used to imply ordered, which is no
+        * longer the case on NUMA machines due to per-node pools.  While
+        * alloc_ordered_workqueue() is the right way to create an ordered
+        * workqueue, keep the previous behavior to avoid subtle breakages
+        * on NUMA.
+        */
+       if ((flags & WQ_UNBOUND) && max_active == 1)
+               flags |= __WQ_ORDERED;
+
        /* see the comment above the definition of WQ_POWER_EFFICIENT */
        if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
                flags |= WQ_UNBOUND;