This is a note to let you know that I've just added the patch titled
workqueue: restore WQ_UNBOUND/max_active==1 to be ordered
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
workqueue-restore-wq_unbound-max_active-1-to-be-ordered.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 5c0338c68706be53b3dc472e4308961c36e4ece1 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@xxxxxxxxxx>
Date: Tue, 18 Jul 2017 18:41:52 -0400
Subject: workqueue: restore WQ_UNBOUND/max_active==1 to be ordered
From: Tejun Heo <tj@xxxxxxxxxx>
commit 5c0338c68706be53b3dc472e4308961c36e4ece1 upstream.
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@xxxxxxxxxx>
Reported-by: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Reported-by: Alexei Potashnik <alexei@xxxxxxxxxxxxxxx>
Fixes: 4c16bd327c74 ("workqueue: implement NUMA affinity for unbound workqueues")
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/workqueue.c | 10 ++++++++++
1 file changed, 10 insertions(+)
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3915,6 +3915,16 @@ struct workqueue_struct *__alloc_workque
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;
Patches currently in stable-queue which might be from tj@xxxxxxxxxx are
queue-4.9/cgroup-create-dfl_root-files-on-subsys-registration.patch
queue-4.9/cgroup-fix-error-return-value-from-cgroup_subtree_control.patch
queue-4.9/workqueue-restore-wq_unbound-max_active-1-to-be-ordered.patch
queue-4.9/libata-array-underflow-in-ata_find_dev.patch