This is a note to let you know that I've just added the patch titled
workqueue: fix ordered workqueues in NUMA setups
to the 3.10-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-fix-ordered-workqueues-in-numa-setups.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 8a2b75384444488fc4f2cbb9f0921b6a0794838f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@xxxxxxxxxx>
Date: Thu, 5 Sep 2013 12:30:04 -0400
Subject: workqueue: fix ordered workqueues in NUMA setups
From: Tejun Heo <tj@xxxxxxxxxx>
commit 8a2b75384444488fc4f2cbb9f0921b6a0794838f upstream.
An ordered workqueue implements execution ordering by using single
pool_workqueue with max_active == 1. On a given pool_workqueue, work
items are processed in FIFO order and limiting max_active to 1
enforces the queued work items to be processed one by one.
Unfortunately, 4c16bd327c ("workqueue: implement NUMA affinity for
unbound workqueues") accidentally broke this guarantee by applying
NUMA affinity to ordered workqueues too. On NUMA setups, an ordered
workqueue would end up with separate pool_workqueues for different
nodes. Each pool_workqueue still limits max_active to 1 but multiple
work items may be executed concurrently and out of order depending on
which node they are queued to.
Fix it by using dedicated ordered_wq_attrs[] when creating ordered
workqueues. The new attrs match the unbound ones except that no_numa
is always set thus forcing all NUMA nodes to share the default
pool_workqueue.
While at it, add sanity check in workqueue creation path which
verifies that an ordered workqueues has only the default
pool_workqueue.
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-by: Libin <huawei.libin@xxxxxxxxxx>
Cc: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/workqueue.c | 24 ++++++++++++++++++++++--
1 file changed, 22 insertions(+), 2 deletions(-)
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -295,6 +295,9 @@ static DEFINE_HASHTABLE(unbound_pool_has
/* I: attributes used when instantiating standard unbound pools on demand */
static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -4059,7 +4062,7 @@ out_unlock:
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
bool highpri = wq->flags & WQ_HIGHPRI;
- int cpu;
+ int cpu, ret;
if (!(wq->flags & WQ_UNBOUND)) {
wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4079,6 +4082,13 @@ static int alloc_and_link_pwqs(struct wo
mutex_unlock(&wq->mutex);
}
return 0;
+ } else if (wq->flags & __WQ_ORDERED) {
+ ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+ /* there should only be single pwq for ordering guarantee */
+ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+ wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+ "ordering guarantee broken for workqueue %s\n", wq->name);
+ return ret;
} else {
return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
}
@@ -4990,13 +5000,23 @@ static int __init init_workqueues(void)
}
}
- /* create default unbound wq attrs */
+ /* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
+
+ /*
+ * An ordered wq should have only one pwq as ordering is
+ * guaranteed by max_active which is enforced by pwqs.
+ * Turn off NUMA so that dfl_pwq is used for all nodes.
+ */
+ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+ attrs->nice = std_nice[i];
+ attrs->no_numa = true;
+ ordered_wq_attrs[i] = attrs;
}
system_wq = alloc_workqueue("events", 0, 0);
Patches currently in stable-queue which might be from tj@xxxxxxxxxx are
queue-3.10/drivers-libata-set-max-sector-to-65535-for-slimtype-dvd-a-ds8a9sh-drive.patch
queue-3.10/cpuset-fix-memory-allocator-deadlock.patch
queue-3.10/workqueue-fix-ordered-workqueues-in-numa-setups.patch
queue-3.10/ahci-add-marvell-9230-to-the-ahci-pci-device-list.patch
queue-3.10/ahci-disabled-fbs-prior-to-issuing-software-reset.patch
queue-3.10/ahci-add-device-ids-for-intel-wildcat-point-lp.patch
queue-3.10/blk-core-fix-memory-corruption-if-blkcg_init_queue-fails.patch
queue-3.10/libata-fix-display-of-sata-speed.patch
queue-3.10/loop-fix-crash-if-blk_alloc_queue-fails.patch
--
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