From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Tejun Heo <tj@kernel.org>, Sasha Levin <sashal@kernel.org>
Subject: [PATCH AUTOSEL 4.19 12/14] workqueue: Call wq_update_unbound_numa() on all CPUs in NUMA node on CPU hotplug
Date: Fri, 8 Sep 2023 20:40:43 -0400 [thread overview]
Message-ID: <20230909004045.3581014-12-sashal@kernel.org> (raw)
In-Reply-To: <20230909004045.3581014-1-sashal@kernel.org>
From: Tejun Heo <tj@kernel.org>
[ Upstream commit 4cbfd3de737b9d00544ff0f673cb75fc37bffb6a ]
When a CPU went online or offline, wq_update_unbound_numa() was called only
on the CPU which was going up or down. This works fine because all CPUs on
the same NUMA node share the same pool_workqueue slot - one CPU updating it
updates it for everyone in the node.
However, future changes will make each CPU use a separate pool_workqueue
even when they're sharing the same worker_pool, which requires updating
pool_workqueue's for all CPUs which may be sharing the same pool_workqueue
on hotplug.
To accommodate the planned changes, this patch updates
workqueue_on/offline_cpu() so that they call wq_update_unbound_numa() for
all CPUs sharing the same NUMA node as the CPU going up or down. In the
current code, the second+ calls would be noops and there shouldn't be any
behavior changes.
* As wq_update_unbound_numa() is now called on multiple CPUs per each
hotplug event, @cpu is renamed to @hotplug_cpu and another @cpu argument
is added. The former indicates the CPU being hot[un]plugged and the latter
the CPU whose pool_workqueue is being updated.
* In wq_update_unbound_numa(), cpu_off is renamed to off_cpu for consistency
with the new @hotplug_cpu.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
kernel/workqueue.c | 34 +++++++++++++++++++++++++---------
1 file changed, 25 insertions(+), 9 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5533206cb6f48..c994b06f60f2f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3907,7 +3907,8 @@ EXPORT_SYMBOL_GPL(apply_workqueue_attrs);
/**
* wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
* @wq: the target workqueue
- * @cpu: the CPU coming up or going down
+ * @cpu: the CPU to update pool association for
+ * @hotplug_cpu: the CPU coming up or going down
* @online: whether @cpu is coming up or going down
*
* This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
@@ -3927,10 +3928,10 @@ EXPORT_SYMBOL_GPL(apply_workqueue_attrs);
* CPU_DOWN_PREPARE.
*/
static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
- bool online)
+ int hotplug_cpu, bool online)
{
int node = cpu_to_node(cpu);
- int cpu_off = online ? -1 : cpu;
+ int off_cpu = online ? -1 : hotplug_cpu;
struct pool_workqueue *old_pwq = NULL, *pwq;
struct workqueue_attrs *target_attrs;
cpumask_t *cpumask;
@@ -3958,7 +3959,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
* and create a new one if they don't match. If the target cpumask
* equals the default pwq's, the default pwq should be used.
*/
- if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) {
+ if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, off_cpu, cpumask)) {
if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
return;
} else {
@@ -4876,8 +4877,15 @@ int workqueue_online_cpu(unsigned int cpu)
}
/* update NUMA affinity of unbound workqueues */
- list_for_each_entry(wq, &workqueues, list)
- wq_update_unbound_numa(wq, cpu, true);
+ list_for_each_entry(wq, &workqueues, list) {
+ int tcpu;
+
+ for_each_possible_cpu(tcpu) {
+ if (cpu_to_node(tcpu) == cpu_to_node(cpu)) {
+ wq_update_unbound_numa(wq, tcpu, cpu, true);
+ }
+ }
+ }
mutex_unlock(&wq_pool_mutex);
return 0;
@@ -4895,8 +4903,15 @@ int workqueue_offline_cpu(unsigned int cpu)
/* update NUMA affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
- list_for_each_entry(wq, &workqueues, list)
- wq_update_unbound_numa(wq, cpu, false);
+ list_for_each_entry(wq, &workqueues, list) {
+ int tcpu;
+
+ for_each_possible_cpu(tcpu) {
+ if (cpu_to_node(tcpu) == cpu_to_node(cpu)) {
+ wq_update_unbound_numa(wq, tcpu, cpu, false);
+ }
+ }
+ }
mutex_unlock(&wq_pool_mutex);
return 0;
@@ -5843,7 +5858,8 @@ int __init workqueue_init(void)
}
list_for_each_entry(wq, &workqueues, list) {
- wq_update_unbound_numa(wq, smp_processor_id(), true);
+ wq_update_unbound_numa(wq, smp_processor_id(), smp_processor_id(),
+ true);
WARN(init_rescuer(wq),
"workqueue: failed to create early rescuer for %s",
wq->name);
--
2.40.1
next prev parent reply other threads:[~2023-09-09 0:51 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-09 0:40 [PATCH AUTOSEL 4.19 01/14] media: dvb-usb-v2: af9035: Fix null-ptr-deref in af9035_i2c_master_xfer Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 02/14] media: dw2102: Fix null-ptr-deref in dw2102_i2c_transfer() Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 03/14] media: af9005: Fix null-ptr-deref in af9005_i2c_xfer Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 04/14] media: anysee: fix null-ptr-deref in anysee_master_xfer Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 05/14] media: az6007: Fix null-ptr-deref in az6007_i2c_xfer() Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 06/14] iio: core: Use min() instead of min_t() to make code more robust Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 07/14] media: tuners: qt1010: replace BUG_ON with a regular error Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 08/14] media: pci: cx23885: replace BUG with error return Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 09/14] usb: gadget: fsl_qe_udc: validate endpoint index for ch9 udc Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 10/14] scsi: target: iscsi: Fix buffer overflow in lio_target_nacl_info_show() Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 11/14] serial: cpm_uart: Avoid suspicious locking Sasha Levin
2023-09-09 0:40 ` Sasha Levin [this message]
2023-09-11 9:57 ` [PATCH AUTOSEL 4.19 12/14] workqueue: Call wq_update_unbound_numa() on all CPUs in NUMA node on CPU hotplug Pavel Machek
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 13/14] media: pci: ipu3-cio2: Initialise timing struct to avoid a compiler warning Sasha Levin
2023-09-09 0:40 ` [PATCH AUTOSEL 4.19 14/14] kobject: Add sanity check for kset->kobj.ktype in kset_register() Sasha Levin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230909004045.3581014-12-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox