summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMarco Crivellari <marco.crivellari@suse.com>2025-09-14 15:44:26 +0200
committerTejun Heo <tj@kernel.org>2025-09-16 10:33:53 -1000
commitdadb3ebcf395ebee3626d88ac7e5e234f15bae2c (patch)
treed34885da2f8e199a69dc16e89491d74a81d2339f
parenta2be943b46b4a7478ea8ddf9bb8e5251c59fceb7 (diff)
workqueue: WQ_PERCPU added to alloc_workqueue users
Currently if a user enqueue a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistentcy cannot be addressed without refactoring the API. alloc_workqueue() treats all queues as per-CPU by default, while unbound workqueues must opt-in via WQ_UNBOUND. This default is suboptimal: most workloads benefit from unbound queues, allowing the scheduler to place worker threads where they’re needed and reducing noise when CPUs are isolated. This patch adds a new WQ_PERCPU flag to explicitly request the use of the per-CPU behavior. Both flags coexist for one release cycle to allow callers to transition their calls. Once migration is complete, WQ_UNBOUND can be removed and unbound will become the implicit default. With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND), any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND must now use WQ_PERCPU. All existing users have been updated accordingly. Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Marco Crivellari <marco.crivellari@suse.com> Signed-off-by: Tejun Heo <tj@kernel.org>
-rw-r--r--include/linux/workqueue.h4
-rw-r--r--kernel/workqueue.c20
2 files changed, 12 insertions, 12 deletions
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index b6834b7aee4b..71a9900c03c7 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -410,7 +410,7 @@ enum wq_flags {
__WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
/* BH wq only allows the following flags */
- __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI,
+ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI | WQ_PERCPU,
};
enum wq_consts {
@@ -570,7 +570,7 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
#define create_workqueue(name) \
- alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
+ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name))
#define create_freezable_workqueue(name) \
alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \
WQ_MEM_RECLAIM, 1, (name))
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 90db8cf015c2..45320e27a16c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7828,22 +7828,22 @@ void __init workqueue_init_early(void)
ordered_wq_attrs[i] = attrs;
}
- system_wq = alloc_workqueue("events", 0, 0);
- system_percpu_wq = alloc_workqueue("events", 0, 0);
- system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
- system_long_wq = alloc_workqueue("events_long", 0, 0);
+ system_wq = alloc_workqueue("events", WQ_PERCPU, 0);
+ system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0);
+ system_highpri_wq = alloc_workqueue("events_highpri",
+ WQ_HIGHPRI | WQ_PERCPU, 0);
+ system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
system_freezable_wq = alloc_workqueue("events_freezable",
- WQ_FREEZABLE, 0);
+ WQ_FREEZABLE | WQ_PERCPU, 0);
system_power_efficient_wq = alloc_workqueue("events_power_efficient",
- WQ_POWER_EFFICIENT, 0);
+ WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient",
- WQ_FREEZABLE | WQ_POWER_EFFICIENT,
- 0);
- system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
+ WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
+ system_bh_wq = alloc_workqueue("events_bh", WQ_BH | WQ_PERCPU, 0);
system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
- WQ_BH | WQ_HIGHPRI, 0);
+ WQ_BH | WQ_HIGHPRI | WQ_PERCPU, 0);
BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq ||
!system_unbound_wq || !system_freezable_wq || !system_dfl_wq ||
!system_power_efficient_wq ||