[PATCH 0/3] mm: replace wq users and add WQ_PERCPU to alloc_workqueue() users

[PATCH 0/3] mm: replace wq users and add WQ_PERCPU to alloc_workqueue() users

[Marco Crivellari]

Hi!

Below is a summary of a discussion about the Workqueue API and cpu isolation
considerations. Details and more information are available here:

        "workqueue: Always use wq_select_unbound_cpu() for WORK_CPU_UNBOUND."
        https://lore.kernel.org/all/20250221112003.1dSuoGyc@linutronix.de/

=== Current situation: problems ===

Let's consider a nohz_full system with isolated CPUs: wq_unbound_cpumask is
set to the housekeeping CPUs, for !WQ_UNBOUND the local CPU is selected.

This leads to different scenarios if a work item is scheduled on an isolated
CPU where "delay" value is 0 or greater then 0:
        schedule_delayed_work(, 0);

This will be handled by __queue_work() that will queue the work item on the
current local (isolated) CPU, while:

        schedule_delayed_work(, 1);

Will move the timer on an housekeeping CPU, and schedule the work there.

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.

=== Plan and future plans ===

This patchset is the first stone on a refactoring needed in order to
address the points aforementioned; it will have a positive impact also
on the cpu isolation, in the long term, moving away percpu workqueue in
favor to an unbound model.

These are the main steps:
1)  API refactoring (that this patch is introducing)
    -   Make more clear and uniform the system wq names, both per-cpu and
        unbound. This to avoid any possible confusion on what should be
        used.

    -   Introduction of WQ_PERCPU: this flag is the complement of WQ_UNBOUND,
        introduced in this patchset and used on all the callers that are not
        currently using WQ_UNBOUND.

        WQ_UNBOUND will be removed in a future release cycle.

        Most users don't need to be per-cpu, because they don't have
        locality requirements, because of that, a next future step will be
        make "unbound" the default behavior.

2)  Check who really needs to be per-cpu
    -   Remove the WQ_PERCPU flag when is not strictly required.

3)  Add a new API (prefer local cpu)
    -   There are users that don't require a local execution, like mentioned
        above; despite that, local execution yeld to performance gain.

        This new API will prefer the local execution, without requiring it.

=== Introduced Changes by this series ===

1) [P 1-2] Replace use of system_wq and system_unbound_wq

        system_wq is a per-CPU workqueue, but his name is not clear.
        system_unbound_wq is to be used when locality is not required.

        Because of that, system_wq has been renamed in system_percpu_wq, and
        system_unbound_wq has been renamed in system_dfl_wq.

2) [P 3] add WQ_PERCPU to remaining alloc_workqueue() users

        Every alloc_workqueue() caller should use one among WQ_PERCPU or
        WQ_UNBOUND. This is actually enforced warning if both or none of them
        are present at the same time.

        WQ_UNBOUND will be removed in a next release cycle.

=== For Maintainers ===

There are prerequisites for this series, already merged in the master branch.
The commits are:

128ea9f6ccfb6960293ae4212f4f97165e42222d ("workqueue: Add system_percpu_wq and
system_dfl_wq")

930c2ea566aff59e962c50b2421d5fcc3b98b8be ("workqueue: Add new WQ_PERCPU flag")


Thanks!

Marco Crivellari (3):
  mm: replace use of system_unbound_wq with system_dfl_wq
  mm: replace use of system_wq with system_percpu_wq
  mm: WQ_PERCPU added to alloc_workqueue users

 mm/backing-dev.c | 6 +++---
 mm/kfence/core.c | 6 +++---
 mm/memcontrol.c  | 4 ++--
 mm/slub.c        | 3 ++-
 mm/vmstat.c      | 3 ++-
 5 files changed, 12 insertions(+), 10 deletions(-)

-- 
2.51.0

[PATCH 1/3] mm: replace use of system_unbound_wq with system_dfl_wq

[Marco Crivellari]

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.

system_unbound_wq should be the default workqueue so as not to enforce
locality constraints for random work whenever it's not required.

Adding system_dfl_wq to encourage its use when unbound work should be used.

queue_work() / queue_delayed_work() / mod_delayed_work() will now use the
new unbound wq: whether the user still use the old wq a warn will be
printed along with a wq redirect to the new one.

The old system_unbound_wq will be kept for a few release cycles.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
---
 mm/backing-dev.c | 2 +-
 mm/kfence/core.c | 6 +++---
 mm/memcontrol.c  | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 783904d8c5ef..e9f9fdcfe052 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -934,7 +934,7 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 	memcg_cgwb_list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
 
-	queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work);
+	queue_work(system_dfl_wq, &cleanup_offline_cgwbs_work);
 }
 
 /**
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 102048821c22..f26d87d59296 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -854,7 +854,7 @@ static void toggle_allocation_gate(struct work_struct *work)
 	/* Disable static key and reset timer. */
 	static_branch_disable(&kfence_allocation_key);
 #endif
-	queue_delayed_work(system_unbound_wq, &kfence_timer,
+	queue_delayed_work(system_dfl_wq, &kfence_timer,
 			   msecs_to_jiffies(kfence_sample_interval));
 }
 
@@ -900,7 +900,7 @@ static void kfence_init_enable(void)
 		atomic_notifier_chain_register(&panic_notifier_list, &kfence_check_canary_notifier);
 
 	WRITE_ONCE(kfence_enabled, true);
-	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
+	queue_delayed_work(system_dfl_wq, &kfence_timer, 0);
 
 	pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE,
 		CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool,
@@ -996,7 +996,7 @@ static int kfence_enable_late(void)
 		return kfence_init_late();
 
 	WRITE_ONCE(kfence_enabled, true);
-	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
+	queue_delayed_work(system_dfl_wq, &kfence_timer, 0);
 	pr_info("re-enabled\n");
 	return 0;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 421740f1bcdc..c2944bc83378 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -651,7 +651,7 @@ static void flush_memcg_stats_dwork(struct work_struct *w)
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	__mem_cgroup_flush_stats(root_mem_cgroup, true);
-	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
+	queue_delayed_work(system_dfl_wq, &stats_flush_dwork, FLUSH_TIME);
 }
 
 unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
@@ -3732,7 +3732,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		goto offline_kmem;
 
 	if (unlikely(mem_cgroup_is_root(memcg)) && !mem_cgroup_disabled())
-		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
+		queue_delayed_work(system_dfl_wq, &stats_flush_dwork,
 				   FLUSH_TIME);
 	lru_gen_online_memcg(memcg);
 
-- 
2.51.0

[PATCH 2/3] mm: replace use of system_wq with system_percpu_wq

[Marco Crivellari]

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.

system_wq is a per-CPU worqueue, yet nothing in its name tells about that
CPU affinity constraint, which is very often not required by users.
Make it clear by adding a system_percpu_wq to all the mm subsystem.

The old wq will be kept for a few release cylces.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
---
 mm/backing-dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index e9f9fdcfe052..7e672424f928 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -966,7 +966,7 @@ static int __init cgwb_init(void)
 {
 	/*
 	 * There can be many concurrent release work items overwhelming
-	 * system_wq.  Put them in a separate wq and limit concurrency.
+	 * system_percpu_wq.  Put them in a separate wq and limit concurrency.
 	 * There's no point in executing many of these in parallel.
 	 */
 	cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
-- 
2.51.0

[PATCH 3/3] mm: WQ_PERCPU added to alloc_workqueue users

[Marco Crivellari]

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 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 all the mm subsystem users 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>
---
 mm/backing-dev.c | 2 +-
 mm/slub.c        | 3 ++-
 mm/vmstat.c      | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7e672424f928..3b392de6367e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -969,7 +969,7 @@ static int __init cgwb_init(void)
 	 * system_percpu_wq.  Put them in a separate wq and limit concurrency.
 	 * There's no point in executing many of these in parallel.
 	 */
-	cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+	cgwb_release_wq = alloc_workqueue("cgwb_release", WQ_PERCPU, 1);
 	if (!cgwb_release_wq)
 		return -ENOMEM;
 
diff --git a/mm/slub.c b/mm/slub.c
index b46f87662e71..cac9d5d7c924 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -6364,7 +6364,8 @@ void __init kmem_cache_init(void)
 void __init kmem_cache_init_late(void)
 {
 #ifndef CONFIG_SLUB_TINY
-	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);
+	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM | WQ_PERCPU,
+				  0);
 	WARN_ON(!flushwq);
 #endif
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4c268ce39ff2..57bf76b1d9d4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2244,7 +2244,8 @@ void __init init_mm_internals(void)
 {
 	int ret __maybe_unused;
 
-	mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0);
+	mm_percpu_wq = alloc_workqueue("mm_percpu_wq",
+				       WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 
 #ifdef CONFIG_SMP
 	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
-- 
2.51.0