Re: [RFC v3 1/2] workqueue: Add support for real-time workers
From: Tvrtko Ursulin
Date: Fri Jul 17 2026 - 06:13:47 EST
On 17/07/2026 10:02, Tvrtko Ursulin via Kernel-dev wrote:
For use cases such as the DRM scheduler submitting work to the GPU on
behalf of low latency userspace applications, where latter have sufficient
privileges to have had successfully obtained realtime Vulkan global
priority, competing with random background CPU load can create large
latency spikes which gets in the way of a smooth user experience.
For these situations the existing WQ_HIGHPRI does not bring a noticeable
improvement and a stronger hint is needed.
Lets add WQ_RTPRI which creates workers with a SCHED_FIFO scheduling class
to improve this.
We use a minimum priority level since we only care about winning the
contest against normal background CPU load. We also limit the number of
instantiated threads, both per workqueue to a maximum of two, or one on a
dual processor machine, and system-wide to one less than the number of
CPUs. The idea of that is to prevent system wide starvation caused by
potentially misbehaving work items.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxx>
Cc: Boris Brezillon <boris.brezillon@xxxxxxxxxxxxx>
Cc: Chia-I Wu <olv@xxxxxxxxxx>
Cc: Liviu Dudau <liviu.dudau@xxxxxxx>
Cc: Matthew Brost <matthew.brost@xxxxxxxxx>
Cc: Steven Price <steven.price@xxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
---
v2:
* Limit WQ_RTPRI to unbound workqueues and make it have strict CPU
affinitity. (Tejun)
* Fixed commit message typos. (AI)
* Fixed sysfs handling, max_active setting and user modified nice
application. (AI)
v3:
* Fix worker->pool null pointer dereference race by moving the
global decrement to detach_dying_workers().
* Rebase for upstream changes.
---
include/linux/workqueue.h | 23 ++++--
kernel/workqueue.c | 152 +++++++++++++++++++++++++++++---------
2 files changed, 135 insertions(+), 40 deletions(-)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index a283766a192a..e9ab53568e0c 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -140,6 +140,13 @@ enum wq_affn_scope {
WQ_AFFN_NR_TYPES,
};
+enum wq_priority {
+ WQ_PRIO_NORMAL = 0,
+ WQ_PRIO_HIGH = 1,
+ WQ_PRIO_RT = 2,
+ NUM_WQ_PRIO, /* Keep last */
+};
+
/**
* struct workqueue_attrs - A struct for workqueue attributes.
*
@@ -147,7 +154,12 @@ enum wq_affn_scope {
*/
struct workqueue_attrs {
/**
- * @nice: nice level
+ * @prio: priority level
+ */
+ enum wq_priority prio;
+
+ /**
+ * @nice: nice level for WQ_PRIO_HIGH
*/
int nice;
@@ -374,8 +386,9 @@ enum wq_flags {
WQ_FREEZABLE = 1 << 2, /* freeze during suspend */
WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
WQ_HIGHPRI = 1 << 4, /* high priority */
- WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */
- WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */
+ WQ_RTPRI = 1 << 5, /* real-time priority, valid only with WQ_UNBOUND */
+ WQ_CPU_INTENSIVE = 1 << 6, /* cpu intensive workqueue */
+ WQ_SYSFS = 1 << 7, /* visible in sysfs, see workqueue_sysfs_register() */
/*
* Per-cpu workqueues are generally preferred because they tend to
@@ -402,8 +415,8 @@ enum wq_flags {
*
* http://thread.gmane.org/gmane.linux.kernel/1480396
*/
- WQ_POWER_EFFICIENT = 1 << 7,
- WQ_PERCPU = 1 << 8, /* bound to a specific cpu */
+ WQ_POWER_EFFICIENT = 1 << 8,
+ WQ_PERCPU = 1 << 9, /* bound to a specific cpu */
__WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */
__WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 78068ae8f28a..30fed46a3164 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -509,10 +509,10 @@ static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */
static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
/* I: attributes used when instantiating standard unbound pools on demand */
-static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS + 1];
/* I: attributes used when instantiating ordered pools on demand */
-static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS + 1];
/*
* I: kthread_worker to release pwq's. pwq release needs to be bounced to a
@@ -546,6 +546,8 @@ EXPORT_SYMBOL_GPL(system_bh_highpri_wq);
struct workqueue_struct *system_dfl_long_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_dfl_long_wq);
+static atomic_t total_rtpri_workers = ATOMIC_INIT(0);
+
static int worker_thread(void *__worker);
static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
static void show_pwq(struct pool_workqueue *pwq);
@@ -1236,9 +1238,7 @@ static bool assign_work(struct work_struct *work, struct worker *worker,
static struct irq_work *bh_pool_irq_work(struct worker_pool *pool)
{
- int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0;
-
- return &per_cpu(bh_pool_irq_works, pool->cpu)[high];
+ return &per_cpu(bh_pool_irq_works, pool->cpu)[pool->attrs->prio];
}
static void kick_bh_pool(struct worker_pool *pool)
@@ -1251,7 +1251,7 @@ static void kick_bh_pool(struct worker_pool *pool)
return;
}
#endif
- if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+ if (pool->attrs->prio >= WQ_PRIO_HIGH)
raise_softirq_irqoff(HI_SOFTIRQ);
else
raise_softirq_irqoff(TASKLET_SOFTIRQ);
@@ -2809,13 +2809,16 @@ static int format_worker_id(char *buf, size_t size, struct worker *worker,
worker->rescue_wq->name);
if (pool) {
- if (pool->cpu >= 0)
+ if (pool->cpu >= 0) {
+ const char *suffix[NUM_WQ_PRIO] = { "", "H", "R" };
+
return scnprintf(buf, size, "kworker/%d:%d%s",
pool->cpu, worker->id,
- pool->attrs->nice < 0 ? "H" : "");
- else
+ suffix[pool->attrs->prio]);
+ } else {
return scnprintf(buf, size, "kworker/u%d:%d",
pool->id, worker->id);
+ }
} else {
return scnprintf(buf, size, "kworker/dying");
}
@@ -2838,12 +2841,30 @@ static struct worker *create_worker(struct worker_pool *pool)
struct worker *worker;
int id;
+ /*
+ * Do not consume all CPUs with RT workers to avoid scheduler
+ * starvation.
+ */
+ if (pool->attrs->prio == WQ_PRIO_RT) {
+ unsigned int max = num_online_cpus();
+
+ if (max > 2)
+ max = max - 1;
+ else
+ max = 1;
+
+ if (atomic_inc_return(&total_rtpri_workers) > max) {
+ atomic_dec(&total_rtpri_workers);
+ return NULL;
Sashiko is warning me here this can create a deadlock when called from maybe_create_worker(). My apparently naive idea was that this would make it wait for a bit, until the load on the currently instantiated workers subsides, at which point need_to_create_worker() would say "not any more" and allow it to exit.
But even more importantly, it is also warning me that strict CPU affinity creates per CPU threads.
So my idea of global limit will just not work.
Tejun, how does this sound to you? Are you okay without having the global limit of RT threads?
I will await sending v4 with other fixes until we can close on this one. I also have some vacation pending so there may be a delay in my replies.
+ }
+ }
+
/* ID is needed to determine kthread name */
id = ida_alloc(&pool->worker_ida, GFP_KERNEL);
if (id < 0) {
pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n",
ERR_PTR(id));
- return NULL;
+ goto fail_ida;
}
worker = alloc_worker(pool->node);
@@ -2871,7 +2892,11 @@ static struct worker *create_worker(struct worker_pool *pool)
goto fail;
}
- set_user_nice(worker->task, pool->attrs->nice);
+ if (pool->attrs->prio == WQ_PRIO_RT)
+ sched_set_fifo_low(worker->task);
+ else
+ set_user_nice(worker->task, pool->attrs->nice);
+
kthread_bind_mask(worker->task, pool_allowed_cpus(pool));
}
@@ -2896,6 +2921,9 @@ static struct worker *create_worker(struct worker_pool *pool)
return worker;
+fail_ida:
+ if (pool->attrs->prio == WQ_PRIO_RT)
+ atomic_dec(&total_rtpri_workers);
fail:
ida_free(&pool->worker_ida, id);
kfree(worker);
I failed on onion unwind here by not reversing the order. Fixed locally.
@@ -2906,8 +2934,11 @@ static void detach_dying_workers(struct list_head *cull_list)
{
struct worker *worker;
- list_for_each_entry(worker, cull_list, entry)
+ list_for_each_entry(worker, cull_list, entry) {
+ if (worker->pool->attrs->prio == WQ_PRIO_RT)
+ atomic_dec(&total_rtpri_workers);
detach_worker(worker);
+ }
}
static void reap_dying_workers(struct list_head *cull_list)
@@ -3773,7 +3804,7 @@ static void drain_dead_softirq_workfn(struct work_struct *work)
* don't hog this CPU's BH.
*/
if (repeat) {
- if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+ if (pool->attrs->prio >= WQ_PRIO_HIGH)
queue_work(system_bh_highpri_wq, work);
else
queue_work(system_bh_wq, work);
@@ -3805,7 +3836,7 @@ void workqueue_softirq_dead(unsigned int cpu)
dead_work.pool = pool;
init_completion(&dead_work.done);
- if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+ if (pool->attrs->prio >= WQ_PRIO_HIGH)
queue_work(system_bh_highpri_wq, &dead_work.work);
else
queue_work(system_bh_wq, &dead_work.work);
@@ -4780,6 +4811,7 @@ struct workqueue_attrs *alloc_workqueue_attrs_noprof(void)
static void copy_workqueue_attrs(struct workqueue_attrs *to,
const struct workqueue_attrs *from)
{
+ to->prio = from->prio;
to->nice = from->nice;
cpumask_copy(to->cpumask, from->cpumask);
cpumask_copy(to->__pod_cpumask, from->__pod_cpumask);
@@ -4811,6 +4843,7 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
{
u32 hash = 0;
+ hash = jhash_1word(attrs->prio, hash);
hash = jhash_1word(attrs->nice, hash);
hash = jhash_1word(attrs->affn_strict, hash);
hash = jhash(cpumask_bits(attrs->__pod_cpumask),
@@ -4825,6 +4858,8 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
static bool wqattrs_equal(const struct workqueue_attrs *a,
const struct workqueue_attrs *b)
{
+ if (a->prio != b->prio)
+ return false;
if (a->nice != b->nice)
return false;
if (a->affn_strict != b->affn_strict)
@@ -5601,11 +5636,17 @@ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu)
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
- bool highpri = wq->flags & WQ_HIGHPRI;
- int cpu, ret;
+ int prio, cpu, ret;
lockdep_assert_held(&wq_pool_mutex);
+ if (wq->flags & WQ_RTPRI)
+ prio = WQ_PRIO_RT;
+ else if (wq->flags & WQ_HIGHPRI)
+ prio = WQ_PRIO_HIGH;
+ else
+ prio = WQ_PRIO_NORMAL;
+
wq->cpu_pwq = alloc_percpu(struct pool_workqueue *);
if (!wq->cpu_pwq)
goto enomem;
@@ -5622,7 +5663,7 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
struct pool_workqueue **pwq_p;
struct worker_pool *pool;
- pool = &(per_cpu_ptr(pools, cpu)[highpri]);
+ pool = &(per_cpu_ptr(pools, cpu)[prio]);
pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu);
*pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL,
@@ -5642,14 +5683,14 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
if (wq->flags & __WQ_ORDERED) {
struct pool_workqueue *dfl_pwq;
- ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]);
+ ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[prio]);
/* there should only be single pwq for ordering guarantee */
dfl_pwq = rcu_access_pointer(wq->dfl_pwq);
WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node ||
wq->pwqs.prev != &dfl_pwq->pwqs_node),
"ordering guarantee broken for workqueue %s\n", wq->name);
} else {
- ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]);
+ ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[prio]);
}
if (ret)
@@ -5814,6 +5855,12 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
return NULL;
}
+ if (flags & WQ_RTPRI) {
+ if (WARN_ON_ONCE((flags & (WQ_HIGHPRI | WQ_UNBOUND)) !=
+ WQ_UNBOUND))
+ return NULL;
+ }
+
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
flags = (flags & ~WQ_PERCPU) | WQ_UNBOUND;
@@ -5857,7 +5904,17 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
flags &= ~WQ_PERCPU;
}
- if (flags & WQ_BH) {
+ if (flags & WQ_RTPRI) {
+ /*
+ * RT workqueues are limited to max half of possible CPUs to
+ * avoid scheduling starvation and have strict CPU affinity for
+ * low latency execution.
+ */
+ max_active = min_t(int, max_active,
+ DIV_ROUND_UP(num_possible_cpus(), 2));
+ wq->unbound_attrs->affn_scope = WQ_AFFN_CPU;
+ wq->unbound_attrs->affn_strict = true;
Sashiko let me know this will get overwritten by default attributes so I have moved it to where latter are initialized in workqueue_init_early().
Regards,
Tvrtko
+ } else if (flags & WQ_BH) {
/*
* BH workqueues always share a single execution context per CPU
* and don't impose any max_active limit.
@@ -6359,17 +6416,26 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
}
}
+static void pr_cont_bh_suffix(enum wq_priority prio)
+{
+ if (prio == WQ_PRIO_RT)
+ pr_cont("bh-rt");
+ else if (prio == WQ_PRIO_HIGH)
+ pr_cont("bh-hi");
+ else
+ pr_cont("bh");
+}
+
static void pr_cont_pool_info(struct worker_pool *pool)
{
pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask);
if (pool->node != NUMA_NO_NODE)
pr_cont(" node=%d", pool->node);
- pr_cont(" flags=0x%x", pool->flags);
+ pr_cont(" flags=0x%x ", pool->flags);
if (pool->flags & POOL_BH)
- pr_cont(" bh%s",
- pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
+ pr_cont_bh_suffix(pool->attrs->prio);
else
- pr_cont(" nice=%d", pool->attrs->nice);
+ pr_cont("prio=%d", pool->attrs->prio);
}
static void pr_cont_worker_id(struct worker *worker)
@@ -6377,8 +6443,7 @@ static void pr_cont_worker_id(struct worker *worker)
struct worker_pool *pool = worker->pool;
if (pool->flags & POOL_BH)
- pr_cont("bh%s",
- pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
+ pr_cont_bh_suffix(pool->attrs->prio);
else
pr_cont("%d%s", task_pid_nr(worker->task),
worker->rescue_wq ? "(RESCUER)" : "");
@@ -7302,7 +7367,11 @@ static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
int written;
mutex_lock(&wq->mutex);
- written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice);
+ if (wq->unbound_attrs->prio != WQ_PRIO_RT)
+ written = scnprintf(buf, PAGE_SIZE, "%d\n",
+ wq->unbound_attrs->nice);
+ else
+ written = -EINVAL;
mutex_unlock(&wq->mutex);
return written;
@@ -7328,13 +7397,20 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
{
struct workqueue_struct *wq = dev_to_wq(dev);
struct workqueue_attrs *attrs;
- int ret = -ENOMEM;
+ int ret;
mutex_lock(&wq_pool_mutex);
attrs = wq_sysfs_prep_attrs(wq);
- if (!attrs)
+ if (!attrs) {
+ ret = -ENOMEM;
goto out_unlock;
+ }
+
+ if (attrs->prio == WQ_PRIO_RT) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
if (sscanf(buf, "%d", &attrs->nice) == 1 &&
attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
@@ -7942,12 +8018,13 @@ static void __init restrict_unbound_cpumask(const char *name, const struct cpuma
cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
}
-static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice)
+static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, enum wq_priority prio, int nice)
{
BUG_ON(init_worker_pool(pool));
pool->cpu = cpu;
cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu));
+ pool->attrs->prio = prio;
pool->attrs->nice = nice;
pool->attrs->affn_strict = true;
pool->node = cpu_to_node(cpu);
@@ -7971,7 +8048,8 @@ static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int n
void __init workqueue_init_early(void)
{
struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM];
- int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
+ int std_prio[NR_STD_WORKER_POOLS + 1] = { 0, WQ_PRIO_HIGH, WQ_PRIO_RT };
+ int std_nice[NR_STD_WORKER_POOLS + 1] = { 0, HIGHPRI_NICE_LEVEL, 0 };
void (*irq_work_fns[NR_STD_WORKER_POOLS])(struct irq_work *) =
{ bh_pool_kick_normal, bh_pool_kick_highpri };
int i, cpu;
@@ -8023,22 +8101,25 @@ void __init workqueue_init_early(void)
i = 0;
for_each_bh_worker_pool(pool, cpu) {
- init_cpu_worker_pool(pool, cpu, std_nice[i]);
+ init_cpu_worker_pool(pool, cpu, std_prio[i], std_nice[i]);
pool->flags |= POOL_BH;
init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]);
i++;
}
i = 0;
- for_each_cpu_worker_pool(pool, cpu)
- init_cpu_worker_pool(pool, cpu, std_nice[i++]);
+ for_each_cpu_worker_pool(pool, cpu) {
+ init_cpu_worker_pool(pool, cpu, std_prio[i], std_nice[i]);
+ i++;
+ }
}
/* create default unbound and ordered wq attrs */
- for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
+ for (i = 0; i < NR_STD_WORKER_POOLS + 1; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs()));
+ attrs->prio = std_prio[i];
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
@@ -8047,6 +8128,7 @@ void __init workqueue_init_early(void)
* guaranteed by max_active which is enforced by pwqs.
*/
BUG_ON(!(attrs = alloc_workqueue_attrs()));
+ attrs->prio = std_prio[i];
attrs->nice = std_nice[i];
attrs->ordered = true;
ordered_wq_attrs[i] = attrs;