[RFC v4 1/2] workqueue: Add support for real-time workers

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.

Signed-off-by: Tvrtko Ursulin <[email protected]>
Cc: Boris Brezillon <[email protected]>
Cc: Bradley Morgan <[email protected]>
Cc: Chia-I Wu <[email protected]>
Cc: Liviu Dudau <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Steven Price <[email protected]>
Cc: Tejun Heo <[email protected]>
---
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.

v4:
 * Fixed onion unwind.
 * Moved affinity setting to default attributes.

v5:
 * Dropped global and local limits.
 * Documented in workqueue.rst.
 * Added NR_WQ_ATTRIBUTES.
 * Reverted BH handling changes.
---
 Documentation/core-api/workqueue.rst |  5 ++
 include/linux/workqueue.h            | 23 ++++++--
 kernel/workqueue.c                   | 80 ++++++++++++++++++++++------
 3 files changed, 86 insertions(+), 22 deletions(-)

diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index 411e1b28b8de..6b6179e0a38a 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -225,6 +225,11 @@ resources, scheduled and executed.
   each other.  Each maintains its separate pool of workers and
   implements concurrency management among its workers.
 
+``WQ_RTPRI``
+  Real time priority workqueues must be created as unbound and have the strict
+  CPU affinity set.  Their worker threads use the FIFO scheduling policy with
+  the lowest priority.
+
 ``WQ_CPU_INTENSIVE``
   Work items of a CPU intensive wq do not contribute to the
   concurrency level.  In other words, runnable CPU intensive
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..6b60380a8742 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -105,6 +105,7 @@ enum work_cancel_flags {
 
 enum wq_internal_consts {
 	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */
+	NR_WQ_ATTRIBUTES	= NUM_WQ_PRIO,	/* # of attributes */
 
 	UNBOUND_POOL_HASH_ORDER	= 6,		/* hashed by pool->attrs */
 	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */
@@ -509,10 +510,10 @@ 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_WQ_ATTRIBUTES];
 
 /* 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_WQ_ATTRIBUTES];
 
 /*
  * I: kthread_worker to release pwq's. pwq release needs to be bounced to a
@@ -2871,7 +2872,11 @@ 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));
 	}
 
@@ -4780,6 +4785,7 @@ 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 +4817,7 @@ 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 +4832,8 @@ 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 +5610,17 @@ 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 +5637,7 @@ 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 +5657,14 @@ 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 +5829,12 @@ 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;
@@ -7302,7 +7323,11 @@ 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 +7353,20 @@ 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 +7974,13 @@ 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 +8004,8 @@ 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_WQ_ATTRIBUTES] = { 0, WQ_PRIO_HIGH, WQ_PRIO_RT };
+	int std_nice[NR_WQ_ATTRIBUTES] = { 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;
@@ -8023,23 +8057,34 @@ 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_WQ_ATTRIBUTES; i++) {
 		struct workqueue_attrs *attrs;
 
 		BUG_ON(!(attrs = alloc_workqueue_attrs()));
+		attrs->prio = std_prio[i];
 		attrs->nice = std_nice[i];
+		if (i == WQ_PRIO_RT) {
+			/*
+			 * RT workqueues have strict CPU affinity for low
+			 * latency execution.
+			 */
+			attrs->affn_scope = WQ_AFFN_CPU;
+			attrs->affn_strict = true;
+		}
 		unbound_std_wq_attrs[i] = attrs;
 
 		/*
@@ -8047,6 +8092,7 @@ 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;
-- 
2.54.0