[RFC PATCH V4 1/5] workqueue: rename system workqueues

[RFC PATCH V4 1/5] workqueue: rename system workqueues

[Wen Yang]

Rename system_wq's wq->name from "events" to "system_percpu",
and similarly for the similarly named workqueues.

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: linux-kernel@vger.kernel.org
---
 kernel/workqueue.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f699122..67b68bb 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -5601,16 +5601,18 @@ int __init workqueue_init_early(void)
 		ordered_wq_attrs[i] = attrs;
 	}
 
-	system_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_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
+	system_wq = alloc_workqueue("system_percpu", 0, 0);
+	system_highpri_wq = alloc_workqueue("system_percpu_highpri",
+					    WQ_HIGHPRI, 0);
+	system_long_wq = alloc_workqueue("system_percpu_long", 0, 0);
+	system_unbound_wq = alloc_workqueue("system_unbound", WQ_UNBOUND,
 					    WQ_UNBOUND_MAX_ACTIVE);
-	system_freezable_wq = alloc_workqueue("events_freezable",
+	system_freezable_wq = alloc_workqueue("system_percpu_freezable",
 					      WQ_FREEZABLE, 0);
-	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
+	system_power_efficient_wq = alloc_workqueue("system_percpu_power_efficient",
 					      WQ_POWER_EFFICIENT, 0);
-	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
+	system_freezable_power_efficient_wq = alloc_workqueue(
+					      "system_percpu_freezable_power_efficient",
 					      WQ_FREEZABLE | WQ_POWER_EFFICIENT,
 					      0);
 	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-- 
1.8.3.1

[RFC PATCH V4 2/5] workqueue: expose attrs for system workqueues

[Wen Yang]

Expose sched_attr for system workqueues, such as:
	# cat   /sys/devices/virtual/workqueue/system_percpu/sched_attr
	policy=0 prio=0 nice=0
 	cat   /sys/devices/virtual/workqueue/system_percpu_highpri/sched_attr
	policy=0 prio=0 nice=-20

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: kernel test robot <xiaolong.ye@intel.com>
Cc: linux-kernel@vger.kernel.org
---
 include/linux/workqueue.h |  6 ++++++
 kernel/workqueue.c        | 50 +++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 4a54ef9..9faaade 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -13,6 +13,7 @@
 #include <linux/threads.h>
 #include <linux/atomic.h>
 #include <linux/cpumask.h>
+#include <uapi/linux/sched/types.h>
 
 struct workqueue_struct;
 
@@ -132,6 +133,11 @@ struct workqueue_attrs {
 	int nice;
 
 	/**
+	 * @sched_attr: kworker's scheduling parameters
+	 */
+	struct sched_attr sched_attr;
+
+	/**
 	 * @cpumask: allowed CPUs
 	 */
 	cpumask_var_t cpumask;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 67b68bb..993f225 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -256,6 +256,7 @@ struct workqueue_struct {
 	int			saved_max_active; /* WQ: saved pwq max_active */
 
 	struct workqueue_attrs	*unbound_attrs;	/* PW: only for unbound wqs */
+	struct workqueue_attrs  *attrs;
 	struct pool_workqueue	*dfl_pwq;	/* PW: only for unbound wqs */
 
 #ifdef CONFIG_SYSFS
@@ -1699,6 +1700,7 @@ static void worker_attach_to_pool(struct worker *worker,
 	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
 	 */
 	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+	sched_setattr(worker->task, &pool->attrs->sched_attr);
 
 	/*
 	 * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains
@@ -3166,10 +3168,20 @@ struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
 	return NULL;
 }
 
+static void copy_sched_attr(struct sched_attr *to,
+		const struct sched_attr *from)
+{
+	to->sched_policy = from->sched_policy;
+	to->sched_priority = from->sched_priority;
+	to->sched_nice = from->sched_nice;
+	to->sched_flags = from->sched_flags;
+}
+
 static void copy_workqueue_attrs(struct workqueue_attrs *to,
 				 const struct workqueue_attrs *from)
 {
 	to->nice = from->nice;
+	copy_sched_attr(&to->sched_attr, &from->sched_attr);
 	cpumask_copy(to->cpumask, from->cpumask);
 	/*
 	 * Unlike hash and equality test, this function doesn't ignore
@@ -3250,7 +3262,7 @@ static void rcu_free_wq(struct rcu_head *rcu)
 		free_percpu(wq->cpu_pwqs);
 	else
 		free_workqueue_attrs(wq->unbound_attrs);
-
+	free_workqueue_attrs(wq->attrs);
 	kfree(wq->rescuer);
 	kfree(wq);
 }
@@ -3979,6 +3991,10 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 			goto err_free_wq;
 	}
 
+	wq->attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	if (!wq->attrs)
+		goto err_free_wq;
+
 	va_start(args, lock_name);
 	vsnprintf(wq->name, sizeof(wq->name), fmt, args);
 	va_end(args);
@@ -3999,6 +4015,11 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
 	INIT_LIST_HEAD(&wq->list);
 
+	wq->attrs->sched_attr.sched_policy = SCHED_NORMAL;
+	wq->attrs->sched_attr.sched_priority = 0;
+	wq->attrs->sched_attr.sched_nice = wq->flags & WQ_HIGHPRI ?
+		HIGHPRI_NICE_LEVEL : 0;
+
 	if (alloc_and_link_pwqs(wq) < 0)
 		goto err_free_wq;
 
@@ -4049,6 +4070,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 
 err_free_wq:
 	free_workqueue_attrs(wq->unbound_attrs);
+	free_workqueue_attrs(wq->attrs);
 	kfree(wq);
 	return NULL;
 err_destroy:
@@ -5043,9 +5065,29 @@ static ssize_t max_active_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(max_active);
 
+static ssize_t sched_attr_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	size_t written;
+	struct workqueue_struct *wq = dev_to_wq(dev);
+
+	mutex_lock(&wq->mutex);
+	written = scnprintf(buf, PAGE_SIZE,
+			"policy=%u prio=%u nice=%d\n",
+			wq->attrs->sched_attr.sched_policy,
+			wq->attrs->sched_attr.sched_priority,
+			wq->attrs->sched_attr.sched_nice);
+	mutex_unlock(&wq->mutex);
+
+	return written;
+}
+
+static DEVICE_ATTR_RO(sched_attr);
+
 static struct attribute *wq_sysfs_attrs[] = {
 	&dev_attr_per_cpu.attr,
 	&dev_attr_max_active.attr,
+	&dev_attr_sched_attr.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(wq_sysfs);
@@ -5254,7 +5296,11 @@ static int __init wq_sysfs_init(void)
 	if (err)
 		return err;
 
-	return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr);
+	err = device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr);
+	if (err)
+		return err;
+	return workqueue_sysfs_register(system_wq) ||
+		workqueue_sysfs_register(system_highpri_wq);
 }
 core_initcall(wq_sysfs_init);
 
-- 
1.8.3.1

[RFC PATCH V4 3/5] workqueue: rename unbound_attrs to attrs

[Wen Yang]

Replace workqueue's unbound_attrs by attrs, so that both unbound
or bound wq can use it.

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: kernel test robot <xiaolong.ye@intel.com>
Cc: linux-kernel@vger.kernel.org
---
 kernel/workqueue.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 993f225..e1613d0 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -255,7 +255,6 @@ struct workqueue_struct {
 	int			nr_drainers;	/* WQ: drain in progress */
 	int			saved_max_active; /* WQ: saved pwq max_active */
 
-	struct workqueue_attrs	*unbound_attrs;	/* PW: only for unbound wqs */
 	struct workqueue_attrs  *attrs;
 	struct pool_workqueue	*dfl_pwq;	/* PW: only for unbound wqs */
 
@@ -3737,7 +3736,7 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
 	/* all pwqs have been created successfully, let's install'em */
 	mutex_lock(&ctx->wq->mutex);
 
-	copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs);
+	copy_workqueue_attrs(ctx->wq->attrs, ctx->attrs);
 
 	/* save the previous pwq and install the new one */
 	for_each_node(node)
@@ -3854,7 +3853,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	lockdep_assert_held(&wq_pool_mutex);
 
 	if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) ||
-	    wq->unbound_attrs->no_numa)
+	    wq->attrs->no_numa)
 		return;
 
 	/*
@@ -3865,7 +3864,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	target_attrs = wq_update_unbound_numa_attrs_buf;
 	cpumask = target_attrs->cpumask;
 
-	copy_workqueue_attrs(target_attrs, wq->unbound_attrs);
+	copy_workqueue_attrs(target_attrs, wq->attrs);
 	pwq = unbound_pwq_by_node(wq, node);
 
 	/*
@@ -3985,12 +3984,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	if (!wq)
 		return NULL;
 
-	if (flags & WQ_UNBOUND) {
-		wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL);
-		if (!wq->unbound_attrs)
-			goto err_free_wq;
-	}
-
 	wq->attrs = alloc_workqueue_attrs(GFP_KERNEL);
 	if (!wq->attrs)
 		goto err_free_wq;
@@ -4069,7 +4062,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	return wq;
 
 err_free_wq:
-	free_workqueue_attrs(wq->unbound_attrs);
 	free_workqueue_attrs(wq->attrs);
 	kfree(wq);
 	return NULL;
@@ -4941,7 +4933,7 @@ static int workqueue_apply_unbound_cpumask(void)
 		if (wq->flags & __WQ_ORDERED)
 			continue;
 
-		ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
+		ctx = apply_wqattrs_prepare(wq, wq->attrs);
 		if (!ctx) {
 			ret = -ENOMEM;
 			break;
@@ -5119,7 +5111,7 @@ 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);
+	written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->attrs->nice);
 	mutex_unlock(&wq->mutex);
 
 	return written;
@@ -5136,7 +5128,7 @@ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
 	if (!attrs)
 		return NULL;
 
-	copy_workqueue_attrs(attrs, wq->unbound_attrs);
+	copy_workqueue_attrs(attrs, wq->attrs);
 	return attrs;
 }
 
@@ -5173,7 +5165,7 @@ static ssize_t wq_cpumask_show(struct device *dev,
 
 	mutex_lock(&wq->mutex);
 	written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
-			    cpumask_pr_args(wq->unbound_attrs->cpumask));
+			    cpumask_pr_args(wq->attrs->cpumask));
 	mutex_unlock(&wq->mutex);
 	return written;
 }
@@ -5210,7 +5202,7 @@ static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&wq->mutex);
 	written = scnprintf(buf, PAGE_SIZE, "%d\n",
-			    !wq->unbound_attrs->no_numa);
+			    !wq->attrs->no_numa);
 	mutex_unlock(&wq->mutex);
 
 	return written;
-- 
1.8.3.1

[RFC PATCH V4 4/5] workqueue: convert ->nice to ->sched_attr

[Wen Yang]

The new /sys interface like this:
	#cat /sys/devices/virtual/workqueue/writeback/sched_attr
	policy=0 prio=0 nice=0

	# echo "policy=0 prio=0 nice=-1" > /sys/devices/virtual/workqueue/writeback/sched_attr
	# cat /sys/devices/virtual/workqueue/writeback/sched_attr
	policy=0 prio=0 nice=-1

Also, the possibility of specifying more than just a priority
for the wq may be useful for a wide variety of applications.

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: kernel test robot <xiaolong.ye@intel.com>
Cc: linux-kernel@vger.kernel.org
---
 include/linux/workqueue.h |   5 --
 kernel/workqueue.c        | 130 ++++++++++++++++++++++++++++------------------
 2 files changed, 79 insertions(+), 56 deletions(-)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 9faaade..d9d0f36 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -128,11 +128,6 @@ struct delayed_work {
  */
 struct workqueue_attrs {
 	/**
-	 * @nice: nice level
-	 */
-	int nice;
-
-	/**
 	 * @sched_attr: kworker's scheduling parameters
 	 */
 	struct sched_attr sched_attr;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e1613d0..8c5aba5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1773,7 +1773,7 @@ static struct worker *create_worker(struct worker_pool *pool)
 
 	if (pool->cpu >= 0)
 		snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id,
-			 pool->attrs->nice < 0  ? "H" : "");
+			 pool->attrs->sched_attr.sched_nice < 0  ? "H" : "");
 	else
 		snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id);
 
@@ -1782,7 +1782,7 @@ static struct worker *create_worker(struct worker_pool *pool)
 	if (IS_ERR(worker->task))
 		goto fail;
 
-	set_user_nice(worker->task, pool->attrs->nice);
+	set_user_nice(worker->task, pool->attrs->sched_attr.sched_nice);
 	kthread_bind_mask(worker->task, pool->attrs->cpumask);
 
 	/* successful, attach the worker to the pool */
@@ -3179,7 +3179,6 @@ static void copy_sched_attr(struct sched_attr *to,
 static void copy_workqueue_attrs(struct workqueue_attrs *to,
 				 const struct workqueue_attrs *from)
 {
-	to->nice = from->nice;
 	copy_sched_attr(&to->sched_attr, &from->sched_attr);
 	cpumask_copy(to->cpumask, from->cpumask);
 	/*
@@ -3195,17 +3194,29 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
 {
 	u32 hash = 0;
 
-	hash = jhash_1word(attrs->nice, hash);
+	hash = jhash_1word(attrs->sched_attr.sched_nice, hash);
 	hash = jhash(cpumask_bits(attrs->cpumask),
 		     BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
 	return hash;
 }
 
+static bool sched_attr_equal(const struct sched_attr *a,
+		const struct sched_attr *b)
+{
+	if (a->sched_policy != b->sched_policy)
+		return false;
+	if (a->sched_priority != b->sched_priority)
+		return false;
+	if (a->sched_nice != b->sched_nice)
+		return false;
+	return true;
+}
+
 /* content equality test */
 static bool wqattrs_equal(const struct workqueue_attrs *a,
 			  const struct workqueue_attrs *b)
 {
-	if (a->nice != b->nice)
+	if (a->sched_attr.sched_nice != b->sched_attr.sched_nice)
 		return false;
 	if (!cpumask_equal(a->cpumask, b->cpumask))
 		return false;
@@ -3259,8 +3270,6 @@ static void rcu_free_wq(struct rcu_head *rcu)
 
 	if (!(wq->flags & WQ_UNBOUND))
 		free_percpu(wq->cpu_pwqs);
-	else
-		free_workqueue_attrs(wq->unbound_attrs);
 	free_workqueue_attrs(wq->attrs);
 	kfree(wq->rescuer);
 	kfree(wq);
@@ -4353,7 +4362,8 @@ 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 nice=%d", pool->flags, pool->attrs->nice);
+	pr_cont(" flags=0x%x nice=%d", pool->flags,
+			pool->attrs->sched_attr.sched_nice);
 }
 
 static void pr_cont_work(bool comma, struct work_struct *work)
@@ -5074,7 +5084,64 @@ static ssize_t sched_attr_show(struct device *dev,
 	return written;
 }
 
-static DEVICE_ATTR_RO(sched_attr);
+static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq);
+
+static int wq_set_unbound_sched_attr(struct workqueue_struct *wq,
+		const struct sched_attr *new)
+{
+	struct workqueue_attrs *attrs;
+	int ret = -ENOMEM;
+
+	apply_wqattrs_lock();
+	attrs = wq_sysfs_prep_attrs(wq);
+	if (!attrs)
+		goto out_unlock;
+	copy_sched_attr(&attrs->sched_attr, new);
+	ret = apply_workqueue_attrs_locked(wq, attrs);
+
+out_unlock:
+	apply_wqattrs_unlock();
+	free_workqueue_attrs(attrs);
+	return ret;
+}
+
+static ssize_t sched_attr_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct workqueue_struct *wq = dev_to_wq(dev);
+	struct sched_attr new = {
+		.size = sizeof(struct sched_attr),
+		.sched_policy = SCHED_NORMAL,
+		.sched_flags = 0,
+		.sched_priority = 0,
+	};
+	int ret = 0;
+
+	if (!capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	if (sscanf(buf, "policy=0 prio=0 nice=%d",
+				&new.sched_nice) != 1)
+		return -EINVAL;
+
+	pr_debug("set wq's sched_attr: policy=%u prio=%u nice=%d\n",
+			new.sched_policy,
+			new.sched_priority,
+			new.sched_nice);
+	mutex_lock(&wq->mutex);
+	if (sched_attr_equal(&wq->attrs->sched_attr, &new)) {
+		mutex_unlock(&wq->mutex);
+		return count;
+	}
+	mutex_unlock(&wq->mutex);
+
+	if (wq->flags & WQ_UNBOUND)
+		ret = wq_set_unbound_sched_attr(wq, &new);
+	else
+		ret = -EPERM;
+	return ret ?: count;
+}
+static DEVICE_ATTR_RW(sched_attr);
 
 static struct attribute *wq_sysfs_attrs[] = {
 	&dev_attr_per_cpu.attr,
@@ -5104,19 +5171,6 @@ static ssize_t wq_pool_ids_show(struct device *dev,
 	return written;
 }
 
-static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
-			    char *buf)
-{
-	struct workqueue_struct *wq = dev_to_wq(dev);
-	int written;
-
-	mutex_lock(&wq->mutex);
-	written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->attrs->nice);
-	mutex_unlock(&wq->mutex);
-
-	return written;
-}
-
 /* prepare workqueue_attrs for sysfs store operations */
 static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
 {
@@ -5132,31 +5186,6 @@ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
 	return attrs;
 }
 
-static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
-{
-	struct workqueue_struct *wq = dev_to_wq(dev);
-	struct workqueue_attrs *attrs;
-	int ret = -ENOMEM;
-
-	apply_wqattrs_lock();
-
-	attrs = wq_sysfs_prep_attrs(wq);
-	if (!attrs)
-		goto out_unlock;
-
-	if (sscanf(buf, "%d", &attrs->nice) == 1 &&
-	    attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
-		ret = apply_workqueue_attrs_locked(wq, attrs);
-	else
-		ret = -EINVAL;
-
-out_unlock:
-	apply_wqattrs_unlock();
-	free_workqueue_attrs(attrs);
-	return ret ?: count;
-}
-
 static ssize_t wq_cpumask_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -5235,7 +5264,6 @@ static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr,
 
 static struct device_attribute wq_sysfs_unbound_attrs[] = {
 	__ATTR(pool_ids, 0444, wq_pool_ids_show, NULL),
-	__ATTR(nice, 0644, wq_nice_show, wq_nice_store),
 	__ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store),
 	__ATTR(numa, 0644, wq_numa_show, wq_numa_store),
 	__ATTR_NULL,
@@ -5610,7 +5638,7 @@ int __init workqueue_init_early(void)
 			BUG_ON(init_worker_pool(pool));
 			pool->cpu = cpu;
 			cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
-			pool->attrs->nice = std_nice[i++];
+			pool->attrs->sched_attr.sched_nice = std_nice[i++];
 			pool->node = cpu_to_node(cpu);
 
 			/* alloc pool ID */
@@ -5625,7 +5653,7 @@ int __init workqueue_init_early(void)
 		struct workqueue_attrs *attrs;
 
 		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
-		attrs->nice = std_nice[i];
+		attrs->sched_attr.sched_nice = std_nice[i];
 		unbound_std_wq_attrs[i] = attrs;
 
 		/*
@@ -5634,7 +5662,7 @@ int __init workqueue_init_early(void)
 		 * Turn off NUMA so that dfl_pwq is used for all nodes.
 		 */
 		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
-		attrs->nice = std_nice[i];
+		attrs->sched_attr.sched_nice = std_nice[i];
 		attrs->no_numa = true;
 		ordered_wq_attrs[i] = attrs;
 	}
-- 
1.8.3.1

[RFC PATCH V4 5/5] workqueue: introduce a way to set workqueue's scheduler

[Wen Yang]

When pinning RT threads to specific cores using CPU affinity, the
kworkers on the same CPU would starve, which may lead to some kind
of priority inversion. In that case, the RT threads would also
suffer high performance impact.

The priority inversion looks like,
CPU 0:  libvirtd acquired cgroup_mutex, and triggered
lru_add_drain_per_cpu, then waiting for all the kworkers to complete:
	PID: 44145  TASK: ffff8807bec7b980  CPU: 0   COMMAND: "libvirtd"
	#0 [ffff8807f2cbb9d0] __schedule at ffffffff816410ed
	#1 [ffff8807f2cbba38] schedule at ffffffff81641789
	#2 [ffff8807f2cbba48] schedule_timeout at ffffffff8163f479
	#3 [ffff8807f2cbbaf8] wait_for_completion at ffffffff81641b56
	#4 [ffff8807f2cbbb58] flush_work at ffffffff8109efdc
	#5 [ffff8807f2cbbbd0] lru_add_drain_all at ffffffff81179002
	#6 [ffff8807f2cbbc08] migrate_prep at ffffffff811c77be
	#7 [ffff8807f2cbbc18] do_migrate_pages at ffffffff811b8010
	#8 [ffff8807f2cbbcf8] cpuset_migrate_mm at ffffffff810fea6c
	#9 [ffff8807f2cbbd10] cpuset_attach at ffffffff810ff91e
	#10 [ffff8807f2cbbd50] cgroup_attach_task at ffffffff810f9972
	#11 [ffff8807f2cbbe08] attach_task_by_pid at ffffffff810fa520
	#12 [ffff8807f2cbbe58] cgroup_tasks_write at ffffffff810fa593
	#13 [ffff8807f2cbbe68] cgroup_file_write at ffffffff810f8773
	#14 [ffff8807f2cbbef8] vfs_write at ffffffff811dfdfd
	#15 [ffff8807f2cbbf38] sys_write at ffffffff811e089f
	#16 [ffff8807f2cbbf80] system_call_fastpath at ffffffff8164c809

CPU 43: kworker/43 starved because of the RT threads:
	CURRENT: PID: 21294  TASK: ffff883fd2d45080  COMMAND: "lwip"
	RT PRIO_ARRAY: ffff883fff3f4950
	[ 79] PID: 21294  TASK: ffff883fd2d45080  COMMAND: "lwip"
	[ 79] PID: 21295  TASK: ffff88276d481700  COMMAND: "ovdk-ovsvswitch"
	[ 79] PID: 21351  TASK: ffff8807be822280  COMMAND: "dispatcher"
	[ 79] PID: 21129  TASK: ffff8807bef0f300  COMMAND: "ovdk-ovsvswitch"
	[ 79] PID: 21337  TASK: ffff88276d482e00  COMMAND: "handler_3"
	[ 79] PID: 21352  TASK: ffff8807be824500  COMMAND: "flow_dumper"
	[ 79] PID: 21336  TASK: ffff88276d480b80  COMMAND: "handler_2"
	[ 79] PID: 21342  TASK: ffff88276d484500  COMMAND: "handler_8"
	[ 79] PID: 21341  TASK: ffff88276d482280  COMMAND: "handler_7"
	[ 79] PID: 21338  TASK: ffff88276d483980  COMMAND: "handler_4"
	[ 79] PID: 21339  TASK: ffff88276d480000  COMMAND: "handler_5"
	[ 79] PID: 21340  TASK: ffff88276d486780  COMMAND: "handler_6"
	CFS RB_ROOT: ffff883fff3f4868
	[120] PID: 37959  TASK: ffff88276e148000  COMMAND: "kworker/43:1"

CPU 28: Systemd(Victim) was blocked by cgroup_mutex:
	PID: 1      TASK: ffff883fd2d40000  CPU: 28  COMMAND: "systemd"
	#0 [ffff881fd317bd60] __schedule at ffffffff816410ed
	#1 [ffff881fd317bdc8] schedule_preempt_disabled at ffffffff81642869
	#2 [ffff881fd317bdd8] __mutex_lock_slowpath at ffffffff81640565
	#3 [ffff881fd317be38] mutex_lock at ffffffff8163f9cf
	#4 [ffff881fd317be50] proc_cgroup_show at ffffffff810fd256
	#5 [ffff881fd317be98] seq_read at ffffffff81203cda
	#6 [ffff881fd317bf08] vfs_read at ffffffff811dfc6c
	#7 [ffff881fd317bf38] sys_read at ffffffff811e07bf
	#8 [ffff881fd317bf80] system_call_fastpath at ffffffff81

The simplest way to fix that is to set the scheduler of kworkers to
higher RT priority, just like,
chrt --fifo -p 61 <kworker_pid>
However, it can not avoid other WORK_CPU_BOUND worker threads running
and starving.

This patch introduces a way to set the scheduler(policy and priority)
of percpu worker_pool, in that way, user could set proper scheduler
policy and priority of the worker_pool as needed, which could apply
to all the WORK_CPU_BOUND workers on the same CPU. On the other hand,
we could using /sys/devices/virtual/workqueue/cpumask for
WORK_CPU_UNBOUND workers to prevent them starving.

Tejun Heo suggested:
"* Add scheduler type to wq_attrs so that unbound workqueues can be
 configured.

* Rename system_wq's wq->name from "events" to "system_percpu", and
 similarly for the similarly named workqueues.

* Enable wq_attrs (only the applicable part should show up in the
 interface) for system_percpu and system_percpu_highpri, and use that
 to change the attributes of the percpu pools."

This patch implements the basic infrastructure and /sys interface,
such as:
	# cat  /sys/devices/virtual/workqueue/system_percpu/sched_attr
	policy=0 prio=0 nice=0
	# echo "policy=1 prio=1 nice=0" > /sys/devices/virtual/workqueue/system_percpu/sched_attr
	# cat  /sys/devices/virtual/workqueue/system_percpu/sched_attr
	policy=1 prio=1 nice=0
	# cat  /sys/devices/virtual/workqueue/system_percpu_highpri/sched_attr
	policy=0 prio=0 nice=-20
	# echo "policy=1 prio=2 nice=0" > /sys/devices/virtual/workqueue/system_percpu_highpri/sched_attr
	# cat  /sys/devices/virtual/workqueue/system_percpu_highpri/sched_attr
	policy=1 prio=2 nice=0

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: kernel test robot <xiaolong.ye@intel.com>
Cc: linux-kernel@vger.kernel.org
---
 kernel/workqueue.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 6 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8c5aba5..7eb33b5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3194,7 +3194,10 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
 {
 	u32 hash = 0;
 
-	hash = jhash_1word(attrs->sched_attr.sched_nice, hash);
+	hash = jhash_3words(attrs->sched_attr.sched_policy,
+			attrs->sched_attr.sched_priority,
+			attrs->sched_attr.sched_nice,
+			hash);
 	hash = jhash(cpumask_bits(attrs->cpumask),
 		     BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
 	return hash;
@@ -3216,7 +3219,7 @@ static bool sched_attr_equal(const struct sched_attr *a,
 static bool wqattrs_equal(const struct workqueue_attrs *a,
 			  const struct workqueue_attrs *b)
 {
-	if (a->sched_attr.sched_nice != b->sched_attr.sched_nice)
+	if (!sched_attr_equal(&a->sched_attr, &b->sched_attr))
 		return false;
 	if (!cpumask_equal(a->cpumask, b->cpumask))
 		return false;
@@ -4362,7 +4365,9 @@ 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 nice=%d", pool->flags,
+	pr_cont(" flags=0x%x policy=%u prio=%u nice=%d", pool->flags,
+			pool->attrs->sched_attr.sched_policy,
+			pool->attrs->sched_attr.sched_priority,
 			pool->attrs->sched_attr.sched_nice);
 }
 
@@ -5105,6 +5110,42 @@ static int wq_set_unbound_sched_attr(struct workqueue_struct *wq,
 	return ret;
 }
 
+static int wq_set_bound_sched_attr(struct workqueue_struct *wq,
+		const struct sched_attr *new)
+{
+	struct pool_workqueue *pwq;
+	struct worker_pool *pool;
+	struct worker *worker;
+	int ret = 0;
+
+	apply_wqattrs_lock();
+	for_each_pwq(pwq, wq) {
+		pool = pwq->pool;
+		mutex_lock(&pool->attach_mutex);
+		for_each_pool_worker(worker, pool) {
+			ret = sched_setattr(worker->task, new);
+			if (ret) {
+				pr_err("%s:%d err[%d]",
+						__func__, __LINE__, ret);
+				pr_err(" worker[%s] policy[%d] prio[%d] nice[%d]\n",
+						worker->task->comm,
+						new->sched_policy,
+						new->sched_priority,
+						new->sched_nice);
+			}
+		}
+		copy_sched_attr(&pool->attrs->sched_attr, new);
+		mutex_unlock(&pool->attach_mutex);
+	}
+	apply_wqattrs_unlock();
+
+	mutex_lock(&wq->mutex);
+	copy_sched_attr(&wq->attrs->sched_attr, new);
+	mutex_unlock(&wq->mutex);
+
+	return ret;
+}
+
 static ssize_t sched_attr_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -5120,8 +5161,10 @@ static ssize_t sched_attr_store(struct device *dev,
 	if (!capable(CAP_SYS_NICE))
 		return -EPERM;
 
-	if (sscanf(buf, "policy=0 prio=0 nice=%d",
-				&new.sched_nice) != 1)
+	if (sscanf(buf, "policy=%u prio=%u nice=%d",
+				&new.sched_policy,
+				&new.sched_priority,
+				&new.sched_nice) != 3)
 		return -EINVAL;
 
 	pr_debug("set wq's sched_attr: policy=%u prio=%u nice=%d\n",
@@ -5138,7 +5181,7 @@ static ssize_t sched_attr_store(struct device *dev,
 	if (wq->flags & WQ_UNBOUND)
 		ret = wq_set_unbound_sched_attr(wq, &new);
 	else
-		ret = -EPERM;
+		ret = wq_set_bound_sched_attr(wq, &new);
 	return ret ?: count;
 }
 static DEVICE_ATTR_RW(sched_attr);
-- 
1.8.3.1

Re: [RFC PATCH V4 1/5] workqueue: rename system workqueues

[Tejun Heo]

Hello,

On Thu, Jan 25, 2018 at 03:01:40PM +0800, Wen Yang wrote:
> Rename system_wq's wq->name from "events" to "system_percpu",
> and similarly for the similarly named workqueues.
> 
> Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
> Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
> Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
> Suggested-by: Tejun Heo <tj@kernel.org>
> Cc: Tejun Heo <tj@kernel.org>
> Cc: Lai Jiangshan <jiangshanlai@gmail.com>
> Cc: linux-kernel@vger.kernel.org

The patches don't seem split right.  There are a number of chunks
which seem to be in the wrong patch.  Can you plesae go over each
patch and verify that they look, build and run okay?

Thanks.

-- 
tejun

Re: [RFC PATCH V4 1/5] workqueue: rename system workqueues

[Tejun Heo]

Hello,

On Thu, Jan 25, 2018 at 07:54:41AM -0800, Tejun Heo wrote:
> On Thu, Jan 25, 2018 at 03:01:40PM +0800, Wen Yang wrote:
> > Rename system_wq's wq->name from "events" to "system_percpu",
> > and similarly for the similarly named workqueues.
> > 
> > Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
> > Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
> > Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
> > Suggested-by: Tejun Heo <tj@kernel.org>
> > Cc: Tejun Heo <tj@kernel.org>
> > Cc: Lai Jiangshan <jiangshanlai@gmail.com>
> > Cc: linux-kernel@vger.kernel.org
> 
> The patches don't seem split right.  There are a number of chunks
> which seem to be in the wrong patch.  Can you plesae go over each
> patch and verify that they look, build and run okay?

Just building the same tree structure for different hierarchies.  Just
run tree(1) in /sys/fs/cgroup on a systemd cgroup1 system with some
controllers enabled and look at the output.

Thanks.

-- 
tejun