workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity

Unbound workqueues are now NUMA aware.  Let's add some control knobs
and update sysfs interface accordingly.

* Add kernel param workqueue.numa_disable which disables NUMA affinity
  globally.

* Replace sysfs file "pool_id" with "pool_ids" which contain
  node:pool_id pairs.  This change is userland-visible but "pool_id"
  hasn't seen a release yet, so this is okay.

* Add a new sysf files "numa" which can toggle NUMA affinity on
  individual workqueues.  This is implemented as attrs->no_numa whichn
  is special in that it isn't part of a pool's attributes.  It only
  affects how apply_workqueue_attrs() picks which pools to use.

After "pool_ids" change, first_pwq() doesn't have any user left.
Removed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>

Documentation/kernel-parameters.txt

@@ -3222,6 +3222,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			or other driver-specific files in the
 			Documentation/watchdog/ directory.
 
+	workqueue.disable_numa
+			By default, all work items queued to unbound
+			workqueues are affine to the NUMA nodes they're
+			issued on, which results in better behavior in
+			general.  If NUMA affinity needs to be disabled for
+			whatever reason, this option can be used.  Note
+			that this also can be controlled per-workqueue for
+			workqueues visible under /sys/bus/workqueue/.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.

include/linux/workqueue.h

@@ -119,10 +119,15 @@ struct delayed_work {
 /*
  * A struct for workqueue attributes.  This can be used to change
  * attributes of an unbound workqueue.
+ *
+ * Unlike other fields, ->no_numa isn't a property of a worker_pool.  It
+ * only modifies how apply_workqueue_attrs() select pools and thus doesn't
+ * participate in pool hash calculations or equality comparisons.
  */
 struct workqueue_attrs {
 	int			nice;		/* nice level */
 	cpumask_var_t		cpumask;	/* allowed CPUs */
+	bool			no_numa;	/* disable NUMA affinity */
 };
 
 static inline struct delayed_work *to_delayed_work(struct work_struct *work)

kernel/workqueue.c

@@ -268,6 +268,9 @@ static int wq_numa_tbl_len;		/* highest possible NUMA node id + 1 */
 static cpumask_var_t *wq_numa_possible_cpumask;
 					/* possible CPUs of each node */
 
+static bool wq_disable_numa;
+module_param_named(disable_numa, wq_disable_numa, bool, 0444);
+
 static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
 
 /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
@@ -516,21 +519,6 @@ static int worker_pool_assign_id(struct worker_pool *pool)
 	return ret;
 }
 
-/**
- * first_pwq - return the first pool_workqueue of the specified workqueue
- * @wq: the target workqueue
- *
- * This must be called either with wq->mutex held or sched RCU read locked.
- * If the pwq needs to be used beyond the locking in effect, the caller is
- * responsible for guaranteeing that the pwq stays online.
- */
-static struct pool_workqueue *first_pwq(struct workqueue_struct *wq)
-{
-	assert_rcu_or_wq_mutex(wq);
-	return list_first_or_null_rcu(&wq->pwqs, struct pool_workqueue,
-				      pwqs_node);
-}
-
 /**
  * unbound_pwq_by_node - return the unbound pool_workqueue for the given node
  * @wq: the target workqueue
@@ -3114,16 +3102,21 @@ static struct device_attribute wq_sysfs_attrs[] = {
 	__ATTR_NULL,
 };
 
-static ssize_t wq_pool_id_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t wq_pool_ids_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct workqueue_struct *wq = dev_to_wq(dev);
-	struct worker_pool *pool;
-	int written;
+	const char *delim = "";
+	int node, written = 0;
 
 	rcu_read_lock_sched();
-	pool = first_pwq(wq)->pool;
-	written = scnprintf(buf, PAGE_SIZE, "%d\n", pool->id);
+	for_each_node(node) {
+		written += scnprintf(buf + written, PAGE_SIZE - written,
+				     "%s%d:%d", delim, node,
+				     unbound_pwq_by_node(wq, node)->pool->id);
+		delim = " ";
+	}
+	written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
 	rcu_read_unlock_sched();
 
 	return written;
@@ -3212,10 +3205,46 @@ static ssize_t wq_cpumask_store(struct device *dev,
 	return ret ?: count;
 }
 
+static ssize_t wq_numa_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->unbound_attrs->no_numa);
+	mutex_unlock(&wq->mutex);
+
+	return written;
+}
+
+static ssize_t wq_numa_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 v, ret;
+
+	attrs = wq_sysfs_prep_attrs(wq);
+	if (!attrs)
+		return -ENOMEM;
+
+	ret = -EINVAL;
+	if (sscanf(buf, "%d", &v) == 1) {
+		attrs->no_numa = !v;
+		ret = apply_workqueue_attrs(wq, attrs);
+	}
+
+	free_workqueue_attrs(attrs);
+	return ret ?: count;
+}
+
 static struct device_attribute wq_sysfs_unbound_attrs[] = {
-	__ATTR(pool_id, 0444, wq_pool_id_show, NULL),
+	__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,
 };
 
@@ -3750,7 +3779,7 @@ static void free_unbound_pwq(struct pool_workqueue *pwq)
 static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
 				 int cpu_going_down, cpumask_t *cpumask)
 {
-	if (!wq_numa_enabled)
+	if (!wq_numa_enabled || attrs->no_numa)
 		goto use_dfl;
 
 	/* does @node have any online CPUs @attrs wants? */
@@ -3951,6 +3980,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	cpumask = target_attrs->cpumask;
 
 	mutex_lock(&wq->mutex);
+	if (wq->unbound_attrs->no_numa)
+		goto out_unlock;
 
 	copy_workqueue_attrs(target_attrs, wq->unbound_attrs);
 	pwq = unbound_pwq_by_node(wq, node);
@@ -4763,6 +4794,11 @@ static void __init wq_numa_init(void)
 	if (num_possible_nodes() <= 1)
 		return;
 
+	if (wq_disable_numa) {
+		pr_info("workqueue: NUMA affinity support disabled\n");
+		return;
+	}
+
 	wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL);
 	BUG_ON(!wq_update_unbound_numa_attrs_buf);