2 files changed, 113 insertions, 24 deletions

diff --git a/kernel/async.c b/kernel/async.c
index a893d6170944..f6bd0d9885e1 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -149,7 +149,25 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
-static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain)
+/**
+ * async_schedule_node_domain - NUMA specific version of async_schedule_domain
+ * @func: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @node: NUMA node that we want to schedule this on or close to
+ * @domain: the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @domain may be used in the async_synchronize_*_domain() functions to
+ * wait within a certain synchronization domain rather than globally.
+ *
+ * Note: This function may be called from atomic or non-atomic contexts.
+ *
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
+ */
+async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
+					  int node, struct async_domain *domain)
 {
 	struct async_entry *entry;
 	unsigned long flags;
@@ -195,43 +213,30 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy
 	current->flags |= PF_USED_ASYNC;
 
 	/* schedule for execution */
-	queue_work(system_unbound_wq, &entry->work);
+	queue_work_node(node, system_unbound_wq, &entry->work);
 
 	return newcookie;
 }
+EXPORT_SYMBOL_GPL(async_schedule_node_domain);
 
 /**
- * async_schedule - schedule a function for asynchronous execution
+ * async_schedule_node - NUMA specific version of async_schedule
  * @func: function to execute asynchronously
  * @data: data pointer to pass to the function
+ * @node: NUMA node that we want to schedule this on or close to
  *
  * Returns an async_cookie_t that may be used for checkpointing later.
  * Note: This function may be called from atomic or non-atomic contexts.
- */
-async_cookie_t async_schedule(async_func_t func, void *data)
-{
-	return __async_schedule(func, data, &async_dfl_domain);
-}
-EXPORT_SYMBOL_GPL(async_schedule);
-
-/**
- * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
- * @func: function to execute asynchronously
- * @data: data pointer to pass to the function
- * @domain: the domain
  *
- * Returns an async_cookie_t that may be used for checkpointing later.
- * @domain may be used in the async_synchronize_*_domain() functions to
- * wait within a certain synchronization domain rather than globally.  A
- * synchronization domain is specified via @domain.  Note: This function
- * may be called from atomic or non-atomic contexts.
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
  */
-async_cookie_t async_schedule_domain(async_func_t func, void *data,
-				     struct async_domain *domain)
+async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 {
-	return __async_schedule(func, data, domain);
+	return async_schedule_node_domain(func, data, node, &async_dfl_domain);
 }
-EXPORT_SYMBOL_GPL(async_schedule_domain);
+EXPORT_SYMBOL_GPL(async_schedule_node);
 
 /**
  * async_synchronize_full - synchronize all asynchronous function calls
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index fc5d23d752a5..1ce2697254d1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1512,6 +1512,90 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL(queue_work_on);
 
+/**
+ * workqueue_select_cpu_near - Select a CPU based on NUMA node
+ * @node: NUMA node ID that we want to select a CPU from
+ *
+ * This function will attempt to find a "random" cpu available on a given
+ * node. If there are no CPUs available on the given node it will return
+ * WORK_CPU_UNBOUND indicating that we should just schedule to any
+ * available CPU if we need to schedule this work.
+ */
+static int workqueue_select_cpu_near(int node)
+{
+	int cpu;
+
+	/* No point in doing this if NUMA isn't enabled for workqueues */
+	if (!wq_numa_enabled)
+		return WORK_CPU_UNBOUND;
+
+	/* Delay binding to CPU if node is not valid or online */
+	if (node < 0 || node >= MAX_NUMNODES || !node_online(node))
+		return WORK_CPU_UNBOUND;
+
+	/* Use local node/cpu if we are already there */
+	cpu = raw_smp_processor_id();
+	if (node == cpu_to_node(cpu))
+		return cpu;
+
+	/* Use "random" otherwise know as "first" online CPU of node */
+	cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
+
+	/* If CPU is valid return that, otherwise just defer */
+	return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND;
+}
+
+/**
+ * queue_work_node - queue work on a "random" cpu for a given NUMA node
+ * @node: NUMA node that we are targeting the work for
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * We queue the work to a "random" CPU within a given NUMA node. The basic
+ * idea here is to provide a way to somehow associate work with a given
+ * NUMA node.
+ *
+ * This function will only make a best effort attempt at getting this onto
+ * the right NUMA node. If no node is requested or the requested node is
+ * offline then we just fall back to standard queue_work behavior.
+ *
+ * Currently the "random" CPU ends up being the first available CPU in the
+ * intersection of cpu_online_mask and the cpumask of the node, unless we
+ * are running on the node. In that case we just use the current CPU.
+ *
+ * Return: %false if @work was already on a queue, %true otherwise.
+ */
+bool queue_work_node(int node, struct workqueue_struct *wq,
+		     struct work_struct *work)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * This current implementation is specific to unbound workqueues.
+	 * Specifically we only return the first available CPU for a given
+	 * node instead of cycling through individual CPUs within the node.
+	 *
+	 * If this is used with a per-cpu workqueue then the logic in
+	 * workqueue_select_cpu_near would need to be updated to allow for
+	 * some round robin type logic.
+	 */
+	WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND));
+
+	local_irq_save(flags);
+
+	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+		int cpu = workqueue_select_cpu_near(node);
+
+		__queue_work(cpu, wq, work);
+		ret = true;
+	}
+
+	local_irq_restore(flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work_node);
+
 void delayed_work_timer_fn(struct timer_list *t)
 {
 	struct delayed_work *dwork = from_timer(dwork, t, timer);