[PATCH v2 4/9] workqueue: account nr_active by the backing pool

[Breno Leitao]

pwq_tryinc_nr_active() and pwq_dec_nr_active() choose between the shared
per-node nr_active and the plain per-pwq one by testing
wq_node_nr_active() for NULL.

Test the backing pool with is_percpu_pool() instead, so the accounting
follows the pool that runs the work rather than the workqueue type.

No functional change.

Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 kernel/workqueue.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b96090c85bcaa..7b20d459d6442 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1615,9 +1615,8 @@ static bool is_percpu_pool(struct worker_pool *pool)
  * @wq: workqueue of interest
  * @node: NUMA node, can be %NUMA_NO_NODE
  *
- * Determine wq_node_nr_active to use for @wq on @node. Returns:
- *
- * - %NULL for per-cpu workqueues as they don't need to use shared nr_active.
+ * Determine wq_node_nr_active to use for @wq on @node. @wq must be unbound.
+ * Returns:
  *
  * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE.
  *
@@ -1626,7 +1625,7 @@ static bool is_percpu_pool(struct worker_pool *pool)
 static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq,
 						   int node)
 {
-	if (!(wq->flags & WQ_UNBOUND))
+	if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
 		return NULL;
 
 	if (node == NUMA_NO_NODE)
@@ -1782,13 +1781,16 @@ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill)
 {
 	struct workqueue_struct *wq = pwq->wq;
 	struct worker_pool *pool = pwq->pool;
-	struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node);
+	struct wq_node_nr_active *nna;
 	bool obtained = false;
 
 	lockdep_assert_held(&pool->lock);
 
-	if (!nna) {
-		/* BH or per-cpu workqueue, pwq->nr_active is sufficient */
+	/*
+	 * A concurrency-managed per-cpu pool accounts nr_active per pwq, so
+	 * pwq->nr_active against wq->max_active is sufficient.
+	 */
+	if (is_percpu_pool(pool)) {
 		obtained = pwq->nr_active < READ_ONCE(wq->max_active);
 		goto out;
 	}
@@ -1796,6 +1798,8 @@ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill)
 	if (unlikely(pwq->plugged))
 		return false;
 
+	nna = wq_node_nr_active(wq, pool->node);
+
 	/*
 	 * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is
 	 * already waiting on $nna, pwq_dec_nr_active() will maintain the
@@ -2013,7 +2017,7 @@ static void node_activate_pending_pwq(struct wq_node_nr_active *nna,
 static void pwq_dec_nr_active(struct pool_workqueue *pwq)
 {
 	struct worker_pool *pool = pwq->pool;
-	struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node);
+	struct wq_node_nr_active *nna;
 
 	lockdep_assert_held(&pool->lock);
 
@@ -2024,14 +2028,16 @@ static void pwq_dec_nr_active(struct pool_workqueue *pwq)
 	pwq->nr_active--;
 
 	/*
-	 * For a percpu workqueue, it's simple. Just need to kick the first
+	 * A concurrency-managed per-cpu pool only needs to kick the first
 	 * inactive work item on @pwq itself.
 	 */
-	if (!nna) {
+	if (is_percpu_pool(pool)) {
 		pwq_activate_first_inactive(pwq, false);
 		return;
 	}
 
+	nna = wq_node_nr_active(pwq->wq, pool->node);
+
 	/*
 	 * If @pwq is for an unbound workqueue, it's more complicated because
 	 * multiple pwqs and pools may be sharing the nr_active count. When a

-- 
2.53.0-Meta