Received-SPF: pass (google.com: domain of linux-kernel+bounces-39001-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Sender: Tejun Heo <htejun@gmail.com>
From: Tejun Heo <tj@kernel.org>
To: jiangshanlai@gmail.com
Cc: linux-kernel@vger.kernel.org,
	Naohiro.Aota@wdc.com,
	kernel-team@meta.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 04/10] workqueue: Move nr_active handling into helpers
Date: Thu, 25 Jan 2024 07:05:57 -1000
Message-ID: <20240125170628.2017784-5-tj@kernel.org>
In-Reply-To: <20240125170628.2017784-1-tj@kernel.org>
References: <20240125170628.2017784-1-tj@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

__queue_work(), pwq_dec_nr_in_flight() and wq_adjust_max_active() were
open-coding nr_active handling, which is fine given that the operations are
trivial. However, the planned unbound nr_active update will make them more
complicated, so let's move them into helpers.

- pwq_tryinc_nr_active() is added. It increments nr_active if under
  max_active limit and return a boolean indicating whether inc was
  successful. Note that the function is structured to accommodate future
  changes. __queue_work() is updated to use the new helper.

- pwq_activate_first_inactive() is updated to use pwq_tryinc_nr_active() and
  thus no longer assumes that nr_active is under max_active and returns a
  boolean to indicate whether a work item has been activated.

- wq_adjust_max_active() no longer tests directly whether a work item can be
  activated. Instead, it's updated to use the return value of
  pwq_activate_first_inactive() to tell whether a work item has been
  activated.

- nr_active decrement and activating the first inactive work item is
  factored into pwq_dec_nr_active().

v3: - WARN_ON_ONCE(!WORK_STRUCT_INACTIVE) added to __pwq_activate_work() as
      now we're calling the function unconditionally from
      pwq_activate_first_inactive().

v2: - wq->max_active now uses WRITE/READ_ONCE() as suggested by Lai.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
---
 kernel/workqueue.c | 86 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 67 insertions(+), 19 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 3a4c269204f3..6a0ce3a3cca2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1464,11 +1464,14 @@ static bool pwq_is_empty(struct pool_workqueue *pwq)
 static void __pwq_activate_work(struct pool_workqueue *pwq,
 				struct work_struct *work)
 {
+	unsigned long *wdb = work_data_bits(work);
+
+	WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE));
 	trace_workqueue_activate_work(work);
 	if (list_empty(&pwq->pool->worklist))
 		pwq->pool->watchdog_ts = jiffies;
 	move_linked_works(work, &pwq->pool->worklist, NULL);
-	__clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work));
+	__clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb);
 }
 
 /**
@@ -1493,12 +1496,66 @@ static bool pwq_activate_work(struct pool_workqueue *pwq,
 	return true;
 }
 
-static void pwq_activate_first_inactive(struct pool_workqueue *pwq)
+/**
+ * pwq_tryinc_nr_active - Try to increment nr_active for a pwq
+ * @pwq: pool_workqueue of interest
+ *
+ * Try to increment nr_active for @pwq. Returns %true if an nr_active count is
+ * successfully obtained. %false otherwise.
+ */
+static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq)
+{
+	struct workqueue_struct *wq = pwq->wq;
+	struct worker_pool *pool = pwq->pool;
+	bool obtained;
+
+	lockdep_assert_held(&pool->lock);
+
+	obtained = pwq->nr_active < READ_ONCE(wq->max_active);
+
+	if (obtained)
+		pwq->nr_active++;
+	return obtained;
+}
+
+/**
+ * pwq_activate_first_inactive - Activate the first inactive work item on a pwq
+ * @pwq: pool_workqueue of interest
+ *
+ * Activate the first inactive work item of @pwq if available and allowed by
+ * max_active limit.
+ *
+ * Returns %true if an inactive work item has been activated. %false if no
+ * inactive work item is found or max_active limit is reached.
+ */
+static bool pwq_activate_first_inactive(struct pool_workqueue *pwq)
+{
+	struct work_struct *work =
+		list_first_entry_or_null(&pwq->inactive_works,
+					 struct work_struct, entry);
+
+	if (work && pwq_tryinc_nr_active(pwq)) {
+		__pwq_activate_work(pwq, work);
+		return true;
+	} else {
+		return false;
+	}
+}
+
+/**
+ * pwq_dec_nr_active - Retire an active count
+ * @pwq: pool_workqueue of interest
+ *
+ * Decrement @pwq's nr_active and try to activate the first inactive work item.
+ */
+static void pwq_dec_nr_active(struct pool_workqueue *pwq)
 {
-	struct work_struct *work = list_first_entry(&pwq->inactive_works,
-						    struct work_struct, entry);
+	struct worker_pool *pool = pwq->pool;
 
-	pwq_activate_work(pwq, work);
+	lockdep_assert_held(&pool->lock);
+
+	pwq->nr_active--;
+	pwq_activate_first_inactive(pwq);
 }
 
 /**
@@ -1516,14 +1573,8 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_
 {
 	int color = get_work_color(work_data);
 
-	if (!(work_data & WORK_STRUCT_INACTIVE)) {
-		pwq->nr_active--;
-		if (!list_empty(&pwq->inactive_works)) {
-			/* one down, submit an inactive one */
-			if (pwq->nr_active < READ_ONCE(pwq->wq->max_active))
-				pwq_activate_first_inactive(pwq);
-		}
-	}
+	if (!(work_data & WORK_STRUCT_INACTIVE))
+		pwq_dec_nr_active(pwq);
 
 	pwq->nr_in_flight[color]--;
 
@@ -1825,13 +1876,11 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 * @work must also queue behind existing inactive work items to maintain
 	 * ordering when max_active changes. See wq_adjust_max_active().
 	 */
-	if (list_empty(&pwq->inactive_works) &&
-	    pwq->nr_active < READ_ONCE(pwq->wq->max_active)) {
+	if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq)) {
 		if (list_empty(&pool->worklist))
 			pool->watchdog_ts = jiffies;
 
 		trace_workqueue_activate_work(work);
-		pwq->nr_active++;
 		insert_work(pwq, work, &pool->worklist, work_flags);
 		kick_pool(pool);
 	} else {
@@ -4684,9 +4733,8 @@ static void wq_adjust_max_active(struct workqueue_struct *wq)
 		/* this function can be called during early boot w/ irq disabled */
 		raw_spin_lock_irqsave(&pwq->pool->lock, flags);
 
-		while (!list_empty(&pwq->inactive_works) &&
-		       pwq->nr_active < wq->max_active)
-			pwq_activate_first_inactive(pwq);
+		while (pwq_activate_first_inactive(pwq))
+			;
 
 		kick_pool(pwq->pool);
 
-- 
2.43.0