Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Sender: Tejun Heo <htejun@gmail.com>
Date:   Mon, 7 Aug 2023 15:15:21 -1000
From:   Tejun Heo <tj@kernel.org>
To:     jiangshanlai@gmail.com
Cc:     torvalds@linux-foundation.org, peterz@infradead.org,
        linux-kernel@vger.kernel.org, kernel-team@meta.com,
        joshdon@google.com, brho@google.com, briannorris@chromium.org,
        nhuck@google.com, agk@redhat.com, snitzer@kernel.org,
        void@manifault.com
Subject: [PATCH v2 03/24] workqueue: Not all work insertion needs to wake up
 a worker
Message-ID: <ZNGXKdKfDfDfB5S1@slm.duckdns.org>
References: <20230519001709.2563-1-tj@kernel.org>
 <20230519001709.2563-4-tj@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20230519001709.2563-4-tj@kernel.org>
Precedence: bulk

insert_work() always tried to wake up a worker; however, the only time it
needs to try to wake up a worker is when a new active work item is queued.
When a work item goes on the inactive list or queueing a flush work item,
there's no reason to try to wake up a worker.

This patch moves the worker wakeup logic out of insert_work() and places it
in the active new work item queueing path in __queue_work().

While at it:

* __queue_work() is dereferencing pwq->pool repeatedly. Add local variable
  pool.

* Every caller of insert_work() calls debug_work_activate(). Consolidate the
  invocations into insert_work().

* In __queue_work() pool->watchdog_ts update is relocated slightly. This is
  to better accommodate future changes.

This makes wakeups more precise and will help the planned change to assign
work items to workers before waking them up. No behavior changes intended.

v2: WARN_ON_ONCE(pool != last_pool) added in __queue_work() to clarify as
    suggested by Lai.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
---
 kernel/workqueue.c |   38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1539,7 +1539,7 @@ fail:
 static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 			struct list_head *head, unsigned int extra_flags)
 {
-	struct worker_pool *pool = pwq->pool;
+	debug_work_activate(work);
 
 	/* record the work call stack in order to print it in KASAN reports */
 	kasan_record_aux_stack_noalloc(work);
@@ -1548,9 +1548,6 @@ static void insert_work(struct pool_work
 	set_work_pwq(work, pwq, extra_flags);
 	list_add_tail(&work->entry, head);
 	get_pwq(pwq);
-
-	if (__need_more_worker(pool))
-		wake_up_worker(pool);
 }
 
 /*
@@ -1604,8 +1601,7 @@ static void __queue_work(int cpu, struct
 			 struct work_struct *work)
 {
 	struct pool_workqueue *pwq;
-	struct worker_pool *last_pool;
-	struct list_head *worklist;
+	struct worker_pool *last_pool, *pool;
 	unsigned int work_flags;
 	unsigned int req_cpu = cpu;
 
@@ -1639,13 +1635,15 @@ retry:
 		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
 	}
 
+	pool = pwq->pool;
+
 	/*
 	 * If @work was previously on a different pool, it might still be
 	 * running there, in which case the work needs to be queued on that
 	 * pool to guarantee non-reentrancy.
 	 */
 	last_pool = get_work_pool(work);
-	if (last_pool && last_pool != pwq->pool) {
+	if (last_pool && last_pool != pool) {
 		struct worker *worker;
 
 		raw_spin_lock(&last_pool->lock);
@@ -1654,13 +1652,15 @@ retry:
 
 		if (worker && worker->current_pwq->wq == wq) {
 			pwq = worker->current_pwq;
+			pool = pwq->pool;
+			WARN_ON_ONCE(pool != last_pool);
 		} else {
 			/* meh... not running there, queue here */
 			raw_spin_unlock(&last_pool->lock);
-			raw_spin_lock(&pwq->pool->lock);
+			raw_spin_lock(&pool->lock);
 		}
 	} else {
-		raw_spin_lock(&pwq->pool->lock);
+		raw_spin_lock(&pool->lock);
 	}
 
 	/*
@@ -1673,7 +1673,7 @@ retry:
 	 */
 	if (unlikely(!pwq->refcnt)) {
 		if (wq->flags & WQ_UNBOUND) {
-			raw_spin_unlock(&pwq->pool->lock);
+			raw_spin_unlock(&pool->lock);
 			cpu_relax();
 			goto retry;
 		}
@@ -1692,21 +1692,22 @@ retry:
 	work_flags = work_color_to_flags(pwq->work_color);
 
 	if (likely(pwq->nr_active < pwq->max_active)) {
+		if (list_empty(&pool->worklist))
+			pool->watchdog_ts = jiffies;
+
 		trace_workqueue_activate_work(work);
 		pwq->nr_active++;
-		worklist = &pwq->pool->worklist;
-		if (list_empty(worklist))
-			pwq->pool->watchdog_ts = jiffies;
+		insert_work(pwq, work, &pool->worklist, work_flags);
+
+		if (__need_more_worker(pool))
+			wake_up_worker(pool);
 	} else {
 		work_flags |= WORK_STRUCT_INACTIVE;
-		worklist = &pwq->inactive_works;
+		insert_work(pwq, work, &pwq->inactive_works, work_flags);
 	}
 
-	debug_work_activate(work);
-	insert_work(pwq, work, worklist, work_flags);
-
 out:
-	raw_spin_unlock(&pwq->pool->lock);
+	raw_spin_unlock(&pool->lock);
 	rcu_read_unlock();
 }
 
@@ -3010,7 +3011,6 @@ static void insert_wq_barrier(struct poo
 	pwq->nr_in_flight[work_color]++;
 	work_flags |= work_color_to_flags(work_color);
 
-	debug_work_activate(&barr->work);
 	insert_work(pwq, &barr->work, head, work_flags);
 }