kthread_worker: reimplement flush_kthread_work() to allow freeing the work item being executed

kthread_worker provides minimalistic workqueue-like interface for
users which need a dedicated worker thread (e.g. for realtime
priority).  It has basic queue, flush_work, flush_worker operations
which mostly match the workqueue counterparts; however, due to the way
flush_work() is implemented, it has a noticeable difference of not
allowing work items to be freed while being executed.

While the current users of kthread_worker are okay with the current
behavior, the restriction does impede some valid use cases.  Also,
removing this difference isn't difficult and actually makes the code
easier to understand.

This patch reimplements flush_kthread_work() such that it uses a
flush_work item instead of queue/done sequence numbers.

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 27 insertions, 21 deletions

diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4bfbff36d447..b579af57ea10 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -360,16 +360,12 @@ repeat:
                                         struct kthread_work, node);
                 list_del_init(&work->node);
         }
+        worker->current_work = work;
         spin_unlock_irq(&worker->lock);
 
         if (work) {
                 __set_current_state(TASK_RUNNING);
                 work->func(work);
-                smp_wmb();      /* wmb worker-b0 paired with flush-b1 */
-                work->done_seq = work->queue_seq;
-                smp_mb();       /* mb worker-b1 paired with flush-b0 */
-                if (atomic_read(&work->flushing))
-                        wake_up_all(&work->done);
         } else if (!freezing(current))
                 schedule();
 
@@ -386,7 +382,7 @@ static void insert_kthread_work(struct kthread_worker *worker,
         lockdep_assert_held(&worker->lock);
 
         list_add_tail(&work->node, pos);
-        work->queue_seq++;
+        work->worker = worker;
         if (likely(worker->task))
                 wake_up_process(worker->task);
 }
@@ -436,25 +432,35 @@ static void kthread_flush_work_fn(struct kthread_work *work)
  */
 void flush_kthread_work(struct kthread_work *work)
 {
-        int seq = work->queue_seq;
+        struct kthread_flush_work fwork = {
+                KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
+                COMPLETION_INITIALIZER_ONSTACK(fwork.done),
+        };
+        struct kthread_worker *worker;
+        bool noop = false;
+
+retry:
+        worker = work->worker;
+        if (!worker)
+                return;
 
-        atomic_inc(&work->flushing);
+        spin_lock_irq(&worker->lock);
+        if (work->worker != worker) {
+                spin_unlock_irq(&worker->lock);
+                goto retry;
+        }
 
-        /*
-         * mb flush-b0 paired with worker-b1, to make sure either
-         * worker sees the above increment or we see done_seq update.
-         */
-        smp_mb__after_atomic_inc();
+        if (!list_empty(&work->node))
+                insert_kthread_work(worker, &fwork.work, work->node.next);
+        else if (worker->current_work == work)
+                insert_kthread_work(worker, &fwork.work, worker->work_list.next);
+        else
+                noop = true;
 
-        /* A - B <= 0 tests whether B is in front of A regardless of overflow */
-        wait_event(work->done, seq - work->done_seq <= 0);
-        atomic_dec(&work->flushing);
+        spin_unlock_irq(&worker->lock);
 
-        /*
-         * rmb flush-b1 paired with worker-b0, to make sure our caller
-         * sees every change made by work->func().
-         */
-        smp_mb__after_atomic_dec();
+        if (!noop)
+                wait_for_completion(&fwork.done);
 }
 EXPORT_SYMBOL_GPL(flush_kthread_work);