diff --git a/fs/io-wq.c b/fs/io-wq.c
index b26291a3fdee76a7ad38ae8a5b30e96bd7051824..8cc58f02dc007a38ddae623c0c9729e19ba0394b 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -107,6 +107,9 @@ struct io_wq {
 	unsigned long state;
 	unsigned nr_wqes;
 
+	get_work_fn *get_work;
+	put_work_fn *put_work;
+
 	struct task_struct *manager;
 	struct user_struct *user;
 	struct mm_struct *mm;
@@ -393,7 +396,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
 static void io_worker_handle_work(struct io_worker *worker)
 	__releases(wqe->lock)
 {
-	struct io_wq_work *work, *old_work;
+	struct io_wq_work *work, *old_work = NULL, *put_work = NULL;
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
 
@@ -425,6 +428,8 @@ static void io_worker_handle_work(struct io_worker *worker)
 			wqe->flags |= IO_WQE_FLAG_STALLED;
 
 		spin_unlock_irq(&wqe->lock);
+		if (put_work && wq->put_work)
+			wq->put_work(old_work);
 		if (!work)
 			break;
 next:
@@ -445,6 +450,11 @@ static void io_worker_handle_work(struct io_worker *worker)
 		if (worker->mm)
 			work->flags |= IO_WQ_WORK_HAS_MM;
 
+		if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) {
+			put_work = work;
+			wq->get_work(work);
+		}
+
 		old_work = work;
 		work->func(&work);
 
@@ -456,6 +466,12 @@ static void io_worker_handle_work(struct io_worker *worker)
 		}
 		if (work && work != old_work) {
 			spin_unlock_irq(&wqe->lock);
+
+			if (put_work && wq->put_work) {
+				wq->put_work(put_work);
+				put_work = NULL;
+			}
+
 			/* dependent work not hashed */
 			hash = -1U;
 			goto next;
@@ -951,13 +967,15 @@ void io_wq_flush(struct io_wq *wq)
 
 		init_completion(&data.done);
 		INIT_IO_WORK(&data.work, io_wq_flush_func);
+		data.work.flags |= IO_WQ_WORK_INTERNAL;
 		io_wqe_enqueue(wqe, &data.work);
 		wait_for_completion(&data.done);
 	}
 }
 
 struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
-			   struct user_struct *user)
+			   struct user_struct *user, get_work_fn *get_work,
+			   put_work_fn *put_work)
 {
 	int ret = -ENOMEM, i, node;
 	struct io_wq *wq;
@@ -973,6 +991,9 @@ struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	wq->get_work = get_work;
+	wq->put_work = put_work;
+
 	/* caller must already hold a reference to this */
 	wq->user = user;
 
diff --git a/fs/io-wq.h b/fs/io-wq.h
index cc50754d028cc1b092799aa1ea27edc0d48cc9b5..4b29f922f80cfc2b916374eedf788a8526b93861 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -10,6 +10,7 @@ enum {
 	IO_WQ_WORK_NEEDS_USER	= 8,
 	IO_WQ_WORK_NEEDS_FILES	= 16,
 	IO_WQ_WORK_UNBOUND	= 32,
+	IO_WQ_WORK_INTERNAL	= 64,
 
 	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
 };
@@ -34,8 +35,12 @@ struct io_wq_work {
 		(work)->files = NULL;			\
 	} while (0)					\
 
+typedef void (get_work_fn)(struct io_wq_work *);
+typedef void (put_work_fn)(struct io_wq_work *);
+
 struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
-				struct user_struct *user);
+				struct user_struct *user,
+				get_work_fn *get_work, put_work_fn *put_work);
 void io_wq_destroy(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 84f39ebe7fcb7760e68d7156005fafa72c55fe7e..1819daed8e7452eb49285fdb5fe699a91197606a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3825,6 +3825,20 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
 	return done ? done : err;
 }
 
+static void io_put_work(struct io_wq_work *work)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	io_put_req(req);
+}
+
+static void io_get_work(struct io_wq_work *work)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	refcount_inc(&req->refs);
+}
+
 static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			       struct io_uring_params *p)
 {
@@ -3874,7 +3888,8 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 
 	/* Do QD, or 4 * CPUS, whatever is smallest */
 	concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
-	ctx->io_wq = io_wq_create(concurrency, ctx->sqo_mm, ctx->user);
+	ctx->io_wq = io_wq_create(concurrency, ctx->sqo_mm, ctx->user,
+					io_get_work, io_put_work);
 	if (IS_ERR(ctx->io_wq)) {
 		ret = PTR_ERR(ctx->io_wq);
 		ctx->io_wq = NULL;