io_wq: add per-wq work handler instead of per work

io_uring is the only user of io-wq, and now it uses only io-wq callback
for all its requests, namely io_wq_submit_work(). Instead of storing
work->runner callback in each instance of io_wq_work, keep it in io-wq
itself.

pros:
- reduces io_wq_work size
- more robust -- ->func won't be invalidated with mem{cpy,set}(req)
- helps other work

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 12 insertions, 8 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 4023c9846860..d7dc638f4b8e 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -112,6 +112,7 @@ struct io_wq {
 	unsigned long state;
 
 	free_work_fn *free_work;
+	io_wq_work_fn *do_work;
 
 	struct task_struct *manager;
 	struct user_struct *user;
@@ -528,7 +529,7 @@ get_next:
 
 			hash = io_get_work_hash(work);
 			linked = old_work = work;
-			linked->func(&linked);
+			wq->do_work(&linked);
 			linked = (old_work == linked) ? NULL : linked;
 
 			work = next_hashed;
@@ -785,7 +786,7 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
 		struct io_wq_work *old_work = work;
 
 		work->flags |= IO_WQ_WORK_CANCEL;
-		work->func(&work);
+		wq->do_work(&work);
 		work = (work == old_work) ? NULL : work;
 		wq->free_work(old_work);
 	} while (work);
@@ -1023,7 +1024,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	int ret = -ENOMEM, node;
 	struct io_wq *wq;
 
-	if (WARN_ON_ONCE(!data->free_work))
+	if (WARN_ON_ONCE(!data->free_work || !data->do_work))
 		return ERR_PTR(-EINVAL);
 
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
@@ -1037,6 +1038,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	}
 
 	wq->free_work = data->free_work;
+	wq->do_work = data->do_work;
 
 	/* caller must already hold a reference to this */
 	wq->user = data->user;
@@ -1093,7 +1095,7 @@ err:
 
 bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
 {
-	if (data->free_work != wq->free_work)
+	if (data->free_work != wq->free_work || data->do_work != wq->do_work)
 		return false;
 
 	return refcount_inc_not_zero(&wq->use_refs);
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 5ba12de7572f..2db24d31fbc5 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -85,7 +85,6 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	void (*func)(struct io_wq_work **);
 	struct files_struct *files;
 	struct mm_struct *mm;
 	const struct cred *creds;
@@ -94,9 +93,9 @@ struct io_wq_work {
 	pid_t task_pid;
 };
 
-#define INIT_IO_WORK(work, _func)				\
+#define INIT_IO_WORK(work)					\
 	do {							\
-		*(work) = (struct io_wq_work){ .func = _func };	\
+		*(work) = (struct io_wq_work){};		\
 	} while (0)						\
 
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
@@ -108,10 +107,12 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
 }
 
 typedef void (free_work_fn)(struct io_wq_work *);
+typedef void (io_wq_work_fn)(struct io_wq_work **);
 
 struct io_wq_data {
 	struct user_struct *user;
 
+	io_wq_work_fn *do_work;
 	free_work_fn *free_work;
 };
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 35d96d2a4c8c..3ffe03194c1e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5776,7 +5776,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = NULL;
 	req->result = 0;
-	INIT_IO_WORK(&req->work, io_wq_submit_work);
+	INIT_IO_WORK(&req->work);
 
 	if (unlikely(req->opcode >= IORING_OP_LAST))
 		return -EINVAL;
@@ -6796,6 +6796,7 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx,
 
 	data.user = ctx->user;
 	data.free_work = io_free_work;
+	data.do_work = io_wq_submit_work;
 
 	if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
 		/* Do QD, or 4 * CPUS, whatever is smallest */