io_uring: don't keep submit_state on stack

struct io_submit_state is quite big (168 bytes) and going to grow. It's
better to not keep it on stack as it is now. Move it to context, it's
always protected by uring_lock, so it's fine to have only one instance
of it.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -264,6 +264,39 @@ struct io_sq_data {
 	unsigned		sq_thread_idle;
 };
 
+#define IO_IOPOLL_BATCH			8
+
+struct io_comp_state {
+	unsigned int		nr;
+	struct list_head	list;
+	struct io_ring_ctx	*ctx;
+};
+
+struct io_submit_state {
+	struct blk_plug		plug;
+
+	/*
+	 * io_kiocb alloc cache
+	 */
+	void			*reqs[IO_IOPOLL_BATCH];
+	unsigned int		free_reqs;
+
+	bool			plug_started;
+
+	/*
+	 * Batch completion logic
+	 */
+	struct io_comp_state	comp;
+
+	/*
+	 * File reference cache
+	 */
+	struct file		*file;
+	unsigned int		fd;
+	unsigned int		file_refs;
+	unsigned int		ios_left;
+};
+
 struct io_ring_ctx {
 	struct {
 		struct percpu_ref	refs;
@@ -406,6 +439,7 @@ struct io_ring_ctx {
 
 	struct work_struct		exit_work;
 	struct io_restriction		restrictions;
+	struct io_submit_state		submit_state;
 };
 
 /*
@@ -758,39 +792,6 @@ struct io_defer_entry {
 	u32			seq;
 };
 
-#define IO_IOPOLL_BATCH			8
-
-struct io_comp_state {
-	unsigned int		nr;
-	struct list_head	list;
-	struct io_ring_ctx	*ctx;
-};
-
-struct io_submit_state {
-	struct blk_plug		plug;
-
-	/*
-	 * io_kiocb alloc cache
-	 */
-	void			*reqs[IO_IOPOLL_BATCH];
-	unsigned int		free_reqs;
-
-	bool			plug_started;
-
-	/*
-	 * Batch completion logic
-	 */
-	struct io_comp_state	comp;
-
-	/*
-	 * File reference cache
-	 */
-	struct file		*file;
-	unsigned int		fd;
-	unsigned int		file_refs;
-	unsigned int		ios_left;
-};
-
 struct io_op_def {
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
@@ -1997,9 +1998,10 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
 	return NULL;
 }
 
-static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx,
-				     struct io_submit_state *state)
+static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
 {
+	struct io_submit_state *state = &ctx->submit_state;
+
 	if (!state->free_reqs) {
 		gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 		size_t sz;
@@ -6758,9 +6760,9 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
 				IOSQE_BUFFER_SELECT)
 
 static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
-		       const struct io_uring_sqe *sqe,
-		       struct io_submit_state *state)
+		       const struct io_uring_sqe *sqe)
 {
+	struct io_submit_state *state;
 	unsigned int sqe_flags;
 	int id, ret;
 
@@ -6812,6 +6814,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
 	req->flags |= sqe_flags;
+	state = &ctx->submit_state;
 
 	/*
 	 * Plug now if we have more than 1 IO left after this, and the target
@@ -6838,7 +6841,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 {
-	struct io_submit_state state;
 	struct io_submit_link link;
 	int i, submitted = 0;
 
@@ -6857,7 +6859,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	percpu_counter_add(&current->io_uring->inflight, nr);
 	refcount_add(nr, &current->usage);
 
-	io_submit_state_start(&state, ctx, nr);
+	io_submit_state_start(&ctx->submit_state, ctx, nr);
 	link.head = NULL;
 
 	for (i = 0; i < nr; i++) {
@@ -6870,7 +6872,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 			io_consume_sqe(ctx);
 			break;
 		}
-		req = io_alloc_req(ctx, &state);
+		req = io_alloc_req(ctx);
 		if (unlikely(!req)) {
 			if (!submitted)
 				submitted = -EAGAIN;
@@ -6880,7 +6882,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 		/* will complete beyond this point, count as submitted */
 		submitted++;
 
-		err = io_init_req(ctx, req, sqe, &state);
+		err = io_init_req(ctx, req, sqe);
 		if (unlikely(err)) {
 fail_req:
 			io_put_req(req);
@@ -6890,7 +6892,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 
 		trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
 					true, ctx->flags & IORING_SETUP_SQPOLL);
-		err = io_submit_sqe(req, sqe, &link, &state.comp);
+		err = io_submit_sqe(req, sqe, &link, &ctx->submit_state.comp);
 		if (err)
 			goto fail_req;
 	}
@@ -6905,8 +6907,8 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 		put_task_struct_many(current, unused);
 	}
 	if (link.head)
-		io_queue_link_head(link.head, &state.comp);
-	io_submit_state_end(&state);
+		io_queue_link_head(link.head, &ctx->submit_state.comp);
+	io_submit_state_end(&ctx->submit_state);
 
 	 /* Commit SQ ring head once we've consumed and submitted all SQEs */
 	io_commit_sqring(ctx);