io_uring: add general async offload context

Right now we just copy the sqe for async offload, but we want to store
more context across an async punt. In preparation for doing so, put the
sqe copy inside a structure that we can expand. With this pointer added,
we can get rid of REQ_F_FREE_SQE, as that is now indicated by whether
req->io is NULL or not.

No functional changes in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -308,6 +308,10 @@ struct io_timeout {
 	struct io_timeout_data		*data;
 };
 
+struct io_async_ctx {
+	struct io_uring_sqe		sqe;
+};
+
 /*
  * NOTE! Each of the iocb union members has the file pointer
  * as the first entry in their struct definition. So you can
@@ -323,6 +327,7 @@ struct io_kiocb {
 	};
 
 	const struct io_uring_sqe	*sqe;
+	struct io_async_ctx		*io;
 	struct file			*ring_file;
 	int				ring_fd;
 	bool				has_user;
@@ -353,7 +358,6 @@ struct io_kiocb {
 #define REQ_F_TIMEOUT_NOSEQ	8192	/* no timeout sequence */
 #define REQ_F_INFLIGHT		16384	/* on inflight list */
 #define REQ_F_COMP_LOCKED	32768	/* completion under lock */
-#define REQ_F_FREE_SQE		65536	/* free sqe if not async queued */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -806,6 +810,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	}
 
 got_it:
+	req->io = NULL;
 	req->ring_file = NULL;
 	req->file = NULL;
 	req->ctx = ctx;
@@ -836,8 +841,8 @@ static void __io_free_req(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (req->flags & REQ_F_FREE_SQE)
-		kfree(req->sqe);
+	if (req->io)
+		kfree(req->io);
 	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
 		fput(req->file);
 	if (req->flags & REQ_F_INFLIGHT) {
@@ -1079,9 +1084,9 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			 * completions for those, only batch free for fixed
 			 * file and non-linked commands.
 			 */
-			if (((req->flags &
-				(REQ_F_FIXED_FILE|REQ_F_LINK|REQ_F_FREE_SQE)) ==
-			    REQ_F_FIXED_FILE) && !io_is_fallback_req(req)) {
+			if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
+			    REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
+			    !req->io) {
 				reqs[to_free++] = req;
 				if (to_free == ARRAY_SIZE(reqs))
 					io_free_req_many(ctx, reqs, &to_free);
@@ -2259,7 +2264,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (!poll->wait)
 		return -ENOMEM;
 
-	req->sqe = NULL;
+	req->io = NULL;
 	INIT_IO_WORK(&req->work, io_poll_complete_work);
 	events = READ_ONCE(sqe->poll_events);
 	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
@@ -2602,27 +2607,27 @@ static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 static int io_req_defer(struct io_kiocb *req)
 {
-	struct io_uring_sqe *sqe_copy;
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_async_ctx *io;
 
 	/* Still need defer if there is pending req in defer list. */
 	if (!req_need_defer(req) && list_empty(&ctx->defer_list))
 		return 0;
 
-	sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
-	if (!sqe_copy)
+	io = kmalloc(sizeof(*io), GFP_KERNEL);
+	if (!io)
 		return -EAGAIN;
 
 	spin_lock_irq(&ctx->completion_lock);
 	if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
 		spin_unlock_irq(&ctx->completion_lock);
-		kfree(sqe_copy);
+		kfree(io);
 		return 0;
 	}
 
-	memcpy(sqe_copy, req->sqe, sizeof(*sqe_copy));
-	req->flags |= REQ_F_FREE_SQE;
-	req->sqe = sqe_copy;
+	memcpy(&io->sqe, req->sqe, sizeof(io->sqe));
+	req->sqe = &io->sqe;
+	req->io = io;
 
 	trace_io_uring_defer(ctx, req, req->user_data);
 	list_add_tail(&req->list, &ctx->defer_list);
@@ -2955,14 +2960,16 @@ static void __io_queue_sqe(struct io_kiocb *req)
 	 */
 	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
 	    (req->flags & REQ_F_MUST_PUNT))) {
-		struct io_uring_sqe *sqe_copy;
+		struct io_async_ctx *io;
 
-		sqe_copy = kmemdup(req->sqe, sizeof(*sqe_copy), GFP_KERNEL);
-		if (!sqe_copy)
+		io = kmalloc(sizeof(*io), GFP_KERNEL);
+		if (!io)
 			goto err;
 
-		req->sqe = sqe_copy;
-		req->flags |= REQ_F_FREE_SQE;
+		memcpy(&io->sqe, req->sqe, sizeof(io->sqe));
+
+		req->sqe = &io->sqe;
+		req->io = io;
 
 		if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) {
 			ret = io_grab_files(req);
@@ -3063,7 +3070,7 @@ static void io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state,
 	 */
 	if (*link) {
 		struct io_kiocb *prev = *link;
-		struct io_uring_sqe *sqe_copy;
+		struct io_async_ctx *io;
 
 		if (req->sqe->flags & IOSQE_IO_DRAIN)
 			(*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
@@ -3079,14 +3086,15 @@ static void io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state,
 			}
 		}
 
-		sqe_copy = kmemdup(req->sqe, sizeof(*sqe_copy), GFP_KERNEL);
-		if (!sqe_copy) {
+		io = kmalloc(sizeof(*io), GFP_KERNEL);
+		if (!io) {
 			ret = -EAGAIN;
 			goto err_req;
 		}
 
-		req->sqe = sqe_copy;
-		req->flags |= REQ_F_FREE_SQE;
+		memcpy(&io->sqe, req->sqe, sizeof(io->sqe));
+		req->sqe = &io->sqe;
+		req->io = io;
 		trace_io_uring_link(ctx, req, prev);
 		list_add_tail(&req->list, &prev->link_list);
 	} else if (req->sqe->flags & IOSQE_IO_LINK) {