1 files changed, 32 insertions, 44 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index efa7849b82c1..db592fa549b7 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -422,24 +422,6 @@ static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
 	return req->link;
 }
 
-static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
-{
-	if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
-		return NULL;
-	return __io_prep_linked_timeout(req);
-}
-
-static noinline void __io_arm_ltimeout(struct io_kiocb *req)
-{
-	io_queue_linked_timeout(__io_prep_linked_timeout(req));
-}
-
-static inline void io_arm_ltimeout(struct io_kiocb *req)
-{
-	if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
-		__io_arm_ltimeout(req);
-}
-
 static void io_prep_async_work(struct io_kiocb *req)
 {
 	const struct io_issue_def *def = &io_issue_defs[req->opcode];
@@ -493,7 +475,6 @@ static void io_prep_async_link(struct io_kiocb *req)
 
 static void io_queue_iowq(struct io_kiocb *req)
 {
-	struct io_kiocb *link = io_prep_linked_timeout(req);
 	struct io_uring_task *tctx = req->task->io_uring;
 
 	BUG_ON(!tctx);
@@ -518,8 +499,6 @@ static void io_queue_iowq(struct io_kiocb *req)
 
 	trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work));
 	io_wq_enqueue(tctx->io_wq, &req->work);
-	if (link)
-		io_queue_linked_timeout(link);
 }
 
 static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
@@ -940,6 +919,14 @@ static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u
 {
 	bool filled;
 
+	/*
+	 * If multishot has already posted deferred completions, ensure that
+	 * those are flushed first before posting this one. If not, CQEs
+	 * could get reordered.
+	 */
+	if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+		__io_submit_flush_completions(ctx);
+
 	io_cq_lock(ctx);
 	filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
 	if (!filled && allow_overflow)
@@ -1247,21 +1234,22 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 	while (node) {
 		req = container_of(node, struct io_kiocb, io_task_work.node);
 		node = node->next;
-		if (sync && last_ctx != req->ctx) {
+		if (last_ctx != req->ctx) {
 			if (last_ctx) {
-				flush_delayed_work(&last_ctx->fallback_work);
+				if (sync)
+					flush_delayed_work(&last_ctx->fallback_work);
 				percpu_ref_put(&last_ctx->refs);
 			}
 			last_ctx = req->ctx;
 			percpu_ref_get(&last_ctx->refs);
 		}
-		if (llist_add(&req->io_task_work.node,
-			      &req->ctx->fallback_llist))
-			schedule_delayed_work(&req->ctx->fallback_work, 1);
+		if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist))
+			schedule_delayed_work(&last_ctx->fallback_work, 1);
 	}
 
 	if (last_ctx) {
-		flush_delayed_work(&last_ctx->fallback_work);
+		if (sync)
+			flush_delayed_work(&last_ctx->fallback_work);
 		percpu_ref_put(&last_ctx->refs);
 	}
 }
@@ -1862,17 +1850,24 @@ static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
 	return !!req->file;
 }
 
+#define REQ_ISSUE_SLOW_FLAGS	(REQ_F_CREDS | REQ_F_ARM_LTIMEOUT)
+
 static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 {
 	const struct io_issue_def *def = &io_issue_defs[req->opcode];
 	const struct cred *creds = NULL;
+	struct io_kiocb *link = NULL;
 	int ret;
 
 	if (unlikely(!io_assign_file(req, def, issue_flags)))
 		return -EBADF;
 
-	if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
-		creds = override_creds(req->creds);
+	if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) {
+		if ((req->flags & REQ_F_CREDS) && req->creds != current_cred())
+			creds = override_creds(req->creds);
+		if (req->flags & REQ_F_ARM_LTIMEOUT)
+			link = __io_prep_linked_timeout(req);
+	}
 
 	if (!def->audit_skip)
 		audit_uring_entry(req->opcode);
@@ -1882,8 +1877,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	if (!def->audit_skip)
 		audit_uring_exit(!ret, ret);
 
-	if (creds)
-		revert_creds(creds);
+	if (unlikely(creds || link)) {
+		if (creds)
+			revert_creds(creds);
+		if (link)
+			io_queue_linked_timeout(link);
+	}
 
 	if (ret == IOU_OK) {
 		if (issue_flags & IO_URING_F_COMPLETE_DEFER)
@@ -1916,7 +1915,7 @@ struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
 	struct io_kiocb *nxt = NULL;
 
-	if (req_ref_put_and_test(req)) {
+	if (req_ref_put_and_test_atomic(req)) {
 		if (req->flags & IO_REQ_LINK_FLAGS)
 			nxt = io_req_find_next(req);
 		io_free_req(req);
@@ -1938,8 +1937,6 @@ void io_wq_submit_work(struct io_wq_work *work)
 	else
 		req_ref_get(req);
 
-	io_arm_ltimeout(req);
-
 	/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
 	if (work->flags & IO_WQ_WORK_CANCEL) {
 fail:
@@ -2035,15 +2032,11 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 static void io_queue_async(struct io_kiocb *req, int ret)
 	__must_hold(&req->ctx->uring_lock)
 {
-	struct io_kiocb *linked_timeout;
-
 	if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
 		io_req_defer_failed(req, ret);
 		return;
 	}
 
-	linked_timeout = io_prep_linked_timeout(req);
-
 	switch (io_arm_poll_handler(req, 0)) {
 	case IO_APOLL_READY:
 		io_kbuf_recycle(req, 0);
@@ -2056,9 +2049,6 @@ static void io_queue_async(struct io_kiocb *req, int ret)
 	case IO_APOLL_OK:
 		break;
 	}
-
-	if (linked_timeout)
-		io_queue_linked_timeout(linked_timeout);
 }
 
 static inline void io_queue_sqe(struct io_kiocb *req)
@@ -2072,9 +2062,7 @@ static inline void io_queue_sqe(struct io_kiocb *req)
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
 	 * doesn't support non-blocking read/write attempts
 	 */
-	if (likely(!ret))
-		io_arm_ltimeout(req);
-	else
+	if (unlikely(ret))
 		io_queue_async(req, ret);
 }