1 files changed, 43 insertions, 48 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 19de7129ae0b..52ada466bf98 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -441,24 +441,6 @@ 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];
@@ -511,7 +493,6 @@ 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);
@@ -536,8 +517,6 @@ 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 void io_req_queue_iowq_tw(struct io_kiocb *req, struct io_tw_state *ts)
@@ -651,6 +630,7 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying)
 		 * to care for a non-real case.
 		 */
 		if (need_resched()) {
+			ctx->cqe_sentinel = ctx->cqe_cached;
 			io_cq_unlock_post(ctx);
 			mutex_unlock(&ctx->uring_lock);
 			cond_resched();
@@ -884,13 +864,26 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
 	struct io_ring_ctx *ctx = req->ctx;
 	bool posted;
 
+	/*
+	 * 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);
+
 	lockdep_assert(!io_wq_current_is_worker());
 	lockdep_assert_held(&ctx->uring_lock);
 
-	__io_cq_lock(ctx);
-	posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	if (!ctx->lockless_cq) {
+		spin_lock(&ctx->completion_lock);
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+		spin_unlock(&ctx->completion_lock);
+	} else {
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	}
+
 	ctx->submit_state.cq_flush = true;
-	__io_cq_unlock_post(ctx);
 	return posted;
 }
 
@@ -1103,21 +1096,22 @@ 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);
 	}
 }
@@ -1687,7 +1681,7 @@ queue:
 	spin_unlock(&ctx->completion_lock);
 
 	io_prep_async_link(req);
-	de = kmalloc(sizeof(*de), GFP_KERNEL);
+	de = kmalloc(sizeof(*de), GFP_KERNEL_ACCOUNT);
 	if (!de) {
 		ret = -ENOMEM;
 		io_req_defer_failed(req, ret);
@@ -1722,17 +1716,24 @@ 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);
@@ -1742,8 +1743,12 @@ 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)
@@ -1756,7 +1761,6 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (ret == IOU_ISSUE_SKIP_COMPLETE) {
 		ret = 0;
-		io_arm_ltimeout(req);
 
 		/* If the op doesn't have a file, we're not polling for it */
 		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
@@ -1777,7 +1781,7 @@ 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);
@@ -1799,8 +1803,6 @@ 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 (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) {
 fail:
@@ -1920,15 +1922,11 @@ 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);
@@ -1941,9 +1939,6 @@ 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)
@@ -2921,7 +2916,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 			struct task_struct *tsk;
 
 			io_sq_thread_park(sqd);
-			tsk = sqd->thread;
+			tsk = sqpoll_task_locked(sqd);
 			if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
 				io_wq_cancel_cb(tsk->io_uring->io_wq,
 						io_cancel_ctx_cb, ctx, true);
@@ -3158,7 +3153,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 	s64 inflight;
 	DEFINE_WAIT(wait);
 
-	WARN_ON_ONCE(sqd && sqd->thread != current);
+	WARN_ON_ONCE(sqd && sqpoll_task_locked(sqd) != current);
 
 	if (!current->io_uring)
 		return;