Merge tag 'io_uring-5.15-2021-09-11' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:

 - Fix an off-by-one in a BUILD_BUG_ON() check. Not a real issue right
   now as we have plenty of flags left, but could become one. (Hao)

 - Fix lockdep issue introduced in this merge window (me)

 - Fix a few issues with the worker creation (me, Pavel, Qiang)

 - Fix regression with wq_has_sleeper() for IOPOLL (Pavel)

 - Timeout link error propagation fix (Pavel)

* tag 'io_uring-5.15-2021-09-11' of git://git.kernel.dk/linux-block:
  io_uring: fix off-by-one in BUILD_BUG_ON check of __REQ_F_LAST_BIT
  io_uring: fail links of cancelled timeouts
  io-wq: fix memory leak in create_io_worker()
  io-wq: fix silly logic error in io_task_work_match()
  io_uring: drop ctx->uring_lock before acquiring sqd->lock
  io_uring: fix missing mb() before waitqueue_active
  io-wq: fix cancellation on create-worker failure

1 files changed, 14 insertions, 2 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 855ea544807f..16fb7436043c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1482,6 +1482,8 @@ static void io_kill_timeout(struct io_kiocb *req, int status)
 	struct io_timeout_data *io = req->async_data;
 
 	if (hrtimer_try_to_cancel(&io->timer) != -1) {
+		if (status)
+			req_set_fail(req);
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
@@ -1619,8 +1621,11 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 
 static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
 {
+	/* see waitqueue_active() comment */
+	smp_mb();
+
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		if (wq_has_sleeper(&ctx->cq_wait))
+		if (waitqueue_active(&ctx->cq_wait))
 			wake_up_all(&ctx->cq_wait);
 	}
 	if (io_should_trigger_evfd(ctx))
@@ -10550,7 +10555,14 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		sqd = ctx->sq_data;
 		if (sqd) {
+			/*
+			 * Observe the correct sqd->lock -> ctx->uring_lock
+			 * ordering. Fine to drop uring_lock here, we hold
+			 * a ref to the ctx.
+			 */
+			mutex_unlock(&ctx->uring_lock);
 			mutex_lock(&sqd->lock);
+			mutex_lock(&ctx->uring_lock);
 			tctx = sqd->thread->io_uring;
 		}
 	} else {
@@ -10853,7 +10865,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
 
 	BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
-	BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
+	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
 
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
 				SLAB_ACCOUNT);