Merge tag 'io_uring-5.15-2021-10-22' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
"Two fixes for the max workers limit API that was introduced this
series: one fix for an issue with that code, and one fixing a linked
timeout regression in this series"

* tag 'io_uring-5.15-2021-10-22' of git://git.kernel.dk/linux-block:
io_uring: apply worker limits to previous users
io_uring: fix ltimeout unprep
io_uring: apply max_workers limit to all future users
io-wq: max_worker fixes

fs/io-wq.c

···
 		pr_warn_once("io-wq is not configured for unbound workers");
 
 	raw_spin_lock(&wqe->lock);
-	if (acct->nr_workers == acct->max_workers) {
+	if (acct->nr_workers >= acct->max_workers) {
 		raw_spin_unlock(&wqe->lock);
 		return true;
 	}
···
 
 	rcu_read_lock();
 	for_each_node(node) {
+		struct io_wqe *wqe = wq->wqes[node];
 		struct io_wqe_acct *acct;
 
+		raw_spin_lock(&wqe->lock);
 		for (i = 0; i < IO_WQ_ACCT_NR; i++) {
-			acct = &wq->wqes[node]->acct[i];
+			acct = &wqe->acct[i];
 			prev = max_t(int, acct->max_workers, prev);
 			if (new_count[i])
 				acct->max_workers = new_count[i];
 			new_count[i] = prev;
 		}
+		raw_spin_unlock(&wqe->lock);
 	}
 	rcu_read_unlock();
 	return 0;

fs/io_uring.c

···
 		struct work_struct		exit_work;
 		struct list_head		tctx_list;
 		struct completion		ref_comp;
+		u32				iowq_limits[2];
+		bool				iowq_limits_set;
 	};
 };
 
···
 		req->flags |= REQ_F_INFLIGHT;
 		atomic_inc(&current->io_uring->inflight_tracked);
 	}
-}
-
-static inline void io_unprep_linked_timeout(struct io_kiocb *req)
-{
-	req->flags &= ~REQ_F_LINK_TIMEOUT;
 }
 
 static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
···
 		switch (io_arm_poll_handler(req)) {
 		case IO_APOLL_READY:
 			if (linked_timeout)
-				io_unprep_linked_timeout(req);
+				io_queue_linked_timeout(linked_timeout);
 			goto issue_sqe;
 		case IO_APOLL_ABORTED:
 			/*
···
 		ret = io_uring_alloc_task_context(current, ctx);
 		if (unlikely(ret))
 			return ret;
+
 		tctx = current->io_uring;
+		if (ctx->iowq_limits_set) {
+			unsigned int limits[2] = { ctx->iowq_limits[0],
+						   ctx->iowq_limits[1], };
+
+			ret = io_wq_max_workers(tctx->io_wq, limits);
+			if (ret)
+				return ret;
+		}
 	}
 	if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
 		node = kmalloc(sizeof(*node), GFP_KERNEL);
···
 
 static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 					void __user *arg)
+	__must_hold(&ctx->uring_lock)
 {
+	struct io_tctx_node *node;
 	struct io_uring_task *tctx = NULL;
 	struct io_sq_data *sqd = NULL;
 	__u32 new_count[2];
···
 		tctx = current->io_uring;
 	}
 
-	ret = -EINVAL;
-	if (!tctx || !tctx->io_wq)
-		goto err;
+	BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
 
-	ret = io_wq_max_workers(tctx->io_wq, new_count);
-	if (ret)
-		goto err;
+	memcpy(ctx->iowq_limits, new_count, sizeof(new_count));
+	ctx->iowq_limits_set = true;
+
+	ret = -EINVAL;
+	if (tctx && tctx->io_wq) {
+		ret = io_wq_max_workers(tctx->io_wq, new_count);
+		if (ret)
+			goto err;
+	} else {
+		memset(new_count, 0, sizeof(new_count));
+	}
 
 	if (sqd) {
 		mutex_unlock(&sqd->lock);
···
 	if (copy_to_user(arg, new_count, sizeof(new_count)))
 		return -EFAULT;
 
+	/* that's it for SQPOLL, only the SQPOLL task creates requests */
+	if (sqd)
+		return 0;
+
+	/* now propagate the restriction to all registered users */
+	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+		struct io_uring_task *tctx = node->task->io_uring;
+
+		if (WARN_ON_ONCE(!tctx->io_wq))
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(new_count); i++)
+			new_count[i] = ctx->iowq_limits[i];
+		/* ignore errors, it always returns zero anyway */
+		(void)io_wq_max_workers(tctx->io_wq, new_count);
+	}
 	return 0;
 err:
 	if (sqd) {