Merge tag 'io_uring-6.3-2023-03-09' of git://git.kernel.dk/linux

Pull io_uring fixes from Jens Axboe:

 - Stop setting PF_NO_SETAFFINITY on io-wq workers.

   This has been reported in the past as it confuses some applications,
   as some of their threads will fail with -1/EINVAL if attempted
   affinitized. Most recent report was on cpusets, where enabling that
   with io-wq workers active will fail.

   Just deal with the mask changing by checking when a worker times out,
   and then exit if we have no work pending.

 - Fix an issue with passthrough support where we don't properly check
   if the file type has pollable uring_cmd support.

 - Fix a reported W=1 warning on a variable being set and unused. Add a
   special helper for iterating these lists that doesn't save the
   previous list element, if that iterator never ends up using it.

* tag 'io_uring-6.3-2023-03-09' of git://git.kernel.dk/linux:
  io_uring: silence variable ‘prev’ set but not used warning
  io_uring/uring_cmd: ensure that device supports IOPOLL
  io_uring/io-wq: stop setting PF_NO_SETAFFINITY on io-wq workers

4 files changed, 20 insertions, 9 deletions

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 411bb2d1acd4..f81c0a7136a5 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -616,7 +616,7 @@ static int io_wqe_worker(void *data)
 	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
-	bool last_timeout = false;
+	bool exit_mask = false, last_timeout = false;
 	char buf[TASK_COMM_LEN];
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
@@ -632,8 +632,11 @@ static int io_wqe_worker(void *data)
 			io_worker_handle_work(worker);
 
 		raw_spin_lock(&wqe->lock);
-		/* timed out, exit unless we're the last worker */
-		if (last_timeout && acct->nr_workers > 1) {
+		/*
+		 * Last sleep timed out. Exit if we're not the last worker,
+		 * or if someone modified our affinity.
+		 */
+		if (last_timeout && (exit_mask || acct->nr_workers > 1)) {
 			acct->nr_workers--;
 			raw_spin_unlock(&wqe->lock);
 			__set_current_state(TASK_RUNNING);
@@ -652,7 +655,11 @@ static int io_wqe_worker(void *data)
 				continue;
 			break;
 		}
-		last_timeout = !ret;
+		if (!ret) {
+			last_timeout = true;
+			exit_mask = !cpumask_test_cpu(raw_smp_processor_id(),
+							wqe->cpu_mask);
+		}
 	}
 
 	if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
@@ -704,7 +711,6 @@ static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker,
 	tsk->worker_private = worker;
 	worker->task = tsk;
 	set_cpus_allowed_ptr(tsk, wqe->cpu_mask);
-	tsk->flags |= PF_NO_SETAFFINITY;
 
 	raw_spin_lock(&wqe->lock);
 	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index fd1cc35a1c00..722624b6d0dc 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1499,14 +1499,14 @@ void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node)
 static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
 	__must_hold(&ctx->uring_lock)
 {
-	struct io_wq_work_node *node, *prev;
 	struct io_submit_state *state = &ctx->submit_state;
+	struct io_wq_work_node *node;
 
 	__io_cq_lock(ctx);
 	/* must come first to preserve CQE ordering in failure cases */
 	if (state->cqes_count)
 		__io_flush_post_cqes(ctx);
-	wq_list_for_each(node, prev, &state->compl_reqs) {
+	__wq_list_for_each(node, &state->compl_reqs) {
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 					    comp_list);
 
diff --git a/io_uring/slist.h b/io_uring/slist.h
index 7c198a40d5f1..0eb194817242 100644
--- a/io_uring/slist.h
+++ b/io_uring/slist.h
@@ -3,6 +3,9 @@
 
 #include <linux/io_uring_types.h>
 
+#define __wq_list_for_each(pos, head)				\
+	for (pos = (head)->first; pos; pos = (pos)->next)
+
 #define wq_list_for_each(pos, prv, head)			\
 	for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
 
@@ -113,4 +116,4 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
 	return container_of(work->list.next, struct io_wq_work, list);
 }
 
-#endif // INTERNAL_IO_SLIST_H
\ No newline at end of file
+#endif // INTERNAL_IO_SLIST_H
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 446a189b78b0..2e4c483075d3 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -108,7 +108,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *file = req->file;
 	int ret;
 
-	if (!req->file->f_op->uring_cmd)
+	if (!file->f_op->uring_cmd)
 		return -EOPNOTSUPP;
 
 	ret = security_uring_cmd(ioucmd);
@@ -120,6 +120,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 	if (ctx->flags & IORING_SETUP_CQE32)
 		issue_flags |= IO_URING_F_CQE32;
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
+		if (!file->f_op->uring_cmd_iopoll)
+			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
 		WRITE_ONCE(ioucmd->cookie, NULL);