io_uring: provide IORING_ENTER_SQ_WAIT for SQPOLL SQ ring waits

When using SQPOLL, applications can run into the issue of running out of
SQ ring entries because the thread hasn't consumed them yet. The only
option for dealing with that is checking later, or busy checking for the
condition.

Provide IORING_ENTER_SQ_WAIT if applications want to wait on this
condition.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -301,6 +301,7 @@ struct io_ring_ctx {
 
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */
 
+	struct wait_queue_head	sqo_sq_wait;
 	struct wait_queue_entry	sqo_wait_entry;
 	struct list_head	sqd_list;
 
@@ -1072,6 +1073,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	init_waitqueue_head(&ctx->sqo_sq_wait);
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
@@ -1324,6 +1326,13 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 		__io_queue_deferred(ctx);
 }
 
+static inline bool io_sqring_full(struct io_ring_ctx *ctx)
+{
+	struct io_rings *r = ctx->rings;
+
+	return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries;
+}
+
 static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
@@ -6736,6 +6745,10 @@ again:
 	if (likely(!percpu_ref_is_dying(&ctx->refs)))
 		ret = io_submit_sqes(ctx, to_submit);
 	mutex_unlock(&ctx->uring_lock);
+
+	if (!io_sqring_full(ctx) && wq_has_sleeper(&ctx->sqo_sq_wait))
+		wake_up(&ctx->sqo_sq_wait);
+
 	return SQT_DID_WORK;
 }
 
@@ -8231,8 +8244,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	 * io_commit_cqring
 	 */
 	smp_rmb();
-	if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head !=
+	if (!io_sqring_full(ctx))
-	    ctx->rings->sq_ring_entries)
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (io_cqring_events(ctx, false))
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -8801,6 +8813,25 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
 
 #endif /* !CONFIG_MMU */
 
+static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
+{
+	DEFINE_WAIT(wait);
+
+	do {
+		if (!io_sqring_full(ctx))
+			break;
+
+		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
+
+		if (!io_sqring_full(ctx))
+			break;
+
+		schedule();
+	} while (!signal_pending(current));
+
+	finish_wait(&ctx->sqo_sq_wait, &wait);
+}
+
 SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		u32, min_complete, u32, flags, const sigset_t __user *, sig,
 		size_t, sigsz)
@@ -8812,7 +8843,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 
 	io_run_task_work();
 
-	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP))
+	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
+			IORING_ENTER_SQ_WAIT))
 		return -EINVAL;
 
 	f = fdget(fd);
@@ -8843,6 +8875,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			io_cqring_overflow_flush(ctx, false, NULL, NULL);
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sq_data->wait);
+		if (flags & IORING_ENTER_SQ_WAIT)
+			io_sqpoll_wait_sq(ctx);
 		submitted = to_submit;
 	} else if (to_submit) {
 		ret = io_uring_add_task_file(f.file);

include/uapi/linux/io_uring.h

@@ -225,6 +225,7 @@ struct io_cqring_offsets {
  */
 #define IORING_ENTER_GETEVENTS	(1U << 0)
 #define IORING_ENTER_SQ_WAKEUP	(1U << 1)
+#define IORING_ENTER_SQ_WAIT	(1U << 2)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success