diff --git a/fs/io_uring.c b/fs/io_uring.c
index eff29d705a26..b2f88c2dc2fd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2052,11 +2052,11 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 }
 
 static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s)
+			struct sqe_submit *s, bool force_nonblock)
 {
 	int ret;
 
-	ret = __io_submit_sqe(ctx, req, s, true);
+	ret = __io_submit_sqe(ctx, req, s, force_nonblock);
 	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
 
@@ -2099,7 +2099,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 }
 
 static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s)
+			struct sqe_submit *s, bool force_nonblock)
 {
 	int ret;
 
@@ -2112,17 +2112,18 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		return 0;
 	}
 
-	return __io_queue_sqe(ctx, req, s);
+	return __io_queue_sqe(ctx, req, s, force_nonblock);
 }
 
 static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			      struct sqe_submit *s, struct io_kiocb *shadow)
+			      struct sqe_submit *s, struct io_kiocb *shadow,
+			      bool force_nonblock)
 {
 	int ret;
 	int need_submit = false;
 
 	if (!shadow)
-		return io_queue_sqe(ctx, req, s);
+		return io_queue_sqe(ctx, req, s, force_nonblock);
 
 	/*
 	 * Mark the first IO in link list as DRAIN, let all the following
@@ -2151,7 +2152,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	spin_unlock_irq(&ctx->completion_lock);
 
 	if (need_submit)
-		return __io_queue_sqe(ctx, req, s);
+		return __io_queue_sqe(ctx, req, s, force_nonblock);
 
 	return 0;
 }
@@ -2159,7 +2160,8 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
 
 static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
-			  struct io_submit_state *state, struct io_kiocb **link)
+			  struct io_submit_state *state, struct io_kiocb **link,
+			  bool force_nonblock)
 {
 	struct io_uring_sqe *sqe_copy;
 	struct io_kiocb *req;
@@ -2212,7 +2214,7 @@ err:
 		INIT_LIST_HEAD(&req->link_list);
 		*link = req;
 	} else {
-		io_queue_sqe(ctx, req, s);
+		io_queue_sqe(ctx, req, s, force_nonblock);
 	}
 }
 
@@ -2316,7 +2318,8 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 		 * that's the end of the chain. Submit the previous link.
 		 */
 		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req);
+			io_queue_link_head(ctx, link, &link->submit, shadow_req,
+						true);
 			link = NULL;
 		}
 		prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0;
@@ -2337,13 +2340,13 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 			sqes[i].has_user = has_user;
 			sqes[i].needs_lock = true;
 			sqes[i].needs_fixed_file = true;
-			io_submit_sqe(ctx, &sqes[i], statep, &link);
+			io_submit_sqe(ctx, &sqes[i], statep, &link, true);
 			submitted++;
 		}
 	}
 
 	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req);
+		io_queue_link_head(ctx, link, &link->submit, shadow_req, true);
 	if (statep)
 		io_submit_state_end(&state);
 
@@ -2475,7 +2478,8 @@ static int io_sq_thread(void *data)
 	return 0;
 }
 
-static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
+static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
+			  bool block_for_last)
 {
 	struct io_submit_state state, *statep = NULL;
 	struct io_kiocb *link = NULL;
@@ -2489,6 +2493,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 	}
 
 	for (i = 0; i < to_submit; i++) {
+		bool force_nonblock = true;
 		struct sqe_submit s;
 
 		if (!io_get_sqring(ctx, &s))
@@ -2499,7 +2504,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		 * that's the end of the chain. Submit the previous link.
 		 */
 		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req);
+			io_queue_link_head(ctx, link, &link->submit, shadow_req,
+						force_nonblock);
 			link = NULL;
 		}
 		prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
@@ -2517,12 +2523,24 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
 		submit++;
-		io_submit_sqe(ctx, &s, statep, &link);
+
+		/*
+		 * The caller will block for events after submit, submit the
+		 * last IO non-blocking. This is either the only IO it's
+		 * submitting, or it already submitted the previous ones. This
+		 * improves performance by avoiding an async punt that we don't
+		 * need to do.
+		 */
+		if (block_for_last && submit == to_submit)
+			force_nonblock = false;
+
+		io_submit_sqe(ctx, &s, statep, &link, force_nonblock);
 	}
 	io_commit_sqring(ctx);
 
 	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req);
+		io_queue_link_head(ctx, link, &link->submit, shadow_req,
+					block_for_last);
 	if (statep)
 		io_submit_state_end(statep);
 
@@ -3290,10 +3308,21 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 
 	ret = 0;
 	if (to_submit) {
+		bool block_for_last = false;
+
 		to_submit = min(to_submit, ctx->sq_entries);
 
+		/*
+		 * Allow last submission to block in a series, IFF the caller
+		 * asked to wait for events and we don't currently have
+		 * enough. This potentially avoids an async punt.
+		 */
+		if (to_submit == min_complete &&
+		    io_cqring_events(ctx->rings) < min_complete)
+			block_for_last = true;
+
 		mutex_lock(&ctx->uring_lock);
-		submitted = io_ring_submit(ctx, to_submit);
+		submitted = io_ring_submit(ctx, to_submit, block_for_last);
 		mutex_unlock(&ctx->uring_lock);
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {