diff --git a/fs/io_uring.c b/fs/io_uring.c
index a3ad011820d5639f1b066e1541d77db6a8c91688..e75054ae331ed443c2f325a9b491a0f203a91e7a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1261,6 +1261,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (cqe) {
 		clear_bit(0, &ctx->sq_check_overflow);
 		clear_bit(0, &ctx->cq_check_overflow);
+		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
@@ -1298,6 +1299,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		if (list_empty(&ctx->cq_overflow_list)) {
 			set_bit(0, &ctx->sq_check_overflow);
 			set_bit(0, &ctx->cq_check_overflow);
+			ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
 		}
 		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
@@ -6044,9 +6046,9 @@ static int io_sq_thread(void *data)
 			}
 
 			/* Tell userspace we may need a wakeup call */
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
-			/* make sure to read SQ tail after writing flags */
-			smp_mb();
+			spin_unlock_irq(&ctx->completion_lock);
 
 			to_submit = io_sqring_entries(ctx);
 			if (!to_submit || ret == -EBUSY) {
@@ -6064,13 +6066,17 @@ static int io_sq_thread(void *data)
 				schedule();
 				finish_wait(&ctx->sqo_wait, &wait);
 
+				spin_lock_irq(&ctx->completion_lock);
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				spin_unlock_irq(&ctx->completion_lock);
 				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+			spin_unlock_irq(&ctx->completion_lock);
 		}
 
 		mutex_lock(&ctx->uring_lock);
@@ -7427,6 +7433,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			if (list_empty(&ctx->cq_overflow_list)) {
 				clear_bit(0, &ctx->sq_check_overflow);
 				clear_bit(0, &ctx->cq_check_overflow);
+				ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 			}
 			spin_unlock_irq(&ctx->completion_lock);
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a279151437fcf126cf37c32a736b5295230c8df4..d25c42ae605227dfb13b3dd8720e36de1b2a5ae5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -197,6 +197,7 @@ struct io_sqring_offsets {
  * sq_ring->flags
  */
 #define IORING_SQ_NEED_WAKEUP	(1U << 0) /* needs io_uring_enter wakeup */
+#define IORING_SQ_CQ_OVERFLOW	(1U << 1) /* CQ ring is overflown */
 
 struct io_cqring_offsets {
 	__u32 head;