io_uring: only return -EBUSY for submit on non-flushed backlog

to #25570445

commit c4a2ed72c9a61594b6afc23e1fbc78878d32b5a3 upstream.

We return -EBUSY on submit when we have a CQ ring overflow backlog, but
that can be a bit problematic if the application is using pure userspace
poll of the CQ ring. For that case, if the ring briefly overflowed and
we have pending entries in the backlog, the submit flushes the backlog
successfully but still returns -EBUSY. If we're able to fully flush the
CQ ring backlog, let the submission proceed.
Reported-by: NDan Melnic <dmm@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Reviewed-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

fs/io_uring.c

@@ -637,7 +637,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 		eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
-static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
+/* Returns true if there are no backlogged entries after the flush */
+static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 {
 	struct io_rings *rings = ctx->rings;
 	struct io_uring_cqe *cqe;
@@ -647,10 +648,10 @@ static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 
 	if (!force) {
 		if (list_empty_careful(&ctx->cq_overflow_list))
-			return;
+			return true;
 		if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) ==
 		    rings->cq_ring_entries))
-			return;
+			return false;
 	}
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
@@ -659,6 +660,7 @@ static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (force)
 		ctx->cq_overflow_flushed = true;
 
+	cqe = NULL;
 	while (!list_empty(&ctx->cq_overflow_list)) {
 		cqe = io_get_cqring(ctx);
 		if (!cqe && !force)
@@ -686,6 +688,8 @@ static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 		list_del(&req->list);
 		io_put_req(req);
 	}
+
+	return cqe != NULL;
 }
 
 static void io_cqring_fill_event(struct io_kiocb *req, long res)
@@ -3076,10 +3080,10 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 	int i, submitted = 0;
 	bool mm_fault = false;
 
-	if (!list_empty(&ctx->cq_overflow_list)) {
-		io_cqring_overflow_flush(ctx, false);
+	/* if we have a backlog and couldn't flush it all, return BUSY */
+	if (!list_empty(&ctx->cq_overflow_list) &&
+	    !io_cqring_overflow_flush(ctx, false))
 		return -EBUSY;
-	}
 
 	if (nr > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, nr);