[PATCH 4.9 26/39] virtio_ring: Avoid loop when vq is broken in virtqueue_poll

[Greg Kroah-Hartman]

From: Mao Wenan <wenan.mao@xxxxxxxxxxxxxxxxx>

[ Upstream commit 481a0d7422db26fb63e2d64f0652667a5c6d0f3e ]

The loop may exist if vq->broken is true,
virtqueue_get_buf_ctx_packed or virtqueue_get_buf_ctx_split
will return NULL, so virtnet_poll will reschedule napi to
receive packet, it will lead cpu usage(si) to 100%.

call trace as below:
virtnet_poll
	virtnet_receive
		virtqueue_get_buf_ctx
			virtqueue_get_buf_ctx_packed
			virtqueue_get_buf_ctx_split
	virtqueue_napi_complete
		virtqueue_poll           //return true
		virtqueue_napi_schedule //it will reschedule napi

to fix this, return false if vq is broken in virtqueue_poll.

Signed-off-by: Mao Wenan <wenan.mao@xxxxxxxxxxxxxxxxx>
Acked-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Link: https://lore.kernel.org/r/1596354249-96204-1-git-send-email-wenan.mao@xxxxxxxxxxxxxxxxx
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Acked-by: Jason Wang <jasowang@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/virtio/virtio_ring.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index e459cd7302e27..5cad9f41c238b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -785,6 +785,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (unlikely(vq->broken))
+		return false;
+
 	virtio_mb(vq->weak_barriers);
 	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
 }
-- 
2.25.1