virtio_ring: Avoid loop when vq is broken in virtqueue_poll
authorMao Wenan <wenan.mao@linux.alibaba.com>
Sun, 2 Aug 2020 07:44:09 +0000 (15:44 +0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 26 Aug 2020 08:29:05 +0000 (10:29 +0200)
[ 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@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/1596354249-96204-1-git-send-email-wenan.mao@linux.alibaba.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drivers/virtio/virtio_ring.c

index e459cd7302e2739efb5c699c3f402d7ab407aee5..5cad9f41c238b952e0eea63363a8f3b10324a512 100644 (file)
@@ -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);
 }