From cbdadbbf0c790f79350a8f36029208944c5487d0 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 9 Jul 2013 08:13:04 +0300 Subject: [PATCH] virtio_net: fix race in RX VQ processing virtio net called virtqueue_enable_cq on RX path after napi_complete, so with NAPI_STATE_SCHED clear - outside the implicit napi lock. This violates the requirement to synchronize virtqueue_enable_cq wrt virtqueue_add_buf. In particular, used event can move backwards, causing us to lose interrupts. In a debug build, this can trigger panic within START_USE. Jason Wang reports that he can trigger the races artificially, by adding udelay() in virtqueue_enable_cb() after virtio_mb(). However, we must call napi_complete to clear NAPI_STATE_SCHED before polling the virtqueue for used buffers, otherwise napi_schedule_prep in a callback will fail, causing us to lose RX events. To fix, call virtqueue_enable_cb_prepare with NAPI_STATE_SCHED set (under napi lock), later call virtqueue_poll with NAPI_STATE_SCHED clear (outside the lock). Reported-by: Jason Wang Tested-by: Jason Wang Acked-by: Jason Wang Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c9e00387d999..42d670a468f8 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -602,7 +602,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget) container_of(napi, struct receive_queue, napi); struct virtnet_info *vi = rq->vq->vdev->priv; void *buf; - unsigned int len, received = 0; + unsigned int r, len, received = 0; again: while (received < budget && @@ -619,8 +619,9 @@ again: /* Out of packets? */ if (received < budget) { + r = virtqueue_enable_cb_prepare(rq->vq); napi_complete(napi); - if (unlikely(!virtqueue_enable_cb(rq->vq)) && + if (unlikely(virtqueue_poll(rq->vq, r)) && napi_schedule_prep(napi)) { virtqueue_disable_cb(rq->vq); __napi_schedule(napi);