From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760648Ab3GZVlp (ORCPT ); Fri, 26 Jul 2013 17:41:45 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:50738 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932397Ab3GZUsZ (ORCPT ); Fri, 26 Jul 2013 16:48:25 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Jason Wang , "Michael S. Tsirkin" , "David S. Miller" Subject: [ 19/79] virtio_net: fix race in RX VQ processing Date: Fri, 26 Jul 2013 13:47:09 -0700 Message-Id: <20130726204723.956415614@linuxfoundation.org> X-Mailer: git-send-email 1.8.3.rc0.20.gb99dd2e In-Reply-To: <20130726204721.849052763@linuxfoundation.org> References: <20130726204721.849052763@linuxfoundation.org> User-Agent: quilt/0.60-5.1.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.10-stable review patch. If anyone has any objections, please let me know. ------------------ From: "Michael S. Tsirkin" [ Upstream commit cbdadbbf0c790f79350a8f36029208944c5487d0 ] 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 Signed-off-by: Greg Kroah-Hartman --- drivers/net/virtio_net.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -602,7 +602,7 @@ static int virtnet_poll(struct napi_stru 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);