From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen@networkplumber.org>
Subject: Re: [PATCH] kni: unregister an unregisterd net_device
 could cause a kernel crash
Date: Thu, 8 Sep 2016 09:47:35 -0700
Message-ID: <20160908094735.5861477b@xeon-e3>
References: <1473388936-2706-1-git-send-email-zhouyates@gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Cc: ferruh.yigit@intel.com, dev@dpdk.org
To: zhouyangchao <zhouyates@gmail.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mail-pa0-f47.google.com (mail-pa0-f47.google.com
 [209.85.220.47]) by dpdk.org (Postfix) with ESMTP id 4A7E2558B
 for <dev@dpdk.org>; Thu,  8 Sep 2016 18:47:26 +0200 (CEST)
Received: by mail-pa0-f47.google.com with SMTP id id6so19001650pad.3
 for <dev@dpdk.org>; Thu, 08 Sep 2016 09:47:26 -0700 (PDT)
In-Reply-To: <1473388936-2706-1-git-send-email-zhouyates@gmail.com>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On Fri,  9 Sep 2016 10:42:16 +0800
zhouyangchao <zhouyates@gmail.com> wrote:

> Signed-off-by: zhouyangchao <zhouyates@gmail.com>
> ---
>  lib/librte_eal/linuxapp/kni/kni_misc.c |    3 +++
>  1 files changed, 3 insertions(+), 0 deletions(-)
> 
> diff --git a/lib/librte_eal/linuxapp/kni/kni_misc.c b/lib/librte_eal/linuxapp/kni/kni_misc.c
> index 67e9b7d..17b6d7a 100644
> --- a/lib/librte_eal/linuxapp/kni/kni_misc.c
> +++ b/lib/librte_eal/linuxapp/kni/kni_misc.c
> @@ -361,6 +361,9 @@ kni_dev_remove(struct kni_dev *dev)
>  		igb_kni_remove(dev->pci_dev);
>  
>  	if (dev->net_dev) {
> +		if (dev->net_dev->state == NETREG_REGISTERED) {
> +			unregister_netdev(dev->net_dev);
> +		}
>  		unregister_netdev(dev->net_dev);
>  		free_netdev(dev->net_dev);
>  	}

The real problem is kni_dev_remove should not be called when register_netdevice
fails. Why not just fix that unwind path.