From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 235372BE4 for ; Mon, 25 Apr 2016 09:33:58 +0200 (CEST) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga102.jf.intel.com with ESMTP; 25 Apr 2016 00:33:57 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.24,531,1455004800"; d="scan'208";a="939490394" Received: from fmsmsx107.amr.corp.intel.com ([10.18.124.205]) by orsmga001.jf.intel.com with ESMTP; 25 Apr 2016 00:33:43 -0700 Received: from fmsmsx153.amr.corp.intel.com (10.18.125.6) by fmsmsx107.amr.corp.intel.com (10.18.124.205) with Microsoft SMTP Server (TLS) id 14.3.248.2; Mon, 25 Apr 2016 00:33:42 -0700 Received: from shsmsx104.ccr.corp.intel.com (10.239.4.70) by FMSMSX153.amr.corp.intel.com (10.18.125.6) with Microsoft SMTP Server (TLS) id 14.3.248.2; Mon, 25 Apr 2016 00:33:42 -0700 Received: from shsmsx101.ccr.corp.intel.com ([169.254.1.136]) by SHSMSX104.ccr.corp.intel.com ([169.254.5.184]) with mapi id 14.03.0248.002; Mon, 25 Apr 2016 15:33:40 +0800 From: "Xie, Huawei" To: "Tan, Jianfeng" , "dev@dpdk.org" CC: "yuanhan.liu@linux.intel.com" , "Stephen Hemminger" Thread-Topic: [PATCH v2] virtio: fix segfault when transmit pkts Thread-Index: AdGexMlnk4tr0GkvWUC33ZQUXpHbnw== Date: Mon, 25 Apr 2016 07:33:40 +0000 Message-ID: References: <1461242170-146337-1-git-send-email-jianfeng.tan@intel.com> <1461551865-15930-1-git-send-email-jianfeng.tan@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v2] virtio: fix segfault when transmit pkts X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 25 Apr 2016 07:33:59 -0000 On 4/25/2016 10:37 AM, Tan, Jianfeng wrote:=0A= > Issue: when using virtio nic to transmit pkts, it causes segment fault.= =0A= >=0A= > How to reproduce:=0A= > Basically, we need to construct a case with vm send packets to vhost-user= ,=0A= > and this issue does not happen when transmitting packets using indirect= =0A= > desc. Besides, make sure all descriptors are exhausted before vhost=0A= > dequeues any packets.=0A= >=0A= > a. start testpmd with vhost.=0A= > $ testpmd -c 0x3 -n 4 --socket-mem 1024,0 --no-pci \=0A= > --vdev 'eth_vhost0,iface=3D/tmp/sock0,queues=3D1' -- -i --nb-cores=3D= 1=0A= >=0A= > b. start a qemu with a virtio nic connected with the vhost-user port, jus= t=0A= > make sure mrg_rxbuf is enabled.=0A= >=0A= > c. enable testpmd on the host.=0A= > testpmd> set fwd io=0A= > testpmd> start (better without start vhost-user)=0A= >=0A= > d. start testpmd in VM.=0A= > $testpmd -c 0x3 -n 4 -m 1024 -- -i --disable-hw-vlan-filter --txqflags= =3D0xf01=0A= > testpmd> set fwd txonly=0A= > testpmd> start=0A= >=0A= > How to fix: this bug is because inside virtqueue_enqueue_xmit(), the flag= of=0A= > desc has been updated inside the do {} while (), not necessary to update = after=0A= > the loop. (And if we do that after the loop, if all descs could have run = out,=0A= > idx is VQ_RING_DESC_CHAIN_END (32768), use this idx to reference the star= t_dp=0A= > array will lead to segment fault.)=0A= >=0A= > Fixes: dd856dfcb9e ("virtio: use any layout on Tx")=0A= >=0A= > Signed-off-by: Jianfeng Tan =0A= > ---=0A= > v2: refine the commit message.=0A= >=0A= > drivers/net/virtio/virtio_rxtx.c | 2 --=0A= > 1 file changed, 2 deletions(-)=0A= >=0A= > diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio= _rxtx.c=0A= > index ef21d8e..432aeab 100644=0A= > --- a/drivers/net/virtio/virtio_rxtx.c=0A= > +++ b/drivers/net/virtio/virtio_rxtx.c=0A= > @@ -271,8 +271,6 @@ virtqueue_enqueue_xmit(struct virtqueue *txvq, struct= rte_mbuf *cookie,=0A= > idx =3D start_dp[idx].next;=0A= > } while ((cookie =3D cookie->next) !=3D NULL);=0A= > =0A= > - start_dp[idx].flags &=3D ~VRING_DESC_F_NEXT;=0A= > -=0A= > if (use_indirect)=0A= > idx =3D txvq->vq_ring.desc[head_idx].next;=0A= > =0A= =0A= Ack the code.=0A= =0A= Acked-by: Huawei Xie =0A=