From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id EB3C4593A for ; Mon, 5 Jan 2015 02:01:04 +0100 (CET) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP; 04 Jan 2015 16:56:26 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.07,696,1413270000"; d="scan'208";a="656722351" Received: from pgsmsx103.gar.corp.intel.com ([10.221.44.82]) by fmsmga002.fm.intel.com with ESMTP; 04 Jan 2015 17:01:02 -0800 Received: from shsmsx103.ccr.corp.intel.com (10.239.110.14) by PGSMSX103.gar.corp.intel.com (10.221.44.82) with Microsoft SMTP Server (TLS) id 14.3.195.1; Mon, 5 Jan 2015 09:00:32 +0800 Received: from shsmsx102.ccr.corp.intel.com ([169.254.2.216]) by SHSMSX103.ccr.corp.intel.com ([169.254.4.240]) with mapi id 14.03.0195.001; Mon, 5 Jan 2015 09:00:31 +0800 From: "Ouyang, Changchun" To: Vlad Zolotarov , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH v4 4/6] ether: Check VMDq RSS mode Thread-Index: AQHQJ+7Af2HXAdw//UuhL/WSKplfqpyvH4kAgACIdUD//4hzAIABhEVg Date: Mon, 5 Jan 2015 01:00:30 +0000 Message-ID: References: <1419398584-19520-1-git-send-email-changchun.ouyang@intel.com> <1420355937-18484-1-git-send-email-changchun.ouyang@intel.com> <1420355937-18484-5-git-send-email-changchun.ouyang@intel.com> <54A8FD9A.8040701@cloudius-systems.com> <54A90BC8.8020307@cloudius-systems.com> In-Reply-To: <54A90BC8.8020307@cloudius-systems.com> Accept-Language: zh-CN, 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 v4 4/6] ether: Check VMDq RSS mode 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, 05 Jan 2015 01:01:05 -0000 > -----Original Message----- > From: Vlad Zolotarov [mailto:vladz@cloudius-systems.com] > Sent: Sunday, January 4, 2015 5:46 PM > To: Ouyang, Changchun; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v4 4/6] ether: Check VMDq RSS mode >=20 >=20 > On 01/04/15 10:58, Ouyang, Changchun wrote: > >> -----Original Message----- > >> From: Vlad Zolotarov [mailto:vladz@cloudius-systems.com] > >> Sent: Sunday, January 4, 2015 4:45 PM > >> To: Ouyang, Changchun; dev@dpdk.org > >> Subject: Re: [dpdk-dev] [PATCH v4 4/6] ether: Check VMDq RSS mode > >> > >> > >> On 01/04/15 09:18, Ouyang Changchun wrote: > >>> Check mq mode for VMDq RSS, handle it correctly instead of returning > >>> an error; Also remove the limitation of per pool queue number has > >>> max value of 1, because the per pool queue number could be 2 or 4 if > >>> it is VMDq RSS mode; > >>> > >>> The number of rxq specified in config will determine the mq mode for > >> VMDq RSS. > >>> Signed-off-by: Changchun Ouyang > >>> --- > >>> lib/librte_ether/rte_ethdev.c | 39 > >> ++++++++++++++++++++++++++++++++++----- > >>> 1 file changed, 34 insertions(+), 5 deletions(-) > >>> > >>> diff --git a/lib/librte_ether/rte_ethdev.c > >>> b/lib/librte_ether/rte_ethdev.c index 95f2ceb..59ff325 100644 > >>> --- a/lib/librte_ether/rte_ethdev.c > >>> +++ b/lib/librte_ether/rte_ethdev.c > >>> @@ -510,8 +510,7 @@ rte_eth_dev_check_mq_mode(uint8_t port_id, > >>> uint16_t nb_rx_q, uint16_t nb_tx_q, > >>> > >>> if (RTE_ETH_DEV_SRIOV(dev).active !=3D 0) { > >>> /* check multi-queue mode */ > >>> - if ((dev_conf->rxmode.mq_mode =3D=3D ETH_MQ_RX_RSS) || > >>> - (dev_conf->rxmode.mq_mode =3D=3D ETH_MQ_RX_DCB) || > >>> + if ((dev_conf->rxmode.mq_mode =3D=3D ETH_MQ_RX_DCB) || > >>> (dev_conf->rxmode.mq_mode =3D=3D ETH_MQ_RX_DCB_RSS) > >> || > >>> (dev_conf->txmode.mq_mode =3D=3D ETH_MQ_TX_DCB)) { > >>> /* SRIOV only works in VMDq enable mode */ @@ - > >> 525,7 +524,6 @@ > >>> rte_eth_dev_check_mq_mode(uint8_t port_id, uint16_t nb_rx_q, > >> uint16_t nb_tx_q, > >>> } > >>> > >>> switch (dev_conf->rxmode.mq_mode) { > >>> - case ETH_MQ_RX_VMDQ_RSS: > >>> case ETH_MQ_RX_VMDQ_DCB: > >>> case ETH_MQ_RX_VMDQ_DCB_RSS: > >>> /* DCB/RSS VMDQ in SRIOV mode, not implement > >> yet */ @@ -534,6 > >>> +532,39 @@ rte_eth_dev_check_mq_mode(uint8_t port_id, uint16_t > >> nb_rx_q, uint16_t nb_tx_q, > >>> "unsupported VMDQ mq_mode > >> rx %u\n", > >>> port_id, dev_conf- > >>> rxmode.mq_mode); > >>> return (-EINVAL); > >>> + case ETH_MQ_RX_RSS: > >>> + PMD_DEBUG_TRACE("ethdev port_id=3D%" PRIu8 > >>> + " SRIOV active, " > >>> + "Rx mq mode is changed from:" > >>> + "mq_mode %u into VMDQ > >> mq_mode %u\n", > >>> + port_id, > >>> + dev_conf->rxmode.mq_mode, > >>> + dev->data- > >>> dev_conf.rxmode.mq_mode); > >>> + case ETH_MQ_RX_VMDQ_RSS: > >>> + dev->data->dev_conf.rxmode.mq_mode =3D > >> ETH_MQ_RX_VMDQ_RSS; > >>> + if (nb_rx_q < > >> RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool) { >=20 > Missed that before: shouldn't it be "<=3D" here? Agree with you, need <=3D here, I will fix it in v5 >=20 > >>> + switch (nb_rx_q) { > >>> + case 1: > >>> + case 2: > >>> + RTE_ETH_DEV_SRIOV(dev).active =3D > >>> + ETH_64_POOLS; > >>> + break; > >>> + case 4: > >>> + RTE_ETH_DEV_SRIOV(dev).active =3D > >>> + ETH_32_POOLS; > >>> + break; > >>> + default: > >>> + PMD_DEBUG_TRACE("ethdev > >> port_id=3D%d" > >>> + " SRIOV active, " > >>> + "queue number invalid\n", > >>> + port_id); > >>> + return -EINVAL; > >>> + } > >>> + RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool =3D > >> nb_rx_q; > >>> + RTE_ETH_DEV_SRIOV(dev).def_pool_q_idx =3D > >>> + dev->pci_dev->max_vfs * nb_rx_q; > >>> + } > >> Don't u need to return an error in the "else" here? > > Actually it has such a check after these code snippet, and it does > > return error for the else case, Because it is original logic, I don't c= hange any > code around it, so it doesn't display here, you can check the codes. >=20 > I see. The flow is a bit confusing since the switch-case above will end u= p > executing a "default" clause which will set > RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool to 1 and then the error message > in the check u are referring will be a bit confusing. ' set RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool to 1 ' is original code, which i= s for vmdq only case, or single queue case. It is in default clause, and not in VMDQ_RSS clause. I think my new code is ok here. > > > > Thanks > > Changchun > > > >