From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Marc E. Cooper" Subject: Port link speed and link duplex always set to auto-negotiate & manual link speed configuration of 100Mb link speed not possible Date: Thu, 8 Jan 2015 16:26:29 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable To: "dev-VfR2kkLFssw@public.gmane.org" Return-path: In-Reply-To: Content-Language: en-US Content-ID: List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" I believe there are defects in the code supporting manual configuration of port link speed and link duplex to values other than auto-negotiate. The TESTPMD application from DPDK version 1.8.0 was executed on 2 different systems having 4x1G NICs with the following Ethernet controllers: * Intel Corporation 82576 Gigabit Network Connection (rev 01) * Intel Corporation I350 Gigabit Network Connection (rev 01) There appears to be two issues in the code: * "hw->mac.autoneg=B2 is always set to true (1). The force speed and duple= x code path is not followed. * "hw->mac.forced_speed_duplex" is never set. A forced link speed configuration will always default to 10Mb regardless of whether configured for 100Mb or 10Mb. For example, e1000_phy_force_speed_duplex_setup() will always configure link speed to 10mb since it checks for the following condition "if (mac->forced_speed_duplex & E1000_ALL_100_SPEED)=B2. Changes are needed within =B3igb_ethdev.c=B2 and =B3em_ethdev.c=B2 within =B3lib/librte_pmd_e1000=B2. The switch statements that setup link speed an= d link duplex within these files need to manually set "hw->mac.autoneg" and "hw->mac.forced_speed_duplex" as shown below: [root@box librte_pmd_e1000]# pwd /home/marc/dpdk/dpdk-1.8.0/lib/librte_pmd_e1000 [root@box librte_pmd_e1000]# diff -p igb_ethdev.c.orig igb_ethdev.c *** igb_ethdev.c.orig 2015-01-08 09:59:52.937215791 -0500 --- igb_ethdev.c 2015-01-08 10:01:44.073730592 -0500 *************** eth_igb_start(struct rte_eth_dev *dev) *** 871,876 **** --- 871,878 ---- hw->phy.autoneg_advertised =3D ADVERTISE_10_FULL; else goto error_invalid_config; + hw->mac.autoneg =3D 0; + hw->mac.forced_speed_duplex |=3D hw->phy.autoneg_advertised= ; break; case ETH_LINK_SPEED_100: if (dev->data->dev_conf.link_duplex =3D=3D ETH_LINK_AUTONEG_DUPLEX) *************** eth_igb_start(struct rte_eth_dev *dev) *** 881,886 **** --- 883,890 ---- hw->phy.autoneg_advertised =3D ADVERTISE_100_FULL; else goto error_invalid_config; + hw->mac.autoneg =3D 0; + hw->mac.forced_speed_duplex |=3D hw->phy.autoneg_advertised= ; break; case ETH_LINK_SPEED_1000: if ((dev->data->dev_conf.link_duplex =3D=3D ETH_LINK_AUTONEG_DUPLEX) || *************** eth_igb_start(struct rte_eth_dev *dev) *** 888,893 **** --- 892,899 ---- hw->phy.autoneg_advertised =3D ADVERTISE_1000_FULL; else goto error_invalid_config; + hw->mac.autoneg =3D 0; + hw->mac.forced_speed_duplex |=3D hw->phy.autoneg_advertised= ; break; case ETH_LINK_SPEED_10000: default: [root@box librte_pmd_e1000]# After only setting hw->mac.autoneg =3D 0 in the switch statement cases described above I experimented with configuring the peer (switch) ports for 100Mb full duplex. Within TESTPMD the ports were also configured for 100Mb full duplex using =B3port config all speed 100 duplex full=B2. The links failed to establish. I enabled debug statements within =B3e1000_phy_force_speed_duplex_setup()=B2 found in =B3lib/librte_pmd_e1000/e1000/e1000_phy.c=B2 to display whether 100mb or 10= mb was being forced. It was observed that 10Mb was being forced when the link speed was manually configured for 100Mb. Setting =B3hw->mac.force_speed_duplex=B2 as shown above seemed to resolve this issu= e and the links came up. =20 Are these known issues? -Marc