My bad I will fix it. Sorry for your trouble. It should be: port_conf.txmode.offloads &= dev_info.tx_offload_capa
http://patches.dpdk.org/patch/47877/ Thanks, Ori From: Cliff Burdick <shakl...@gmail.com> Sent: Tuesday, November 6, 2018 3:18 AM To: Ori Kam <or...@mellanox.com> Cc: Shahaf Shuler <shah...@mellanox.com>; users <users@dpdk.org> Subject: Re: [dpdk-users] flow_filtering failed on mlx5 Hi Ori, your patch has: port_conf.txmode.offloads &= dev_info.rx_offload_capa; Should that right side by rx_offload_capa instead? On Mon, Nov 5, 2018 at 11:42 AM Cliff Burdick <shakl...@gmail.com<mailto:shakl...@gmail.com>> wrote: Thanks Ori. I confirmed that the latest patch works with VLAN tags as well. On Mon, Nov 5, 2018 at 6:05 AM Ori Kam <or...@mellanox.com<mailto:or...@mellanox.com>> wrote: Just verified by running the code at least in Mellanox there is no difference. Best, Ori From: Cliff Burdick <shakl...@gmail.com<mailto:shakl...@gmail.com>> Sent: Monday, November 5, 2018 3:57 PM To: Ori Kam <or...@mellanox.com<mailto:or...@mellanox.com>> Cc: Shahaf Shuler <shah...@mellanox.com<mailto:shah...@mellanox.com>>; users <users@dpdk.org<mailto:users@dpdk.org>> Subject: Re: [dpdk-users] flow_filtering failed on mlx5 The example code used to allow a VLAN tag, but with this patch it seems like it will not anymore. I'm on a connectx-5. Should we set the mask to NULL to achieve the same functionality as before? Thanks On Mon, Nov 5, 2018, 05:54 Ori Kam <or...@mellanox.com<mailto:or...@mellanox.com> wrote: Glad to help, That’s depends on the NIC but normally it should just be ETH / IPV4 traffic. Best, Ori From: Cliff Burdick <shakl...@gmail.com<mailto:shakl...@gmail.com>> Sent: Monday, November 5, 2018 3:42 PM To: Ori Kam <or...@mellanox.com<mailto:or...@mellanox.com>> Cc: Shahaf Shuler <shah...@mellanox.com<mailto:shah...@mellanox.com>>; users <users@dpdk.org<mailto:users@dpdk.org>> Subject: Re: [dpdk-users] flow_filtering failed on mlx5 Thanks Ori! I'll test out the patch today. Just to make sure, by removing the vlan item, does that not allow vlan tags anymore, or is it just ignoring one if present? On Mon, Nov 5, 2018, 05:18 Ori Kam <or...@mellanox.com<mailto:or...@mellanox.com> wrote: Hi Cliff, There was an issue I solved it, and submitted relevant patches. You can look at them: http://patches.dpdk.org/patch/47806/<https://emea01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fpatches.dpdk.org%2Fpatch%2F47806%2F&data=02%7C01%7Corika%40mellanox.com%7C1d291f628ee8481870d708d64385c999%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C636770639223171986&sdata=JazsU0jMRyOn3TzJ7xSMLJauwKEKseqBv%2FNjEuUlKR8%3D&reserved=0> http://patches.dpdk.org/patch/47807/<https://emea01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fpatches.dpdk.org%2Fpatch%2F47807%2F&data=02%7C01%7Corika%40mellanox.com%7C1d291f628ee8481870d708d64385c999%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C636770639223171986&sdata=obluFDHN0HU5sbKO6Hbq9QovrCbFg0h%2FmdBH7pRnoXg%3D&reserved=0> Best, Ori > -----Original Message----- > From: Shahaf Shuler > Sent: Monday, November 5, 2018 9:10 AM > To: Cliff Burdick <shakl...@gmail.com<mailto:shakl...@gmail.com>>; users > <users@dpdk.org<mailto:users@dpdk.org>>; Ori Kam > <or...@mellanox.com<mailto:or...@mellanox.com>> > Subject: RE: [dpdk-users] flow_filtering failed on mlx5 > > +Ori the maintainer of the example code. > > Saturday, November 3, 2018 5:31 AM, Cliff Burdick: > > Subject: [dpdk-users] flow_filtering failed on mlx5 > > > > Hi I'm trying to run the flow_filtering example on a connectx-5, and it > > seems > > to fail with dpdk 18.08: > > > > $ sudo ./build/flow -l 1 -n 1 > > EAL: Detected 48 lcore(s) > > EAL: Detected 2 NUMA nodes > > EAL: Multi-process socket /var/run/dpdk/rte/mp_socket > > EAL: Probing VFIO support... > > EAL: PCI device 0000:01:00.0 on NUMA socket 0 > > EAL: probe driver: 15b3:1013 net_mlx5 > > EAL: PCI device 0000:01:00.1 on NUMA socket 0 > > EAL: probe driver: 15b3:1013 net_mlx5 > > EAL: PCI device 0000:81:00.0 on NUMA socket 1 > > EAL: probe driver: 8086:1528 net_ixgbe > > EAL: PCI device 0000:81:00.1 on NUMA socket 1 > > EAL: probe driver: 8086:1528 net_ixgbe > > EAL: PCI device 0000:82:00.0 on NUMA socket 1 > > EAL: probe driver: 15b3:1013 net_mlx5 > > EAL: PCI device 0000:82:00.1 on NUMA socket 1 > > EAL: probe driver: 15b3:1013 net_mlx5 > > :: warn: 5 ports detected, but we use only one: port 0 > > :: initializing port: 0 > > Ethdev port_id=0 requested Tx offloads 0x3f doesn't match Tx offloads > > capabilities 0xc86af in rte_eth_dev_configure() > > EAL: Error - exiting with code: 1 > > Cause: :: cannot configure device: err=-22, port=0 > > > > > > Has anyone got this to work?
