[ovs-dev] [PATCH] fix match issue for decap when the remote_ip=flow in userspace implementation

2015-08-13 Thread Mengke
From: mengke In the test the bridge is configured with type "netdev" and the VXLAN port is configured with "options: remote_ip=flow options: key=flow", the VXLAN packets can't be matched for the rule (ovs-ofctl add-flow br-int "priority=200,in_port=2,tun_src=

[ovs-dev] [PATCH 3/7] vxlan-gpe-nsh: tun_nodecap mode in DPDk-netdev dataplane.

2015-09-30 Thread mengke
: Ricky Li Signed-off-by: Mengke Liu --- datapath/linux/compat/include/linux/openvswitch.h | 23 + lib/dpif-netdev.c | 36 +++ lib/dpif.c| 1 + lib/netdev-bsd.c | 1 + lib/netdev

[ovs-dev] [PATCH 2/7] vxlan-gpe-nsh: decap and encap in DPDK-netdev dataplane and control plane.

2015-09-30 Thread mengke
re appended and implemented at data plane level. Finally packets will be reprocessed by function 'dp_netdev_input'. Signed-off-by: Ricky Li Signed-off-by: Mengke Liu --- lib/netdev-vport.c | 166 +++- lib/odp-util.c | 175

[ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-09-30 Thread mengke
eader to build the packet with Ethernet+NSH format. For the vport with the feature of conversion from Ethernet+NSH to VxLAN-GPE+NSH, the packets are processed inversely. Ricky Li, Mengke Liu, Pritesh Kothari(7): vxlan-gpe-nsh: decap and encap in kernel dataplane and control plane. vxlan-gp

[ovs-dev] [PATCH 5/7] Ethernet-nsh: decap and encap in DPDK-netdev dataplane.

2015-09-30 Thread mengke
if the Ethernet NSH port are found, the decapsulation will be implemented. The tunnel pop actions will be implemented and the related fields will be parsed. Signed-off-by: Ricky Li Signed-off-by: Mengke Liu --- datapath/linux/compat/include/linux/openvswitch.h | 2 +

[ovs-dev] [PATCH 4/7] vxlan-gpe-nsh: convert vxlan-gpe nsh to ethernet nsh in DPDK-netdev dataplane.

2015-09-30 Thread mengke
vport will remove Outer MAC header, Outer IP header, UDP header, VxLAN-GPE header, and then modify and push the outer MAC header. Then the packet with VxLAN-GPE+NSH format is converted to Outer MAC header + NSH header + original packet. Signed-off-by: Ricky Li Signed-off-by: Mengke Liu

[ovs-dev] [PATCH 7/7] Ethernet-nsh: convert eth nsh to vxlan-gpe nsh in DPDK-netdev dataplane.

2015-09-30 Thread mengke
push the outer MAC header + Outer IP header + UDP header + VxLAN-GPE. Then the packet with Ethernet+NSH format is converted to VxLAN-GPE NSH packet. Signed-off-by: Ricky Li Signed-off-by: Mengke Liu --- datapath/linux/compat/include/linux/openvswitch.h | 3 +- lib/netdev-vport.c

[ovs-dev] [PATCH 6/7] Ethernet-nsh: tun_nodecap mode in DPDK-netdev dataplane.

2015-09-30 Thread mengke
: Ricky Li Signed-off-by: Mengke Liu --- lib/netdev-vport.c | 43 ++- lib/odp-util.c | 3 ++- lib/packets.c | 10 +- tests/tunnel.at| 21 + 4 files changed, 74 insertions(+), 3 deletions(-) diff --git a/lib/netdev

Re: [ovs-dev] [PATCH] fix match issue for decap when the remote_ip=flow in userspace implementation

2015-08-13 Thread Liu, Mengke
OK , Thanks. -Original Message- From: Jesse Gross [mailto:je...@nicira.com] Sent: Friday, August 14, 2015 9:17 AM To: Liu, Mengke Cc: dev@openvswitch.org Subject: Re: [ovs-dev] [PATCH] fix match issue for decap when the remote_ip=flow in userspace implementation On Thu, Aug 13, 2015 at

Re: [ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-10-14 Thread Liu, Mengke
NSH header is already an independent protocol layer but not belong to the tunnel layer. 2) Define a new “nsh_metadata” fields for NSH variable context header. Which one do you prefer? Please tell us for you inputs on our modification plan. Best Regards Mengke -Original Message- F

Re: [ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-10-25 Thread Liu, Mengke
format as Geneve, so in theory they could be shared (and it would be nice to > avoid duplicating these). The main thing that concerns me about this is the > possibility that the protocols will diverge in the future or some other > protocol > that does not have the same format will want t

Re: [ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-11-02 Thread Liu, Mengke
d-geneve-map” to “add-tlv-map”. An example in our initial design for NSH MD-type 2 support: ovs-ofctl add-tlv-map br0 {class=0x,type=0,len=4}->tun_metadata0 ovs-ofctl add-flow br0 in_port=LOCAL, actions=push_nsh, set_field:221->nsp, set_field:3->nsi, set_field:2->nsh_md_type,set_field:111->tun_metadata0, 1 What do you think about this proposal for NSH TLV support? -Mengke ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-12-10 Thread Liu, Mengke
> -Original Message- > From: jgr...@nicira.com [mailto:jgr...@nicira.com] On Behalf Of Jesse > Gross > Sent: Tuesday, December 8, 2015 12:32 AM > To: Liu, Mengke > Cc: dev@openvswitch.org; Pritesh Kothari (pritkoth) ; > Zhou, Danny ; Li, Ricky ; > pa...@cisco.com

[ovs-dev] [CudaMailTagged] [PATCH] geneve-map-rename: rename geneve-map to tlv-map.

2015-12-14 Thread Mengke Liu
eader(the same TLV format as Geneve) or other protocol can reuse the field tun_metadata in the future. Signed-off-by: Mengke Liu Signed-off-by: Ricky Li --- include/openflow/nicira-ext.h | 44 +- lib/dpif-netdev.c | 2 +- lib/geneve.h | 4

Re: [ovs-dev] [PATCH 0/7] Enable NSH based Service Function Chaining support in OVS

2015-12-14 Thread Liu, Mengke
> -Original Message- > From: Jesse Gross [mailto:je...@kernel.org] > Sent: Saturday, December 12, 2015 1:41 AM > To: Liu, Mengke > Cc: dev@openvswitch.org; Pritesh Kothari (pritkoth) ; > Zhou, Danny ; Li, Ricky ; > pa...@cisco.com > Subject: Re: [ovs-dev] [PAT

[ovs-dev] [PATCH v2] geneve-map-rename: rename geneve-map to tlv-map.

2015-12-15 Thread Mengke Liu
ader (the same TLV format as Geneve) or other protocol can reuse the field tun_metadata in the future. Some notes in patch v2: 1) The names for various commands and error codes are modified to stand for TLV. 2) Add a little more detailed description for option TLV. Signed-off-by: Mengke Liu Sign