Re: [ovs-dev] [PATCH ovn] MAINTAINERS: Move myself to emeritus status

On Mon, Feb 20, 2023 at 4:41 PM Russell Bryant wrote: > > From: Russell Bryant > > I have not been involved in OVN development long enough that I should > transition to emeritus status. > > Signed-off-by: Russell Bryant Thanks for all the contributions. I applied this patch to the main

Re: [ovs-dev] [PATCH ovn 3/3] northd: Use dynamic mac-binding for virtual port IPs.

On Wed, Feb 22, 2023 at 10:35 PM Han Zhou wrote: > > Today ARP resolve flows (static mac-bindings) are programmed for virtual > ports once their virtual parent is claimed. As a result, during virtual > parent failover, the traffic won't switch to the new parent until the > ARP resolve flow is

Re: [ovs-dev] Deadlock happen when delete vhostuserclient port while qemu destroy virtio

>On 2/23/23 10:35, Han Ding wrote: >> >> When use ovs-vsctl to delete vhostuserclient port while qemu destroy virtio, >> there is a deadlock between OVS main thread and the vhost-events thread. >> >> openvswitch is 2.14 and dpdk is 20.11 > >FWIW, 2.14 supposed to be used with 19.11. Thanks

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

> -Original Message- > From: Aaron Conole mailto:acon...@redhat.com>> > Date: Wednesday 22 February 2023 at 18:11 > To: "d...@openvswitch.org " > mailto:d...@openvswitch.org>> > Cc: Eli Britstein mailto:el...@nvidia.com>>, Gaetan Rivet >

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

> -Original Message- > From: Robin Jarry mailto:rja...@redhat.com>> > Date: Thursday 23 February 2023 at 22:43 > To: Gaetan Rivet mailto:gaet...@nvidia.com>>, Aaron > Conole mailto:acon...@redhat.com>> > Cc: "d...@openvswitch.org " >

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

Salut Gaëtan, Gaetan Rivet, Feb 23, 2023 at 22:33: > I've looked at your patch Robin and the offloads you insert in > dpdk_cp_prot_add_flow use the following: > > const struct rte_flow_attr attr = { .ingress = 1 }; > > implicitly setting transfer and group to 0. If either of those had > been

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

> -Original Message- > From: Robin Jarry mailto:rja...@redhat.com>> > Date: Thursday 23 February 2023 at 22:14 > To: Aaron Conole mailto:acon...@redhat.com>> > Cc: "d...@openvswitch.org " > mailto:d...@openvswitch.org>>, Eli Britstein >

Re: [ovs-dev] [PATCH v22 5/8] netdev-offload: Add netdev offload recv and recv_wait APIs

On 2/23/23 21:19, Ilya Maximets wrote: > On 2/23/23 12:27, Chris Mi wrote: >> Iterate each registered offload API. It's not a problem for today >> since we only have one implementation. >> >> Signed-off-by: Chris Mi >> Reviewed-by: Roi Dayan >> --- >> lib/netdev-offload.c | 32

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

Aaron Conole, Feb 23, 2023 at 22:09: > Thanks for taking a look. You're saying that you tested without this > patch applied, yes? That could be. I only know of one hardware which > requires CAP_SYS_RAWIO for rte_flow to function. Yes that is correct, I tested *without* this patch applied and

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

"Robin Jarry" writes: > Aaron Conole, Feb 22, 2023 at 18:07: >> Open vSwitch generally tries to let the underlying operating system >> managed the low level details of hardware, for example DMA mapping, >> bus arbitration, etc. However, when using DPDK, the underlying >> operating system yields

Re: [ovs-dev] [PATCH v22 7/8] netdev-offload-tc: Add offload support for sFlow

On 2/23/23 12:27, Chris Mi wrote: > Create a unique group ID to map the sFlow info when offloading sample > action to TC. When showing the offloaded datapath flows, translate the > group ID from TC sample action to sFlow info using the mapping. > > Signed-off-by: Chris Mi > Reviewed-by: Roi

Re: [ovs-dev] [PATCH v22 5/8] netdev-offload: Add netdev offload recv and recv_wait APIs

On 2/23/23 12:27, Chris Mi wrote: > Iterate each registered offload API. It's not a problem for today > since we only have one implementation. > > Signed-off-by: Chris Mi > Reviewed-by: Roi Dayan > --- > lib/netdev-offload.c | 32 > lib/netdev-offload.h | 4

Re: [ovs-dev] [PATCH v22 4/8] netdev-offload-tc: Add sFlow offload API for TC

On 2/23/23 12:26, Chris Mi wrote: > Initialize psample socket. Add sFlow recv API to receive sampled > packets from psample socket. Add sFow recv wait API to add psample > socket fd to poll list. > > Signed-off-by: Chris Mi > Reviewed-by: Roi Dayan > --- > lib/dpif.h| 7

Re: [ovs-dev] [PATCH v22 3/8] netdev-offload-tc: Introduce group ID management API

On 2/23/23 12:26, Chris Mi wrote: > When offloading sample action to TC, userspace creates a unique ID > to map sFlow action and tunnel info and passes this ID to kernel > instead of the sFlow info. Psample will send this ID and sampled > packet to userspace. Using the ID, userspace can recover

Re: [ovs-dev] [PATCH v9] netdev-dpdk: add control plane protection support

For the record, I have tested this feature as a non-privileged user: ovs-ctl --ovs-user="openvswitch:hugetlbfs" start With the proper UDEV rules for vfio based devices, I have successfully configured cp-protection=lacp on i40e (Intel X710 NICs) and mlx5 (ConnectX-5 Ex NICs) drivers.

Re: [ovs-dev] [RFC] dpdk: Allow retaining cap_sys_rawio privileges

Aaron Conole, Feb 22, 2023 at 18:07: > Open vSwitch generally tries to let the underlying operating system > managed the low level details of hardware, for example DMA mapping, > bus arbitration, etc. However, when using DPDK, the underlying > operating system yields control of many of these

[ovs-dev] [PATCH] ofproto: Fix re-creation of tunnel backing interfaces on restart.

Tunnel OpenFlow ports do not exist in the datapath, instead there is a tunnel backing interface that serves all the tunnels of the same type. For example, if the geneve port 'my_tunnel' is added to OVS, it will create 'geneve_sys_6041' datapath port, if it doesn't already exist, and use this port

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On Thu, Feb 23, 2023 at 03:19:37PM +0100, Ilya Maximets wrote: > On 2/23/23 14:02, Simon Horman wrote: ... > > +exit 77 > > +fi > > +]) > > +AT_CHECK([ > > +if ! tc filter add dev veth0 parent : \ > > 'dnl' is prefered for the line break. autotest

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On Thu, Feb 23, 2023 at 04:36:25PM +0100, Ilya Maximets wrote: > On 2/23/23 16:33, Simon Horman wrote: > > On Thu, Feb 23, 2023 at 04:09:10PM +0100, Ilya Maximets wrote: > >> On 2/23/23 15:19, Ilya Maximets wrote: > >>> On 2/23/23 14:02, Simon Horman wrote: > > > > ... > > > +AT_CHECK([

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On 2/23/23 16:33, Simon Horman wrote: > On Thu, Feb 23, 2023 at 04:09:10PM +0100, Ilya Maximets wrote: >> On 2/23/23 15:19, Ilya Maximets wrote: >>> On 2/23/23 14:02, Simon Horman wrote: > > ... > +AT_CHECK([ +if ! tc qdisc add dev veth0 handle : ingress; then +

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On Thu, Feb 23, 2023 at 04:09:10PM +0100, Ilya Maximets wrote: > On 2/23/23 15:19, Ilya Maximets wrote: > > On 2/23/23 14:02, Simon Horman wrote: ... > >> +AT_CHECK([ > >> +if ! tc qdisc add dev veth0 handle : ingress; then > >> +ip link del veth0 > > > > Instead of

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On Thu, Feb 23, 2023 at 03:19:37PM +0100, Ilya Maximets wrote: > On 2/23/23 14:02, Simon Horman wrote: > > Move check for tc ingress pps support to from aclocal to test script > > > > This has several problems: > > > > 1. Stderror from failing commands is output when executing > >various

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On 2/23/23 15:19, Ilya Maximets wrote: > On 2/23/23 14:02, Simon Horman wrote: >> Move check for tc ingress pps support to from aclocal to test script >> >> This has several problems: >> >> 1. Stderror from failing commands is output when executing >>various make targets. >> >> 2. There are

Re: [ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

On 2/23/23 14:02, Simon Horman wrote: > Move check for tc ingress pps support to from aclocal to test script > > This has several problems: > > 1. Stderror from failing commands is output when executing >various make targets. > > 2. There are various failure conditions that lead >to

Re: [ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: Use on stack sw_flow_key in ovs_packet_cmd_execute

Sure, will redo the post when window open Have a great day eddy From: Paolo Abeni Sent: Thursday, February 23, 2023 12:41 To: Eddy Tao; net...@vger.kernel.org Cc: Pravin B Shelar; David S. Miller; Eric Dumazet; Jakub Kicinski; d...@openvswitch.org;

Re: [ovs-dev] Deadlock happen when delete vhostuserclient port while qemu destroy virtio

On 2/23/23 10:35, Han Ding wrote: > > When use ovs-vsctl to delete vhostuserclient port while qemu destroy virtio, > there is a deadlock between OVS main thread and the vhost-events thread. > > openvswitch is 2.14 and dpdk is 20.11 FWIW, 2.14 supposed to be used with 19.11. > > Main thread: >

Re: [ovs-dev] [PATCH v21 0/8] Add offload support for sFlow

On 2/23/23 14:12, Chris Mi wrote: > On 2/23/2023 9:04 PM, Ilya Maximets wrote: >> On 2/23/23 12:24, Chris Mi wrote: >>> Hi Ilya, >>> >>> Sorry for late response. Please see my comments in-line. >>> >>> On 1/17/2023 11:00 PM, Ilya Maximets wrote: On 3/17/22 02:12, Chris Mi wrote: > This

Re: [ovs-dev] [PATCH v22 6/8] dpif-netlink: Add netdev offload recv in normal recv upcalls

On 2/23/23 12:27, Chris Mi wrote: > In thread handler 0, add netdev offload recv in normal recv upcalls. > To avoid starvation, introduce a flag to alternate the order of > receiving normal upcalls and offload upcalls based on that flag. > > Add similar change for recv_wait. > > Signed-off-by:

Re: [ovs-dev] [PATCH v21 0/8] Add offload support for sFlow

On 2/23/2023 9:04 PM, Ilya Maximets wrote: On 2/23/23 12:24, Chris Mi wrote: Hi Ilya, Sorry for late response. Please see my comments in-line. On 1/17/2023 11:00 PM, Ilya Maximets wrote: On 3/17/22 02:12, Chris Mi wrote: This patch set adds offload support for sFlow. Psample is a genetlink

Re: [ovs-dev] [PATCH v21 0/8] Add offload support for sFlow

On 2/23/23 12:24, Chris Mi wrote: > Hi Ilya, > > Sorry for late response. Please see my comments in-line. > > On 1/17/2023 11:00 PM, Ilya Maximets wrote: >> On 3/17/22 02:12, Chris Mi wrote: >>> This patch set adds offload support for sFlow. >>> >>> Psample is a genetlink channel for packet

[ovs-dev] [PATCH] test: move check for tc ingress pps support to test script

Move check for tc ingress pps support to from aclocal to test script This has several problems: 1. Stderror from failing commands is output when executing various make targets. 2. There are various failure conditions that lead to veth0 and veth1 being created by not cleaned up. 3. The

Re: [ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: Use on stack sw_flow_key in ovs_packet_cmd_execute

On Thu, 2023-02-23 at 20:24 +0800, Eddy Tao wrote: > Sorry, there is a typo in the mail, i will resend shortly, please, don't do that. # Form letter - net-next is closed The merge window for v6.3 has begun and therefore net-next is closed for new drivers, features, code refactoring and

Re: [ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: Use on stack sw_flow_key in ovs_packet_cmd_execute

On Thu, Feb 23, 2023 at 08:24:50PM +0800, Eddy Tao wrote: > Sorry, there is a typo in the mail, i will resend shortly, please ignore it > for now net-next is now closed. You'll need to repost this patch after v6.3-rc1 has been tagged. Or post it as an RFC. Ref:

[ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: ovs_packet_cmd_execute put sw_flow mainbody in stack

Use on stack sw_flow_key in ovs_packet_cmd_execute Reason: As key function in slow-path, ovs_packet_cmd_execute allocate transient memory for sw_flow and frees it at the end of function. The procedure is not efficient in 2 aspects 1. actuall sw_flow_key is what the

Re: [ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: Use on stack sw_flow_key in ovs_packet_cmd_execute

Sorry, there is a typo in the mail, i will resend shortly, please ignore it for now On 2023/2/23 20:21, Eddy Tao wrote: Use on stack sw_flow_key in ovs_packet_cmd_execute Reason: As key function in slow-path, ovs_packet_cmd_execute and ovs_flow_cmd_new allocate transient memory for

[ovs-dev] [PATCH net-next v2 1/1] net: openvswitch: Use on stack sw_flow_key in ovs_packet_cmd_execute

Use on stack sw_flow_key in ovs_packet_cmd_execute Reason: As key function in slow-path, ovs_packet_cmd_execute and ovs_flow_cmd_new allocate transient memory for sw_flow and frees it at the end of function. The procedure is not efficient in 2 aspects 1. actuall

[ovs-dev] [PATCH v22 7/8] netdev-offload-tc: Add offload support for sFlow

Create a unique group ID to map the sFlow info when offloading sample action to TC. When showing the offloaded datapath flows, translate the group ID from TC sample action to sFlow info using the mapping. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan --- lib/netdev-offload-tc.c | 244

[ovs-dev] [PATCH v22 6/8] dpif-netlink: Add netdev offload recv in normal recv upcalls

In thread handler 0, add netdev offload recv in normal recv upcalls. To avoid starvation, introduce a flag to alternate the order of receiving normal upcalls and offload upcalls based on that flag. Add similar change for recv_wait. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan ---

[ovs-dev] [PATCH v22 8/8] system-offloads-traffic.at: Add sFlow offload test cases

Add two sFlow offload test caes: 3: sflow offloads with sampling=1 - ping between two ports - offloads enabled ok 4: sflow offloads with sampling=2 - ping between two ports - offloads enabled ok Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Acked-by: Eelco Chaudron ---

[ovs-dev] [PATCH v22 5/8] netdev-offload: Add netdev offload recv and recv_wait APIs

Iterate each registered offload API. It's not a problem for today since we only have one implementation. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan --- lib/netdev-offload.c | 32 lib/netdev-offload.h | 4 2 files changed, 36 insertions(+) diff --git

[ovs-dev] [PATCH v22 4/8] netdev-offload-tc: Add sFlow offload API for TC

Initialize psample socket. Add sFlow recv API to receive sampled packets from psample socket. Add sFow recv wait API to add psample socket fd to poll list. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan --- lib/dpif.h| 7 ++ lib/netdev-offload-provider.h | 11 ++

[ovs-dev] [PATCH v22 3/8] netdev-offload-tc: Introduce group ID management API

When offloading sample action to TC, userspace creates a unique ID to map sFlow action and tunnel info and passes this ID to kernel instead of the sFlow info. Psample will send this ID and sampled packet to userspace. Using the ID, userspace can recover the sFlow info and send sampled packet to

[ovs-dev] [PATCH v22 0/8] Add offload support for sFlow

v2-v1: - Fix robot errors. v3-v2: - Remove Gerrit Change-Id. - Add patch #9 to fix older kernels build issue. - Add travis test result. v4-v3: - Fix offload issue when sampling rate is 1. v5-v4: - Move polling thread from ofproto to netdev-offload-tc. v6-v5: - Rebase. - Add GitHub Actions test

[ovs-dev] [PATCH v22 1/8] compat: Add psample and tc sample action defines for older kernels

Update kernel UAPI to support psample and the tc sample action. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Acked-by: Eelco Chaudron --- include/linux/automake.mk| 4 ++- include/linux/psample.h | 62 include/linux/tc_act/tc_sample.h | 25

[ovs-dev] [PATCH v22 2/8] ovs-kmod-ctl: Load kernel module psample

Load kernel module psample to receive sampled packets from TC. Before removing kernel module psample, remove act_sample first. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Acked-by: Eelco Chaudron --- utilities/ovs-kmod-ctl.in | 14 ++ 1 file changed, 14 insertions(+) diff

Re: [ovs-dev] [PATCH v21 0/8] Add offload support for sFlow

Hi Ilya, Sorry for late response. Please see my comments in-line. On 1/17/2023 11:00 PM, Ilya Maximets wrote: On 3/17/22 02:12, Chris Mi wrote: This patch set adds offload support for sFlow. Psample is a genetlink channel for packet sampling. TC action act_sample uses psample to send sampled

Re: [ovs-dev] [PATCH ovn 0/2] fix IP fragmented traffic hitting LB

On Feb 23, Ales Musil wrote: > On Wed, Feb 22, 2023 at 4:58 PM Lorenzo Bianconi < > lorenzo.bianc...@redhat.com> wrote: > > > Lorenzo Bianconi (2): > > northd: move defrag router pipeline stage forward > > northd: add flows to defrag IP traffic > > > > northd/northd.c | 50 ++-- > >

Re: [ovs-dev] [PATCH ovn 0/2] fix IP fragmented traffic hitting LB

On Thu, Feb 23, 2023 at 7:29 AM Ales Musil wrote: > > > On Wed, Feb 22, 2023 at 4:58 PM Lorenzo Bianconi < > lorenzo.bianc...@redhat.com> wrote: > >> Lorenzo Bianconi (2): >> northd: move defrag router pipeline stage forward >> northd: add flows to defrag IP traffic >> >> northd/northd.c

[ovs-dev] Deadlock happen when delete vhostuserclient port while qemu destroy virtio

When use ovs-vsctl to delete vhostuserclient port while qemu destroy virtio, there is a deadlock between OVS main thread and the vhost-events thread. openvswitch is 2.14 and dpdk is 20.11 Main thread: ofport_remove -> netdev_unref -> netdev_dpdk_vhost_destruct ->

Re: [ovs-dev] [PATCH v6] netdev-offload-tc: del ufid mapping if device not exist

On Thu, Feb 23, 2023 at 10:24:54AM +0800, Faicker Mo wrote: > I can run the fail-test more easier. > There exists a flow in verbose log like this, > recirc_id(0),in_port(2),eth(src=aa:1a:54:e9:c5:56,dst=86:29:2a:05:94:90),eth_type(0x0800),ipv4(frag=no), > packets:1, bytes:84, used:12.240s,