kernel/linux.git/net/openvswitch/datapath.h, branch v6.12.80

Revert "openvswitch: switch to per-action label counting in conntrack"

2025-03-22T19:54:13+00:00

[ Upstream commit 1063ae07383c0ddc5bcce170260c143825846b03 ] Currently, ovs_ct_set_labels() is only called for confirmed conntrack entries (ct) within ovs_ct_commit(). However, if the conntrack entry does not have the labels_ext extension, attempting to allocate it in ovs_ct_get_conn_labels() for a confirmed entry triggers a warning in nf_ct_ext_add(): WARN_ON(nf_ct_is_confirmed(ct)); This happens when the conntrack entry is created externally before OVS increments net->ct.labels_used. The issue has become more likely since commit fcb1aa5163b1 ("openvswitch: switch to per-action label counting in conntrack"), which changed to use per-action label counting and increment net->ct.labels_used when a flow with ct action is added. Since there’s no straightforward way to fully resolve this issue at the moment, this reverts the commit to avoid breaking existing use cases. Fixes: fcb1aa5163b1 ("openvswitch: switch to per-action label counting in conntrack") Reported-by: Jianbo Liu Signed-off-by: Xin Long Acked-by: Aaron Conole Link: https://patch.msgid.link/1bdeb2f3a812bca016a225d3de714427b2cd4772.1741457143.git.lucien.xin@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin

openvswitch: switch to per-action label counting in conntrack

2024-08-16T02:05:19+00:00

Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action label counting"), we should also switch to per-action label counting in openvswitch conntrack, as Florian suggested. The difference is that nf_connlabels_get() is called unconditionally when creating an ct action in ovs_ct_copy_action(). As with these flows: table=0,ip,actions=ct(commit,table=1) table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2) it needs to make sure the label ext is created in the 1st flow before the ct is committed in ovs_ct_commit(). Otherwise, the warning in nf_ct_ext_add() when creating the label ext in the 2nd flow will be triggered: WARN_ON(nf_ct_is_confirmed(ct)); Signed-off-by: Xin Long Reviewed-by: Aaron Conole Acked-by: Florian Westphal Link: https://patch.msgid.link/6b9347d5c1a0b364e88d900b29a616c3f8e5b1ca.1723483073.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski

net: openvswitch: store sampling probability in cb.

2024-07-06T00:45:47+00:00

When a packet sample is observed, the sampling rate that was used is important to estimate the real frequency of such event. Store the probability of the parent sample action in the skb's cb area and use it in psample action to pass it down to psample module. Reviewed-by: Aaron Conole Acked-by: Eelco Chaudron Reviewed-by: Ilya Maximets Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-7-amorenoz@redhat.com Signed-off-by: Jakub Kicinski

net/sched: Enable tc skb ext allocation on chain miss only when needed

2022-02-05T10:12:53+00:00

Currently tc skb extension is used to send miss info from tc to ovs datapath module, and driver to tc. For the tc to ovs miss it is currently always allocated even if it will not be used by ovs datapath (as it depends on a requested feature). Export the static key which is used by openvswitch module to guard this code path as well, so it will be skipped if ovs datapath doesn't need it. Enable this code path once ovs datapath needs it. Signed-off-by: Paul Blakey Reviewed-by: Jamal Hadi Salim Signed-off-by: David S. Miller

openvswitch: Introduce per-cpu upcall dispatch

2021-07-16T18:06:33+00:00

The Open vSwitch kernel module uses the upcall mechanism to send packets from kernel space to user space when it misses in the kernel space flow table. The upcall sends packets via a Netlink socket. Currently, a Netlink socket is created for every vport. In this way, there is a 1:1 mapping between a vport and a Netlink socket. When a packet is received by a vport, if it needs to be sent to user space, it is sent via the corresponding Netlink socket. This mechanism, with various iterations of the corresponding user space code, has seen some limitations and issues: * On systems with a large number of vports, there is a correspondingly large number of Netlink sockets which can limit scaling. (https://bugzilla.redhat.com/show_bug.cgi?id=1526306) * Packet reordering on upcalls. (https://bugzilla.redhat.com/show_bug.cgi?id=1844576) * A thundering herd issue. (https://bugzilla.redhat.com/show_bug.cgi?id=1834444) This patch introduces an alternative, feature-negotiated, upcall mode using a per-cpu dispatch rather than a per-vport dispatch. In this mode, the Netlink socket to be used for the upcall is selected based on the CPU of the thread that is executing the upcall. In this way, it resolves the issues above as: a) The number of Netlink sockets scales with the number of CPUs rather than the number of vports. b) Ordering per-flow is maintained as packets are distributed to CPUs based on mechanisms such as RSS and flows are distributed to a single user space thread. c) Packets from a flow can only wake up one user space thread. The corresponding user space code can be found at: https://mail.openvswitch.org/pipermail/ovs-dev/2021-July/385139.html Bugzilla: https://bugzilla.redhat.com/1844576 Signed-off-by: Mark Gray Acked-by: Flavio Leitner Acked-by: Pravin B Shelar Signed-off-by: David S. Miller

net: openvswitch: add masks cache hit counter

2020-08-03T22:17:48+00:00

Add a counter that counts the number of masks cache hits, and export it through the megaflow netlink statistics. Reviewed-by: Paolo Abeni Reviewed-by: Tonghao Zhang Signed-off-by: Eelco Chaudron Signed-off-by: David S. Miller

net: openvswitch: fixes potential deadlock in dp cleanup code

2020-07-24T23:58:38+00:00

The previous patch introduced a deadlock, this patch fixes it by making sure the work is canceled without holding the global ovs lock. This is done by moving the reorder processing one layer up to the netns level. Fixes: eac87c413bf9 ("net: openvswitch: reorder masks array based on usage") Reported-by: syzbot+2c4ff3614695f75ce26c@syzkaller.appspotmail.com Reported-by: syzbot+bad6507e5db05017b008@syzkaller.appspotmail.com Reviewed-by: Paolo Signed-off-by: Eelco Chaudron Signed-off-by: David S. Miller

net: openvswitch: reorder masks array based on usage

2020-07-17T17:36:50+00:00

This patch reorders the masks array every 4 seconds based on their usage count. This greatly reduces the masks per packet hit, and hence the overall performance. Especially in the OVS/OVN case for OpenShift. Here are some results from the OVS/OVN OpenShift test, which use 8 pods, each pod having 512 uperf connections, each connection sends a 64-byte request and gets a 1024-byte response (TCP). All uperf clients are on 1 worker node while all uperf servers are on the other worker node. Kernel without this patch : 7.71 Gbps Kernel with this patch applied: 14.52 Gbps We also run some tests to verify the rebalance activity does not lower the flow insertion rate, which does not. Signed-off-by: Eelco Chaudron Tested-by: Andrew Theurer Reviewed-by: Paolo Abeni Signed-off-by: David S. Miller

net: openvswitch: expand the meters supported number

2020-04-24T01:26:11+00:00

In kernel datapath of Open vSwitch, there are only 1024 buckets of meter in one datapath. If installing more than 1024 (e.g. 8192) meters, it may lead to the performance drop. But in some case, for example, Open vSwitch used as edge gateway, there should be 20K at least, where meters used for IP address bandwidth limitation. [Open vSwitch userspace datapath has this issue too.] For more scalable meter, this patch use meter array instead of hash tables, and expand/shrink the array when necessary. So we can install more meters than before in the datapath. Introducing the struct *dp_meter_instance, it's easy to expand meter though changing the *ti point in the struct *dp_meter_table. Cc: Pravin B Shelar Cc: Andy Zhou Signed-off-by: Tonghao Zhang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller

net: openvswitch: add hash info to upcall

2019-11-15T01:29:46+00:00

When using the kernel datapath, the upcall don't include skb hash info relatived. That will introduce some problem, because the hash of skb is important in kernel stack. For example, VXLAN module uses it to select UDP src port. The tx queue selection may also use the hash in stack. Hash is computed in different ways. Hash is random for a TCP socket, and hash may be computed in hardware, or software stack. Recalculation hash is not easy. Hash of TCP socket is computed: tcp_v4_connect -> sk_set_txhash (is random) __tcp_transmit_skb -> skb_set_hash_from_sk There will be one upcall, without information of skb hash, to ovs-vswitchd, for the first packet of a TCP session. The rest packets will be processed in Open vSwitch modules, hash kept. If this tcp session is forward to VXLAN module, then the UDP src port of first tcp packet is different from rest packets. TCP packets may come from the host or dockers, to Open vSwitch. To fix it, we store the hash info to upcall, and restore hash when packets sent back. +---------------+ +-------------------------+ | Docker/VMs | | ovs-vswitchd | +----+----------+ +-+--------------------+--+ | ^ | | | | | | upcall v restore packet hash (not recalculate) | +-+--------------------+--+ | tap netdev | | vxlan module +---------------> +--> Open vSwitch ko +--> or internal type | | +-------------------------+ Reported-at: https://mail.openvswitch.org/pipermail/ovs-dev/2019-October/364062.html Signed-off-by: Tonghao Zhang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller