| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250919213153.103606-15-daniel@iogearbox.net>
Date: Fri, 19 Sep 2025 23:31:47 +0200
From: Daniel Borkmann <daniel@...earbox.net>
To: netdev@...r.kernel.org
Cc: bpf@...r.kernel.org,
kuba@...nel.org,
davem@...emloft.net,
razor@...ckwall.org,
pabeni@...hat.com,
willemb@...gle.com,
sdf@...ichev.me,
john.fastabend@...il.com,
martin.lau@...nel.org,
jordan@...fe.io,
maciej.fijalkowski@...el.com,
magnus.karlsson@...el.com,
David Wei <dw@...idwei.uk>
Subject: [PATCH net-next 14/20] netkit: Add single device mode for netkit
Add a single device mode for netkit instead of netkit pairs. The primary
target for the paired devices is to connect network namespaces, of course,
and support has been implemented in projects like Cilium [0]. For the rxq
binding the plan is to support two main scenarios related to single device
mode:
* For the use-case of io_uring zero-copy, the control plane can either
set up a netkit pair where the peer device can perform rxq binding which
is then tied to the lifetime of the peer device, or the control plane
can use a regular netkit pair to connect the hostns to a Pod/container
and dynamically add/remove rxq bindings through a single device without
having to interrupt the device pair. In the case of io_uring, the memory
pool is used as skb non-linear pages, and thus the skb will go its way
through the regular stack into netkit. Things like the netkit policy when
no BPF is attached or skb scrubbing etc apply as-is in case the paired
devices are used, or if the backend memory is tied to the single device
and traffic goes through a paired device.
* For the use-case of AF_XDP, the control plane needs to use netkit in the
single device mode. The single device mode currently enforces only a
pass policy when no BPF is attached, and does not yet support BPF link
attachments for AF_XDP. skbs sent to that device get dropped at the
moment. Given AF_XDP operates at a lower layer of the stack tying this
to the netkit pair did not make sense. In future, the plan is to allow
BPF at the XDP layer which can: i) process traffic coming from the AF_XDP
application (e.g. QEMU with AF_XDP backend) to filter egress traffic or
to push selected egress traffic up to the single netkit device to the
local stack (e.g. DHCP requests), and ii) vice-versa skbs sent to the
single netkit into the AF_XDP application (e.g. DHCP replies). Also,
the control-plane can dynamically add/remove rxq bindings for the single
netkit device without having to interrupt (e.g. down/up cycle) the main
netkit pair for the Pod which has traffic going in and out.
Signed-off-by: Daniel Borkmann <daniel@...earbox.net>
Co-developed-by: David Wei <dw@...idwei.uk>
Signed-off-by: David Wei <dw@...idwei.uk>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
---
drivers/net/netkit.c | 108 ++++++++++++++++++++++-------------
include/uapi/linux/if_link.h | 6 ++
2 files changed, 74 insertions(+), 40 deletions(-)
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 492be60f2e70..ceb1393ee599 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -25,6 +25,7 @@ struct netkit {
/* Needed in slow-path */
enum netkit_mode mode;
+ enum netkit_pairing pair;
bool primary;
u32 headroom;
};
@@ -133,6 +134,10 @@ static int netkit_open(struct net_device *dev)
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
+ if (nk->pair == NETKIT_DEVICE_SINGLE) {
+ netif_carrier_on(dev);
+ return 0;
+ }
if (!peer)
return -ENOTCONN;
if (peer->flags & IFF_UP) {
@@ -333,6 +338,7 @@ static int netkit_new_link(struct net_device *dev,
enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT;
enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT;
struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr;
+ enum netkit_pairing pair = NETKIT_DEVICE_PAIR;
enum netkit_action policy_prim = NETKIT_PASS;
enum netkit_action policy_peer = NETKIT_PASS;
struct nlattr **data = params->data;
@@ -341,7 +347,7 @@ static int netkit_new_link(struct net_device *dev,
struct nlattr **tb = params->tb;
u16 headroom = 0, tailroom = 0;
struct ifinfomsg *ifmp = NULL;
- struct net_device *peer;
+ struct net_device *peer = NULL;
char ifname[IFNAMSIZ];
struct netkit *nk;
int err;
@@ -378,6 +384,8 @@ static int netkit_new_link(struct net_device *dev,
headroom = nla_get_u16(data[IFLA_NETKIT_HEADROOM]);
if (data[IFLA_NETKIT_TAILROOM])
tailroom = nla_get_u16(data[IFLA_NETKIT_TAILROOM]);
+ if (data[IFLA_NETKIT_PAIRING])
+ pair = nla_get_u32(data[IFLA_NETKIT_PAIRING]);
}
if (ifmp && tbp[IFLA_IFNAME]) {
@@ -390,45 +398,49 @@ static int netkit_new_link(struct net_device *dev,
if (mode != NETKIT_L2 &&
(tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS]))
return -EOPNOTSUPP;
+ if (pair != NETKIT_DEVICE_PAIR &&
+ (tb != tbp ||
+ tb[IFLA_NETKIT_PEER_POLICY] ||
+ tb[IFLA_NETKIT_PEER_SCRUB] ||
+ policy_prim != NETKIT_PASS))
+ return -EOPNOTSUPP;
- peer = rtnl_create_link(peer_net, ifname, ifname_assign_type,
- &netkit_link_ops, tbp, extack);
- if (IS_ERR(peer))
- return PTR_ERR(peer);
-
- netif_inherit_tso_max(peer, dev);
- if (headroom) {
- peer->needed_headroom = headroom;
- dev->needed_headroom = headroom;
- }
- if (tailroom) {
- peer->needed_tailroom = tailroom;
- dev->needed_tailroom = tailroom;
- }
-
- if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS]))
- eth_hw_addr_random(peer);
- if (ifmp && dev->ifindex)
- peer->ifindex = ifmp->ifi_index;
-
- nk = netkit_priv(peer);
- nk->primary = false;
- nk->policy = policy_peer;
- nk->scrub = scrub_peer;
- nk->mode = mode;
- nk->headroom = headroom;
- bpf_mprog_bundle_init(&nk->bundle);
+ if (pair == NETKIT_DEVICE_PAIR) {
+ peer = rtnl_create_link(peer_net, ifname, ifname_assign_type,
+ &netkit_link_ops, tbp, extack);
+ if (IS_ERR(peer))
+ return PTR_ERR(peer);
+
+ netif_inherit_tso_max(peer, dev);
+ if (headroom)
+ peer->needed_headroom = headroom;
+ if (tailroom)
+ peer->needed_tailroom = tailroom;
+ if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS]))
+ eth_hw_addr_random(peer);
+ if (ifmp && dev->ifindex)
+ peer->ifindex = ifmp->ifi_index;
- err = register_netdevice(peer);
- if (err < 0)
- goto err_register_peer;
- netif_carrier_off(peer);
- if (mode == NETKIT_L2)
- dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL);
+ nk = netkit_priv(peer);
+ nk->primary = false;
+ nk->policy = policy_peer;
+ nk->scrub = scrub_peer;
+ nk->mode = mode;
+ nk->pair = pair;
+ nk->headroom = headroom;
+ bpf_mprog_bundle_init(&nk->bundle);
+
+ err = register_netdevice(peer);
+ if (err < 0)
+ goto err_register_peer;
+ netif_carrier_off(peer);
+ if (mode == NETKIT_L2)
+ dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL);
- err = rtnl_configure_link(peer, NULL, 0, NULL);
- if (err < 0)
- goto err_configure_peer;
+ err = rtnl_configure_link(peer, NULL, 0, NULL);
+ if (err < 0)
+ goto err_configure_peer;
+ }
if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
@@ -436,12 +448,17 @@ static int netkit_new_link(struct net_device *dev,
nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
strscpy(dev->name, "nk%d", IFNAMSIZ);
+ if (headroom)
+ dev->needed_headroom = headroom;
+ if (tailroom)
+ dev->needed_tailroom = tailroom;
nk = netkit_priv(dev);
nk->primary = true;
nk->policy = policy_prim;
nk->scrub = scrub_prim;
nk->mode = mode;
+ nk->pair = pair;
nk->headroom = headroom;
bpf_mprog_bundle_init(&nk->bundle);
@@ -453,10 +470,12 @@ static int netkit_new_link(struct net_device *dev,
dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL);
rcu_assign_pointer(netkit_priv(dev)->peer, peer);
- rcu_assign_pointer(netkit_priv(peer)->peer, dev);
+ if (peer)
+ rcu_assign_pointer(netkit_priv(peer)->peer, dev);
return 0;
err_configure_peer:
- unregister_netdevice(peer);
+ if (peer)
+ unregister_netdevice(peer);
return err;
err_register_peer:
free_netdev(peer);
@@ -516,6 +535,8 @@ static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 whi
nk = netkit_priv(dev);
if (!nk->primary)
return ERR_PTR(-EACCES);
+ if (nk->pair == NETKIT_DEVICE_SINGLE)
+ return ERR_PTR(-EOPNOTSUPP);
if (which == BPF_NETKIT_PEER) {
dev = rcu_dereference_rtnl(nk->peer);
if (!dev)
@@ -877,6 +898,7 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
{ IFLA_NETKIT_PEER_INFO, "peer info" },
{ IFLA_NETKIT_HEADROOM, "headroom" },
{ IFLA_NETKIT_TAILROOM, "tailroom" },
+ { IFLA_NETKIT_PAIRING, "pairing" },
};
if (!nk->primary) {
@@ -896,9 +918,11 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
}
if (data[IFLA_NETKIT_POLICY]) {
+ err = -EOPNOTSUPP;
attr = data[IFLA_NETKIT_POLICY];
policy = nla_get_u32(attr);
- err = netkit_check_policy(policy, attr, extack);
+ if (nk->pair == NETKIT_DEVICE_PAIR)
+ err = netkit_check_policy(policy, attr, extack);
if (err)
return err;
WRITE_ONCE(nk->policy, policy);
@@ -929,6 +953,7 @@ static size_t netkit_get_size(const struct net_device *dev)
nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */
nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_HEADROOM */
nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_TAILROOM */
+ nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PAIRING */
0;
}
@@ -949,6 +974,8 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
return -EMSGSIZE;
if (nla_put_u16(skb, IFLA_NETKIT_TAILROOM, dev->needed_tailroom))
return -EMSGSIZE;
+ if (nla_put_u32(skb, IFLA_NETKIT_PAIRING, nk->pair))
+ return -EMSGSIZE;
if (peer) {
nk = netkit_priv(peer);
@@ -970,6 +997,7 @@ static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
[IFLA_NETKIT_TAILROOM] = { .type = NLA_U16 },
[IFLA_NETKIT_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
[IFLA_NETKIT_PEER_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
+ [IFLA_NETKIT_PAIRING] = NLA_POLICY_MAX(NLA_U32, NETKIT_DEVICE_SINGLE),
[IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT,
.reject_message = "Primary attribute is read-only" },
};
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 45f56c9f95d9..4a2f781f3cca 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1294,6 +1294,11 @@ enum netkit_mode {
NETKIT_L3,
};
+enum netkit_pairing {
+ NETKIT_DEVICE_PAIR,
+ NETKIT_DEVICE_SINGLE,
+};
+
/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
* the BPF program if attached. This also means the latter can
* consume the two fields if they were populated earlier.
@@ -1318,6 +1323,7 @@ enum {
IFLA_NETKIT_PEER_SCRUB,
IFLA_NETKIT_HEADROOM,
IFLA_NETKIT_TAILROOM,
+ IFLA_NETKIT_PAIRING,
__IFLA_NETKIT_MAX,
};
#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1)
--
2.43.0
Powered by blists - more mailing lists