netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:18 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add xsk support for af_xdp applications
Enable support for AF_XDP applications to operate on a netkit device.
The goal is that AF_XDP applications can natively consume AF_XDP
from network namespaces. The use-case from Cilium side is to support
Kubernetes KubeVirt VMs through QEMU's AF_XDP backend. KubeVirt is a
virtual machine management add-on for Kubernetes which aims to provide
a common ground for virtualization. KubeVirt spawns the VMs inside
Kubernetes Pods which reside in their own network namespace just like
regular Pods.
Raw QEMU AF_XDP backend example with eth0 being a physical device with
16 queues where netkit is bound to the last queue (for multi-queue RSS
context can be used if supported by the driver):
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type ether \
src 00:00:00:00:00:00 \
src-mask ff:ff:ff:ff:ff:ff \
dst $mac dst-mask 00:00:00:00:00:00 \
proto 0 proto-mask 0xffff action 15
[ ... setup BPF/XDP prog on eth0 to steer into shared xsk map ... ]
# ip netns add foo
# ip link add numrxqueues 2 nk type netkit single
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk netns foo
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk up
# ip netns exec foo qemu-system-x86_64 \
-kernel $kernel \
-drive file=${image_name},index=0,media=disk,format=raw \
-append "root=/dev/sda rw console=ttyS0" \
-cpu host \
-m $memory \
-enable-kvm \
-device virtio-net-pci,netdev=net0,mac=$mac \
-netdev af-xdp,ifname=nk,id=net0,mode=native,queues=1,start-queue=1,inhibit=on,map-path=$dir/xsks_map \
-nographic
We have tested the above against a dual-port Nvidia ConnectX-6 (mlx5)
100G NIC with successful network connectivity out of QEMU. An earlier
iteration of this work was presented at LSF/MM/BPF [0] and more
recently at LPC [1].
For getting to a first starting point to connect all things with
KubeVirt, bind mounting the xsk map from Cilium into the VM launcher
Pod which acts as a regular Kubernetes Pod while not perfect, is not
a big problem given its out of reach from the application sitting
inside the VM (and some of the control plane aspects are baked in
the launcher Pod already), so the isolation barrier is still the VM.
Eventually the goal is to have a XDP/XSK redirect extension where
there is no need to have the xsk map, and the BPF program can just
derive the target xsk through the queue where traffic was received
on.
The exposure through netkit is because Cilium should not act as a
proxy handing out xsk sockets. Existing applications expect a netdev
from kernel side and should not need to rewrite just to implement
against a CNI's protocol. Also, all the memory should not be accounted
against Cilium but rather the application Pod itself which is consuming
AF_XDP. Further, on up/downgrades we expect the data plane to being
completely decoupled from the control plane; if Cilium would own the
sockets that would be disruptive. Another use-case which opens up and
is regularly asked from users would be to have DPDK applications on
top of AF_XDP in regular Kubernetes Pods.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0]
Link: https://lpc.events/event/19/contributions/2275/ [1]
Link: https://patch.msgid.link/20260402231031.447597-14-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:30 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2025-10-31 22:20:59 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2025-10-31 22:20:59 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2025-10-31 22:20:59 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2025-10-31 22:20:59 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-05-24 18:36:17 +02:00
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-12 08:56:19 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-09-12 08:56:19 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
2024-05-24 18:36:17 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-24 18:36:17 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-12 08:56:19 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-02-22 10:50:08 +00:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-06-08 08:40:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2026-06-08 08:40:12 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2024-05-24 18:36:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:18 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add xsk support for af_xdp applications
Enable support for AF_XDP applications to operate on a netkit device.
The goal is that AF_XDP applications can natively consume AF_XDP
from network namespaces. The use-case from Cilium side is to support
Kubernetes KubeVirt VMs through QEMU's AF_XDP backend. KubeVirt is a
virtual machine management add-on for Kubernetes which aims to provide
a common ground for virtualization. KubeVirt spawns the VMs inside
Kubernetes Pods which reside in their own network namespace just like
regular Pods.
Raw QEMU AF_XDP backend example with eth0 being a physical device with
16 queues where netkit is bound to the last queue (for multi-queue RSS
context can be used if supported by the driver):
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type ether \
src 00:00:00:00:00:00 \
src-mask ff:ff:ff:ff:ff:ff \
dst $mac dst-mask 00:00:00:00:00:00 \
proto 0 proto-mask 0xffff action 15
[ ... setup BPF/XDP prog on eth0 to steer into shared xsk map ... ]
# ip netns add foo
# ip link add numrxqueues 2 nk type netkit single
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk netns foo
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk up
# ip netns exec foo qemu-system-x86_64 \
-kernel $kernel \
-drive file=${image_name},index=0,media=disk,format=raw \
-append "root=/dev/sda rw console=ttyS0" \
-cpu host \
-m $memory \
-enable-kvm \
-device virtio-net-pci,netdev=net0,mac=$mac \
-netdev af-xdp,ifname=nk,id=net0,mode=native,queues=1,start-queue=1,inhibit=on,map-path=$dir/xsks_map \
-nographic
We have tested the above against a dual-port Nvidia ConnectX-6 (mlx5)
100G NIC with successful network connectivity out of QEMU. An earlier
iteration of this work was presented at LSF/MM/BPF [0] and more
recently at LPC [1].
For getting to a first starting point to connect all things with
KubeVirt, bind mounting the xsk map from Cilium into the VM launcher
Pod which acts as a regular Kubernetes Pod while not perfect, is not
a big problem given its out of reach from the application sitting
inside the VM (and some of the control plane aspects are baked in
the launcher Pod already), so the isolation barrier is still the VM.
Eventually the goal is to have a XDP/XSK redirect extension where
there is no need to have the xsk map, and the BPF program can just
derive the target xsk through the queue where traffic was received
on.
The exposure through netkit is because Cilium should not act as a
proxy handing out xsk sockets. Existing applications expect a netdev
from kernel side and should not need to rewrite just to implement
against a CNI's protocol. Also, all the memory should not be accounted
against Cilium but rather the application Pod itself which is consuming
AF_XDP. Further, on up/downgrades we expect the data plane to being
completely decoupled from the control plane; if Cilium would own the
sockets that would be disruptive. Another use-case which opens up and
is regularly asked from users would be to have DPDK applications on
top of AF_XDP in regular Kubernetes Pods.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0]
Link: https://lpc.events/event/19/contributions/2275/ [1]
Link: https://patch.msgid.link/20260402231031.447597-14-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:30 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-04-16 11:57:09 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-05-24 18:36:16 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Add xsk support for af_xdp applications
Enable support for AF_XDP applications to operate on a netkit device.
The goal is that AF_XDP applications can natively consume AF_XDP
from network namespaces. The use-case from Cilium side is to support
Kubernetes KubeVirt VMs through QEMU's AF_XDP backend. KubeVirt is a
virtual machine management add-on for Kubernetes which aims to provide
a common ground for virtualization. KubeVirt spawns the VMs inside
Kubernetes Pods which reside in their own network namespace just like
regular Pods.
Raw QEMU AF_XDP backend example with eth0 being a physical device with
16 queues where netkit is bound to the last queue (for multi-queue RSS
context can be used if supported by the driver):
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type ether \
src 00:00:00:00:00:00 \
src-mask ff:ff:ff:ff:ff:ff \
dst $mac dst-mask 00:00:00:00:00:00 \
proto 0 proto-mask 0xffff action 15
[ ... setup BPF/XDP prog on eth0 to steer into shared xsk map ... ]
# ip netns add foo
# ip link add numrxqueues 2 nk type netkit single
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk netns foo
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk up
# ip netns exec foo qemu-system-x86_64 \
-kernel $kernel \
-drive file=${image_name},index=0,media=disk,format=raw \
-append "root=/dev/sda rw console=ttyS0" \
-cpu host \
-m $memory \
-enable-kvm \
-device virtio-net-pci,netdev=net0,mac=$mac \
-netdev af-xdp,ifname=nk,id=net0,mode=native,queues=1,start-queue=1,inhibit=on,map-path=$dir/xsks_map \
-nographic
We have tested the above against a dual-port Nvidia ConnectX-6 (mlx5)
100G NIC with successful network connectivity out of QEMU. An earlier
iteration of this work was presented at LSF/MM/BPF [0] and more
recently at LPC [1].
For getting to a first starting point to connect all things with
KubeVirt, bind mounting the xsk map from Cilium into the VM launcher
Pod which acts as a regular Kubernetes Pod while not perfect, is not
a big problem given its out of reach from the application sitting
inside the VM (and some of the control plane aspects are baked in
the launcher Pod already), so the isolation barrier is still the VM.
Eventually the goal is to have a XDP/XSK redirect extension where
there is no need to have the xsk map, and the BPF program can just
derive the target xsk through the queue where traffic was received
on.
The exposure through netkit is because Cilium should not act as a
proxy handing out xsk sockets. Existing applications expect a netdev
from kernel side and should not need to rewrite just to implement
against a CNI's protocol. Also, all the memory should not be accounted
against Cilium but rather the application Pod itself which is consuming
AF_XDP. Further, on up/downgrades we expect the data plane to being
completely decoupled from the control plane; if Cilium would own the
sockets that would be disruptive. Another use-case which opens up and
is regularly asked from users would be to have DPDK applications on
top of AF_XDP in regular Kubernetes Pods.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0]
Link: https://lpc.events/event/19/contributions/2275/ [1]
Link: https://patch.msgid.link/20260402231031.447597-14-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:30 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 01:42:15 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-23 14:00:53 +02:00
|
|
|
|
2024-08-29 14:33:37 +02:00
|
|
|
|
2026-05-14 10:22:29 -07:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-08-29 14:33:37 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-24 18:36:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
2025-02-19 20:50:29 +08:00
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
rtnetlink: Pack newlink() params into struct
There are 4 net namespaces involved when creating links:
- source netns - where the netlink socket resides,
- target netns - where to put the device being created,
- link netns - netns associated with the device (backend),
- peer netns - netns of peer device.
Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.
+------------+-------------------+---------+---------+
| peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
+------------+-------------------+---------+---------+
| | absent | source | target |
| absent +-------------------+---------+---------+
| | present | link | link |
+------------+-------------------+---------+---------+
| | absent | peer | target |
| present +-------------------+---------+---------+
| | present | peer | link |
+------------+-------------------+---------+---------+
When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.
On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.
To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-02-19 20:50:28 +08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-10-04 12:13:32 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 16:48:21 -08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-24 18:36:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-05-24 18:36:16 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
netkit: Add xsk support for af_xdp applications
Enable support for AF_XDP applications to operate on a netkit device.
The goal is that AF_XDP applications can natively consume AF_XDP
from network namespaces. The use-case from Cilium side is to support
Kubernetes KubeVirt VMs through QEMU's AF_XDP backend. KubeVirt is a
virtual machine management add-on for Kubernetes which aims to provide
a common ground for virtualization. KubeVirt spawns the VMs inside
Kubernetes Pods which reside in their own network namespace just like
regular Pods.
Raw QEMU AF_XDP backend example with eth0 being a physical device with
16 queues where netkit is bound to the last queue (for multi-queue RSS
context can be used if supported by the driver):
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type ether \
src 00:00:00:00:00:00 \
src-mask ff:ff:ff:ff:ff:ff \
dst $mac dst-mask 00:00:00:00:00:00 \
proto 0 proto-mask 0xffff action 15
[ ... setup BPF/XDP prog on eth0 to steer into shared xsk map ... ]
# ip netns add foo
# ip link add numrxqueues 2 nk type netkit single
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk netns foo
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk up
# ip netns exec foo qemu-system-x86_64 \
-kernel $kernel \
-drive file=${image_name},index=0,media=disk,format=raw \
-append "root=/dev/sda rw console=ttyS0" \
-cpu host \
-m $memory \
-enable-kvm \
-device virtio-net-pci,netdev=net0,mac=$mac \
-netdev af-xdp,ifname=nk,id=net0,mode=native,queues=1,start-queue=1,inhibit=on,map-path=$dir/xsks_map \
-nographic
We have tested the above against a dual-port Nvidia ConnectX-6 (mlx5)
100G NIC with successful network connectivity out of QEMU. An earlier
iteration of this work was presented at LSF/MM/BPF [0] and more
recently at LPC [1].
For getting to a first starting point to connect all things with
KubeVirt, bind mounting the xsk map from Cilium into the VM launcher
Pod which acts as a regular Kubernetes Pod while not perfect, is not
a big problem given its out of reach from the application sitting
inside the VM (and some of the control plane aspects are baked in
the launcher Pod already), so the isolation barrier is still the VM.
Eventually the goal is to have a XDP/XSK redirect extension where
there is no need to have the xsk map, and the BPF program can just
derive the target xsk through the queue where traffic was received
on.
The exposure through netkit is because Cilium should not act as a
proxy handing out xsk sockets. Existing applications expect a netdev
from kernel side and should not need to rewrite just to implement
against a CNI's protocol. Also, all the memory should not be accounted
against Cilium but rather the application Pod itself which is consuming
AF_XDP. Further, on up/downgrades we expect the data plane to being
completely decoupled from the control plane; if Cilium would own the
sockets that would be disruptive. Another use-case which opens up and
is regularly asked from users would be to have DPDK applications on
top of AF_XDP in regular Kubernetes Pods.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0]
Link: https://lpc.events/event/19/contributions/2275/ [1]
Link: https://patch.msgid.link/20260402231031.447597-14-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:30 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-10 11:20:38 +08:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-10 11:20:38 +08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-10 11:20:32 +08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
treewide: Replace kmalloc with kmalloc_obj for non-scalar types
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-27 21:05:33 +01:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-04-10 09:23:34 +02:00
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-04 12:13:32 +02:00
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
2024-12-21 00:46:56 +01:00
|
|
|
|
|
|
|
|
|
netkit: Add option for scrubbing skb meta data
Jordan reported that when running Cilium with netkit in per-endpoint-routes
mode, network policy misclassifies traffic. In this direct routing mode
of Cilium which is used in case of GKE/EKS/AKS, the Pod's BPF program to
enforce policy sits on the netkit primary device's egress side.
The issue here is that in case of netkit's netkit_prep_forward(), it will
clear meta data such as skb->mark and skb->priority before executing the
BPF program. Thus, identity data stored in there from earlier BPF programs
(e.g. from tcx ingress on the physical device) gets cleared instead of
being made available for the primary's program to process. While for traffic
egressing the Pod via the peer device this might be desired, this is
different for the primary one where compared to tcx egress on the host
veth this information would be available.
To address this, add a new parameter for the device orchestration to
allow control of skb->mark and skb->priority scrubbing, to make the two
accessible from BPF (and eventually leave it up to the program to scrub).
By default, the current behavior is retained. For netkit peer this also
enables the use case where applications could cooperate/signal intent to
the BPF program.
Note that struct netkit has a 4 byte hole between policy and bundle which
is used here, in other words, struct netkit's first cacheline content used
in fast-path does not get moved around.
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Jordan Rife <jrife@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://github.com/cilium/cilium/issues/34042
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2024-10-04 12:13:31 +02:00
|
|
|
|
|
|
|
|
|
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
leasing 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 leasing 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 leasing 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 manage rxq leasing 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@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Jordan Rife <jordan@jrife.io>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0]
Link: https://patch.msgid.link/20260402231031.447597-11-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:27 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 16:48:21 -08:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
netkit: Add netkit notifier to check for unregistering devices
Add a netdevice notifier in netkit to watch for NETDEV_UNREGISTER events.
If the target device is indeed NETREG_UNREGISTERING and previously leased
a queue to a netkit device, then collect the related netkit devices and
batch-unregister_netdevice_many() them.
If this were not done, then the netkit device would hold a reference on
the physical device preventing it from going away. However, in case of
both io_uring zero-copy as well as AF_XDP this situation is handled
gracefully and the allocated resources are torn down.
In the case where mentioned infra is used through netkit, the applications
have a reference on netkit, and netkit in turn holds a reference on the
physical device. In order to have netkit release the reference on the
physical device, we need such watcher to then unregister the netkit ones.
This is generally quite similar to the dependency handling in case of
tunnels (e.g. vxlan bound to a underlying netdev) where the tunnel device
gets removed along with the physical device.
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
[...]
8: nk@NONE: <BROADCAST,MULTICAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
[...]
# rmmod mlx5_ib
# rmmod mlx5_core
[...]
[ 309.261822] mlx5_core 0000:0a:00.0 mlx5_0: Port: 1 Link DOWN
[ 344.235236] mlx5_core 0000:0a:00.1: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.246948] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.463754] mlx5_core 0000:0a:00.1: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0)
[ 344.770155] mlx5_core 0000:0a:00.1: E-Switch: cleanup
[...]
# ip a
[...]
[ both enp10s0f0np0 and nk gone ]
[...]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-13-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:29 +02:00
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
|
|
|
|
|
netkit, bpf: Add bpf programmable net device
This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.
One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).
In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.
Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.
Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.
An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.
Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2023-10-24 23:48:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netkit: Implement rtnl_link_ops->alloc and ndo_queue_create
Implement rtnl_link_ops->alloc that allows the number of rx queues to be
set when netkit is created. By default, netkit has only a single rxq (and
single txq). The number of queues is deliberately not allowed to be changed
via ethtool -L and is fixed for the lifetime of a netkit instance.
For netkit device creation, numrxqueues with larger than one rxq can be
specified. These rxqs are leasable to real rxqs in physical netdevs:
ip link add type netkit peer numrxqueues 64 # for device pair
ip link add numrxqueues 64 type netkit single # for single device
The limit of numrxqueues for netkit is currently set to 1024, which allows
leasing multiple real rxqs from physical netdevs.
The implementation of ndo_queue_create() adds a new rxq during the queue
lease operation. We allow to create queues either in single device mode
or for the case of dual device mode for the netkit peer device which gets
placed into the target network namespace. For dual device mode the lease
against the primary device does not make sense for the targeted use cases,
and therefore gets rejected.
We also need to add a lockdep class for netkit, such that lockdep does
not trip over us, similarly done as in commit 0bef512012b1 ("net: add
netdev_lockdep_set_classes() to virtual drivers").
This is also the last missing bit to netkit for supporting io_uring with
zero-copy mode [0]. Up until this point it was not possible to consume the
latter out of containers or Kubernetes Pods where applications are in their
own network namespace.
io_uring example with eth0 being a physical device with 16 queues where
netkit is bound to the last queue, iou-zcrx.c is binary from selftests;
ethtool configuration (tcp-data-split, hds_thresh, RSS, flow steering)
is done on the physical device by the control plane; here, flow steering
to that queue is based on the service VIP:port of the server utilizing
io_uring:
# ethtool -X eth0 start 0 equal 15
# ethtool -X eth0 start 15 equal 1 context new
# ethtool --config-ntuple eth0 flow-type tcp4 dst-ip 1.2.3.4 dst-port 5000 action 15
# ip netns add foo
# ip link add type netkit peer numrxqueues 2
# ynl --family netdev --output-json --do queue-create \
--json "{"ifindex": $(ifindex nk0), "type": "rx", \
"lease": { "ifindex": $(ifindex eth0), \
"queue": { "type": "rx", "id": 15 } } }"
{'id': 1}
# ip link set nk0 netns foo
# ip link set nk1 up
# ip netns exec foo ip link set lo up
# ip netns exec foo ip link set nk0 up
# ip netns exec foo ip addr add 1.2.3.4/32 dev nk0
[ ... setup routing etc to get external traffic into the netns ... ]
# ip netns exec foo ./iou-zcrx -s -p 5000 -i nk0 -q 1
Remote io_uring client:
# ./iou-zcrx -c -h 1.2.3.4 -p 5000 -l 12840 -z 65536
We have tested the above against a Broadcom BCM957504 (bnxt_en) 100G NIC,
supporting TCP header/data split.
Similarly, this also works for devmem which we tested using ncdevmem:
# ip netns exec foo ./ncdevmem -s 1.2.3.4 -l -p 5000 -f nk0 -t 1 -q 1
And on the remote client:
# ./ncdevmem -s 1.2.3.4 -p 5000 -f eth0
For Cilium, the plan is to open up support for the various memory providers
for regular Kubernetes Pods when Cilium is configured with netkit datapath
mode.
Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://kernel-recipes.org/en/2024/schedule/efficient-zero-copy-networking-using-io_uring [0]
Link: https://patch.msgid.link/20260402231031.447597-12-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-04-03 01:10:28 +02:00
|
|
|
|
