iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'Add bpf programmable net device'

Browse Source 
Daniel Borkmann says:

====================
This work adds a BPF programmable device which can operate in L3 or L2
mode where the BPF program is part of the xmit routine. It's program
management is done via bpf_mprog and it comes with BPF link support.
For details see patch 1 and following. Thanks!

v3 -> v4:
  - Moved netkit_release_all() into ndo_uninit (Stan)
  - Two small commit msg corrections (Toke)
  - Added Acked/Reviewed-by
v2 -> v3:
  - Remove setting dev->min_mtu to ETH_MIN_MTU (Andrew)
  - Do not populate ethtool info->version (Andrew)
  - Populate netdev private data before register_netdevice (Andrew)
  - Use strscpy for ifname template (Jakub)
  - Use GFP_KERNEL_ACCOUNT for link kzalloc (Jakub)
  - Carry and dump link attach type for bpftool (Toke)
v1 -> v2:
  - Rename from meta (Toke, Andrii, Alexei)
  - Reuse skb_scrub_packet (Stan)
  - Remove IFF_META and use netdev_ops (Toke)
  - Add comment to multicast handler (Toke)
  - Remove silly version info (Toke)
  - Fix attach_type_name (Quentin)
  - Rework libbpf link attach api to be similar
    as tcx (Andrii)
  - Move flags last for bpf_netkit_opts (Andrii)
  - Rebased to bpf_mprog query api changes
  - Folded link support patch into main one
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
This commit is contained in:
Martin KaFai Lau 2023-10-24 16:05:02 -07:00
commit 22360fad58
25 changed files with 2433 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
MAINTAINERS
View File

@ -3795,6 +3795,15 @@ L: bpf@vger.kernel.org
S: Odd Fixes
K: (?:\b|_)bpf(?:\b|_)
BPF [NETKIT] (BPF-programmable network device)
M: Daniel Borkmann <daniel@iogearbox.net>
M: Nikolay Aleksandrov <razor@blackwall.org>
L: bpf@vger.kernel.org
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/netkit.c
F: include/net/netkit.h
BPF [NETWORKING] (struct_ops, reuseport)
M: Martin KaFai Lau <martin.lau@linux.dev>
L: bpf@vger.kernel.org

9
drivers/net/Kconfig
View File

@ -448,6 +448,15 @@ config NLMON
diagnostics, etc. This is mostly intended for developers or support
to debug netlink issues. If unsure, say N.
config NETKIT
bool "BPF-programmable network device"
depends on BPF_SYSCALL
help
The netkit device is a virtual networking device where BPF programs
can be attached to the device(s) transmission routine in order to
implement the driver's internal logic. The device can be configured
to operate in L3 or L2 mode. If unsure, say N.
config NET_VRF
tristate "Virtual Routing and Forwarding (Lite)"
depends on IP_MULTIPLE_TABLES

1
drivers/net/Makefile
View File

@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO) += mdio.o
obj-$(CONFIG_NET) += loopback.o
obj-$(CONFIG_NETDEV_LEGACY_INIT) += Space.o
obj-$(CONFIG_NETCONSOLE) += netconsole.o
obj-$(CONFIG_NETKIT) += netkit.o
obj-y += phy/
obj-y += pse-pd/
obj-y += mdio/

940
drivers/net/netkit.c Normal file
View File

@ -0,0 +1,940 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2023 Isovalent */
#include <linux/netdevice.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/filter.h>
#include <linux/netfilter_netdev.h>
#include <linux/bpf_mprog.h>
#include <net/netkit.h>
#include <net/dst.h>
#include <net/tcx.h>
#define DRV_NAME "netkit"
struct netkit {
/* Needed in fast-path */
struct net_device __rcu *peer;
struct bpf_mprog_entry __rcu *active;
enum netkit_action policy;
struct bpf_mprog_bundle bundle;
/* Needed in slow-path */
enum netkit_mode mode;
bool primary;
u32 headroom;
};
struct netkit_link {
struct bpf_link link;
struct net_device *dev;
u32 location;
};
static __always_inline int
netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
enum netkit_action ret)
{
const struct bpf_mprog_fp *fp;
const struct bpf_prog *prog;
bpf_mprog_foreach_prog(entry, fp, prog) {
bpf_compute_data_pointers(skb);
ret = bpf_prog_run(prog, skb);
if (ret != NETKIT_NEXT)
break;
}
return ret;
}
static void netkit_prep_forward(struct sk_buff *skb, bool xnet)
{
skb_scrub_packet(skb, xnet);
skb->priority = 0;
nf_skip_egress(skb, true);
}
static struct netkit *netkit_priv(const struct net_device *dev)
{
return netdev_priv(dev);
}
static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
enum netkit_action ret = READ_ONCE(nk->policy);
netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
const struct bpf_mprog_entry *entry;
struct net_device *peer;
rcu_read_lock();
peer = rcu_dereference(nk->peer);
if (unlikely(!peer || !(peer->flags & IFF_UP) ||
!pskb_may_pull(skb, ETH_HLEN) ||
skb_orphan_frags(skb, GFP_ATOMIC)))
goto drop;
netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)));
skb->dev = peer;
entry = rcu_dereference(nk->active);
if (entry)
ret = netkit_run(entry, skb, ret);
switch (ret) {
case NETKIT_NEXT:
case NETKIT_PASS:
skb->protocol = eth_type_trans(skb, skb->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
__netif_rx(skb);
break;
case NETKIT_REDIRECT:
skb_do_redirect(skb);
break;
case NETKIT_DROP:
default:
drop:
kfree_skb(skb);
dev_core_stats_tx_dropped_inc(dev);
ret_dev = NET_XMIT_DROP;
break;
}
rcu_read_unlock();
return ret_dev;
}
static int netkit_open(struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
if (!peer)
return -ENOTCONN;
if (peer->flags & IFF_UP) {
netif_carrier_on(dev);
netif_carrier_on(peer);
}
return 0;
}
static int netkit_close(struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
netif_carrier_off(dev);
if (peer)
netif_carrier_off(peer);
return 0;
}
static int netkit_get_iflink(const struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer;
int iflink = 0;
rcu_read_lock();
peer = rcu_dereference(nk->peer);
if (peer)
iflink = peer->ifindex;
rcu_read_unlock();
return iflink;
}
static void netkit_set_multicast(struct net_device *dev)
{
/* Nothing to do, we receive whatever gets pushed to us! */
}
static void netkit_set_headroom(struct net_device *dev, int headroom)
{
struct netkit *nk = netkit_priv(dev), *nk2;
struct net_device *peer;
if (headroom < 0)
headroom = NET_SKB_PAD;
rcu_read_lock();
peer = rcu_dereference(nk->peer);
if (unlikely(!peer))
goto out;
nk2 = netkit_priv(peer);
nk->headroom = headroom;
headroom = max(nk->headroom, nk2->headroom);
peer->needed_headroom = headroom;
dev->needed_headroom = headroom;
out:
rcu_read_unlock();
}
static struct net_device *netkit_peer_dev(struct net_device *dev)
{
return rcu_dereference(netkit_priv(dev)->peer);
}
static void netkit_uninit(struct net_device *dev);
static const struct net_device_ops netkit_netdev_ops = {
.ndo_open = netkit_open,
.ndo_stop = netkit_close,
.ndo_start_xmit = netkit_xmit,
.ndo_set_rx_mode = netkit_set_multicast,
.ndo_set_rx_headroom = netkit_set_headroom,
.ndo_get_iflink = netkit_get_iflink,
.ndo_get_peer_dev = netkit_peer_dev,
.ndo_uninit = netkit_uninit,
.ndo_features_check = passthru_features_check,
};
static void netkit_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
strscpy(info->driver, DRV_NAME, sizeof(info->driver));
}
static const struct ethtool_ops netkit_ethtool_ops = {
.get_drvinfo = netkit_get_drvinfo,
};
static void netkit_setup(struct net_device *dev)
{
static const netdev_features_t netkit_features_hw_vlan =
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_STAG_TX |
NETIF_F_HW_VLAN_STAG_RX;
static const netdev_features_t netkit_features =
netkit_features_hw_vlan |
NETIF_F_SG |
NETIF_F_FRAGLIST |
NETIF_F_HW_CSUM |
NETIF_F_RXCSUM |
NETIF_F_SCTP_CRC |
NETIF_F_HIGHDMA |
NETIF_F_GSO_SOFTWARE |
NETIF_F_GSO_ENCAP_ALL;
ether_setup(dev);
dev->max_mtu = ETH_MAX_MTU;
dev->flags |= IFF_NOARP;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
dev->priv_flags |= IFF_PHONY_HEADROOM;
dev->priv_flags |= IFF_NO_QUEUE;
dev->ethtool_ops = &netkit_ethtool_ops;
dev->netdev_ops = &netkit_netdev_ops;
dev->features |= netkit_features | NETIF_F_LLTX;
dev->hw_features = netkit_features;
dev->hw_enc_features = netkit_features;
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
dev->vlan_features = dev->features & ~netkit_features_hw_vlan;
dev->needs_free_netdev = true;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
}
static struct net *netkit_get_link_net(const struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
return peer ? dev_net(peer) : dev_net(dev);
}
static int netkit_check_policy(int policy, struct nlattr *tb,
struct netlink_ext_ack *extack)
{
switch (policy) {
case NETKIT_PASS:
case NETKIT_DROP:
return 0;
default:
NL_SET_ERR_MSG_ATTR(extack, tb,
"Provided default xmit policy not supported");
return -EINVAL;
}
}
static int netkit_check_mode(int mode, struct nlattr *tb,
struct netlink_ext_ack *extack)
{
switch (mode) {
case NETKIT_L2:
case NETKIT_L3:
return 0;
default:
NL_SET_ERR_MSG_ATTR(extack, tb,
"Provided device mode can only be L2 or L3");
return -EINVAL;
}
}
static int netkit_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct nlattr *attr = tb[IFLA_ADDRESS];
if (!attr)
return 0;
NL_SET_ERR_MSG_ATTR(extack, attr,
"Setting Ethernet address is not supported");
return -EOPNOTSUPP;
}
static struct rtnl_link_ops netkit_link_ops;
static int netkit_new_link(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr;
enum netkit_action default_prim = NETKIT_PASS;
enum netkit_action default_peer = NETKIT_PASS;
enum netkit_mode mode = NETKIT_L3;
unsigned char ifname_assign_type;
struct ifinfomsg *ifmp = NULL;
struct net_device *peer;
char ifname[IFNAMSIZ];
struct netkit *nk;
struct net *net;
int err;
if (data) {
if (data[IFLA_NETKIT_MODE]) {
attr = data[IFLA_NETKIT_MODE];
mode = nla_get_u32(attr);
err = netkit_check_mode(mode, attr, extack);
if (err < 0)
return err;
}
if (data[IFLA_NETKIT_PEER_INFO]) {
attr = data[IFLA_NETKIT_PEER_INFO];
ifmp = nla_data(attr);
err = rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack);
if (err < 0)
return err;
err = netkit_validate(peer_tb, NULL, extack);
if (err < 0)
return err;
tbp = peer_tb;
}
if (data[IFLA_NETKIT_POLICY]) {
attr = data[IFLA_NETKIT_POLICY];
default_prim = nla_get_u32(attr);
err = netkit_check_policy(default_prim, attr, extack);
if (err < 0)
return err;
}
if (data[IFLA_NETKIT_PEER_POLICY]) {
attr = data[IFLA_NETKIT_PEER_POLICY];
default_peer = nla_get_u32(attr);
err = netkit_check_policy(default_peer, attr, extack);
if (err < 0)
return err;
}
}
if (ifmp && tbp[IFLA_IFNAME]) {
nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
ifname_assign_type = NET_NAME_USER;
} else {
strscpy(ifname, "nk%d", IFNAMSIZ);
ifname_assign_type = NET_NAME_ENUM;
}
net = rtnl_link_get_net(src_net, tbp);
if (IS_ERR(net))
return PTR_ERR(net);
peer = rtnl_create_link(net, ifname, ifname_assign_type,
&netkit_link_ops, tbp, extack);
if (IS_ERR(peer)) {
put_net(net);
return PTR_ERR(peer);
}
netif_inherit_tso_max(peer, dev);
if (mode == NETKIT_L2)
eth_hw_addr_random(peer);
if (ifmp && dev->ifindex)
peer->ifindex = ifmp->ifi_index;
nk = netkit_priv(peer);
nk->primary = false;
nk->policy = default_peer;
nk->mode = mode;
bpf_mprog_bundle_init(&nk->bundle);
RCU_INIT_POINTER(nk->active, NULL);
RCU_INIT_POINTER(nk->peer, NULL);
err = register_netdevice(peer);
put_net(net);
if (err < 0)
goto err_register_peer;
netif_carrier_off(peer);
if (mode == NETKIT_L2)
dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL);
err = rtnl_configure_link(peer, NULL, 0, NULL);
if (err < 0)
goto err_configure_peer;
if (mode == NETKIT_L2)
eth_hw_addr_random(dev);
if (tb[IFLA_IFNAME])
nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
strscpy(dev->name, "nk%d", IFNAMSIZ);
nk = netkit_priv(dev);
nk->primary = true;
nk->policy = default_prim;
nk->mode = mode;
bpf_mprog_bundle_init(&nk->bundle);
RCU_INIT_POINTER(nk->active, NULL);
RCU_INIT_POINTER(nk->peer, NULL);
err = register_netdevice(dev);
if (err < 0)
goto err_configure_peer;
netif_carrier_off(dev);
if (mode == NETKIT_L2)
dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL);
rcu_assign_pointer(netkit_priv(dev)->peer, peer);
rcu_assign_pointer(netkit_priv(peer)->peer, dev);
return 0;
err_configure_peer:
unregister_netdevice(peer);
return err;
err_register_peer:
free_netdev(peer);
return err;
}
static struct bpf_mprog_entry *netkit_entry_fetch(struct net_device *dev,
bool bundle_fallback)
{
struct netkit *nk = netkit_priv(dev);
struct bpf_mprog_entry *entry;
ASSERT_RTNL();
entry = rcu_dereference_rtnl(nk->active);
if (entry)
return entry;
if (bundle_fallback)
return &nk->bundle.a;
return NULL;
}
static void netkit_entry_update(struct net_device *dev,
struct bpf_mprog_entry *entry)
{
struct netkit *nk = netkit_priv(dev);
ASSERT_RTNL();
rcu_assign_pointer(nk->active, entry);
}
static void netkit_entry_sync(void)
{
synchronize_rcu();
}
static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 which)
{
struct net_device *dev;
struct netkit *nk;
ASSERT_RTNL();
switch (which) {
case BPF_NETKIT_PRIMARY:
case BPF_NETKIT_PEER:
break;
default:
return ERR_PTR(-EINVAL);
}
dev = __dev_get_by_index(net, ifindex);
if (!dev)
return ERR_PTR(-ENODEV);
if (dev->netdev_ops != &netkit_netdev_ops)
return ERR_PTR(-ENXIO);
nk = netkit_priv(dev);
if (!nk->primary)
return ERR_PTR(-EACCES);
if (which == BPF_NETKIT_PEER) {
dev = rcu_dereference_rtnl(nk->peer);
if (!dev)
return ERR_PTR(-ENODEV);
}
return dev;
}
int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_mprog_entry *entry, *entry_new;
struct bpf_prog *replace_prog = NULL;
struct net_device *dev;
int ret;
rtnl_lock();
dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex,
attr->attach_type);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto out;
}
entry = netkit_entry_fetch(dev, true);
if (attr->attach_flags & BPF_F_REPLACE) {
replace_prog = bpf_prog_get_type(attr->replace_bpf_fd,
prog->type);
if (IS_ERR(replace_prog)) {
ret = PTR_ERR(replace_prog);
replace_prog = NULL;
goto out;
}
}
ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog,
attr->attach_flags, attr->relative_fd,
attr->expected_revision);
if (!ret) {
if (entry != entry_new) {
netkit_entry_update(dev, entry_new);
netkit_entry_sync();
}
bpf_mprog_commit(entry);
}
out:
if (replace_prog)
bpf_prog_put(replace_prog);
rtnl_unlock();
return ret;
}
int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_mprog_entry *entry, *entry_new;
struct net_device *dev;
int ret;
rtnl_lock();
dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex,
attr->attach_type);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto out;
}
entry = netkit_entry_fetch(dev, false);
if (!entry) {
ret = -ENOENT;
goto out;
}
ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags,
attr->relative_fd, attr->expected_revision);
if (!ret) {
if (!bpf_mprog_total(entry_new))
entry_new = NULL;
netkit_entry_update(dev, entry_new);
netkit_entry_sync();
bpf_mprog_commit(entry);
}
out:
rtnl_unlock();
return ret;
}
int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
{
struct net_device *dev;
int ret;
rtnl_lock();
dev = netkit_dev_fetch(current->nsproxy->net_ns,
attr->query.target_ifindex,
attr->query.attach_type);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto out;
}
ret = bpf_mprog_query(attr, uattr, netkit_entry_fetch(dev, false));
out:
rtnl_unlock();
return ret;
}
static struct netkit_link *netkit_link(const struct bpf_link *link)
{
return container_of(link, struct netkit_link, link);
}
static int netkit_link_prog_attach(struct bpf_link *link, u32 flags,
u32 id_or_fd, u64 revision)
{
struct netkit_link *nkl = netkit_link(link);
struct bpf_mprog_entry *entry, *entry_new;
struct net_device *dev = nkl->dev;
int ret;
ASSERT_RTNL();
entry = netkit_entry_fetch(dev, true);
ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags,
id_or_fd, revision);
if (!ret) {
if (entry != entry_new) {
netkit_entry_update(dev, entry_new);
netkit_entry_sync();
}
bpf_mprog_commit(entry);
}
return ret;
}
static void netkit_link_release(struct bpf_link *link)
{
struct netkit_link *nkl = netkit_link(link);
struct bpf_mprog_entry *entry, *entry_new;
struct net_device *dev;
int ret = 0;
rtnl_lock();
dev = nkl->dev;
if (!dev)
goto out;
entry = netkit_entry_fetch(dev, false);
if (!entry) {
ret = -ENOENT;
goto out;
}
ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0);
if (!ret) {
if (!bpf_mprog_total(entry_new))
entry_new = NULL;
netkit_entry_update(dev, entry_new);
netkit_entry_sync();
bpf_mprog_commit(entry);
nkl->dev = NULL;
}
out:
WARN_ON_ONCE(ret);
rtnl_unlock();
}
static int netkit_link_update(struct bpf_link *link, struct bpf_prog *nprog,
struct bpf_prog *oprog)
{
struct netkit_link *nkl = netkit_link(link);
struct bpf_mprog_entry *entry, *entry_new;
struct net_device *dev;
int ret = 0;
rtnl_lock();
dev = nkl->dev;
if (!dev) {
ret = -ENOLINK;
goto out;
}
if (oprog && link->prog != oprog) {
ret = -EPERM;
goto out;
}
oprog = link->prog;
if (oprog == nprog) {
bpf_prog_put(nprog);
goto out;
}
entry = netkit_entry_fetch(dev, false);
if (!entry) {
ret = -ENOENT;
goto out;
}
ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog,
BPF_F_REPLACE | BPF_F_ID,
link->prog->aux->id, 0);
if (!ret) {
WARN_ON_ONCE(entry != entry_new);
oprog = xchg(&link->prog, nprog);
bpf_prog_put(oprog);
bpf_mprog_commit(entry);
}
out:
rtnl_unlock();
return ret;
}
static void netkit_link_dealloc(struct bpf_link *link)
{
kfree(netkit_link(link));
}
static void netkit_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
{
const struct netkit_link *nkl = netkit_link(link);
u32 ifindex = 0;
rtnl_lock();
if (nkl->dev)
ifindex = nkl->dev->ifindex;
rtnl_unlock();
seq_printf(seq, "ifindex:\t%u\n", ifindex);
seq_printf(seq, "attach_type:\t%u (%s)\n",
nkl->location,
nkl->location == BPF_NETKIT_PRIMARY ? "primary" : "peer");
}
static int netkit_link_fill_info(const struct bpf_link *link,
struct bpf_link_info *info)
{
const struct netkit_link *nkl = netkit_link(link);
u32 ifindex = 0;
rtnl_lock();
if (nkl->dev)
ifindex = nkl->dev->ifindex;
rtnl_unlock();
info->netkit.ifindex = ifindex;
info->netkit.attach_type = nkl->location;
return 0;
}
static int netkit_link_detach(struct bpf_link *link)
{
netkit_link_release(link);
return 0;
}
static const struct bpf_link_ops netkit_link_lops = {
.release = netkit_link_release,
.detach = netkit_link_detach,
.dealloc = netkit_link_dealloc,
.update_prog = netkit_link_update,
.show_fdinfo = netkit_link_fdinfo,
.fill_link_info = netkit_link_fill_info,
};
static int netkit_link_init(struct netkit_link *nkl,
struct bpf_link_primer *link_primer,
const union bpf_attr *attr,
struct net_device *dev,
struct bpf_prog *prog)
{
bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT,
&netkit_link_lops, prog);
nkl->location = attr->link_create.attach_type;
nkl->dev = dev;
return bpf_link_prime(&nkl->link, link_primer);
}
int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_link_primer link_primer;
struct netkit_link *nkl;
struct net_device *dev;
int ret;
rtnl_lock();
dev = netkit_dev_fetch(current->nsproxy->net_ns,
attr->link_create.target_ifindex,
attr->link_create.attach_type);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto out;
}
nkl = kzalloc(sizeof(*nkl), GFP_KERNEL_ACCOUNT);
if (!nkl) {
ret = -ENOMEM;
goto out;
}
ret = netkit_link_init(nkl, &link_primer, attr, dev, prog);
if (ret) {
kfree(nkl);
goto out;
}
ret = netkit_link_prog_attach(&nkl->link,
attr->link_create.flags,
attr->link_create.netkit.relative_fd,
attr->link_create.netkit.expected_revision);
if (ret) {
nkl->dev = NULL;
bpf_link_cleanup(&link_primer);
goto out;
}
ret = bpf_link_settle(&link_primer);
out:
rtnl_unlock();
return ret;
}
static void netkit_release_all(struct net_device *dev)
{
struct bpf_mprog_entry *entry;
struct bpf_tuple tuple = {};
struct bpf_mprog_fp *fp;
struct bpf_mprog_cp *cp;
entry = netkit_entry_fetch(dev, false);
if (!entry)
return;
netkit_entry_update(dev, NULL);
netkit_entry_sync();
bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
if (tuple.link)
netkit_link(tuple.link)->dev = NULL;
else
bpf_prog_put(tuple.prog);
}
}
static void netkit_uninit(struct net_device *dev)
{
netkit_release_all(dev);
}
static void netkit_del_link(struct net_device *dev, struct list_head *head)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
RCU_INIT_POINTER(nk->peer, NULL);
unregister_netdevice_queue(dev, head);
if (peer) {
nk = netkit_priv(peer);
RCU_INIT_POINTER(nk->peer, NULL);
unregister_netdevice_queue(peer, head);
}
}
static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
enum netkit_action policy;
struct nlattr *attr;
int err;
if (!nk->primary) {
NL_SET_ERR_MSG(extack,
"netkit link settings can be changed only through the primary device");
return -EACCES;
}
if (data[IFLA_NETKIT_MODE]) {
NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE],
"netkit link operating mode cannot be changed after device creation");
return -EACCES;
}
if (data[IFLA_NETKIT_POLICY]) {
attr = data[IFLA_NETKIT_POLICY];
policy = nla_get_u32(attr);
err = netkit_check_policy(policy, attr, extack);
if (err)
return err;
WRITE_ONCE(nk->policy, policy);
}
if (data[IFLA_NETKIT_PEER_POLICY]) {
err = -EOPNOTSUPP;
attr = data[IFLA_NETKIT_PEER_POLICY];
policy = nla_get_u32(attr);
if (peer)
err = netkit_check_policy(policy, attr, extack);
if (err)
return err;
nk = netkit_priv(peer);
WRITE_ONCE(nk->policy, policy);
}
return 0;
}
static size_t netkit_get_size(const struct net_device *dev)
{
return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */
nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */
nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */
nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */
0;
}
static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct netkit *nk = netkit_priv(dev);
struct net_device *peer = rtnl_dereference(nk->peer);
if (nla_put_u8(skb, IFLA_NETKIT_PRIMARY, nk->primary))
return -EMSGSIZE;
if (nla_put_u32(skb, IFLA_NETKIT_POLICY, nk->policy))
return -EMSGSIZE;
if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode))
return -EMSGSIZE;
if (peer) {
nk = netkit_priv(peer);
if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy))
return -EMSGSIZE;
}
return 0;
}
static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
[IFLA_NETKIT_PEER_INFO] = { .len = sizeof(struct ifinfomsg) },
[IFLA_NETKIT_POLICY] = { .type = NLA_U32 },
[IFLA_NETKIT_MODE] = { .type = NLA_U32 },
[IFLA_NETKIT_PEER_POLICY] = { .type = NLA_U32 },
[IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT,
.reject_message = "Primary attribute is read-only" },
};
static struct rtnl_link_ops netkit_link_ops = {
.kind = DRV_NAME,
.priv_size = sizeof(struct netkit),
.setup = netkit_setup,
.newlink = netkit_new_link,
.dellink = netkit_del_link,
.changelink = netkit_change_link,
.get_link_net = netkit_get_link_net,
.get_size = netkit_get_size,
.fill_info = netkit_fill_info,
.policy = netkit_policy,
.validate = netkit_validate,
.maxtype = IFLA_NETKIT_MAX,
};
static __init int netkit_init(void)
{
BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT ||
(int)NETKIT_PASS != (int)TCX_PASS ||
(int)NETKIT_DROP != (int)TCX_DROP ||
(int)NETKIT_REDIRECT != (int)TCX_REDIRECT);
return rtnl_link_register(&netkit_link_ops);
}
static __exit void netkit_exit(void)
{
rtnl_link_unregister(&netkit_link_ops);
}
module_init(netkit_init);
module_exit(netkit_exit);
MODULE_DESCRIPTION("BPF-programmable network device");
MODULE_AUTHOR("Daniel Borkmann <daniel@iogearbox.net>");
MODULE_AUTHOR("Nikolay Aleksandrov <razor@blackwall.org>");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);

38
include/net/netkit.h Normal file
View File

@ -0,0 +1,38 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2023 Isovalent */
#ifndef __NET_NETKIT_H
#define __NET_NETKIT_H
#include <linux/bpf.h>
#ifdef CONFIG_NETKIT
int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
#else
static inline int netkit_prog_attach(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
static inline int netkit_link_attach(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
static inline int netkit_prog_detach(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
static inline int netkit_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return -EINVAL;
}
#endif /* CONFIG_NETKIT */
#endif /* __NET_NETKIT_H */

14
include/uapi/linux/bpf.h
View File

@ -1052,6 +1052,8 @@ enum bpf_attach_type {
BPF_CGROUP_UNIX_RECVMSG,
BPF_CGROUP_UNIX_GETPEERNAME,
BPF_CGROUP_UNIX_GETSOCKNAME,
BPF_NETKIT_PRIMARY,
BPF_NETKIT_PEER,
__MAX_BPF_ATTACH_TYPE
};
@ -1071,6 +1073,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_NETFILTER = 10,
BPF_LINK_TYPE_TCX = 11,
BPF_LINK_TYPE_UPROBE_MULTI = 12,
BPF_LINK_TYPE_NETKIT = 13,
MAX_BPF_LINK_TYPE,
};
@ -1656,6 +1659,13 @@ union bpf_attr {
__u32 flags;
__u32 pid;
} uprobe_multi;
struct {
union {
__u32 relative_fd;
__u32 relative_id;
};
__u64 expected_revision;
} netkit;
};
} link_create;
@ -6576,6 +6586,10 @@ struct bpf_link_info {
__u32 ifindex;
__u32 attach_type;
} tcx;
struct {
__u32 ifindex;
__u32 attach_type;
} netkit;
};
} __attribute__((aligned(8)));

24
include/uapi/linux/if_link.h
View File

@ -756,6 +756,30 @@ struct tunnel_msg {
__u32 ifindex;
};
/* netkit section */
enum netkit_action {
NETKIT_NEXT = -1,
NETKIT_PASS = 0,
NETKIT_DROP = 2,
NETKIT_REDIRECT = 7,
};
enum netkit_mode {
NETKIT_L2,
NETKIT_L3,
};
enum {
IFLA_NETKIT_UNSPEC,
IFLA_NETKIT_PEER_INFO,
IFLA_NETKIT_PRIMARY,
IFLA_NETKIT_POLICY,
IFLA_NETKIT_PEER_POLICY,
IFLA_NETKIT_MODE,
__IFLA_NETKIT_MAX,
};
#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1)
/* VXLAN section */
/* include statistics in the dump */

30
kernel/bpf/syscall.c
View File

@ -35,8 +35,9 @@
#include <linux/rcupdate_trace.h>
#include <linux/memcontrol.h>
#include <linux/trace_events.h>
#include <net/netfilter/nf_bpf_link.h>
#include <net/netfilter/nf_bpf_link.h>
#include <net/netkit.h>
#include <net/tcx.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@ -3730,6 +3731,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
return BPF_PROG_TYPE_LSM;
case BPF_TCX_INGRESS:
case BPF_TCX_EGRESS:
case BPF_NETKIT_PRIMARY:
case BPF_NETKIT_PEER:
return BPF_PROG_TYPE_SCHED_CLS;
default:
return BPF_PROG_TYPE_UNSPEC;
@ -3781,7 +3784,9 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
return 0;
case BPF_PROG_TYPE_SCHED_CLS:
if (attach_type != BPF_TCX_INGRESS &&
attach_type != BPF_TCX_EGRESS)
attach_type != BPF_TCX_EGRESS &&
attach_type != BPF_NETKIT_PRIMARY &&
attach_type != BPF_NETKIT_PEER)
return -EINVAL;
return 0;
default:
@ -3864,7 +3869,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ret = cgroup_bpf_prog_attach(attr, ptype, prog);
break;
case BPF_PROG_TYPE_SCHED_CLS:
ret = tcx_prog_attach(attr, prog);
if (attr->attach_type == BPF_TCX_INGRESS ||
attr->attach_type == BPF_TCX_EGRESS)
ret = tcx_prog_attach(attr, prog);
else
ret = netkit_prog_attach(attr, prog);
break;
default:
ret = -EINVAL;
@ -3925,7 +3934,11 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ret = cgroup_bpf_prog_detach(attr, ptype);
break;
case BPF_PROG_TYPE_SCHED_CLS:
ret = tcx_prog_detach(attr, prog);
if (attr->attach_type == BPF_TCX_INGRESS ||
attr->attach_type == BPF_TCX_EGRESS)
ret = tcx_prog_detach(attr, prog);
else
ret = netkit_prog_detach(attr, prog);
break;
default:
ret = -EINVAL;
@ -3992,6 +4005,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_TCX_INGRESS:
case BPF_TCX_EGRESS:
return tcx_prog_query(attr, uattr);
case BPF_NETKIT_PRIMARY:
case BPF_NETKIT_PEER:
return netkit_prog_query(attr, uattr);
default:
return -EINVAL;
}
@ -4973,7 +4989,11 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
ret = bpf_xdp_link_attach(attr, prog);
break;
case BPF_PROG_TYPE_SCHED_CLS:
ret = tcx_link_attach(attr, prog);
if (attr->link_create.attach_type == BPF_TCX_INGRESS ||
attr->link_create.attach_type == BPF_TCX_EGRESS)
ret = tcx_link_attach(attr, prog);
else
ret = netkit_link_attach(attr, prog);
break;
case BPF_PROG_TYPE_NETFILTER:
ret = bpf_nf_link_attach(attr, prog);

8
tools/bpf/bpftool/Documentation/bpftool-net.rst
View File

@ -37,7 +37,7 @@ DESCRIPTION
**bpftool net { show | list }** [ **dev** *NAME* ]
List bpf program attachments in the kernel networking subsystem.
Currently, device driver xdp attachments, tcx and old-style tc
Currently, device driver xdp attachments, tcx, netkit and old-style tc
classifier/action attachments, flow_dissector as well as netfilter
attachments are implemented, i.e., for
program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**,
@ -52,11 +52,11 @@ DESCRIPTION
bpf programs, users should consult other tools, e.g., iproute2.
The current output will start with all xdp program attachments, followed by
all tcx, then tc class/qdisc bpf program attachments, then flow_dissector
and finally netfilter programs. Both xdp programs and tcx/tc programs are
all tcx, netkit, then tc class/qdisc bpf program attachments, then flow_dissector
and finally netfilter programs. Both xdp programs and tcx/netkit/tc programs are
ordered based on ifindex number. If multiple bpf programs attached
to the same networking device through **tc**, the order will be first
all bpf programs attached to tcx, then tc classes, then all bpf programs
all bpf programs attached to tcx, netkit, then tc classes, then all bpf programs
attached to non clsact qdiscs, and finally all bpf programs attached
to root and clsact qdisc.

9
tools/bpf/bpftool/link.c
View File

@ -451,6 +451,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
show_link_ifindex_json(info->tcx.ifindex, json_wtr);
show_link_attach_type_json(info->tcx.attach_type, json_wtr);
break;
case BPF_LINK_TYPE_NETKIT:
show_link_ifindex_json(info->netkit.ifindex, json_wtr);
show_link_attach_type_json(info->netkit.attach_type, json_wtr);
break;
case BPF_LINK_TYPE_XDP:
show_link_ifindex_json(info->xdp.ifindex, json_wtr);
break;
@ -791,6 +795,11 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
show_link_ifindex_plain(info->tcx.ifindex);
show_link_attach_type_plain(info->tcx.attach_type);
break;
case BPF_LINK_TYPE_NETKIT:
printf("\n\t");
show_link_ifindex_plain(info->netkit.ifindex);
show_link_attach_type_plain(info->netkit.attach_type);
break;
case BPF_LINK_TYPE_XDP:
printf("\n\t");
show_link_ifindex_plain(info->xdp.ifindex);

7
tools/bpf/bpftool/net.c
View File

@ -79,6 +79,8 @@ static const char * const attach_type_strings[] = {
static const char * const attach_loc_strings[] = {
[BPF_TCX_INGRESS] = "tcx/ingress",
[BPF_TCX_EGRESS] = "tcx/egress",
[BPF_NETKIT_PRIMARY] = "netkit/primary",
[BPF_NETKIT_PEER] = "netkit/peer",
};
const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings);
@ -506,6 +508,9 @@ static void show_dev_tc_bpf(struct ip_devname_ifindex *dev)
{
__show_dev_tc_bpf(dev, BPF_TCX_INGRESS);
__show_dev_tc_bpf(dev, BPF_TCX_EGRESS);
__show_dev_tc_bpf(dev, BPF_NETKIT_PRIMARY);
__show_dev_tc_bpf(dev, BPF_NETKIT_PEER);
}
static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid,
@ -926,7 +931,7 @@ static int do_help(int argc, char **argv)
" ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n"
" " HELP_SPEC_OPTIONS " }\n"
"\n"
"Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n"
"Note: Only xdp, tcx, tc, netkit, flow_dissector and netfilter attachments\n"
" are currently supported.\n"
" For progs attached to cgroups, use \"bpftool cgroup\"\n"
" to dump program attachments. For program types\n"

14
tools/include/uapi/linux/bpf.h
View File

@ -1052,6 +1052,8 @@ enum bpf_attach_type {
BPF_CGROUP_UNIX_RECVMSG,
BPF_CGROUP_UNIX_GETPEERNAME,
BPF_CGROUP_UNIX_GETSOCKNAME,
BPF_NETKIT_PRIMARY,
BPF_NETKIT_PEER,
__MAX_BPF_ATTACH_TYPE
};
@ -1071,6 +1073,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_NETFILTER = 10,
BPF_LINK_TYPE_TCX = 11,
BPF_LINK_TYPE_UPROBE_MULTI = 12,
BPF_LINK_TYPE_NETKIT = 13,
MAX_BPF_LINK_TYPE,
};
@ -1656,6 +1659,13 @@ union bpf_attr {
__u32 flags;
__u32 pid;
} uprobe_multi;
struct {
union {
__u32 relative_fd;
__u32 relative_id;
};
__u64 expected_revision;
} netkit;
};
} link_create;
@ -6576,6 +6586,10 @@ struct bpf_link_info {
__u32 ifindex;
__u32 attach_type;
} tcx;
struct {
__u32 ifindex;
__u32 attach_type;
} netkit;
};
} __attribute__((aligned(8)));

141
tools/include/uapi/linux/if_link.h
View File

@ -211,6 +211,9 @@ struct rtnl_link_stats {
* @rx_nohandler: Number of packets received on the interface
* but dropped by the networking stack because the device is
* not designated to receive packets (e.g. backup link in a bond).
*
* @rx_otherhost_dropped: Number of packets dropped due to mismatch
* in destination MAC address.
*/
struct rtnl_link_stats64 {
__u64 rx_packets;
@ -243,6 +246,23 @@ struct rtnl_link_stats64 {
__u64 rx_compressed;
__u64 tx_compressed;
__u64 rx_nohandler;
__u64 rx_otherhost_dropped;
};
/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
* for struct rtnl_link_stats64.
*/
struct rtnl_hw_stats64 {
__u64 rx_packets;
__u64 tx_packets;
__u64 rx_bytes;
__u64 tx_bytes;
__u64 rx_errors;
__u64 tx_errors;
__u64 rx_dropped;
__u64 tx_dropped;
__u64 multicast;
};
/* The struct should be in sync with struct ifmap */
@ -350,7 +370,13 @@ enum {
IFLA_GRO_MAX_SIZE,
IFLA_TSO_MAX_SIZE,
IFLA_TSO_MAX_SEGS,
IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */
IFLA_DEVLINK_PORT,
IFLA_GSO_IPV4_MAX_SIZE,
IFLA_GRO_IPV4_MAX_SIZE,
IFLA_DPLL_PIN,
__IFLA_MAX
};
@ -539,6 +565,12 @@ enum {
IFLA_BRPORT_MRP_IN_OPEN,
IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
IFLA_BRPORT_LOCKED,
IFLA_BRPORT_MAB,
IFLA_BRPORT_MCAST_N_GROUPS,
IFLA_BRPORT_MCAST_MAX_GROUPS,
IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
IFLA_BRPORT_BACKUP_NHID,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@ -716,7 +748,79 @@ enum ipvlan_mode {
#define IPVLAN_F_PRIVATE 0x01
#define IPVLAN_F_VEPA 0x02
/* Tunnel RTM header */
struct tunnel_msg {
__u8 family;
__u8 flags;
__u16 reserved2;
__u32 ifindex;
};
/* netkit section */
enum netkit_action {
NETKIT_NEXT = -1,
NETKIT_PASS = 0,
NETKIT_DROP = 2,
NETKIT_REDIRECT = 7,
};
enum netkit_mode {
NETKIT_L2,
NETKIT_L3,
};
enum {
IFLA_NETKIT_UNSPEC,
IFLA_NETKIT_PEER_INFO,
IFLA_NETKIT_PRIMARY,
IFLA_NETKIT_POLICY,
IFLA_NETKIT_PEER_POLICY,
IFLA_NETKIT_MODE,
__IFLA_NETKIT_MAX,
};
#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1)
/* VXLAN section */
/* include statistics in the dump */
#define TUNNEL_MSG_FLAG_STATS 0x01
#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
enum {
VNIFILTER_ENTRY_STATS_UNSPEC,
VNIFILTER_ENTRY_STATS_RX_BYTES,
VNIFILTER_ENTRY_STATS_RX_PKTS,
VNIFILTER_ENTRY_STATS_RX_DROPS,
VNIFILTER_ENTRY_STATS_RX_ERRORS,
VNIFILTER_ENTRY_STATS_TX_BYTES,
VNIFILTER_ENTRY_STATS_TX_PKTS,
VNIFILTER_ENTRY_STATS_TX_DROPS,
VNIFILTER_ENTRY_STATS_TX_ERRORS,
VNIFILTER_ENTRY_STATS_PAD,
__VNIFILTER_ENTRY_STATS_MAX
};
#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
enum {
VXLAN_VNIFILTER_ENTRY_UNSPEC,
VXLAN_VNIFILTER_ENTRY_START,
VXLAN_VNIFILTER_ENTRY_END,
VXLAN_VNIFILTER_ENTRY_GROUP,
VXLAN_VNIFILTER_ENTRY_GROUP6,
VXLAN_VNIFILTER_ENTRY_STATS,
__VXLAN_VNIFILTER_ENTRY_MAX
};
#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1)
enum {
VXLAN_VNIFILTER_UNSPEC,
VXLAN_VNIFILTER_ENTRY,
__VXLAN_VNIFILTER_MAX
};
#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1)
enum {
IFLA_VXLAN_UNSPEC,
IFLA_VXLAN_ID,
@ -748,6 +852,8 @@ enum {
IFLA_VXLAN_GPE,
IFLA_VXLAN_TTL_INHERIT,
IFLA_VXLAN_DF,
IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
IFLA_VXLAN_LOCALBYPASS,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
@ -781,6 +887,7 @@ enum {
IFLA_GENEVE_LABEL,
IFLA_GENEVE_TTL_INHERIT,
IFLA_GENEVE_DF,
IFLA_GENEVE_INNER_PROTO_INHERIT,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
@ -826,6 +933,8 @@ enum {
IFLA_GTP_FD1,
IFLA_GTP_PDP_HASHSIZE,
IFLA_GTP_ROLE,
IFLA_GTP_CREATE_SOCKETS,
IFLA_GTP_RESTART_COUNT,
__IFLA_GTP_MAX,
};
#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@ -1162,6 +1271,17 @@ enum {
#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1))
enum {
IFLA_STATS_GETSET_UNSPEC,
IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
* a filter mask for the corresponding group.
*/
IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
__IFLA_STATS_GETSET_MAX,
};
#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
/* These are embedded into IFLA_STATS_LINK_XSTATS:
* [IFLA_STATS_LINK_XSTATS]
* -> [LINK_XSTATS_TYPE_xxx]
@ -1179,10 +1299,21 @@ enum {
enum {
IFLA_OFFLOAD_XSTATS_UNSPEC,
IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */
IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */
__IFLA_OFFLOAD_XSTATS_MAX
};
#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
enum {
IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */
IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */
__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
};
#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
/* XDP section */
#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
@ -1281,4 +1412,14 @@ enum {
#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
/* DSA section */
enum {
IFLA_DSA_UNSPEC,
IFLA_DSA_MASTER,
__IFLA_DSA_MAX,
};
#define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1)
#endif /* _UAPI_LINUX_IF_LINK_H */

16
tools/lib/bpf/bpf.c
View File

@ -810,6 +810,22 @@ int bpf_link_create(int prog_fd, int target_fd,
if (!OPTS_ZEROED(opts, tcx))
return libbpf_err(-EINVAL);
break;
case BPF_NETKIT_PRIMARY:
case BPF_NETKIT_PEER:
relative_fd = OPTS_GET(opts, netkit.relative_fd, 0);
relative_id = OPTS_GET(opts, netkit.relative_id, 0);
if (relative_fd && relative_id)
return libbpf_err(-EINVAL);
if (relative_id) {
attr.link_create.netkit.relative_id = relative_id;
attr.link_create.flags |= BPF_F_ID;
} else {
attr.link_create.netkit.relative_fd = relative_fd;
}
attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0);
if (!OPTS_ZEROED(opts, netkit))
return libbpf_err(-EINVAL);
break;
default:
if (!OPTS_ZEROED(opts, flags))
return libbpf_err(-EINVAL);

5
tools/lib/bpf/bpf.h
View File

@ -415,6 +415,11 @@ struct bpf_link_create_opts {
__u32 relative_id;
__u64 expected_revision;
} tcx;
struct {
__u32 relative_fd;
__u32 relative_id;
__u64 expected_revision;
} netkit;
};
size_t :0;
};

39
tools/lib/bpf/libbpf.c
View File

@ -126,6 +126,8 @@ static const char * const attach_type_name[] = {
[BPF_TCX_INGRESS] = "tcx_ingress",
[BPF_TCX_EGRESS] = "tcx_egress",
[BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi",
[BPF_NETKIT_PRIMARY] = "netkit_primary",
[BPF_NETKIT_PEER] = "netkit_peer",
};
static const char * const link_type_name[] = {
@ -142,6 +144,7 @@ static const char * const link_type_name[] = {
[BPF_LINK_TYPE_NETFILTER] = "netfilter",
[BPF_LINK_TYPE_TCX] = "tcx",
[BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi",
[BPF_LINK_TYPE_NETKIT] = "netkit",
};
static const char * const map_type_name[] = {
@ -8915,6 +8918,8 @@ static const struct bpf_sec_def section_defs[] = {
SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */
SEC_DEF("netkit/primary", SCHED_CLS, BPF_NETKIT_PRIMARY, SEC_NONE),
SEC_DEF("netkit/peer", SCHED_CLS, BPF_NETKIT_PEER, SEC_NONE),
SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp),
SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp),
SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
@ -12126,6 +12131,40 @@ bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts);
}
struct bpf_link *
bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
const struct bpf_netkit_opts *opts)
{
LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
__u32 relative_id;
int relative_fd;
if (!OPTS_VALID(opts, bpf_netkit_opts))
return libbpf_err_ptr(-EINVAL);
relative_id = OPTS_GET(opts, relative_id, 0);
relative_fd = OPTS_GET(opts, relative_fd, 0);
/* validate we don't have unexpected combinations of non-zero fields */
if (!ifindex) {
pr_warn("prog '%s': target netdevice ifindex cannot be zero\n",
prog->name);
return libbpf_err_ptr(-EINVAL);
}
if (relative_fd && relative_id) {
pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
prog->name);
return libbpf_err_ptr(-EINVAL);
}
link_create_opts.netkit.expected_revision = OPTS_GET(opts, expected_revision, 0);
link_create_opts.netkit.relative_fd = relative_fd;
link_create_opts.netkit.relative_id = relative_id;
link_create_opts.flags = OPTS_GET(opts, flags, 0);
return bpf_program_attach_fd(prog, ifindex, "netkit", &link_create_opts);
}
struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
int target_fd,
const char *attach_func_name)

15
tools/lib/bpf/libbpf.h
View File

@ -800,6 +800,21 @@ LIBBPF_API struct bpf_link *
bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
const struct bpf_tcx_opts *opts);
struct bpf_netkit_opts {
/* size of this struct, for forward/backward compatibility */
size_t sz;
__u32 flags;
__u32 relative_fd;
__u32 relative_id;
__u64 expected_revision;
size_t :0;
};
#define bpf_netkit_opts__last_field expected_revision
LIBBPF_API struct bpf_link *
bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
const struct bpf_netkit_opts *opts);
struct bpf_map;
LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);

1
tools/lib/bpf/libbpf.map
View File

@ -398,6 +398,7 @@ LIBBPF_1.3.0 {
bpf_object__unpin;
bpf_prog_detach_opts;
bpf_program__attach_netfilter;
bpf_program__attach_netkit;
bpf_program__attach_tcx;
bpf_program__attach_uprobe_multi;
ring__avail_data_size;

19
tools/testing/selftests/bpf/Makefile
View File

@ -585,11 +585,20 @@ endef
# Define test_progs test runner.
TRUNNER_TESTS_DIR := prog_tests
TRUNNER_BPF_PROGS_DIR := progs
TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
network_helpers.c testing_helpers.c \
btf_helpers.c flow_dissector_load.h \
cap_helpers.c test_loader.c xsk.c disasm.c \
json_writer.c unpriv_helpers.c \
TRUNNER_EXTRA_SOURCES := test_progs.c \
cgroup_helpers.c \
trace_helpers.c \
network_helpers.c \
testing_helpers.c \
btf_helpers.c \
cap_helpers.c \
unpriv_helpers.c \
netlink_helpers.c \
test_loader.c \
xsk.c \
disasm.c \
json_writer.c \
flow_dissector_load.h \
ip_check_defrag_frags.h
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \
$(OUTPUT)/liburandom_read.so \

1
tools/testing/selftests/bpf/config
View File

@ -71,6 +71,7 @@ CONFIG_NETFILTER_SYNPROXY=y
CONFIG_NETFILTER_XT_CONNMARK=y
CONFIG_NETFILTER_XT_MATCH_STATE=y
CONFIG_NETFILTER_XT_TARGET_CT=y
CONFIG_NETKIT=y
CONFIG_NF_CONNTRACK=y
CONFIG_NF_CONNTRACK_MARK=y
CONFIG_NF_DEFRAG_IPV4=y

358
tools/testing/selftests/bpf/netlink_helpers.c Normal file
View File

@ -0,0 +1,358 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/* Taken & modified from iproute2's libnetlink.c
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>
#include <sys/socket.h>
#include "netlink_helpers.h"
static int rcvbuf = 1024 * 1024;
void rtnl_close(struct rtnl_handle *rth)
{
if (rth->fd >= 0) {
close(rth->fd);
rth->fd = -1;
}
}
int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions,
int protocol)
{
socklen_t addr_len;
int sndbuf = 32768;
int one = 1;
memset(rth, 0, sizeof(*rth));
rth->proto = protocol;
rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol);
if (rth->fd < 0) {
perror("Cannot open netlink socket");
return -1;
}
if (setsockopt(rth->fd, SOL_SOCKET, SO_SNDBUF,
&sndbuf, sizeof(sndbuf)) < 0) {
perror("SO_SNDBUF");
goto err;
}
if (setsockopt(rth->fd, SOL_SOCKET, SO_RCVBUF,
&rcvbuf, sizeof(rcvbuf)) < 0) {
perror("SO_RCVBUF");
goto err;
}
/* Older kernels may no support extended ACK reporting */
setsockopt(rth->fd, SOL_NETLINK, NETLINK_EXT_ACK,
&one, sizeof(one));
memset(&rth->local, 0, sizeof(rth->local));
rth->local.nl_family = AF_NETLINK;
rth->local.nl_groups = subscriptions;
if (bind(rth->fd, (struct sockaddr *)&rth->local,
sizeof(rth->local)) < 0) {
perror("Cannot bind netlink socket");
goto err;
}
addr_len = sizeof(rth->local);
if (getsockname(rth->fd, (struct sockaddr *)&rth->local,
&addr_len) < 0) {
perror("Cannot getsockname");
goto err;
}
if (addr_len != sizeof(rth->local)) {
fprintf(stderr, "Wrong address length %d\n", addr_len);
goto err;
}
if (rth->local.nl_family != AF_NETLINK) {
fprintf(stderr, "Wrong address family %d\n",
rth->local.nl_family);
goto err;
}
rth->seq = time(NULL);
return 0;
err:
rtnl_close(rth);
return -1;
}
int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
{
return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE);
}
static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags)
{
int len;
do {
len = recvmsg(fd, msg, flags);
} while (len < 0 && (errno == EINTR || errno == EAGAIN));
if (len < 0) {
fprintf(stderr, "netlink receive error %s (%d)\n",
strerror(errno), errno);
return -errno;
}
if (len == 0) {
fprintf(stderr, "EOF on netlink\n");
return -ENODATA;
}
return len;
}
static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer)
{
struct iovec *iov = msg->msg_iov;
char *buf;
int len;
iov->iov_base = NULL;
iov->iov_len = 0;
len = __rtnl_recvmsg(fd, msg, MSG_PEEK | MSG_TRUNC);
if (len < 0)
return len;
if (len < 32768)
len = 32768;
buf = malloc(len);
if (!buf) {
fprintf(stderr, "malloc error: not enough buffer\n");
return -ENOMEM;
}
iov->iov_base = buf;
iov->iov_len = len;
len = __rtnl_recvmsg(fd, msg, 0);
if (len < 0) {
free(buf);
return len;
}
if (answer)
*answer = buf;
else
free(buf);
return len;
}
static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err,
nl_ext_ack_fn_t errfn)
{
fprintf(stderr, "RTNETLINK answers: %s\n",
strerror(-err->error));
}
static int __rtnl_talk_iov(struct rtnl_handle *rtnl, struct iovec *iov,
size_t iovlen, struct nlmsghdr **answer,
bool show_rtnl_err, nl_ext_ack_fn_t errfn)
{
struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
struct iovec riov;
struct msghdr msg = {
.msg_name = &nladdr,
.msg_namelen = sizeof(nladdr),
.msg_iov = iov,
.msg_iovlen = iovlen,
};
unsigned int seq = 0;
struct nlmsghdr *h;
int i, status;
char *buf;
for (i = 0; i < iovlen; i++) {
h = iov[i].iov_base;
h->nlmsg_seq = seq = ++rtnl->seq;
if (answer == NULL)
h->nlmsg_flags |= NLM_F_ACK;
}
status = sendmsg(rtnl->fd, &msg, 0);
if (status < 0) {
perror("Cannot talk to rtnetlink");
return -1;
}
/* change msg to use the response iov */
msg.msg_iov = &riov;
msg.msg_iovlen = 1;
i = 0;
while (1) {
next:
status = rtnl_recvmsg(rtnl->fd, &msg, &buf);
++i;
if (status < 0)
return status;
if (msg.msg_namelen != sizeof(nladdr)) {
fprintf(stderr,
"Sender address length == %d!\n",
msg.msg_namelen);
exit(1);
}
for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) {
int len = h->nlmsg_len;
int l = len - sizeof(*h);
if (l < 0 || len > status) {
if (msg.msg_flags & MSG_TRUNC) {
fprintf(stderr, "Truncated message!\n");
free(buf);
return -1;
}
fprintf(stderr,
"Malformed message: len=%d!\n",
len);
exit(1);
}
if (nladdr.nl_pid != 0 ||
h->nlmsg_pid != rtnl->local.nl_pid ||
h->nlmsg_seq > seq || h->nlmsg_seq < seq - iovlen) {
/* Don't forget to skip that message. */
status -= NLMSG_ALIGN(len);
h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
continue;
}
if (h->nlmsg_type == NLMSG_ERROR) {
struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h);
int error = err->error;
if (l < sizeof(struct nlmsgerr)) {
fprintf(stderr, "ERROR truncated\n");
free(buf);
return -1;
}
if (error) {
errno = -error;
if (rtnl->proto != NETLINK_SOCK_DIAG &&
show_rtnl_err)
rtnl_talk_error(h, err, errfn);
}
if (i < iovlen) {
free(buf);
goto next;
}
if (error) {
free(buf);
return -i;
}
if (answer)
*answer = (struct nlmsghdr *)buf;
else
free(buf);
return 0;
}
if (answer) {
*answer = (struct nlmsghdr *)buf;
return 0;
}
fprintf(stderr, "Unexpected reply!\n");
status -= NLMSG_ALIGN(len);
h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
}
free(buf);
if (msg.msg_flags & MSG_TRUNC) {
fprintf(stderr, "Message truncated!\n");
continue;
}
if (status) {
fprintf(stderr, "Remnant of size %d!\n", status);
exit(1);
}
}
}
static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
struct nlmsghdr **answer, bool show_rtnl_err,
nl_ext_ack_fn_t errfn)
{
struct iovec iov = {
.iov_base = n,
.iov_len = n->nlmsg_len,
};
return __rtnl_talk_iov(rtnl, &iov, 1, answer, show_rtnl_err, errfn);
}
int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
struct nlmsghdr **answer)
{
return __rtnl_talk(rtnl, n, answer, true, NULL);
}
int addattr(struct nlmsghdr *n, int maxlen, int type)
{
return addattr_l(n, maxlen, type, NULL, 0);
}
int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data)
{
return addattr_l(n, maxlen, type, &data, sizeof(__u8));
}
int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data)
{
return addattr_l(n, maxlen, type, &data, sizeof(__u16));
}
int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data)
{
return addattr_l(n, maxlen, type, &data, sizeof(__u32));
}
int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data)
{
return addattr_l(n, maxlen, type, &data, sizeof(__u64));
}
int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str)
{
return addattr_l(n, maxlen, type, str, strlen(str)+1);
}
int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data,
int alen)
{
int len = RTA_LENGTH(alen);
struct rtattr *rta;
if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) {
fprintf(stderr, "%s: Message exceeded bound of %d\n",
__func__, maxlen);
return -1;
}
rta = NLMSG_TAIL(n);
rta->rta_type = type;
rta->rta_len = len;
if (alen)
memcpy(RTA_DATA(rta), data, alen);
n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
return 0;
}
int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len)
{
if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) {
fprintf(stderr, "%s: Message exceeded bound of %d\n",
__func__, maxlen);
return -1;
}
memcpy(NLMSG_TAIL(n), data, len);
memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len);
n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len);
return 0;
}
struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type)
{
struct rtattr *nest = NLMSG_TAIL(n);
addattr_l(n, maxlen, type, NULL, 0);
return nest;
}
int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest)
{
nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest;
return n->nlmsg_len;
}

46
tools/testing/selftests/bpf/netlink_helpers.h Normal file
View File

@ -0,0 +1,46 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef NETLINK_HELPERS_H
#define NETLINK_HELPERS_H
#include <string.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
struct rtnl_handle {
int fd;
struct sockaddr_nl local;
struct sockaddr_nl peer;
__u32 seq;
__u32 dump;
int proto;
FILE *dump_fp;
#define RTNL_HANDLE_F_LISTEN_ALL_NSID 0x01
#define RTNL_HANDLE_F_SUPPRESS_NLERR 0x02
#define RTNL_HANDLE_F_STRICT_CHK 0x04
int flags;
};
#define NLMSG_TAIL(nmsg) \
((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len)))
typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
const struct nlmsghdr *inner_nlh);
int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
__attribute__((warn_unused_result));
void rtnl_close(struct rtnl_handle *rth);
int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
struct nlmsghdr **answer)
__attribute__((warn_unused_result));
int addattr(struct nlmsghdr *n, int maxlen, int type);
int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data);
int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data);
int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data);
int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data);
int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen);
int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
#endif /* NETLINK_HELPERS_H */

4
tools/testing/selftests/bpf/prog_tests/tc_helpers.h
View File

@ -4,6 +4,10 @@
#define TC_HELPERS
#include <test_progs.h>
#ifndef loopback
# define loopback 1
#endif
static inline __u32 id_from_prog_fd(int fd)
{
struct bpf_prog_info prog_info = {};

687
tools/testing/selftests/bpf/prog_tests/tc_netkit.c Normal file
View File

@ -0,0 +1,687 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2023 Isovalent */
#include <uapi/linux/if_link.h>
#include <net/if.h>
#include <test_progs.h>
#define netkit_peer "nk0"
#define netkit_name "nk1"
#define ping_addr_neigh 0x0a000002 /* 10.0.0.2 */
#define ping_addr_noneigh 0x0a000003 /* 10.0.0.3 */
#include "test_tc_link.skel.h"
#include "netlink_helpers.h"
#include "tc_helpers.h"
#define ICMP_ECHO 8
struct icmphdr {
__u8 type;
__u8 code;
__sum16 checksum;
struct {
__be16 id;
__be16 sequence;
} echo;
};
struct iplink_req {
struct nlmsghdr n;
struct ifinfomsg i;
char buf[1024];
};
static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
bool same_netns)
{
struct rtnl_handle rth = { .fd = -1 };
struct iplink_req req = {};
struct rtattr *linkinfo, *data;
const char *type = "netkit";
int err;
err = rtnl_open(&rth, 0);
if (!ASSERT_OK(err, "open_rtnetlink"))
return err;
memset(&req, 0, sizeof(req));
req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
req.n.nlmsg_type = RTM_NEWLINK;
req.i.ifi_family = AF_UNSPEC;
addattr_l(&req.n, sizeof(req), IFLA_IFNAME, netkit_name,
strlen(netkit_name));
linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy);
addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy);
addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
addattr_nest_end(&req.n, data);
addattr_nest_end(&req.n, linkinfo);
err = rtnl_talk(&rth, &req.n, NULL);
ASSERT_OK(err, "talk_rtnetlink");
rtnl_close(&rth);
*ifindex = if_nametoindex(netkit_name);
ASSERT_GT(*ifindex, 0, "retrieve_ifindex");
ASSERT_OK(system("ip netns add foo"), "create netns");
ASSERT_OK(system("ip link set dev " netkit_name " up"),
"up primary");
ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"),
"addr primary");
if (same_netns) {
ASSERT_OK(system("ip link set dev " netkit_peer " up"),
"up peer");
ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"),
"addr peer");
} else {
ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
"move peer");
ASSERT_OK(system("ip netns exec foo ip link set dev "
netkit_peer " up"), "up peer");
ASSERT_OK(system("ip netns exec foo ip addr add dev "
netkit_peer " 10.0.0.2/24"), "addr peer");
}
return err;
}
static void destroy_netkit(void)
{
ASSERT_OK(system("ip link del dev " netkit_name), "del primary");
ASSERT_OK(system("ip netns del foo"), "delete netns");
ASSERT_EQ(if_nametoindex(netkit_name), 0, netkit_name "_ifindex");
}
static int __send_icmp(__u32 dest)
{
struct sockaddr_in addr;
struct icmphdr icmp;
int sock, ret;
ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0");
if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)"))
return ret;
sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP);
if (!ASSERT_GE(sock, 0, "icmp_socket"))
return -errno;
ret = setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
netkit_name, strlen(netkit_name) + 1);
if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)"))
goto out;
memset(&addr, 0, sizeof(addr));
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = htonl(dest);
memset(&icmp, 0, sizeof(icmp));
icmp.type = ICMP_ECHO;
icmp.echo.id = 1234;
icmp.echo.sequence = 1;
ret = sendto(sock, &icmp, sizeof(icmp), 0,
(struct sockaddr *)&addr, sizeof(addr));
if (!ASSERT_GE(ret, 0, "icmp_sendto"))
ret = -errno;
else
ret = 0;
out:
close(sock);
return ret;
}
static int send_icmp(void)
{
return __send_icmp(ping_addr_neigh);
}
void serial_test_tc_netkit_basic(void)
{
LIBBPF_OPTS(bpf_prog_query_opts, optq);
LIBBPF_OPTS(bpf_netkit_opts, optl);
__u32 prog_ids[2], link_ids[2];
__u32 pid1, pid2, lid1, lid2;
struct test_tc_link *skel;
struct bpf_link *link;
int err, ifindex;
err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
&ifindex, false);
if (err)
return;
skel = test_tc_link__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
goto cleanup;
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
BPF_NETKIT_PEER), 0, "tc2_attach_type");
err = test_tc_link__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc1 = link;
lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
optq.prog_ids = prog_ids;
optq.link_ids = link_ids;
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc2 = link;
lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 1);
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PEER, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
cleanup:
test_tc_link__destroy(skel);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
destroy_netkit();
}
static void serial_test_tc_netkit_multi_links_target(int mode, int target)
{
LIBBPF_OPTS(bpf_prog_query_opts, optq);
LIBBPF_OPTS(bpf_netkit_opts, optl);
__u32 prog_ids[3], link_ids[3];
__u32 pid1, pid2, lid1, lid2;
struct test_tc_link *skel;
struct bpf_link *link;
int err, ifindex;
err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
&ifindex, false);
if (err)
return;
skel = test_tc_link__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
goto cleanup;
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
target), 0, "tc1_attach_type");
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
target), 0, "tc2_attach_type");
err = test_tc_link__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
assert_mprog_count_ifindex(ifindex, target, 0);
ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc1 = link;
lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
assert_mprog_count_ifindex(ifindex, target, 1);
optq.prog_ids = prog_ids;
optq.link_ids = link_ids;
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, target, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
LIBBPF_OPTS_RESET(optl,
.flags = BPF_F_BEFORE,
.relative_fd = bpf_program__fd(skel->progs.tc1),
);
link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc2 = link;
lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
assert_mprog_count_ifindex(ifindex, target, 2);
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, target, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 2, "count");
ASSERT_EQ(optq.revision, 3, "revision");
ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
cleanup:
test_tc_link__destroy(skel);
assert_mprog_count_ifindex(ifindex, target, 0);
destroy_netkit();
}
void serial_test_tc_netkit_multi_links(void)
{
serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PEER);
serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PEER);
}
static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
{
LIBBPF_OPTS(bpf_prog_attach_opts, opta);
LIBBPF_OPTS(bpf_prog_detach_opts, optd);
LIBBPF_OPTS(bpf_prog_query_opts, optq);
__u32 pid1, pid2, fd1, fd2;
__u32 prog_ids[3];
struct test_tc_link *skel;
int err, ifindex;
err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
&ifindex, false);
if (err)
return;
skel = test_tc_link__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_load"))
goto cleanup;
fd1 = bpf_program__fd(skel->progs.tc1);
fd2 = bpf_program__fd(skel->progs.tc2);
pid1 = id_from_prog_fd(fd1);
pid2 = id_from_prog_fd(fd2);
ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
assert_mprog_count_ifindex(ifindex, target, 0);
ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
err = bpf_prog_attach_opts(fd1, ifindex, target, &opta);
if (!ASSERT_EQ(err, 0, "prog_attach"))
goto cleanup;
assert_mprog_count_ifindex(ifindex, target, 1);
optq.prog_ids = prog_ids;
memset(prog_ids, 0, sizeof(prog_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, target, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup_fd1;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
LIBBPF_OPTS_RESET(opta,
.flags = BPF_F_BEFORE,
.relative_fd = fd1,
);
err = bpf_prog_attach_opts(fd2, ifindex, target, &opta);
if (!ASSERT_EQ(err, 0, "prog_attach"))
goto cleanup_fd1;
assert_mprog_count_ifindex(ifindex, target, 2);
memset(prog_ids, 0, sizeof(prog_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, target, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup_fd2;
ASSERT_EQ(optq.count, 2, "count");
ASSERT_EQ(optq.revision, 3, "revision");
ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
cleanup_fd2:
err = bpf_prog_detach_opts(fd2, ifindex, target, &optd);
ASSERT_OK(err, "prog_detach");
assert_mprog_count_ifindex(ifindex, target, 1);
cleanup_fd1:
err = bpf_prog_detach_opts(fd1, ifindex, target, &optd);
ASSERT_OK(err, "prog_detach");
assert_mprog_count_ifindex(ifindex, target, 0);
cleanup:
test_tc_link__destroy(skel);
assert_mprog_count_ifindex(ifindex, target, 0);
destroy_netkit();
}
void serial_test_tc_netkit_multi_opts(void)
{
serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PEER);
serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PEER);
}
void serial_test_tc_netkit_device(void)
{
LIBBPF_OPTS(bpf_prog_query_opts, optq);
LIBBPF_OPTS(bpf_netkit_opts, optl);
__u32 prog_ids[2], link_ids[2];
__u32 pid1, pid2, lid1;
struct test_tc_link *skel;
struct bpf_link *link;
int err, ifindex, ifindex2;
err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
&ifindex, true);
if (err)
return;
ifindex2 = if_nametoindex(netkit_peer);
ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
skel = test_tc_link__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
goto cleanup;
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
BPF_NETKIT_PEER), 0, "tc2_attach_type");
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3,
BPF_NETKIT_PRIMARY), 0, "tc3_attach_type");
err = test_tc_link__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc1 = link;
lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
optq.prog_ids = prog_ids;
optq.link_ids = link_ids;
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PRIMARY, &optq);
ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PEER, &optq);
ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
link = bpf_program__attach_netkit(skel->progs.tc2, ifindex2, &optl);
if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
bpf_link__destroy(link);
goto cleanup;
}
link = bpf_program__attach_netkit(skel->progs.tc3, ifindex2, &optl);
if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
bpf_link__destroy(link);
goto cleanup;
}
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
cleanup:
test_tc_link__destroy(skel);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
destroy_netkit();
}
static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
{
LIBBPF_OPTS(bpf_prog_query_opts, optq);
LIBBPF_OPTS(bpf_netkit_opts, optl);
__u32 prog_ids[2], link_ids[2];
__u32 pid1, lid1;
struct test_tc_link *skel;
struct bpf_link *link;
int err, ifindex;
err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
&ifindex, false);
if (err)
return;
skel = test_tc_link__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
goto cleanup;
ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
err = test_tc_link__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
assert_mprog_count_ifindex(ifindex, target, 0);
ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
if (!ASSERT_OK_PTR(link, "link_attach"))
goto cleanup;
skel->links.tc1 = link;
lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
assert_mprog_count_ifindex(ifindex, target, 1);
optq.prog_ids = prog_ids;
optq.link_ids = link_ids;
memset(prog_ids, 0, sizeof(prog_ids));
memset(link_ids, 0, sizeof(link_ids));
optq.count = ARRAY_SIZE(prog_ids);
err = bpf_prog_query_opts(ifindex, target, &optq);
if (!ASSERT_OK(err, "prog_query"))
goto cleanup;
ASSERT_EQ(optq.count, 1, "count");
ASSERT_EQ(optq.revision, 2, "revision");
ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
tc_skel_reset_all_seen(skel);
ASSERT_EQ(__send_icmp(ping_addr_noneigh), 0, "icmp_pkt");
ASSERT_EQ(skel->bss->seen_tc1, true /* L2: ARP */, "seen_tc1");
ASSERT_EQ(skel->bss->seen_eth, mode == NETKIT_L3, "seen_eth");
cleanup:
test_tc_link__destroy(skel);
assert_mprog_count_ifindex(ifindex, target, 0);
destroy_netkit();
}
void serial_test_tc_netkit_neigh_links(void)
{
serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
}

13
tools/testing/selftests/bpf/progs/test_tc_link.c
View File

@ -1,7 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2023 Isovalent */
#include <stdbool.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>
char LICENSE[] SEC("license") = "GPL";
@ -12,10 +16,19 @@ bool seen_tc3;
bool seen_tc4;
bool seen_tc5;
bool seen_tc6;
bool seen_eth;
SEC("tc/ingress")
int tc1(struct __sk_buff *skb)
{
struct ethhdr eth = {};
if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
goto out;
if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
goto out;
seen_eth = eth.h_proto == bpf_htons(ETH_P_IP);
out:
seen_tc1 = true;
return TCX_NEXT;
}