Merge branch 'net-notify-users-when-an-iface-cannot-change-its-netns'

Nicolas Dichtel says:

====================
net: notify users when an iface cannot change its netns

This series adds a way to see if an interface cannot be moved to another netns.

 Documentation/netlink/specs/rt_link.yaml           |  3 ++
 .../networking/net_cachelines/net_device.rst       |  2 +-
 Documentation/networking/switchdev.rst             |  2 +-
 drivers/net/amt.c                                  |  2 +-
 drivers/net/bonding/bond_main.c                    |  2 +-
 drivers/net/ethernet/adi/adin1110.c                |  2 +-
 .../net/ethernet/marvell/prestera/prestera_main.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  2 +-
 drivers/net/ethernet/rocker/rocker_main.c          |  2 +-
 drivers/net/ethernet/ti/cpsw_new.c                 |  2 +-
 drivers/net/loopback.c                             |  2 +-
 drivers/net/net_failover.c                         |  2 +-
 drivers/net/team/team_core.c                       |  2 +-
 drivers/net/vrf.c                                  |  2 +-
 include/linux/netdevice.h                          |  9 +++--
 include/uapi/linux/if_link.h                       |  1 +
 net/batman-adv/soft-interface.c                    |  2 +-
 net/bridge/br_device.c                             |  2 +-
 net/core/dev.c                                     | 45 +++++++++++++++++-----
 net/core/rtnetlink.c                               |  5 ++-
 net/hsr/hsr_device.c                               |  2 +-
 net/ieee802154/6lowpan/core.c                      |  2 +-
 net/ieee802154/core.c                              | 10 ++---
 net/ipv4/ip_tunnel.c                               |  2 +-
 net/ipv4/ipmr.c                                    |  2 +-
 net/ipv6/ip6_gre.c                                 |  2 +-
 net/ipv6/ip6_tunnel.c                              |  2 +-
 net/ipv6/ip6mr.c                                   |  2 +-
 net/ipv6/sit.c                                     |  2 +-
 net/openvswitch/vport-internal_dev.c               |  2 +-
 net/wireless/core.c                                | 10 ++---
 tools/testing/selftests/net/forwarding/README      |  2 +-
 34 files changed, 86 insertions(+), 53 deletions(-)

Comments are welcome.

Regards,
Nicolas
====================

Link: https://patch.msgid.link/20250228102144.154802-1-nicolas.dichtel@6wind.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This commit is contained in:
Paolo Abeni 2025-03-04 12:44:51 +01:00
commit 265e352b6c
34 changed files with 86 additions and 53 deletions

View File

@ -1160,6 +1160,9 @@ attribute-sets:
name: max-pacing-offload-horizon
type: uint
doc: EDT offload horizon supported by the device (in nsec).
-
name: netns-immutable
type: u8
-
name: af-spec-attrs
attributes:

View File

@ -167,7 +167,7 @@ unsigned:1 wol_enabled
unsigned:1 threaded napi_poll(napi_enable,dev_set_threaded)
unsigned_long:1 see_all_hwtstamp_requests
unsigned_long:1 change_proto_down
unsigned_long:1 netns_local
unsigned_long:1 netns_immutable
unsigned_long:1 fcoe_mtu
struct list_head net_notifier_list
struct macsec_ops* macsec_ops

View File

@ -137,7 +137,7 @@ would be sub-port 0 on port 1 on switch 1.
Port Features
^^^^^^^^^^^^^
dev->netns_local
dev->netns_immutable
If the switchdev driver (and device) only supports offloading of the default
network namespace (netns), the driver should set this private flag to prevent

View File

@ -3099,7 +3099,7 @@ static void amt_link_setup(struct net_device *dev)
dev->addr_len = 0;
dev->priv_flags |= IFF_NO_QUEUE;
dev->lltx = true;
dev->netns_local = true;
dev->netns_immutable = true;
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM;
dev->hw_features |= NETIF_F_FRAGLIST | NETIF_F_RXCSUM;

View File

@ -6025,7 +6025,7 @@ void bond_setup(struct net_device *bond_dev)
bond_dev->lltx = true;
/* Don't allow bond devices to change network namespaces. */
bond_dev->netns_local = true;
bond_dev->netns_immutable = true;
/* By default, we declare the bond to be fully
* VLAN hardware accelerated capable. Special

View File

@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
netdev->netdev_ops = &adin1110_netdev_ops;
netdev->ethtool_ops = &adin1110_ethtool_ops;
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->netns_local = true;
netdev->netns_immutable = true;
port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false);
if (IS_ERR(port_priv->phydev)) {

View File

@ -634,7 +634,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
goto err_dl_port_register;
dev->features |= NETIF_F_HW_TC;
dev->netns_local = true;
dev->netns_immutable = true;
dev->netdev_ops = &prestera_netdev_ops;
dev->ethtool_ops = &prestera_ethtool_ops;
SET_NETDEV_DEV(dev, sw->dev->dev);

View File

@ -4423,9 +4423,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
if (mlx5e_is_uplink_rep(priv)) {
features = mlx5e_fix_uplink_rep_features(netdev, features);
netdev->netns_local = true;
netdev->netns_immutable = true;
} else {
netdev->netns_local = false;
netdev->netns_immutable = false;
}
mutex_unlock(&priv->state_lock);

View File

@ -905,7 +905,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
netdev->features |= netdev->hw_features;
netdev->netns_local = true;
netdev->netns_immutable = true;
}
static int mlx5e_init_rep(struct mlx5_core_dev *mdev,

View File

@ -1579,7 +1579,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
dev->lltx = true;
dev->netns_local = true;
dev->netns_immutable = true;
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;

View File

@ -2576,7 +2576,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
rocker_carrier_init(rocker_port);
dev->features |= NETIF_F_SG;
dev->netns_local = true;
dev->netns_immutable = true;
/* MTU range: 68 - 9000 */
dev->min_mtu = ROCKER_PORT_MIN_MTU;

View File

@ -1409,7 +1409,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC;
ndev->netns_local = true;
ndev->netns_immutable = true;
ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
NETDEV_XDP_ACT_REDIRECT |

View File

@ -172,7 +172,7 @@ static void gen_lo_setup(struct net_device *dev,
dev->flags = IFF_LOOPBACK;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
dev->lltx = true;
dev->netns_local = true;
dev->netns_immutable = true;
netif_keep_dst(dev);
dev->hw_features = NETIF_F_GSO_SOFTWARE;
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST

View File

@ -734,7 +734,7 @@ struct failover *net_failover_create(struct net_device *standby_dev)
failover_dev->lltx = true;
/* Don't allow failover devices to change network namespaces. */
failover_dev->netns_local = true;
failover_dev->netns_immutable = true;
failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
NETIF_F_HW_VLAN_CTAG_TX |

View File

@ -2203,7 +2203,7 @@ static void team_setup(struct net_device *dev)
dev->lltx = true;
/* Don't allow team devices to change network namespaces. */
dev->netns_local = true;
dev->netns_immutable = true;
dev->features |= NETIF_F_GRO;

View File

@ -1617,7 +1617,7 @@ static void vrf_setup(struct net_device *dev)
dev->lltx = true;
/* don't allow vrf devices to change network namespaces. */
dev->netns_local = true;
dev->netns_immutable = true;
/* does not make sense for a VLAN to be added to a vrf device */
dev->features |= NETIF_F_VLAN_CHALLENGED;

View File

@ -2021,7 +2021,7 @@ enum netdev_reg_state {
* regardless of source, even if those aren't
* HWTSTAMP_SOURCE_NETDEV
* @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
* @netns_local: interface can't change network namespaces
* @netns_immutable: interface can't change network namespaces
* @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes
*
* @net_notifier_list: List of per-net netdev notifier block
@ -2429,7 +2429,7 @@ struct net_device {
/* priv_flags_slow, ungrouped to save space */
unsigned long see_all_hwtstamp_requests:1;
unsigned long change_proto_down:1;
unsigned long netns_local:1;
unsigned long netns_immutable:1;
unsigned long fcoe_mtu:1;
struct list_head net_notifier_list;
@ -4191,12 +4191,13 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
int dev_set_alias(struct net_device *, const char *, size_t);
int dev_get_alias(const struct net_device *, char *, size_t);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex);
const char *pat, int new_ifindex,
struct netlink_ext_ack *extack);
static inline
int dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat)
{
return __dev_change_net_namespace(dev, net, pat, 0);
return __dev_change_net_namespace(dev, net, pat, 0, NULL);
}
int __dev_set_mtu(struct net_device *, int);
int dev_set_mtu(struct net_device *, int);

View File

@ -378,6 +378,7 @@ enum {
IFLA_GRO_IPV4_MAX_SIZE,
IFLA_DPLL_PIN,
IFLA_MAX_PACING_OFFLOAD_HORIZON,
IFLA_NETNS_IMMUTABLE,
__IFLA_MAX
};

View File

@ -1037,7 +1037,7 @@ static void batadv_softif_init_early(struct net_device *dev)
dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
dev->priv_flags |= IFF_NO_QUEUE;
dev->lltx = true;
dev->netns_local = true;
dev->netns_immutable = true;
/* can't call min_mtu, because the needed variables
* have not been initialized yet

View File

@ -488,7 +488,7 @@ void br_dev_setup(struct net_device *dev)
SET_NETDEV_DEVTYPE(dev, &br_type);
dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
dev->lltx = true;
dev->netns_local = true;
dev->netns_immutable = true;
dev->features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;

View File

@ -12131,6 +12131,7 @@ EXPORT_SYMBOL(unregister_netdev);
* is already taken in the destination network namespace.
* @new_ifindex: If not zero, specifies device index in the target
* namespace.
* @extack: netlink extended ack
*
* This function shuts down a device interface and moves it
* to a new network namespace. On success 0 is returned, on
@ -12140,7 +12141,8 @@ EXPORT_SYMBOL(unregister_netdev);
*/
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex)
const char *pat, int new_ifindex,
struct netlink_ext_ack *extack)
{
struct netdev_name_node *name_node;
struct net *net_old = dev_net(dev);
@ -12151,12 +12153,16 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
/* Don't allow namespace local devices to be moved. */
err = -EINVAL;
if (dev->netns_local)
if (dev->netns_immutable) {
NL_SET_ERR_MSG(extack, "The interface netns is immutable");
goto out;
}
/* Ensure the device has been registered */
if (dev->reg_state != NETREG_REGISTERED)
if (dev->reg_state != NETREG_REGISTERED) {
NL_SET_ERR_MSG(extack, "The interface isn't registered");
goto out;
}
/* Get out if there is nothing todo */
err = 0;
@ -12169,30 +12175,49 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
err = -EEXIST;
if (netdev_name_in_use(net, dev->name)) {
/* We get here if we can't use the current device name */
if (!pat)
if (!pat) {
NL_SET_ERR_MSG(extack,
"An interface with the same name exists in the target netns");
goto out;
}
err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST);
if (err < 0)
if (err < 0) {
NL_SET_ERR_MSG_FMT(extack,
"Unable to use '%s' for the new interface name in the target netns",
pat);
goto out;
}
}
/* Check that none of the altnames conflicts. */
err = -EEXIST;
netdev_for_each_altname(dev, name_node)
if (netdev_name_in_use(net, name_node->name))
netdev_for_each_altname(dev, name_node) {
if (netdev_name_in_use(net, name_node->name)) {
NL_SET_ERR_MSG_FMT(extack,
"An interface with the altname %s exists in the target netns",
name_node->name);
goto out;
}
}
/* Check that new_ifindex isn't used yet. */
if (new_ifindex) {
err = dev_index_reserve(net, new_ifindex);
if (err < 0)
if (err < 0) {
NL_SET_ERR_MSG_FMT(extack,
"The ifindex %d is not available in the target netns",
new_ifindex);
goto out;
}
} else {
/* If there is an ifindex conflict assign a new one */
err = dev_index_reserve(net, dev->ifindex);
if (err == -EBUSY)
err = dev_index_reserve(net, 0);
if (err < 0)
if (err < 0) {
NL_SET_ERR_MSG(extack,
"Unable to allocate a new ifindex in the target netns");
goto out;
}
new_ifindex = err;
}
@ -12533,7 +12558,7 @@ static void __net_exit default_device_exit_net(struct net *net)
char fb_name[IFNAMSIZ];
/* Ignore unmoveable devices (i.e. loopback) */
if (dev->netns_local)
if (dev->netns_immutable)
continue;
/* Leave virtual devices for the generic cleanup */

View File

@ -1292,6 +1292,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(1) /* IFLA_NETNS_IMMUTABLE */
+ nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+ nla_total_size(4) /* IFLA_LINK_NETNSID */
+ nla_total_size(4) /* IFLA_GROUP */
@ -2046,6 +2047,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
netif_running(dev) ? READ_ONCE(dev->operstate) :
IF_OPER_DOWN) ||
nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) ||
nla_put_u8(skb, IFLA_NETNS_IMMUTABLE, dev->netns_immutable) ||
nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) ||
nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) ||
nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) ||
@ -2234,6 +2236,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_ALLMULTI] = { .type = NLA_REJECT },
[IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
[IFLA_NETNS_IMMUTABLE] = { .type = NLA_REJECT },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@ -3025,7 +3028,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex);
err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex, extack);
if (err)
goto errout;

View File

@ -643,7 +643,7 @@ void hsr_dev_setup(struct net_device *dev)
/* Not sure about this. Taken from bridge code. netdevice.h says
* it means "Does not change network namespaces".
*/
dev->netns_local = true;
dev->netns_immutable = true;
dev->needs_free_netdev = true;

View File

@ -116,7 +116,7 @@ static void lowpan_setup(struct net_device *ldev)
ldev->netdev_ops = &lowpan_netdev_ops;
ldev->header_ops = &lowpan_header_ops;
ldev->needs_free_netdev = true;
ldev->netns_local = true;
ldev->netns_immutable = true;
}
static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[],

View File

@ -226,11 +226,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) {
if (!wpan_dev->netdev)
continue;
wpan_dev->netdev->netns_local = false;
wpan_dev->netdev->netns_immutable = false;
err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d");
if (err)
break;
wpan_dev->netdev->netns_local = true;
wpan_dev->netdev->netns_immutable = true;
}
if (err) {
@ -242,11 +242,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
list) {
if (!wpan_dev->netdev)
continue;
wpan_dev->netdev->netns_local = false;
wpan_dev->netdev->netns_immutable = false;
err = dev_change_net_namespace(wpan_dev->netdev, net,
"wpan%d");
WARN_ON(err);
wpan_dev->netdev->netns_local = true;
wpan_dev->netdev->netns_immutable = true;
}
return err;
@ -291,7 +291,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
switch (state) {
/* TODO NETDEV_DEVTYPE */
case NETDEV_REGISTER:
dev->netns_local = true;
dev->netns_immutable = true;
wpan_dev->identifier = ++rdev->wpan_dev_id;
list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
rdev->devlist_generation++;

View File

@ -1162,7 +1162,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
* Allowing to move it to another netns is clearly unsafe.
*/
if (!IS_ERR(itn->fb_tunnel_dev)) {
itn->fb_tunnel_dev->netns_local = true;
itn->fb_tunnel_dev->netns_immutable = true;
itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
itn->type = itn->fb_tunnel_dev->type;

View File

@ -563,7 +563,7 @@ static void reg_vif_setup(struct net_device *dev)
dev->flags = IFF_NOARP;
dev->netdev_ops = &reg_vif_netdev_ops;
dev->needs_free_netdev = true;
dev->netns_local = true;
dev->netns_immutable = true;
}
static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)

View File

@ -1620,7 +1620,7 @@ static int __net_init ip6gre_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
ign->fb_tunnel_dev->netns_local = true;
ign->fb_tunnel_dev->netns_immutable = true;
ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;

View File

@ -2265,7 +2265,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
ip6n->fb_tnl_dev->netns_local = true;
ip6n->fb_tnl_dev->netns_immutable = true;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)

View File

@ -668,7 +668,7 @@ static void reg_vif_setup(struct net_device *dev)
dev->flags = IFF_NOARP;
dev->netdev_ops = &reg_vif_netdev_ops;
dev->needs_free_netdev = true;
dev->netns_local = true;
dev->netns_immutable = true;
}
static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)

View File

@ -1859,7 +1859,7 @@ static int __net_init sit_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
sitn->fb_tunnel_dev->netns_local = true;
sitn->fb_tunnel_dev->netns_immutable = true;
t = netdev_priv(sitn->fb_tunnel_dev);
t->net = net;

View File

@ -149,7 +149,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
/* Restrict bridge port to current netns. */
if (vport->port_no == OVSP_LOCAL)
vport->dev->netns_local = true;
vport->dev->netns_immutable = true;
rtnl_lock();
err = register_netdevice(vport->dev);

View File

@ -162,11 +162,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
if (!wdev->netdev)
continue;
wdev->netdev->netns_local = false;
wdev->netdev->netns_immutable = false;
err = dev_change_net_namespace(wdev->netdev, net, "wlan%d");
if (err)
break;
wdev->netdev->netns_local = true;
wdev->netdev->netns_immutable = true;
}
if (err) {
@ -178,11 +178,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
list) {
if (!wdev->netdev)
continue;
wdev->netdev->netns_local = false;
wdev->netdev->netns_immutable = false;
err = dev_change_net_namespace(wdev->netdev, net,
"wlan%d");
WARN_ON(err);
wdev->netdev->netns_local = true;
wdev->netdev->netns_immutable = true;
}
return err;
@ -1513,7 +1513,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
SET_NETDEV_DEVTYPE(dev, &wiphy_type);
wdev->netdev = dev;
/* can only change netns with wiphy */
dev->netns_local = true;
dev->netns_immutable = true;
cfg80211_init_wdev(wdev);
break;

View File

@ -6,7 +6,7 @@ to easily create and test complex environments.
Unfortunately, these namespaces can not be used with actual switching
ASICs, as their ports can not be migrated to other network namespaces
(dev->netns_local) and most of them probably do not support the
(dev->netns_immutable) and most of them probably do not support the
L1-separation provided by namespaces.
However, a similar kind of flexibility can be achieved by using VRFs and