ipv4: centralize devconf sysctl handling
Subsystems (4)
PATCH v5 1/3 ipv4: centralize devconf sysctl handling
The logic for handling IPv4 devconf sysctls is scattered. Notification and cache flushes are managed in devinet_conf_proc(), while a separate ipv4_doint_and_flush() function and DEVINET_SYSCTL_FLUSHING_ENTRY macro is used for properties that solely require a cache flush.
This patch refactors the sysctl handling by introducing a centralized helper, devinet_conf_post_set(). This new function evaluates the changed attribute and handles all necessary operations like triggering netlink notifications. It returns a boolean indicating whether a routing cache flush is required.
Note that the boolean is necessary as this function will be re-used for netlink IPv4 devconf handling where the cache flushing must wait until all the attributes have been processed.
Finally, this is introducing a small change in behavior for IPV4_DEVCONF_ROUTE_LOCALNET. As commit d0daebc3d622 ("ipv4: Add interface option to enable routing of 127.0.0.0/8") intended, the cache flush should only be performed when ROUTE_LOCALNET changes from 1 to 0. Unfortunately, this was not true because while implementing it the DEVINET_SYSCTL_FLUSHING_ENTRY was used for the attribute, making the code related to it on devinet_conf_proc() dead.
IPV4_DEVCONF_FORWARDING is still being handled separately as it requires more operations.
---
v2: no changes
v3: no changes
v4: no changes
v5: no changes
--- net/ipv4/devinet.c | 127 ++++++++++++++++++++++++--------------------- 1 file changed, 68 insertions(+), 59 deletions(-)
net/ipv4/devinet.c +68 -59
@@ -2128,6 +2128,46 @@ static int inet_validate_link_af(const struct net_device *dev,return 0 ; } +static bool devinet_conf_post_set (struct net *net,struct ipv4_devconf *cnf, +int attr,int new,int old,int ifindex) +{ +if (new == old) +return false; + +switch (attr) { +case IPV4_DEVCONF_ROUTE_LOCALNET : +case IPV4_DEVCONF_ACCEPT_LOCAL : +if (new ==0 ) +return true; +break ; +case IPV4_DEVCONF_NOXFRM : +case IPV4_DEVCONF_NOPOLICY : +case IPV4_DEVCONF_PROMOTE_SECONDARIES : +case IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST : +case IPV4_DEVCONF_BC_FORWARDING : +return true; +case IPV4_DEVCONF_RP_FILTER : +inet_netconf_notify_devconf (net,RTM_NEWNETCONF , +NETCONFA_RP_FILTER , + ifindex, cnf); +break ; +case IPV4_DEVCONF_PROXY_ARP : +inet_netconf_notify_devconf (net,RTM_NEWNETCONF , +NETCONFA_PROXY_NEIGH , + ifindex, cnf); +break ; +case IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN : +inet_netconf_notify_devconf (net,RTM_NEWNETCONF , +NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN , + ifindex, cnf); +break ; +default : +break ; + } + +return false; +} +static int inet_set_link_af (struct net_device *dev,const struct nlattr *nla,struct netlink_ext_ack *extack) {
@@ -2509,44 +2549,31 @@ static int devinet_conf_proc(const struct ctl_table *ctl, int write,if (write) {struct ipv4_devconf *cnf = ctl->extra1; -struct net *net = ctl->extra2;int i = (int *)ctl->data - cnf->data; +struct net *net = ctl->extra2;int ifindex; -set_bit (i, cnf->state); - -if (cnf == net->ipv4.devconf_dflt) -devinet_copy_dflt_conf (net, i); -if (i ==IPV4_DEVCONF_ACCEPT_LOCAL -1 || - i ==IPV4_DEVCONF_ROUTE_LOCALNET -1 ) -if ((new_value ==0 ) && (old_value !=0 )) -rt_cache_flush (net); +/* These attributes are bypassing the tracking state, +* for the rest track the state and propagate the changes +* to default config +*/ +switch (i +1 ) { +case IPV4_DEVCONF_NOXFRM : +case IPV4_DEVCONF_NOPOLICY : +case IPV4_DEVCONF_PROMOTE_SECONDARIES : +case IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST : +break ; +default : +set_bit (i, cnf->state); +if (cnf == net->ipv4.devconf_dflt) +devinet_copy_dflt_conf (net, i); +break ; + } -if (i ==IPV4_DEVCONF_BC_FORWARDING -1 && - new_value != old_value) + ifindex =devinet_conf_ifindex (net, cnf); +if (devinet_conf_post_set (net, cnf, i +1 , new_value, + old_value, ifindex))rt_cache_flush (net); - -if (i ==IPV4_DEVCONF_RP_FILTER -1 && - new_value != old_value) { - ifindex =devinet_conf_ifindex (net, cnf); -inet_netconf_notify_devconf (net,RTM_NEWNETCONF , -NETCONFA_RP_FILTER , - ifindex, cnf); - } -if (i ==IPV4_DEVCONF_PROXY_ARP -1 && - new_value != old_value) { - ifindex =devinet_conf_ifindex (net, cnf); -inet_netconf_notify_devconf (net,RTM_NEWNETCONF , -NETCONFA_PROXY_NEIGH , - ifindex, cnf); - } -if (i ==IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN -1 && - new_value != old_value) { - ifindex =devinet_conf_ifindex (net, cnf); -inet_netconf_notify_devconf (net,RTM_NEWNETCONF , -NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN , - ifindex, cnf); - } }return ret;
@@ -2599,20 +2626,6 @@ static int devinet_sysctl_forward(const struct ctl_table *ctl, int write,return ret; } -static int ipv4_doint_and_flush (const struct ctl_table *ctl,int write, -void *buffer,size_t *lenp,loff_t *ppos) -{ -int *valp = ctl->data; -int val = *valp; -int ret =proc_dointvec (ctl, write, buffer, lenp, ppos); -struct net *net = ctl->extra2; - -if (write && *valp != val) -rt_cache_flush (net); - -return ret; -} -#define DEVINET_SYSCTL_ENTRY (attr, name, mval, proc) \ { \ .procname = name, \
@@ -2633,9 +2646,6 @@ static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write,#define DEVINET_SYSCTL_COMPLEX_ENTRY (attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) -#define DEVINET_SYSCTL_FLUSHING_ENTRY (attr, name) \ - DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) - static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[IPV4_DEVCONF_MAX];
@@ -2678,15 +2688,14 @@ static struct devinet_sysctl_table { "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), - - DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), - DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), - DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, - "promote_secondaries"), - DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, - "route_localnet"), -DEVINET_SYSCTL_FLUSHING_ENTRY (DROP_UNICAST_IN_L2_MULTICAST , - "drop_unicast_in_l2_multicast"), + DEVINET_SYSCTL_RW_ENTRY(NOXFRM, "disable_xfrm"), + DEVINET_SYSCTL_RW_ENTRY(NOPOLICY, "disable_policy"), + DEVINET_SYSCTL_RW_ENTRY(PROMOTE_SECONDARIES, + "promote_secondaries"), + DEVINET_SYSCTL_RW_ENTRY(ROUTE_LOCALNET, + "route_localnet"), +DEVINET_SYSCTL_RW_ENTRY (DROP_UNICAST_IN_L2_MULTICAST , + "drop_unicast_in_l2_multicast"), }, };
Signature · 1 line
2.54.0
PATCH v5 2/3 ipv4: handle devconf post-set actions on netlink updates
When IPv4 device configuration parameters are updated via netlink, the kernel currently only updates the value. This bypasses several post-modification actions that occur when these same parameters are updated via sysctl, such as flushing the routing cache or emitting RTM_NEWNETCONF notifications.
This patch addresses the inconsistency by calling the devinet_conf_post_set() helper inside inet_set_link_af(). If a flush is required, we defer it until the netlink attribute parsing loop completes.
This ensures consistent behavior and side-effects for devconf changes, regardless of whether they are initiated via sysctl or netlink.
---
v2: handled forwarding notification and disabling LRO
v3: no changes
v4: no changes
v5: no changes
--- net/ipv4/devinet.c | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-)
net/ipv4/devinet.c +27 -2
@@ -2161,6 +2161,20 @@ static bool devinet_conf_post_set(struct net *net, struct ipv4_devconf *cnf,NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN , ifindex, cnf);break ; +case IPV4_DEVCONF_FORWARDING : +if (new ==1 ) { +/* it is safe to use container_of() because forwarding case +* is only used by the netlink path +*/ + struct in_device *idev = container_of(cnf, struct in_device, cnf); + +netif_disable_lro (idev->dev); + } + +inet_netconf_notify_devconf (net,RTM_NEWNETCONF , +NETCONFA_FORWARDING , + ifindex, cnf); +return true;default :break ; }
@@ -2173,6 +2187,8 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, {struct in_device *in_dev =__in_dev_get_rtnl (dev);struct nlattr *a, *tb[IFLA_INET_MAX +1 ]; +struct net *net =dev_net (dev); +bool flush_cache = false;int rem;if (!in_dev)
@@ -2182,8 +2198,17 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla,return -EINVAL ;if (tb[IFLA_INET_CONF ]) { -nla_for_each_nested (a, tb[IFLA_INET_CONF ], rem) -ipv4_devconf_set (in_dev,nla_type (a),nla_get_u32 (a)); +nla_for_each_nested (a, tb[IFLA_INET_CONF ], rem) { +int old_value =ipv4_devconf_get (in_dev,nla_type (a)); +int new_value =nla_get_u32 (a); + +ipv4_devconf_set (in_dev,nla_type (a), new_value); +if (devinet_conf_post_set (net, &in_dev->cnf,nla_type (a), new_value, + old_value, dev->ifindex)) + flush_cache = true; + } +if (flush_cache) +rt_cache_flush (net); }return 0 ;
Signature · 1 line
2.54.0
PATCH v5 3/3 selftests: net: add test for IPv4 devconf netlink notifications
In reply to Fernando Fernandez ManceraIntroduce a new test, ipv4_devconf_notify, to verify that the kernel sends the appropriate netlink notifications when IPv4 devconf parameters are modified.
The test depends on the newly introduced iproute2 command:
ip link set dev <ifname> inet
---
v3: added this patch to the series as requested by Paolo.
v4: fixed lint warnings, some of them cannot be fixed as they are related to the YNL hack.
v5: use the newly introduce iproute2 inet command, drop the YNL hack
--- tools/testing/selftests/net/rtnetlink.py | 41 +++++++++++++++++++++--- 1 file changed, 37 insertions(+), 4 deletions(-)
tools/testing/selftests/net/rtnetlink.py +37 -4
@@ -1,17 +1,20 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_exit, ksft_run, ksft_ge, RtnlAddrFamily import socket +import time +from lib.py import bkg, ip, ksft_exit, ksft_run, ksft_ge, ksft_true, KsftSkipEx +from lib.py import NetNS, NetNSEnter, RtnlAddrFamily IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01' -def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None: +def dump_mcaddr_check() -> None: """ Verify that at least one interface has the IPv4 all-hosts multicast address. At least the loopback interface should have this address. """ + rtnl = RtnlAddrFamily() addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True) all_host_multicasts = [
@@ -21,9 +24,39 @@ def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None: ksft_ge(len(all_host_multicasts), 1, "No interface found with the IPv4 all-hosts multicast address") +def ipv4_devconf_notify() -> None: + """ + Configure an interface and set ipv4-devconf values through netlink + to verify that the appropriate netlink notifications are being sent. + """ + + with NetNS() as ns: + with NetNSEnter(str(ns)): + ifname = "dummy1" + ip(f"link add name {ifname} type dummy", ns=str(ns)) + + with bkg("ip monitor", ns=str(ns)) as cmd_obj: + time.sleep(1) + try: + ip(f"link set dev {ifname} inet forwarding on") + ip(f"link set dev {ifname} inet proxy_arp on") + ip(f"link set dev {ifname} inet rp_filter 1") + ip(f"link set dev {ifname} inet ignore_routes_with_linkdown on") + except: + raise KsftSkipEx("iproute2 does not support IPv4 devconf attributes") + time.sleep(1) + + ksft_true(f"inet {ifname} ignore_routes_with_linkdown on" in cmd_obj.stdout, + f"No 'ignore_routes_with_linkdown on' notificiation found for interface {ifname}") + ksft_true(f"inet {ifname} rp_filter strict" in cmd_obj.stdout, + f"No 'rp_filter strict' notificiation found for interface {ifname}") + ksft_true(f"inet {ifname} proxy_neigh on" in cmd_obj.stdout, + f"No 'proxy_neigh on' notificiation found for interface {ifname}") + ksft_true(f"inet {ifname} forwarding on" in cmd_obj.stdout, + f"No 'forwarding on' notificiation found for interface {ifname}") + def main() -> None: - rtnl = RtnlAddrFamily() - ksft_run([dump_mcaddr_check], args=(rtnl, )) + ksft_run([dump_mcaddr_check, ipv4_devconf_notify]) ksft_exit() if __name__ == "__main__":
Signature · 1 line
2.54.0
Jakub Kicinski
maintainerQuoted 4 lines · On Sun, 7 Jun 2026 13:01:21 +0200 Fernando Fernandez Mancera wrote:
The logic for handling IPv4 devconf sysctls is scattered. Notification and cache flushes are managed in
devinet_conf_proc(), while a separateipv4_doint_and_flush()function andDEVINET_SYSCTL_FLUSHING_ENTRYmacro is used for properties that solely require a cache flush.
Hi Fernando!
Do you have the necessary iproute2 patches pushed out somewhere? I'll pull them in the CI to make sure the test works.
Quoted 11 lines · Jakub Kicinski
Quoted 4 lines · On Sun, 7 Jun 2026 13:01:21 +0200 Fernando Fernandez Mancera wrote:
The logic for handling IPv4 devconf sysctls is scattered. Notification and cache flushes are managed in
devinet_conf_proc(), while a separateipv4_doint_and_flush()function andDEVINET_SYSCTL_FLUSHING_ENTRYmacro is used for properties that solely require a cache flush.Hi Fernando!
Do you have the necessary iproute2 patches pushed out somewhere? I'll pull them in the CI to make sure the test works.
Oh sorry, I thought this was using iproute2-next.
Yes, feel free to find it either here [0] or pick it from [1].
[0] https://lore.kernel.org/netdev/[email protected]/
Thanks,
Fernando.
Jakub Kicinski
maintainerQuoted 13 lines · On Mon, 8 Jun 2026 19:41:54 +0200 Fernando Fernandez Mancera wrote:
Quoted 11 lines · Jakub Kicinski
Quoted 4 lines · On Sun, 7 Jun 2026 13:01:21 +0200 Fernando Fernandez Mancera wrote:
The logic for handling IPv4 devconf sysctls is scattered. Notification and cache flushes are managed in
devinet_conf_proc(), while a separateipv4_doint_and_flush()function andDEVINET_SYSCTL_FLUSHING_ENTRYmacro is used for properties that solely require a cache flush.Hi Fernando!
Do you have the necessary iproute2 patches pushed out somewhere? I'll pull them in the CI to make sure the test works.
Quoted 8 lines
Oh sorry, I thought this was using iproute2-next.
Yes, feel free to find it either here [0] or pick it from [1].
Tests pass, thanks!
but ruff check fails with
tools/testing/selftests/net/rtnetlink.py:45: [E722] Do not use bare except
There's a specific error cmd()/ip() raises on non-zero return, you can catch that one.
Signature · 1 line
pw-bot: cr