Skip to contentSkip to conversation

ipv4: centralize devconf sysctl handling

PATCH Superseded Fernando Fernandez Mancera 2 participants 4 messages Mar 27 – Mar 31

Subsystems (3)

v2 of 6 Superseded Latest is v6 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/2 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

---
 net/ipv4/devinet.c | 127 ++++++++++++++++++++++++---------------------
 1 file changed, 68 insertions(+), 59 deletions(-)
net/ipv4/devinet.c +68 -59
index 58fe7cb69545..8300516fb38f 100644
@@ -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
2.53.0
#1 lore raw

PATCH v2 2/2 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

---
 net/ipv4/devinet.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)
net/ipv4/devinet.c +27 -2
index 8300516fb38f..a35b72662e43 100644
@@ -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
2.53.0
maintainer
#2 lore raw

Re: [PATCH 2/2 net-next v2] ipv4: handle devconf post-set actions on netlink updates

Quoted 10 lines · Fernando Fernandez Mancera

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.

IMHO the above deserve some additional self-test triggering the relevant code.

Quoted 15 lines

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

---
 net/ipv4/devinet.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)
net/ipv4/devinet.c +0 -0
index 8300516fb38f..a35b72662e43 100644

net/ipv4/devinet.c static bool devinet_conf_post_set(struct net *net, struct ipv4_devconf *cnf, · line 2165

Quoted 5 lines
net/ipv4/devinet.c +2 -0
@@ -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) {

AI reviews says:

Does this check miss cases where forwarding is enabled with a value other than 1?
The sysctl path allows enabling IP forwarding with any non-zero value. If a user sets IPV4_DEVCONF_FORWARDING to 2 via netlink, forwarding will be enabled but this check is bypassed, leaving Large Receive Offload (LRO) enabled. Could this cause LRO-coalesced packets to be forwarded without proper software segmentation?

net/ipv4/devinet.c static bool devinet_conf_post_set(struct net *net, struct ipv4_devconf *cnf, · line 2171

Quoted 6 lines
net/ipv4/devinet.c +6 -0
+			/* 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);

AI review says:

Is it safe to call netif_disable_lro() here without holding the device operations lock?
While inet_set_link_af() runs under rtnl_lock(), netif_disable_lro() modifies device features and calls netdev_update_features(), which asserts that the device operations lock is held. Calling this without the lock might trigger an assertion or expose the device to data races with concurrent feature updates or BPF/XDP attachments. Should this use dev_disable_lro() instead, which acquires the required lock before disabling LRO?

/P

#3 lore raw

Re: [PATCH 2/2 net-next v2] ipv4: handle devconf post-set actions on netlink updates

Quoted 7 lines · Paolo Abeni
Quoted 6 lines · Fernando Fernandez Mancera

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.

Quoted 8 lines
Quoted 4 lines

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.

IMHO the above deserve some additional self-test triggering the relevant code.

Hi Paolo,

sure, I could include a selftest for this.

Quoted 23 lines
Quoted 15 lines

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

---
  net/ipv4/devinet.c | 29 +++++++++++++++++++++++++++--
  1 file changed, 27 insertions(+), 2 deletions(-)
net/ipv4/devinet.c +0 -0
index 8300516fb38f..a35b72662e43 100644

net/ipv4/devinet.c static bool devinet_conf_post_set(struct net *net, struct ipv4_devconf *cnf, · line 2165

Quoted 5 lines
net/ipv4/devinet.c +2 -0
@@ -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) {

AI reviews says:

Quoted 8 lines

Does this check miss cases where forwarding is enabled with a value other than 1?
The sysctl path allows enabling IP forwarding with any non-zero value. If a user sets IPV4_DEVCONF_FORWARDING to 2 via netlink, forwarding will be enabled but this check is bypassed, leaving Large Receive Offload (LRO) enabled. Could this cause LRO-coalesced packets to be forwarded without proper software segmentation?

If a user sets IPV4_DEVCONF_FORWARDING to 2 via netlink the value would be rejected. There is netlink attribute validation and FORWARDING is set as boolean with the range [0, 1].

This cannot happen.

Quoted 9 lines

net/ipv4/devinet.c static bool devinet_conf_post_set(struct net *net, struct ipv4_devconf *cnf, · line 2171

Quoted 6 lines
net/ipv4/devinet.c +6 -0
+			/* 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);

AI review says:

Quoted 9 lines

Is it safe to call netif_disable_lro() here without holding the device operations lock?
While inet_set_link_af() runs under rtnl_lock(), netif_disable_lro() modifies device features and calls netdev_update_features(), which asserts that the device operations lock is held. Calling this without the lock might trigger an assertion or expose the device to data races with concurrent feature updates or BPF/XDP attachments. Should this use dev_disable_lro() instead, which acquires the required lock before disabling LRO?

It is not possible to call this without the holding the lock. The device operations lock is held when handling IFLA_AF_SPEC at net/core/rtnetlink.c. Calling netif_disable_lro() is the right thing to do IMHO. Keep on mind that FORWARDING case here is only triggered by netlink path and not sysctl.

Thanks,
Fernando.

Quoted 3 lines

/P