aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/devinet.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/devinet.c')
-rw-r--r--net/ipv4/devinet.c2065
1 files changed, 1423 insertions, 642 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 95b9d81ac48..e9449376b58 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1,8 +1,6 @@
/*
* NET3 IP device support routines.
*
- * Version: $Id: devinet.c,v 1.44 2001/10/31 21:55:54 davem Exp $
- *
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
@@ -27,16 +25,13 @@
* if no match found.
*/
-#include <linux/config.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
@@ -44,64 +39,163 @@
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
+#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
-#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
+#include <linux/slab.h>
+#include <linux/hash.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>
+#include <linux/netconf.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip_fib.h>
-
-struct ipv4_devconf ipv4_devconf = {
- .accept_redirects = 1,
- .send_redirects = 1,
- .secure_redirects = 1,
- .shared_media = 1,
+#include <net/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/addrconf.h>
+
+#include "fib_lookup.h"
+
+static struct ipv4_devconf ipv4_devconf = {
+ .data = {
+ [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
+ [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
+ [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
+ },
};
static struct ipv4_devconf ipv4_devconf_dflt = {
- .accept_redirects = 1,
- .send_redirects = 1,
- .secure_redirects = 1,
- .shared_media = 1,
- .accept_source_route = 1,
+ .data = {
+ [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
+ [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
+ [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
+ [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
+ [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
+ },
};
-static void rtmsg_ifa(int event, struct in_ifaddr *);
+#define IPV4_DEVCONF_DFLT(net, attr) \
+ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr)
+
+static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
+ [IFA_LOCAL] = { .type = NLA_U32 },
+ [IFA_ADDRESS] = { .type = NLA_U32 },
+ [IFA_BROADCAST] = { .type = NLA_U32 },
+ [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
+ [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
+ [IFA_FLAGS] = { .type = NLA_U32 },
+};
+
+#define IN4_ADDR_HSIZE_SHIFT 8
+#define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT)
+
+static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
+
+static u32 inet_addr_hash(struct net *net, __be32 addr)
+{
+ u32 val = (__force u32) addr ^ net_hash_mix(net);
+
+ return hash_32(val, IN4_ADDR_HSIZE_SHIFT);
+}
+
+static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
+{
+ u32 hash = inet_addr_hash(net, ifa->ifa_local);
+
+ ASSERT_RTNL();
+ hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
+}
+
+static void inet_hash_remove(struct in_ifaddr *ifa)
+{
+ ASSERT_RTNL();
+ hlist_del_init_rcu(&ifa->hash);
+}
-static struct notifier_block *inetaddr_chain;
+/**
+ * __ip_dev_find - find the first device with a given source address.
+ * @net: the net namespace
+ * @addr: the source address
+ * @devref: if true, take a reference on the found device
+ *
+ * If a caller uses devref=false, it should be protected by RCU, or RTNL
+ */
+struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
+{
+ u32 hash = inet_addr_hash(net, addr);
+ struct net_device *result = NULL;
+ struct in_ifaddr *ifa;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
+ if (ifa->ifa_local == addr) {
+ struct net_device *dev = ifa->ifa_dev->dev;
+
+ if (!net_eq(dev_net(dev), net))
+ continue;
+ result = dev;
+ break;
+ }
+ }
+ if (!result) {
+ struct flowi4 fl4 = { .daddr = addr };
+ struct fib_result res = { 0 };
+ struct fib_table *local;
+
+ /* Fallback to FIB local table so that communication
+ * over loopback subnets work.
+ */
+ local = fib_get_table(net, RT_TABLE_LOCAL);
+ if (local &&
+ !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
+ res.type == RTN_LOCAL)
+ result = FIB_RES_DEV(res);
+ }
+ if (result && devref)
+ dev_hold(result);
+ rcu_read_unlock();
+ return result;
+}
+EXPORT_SYMBOL(__ip_dev_find);
+
+static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
+
+static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy);
#ifdef CONFIG_SYSCTL
-static void devinet_sysctl_register(struct in_device *in_dev,
- struct ipv4_devconf *p);
-static void devinet_sysctl_unregister(struct ipv4_devconf *p);
+static void devinet_sysctl_register(struct in_device *idev);
+static void devinet_sysctl_unregister(struct in_device *idev);
+#else
+static void devinet_sysctl_register(struct in_device *idev)
+{
+}
+static void devinet_sysctl_unregister(struct in_device *idev)
+{
+}
#endif
/* Locks all the inet devices. */
static struct in_ifaddr *inet_alloc_ifa(void)
{
- struct in_ifaddr *ifa = kmalloc(sizeof(*ifa), GFP_KERNEL);
-
- if (ifa) {
- memset(ifa, 0, sizeof(*ifa));
- INIT_RCU_HEAD(&ifa->rcu_head);
- }
-
- return ifa;
+ return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL);
}
static void inet_rcu_free_ifa(struct rcu_head *head)
@@ -112,7 +206,7 @@ static void inet_rcu_free_ifa(struct rcu_head *head)
kfree(ifa);
}
-static inline void inet_free_ifa(struct in_ifaddr *ifa)
+static void inet_free_ifa(struct in_ifaddr *ifa)
{
call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
}
@@ -121,53 +215,50 @@ void in_dev_finish_destroy(struct in_device *idev)
{
struct net_device *dev = idev->dev;
- BUG_TRAP(!idev->ifa_list);
- BUG_TRAP(!idev->mc_list);
+ WARN_ON(idev->ifa_list);
+ WARN_ON(idev->mc_list);
+ kfree(rcu_dereference_protected(idev->mc_hash, 1));
#ifdef NET_REFCNT_DEBUG
- printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n",
- idev, dev ? dev->name : "NIL");
+ pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL");
#endif
dev_put(dev);
if (!idev->dead)
- printk("Freeing alive in_device %p\n", idev);
- else {
+ pr_err("Freeing alive in_device %p\n", idev);
+ else
kfree(idev);
- }
}
+EXPORT_SYMBOL(in_dev_finish_destroy);
-struct in_device *inetdev_init(struct net_device *dev)
+static struct in_device *inetdev_init(struct net_device *dev)
{
struct in_device *in_dev;
ASSERT_RTNL();
- in_dev = kmalloc(sizeof(*in_dev), GFP_KERNEL);
+ in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
if (!in_dev)
goto out;
- memset(in_dev, 0, sizeof(*in_dev));
- INIT_RCU_HEAD(&in_dev->rcu_head);
- memcpy(&in_dev->cnf, &ipv4_devconf_dflt, sizeof(in_dev->cnf));
+ memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt,
+ sizeof(in_dev->cnf));
in_dev->cnf.sysctl = NULL;
in_dev->dev = dev;
- if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL)
+ in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl);
+ if (!in_dev->arp_parms)
goto out_kfree;
+ if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
+ dev_disable_lro(dev);
/* Reference in_dev->dev */
dev_hold(dev);
-#ifdef CONFIG_SYSCTL
- neigh_sysctl_register(dev, in_dev->arp_parms, NET_IPV4,
- NET_IPV4_NEIGH, "ipv4", NULL, NULL);
-#endif
-
- /* Account for reference dev->ip_ptr */
+ /* Account for reference dev->ip_ptr (below) */
in_dev_hold(in_dev);
- rcu_assign_pointer(dev->ip_ptr, in_dev);
-#ifdef CONFIG_SYSCTL
- devinet_sysctl_register(in_dev, &in_dev->cnf);
-#endif
+ devinet_sysctl_register(in_dev);
ip_mc_init_dev(in_dev);
if (dev->flags & IFF_UP)
ip_mc_up(in_dev);
+
+ /* we can receive as soon as ip_ptr is set -- do this last */
+ rcu_assign_pointer(dev->ip_ptr, in_dev);
out:
return in_dev;
out_kfree:
@@ -190,8 +281,6 @@ static void inetdev_destroy(struct in_device *in_dev)
ASSERT_RTNL();
dev = in_dev->dev;
- if (dev == &loopback_dev)
- return;
in_dev->dead = 1;
@@ -202,22 +291,16 @@ static void inetdev_destroy(struct in_device *in_dev)
inet_free_ifa(ifa);
}
-#ifdef CONFIG_SYSCTL
- devinet_sysctl_unregister(&in_dev->cnf);
-#endif
-
- dev->ip_ptr = NULL;
+ RCU_INIT_POINTER(dev->ip_ptr, NULL);
-#ifdef CONFIG_SYSCTL
- neigh_sysctl_unregister(in_dev->arp_parms);
-#endif
+ devinet_sysctl_unregister(in_dev);
neigh_parms_release(&arp_tbl, in_dev->arp_parms);
arp_ifdown(dev);
call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}
-int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b)
+int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
rcu_read_lock();
for_primary_ifa(in_dev) {
@@ -232,8 +315,8 @@ int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b)
return 0;
}
-static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
- int destroy)
+static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
+ int destroy, struct nlmsghdr *nlh, u32 portid)
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1 = *ifap;
@@ -243,7 +326,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
ASSERT_RTNL();
- /* 1. Deleting primary ifaddr forces deletion all secondaries
+ /* 1. Deleting primary ifaddr forces deletion all secondaries
* unless alias promotion is set
**/
@@ -251,7 +334,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
struct in_ifaddr **ifap1 = &ifa1->ifa_next;
while ((ifa = *ifap1) != NULL) {
- if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
+ if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
ifa1->ifa_scope <= ifa->ifa_scope)
last_prim = ifa;
@@ -264,10 +347,12 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
if (!do_promote) {
+ inet_hash_remove(ifa);
*ifap1 = ifa->ifa_next;
- rtmsg_ifa(RTM_DELADDR, ifa);
- notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa);
+ rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid);
+ blocking_notifier_call_chain(&inetaddr_chain,
+ NETDEV_DOWN, ifa);
inet_free_ifa(ifa);
} else {
promote = ifa;
@@ -276,9 +361,21 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
}
+ /* On promotion all secondaries from subnet are changing
+ * the primary IP, we must remove all their routes silently
+ * and later to add them back with new prefsrc. Do this
+ * while all addresses are on the device list.
+ */
+ for (ifa = promote; ifa; ifa = ifa->ifa_next) {
+ if (ifa1->ifa_mask == ifa->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, ifa))
+ fib_del_ifaddr(ifa, ifa1);
+ }
+
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
+ inet_hash_remove(ifa1);
/* 3. Announce address deletion */
@@ -290,10 +387,11 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
is valid, it will try to restore deleted routes... Grr.
So that, this order is correct.
*/
- rtmsg_ifa(RTM_DELADDR, ifa1);
- notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
+ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid);
+ blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
if (promote) {
+ struct in_ifaddr *next_sec = promote->ifa_next;
if (prev_prom) {
prev_prom->ifa_next = promote->ifa_next;
@@ -302,9 +400,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
promote->ifa_flags &= ~IFA_F_SECONDARY;
- rtmsg_ifa(RTM_NEWADDR, promote);
- notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote);
- for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
+ rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid);
+ blocking_notifier_call_chain(&inetaddr_chain,
+ NETDEV_UP, promote);
+ for (ifa = next_sec; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
@@ -312,15 +411,22 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
}
- if (destroy) {
+ if (destroy)
inet_free_ifa(ifa1);
+}
- if (!in_dev->ifa_list)
- inetdev_destroy(in_dev);
- }
+static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
+ int destroy)
+{
+ __inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
-static int inet_insert_ifa(struct in_ifaddr *ifa)
+static void check_lifetime(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
+
+static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
+ u32 portid)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap, **last_primary;
@@ -355,22 +461,32 @@ static int inet_insert_ifa(struct in_ifaddr *ifa)
}
if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
- net_srandom(ifa->ifa_local);
+ prandom_seed((__force u32) ifa->ifa_local);
ifap = last_primary;
}
ifa->ifa_next = *ifap;
*ifap = ifa;
+ inet_hash_insert(dev_net(in_dev->dev), ifa);
+
+ cancel_delayed_work(&check_lifetime_work);
+ queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
+
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
- rtmsg_ifa(RTM_NEWADDR, ifa);
- notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
+ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid);
+ blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
return 0;
}
+static int inet_insert_ifa(struct in_ifaddr *ifa)
+{
+ return __inet_insert_ifa(ifa, NULL, 0);
+}
+
static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
@@ -378,38 +494,42 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
ASSERT_RTNL();
if (!in_dev) {
- in_dev = inetdev_init(dev);
- if (!in_dev) {
- inet_free_ifa(ifa);
- return -ENOBUFS;
- }
+ inet_free_ifa(ifa);
+ return -ENOBUFS;
}
+ ipv4_devconf_setall(in_dev);
+ neigh_parms_data_state_setall(in_dev->arp_parms);
if (ifa->ifa_dev != in_dev) {
- BUG_TRAP(!ifa->ifa_dev);
+ WARN_ON(ifa->ifa_dev);
in_dev_hold(in_dev);
ifa->ifa_dev = in_dev;
}
- if (LOOPBACK(ifa->ifa_local))
+ if (ipv4_is_loopback(ifa->ifa_local))
ifa->ifa_scope = RT_SCOPE_HOST;
return inet_insert_ifa(ifa);
}
-struct in_device *inetdev_by_index(int ifindex)
+/* Caller must hold RCU or RTNL :
+ * We dont take a reference on found in_device
+ */
+struct in_device *inetdev_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct in_device *in_dev = NULL;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(ifindex);
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
- in_dev = in_dev_get(dev);
- read_unlock(&dev_base_lock);
+ in_dev = rcu_dereference_rtnl(dev->ip_ptr);
+ rcu_read_unlock();
return in_dev;
}
+EXPORT_SYMBOL(inetdev_by_index);
/* Called only from RTNL semaphored context. No locks. */
-struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix,
- u32 mask)
+struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
+ __be32 mask)
{
ASSERT_RTNL();
@@ -420,117 +540,340 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix,
return NULL;
}
-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
- struct rtattr **rta = arg;
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[IFA_MAX+1];
struct in_device *in_dev;
- struct ifaddrmsg *ifm = NLMSG_DATA(nlh);
+ struct ifaddrmsg *ifm;
struct in_ifaddr *ifa, **ifap;
+ int err = -EINVAL;
ASSERT_RTNL();
- if ((in_dev = inetdev_by_index(ifm->ifa_index)) == NULL)
- goto out;
- __in_dev_put(in_dev);
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+ if (err < 0)
+ goto errout;
+
+ ifm = nlmsg_data(nlh);
+ in_dev = inetdev_by_index(net, ifm->ifa_index);
+ if (in_dev == NULL) {
+ err = -ENODEV;
+ goto errout;
+ }
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
- if ((rta[IFA_LOCAL - 1] &&
- memcmp(RTA_DATA(rta[IFA_LOCAL - 1]),
- &ifa->ifa_local, 4)) ||
- (rta[IFA_LABEL - 1] &&
- rtattr_strcmp(rta[IFA_LABEL - 1], ifa->ifa_label)) ||
- (rta[IFA_ADDRESS - 1] &&
- (ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
- !inet_ifa_match(*(u32*)RTA_DATA(rta[IFA_ADDRESS - 1]),
- ifa))))
+ if (tb[IFA_LOCAL] &&
+ ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL]))
continue;
- inet_del_ifa(in_dev, ifap, 1);
+
+ if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
+ continue;
+
+ if (tb[IFA_ADDRESS] &&
+ (ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
+ !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa)))
+ continue;
+
+ __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
return 0;
}
-out:
- return -EADDRNOTAVAIL;
+
+ err = -EADDRNOTAVAIL;
+errout:
+ return err;
}
-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+#define INFINITY_LIFE_TIME 0xFFFFFFFF
+
+static void check_lifetime(struct work_struct *work)
{
- struct rtattr **rta = arg;
- struct net_device *dev;
- struct in_device *in_dev;
- struct ifaddrmsg *ifm = NLMSG_DATA(nlh);
+ unsigned long now, next, next_sec, next_sched;
struct in_ifaddr *ifa;
- int rc = -EINVAL;
+ struct hlist_node *n;
+ int i;
- ASSERT_RTNL();
+ now = jiffies;
+ next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
- if (ifm->ifa_prefixlen > 32 || !rta[IFA_LOCAL - 1])
- goto out;
+ for (i = 0; i < IN4_ADDR_HSIZE; i++) {
+ bool change_needed = false;
- rc = -ENODEV;
- if ((dev = __dev_get_by_index(ifm->ifa_index)) == NULL)
- goto out;
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) {
+ unsigned long age;
- rc = -ENOBUFS;
- if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) {
- in_dev = inetdev_init(dev);
- if (!in_dev)
- goto out;
+ if (ifa->ifa_flags & IFA_F_PERMANENT)
+ continue;
+
+ /* We try to batch several events at once. */
+ age = (now - ifa->ifa_tstamp +
+ ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+
+ if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_valid_lft) {
+ change_needed = true;
+ } else if (ifa->ifa_preferred_lft ==
+ INFINITY_LIFE_TIME) {
+ continue;
+ } else if (age >= ifa->ifa_preferred_lft) {
+ if (time_before(ifa->ifa_tstamp +
+ ifa->ifa_valid_lft * HZ, next))
+ next = ifa->ifa_tstamp +
+ ifa->ifa_valid_lft * HZ;
+
+ if (!(ifa->ifa_flags & IFA_F_DEPRECATED))
+ change_needed = true;
+ } else if (time_before(ifa->ifa_tstamp +
+ ifa->ifa_preferred_lft * HZ,
+ next)) {
+ next = ifa->ifa_tstamp +
+ ifa->ifa_preferred_lft * HZ;
+ }
+ }
+ rcu_read_unlock();
+ if (!change_needed)
+ continue;
+ rtnl_lock();
+ hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) {
+ unsigned long age;
+
+ if (ifa->ifa_flags & IFA_F_PERMANENT)
+ continue;
+
+ /* We try to batch several events at once. */
+ age = (now - ifa->ifa_tstamp +
+ ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+
+ if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_valid_lft) {
+ struct in_ifaddr **ifap;
+
+ for (ifap = &ifa->ifa_dev->ifa_list;
+ *ifap != NULL; ifap = &(*ifap)->ifa_next) {
+ if (*ifap == ifa) {
+ inet_del_ifa(ifa->ifa_dev,
+ ifap, 1);
+ break;
+ }
+ }
+ } else if (ifa->ifa_preferred_lft !=
+ INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_preferred_lft &&
+ !(ifa->ifa_flags & IFA_F_DEPRECATED)) {
+ ifa->ifa_flags |= IFA_F_DEPRECATED;
+ rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
+ }
+ }
+ rtnl_unlock();
}
- if ((ifa = inet_alloc_ifa()) == NULL)
- goto out;
+ next_sec = round_jiffies_up(next);
+ next_sched = next;
+
+ /* If rounded timeout is accurate enough, accept it. */
+ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ))
+ next_sched = next_sec;
+
+ now = jiffies;
+ /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */
+ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX))
+ next_sched = now + ADDRCONF_TIMER_FUZZ_MAX;
+
+ queue_delayed_work(system_power_efficient_wq, &check_lifetime_work,
+ next_sched - now);
+}
+
+static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
+ __u32 prefered_lft)
+{
+ unsigned long timeout;
+
+ ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED);
+
+ timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ if (addrconf_finite_timeout(timeout))
+ ifa->ifa_valid_lft = timeout;
+ else
+ ifa->ifa_flags |= IFA_F_PERMANENT;
+
+ timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ if (timeout == 0)
+ ifa->ifa_flags |= IFA_F_DEPRECATED;
+ ifa->ifa_preferred_lft = timeout;
+ }
+ ifa->ifa_tstamp = jiffies;
+ if (!ifa->ifa_cstamp)
+ ifa->ifa_cstamp = ifa->ifa_tstamp;
+}
+
+static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
+ __u32 *pvalid_lft, __u32 *pprefered_lft)
+{
+ struct nlattr *tb[IFA_MAX+1];
+ struct in_ifaddr *ifa;
+ struct ifaddrmsg *ifm;
+ struct net_device *dev;
+ struct in_device *in_dev;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
+ if (err < 0)
+ goto errout;
+
+ ifm = nlmsg_data(nlh);
+ err = -EINVAL;
+ if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL)
+ goto errout;
- if (!rta[IFA_ADDRESS - 1])
- rta[IFA_ADDRESS - 1] = rta[IFA_LOCAL - 1];
- memcpy(&ifa->ifa_local, RTA_DATA(rta[IFA_LOCAL - 1]), 4);
- memcpy(&ifa->ifa_address, RTA_DATA(rta[IFA_ADDRESS - 1]), 4);
+ dev = __dev_get_by_index(net, ifm->ifa_index);
+ err = -ENODEV;
+ if (dev == NULL)
+ goto errout;
+
+ in_dev = __in_dev_get_rtnl(dev);
+ err = -ENOBUFS;
+ if (in_dev == NULL)
+ goto errout;
+
+ ifa = inet_alloc_ifa();
+ if (ifa == NULL)
+ /*
+ * A potential indev allocation can be left alive, it stays
+ * assigned to its device and is destroy with it.
+ */
+ goto errout;
+
+ ipv4_devconf_setall(in_dev);
+ neigh_parms_data_state_setall(in_dev->arp_parms);
+ in_dev_hold(in_dev);
+
+ if (tb[IFA_ADDRESS] == NULL)
+ tb[IFA_ADDRESS] = tb[IFA_LOCAL];
+
+ INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_prefixlen = ifm->ifa_prefixlen;
ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
- if (rta[IFA_BROADCAST - 1])
- memcpy(&ifa->ifa_broadcast,
- RTA_DATA(rta[IFA_BROADCAST - 1]), 4);
- if (rta[IFA_ANYCAST - 1])
- memcpy(&ifa->ifa_anycast, RTA_DATA(rta[IFA_ANYCAST - 1]), 4);
- ifa->ifa_flags = ifm->ifa_flags;
+ ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
+ ifm->ifa_flags;
ifa->ifa_scope = ifm->ifa_scope;
- in_dev_hold(in_dev);
- ifa->ifa_dev = in_dev;
- if (rta[IFA_LABEL - 1])
- rtattr_strlcpy(ifa->ifa_label, rta[IFA_LABEL - 1], IFNAMSIZ);
+ ifa->ifa_dev = in_dev;
+
+ ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]);
+ ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]);
+
+ if (tb[IFA_BROADCAST])
+ ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);
+
+ if (tb[IFA_LABEL])
+ nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
- rc = inet_insert_ifa(ifa);
-out:
- return rc;
+ if (tb[IFA_CACHEINFO]) {
+ struct ifa_cacheinfo *ci;
+
+ ci = nla_data(tb[IFA_CACHEINFO]);
+ if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
+ err = -EINVAL;
+ goto errout_free;
+ }
+ *pvalid_lft = ci->ifa_valid;
+ *pprefered_lft = ci->ifa_prefered;
+ }
+
+ return ifa;
+
+errout_free:
+ inet_free_ifa(ifa);
+errout:
+ return ERR_PTR(err);
+}
+
+static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
+{
+ struct in_device *in_dev = ifa->ifa_dev;
+ struct in_ifaddr *ifa1, **ifap;
+
+ if (!ifa->ifa_local)
+ return NULL;
+
+ for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
+ ifap = &ifa1->ifa_next) {
+ if (ifa1->ifa_mask == ifa->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, ifa) &&
+ ifa1->ifa_local == ifa->ifa_local)
+ return ifa1;
+ }
+ return NULL;
+}
+
+static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+ struct net *net = sock_net(skb->sk);
+ struct in_ifaddr *ifa;
+ struct in_ifaddr *ifa_existing;
+ __u32 valid_lft = INFINITY_LIFE_TIME;
+ __u32 prefered_lft = INFINITY_LIFE_TIME;
+
+ ASSERT_RTNL();
+
+ ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft);
+ if (IS_ERR(ifa))
+ return PTR_ERR(ifa);
+
+ ifa_existing = find_matching_ifa(ifa);
+ if (!ifa_existing) {
+ /* It would be best to check for !NLM_F_CREATE here but
+ * userspace already relies on not having to provide this.
+ */
+ set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+ return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+ } else {
+ inet_free_ifa(ifa);
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL ||
+ !(nlh->nlmsg_flags & NLM_F_REPLACE))
+ return -EEXIST;
+ ifa = ifa_existing;
+ set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+ cancel_delayed_work(&check_lifetime_work);
+ queue_delayed_work(system_power_efficient_wq,
+ &check_lifetime_work, 0);
+ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
+ blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
+ }
+ return 0;
}
/*
* Determine a default network mask, based on the IP address.
*/
-static __inline__ int inet_abc_len(u32 addr)
+static int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
- if (ZERONET(addr))
- rc = 0;
+ if (ipv4_is_zeronet(addr))
+ rc = 0;
else {
- addr = ntohl(addr);
+ __u32 haddr = ntohl(addr);
- if (IN_CLASSA(addr))
+ if (IN_CLASSA(haddr))
rc = 8;
- else if (IN_CLASSB(addr))
+ else if (IN_CLASSB(haddr))
rc = 16;
- else if (IN_CLASSC(addr))
+ else if (IN_CLASSC(haddr))
rc = 24;
}
- return rc;
+ return rc;
}
-int devinet_ioctl(unsigned int cmd, void __user *arg)
+int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct ifreq ifr;
struct sockaddr_in sin_orig;
@@ -558,11 +901,9 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
if (colon)
*colon = 0;
-#ifdef CONFIG_KMOD
- dev_load(ifr.ifr_name);
-#endif
+ dev_load(net, ifr.ifr_name);
- switch(cmd) {
+ switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
case SIOCGIFBRDADDR: /* Get the broadcast address */
case SIOCGIFDSTADDR: /* Get the destination address */
@@ -577,16 +918,16 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
break;
case SIOCSIFFLAGS:
- ret = -EACCES;
- if (!capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto out;
break;
case SIOCSIFADDR: /* Set interface address (and family) */
case SIOCSIFBRDADDR: /* Set the broadcast address */
case SIOCSIFDSTADDR: /* Set the destination address */
case SIOCSIFNETMASK: /* Set the netmask for the interface */
- ret = -EACCES;
- if (!capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto out;
ret = -EINVAL;
if (sin->sin_family != AF_INET)
@@ -600,13 +941,15 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
rtnl_lock();
ret = -ENODEV;
- if ((dev = __dev_get_by_name(ifr.ifr_name)) == NULL)
+ dev = __dev_get_by_name(net, ifr.ifr_name);
+ if (!dev)
goto done;
if (colon)
*colon = ':';
- if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) {
+ in_dev = __in_dev_get_rtnl(dev);
+ if (in_dev) {
if (tryaddrmatch) {
/* Matthias Andree */
/* compare label and address (4.4BSD style) */
@@ -617,7 +960,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
ifap = &ifa->ifa_next) {
if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
- ifa->ifa_address) {
+ ifa->ifa_local) {
break; /* found */
}
}
@@ -637,7 +980,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
goto done;
- switch(cmd) {
+ switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
sin->sin_addr.s_addr = ifa->ifa_local;
goto rarok;
@@ -674,8 +1017,10 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
if (!ifa) {
ret = -ENOBUFS;
- if ((ifa = inet_alloc_ifa()) == NULL)
+ ifa = inet_alloc_ifa();
+ if (!ifa)
break;
+ INIT_HLIST_NODE(&ifa->hash);
if (colon)
memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
else
@@ -686,7 +1031,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
break;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_broadcast = 0;
- ifa->ifa_anycast = 0;
+ ifa->ifa_scope = 0;
}
ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr;
@@ -702,6 +1047,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
ifa->ifa_prefixlen = 32;
ifa->ifa_mask = inet_make_mask(32);
}
+ set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
ret = inet_set_ifa(dev, ifa);
break;
@@ -737,7 +1083,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
break;
ret = 0;
if (ifa->ifa_mask != sin->sin_addr.s_addr) {
- u32 old_mask = ifa->ifa_mask;
+ __be32 old_mask = ifa->ifa_mask;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_mask = sin->sin_addr.s_addr;
ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask);
@@ -776,10 +1122,10 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
struct ifreq ifr;
int done = 0;
- if (!in_dev || (ifa = in_dev->ifa_list) == NULL)
+ if (!in_dev)
goto out;
- for (; ifa; ifa = ifa->ifa_next) {
+ for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
if (!buf) {
done += sizeof(ifr);
continue;
@@ -787,10 +1133,7 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
if (len < (int) sizeof(ifr))
break;
memset(&ifr, 0, sizeof(struct ifreq));
- if (ifa->ifa_label)
- strcpy(ifr.ifr_name, ifa->ifa_label);
- else
- strcpy(ifr.ifr_name, dev->name);
+ strcpy(ifr.ifr_name, ifa->ifa_label);
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET;
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
@@ -808,10 +1151,11 @@ out:
return done;
}
-u32 inet_select_addr(const struct net_device *dev, u32 dst, int scope)
+__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
- u32 addr = 0;
+ __be32 addr = 0;
struct in_device *in_dev;
+ struct net *net = dev_net(dev);
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
@@ -828,42 +1172,39 @@ u32 inet_select_addr(const struct net_device *dev, u32 dst, int scope)
if (!addr)
addr = ifa->ifa_local;
} endfor_ifa(in_dev);
-no_in_dev:
- rcu_read_unlock();
if (addr)
- goto out;
+ goto out_unlock;
+no_in_dev:
/* Not loopback addresses on loopback should be preferred
in this case. It is importnat that lo is the first interface
in dev_base list.
*/
- read_lock(&dev_base_lock);
- rcu_read_lock();
- for (dev = dev_base; dev; dev = dev->next) {
- if ((in_dev = __in_dev_get_rcu(dev)) == NULL)
+ for_each_netdev_rcu(net, dev) {
+ in_dev = __in_dev_get_rcu(dev);
+ if (!in_dev)
continue;
for_primary_ifa(in_dev) {
if (ifa->ifa_scope != RT_SCOPE_LINK &&
ifa->ifa_scope <= scope) {
addr = ifa->ifa_local;
- goto out_unlock_both;
+ goto out_unlock;
}
} endfor_ifa(in_dev);
}
-out_unlock_both:
- read_unlock(&dev_base_lock);
+out_unlock:
rcu_read_unlock();
-out:
return addr;
}
+EXPORT_SYMBOL(inet_select_addr);
-static u32 confirm_addr_indev(struct in_device *in_dev, u32 dst,
- u32 local, int scope)
+static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
+ __be32 local, int scope)
{
int same = 0;
- u32 addr = 0;
+ __be32 addr = 0;
for_ifa(in_dev) {
if (!addr &&
@@ -893,44 +1234,40 @@ static u32 confirm_addr_indev(struct in_device *in_dev, u32 dst,
}
} endfor_ifa(in_dev);
- return same? addr : 0;
+ return same ? addr : 0;
}
/*
* Confirm that local IP address exists using wildcards:
- * - dev: only on this interface, 0=any interface
+ * - net: netns to check, cannot be NULL
+ * - in_dev: only on this interface, NULL=any interface
* - dst: only in the same subnet as dst, 0=any dst
* - local: address, 0=autoselect the local address
* - scope: maximum allowed scope value for the local address
*/
-u32 inet_confirm_addr(const struct net_device *dev, u32 dst, u32 local, int scope)
+__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev,
+ __be32 dst, __be32 local, int scope)
{
- u32 addr = 0;
- struct in_device *in_dev;
-
- if (dev) {
- rcu_read_lock();
- if ((in_dev = __in_dev_get_rcu(dev)))
- addr = confirm_addr_indev(in_dev, dst, local, scope);
- rcu_read_unlock();
+ __be32 addr = 0;
+ struct net_device *dev;
- return addr;
- }
+ if (in_dev != NULL)
+ return confirm_addr_indev(in_dev, dst, local, scope);
- read_lock(&dev_base_lock);
rcu_read_lock();
- for (dev = dev_base; dev; dev = dev->next) {
- if ((in_dev = __in_dev_get_rcu(dev))) {
+ for_each_netdev_rcu(net, dev) {
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev) {
addr = confirm_addr_indev(in_dev, dst, local, scope);
if (addr)
break;
}
}
rcu_read_unlock();
- read_unlock(&dev_base_lock);
return addr;
}
+EXPORT_SYMBOL(inet_confirm_addr);
/*
* Device notifier
@@ -938,74 +1275,105 @@ u32 inet_confirm_addr(const struct net_device *dev, u32 dst, u32 local, int scop
int register_inetaddr_notifier(struct notifier_block *nb)
{
- return notifier_chain_register(&inetaddr_chain, nb);
+ return blocking_notifier_chain_register(&inetaddr_chain, nb);
}
+EXPORT_SYMBOL(register_inetaddr_notifier);
int unregister_inetaddr_notifier(struct notifier_block *nb)
{
- return notifier_chain_unregister(&inetaddr_chain, nb);
+ return blocking_notifier_chain_unregister(&inetaddr_chain, nb);
}
+EXPORT_SYMBOL(unregister_inetaddr_notifier);
-/* Rename ifa_labels for a device name change. Make some effort to preserve existing
- * alias numbering and to create unique labels if possible.
+/* Rename ifa_labels for a device name change. Make some effort to preserve
+ * existing alias numbering and to create unique labels if possible.
*/
static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
-{
+{
struct in_ifaddr *ifa;
int named = 0;
- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
- char old[IFNAMSIZ], *dot;
+ for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
+ char old[IFNAMSIZ], *dot;
memcpy(old, ifa->ifa_label, IFNAMSIZ);
- memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
if (named++ == 0)
- continue;
- dot = strchr(ifa->ifa_label, ':');
- if (dot == NULL) {
- sprintf(old, ":%d", named);
+ goto skip;
+ dot = strchr(old, ':');
+ if (dot == NULL) {
+ sprintf(old, ":%d", named);
dot = old;
}
- if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) {
- strcat(ifa->ifa_label, dot);
- } else {
- strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
- }
- }
-}
+ if (strlen(dot) + strlen(dev->name) < IFNAMSIZ)
+ strcat(ifa->ifa_label, dot);
+ else
+ strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
+skip:
+ rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
+ }
+}
+
+static bool inetdev_valid_mtu(unsigned int mtu)
+{
+ return mtu >= 68;
+}
+
+static void inetdev_send_gratuitous_arp(struct net_device *dev,
+ struct in_device *in_dev)
+
+{
+ struct in_ifaddr *ifa;
+
+ for (ifa = in_dev->ifa_list; ifa;
+ ifa = ifa->ifa_next) {
+ arp_send(ARPOP_REQUEST, ETH_P_ARP,
+ ifa->ifa_local, dev,
+ ifa->ifa_local, NULL,
+ dev->dev_addr, NULL);
+ }
+}
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
if (!in_dev) {
- if (event == NETDEV_REGISTER && dev == &loopback_dev) {
+ if (event == NETDEV_REGISTER) {
in_dev = inetdev_init(dev);
if (!in_dev)
- panic("devinet: Failed to create loopback\n");
- in_dev->cnf.no_xfrm = 1;
- in_dev->cnf.no_policy = 1;
+ return notifier_from_errno(-ENOMEM);
+ if (dev->flags & IFF_LOOPBACK) {
+ IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
+ IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
+ }
+ } else if (event == NETDEV_CHANGEMTU) {
+ /* Re-enabling IP */
+ if (inetdev_valid_mtu(dev->mtu))
+ in_dev = inetdev_init(dev);
}
goto out;
}
switch (event) {
case NETDEV_REGISTER:
- printk(KERN_DEBUG "inetdev_event: bug\n");
- dev->ip_ptr = NULL;
+ pr_debug("%s: bug\n", __func__);
+ RCU_INIT_POINTER(dev->ip_ptr, NULL);
break;
case NETDEV_UP:
- if (dev->mtu < 68)
+ if (!inetdev_valid_mtu(dev->mtu))
break;
- if (dev == &loopback_dev) {
- struct in_ifaddr *ifa;
- if ((ifa = inet_alloc_ifa()) != NULL) {
+ if (dev->flags & IFF_LOOPBACK) {
+ struct in_ifaddr *ifa = inet_alloc_ifa();
+
+ if (ifa) {
+ INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_local =
ifa->ifa_address = htonl(INADDR_LOOPBACK);
ifa->ifa_prefixlen = 8;
@@ -1014,18 +1382,36 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
ifa->ifa_dev = in_dev;
ifa->ifa_scope = RT_SCOPE_HOST;
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ set_ifa_lifetime(ifa, INFINITY_LIFE_TIME,
+ INFINITY_LIFE_TIME);
+ ipv4_devconf_setall(in_dev);
+ neigh_parms_data_state_setall(in_dev->arp_parms);
inet_insert_ifa(ifa);
}
}
ip_mc_up(in_dev);
+ /* fall through */
+ case NETDEV_CHANGEADDR:
+ if (!IN_DEV_ARP_NOTIFY(in_dev))
+ break;
+ /* fall through */
+ case NETDEV_NOTIFY_PEERS:
+ /* Send gratuitous ARP to notify of link change */
+ inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
break;
+ case NETDEV_PRE_TYPE_CHANGE:
+ ip_mc_unmap(in_dev);
+ break;
+ case NETDEV_POST_TYPE_CHANGE:
+ ip_mc_remap(in_dev);
+ break;
case NETDEV_CHANGEMTU:
- if (dev->mtu >= 68)
+ if (inetdev_valid_mtu(dev->mtu))
break;
- /* MTU falled under 68, disable IP */
+ /* disable IP when MTU is not enough */
case NETDEV_UNREGISTER:
inetdev_destroy(in_dev);
break;
@@ -1035,13 +1421,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
*/
inetdev_changename(dev, in_dev);
-#ifdef CONFIG_SYSCTL
- devinet_sysctl_unregister(&in_dev->cnf);
- neigh_sysctl_unregister(in_dev->arp_parms);
- neigh_sysctl_register(dev, in_dev->arp_parms, NET_IPV4,
- NET_IPV4_NEIGH, "ipv4", NULL, NULL);
- devinet_sysctl_register(in_dev, &in_dev->cnf);
-#endif
+ devinet_sysctl_unregister(in_dev);
+ devinet_sysctl_register(in_dev);
break;
}
out:
@@ -1049,506 +1430,906 @@ out:
}
static struct notifier_block ip_netdev_notifier = {
- .notifier_call =inetdev_event,
+ .notifier_call = inetdev_event,
};
+static size_t inet_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+ + nla_total_size(4) /* IFA_ADDRESS */
+ + nla_total_size(4) /* IFA_LOCAL */
+ + nla_total_size(4) /* IFA_BROADCAST */
+ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+ + nla_total_size(4) /* IFA_FLAGS */
+ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
+}
+
+static inline u32 cstamp_delta(unsigned long cstamp)
+{
+ return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
+}
+
+static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp,
+ unsigned long tstamp, u32 preferred, u32 valid)
+{
+ struct ifa_cacheinfo ci;
+
+ ci.cstamp = cstamp_delta(cstamp);
+ ci.tstamp = cstamp_delta(tstamp);
+ ci.ifa_prefered = preferred;
+ ci.ifa_valid = valid;
+
+ return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci);
+}
+
static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
- u32 pid, u32 seq, int event, unsigned int flags)
+ u32 portid, u32 seq, int event, unsigned int flags)
{
struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
- unsigned char *b = skb->tail;
+ u32 preferred, valid;
+
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
+ if (nlh == NULL)
+ return -EMSGSIZE;
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags);
- ifm = NLMSG_DATA(nlh);
+ ifm = nlmsg_data(nlh);
ifm->ifa_family = AF_INET;
ifm->ifa_prefixlen = ifa->ifa_prefixlen;
- ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT;
+ ifm->ifa_flags = ifa->ifa_flags;
ifm->ifa_scope = ifa->ifa_scope;
ifm->ifa_index = ifa->ifa_dev->dev->ifindex;
- if (ifa->ifa_address)
- RTA_PUT(skb, IFA_ADDRESS, 4, &ifa->ifa_address);
- if (ifa->ifa_local)
- RTA_PUT(skb, IFA_LOCAL, 4, &ifa->ifa_local);
- if (ifa->ifa_broadcast)
- RTA_PUT(skb, IFA_BROADCAST, 4, &ifa->ifa_broadcast);
- if (ifa->ifa_anycast)
- RTA_PUT(skb, IFA_ANYCAST, 4, &ifa->ifa_anycast);
- if (ifa->ifa_label[0])
- RTA_PUT(skb, IFA_LABEL, IFNAMSIZ, &ifa->ifa_label);
- nlh->nlmsg_len = skb->tail - b;
- return skb->len;
-nlmsg_failure:
-rtattr_failure:
- skb_trim(skb, b - skb->data);
- return -1;
+ if (!(ifm->ifa_flags & IFA_F_PERMANENT)) {
+ preferred = ifa->ifa_preferred_lft;
+ valid = ifa->ifa_valid_lft;
+ if (preferred != INFINITY_LIFE_TIME) {
+ long tval = (jiffies - ifa->ifa_tstamp) / HZ;
+
+ if (preferred > tval)
+ preferred -= tval;
+ else
+ preferred = 0;
+ if (valid != INFINITY_LIFE_TIME) {
+ if (valid > tval)
+ valid -= tval;
+ else
+ valid = 0;
+ }
+ }
+ } else {
+ preferred = INFINITY_LIFE_TIME;
+ valid = INFINITY_LIFE_TIME;
+ }
+ if ((ifa->ifa_address &&
+ nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) ||
+ (ifa->ifa_local &&
+ nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) ||
+ (ifa->ifa_broadcast &&
+ nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) ||
+ (ifa->ifa_label[0] &&
+ nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
+ nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) ||
+ put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp,
+ preferred, valid))
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
}
static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
- int idx, ip_idx;
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx, s_idx;
+ int ip_idx, s_ip_idx;
struct net_device *dev;
struct in_device *in_dev;
struct in_ifaddr *ifa;
- int s_ip_idx, s_idx = cb->args[0];
+ struct hlist_head *head;
- s_ip_idx = ip_idx = cb->args[1];
- read_lock(&dev_base_lock);
- for (dev = dev_base, idx = 0; dev; dev = dev->next, idx++) {
- if (idx < s_idx)
- continue;
- if (idx > s_idx)
- s_ip_idx = 0;
+ s_h = cb->args[0];
+ s_idx = idx = cb->args[1];
+ s_ip_idx = ip_idx = cb->args[2];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
rcu_read_lock();
- if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
- rcu_read_unlock();
- continue;
- }
+ cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+ net->dev_base_seq;
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ if (h > s_h || idx > s_idx)
+ s_ip_idx = 0;
+ in_dev = __in_dev_get_rcu(dev);
+ if (!in_dev)
+ goto cont;
- for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
- ifa = ifa->ifa_next, ip_idx++) {
- if (ip_idx < s_ip_idx)
- continue;
- if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid,
+ for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
+ ifa = ifa->ifa_next, ip_idx++) {
+ if (ip_idx < s_ip_idx)
+ continue;
+ if (inet_fill_ifaddr(skb, ifa,
+ NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWADDR, NLM_F_MULTI) <= 0) {
- rcu_read_unlock();
- goto done;
+ rcu_read_unlock();
+ goto done;
+ }
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
}
+cont:
+ idx++;
}
rcu_read_unlock();
}
done:
- read_unlock(&dev_base_lock);
- cb->args[0] = idx;
- cb->args[1] = ip_idx;
+ cb->args[0] = h;
+ cb->args[1] = idx;
+ cb->args[2] = ip_idx;
return skb->len;
}
-static void rtmsg_ifa(int event, struct in_ifaddr* ifa)
+static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
+ u32 portid)
+{
+ struct sk_buff *skb;
+ u32 seq = nlh ? nlh->nlmsg_seq : 0;
+ int err = -ENOBUFS;
+ struct net *net;
+
+ net = dev_net(ifa->ifa_dev->dev);
+ skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0);
+ if (err < 0) {
+ /* -EMSGSIZE implies BUG in inet_nlmsg_size() */
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(skb);
+ goto errout;
+ }
+ rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
+ return;
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
+}
+
+static size_t inet_get_link_af_size(const struct net_device *dev)
+{
+ struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
+
+ if (!in_dev)
+ return 0;
+
+ return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */
+}
+
+static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
+ struct nlattr *nla;
+ int i;
+
+ if (!in_dev)
+ return -ENODATA;
+
+ nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4);
+ if (nla == NULL)
+ return -EMSGSIZE;
+
+ for (i = 0; i < IPV4_DEVCONF_MAX; i++)
+ ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i];
+
+ return 0;
+}
+
+static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = {
+ [IFLA_INET_CONF] = { .type = NLA_NESTED },
+};
+
+static int inet_validate_link_af(const struct net_device *dev,
+ const struct nlattr *nla)
+{
+ struct nlattr *a, *tb[IFLA_INET_MAX+1];
+ int err, rem;
+
+ if (dev && !__in_dev_get_rtnl(dev))
+ return -EAFNOSUPPORT;
+
+ err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy);
+ if (err < 0)
+ return err;
+
+ if (tb[IFLA_INET_CONF]) {
+ nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) {
+ int cfgid = nla_type(a);
+
+ if (nla_len(a) < 4)
+ return -EINVAL;
+
+ if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX)
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+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];
+ int rem;
+
+ if (!in_dev)
+ return -EAFNOSUPPORT;
+
+ if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0)
+ BUG();
+
+ 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));
+ }
+
+ return 0;
+}
+
+static int inet_netconf_msgsize_devconf(int type)
{
- int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + 128);
- struct sk_buff *skb = alloc_skb(size, GFP_KERNEL);
+ int size = NLMSG_ALIGN(sizeof(struct netconfmsg))
+ + nla_total_size(4); /* NETCONFA_IFINDEX */
+
+ /* type -1 is used for ALL */
+ if (type == -1 || type == NETCONFA_FORWARDING)
+ size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_RP_FILTER)
+ size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_MC_FORWARDING)
+ size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_PROXY_NEIGH)
+ size += nla_total_size(4);
+
+ return size;
+}
+
+static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
+ struct ipv4_devconf *devconf, u32 portid,
+ u32 seq, int event, unsigned int flags,
+ int type)
+{
+ struct nlmsghdr *nlh;
+ struct netconfmsg *ncm;
+
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
+ flags);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ ncm = nlmsg_data(nlh);
+ ncm->ncm_family = AF_INET;
+
+ if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
+ goto nla_put_failure;
+
+ /* type -1 is used for ALL */
+ if ((type == -1 || type == NETCONFA_FORWARDING) &&
+ nla_put_s32(skb, NETCONFA_FORWARDING,
+ IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
+ goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_RP_FILTER) &&
+ nla_put_s32(skb, NETCONFA_RP_FILTER,
+ IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
+ goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+ nla_put_s32(skb, NETCONFA_MC_FORWARDING,
+ IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
+ goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_PROXY_NEIGH) &&
+ nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
+ IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
- if (!skb)
- netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, ENOBUFS);
- else if (inet_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) {
+void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+ struct ipv4_devconf *devconf)
+{
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
+ RTM_NEWNETCONF, 0, type);
+ if (err < 0) {
+ /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
+ WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
- netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, EINVAL);
- } else {
- netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV4_IFADDR, GFP_KERNEL);
+ goto errout;
}
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC);
+ return;
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err);
}
-static struct rtnetlink_link inet_rtnetlink_table[RTM_NR_MSGTYPES] = {
- [RTM_NEWADDR - RTM_BASE] = { .doit = inet_rtm_newaddr, },
- [RTM_DELADDR - RTM_BASE] = { .doit = inet_rtm_deladdr, },
- [RTM_GETADDR - RTM_BASE] = { .dumpit = inet_dump_ifaddr, },
- [RTM_NEWROUTE - RTM_BASE] = { .doit = inet_rtm_newroute, },
- [RTM_DELROUTE - RTM_BASE] = { .doit = inet_rtm_delroute, },
- [RTM_GETROUTE - RTM_BASE] = { .doit = inet_rtm_getroute,
- .dumpit = inet_dump_fib, },
-#ifdef CONFIG_IP_MULTIPLE_TABLES
- [RTM_NEWRULE - RTM_BASE] = { .doit = inet_rtm_newrule, },
- [RTM_DELRULE - RTM_BASE] = { .doit = inet_rtm_delrule, },
- [RTM_GETRULE - RTM_BASE] = { .dumpit = inet_dump_rules, },
-#endif
+static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
+ [NETCONFA_IFINDEX] = { .len = sizeof(int) },
+ [NETCONFA_FORWARDING] = { .len = sizeof(int) },
+ [NETCONFA_RP_FILTER] = { .len = sizeof(int) },
+ [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) },
};
+static int inet_netconf_get_devconf(struct sk_buff *in_skb,
+ struct nlmsghdr *nlh)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct nlattr *tb[NETCONFA_MAX+1];
+ struct netconfmsg *ncm;
+ struct sk_buff *skb;
+ struct ipv4_devconf *devconf;
+ struct in_device *in_dev;
+ struct net_device *dev;
+ int ifindex;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
+ devconf_ipv4_policy);
+ if (err < 0)
+ goto errout;
+
+ err = EINVAL;
+ if (!tb[NETCONFA_IFINDEX])
+ goto errout;
+
+ ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]);
+ switch (ifindex) {
+ case NETCONFA_IFINDEX_ALL:
+ devconf = net->ipv4.devconf_all;
+ break;
+ case NETCONFA_IFINDEX_DEFAULT:
+ devconf = net->ipv4.devconf_dflt;
+ break;
+ default:
+ dev = __dev_get_by_index(net, ifindex);
+ if (dev == NULL)
+ goto errout;
+ in_dev = __in_dev_get_rtnl(dev);
+ if (in_dev == NULL)
+ goto errout;
+ devconf = &in_dev->cnf;
+ break;
+ }
+
+ err = -ENOBUFS;
+ skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet_netconf_fill_devconf(skb, ifindex, devconf,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, RTM_NEWNETCONF, 0,
+ -1);
+ if (err < 0) {
+ /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(skb);
+ goto errout;
+ }
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+errout:
+ return err;
+}
+
+static int inet_netconf_dump_devconf(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx, s_idx;
+ struct net_device *dev;
+ struct in_device *in_dev;
+ struct hlist_head *head;
+
+ s_h = cb->args[0];
+ s_idx = idx = cb->args[1];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ rcu_read_lock();
+ cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+ net->dev_base_seq;
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ in_dev = __in_dev_get_rcu(dev);
+ if (!in_dev)
+ goto cont;
+
+ if (inet_netconf_fill_devconf(skb, dev->ifindex,
+ &in_dev->cnf,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF,
+ NLM_F_MULTI,
+ -1) <= 0) {
+ rcu_read_unlock();
+ goto done;
+ }
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ rcu_read_unlock();
+ }
+ if (h == NETDEV_HASHENTRIES) {
+ if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+ if (h == NETDEV_HASHENTRIES + 1) {
+ if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
+ net->ipv4.devconf_dflt,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+done:
+ cb->args[0] = h;
+ cb->args[1] = idx;
+
+ return skb->len;
+}
+
#ifdef CONFIG_SYSCTL
-void inet_forward_change(void)
+static void devinet_copy_dflt_conf(struct net *net, int i)
{
struct net_device *dev;
- int on = ipv4_devconf.forwarding;
- ipv4_devconf.accept_redirects = !on;
- ipv4_devconf_dflt.forwarding = on;
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
+ struct in_device *in_dev;
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev && !test_bit(i, in_dev->cnf.state))
+ in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i];
+ }
+ rcu_read_unlock();
+}
- read_lock(&dev_base_lock);
- for (dev = dev_base; dev; dev = dev->next) {
+/* called with RTNL locked */
+static void inet_forward_change(struct net *net)
+{
+ struct net_device *dev;
+ int on = IPV4_DEVCONF_ALL(net, FORWARDING);
+
+ IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
+ IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
+ inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all);
+ inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv4.devconf_dflt);
+
+ for_each_netdev(net, dev) {
struct in_device *in_dev;
+ if (on)
+ dev_disable_lro(dev);
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
- if (in_dev)
- in_dev->cnf.forwarding = on;
+ if (in_dev) {
+ IN_DEV_CONF_SET(in_dev, FORWARDING, on);
+ inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ dev->ifindex, &in_dev->cnf);
+ }
rcu_read_unlock();
}
- read_unlock(&dev_base_lock);
+}
- rt_cache_flush(0);
+static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf)
+{
+ if (cnf == net->ipv4.devconf_dflt)
+ return NETCONFA_IFINDEX_DEFAULT;
+ else if (cnf == net->ipv4.devconf_all)
+ return NETCONFA_IFINDEX_ALL;
+ else {
+ struct in_device *idev
+ = container_of(cnf, struct in_device, cnf);
+ return idev->dev->ifindex;
+ }
}
-static int devinet_sysctl_forward(ctl_table *ctl, int write,
- struct file* filp, void __user *buffer,
+static int devinet_conf_proc(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int old_value = *(int *)ctl->data;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
+
+ if (write) {
+ struct ipv4_devconf *cnf = ctl->extra1;
+ struct net *net = ctl->extra2;
+ int i = (int *)ctl->data - cnf->data;
+ 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);
+
+ if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
+ new_value != old_value) {
+ ifindex = devinet_conf_ifindex(net, cnf);
+ inet_netconf_notify_devconf(net, 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, NETCONFA_PROXY_NEIGH,
+ ifindex, cnf);
+ }
+ }
+
+ return ret;
+}
+
+static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
- int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+ loff_t pos = *ppos;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write && *valp != val) {
- if (valp == &ipv4_devconf.forwarding)
- inet_forward_change();
- else if (valp != &ipv4_devconf_dflt.forwarding)
- rt_cache_flush(0);
+ struct net *net = ctl->extra2;
+
+ if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) {
+ if (!rtnl_trylock()) {
+ /* Restore the original values before restarting */
+ *valp = val;
+ *ppos = pos;
+ return restart_syscall();
+ }
+ if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
+ inet_forward_change(net);
+ } else {
+ struct ipv4_devconf *cnf = ctl->extra1;
+ struct in_device *idev =
+ container_of(cnf, struct in_device, cnf);
+ if (*valp)
+ dev_disable_lro(idev->dev);
+ inet_netconf_notify_devconf(net,
+ NETCONFA_FORWARDING,
+ idev->dev->ifindex,
+ cnf);
+ }
+ rtnl_unlock();
+ rt_cache_flush(net);
+ } else
+ inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv4.devconf_dflt);
}
return ret;
}
-int ipv4_doint_and_flush(ctl_table *ctl, int write,
- struct file* filp, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int ipv4_doint_and_flush(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
- int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ struct net *net = ctl->extra2;
if (write && *valp != val)
- rt_cache_flush(0);
+ rt_cache_flush(net);
return ret;
}
-int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen,
- void **context)
-{
- int *valp = table->data;
- int new;
-
- if (!newval || !newlen)
- return 0;
-
- if (newlen != sizeof(int))
- return -EINVAL;
+#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \
+ { \
+ .procname = name, \
+ .data = ipv4_devconf.data + \
+ IPV4_DEVCONF_ ## attr - 1, \
+ .maxlen = sizeof(int), \
+ .mode = mval, \
+ .proc_handler = proc, \
+ .extra1 = &ipv4_devconf, \
+ }
- if (get_user(new, (int __user *)newval))
- return -EFAULT;
+#define DEVINET_SYSCTL_RW_ENTRY(attr, name) \
+ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc)
- if (new == *valp)
- return 0;
+#define DEVINET_SYSCTL_RO_ENTRY(attr, name) \
+ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc)
- if (oldval && oldlenp) {
- size_t len;
-
- if (get_user(len, oldlenp))
- return -EFAULT;
-
- if (len) {
- if (len > table->maxlen)
- len = table->maxlen;
- if (copy_to_user(oldval, valp, len))
- return -EFAULT;
- if (put_user(len, oldlenp))
- return -EFAULT;
- }
- }
-
- *valp = new;
- rt_cache_flush(0);
- return 1;
-}
+#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;
- ctl_table devinet_vars[__NET_IPV4_CONF_MAX];
- ctl_table devinet_dev[2];
- ctl_table devinet_conf_dir[2];
- ctl_table devinet_proto_dir[2];
- ctl_table devinet_root_dir[2];
+ struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX];
} devinet_sysctl = {
.devinet_vars = {
- {
- .ctl_name = NET_IPV4_CONF_FORWARDING,
- .procname = "forwarding",
- .data = &ipv4_devconf.forwarding,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &devinet_sysctl_forward,
- },
- {
- .ctl_name = NET_IPV4_CONF_MC_FORWARDING,
- .procname = "mc_forwarding",
- .data = &ipv4_devconf.mc_forwarding,
- .maxlen = sizeof(int),
- .mode = 0444,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_ACCEPT_REDIRECTS,
- .procname = "accept_redirects",
- .data = &ipv4_devconf.accept_redirects,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_SECURE_REDIRECTS,
- .procname = "secure_redirects",
- .data = &ipv4_devconf.secure_redirects,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_SHARED_MEDIA,
- .procname = "shared_media",
- .data = &ipv4_devconf.shared_media,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_RP_FILTER,
- .procname = "rp_filter",
- .data = &ipv4_devconf.rp_filter,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_SEND_REDIRECTS,
- .procname = "send_redirects",
- .data = &ipv4_devconf.send_redirects,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE,
- .procname = "accept_source_route",
- .data = &ipv4_devconf.accept_source_route,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_PROXY_ARP,
- .procname = "proxy_arp",
- .data = &ipv4_devconf.proxy_arp,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_MEDIUM_ID,
- .procname = "medium_id",
- .data = &ipv4_devconf.medium_id,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_BOOTP_RELAY,
- .procname = "bootp_relay",
- .data = &ipv4_devconf.bootp_relay,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_LOG_MARTIANS,
- .procname = "log_martians",
- .data = &ipv4_devconf.log_martians,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_TAG,
- .procname = "tag",
- .data = &ipv4_devconf.tag,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_ARPFILTER,
- .procname = "arp_filter",
- .data = &ipv4_devconf.arp_filter,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_ARP_ANNOUNCE,
- .procname = "arp_announce",
- .data = &ipv4_devconf.arp_announce,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_ARP_IGNORE,
- .procname = "arp_ignore",
- .data = &ipv4_devconf.arp_ignore,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .ctl_name = NET_IPV4_CONF_NOXFRM,
- .procname = "disable_xfrm",
- .data = &ipv4_devconf.no_xfrm,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &ipv4_doint_and_flush,
- .strategy = &ipv4_doint_and_flush_strategy,
- },
- {
- .ctl_name = NET_IPV4_CONF_NOPOLICY,
- .procname = "disable_policy",
- .data = &ipv4_devconf.no_policy,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &ipv4_doint_and_flush,
- .strategy = &ipv4_doint_and_flush_strategy,
- },
- {
- .ctl_name = NET_IPV4_CONF_FORCE_IGMP_VERSION,
- .procname = "force_igmp_version",
- .data = &ipv4_devconf.force_igmp_version,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &ipv4_doint_and_flush,
- .strategy = &ipv4_doint_and_flush_strategy,
- },
- {
- .ctl_name = NET_IPV4_CONF_PROMOTE_SECONDARIES,
- .procname = "promote_secondaries",
- .data = &ipv4_devconf.promote_secondaries,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &ipv4_doint_and_flush,
- .strategy = &ipv4_doint_and_flush_strategy,
- },
- },
- .devinet_dev = {
- {
- .ctl_name = NET_PROTO_CONF_ALL,
- .procname = "all",
- .mode = 0555,
- .child = devinet_sysctl.devinet_vars,
- },
- },
- .devinet_conf_dir = {
- {
- .ctl_name = NET_IPV4_CONF,
- .procname = "conf",
- .mode = 0555,
- .child = devinet_sysctl.devinet_dev,
- },
- },
- .devinet_proto_dir = {
- {
- .ctl_name = NET_IPV4,
- .procname = "ipv4",
- .mode = 0555,
- .child = devinet_sysctl.devinet_conf_dir,
- },
- },
- .devinet_root_dir = {
- {
- .ctl_name = CTL_NET,
- .procname = "net",
- .mode = 0555,
- .child = devinet_sysctl.devinet_proto_dir,
- },
+ DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
+ devinet_sysctl_forward),
+ DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),
+
+ DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
+ DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
+ DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"),
+ DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"),
+ DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"),
+ DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
+ "accept_source_route"),
+ DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"),
+ DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"),
+ DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
+ DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
+ DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
+ DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"),
+ DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"),
+ DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"),
+ DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"),
+ DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
+ DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
+ DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
+ DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
+ DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION,
+ "force_igmp_version"),
+ DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL,
+ "igmpv2_unsolicited_report_interval"),
+ DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL,
+ "igmpv3_unsolicited_report_interval"),
+
+ 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"),
},
};
-static void devinet_sysctl_register(struct in_device *in_dev,
- struct ipv4_devconf *p)
+static int __devinet_sysctl_register(struct net *net, char *dev_name,
+ struct ipv4_devconf *p)
{
int i;
- struct net_device *dev = in_dev ? in_dev->dev : NULL;
- struct devinet_sysctl_table *t = kmalloc(sizeof(*t), GFP_KERNEL);
- char *dev_name = NULL;
+ struct devinet_sysctl_table *t;
+ char path[sizeof("net/ipv4/conf/") + IFNAMSIZ];
+ t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL);
if (!t)
- return;
- memcpy(t, &devinet_sysctl, sizeof(*t));
+ goto out;
+
for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) {
t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf;
- t->devinet_vars[i].de = NULL;
+ t->devinet_vars[i].extra1 = p;
+ t->devinet_vars[i].extra2 = net;
}
- if (dev) {
- dev_name = dev->name;
- t->devinet_dev[0].ctl_name = dev->ifindex;
- } else {
- dev_name = "default";
- t->devinet_dev[0].ctl_name = NET_PROTO_CONF_DEFAULT;
- }
+ snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name);
- /*
- * Make a copy of dev_name, because '.procname' is regarded as const
- * by sysctl and we wouldn't want anyone to change it under our feet
- * (see SIOCSIFNAME).
- */
- dev_name = kstrdup(dev_name, GFP_KERNEL);
- if (!dev_name)
- goto free;
-
- t->devinet_dev[0].procname = dev_name;
- t->devinet_dev[0].child = t->devinet_vars;
- t->devinet_dev[0].de = NULL;
- t->devinet_conf_dir[0].child = t->devinet_dev;
- t->devinet_conf_dir[0].de = NULL;
- t->devinet_proto_dir[0].child = t->devinet_conf_dir;
- t->devinet_proto_dir[0].de = NULL;
- t->devinet_root_dir[0].child = t->devinet_proto_dir;
- t->devinet_root_dir[0].de = NULL;
-
- t->sysctl_header = register_sysctl_table(t->devinet_root_dir, 0);
+ t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars);
if (!t->sysctl_header)
- goto free_procname;
+ goto free;
p->sysctl = t;
- return;
+ return 0;
- /* error path */
- free_procname:
- kfree(dev_name);
- free:
+free:
+ kfree(t);
+out:
+ return -ENOBUFS;
+}
+
+static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
+{
+ struct devinet_sysctl_table *t = cnf->sysctl;
+
+ if (t == NULL)
+ return;
+
+ cnf->sysctl = NULL;
+ unregister_net_sysctl_table(t->sysctl_header);
kfree(t);
- return;
}
-static void devinet_sysctl_unregister(struct ipv4_devconf *p)
+static void devinet_sysctl_register(struct in_device *idev)
{
- if (p->sysctl) {
- struct devinet_sysctl_table *t = p->sysctl;
- p->sysctl = NULL;
- unregister_sysctl_table(t->sysctl_header);
- kfree(t->devinet_dev[0].procname);
- kfree(t);
+ neigh_sysctl_register(idev->dev, idev->arp_parms, NULL);
+ __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
+ &idev->cnf);
+}
+
+static void devinet_sysctl_unregister(struct in_device *idev)
+{
+ __devinet_sysctl_unregister(&idev->cnf);
+ neigh_sysctl_unregister(idev->arp_parms);
+}
+
+static struct ctl_table ctl_forward_entry[] = {
+ {
+ .procname = "ip_forward",
+ .data = &ipv4_devconf.data[
+ IPV4_DEVCONF_FORWARDING - 1],
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = devinet_sysctl_forward,
+ .extra1 = &ipv4_devconf,
+ .extra2 = &init_net,
+ },
+ { },
+};
+#endif
+
+static __net_init int devinet_init_net(struct net *net)
+{
+ int err;
+ struct ipv4_devconf *all, *dflt;
+#ifdef CONFIG_SYSCTL
+ struct ctl_table *tbl = ctl_forward_entry;
+ struct ctl_table_header *forw_hdr;
+#endif
+
+ err = -ENOMEM;
+ all = &ipv4_devconf;
+ dflt = &ipv4_devconf_dflt;
+
+ if (!net_eq(net, &init_net)) {
+ all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL);
+ if (all == NULL)
+ goto err_alloc_all;
+
+ dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL);
+ if (dflt == NULL)
+ goto err_alloc_dflt;
+
+#ifdef CONFIG_SYSCTL
+ tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL);
+ if (tbl == NULL)
+ goto err_alloc_ctl;
+
+ tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1];
+ tbl[0].extra1 = all;
+ tbl[0].extra2 = net;
+#endif
}
+
+#ifdef CONFIG_SYSCTL
+ err = __devinet_sysctl_register(net, "all", all);
+ if (err < 0)
+ goto err_reg_all;
+
+ err = __devinet_sysctl_register(net, "default", dflt);
+ if (err < 0)
+ goto err_reg_dflt;
+
+ err = -ENOMEM;
+ forw_hdr = register_net_sysctl(net, "net/ipv4", tbl);
+ if (forw_hdr == NULL)
+ goto err_reg_ctl;
+ net->ipv4.forw_hdr = forw_hdr;
+#endif
+
+ net->ipv4.devconf_all = all;
+ net->ipv4.devconf_dflt = dflt;
+ return 0;
+
+#ifdef CONFIG_SYSCTL
+err_reg_ctl:
+ __devinet_sysctl_unregister(dflt);
+err_reg_dflt:
+ __devinet_sysctl_unregister(all);
+err_reg_all:
+ if (tbl != ctl_forward_entry)
+ kfree(tbl);
+err_alloc_ctl:
+#endif
+ if (dflt != &ipv4_devconf_dflt)
+ kfree(dflt);
+err_alloc_dflt:
+ if (all != &ipv4_devconf)
+ kfree(all);
+err_alloc_all:
+ return err;
}
+
+static __net_exit void devinet_exit_net(struct net *net)
+{
+#ifdef CONFIG_SYSCTL
+ struct ctl_table *tbl;
+
+ tbl = net->ipv4.forw_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->ipv4.forw_hdr);
+ __devinet_sysctl_unregister(net->ipv4.devconf_dflt);
+ __devinet_sysctl_unregister(net->ipv4.devconf_all);
+ kfree(tbl);
#endif
+ kfree(net->ipv4.devconf_dflt);
+ kfree(net->ipv4.devconf_all);
+}
+
+static __net_initdata struct pernet_operations devinet_ops = {
+ .init = devinet_init_net,
+ .exit = devinet_exit_net,
+};
+
+static struct rtnl_af_ops inet_af_ops = {
+ .family = AF_INET,
+ .fill_link_af = inet_fill_link_af,
+ .get_link_af_size = inet_get_link_af_size,
+ .validate_link_af = inet_validate_link_af,
+ .set_link_af = inet_set_link_af,
+};
void __init devinet_init(void)
{
+ int i;
+
+ for (i = 0; i < IN4_ADDR_HSIZE; i++)
+ INIT_HLIST_HEAD(&inet_addr_lst[i]);
+
+ register_pernet_subsys(&devinet_ops);
+
register_gifconf(PF_INET, inet_gifconf);
register_netdevice_notifier(&ip_netdev_notifier);
- rtnetlink_links[PF_INET] = inet_rtnetlink_table;
-#ifdef CONFIG_SYSCTL
- devinet_sysctl.sysctl_header =
- register_sysctl_table(devinet_sysctl.devinet_root_dir, 0);
- devinet_sysctl_register(NULL, &ipv4_devconf_dflt);
-#endif
+
+ queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
+
+ rtnl_af_register(&inet_af_ops);
+
+ rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL);
+ rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL);
+ rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL);
+ rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
+ inet_netconf_dump_devconf, NULL);
}
-EXPORT_SYMBOL(devinet_ioctl);
-EXPORT_SYMBOL(in_dev_finish_destroy);
-EXPORT_SYMBOL(inet_select_addr);
-EXPORT_SYMBOL(inetdev_by_index);
-EXPORT_SYMBOL(register_inetaddr_notifier);
-EXPORT_SYMBOL(unregister_inetaddr_notifier);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-05 17:29:03 +0000