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.c863
1 files changed, 737 insertions, 126 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 3b067704ab3..e9449376b58 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -27,7 +27,6 @@
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
@@ -51,10 +50,12 @@
#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>
@@ -62,6 +63,9 @@
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
+#include <net/addrconf.h>
+
+#include "fib_lookup.h"
static struct ipv4_devconf ipv4_devconf = {
.data = {
@@ -69,6 +73,8 @@ static struct ipv4_devconf ipv4_devconf = {
[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*/,
},
};
@@ -79,6 +85,8 @@ static struct ipv4_devconf ipv4_devconf_dflt = {
[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*/,
},
};
@@ -90,8 +98,82 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[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);
+}
+
+/**
+ * __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);
@@ -101,10 +183,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
static void devinet_sysctl_register(struct in_device *idev);
static void devinet_sysctl_unregister(struct in_device *idev);
#else
-static inline void devinet_sysctl_register(struct in_device *idev)
+static void devinet_sysctl_register(struct in_device *idev)
{
}
-static inline void devinet_sysctl_unregister(struct in_device *idev)
+static void devinet_sysctl_unregister(struct in_device *idev)
{
}
#endif
@@ -124,7 +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);
}
@@ -135,9 +217,9 @@ void in_dev_finish_destroy(struct in_device *idev)
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)
@@ -209,7 +291,7 @@ static void inetdev_destroy(struct in_device *in_dev)
inet_free_ifa(ifa);
}
- rcu_assign_pointer(dev->ip_ptr, NULL);
+ RCU_INIT_POINTER(dev->ip_ptr, NULL);
devinet_sysctl_unregister(in_dev);
neigh_parms_release(&arp_tbl, in_dev->arp_parms);
@@ -234,7 +316,7 @@ int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
}
static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
- int destroy, struct nlmsghdr *nlh, u32 pid)
+ int destroy, struct nlmsghdr *nlh, u32 portid)
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1 = *ifap;
@@ -265,9 +347,10 @@ 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, nlh, pid);
+ rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_DOWN, ifa);
inet_free_ifa(ifa);
@@ -278,9 +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 */
@@ -292,10 +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, nlh, pid);
+ 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;
@@ -304,10 +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, nlh, pid);
+ rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_UP, promote);
- for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
+ for (ifa = next_sec; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
@@ -325,8 +421,12 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
+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 pid)
+ u32 portid)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap, **last_primary;
@@ -361,17 +461,22 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
}
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, nlh, pid);
+ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
return 0;
@@ -393,6 +498,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
return -ENOBUFS;
}
ipv4_devconf_setall(in_dev);
+ neigh_parms_data_state_setall(in_dev->arp_parms);
if (ifa->ifa_dev != in_dev) {
WARN_ON(ifa->ifa_dev);
in_dev_hold(in_dev);
@@ -434,7 +540,7 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 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 net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
@@ -470,7 +576,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg
!inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa)))
continue;
- __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid);
+ __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
return 0;
}
@@ -479,7 +585,132 @@ errout:
return err;
}
-static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
+#define INFINITY_LIFE_TIME 0xFFFFFFFF
+
+static void check_lifetime(struct work_struct *work)
+{
+ unsigned long now, next, next_sec, next_sched;
+ struct in_ifaddr *ifa;
+ struct hlist_node *n;
+ int i;
+
+ now = jiffies;
+ next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
+
+ for (i = 0; i < IN4_ADDR_HSIZE; i++) {
+ bool change_needed = false;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(ifa, &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) {
+ 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();
+ }
+
+ 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;
@@ -516,14 +747,17 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
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);
- 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;
ifa->ifa_dev = in_dev;
@@ -538,31 +772,87 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ 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 int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+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);
+ ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
- return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid);
+ 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(__be32 addr)
+static int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
@@ -628,16 +918,16 @@ int devinet_ioctl(struct net *net, 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)
@@ -670,7 +960,7 @@ int devinet_ioctl(struct net *net, 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 */
}
}
@@ -730,6 +1020,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
ifa = inet_alloc_ifa();
if (!ifa)
break;
+ INIT_HLIST_NODE(&ifa->hash);
if (colon)
memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
else
@@ -756,6 +1047,7 @@ int devinet_ioctl(struct net *net, 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;
@@ -841,10 +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 =
@@ -950,22 +1239,21 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
/*
* Confirm that local IP address exists using wildcards:
- * - in_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
*/
-__be32 inet_confirm_addr(struct in_device *in_dev,
+__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev,
__be32 dst, __be32 local, int scope)
{
__be32 addr = 0;
struct net_device *dev;
- struct net *net;
- if (scope != RT_SCOPE_LINK)
+ if (in_dev != NULL)
return confirm_addr_indev(in_dev, dst, local, scope);
- net = dev_net(in_dev->dev);
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
in_dev = __in_dev_get_rcu(dev);
@@ -979,6 +1267,7 @@ __be32 inet_confirm_addr(struct in_device *in_dev,
return addr;
}
+EXPORT_SYMBOL(inet_confirm_addr);
/*
* Device notifier
@@ -1025,17 +1314,32 @@ skip:
}
}
-static inline bool inetdev_valid_mtu(unsigned mtu)
+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();
@@ -1059,8 +1363,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
switch (event) {
case NETDEV_REGISTER:
- printk(KERN_DEBUG "inetdev_event: bug\n");
- rcu_assign_pointer(dev->ip_ptr, NULL);
+ pr_debug("%s: bug\n", __func__);
+ RCU_INIT_POINTER(dev->ip_ptr, NULL);
break;
case NETDEV_UP:
if (!inetdev_valid_mtu(dev->mtu))
@@ -1069,6 +1373,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
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;
@@ -1077,23 +1382,22 @@ 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_NOTIFY_PEERS:
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 */
- if (IN_DEV_ARP_NOTIFY(in_dev)) {
- struct in_ifaddr *ifa = in_dev->ifa_list;
-
- if (ifa)
- arp_send(ARPOP_REQUEST, ETH_P_ARP,
- ifa->ifa_address, dev,
- ifa->ifa_address, NULL,
- dev->dev_addr, NULL);
- }
+ inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
@@ -1129,43 +1433,86 @@ static struct notifier_block ip_netdev_notifier = {
.notifier_call = inetdev_event,
};
-static inline size_t inet_nlmsg_size(void)
+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(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;
+ u32 preferred, valid;
- nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags);
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
if (nlh == NULL)
return -EMSGSIZE;
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)
- NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address);
+ 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 (ifa->ifa_local)
- NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local);
-
- if (ifa->ifa_broadcast)
- NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast);
-
- if (ifa->ifa_label[0])
- NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label);
+ 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);
@@ -1184,7 +1531,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
struct in_device *in_dev;
struct in_ifaddr *ifa;
struct hlist_head *head;
- struct hlist_node *node;
s_h = cb->args[0];
s_idx = idx = cb->args[1];
@@ -1194,7 +1540,9 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
idx = 0;
head = &net->dev_index_head[h];
rcu_read_lock();
- hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
+ 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)
@@ -1208,12 +1556,13 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
if (ip_idx < s_ip_idx)
continue;
if (inet_fill_ifaddr(skb, ifa,
- NETLINK_CB(cb->skb).pid,
+ NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWADDR, NLM_F_MULTI) <= 0) {
rcu_read_unlock();
goto done;
}
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
}
cont:
idx++;
@@ -1230,7 +1579,7 @@ done:
}
static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
- u32 pid)
+ u32 portid)
{
struct sk_buff *skb;
u32 seq = nlh ? nlh->nlmsg_seq : 0;
@@ -1242,14 +1591,14 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
if (skb == NULL)
goto errout;
- err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0);
+ 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, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
+ rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
return;
errout:
if (err < 0)
@@ -1258,7 +1607,7 @@ errout:
static size_t inet_get_link_af_size(const struct net_device *dev)
{
- struct in_device *in_dev = __in_dev_get_rtnl(dev);
+ struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
if (!in_dev)
return 0;
@@ -1268,7 +1617,7 @@ static size_t inet_get_link_af_size(const struct net_device *dev)
static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
{
- struct in_device *in_dev = __in_dev_get_rtnl(dev);
+ struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
struct nlattr *nla;
int i;
@@ -1337,6 +1686,232 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
return 0;
}
+static int inet_netconf_msgsize_devconf(int type)
+{
+ 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;
+}
+
+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);
+ 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 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
static void devinet_copy_dflt_conf(struct net *net, int i)
@@ -1362,6 +1937,12 @@ static void inet_forward_change(struct net *net)
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;
@@ -1369,33 +1950,69 @@ static void inet_forward_change(struct net *net)
dev_disable_lro(dev);
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
- if (in_dev)
+ 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();
}
}
-static int devinet_conf_proc(ctl_table *ctl, int write,
+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_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(ctl_table *ctl, int write,
+static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -1416,23 +2033,31 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
}
if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
inet_forward_change(net);
- } else if (*valp) {
+ } else {
struct ipv4_devconf *cnf = ctl->extra1;
struct in_device *idev =
container_of(cnf, struct in_device, cnf);
- dev_disable_lro(idev->dev);
+ if (*valp)
+ dev_disable_lro(idev->dev);
+ inet_netconf_notify_devconf(net,
+ NETCONFA_FORWARDING,
+ idev->dev->ifindex,
+ cnf);
}
rtnl_unlock();
- rt_cache_flush(net, 0);
- }
+ 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,
- 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;
@@ -1440,7 +2065,7 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
struct net *net = ctl->extra2;
if (write && *valp != val)
- rt_cache_flush(net, 0);
+ rt_cache_flush(net);
return ret;
}
@@ -1471,7 +2096,6 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
static struct devinet_sysctl_table {
struct ctl_table_header *sysctl_header;
struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX];
- char *dev_name;
} devinet_sysctl = {
.devinet_vars = {
DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
@@ -1498,13 +2122,19 @@ static struct devinet_sysctl_table {
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(FORCE_IGMP_VERSION,
- "force_igmp_version"),
DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES,
"promote_secondaries"),
+ DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET,
+ "route_localnet"),
},
};
@@ -1513,16 +2143,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
{
int i;
struct devinet_sysctl_table *t;
-
-#define DEVINET_CTL_PATH_DEV 3
-
- struct ctl_path devinet_ctl_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { .procname = "conf", },
- { /* to be set */ },
- { },
- };
+ char path[sizeof("net/ipv4/conf/") + IFNAMSIZ];
t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL);
if (!t)
@@ -1534,27 +2155,15 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
t->devinet_vars[i].extra2 = net;
}
- /*
- * 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).
- */
- t->dev_name = kstrdup(dev_name, GFP_KERNEL);
- if (!t->dev_name)
- goto free;
-
- devinet_ctl_path[DEVINET_CTL_PATH_DEV].procname = t->dev_name;
+ snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name);
- t->sysctl_header = register_net_sysctl_table(net, devinet_ctl_path,
- t->devinet_vars);
+ t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars);
if (!t->sysctl_header)
- goto free_procname;
+ goto free;
p->sysctl = t;
return 0;
-free_procname:
- kfree(t->dev_name);
free:
kfree(t);
out:
@@ -1569,14 +2178,13 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
return;
cnf->sysctl = NULL;
- unregister_sysctl_table(t->sysctl_header);
- kfree(t->dev_name);
+ unregister_net_sysctl_table(t->sysctl_header);
kfree(t);
}
static void devinet_sysctl_register(struct in_device *idev)
{
- neigh_sysctl_register(idev->dev, idev->arp_parms, "ipv4", NULL);
+ neigh_sysctl_register(idev->dev, idev->arp_parms, NULL);
__devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
&idev->cnf);
}
@@ -1600,12 +2208,6 @@ static struct ctl_table ctl_forward_entry[] = {
},
{ },
};
-
-static __net_initdata struct ctl_path net_ipv4_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { },
-};
#endif
static __net_init int devinet_init_net(struct net *net)
@@ -1651,7 +2253,7 @@ static __net_init int devinet_init_net(struct net *net)
goto err_reg_dflt;
err = -ENOMEM;
- forw_hdr = register_net_sysctl_table(net, net_ipv4_path, tbl);
+ forw_hdr = register_net_sysctl(net, "net/ipv4", tbl);
if (forw_hdr == NULL)
goto err_reg_ctl;
net->ipv4.forw_hdr = forw_hdr;
@@ -1710,15 +2312,24 @@ static struct rtnl_af_ops inet_af_ops = {
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);
+ 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);
- rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL);
- rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr);
+ 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);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 13:16:31 +0000