1 files changed, 111 insertions, 5 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index df4616fce929..cd9ca0811cfa 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -51,6 +51,7 @@
 #include <linux/inetdevice.h>
 #include <linux/igmp.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 #endif
@@ -63,6 +64,8 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 
+#include "fib_lookup.h"
+
 static struct ipv4_devconf ipv4_devconf = {
         .data = {
                 [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
@@ -92,6 +95,85 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
         [IFA_LABEL]             = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
 };
 
+/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE
+ * value.  So if you change this define, make appropriate changes to
+ * inet_addr_hash as well.
+ */
+#define IN4_ADDR_HSIZE  256
+static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
+static DEFINE_SPINLOCK(inet_addr_hash_lock);
+
+static inline unsigned int inet_addr_hash(struct net *net, __be32 addr)
+{
+        u32 val = (__force u32) addr ^ hash_ptr(net, 8);
+
+        return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) &
+                (IN4_ADDR_HSIZE - 1));
+}
+
+static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
+{
+        unsigned int hash = inet_addr_hash(net, ifa->ifa_local);
+
+        spin_lock(&inet_addr_hash_lock);
+        hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
+        spin_unlock(&inet_addr_hash_lock);
+}
+
+static void inet_hash_remove(struct in_ifaddr *ifa)
+{
+        spin_lock(&inet_addr_hash_lock);
+        hlist_del_init_rcu(&ifa->hash);
+        spin_unlock(&inet_addr_hash_lock);
+}
+
+/**
+ * __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)
+{
+        unsigned int hash = inet_addr_hash(net, addr);
+        struct net_device *result = NULL;
+        struct in_ifaddr *ifa;
+        struct hlist_node *node;
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) {
+                struct net_device *dev = ifa->ifa_dev->dev;
+
+                if (!net_eq(dev_net(dev), net))
+                        continue;
+                if (ifa->ifa_local == addr) {
+                        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);
@@ -265,6 +347,7 @@ 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);
@@ -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 */
 
@@ -296,6 +391,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
         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;
@@ -307,7 +403,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
                 rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
                 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;
@@ -368,6 +464,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
         ifa->ifa_next = *ifap;
         *ifap = ifa;
 
+        inet_hash_insert(dev_net(in_dev->dev), ifa);
+
         /* Send message first, then call notifier.
            Notifier will trigger FIB update, so that
            listeners of netlink will know about new ifaddr */
@@ -521,6 +619,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
         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;
@@ -670,7 +769,7 @@ 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 */
                                 }
                         }
@@ -728,6 +827,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
                 if (!ifa) {
                         ret = -ENOBUFS;
                         ifa = inet_alloc_ifa();
+                        INIT_HLIST_NODE(&ifa->hash);
                         if (!ifa)
                                 break;
                         if (colon)
@@ -1040,8 +1140,8 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev,
                 return;
 
         arp_send(ARPOP_REQUEST, ETH_P_ARP,
-                 ifa->ifa_address, dev,
-                 ifa->ifa_address, NULL,
+                 ifa->ifa_local, dev,
+                 ifa->ifa_local, NULL,
                  dev->dev_addr, NULL);
 }
 
@@ -1084,6 +1184,7 @@ 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;
@@ -1579,7 +1680,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
                 return;
 
         cnf->sysctl = NULL;
-        unregister_sysctl_table(t->sysctl_header);
+        unregister_net_sysctl_table(t->sysctl_header);
         kfree(t->dev_name);
         kfree(t);
 }
@@ -1720,6 +1821,11 @@ 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);