1 files changed, 24 insertions, 56 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e4ba974f143..ff622069fce 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -202,11 +202,6 @@ EXPORT_SYMBOL(ip_tos2prio);
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
 #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
 
-static inline int rt_genid(struct net *net)
-{
-        return atomic_read(&net->ipv4.rt_genid);
-}
-
 #ifdef CONFIG_PROC_FS
 static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
 {
@@ -447,27 +442,9 @@ static inline bool rt_is_expired(const struct rtable *rth)
         return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
 }
 
-/*
- * Perturbation of rt_genid by a small quantity [1..256]
- * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
- * many times (2^24) without giving recent rt_genid.
- * Jenkins hash is strong enough that litle changes of rt_genid are OK.
- */
-static void rt_cache_invalidate(struct net *net)
-{
-        unsigned char shuffle;
-
-        get_random_bytes(&shuffle, sizeof(shuffle));
-        atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
-}
-
-/*
- * delay < 0  : invalidate cache (fast : entries will be deleted later)
- * delay >= 0 : invalidate & flush cache (can be long)
- */
-void rt_cache_flush(struct net *net, int delay)
+void rt_cache_flush(struct net *net)
 {
-        rt_cache_invalidate(net);
+        rt_genid_bump(net);
 }
 
 static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
@@ -934,12 +911,14 @@ static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
         if (mtu < ip_rt_min_pmtu)
                 mtu = ip_rt_min_pmtu;
 
+        rcu_read_lock();
         if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
                 struct fib_nh *nh = &FIB_RES_NH(res);
 
                 update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
                                       jiffies + ip_rt_mtu_expires);
         }
+        rcu_read_unlock();
         return mtu;
 }
 
@@ -956,7 +935,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
                 dst->obsolete = DST_OBSOLETE_KILL;
         } else {
                 rt->rt_pmtu = mtu;
-                dst_set_expires(&rt->dst, ip_rt_mtu_expires);
+                rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
         }
 }
 
@@ -1132,10 +1111,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
         const struct rtable *rt = (const struct rtable *) dst;
         unsigned int mtu = rt->rt_pmtu;
 
-        if (mtu && time_after_eq(jiffies, rt->dst.expires))
-                mtu = 0;
-
-        if (!mtu)
+        if (!mtu || time_after_eq(jiffies, rt->dst.expires))
                 mtu = dst_metric_raw(dst, RTAX_MTU);
 
         if (mtu && rt_is_output_route(rt))
@@ -1263,7 +1239,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 {
         struct rtable *rt = (struct rtable *) dst;
 
-        if (dst->flags & DST_NOCACHE) {
+        if (!list_empty(&rt->rt_uncached)) {
                 spin_lock_bh(&rt_uncached_lock);
                 list_del(&rt->rt_uncached);
                 spin_unlock_bh(&rt_uncached_lock);
@@ -1587,11 +1563,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
         if (ipv4_is_zeronet(daddr))
                 goto martian_destination;
 
-        if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) {
-                if (ipv4_is_loopback(daddr))
+        /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(),
+         * and call it once if daddr or/and saddr are loopback addresses
+         */
+        if (ipv4_is_loopback(daddr)) {
+                if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
                         goto martian_destination;
-
-                if (ipv4_is_loopback(saddr))
+        } else if (ipv4_is_loopback(saddr)) {
+                if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
                         goto martian_source;
         }
 
@@ -1616,7 +1595,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
         if (res.type == RTN_LOCAL) {
                 err = fib_validate_source(skb, saddr, daddr, tos,
-                                          net->loopback_dev->ifindex,
+                                          LOOPBACK_IFINDEX,
                                           dev, in_dev, &itag);
                 if (err < 0)
                         goto martian_source_keep_err;
@@ -1892,7 +1871,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 
         orig_oif = fl4->flowi4_oif;
 
-        fl4->flowi4_iif = net->loopback_dev->ifindex;
+        fl4->flowi4_iif = LOOPBACK_IFINDEX;
         fl4->flowi4_tos = tos & IPTOS_RT_MASK;
         fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
                          RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
@@ -1981,7 +1960,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
                 if (!fl4->daddr)
                         fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
                 dev_out = net->loopback_dev;
-                fl4->flowi4_oif = net->loopback_dev->ifindex;
+                fl4->flowi4_oif = LOOPBACK_IFINDEX;
                 res.type = RTN_LOCAL;
                 flags |= RTCF_LOCAL;
                 goto make_route;
@@ -2028,7 +2007,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
                 }
                 dev_out = net->loopback_dev;
                 fl4->flowi4_oif = dev_out->ifindex;
-                res.fi = NULL;
                 flags |= RTCF_LOCAL;
                 goto make_route;
         }
@@ -2153,7 +2131,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
-                        struct flowi4 *fl4, struct sk_buff *skb, u32 pid,
+                        struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
                         u32 seq, int event, int nowait, unsigned int flags)
 {
         struct rtable *rt = skb_rtable(skb);
@@ -2163,7 +2141,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
         u32 error;
         u32 metrics[RTAX_MAX];
 
-        nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
+        nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags);
         if (nlh == NULL)
                 return -EMSGSIZE;
 
@@ -2323,12 +2301,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
                 rt->rt_flags |= RTCF_NOTIFY;
 
         err = rt_fill_info(net, dst, src, &fl4, skb,
-                           NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
+                           NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
                            RTM_NEWROUTE, 0, 0);
         if (err <= 0)
                 goto errout_free;
 
-        err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
+        err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
         return err;
 
@@ -2344,7 +2322,7 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 
 void ip_rt_multicast_event(struct in_device *in_dev)
 {
-        rt_cache_flush(dev_net(in_dev->dev), 0);
+        rt_cache_flush(dev_net(in_dev->dev));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -2353,16 +2331,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
                                         size_t *lenp, loff_t *ppos)
 {
         if (write) {
-                int flush_delay;
-                ctl_table ctl;
-                struct net *net;
-
-                memcpy(&ctl, __ctl, sizeof(ctl));
-                ctl.data = &flush_delay;
-                proc_dointvec(&ctl, write, buffer, lenp, ppos);
-
-                net = (struct net *)__ctl->extra1;
-                rt_cache_flush(net, flush_delay);
+                rt_cache_flush((struct net *)__ctl->extra1);
                 return 0;
         }
 
@@ -2532,8 +2501,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
 
 static __net_init int rt_genid_init(struct net *net)
 {
-        get_random_bytes(&net->ipv4.rt_genid,
-                         sizeof(net->ipv4.rt_genid));
+        atomic_set(&net->rt_genid, 0);
         get_random_bytes(&net->ipv4.dev_addr_genid,
                          sizeof(net->ipv4.dev_addr_genid));
         return 0;