1 files changed, 115 insertions, 81 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 155138d8ec8b..46af62363b8c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,7 +112,7 @@
 #include <net/secure_seq.h>
 
 #define RT_FL_TOS(oldflp4) \
-    ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+        ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
 #define IP_MAX_MTU      0xFFF0
 
@@ -131,6 +131,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly         = 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly       = 256;
 static int rt_chain_length_max __read_mostly    = 20;
+static int redirect_genid;
 
 /*
  *      Interface to generic destination cache.
@@ -138,7 +139,7 @@ static int rt_chain_length_max __read_mostly	= 20;
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int      ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int      ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int      ipv4_mtu(const struct dst_entry *dst);
 static void              ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void              ipv4_link_failure(struct sk_buff *skb);
@@ -193,7 +194,7 @@ static struct dst_ops ipv4_dst_ops = {
         .gc =                   rt_garbage_collect,
         .check =                ipv4_dst_check,
         .default_advmss =       ipv4_default_advmss,
-        .default_mtu =          ipv4_default_mtu,
+        .mtu =                  ipv4_mtu,
         .cow_metrics =          ipv4_cow_metrics,
         .destroy =              ipv4_dst_destroy,
         .ifdown =               ipv4_dst_ifdown,
@@ -416,9 +417,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
         else {
                 struct rtable *r = v;
                 struct neighbour *n;
-                int len;
+                int len, HHUptod;
 
+                rcu_read_lock();
                 n = dst_get_neighbour(&r->dst);
+                HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+                rcu_read_unlock();
+
                 seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
                               "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
                         r->dst.dev ? r->dst.dev->name : "*",
@@ -432,7 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
                               dst_metric(&r->dst, RTAX_RTTVAR)),
                         r->rt_key_tos,
                         -1,
-                        (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+                        HHUptod,
                         r->rt_spec_dst, &len);
 
                 seq_printf(seq, "%*s\n", 127 - len, "");
@@ -837,6 +842,7 @@ static void rt_cache_invalidate(struct net *net)
 
         get_random_bytes(&shuffle, sizeof(shuffle));
         atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+        redirect_genid++;
 }
 
 /*
@@ -1304,16 +1310,40 @@ static void rt_del(unsigned hash, struct rtable *rt)
         spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+        struct rtable *rt = (struct rtable *) dst;
+        __be32 orig_gw = rt->rt_gateway;
+        struct neighbour *n, *old_n;
+
+        dst_confirm(&rt->dst);
+
+        rt->rt_gateway = peer->redirect_learned.a4;
+
+        n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+        if (IS_ERR(n)) {
+                rt->rt_gateway = orig_gw;
+                return;
+        }
+        old_n = xchg(&rt->dst._neighbour, n);
+        if (old_n)
+                neigh_release(old_n);
+        if (!(n->nud_state & NUD_VALID)) {
+                neigh_event_send(n, NULL);
+        } else {
+                rt->rt_flags |= RTCF_REDIRECTED;
+                call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+        }
+}
+
 /* called in rcu_read_lock() section */
 void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
                     __be32 saddr, struct net_device *dev)
 {
         int s, i;
         struct in_device *in_dev = __in_dev_get_rcu(dev);
-        struct rtable *rt;
         __be32 skeys[2] = { saddr, 0 };
         int    ikeys[2] = { dev->ifindex, 0 };
-        struct flowi4 fl4;
         struct inet_peer *peer;
         struct net *net;
 
@@ -1336,33 +1366,44 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
                         goto reject_redirect;
         }
 
-        memset(&fl4, 0, sizeof(fl4));
-        fl4.daddr = daddr;
         for (s = 0; s < 2; s++) {
                 for (i = 0; i < 2; i++) {
-                        fl4.flowi4_oif = ikeys[i];
-                        fl4.saddr = skeys[s];
-                        rt = __ip_route_output_key(net, &fl4);
-                        if (IS_ERR(rt))
-                                continue;
-
-                        if (rt->dst.error || rt->dst.dev != dev ||
-                            rt->rt_gateway != old_gw) {
-                                ip_rt_put(rt);
-                                continue;
-                        }
-
-                        if (!rt->peer)
-                                rt_bind_peer(rt, rt->rt_dst, 1);
+                        unsigned int hash;
+                        struct rtable __rcu **rthp;
+                        struct rtable *rt;
+
+                        hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+                        rthp = &rt_hash_table[hash].chain;
+
+                        while ((rt = rcu_dereference(*rthp)) != NULL) {
+                                rthp = &rt->dst.rt_next;
+
+                                if (rt->rt_key_dst != daddr ||
+                                    rt->rt_key_src != skeys[s] ||
+                                    rt->rt_oif != ikeys[i] ||
+                                    rt_is_input_route(rt) ||
+                                    rt_is_expired(rt) ||
+                                    !net_eq(dev_net(rt->dst.dev), net) ||
+                                    rt->dst.error ||
+                                    rt->dst.dev != dev ||
+                                    rt->rt_gateway != old_gw)
+                                        continue;
 
-                        peer = rt->peer;
-                        if (peer) {
-                                peer->redirect_learned.a4 = new_gw;
-                                atomic_inc(&__rt_peer_genid);
+                                if (!rt->peer)
+                                        rt_bind_peer(rt, rt->rt_dst, 1);
+
+                                peer = rt->peer;
+                                if (peer) {
+                                        if (peer->redirect_learned.a4 != new_gw ||
+                                            peer->redirect_genid != redirect_genid) {
+                                                peer->redirect_learned.a4 = new_gw;
+                                                peer->redirect_genid = redirect_genid;
+                                                atomic_inc(&__rt_peer_genid);
+                                        }
+                                        check_peer_redir(&rt->dst, peer);
+                                }
                         }
-
-                        ip_rt_put(rt);
-                        return;
                 }
         }
         return;
@@ -1649,40 +1690,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
         }
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
-        struct rtable *rt = (struct rtable *) dst;
-        __be32 orig_gw = rt->rt_gateway;
-        struct neighbour *n, *old_n;
-
-        dst_confirm(&rt->dst);
-
-        rt->rt_gateway = peer->redirect_learned.a4;
-
-        n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
-        if (IS_ERR(n))
-                return PTR_ERR(n);
-        old_n = xchg(&rt->dst._neighbour, n);
-        if (old_n)
-                neigh_release(old_n);
-        if (!n || !(n->nud_state & NUD_VALID)) {
-                if (n)
-                        neigh_event_send(n, NULL);
-                rt->rt_gateway = orig_gw;
-                return -EAGAIN;
-        } else {
-                rt->rt_flags |= RTCF_REDIRECTED;
-                call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
-        }
-        return 0;
-}
 
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
 {
-        struct rtable *rt = (struct rtable *) dst;
-
-        if (rt_is_expired(rt))
-                return NULL;
         if (rt->rt_peer_genid != rt_peer_genid()) {
                 struct inet_peer *peer;
 
@@ -1691,17 +1701,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
                 peer = rt->peer;
                 if (peer) {
-                        check_peer_pmtu(dst, peer);
+                        check_peer_pmtu(&rt->dst, peer);
 
+                        if (peer->redirect_genid != redirect_genid)
+                                peer->redirect_learned.a4 = 0;
                         if (peer->redirect_learned.a4 &&
-                            peer->redirect_learned.a4 != rt->rt_gateway) {
-                                if (check_peer_redir(dst, peer))
-                                        return NULL;
-                        }
+                            peer->redirect_learned.a4 != rt->rt_gateway)
+                                check_peer_redir(&rt->dst, peer);
                 }
 
                 rt->rt_peer_genid = rt_peer_genid();
         }
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+        struct rtable *rt = (struct rtable *) dst;
+
+        if (rt_is_expired(rt))
+                return NULL;
+        ipv4_validate_peer(rt);
         return dst;
 }
 
@@ -1806,12 +1825,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
         return advmss;
 }
 
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-        unsigned int mtu = dst->dev->mtu;
+        const struct rtable *rt = (const struct rtable *) dst;
+        unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+        if (mtu && rt_is_output_route(rt))
+                return mtu;
+
+        mtu = dst->dev->mtu;
 
         if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-                const struct rtable *rt = (const struct rtable *) dst;
 
                 if (rt->rt_gateway != rt->rt_dst && mtu > 576)
                         mtu = 576;
@@ -1844,6 +1868,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
                 dst_init_metrics(&rt->dst, peer->metrics, false);
 
                 check_peer_pmtu(&rt->dst, peer);
+                if (peer->redirect_genid != redirect_genid)
+                        peer->redirect_learned.a4 = 0;
                 if (peer->redirect_learned.a4 &&
                     peer->redirect_learned.a4 != rt->rt_gateway) {
                         rt->rt_gateway = peer->redirect_learned.a4;
@@ -2349,6 +2375,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
                     rth->rt_mark == skb->mark &&
                     net_eq(dev_net(rth->dst.dev), net) &&
                     !rt_is_expired(rth)) {
+                        ipv4_validate_peer(rth);
                         if (noref) {
                                 dst_use_noref(&rth->dst, jiffies);
                                 skb_dst_set_noref(skb, &rth->dst);
@@ -2407,11 +2434,11 @@ EXPORT_SYMBOL(ip_route_input_common);
 static struct rtable *__mkroute_output(const struct fib_result *res,
                                        const struct flowi4 *fl4,
                                        __be32 orig_daddr, __be32 orig_saddr,
-                                       int orig_oif, struct net_device *dev_out,
+                                       int orig_oif, __u8 orig_rtos,
+                                       struct net_device *dev_out,
                                        unsigned int flags)
 {
         struct fib_info *fi = res->fi;
-        u32 tos = RT_FL_TOS(fl4);
         struct in_device *in_dev;
         u16 type = res->type;
         struct rtable *rth;
@@ -2462,7 +2489,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
         rth->rt_genid = rt_genid(dev_net(dev_out));
         rth->rt_flags   = flags;
         rth->rt_type    = type;
-        rth->rt_key_tos = tos;
+        rth->rt_key_tos = orig_rtos;
         rth->rt_dst     = fl4->daddr;
         rth->rt_src     = fl4->saddr;
         rth->rt_route_iif = 0;
@@ -2512,7 +2539,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 {
         struct net_device *dev_out = NULL;
-        u32 tos = RT_FL_TOS(fl4);
+        __u8 tos = RT_FL_TOS(fl4);
         unsigned int flags = 0;
         struct fib_result res;
         struct rtable *rth;
@@ -2688,7 +2715,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 
 make_route:
         rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
-                               dev_out, flags);
+                               tos, dev_out, flags);
         if (!IS_ERR(rth)) {
                 unsigned int hash;
 
@@ -2724,6 +2751,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
                             (IPTOS_RT_MASK | RTO_ONLINK)) &&
                     net_eq(dev_net(rth->dst.dev), net) &&
                     !rt_is_expired(rth)) {
+                        ipv4_validate_peer(rth);
                         dst_use(&rth->dst, jiffies);
                         RT_CACHE_STAT_INC(out_hit);
                         rcu_read_unlock_bh();
@@ -2747,9 +2775,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo
         return NULL;
 }
 
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 {
-        return 0;
+        unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+        return mtu ? : dst->dev->mtu;
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -2767,7 +2797,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
         .protocol               =       cpu_to_be16(ETH_P_IP),
         .destroy                =       ipv4_dst_destroy,
         .check                  =       ipv4_blackhole_dst_check,
-        .default_mtu            =       ipv4_blackhole_default_mtu,
+        .mtu                    =       ipv4_blackhole_mtu,
         .default_advmss         =       ipv4_default_advmss,
         .update_pmtu            =       ipv4_rt_blackhole_update_pmtu,
         .cow_metrics            =       ipv4_rt_blackhole_cow_metrics,
@@ -2845,7 +2875,7 @@ static int rt_fill_info(struct net *net,
         struct rtable *rt = skb_rtable(skb);
         struct rtmsg *r;
         struct nlmsghdr *nlh;
-        long expires = 0;
+        unsigned long expires = 0;
         const struct inet_peer *peer = rt->peer;
         u32 id = 0, ts = 0, tsage = 0, error;
 
@@ -2902,8 +2932,12 @@ static int rt_fill_info(struct net *net,
                         tsage = get_seconds() - peer->tcp_ts_stamp;
                 }
                 expires = ACCESS_ONCE(peer->pmtu_expires);
-                if (expires)
-                        expires -= jiffies;
+                if (expires) {
+                        if (time_before(jiffies, expires))
+                                expires -= jiffies;
+                        else
+                                expires = 0;
+                }
         }
 
         if (rt_is_input_route(rt)) {